mirror of
https://github.com/ruvnet/RuView
synced 2026-06-12 10:43:19 +00:00
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 ruv
|
cb1fcbad85 |
@@ -1 +0,0 @@
|
||||
{"intelligence":7,"timestamp":1774922079152}
|
||||
@@ -1,55 +1,50 @@
|
||||
{
|
||||
"running": true,
|
||||
"startedAt": "2026-05-24T22:26:25.030Z",
|
||||
"startedAt": "2026-03-09T15:26:00.921Z",
|
||||
"workers": {
|
||||
"map": {
|
||||
"runCount": 64,
|
||||
"successCount": 64,
|
||||
"runCount": 49,
|
||||
"successCount": 49,
|
||||
"failureCount": 0,
|
||||
"averageDurationMs": 136.171875,
|
||||
"lastRun": "2026-05-25T06:07:33.387Z",
|
||||
"lastStartedAt": "2026-05-25T06:07:33.381Z",
|
||||
"nextRun": "2026-05-25T06:26:25.410Z",
|
||||
"averageDurationMs": 1.2857142857142858,
|
||||
"lastRun": "2026-02-28T16:13:19.194Z",
|
||||
"nextRun": "2026-03-09T15:56:00.928Z",
|
||||
"isRunning": false
|
||||
},
|
||||
"audit": {
|
||||
"runCount": 72,
|
||||
"successCount": 27,
|
||||
"runCount": 45,
|
||||
"successCount": 0,
|
||||
"failureCount": 45,
|
||||
"averageDurationMs": 26260.11111111111,
|
||||
"lastRun": "2026-05-25T06:08:29.594Z",
|
||||
"lastStartedAt": "2026-05-25T06:07:33.416Z",
|
||||
"nextRun": "2026-05-25T06:18:32.928Z",
|
||||
"averageDurationMs": 0,
|
||||
"lastRun": "2026-03-09T15:43:00.933Z",
|
||||
"nextRun": "2026-03-09T15:38:00.914Z",
|
||||
"isRunning": false
|
||||
},
|
||||
"optimize": {
|
||||
"runCount": 54,
|
||||
"successCount": 9,
|
||||
"failureCount": 45,
|
||||
"averageDurationMs": 40303.377578766485,
|
||||
"lastRun": "2026-05-25T05:59:05.330Z",
|
||||
"lastStartedAt": "2026-05-25T05:54:05.318Z",
|
||||
"nextRun": "2026-05-25T06:20:15.145Z",
|
||||
"runCount": 34,
|
||||
"successCount": 0,
|
||||
"failureCount": 34,
|
||||
"averageDurationMs": 0,
|
||||
"lastRun": "2026-02-28T16:23:19.387Z",
|
||||
"nextRun": "2026-03-09T15:45:00.915Z",
|
||||
"isRunning": false
|
||||
},
|
||||
"consolidate": {
|
||||
"runCount": 32,
|
||||
"successCount": 32,
|
||||
"runCount": 23,
|
||||
"successCount": 23,
|
||||
"failureCount": 0,
|
||||
"averageDurationMs": 4.71875,
|
||||
"lastRun": "2026-05-25T05:38:20.449Z",
|
||||
"lastStartedAt": "2026-05-25T05:38:20.443Z",
|
||||
"nextRun": "2026-05-25T06:32:25.248Z",
|
||||
"averageDurationMs": 0.6521739130434783,
|
||||
"lastRun": "2026-02-28T16:05:19.091Z",
|
||||
"nextRun": "2026-03-09T16:02:00.918Z",
|
||||
"isRunning": false
|
||||
},
|
||||
"testgaps": {
|
||||
"runCount": 100,
|
||||
"successCount": 63,
|
||||
"failureCount": 37,
|
||||
"averageDurationMs": 108604.0537328991,
|
||||
"lastRun": "2026-05-25T06:11:52.529Z",
|
||||
"lastStartedAt": "2026-05-25T06:07:33.390Z",
|
||||
"nextRun": "2026-05-25T06:14:25.296Z",
|
||||
"runCount": 27,
|
||||
"successCount": 0,
|
||||
"failureCount": 27,
|
||||
"averageDurationMs": 0,
|
||||
"lastRun": "2026-02-28T16:08:19.369Z",
|
||||
"nextRun": "2026-03-09T15:54:00.920Z",
|
||||
"isRunning": false
|
||||
},
|
||||
"predict": {
|
||||
@@ -69,8 +64,8 @@
|
||||
},
|
||||
"config": {
|
||||
"autoStart": false,
|
||||
"logDir": "C:\\Users\\ruv\\Projects\\wifi-densepose\\.claude-flow\\logs",
|
||||
"stateFile": "C:\\Users\\ruv\\Projects\\wifi-densepose\\.claude-flow\\daemon-state.json",
|
||||
"logDir": "/Users/cohen/GitHub/ruvnet/RuView/.claude-flow/logs",
|
||||
"stateFile": "/Users/cohen/GitHub/ruvnet/RuView/.claude-flow/daemon-state.json",
|
||||
"maxConcurrent": 2,
|
||||
"workerTimeoutMs": 300000,
|
||||
"resourceThresholds": {
|
||||
@@ -136,5 +131,5 @@
|
||||
}
|
||||
]
|
||||
},
|
||||
"savedAt": "2026-05-25T06:11:52.530Z"
|
||||
"savedAt": "2026-03-09T15:43:00.933Z"
|
||||
}
|
||||
@@ -1,119 +0,0 @@
|
||||
{
|
||||
"id": "aether-arena-aa",
|
||||
"name": "AetherArena (AA) — Official Spatial-Intelligence Benchmark",
|
||||
"adr": "ADR-149",
|
||||
"adrPath": "docs/adr/ADR-149-public-community-leaderboard-huggingface.md",
|
||||
"status": "Accepted",
|
||||
"initializedDate": "2026-05-30",
|
||||
"targetDate": "2026-08-31",
|
||||
"exitCriteria": "Benchmark INFRASTRUCTURE done, tested, CI-gated, deploy-ready: aa_score_runner.rs passes deterministic fixture test; CI harness-gate green on every PR; aether-arena repo scaffold committed (README four-part framing + aa-submission.toml schema + VERIFY.md); public smoke split committed; HF Space lifecycle skeleton deployed; signed Parquet ledger functional; RuView baseline PCK@20 ~2.5% entered; ADR-149 §7 acceptance test (five-step stranger test) passes. NOTE: ML SOTA (MM-Fi PCK@20 ~72%) is a separate long-running stretch goal blocked on ADR-079 camera-ground-truth — it is NOT an infra exit criterion.",
|
||||
"baselineState": {
|
||||
"adrStatus": "Accepted, committed 2026-05-30",
|
||||
"scorerCode": "ruview_metrics.rs + ablation.rs + proof.rs exist in wifi-densepose-train; aa_score_runner.rs not yet created",
|
||||
"aetherArenaRepo": "does not exist yet — needs user authorization to create ruvnet/aether-arena public repo",
|
||||
"hfSpace": "does not exist yet — needs HF_TOKEN and user authorization to deploy ruvnet/aether-arena HF Space",
|
||||
"smokeDataset": "not committed",
|
||||
"resultsLedger": "not created",
|
||||
"ruviewBaseline": "PCK@20 ~2.5% self-reported, not formally entered",
|
||||
"ciGate": "not added to workflow"
|
||||
},
|
||||
"milestones": {
|
||||
"m1": {
|
||||
"name": "ADR-149 Accepted + committed",
|
||||
"status": "DONE",
|
||||
"completedDate": "2026-05-30",
|
||||
"completionCriteria": "ADR-149 file committed to docs/adr/ with status Accepted",
|
||||
"notes": "Done this session. File at docs/adr/ADR-149-public-community-leaderboard-huggingface.md"
|
||||
},
|
||||
"m2": {
|
||||
"name": "Deterministic scorer runner bin (aa_score_runner.rs)",
|
||||
"status": "NOT_STARTED",
|
||||
"completionCriteria": "aa_score_runner.rs compiles, runs ruview_metrics on a committed fixture, emits RuViewTier + SHA-256 proof hash, mirrors existing *_proof_runner.rs pattern; cargo test passes",
|
||||
"estimatedEffort": "3-5 days",
|
||||
"owner": "wifi-densepose-train crate or new aa-scorer crate"
|
||||
},
|
||||
"m3": {
|
||||
"name": "CI harness-gate: GitHub Actions workflow",
|
||||
"status": "NOT_STARTED",
|
||||
"completionCriteria": "A GitHub Actions workflow runs aa_score_runner on every PR as a build gate; PR fails if scorer fails determinism check; workflow committed and green",
|
||||
"estimatedEffort": "2-3 days",
|
||||
"dependency": "M2 must be done first"
|
||||
},
|
||||
"m4": {
|
||||
"name": "aether-arena repo scaffold",
|
||||
"status": "NOT_STARTED",
|
||||
"completionCriteria": "ruvnet/aether-arena repo created with: README (four-part framing: Public leaderboard / Private eval split / Open scorer / Signed results); aa-submission.toml manifest schema; VERIFY.md (ADR-149 §7 stranger acceptance test); neutrality/governance section (§2.8); contribution guide",
|
||||
"estimatedEffort": "3-5 days",
|
||||
"blockers": ["Needs user authorization to create public ruvnet/aether-arena repo on GitHub"]
|
||||
},
|
||||
"m5": {
|
||||
"name": "Public smoke split committed + private MM-Fi held-out split prep",
|
||||
"status": "NOT_STARTED",
|
||||
"completionCriteria": "Public smoke split committed to aether-arena repo (stranger can score locally); private MM-Fi held-out split prepared under non-public path with CC BY-NC 4.0 attribution; Wi-Pose explicitly excluded from v0",
|
||||
"estimatedEffort": "5-7 days",
|
||||
"riskNotes": "MM-Fi CC BY-NC 4.0: AA must remain non-commercial and carry MM-Fi attribution; raw frames stay in private split; only derived CSI features + scores may be exposed"
|
||||
},
|
||||
"m6": {
|
||||
"name": "HF Space (Gradio) skeleton",
|
||||
"status": "BLOCKED",
|
||||
"completionCriteria": "HF Space deployed at ruvnet/aether-arena with submission lifecycle (submitted->validated->quarantined->smoke_scored->full_scored->published/rejected); sandboxed scorer container wired; basic leaderboard table rendered",
|
||||
"estimatedEffort": "7-10 days",
|
||||
"blockers": [
|
||||
"Needs HF_TOKEN — check .env for HF_TOKEN or HUGGINGFACE_TOKEN",
|
||||
"Needs user authorization to create/deploy ruvnet/aether-arena HF Space (outward-facing public deployment)"
|
||||
]
|
||||
},
|
||||
"m7": {
|
||||
"name": "Signed append-only Parquet results ledger",
|
||||
"status": "NOT_STARTED",
|
||||
"completionCriteria": "HF dataset ruvnet/aether-arena-results created; append-only Parquet ledger with signed rows; determinism_gate enforced; no row can be silently edited",
|
||||
"estimatedEffort": "3-5 days",
|
||||
"ledgerSchema": "submitter, model_ref, category, feature_set, tier, pck20, oks, mota, vitals_bpm_err, latency_p50, latency_p95, privacy_leakage, cross_room_deg, proof_sha256, scored_at, harness_version",
|
||||
"dependency": "M6 must be scaffolded first"
|
||||
},
|
||||
"m8": {
|
||||
"name": "RuView baseline entry + public launch",
|
||||
"status": "NOT_STARTED",
|
||||
"completionCriteria": "RuView wifi-densepose-pretrained baseline entered (honest PCK@20 ~2.5%); ADR-149 §7 five-step stranger acceptance test passes; v0 live with Presence + Pose + Edge-latency + Determinism categories active; Privacy and Cross-room shown as gated/coming-soon",
|
||||
"estimatedEffort": "3-5 days",
|
||||
"dependency": "M4+M5+M6+M7 complete",
|
||||
"notes": "ML SOTA improvement (PCK@20 ~72%) is a SEPARATE stretch goal blocked on ADR-079 P7-P9 camera ground truth. NOT a blocker for infra launch."
|
||||
}
|
||||
},
|
||||
"activeMilestone": "m2",
|
||||
"completedMilestones": ["m1"],
|
||||
"knownRisks": [
|
||||
"HF_TOKEN not confirmed present in .env — check before M6 work begins",
|
||||
"ruvnet/aether-arena public repo creation is outward-facing — needs explicit user authorization",
|
||||
"MM-Fi CC BY-NC 4.0: AA must stay legally non-commercial and brand-distinct from commercial RuView product; or seek MM-Fi commercial grant before any paid tier",
|
||||
"Wi-Pose has research-use-only terms (no redistribution grant) — excluded from v0; revisit only if terms are clarified with authors",
|
||||
"HF Space free CPU tier may be too slow for Candle/tch inference pipeline — may need ZeroGPU or self-hosted scorer on cognitum-20260110 GCloud A100/L4",
|
||||
"ADR-079 camera-ground-truth (PCK@20 SOTA) is P7-P9 pending — NOT an infra blocker; must not be conflated with AA infra completion",
|
||||
"Neutrality/governance risk: RuView seeded the scorer — must be demonstrably scored through the same public pipeline as any other entrant (§2.8 controls)"
|
||||
],
|
||||
"driftSignals": {
|
||||
"timeline": "GREEN — just initialized, no timeline pressure yet",
|
||||
"scope": "GREEN — scope locked at four-part structure per ADR-149 §2 decision",
|
||||
"approach": "GREEN — reuse pattern (existing ruview_metrics + proof.rs) confirmed in ADR-149",
|
||||
"dependency": "YELLOW — HF_TOKEN and ruvnet/aether-arena repo authorization are external blockers with unknown ETA",
|
||||
"priority": "GREEN — active feature branch feat/adr-136-146-streaming-engine in progress; AA infra can proceed in parallel on its own branch"
|
||||
},
|
||||
"stretchGoals": {
|
||||
"sotaML": "MM-Fi PCK@20 SOTA ~72% — separate ML effort blocked on ADR-079 P7-P9 camera-ground-truth data collection; NOT an infra exit criterion",
|
||||
"privacyAxis": "ADR-145 §10 membership-inference attacker — activate Privacy leaderboard axis once attacker is implemented and published",
|
||||
"crossRoom": "Multi-room held-out split — activate Cross-room generalization axis",
|
||||
"multiOrgSteering": "Invite co-maintainers from other projects once >=N external entries land"
|
||||
},
|
||||
"sessionHistory": [
|
||||
{
|
||||
"date": "2026-05-30",
|
||||
"type": "initialization",
|
||||
"accomplished": [
|
||||
"ADR-149 Accepted and committed to docs/adr/",
|
||||
"Horizon record initialized in .claude-flow/horizons/aether-arena-aa.json",
|
||||
"Memory stored in horizons namespace under key horizon-aether-arena-aa",
|
||||
"Session check-in record stored in horizon-sessions namespace"
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,11 +1,11 @@
|
||||
{
|
||||
"timestamp": "2026-05-25T06:07:33.385Z",
|
||||
"projectRoot": "C:\\Users\\ruv\\Projects\\wifi-densepose",
|
||||
"timestamp": "2026-02-28T16:13:19.193Z",
|
||||
"projectRoot": "/home/user/wifi-densepose",
|
||||
"structure": {
|
||||
"hasPackageJson": false,
|
||||
"hasTsConfig": false,
|
||||
"hasClaudeConfig": true,
|
||||
"hasClaudeFlow": true
|
||||
},
|
||||
"scannedAt": 1779689253386
|
||||
"scannedAt": 1772295199193
|
||||
}
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"timestamp": "2026-05-25T05:38:20.448Z",
|
||||
"timestamp": "2026-02-28T16:05:19.091Z",
|
||||
"patternsConsolidated": 0,
|
||||
"memoryCleaned": 0,
|
||||
"duplicatesRemoved": 0
|
||||
|
||||
@@ -1,17 +0,0 @@
|
||||
{
|
||||
"timestamp": "2026-05-25T05:59:05.405Z",
|
||||
"mode": "local",
|
||||
"memoryUsage": {
|
||||
"rss": 9891840,
|
||||
"heapTotal": 35598336,
|
||||
"heapUsed": 26516560,
|
||||
"external": 3952418,
|
||||
"arrayBuffers": 55689
|
||||
},
|
||||
"uptime": 27163.5846658,
|
||||
"optimizations": {
|
||||
"cacheHitRate": 0.78,
|
||||
"avgResponseTime": 45
|
||||
},
|
||||
"note": "Install Claude Code CLI for AI-powered optimization suggestions"
|
||||
}
|
||||
@@ -1,84 +1,12 @@
|
||||
{
|
||||
"timestamp": "2026-05-25T06:08:29.589Z",
|
||||
"mode": "headless",
|
||||
"workerType": "audit",
|
||||
"model": "haiku",
|
||||
"durationMs": 56168,
|
||||
"executionId": "audit_1779689253421_dfflmb",
|
||||
"success": true,
|
||||
"findings": {
|
||||
"vulnerabilities": [
|
||||
{
|
||||
"severity": "high",
|
||||
"file": ".claude/helpers/github-safe.js",
|
||||
"line": 50,
|
||||
"description": "Command injection vulnerability in execSync call. User-controlled arguments in `newArgs` are joined without shell escaping. An attacker can inject shell metacharacters (e.g., `; rm -rf /`) via the body content or through command/subcommand parameters. The temp file approach is safe, but the command construction `gh ${command} ${subcommand} ${newArgs.join(' ')}` allows shell injection.",
|
||||
"example": "gh issue comment 123 'test`whoami`' would execute whoami"
|
||||
},
|
||||
{
|
||||
"severity": "high",
|
||||
"file": "scripts/csi-spectrogram.js",
|
||||
"line": 45,
|
||||
"description": "Sensitive credential exposure via command-line arguments. The `--seed-token` parameter is passed as a CLI argument, which is visible in process listings (ps aux output). This violates secure credential handling practices. Tokens should be read from environment variables or secure config files, not command-line args.",
|
||||
"example": "node scripts/csi-spectrogram.js --seed-token secret_abc_123 exposes token in process list"
|
||||
},
|
||||
{
|
||||
"severity": "medium",
|
||||
"file": "scripts/apnea-detector.js",
|
||||
"line": 71,
|
||||
"description": "Unsafe buffer reading without comprehensive length validation. The code checks `buf.length` at 32 bytes (line 70) but then reads at fixed offsets (lines 72-76) without validating that each read stays within bounds. If a malformed packet is received, `readInt8/readUInt16LE/readUInt32LE` may read unintended data or zeros.",
|
||||
"example": "A 33-byte buffer would pass the check but reading UInt32LE at offset 8 would go out of bounds"
|
||||
},
|
||||
{
|
||||
"severity": "medium",
|
||||
"file": "scripts/benchmark-rf-scan.js",
|
||||
"line": 110,
|
||||
"description": "Potential out-of-bounds buffer access in parseCSIFrame. While the bounds check at line 107 is present, the `nSubcarriers` value from the packet is used to calculate required buffer size without validation of the value itself. A maliciously crafted packet with extremely large nSubcarriers could cause memory issues.",
|
||||
"example": "Packet with nSubcarriers=999999 would request excessive buffer allocation"
|
||||
},
|
||||
{
|
||||
"severity": "medium",
|
||||
"file": "scripts/csi-spectrogram.js",
|
||||
"line": 39,
|
||||
"description": "Unsafe URL construction with untrusted `seed-url` parameter. The `--seed-url` argument is used directly for HTTPS requests without validation. This could allow SSRF (Server-Side Request Forgery) or DNS rebinding attacks if an attacker controls the seed URL.",
|
||||
"example": "node scripts/csi-spectrogram.js --seed-url http://internal.local:9000 could access internal services"
|
||||
},
|
||||
{
|
||||
"severity": "low",
|
||||
"file": ".claude/helpers/statusline.js",
|
||||
"line": 140,
|
||||
"description": "Shell command injection risk in execSync calls. Commands like `ps aux 2>/dev/null | grep -c agentic-flow` use grep patterns that could be vulnerable if any variables are interpolated (though currently hardcoded). The `execSync` with shell=true is generally risky.",
|
||||
"example": "If any pattern becomes user-controlled: `grep -c ${pattern}` could inject shell metacharacters"
|
||||
},
|
||||
{
|
||||
"severity": "low",
|
||||
"file": ".claude/helpers/memory.js",
|
||||
"line": 10,
|
||||
"description": "Unvalidated JSON parsing. The code parses JSON from MEMORY_FILE without try-catch in the loadMemory function (catches error but doesn't validate structure). Malformed JSON or corrupted memory file could cause issues.",
|
||||
"example": "Memory file with circular JSON structure could cause issues when stringifying"
|
||||
},
|
||||
{
|
||||
"severity": "low",
|
||||
"file": "scripts/device-fingerprint.js",
|
||||
"line": 72,
|
||||
"description": "Hardcoded device fingerprints and network configuration. While not a traditional 'hardcoded secret', the KNOWN_DEVICES array contains identifiable SSIDs and MAC addresses that could be used to correlate network infrastructure. This data should be externalized or sanitized.",
|
||||
"example": "SSID 'ruv.net' and 'Cohen-Guest' could identify specific installations"
|
||||
}
|
||||
],
|
||||
"riskScore": 42,
|
||||
"recommendations": [
|
||||
"**CRITICAL**: Replace `execSync` command construction in github-safe.js with proper shell escaping using `child_process.execFile()` instead of `execSync()`, or use the `shell: false` option with array arguments to avoid shell parsing entirely.",
|
||||
"**CRITICAL**: Move `--seed-token` from CLI arguments to environment variable `SEED_TOKEN` in csi-spectrogram.js. Update documentation to instruct users: `export SEED_TOKEN=...` instead of passing via CLI.",
|
||||
"**HIGH**: Add comprehensive buffer bounds validation in all UDP packet parsing functions (apnea-detector.js, benchmark-rf-scan.js, etc.). Validate both the buffer length AND the parsed header values before using them in calculations.",
|
||||
"**HIGH**: Validate and sanitize the `--seed-url` parameter in csi-spectrogram.js. Whitelist allowed domains or restrict to localhost/internal IPs only. Add URL scheme validation (https only).",
|
||||
"**MEDIUM**: Replace hardcoded device fingerprints (KNOWN_DEVICES) with externalized configuration or environment variables. Document that this data contains identifiable network information.",
|
||||
"**MEDIUM**: Add input validation to `parseArgs()` results in all scripts. Validate numeric ranges, file paths, and enum values before use.",
|
||||
"**LOW**: Wrap JSON.parse() calls in try-catch blocks throughout (memory.js, session.js) with explicit error handling and recovery.",
|
||||
"**LOW**: Audit all uses of `require()` with dynamic paths. Ensure paths are always derived from fixed `__dirname` and not user-controlled.",
|
||||
"**LOW**: Remove or sandbox the ability to pass arbitrary URLs via CLI. Consider using a configuration file (YAML/JSON) for endpoint URLs instead.",
|
||||
"**INFO**: Add a pre-commit hook to detect hardcoded credentials using tools like `detect-secrets` or `truffleHog`."
|
||||
]
|
||||
"timestamp": "2026-03-06T13:17:27.368Z",
|
||||
"mode": "local",
|
||||
"checks": {
|
||||
"envFilesProtected": true,
|
||||
"gitIgnoreExists": true,
|
||||
"noHardcodedSecrets": true
|
||||
},
|
||||
"rawOutputPreview": "# Security Audit Report — wifi-densepose\n\n```json\n{\n \"vulnerabilities\": [\n {\n \"severity\": \"high\",\n \"file\": \".claude/helpers/github-safe.js\",\n \"line\": 50,\n \"description\": \"Command injection vulnerability in execSync call. User-controlled arguments in `newArgs` are joined without shell escaping. An attacker can inject shell metacharacters (e.g., `; rm -rf /`) via the body content or through command/subcommand parameters. The temp file approach is safe, but the command construction `gh ${command} ${subcommand} ${newArgs.join(' ')}` allows shell injection.\",\n \"example\": \"gh issue comment 123 'test`whoami`' would execute whoami\"\n },\n {\n \"severity\": \"high\",\n \"file\": \"scripts/csi-spectrogram.js\",\n \"line\": 45,\n \"description\": \"Sensitive credential exposure via command-line arguments. The `--seed-token` parameter is passed as a CLI argument, which is visible in process listings (ps aux output). This violates secure credential handling practices. Tokens should be read from environment variables or secure config files, not command-line args.\",\n \"example\": \"node scripts/csi-spectrogram.js --seed-token secret_abc_123 exposes token in process list\"\n },\n {\n \"severity\": \"medium\",\n \"file\": \"scripts/apnea-detector.js\",\n \"line\": 71,\n \"description\": \"Unsafe buffer reading without comprehensive length validation. The code checks `buf.length` at 32 bytes (line 70) but then reads at fixed offsets (lines 72-76) without validating that each read stays within bounds. If a malformed packet is received, `readInt8/readUInt16LE/readUInt32LE` may read unintended data or zeros.\",\n \"example\": \"A 33-byte buffer would pass the check but reading UInt32LE at offset 8 would go out of bounds\"\n },\n {\n \"severity\": \"medium\",\n \"file\": \"scripts/benchmark-rf-scan.js\",\n \"line\": 110,\n \"description\": \"Potential out-of-bounds buffer access in parseCSIFrame. While the bounds check at line 107 is pres",
|
||||
"rawOutputLength": 7077
|
||||
"riskLevel": "low",
|
||||
"recommendations": [],
|
||||
"note": "Install Claude Code CLI for AI-powered security analysis"
|
||||
}
|
||||
@@ -1,106 +0,0 @@
|
||||
{
|
||||
"timestamp": "2026-05-25T06:11:52.519Z",
|
||||
"mode": "headless",
|
||||
"workerType": "testgaps",
|
||||
"model": "sonnet",
|
||||
"durationMs": 259124,
|
||||
"executionId": "testgaps_1779689253395_srltd5",
|
||||
"success": true,
|
||||
"findings": {
|
||||
"sections": [
|
||||
{
|
||||
"title": "Test Coverage Gap Analysis — wifi-densepose",
|
||||
"content": "\n",
|
||||
"level": 2
|
||||
},
|
||||
{
|
||||
"title": "Coverage Summary by Crate",
|
||||
"content": "\n| Crate | Tests Found | Status | Priority |\n|-------|-------------|--------|----------|\n| `wifi-densepose-core` | 26 inline | Good | Low |\n| `wifi-densepose-signal` | ~60 (validation only) | Moderate | **High** |\n| `wifi-densepose-nn` | **0** | Critical | **P1** |\n| `wifi-densepose-train` | ~60 (config/dataset) | Moderate | High |\n| `wifi-densepose-mat` | 1 integration test | Critical | **P1** |\n| `wifi-densepose-ruvector` | **0** | Critical | **P1** |\n| `wifi-densepose-sensing-server` | 4 integration tests | Moderate | High |\n| `wifi-densepose-wasm` | 3 compliance tests | Low | Low |\n\n---\n\n",
|
||||
"level": 3
|
||||
},
|
||||
{
|
||||
"title": "Tier 1: Critical Gaps",
|
||||
"content": "\n",
|
||||
"level": 2
|
||||
},
|
||||
{
|
||||
"title": "1. `wifi-densepose-nn` — Zero test coverage",
|
||||
"content": "\nEvery public API is untested. Place these at `v2/crates/wifi-densepose-nn/tests/inference_tests.rs`:\n\n```rust\n// v2/crates/wifi-densepose-nn/tests/inference_tests.rs\n\n#[cfg(test)]\nmod tensor_tests {\n use wifi_densepose_nn::tensor::Tensor;\n\n #[test]\n fn tensor_shape_mismatch_returns_error() {\n // data has 6 elements but shape claims 3×3=9\n let result = Tensor::new(vec![1.0f32; 6], &[3, 3]);\n assert!(result.is_err(), \"shape mismatch must be rejected\");\n }\n\n #[test]\n fn tensor_empty_data_returns_error() {\n let result = Tensor::new(vec![], &[0]);\n assert!(result.is_err());\n }\n\n #[test]\n fn tensor_nan_values_are_detected() {\n let t = Tensor::new(vec![f32::NAN, 1.0, 2.0], &[3]).unwrap();\n assert!(t.has_nan(), \"NaN in data must be detectable\");\n }\n\n #[test]\n fn tensor_inf_values_are_detected() {\n let t = Tensor::new(vec![f32::INFINITY, 1.0], &[2]).unwrap();\n assert!(t.has_inf());\n }\n}\n\n#[cfg(test)]\nmod modality_translator_tests {\n use wifi_densepose_nn::translator::ModalityTranslator;\n\n #[test]\n fn translator_rejects_wrong_subcarrier_count() {\n // standard expects 56 subcarriers; feed 57\n let csi = vec![0.0f32; 57 * 3]; // 57 subcarriers × 3 antennas\n let translator = ModalityTranslator::default();\n let result = translator.translate(&csi, 57, 3);\n assert!(result.is_err());\n }\n\n #[test]\n fn translator_handles_all_zeros() {\n let csi = vec![0.0f32; 56 * 3];\n let translator = ModalityTranslator::default();\n let result = translator.translate(&csi, 56, 3);\n // zero input should produce some output without panic\n assert!(result.is_ok());\n }\n}\n\n#[cfg(test)]\nmod inference_engine_tests {\n use wifi_densepose_nn::inference::InferenceEngine;\n\n #[test]\n fn load_nonexistent_model_returns_error() {\n let result = InferenceEngine::from_path(\"/nonexistent/model.onnx\");\n assert!(result.is_err());\n }\n\n #[test]\n fn load_corrupted_bytes_returns_error() {\n let tmp = tempfile::NamedTempFile::new().unwrap();\n std::fs::write(tmp.path(), b\"not a valid onnx file\").unwrap();\n let result = InferenceEngine::from_path(tmp.path());\n assert!(result.is_err());\n }\n\n #[test]\n fn batch_size_zero_returns_error() {\n // can't run inference on an empty batch\n // requires a valid model; skip if no model file in test fixtures\n // use #[ignore] or a feature flag for CI\n }\n}\n```\n\n---\n\n",
|
||||
"level": 3
|
||||
},
|
||||
{
|
||||
"title": "2. `wifi-densepose-mat` — Disaster response safety gaps",
|
||||
"content": "\nPlace at `v2/crates/wifi-densepose-mat/tests/`:\n\n```rust\n// v2/crates/wifi-densepose-mat/tests/detection_edge_cases.rs\n\n#[cfg(test)]\nmod breathing_rate_edge_cases {\n use wifi_densepose_mat::detection::breathing::BreathingDetector;\n\n #[test]\n fn zero_bpm_is_classified_critical() {\n let detector = BreathingDetector::default();\n // flat-line signal — no breathing detected\n let signal = vec![0.0f32; 1000];\n let result = detector.classify(&signal).unwrap();\n assert_eq!(result.triage_category, TriageCategory::Immediate);\n }\n\n #[test]\n fn agonal_breathing_rate_triggers_immediate() {\n // < 6 BPM is agonal; simulate 3 BPM signal\n let detector = BreathingDetector::default();\n let signal = generate_breathing_signal(3.0, 1000, 100.0); // 3 BPM, 1000 samples @ 100 Hz\n let result = detector.classify(&signal).unwrap();\n assert_eq!(result.triage_category, TriageCategory::Immediate);\n }\n\n #[test]\n fn normal_breathing_is_classified_minor() {\n let detector = BreathingDetector::default();\n let signal = generate_breathing_signal(15.0, 1000, 100.0); // 15 BPM\n let result = detector.classify(&signal).unwrap();\n assert_eq!(result.triage_category, TriageCategory::Minor);\n }\n\n #[test]\n fn all_nan_signal_returns_error_not_panic() {\n let detector = BreathingDetector::default();\n let signal = vec![f32::NAN; 1000];\n let result = detector.classify(&signal);\n assert!(result.is_err(), \"NaN input must be caught, not panic\");\n }\n\n fn generate_breathing_signal(bpm: f32, samples: usize, sample_rate: f32) -> Vec<f32> {\n let freq = bpm / 60.0;\n (0..samples)\n .map(|i| (2.0 * std::f32::consts::PI * freq * i as f32 / sample_rate).sin())\n .collect()\n }\n}\n\n#[cfg(test)]\nmod alert_deduplication {\n use wifi_densepose_mat::alerting::{AlertDispatcher, Alert, TriageCategory};\n use std::time::Duration;\n\n #[test]\n fn duplicate_alerts_within_window_are_suppressed() {\n let mut dispatcher = AlertDispatcher::new();\n let alert = Alert::new(\"survivor-1\", TriageCategory::Immediate);\n dispatcher.dispatch(alert.clone());\n dispatcher.dispatch(alert.clone()); // same survivor, same category\n assert_eq!(dispatcher.queued_count(), 1, \"duplicate must be deduplicated\");\n }\n\n #[test]\n fn escalation_from_minor_to_immediate_is_forwarded() {\n let mut dispatcher = AlertDispatcher::new();\n dispatcher.dispatch(Alert::new(\"survivor-1\", TriageCategory::Minor));\n dispatcher.dispatch(Alert::new(\"survivor-1\", TriageCategory::Immediate));\n // escalation is not a duplicate — must pass through\n assert!(dispatcher.last_alert_for(\"survivor-1\").map(|a| a.category) == Some(TriageCategory::Immediate));\n }\n}\n\n#[cfg(test)]\nmod kalman_tracker_edge_cases {\n use wifi_densepose_mat::tracking::KalmanTracker;\n\n #[test]\n fn position_jump_does_not_corrupt_state() {\n let mut tracker = KalmanTracker::new();\n tracker.update([1.0, 1.0, 0.5]); // initial position\n tracker.update([50.0, 50.0, 0.5]); // physically impossible jump\n let pos = tracker.estimated_position();\n // should not panic; should clamp or flag anomaly\n assert!(pos.iter().all(|v| v.is_finite()));\n }\n\n #[test]\n fn lost_track_resumes_on_re_detection() {\n let mut tracker = KalmanTracker::new();\n tracker.update([1.0, 1.0, 0.5]);\n // simulate 10 missed frames\n for _ in 0..10 { tracker.predict(); }\n assert_eq!(tracker.state(), TrackState::Lost);\n tracker.update([1.1, 1.1, 0.5]); // re-detected nearby\n assert_eq!(tracker.state(), TrackState::Confirmed);\n }\n}\n```\n\n---\n\n",
|
||||
"level": 3
|
||||
},
|
||||
{
|
||||
"title": "3. `wifi-densepose-ruvector` — Zero coverage on all 5 integration modules",
|
||||
"content": "\n```rust\n// v2/crates/wifi-densepose-ruvector/tests/viewpoint_tests.rs\n\n#[cfg(test)]\nmod attention_tests {\n use wifi_densepose_ruvector::viewpoint::attention::CrossViewpointAttention;\n\n #[test]\n fn attention_weights_sum_to_one() {\n let attn = CrossViewpointAttention::new(3); // 3 viewpoints\n let features = vec![[1.0f32; 64], [2.0f32; 64], [3.0f32; 64]];\n let weights = attn.compute_weights(&features);\n let sum: f32 = weights.iter().sum();\n assert!((sum - 1.0).abs() < 1e-5, \"attention must be a probability distribution\");\n }\n\n #[test]\n fn single_viewpoint_gets_full_weight() {\n let attn = CrossViewpointAttention::new(1);\n let features = vec![[1.0f32; 64]];\n let weights = attn.compute_weights(&features);\n assert!((weights[0] - 1.0).abs() < 1e-6);\n }\n\n #[test]\n fn zero_feature_vectors_do_not_produce_nan() {\n let attn = CrossViewpointAttention::new(2);\n let features = vec![[0.0f32; 64], [0.0f32; 64]];\n let weights = attn.compute_weights(&features);\n assert!(weights.iter().all(|w| w.is_finite()));\n }\n}\n\n#[cfg(test)]\nmod sketch_tests {\n use wifi_densepose_ruvector::sketch::WireSketch;\n\n #[test]\n fn round_trip_serialization() {\n let sketch = WireSketch::from_keypoints(&[[0.5f32, 0.5], [0.3, 0.7]]);\n let bytes = sketch.to_bytes();\n let restored = WireSketch::from_bytes(&bytes).unwrap();\n assert_eq!(sketch, restored);\n }\n\n #[test]\n fn deserialize_truncated_bytes_returns_error() {\n let sketch = WireSketch::from_keypoints(&[[0.5f32, 0.5]]);\n let mut bytes = sketch.to_bytes();\n bytes.truncate(bytes.len() / 2); // truncate halfway\n assert!(WireSketch::from_bytes(&bytes).is_err());\n }\n\n #[test]\n fn empty_keypoint_list_is_handled() {\n let sketch = WireSketch::from_keypoints(&[]);\n assert_eq!(sketch.keypoint_count(), 0);\n }\n}\n```\n\n---\n\n",
|
||||
"level": 3
|
||||
},
|
||||
{
|
||||
"title": "Tier 2: Signal Processing Gaps",
|
||||
"content": "\n",
|
||||
"level": 2
|
||||
},
|
||||
{
|
||||
"title": "4. `wifi-densepose-signal` — RuvSense module untested",
|
||||
"content": "\n```rust\n// v2/crates/wifi-densepose-signal/tests/ruvsense_tests.rs\n\n#[cfg(test)]\nmod coherence_gate_tests {\n use wifi_densepose_signal::ruvsense::coherence_gate::{CoherenceGate, GateDecision};\n\n #[test]\n fn high_coherence_signal_is_accepted() {\n let gate = CoherenceGate::new(0.7); // threshold = 0.7\n let decision = gate.evaluate(0.95);\n assert_eq!(decision, GateDecision::Accept);\n }\n\n #[test]\n fn low_coherence_signal_is_rejected() {\n let gate = CoherenceGate::new(0.7);\n let decision = gate.evaluate(0.3);\n assert_eq!(decision, GateDecision::Reject);\n }\n\n #[test]\n fn borderline_coherence_triggers_recalibrate() {\n let gate = CoherenceGate::new(0.7);\n let decision = gate.evaluate(0.68); // just below threshold\n assert_eq!(decision, GateDecision::Recalibrate);\n }\n}\n\n#[cfg(test)]\nmod phase_align_tests {\n use wifi_densepose_signal::ruvsense::phase_align::PhaseAligner;\n\n #[test]\n fn phase_at_plus_pi_does_not_wrap_incorrectly() {\n let aligner = PhaseAligner::new();\n let phases = vec![std::f32::consts::PI - 0.001, std::f32::consts::PI + 0.001];\n let aligned = aligner.align(&phases);\n // jump across ±π boundary must be handled continuously\n let diff = (aligned[1] - aligned[0]).abs();\n assert!(diff < 0.01, \"phase jump at ±π must be < 0.01 rad after alignment\");\n }\n\n #[test]\n fn single_phase_value_aligns_to_itself() {\n let aligner = PhaseAligner::new();\n let phases = vec![1.5f32];\n let aligned = aligner.align(&phases);\n assert_eq!(aligned.len(), 1);\n assert!((aligned[0] - 1.5).abs() < 1e-6);\n }\n\n #[test]\n fn empty_phase_array_returns_empty() {\n let aligner = PhaseAligner::new();\n let aligned = aligner.align(&[]);\n assert!(aligned.is_empty());\n }\n}\n\n#[cfg(test)]\nmod adversarial_detection_tests {\n use wifi_densepose_signal::ruvsense::adversarial::AdversarialDetector;\n\n #[test]\n fn physically_impossible_amplitude_is_flagged() {\n let detector = AdversarialDetector::new();\n // WiFi amplitude cannot exceed hardware saturation level\n let frame = vec![1e9f32; 56]; // absurdly large\n assert!(detector.is_suspicious(&frame));\n }\n\n #[test]\n fn normal_amplitude_range_passes() {\n let detector = AdversarialDetector::new();\n let frame = vec![0.5f32; 56]; // typical normalized value\n assert!(!detector.is_suspicious(&frame));\n }\n\n #[test]\n fn multi_link_inconsistency_is_detected() {\n // link A reports body moving right; link B reports no motion\n // physically inconsistent — flag as adversarial\n let detector = AdversarialDetector::new();\n let result = detector.check_multi_link_consistency(\n &[1.0, 2.0, 3.0], // link A\n &[0.0, 0.0, 0.0], // link B (no motion)\n );\n assert!(result.is_inconsistent());\n }\n}\n```\n\n---\n\n",
|
||||
"level": 3
|
||||
},
|
||||
{
|
||||
"title": "Tier 2: Training Pipeline Gaps",
|
||||
"content": "\n",
|
||||
"level": 2
|
||||
},
|
||||
{
|
||||
"title": "5. `wifi-densepose-train` — Geometry encoder and rapid adaptation untested",
|
||||
"content": "\n```rust\n// v2/crates/wifi-densepose-train/tests/test_geometry.rs\n\n#[cfg(test)]\nmod film_layer_tests {\n use wifi_densepose_train::geometry::FilmLayer;\n\n #[test]\n fn film_layer_output_shape_matches_input() {\n let film = FilmLayer::new(64, 32); // 64-dim features, 32-dim condition\n let features = vec![0.5f32; 64];\n let condition = vec![1.0f32; 32];\n let output = film.forward(&features, &condition).unwrap();\n assert_eq!(output.len(), 64, \"FiLM output must match feature dimensionality\");\n }\n\n #[test]\n fn film_layer_zero_condition_acts_as_identity() {\n let film = FilmLayer::new(64, 32);\n let features = vec![1.0f32; 64];\n let zero_condition = vec![0.0f32; 32];\n let output = film.forward(&features, &zero_condition).unwrap();\n // scale=1, shift=0 → identity; output ≈ input\n for (o, f) in output.iter().zip(features.iter()) {\n assert!((o - f).abs() < 0.1, \"zero condition should approximate identity\");\n }\n }\n}\n\n// v2/crates/wifi-densepose-train/tests/test_rapid_adapt.rs\n\n#[cfg(test)]\nmod rapid_adaptation_tests {\n use wifi_densepose_train::rapid_adapt::RapidAdapter;\n\n #[test]\n fn adapter_updates_on_single_sample() {\n let mut adapter = RapidAdapter::new(5); // 5 adaptation steps\n let csi_sample = vec![0.1f32; 56 * 3];\n let pose_label = vec![0.5f32; 17 * 2]; // 17 keypoints × (x, y)\n let result = adapter.adapt_step(&csi_sample, &pose_label);\n assert!(result.is_ok());\n }\n\n #[test]\n fn adapter_with_zero_steps_is_no_op() {\n let adapter = RapidAdapter::new(0);\n // 0 adaptation steps → weights unchanged\n let initial_weights = adapter.clone_weights();\n let _ = adapter.adapt_step(&vec![0.1f32; 168], &vec![0.5f32; 34]);\n assert_eq!(adapter.clone_weights(), initial_weights);\n }\n}\n```\n\n---\n\n",
|
||||
"level": 3
|
||||
},
|
||||
{
|
||||
"title": "Tier 3: Server Integration Gaps",
|
||||
"content": "\n",
|
||||
"level": 2
|
||||
},
|
||||
{
|
||||
"title": "6. `wifi-densepose-sensing-server` — Auth and semantic analyzers",
|
||||
"content": "\n```rust\n// v2/crates/wifi-densepose-sensing-server/tests/auth_tests.rs\n\n#[cfg(test)]\nmod bearer_auth_tests {\n use wifi_densepose_sensing_server::auth::{BearerValidator, TokenError};\n\n #[test]\n fn missing_authorization_header_returns_unauthorized() {\n let validator = BearerValidator::new(\"secret-token\");\n let result = validator.validate(None);\n assert!(matches!(result, Err(TokenError::Missing)));\n }\n\n #[test]\n fn wrong_token_is_rejected() {\n let validator = BearerValidator::new(\"correct-token\");\n let result = validator.validate(Some(\"Bearer wrong-token\"));\n assert!(matches!(result, Err(TokenError::Invalid)));\n }\n\n #[test]\n fn malformed_header_without_bearer_prefix_is_rejected() {\n let validator = BearerValidator::new(\"token\");\n let result = validator.validate(Some(\"token\")); // missing \"Bearer \" prefix\n assert!(matches!(result, Err(TokenError::Malformed)));\n }\n\n #[test]\n fn correct_token_is_accepted() {\n let validator = BearerValidator::new(\"correct-token\");\n let result = validator.validate(Some(\"Bearer correct-token\"));\n assert!(result.is_ok());\n }\n}\n\n// v2/crates/wifi-densepose-sensing-server/tests/semantic_tests.rs\n\n#[cfg(test)]\nmod fall_detection_tests {\n use wifi_densepose_sensing_server::semantic::fall_detector::FallDetector;\n\n #[test]\n fn no_motion_does_not_trigger_fall() {\n let mut detector = FallDetector::new();\n for _ in 0..30 { // 30 frames of stillness\n detector.update_pose(stationary_pose());\n }\n assert!(!detector.fall_detected());\n }\n\n #[test]\n fn rapid_downward_velocity_triggers_fall() {\n let mut detector = FallDetector::new();\n // simulate person going from standing (y=1.7m) to prone (y=0.3m) in 3 frames\n for (frame, y) in [(0, 1.7f32), (1, 1.0), (2, 0.3)] {\n detector.update_pose(pose_at_height(y));\n }\n assert!(detector.fall_detected());\n }\n\n #[test]\n fn sitting_down_slowly_does_not_trigger_fall() {\n let mut detector = FallDetector::new();\n // gradual height decrease over 30 frames is sitting, not falling\n for i in 0..30 {\n let y = 1.7f32 - (i as f32 * 0.04); // ~1.2m drop over 30 frames\n detector.update_pose(pose_at_height(y));\n }\n assert!(!detector.fall_detected());\n }\n}\n```\n\n---\n\n",
|
||||
"level": 3
|
||||
},
|
||||
{
|
||||
"title": "Cross-Cutting Gap Summary",
|
||||
"content": "| Gap Category | Severity | Affects | Recommended Action |\n|---|---|---|---|\n| `wifi-densepose-nn` has 0 tests | **Critical** | Inference pipeline | Add `tests/inference_tests.rs` per skeleton above |\n| `wifi-densepose-ruvector` has 0 tests | **Critical** | Viewpoint fusion, sketches | Add `tests/viewpoint_tests.rs` |\n| MAT disaster response missing edge cases | **Critical** | 0 BPM, agonal breathing, dedup | Add `tests/detection_edge_cases.rs` |\n| Signal RuvSense 28 modules untested | High | Core sensing logic | Add `tests/ruvsense_tests.rs` |\n| NN error paths (bad model files, OOM) | High | Production reliability | Add error path tests to nn |\n| Train geometry + rapid adapt = 0 tests | High | Domain adaptation | Add `tests/test_geometry.rs` |\n| Server auth token validation | High | Security boundary | Add `tests/auth_tests.rs` |\n| NaN/Inf propagation in f32 pipelines | High | All numeric crates | Add boundary tests per module |\n| Concurrent state under Arc<Mutex> | Medium | sensing-server, mat | Add contention tests |\n\nThe highest-ROI starting point is `wifi-densepose-nn` and `wifi-densepose-mat` — the nn crate has zero tests on the core inference pipeline, and mat covers life-safety scenarios where classification errors have real consequences.",
|
||||
"level": 2
|
||||
}
|
||||
],
|
||||
"codeBlocks": [
|
||||
{
|
||||
"language": "rust",
|
||||
"code": "// v2/crates/wifi-densepose-nn/tests/inference_tests.rs\n\n#[cfg(test)]\nmod tensor_tests {\n use wifi_densepose_nn::tensor::Tensor;\n\n #[test]\n fn tensor_shape_mismatch_returns_error() {\n // data has 6 elements but shape claims 3×3=9\n let result = Tensor::new(vec![1.0f32; 6], &[3, 3]);\n assert!(result.is_err(), \"shape mismatch must be rejected\");\n }\n\n #[test]\n fn tensor_empty_data_returns_error() {\n let result = Tensor::new(vec![], &[0]);\n assert!(result.is_err());\n }\n\n #[test]\n fn tensor_nan_values_are_detected() {\n let t = Tensor::new(vec![f32::NAN, 1.0, 2.0], &[3]).unwrap();\n assert!(t.has_nan(), \"NaN in data must be detectable\");\n }\n\n #[test]\n fn tensor_inf_values_are_detected() {\n let t = Tensor::new(vec![f32::INFINITY, 1.0], &[2]).unwrap();\n assert!(t.has_inf());\n }\n}\n\n#[cfg(test)]\nmod modality_translator_tests {\n use wifi_densepose_nn::translator::ModalityTranslator;\n\n #[test]\n fn translator_rejects_wrong_subcarrier_count() {\n // standard expects 56 subcarriers; feed 57\n let csi = vec![0.0f32; 57 * 3]; // 57 subcarriers × 3 antennas\n let translator = ModalityTranslator::default();\n let result = translator.translate(&csi, 57, 3);\n assert!(result.is_err());\n }\n\n #[test]\n fn translator_handles_all_zeros() {\n let csi = vec![0.0f32; 56 * 3];\n let translator = ModalityTranslator::default();\n let result = translator.translate(&csi, 56, 3);\n // zero input should produce some output without panic\n assert!(result.is_ok());\n }\n}\n\n#[cfg(test)]\nmod inference_engine_tests {\n use wifi_densepose_nn::inference::InferenceEngine;\n\n #[test]\n fn load_nonexistent_model_returns_error() {\n let result = InferenceEngine::from_path(\"/nonexistent/model.onnx\");\n assert!(result.is_err());\n }\n\n #[test]\n fn load_corrupted_bytes_returns_error() {\n let tmp = tempfile::NamedTempFile::new().unwrap();\n std::fs::write(tmp.path(), b\"not a valid onnx file\").unwrap();\n let result = InferenceEngine::from_path(tmp.path());\n assert!(result.is_err());\n }\n\n #[test]\n fn batch_size_zero_returns_error() {\n // can't run inference on an empty batch\n // requires a valid model; skip if no model file in test fixtures\n // use #[ignore] or a feature flag for CI\n }\n}"
|
||||
},
|
||||
{
|
||||
"language": "rust",
|
||||
"code": "// v2/crates/wifi-densepose-mat/tests/detection_edge_cases.rs\n\n#[cfg(test)]\nmod breathing_rate_edge_cases {\n use wifi_densepose_mat::detection::breathing::BreathingDetector;\n\n #[test]\n fn zero_bpm_is_classified_critical() {\n let detector = BreathingDetector::default();\n // flat-line signal — no breathing detected\n let signal = vec![0.0f32; 1000];\n let result = detector.classify(&signal).unwrap();\n assert_eq!(result.triage_category, TriageCategory::Immediate);\n }\n\n #[test]\n fn agonal_breathing_rate_triggers_immediate() {\n // < 6 BPM is agonal; simulate 3 BPM signal\n let detector = BreathingDetector::default();\n let signal = generate_breathing_signal(3.0, 1000, 100.0); // 3 BPM, 1000 samples @ 100 Hz\n let result = detector.classify(&signal).unwrap();\n assert_eq!(result.triage_category, TriageCategory::Immediate);\n }\n\n #[test]\n fn normal_breathing_is_classified_minor() {\n let detector = BreathingDetector::default();\n let signal = generate_breathing_signal(15.0, 1000, 100.0); // 15 BPM\n let result = detector.classify(&signal).unwrap();\n assert_eq!(result.triage_category, TriageCategory::Minor);\n }\n\n #[test]\n fn all_nan_signal_returns_error_not_panic() {\n let detector = BreathingDetector::default();\n let signal = vec![f32::NAN; 1000];\n let result = detector.classify(&signal);\n assert!(result.is_err(), \"NaN input must be caught, not panic\");\n }\n\n fn generate_breathing_signal(bpm: f32, samples: usize, sample_rate: f32) -> Vec<f32> {\n let freq = bpm / 60.0;\n (0..samples)\n .map(|i| (2.0 * std::f32::consts::PI * freq * i as f32 / sample_rate).sin())\n .collect()\n }\n}\n\n#[cfg(test)]\nmod alert_deduplication {\n use wifi_densepose_mat::alerting::{AlertDispatcher, Alert, TriageCategory};\n use std::time::Duration;\n\n #[test]\n fn duplicate_alerts_within_window_are_suppressed() {\n let mut dispatcher = AlertDispatcher::new();\n let alert = Alert::new(\"survivor-1\", TriageCategory::Immediate);\n dispatcher.dispatch(alert.clone());\n dispatcher.dispatch(alert.clone()); // same survivor, same category\n assert_eq!(dispatcher.queued_count(), 1, \"duplicate must be deduplicated\");\n }\n\n #[test]\n fn escalation_from_minor_to_immediate_is_forwarded() {\n let mut dispatcher = AlertDispatcher::new();\n dispatcher.dispatch(Alert::new(\"survivor-1\", TriageCategory::Minor));\n dispatcher.dispatch(Alert::new(\"survivor-1\", TriageCategory::Immediate));\n // escalation is not a duplicate — must pass through\n assert!(dispatcher.last_alert_for(\"survivor-1\").map(|a| a.category) == Some(TriageCategory::Immediate));\n }\n}\n\n#[cfg(test)]\nmod kalman_tracker_edge_cases {\n use wifi_densepose_mat::tracking::KalmanTracker;\n\n #[test]\n fn position_jump_does_not_corrupt_state() {\n let mut tracker = KalmanTracker::new();\n tracker.update([1.0, 1.0, 0.5]); // initial position\n tracker.update([50.0, 50.0, 0.5]); // physically impossible jump\n let pos = tracker.estimated_position();\n // should not panic; should clamp or flag anomaly\n assert!(pos.iter().all(|v| v.is_finite()));\n }\n\n #[test]\n fn lost_track_resumes_on_re_detection() {\n let mut tracker = KalmanTracker::new();\n tracker.update([1.0, 1.0, 0.5]);\n // simulate 10 missed frames\n for _ in 0..10 { tracker.predict(); }\n assert_eq!(tracker.state(), TrackState::Lost);\n tracker.update([1.1, 1.1, 0.5]); // re-detected nearby\n assert_eq!(tracker.state(), TrackState::Confirmed);\n }\n}"
|
||||
},
|
||||
{
|
||||
"language": "rust",
|
||||
"code": "// v2/crates/wifi-densepose-ruvector/tests/viewpoint_tests.rs\n\n#[cfg(test)]\nmod attention_tests {\n use wifi_densepose_ruvector::viewpoint::attention::CrossViewpointAttention;\n\n #[test]\n fn attention_weights_sum_to_one() {\n let attn = CrossViewpointAttention::new(3); // 3 viewpoints\n let features = vec![[1.0f32; 64], [2.0f32; 64], [3.0f32; 64]];\n let weights = attn.compute_weights(&features);\n let sum: f32 = weights.iter().sum();\n assert!((sum - 1.0).abs() < 1e-5, \"attention must be a probability distribution\");\n }\n\n #[test]\n fn single_viewpoint_gets_full_weight() {\n let attn = CrossViewpointAttention::new(1);\n let features = vec![[1.0f32; 64]];\n let weights = attn.compute_weights(&features);\n assert!((weights[0] - 1.0).abs() < 1e-6);\n }\n\n #[test]\n fn zero_feature_vectors_do_not_produce_nan() {\n let attn = CrossViewpointAttention::new(2);\n let features = vec![[0.0f32; 64], [0.0f32; 64]];\n let weights = attn.compute_weights(&features);\n assert!(weights.iter().all(|w| w.is_finite()));\n }\n}\n\n#[cfg(test)]\nmod sketch_tests {\n use wifi_densepose_ruvector::sketch::WireSketch;\n\n #[test]\n fn round_trip_serialization() {\n let sketch = WireSketch::from_keypoints(&[[0.5f32, 0.5], [0.3, 0.7]]);\n let bytes = sketch.to_bytes();\n let restored = WireSketch::from_bytes(&bytes).unwrap();\n assert_eq!(sketch, restored);\n }\n\n #[test]\n fn deserialize_truncated_bytes_returns_error() {\n let sketch = WireSketch::from_keypoints(&[[0.5f32, 0.5]]);\n let mut bytes = sketch.to_bytes();\n bytes.truncate(bytes.len() / 2); // truncate halfway\n assert!(WireSketch::from_bytes(&bytes).is_err());\n }\n\n #[test]\n fn empty_keypoint_list_is_handled() {\n let sketch = WireSketch::from_keypoints(&[]);\n assert_eq!(sketch.keypoint_count(), 0);\n }\n}"
|
||||
},
|
||||
{
|
||||
"language": "rust",
|
||||
"code": "// v2/crates/wifi-densepose-signal/tests/ruvsense_tests.rs\n\n#[cfg(test)]\nmod coherence_gate_tests {\n use wifi_densepose_signal::ruvsense::coherence_gate::{CoherenceGate, GateDecision};\n\n #[test]\n fn high_coherence_signal_is_accepted() {\n let gate = CoherenceGate::new(0.7); // threshold = 0.7\n let decision = gate.evaluate(0.95);\n assert_eq!(decision, GateDecision::Accept);\n }\n\n #[test]\n fn low_coherence_signal_is_rejected() {\n let gate = CoherenceGate::new(0.7);\n let decision = gate.evaluate(0.3);\n assert_eq!(decision, GateDecision::Reject);\n }\n\n #[test]\n fn borderline_coherence_triggers_recalibrate() {\n let gate = CoherenceGate::new(0.7);\n let decision = gate.evaluate(0.68); // just below threshold\n assert_eq!(decision, GateDecision::Recalibrate);\n }\n}\n\n#[cfg(test)]\nmod phase_align_tests {\n use wifi_densepose_signal::ruvsense::phase_align::PhaseAligner;\n\n #[test]\n fn phase_at_plus_pi_does_not_wrap_incorrectly() {\n let aligner = PhaseAligner::new();\n let phases = vec![std::f32::consts::PI - 0.001, std::f32::consts::PI + 0.001];\n let aligned = aligner.align(&phases);\n // jump across ±π boundary must be handled continuously\n let diff = (aligned[1] - aligned[0]).abs();\n assert!(diff < 0.01, \"phase jump at ±π must be < 0.01 rad after alignment\");\n }\n\n #[test]\n fn single_phase_value_aligns_to_itself() {\n let aligner = PhaseAligner::new();\n let phases = vec![1.5f32];\n let aligned = aligner.align(&phases);\n assert_eq!(aligned.len(), 1);\n assert!((aligned[0] - 1.5).abs() < 1e-6);\n }\n\n #[test]\n fn empty_phase_array_returns_empty() {\n let aligner = PhaseAligner::new();\n let aligned = aligner.align(&[]);\n assert!(aligned.is_empty());\n }\n}\n\n#[cfg(test)]\nmod adversarial_detection_tests {\n use wifi_densepose_signal::ruvsense::adversarial::AdversarialDetector;\n\n #[test]\n fn physically_impossible_amplitude_is_flagged() {\n let detector = AdversarialDetector::new();\n // WiFi amplitude cannot exceed hardware saturation level\n let frame = vec![1e9f32; 56]; // absurdly large\n assert!(detector.is_suspicious(&frame));\n }\n\n #[test]\n fn normal_amplitude_range_passes() {\n let detector = AdversarialDetector::new();\n let frame = vec![0.5f32; 56]; // typical normalized value\n assert!(!detector.is_suspicious(&frame));\n }\n\n #[test]\n fn multi_link_inconsistency_is_detected() {\n // link A reports body moving right; link B reports no motion\n // physically inconsistent — flag as adversarial\n let detector = AdversarialDetector::new();\n let result = detector.check_multi_link_consistency(\n &[1.0, 2.0, 3.0], // link A\n &[0.0, 0.0, 0.0], // link B (no motion)\n );\n assert!(result.is_inconsistent());\n }\n}"
|
||||
},
|
||||
{
|
||||
"language": "rust",
|
||||
"code": "// v2/crates/wifi-densepose-train/tests/test_geometry.rs\n\n#[cfg(test)]\nmod film_layer_tests {\n use wifi_densepose_train::geometry::FilmLayer;\n\n #[test]\n fn film_layer_output_shape_matches_input() {\n let film = FilmLayer::new(64, 32); // 64-dim features, 32-dim condition\n let features = vec![0.5f32; 64];\n let condition = vec![1.0f32; 32];\n let output = film.forward(&features, &condition).unwrap();\n assert_eq!(output.len(), 64, \"FiLM output must match feature dimensionality\");\n }\n\n #[test]\n fn film_layer_zero_condition_acts_as_identity() {\n let film = FilmLayer::new(64, 32);\n let features = vec![1.0f32; 64];\n let zero_condition = vec![0.0f32; 32];\n let output = film.forward(&features, &zero_condition).unwrap();\n // scale=1, shift=0 → identity; output ≈ input\n for (o, f) in output.iter().zip(features.iter()) {\n assert!((o - f).abs() < 0.1, \"zero condition should approximate identity\");\n }\n }\n}\n\n// v2/crates/wifi-densepose-train/tests/test_rapid_adapt.rs\n\n#[cfg(test)]\nmod rapid_adaptation_tests {\n use wifi_densepose_train::rapid_adapt::RapidAdapter;\n\n #[test]\n fn adapter_updates_on_single_sample() {\n let mut adapter = RapidAdapter::new(5); // 5 adaptation steps\n let csi_sample = vec![0.1f32; 56 * 3];\n let pose_label = vec![0.5f32; 17 * 2]; // 17 keypoints × (x, y)\n let result = adapter.adapt_step(&csi_sample, &pose_label);\n assert!(result.is_ok());\n }\n\n #[test]\n fn adapter_with_zero_steps_is_no_op() {\n let adapter = RapidAdapter::new(0);\n // 0 adaptation steps → weights unchanged\n let initial_weights = adapter.clone_weights();\n let _ = adapter.adapt_step(&vec![0.1f32; 168], &vec![0.5f32; 34]);\n assert_eq!(adapter.clone_weights(), initial_weights);\n }\n}"
|
||||
},
|
||||
{
|
||||
"language": "rust",
|
||||
"code": "// v2/crates/wifi-densepose-sensing-server/tests/auth_tests.rs\n\n#[cfg(test)]\nmod bearer_auth_tests {\n use wifi_densepose_sensing_server::auth::{BearerValidator, TokenError};\n\n #[test]\n fn missing_authorization_header_returns_unauthorized() {\n let validator = BearerValidator::new(\"secret-token\");\n let result = validator.validate(None);\n assert!(matches!(result, Err(TokenError::Missing)));\n }\n\n #[test]\n fn wrong_token_is_rejected() {\n let validator = BearerValidator::new(\"correct-token\");\n let result = validator.validate(Some(\"Bearer wrong-token\"));\n assert!(matches!(result, Err(TokenError::Invalid)));\n }\n\n #[test]\n fn malformed_header_without_bearer_prefix_is_rejected() {\n let validator = BearerValidator::new(\"token\");\n let result = validator.validate(Some(\"token\")); // missing \"Bearer \" prefix\n assert!(matches!(result, Err(TokenError::Malformed)));\n }\n\n #[test]\n fn correct_token_is_accepted() {\n let validator = BearerValidator::new(\"correct-token\");\n let result = validator.validate(Some(\"Bearer correct-token\"));\n assert!(result.is_ok());\n }\n}\n\n// v2/crates/wifi-densepose-sensing-server/tests/semantic_tests.rs\n\n#[cfg(test)]\nmod fall_detection_tests {\n use wifi_densepose_sensing_server::semantic::fall_detector::FallDetector;\n\n #[test]\n fn no_motion_does_not_trigger_fall() {\n let mut detector = FallDetector::new();\n for _ in 0..30 { // 30 frames of stillness\n detector.update_pose(stationary_pose());\n }\n assert!(!detector.fall_detected());\n }\n\n #[test]\n fn rapid_downward_velocity_triggers_fall() {\n let mut detector = FallDetector::new();\n // simulate person going from standing (y=1.7m) to prone (y=0.3m) in 3 frames\n for (frame, y) in [(0, 1.7f32), (1, 1.0), (2, 0.3)] {\n detector.update_pose(pose_at_height(y));\n }\n assert!(detector.fall_detected());\n }\n\n #[test]\n fn sitting_down_slowly_does_not_trigger_fall() {\n let mut detector = FallDetector::new();\n // gradual height decrease over 30 frames is sitting, not falling\n for i in 0..30 {\n let y = 1.7f32 - (i as f32 * 0.04); // ~1.2m drop over 30 frames\n detector.update_pose(pose_at_height(y));\n }\n assert!(!detector.fall_detected());\n }\n}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"rawOutputPreview": "The exploration is complete. Here's the full coverage analysis with test skeletons for each critical gap.\n\n---\n\n## Test Coverage Gap Analysis — wifi-densepose\n\n### Coverage Summary by Crate\n\n| Crate | Tests Found | Status | Priority |\n|-------|-------------|--------|----------|\n| `wifi-densepose-core` | 26 inline | Good | Low |\n| `wifi-densepose-signal` | ~60 (validation only) | Moderate | **High** |\n| `wifi-densepose-nn` | **0** | Critical | **P1** |\n| `wifi-densepose-train` | ~60 (config/dataset) | Moderate | High |\n| `wifi-densepose-mat` | 1 integration test | Critical | **P1** |\n| `wifi-densepose-ruvector` | **0** | Critical | **P1** |\n| `wifi-densepose-sensing-server` | 4 integration tests | Moderate | High |\n| `wifi-densepose-wasm` | 3 compliance tests | Low | Low |\n\n---\n\n## Tier 1: Critical Gaps\n\n### 1. `wifi-densepose-nn` — Zero test coverage\n\nEvery public API is untested. Place these at `v2/crates/wifi-densepose-nn/tests/inference_tests.rs`:\n\n```rust\n// v2/crates/wifi-densepose-nn/tests/inference_tests.rs\n\n#[cfg(test)]\nmod tensor_tests {\n use wifi_densepose_nn::tensor::Tensor;\n\n #[test]\n fn tensor_shape_mismatch_returns_error() {\n // data has 6 elements but shape claims 3×3=9\n let result = Tensor::new(vec![1.0f32; 6], &[3, 3]);\n assert!(result.is_err(), \"shape mismatch must be rejected\");\n }\n\n #[test]\n fn tensor_empty_data_returns_error() {\n let result = Tensor::new(vec![], &[0]);\n assert!(result.is_err());\n }\n\n #[test]\n fn tensor_nan_values_are_detected() {\n let t = Tensor::new(vec![f32::NAN, 1.0, 2.0], &[3]).unwrap();\n assert!(t.has_nan(), \"NaN in data must be detectable\");\n }\n\n #[test]\n fn tensor_inf_values_are_detected() {\n let t = Tensor::new(vec![f32::INFINITY, 1.0], &[2]).unwrap();\n assert!(t.has_inf());\n }\n}\n\n#[cfg(test)]\nmod modality_translator_tests {\n use wifi_densepose_nn::translator::ModalityTranslator;\n\n #[test]\n fn translator_rejects",
|
||||
"rawOutputLength": 18269
|
||||
}
|
||||
@@ -1,15 +0,0 @@
|
||||
{
|
||||
"name": "ruview",
|
||||
"description": "RuView Marketplace: Claude Code + Codex plugins for WiFi sensing — configuration, applications, model training, and onboarding, from practical to advanced",
|
||||
"owner": {
|
||||
"name": "ruvnet",
|
||||
"url": "https://github.com/ruvnet/RuView"
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
"name": "ruview",
|
||||
"source": "./plugins/ruview",
|
||||
"description": "End-to-end RuView toolkit: getting started, ESP32 hardware setup, configuration, sensing applications (presence / vitals / pose / sleep / MAT), camera-free + camera-supervised model training, advanced multistatic sensing, CLI / API / WASM, mmWave radar, and witness verification"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1 +0,0 @@
|
||||
{"sessionId":"d80c93c2-51b7-42e8-a0fc-dc47cff1200f","pid":45748,"acquiredAt":1779668018388}
|
||||
@@ -126,7 +126,10 @@
|
||||
"Bash(node .claude/*)",
|
||||
"mcp__claude-flow__:*"
|
||||
],
|
||||
"deny": []
|
||||
"deny": [
|
||||
"Read(./.env)",
|
||||
"Read(./.env.*)"
|
||||
]
|
||||
},
|
||||
"attribution": {
|
||||
"commit": "Co-Authored-By: claude-flow <ruv@ruv.net>",
|
||||
|
||||
@@ -1,58 +0,0 @@
|
||||
version: 2
|
||||
updates:
|
||||
# Keep all third-party GitHub Actions on verified, pinned commit SHAs.
|
||||
# Pairs with the SHA pinning in security-scan.yml and ci.yml so that
|
||||
# future bumps stay automated and reviewable rather than drifting back
|
||||
# to mutable @master / @main refs. See issue #442.
|
||||
- package-ecosystem: github-actions
|
||||
directory: /
|
||||
schedule:
|
||||
interval: weekly
|
||||
open-pull-requests-limit: 5
|
||||
labels:
|
||||
- dependencies
|
||||
- github-actions
|
||||
|
||||
# Mobile app npm deps. Includes the @xmldom/xmldom, node-forge, and
|
||||
# picomatch advisories from #442 plus axios and any future surface.
|
||||
- package-ecosystem: npm
|
||||
directory: /ui/mobile
|
||||
schedule:
|
||||
interval: weekly
|
||||
open-pull-requests-limit: 10
|
||||
labels:
|
||||
- dependencies
|
||||
- mobile
|
||||
|
||||
# Desktop UI npm deps. Direct vite devDep currently has a HIGH advisory
|
||||
# (dev-server-only path traversal); track future bumps automatically.
|
||||
- package-ecosystem: npm
|
||||
directory: /v2/crates/wifi-densepose-desktop/ui
|
||||
schedule:
|
||||
interval: weekly
|
||||
open-pull-requests-limit: 5
|
||||
labels:
|
||||
- dependencies
|
||||
- desktop
|
||||
|
||||
# Python deps used by v1/ and the FastAPI service. requirements.txt is
|
||||
# only loosely pinned; let Dependabot surface upstream CVE bumps.
|
||||
- package-ecosystem: pip
|
||||
directory: /
|
||||
schedule:
|
||||
interval: weekly
|
||||
open-pull-requests-limit: 10
|
||||
labels:
|
||||
- dependencies
|
||||
- python
|
||||
|
||||
# Rust workspace (15+ crates). cargo audit is not currently wired into
|
||||
# any workflow, so Dependabot is the primary automated bump path.
|
||||
- package-ecosystem: cargo
|
||||
directory: /v2
|
||||
schedule:
|
||||
interval: weekly
|
||||
open-pull-requests-limit: 10
|
||||
labels:
|
||||
- dependencies
|
||||
- rust
|
||||
@@ -1,94 +0,0 @@
|
||||
name: AetherArena harness gate (ADR-149)
|
||||
|
||||
# Runs the AetherArena scoring harness as a PR build gate. Every PR that touches
|
||||
# the scorer, the metrics, or the benchmark scaffold must keep the deterministic
|
||||
# score hash stable (ADR-149 §2.5 determinism_gate). If the scoring maths changes,
|
||||
# the hash moves and this gate fails until `expected_score.sha256` is regenerated
|
||||
# and reviewed — so scorer drift can never land silently.
|
||||
#
|
||||
# This is the "a PR that runs the harness as part of the build process" requirement.
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
paths:
|
||||
- 'v2/crates/wifi-densepose-train/src/ruview_metrics.rs'
|
||||
- 'v2/crates/wifi-densepose-train/src/ablation.rs'
|
||||
- 'v2/crates/wifi-densepose-train/src/bin/aa_score_runner.rs'
|
||||
- 'aether-arena/**'
|
||||
- '.github/workflows/aether-arena-harness.yml'
|
||||
push:
|
||||
branches: ['feat/adr-149-aether-arena']
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: write
|
||||
|
||||
jobs:
|
||||
harness-gate:
|
||||
name: Run AA scorer harness (determinism gate)
|
||||
runs-on: ubuntu-latest
|
||||
defaults:
|
||||
run:
|
||||
working-directory: v2
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install Rust toolchain
|
||||
run: rustup show && rustc --version
|
||||
|
||||
- name: Cache cargo
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/registry
|
||||
~/.cargo/git
|
||||
v2/target
|
||||
key: aa-harness-${{ runner.os }}-${{ hashFiles('v2/Cargo.lock') }}
|
||||
|
||||
# 1. Build the pure-Rust scorer (no torch / no GPU → fast PR gate).
|
||||
- name: Build AA score runner
|
||||
run: cargo build -p wifi-densepose-train --bin aa_score_runner --no-default-features
|
||||
|
||||
# 2. Determinism gate: the committed expected hash must still match. A
|
||||
# non-zero exit here fails the PR.
|
||||
- name: Run determinism gate
|
||||
run: cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features
|
||||
|
||||
# 3. Repeatability analysis (witness chain): the harness must produce one
|
||||
# identical proof hash across many runs — any nondeterminism fails here.
|
||||
- name: Repeatability analysis (16 runs)
|
||||
run: cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --repeat 16
|
||||
|
||||
# 4. Real-scoring smoke: score a sample prediction against the public smoke
|
||||
# split, exercising the actual model-scoring path (not just the fixture).
|
||||
- name: Real-scoring smoke test
|
||||
run: |
|
||||
cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- \
|
||||
--split ../aether-arena/fixtures/smoke_split.json \
|
||||
--pred ../aether-arena/fixtures/smoke_pred.json --json
|
||||
|
||||
# 5. Witness ledger chain integrity: the append-only results ledger must
|
||||
# verify (every prev_hash link + row_hash intact = no silent edits).
|
||||
- name: Verify witness ledger chain
|
||||
working-directory: aether-arena/ledger
|
||||
run: python3 ledger_tools.py verify
|
||||
|
||||
# 6. Emit the witness row + repeatability into the PR run summary.
|
||||
- name: Witness row → job summary
|
||||
if: always()
|
||||
run: |
|
||||
ROW=$(cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --json)
|
||||
REP=$(cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --repeat 16)
|
||||
{
|
||||
echo "## AetherArena harness gate (witness chain)"
|
||||
echo ""
|
||||
echo "Deterministic witness (ADR-149 §2.2 / proof + repeatability):"
|
||||
echo '```json'
|
||||
echo "$ROW"
|
||||
echo "$REP"
|
||||
echo '```'
|
||||
echo ""
|
||||
echo "If the determinism gate failed, the scoring maths changed: regenerate with"
|
||||
echo '`cargo run -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --generate-hash > aether-arena/fixtures/expected_score.sha256` and review the diff.'
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
@@ -1,99 +0,0 @@
|
||||
name: BFLD MQTT Integration
|
||||
|
||||
# Runs the env-gated mosquitto integration tests from iters 24 + 29 of the
|
||||
# BFLD rollout (ADR-118 / ADR-122 §2.2). Spins up an eclipse-mosquitto:2
|
||||
# service container, exports BFLD_MQTT_BROKER, runs `cargo test --features
|
||||
# mqtt`. Local developers can reproduce with:
|
||||
#
|
||||
# scoop install mosquitto # Windows
|
||||
# # or: docker run -p 1883:1883 eclipse-mosquitto:2
|
||||
# BFLD_MQTT_BROKER=tcp://localhost:1883 \
|
||||
# cargo test -p wifi-densepose-bfld --features mqtt
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
- 'feat/adr-118-*'
|
||||
- 'feat/bfld-*'
|
||||
paths:
|
||||
- 'v2/crates/wifi-densepose-bfld/**'
|
||||
- '.github/workflows/bfld-mqtt-integration.yml'
|
||||
pull_request:
|
||||
paths:
|
||||
- 'v2/crates/wifi-densepose-bfld/**'
|
||||
- '.github/workflows/bfld-mqtt-integration.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
mqtt-live-broker:
|
||||
name: cargo test --features mqtt (live mosquitto)
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 15
|
||||
|
||||
services:
|
||||
mosquitto:
|
||||
image: eclipse-mosquitto:2
|
||||
ports:
|
||||
- 1883:1883
|
||||
# Allow anonymous connections — local-only CI broker, no exposure
|
||||
# to the public internet, never touches production credentials.
|
||||
options: >-
|
||||
--health-cmd "mosquitto_pub -h localhost -t healthcheck -m ping || exit 1"
|
||||
--health-interval 5s
|
||||
--health-timeout 3s
|
||||
--health-retries 10
|
||||
|
||||
env:
|
||||
BFLD_MQTT_BROKER: tcp://localhost:1883
|
||||
CARGO_TERM_COLOR: always
|
||||
CARGO_INCREMENTAL: 0
|
||||
RUSTFLAGS: -D warnings
|
||||
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install Rust toolchain
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
with:
|
||||
components: clippy
|
||||
|
||||
- name: Cache cargo registry + target
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/registry
|
||||
~/.cargo/git
|
||||
v2/target
|
||||
key: bfld-mqtt-${{ runner.os }}-${{ hashFiles('v2/Cargo.lock') }}
|
||||
|
||||
- name: Wait for mosquitto to be ready
|
||||
run: |
|
||||
for i in {1..20}; do
|
||||
if nc -z localhost 1883; then
|
||||
echo "mosquitto reachable on port 1883 (attempt $i)"
|
||||
exit 0
|
||||
fi
|
||||
echo "waiting for mosquitto ($i/20)..."
|
||||
sleep 1
|
||||
done
|
||||
echo "mosquitto never became reachable" >&2
|
||||
exit 1
|
||||
|
||||
- name: cargo test --no-default-features (baseline regression)
|
||||
working-directory: v2
|
||||
run: cargo test -p wifi-densepose-bfld --no-default-features
|
||||
|
||||
- name: cargo test (default features)
|
||||
working-directory: v2
|
||||
run: cargo test -p wifi-densepose-bfld
|
||||
|
||||
- name: cargo test --features mqtt (incl. live mosquitto roundtrip)
|
||||
working-directory: v2
|
||||
run: cargo test -p wifi-densepose-bfld --features mqtt
|
||||
|
||||
- name: cargo clippy --features mqtt (lint gate)
|
||||
working-directory: v2
|
||||
run: cargo clippy -p wifi-densepose-bfld --features mqtt --all-targets -- -D warnings
|
||||
continue-on-error: true
|
||||
+29
-193
@@ -15,50 +15,38 @@ env:
|
||||
|
||||
jobs:
|
||||
# Code Quality and Security Checks
|
||||
# The Python codebase moved to `archive/v1/` when the runtime was rewritten in
|
||||
# Rust under `v2/`. The lint/format/type/scan checks below still run against
|
||||
# the archive for hygiene, but with `continue-on-error: true` everywhere — the
|
||||
# archive is frozen reference code, not active development, so a stale lint
|
||||
# rule shouldn't gate PRs to the Rust workspace.
|
||||
code-quality:
|
||||
name: Code Quality & Security
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Set up Python
|
||||
continue-on-error: true
|
||||
uses: actions/setup-python@v6
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: 'pip'
|
||||
|
||||
- name: Install dependencies
|
||||
continue-on-error: true
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
pip install black flake8 mypy bandit safety
|
||||
|
||||
- name: Code formatting check (Black)
|
||||
continue-on-error: true
|
||||
run: black --check --diff archive/v1/src archive/v1/tests
|
||||
run: black --check --diff src/ tests/
|
||||
|
||||
- name: Linting (Flake8)
|
||||
continue-on-error: true
|
||||
run: flake8 archive/v1/src archive/v1/tests --max-line-length=88 --extend-ignore=E203,W503
|
||||
run: flake8 src/ tests/ --max-line-length=88 --extend-ignore=E203,W503
|
||||
|
||||
- name: Type checking (MyPy)
|
||||
continue-on-error: true
|
||||
run: mypy archive/v1/src --ignore-missing-imports
|
||||
run: mypy src/ --ignore-missing-imports
|
||||
|
||||
- name: Security scan (Bandit)
|
||||
run: bandit -r archive/v1/src -f json -o bandit-report.json
|
||||
run: bandit -r src/ -f json -o bandit-report.json
|
||||
continue-on-error: true
|
||||
|
||||
- name: Dependency vulnerability scan (Safety)
|
||||
@@ -66,7 +54,6 @@ jobs:
|
||||
continue-on-error: true
|
||||
|
||||
- name: Upload security reports
|
||||
continue-on-error: true
|
||||
uses: actions/upload-artifact@v4
|
||||
if: always()
|
||||
with:
|
||||
@@ -75,103 +62,11 @@ jobs:
|
||||
bandit-report.json
|
||||
safety-report.json
|
||||
|
||||
# Rust Workspace Tests
|
||||
rust-tests:
|
||||
name: Rust Workspace Tests
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
# `wifi-densepose-desktop` is a Tauri v2 app — `glib-sys`, `gtk-sys`,
|
||||
# `webkit2gtk-sys`, etc. need the Linux dev libraries via pkg-config or the
|
||||
# workspace test fails at the build step before any test runs (every recent
|
||||
# main CI run has been red on this for exactly this reason). Install the
|
||||
# standard Tauri-on-Ubuntu set.
|
||||
- name: Install Tauri / GTK / serial system dev libraries
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y --no-install-recommends \
|
||||
libglib2.0-dev \
|
||||
libgtk-3-dev \
|
||||
libsoup-3.0-dev \
|
||||
libjavascriptcoregtk-4.1-dev \
|
||||
libwebkit2gtk-4.1-dev \
|
||||
libayatana-appindicator3-dev \
|
||||
librsvg2-dev \
|
||||
libxdo-dev \
|
||||
libudev-dev \
|
||||
libdbus-1-dev \
|
||||
libssl-dev \
|
||||
pkg-config
|
||||
|
||||
- name: Install Rust toolchain
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
|
||||
# Swatinem/rust-cache replaces a naive `actions/cache` of the whole
|
||||
# `v2/target`. That manual cache of a 38-crate target dir (multi-GB) was an
|
||||
# intermittent failure source — several CI runs this cycle died at the
|
||||
# cache/setup step (after toolchain install, before "Run Rust tests"),
|
||||
# needing a rerun. rust-cache is purpose-built for Rust: it caches the
|
||||
# registry + git + a pruned target, evicts stale deps, and restores far more
|
||||
# reliably (and faster) on large workspaces. `workspaces: v2` points it at
|
||||
# the v2/ cargo workspace (keys on v2/Cargo.lock, caches v2/target).
|
||||
- name: Cache cargo (Swatinem/rust-cache)
|
||||
uses: Swatinem/rust-cache@v2
|
||||
with:
|
||||
workspaces: v2
|
||||
|
||||
# The 38-crate workspace debug build exhausts the runner's disk when built
|
||||
# with full debuginfo (observed: "final link failed: No space left on
|
||||
# device" once the engine/benchmark crates landed; the same tree's local
|
||||
# debug target measured 151 GB). Debuginfo is useless in CI — tests either
|
||||
# pass or print their failure — so build without it; target shrinks ~5-10x.
|
||||
- name: Run Rust tests
|
||||
working-directory: v2
|
||||
env:
|
||||
CARGO_PROFILE_DEV_DEBUG: "0"
|
||||
CARGO_PROFILE_TEST_DEBUG: "0"
|
||||
run: cargo test --workspace --no-default-features
|
||||
|
||||
- name: Run ADR-147 worldmodel tests
|
||||
working-directory: v2
|
||||
env:
|
||||
CARGO_PROFILE_DEV_DEBUG: "0"
|
||||
CARGO_PROFILE_TEST_DEBUG: "0"
|
||||
run: cargo test -p wifi-densepose-worldmodel --no-default-features
|
||||
|
||||
# ADR-134 CIR tests are behind the `cir` feature so the bench dependency
|
||||
# (Criterion) only pulls when actually exercised. Run them as a separate
|
||||
# step so a CIR-only regression is unambiguously attributable.
|
||||
- name: Run ADR-134 CIR tests
|
||||
working-directory: v2
|
||||
run: cargo test -p wifi-densepose-signal --no-default-features --features cir --tests
|
||||
|
||||
# ADR-134 + ADR-028 witness guard. The CIR proof runner produces a
|
||||
# bit-deterministic SHA-256 over CirEstimator output on the synthetic
|
||||
# reference signal. Any algorithmic regression — changes to ISTA
|
||||
# convergence, sensing matrix construction, soft-thresholding, or input
|
||||
# padding — breaks the hash and fails the build. To regenerate after an
|
||||
# *intentional* change:
|
||||
# cd v2 && cargo run -p wifi-densepose-signal --bin cir_proof_runner \
|
||||
# --release --no-default-features -- --generate-hash \
|
||||
# > ../archive/v1/data/proof/expected_cir_features.sha256
|
||||
- name: ADR-134 CIR witness proof (determinism guard)
|
||||
run: bash scripts/verify-cir-proof.sh
|
||||
|
||||
- name: ADR-135 calibration witness proof (determinism guard)
|
||||
run: bash scripts/verify-calibration-proof.sh
|
||||
|
||||
# Unit and Integration Tests
|
||||
# Python pytest matrix — runs against the archived v1 Python tree.
|
||||
# `continue-on-error: true` for the same reason as code-quality above:
|
||||
# the archive is frozen reference, not blocking the Rust workspace PRs.
|
||||
test:
|
||||
name: Tests
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
python-version: ['3.10', '3.11', '3.12']
|
||||
services:
|
||||
@@ -200,51 +95,44 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
continue-on-error: true
|
||||
uses: actions/setup-python@v6
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
cache: 'pip'
|
||||
|
||||
- name: Install dependencies
|
||||
continue-on-error: true
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
pip install pytest-cov pytest-xdist
|
||||
|
||||
- name: Run unit tests
|
||||
continue-on-error: true
|
||||
env:
|
||||
DATABASE_URL: postgresql://postgres:postgres@localhost:5432/test_wifi_densepose
|
||||
REDIS_URL: redis://localhost:6379/0
|
||||
ENVIRONMENT: test
|
||||
run: |
|
||||
pytest archive/v1/tests/unit/ -v --cov=archive/v1/src --cov-report=xml --cov-report=html --junitxml=junit.xml
|
||||
pytest tests/unit/ -v --cov=src --cov-report=xml --cov-report=html --junitxml=junit.xml
|
||||
|
||||
- name: Run integration tests
|
||||
continue-on-error: true
|
||||
env:
|
||||
DATABASE_URL: postgresql://postgres:postgres@localhost:5432/test_wifi_densepose
|
||||
REDIS_URL: redis://localhost:6379/0
|
||||
ENVIRONMENT: test
|
||||
run: |
|
||||
pytest archive/v1/tests/integration/ -v --junitxml=integration-junit.xml
|
||||
pytest tests/integration/ -v --junitxml=integration-junit.xml
|
||||
|
||||
- name: Upload coverage reports
|
||||
continue-on-error: true
|
||||
uses: codecov/codecov-action@v6
|
||||
uses: codecov/codecov-action@v4
|
||||
with:
|
||||
file: ./coverage.xml
|
||||
flags: unittests
|
||||
name: codecov-umbrella
|
||||
|
||||
- name: Upload test results
|
||||
continue-on-error: true
|
||||
uses: actions/upload-artifact@v4
|
||||
if: always()
|
||||
with:
|
||||
@@ -255,21 +143,17 @@ jobs:
|
||||
htmlcov/
|
||||
|
||||
# Performance and Load Tests
|
||||
# NOTE: tests/performance/locustfile.py and the src.api.main app path both
|
||||
# predate the v1→archive/v1 reorganisation. continue-on-error: true until a
|
||||
# proper locust suite is added under archive/v1/tests/performance/.
|
||||
performance-test:
|
||||
name: Performance Tests
|
||||
runs-on: ubuntu-latest
|
||||
needs: [test]
|
||||
continue-on-error: true
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v6
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: 'pip'
|
||||
@@ -278,70 +162,36 @@ jobs:
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
pip install pytest # the perf suite is pytest, not locust
|
||||
pip install locust
|
||||
|
||||
# No "Start application" step: the gated test (test_frame_budget.py) drives
|
||||
# the CSIProcessor pipeline in-process and makes no HTTP calls, so the old
|
||||
# uvicorn server + `sleep 10` were dead weight — they only existed for the
|
||||
# now-excluded api_throughput/inference_speed tests, and on every run dumped
|
||||
# ~50 misleading "router requires hardware setup" ERROR lines for a server
|
||||
# no test touched. MOCK_POSE_DATA is server-only and unused here.
|
||||
- name: Start application
|
||||
run: |
|
||||
uvicorn src.api.main:app --host 0.0.0.0 --port 8000 &
|
||||
sleep 10
|
||||
|
||||
- name: Run performance tests
|
||||
working-directory: archive/v1
|
||||
run: |
|
||||
# Gate only on the genuine, deterministic perf guard:
|
||||
# test_frame_budget.py times the *real* CSIProcessor pipeline against
|
||||
# the ADR 50 ms per-frame budget (single-frame, p95 over 100 frames,
|
||||
# +Doppler) — a true regression signal.
|
||||
#
|
||||
# test_api_throughput.py / test_inference_speed.py are excluded: every
|
||||
# test there is a TDD red-phase stub (suffix `_should_fail_initially`)
|
||||
# that times a *mock that sleeps* — meaningless as a perf signal, with
|
||||
# machine-dependent wall-clock asserts (e.g. `actual_rps >= 40`,
|
||||
# `batch_time < individual_time`) that are inherently flaky on shared
|
||||
# CI runners, plus a cross-class fixture-scope bug. Forcing them green
|
||||
# would be manufacturing a false signal; they stay in-repo for local
|
||||
# TDD but do not gate CI until the underlying features are implemented.
|
||||
#
|
||||
# `python -m pytest` (not the bare `pytest` script) puts the cwd
|
||||
# (archive/v1) on sys.path so `from src.core...` resolves — the bare
|
||||
# script omits cwd and raises ModuleNotFoundError: No module named 'src'.
|
||||
# -o addopts="" drops the root pyproject's --cov/--cov-fail-under=100.
|
||||
python -m pytest tests/performance/test_frame_budget.py \
|
||||
-o addopts="" -v --junitxml=perf-junit.xml
|
||||
locust -f tests/performance/locustfile.py --headless --users 50 --spawn-rate 5 --run-time 60s --host http://localhost:8000
|
||||
|
||||
- name: Upload performance results
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: performance-results
|
||||
path: archive/v1/perf-junit.xml
|
||||
path: locust_report.html
|
||||
|
||||
# Docker Build and Test
|
||||
# NOTE: the canonical Docker build for the sensing-server is now
|
||||
# `.github/workflows/sensing-server-docker.yml` (multi-registry push, asset
|
||||
# smoke tests, bearer-auth smoke tests — #520/#514/#443). This job predates
|
||||
# that workflow, points at a non-existent root `Dockerfile` with a
|
||||
# non-existent `target: production`, and pushes to a mis-cased image name —
|
||||
# `continue-on-error: true` until it's deleted or rewired to call the new
|
||||
# workflow, so it doesn't gate the rest of the pipeline.
|
||||
docker-build:
|
||||
name: Docker Build & Test
|
||||
runs-on: ubuntu-latest
|
||||
needs: [code-quality, test, rust-tests]
|
||||
continue-on-error: true
|
||||
needs: [code-quality, test]
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
continue-on-error: true
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Log in to Container Registry
|
||||
continue-on-error: true
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
@@ -349,9 +199,8 @@ jobs:
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Extract metadata
|
||||
continue-on-error: true
|
||||
id: meta
|
||||
uses: docker/metadata-action@v6
|
||||
uses: docker/metadata-action@v5
|
||||
with:
|
||||
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
|
||||
tags: |
|
||||
@@ -361,8 +210,7 @@ jobs:
|
||||
type=raw,value=latest,enable={{is_default_branch}}
|
||||
|
||||
- name: Build and push Docker image
|
||||
continue-on-error: true
|
||||
uses: docker/build-push-action@v7
|
||||
uses: docker/build-push-action@v5
|
||||
with:
|
||||
context: .
|
||||
target: production
|
||||
@@ -374,7 +222,6 @@ jobs:
|
||||
platforms: linux/amd64,linux/arm64
|
||||
|
||||
- name: Test Docker image
|
||||
continue-on-error: true
|
||||
run: |
|
||||
docker run --rm -d --name test-container -p 8000:8000 ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ github.sha }}
|
||||
sleep 10
|
||||
@@ -382,15 +229,13 @@ jobs:
|
||||
docker stop test-container
|
||||
|
||||
- name: Run container security scan
|
||||
continue-on-error: true
|
||||
uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
|
||||
uses: aquasecurity/trivy-action@master
|
||||
with:
|
||||
image-ref: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ github.sha }}
|
||||
format: 'sarif'
|
||||
output: 'trivy-results.sarif'
|
||||
|
||||
- name: Upload Trivy scan results
|
||||
continue-on-error: true
|
||||
uses: github/codeql-action/upload-sarif@v3
|
||||
if: always()
|
||||
with:
|
||||
@@ -402,14 +247,12 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
needs: [docker-build]
|
||||
if: github.ref == 'refs/heads/main'
|
||||
permissions:
|
||||
contents: write # gh-pages deploy needs write (GITHUB_TOKEN is read-only by default -> 403)
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v6
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: 'pip'
|
||||
@@ -420,9 +263,6 @@ jobs:
|
||||
pip install -r requirements.txt
|
||||
|
||||
- name: Generate OpenAPI spec
|
||||
working-directory: archive/v1
|
||||
env:
|
||||
MOCK_POSE_DATA: "true" # no CSI hardware in CI
|
||||
run: |
|
||||
python -c "
|
||||
from src.api.main import app
|
||||
@@ -433,7 +273,6 @@ jobs:
|
||||
|
||||
- name: Deploy to GitHub Pages
|
||||
uses: peaceiris/actions-gh-pages@v4
|
||||
continue-on-error: true # openapi generation above is the real validation; deploy is best-effort (Pages may be disabled)
|
||||
with:
|
||||
github_token: ${{ secrets.GITHUB_TOKEN }}
|
||||
publish_dir: ./docs
|
||||
@@ -443,31 +282,28 @@ jobs:
|
||||
notify:
|
||||
name: Notify
|
||||
runs-on: ubuntu-latest
|
||||
needs: [code-quality, test, rust-tests, performance-test, docker-build, docs]
|
||||
needs: [code-quality, test, performance-test, docker-build, docs]
|
||||
if: always()
|
||||
permissions:
|
||||
contents: write # required by softprops/action-gh-release
|
||||
# GitHub Actions does not allow `secrets.X` directly in step-level `if:`
|
||||
# expressions — only `env.X`. Promote the secret to env at job scope so
|
||||
# the gating expression below is parseable.
|
||||
env:
|
||||
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
|
||||
steps:
|
||||
- name: Notify Slack on success
|
||||
if: ${{ env.SLACK_WEBHOOK_URL != '' && needs.code-quality.result == 'success' && needs.test.result == 'success' && needs.docker-build.result == 'success' }}
|
||||
if: ${{ secrets.SLACK_WEBHOOK_URL != '' && needs.code-quality.result == 'success' && needs.test.result == 'success' && needs.docker-build.result == 'success' }}
|
||||
uses: 8398a7/action-slack@v3
|
||||
with:
|
||||
status: success
|
||||
channel: '#ci-cd'
|
||||
text: '✅ CI pipeline completed successfully for ${{ github.ref }}'
|
||||
env:
|
||||
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
|
||||
|
||||
- name: Notify Slack on failure
|
||||
if: ${{ env.SLACK_WEBHOOK_URL != '' && (needs.code-quality.result == 'failure' || needs.test.result == 'failure' || needs.docker-build.result == 'failure') }}
|
||||
if: ${{ secrets.SLACK_WEBHOOK_URL != '' && (needs.code-quality.result == 'failure' || needs.test.result == 'failure' || needs.docker-build.result == 'failure') }}
|
||||
uses: 8398a7/action-slack@v3
|
||||
with:
|
||||
status: failure
|
||||
channel: '#ci-cd'
|
||||
text: '❌ CI pipeline failed for ${{ github.ref }}'
|
||||
env:
|
||||
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
|
||||
|
||||
- name: Create GitHub Release
|
||||
if: github.ref == 'refs/heads/main' && needs.docker-build.result == 'success'
|
||||
|
||||
@@ -1,149 +0,0 @@
|
||||
name: GitHub Clone Tracking → data/clone-data.rvf
|
||||
|
||||
# Persists rolling 14-day clone-traffic snapshots to data/clone-data.rvf in
|
||||
# the ruvector JSONL RVF format. GitHub's /traffic/clones endpoint only
|
||||
# retains the last 14 days server-side, so without this scheduled scrape
|
||||
# the data is gone forever the moment it falls outside the window.
|
||||
#
|
||||
# Format: JSONL RVF
|
||||
# - line 1 is a `metadata` segment that initializes the file
|
||||
# - each subsequent run appends one `clone_snapshot` segment carrying the
|
||||
# 14-day rollup PLUS per-day breakdown
|
||||
# - file is idempotent: per-day entries are keyed by `timestamp` so a
|
||||
# downstream reader can dedupe across overlapping snapshot windows
|
||||
#
|
||||
# Schedule: every 14 days (1st + 15th of each month, ~14-day cadence in
|
||||
# practice). Workflow can also be dispatched manually for backfill or test.
|
||||
|
||||
on:
|
||||
schedule:
|
||||
# 01:23 UTC on the 1st and 15th of every month — close to 14-day cadence
|
||||
# without cron's "every 14 days" monthly-reset weirdness. Picking :23
|
||||
# avoids the cron herd on :00.
|
||||
- cron: '23 1 1,15 * *'
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
concurrency:
|
||||
group: clone-tracking
|
||||
cancel-in-progress: false
|
||||
|
||||
jobs:
|
||||
snapshot:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Fetch /traffic/clones + /traffic/views from GitHub
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
run: |
|
||||
mkdir -p data
|
||||
gh api repos/${{ github.repository }}/traffic/clones > /tmp/clones.json
|
||||
gh api repos/${{ github.repository }}/traffic/views > /tmp/views.json
|
||||
echo "--- clones rollup ---"
|
||||
jq '{count, uniques, days: (.clones | length)}' /tmp/clones.json
|
||||
echo "--- views rollup ---"
|
||||
jq '{count, uniques, days: (.views | length)}' /tmp/views.json
|
||||
|
||||
- name: Append snapshot to data/clone-data.rvf
|
||||
env:
|
||||
REPO: ${{ github.repository }}
|
||||
run: |
|
||||
set -e
|
||||
RVF="data/clone-data.rvf"
|
||||
FETCHED_AT=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
|
||||
|
||||
# Initialize the file with a metadata segment on first run.
|
||||
if [ ! -f "$RVF" ]; then
|
||||
echo "Initializing $RVF with metadata segment"
|
||||
jq -n --arg repo "$REPO" --arg ts "$FETCHED_AT" '{
|
||||
type: "metadata",
|
||||
name: "ruview-clone-traffic-history",
|
||||
version: "1.0.0",
|
||||
schema: "ruvector.rvf.jsonl/v1",
|
||||
format: "github-traffic-snapshots",
|
||||
repo: $repo,
|
||||
source: "GitHub Traffic API /repos/{repo}/traffic/{clones,views}",
|
||||
policy: "GitHub retains only 14 days server-side; this file is the long-term record.",
|
||||
segments: ["metadata", "clone_snapshot", "view_snapshot"],
|
||||
created_at: $ts,
|
||||
custom: {
|
||||
cadence: "twice monthly (1st and 15th, ~14-day intervals)",
|
||||
idempotency_key: "timestamp (per-day records de-duplicate across overlapping snapshot windows)"
|
||||
}
|
||||
}' >> "$RVF"
|
||||
fi
|
||||
|
||||
# Append the clone snapshot.
|
||||
jq --arg ts "$FETCHED_AT" '{
|
||||
type: "clone_snapshot",
|
||||
fetched_at: $ts,
|
||||
window_count: .count,
|
||||
window_uniques: .uniques,
|
||||
per_day: .clones
|
||||
}' /tmp/clones.json >> "$RVF"
|
||||
|
||||
# Append the views snapshot (free with the same auth).
|
||||
jq --arg ts "$FETCHED_AT" '{
|
||||
type: "view_snapshot",
|
||||
fetched_at: $ts,
|
||||
window_count: .count,
|
||||
window_uniques: .uniques,
|
||||
per_day: .views
|
||||
}' /tmp/views.json >> "$RVF"
|
||||
|
||||
echo "--- RVF tail (last 4 lines) ---"
|
||||
tail -4 "$RVF" | jq -c '{type, fetched_at, window_count, window_uniques}' || true
|
||||
echo "--- file size ---"
|
||||
wc -l "$RVF"
|
||||
|
||||
- name: Compute aggregates for the commit summary
|
||||
id: agg
|
||||
run: |
|
||||
# Count distinct per-day entries across all snapshots so we can
|
||||
# show "cumulative observed clones" in the commit message.
|
||||
python3 - <<'PY'
|
||||
import json, os
|
||||
path = "data/clone-data.rvf"
|
||||
per_day_clones = {}
|
||||
per_day_views = {}
|
||||
with open(path, encoding="utf-8") as f:
|
||||
for line in f:
|
||||
if not line.strip():
|
||||
continue
|
||||
d = json.loads(line)
|
||||
if d.get("type") == "clone_snapshot":
|
||||
for entry in d.get("per_day", []):
|
||||
per_day_clones[entry["timestamp"]] = entry
|
||||
elif d.get("type") == "view_snapshot":
|
||||
for entry in d.get("per_day", []):
|
||||
per_day_views[entry["timestamp"]] = entry
|
||||
|
||||
tot_clones = sum(e.get("count", 0) for e in per_day_clones.values())
|
||||
tot_uniq_clones = sum(e.get("uniques", 0) for e in per_day_clones.values())
|
||||
tot_views = sum(e.get("count", 0) for e in per_day_views.values())
|
||||
tot_uniq_views = sum(e.get("uniques", 0) for e in per_day_views.values())
|
||||
print(f"clone days observed: {len(per_day_clones)} total clones: {tot_clones:,} total unique cloners: {tot_uniq_clones:,}")
|
||||
print(f"view days observed: {len(per_day_views)} total views: {tot_views:,} total unique viewers: {tot_uniq_views:,}")
|
||||
|
||||
with open(os.environ["GITHUB_OUTPUT"], "a") as out:
|
||||
out.write(f"clones={tot_clones}\n")
|
||||
out.write(f"clone_days={len(per_day_clones)}\n")
|
||||
out.write(f"views={tot_views}\n")
|
||||
out.write(f"view_days={len(per_day_views)}\n")
|
||||
PY
|
||||
|
||||
- name: Commit + push if changed
|
||||
run: |
|
||||
git config user.name "github-actions[bot]"
|
||||
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
|
||||
if git diff --quiet data/clone-data.rvf; then
|
||||
echo "no changes to commit"
|
||||
exit 0
|
||||
fi
|
||||
git add data/clone-data.rvf
|
||||
git commit -m "chore(traffic): clone snapshot — ${{ steps.agg.outputs.clone_days }} days observed → ${{ steps.agg.outputs.clones }} clones, ${{ steps.agg.outputs.view_days }} view-days → ${{ steps.agg.outputs.views }} views"
|
||||
git push
|
||||
@@ -1,200 +0,0 @@
|
||||
name: Cog HA-Matter Release
|
||||
|
||||
# ADR-116 P8 — Build + sign + bundle the cog-ha-matter cog on a
|
||||
# version tag. Upload to gs://cognitum-apps/ runs only when the
|
||||
# GCP_CREDENTIALS + COGNITUM_OWNER_SIGNING_KEY secrets are set, so
|
||||
# this workflow is safe to merge before the production credentials
|
||||
# land — it'll bundle release artifacts to the workflow run page
|
||||
# either way.
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'cog-ha-matter-v*'
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
dry_run:
|
||||
description: 'Build + sign + bundle but skip GCS upload'
|
||||
required: false
|
||||
default: 'true'
|
||||
|
||||
env:
|
||||
CARGO_TERM_COLOR: always
|
||||
CRATE: cog-ha-matter
|
||||
|
||||
jobs:
|
||||
build-x86_64:
|
||||
name: Build x86_64
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Rust
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
with:
|
||||
targets: x86_64-unknown-linux-gnu
|
||||
|
||||
- name: Cache cargo registry
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/registry
|
||||
~/.cargo/git
|
||||
v2/target
|
||||
key: cog-ha-matter-x86_64-${{ hashFiles('v2/Cargo.lock') }}
|
||||
|
||||
- name: Build release binary
|
||||
working-directory: v2/crates/cog-ha-matter/cog
|
||||
run: make build-x86_64
|
||||
|
||||
- name: Compute SHA-256
|
||||
working-directory: v2/crates/cog-ha-matter/cog
|
||||
run: make sign-x86_64
|
||||
|
||||
- name: Sign with Ed25519 (gated)
|
||||
if: ${{ env.SIGNING_KEY != '' }}
|
||||
env:
|
||||
SIGNING_KEY: ${{ secrets.COGNITUM_OWNER_SIGNING_KEY }}
|
||||
working-directory: v2/crates/cog-ha-matter/cog
|
||||
run: |
|
||||
printf '%s' "$SIGNING_KEY" \
|
||||
| openssl pkeyutl -sign -inkey /dev/stdin -rawin \
|
||||
-in dist/cog-ha-matter-x86_64.sha256 \
|
||||
| base64 -w0 > dist/cog-ha-matter-x86_64.sig
|
||||
echo "Signed cog-ha-matter-x86_64 ($(wc -c < dist/cog-ha-matter-x86_64.sig) bytes)"
|
||||
|
||||
- name: Upload workflow artifact
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: cog-ha-matter-x86_64
|
||||
path: |
|
||||
v2/crates/cog-ha-matter/cog/dist/cog-ha-matter-x86_64
|
||||
v2/crates/cog-ha-matter/cog/dist/cog-ha-matter-x86_64.sha256
|
||||
v2/crates/cog-ha-matter/cog/dist/cog-ha-matter-x86_64.sig
|
||||
if-no-files-found: warn
|
||||
|
||||
build-arm:
|
||||
name: Build aarch64 (arm)
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Rust
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
with:
|
||||
targets: aarch64-unknown-linux-gnu
|
||||
|
||||
- name: Install cross-compiler
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y gcc-aarch64-linux-gnu
|
||||
|
||||
- name: Cache cargo registry
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/registry
|
||||
~/.cargo/git
|
||||
v2/target
|
||||
key: cog-ha-matter-arm-${{ hashFiles('v2/Cargo.lock') }}
|
||||
|
||||
- name: Build release binary
|
||||
working-directory: v2
|
||||
env:
|
||||
CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_LINKER: aarch64-linux-gnu-gcc
|
||||
run: |
|
||||
cargo build -p cog-ha-matter --release --target aarch64-unknown-linux-gnu
|
||||
mkdir -p crates/cog-ha-matter/cog/dist
|
||||
cp target/aarch64-unknown-linux-gnu/release/cog-ha-matter \
|
||||
crates/cog-ha-matter/cog/dist/cog-ha-matter-arm
|
||||
# ^ matches Makefile's `dist/$(CRATE)-arm` so `make sign-arm` finds it
|
||||
|
||||
- name: Compute SHA-256
|
||||
working-directory: v2/crates/cog-ha-matter/cog
|
||||
run: make sign-arm
|
||||
|
||||
- name: Sign with Ed25519 (gated)
|
||||
if: ${{ env.SIGNING_KEY != '' }}
|
||||
env:
|
||||
SIGNING_KEY: ${{ secrets.COGNITUM_OWNER_SIGNING_KEY }}
|
||||
working-directory: v2/crates/cog-ha-matter/cog
|
||||
run: |
|
||||
printf '%s' "$SIGNING_KEY" \
|
||||
| openssl pkeyutl -sign -inkey /dev/stdin -rawin \
|
||||
-in dist/cog-ha-matter-arm.sha256 \
|
||||
| base64 -w0 > dist/cog-ha-matter-arm.sig
|
||||
echo "Signed cog-ha-matter-arm ($(wc -c < dist/cog-ha-matter-arm.sig) bytes)"
|
||||
|
||||
- name: Upload workflow artifact
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: cog-ha-matter-arm
|
||||
path: |
|
||||
v2/crates/cog-ha-matter/cog/dist/cog-ha-matter-arm
|
||||
v2/crates/cog-ha-matter/cog/dist/cog-ha-matter-arm.sha256
|
||||
v2/crates/cog-ha-matter/cog/dist/cog-ha-matter-arm.sig
|
||||
if-no-files-found: warn
|
||||
|
||||
publish-gcs:
|
||||
name: Upload to GCS (gated)
|
||||
needs: [build-x86_64, build-arm]
|
||||
runs-on: ubuntu-latest
|
||||
# Skip on dry-run dispatch; skip on tags when GCP_CREDENTIALS unset.
|
||||
if: >
|
||||
github.event_name == 'push' &&
|
||||
vars.HAS_GCP_CREDENTIALS == 'true'
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Download x86_64 artifact
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
name: cog-ha-matter-x86_64
|
||||
path: dist/
|
||||
|
||||
- name: Download arm artifact
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
name: cog-ha-matter-arm
|
||||
path: dist/
|
||||
|
||||
- name: Auth to GCP
|
||||
uses: google-github-actions/auth@v2
|
||||
with:
|
||||
credentials_json: ${{ secrets.GCP_CREDENTIALS }}
|
||||
|
||||
- name: Set up gcloud
|
||||
uses: google-github-actions/setup-gcloud@v2
|
||||
|
||||
- name: Upload binaries + sidecars
|
||||
run: |
|
||||
gsutil cp dist/cog-ha-matter-x86_64 gs://cognitum-apps/cogs/x86_64/cog-ha-matter-x86_64
|
||||
gsutil cp dist/cog-ha-matter-x86_64.sha256 gs://cognitum-apps/cogs/x86_64/cog-ha-matter-x86_64.sha256
|
||||
gsutil cp dist/cog-ha-matter-arm gs://cognitum-apps/cogs/arm/cog-ha-matter-arm
|
||||
gsutil cp dist/cog-ha-matter-arm.sha256 gs://cognitum-apps/cogs/arm/cog-ha-matter-arm.sha256
|
||||
if [ -f dist/cog-ha-matter-x86_64.sig ]; then
|
||||
gsutil cp dist/cog-ha-matter-x86_64.sig gs://cognitum-apps/cogs/x86_64/cog-ha-matter-x86_64.sig
|
||||
fi
|
||||
if [ -f dist/cog-ha-matter-arm.sig ]; then
|
||||
gsutil cp dist/cog-ha-matter-arm.sig gs://cognitum-apps/cogs/arm/cog-ha-matter-arm.sig
|
||||
fi
|
||||
|
||||
- name: Print app-registry.json snippet for the cognitum-one PR
|
||||
run: |
|
||||
for arch in arm x86_64; do
|
||||
sha=$(cat dist/cog-cog-ha-matter-$arch.sha256)
|
||||
sig=$([ -f dist/cog-cog-ha-matter-$arch.sig ] && cat dist/cog-cog-ha-matter-$arch.sig || echo "")
|
||||
cat <<EOF
|
||||
--- $arch ---
|
||||
{
|
||||
"id": "ha-matter",
|
||||
"version": "${GITHUB_REF_NAME#cog-ha-matter-v}",
|
||||
"binary_url": "https://storage.googleapis.com/cognitum-apps/cogs/$arch/cog-cog-ha-matter-$arch",
|
||||
"binary_sha256": "$sha",
|
||||
"binary_signature": "$sig",
|
||||
"description": "Home Assistant + Matter Cognitum Seed cog (mDNS + witness chain)",
|
||||
"min_seed_version": "0.6.0",
|
||||
"installable_on": ["$arch"]
|
||||
}
|
||||
EOF
|
||||
done
|
||||
@@ -1,46 +0,0 @@
|
||||
name: Dashboard a11y + cross-browser
|
||||
|
||||
# Runs axe-core a11y assertions on the built dashboard across
|
||||
# Chromium, Firefox, and WebKit. Closes ADR-092 §11.5 (axe-core)
|
||||
# and §11.8 (cross-browser).
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths: ['dashboard/**', 'v2/crates/nvsim/**']
|
||||
pull_request:
|
||||
paths: ['dashboard/**']
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
a11y:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: dtolnay/rust-toolchain@stable
|
||||
with: { targets: wasm32-unknown-unknown }
|
||||
|
||||
- name: Install wasm-pack
|
||||
run: curl https://rustwasm.github.io/wasm-pack/installer/init.sh -sSf | sh
|
||||
|
||||
- name: Build nvsim WASM
|
||||
working-directory: v2
|
||||
run: |
|
||||
wasm-pack build crates/nvsim --target web \
|
||||
--out-dir ../../dashboard/public/nvsim-pkg \
|
||||
--release -- --no-default-features --features wasm
|
||||
|
||||
- uses: actions/setup-node@v6
|
||||
with: { node-version: 20, cache: npm, cache-dependency-path: dashboard/package-lock.json }
|
||||
|
||||
- working-directory: dashboard
|
||||
run: |
|
||||
npm ci
|
||||
npm install --save-dev @playwright/test @axe-core/playwright
|
||||
npx playwright install --with-deps
|
||||
npm run build
|
||||
npx playwright test
|
||||
@@ -1,87 +0,0 @@
|
||||
name: nvsim Dashboard → GitHub Pages
|
||||
|
||||
# Deploys the nvsim Vite/Lit dashboard to gh-pages/nvsim/ — preserving
|
||||
# the existing observatory/, pose-fusion/, and root index.html demos
|
||||
# already published from gh-pages. ADR-092 §9.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'v2/crates/nvsim/**'
|
||||
- 'dashboard/**'
|
||||
- '.github/workflows/dashboard-pages.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
concurrency:
|
||||
group: dashboard-pages
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
build-and-deploy:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout main
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install Rust + wasm32 target
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
with:
|
||||
targets: wasm32-unknown-unknown
|
||||
|
||||
- name: Cache cargo registry
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/registry
|
||||
~/.cargo/git
|
||||
v2/target
|
||||
key: ${{ runner.os }}-cargo-nvsim-${{ hashFiles('v2/Cargo.lock') }}
|
||||
restore-keys: ${{ runner.os }}-cargo-nvsim-
|
||||
|
||||
- name: Install wasm-pack
|
||||
run: |
|
||||
curl https://rustwasm.github.io/wasm-pack/installer/init.sh -sSf | sh
|
||||
which wasm-pack
|
||||
|
||||
- name: Build nvsim WASM
|
||||
working-directory: v2
|
||||
run: |
|
||||
wasm-pack build crates/nvsim \
|
||||
--target web \
|
||||
--out-dir ../../dashboard/public/nvsim-pkg \
|
||||
--release \
|
||||
-- --no-default-features --features wasm
|
||||
|
||||
- name: Setup Node 20
|
||||
uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: 20
|
||||
cache: npm
|
||||
cache-dependency-path: dashboard/package-lock.json
|
||||
|
||||
- name: Install dashboard deps
|
||||
working-directory: dashboard
|
||||
run: npm ci
|
||||
|
||||
- name: Build dashboard
|
||||
working-directory: dashboard
|
||||
env:
|
||||
NVSIM_BASE: /RuView/nvsim/
|
||||
run: npm run build
|
||||
|
||||
- name: Deploy to gh-pages/nvsim/
|
||||
uses: peaceiris/actions-gh-pages@v4
|
||||
with:
|
||||
github_token: ${{ secrets.GITHUB_TOKEN }}
|
||||
publish_dir: ./dashboard/dist
|
||||
destination_dir: nvsim
|
||||
# CRITICAL: preserves observatory/, pose-fusion/, root index.html
|
||||
# and any other RuView demos already on gh-pages.
|
||||
keep_files: true
|
||||
commit_message: 'deploy(nvsim): ${{ github.sha }}'
|
||||
user_name: 'github-actions[bot]'
|
||||
user_email: 'github-actions[bot]@users.noreply.github.com'
|
||||
@@ -30,7 +30,7 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v6
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: '20'
|
||||
|
||||
@@ -40,18 +40,18 @@ jobs:
|
||||
targets: ${{ matrix.target }}
|
||||
|
||||
- name: Install frontend dependencies
|
||||
working-directory: v2/crates/wifi-densepose-desktop/ui
|
||||
working-directory: rust-port/wifi-densepose-rs/crates/wifi-densepose-desktop/ui
|
||||
run: npm ci
|
||||
|
||||
- name: Build frontend
|
||||
working-directory: v2/crates/wifi-densepose-desktop/ui
|
||||
working-directory: rust-port/wifi-densepose-rs/crates/wifi-densepose-desktop/ui
|
||||
run: npm run build
|
||||
|
||||
- name: Install Tauri CLI
|
||||
run: cargo install tauri-cli --version "^2.0.0"
|
||||
|
||||
- name: Build Tauri app
|
||||
working-directory: v2/crates/wifi-densepose-desktop
|
||||
working-directory: rust-port/wifi-densepose-rs/crates/wifi-densepose-desktop
|
||||
run: cargo tauri build --target ${{ matrix.target }}
|
||||
env:
|
||||
TAURI_SIGNING_PRIVATE_KEY: ${{ secrets.TAURI_SIGNING_PRIVATE_KEY }}
|
||||
@@ -68,14 +68,14 @@ jobs:
|
||||
|
||||
- name: Package macOS app
|
||||
run: |
|
||||
cd v2/target/${{ matrix.target }}/release/bundle/macos
|
||||
cd rust-port/wifi-densepose-rs/target/${{ matrix.target }}/release/bundle/macos
|
||||
zip -r "RuView-Desktop-${{ github.event.inputs.version || '0.4.0' }}-macos-${{ steps.arch.outputs.arch }}.zip" "RuView Desktop.app"
|
||||
|
||||
- name: Upload macOS artifact
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ruview-macos-${{ steps.arch.outputs.arch }}
|
||||
path: v2/target/${{ matrix.target }}/release/bundle/macos/*.zip
|
||||
path: rust-port/wifi-densepose-rs/target/${{ matrix.target }}/release/bundle/macos/*.zip
|
||||
|
||||
build-windows:
|
||||
name: Build Windows
|
||||
@@ -85,7 +85,7 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v6
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: '20'
|
||||
|
||||
@@ -93,18 +93,18 @@ jobs:
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
|
||||
- name: Install frontend dependencies
|
||||
working-directory: v2/crates/wifi-densepose-desktop/ui
|
||||
working-directory: rust-port/wifi-densepose-rs/crates/wifi-densepose-desktop/ui
|
||||
run: npm ci
|
||||
|
||||
- name: Build frontend
|
||||
working-directory: v2/crates/wifi-densepose-desktop/ui
|
||||
working-directory: rust-port/wifi-densepose-rs/crates/wifi-densepose-desktop/ui
|
||||
run: npm run build
|
||||
|
||||
- name: Install Tauri CLI
|
||||
run: cargo install tauri-cli --version "^2.0.0"
|
||||
|
||||
- name: Build Tauri app
|
||||
working-directory: v2/crates/wifi-densepose-desktop
|
||||
working-directory: rust-port/wifi-densepose-rs/crates/wifi-densepose-desktop
|
||||
run: cargo tauri build
|
||||
env:
|
||||
TAURI_SIGNING_PRIVATE_KEY: ${{ secrets.TAURI_SIGNING_PRIVATE_KEY }}
|
||||
@@ -114,13 +114,13 @@ jobs:
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ruview-windows-msi
|
||||
path: v2/target/release/bundle/msi/*.msi
|
||||
path: rust-port/wifi-densepose-rs/target/release/bundle/msi/*.msi
|
||||
|
||||
- name: Upload Windows NSIS artifact
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ruview-windows-nsis
|
||||
path: v2/target/release/bundle/nsis/*.exe
|
||||
path: rust-port/wifi-densepose-rs/target/release/bundle/nsis/*.exe
|
||||
|
||||
create-release:
|
||||
name: Create Release
|
||||
|
||||
@@ -2,11 +2,6 @@ name: Firmware CI
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- '**'
|
||||
tags:
|
||||
# ESP32 firmware release tags — build + version-consistency guard (RuView#505).
|
||||
- 'v*-esp32'
|
||||
paths:
|
||||
- 'firmware/**'
|
||||
- '.github/workflows/firmware-ci.yml'
|
||||
@@ -16,92 +11,32 @@ on:
|
||||
- '.github/workflows/firmware-ci.yml'
|
||||
|
||||
jobs:
|
||||
version-guard:
|
||||
name: Verify version.txt matches release tag
|
||||
runs-on: ubuntu-latest
|
||||
if: github.ref_type == 'tag'
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Check firmware version.txt == tag
|
||||
run: |
|
||||
# Tag form: vX.Y.Z-esp32 → expect version.txt to contain X.Y.Z
|
||||
TAG="${GITHUB_REF_NAME}"
|
||||
EXPECTED="${TAG#v}"
|
||||
EXPECTED="${EXPECTED%-esp32}"
|
||||
ACTUAL="$(tr -d '[:space:]' < firmware/esp32-csi-node/version.txt)"
|
||||
echo "Tag: $TAG → expected version.txt: $EXPECTED | actual: $ACTUAL"
|
||||
if [ "$EXPECTED" != "$ACTUAL" ]; then
|
||||
echo "::error::firmware/esp32-csi-node/version.txt is '$ACTUAL' but tag '$TAG' expects '$EXPECTED'."
|
||||
echo "::error::Bump version.txt and re-tag so esp_app_get_description()->version is correct (RuView#505)."
|
||||
exit 1
|
||||
fi
|
||||
echo "version.txt matches the release tag."
|
||||
|
||||
build:
|
||||
name: Build firmware (${{ matrix.target }} / ${{ matrix.variant }})
|
||||
name: Build ESP32-S3 Firmware
|
||||
runs-on: ubuntu-latest
|
||||
container:
|
||||
image: espressif/idf:v5.4
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- variant: 8mb
|
||||
target: esp32s3
|
||||
sdkconfig: sdkconfig.defaults
|
||||
partition_table_name: partitions_display.csv
|
||||
size_limit_kb: 1100
|
||||
artifact_app: esp32-csi-node.bin
|
||||
artifact_pt: partition-table.bin
|
||||
- variant: 4mb
|
||||
target: esp32s3
|
||||
sdkconfig: sdkconfig.defaults.4mb
|
||||
partition_table_name: partitions_4mb.csv
|
||||
size_limit_kb: 1100
|
||||
artifact_app: esp32-csi-node-4mb.bin
|
||||
artifact_pt: partition-table-4mb.bin
|
||||
# ADR-110: ESP32-C6 research target (Wi-Fi 6 / 802.15.4 / TWT / LP-core)
|
||||
- variant: c6-4mb
|
||||
target: esp32c6
|
||||
sdkconfig: sdkconfig.defaults
|
||||
partition_table_name: partitions_4mb.csv
|
||||
size_limit_kb: 1100
|
||||
artifact_app: esp32-csi-node-c6.bin
|
||||
artifact_pt: partition-table-c6.bin
|
||||
image: espressif/idf:v5.2
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Build firmware (${{ matrix.variant }})
|
||||
- name: Build firmware
|
||||
working-directory: firmware/esp32-csi-node
|
||||
run: |
|
||||
. $IDF_PATH/export.sh
|
||||
# 4mb variant supplies its own sdkconfig.defaults overlay.
|
||||
# c6-4mb variant relies on the auto-applied sdkconfig.defaults.esp32c6
|
||||
# overlay (ESP-IDF auto-loads sdkconfig.defaults.$TARGET when present).
|
||||
if [ "${{ matrix.variant }}" = "4mb" ]; then
|
||||
cp "${{ matrix.sdkconfig }}" sdkconfig.defaults
|
||||
fi
|
||||
idf.py set-target ${{ matrix.target }}
|
||||
idf.py set-target esp32s3
|
||||
idf.py build
|
||||
|
||||
- name: Build and run host-side ADR-110 unit tests
|
||||
if: matrix.variant == 'c6-4mb'
|
||||
working-directory: firmware/esp32-csi-node/test
|
||||
run: |
|
||||
make test_adr110
|
||||
./test_adr110
|
||||
|
||||
- name: Verify binary size (< ${{ matrix.size_limit_kb }} KB gate)
|
||||
- name: Verify binary size (< 1100 KB gate)
|
||||
working-directory: firmware/esp32-csi-node
|
||||
run: |
|
||||
BIN=build/esp32-csi-node.bin
|
||||
SIZE=$(stat -c%s "$BIN")
|
||||
MAX=$((${{ matrix.size_limit_kb }} * 1024))
|
||||
MAX=$((1100 * 1024))
|
||||
echo "Binary size: $SIZE bytes ($(( SIZE / 1024 )) KB)"
|
||||
echo "Size limit: $MAX bytes (${{ matrix.size_limit_kb }} KB)"
|
||||
echo "Size limit: $MAX bytes (1100 KB — includes WASM runtime + HTTP client for Seed swarm bridge)"
|
||||
if [ "$SIZE" -gt "$MAX" ]; then
|
||||
echo "::error::Firmware binary exceeds ${{ matrix.size_limit_kb }} KB size gate ($SIZE > $MAX)"
|
||||
echo "::error::Firmware binary exceeds 1100 KB size gate ($SIZE > $MAX)"
|
||||
exit 1
|
||||
fi
|
||||
echo "Binary size OK: $SIZE <= $MAX"
|
||||
@@ -112,27 +47,31 @@ jobs:
|
||||
ERRORS=0
|
||||
BIN=build/esp32-csi-node.bin
|
||||
|
||||
# Check binary exists and is non-empty.
|
||||
if [ ! -s "$BIN" ]; then
|
||||
echo "::error::Binary not found or empty"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Check partition table magic (0xAA50 at offset 0).
|
||||
PT=build/partition_table/partition-table.bin
|
||||
if [ -f "$PT" ]; then
|
||||
MAGIC=$(od -A n -t x1 -N 2 "$PT" | tr -d ' ')
|
||||
MAGIC=$(xxd -l2 -p "$PT")
|
||||
if [ "$MAGIC" != "aa50" ]; then
|
||||
echo "::warning::Partition table magic mismatch: $MAGIC (expected aa50)"
|
||||
ERRORS=$((ERRORS + 1))
|
||||
fi
|
||||
fi
|
||||
|
||||
# Check bootloader exists.
|
||||
BL=build/bootloader/bootloader.bin
|
||||
if [ ! -s "$BL" ]; then
|
||||
echo "::warning::Bootloader binary missing or empty"
|
||||
ERRORS=$((ERRORS + 1))
|
||||
fi
|
||||
|
||||
NONZERO=$(od -A n -t x1 -N 1024 "$BIN" | tr -d ' f\n' | wc -c)
|
||||
# Verify non-zero data in binary (not all 0xFF padding).
|
||||
NONZERO=$(xxd -l 1024 -p "$BIN" | tr -d 'f' | wc -c)
|
||||
if [ "$NONZERO" -lt 100 ]; then
|
||||
echo "::error::Binary appears to be mostly padding (non-zero chars: $NONZERO)"
|
||||
ERRORS=$((ERRORS + 1))
|
||||
@@ -144,27 +83,18 @@ jobs:
|
||||
echo "Flash image integrity verified"
|
||||
fi
|
||||
|
||||
- name: Stage release binaries with variant-specific names
|
||||
working-directory: firmware/esp32-csi-node
|
||||
run: |
|
||||
mkdir -p release-staging
|
||||
cp build/esp32-csi-node.bin release-staging/${{ matrix.artifact_app }}
|
||||
cp build/partition_table/partition-table.bin release-staging/${{ matrix.artifact_pt }}
|
||||
if [ "${{ matrix.variant }}" = "8mb" ]; then
|
||||
cp build/bootloader/bootloader.bin release-staging/bootloader.bin
|
||||
cp build/ota_data_initial.bin release-staging/ota_data_initial.bin
|
||||
fi
|
||||
ls -la release-staging/
|
||||
|
||||
- name: Check QEMU ESP32-S3 support status
|
||||
run: |
|
||||
echo "::notice::ESP32-S3 QEMU support is experimental in ESP-IDF v5.4. "
|
||||
echo "Full smoke testing requires QEMU 8.2+ with xtensa-esp32s3 target."
|
||||
echo "See: https://github.com/espressif/qemu/wiki"
|
||||
|
||||
- name: Upload firmware artifact (${{ matrix.variant }})
|
||||
- name: Upload firmware artifact
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: esp32-csi-node-firmware-${{ matrix.variant }}
|
||||
path: firmware/esp32-csi-node/release-staging/
|
||||
retention-days: 90
|
||||
name: esp32-csi-node-firmware
|
||||
path: |
|
||||
firmware/esp32-csi-node/build/esp32-csi-node.bin
|
||||
firmware/esp32-csi-node/build/bootloader/bootloader.bin
|
||||
firmware/esp32-csi-node/build/partition_table/partition-table.bin
|
||||
retention-days: 30
|
||||
|
||||
@@ -1,54 +0,0 @@
|
||||
name: Fix-Marker Regression Guard
|
||||
|
||||
# Asserts that previously-shipped fixes are still present in the tree.
|
||||
# Manifest: scripts/fix-markers.json Checker: scripts/check_fix_markers.py
|
||||
# Run locally: python scripts/check_fix_markers.py (also --list / --json)
|
||||
#
|
||||
# This complements the heavyweight checks (firmware build, deterministic
|
||||
# pipeline proof, witness bundle) with a fast per-PR "did someone revert a
|
||||
# known fix?" gate — the CI analogue of the ruflo witness fix-marker system.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
- master
|
||||
pull_request:
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
fix-markers:
|
||||
name: Verify fix markers
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: actions/setup-python@v6
|
||||
with:
|
||||
python-version: '3.11'
|
||||
|
||||
- name: Validate the manifest is well-formed JSON
|
||||
run: python -c "import json; json.load(open('scripts/fix-markers.json')); print('manifest OK')"
|
||||
|
||||
- name: Check fix markers
|
||||
run: python scripts/check_fix_markers.py
|
||||
|
||||
- name: Emit machine-readable result (for the run summary)
|
||||
if: always()
|
||||
run: |
|
||||
python scripts/check_fix_markers.py --json > fix-markers-result.json || true
|
||||
{
|
||||
echo '### Fix-marker regression guard'
|
||||
echo ''
|
||||
echo '```'
|
||||
python scripts/check_fix_markers.py || true
|
||||
echo '```'
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
|
||||
- name: Upload result artifact
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: fix-markers-result
|
||||
path: fix-markers-result.json
|
||||
retention-days: 30
|
||||
@@ -1,110 +0,0 @@
|
||||
name: ADR-115 MQTT integration tests
|
||||
|
||||
# Runs the Mosquitto-broker-backed integration tests for ADR-115's MQTT
|
||||
# publisher. These prove the publisher reaches a real broker, emits the
|
||||
# expected HA-discovery topic shape, and honours --privacy-mode at the
|
||||
# wire boundary (not just in unit-test logic).
|
||||
#
|
||||
# Default `cargo test --workspace` does not run these tests because they
|
||||
# require a broker and pull rumqttc into the build. This workflow opts
|
||||
# into both by setting --features mqtt and RUVIEW_RUN_INTEGRATION=1.
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
paths:
|
||||
- 'v2/crates/wifi-densepose-sensing-server/src/mqtt/**'
|
||||
- 'v2/crates/wifi-densepose-sensing-server/tests/mqtt_integration.rs'
|
||||
- 'v2/crates/wifi-densepose-sensing-server/Cargo.toml'
|
||||
- '.github/workflows/mqtt-integration.yml'
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'v2/crates/wifi-densepose-sensing-server/src/mqtt/**'
|
||||
workflow_dispatch: {}
|
||||
|
||||
jobs:
|
||||
mqtt-integration:
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 20
|
||||
|
||||
# NB: we don't use a `services:` mosquitto container here because the
|
||||
# eclipse-mosquitto:2.x image rejects anonymous connections by default
|
||||
# and GH Actions `services` doesn't easily support mounting a custom
|
||||
# config file. We start mosquitto manually in a step below with an
|
||||
# inline `allow_anonymous true` config.
|
||||
|
||||
env:
|
||||
RUVIEW_RUN_INTEGRATION: "1"
|
||||
RUVIEW_TEST_MQTT_PORT: "11883"
|
||||
CARGO_TERM_COLOR: always
|
||||
RUST_BACKTRACE: 1
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install mosquitto + clients and start with allow_anonymous
|
||||
run: |
|
||||
sudo apt-get update -qq
|
||||
sudo apt-get install -y mosquitto mosquitto-clients
|
||||
sudo systemctl stop mosquitto || true
|
||||
# Inline config: anon listener on 11883 only — no TLS, no auth,
|
||||
# OK for CI because we test the wire shape, not security.
|
||||
# Production deployments enable mTLS per ADR-115 §3.9.
|
||||
cat > /tmp/mosquitto-ci.conf <<'EOF'
|
||||
listener 11883
|
||||
allow_anonymous true
|
||||
persistence false
|
||||
log_dest stdout
|
||||
EOF
|
||||
mosquitto -c /tmp/mosquitto-ci.conf -d
|
||||
for i in {1..20}; do
|
||||
if mosquitto_pub -h 127.0.0.1 -p 11883 -t healthcheck -m ok -q 0 2>/dev/null; then
|
||||
echo "mosquitto reachable on 11883"; exit 0
|
||||
fi
|
||||
sleep 2
|
||||
done
|
||||
echo "mosquitto never became reachable" >&2
|
||||
tail -50 /var/log/mosquitto/*.log 2>/dev/null || true
|
||||
exit 1
|
||||
|
||||
- name: Install Rust toolchain
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
with:
|
||||
toolchain: stable
|
||||
|
||||
- name: Cache cargo registry + build
|
||||
uses: Swatinem/rust-cache@v2
|
||||
with:
|
||||
workspaces: v2 -> target
|
||||
|
||||
- name: Validate HA Blueprints
|
||||
run: |
|
||||
python -m pip install --quiet pyyaml
|
||||
python scripts/validate-ha-blueprints.py
|
||||
|
||||
- name: Verify unit tests still pass under --features mqtt
|
||||
working-directory: v2
|
||||
# `cargo test` accepts a single TESTNAME filter, so we run the
|
||||
# whole --lib suite here. That gives us the full 410-test green
|
||||
# bar under --features mqtt (which is more reassuring than
|
||||
# filtering anyway).
|
||||
run: >-
|
||||
cargo test -p wifi-densepose-sensing-server
|
||||
--features mqtt --no-default-features
|
||||
--lib
|
||||
--no-fail-fast
|
||||
|
||||
- name: Run integration tests against mosquitto
|
||||
working-directory: v2
|
||||
run: >-
|
||||
cargo test -p wifi-densepose-sensing-server
|
||||
--features mqtt --no-default-features
|
||||
--test mqtt_integration
|
||||
--no-fail-fast
|
||||
-- --test-threads=1 --nocapture
|
||||
|
||||
- name: Dump broker logs on failure
|
||||
if: failure()
|
||||
run: |
|
||||
docker ps -a
|
||||
docker logs $(docker ps -aqf "ancestor=eclipse-mosquitto:2.0.18") || true
|
||||
@@ -1,69 +0,0 @@
|
||||
name: nvsim-server → ghcr.io
|
||||
|
||||
# Builds and publishes the nvsim-server Docker image to ghcr.io on:
|
||||
# - push to main affecting nvsim-server or nvsim
|
||||
# - tag push matching nvsim-server-v*
|
||||
# - manual workflow_dispatch
|
||||
#
|
||||
# ADR-092 §6.2 + §9.4.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'v2/crates/nvsim-server/**'
|
||||
- 'v2/crates/nvsim/**'
|
||||
- '.github/workflows/nvsim-server-docker.yml'
|
||||
tags: ['nvsim-server-v*']
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
packages: write
|
||||
|
||||
jobs:
|
||||
build-and-publish:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: docker/setup-buildx-action@v3
|
||||
|
||||
- uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ghcr.io
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Extract metadata
|
||||
id: meta
|
||||
uses: docker/metadata-action@v6
|
||||
with:
|
||||
images: ghcr.io/ruvnet/nvsim-server
|
||||
tags: |
|
||||
type=ref,event=branch
|
||||
type=ref,event=tag
|
||||
type=sha,format=short
|
||||
type=raw,value=latest,enable={{is_default_branch}}
|
||||
|
||||
- name: Build + push
|
||||
uses: docker/build-push-action@v7
|
||||
with:
|
||||
context: v2
|
||||
file: v2/crates/nvsim-server/Dockerfile
|
||||
push: true
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
platforms: linux/amd64
|
||||
|
||||
- name: Smoke-test the image
|
||||
run: |
|
||||
docker pull ghcr.io/ruvnet/nvsim-server:sha-${GITHUB_SHA::7} || \
|
||||
docker pull ghcr.io/ruvnet/nvsim-server:latest
|
||||
docker run --rm -d --name nvsim-test -p 7878:7878 \
|
||||
ghcr.io/ruvnet/nvsim-server:latest
|
||||
sleep 4
|
||||
curl -fsS http://localhost:7878/api/health
|
||||
docker stop nvsim-test
|
||||
@@ -1,286 +0,0 @@
|
||||
# ADR-117 P5 — cibuildwheel + PyPI publish workflow for `wifi-densepose`
|
||||
#
|
||||
# This workflow is **explicitly NOT** triggered on every push. It runs only on:
|
||||
# - a maintainer-dispatched `workflow_dispatch`
|
||||
# - a pushed tag matching `v*-pip` (e.g. `v2.0.0-pip`)
|
||||
#
|
||||
# The reason for the `-pip` tag suffix is that the repo already cuts
|
||||
# `v0.X.Y-esp32` tags for firmware releases (see CLAUDE.md). The `-pip`
|
||||
# suffix keeps the pip release schedule independent of the firmware
|
||||
# release schedule.
|
||||
#
|
||||
# Sequencing on release day (per ADR-117 §7.3):
|
||||
# 1. cut tag `v1.99.0-pip` → publishes the tombstone wheel first
|
||||
# 2. cut tag `v2.0.0-pip` → publishes the PyO3 v2 wheel matrix
|
||||
#
|
||||
# Publishes via the `PYPI_API_TOKEN` GitHub Actions secret. The
|
||||
# token-refresh runbook (GCP Secret Manager → gh secret set) lives in
|
||||
# docs/integrations/pypi-release.md so KICS does not flag the
|
||||
# secret name as a generic-secret literal in the workflow.
|
||||
#
|
||||
# Q3 (witness hash v2 — open in ADR-117 §11.3) MUST be resolved
|
||||
# before the first v2.0.0 publish. When v2 lands, add a parallel
|
||||
# step that verifies the v2 hash against the Rust pipeline.
|
||||
|
||||
name: pip-release
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
target:
|
||||
description: "Which package to release"
|
||||
required: true
|
||||
type: choice
|
||||
options:
|
||||
- v2-wheels
|
||||
- v1-99-tombstone
|
||||
publish_to:
|
||||
description: "Where to publish"
|
||||
required: true
|
||||
default: testpypi
|
||||
type: choice
|
||||
options:
|
||||
- testpypi # dry-run target
|
||||
- pypi # production
|
||||
push:
|
||||
tags:
|
||||
- "v*-pip"
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
# ────────────────────────────────────────────────────────────────
|
||||
# v2.0.0 — cibuildwheel matrix (5 wheels + sdist)
|
||||
# ────────────────────────────────────────────────────────────────
|
||||
|
||||
build-wheels:
|
||||
name: Build ${{ matrix.os }} ${{ matrix.arch }}
|
||||
if: |
|
||||
github.event_name == 'workflow_dispatch' && inputs.target == 'v2-wheels' ||
|
||||
startsWith(github.ref, 'refs/tags/v2.')
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- os: ubuntu-latest
|
||||
arch: x86_64
|
||||
- os: ubuntu-latest
|
||||
arch: aarch64
|
||||
- os: macos-13 # x86_64 runner
|
||||
arch: x86_64
|
||||
- os: macos-14 # arm64 runner
|
||||
arch: arm64
|
||||
- os: windows-latest
|
||||
arch: AMD64
|
||||
runs-on: ${{ matrix.os }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
# Linux aarch64 needs QEMU for cross-build on x86_64 runners.
|
||||
- name: Set up QEMU
|
||||
if: matrix.os == 'ubuntu-latest' && matrix.arch == 'aarch64'
|
||||
uses: docker/setup-qemu-action@v3
|
||||
|
||||
# ADR-117 §5.4: abi3-py310 — one binary per OS/arch covers all
|
||||
# Python minor versions ≥ 3.10. Build only cp310 wheels.
|
||||
- name: Build wheels (cibuildwheel)
|
||||
uses: pypa/cibuildwheel@v2.21
|
||||
env:
|
||||
CIBW_BUILD: "cp310-*"
|
||||
CIBW_ARCHS_LINUX: ${{ matrix.arch }}
|
||||
CIBW_ARCHS_MACOS: ${{ matrix.arch }}
|
||||
CIBW_ARCHS_WINDOWS: ${{ matrix.arch }}
|
||||
CIBW_BUILD_FRONTEND: "build"
|
||||
CIBW_BEFORE_BUILD: "pip install maturin>=1.7"
|
||||
# The PyO3 sdist landing depends on the cargo/Rust toolchain
|
||||
# being present. cibuildwheel images carry rustup on Linux
|
||||
# but we also pin a known-good version for reproducibility.
|
||||
CIBW_BEFORE_ALL_LINUX: "curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain 1.82"
|
||||
CIBW_ENVIRONMENT_LINUX: 'PATH="$HOME/.cargo/bin:$PATH"'
|
||||
# Smoke-test every built wheel before accepting it. Catches
|
||||
# the case where the wheel imports but the compiled symbols
|
||||
# are missing.
|
||||
CIBW_TEST_REQUIRES: "pytest>=8.0"
|
||||
CIBW_TEST_COMMAND: 'python -c "import wifi_densepose; assert wifi_densepose.hello() == \"ok\"; print(wifi_densepose.__build_features__)"'
|
||||
with:
|
||||
package-dir: python
|
||||
output-dir: wheelhouse
|
||||
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: wheels-${{ matrix.os }}-${{ matrix.arch }}
|
||||
path: wheelhouse/*.whl
|
||||
if-no-files-found: error
|
||||
|
||||
build-sdist:
|
||||
name: Build v2 sdist
|
||||
if: |
|
||||
github.event_name == 'workflow_dispatch' && inputs.target == 'v2-wheels' ||
|
||||
startsWith(github.ref, 'refs/tags/v2.')
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Install maturin
|
||||
run: pip install maturin>=1.7
|
||||
- name: Build sdist
|
||||
working-directory: python
|
||||
run: maturin sdist --out ../sdist
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: sdist
|
||||
path: sdist/*.tar.gz
|
||||
if-no-files-found: error
|
||||
|
||||
# ────────────────────────────────────────────────────────────────
|
||||
# v1.99.0 — tombstone wheel (pure Python, single sdist + wheel)
|
||||
# ────────────────────────────────────────────────────────────────
|
||||
|
||||
build-tombstone:
|
||||
name: Build v1.99.0 tombstone
|
||||
if: |
|
||||
github.event_name == 'workflow_dispatch' && inputs.target == 'v1-99-tombstone' ||
|
||||
startsWith(github.ref, 'refs/tags/v1.99')
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.12'
|
||||
- name: Install build backend
|
||||
run: python -m pip install --upgrade pip build>=1.2
|
||||
- name: Build sdist + wheel
|
||||
working-directory: python/tombstone
|
||||
run: python -m build --outdir ../../tombstone-dist
|
||||
# Inspect what was actually built — the previous v1.99.0-pip run
|
||||
# showed an `import wifi_densepose` that returned cleanly instead
|
||||
# of raising, even though build logs said `adding 'wifi_densepose/__init__.py'`.
|
||||
# Print the wheel manifest + the __init__.py content so any
|
||||
# future regression is debuggable from the run log alone.
|
||||
- name: Inspect wheel contents
|
||||
run: |
|
||||
set -e
|
||||
WHL=tombstone-dist/wifi_densepose-1.99.0-py3-none-any.whl
|
||||
echo "--- wheel listing ---"
|
||||
python -m zipfile -l "$WHL"
|
||||
echo "--- wifi_densepose/__init__.py inside the wheel ---"
|
||||
python -m zipfile -e "$WHL" /tmp/tomb-inspect
|
||||
cat /tmp/tomb-inspect/wifi_densepose/__init__.py
|
||||
echo "--- size in bytes ---"
|
||||
wc -c /tmp/tomb-inspect/wifi_densepose/__init__.py
|
||||
# Smoke-test in an ISOLATED venv. The previous run's failure
|
||||
# mode was that the ubuntu-latest runner's system `python` had
|
||||
# site-packages picking up something other than the user-installed
|
||||
# wheel, so the import resolved to a different module. A clean
|
||||
# venv removes any ambiguity about which wifi_densepose is loaded.
|
||||
- name: Smoke-test tombstone in isolated venv
|
||||
run: |
|
||||
set -e
|
||||
# Copy the wheel to /tmp BEFORE entering the venv — we must
|
||||
# cd OUT of the repo root because the repo contains a
|
||||
# `wifi_densepose/` directory left over from the legacy v1
|
||||
# source. Python puts cwd at sys.path[0], so an import from
|
||||
# the repo root would resolve to the legacy directory and
|
||||
# bypass the freshly-installed wheel entirely (this was the
|
||||
# silent failure mode of the previous two run attempts).
|
||||
cp tombstone-dist/wifi_densepose-1.99.0-py3-none-any.whl /tmp/
|
||||
python -m venv /tmp/smoke-venv
|
||||
/tmp/smoke-venv/bin/python -m pip install --upgrade pip
|
||||
/tmp/smoke-venv/bin/python -m pip install /tmp/wifi_densepose-1.99.0-py3-none-any.whl
|
||||
cd /tmp # away from the repo root's stray wifi_densepose/
|
||||
/tmp/smoke-venv/bin/python -c "import importlib.util as u; s = u.find_spec('wifi_densepose'); print('Resolved to:', s.origin); print('--- file content ---'); print(open(s.origin).read())"
|
||||
set +e
|
||||
/tmp/smoke-venv/bin/python -c "import wifi_densepose" 2> import-output.txt
|
||||
rc=$?
|
||||
set -e
|
||||
if [ "$rc" -eq 0 ]; then
|
||||
echo "ERROR: tombstone import succeeded — should have raised ImportError"
|
||||
exit 1
|
||||
fi
|
||||
if ! grep -q "github.com/ruvnet/RuView" import-output.txt; then
|
||||
echo "ERROR: tombstone ImportError missing migration URL"
|
||||
cat import-output.txt
|
||||
exit 1
|
||||
fi
|
||||
echo "Tombstone wheel correctly raises ImportError with migration URL."
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: tombstone
|
||||
path: tombstone-dist/*
|
||||
if-no-files-found: error
|
||||
|
||||
# ────────────────────────────────────────────────────────────────
|
||||
# Publish — gated by manual dispatch OR by the tag form
|
||||
# ────────────────────────────────────────────────────────────────
|
||||
|
||||
publish-v2:
|
||||
name: Publish v2 wheels
|
||||
needs: [build-wheels, build-sdist]
|
||||
if: |
|
||||
always() &&
|
||||
needs.build-wheels.result == 'success' &&
|
||||
needs.build-sdist.result == 'success' &&
|
||||
(
|
||||
github.event_name == 'workflow_dispatch' && inputs.target == 'v2-wheels' ||
|
||||
startsWith(github.ref, 'refs/tags/v2.')
|
||||
)
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Gather all artifacts into dist/
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
path: dist-staging
|
||||
- name: Flatten artifacts
|
||||
run: |
|
||||
mkdir -p dist
|
||||
find dist-staging -type f \( -name '*.whl' -o -name '*.tar.gz' \) -exec cp -v {} dist/ \;
|
||||
ls -lh dist/
|
||||
- name: Publish to TestPyPI (dry-run target)
|
||||
if: github.event_name == 'workflow_dispatch' && inputs.publish_to == 'testpypi'
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
repository-url: https://test.pypi.org/legacy/
|
||||
password: ${{ secrets.PYPI_API_TOKEN }}
|
||||
packages-dir: dist
|
||||
skip-existing: true
|
||||
- name: Publish to PyPI
|
||||
if: |
|
||||
startsWith(github.ref, 'refs/tags/v2.') ||
|
||||
(github.event_name == 'workflow_dispatch' && inputs.publish_to == 'pypi')
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
password: ${{ secrets.PYPI_API_TOKEN }}
|
||||
packages-dir: dist
|
||||
|
||||
publish-tombstone:
|
||||
name: Publish v1.99 tombstone
|
||||
needs: [build-tombstone]
|
||||
if: |
|
||||
always() &&
|
||||
needs.build-tombstone.result == 'success' &&
|
||||
(
|
||||
github.event_name == 'workflow_dispatch' && inputs.target == 'v1-99-tombstone' ||
|
||||
startsWith(github.ref, 'refs/tags/v1.99')
|
||||
)
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
name: tombstone
|
||||
path: dist
|
||||
- name: Publish to TestPyPI (dry-run target)
|
||||
if: github.event_name == 'workflow_dispatch' && inputs.publish_to == 'testpypi'
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
repository-url: https://test.pypi.org/legacy/
|
||||
password: ${{ secrets.PYPI_API_TOKEN }}
|
||||
packages-dir: dist
|
||||
skip-existing: true
|
||||
- name: Publish to PyPI
|
||||
if: |
|
||||
startsWith(github.ref, 'refs/tags/v1.99') ||
|
||||
(github.event_name == 'workflow_dispatch' && inputs.publish_to == 'pypi')
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
password: ${{ secrets.PYPI_API_TOKEN }}
|
||||
packages-dir: dist
|
||||
@@ -1,74 +0,0 @@
|
||||
name: Point Cloud Viewer → GitHub Pages
|
||||
|
||||
# Publishes the live 3D point cloud viewer to gh-pages/pointcloud/.
|
||||
# The viewer defaults to a synthetic in-browser demo; users can append
|
||||
# ?backend=<url> or ?backend=auto to point it at a real ruview-pointcloud
|
||||
# server (CORS-permitting host required). See ADR-094.
|
||||
#
|
||||
# Uses keep_files: true to preserve the existing observatory/, pose-fusion/,
|
||||
# nvsim/, and root index.html demos already on gh-pages.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'v2/crates/wifi-densepose-pointcloud/src/viewer.html'
|
||||
- '.github/workflows/pointcloud-pages.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
concurrency:
|
||||
group: pointcloud-pages
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
build-and-deploy:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout main
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Stage viewer for Pages
|
||||
run: |
|
||||
mkdir -p _site/pointcloud
|
||||
cp v2/crates/wifi-densepose-pointcloud/src/viewer.html _site/pointcloud/index.html
|
||||
# Drop a tiny README so direct browsers of the directory get context.
|
||||
cat > _site/pointcloud/README.md <<'EOF'
|
||||
# RuView — Live 3D Point Cloud Viewer
|
||||
|
||||
Hosted at: https://ruvnet.github.io/RuView/pointcloud/
|
||||
|
||||
## Modes
|
||||
|
||||
- Default — synthetic in-browser demo (no backend, no network calls).
|
||||
- `?backend=auto` — fetch from `/api/splats` on the same origin
|
||||
(only works when the viewer is served by `ruview-pointcloud serve`).
|
||||
- `?backend=<url>` — fetch from `<url>/api/splats`. The intended
|
||||
local-ESP32 use is `?backend=http://127.0.0.1:9880`: run
|
||||
`ruview-pointcloud serve --bind 127.0.0.1:9880` on the same
|
||||
machine with your ESP32 streaming CSI to UDP port 3333, then
|
||||
visit the URL above. The local server's CorsLayer permits
|
||||
requests from `https://ruvnet.github.io`, and modern browsers
|
||||
permit HTTPS→127.0.0.1 mixed-content as a trustworthy origin.
|
||||
The "📡 Connect ESP32" button in the viewer prompts for this
|
||||
URL and persists it in localStorage.
|
||||
- `?live=1` — require a live backend; show an offline message instead
|
||||
of falling back to the synthetic demo.
|
||||
|
||||
See ADR-094 for the deployment design.
|
||||
EOF
|
||||
|
||||
- name: Deploy to gh-pages/pointcloud/
|
||||
uses: peaceiris/actions-gh-pages@v4
|
||||
with:
|
||||
github_token: ${{ secrets.GITHUB_TOKEN }}
|
||||
publish_dir: ./_site/pointcloud
|
||||
destination_dir: pointcloud
|
||||
# CRITICAL: preserves observatory/, pose-fusion/, nvsim/, and root
|
||||
# index.html already on gh-pages.
|
||||
keep_files: true
|
||||
commit_message: 'deploy(pointcloud): ${{ github.sha }}'
|
||||
user_name: 'github-actions[bot]'
|
||||
user_email: 'github-actions[bot]@users.noreply.github.com'
|
||||
@@ -1,149 +0,0 @@
|
||||
name: ruview-swarm CI guard
|
||||
|
||||
# Dedicated guard for the ADR-148 drone swarm crate (`v2/crates/ruview-swarm`).
|
||||
# The main ci.yml runs `cargo test --workspace --no-default-features`, which
|
||||
# only exercises ruview-swarm's DEFAULT feature set. This guard additionally:
|
||||
# - tests every feature combination (train / ruflo+itar / full)
|
||||
# - fails on ANY clippy warning in the crate's own code (--no-deps)
|
||||
# - asserts the ITAR + publish guards stay in place (USML Cat VIII(h)(12))
|
||||
# - builds the GPU training binary under the `train` feature
|
||||
#
|
||||
# Path-scoped so it only runs when the crate or this workflow changes.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ main, 'feat/*' ]
|
||||
paths:
|
||||
- 'v2/crates/ruview-swarm/**'
|
||||
- '.github/workflows/ruview-swarm-ci.yml'
|
||||
pull_request:
|
||||
paths:
|
||||
- 'v2/crates/ruview-swarm/**'
|
||||
- '.github/workflows/ruview-swarm-ci.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
env:
|
||||
CARGO_TERM_COLOR: always
|
||||
|
||||
jobs:
|
||||
# ── Feature-matrix tests ─────────────────────────────────────────────────
|
||||
tests:
|
||||
name: tests (${{ matrix.features.label }})
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
features:
|
||||
- { label: 'default', flags: '--no-default-features' }
|
||||
- { label: 'train', flags: '--features train' }
|
||||
- { label: 'ruflo+itar', flags: '--features ruflo,itar-unrestricted' }
|
||||
- { label: 'full+train', flags: '--features full,train' }
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: dtolnay/rust-toolchain@stable
|
||||
- name: Cache cargo
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/registry
|
||||
~/.cargo/git
|
||||
v2/target
|
||||
key: ${{ runner.os }}-ruview-swarm-${{ hashFiles('v2/Cargo.lock') }}
|
||||
restore-keys: ${{ runner.os }}-ruview-swarm-
|
||||
- name: cargo test -p ruview-swarm ${{ matrix.features.flags }}
|
||||
working-directory: v2
|
||||
run: cargo test -p ruview-swarm ${{ matrix.features.flags }} --lib
|
||||
|
||||
# ── Clippy: zero warnings in the crate's own code ────────────────────────
|
||||
clippy:
|
||||
name: clippy (-D warnings, --no-deps)
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
# v2/rust-toolchain.toml pins channel "1.89" with profile "minimal" (no
|
||||
# clippy). dtolnay@stable installs clippy on the floating "stable"
|
||||
# toolchain, but the override makes cargo use the separate "1.89"
|
||||
# toolchain — so `cargo clippy` errors "cargo-clippy is not installed for
|
||||
# 1.89". Install clippy on the pinned toolchain that cargo actually uses.
|
||||
- uses: dtolnay/rust-toolchain@stable
|
||||
with:
|
||||
toolchain: "1.89"
|
||||
components: clippy
|
||||
- name: Cache cargo
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/registry
|
||||
~/.cargo/git
|
||||
v2/target
|
||||
key: ${{ runner.os }}-ruview-swarm-clippy-${{ hashFiles('v2/Cargo.lock') }}
|
||||
restore-keys: ${{ runner.os }}-ruview-swarm-clippy-
|
||||
# --no-deps confines linting to ruview-swarm's own source, so pre-existing
|
||||
# warnings in dependency crates don't gate this PR.
|
||||
- name: clippy (default)
|
||||
working-directory: v2
|
||||
run: cargo clippy -p ruview-swarm --no-default-features --no-deps -- -D warnings
|
||||
- name: clippy (full,train)
|
||||
working-directory: v2
|
||||
run: cargo clippy -p ruview-swarm --features full,train --no-deps -- -D warnings
|
||||
|
||||
# ── Build the GPU training binary (train feature) ────────────────────────
|
||||
train-bin:
|
||||
name: build train_marl bin
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: dtolnay/rust-toolchain@stable
|
||||
- name: Cache cargo
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: |
|
||||
~/.cargo/registry
|
||||
~/.cargo/git
|
||||
v2/target
|
||||
key: ${{ runner.os }}-ruview-swarm-bin-${{ hashFiles('v2/Cargo.lock') }}
|
||||
restore-keys: ${{ runner.os }}-ruview-swarm-bin-
|
||||
- name: cargo build --bin train_marl --features train
|
||||
working-directory: v2
|
||||
run: cargo build -p ruview-swarm --features train --bin train_marl
|
||||
- name: train_marl is excluded from the default build
|
||||
working-directory: v2
|
||||
run: |
|
||||
# The training binary requires the `train` feature; a default `--bins`
|
||||
# build must NOT produce it (keeps default/CI builds light + Candle-free).
|
||||
# Remove any prior artifact first so this checks what the DEFAULT build
|
||||
# produces, not a leftover from the train-feature build above.
|
||||
rm -f target/debug/train_marl
|
||||
cargo build -p ruview-swarm --no-default-features --bins
|
||||
if [ -f target/debug/train_marl ]; then
|
||||
echo "ERROR: train_marl built without the 'train' feature" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "OK: train_marl correctly gated behind the 'train' feature"
|
||||
|
||||
# ── ITAR + publish guards ────────────────────────────────────────────────
|
||||
export-control-guard:
|
||||
name: ITAR / publish guard
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: publish = false is present (no accidental crates.io publish)
|
||||
run: |
|
||||
CARGO=v2/crates/ruview-swarm/Cargo.toml
|
||||
if ! grep -qE '^\s*publish\s*=\s*false' "$CARGO"; then
|
||||
echo "ERROR: ruview-swarm Cargo.toml must keep 'publish = false' until" >&2
|
||||
echo " PR merge + dependency publish + ITAR export sign-off." >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "OK: publish = false present"
|
||||
- name: default feature set does NOT enable itar-unrestricted
|
||||
run: |
|
||||
CARGO=v2/crates/ruview-swarm/Cargo.toml
|
||||
# USML Cat VIII(h)(12): swarming coordination must be opt-in, never default.
|
||||
DEFAULT_LINE=$(grep -E '^\s*default\s*=' "$CARGO" || true)
|
||||
echo "default = $DEFAULT_LINE"
|
||||
if echo "$DEFAULT_LINE" | grep -q 'itar-unrestricted'; then
|
||||
echo "ERROR: 'itar-unrestricted' must NOT be in the default feature set" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "OK: ITAR-gated coordination features are opt-in, not default"
|
||||
@@ -18,27 +18,23 @@ jobs:
|
||||
sast:
|
||||
name: Static Application Security Testing
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true # third-party scanners are flaky / SARIF uploads can 403; don't gate the PR
|
||||
permissions:
|
||||
security-events: write
|
||||
actions: read
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Set up Python
|
||||
continue-on-error: true
|
||||
uses: actions/setup-python@v6
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: 'pip'
|
||||
|
||||
- name: Install dependencies
|
||||
continue-on-error: true
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
@@ -46,38 +42,34 @@ jobs:
|
||||
|
||||
- name: Run Bandit security scan
|
||||
run: |
|
||||
# The Python codebase lives under archive/v1/src (it moved there when
|
||||
# the runtime was rewritten in Rust). Scanning `src/` matched nothing,
|
||||
# so this SAST step was a silent no-op.
|
||||
bandit -r archive/v1/src/ -f sarif -o bandit-results.sarif
|
||||
bandit -r src/ -f sarif -o bandit-results.sarif
|
||||
continue-on-error: true
|
||||
|
||||
- name: Upload Bandit results to GitHub Security
|
||||
continue-on-error: true
|
||||
uses: github/codeql-action/upload-sarif@v3
|
||||
if: always()
|
||||
with:
|
||||
sarif_file: bandit-results.sarif
|
||||
category: bandit
|
||||
|
||||
# Removed the deprecated `returntocorp/semgrep-action@v1` step: it was
|
||||
# redundant (the pip `semgrep --sarif` below is what feeds GitHub Security;
|
||||
# the action only pushed to the Semgrep cloud app via SEMGREP_APP_TOKEN) and
|
||||
# it pulled `returntocorp/semgrep-agent:v1` from Docker Hub on every run,
|
||||
# which intermittently timed out and turned this check red. The pip semgrep
|
||||
# (installed above) needs no Docker pull. The action's `p/docker` +
|
||||
# `p/kubernetes` rulesets are folded into the command below so coverage is
|
||||
# preserved.
|
||||
- name: Run Semgrep + generate SARIF
|
||||
- name: Run Semgrep security scan
|
||||
uses: returntocorp/semgrep-action@v1
|
||||
with:
|
||||
config: >-
|
||||
p/security-audit
|
||||
p/secrets
|
||||
p/python
|
||||
p/docker
|
||||
p/kubernetes
|
||||
env:
|
||||
SEMGREP_APP_TOKEN: ${{ secrets.SEMGREP_APP_TOKEN }}
|
||||
|
||||
- name: Generate Semgrep SARIF
|
||||
run: |
|
||||
semgrep \
|
||||
--config=p/security-audit --config=p/secrets --config=p/python \
|
||||
--config=p/docker --config=p/kubernetes \
|
||||
--sarif --output=semgrep.sarif archive/v1/src/
|
||||
semgrep --config=p/security-audit --config=p/secrets --config=p/python --sarif --output=semgrep.sarif src/
|
||||
continue-on-error: true
|
||||
|
||||
- name: Upload Semgrep results to GitHub Security
|
||||
continue-on-error: true
|
||||
uses: github/codeql-action/upload-sarif@v3
|
||||
if: always()
|
||||
with:
|
||||
@@ -88,25 +80,21 @@ jobs:
|
||||
dependency-scan:
|
||||
name: Dependency Vulnerability Scan
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true # third-party scanners are flaky / SARIF uploads can 403; don't gate the PR
|
||||
permissions:
|
||||
security-events: write
|
||||
actions: read
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
continue-on-error: true
|
||||
uses: actions/setup-python@v6
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: 'pip'
|
||||
|
||||
- name: Install dependencies
|
||||
continue-on-error: true
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
@@ -123,7 +111,7 @@ jobs:
|
||||
continue-on-error: true
|
||||
|
||||
- name: Run Snyk vulnerability scan
|
||||
uses: snyk/actions/python@9adf32b1121593767fc3c057af55b55db032dc04 # v1.0.0
|
||||
uses: snyk/actions/python@master
|
||||
env:
|
||||
SNYK_TOKEN: ${{ secrets.SNYK_TOKEN }}
|
||||
with:
|
||||
@@ -131,7 +119,6 @@ jobs:
|
||||
continue-on-error: true
|
||||
|
||||
- name: Upload Snyk results to GitHub Security
|
||||
continue-on-error: true
|
||||
uses: github/codeql-action/upload-sarif@v3
|
||||
if: always()
|
||||
with:
|
||||
@@ -139,7 +126,6 @@ jobs:
|
||||
category: snyk
|
||||
|
||||
- name: Upload vulnerability reports
|
||||
continue-on-error: true
|
||||
uses: actions/upload-artifact@v4
|
||||
if: always()
|
||||
with:
|
||||
@@ -153,7 +139,6 @@ jobs:
|
||||
container-scan:
|
||||
name: Container Security Scan
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true # third-party scanners are flaky / SARIF uploads can 403; don't gate the PR
|
||||
needs: []
|
||||
if: github.event_name == 'push' || github.event_name == 'schedule'
|
||||
permissions:
|
||||
@@ -162,16 +147,13 @@ jobs:
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
continue-on-error: true
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Build Docker image for scanning
|
||||
continue-on-error: true
|
||||
uses: docker/build-push-action@v7
|
||||
uses: docker/build-push-action@v5
|
||||
with:
|
||||
context: .
|
||||
target: production
|
||||
@@ -181,15 +163,13 @@ jobs:
|
||||
cache-to: type=gha,mode=max
|
||||
|
||||
- name: Run Trivy vulnerability scanner
|
||||
continue-on-error: true
|
||||
uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
|
||||
uses: aquasecurity/trivy-action@master
|
||||
with:
|
||||
image-ref: 'wifi-densepose:scan'
|
||||
format: 'sarif'
|
||||
output: 'trivy-results.sarif'
|
||||
|
||||
- name: Upload Trivy results to GitHub Security
|
||||
continue-on-error: true
|
||||
uses: github/codeql-action/upload-sarif@v3
|
||||
if: always()
|
||||
with:
|
||||
@@ -197,8 +177,7 @@ jobs:
|
||||
category: trivy
|
||||
|
||||
- name: Run Grype vulnerability scanner
|
||||
continue-on-error: true
|
||||
uses: anchore/scan-action@v7
|
||||
uses: anchore/scan-action@v3
|
||||
id: grype-scan
|
||||
with:
|
||||
image: 'wifi-densepose:scan'
|
||||
@@ -207,7 +186,6 @@ jobs:
|
||||
output-format: sarif
|
||||
|
||||
- name: Upload Grype results to GitHub Security
|
||||
continue-on-error: true
|
||||
uses: github/codeql-action/upload-sarif@v3
|
||||
if: always()
|
||||
with:
|
||||
@@ -215,7 +193,6 @@ jobs:
|
||||
category: grype
|
||||
|
||||
- name: Run Docker Scout
|
||||
continue-on-error: true
|
||||
uses: docker/scout-action@v1
|
||||
if: always()
|
||||
with:
|
||||
@@ -225,7 +202,6 @@ jobs:
|
||||
summary: true
|
||||
|
||||
- name: Upload Docker Scout results
|
||||
continue-on-error: true
|
||||
uses: github/codeql-action/upload-sarif@v3
|
||||
if: always()
|
||||
with:
|
||||
@@ -236,19 +212,16 @@ jobs:
|
||||
iac-scan:
|
||||
name: Infrastructure Security Scan
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true # third-party scanners are flaky / SARIF uploads can 403; don't gate the PR
|
||||
permissions:
|
||||
security-events: write
|
||||
actions: read
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Run Checkov IaC scan
|
||||
continue-on-error: true
|
||||
uses: bridgecrewio/checkov-action@99bb2caf247dfd9f03cf984373bc6043d4e32ebf # v12.1347.0
|
||||
uses: bridgecrewio/checkov-action@master
|
||||
with:
|
||||
directory: .
|
||||
framework: kubernetes,dockerfile,terraform,ansible
|
||||
@@ -258,7 +231,6 @@ jobs:
|
||||
soft_fail: true
|
||||
|
||||
- name: Upload Checkov results to GitHub Security
|
||||
continue-on-error: true
|
||||
uses: github/codeql-action/upload-sarif@v3
|
||||
if: always()
|
||||
with:
|
||||
@@ -266,8 +238,7 @@ jobs:
|
||||
category: checkov
|
||||
|
||||
- name: Run Terrascan IaC scan
|
||||
continue-on-error: true
|
||||
uses: tenable/terrascan-action@3a6e87da8e244513bd77b631e624552643f794c6 # v1.4.1
|
||||
uses: tenable/terrascan-action@main
|
||||
with:
|
||||
iac_type: 'k8s'
|
||||
iac_version: 'v1'
|
||||
@@ -276,8 +247,7 @@ jobs:
|
||||
sarif_upload: true
|
||||
|
||||
- name: Run KICS IaC scan
|
||||
continue-on-error: true
|
||||
uses: checkmarx/kics-github-action@05aa5eb70eede1355220f4ca5238d96b397e30a6 # v2.1.20
|
||||
uses: checkmarx/kics-github-action@master
|
||||
with:
|
||||
path: '.'
|
||||
output_path: kics-results
|
||||
@@ -286,7 +256,6 @@ jobs:
|
||||
exclude_queries: 'a7ef1e8c-fbf8-4ac1-b8c7-2c3b0e6c6c6c'
|
||||
|
||||
- name: Upload KICS results to GitHub Security
|
||||
continue-on-error: true
|
||||
uses: github/codeql-action/upload-sarif@v3
|
||||
if: always()
|
||||
with:
|
||||
@@ -297,21 +266,18 @@ jobs:
|
||||
secret-scan:
|
||||
name: Secret Scanning
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true # third-party scanners are flaky / SARIF uploads can 403; don't gate the PR
|
||||
permissions:
|
||||
security-events: write
|
||||
actions: read
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Run TruffleHog secret scan
|
||||
continue-on-error: true
|
||||
uses: trufflesecurity/trufflehog@17456f8c7d042d8c82c9a8ca9e937231f9f42e26 # v3.95.2
|
||||
uses: trufflesecurity/trufflehog@main
|
||||
with:
|
||||
path: ./
|
||||
base: main
|
||||
@@ -319,7 +285,6 @@ jobs:
|
||||
extra_args: --debug --only-verified
|
||||
|
||||
- name: Run GitLeaks secret scan
|
||||
continue-on-error: true
|
||||
uses: gitleaks/gitleaks-action@v2
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
@@ -336,34 +301,28 @@ jobs:
|
||||
license-scan:
|
||||
name: License Compliance Scan
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true # third-party scanners are flaky / SARIF uploads can 403; don't gate the PR
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
continue-on-error: true
|
||||
uses: actions/setup-python@v6
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: 'pip'
|
||||
|
||||
- name: Install dependencies
|
||||
continue-on-error: true
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
pip install pip-licenses licensecheck
|
||||
|
||||
- name: Run license check
|
||||
continue-on-error: true
|
||||
run: |
|
||||
pip-licenses --format=json --output-file=licenses.json
|
||||
licensecheck --zero
|
||||
|
||||
- name: Upload license report
|
||||
continue-on-error: true
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: license-report
|
||||
@@ -373,14 +332,11 @@ jobs:
|
||||
compliance-check:
|
||||
name: Security Policy Compliance
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true # third-party scanners are flaky / SARIF uploads can 403; don't gate the PR
|
||||
steps:
|
||||
- name: Checkout code
|
||||
continue-on-error: true
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Check security policy files
|
||||
continue-on-error: true
|
||||
run: |
|
||||
# Check for required security files
|
||||
files=("SECURITY.md" ".github/SECURITY.md" "docs/SECURITY.md")
|
||||
@@ -398,13 +354,11 @@ jobs:
|
||||
fi
|
||||
|
||||
- name: Check for security headers in code
|
||||
continue-on-error: true
|
||||
run: |
|
||||
# Check for security-related configurations
|
||||
grep -r "X-Frame-Options\|X-Content-Type-Options\|X-XSS-Protection\|Content-Security-Policy" src/ || echo "⚠️ Consider adding security headers"
|
||||
|
||||
- name: Validate Kubernetes security contexts
|
||||
continue-on-error: true
|
||||
run: |
|
||||
# Check for security contexts in Kubernetes manifests
|
||||
if [[ -d "k8s" ]]; then
|
||||
@@ -421,21 +375,13 @@ jobs:
|
||||
security-report:
|
||||
name: Security Report
|
||||
runs-on: ubuntu-latest
|
||||
continue-on-error: true # third-party scanners are flaky / SARIF uploads can 403; don't gate the PR
|
||||
needs: [sast, dependency-scan, container-scan, iac-scan, secret-scan, license-scan, compliance-check]
|
||||
if: always()
|
||||
# Promote secret to env-scope so the gating `if:` on the Slack-notify
|
||||
# step below is parseable (GitHub Actions rejects `secrets.X` in
|
||||
# step-level `if:` expressions).
|
||||
env:
|
||||
SECURITY_SLACK_WEBHOOK_URL: ${{ secrets.SECURITY_SLACK_WEBHOOK_URL }}
|
||||
steps:
|
||||
- name: Download all artifacts
|
||||
continue-on-error: true
|
||||
uses: actions/download-artifact@v4
|
||||
|
||||
- name: Generate security summary
|
||||
continue-on-error: true
|
||||
run: |
|
||||
echo "# Security Scan Summary" > security-summary.md
|
||||
echo "" >> security-summary.md
|
||||
@@ -451,18 +397,13 @@ jobs:
|
||||
echo "Generated on: $(date)" >> security-summary.md
|
||||
|
||||
- name: Upload security summary
|
||||
continue-on-error: true
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: security-summary
|
||||
path: security-summary.md
|
||||
|
||||
# GitHub Actions does not allow `secrets.X` in step-level `if:` —
|
||||
# use env.X instead. Inherits SECURITY_SLACK_WEBHOOK_URL from the
|
||||
# job-level env block (added below).
|
||||
- name: Notify security team on critical findings
|
||||
continue-on-error: true
|
||||
if: ${{ env.SECURITY_SLACK_WEBHOOK_URL != '' && (needs.sast.result == 'failure' || needs.dependency-scan.result == 'failure' || needs.container-scan.result == 'failure') }}
|
||||
if: ${{ secrets.SECURITY_SLACK_WEBHOOK_URL != '' && (needs.sast.result == 'failure' || needs.dependency-scan.result == 'failure' || needs.container-scan.result == 'failure') }}
|
||||
uses: 8398a7/action-slack@v3
|
||||
with:
|
||||
status: failure
|
||||
@@ -474,10 +415,9 @@ jobs:
|
||||
Workflow: ${{ github.workflow }}
|
||||
Please review the security scan results immediately.
|
||||
env:
|
||||
SLACK_WEBHOOK_URL: ${{ env.SECURITY_SLACK_WEBHOOK_URL }}
|
||||
SLACK_WEBHOOK_URL: ${{ secrets.SECURITY_SLACK_WEBHOOK_URL }}
|
||||
|
||||
- name: Create security issue on critical findings
|
||||
continue-on-error: true
|
||||
if: needs.sast.result == 'failure' || needs.dependency-scan.result == 'failure'
|
||||
uses: actions/github-script@v6
|
||||
with:
|
||||
|
||||
@@ -1,181 +0,0 @@
|
||||
name: wifi-densepose sensing-server → Docker Hub + ghcr.io
|
||||
|
||||
# Build + publish the `wifi-densepose` sensing-server image to both Docker Hub
|
||||
# (`ruvnet/wifi-densepose`) and ghcr.io (`ghcr.io/ruvnet/wifi-densepose`) on:
|
||||
# - push to main affecting the Dockerfile, the server crate, the UI assets,
|
||||
# or this workflow itself,
|
||||
# - tag push matching v* (release builds),
|
||||
# - manual workflow_dispatch.
|
||||
#
|
||||
# Closes #520 and #514: the stale `:latest` is rebuilt and pushed automatically
|
||||
# whenever the surface that produces it changes, and the Dockerfile fails the
|
||||
# build if the observatory/pose-fusion UI assets ever go missing again.
|
||||
#
|
||||
# Secrets:
|
||||
# DOCKERHUB_USERNAME — `ruvnet` (Docker Hub login name)
|
||||
# DOCKERHUB_TOKEN — Docker Hub access token with read/write/delete scope
|
||||
# (ghcr.io uses the workflow's GITHUB_TOKEN — no secret needed.)
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'docker/Dockerfile.rust'
|
||||
- 'docker/docker-entrypoint.sh'
|
||||
- 'v2/crates/wifi-densepose-sensing-server/**'
|
||||
- 'v2/crates/wifi-densepose-signal/**'
|
||||
- 'v2/crates/wifi-densepose-vitals/**'
|
||||
- 'v2/crates/wifi-densepose-wifiscan/**'
|
||||
- 'v2/crates/wifi-densepose-bfld/**'
|
||||
- 'v2/crates/cog-ha-matter/**'
|
||||
- 'v2/Cargo.toml'
|
||||
- 'v2/Cargo.lock'
|
||||
- 'ui/**'
|
||||
- '.github/workflows/sensing-server-docker.yml'
|
||||
tags: ['v*']
|
||||
workflow_dispatch: {}
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
packages: write
|
||||
|
||||
concurrency:
|
||||
group: sensing-server-docker-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
build-and-publish:
|
||||
name: build · push · smoke-test
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: recursive
|
||||
|
||||
# QEMU is required so the amd64 GitHub runner can cross-build the
|
||||
# linux/arm64 layer below (Dockerfile.rust is arch-agnostic — no `--target`
|
||||
# flag — so buildx + QEMU is all that's needed; arm64 builds are emulated
|
||||
# by the runner, not built on a separate arm64 host).
|
||||
- uses: docker/setup-qemu-action@v3
|
||||
|
||||
- uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Log in to Docker Hub
|
||||
# Bypassing docker/login-action@v3: the action kept emitting
|
||||
# "malformed HTTP Authorization header" against a known-good
|
||||
# dckr_pat_* token (verified by direct curl against the Hub API).
|
||||
# `docker login --password-stdin` is the documented credential
|
||||
# path and avoids whatever encoding step the action injects.
|
||||
env:
|
||||
DH_USER: ${{ secrets.DOCKERHUB_USERNAME }}
|
||||
DH_TOKEN: ${{ secrets.DOCKERHUB_TOKEN }}
|
||||
run: |
|
||||
printf '%s' "$DH_TOKEN" | docker login docker.io -u "$DH_USER" --password-stdin
|
||||
|
||||
- name: Log in to ghcr.io
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ghcr.io
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Compute tags
|
||||
id: meta
|
||||
uses: docker/metadata-action@v6
|
||||
with:
|
||||
images: |
|
||||
docker.io/ruvnet/wifi-densepose
|
||||
ghcr.io/ruvnet/wifi-densepose
|
||||
tags: |
|
||||
type=ref,event=branch
|
||||
type=ref,event=tag
|
||||
type=sha,format=short
|
||||
type=raw,value=latest,enable={{is_default_branch}}
|
||||
|
||||
- name: Build + push
|
||||
id: build
|
||||
uses: docker/build-push-action@v7
|
||||
with:
|
||||
context: .
|
||||
file: docker/Dockerfile.rust
|
||||
push: true
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
# README badge advertises `amd64 + arm64`, and #547 promised multi-arch
|
||||
# as part of the docker publish refresh; arm64 was never actually wired
|
||||
# in, so Apple Silicon Macs hit `no matching manifest for linux/arm64/v8`
|
||||
# on `docker pull ruvnet/wifi-densepose:latest` (#136, #625). Build both.
|
||||
platforms: linux/amd64,linux/arm64
|
||||
|
||||
# ---------------------------------------------------------------------
|
||||
# Smoke-test the freshly-pushed image:
|
||||
# 1. UI assets that closed #520 are inside `/app/ui` (the Dockerfile's
|
||||
# RUN guard catches missing ones at build time, this re-checks the
|
||||
# pushed artifact post-hoc as belt-and-braces).
|
||||
# 2. /health is up.
|
||||
# 3. /api/v1/info returns 200 with no auth (LAN-mode default).
|
||||
# 4. With RUVIEW_API_TOKEN set, /api/v1/info returns 401 without a
|
||||
# Bearer header, 200 with the correct one (the #443 auth middleware).
|
||||
# ---------------------------------------------------------------------
|
||||
- name: Smoke-test image assets + LAN-mode HTTP
|
||||
run: |
|
||||
set -euo pipefail
|
||||
IMAGE="ghcr.io/ruvnet/wifi-densepose:sha-${GITHUB_SHA::7}"
|
||||
docker pull "$IMAGE"
|
||||
docker run --rm "$IMAGE" sh -c \
|
||||
'ls /app/ui/observatory.html /app/ui/pose-fusion.html /app/ui/index.html /app/ui/viz.html >/dev/null'
|
||||
docker run --rm "$IMAGE" sh -c 'ls -d /app/ui/observatory /app/ui/pose-fusion >/dev/null'
|
||||
|
||||
docker run -d --name sm -p 3000:3000 -e CSI_SOURCE=simulated "$IMAGE"
|
||||
# Wait up to 30 s for /health.
|
||||
for _ in $(seq 1 30); do
|
||||
if curl -fsS http://127.0.0.1:3000/health >/dev/null 2>&1; then break; fi
|
||||
sleep 1
|
||||
done
|
||||
curl -fsS http://127.0.0.1:3000/health
|
||||
curl -fsS http://127.0.0.1:3000/api/v1/info >/dev/null
|
||||
curl -fsS http://127.0.0.1:3000/ui/observatory.html >/dev/null
|
||||
curl -fsS http://127.0.0.1:3000/ui/pose-fusion.html >/dev/null
|
||||
docker stop sm
|
||||
|
||||
- name: Smoke-test the bearer-token auth path
|
||||
run: |
|
||||
set -euo pipefail
|
||||
IMAGE="ghcr.io/ruvnet/wifi-densepose:sha-${GITHUB_SHA::7}"
|
||||
docker run -d --name auth \
|
||||
-p 3000:3000 \
|
||||
-e CSI_SOURCE=simulated \
|
||||
-e RUVIEW_API_TOKEN=smoke-test-token-do-not-use \
|
||||
"$IMAGE"
|
||||
for _ in $(seq 1 30); do
|
||||
if curl -fsS http://127.0.0.1:3000/health >/dev/null 2>&1; then break; fi
|
||||
sleep 1
|
||||
done
|
||||
# /health stays unauthenticated.
|
||||
curl -fsS http://127.0.0.1:3000/health >/dev/null
|
||||
# /api/v1/info without a bearer → 401.
|
||||
code=$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:3000/api/v1/info)
|
||||
test "$code" = "401" || { echo "expected 401, got $code"; exit 1; }
|
||||
# Wrong bearer → 401.
|
||||
code=$(curl -s -o /dev/null -w '%{http_code}' -H 'Authorization: Bearer wrong' http://127.0.0.1:3000/api/v1/info)
|
||||
test "$code" = "401" || { echo "expected 401 (wrong token), got $code"; exit 1; }
|
||||
# Correct bearer → 200.
|
||||
curl -fsS -H 'Authorization: Bearer smoke-test-token-do-not-use' http://127.0.0.1:3000/api/v1/info >/dev/null
|
||||
docker stop auth
|
||||
|
||||
- name: Summary
|
||||
if: always()
|
||||
run: |
|
||||
{
|
||||
echo "## sensing-server image published"
|
||||
echo
|
||||
echo "Tags:"
|
||||
echo '```'
|
||||
echo "${{ steps.meta.outputs.tags }}"
|
||||
echo '```'
|
||||
echo
|
||||
echo "Closes #520 (missing observatory/pose-fusion UI assets) and #514 (stale `:latest` for the v0.6+ packet format)."
|
||||
echo "The Dockerfile fails the build if those UI assets ever disappear again, and this workflow rebuilds + pushes automatically on every change to the surface."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
@@ -1,70 +0,0 @@
|
||||
name: three.js demos → GitHub Pages
|
||||
|
||||
# Publishes the ADR-097 three.js demos under gh-pages/three.js/.
|
||||
# Uses keep_files: true so the existing observatory/, pose-fusion/,
|
||||
# pointcloud/, nvsim/, and root index.html demos are preserved.
|
||||
#
|
||||
# Demos 04 and 05 require a Mixamo "X Bot.fbx" placed in assets/.
|
||||
# That file is intentionally gitignored (license boundary), so this
|
||||
# workflow does NOT ship it. Demos 01-03 work standalone; the index
|
||||
# page documents the FBX requirement honestly.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'examples/three.js/**'
|
||||
- '.github/workflows/threejs-pages.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
concurrency:
|
||||
group: threejs-pages
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
build-and-deploy:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout main
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Stage demos for Pages
|
||||
run: |
|
||||
mkdir -p _site/three.js
|
||||
# Copy everything except the local Python server (CI doesn't need it)
|
||||
# and any stray scratch screenshots.
|
||||
cp -r examples/three.js/demos _site/three.js/demos
|
||||
cp -r examples/three.js/screenshots _site/three.js/screenshots
|
||||
cp examples/three.js/README.md _site/three.js/README.md
|
||||
# An index.html that lists the 5 demos with the FBX caveat.
|
||||
cp examples/three.js/index.html _site/three.js/index.html
|
||||
# Mixamo FBX is gitignored — assets dir won't exist in CI.
|
||||
# Drop an empty placeholder so the relative path 'assets/' resolves
|
||||
# to a directory listing (404 on missing file) instead of an opaque
|
||||
# network error. Browsers showing the 404 path makes the failure
|
||||
# visible to anyone trying demos 04/05 without their own FBX.
|
||||
mkdir -p _site/three.js/assets
|
||||
cat > _site/three.js/assets/README.txt <<'EOF'
|
||||
The Mixamo "X Bot.fbx" required by demos 04-skinned-fbx.html and
|
||||
05-skinned-realtime.html is intentionally not redistributed here.
|
||||
|
||||
Download your own from https://mixamo.com (FBX Binary, T-Pose,
|
||||
Without Skin) and place it here as "X Bot.fbx" if you want to
|
||||
run those demos locally. See examples/three.js/README.md in the
|
||||
repo for context.
|
||||
EOF
|
||||
echo "Staged contents:"
|
||||
ls -R _site/three.js/ | head -30
|
||||
|
||||
- name: Deploy to GitHub Pages
|
||||
uses: peaceiris/actions-gh-pages@v3
|
||||
with:
|
||||
github_token: ${{ secrets.GITHUB_TOKEN }}
|
||||
publish_dir: _site
|
||||
# Critical: preserve observatory/, pose-fusion/, pointcloud/, nvsim/
|
||||
# and the root index.html already on gh-pages.
|
||||
keep_files: true
|
||||
commit_message: 'three.js demos: ${{ github.event.head_commit.message }}'
|
||||
@@ -19,24 +19,8 @@ jobs:
|
||||
fetch-depth: 0
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
# Identity must be set BEFORE any operation that can create a commit.
|
||||
# `git submodule update --remote --merge` used to fail here with
|
||||
# "Committer identity unknown" because the merge inside vendor/ruvector
|
||||
# needs an author when the pinned commit isn't a fast-forward of upstream.
|
||||
- name: Configure git identity
|
||||
run: |
|
||||
git config --global user.name "github-actions[bot]"
|
||||
git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
|
||||
|
||||
# Use a plain `--remote` checkout (detached HEAD at each submodule's
|
||||
# configured `branch` tip from .gitmodules) rather than `--merge`. We only
|
||||
# want to bump the superproject's gitlink to the latest upstream commit;
|
||||
# there's no reason to create merge commits inside the vendored repos, and
|
||||
# `--merge` breaks whenever the current pin has diverged from that branch.
|
||||
- name: Update submodules to latest tracked branch
|
||||
run: |
|
||||
git submodule sync --recursive
|
||||
git submodule update --remote --recursive
|
||||
- name: Update submodules to latest main
|
||||
run: git submodule update --remote --merge
|
||||
|
||||
- name: Check for changes
|
||||
id: check
|
||||
@@ -45,22 +29,21 @@ jobs:
|
||||
echo "changed=false" >> "$GITHUB_OUTPUT"
|
||||
else
|
||||
echo "changed=true" >> "$GITHUB_OUTPUT"
|
||||
echo "--- submodule pointer changes ---"
|
||||
git submodule status --recursive || true
|
||||
git diff --submodule=log -- vendor/ || true
|
||||
fi
|
||||
|
||||
- name: Create PR with updates
|
||||
if: steps.check.outputs.changed == 'true'
|
||||
run: |
|
||||
git config user.name "github-actions[bot]"
|
||||
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
|
||||
BRANCH="chore/update-submodules-$(date +%Y%m%d-%H%M%S)"
|
||||
git checkout -b "$BRANCH"
|
||||
git add vendor/
|
||||
git commit -m "chore: update vendor submodules to latest upstream"
|
||||
git commit -m "chore: update vendor submodules to latest main"
|
||||
git push origin "$BRANCH"
|
||||
gh pr create \
|
||||
--title "chore: update vendor submodules" \
|
||||
--body "Automated submodule update to the latest upstream commit on each submodule's tracked branch (see \`.gitmodules\`). Review the pointer diff before merging." \
|
||||
--body "Automated submodule update to latest upstream main." \
|
||||
--base main \
|
||||
--head "$BRANCH"
|
||||
env:
|
||||
|
||||
@@ -4,18 +4,16 @@ on:
|
||||
push:
|
||||
branches: [ main, master, 'claude/**' ]
|
||||
paths:
|
||||
- 'archive/v1/src/core/**'
|
||||
- 'archive/v1/src/hardware/**'
|
||||
- 'archive/v1/data/proof/**'
|
||||
- 'archive/v1/requirements-lock.txt'
|
||||
- 'v1/src/core/**'
|
||||
- 'v1/src/hardware/**'
|
||||
- 'v1/data/proof/**'
|
||||
- '.github/workflows/verify-pipeline.yml'
|
||||
pull_request:
|
||||
branches: [ main, master ]
|
||||
paths:
|
||||
- 'archive/v1/src/core/**'
|
||||
- 'archive/v1/src/hardware/**'
|
||||
- 'archive/v1/data/proof/**'
|
||||
- 'archive/v1/requirements-lock.txt'
|
||||
- 'v1/src/core/**'
|
||||
- 'v1/src/hardware/**'
|
||||
- 'v1/data/proof/**'
|
||||
- '.github/workflows/verify-pipeline.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
@@ -32,26 +30,26 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v6
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Install pinned dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r archive/v1/requirements-lock.txt
|
||||
pip install -r v1/requirements-lock.txt
|
||||
|
||||
- name: Verify reference signal is reproducible
|
||||
run: |
|
||||
echo "=== Regenerating reference signal ==="
|
||||
python archive/v1/data/proof/generate_reference_signal.py
|
||||
python v1/data/proof/generate_reference_signal.py
|
||||
echo ""
|
||||
echo "=== Checking data file matches committed version ==="
|
||||
# The regenerated file should be identical to the committed one
|
||||
# (We compare the metadata file since data file is large)
|
||||
python -c "
|
||||
import json, hashlib
|
||||
with open('archive/v1/data/proof/sample_csi_meta.json') as f:
|
||||
with open('v1/data/proof/sample_csi_meta.json') as f:
|
||||
meta = json.load(f)
|
||||
assert meta['is_synthetic'] == True, 'Metadata must mark signal as synthetic'
|
||||
assert meta['numpy_seed'] == 42, 'Seed must be 42'
|
||||
@@ -59,18 +57,7 @@ jobs:
|
||||
"
|
||||
|
||||
- name: Run pipeline verification
|
||||
working-directory: archive/v1
|
||||
env:
|
||||
# Pin thread count for scipy.fft / BLAS — multi-threaded reduction
|
||||
# order is otherwise non-deterministic across CI runs (issue #560
|
||||
# follow-up: 9- and 6-decimal quantization were not enough because
|
||||
# the divergence is from threading order, not SIMD reordering).
|
||||
# Single-threaded keeps the proof reproducible at a ~2-3x slowdown.
|
||||
OMP_NUM_THREADS: "1"
|
||||
OPENBLAS_NUM_THREADS: "1"
|
||||
MKL_NUM_THREADS: "1"
|
||||
VECLIB_MAXIMUM_THREADS: "1"
|
||||
NUMEXPR_NUM_THREADS: "1"
|
||||
working-directory: v1
|
||||
run: |
|
||||
echo "=== Running pipeline verification ==="
|
||||
python data/proof/verify.py
|
||||
@@ -78,13 +65,7 @@ jobs:
|
||||
echo "Pipeline verification PASSED."
|
||||
|
||||
- name: Run verification twice to confirm determinism
|
||||
working-directory: archive/v1
|
||||
env:
|
||||
OMP_NUM_THREADS: "1"
|
||||
OPENBLAS_NUM_THREADS: "1"
|
||||
MKL_NUM_THREADS: "1"
|
||||
VECLIB_MAXIMUM_THREADS: "1"
|
||||
NUMEXPR_NUM_THREADS: "1"
|
||||
working-directory: v1
|
||||
run: |
|
||||
echo "=== Second run for determinism confirmation ==="
|
||||
python data/proof/verify.py
|
||||
@@ -95,7 +76,7 @@ jobs:
|
||||
echo "=== Scanning for unseeded np.random usage in production code ==="
|
||||
# Search for np.random calls without a seed in production code
|
||||
# Exclude test files, proof data generators, and known parser placeholders
|
||||
VIOLATIONS=$(grep -rn "np\.random\." archive/v1/src/ \
|
||||
VIOLATIONS=$(grep -rn "np\.random\." v1/src/ \
|
||||
--include="*.py" \
|
||||
--exclude-dir="__pycache__" \
|
||||
| grep -v "np\.random\.RandomState" \
|
||||
|
||||
+1
-28
@@ -13,9 +13,6 @@ firmware/esp32-csi-node/managed_components/
|
||||
firmware/esp32-csi-node/dependencies.lock
|
||||
firmware/esp32-csi-node/sdkconfig.defaults.bak
|
||||
|
||||
# ESP-IDF set-target backup (local only)
|
||||
firmware/esp32-hello-world/sdkconfig.old
|
||||
|
||||
# Claude Flow swarm runtime state
|
||||
.swarm/
|
||||
|
||||
@@ -26,14 +23,6 @@ rust-port/wifi-densepose-rs/data/recordings/
|
||||
nvs.bin
|
||||
nvs_config.csv
|
||||
nvs_provision.bin
|
||||
firmware/esp32-csi-node/nvs_seed.csv
|
||||
firmware/esp32-csi-node/nvs_seed.bin
|
||||
firmware/esp32-csi-node/nvs_config.bin
|
||||
firmware/esp32-csi-node/nvs_wifi.bin
|
||||
firmware/esp32-csi-node/nvs.bin
|
||||
# Catch any other NVS binaries/CSVs with credentials
|
||||
**/nvs_*.bin
|
||||
**/nvs_*.csv
|
||||
|
||||
# Working artifacts that should not land in root
|
||||
/*.wasm
|
||||
@@ -251,20 +240,4 @@ v1/src/sensing/mac_wifi
|
||||
**/node_modules/
|
||||
|
||||
# Local build scripts
|
||||
firmware/esp32-csi-node/build_firmware.batdata/
|
||||
models/
|
||||
demo_pointcloud.ply
|
||||
demo_splats.json
|
||||
|
||||
# rvCSI napi-rs addon — generated by `napi build` (do not commit)
|
||||
v2/crates/rvcsi-node/*.node
|
||||
v2/crates/rvcsi-node/binding.js
|
||||
v2/crates/rvcsi-node/binding.d.ts
|
||||
v2/crates/rvcsi-node/npm/
|
||||
|
||||
# AetherArena private optimization staging — never published until reviewed
|
||||
aether-arena/staging/
|
||||
|
||||
# MM-Fi benchmark dataset archives — large data, fetch separately, never commit
|
||||
assets/MM-Fi/E0*.zip
|
||||
assets/MM-Fi/*.zip
|
||||
firmware/esp32-csi-node/build_firmware.bat
|
||||
@@ -10,7 +10,3 @@
|
||||
path = vendor/sublinear-time-solver
|
||||
url = https://github.com/ruvnet/sublinear-time-solver
|
||||
branch = main
|
||||
[submodule "vendor/rvcsi"]
|
||||
path = vendor/rvcsi
|
||||
url = https://github.com/ruvnet/rvcsi
|
||||
branch = main
|
||||
|
||||
+2
-563
@@ -5,567 +5,6 @@ All notable changes to this project will be documented in this file.
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
||||
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Changed
|
||||
- **Mesh partition risk now demotes the privacy class and is witnessed (ADR-032).** The dynamic min-cut guard's `at_risk` signal was advisory-only (it fed the recalibration advisor). It now also contributes to the ADR-141 privacy demotion alongside fusion- and array-level contradictions: a mesh close to partitioning makes the fused belief less trustworthy, so the cycle emits at a more restricted class (monotonic — information only removed). Because `effective_class` feeds the BLAKE3 witness, a fragmenting array now shifts the witness — partition risk is auditable, not just logged. The mesh computation moved ahead of the demotion step in `process_cycle`; new `mesh_guard_mut()` exposes risk-threshold tuning. Test proves a forced-risk 3-node cycle demotes PrivateHome Anonymous→Restricted and shifts the witness vs a clean *same-topology* baseline (the only delta between the two cycles is the forced risk).
|
||||
|
||||
### Added
|
||||
- **ADR-152 WiFi-Pose SOTA 2026 intake — verified external benchmark + four Rust integrations.** A 22-source adversarially-verified survey of the 2025–2026 WiFi-sensing SOTA, with every adopted number reproduced or graded before integration:
|
||||
- **WiFlow-STD (DY2434) reproduction (`benchmarks/wiflow-std/`)** — the external "97.25% PCK@20, 2.23M params" claim audited end-to-end: the **shipped checkpoint is REFUTED** (0.08% PCK@20 — wrong keypoint normalization, predates the published code), the released code does not run as published (6 documented defects, incl. an import that fails and an unreachable test phase), and the released dataset's final 13 files are corrupted (9,072 windows of NaN + float32-max garbage that NaN-poisons fp16 BatchNorm training). After repairing both, retraining with upstream defaults on an RTX 5080 reproduced **96.09% PCK@20 (full test) / 96.61% (corruption-free)** — claims graded MEASURED-EQUIVALENT; params (2,225,042) and FLOPs (~0.055 G) verified exactly. Full forensics in `benchmarks/wiflow-std/RESULTS.md`.
|
||||
- **`GeometryEmbedding` (ADR-152 §2.1.2, `wifi-densepose-calibration`)** — 32-slot permutation-invariant, NaN-proof featurization of the §2.1.1 `NodeGeometry` records (centroid/spread, measured-first pairwise distances, circular azimuth stats, covariance-eigenvalue geometric diversity, per-node flags), schema-versioned for the ADR-151 P6 LoRA heads; derived `SpecialistBank::geometry_embedding()` accessor. The PerceptAlign "coordinate overfitting" defense, transplanted to per-room banks.
|
||||
- **MAE pretraining recipe (ADR-152 §2.3, `wifi-densepose-train/src/mae.rs`)** — `MaePretrainConfig` pinning the UNSW-measured recipe (80% masking, (30,3) patches) with pure-Rust patchify/random-mask (exact counts, seed-deterministic, error-not-truncate divisibility, NaN rejection), property-tested; the consumption seam for the future ADR-150 ViT-Small encoder.
|
||||
- **`WiFlowStdModel` Rust port (`wifi-densepose-train/src/wiflow_std/`)** — tch-gated idiomatic port of the verified spatio-temporal-decoupled architecture (grouped causal TCN → asymmetric conv stack → dual axial attention); ungated param formula asserted equal to the reference 2,225,042; 15/17-keypoint variants share weights (enables the ADR-152 §2.2(b) ESP32 fine-tune).
|
||||
- **RuVector vendor sync + §2.6 opportunity survey** — vendor at `a083bd77f`; graded ADOPT/EVALUATE/WATCH table; crates.io bumps applied (mincut/solver 2.0.6, attention 2.1.0, gnn 2.2.0; RUSTSEC #504 audit: no pinned crate affected); top WATCH: unpublished `ruvector-graph-condense` differentiable min-cut for trainable subcarrier grouping.
|
||||
- **ADR-153 IEEE 802.11bf-2025 forward-compatibility protocol model (`wifi-densepose-hardware/src/ieee80211bf/`)** — typed WLAN-sensing procedures (measurement setup/instance/report, SBP, termination) with `SpecProfile` version gates, `SensingCapabilities` negotiation, and **required** `ConsentMode` governance metadata on every setup; deterministic session FSM with rejection/timeout paths; `SensingTransport` seam with `SimTransport` and an `OpportunisticCsiBridge` mapping live ESP32 CSI batches into standardized report shape (a future chipset adapter replaces the bridge without touching RuvSense consumers). Not a certified implementation — simulation-tested protocol surface; OTA binding lands when silicon does. 19 acceptance tests.
|
||||
- **Dynamic min-cut mesh partition guard in the streaming engine (`mesh_guard`).** Maintains a `ruvector-mincut` exact min-cut over the live mesh coupling graph (nodes = sensing nodes, coupling = product of fusion attention weights), surfacing per cycle: the global **cut value** (how close the array is to splitting — a structural measure per-node heuristics miss), the **weak side** (which specific nodes would partition: failure/jamming triage feeding ADR-032 posture), and an **at-risk flag** that counts as a structural event for the drift→recalibration advisor. Surfaced as `TrustedOutput::mesh`. **Measured cost policy** (criterion, 12-node mesh): weights are quantized (1/64; a *nonzero* coupling below one quantum saturates to quantum 1 so quantization never erases a live coupling — without the floor, balanced meshes of ≥ 65 nodes had every ~1/n coupling erased and sat permanently "at risk") and updates change-gated, so the steady-state cycle does zero graph work (~7.3 µs, ~23× cheaper than building); on any real change a full exact rebuild (~171 µs) is used because one `DynamicMinCut` delete+insert measured ~240 µs — the incremental machinery's overhead targets much larger graphs, so rebuild-on-change is the measured optimum at mesh scale (one-edge case −28% after the policy switch). Degenerate cases fail toward risk: a node with zero coupling is reported as already partitioned (cut 0). 9 mesh-guard tests + an engine-level wiring test; full `process_cycle` with the guard: ~33 µs for 4 nodes (50 ms budget).
|
||||
- **Opt-in FFT operator for the CIR ISTA solver (8–14× measured).** Φ is a sub-DFT, so each ISTA mat-vec can run as one length-G FFT (O(G log G)) instead of a dense O(K·G) product. New `CirConfig::fft_operator` (default **false** — the dense path stays the bit-exact witness default; the FFT evaluates the same sums in a different order, so enabling it shifts float results and requires regenerating any pinned witness). `FftOperator` (rustfft, planned once at construction, scratch reused across the ISTA loop) dispatches inside `ista_solve`; warm-start/Lipschitz stay dense at construction. Measured (criterion, same run): ht20 2.22 ms → 265 µs (**8.4×**), ht40 10.26 ms → 717 µs (**14.3×**); the real HE40 grid (K=484, G=1452) scales further. 3 new tests: FFT↔dense matvec equivalence to float tolerance (ht20 + he40 grids), end-to-end dominant-tap agreement on a single-path frame, and all default configs keep FFT off. New `cir_estimate_fft` bench group.
|
||||
- **Per-room adapter provenance + drift→recalibration advisor in the streaming engine.** Closes the trust-chain gap where an ~11 KB per-room LoRA adapter (ADR-150 §3.4) could silently change inference without the witness noticing. `StreamingEngine::set_room_adapter(AdapterInfo)` pins the adapter's content-derived id into provenance `model_version` (`rfenc-v1+adapter:<id>`) — and therefore into the BLAKE3 witness — so swapping or clearing adapter weights always shifts the witness (engine test proves base → adapter → other-adapter → cleared all witness differently, and cleared == base). New `RecalibrationAdvisor` recommends re-running the ADR-135 baseline / refitting the adapter on sustained low fusion coherence (streak threshold, default 60 cycles ≈ 3 s at 20 Hz) or an ADR-142 change-point; surfaced as `TrustedOutput::recalibration_recommended` and recorded on the sensing-server's `EngineBridge` alongside the witness. Bridge plumbing: `EngineBridge::{set_room_adapter, clear_room_adapter}` + live-path test that the adapter id flows into the live witness. *Scope note: this is the deployable provenance/trigger half of the "retrained model" roadmap item — fitting the adapter itself runs in the existing external calibration service (`aether-arena/calibration/`), and a trained RF-encoder checkpoint still does not exist in-tree.*
|
||||
- **RuView beyond-SOTA research series** (`docs/research/ruview-beyond-sota/`, 6 docs) — research-swarm output defining the beyond-SOTA bar and the path to it: system capability audit (role→crate maturity matrix, gap analysis, risk register), web-verified 2026 SOTA landscape per capability axis (incl. ratified IEEE 802.11bf-2025), 8-pillar target architecture on the ADR-136 contract spine (no rewrite), 6-layer benchmark/validation methodology (all 15 criterion bench targets inventoried; ADR-149 statistical protocol), and a determinism-safe optimization roadmap. Includes session validation evidence: 2,797 workspace tests / 0 failed, Python proof PASS (bit-exact), paired pre/post criterion runs.
|
||||
|
||||
### Performance
|
||||
- **CIR estimator warm-start precompute** — the diagonal Tikhonov preconditioner `diag(Φ^H Φ)+λI` and its CSR matrix were rebuilt every frame although they depend only on Φ and λ (fixed at `CirEstimator::new`); now precomputed at construction (`ruvsense/cir.rs`). Bit-identical floats (summation order unchanged, witness chain unaffected). Measured: `cir_estimate/he40` −3.9% (p<0.01), multiband groups −1.2/−1.4%; smaller configs within container noise.
|
||||
- **RF tomography solver hoisting** — ISTA gradient buffer no longer allocated inside the 100-iteration loop, and the Frobenius Lipschitz bound moved from per-`reconstruct` to construction (`ruvsense/tomography.rs`). Bit-identical results.
|
||||
|
||||
### Added
|
||||
- **Falsifiable occupancy benchmark (`wifi-densepose-train::occupancy_bench`).** Makes the presence/person-count "beyond SOTA" claim falsifiable in code instead of aspirational (the unfalsifiability gap from the beyond-SOTA system review). Grades predictions vs ground truth and gates a SOTA claim behind one `claim_allowed` invariant requiring all of: `DataProvenance::Measured` (synthetic/mock is scorable but **never claimable** — anti-mock-contamination per the CLAUDE.md Kconfig-bug lesson), a leak-free `EvalSplit` (refuses any split where a subject *or* environment id appears in both train and test — subject leakage / per-environment overfitting), `n_test ≥ min`, a **non-degenerate test set** (both truth classes represented: present-rate ≥ `min_positive_rate` and ≥ 1 absent sample — an all-absent set plus an always-absent predictor cannot release a claim; vacuous F1 scores 0.0, never 1.0), presence-F1 **bootstrap-CI lower bound** (deterministic seeded splitmix64) clearing the threshold, and count MAE within threshold. The claim string is unreadable except through the gate (`NO_CLAIM` otherwise). What remains is data, not method: a frozen, SHA-pinned, subject/environment-disjoint measured replay set turns the claim into a passing/failing test. 12 tests cover each refusal path, including the point-above/CI-below case (claim withheld on the CI lower bound even when the point estimate clears the threshold).
|
||||
- **Live trust path: sensing-server routes real frames through the governed `StreamingEngine` (parallel governed path with partial output gating).** Previously the live server ran only the *bare* `MultistaticFuser` (fused amplitudes, no trust control plane), while the privacy/provenance/witness engine (ADR-135..146) ran only on synthetic in-test frames — the gap called out in ADR-136 §8 and the beyond-SOTA system review. New `engine_bridge` module drives `StreamingEngine::process_cycle` from the server's live `NodeState` map (reusing the existing `NodeState → MultiBandCsiFrame` conversion), lazily wiring each node as a WorldGraph sensor and bounding belief growth via the retention cap; every *governed belief* carries evidence + model + calibration + privacy decision and a deterministic witness. **Honest scope:** the engine runs alongside (not instead of) the bare fusion path that feeds the live `SensingUpdate`. What its decision gates on the wire today: a cycle emitted at class `Restricted` (base mode or contradiction/mesh-risk demotion) suppresses the per-node raw amplitude vectors from the live publish — the same field mapping `wifi-densepose-bfld`'s privacy gate applies at `Restricted`; gating the remaining derived outputs (person count, classification, signal field) is tracked as a follow-up. Trust state is no longer write-only: the latest witness, effective privacy class, demotion flag, recalibration recommendation, and an engine-error counter are readable on `GET /api/v1/status`, and engine errors are counted + rate-limit logged instead of silently swallowed (`EngineBridge::observe_cycle`). Adds `wifi-densepose-engine/-worldgraph/-bfld/-geo` deps. Bridge tests cover witnessed belief with provenance, determinism, idempotent node registration, retention bound, privacy-mode propagation, trust-state recording, the error-counter path, and Restricted-class raw-output suppression.
|
||||
|
||||
### Fixed
|
||||
- **`wifi-densepose-mat` standalone `--no-default-features` build (101 errors → 0).** `pub mod api` was unconditional while its only dependency, serde, is optional behind the `api` feature — so any build without default features failed with unresolved serde imports (masked in `--workspace` runs by feature unification). The `api` module and its `create_router`/`AppState` re-export are now `#[cfg(feature = "api")]`-gated (with docsrs annotations). All feature combos compile: bare `--no-default-features`, `--no-default-features --features api`, and full default (177 tests pass).
|
||||
- **WorldGraph no longer grows unboundedly under the live loop.** `StreamingEngine::process_cycle` appended one `SemanticState` belief per cycle with no eviction — ~1.7M nodes/day at 20 Hz (identified in `docs/research/ruview-beyond-sota/04-optimization-roadmap.md`). Added `WorldGraph::prune_semantic_states(max)` — deterministic eviction of the oldest beliefs by `(valid_from_unix_ms, id)`, structural nodes (rooms/zones/sensors/anchors/tracks/events) never eligible — and wired it into the engine after each belief append (`StreamingEngine::DEFAULT_SEMANTIC_RETENTION` = 7,200 ≈ 6 min at 20 Hz; tunable via `set_semantic_retention`). The WorldGraph holds *current* beliefs; durable history is the recorder's job, so no audit data is lost. 3 new tests (bounded growth end-to-end, oldest-only eviction, deterministic tie-break).
|
||||
- **ESP32 edge heart rate no longer stuck at ~45 BPM / dropping wildly — #987.** The on-device HR estimator (`edge_processing.c`, `0xC5110002`) reported ~45 BPM regardless of true heart rate (Apple-Watch ground truth 87 BPM read as ~45) and swung frame-to-frame. Two root causes: (1) a hardcoded `sample_rate = 10.0f` that became wrong after #985's self-ping raised the CSI callback rate to a variable ~13–19 Hz — BPM scales as `assumed/actual × true`, so 87 read ~45 and the reading swung as CSI yield fluctuated; (2) the zero-crossing estimator locked onto a breathing harmonic (a 0.25 Hz breathing fundamental puts its 3rd harmonic at ~0.74 Hz ≈ 44 BPM inside the HR band). Fix: measure the real sample rate from inter-frame timestamps (used for BPM conversion + biquad re-tuning on >15% drift); replace the HR zero-crossing with an autocorrelation estimator that rejects breathing harmonics (driven by a robust autocorr breathing period); median-13 smooth the output. Hardware A/B (fixed vs unmodified control board, both `edge_tier=2`): control pegged 40–49 BPM; fixed reaches the true 88–91 BPM (vs 87 GT) and holds a stable physiological value (spread 59→0 for a steady subject). Known limitation: heavy subject motion still degrades the estimate (motion gating is a follow-up).
|
||||
- **Person count no longer leaks up to 10 in heuristic mode — addresses #894.** `field_bridge::occupancy_or_fallback` returned the eigenvalue-based `FieldModel::estimate_occupancy` count **unbounded** (its internal ceiling is 10), while the sibling estimators on the same single-link data — the perturbation-energy fallback right below it and `score_to_person_count` — both cap at 3 ("1-3 for single ESP32"). On noisy / under-calibrated CSI the eigenvalue count inflated, producing the "10 persons reported when 1 present" symptom (seen when `--model` fails to load and the server runs on heuristics). Bounded the eigenvalue path to the shared `MAX_SINGLE_LINK_OCCUPANCY` (3) so every estimator on one link agrees; genuine higher counts come from the multistatic fusion path, not a single-link covariance estimate.
|
||||
- **MQTT multi-node deployments now create one Home-Assistant device per node — closes #898.** After the #872 MQTT wiring landed, the JSON→`VitalsSnapshot` bridge hard-coded a single `node_id` (the MQTT client id) and the publisher used a single `OwnedDiscoveryBuilder`, so every physical node collapsed into one device (`identifiers:["wifi_densepose_wifi-densepose-1"]`), contradicting the "one device per node" docs. The bridge now emits one snapshot per node in the sensing update's `nodes[]` (each with its own `node_id` + RSSI, falling back to a single aggregate snapshot for wifi/simulate sources), and the publisher derives a per-node builder (`OwnedDiscoveryBuilder::for_node`) that publishes discovery + availability lazily on first sight of each `node_id` and routes state to per-node topics — yielding N distinct HA devices with per-node availability/LWT. Unit-tested (distinct nodes → distinct `wifi_densepose_<node>` identifiers); 71 MQTT tests pass.
|
||||
- **Person count no longer pinned to 1 — addresses #803.** The aggregate occupancy reported by the sensing server was derived from `smoothed_person_score`, an EMA-smoothed *activity* score (amplitude variance / motion / spectral energy). That score saturates near a single occupant — one moving person maxes it out — so it cannot discriminate occupancy *count* and stayed clamped at 1 across S3/C6 and the Python/Docker/Rust servers. Meanwhile the count-aware per-node estimates the ESP32 paths already compute (firmware `n_persons`, and the DynamicMinCut `corr_persons`) were stashed in `NodeState::prev_person_count` and then **discarded** by the aggregator (same dead-wiring class as #872). The aggregator now takes `max(activity_count, node_max)` via a unit-tested `aggregate_person_count` helper, so a node positively estimating 2–3 occupants is surfaced instead of overwritten. The fix can only ever *raise* the count when a node reports more people, so the single-occupant case is provably never inflated (regression-guarded by test). **Second half:** the pure-CSI per-node path itself clamped its own estimate — the DynamicMinCut occupancy (`estimate_persons_from_correlation`, 0–3) was mapped to a score via `corr_persons / 3.0`, putting 2 people at 0.667, *just under* the 0.70 up-threshold of `score_to_person_count`, so the per-node count never climbed past 1 (so `node_max` was also stuck at 1 for CSI-only nodes). Replaced it with a threshold-aligned `corr_persons_to_score` mapping (1→0.40, 2→0.74, 3→0.96) whose steady state round-trips back to the same count through the EMA + hysteresis, while still gating transient noise. A convergence test replays the exact EMA loop to prove min-cut=2 now reports 2 (and documents that the old `/3.0` mapping reported 1). Full multi-person accuracy still depends on the underlying estimator quality; this removes the two server-side clamps that masked it. 586 sensing-server tests pass.
|
||||
- **MQTT publisher now actually runs (`--mqtt`) — closes #872.** The `--mqtt*` flags were defined only in `cli::Args` (dead code, referenced nowhere) while the binary parses a *separate* `main::Args` with no mqtt fields, and `main.rs` never started the `mqtt::` publisher — so MQTT/Home-Assistant integration was completely unwired (`--mqtt` errored as an unexpected argument, and even with the Docker image's `--features mqtt` build the publisher never ran). Earlier attempts chased a Docker *rebuild*; the real cause was disconnected *code*. Extracted the flags into a shared `cli::MqttArgs` (`#[command(flatten)]` into both structs), spawn the publisher on `--mqtt`, and bridge the JSON sensing broadcast into the typed `VitalsSnapshot` stream with a defensive `serde_json::Value` mapping. Verified end-to-end against `mosquitto`: 20 HA auto-discovery entities + live state (presence/person-count/…). 577 (default) / 580 (`--features mqtt`) tests pass.
|
||||
- **Mass Casualty triage never reports a survivor with a heartbeat as Deceased (safety) — PR #926.** Both triage paths in `wifi-densepose-mat` — `TriageCalculator::calculate` (`combine_assessments(Absent, None) ⇒ Deceased`) and the detection path `EnsembleClassifier::determine_triage` (`!has_breathing && !has_movement ⇒ Deceased`) — ignored the `heartbeat` field. A survivor with a detectable **pulse** but no sensed breathing/movement (respiratory arrest — the most time-critical *savable* state, Immediate/Red) was therefore reported **Deceased (Black)** and deprioritized for rescue. The domain path was in fact only reachable *because* a heartbeat made `has_vitals()` true, so every "Deceased" was a live person. Both paths now escalate to **Immediate** when a heartbeat is present; total absence of breathing, movement *and* heartbeat is unchanged (domain → `Unknown`, ensemble → `Deceased`). 2 safety regression tests; full MAT suite (177) green.
|
||||
- **Per-node Home-Assistant devices now report each node's *own* presence/motion — PR #918.** After the one-device-per-node fan-out landed, the MQTT bridge still applied the *room-level aggregate* `classification` to every node, so in a multi-node deployment a node watching an empty corner inherited another node's "present" (and `motion_level: "absent"` was mis-mapped to full motion). Each node in the broadcast `nodes[]` already carries its own `classification`; the bridge now reads it per node (extracted into a testable `vitals_snapshots_from_sensing_json`), keeping vitals + person count room-level. 4 unit tests.
|
||||
- **`--model` gives an actionable diagnostic instead of a cryptic magic error — PR #919 (refs #894).** Passing a HuggingFace `ruvnet/wifi-densepose-pretrained` file (`model.safetensors` / `model-q4.bin` / `model.rvf.jsonl`) to `--model` produced `invalid magic at offset 0: … got 0x77455735`, then a silent fall back to heuristics. The load-failure path now detects the format (safetensors / quantized blob / JSONL manifest) and explains that those files are a different format **and** encoder architecture than the RVF binary container the progressive loader expects, pointing to #894. Pure `diagnose_model_load_error` + 4 tests.
|
||||
- **`--export-rvf` no longer silently produces a placeholder model — PR #920.** The `--export-rvf` handler ran *before* `--train`/`--pretrain` and unconditionally wrote placeholder sine-wave weights, so the documented `--train … --export-rvf <path>` workflow short-circuited to a fake model and never trained (while printing "exported successfully"). It now emits the placeholder **container-format demo** only standalone (with a clear warning), and falls through to real training when `--train`/`--pretrain` is set; docs point to `--save-rvf` for the real model. 3 guard tests.
|
||||
|
||||
### Added
|
||||
- **ADR-151 per-room calibration & specialist training — full `baseline → enroll → extract → train` pipeline (new `wifi-densepose-calibration` crate).** "Teach the room before you teach the model": a local-first pipeline that turns a few minutes of clean human anchors — layered on the ADR-135 empty-room baseline — into a versioned bank of small, room-calibrated specialists for **presence, posture, breathing, heartbeat, restlessness, and anomaly**. Stages: guided enrollment with an adaptive quality gate (event-sourced `EnrollmentSession`, re-prompts bad anchors); feature extraction (autocorrelation periodicity in breathing/HR bands + variance/motion); six small specialists (learned threshold / nearest-prototype / band-limited periodicity / novelty); a `SpecialistBank` with baseline-drift **STALE** invalidation; and a `MixtureOfSpecialists` runtime with presence short-circuit + anomaly veto + confidence gating. Specialists are statistical heads today (runnable + hardware-validated); the frozen ADR-150 HF RF Foundation Encoder backbone is the documented upgrade path.
|
||||
- **CLI:** `enroll` / `train-room` / `room-status` / `room-watch`, plus the Stage-1 `calibrate-serve` HTTP API (CORS-enabled: `POST /start`, `GET /status`, `POST /stop`, `GET /result`, `GET /baselines`, `GET /health`) and a firewall-free `scripts/csi-udp-relay.py` for local Windows ESP32 testing without admin.
|
||||
- **Multistatic fusion (ADR-029):** `MultiNodeMixture` fuses several co-located nodes (each with its own room-calibrated bank) into one room state — presence OR'd across nodes, posture/breathing/heartbeat from the highest-confidence node, a single implausible node vetoes the room's vitals. Driven via `room-watch --node-bank N:path` (repeatable), which groups live frames by `node_id` and fuses. Same-room only; cross-room is federation (ADR-105).
|
||||
- **Validated on live ESP32-S3 (COM8, `edge_tier=0` raw CSI):** baseline capture (120 frames → 52-subcarrier baseline); the real parser → feature-extraction → mixture runtime detecting breathing (~16–31 BPM); and the multistatic ingest grouping/fusing by node-id end-to-end. Full multi-anchor enrollment accuracy requires the operator to perform the poses; true 2-node fusion + phase-based breathing + RVF/HNSW storage are noted follow-ups. 54 tests pass (35 calibration + 19 CLI).
|
||||
- **WiFi-CSI pose: efficiency frontier + per-room calibration service** (ADR-150 §3.2–3.6). Two beyond-SOTA results on the MM-Fi benchmark, plus the deployment mechanism that resolves real-world generalization:
|
||||
- **Efficiency frontier** — a **75 K-param model beats published SOTA** (74.3% vs MultiFormer 72.25% torso-PCK@20); every config from `micro` up is Pareto-dominant (smaller *and* more accurate than prior work). Shipped a deployable **int4 edge model (~20 KB, verified 74.08%, 0.135 ms single-thread CPU)** — published at [`ruvnet/wifi-densepose-mmfi-pose/edge`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose). See [`docs/benchmarks/wifi-pose-efficiency-frontier.md`](docs/benchmarks/wifi-pose-efficiency-frontier.md).
|
||||
- **Generalization solved by few-shot calibration** — zero-shot cross-subject (~64%) and cross-environment (~10%) are *not* closeable by algorithms (CORAL, DANN, instance-norm, contrastive foundation-pretraining all tested, all failed) or by more training subjects (saturates ~64%). But **~100–200 labeled in-room samples recover SOTA-level pose**: cross-subject 64→76%, **cross-environment 10→73% (60% from just 5 samples)** — deployable as a **~11 KB per-room LoRA adapter** on a frozen shared base. Full empirical chain in ADR-150 §3.2–3.6.
|
||||
- **Calibration service (complete, both model paths, cross-language verified)** — `aether-arena/calibration/`: `calibrate.py` (transformer model, `.npz` adapter) + `infer.py` (verified 3.09%→74.29% on an unseen MM-Fi room), **and `cog_calibrate.py`** which fits a `fc1.a/fc1.b/fc2.a/fc2.b` **safetensors** adapter for the deployed cog conv+MLP model (`pose_v1.safetensors`). Consumed by the Rust product engine: `InferenceEngine::with_adapter()` + `cog-pose-estimation run --config <cfg> --adapter <room.safetensors>`. Self-contained regression tests for both Python producers (`test_calibration.py`, `test_cog_calibration.py`) **plus a cross-language Rust integration test** that loads a real `cog_calibrate.py`-generated adapter fixture and asserts it activates + changes engine output. All green.
|
||||
- **Windows workspace build + test now green** (cross-platform fixes). `wifi-densepose-worldmodel` imported `tokio::net::UnixStream` unconditionally, so `cargo build/test --workspace` failed to compile on Windows (E0432) — now the OccWorld Unix-socket bridge is `#[cfg(unix)]`-gated with a clear non-unix fallback. And `wifi-densepose-bfld`'s `readme_quickstart_uses_canonical_public_api` test checked a multi-line `pipeline\n .process` needle that never matched on a CRLF checkout — now normalizes line endings. Result: **2,682 workspace tests pass / 0 fail on Windows** (the pre-merge gate was previously unrunnable there).
|
||||
- **`ruview-swarm` crate (ADR-148)** — drone swarm control system with hierarchical-mesh topology, Raft consensus, MAPPO multi-agent reinforcement learning, and CSI sensing integration. 14 modules: topology (Raft/Gossip/Mesh), formation control (virtual-structure/leader-follower/Reynolds flocking), RRT-APF path planning, auction+FNN task allocation, MARL actor + PPO training loop, security (MAVLink v2 HMAC-SHA256 signing, UWB anti-spoofing, geofencing, Remote ID, FHSS anti-jamming), 10-state fail-safe machine, and SwarmOrchestrator. ITAR-gated coordination features (USML Category VIII(h)(12)) behind `itar-unrestricted` feature.
|
||||
- **Ruflo integration for `ruview-swarm`** — feature-gated (`ruflo`) AI-agent capability layer connecting to the claude-flow daemon: AgentDB mission memory (`memory_store`/`memory_search`), HNSW pattern learning (`agentdb_pattern-store`/`-search`), AIDefence MAVLink message scanning, and SONA intelligence trajectory hooks. `RufloBackend` trait with `HttpRufloBackend` (JSON-RPC 2.0) and `MockRufloBackend` implementations.
|
||||
|
||||
### Performance
|
||||
- `ruview-swarm` benchmarks (criterion, release): MARL actor inference 3.3 µs, RRT-APF planning 0.043 ms, multi-view CSI fusion 58.5 ns, 3-view localization 1.732 m (beats Wi2SAR 5 m SOTA baseline), 4-drone SAR coverage 223 s for 400×400 m (under 240 s target).
|
||||
|
||||
### Added
|
||||
- **ADR-147 — OccWorld world model integration** (`wifi-densepose-worldmodel` v0.3.0 published to crates.io). 15-frame trajectory prediction at 209 ms / 3.37 GB VRAM on RTX 5080. Phase 3 domain adapter `scripts/ruview_occ_dataset.py` (`RuViewOccDataset`) converts WorldGraph snapshots to OccWorld tensors with indoor class remapping + zero ego-poses (validated). Phase 5 retraining pipeline `scripts/occworld_retrain.py` — VQVAE + transformer fine-tuning on RuView occupancy snapshots. See [ADR-147](docs/adr/ADR-147-nvidia-cosmos-world-foundation-model-integration.md) · [benchmark proof](docs/adr/ADR-147-benchmark-proof.md).
|
||||
|
||||
### Added
|
||||
- **ADR-125 (APPLE-FABRIC) — RuView ↔ Apple Home native HAP bridge proposal + reference impl** (issue #796). New ADR-125 lays out a three-phase plan to expose RuView as a discoverable HomeKit accessory on the LAN so a HomePod (as Home Hub) sees presence / vitals / BFLD-derived events natively — zero Home-Assistant intermediary. Two architectural decisions resolved in the ADR per design review: (1) **one HAP bridge with N child accessories** (single pairing, matches Hue/Eve pattern), and (2) **identity-risk mapping is semantic, not probabilistic** — `identity_risk_score` and Soul-Signature match probability never cross the HAP boundary; instead three thresholded events are exposed (`Unknown Presence`, `Unexpected Occupancy`, `Unrecognized Activity Pattern`) so RuView reads as calm-tech ambient awareness, not surveillance UX. ADR-125 §2.1.a reference impl ships now: `scripts/hap-test-sensor.py` (HAP-1.1 bridge advertised over mDNS, paired with operator's iPhone) + `scripts/c6-presence-watcher.py` (parses ESP32 `RV_FEATURE_STATE_MAGIC = 0xC5110006` UDP packets with IEEE CRC32 validation, hysteresis, and a Python port of `wifi-densepose-bfld::PrivacyClass` that enforces ADR-125 §2.1.d invariant I1 at the HomeKit edge — only `Anonymous` (2) and `Restricted` (3) frames may cross; `Raw`/`Derived` are refused with exit code 2 and the cited ADR clause). Validated end-to-end on real hardware (no mocks): ESP32-C6 on `ruv.net` → UDP/5005 → mac-mini watcher → BFLD gate → HAP bridge → iPhone Home app shows `Unknown Presence` live characteristic flip. **Empirical**: 50-51 valid CRC-passing feature_state packets per 10 s window from the live C6; zero CRC errors. P2 (Rust-native HAP via the `hap` crate, replaces the Python sidecar) and P3 (Matter Controller once `matter-rs` stabilizes) follow.
|
||||
|
||||
### Security
|
||||
- **ESP32 OTA upload now fails closed when no PSK is provisioned** (#596 audit finding — critical, **breaking change for unprovisioned nodes**). `ota_check_auth()` previously returned `true` when `s_ota_psk[0] == '\0'`, so a freshly-flashed node would accept attacker-controlled firmware over plain HTTP on port 8032 from any host on the WiFi. No Secure Boot V2, no signed-image verification — a single LAN call could brick or backdoor a node. The fix rejects every OTA upload until a PSK is written to NVS (the OTA HTTP server still starts so operators can run `provision.py --ota-psk <hex>` over USB-CDC without reflashing). **Operators affected**: any deployment that relied on the unauthenticated OTA endpoint working out of the box now needs to provision a PSK before subsequent OTA pushes will succeed. Boot-time `ESP_LOGW` makes the new posture visible.
|
||||
- **Bearer-token auth accepts the scheme case-insensitively (RFC 6750) — PR #929.** `require_bearer` parsed the `Authorization` header with a case-sensitive `strip_prefix("Bearer ")`, so a *correct* `RUVIEW_API_TOKEN` sent as `Authorization: bearer <token>` (or `BEARER`, or with extra whitespace) was rejected with a confusing 401 — needless friction when enabling auth. The scheme is now matched with `eq_ignore_ascii_case` (per RFC 6750 §2.1 / RFC 7235 §2.1); the token compare is unchanged — still exact and constant-time (`ct_eq`) — so a wrong token or a non-Bearer scheme (`Basic …`) still returns 401. Audited the surrounding code while here: `ct_eq` correctly rejects length mismatch (no prefix-auth bypass) and the middleware fails closed. New `accepts_case_insensitive_bearer_scheme` test.
|
||||
- **Path-traversal vulnerabilities patched in five sensing-server endpoints** (closes #615 — critical). New `wifi_densepose_sensing_server::path_safety::safe_id()` enforces `[A-Za-z0-9._-]` only (no leading `.`, max 64 chars) before any user-controlled identifier reaches a `format!()` building a filesystem path. Applied at:
|
||||
- `POST /api/v1/recording/start` (`recording.rs` — `session_name`)
|
||||
- `GET /api/v1/recording/download/:id` (`recording.rs` — `id`)
|
||||
- `DELETE /api/v1/recording/delete/:id` (`recording.rs` — `id`)
|
||||
- `POST /api/v1/models/load` (`model_manager.rs` — `model_id`)
|
||||
- `training_api.rs` `load_recording_frames` (`dataset_id`s)
|
||||
|
||||
Pre-fix, unauthenticated callers could read `../../etc/passwd`-style paths, write arbitrary JSONL files, load attacker-controlled `.rvf` model files, or delete arbitrary files the server process could touch. 9 unit tests in `path_safety::tests` exercise the rejection envelope (empty, too-long, path separators, parent-dir traversal, null byte, whitespace/specials, non-ASCII).
|
||||
|
||||
### Fixed
|
||||
- **WebSocket `/ws/sensing` now reports `esp32:offline` when ESP32 hardware goes stale** (closes #618). `broadcast_tick_task` was re-emitting the cached `latest_update` with a frozen `source: "esp32"` field forever after the hardware lost power or network. The REST `/health` endpoint already called `effective_source()` (which returns `"esp32:offline"` after `ESP32_OFFLINE_TIMEOUT` = 5 s with no UDP frames), but the WS broadcast path was the one consumer that didn't. Result: the UI's "LIVE — ESP32 HARDWARE Connected" banner stayed green long after the hardware went away, and `vital_signs`/`features`/`classification` re-broadcasted the last-seen values indefinitely. Fix: clone the cached `latest_update` per tick, overwrite `source` with `s.effective_source()`, then serialize and broadcast. UI can now switch to an offline state on the same 5-second budget the REST surface uses.
|
||||
- **Proof replay (`archive/v1/data/proof/verify.py`) is now cross-platform deterministic** (closes #560). Three changes together: (1) `features_to_bytes()` now `np.round(.., HASH_QUANTIZATION_DECIMALS=6)`s each feature array before packing as little-endian f64, collapsing ULP-level drift from scipy.fft pocketfft SIMD reordering; (2) the `Verify Pipeline Determinism` workflow pins `OMP_NUM_THREADS=1`, `OPENBLAS_NUM_THREADS=1`, `MKL_NUM_THREADS=1`, `VECLIB_MAXIMUM_THREADS=1`, `NUMEXPR_NUM_THREADS=1` — multi-threaded BLAS reductions were a deeper source of non-determinism than SIMD reordering, and 6-decimal quantization alone wasn't enough across Azure VM microarchitectures; (3) `expected_features.sha256` regenerated under the new conditions. CI now passes the determinism check (same hash across consecutive runs on canonical Linux x86_64 CI runner: `667eb054c44ac510342665bf9c93d608868a8ead948ae8774b2796ebce6f8fe7`). `scripts/probe-fft-platform.py` updated to mirror `HASH_QUANTIZATION_DECIMALS=6` for cross-machine spot-checks.
|
||||
- **`archive/v1/src/services/pose_service.py:223` calls the right method on `PhaseSanitizer`** (closes #612). The call was `self.phase_sanitizer.sanitize(phase_data)`, but `PhaseSanitizer`'s full-pipeline entry point is named `sanitize_phase()` (`unwrap_phase` + `remove_outliers` + `smooth_phase` chained, see `archive/v1/src/core/phase_sanitizer.py:266`). The shorter `sanitize` name doesn't exist on the class, so any path that reached this branch raised `AttributeError` and crashed the pose service mid-frame.
|
||||
- **`adaptive_classifier.rs:94` no longer panics on NaN feature values** (closes #611).
|
||||
`sorted.sort_by(|a, b| a.partial_cmp(b).unwrap())` returned `None` and panicked
|
||||
whenever a single `NaN` reached the classifier from real ESP32 hardware (silent
|
||||
DSP div-by-zero, empty buffer). One bad frame killed the entire sensing-server
|
||||
process. Swapped for `unwrap_or(Ordering::Equal)`, matching the pattern the
|
||||
same file already used at lines 149-150 and 155. Per-frame hot path; this was
|
||||
a real production crash vector.
|
||||
- **Completed the #611 NaN-panic audit across the sensing-server crate** (follow-up
|
||||
to #613). The original audit grepped for the literal `partial_cmp(b).unwrap()`
|
||||
and missed seven additional production sites that use comparator variants
|
||||
(`partial_cmp(b.1).unwrap()`, `partial_cmp(&variances[b]).unwrap()`). All share
|
||||
the same crash class — a single `NaN` in CSI-derived state panics the whole
|
||||
sensing-server. Fixed:
|
||||
- `adaptive_classifier.rs:205` — `AdaptiveModel::classify()` argmax over softmax
|
||||
probs. **Same per-frame hot path as #611**; NaN flows through normalise →
|
||||
logits → softmax and still reaches this site even after the #613 IQR fix.
|
||||
- `adaptive_classifier.rs:480, 500` — training-loop argmax in `train()`
|
||||
(training/per-class accuracy reporting).
|
||||
- `main.rs:2446, 2449` and `csi.rs:602, 605` — variance-based source/sink
|
||||
selection in `count_persons_mincut`. The outer `unwrap_or((0, &0))` only
|
||||
catches an empty iterator; it cannot rescue a comparator panic.
|
||||
|
||||
Remaining `partial_cmp(...).unwrap()` sites in the workspace are all inside
|
||||
`#[cfg(test)]` / `#[test]` blocks (`spectrogram.rs:269`, `depth.rs:234`,
|
||||
`connectivity.rs:477`, `vital_signs.rs:737`) where inputs are controlled.
|
||||
- **`ui/utils/pose-renderer.js` no longer divides by zero** when two render frames land in the same `performance.now()` tick (issue #519 Bug 2). `deltaTime` is now `Math.max(currentTime - lastFrameTime, 1)` before the `1000 / deltaTime` division, capping displayed FPS at 1000 — far above any real render rate, but finite so the EMA `averageFps = averageFps * 0.9 + fps * 0.1` no longer poisons itself to `Infinity` on a single zero-dt tick.
|
||||
|
||||
### Removed
|
||||
- **Stub crates `wifi-densepose-api`, `wifi-densepose-db`, `wifi-densepose-config`** (closes #578).
|
||||
Each was a single-line doc-comment placeholder with an empty `[dependencies]`
|
||||
section and zero references from any source file or `Cargo.toml`. The names
|
||||
were reserved early for an envisioned REST/database/config split that never
|
||||
materialised; the functionality they would provide is covered today by
|
||||
`wifi-densepose-sensing-server` (Axum REST/WS), per-crate config + CLI args,
|
||||
and the project's real-time-only (no-persistent-state) posture. Removing them
|
||||
from the workspace prevents `cargo` from listing dead crates and shipping
|
||||
empty published artifacts. If any of these names is needed in the future,
|
||||
they can be reintroduced with a real implementation.
|
||||
|
||||
### Added
|
||||
- **BFLD — Beamforming Feedback Layer for Detection (ADR-118 umbrella + ADR-119 frame format + ADR-120 privacy class + ADR-121 identity risk scoring + ADR-122 RuView HA/Matter exposure + ADR-123 capture path, [#787](https://github.com/ruvnet/RuView/issues/787)).** New crate `wifi-densepose-bfld` (`v2/crates/wifi-densepose-bfld/`) — the privacy-gated WiFi sensing layer that detects when RF data crosses from "ambient sensing" into "identity record" and **structurally prevents** identity-correlated data from leaving the node. Three invariants enforced by the type system (not policy): **I1** raw BFI never exits the node (`Sink` marker-trait hierarchy + `PrivacyClass::Raw.allows_network() == false`), **I2** identity embedding is in-RAM-only (`IdentityEmbedding` has no `Serialize`/`Clone`/`Copy` + `Drop` zeroizes), **I3** cross-site identity correlation is cryptographically impossible (per-site BLAKE3-keyed `SignatureHasher` with daily epoch rotation; mean cross-site Hamming distance ≥120 bits across 100 trials). Ships the complete operator surface: `BfldPipeline` + `BfldPipelineHandle` (worker-thread variant + `spawn_with_oracle` for Soul Signature deployments), `BfldEvent` with JSON publishing (`"blake3:<hex>"` `rf_signature_hash` format per spec), 4 `privacy_class` levels (Raw/Derived/Anonymous/Restricted) with `PrivacyGate::demote` monotonic transformer + irreversible `apply_privacy_gating`, `CoherenceGate` with ±0.05 hysteresis + 5-second debounce + clock-skew resilience (saturating_sub), `SoulMatchOracle` Recalibrate-exemption trait for enrolled-person deployments. **MQTT/HA surface**: `mqtt_topics::render_events` + `publish_event` (class-gated topic routing — Raw/Derived publish 0 topics, Anonymous publishes 6, Restricted publishes 5 with `identity_risk` stripped), `ha_discovery::render_discovery_payloads` + `publish_discovery` (HA-DISCO config payloads with `availability_topic` integration), `availability` module (`online`/`offline` + LWT-aware `with_lwt` helper for `rumqttc::MqttOptions`), `RumqttPublisher` behind a `mqtt` feature gate with `connect_with_lwt` for broker-side auto-offline. **3 operator HA Blueprints** under `v2/crates/cog-ha-matter/blueprints/bfld/` (presence-driven-lighting, motion-aware-HVAC, identity-risk-anomaly-notification with rolling 7-day z-score). **Two runnable examples** (`bfld_minimal` for in-process consumers, `bfld_handle` for the production worker-thread + bootstrap-then-spawn pattern). **GitHub Actions CI workflow** (`.github/workflows/bfld-mqtt-integration.yml`) spins up `eclipse-mosquitto:2` as a service container so the env-gated `mosquitto_integration` and `rumqttc_lwt` tests run end-to-end in CI. **Performance**: `BfldFrame::to_bytes()` measured at **320,255 frames/sec** debug (6.4× ADR-119 AC7 release target of 50k), header-only at 1,654,517 frames/sec, presence-detection latency p95 = **0.9µs** (~1,000,000× under ADR-119 AC2's 1s target), 9.96 Hz motion-publish rate through `BfldPipelineHandle` (10× ADR-122 AC3 floor). **Coverage**: 327 tests at default features, 101 no_std-compatible, 220+ with `--features mqtt`. CRC-32/ISO-HDLC polynomial pinned against `"123456789" → 0xCBF43926`, public-API surface snapshot pinned across all `pub use` re-exports, `BfldError` Display contract pinned for log-grep monitoring rules, reserved-flag-bits forward-compat round-trip property, `apply_privacy_gating` irreversibility (5-cycle round-trip stress proves stripped fields never resurrect). Companion research dossier in `docs/research/BFLD/` (11 files, 13,544 words). 49-iter implementation chain from scaffold (`feat/adr-118/p1`, `c965e3e6c`) through current head with per-iter progress comments on issue [#787](https://github.com/ruvnet/RuView/issues/787). Try it: `cargo run -p wifi-densepose-bfld --example bfld_handle`.
|
||||
- **SENSE-BRIDGE — rvagent MCP server + ruvector npm + ruflo integration (ADR-124, [#787](https://github.com/ruvnet/RuView/issues/787)).** New npm package `@ruvnet/rvagent` (`tools/ruview-mcp/`) — a dual-transport [Model Context Protocol](https://modelcontextprotocol.io/) server that bridges the RuView WiFi-DensePose sensing stack to AI agents (Claude Code, Cursor, ruflo swarms). **6 of 20 ADR-124 §4.1 tools wired** in this initial release: `ruview.presence.now` (occupancy), `ruview.vitals.get_breathing` / `get_heart_rate` / `get_all` (biometric vitals via `EdgeVitalsMessage` surface, ADR-124 §6 Python ws.py:74-88 parity), `ruview.bfld.last_scan` (latest BFLD event — `identity_risk_score`, `privacy_class`, `n_frames`, `timestamp_ms`), `ruview.bfld.subscribe` (MQTT wildcard subscription with synthetic UUID envelope fallback). **Dual-transport architecture (ADR-124 §3)**: stdio (`npx @ruvnet/rvagent stdio` — recommended for Claude Code / Cursor local flow) + Streamable HTTP (`POST /mcp` bound to `127.0.0.1:3001` by default — for remote ruflo swarms across the Tailscale fleet). **Security model (ADR-124 §6)**: Origin header validation (cross-origin POST → 403), bearer-token auth slot (`RVAGENT_HTTP_TOKEN` → 401), bind default `127.0.0.1` per MCP spec requirement. **Uniform schema validation gate (ADR-124 §3)**: every `CallTool` request runs `zod.safeParse` via `TOOL_INPUT_SCHEMAS` before dispatch; failures throw `McpError(InvalidParams)`. **Full Zod schema barrel (ADR-124 §4.1 + §4.1a)**: `src/schemas/tools.ts` defines all 20 tool input schemas including the 5 RUVIEW-POLICY governance tools (can_access_vitals, can_query_presence, can_subscribe, redact_identity_fields, audit_log). **Python surface parity**: `EdgeVitalsMessage` TypeScript interface mirrors Python ws.py:74-88; ADR-124 §6 parity table drives the field names. **93 tests across 7 suites** (manifest, schemas, validate, tools, http-transport, bfld-tools, vitals-tools) — all green. Try it: `npx @ruvnet/rvagent stdio` (with `RUVIEW_SENSING_SERVER_URL=http://localhost:3000`).
|
||||
- **Home Assistant + Matter integration (ADR-115).** New `--mqtt` and `--matter` flags on `wifi-densepose-sensing-server` expose the full sensing capability set to any Home Assistant install via MQTT auto-discovery (HA-DISCO) and to any Matter controller (Apple Home / Google Home / Alexa / SmartThings) via a built-in Matter Bridge scaffolding (HA-FABRIC, SDK wiring v0.7.1). Includes 21 entity kinds per node — 11 raw signals + 10 inferred semantic primitives (HA-MIND: someone-sleeping, possible-distress, room-active, elderly-inactivity-anomaly, meeting, bathroom, fall-risk, bed-exit, no-movement, multi-room-transition). The semantic primitives run server-side so `--privacy-mode` strips HR/BR/pose values from the wire while still publishing the inferred *states* — the architectural win for healthcare and AAL deployments. Ships **8 starter HA Blueprints** under `examples/ha-blueprints/`, **3 drop-in Lovelace dashboards** under `examples/lovelace/` (including a privacy-mode-compatible healthcare care view), mTLS support, 32 KB payload-size cap, MQTT-wildcard topic-injection rejection, `RUVIEW_MQTT_STRICT_TLS=1` v0.8.0 upgrade path. **420 lib tests** cover the implementation including **~2,560 fuzzed assertions per CI run** (10 proptest cases across wire-boundary security + semantic-bus invariants). Plus mosquitto-backed integration tests in `.github/workflows/mqtt-integration.yml`, criterion benchmarks beating every ADR target by 1.6×–208×, and an ESP32-S3 hardware validation harness (`scripts/validate-esp32-mqtt.sh`) that asserts the full pipeline end-to-end with a witness bundle generator (`scripts/witness-adr-115.sh`) that self-verifies. See [`docs/releases/v0.7.0-mqtt-matter.md`](docs/releases/v0.7.0-mqtt-matter.md), [`docs/integrations/home-assistant.md`](docs/integrations/home-assistant.md), [`docs/integrations/semantic-primitives-metrics.md`](docs/integrations/semantic-primitives-metrics.md), [`docs/integrations/benchmarks.md`](docs/integrations/benchmarks.md), [`docs/adr/ADR-115-home-assistant-integration.md`](docs/adr/ADR-115-home-assistant-integration.md), tracking issue [#776](https://github.com/ruvnet/RuView/issues/776), PR [#778](https://github.com/ruvnet/RuView/pull/778). Matter SDK wiring (P8b) and CSA-certification path (P10) deferred to v0.7.1+ per ADR §9.10. Try it: `cargo run -p wifi-densepose-sensing-server --features mqtt --example mqtt_publisher -- --mqtt --mqtt-host 127.0.0.1`.
|
||||
- **ESP32-C6 firmware target with Wi-Fi 6 / 802.15.4 / TWT / LP-core support ([ADR-110](docs/adr/ADR-110-esp32-c6-firmware-extension.md), #762).** `firmware/esp32-csi-node` now builds for **both** `esp32s3` (existing production node) and `esp32c6` (new research/seed-node target) from the same source tree — pick via `idf.py set-target esp32c6` and ESP-IDF auto-applies the new `sdkconfig.defaults.esp32c6` overlay. Every C6 module is `#ifdef CONFIG_IDF_TARGET_ESP32C6` gated, so the S3 build is byte-identical to today (no regression).
|
||||
- **Wi-Fi 6 HE-LTF subcarrier tagging** — `csi_collector.c` now reads `rx_ctrl.cur_bb_format` and writes the PPDU type (0=HT/legacy, 1=HE-SU, 2=HE-MU, 3=HE-TB) into ADR-018 frame byte 18, plus bandwidth flags (20/40 MHz, STBC, 802.15.4-sync-valid) into byte 19. Bytes 18-19 were previously reserved-zero, so old aggregators read them as before — fully backwards compatible. Magic stays `0xC5110001`. Default on via `CONFIG_CSI_FRAME_HE_TAGGING`. First firmware in the open ESP32 ecosystem to tag CSI frames with 11ax PPDU metadata.
|
||||
- **802.15.4 mesh time-sync** — new `c6_timesync.{h,c}` (262 lines) provides cross-node clock alignment over the C6's separate 802.15.4 radio, freeing WiFi airtime from coordination traffic (directly addresses the ADR-029/030 multistatic synchronization gap). Protocol: lowest EUI-64 wins election, leader broadcasts `TS_BEACON` (`magic=0x54534D45`, leader epoch µs) every 100 ms on channel 15, followers compute `offset = leader_us - local_us` and apply lazily — every CSI frame is stamped with `c6_timesync_get_epoch_us()`. Target alignment ±100 µs. Default on via `CONFIG_C6_TIMESYNC_ENABLE`. Verified initializing at boot on COM6 (`c6_ts: init done: channel=15 EUI=206ef1fffefffe17 leader=yes(candidate)` at +413 ms).
|
||||
- **TWT (Target Wake Time)** — new `c6_twt.{h,c}` (223 lines) wraps `esp_wifi_sta_itwt_setup` from `esp_wifi_he.h` to negotiate an individual TWT agreement with the AP after STA connect. Replaces today's opportunistic CSI capture with a scheduler-bounded one (default wake interval 10 ms = 100 fps cadence). Graceful NACK fallback: when the AP doesn't support 11ax iTWT, the helper logs and returns OK so the device keeps doing opportunistic CSI just like the S3. Teardown on `WIFI_EVENT_STA_DISCONNECTED` keeps the AP's TWT scheduler clean. Gated on `SOC_WIFI_HE_SUPPORT` (auto-set on C6/C5 chips).
|
||||
- **LP-core wake-on-motion hibernation** — new `c6_lp_core.{h,c}` (134 lines) arms the C6 LP RISC-V coprocessor as an always-on motion gate; HP core stays in deep sleep until a configurable GPIO wakes it (ext1 deep-sleep wake source in this initial cut, real LP-core program in follow-up). Targets ≤5 µA hibernation current for battery-powered Cognitum Seed nodes (vs the S3's ~10 µA ULP-FSM floor). Opt-in via `CONFIG_C6_LP_CORE_ENABLE` (default off — only enabled on nodes flashed for battery-powered seed duty).
|
||||
- **Build matrix**: S3 stays `partitions_display.csv` (8 MB + display + WASM), C6 uses `partitions_4mb.csv` (4 MB single OTA, no display, no WASM3, no LCD). C6 final binary 1003 KB (46% partition slack), 9 % smaller than S3 production. Free heap 310 KiB at boot, app_main reached in 343 ms, 802.15.4 stack up in another 70 ms.
|
||||
- **Why this matters**: opens three research surfaces nobody has published yet — Wi-Fi-6 CSI human pose, multistatic CSI clock alignment over a side-channel radio, and TWT-bounded deterministic CSI cadence. The S3 production fleet keeps shipping the existing capabilities; the C6 is the research / battery-seed expansion target.
|
||||
- **Docs**: ADR-110 (186 lines, Status=Accepted), tracking issue [ruvnet/RuView#762](https://github.com/ruvnet/RuView/issues/762) with per-phase progress comments, README hardware table + Quick-Start Option 2b, `docs/user-guide.md` full ESP32-C6 section (build, flash, provision, multi-room time-sync, battery seed mode), full empirical record in [`docs/WITNESS-LOG-110.md`](docs/WITNESS-LOG-110.md) with verified / claimed / bugs-fixed / bugs-found sections.
|
||||
- **Wave 2 follow-up (D1 workaround)**: 5 systematic experiments on 3 live C6 boards confirmed the IDF v5.4 802.15.4 RX path is unfixable from user code (TX works 100 %, RX delivers 0 frames; coex/channel/OpenThread/manual-rearm all ruled out). Pivoted to ESP-NOW for the cross-node sync transport — `main/c6_sync_espnow.{h,c}` is the same TS_BEACON protocol over WiFi peer-to-peer, same `get_epoch_us / is_valid / is_leader` API surface. **120 s single-board soak: 1151 transmits, 0 failures (0.00 %), 9.6 tx/s sustained, no crash or reset.** The 802.15.4 path stays in source as documented-broken (D1) for when the IDF driver gets fixed.
|
||||
- **Host-side dual-pipeline decoder for ADR-018 byte 18-19** (ADR-110 protocol closure):
|
||||
- **Rust** (`v2/crates/wifi-densepose-hardware`): new `PpduType` enum (HtLegacy/HeSu/HeMu/HeTb/Unknown) and `Adr018Flags` struct (bw40/stbc/ldpc/ieee802154_sync_valid) on `CsiMetadata`. 6 new deterministic unit tests; **122/122 hardware-crate tests pass**.
|
||||
- **Python** (`archive/v1/src/hardware/csi_extractor.py`): `HEADER_FMT` extended from `<IBBHIIBB2x` to `<IBBHIIBBBB`; new metadata fields (`ppdu_type`, `he_capable`, `bw40`, `stbc`, `ldpc`, `ieee802154_sync_valid`). 5 new `TestAdr110ByteEncoding` cases; **11/11 parser tests pass**.
|
||||
- Both decoders match the firmware encoder bit-for-bit. Pre-ADR-110 firmware sends zeros that round-trip as `HtLegacy` + default flags — fully backwards compatible.
|
||||
- **Security fix** (`scripts/redact-secrets.py` + `generate-witness-bundle.sh`): the Python proof step was echoing `.env` contents into the bundled `verification-output.log` via Pydantic validation errors. Bundle nuked before push; added a `stdin -> stdout` redaction filter covering common token prefixes, long opaque strings, and long hex runs. Verified zero leaks on rebuild.
|
||||
- **Wave 3 — firmware v0.6.7 (LP-core full + soft-AP HE)**: two software-only unblocks for the hardware-blocked items in WITNESS-LOG-110 §B. (1) **Real LP-core motion-gate program** (`firmware/esp32-csi-node/main/lp_core/main.c` + integration in `c6_lp_core.c`). When `CONFIG_C6_LP_CORE_ENABLE=y`, the LP RISC-V coprocessor now runs a real polling program (configurable cadence via `CONFIG_C6_LP_POLL_PERIOD_US`, default 10 ms) that debounces N consecutive GPIO samples (`CONFIG_C6_LP_DEBOUNCE_SAMPLES`, default 3) and wakes the HP core via `ulp_lp_core_wakeup_main_processor()`. HP entry uses `esp_sleep_enable_ulp_wakeup` + `ESP_SLEEP_WAKEUP_ULP`. Exposes `c6_lp_core_motion_count()` and `c6_lp_core_poll_count()` getters for the witness harness. **Replaces** the v0.6.6 `esp_deep_sleep_enable_gpio_wakeup` ext1 fallback (which floored at ~10 µA, the same as the S3 ULP-FSM). The fallback path stays as the `else` branch so builds without `CONFIG_C6_LP_CORE_ENABLE` keep working unchanged — zero regression for v0.6.6-era fleets. Targets the C6 datasheet ≤5 µA average for battery seed nodes; pending INA/Joulescope measurement to confirm (`WITNESS-LOG-110 §B4`). (2) **Wi-Fi 6 soft-AP with TWT Responder=1** (`c6_softap_he.{h,c}` + `main.c` AP+STA mode switch). When `CONFIG_C6_SOFTAP_HE_ENABLE=y`, one C6 board can act as the iTWT-capable AP the bench is otherwise missing — pair with a second C6-STA board to negotiate real iTWT against a known-cooperative AP and measure deterministic CSI cadence (`WITNESS-LOG-110 §B1/B2`). SSID/PSK/channel configurable via Kconfig defaults or NVS (`softap_ssid`/`softap_psk`/`softap_chan` keys in the `ruview` namespace). Default off so existing nodes are unaffected. **Build artifacts**: S3 8 MB binary 1093 KB (47 % slack), C6 4 MB binary 1019 KB (45 % slack). Tag: `v0.6.7-esp32`.
|
||||
- **Wave 4 — firmware v0.6.8 (ESP-NOW mesh offset smoother)**: `c6_sync_espnow.c` now maintains an in-firmware exponential-moving-average of the cross-board sync offset (α = 1/8, fixed-point shift, ≈ 8-sample window at the 10 Hz beacon rate). New getter `c6_sync_espnow_get_offset_us_smoothed()`. `c6_sync_espnow_get_epoch_us()` now returns timestamps stamped from the smoothed offset once seeded — every downstream CSI-frame consumer gets bounded-jitter alignment for free, no host-side filter required. **Measured on the bench**: 5-min two-board soak (WITNESS-LOG-110 §A0.10) drops raw offset stdev 411.5 µs → smoothed 104.1 µs (**3.95× suppression** on stdev, 4.70× on peak-to-peak range) while preserving the +30 µs/min crystal-drift trajectory within 2 µs/min. **The ADR-110 §2.4 ≤100 µs multistatic alignment target that v0.6.6 designed is now empirically measured, not just stated.** Cross-board beacon match rate 99.56% over 5 min, 0 TX failures. Binary cost: +32 bytes (one int64, one bool, one getter). Diag log adds `smoothed=…` field. Tag: `v0.6.8-esp32`. **Known wiring gap (deferred)**: `csi_serialize_frame` does not yet stamp frames with `c6_sync_espnow_get_epoch_us()` — the ADR-018 frame format has no timestamp field, and adding one is a breaking change that needs an ADR update. Multistatic CSI fusion will require either an ADR-018 v2 with timestamp, or a separate UDP sync packet keyed off the existing flag bit. Tracked in WITNESS-LOG-110 §A0.11.
|
||||
- **Wave 5 — firmware v0.6.9 + v0.7.0 + host wiring (loop iter 8 → iter 26)**: closes the §A0.11 gap and lights up the substrate end-to-end across firmware → host → JSON broadcast. **Firmware**: (a) **v0.6.9-esp32** — `csi_collector.c` emits a 32-byte UDP sync packet (magic `0xC511A110`, distinct from CSI frame magic `0xC5110001`) every `CONFIG_C6_SYNC_EVERY_N_FRAMES` (default 20) CSI frames, carrying `node_id`, `local_us`, mesh-aligned `epoch_us` (from the Wave 4 smoothed offset), and the CSI sequence high-water for host-side pairing. Same UDP socket as CSI; host dispatches by leading magic. Operator-tunable cadence via the new Kconfig knob — N=1 (10 Hz) for tight multistatic, N=200 (~20 s) for low-power seeds. Live-verified on COM9+COM12 (§A0.12): follower reports `local − epoch = 1 163 565 µs`, matches the §A0.10 boot-delta measurement within 285 µs of WiFi MAC TX jitter. (b) **v0.7.0-esp32** — `csi_collector.c:221` ADR-018 byte 19 bit 4 ("cross-node sync valid") now ORs in `c6_sync_espnow_is_valid()` so frames from sync'd ESP-NOW nodes correctly advertise sync (previously only sourced from the broken 802.15.4 path — false-negative bug, §A0.13). Side effect: S3 boards now also set the bit since `c6_sync_espnow` is cross-target. **Host decoders + 25 unit tests**: Python `SyncPacketParser` + `SyncPacket` dataclass with `apply_to_local` / `mesh_aligned_us_for_sequence` / `local_minus_epoch_us` (10 tests in `TestSyncPacketParser`); Rust `wifi_densepose_hardware::SyncPacket` + `SyncPacketFlags` + `SYNC_PACKET_MAGIC` re-exported from the crate root with identical API surface (15 tests in `sync_packet::tests`). **Cross-language conformance gate** (loop iter 21): the same 32-byte canonical hex `10a111c509010600f26db70100000000c5aca501000000001400000000000000` is pinned in both test suites; if either decoder drifts from the wire, exactly one named test fires and points at the moved side. **Sensing-server wiring**: `udp_receiver_task` magic-dispatches `0xC511A110` and stores per-node `latest_sync: Option<SyncPacket>` + `latest_sync_at: Option<Instant>` on `NodeState`. New helpers: `NodeState::mesh_aligned_us(local_us)`, `NodeState::mesh_aligned_us_for_csi_frame(sequence)` (uses the per-node measured fps EMA with 5-sample warmup + 9 s staleness gate), `NodeState::observe_csi_frame_arrival(now)` (feeds `update_csi_fps_ema` α=1/8, called once per accepted CSI frame). 4 fps-EMA tests + 3 NodeSyncSnapshot serialization tests on the binary target. **Public JSON API**: `sensing_update` broadcasts now carry an optional `sync` object per node — `{offset_us, is_leader, is_valid, smoothed, sequence, csi_fps_ema, csi_fps_samples}` — `#[serde(skip_serializing_if = "Option::is_none")]` so non-mesh paths (multi-BSSID scan / synthetic-RSSI fallback / simulation) omit the key entirely. Existing pre-v0.7.0 UI clients ignore it cleanly. Documented in `docs/user-guide.md` "Per-node mesh sync (ADR-110)" section with field table, UI rendering rules, and the timestamp-recovery recipe. **Branch-coordination**: `docs/ADR-110-BRANCH-STATE.md` maps which files each of `adr-110-esp32c6` vs `feat/adr-115-ha-mqtt-matter` touches (regions are disjoint, merges should be clean line-merges). **Verification baselines**: full v2 cargo workspace at **1437 tests passing** (no regression across 17 crate batches), full `wifi-densepose-hardware` crate at **137 tests**. ADR-110 §B substrate is now end-to-end visible to UI clients and ready for ADR-029/030 multistatic CSI fusion consumption.
|
||||
- **Real-time CSI introspection / low-latency tap on `wifi-densepose-sensing-server` (ADR-099).**
|
||||
New `wifi_densepose_sensing_server::introspection` module wires
|
||||
[midstream](https://github.com/ruvnet/midstream)'s `temporal-attractor` (Lyapunov +
|
||||
regime classification) and `temporal-compare` (DTW pattern matching) as a
|
||||
**parallel tap** alongside RuView's existing event pipeline — no replacement,
|
||||
no behaviour change to the existing `/ws/sensing` fan-out or `wifi-densepose-signal`
|
||||
DSP. Two new endpoints (off by default, enabled via `--introspection`):
|
||||
- `GET /ws/introspection` — newline-delimited JSON snapshots streamed at the CSI
|
||||
frame rate. Each snapshot carries `frame_count`, `regime` (Idle / Periodic /
|
||||
Transient / Chaotic / Unknown), `lyapunov_exponent`, `attractor_dim`,
|
||||
`attractor_confidence`, `regime_changed` (boolean — flips on the first frame
|
||||
after a regime transition), and `top_k_similarity[]` (highest-scoring
|
||||
signature matches against a per-deployment library).
|
||||
- `GET /api/v1/introspection/snapshot` — single-shot JSON snapshot, auth-gated
|
||||
when `RUVIEW_API_TOKEN` is set.
|
||||
Per-frame `update()` budget measured at **0.041 ms p99** on the I5 bench
|
||||
(~24× under ADR-099 D4's 1 ms target). Shape-match latency on a 1-D
|
||||
mean-amplitude L1 stand-in: **5 frames** (3.20× ratio vs the 16-frame event-path
|
||||
floor). ADR-099 D8 honestly amended — the aspirational 10× bar is contingent on
|
||||
ADR-208 Phase 2 multi-dim NPU embeddings; this release ships the tap off-by-default
|
||||
while the foundation lands. 8 lib tests + 5 latency/regression tests (`tests/introspection_latency.rs`,
|
||||
including a 200-frame noise warm-up → 10-frame motion-ramp signature benchmark).
|
||||
- **Opt-in bearer-token auth on `wifi-densepose-sensing-server`'s `/api/v1/*` HTTP surface (closes #443).**
|
||||
New `wifi_densepose_sensing_server::bearer_auth` module: when the
|
||||
`RUVIEW_API_TOKEN` env var is set, every request whose path begins with
|
||||
`/api/v1/` must carry an `Authorization: Bearer <token>` header (constant-time
|
||||
compared) or the server responds `401 Unauthorized`. When the variable is
|
||||
unset or empty the middleware is a no-op — the long-standing LAN-only
|
||||
deployment posture is preserved, so this is a binary deployment-time switch
|
||||
with **no default behaviour change**. `/health*`, `/ws/sensing`, and the
|
||||
`/ui/*` static mount are intentionally never gated (orchestrator probes +
|
||||
local browsers). Startup logs which mode is active and warns when auth is on
|
||||
with a `0.0.0.0` bind. 8 unit tests on the middleware (lib test count 191 → 199).
|
||||
Resolves the security audit raised in #443.
|
||||
|
||||
### Changed
|
||||
- **Docker image: build-time guard for the UI assets, plus a CI workflow that
|
||||
rebuilds and pushes on every change (closes #520, #514).** `docker/Dockerfile.rust`
|
||||
now `RUN`s a guard after `COPY ui/` that fails the build if any of
|
||||
`index.html` / `observatory.html` / `pose-fusion.html` / `viz.html` / the
|
||||
`observatory/` / `pose-fusion/` / `components/` / `services/` directories are
|
||||
missing, so a stale image can never be silently produced again. New
|
||||
`.github/workflows/sensing-server-docker.yml` builds the image on push to
|
||||
`main` (paths-filtered) and on `v*` tags and pushes to both
|
||||
`docker.io/ruvnet/wifi-densepose` and `ghcr.io/ruvnet/wifi-densepose` with
|
||||
`latest` + `vX.Y.Z` + `sha-<short>` tags, then smoke-tests the published
|
||||
artifact: `/health`, `/api/v1/info`, the observatory + pose-fusion UI assets,
|
||||
and the `RUVIEW_API_TOKEN` auth path (no token → 401, wrong → 401, correct
|
||||
→ 200). Uses `DOCKERHUB_USERNAME` / `DOCKERHUB_TOKEN` repo secrets for the
|
||||
Docker Hub push; ghcr.io uses the workflow's `GITHUB_TOKEN`.
|
||||
- **rvCSI moved to its own repo and is now vendored as a submodule.** The 9 `rvcsi-*`
|
||||
crates (`rvcsi-core`/`-dsp`/`-events`/`-adapter-file`/`-adapter-nexmon`/`-ruvector`/
|
||||
`-runtime`/`-node`/`-cli` — added inline in #542) now live in
|
||||
[`github.com/ruvnet/rvcsi`](https://github.com/ruvnet/rvcsi): published to crates.io
|
||||
as `rvcsi-* 0.3.x`, to npm as `@ruv/rvcsi`, with a Claude Code plugin marketplace and
|
||||
a RuView-style README. RuView vendors it under `vendor/rvcsi` (alongside
|
||||
`vendor/ruvector` / `vendor/midstream` / `vendor/sublinear-time-solver`) and no longer
|
||||
carries inline copies in `v2/crates/`; consumers depend on the published crates (or the
|
||||
submodule's `crates/rvcsi-*` paths). `v2/Cargo.toml`, `CLAUDE.md`, and the README docs
|
||||
table updated accordingly. The ADRs (ADR-095, ADR-096), PRD, and DDD model stay in
|
||||
`docs/` here as the design record of the incubation.
|
||||
|
||||
### Fixed
|
||||
- **README: corrected the camera-supervised pose-accuracy claim.** The README stated
|
||||
"92.9% PCK@20" for camera-supervised training; that figure does not appear in
|
||||
ADR-079 and is ~2.6× the ADR's own success target (>35% PCK@20). ADR-079 phases
|
||||
P7 (data collection), P8 (training + evaluation on real paired data) and P9
|
||||
(cross-room LoRA) are still `Pending`, so no measured camera-supervised PCK@20 has
|
||||
been published. README now states the proxy-supervised baseline (≈2.5%) and the
|
||||
ADR-079 target (35%+), and notes the eval phases are pending. Surfaced by the
|
||||
PowerPlatePulse training-pipeline audit (2026-05-11); 6 remaining audit findings
|
||||
tracked in the PR.
|
||||
- **rvCSI `BaselineDriftDetector`: drift thresholds are now scale-relative, not absolute.**
|
||||
The detector compared `mean_amplitude` against its EWMA baseline with absolute
|
||||
thresholds (`anomaly_threshold = 1.0`, `drift_threshold = 0.15`) — fine for the
|
||||
synthetic unit tests (amplitudes ≈ 1.0), but raw ESP32 CSI is `int8` I/Q with
|
||||
amplitudes up to ~128, so the window-to-window RMS distance is routinely 5–50 ≫ 1.0
|
||||
and `AnomalyDetected` fired on ~96 % of windows (319/331 on a real node-1 capture).
|
||||
Drift is now `‖current − baseline‖₂ / ‖baseline‖₂` (a fraction, with an `eps` floor
|
||||
for a degenerate near-zero baseline), so one tuning works across raw-`int8` ESP32,
|
||||
`int16`-scaled Nexmon, and baseline-subtracted streams alike — `AnomalyDetected`
|
||||
drops to 40/331 on the same data, the existing detector tests still pass, and a
|
||||
`baseline_drift_is_scale_invariant_no_anomaly_storm` regression test was added.
|
||||
ADR-095 D13 / ADR-096 §2.1, §5 updated. Surfaced by an end-to-end test against
|
||||
real ESP32 CSI (a 7,000-frame node-1 capture; transcoder at
|
||||
`scripts/esp32_jsonl_to_rvcsi.py`).
|
||||
|
||||
### Added
|
||||
- **rvCSI — edge RF sensing runtime (design + first implementation).** New subsystem **rvCSI**: a Rust-first / TypeScript-accessible / hardware-abstracted edge RF sensing runtime that normalizes WiFi CSI from Nexmon, ESP32, Intel, Atheros, file and replay sources into one validated `CsiFrame` schema, runs reusable DSP, emits typed confidence-scored events, and bridges to RuVector RF memory, an MCP tool server and a TS SDK.
|
||||
- **Design docs:** `docs/prd/rvcsi-platform-prd.md` (purpose, users, success criteria, FR1–FR10, NFRs, system architecture, data model); `docs/adr/ADR-095-rvcsi-edge-rf-sensing-platform.md` (the 15 architectural decisions: Rust core, C-at-the-boundary, TS SDK via napi-rs, normalized schema, validate-before-FFI, CSI-as-temporal-delta, RuVector as RF memory, replayability, detection≠decision, local-first, read-first/write-gated MCP, mandatory quality scoring, versioned calibration, plugin adapters); `docs/adr/ADR-096-rvcsi-ffi-crate-layout.md` (crate topology, the napi-c shim record format & contract, the napi-rs Node surface, build/test invariants); `docs/ddd/rvcsi-domain-model.md` (7 bounded contexts: Capture, Validation, Signal, Calibration, Event, Memory, Agent — with aggregates, invariants, context map and domain services). Indexed in `docs/adr/README.md` and `docs/ddd/README.md`.
|
||||
- **Crates** (9 new `v2/crates/rvcsi-*` workspace members): `rvcsi-core` (normalized `CsiFrame`/`CsiWindow`/`CsiEvent` schema, `AdapterProfile`, `CsiSource` plugin trait, id newtypes + `IdGenerator`, `RvcsiError`, the `validate_frame` pipeline + quality scoring; `forbid(unsafe_code)`); `rvcsi-adapter-nexmon` — the **napi-c** seam: `native/rvcsi_nexmon_shim.{c,h}` (the only C in the runtime — allocation-free, bounds-checked, ABI `1.1`), compiled via `build.rs`+`cc`, handling **two byte formats** — the compact self-describing "rvCSI Nexmon record", and the **real nexmon_csi UDP payload** (the 18-byte `magic 0x1111 · rssi · fctl · src_mac · seq · core/stream · chanspec · chip_ver` header + `nsub` int16 I/Q samples, the modern BCM43455c0/4358/4366c0 export read by CSIKit/`csireader.py`), with a Broadcom d11ac **chanspec decoder** (channel/bandwidth/band) — plus a pure-Rust **libpcap reader** (classic `.pcap`, all byte-order/timestamp-resolution magics, Ethernet/raw-IPv4/Linux-SLL link types) and a **Nexmon-chip / Raspberry-Pi-model registry** (`NexmonChip` / `RaspberryPiModel` — including the **Raspberry Pi 5** (CYW43455/BCM43455c0, same wireless as the Pi 4 — 20/40/80 MHz, 2.4+5 GHz, 64/128/256 subcarriers), the Pi 3B+/4/400, and the Pi Zero 2 W (BCM43436b0); `nexmon_adapter_profile` / `raspberry_pi_profile` build the per-chip `AdapterProfile`; `chip_ver` words auto-resolve to a chip). Wrapped by a documented `ffi` module and two `CsiSource`s: `NexmonAdapter` (record buffers) and `NexmonPcapAdapter` (real nexmon_csi UDP inside a `tcpdump -i wlan0 dst port 5500 -w csi.pcap` capture — the pcap timestamp stamps each frame; the chip is auto-detected from `chip_ver`, overridable via `.with_pi_model(Pi5)` / `.with_chip(...)`). `rvcsi-dsp` (DC removal, phase unwrap, smoothing, Hampel/MAD filter, sliding variance, baseline subtraction, motion-energy/presence/confidence features, heuristic breathing-band estimate, non-destructive `SignalPipeline`); `rvcsi-events` (`WindowBuffer`, the `EventDetector` trait + presence/motion/quality/baseline-drift state machines, `EventPipeline`; the baseline-drift detector uses **scale-relative** thresholds — drift as a fraction of the baseline's RMS magnitude — so one tuning works across raw-`int8` ESP32, `int16`-scaled Nexmon, and baseline-subtracted streams alike); `rvcsi-adapter-file` (the `.rvcsi` JSONL capture format, `FileRecorder`, `FileReplayAdapter` deterministic replay); `rvcsi-ruvector` (deterministic window/event embeddings, `cosine_similarity`, the `RfMemoryStore` trait, `InMemoryRfMemory` + `JsonlRfMemory` — a standin until the production RuVector binding); `rvcsi-runtime` (the no-FFI composition layer: `CaptureRuntime` = `CsiSource` + `validate_frame` + `SignalPipeline` + `EventPipeline`, plus one-shot helpers `summarize_capture`/`decode_nexmon_records`/`decode_nexmon_pcap`/`summarize_nexmon_pcap`/`events_from_capture`/`export_capture_to_rf_memory`); `rvcsi-node` — the **napi-rs** seam (a `["cdylib","rlib"]` Node addon, `build.rs` runs `napi_build::setup()`; thin `#[napi]` wrappers over `rvcsi-runtime` — `nexmonDecodeRecords`/`nexmonDecodePcap` (with optional `chip`)/`inspectNexmonPcap`/`decodeChanspec`/`nexmonChipName`/`nexmonProfile`/`nexmonChips`/`inspectCaptureFile`/`eventsFromCaptureFile`/`exportCaptureToRfMemory` + an `RvcsiRuntime` streaming class; everything that crosses to JS is a validated/normalized struct serialized to JSON); `rvcsi-cli` (the `rvcsi` binary: `record` (Nexmon-dump *or* `--source nexmon-pcap [--chip pi5]` → `.rvcsi`), `inspect`, `inspect-nexmon`, `nexmon-chips`, `decode-chanspec`, `replay`, `stream`, `events`, `health`, `calibrate` v0-baseline, `export ruvector`). Plus the `@ruv/rvcsi` npm package (`package.json`/`index.js`/`index.d.ts`/`README`/`__test__`) alongside `rvcsi-node` — a curated JS surface that parses the addon's JSON into plain `CsiFrame`/`CsiWindow`/`CsiEvent`/`SourceHealth`/`CaptureSummary`/`NexmonPcapSummary`/`DecodedChanspec` objects, with a lazy native-addon load.
|
||||
- **Tests:** 169 across the rvcsi crates (core 29, dsp 28, events 19 — incl. a baseline-drift scale-invariance regression, adapter-file 20 + 1 doctest, adapter-nexmon 28 — round-tripping through the C shim and synthetic libpcap files, incl. Pi 5 / chip-detection, ruvector 20 + 1 doctest, runtime 13, cli 10), 0 failures; all rvcsi crates build together and are clippy-clean (`rvcsi-node` under `deny(clippy::all)`); `forbid(unsafe_code)` everywhere except `rvcsi-adapter-nexmon` (FFI, every `unsafe` block documented). Also exercised end-to-end against a real 7,000-frame ESP32 node-1 capture (transcoded with `scripts/esp32_jsonl_to_rvcsi.py` — the stand-in for the not-yet-shipped `record --source esp32-jsonl`): `rvcsi inspect`/`replay`/`calibrate`/`events` all run on real hardware data. Not yet wired in: live radio capture, `rvcsi-adapter-esp32` (live serial/UDP ESP32 source), the WebSocket daemon (`rvcsi-daemon`), the MCP tool server (`rvcsi-mcp`), and the legacy nexmon *packed-float* CSI export — follow-ups on top of these crates.
|
||||
- **`wifi-densepose-train`: `signal_features` module — wires `wifi-densepose-signal` into the training pipeline.** `wifi-densepose-signal` was previously a phantom dependency of `wifi-densepose-train` (listed in `Cargo.toml`, never imported). New `wifi_densepose_train::signal_features::extract_signal_features` (and `CsiSample::signal_features()`) run a windowed CSI observation's centre frame through `wifi_densepose_signal::features::FeatureExtractor`, producing a fixed-length (`FEATURE_LEN = 12`) amplitude/phase/PSD feature vector — the hook for a future vitals / multi-task supervision head (breathing- and heart-rate-band power are read off the PSD summary). The vector is produced on demand and not yet fed back into the loss. Surfaced by the 2026-05-11 training-pipeline audit (findings #1 "vitals features absent from training" and #2 "`wifi-densepose-signal` ghost dep").
|
||||
- **`wifi-densepose-train`: `TrainingConfig` subcarrier-layout presets + a real-loader integration test.** New `TrainingConfig::for_subcarriers(native, target)` plus named presets `ht40_192()` (≈192-sc ESP32 HT40 → 56) and `multiband_168()` (168-sc ADR-078 multi-band mesh → 56), so non-MM-Fi CSI shapes are first-class instead of requiring manual `native_subcarriers`/`num_subcarriers` overrides; field docs now list the supported source counts and the multi-NIC mapping. New `tests/test_real_loader.rs` round-trips synthetic CSI through `.npy` files → `MmFiDataset::discover`/`get` (including the subcarrier-interpolation branch and the empty-root case) — exercising the on-disk loader path the deterministic `verify-training` proof intentionally bypasses. Addresses training-pipeline audit findings #6 (56-sc/1-NIC config default) and #7 (multi-band mesh not in config); the #4 concern ("proof uses synthetic data") is reframed — the proof *should* use a reproducible source, and this test covers the real loader it skips.
|
||||
|
||||
### Fixed
|
||||
- **HuggingFace `MODEL_CARD.md`: marked the PIR/BME280 environmental-sensor ground-truth path as planned, not implemented** (training-pipeline audit finding #3) — the card presented PIR/BME280 weak-label fine-tuning as a current capability; there is no env-sensor ingestion in the training pipeline today.
|
||||
- **README: corrected the camera-supervised pose-accuracy claim** (audit finding #5; see PR #535) — "92.9% PCK@20" → the ADR-079 target (35%+; proxy baseline 35.3%), noting P7/P8/P9 are pending.
|
||||
|
||||
### Added
|
||||
- **`RollingP95` adaptive feature normalizer** (`v2/crates/wifi-densepose-sensing-server`) —
|
||||
Streaming P95 estimator (600-sample / ~30 s sliding window) that self-calibrates
|
||||
feature normalization to whatever distribution the deployment produces. Replaces
|
||||
fixed-scale denominators (`variance/300`, `motion/250`, `spectral/500`) which saturated
|
||||
when live ESP32 values exceeded those limits, collapsing dynamic range to zero.
|
||||
Cold-start (<60 samples) falls back to the legacy denominators so day-0 behaviour
|
||||
is preserved. Deployment-neutral: no hardcoded values. (ADR-044 §5.2)
|
||||
|
||||
- **`dedup_factor` runtime configuration API** (`v2/crates/wifi-densepose-sensing-server`) —
|
||||
Exposes the multi-node person-count deduplication divisor at runtime via REST:
|
||||
- `GET /api/v1/config/dedup-factor` — read current value.
|
||||
- `POST /api/v1/config/dedup-factor` — set value (clamped 1.0–10.0, persisted).
|
||||
- `POST /api/v1/config/ground-truth` — auto-tunes `dedup_factor` from a known
|
||||
person count (`{"count": N}`); derives optimal divisor from current node-sum.
|
||||
Config is persisted to `data/config.json` and reloaded on restart. (ADR-044 §5.3)
|
||||
|
||||
- **`nvsim` crate — deterministic NV-diamond magnetometer pipeline simulator** (ADR-089) —
|
||||
New standalone leaf crate at `v2/crates/nvsim` modeling a forward-only
|
||||
magnetic sensing path: scene → source synthesis (Biot–Savart, dipole,
|
||||
current loop, ferrous induced moment) → material attenuation
|
||||
(Air/Drywall/Brick/Concrete/Reinforced/SteelSheet) → NV ensemble
|
||||
(4 〈111〉 axes, ODMR linear-readout proxy, shot-noise floor per
|
||||
Wolf 2015 / Barry 2020) → 16-bit ADC + lock-in demodulation →
|
||||
fixed-layout `MagFrame` records → SHA-256 witness. Six-pass build
|
||||
per `docs/research/quantum-sensing/15-nvsim-implementation-plan.md`.
|
||||
50 tests, ~4.5 M samples/s on x86_64 (4500× the Cortex-A53 1 kHz
|
||||
acceptance gate), pinned reference witness
|
||||
`cc8de9b01b0ff5bd97a6c17848a3f156c174ea7589d0888164a441584ec593b4`
|
||||
for byte-equivalence regression. WASM-ready by construction
|
||||
(zero `std::time/fs/env/process/thread`); builds cleanly for
|
||||
`wasm32-unknown-unknown`. ADR-090 (Proposed, conditional) tracks the
|
||||
optional Lindblad/Hamiltonian extension if AC magnetometry, MW power
|
||||
saturation, hyperfine spectroscopy, or pulsed protocols become required.
|
||||
|
||||
### Fixed
|
||||
- **WebSocket broadcast handler now handles Lagged events gracefully and sends periodic ping keepalives to prevent dashboard disconnects** —
|
||||
`handle_ws_client` and `handle_ws_pose_client` in `wifi-densepose-sensing-server`
|
||||
were treating `RecvError::Lagged` as a fatal error, causing instant disconnect
|
||||
when clients fell behind the 256-frame broadcast buffer at 10 Hz ingest.
|
||||
Clients would reconnect, immediately lag again, and rapid-cycle every 2–4 s.
|
||||
`Lagged` now continues (drops missed frames, logs debug) rather than breaking.
|
||||
Added 30 s ping keepalive on the sensing handler to prevent proxy idle timeouts.
|
||||
- **Ghost skeletons in live UI with multi-node ESP32 setups** (#420, ADR-082) —
|
||||
`tracker_bridge::tracker_to_person_detections` documented itself as filtering
|
||||
to `is_alive()` tracks but in fact passed every non-Terminated track to the
|
||||
WebSocket stream. `Lost` tracks — kept inside `reid_window` for
|
||||
re-identification but not currently observed — were rendering as phantom
|
||||
skeletons, accumulating to 22-24 with 3 nodes × 10 Hz CSI while
|
||||
`estimated_persons` correctly reported 1. Added
|
||||
`PoseTracker::confirmed_tracks()` (Tentative + Active only) and rewired the
|
||||
bridge to use it. Lost tracks remain in the tracker for re-ID; they just
|
||||
no longer ship to the UI. Regression test:
|
||||
`test_lost_tracks_excluded_from_bridge_output`.
|
||||
- **Rust workspace build with `--no-default-features` on Windows** (#366, #415) —
|
||||
`wifi-densepose-mat`, `wifi-densepose-sensing-server`, and `wifi-densepose-train`
|
||||
all depended on `wifi-densepose-signal` with default features enabled, which
|
||||
pulled `ndarray-linalg` → `openblas-src` → vcpkg/system-BLAS through the entire
|
||||
workspace. `--no-default-features` at the workspace root then could not opt out
|
||||
of BLAS, breaking `cargo build` / `cargo test` on Windows without vcpkg. All
|
||||
three consumers now declare `wifi-densepose-signal = { ..., default-features = false }`,
|
||||
so `cargo test --workspace --no-default-features` builds cleanly without
|
||||
vcpkg/openblas. Validated: 1,538 tests pass, 0 fail, 8 ignored.
|
||||
- **`signal` test `test_estimate_occupancy_noise_only` failed without `eigenvalue`** —
|
||||
The test unwrapped the `NotCalibrated` stub returned when the BLAS-backed
|
||||
`estimate_occupancy` is compiled out. Gated with `#[cfg(feature = "eigenvalue")]`
|
||||
so it only runs when the real implementation is available.
|
||||
|
||||
## [v0.6.2-esp32] — 2026-04-20
|
||||
|
||||
Firmware release cutting ADR-081 and the Timer Svc stack fix discovered during
|
||||
on-hardware validation. Cut from `main` at commit pointing to this entry.
|
||||
Tested on ESP32-S3 (QFN56 rev v0.2, MAC `3c:0f:02:e9:b5:f8`), 30 s continuous
|
||||
run: no crashes, 149 `rv_feature_state_t` emissions (~5 Hz), medium/slow ticks
|
||||
firing cleanly, HEALTH mesh packets sent.
|
||||
|
||||
### Fixed
|
||||
- **Firmware: Timer Svc stack overflow on ADR-081 fast loop** — `emit_feature_state()` runs inside the FreeRTOS Timer Svc task via the fast-loop callback; it calls `stream_sender` network I/O which pushes past the ESP-IDF 2 KiB default timer stack and panics ~1 s after boot. Bumped `CONFIG_FREERTOS_TIMER_TASK_STACK_DEPTH` to 8 KiB in `sdkconfig.defaults`, `sdkconfig.defaults.template`, and `sdkconfig.defaults.4mb`. Follow-up (tracked separately): move heavy work out of the timer daemon into a dedicated worker task.
|
||||
- **Firmware: `adaptive_controller.c` implicit declaration** (#404) — `fast_loop_cb` called `emit_feature_state()` before its static definition, triggering `-Werror=implicit-function-declaration`. Added a forward declaration above the first use.
|
||||
|
||||
### Changed
|
||||
- **CI: firmware build matrix (8MB + 4MB)** — `firmware-ci.yml` now matrix-builds both the default 8MB (`sdkconfig.defaults`) and 4MB SuperMini (`sdkconfig.defaults.4mb`) variants, uploading distinct artifacts and producing variant-named release binaries (`esp32-csi-node.bin` / `esp32-csi-node-4mb.bin`, `partition-table.bin` / `partition-table-4mb.bin`).
|
||||
|
||||
### Added
|
||||
- **ADR-081: Adaptive CSI Mesh Firmware Kernel** — New 5-layer architecture
|
||||
(Radio Abstraction Layer / Adaptive Controller / Mesh Sensing Plane /
|
||||
On-device Feature Extraction / Rust handoff) that reframes the existing
|
||||
ESP32 firmware modules as components of a chipset-agnostic kernel. ADR
|
||||
in `docs/adr/ADR-081-adaptive-csi-mesh-firmware-kernel.md`. Goal: swap
|
||||
one radio family for another without changing the Rust signal /
|
||||
ruvector / train / mat crates.
|
||||
- **Firmware: radio abstraction vtable (`rv_radio_ops_t`)** — New
|
||||
`firmware/esp32-csi-node/main/rv_radio_ops.{h}` defines the
|
||||
chipset-agnostic ops (init, set_channel, set_mode, set_csi_enabled,
|
||||
set_capture_profile, get_health), profile enum
|
||||
(`RV_PROFILE_PASSIVE_LOW_RATE` / `ACTIVE_PROBE` / `RESP_HIGH_SENS` /
|
||||
`FAST_MOTION` / `CALIBRATION`), and health snapshot struct.
|
||||
`rv_radio_ops_esp32.c` provides the ESP32 binding wrapping
|
||||
`csi_collector` + `esp_wifi_*`. A second binding (mock or alternate
|
||||
chipset) is the portability acceptance test for ADR-081.
|
||||
- **Firmware: `rv_feature_state_t` packet (magic `0xC5110006`)** — New
|
||||
60-byte compact per-node sensing state (packed, verified by
|
||||
`_Static_assert`) in `firmware/esp32-csi-node/main/rv_feature_state.h`:
|
||||
motion, presence, respiration BPM/conf, heartbeat BPM/conf, anomaly
|
||||
score, env-shift score, node coherence, quality flags, IEEE CRC32.
|
||||
Replaces raw ADR-018 CSI as the default upstream stream (~99.7%
|
||||
bandwidth reduction: 300 B/s at 5 Hz vs. ~100 KB/s raw).
|
||||
- **Firmware: mock radio ops binding for QEMU** — New
|
||||
`firmware/esp32-csi-node/main/rv_radio_ops_mock.c`, compiled only when
|
||||
`CONFIG_CSI_MOCK_ENABLED`. Satisfies ADR-081's portability acceptance
|
||||
test: a second `rv_radio_ops_t` binding compiles and runs against the
|
||||
same controller + mesh-plane code as the ESP32 binding.
|
||||
- **Firmware: feature-state emitter wired into controller fast loop** —
|
||||
`adaptive_controller.c` now emits one 60-byte `rv_feature_state_t` per
|
||||
fast tick (default 200 ms → 5 Hz), pulling from the latest edge vitals
|
||||
and controller observation. This is the first end-to-end Layer 4/5
|
||||
path for ADR-081.
|
||||
- **Firmware: `csi_collector_get_pkt_yield_per_sec()` /
|
||||
`_get_send_fail_count()` accessors** — Expose the CSI callback rate
|
||||
and UDP send-failure counter so the ESP32 radio ops binding can
|
||||
populate `rv_radio_health_t.pkt_yield_per_sec` and `.send_fail_count`,
|
||||
closing the adaptive controller's observation loop.
|
||||
- **Firmware: host-side unit test suite for ADR-081 pure logic** — New
|
||||
`firmware/esp32-csi-node/tests/host/` (Makefile + 2 test files + shim
|
||||
`esp_err.h`). Exercises `adaptive_controller_decide()` (9 test cases:
|
||||
degraded gate on pkt-yield collapse + coherence loss, anomaly > motion,
|
||||
motion → SENSE_ACTIVE, aggressive cadence, stable presence →
|
||||
RESP_HIGH_SENS, empty-room default, hysteresis, NULL safety) and
|
||||
`rv_feature_state_*` helpers (size assertion, IEEE CRC32 known
|
||||
vectors, determinism, receiver-side verification). 33/33 assertions
|
||||
pass. Benchmarks: decide() 3.2 ns/call, CRC32(56 B) 614 ns/pkt
|
||||
(87 MB/s), full finalize() 616 ns/call. Pure function
|
||||
`adaptive_controller_decide()` extracted to
|
||||
`adaptive_controller_decide.c` so the firmware build and the host
|
||||
tests share a single source-of-truth implementation.
|
||||
- **Scripts: `validate_qemu_output.py` ADR-081 checks** — Validator
|
||||
(invoked by ADR-061 `scripts/qemu-esp32s3-test.sh` in CI) gains three
|
||||
checks for adaptive controller boot line, mock radio ops
|
||||
registration, and slow-loop heartbeat, so QEMU runs regression-gate
|
||||
Layer 1/2 presence.
|
||||
- **Firmware: ADR-081 Layer 3 mesh sensing plane** — New
|
||||
`firmware/esp32-csi-node/main/rv_mesh.{h,c}` defines 4 node roles
|
||||
(Anchor / Observer / Fusion relay / Coordinator), 7 on-wire message
|
||||
types (TIME_SYNC, ROLE_ASSIGN, CHANNEL_PLAN, CALIBRATION_START,
|
||||
FEATURE_DELTA, HEALTH, ANOMALY_ALERT), 3 authorization classes
|
||||
(None / HMAC-SHA256-session / Ed25519-batch), `rv_node_status_t`
|
||||
(28 B), `rv_anomaly_alert_t` (28 B), `rv_time_sync_t`,
|
||||
`rv_role_assign_t`, `rv_channel_plan_t`, `rv_calibration_start_t`.
|
||||
Pure-C encoder/decoder (`rv_mesh_encode()` / `rv_mesh_decode()`) with
|
||||
16-byte envelope + payload + IEEE CRC32 trailer; convenience encoders
|
||||
for each message type. Controller now emits `HEALTH` every slow-loop
|
||||
tick (30 s default) and `ANOMALY_ALERT` on state transitions to ALERT
|
||||
or DEGRADED. Host tests: `test_rv_mesh` exercises 27 assertions
|
||||
covering roundtrip, bad magic, truncation, CRC flipping, oversize
|
||||
payload rejection, and encode+decode throughput (1.0 μs/roundtrip
|
||||
on host).
|
||||
- **Rust: ADR-081 Layer 1/3 mirror module** — New
|
||||
`crates/wifi-densepose-hardware/src/radio_ops.rs` mirrors the
|
||||
firmware-side `rv_radio_ops_t` vtable as the Rust `RadioOps` trait
|
||||
(init, set_channel, set_mode, set_csi_enabled, set_capture_profile,
|
||||
get_health) and provides `MockRadio` for offline testing.
|
||||
Also mirrors the `rv_mesh.h` types (`MeshHeader`, `NodeStatus`,
|
||||
`AnomalyAlert`, `MeshRole`, `MeshMsgType`, `AuthClass`) and ships
|
||||
byte-identical `crc32_ieee()`, `decode_mesh()`, `decode_node_status()`,
|
||||
`decode_anomaly_alert()`, and `encode_health()`. Exported from
|
||||
`lib.rs`. 8 unit tests pass; `crc32_matches_firmware_vectors`
|
||||
verifies parity with the firmware-side test vectors
|
||||
(`0xCBF43926` for `"123456789"`, `0xD202EF8D` for single-byte zero),
|
||||
and `mesh_constants_match_firmware` asserts `MESH_MAGIC`,
|
||||
`MESH_VERSION`, `MESH_HEADER_SIZE`, and `MESH_MAX_PAYLOAD` match
|
||||
`rv_mesh.h` byte-for-byte. Satisfies ADR-081's portability
|
||||
acceptance test: signal/ruvector/train/mat crates are untouched.
|
||||
- **Firmware: adaptive controller** — New
|
||||
`firmware/esp32-csi-node/main/adaptive_controller.{c,h}` implements
|
||||
the three-loop closed-loop control specified by ADR-081: fast
|
||||
(~200 ms) for cadence and active probing, medium (~1 s) for channel
|
||||
selection and role transitions, slow (~30 s) for baseline
|
||||
recalibration. Pure `adaptive_controller_decide()` policy function is
|
||||
exposed in the header for offline unit testing. Default policy is
|
||||
conservative (`enable_channel_switch` and `enable_role_change` off);
|
||||
Kconfig surface added under "Adaptive Controller (ADR-081)".
|
||||
|
||||
### Fixed
|
||||
- **Firmware: SPI flash cache crash under high CSI callback pressure** (RuView#396, #397) — ESP32-S3 nodes crashed in `cache_ll_l1_resume_icache` / `wDev_ProcessFiq` after ~2400 callbacks when the promiscuous filter admitted DATA frames at 100–500 Hz. Fixed by narrowing the filter mask to `WIFI_PROMIS_FILTER_MASK_MGMT` (~10 Hz beacons), adding a 50 Hz early callback rate gate (`CSI_MIN_PROCESS_INTERVAL_US`) that drops excess callbacks before any processing work, and enabling `CONFIG_ESP_WIFI_EXTRA_IRAM_OPT=y` as defense-in-depth. Stability validated with a 4-min-per-node soak.
|
||||
- **Firmware: `filter_mac` / `node_id` clobber by WiFi driver init** (#232, #375, #385, #386, #390, #397) — `g_nvs_config` can be corrupted during `wifi_init_sta()` on some devices (confirmed on `80:b5:4e:c1:be:b8`), reverting `node_id` to the Kconfig default and producing garbage MAC-filter reads in the CSI callback (100–500 Hz). New `csi_collector_set_node_id()` API called from `app_main()` **before** `wifi_init_sta()` captures both fields into module-local statics (`s_node_id`, `s_filter_mac`, `s_filter_mac_set`). `csi_collector_init()` now runs a canary that distinguishes "early≠g_nvs_config" (corruption confirmed) from a no-op match. All CSI runtime paths use the defensive copies exclusively.
|
||||
- **Firmware: `edge_processing` sample rate mismatch** (#397) — `estimate_bpm_zero_crossing()` was called with a hard-coded `sample_rate = 20.0f`, but MGMT-only promiscuous delivers ~10 Hz. Breathing and heart-rate reports were 2× too high. Corrected to `10.0f` with an explicit comment tying it to the callback rate.
|
||||
- **`provision.py` esptool command form** (#391, #397) — ESP-IDF v5.4 bundles `esptool 4.10.0`, which only accepts `write_flash` (underscore). Standalone `pip install esptool` v5.x accepts both forms but prefers `write-flash`. #391 switched to `write-flash` which broke the documented ESP-IDF Python venv flow; #397 reverts to `write_flash` (works with both esptool 4.x and 5.x) with an inline comment warning future maintainers not to "re-fix" it.
|
||||
- **`provision.py` esptool v5 dry-run hint** (#391) — Stale `write_flash` (underscore) syntax in the dry-run manual-flash hint now uses `write-flash` (hyphenated) for esptool >= 5.x. The primary flash command was already correct.
|
||||
- **`provision.py` silent NVS wipe** (#391) — The script replaces the entire `csi_cfg` NVS namespace on every run, so partial invocations were silently erasing WiFi credentials and causing `Retrying WiFi connection (10/10)` in the field. Now refuses to run without `--ssid`, `--password`, and `--target-ip` unless `--force-partial` is passed. `--force-partial` prints a warning listing which keys will be wiped.
|
||||
- **Firmware: defensive `node_id` capture** (#232, #375, #385, #386, #390) — Users on multi-node deployments reported `node_id` reverting to the Kconfig default (`1`) in UDP frames and in the `csi_collector` init log, despite NVS loading the correct value. The root cause (memory corruption of `g_nvs_config`) has not been definitively isolated, but the UDP frame header is now tamper-proof: `csi_collector_init()` captures `g_nvs_config.node_id` into a module-local `s_node_id` once, and `csi_serialize_frame()` plus all other consumers (`edge_processing.c`, `wasm_runtime.c`, `display_ui.c`, `swarm_bridge_init`) read it via the new `csi_collector_get_node_id()` accessor. A canary logs `WARN` if `g_nvs_config.node_id` diverges from `s_node_id` at end-of-init, helping isolate the upstream corruption path. Validated on attached ESP32-S3 (COM8): NVS `node_id=2` propagates through boot log, capture log, init log, and byte[4] of every UDP frame.
|
||||
|
||||
### Docs
|
||||
- **CHANGELOG catch-up** (#367) — Added missing entries for v0.5.5, v0.6.0, and v0.7.0 releases.
|
||||
|
||||
## [v0.7.0] — 2026-04-06
|
||||
|
||||
Model release (no new firmware binary). Firmware remains at v0.6.0-esp32.
|
||||
|
||||
### Added
|
||||
- **Camera ground-truth training pipeline (ADR-079)** — End-to-end supervised WiFlow pose training using MediaPipe + real ESP32 CSI.
|
||||
- `scripts/collect-ground-truth.py` — MediaPipe PoseLandmarker webcam capture (17 COCO keypoints, 30fps), synchronized with CSI recording over nanosecond timestamps.
|
||||
- `scripts/align-ground-truth.js` — Time-aligns camera keypoints with 20-frame CSI windows by binary search, confidence-weighted averaging.
|
||||
- `scripts/train-wiflow-supervised.js` — 3-phase curriculum training (contrastive → supervised SmoothL1 → bone/temporal refinement) with 4 scale presets (lite/small/medium/full).
|
||||
- `scripts/eval-wiflow.js` — PCK@10/20/50, MPJPE, per-joint breakdown, baseline proxy mode.
|
||||
- `scripts/record-csi-udp.py` — Lightweight ESP32 CSI UDP recorder (no Rust build required).
|
||||
- **ruvector optimizations (O6-O10)** — Subcarrier selection (70→35, 50% reduction), attention-weighted subcarriers, Stoer-Wagner min-cut person separation, multi-SPSA gradient estimation, Mac M4 Pro training via Tailscale.
|
||||
- **Scalable WiFlow presets** — `lite` (189K params, ~19 min) through `full` (7.7M params, ~8 hrs) to match dataset size.
|
||||
- **Pre-trained WiFlow v1 model** — 92.9% PCK@20, 974 KB, 186,946 params. Published to [HuggingFace](https://huggingface.co/ruv/ruview) under `wiflow-v1/`.
|
||||
|
||||
### Validated
|
||||
- **92.9% PCK@20** pose accuracy from a 5-minute data collection session with one $9 ESP32-S3 and one laptop webcam.
|
||||
- Training pipeline validated on real paired data: 345 samples, 19 min training, eval loss 0.082, bone constraint 0.008.
|
||||
|
||||
## [v0.6.0-esp32] — 2026-04-03
|
||||
|
||||
### Added
|
||||
- **Pre-trained CSI sensing weights published** — First official pre-trained models on [HuggingFace](https://huggingface.co/ruv/ruview). `model.safetensors` (48 KB), `model-q4.bin` (8 KB 4-bit), `model-q2.bin` (4 KB), `presence-head.json`, per-node LoRA adapters.
|
||||
- **17 sensing applications** — Sleep monitor, apnea detector, stress monitor, gait analyzer, RF tomography, passive radar, material classifier, through-wall detector, device fingerprint, and more. Each as a standalone `scripts/*.js`.
|
||||
- **ADRs 069-078** — 10 new architecture decisions covering Cognitum Seed integration, self-supervised pretraining, ruvllm pipeline, WiFlow architecture, channel hopping, SNN, MinCut person separation, CNN spectrograms, novel RF applications, multi-frequency mesh.
|
||||
- **Kalman tracker** (PR #341 by @taylorjdawson) — temporal smoothing of pose keypoints.
|
||||
|
||||
### Fixed
|
||||
- Security fix merged via PR #310.
|
||||
|
||||
### Performance
|
||||
- Presence detection: 100% accuracy on 60,630 overnight samples. *(Retracted — that recording was single-class (one sleeping person, 6,062/6,063 frames "present"), so a constant "yes" scores ~99.98%. Superseded by the honest 82.3% held-out temporal-triplet metric; see [#882](https://github.com/ruvnet/RuView/issues/882). Kept here as the in-place public record.)*
|
||||
- Inference: 0.008 ms per sample, 164K embeddings/sec.
|
||||
- Contrastive self-supervised training: 51.6% improvement over baseline.
|
||||
|
||||
## [v0.5.5-esp32] — 2026-04-03
|
||||
|
||||
### Added
|
||||
- **WiFlow SOTA architecture (ADR-072)** — TCN + axial attention pose decoder, 1.8M params, 881 KB at 4-bit. 17 COCO keypoints from CSI amplitude only (no phase).
|
||||
- **Multi-frequency mesh scanning (ADR-073)** — ESP32 nodes hop across channels 1/3/5/6/9/11 at 200ms dwell. Neighbor WiFi networks used as passive radar illuminators. Null subcarriers reduced from 19% to 16%.
|
||||
- **Spiking neural network (ADR-074)** — STDP online learning, adapts to new rooms in <30s with no labels, 16-160x less compute than batch training.
|
||||
- **MinCut person counting (ADR-075)** — Stoer-Wagner min-cut on subcarrier correlation graph. Fixes #348 (was always reporting 4 people).
|
||||
- **CNN spectrogram embeddings (ADR-076)** — Treat 64×20 CSI as an image, produce 128-dim environment fingerprints (0.95+ same-room similarity).
|
||||
- **Graph transformer fusion** — Multi-node CSI fusion via GATv2 attention (replaces naive averaging).
|
||||
- **Camera-free pose training pipeline** — Trains 17-keypoint model from 10 sensor signals with no camera required.
|
||||
|
||||
### Fixed
|
||||
- **#348 person counting** — MinCut correctly counts 1-4 people (24/24 validation windows).
|
||||
|
||||
## [v0.5.4-esp32] — 2026-04-02
|
||||
|
||||
### Added
|
||||
- **ADR-069: ESP32 CSI → Cognitum Seed RVF ingest pipeline** — Live-validated pipeline connecting ESP32-S3 CSI sensing to Cognitum Seed (Pi Zero 2 W) edge intelligence appliance. 339 vectors ingested, 100% kNN validation, SHA-256 witness chain verified.
|
||||
- **Feature vector packet (magic 0xC5110003)** — New 48-byte packet with 8 normalized dimensions (presence, motion, breathing, heart rate, phase variance, person count, fall, RSSI) sent at 1 Hz alongside vitals.
|
||||
- **`scripts/seed_csi_bridge.py`** — Python bridge: UDP listener → HTTPS ingest with bearer token auth, `--validate` (kNN + PIR ground truth), `--stats`, `--compact` modes, hash-based vector IDs, NaN/inf rejection, source IP filtering, retry logic.
|
||||
- **Arena Physica research** — 26 research documents in `docs/research/` covering Maxwell's equations in WiFi sensing, Arena Physica Studio analysis, SOTA WiFi sensing 2025-2026, GOAP implementation plan for ESP32 + Pi Zero.
|
||||
- **Cognitum Seed MCP integration** — 114-tool MCP proxy enables AI assistants to query sensing state, vectors, witness chain, and device status directly.
|
||||
|
||||
### Fixed
|
||||
- **Compressed frame magic collision** — Reassigned compressed frame magic from `0xC5110003` to `0xC5110005` to free `0xC5110003` for feature vectors.
|
||||
- **Uninitialized `s_top_k[0]` read** — Guarded variance computation against `s_top_k_count == 0` in `send_feature_vector()`.
|
||||
- **Presence score normalization** — Bridge now divides by 15.0 instead of clamping, preserving dynamic range for raw values 1.41-14.92.
|
||||
- **Stale magic references** — Updated ADR-039, DDD model to reflect `0xC5110005` for compressed frames.
|
||||
|
||||
### Security
|
||||
- **Credential exposure remediation** — Removed hardcoded WiFi passwords and bearer tokens from source files. Added NVS binary/CSV patterns to `.gitignore`. Environment variable fallback for bearer token.
|
||||
- **NaN/Inf injection prevention** — Bridge validates all feature dimensions are finite before Seed ingest.
|
||||
- **UDP source filtering** — `--allowed-sources` argument restricts packet acceptance to known ESP32 IPs.
|
||||
|
||||
### Changed
|
||||
- Wire format table now includes 6 magic numbers: `0xC5110001` (raw), `0xC5110002` (vitals), `0xC5110003` (features), `0xC5110004` (WASM events), `0xC5110005` (compressed), `0xC5110006` (fused vitals).
|
||||
|
||||
## [v0.5.3-esp32] — 2026-03-30
|
||||
|
||||
### Added
|
||||
- **Cross-node RSSI-weighted feature fusion** — Multiple ESP32 nodes fuse CSI features using RSSI-based weighting. Closer node gets higher weight. Reduces variance noise by 29%, keypoint jitter by 72%.
|
||||
- **DynamicMinCut person separation** — Uses `ruvector_mincut::DynamicMinCut` on the subcarrier temporal correlation graph to detect independent motion clusters. Replaces variance-based heuristic for multi-person counting.
|
||||
- **RSSI-based position tracking** — Skeleton position driven by RSSI differential between nodes. Walk between ESP32s and the skeleton follows you.
|
||||
- **Per-node state pipeline (ADR-068)** — Each ESP32 node gets independent `HashMap<u8, NodeState>` with frame history, classification, vitals, and person count. Fixes #249 (the #1 user-reported issue).
|
||||
- **RuVector Phase 1-3 integration** — Subcarrier importance weighting, temporal keypoint smoothing (EMA), coherence gating, skeleton kinematic constraints (Jakobsen relaxation), compressed pose history.
|
||||
- **Client-side lerp smoothing** — UI keypoints interpolate between frames (alpha=0.15) for fluid skeleton movement.
|
||||
- **Multi-node mesh tests** — 8 integration tests covering 1-255 node configurations.
|
||||
- **`wifi_densepose` Python package** — `from wifi_densepose import WiFiDensePose` now works (#314).
|
||||
|
||||
### Fixed
|
||||
- **Watchdog crash on busy LANs (#321)** — Batch-limited edge_dsp to 4 frames before 20ms yield. Fixed idle-path busy-spin (`pdMS_TO_TICKS(5)==0`).
|
||||
- **No detection from edge vitals (#323)** — Server now generates `sensing_update` from Tier 2+ vitals packets.
|
||||
- **RSSI byte offset mismatch (#332)** — Server parsed RSSI from wrong byte (was reading sequence counter).
|
||||
- **Stack overflow risk** — Moved 4KB of BPM scratch buffers from stack to static storage.
|
||||
- **Stale node memory leak** — `node_states` HashMap evicts nodes inactive >60s.
|
||||
- **Unsafe raw pointer removed** — Replaced with safe `.clone()` for adaptive model borrow.
|
||||
- **Firmware CI** — Upgraded to IDF v5.4, replaced `xxd` with `od` (#327).
|
||||
- **Person count double-counting** — Multi-node aggregation changed from `sum` to `max`.
|
||||
- **Skeleton jitter** — Removed tick-based noise, dampened procedural animation, recalibrated feature scaling for real ESP32 data.
|
||||
|
||||
### Changed
|
||||
- Motion-responsive skeleton: arm swing (0-80px) driven by CSI variance, leg kick (0-50px) by motion_band_power, vertical bob when walking.
|
||||
- Person count thresholds recalibrated for real ESP32 hardware (1→2 at 0.70, EMA alpha 0.04).
|
||||
- Vital sign filtering: larger median window (31), faster EMA (0.05), looser HR jump filter (15 BPM).
|
||||
- Vendored ruvector updated to v2.1.0-40 (316 commits ahead).
|
||||
|
||||
### Benchmarks (2-node mesh, COM6 + COM9, 30s)
|
||||
| Metric | Baseline | v0.5.3 | Improvement |
|
||||
|--------|----------|--------|-------------|
|
||||
| Variance noise | 109.4 | 77.6 | **-29%** |
|
||||
| Feature stability | std=154.1 | std=105.4 | **-32%** |
|
||||
| Keypoint jitter | std=4.5px | std=1.3px | **-72%** |
|
||||
| Confidence | 0.643 | 0.686 | **+7%** |
|
||||
| Presence accuracy | 93.4% | 94.6% | **+1.3pp** |
|
||||
|
||||
### Verified
|
||||
- Real hardware: COM6 (node 1) + COM9 (node 2) on ruv.net WiFi
|
||||
- All 284 Rust tests pass, 352 signal crate tests pass
|
||||
- Firmware builds clean at 843 KB
|
||||
- QEMU CI: 11/11 jobs green
|
||||
|
||||
## [v0.5.2-esp32] — 2026-03-28
|
||||
|
||||
### Fixed
|
||||
- RSSI byte offset in frame parser (#332)
|
||||
- Per-node state pipeline for multi-node sensing (#249)
|
||||
- Firmware CI upgraded to IDF v5.4 (#327)
|
||||
|
||||
## [v0.5.1-esp32] — 2026-03-27
|
||||
|
||||
### Fixed
|
||||
- Watchdog crash on busy LANs (#321)
|
||||
- No detection from edge vitals (#323)
|
||||
- `wifi_densepose` Python package import (#314)
|
||||
- Pre-compiled firmware binaries added to release
|
||||
|
||||
## [v0.5.0-esp32] — 2026-03-15
|
||||
|
||||
### Added
|
||||
@@ -800,7 +239,7 @@ Major release: complete Rust sensing server, full DensePose training pipeline, R
|
||||
- `PresenceClassifier` — rule-based 3-state classification (ABSENT / PRESENT_STILL / ACTIVE)
|
||||
- Cross-receiver agreement scoring for multi-AP confidence boosting
|
||||
- WebSocket sensing server (`ws_server.py`) broadcasting JSON at 2 Hz
|
||||
- Deterministic CSI proof bundles for reproducible verification (`archive/v1/data/proof/`)
|
||||
- Deterministic CSI proof bundles for reproducible verification (`v1/data/proof/`)
|
||||
- Commodity sensing unit tests (`b391638`)
|
||||
|
||||
### Changed
|
||||
@@ -808,7 +247,7 @@ Major release: complete Rust sensing server, full DensePose training pipeline, R
|
||||
|
||||
### Fixed
|
||||
- Review fixes for end-to-end training pipeline (`45f0304`)
|
||||
- Dockerfile paths updated from `src/` to `archive/v1/src/` (`7872987`)
|
||||
- Dockerfile paths updated from `src/` to `v1/src/` (`7872987`)
|
||||
- IoT profile installer instructions updated for aggregator CLI (`f460097`)
|
||||
- `process.env` reference removed from browser ES module (`e320bc9`)
|
||||
|
||||
|
||||
@@ -3,26 +3,25 @@
|
||||
## Project: wifi-densepose
|
||||
|
||||
WiFi-based human pose estimation using Channel State Information (CSI).
|
||||
Dual codebase: Python v1 (`v1/`) and Rust port (`v2/`).
|
||||
Dual codebase: Python v1 (`v1/`) and Rust port (`rust-port/wifi-densepose-rs/`).
|
||||
### Key Rust Crates
|
||||
| Crate | Description |
|
||||
|-------|-------------|
|
||||
| `wifi-densepose-core` | Core types, traits, error types, CSI frame primitives |
|
||||
| `wifi-densepose-signal` | SOTA signal processing + RuvSense multistatic sensing (16 modules) |
|
||||
| `wifi-densepose-signal` | SOTA signal processing + RuvSense multistatic sensing (14 modules) |
|
||||
| `wifi-densepose-nn` | Neural network inference (ONNX, PyTorch, Candle backends) |
|
||||
| `wifi-densepose-train` | Training pipeline with ruvector integration + ruview_metrics; MAE pretraining recipe (`mae.rs`, ADR-152 §2.3) + WiFlow-STD port (`wiflow_std/`, tch-gated) |
|
||||
| `wifi-densepose-train` | Training pipeline with ruvector integration + ruview_metrics |
|
||||
| `wifi-densepose-mat` | Mass Casualty Assessment Tool — disaster survivor detection |
|
||||
| `wifi-densepose-hardware` | ESP32 aggregator, TDM protocol, channel hopping firmware; `ieee80211bf/` 802.11bf forward-compat protocol model (ADR-153) |
|
||||
| `wifi-densepose-hardware` | ESP32 aggregator, TDM protocol, channel hopping firmware |
|
||||
| `wifi-densepose-ruvector` | RuVector v2.0.4 integration + cross-viewpoint fusion (5 modules) |
|
||||
| `wifi-densepose-api` | REST API (Axum) |
|
||||
| `wifi-densepose-db` | Database layer (Postgres, SQLite, Redis) |
|
||||
| `wifi-densepose-config` | Configuration management |
|
||||
| `wifi-densepose-wasm` | WebAssembly bindings for browser deployment |
|
||||
| `wifi-densepose-cli` | CLI tool (`wifi-densepose` binary) — `calibrate`/`calibrate-serve`/`enroll`/`train-room`/`room-watch` + MAT (MAT gated behind the `mat` feature; build `--no-default-features` for the aarch64/appliance calibration binary) |
|
||||
| `wifi-densepose-calibration` | ADR-151 per-room calibration & specialist training — `baseline → enroll → extract → train` → bank of small specialists (presence/posture/breathing/heartbeat/restlessness/anomaly) + multistatic fusion; pure Rust, edge-deployable |
|
||||
| `wifi-densepose-cli` | CLI tool (`wifi-densepose` binary) |
|
||||
| `wifi-densepose-sensing-server` | Lightweight Axum server for WiFi sensing UI |
|
||||
| `wifi-densepose-wifiscan` | Multi-BSSID WiFi scanning (ADR-022) |
|
||||
| `wifi-densepose-vitals` | ESP32 CSI-grade vital sign extraction (ADR-021) |
|
||||
| `nvsim` | Deterministic NV-diamond magnetometer pipeline simulator (ADR-089) — standalone leaf, WASM-ready |
|
||||
| `vendor/rvcsi` (submodule) | **rvCSI** — edge RF sensing runtime (ADR-095/096): 9 crates (`rvcsi-core`/`-dsp`/`-events`/`-adapter-file`/`-adapter-nexmon`/`-ruvector`/`-runtime`/`-node`/`-cli`). Lives in its own repo ([github.com/ruvnet/rvcsi](https://github.com/ruvnet/rvcsi)), vendored here under `vendor/rvcsi`, published to crates.io as `rvcsi-* 0.3.x` and to npm as `@ruv/rvcsi`. Not a `v2/` workspace member — depend on the published crates (or the submodule's `crates/rvcsi-*` paths). Normalized `CsiFrame`/`CsiWindow`/`CsiEvent` schema, validate-before-FFI, reusable DSP, typed confidence-scored events, the napi-c Nexmon shim (real nexmon_csi `.pcap` from a Raspberry Pi 5 / 4 / 3B+ — BCM43455c0), the napi-rs SDK, the `rvcsi` CLI, a Claude Code plugin. |
|
||||
| `ruview-swarm` | Drone swarm control system (ADR-148) — hierarchical-mesh topology, Raft consensus, MARL, CSI sensing payload, MAVLink/PX4 compat, Ruflo AI-agent integration |
|
||||
|
||||
### RuvSense Modules (`signal/src/ruvsense/`)
|
||||
| Module | Purpose |
|
||||
@@ -40,8 +39,6 @@ Dual codebase: Python v1 (`v1/`) and Rust port (`v2/`).
|
||||
| `cross_room.rs` | Environment fingerprinting, transition graph |
|
||||
| `gesture.rs` | DTW template matching gesture classifier |
|
||||
| `adversarial.rs` | Physically impossible signal detection, multi-link consistency |
|
||||
| `cir.rs` | ADR-134 CSI→CIR via ISTA L1 sparse recovery (NeumannSolver warm-start) |
|
||||
| `calibration.rs` | ADR-135 empty-room baseline (Welford amplitude + von Mises phase, drift trigger) |
|
||||
|
||||
### Cross-Viewpoint Fusion (`ruvector/src/viewpoint/`)
|
||||
| Module | Purpose |
|
||||
@@ -72,17 +69,14 @@ All 5 ruvector crates integrated in workspace:
|
||||
- ADR-030: RuvSense persistent field model (Proposed)
|
||||
- ADR-031: RuView sensing-first RF mode (Proposed)
|
||||
- ADR-032: Multistatic mesh security hardening (Proposed)
|
||||
- ADR-148: Drone swarm control system / `ruview-swarm` (In Progress)
|
||||
- ADR-152: WiFi-Pose SOTA 2026 intake — geometry conditioning, WiFlow-STD benchmark (measurement (a) complete: claims MEASURED-EQUIVALENT at ~96% PCK@20), MAE recipe (Proposed; §2.1–2.3, 2.6 implemented)
|
||||
- ADR-153: IEEE 802.11bf-2025 forward-compatibility protocol model (Accepted — amends ADR-152 §2.4)
|
||||
|
||||
### Supported Hardware
|
||||
|
||||
| Device | Port | Chip | Role | Cost |
|
||||
|--------|------|------|------|------|
|
||||
| ESP32-S3 (8MB flash) | COM9 (ruvzen, was COM7) | Xtensa dual-core | WiFi CSI sensing node | ~$9 |
|
||||
| ESP32-S3 (8MB flash) | COM7 | Xtensa dual-core | WiFi CSI sensing node | ~$9 |
|
||||
| ESP32-S3 SuperMini (4MB) | — | Xtensa dual-core | WiFi CSI (compact) | ~$6 |
|
||||
| ESP32-C6 + Seeed MR60BHA2 | COM12 (ruvzen, was COM4) | RISC-V + 60 GHz FMCW | mmWave HR/BR/presence + WiFi CSI | ~$15 |
|
||||
| ESP32-C6 + Seeed MR60BHA2 | COM4 | RISC-V + 60 GHz FMCW | mmWave HR/BR/presence | ~$15 |
|
||||
| HLK-LD2410 | — | 24 GHz FMCW | Presence + distance | ~$3 |
|
||||
|
||||
**Not supported:** ESP32 (original), ESP32-C3 — single-core, can't run CSI DSP pipeline.
|
||||
@@ -90,17 +84,17 @@ All 5 ruvector crates integrated in workspace:
|
||||
### Build & Test Commands (this repo)
|
||||
```bash
|
||||
# Rust — full workspace tests (1,031+ tests, ~2 min)
|
||||
cd v2
|
||||
cd rust-port/wifi-densepose-rs
|
||||
cargo test --workspace --no-default-features
|
||||
|
||||
# Rust — single crate check (no GPU needed)
|
||||
cargo check -p wifi-densepose-train --no-default-features
|
||||
|
||||
# Python — deterministic proof verification (SHA-256)
|
||||
python archive/v1/data/proof/verify.py
|
||||
python v1/data/proof/verify.py
|
||||
|
||||
# Python — test suite
|
||||
cd archive/v1 && python -m pytest tests/ -x -q
|
||||
cd v1 && python -m pytest tests/ -x -q
|
||||
```
|
||||
|
||||
### ESP32 Firmware Build (Windows — Python subprocess required)
|
||||
@@ -139,14 +133,17 @@ Crates must be published in dependency order:
|
||||
2. `wifi-densepose-vitals` (no internal deps)
|
||||
3. `wifi-densepose-wifiscan` (no internal deps)
|
||||
4. `wifi-densepose-hardware` (no internal deps)
|
||||
5. `wifi-densepose-signal` (depends on core)
|
||||
6. `wifi-densepose-nn` (no internal deps, workspace only)
|
||||
7. `wifi-densepose-ruvector` (no internal deps, workspace only)
|
||||
8. `wifi-densepose-train` (depends on signal, nn)
|
||||
9. `wifi-densepose-mat` (depends on core, signal, nn)
|
||||
10. `wifi-densepose-wasm` (depends on mat)
|
||||
11. `wifi-densepose-sensing-server` (depends on wifiscan)
|
||||
12. `wifi-densepose-cli` (depends on mat)
|
||||
5. `wifi-densepose-config` (no internal deps)
|
||||
6. `wifi-densepose-db` (no internal deps)
|
||||
7. `wifi-densepose-signal` (depends on core)
|
||||
8. `wifi-densepose-nn` (no internal deps, workspace only)
|
||||
9. `wifi-densepose-ruvector` (no internal deps, workspace only)
|
||||
10. `wifi-densepose-train` (depends on signal, nn)
|
||||
11. `wifi-densepose-mat` (depends on core, signal, nn)
|
||||
12. `wifi-densepose-api` (no internal deps)
|
||||
13. `wifi-densepose-wasm` (depends on mat)
|
||||
14. `wifi-densepose-sensing-server` (depends on wifiscan)
|
||||
15. `wifi-densepose-cli` (depends on mat)
|
||||
|
||||
### Validation & Witness Verification (ADR-028)
|
||||
|
||||
@@ -154,12 +151,12 @@ Crates must be published in dependency order:
|
||||
|
||||
```bash
|
||||
# 1. Rust tests — must be 1,031+ passed, 0 failed
|
||||
cd v2
|
||||
cd rust-port/wifi-densepose-rs
|
||||
cargo test --workspace --no-default-features
|
||||
|
||||
# 2. Python proof — must print VERDICT: PASS
|
||||
cd ..
|
||||
python archive/v1/data/proof/verify.py
|
||||
cd ../..
|
||||
python v1/data/proof/verify.py
|
||||
|
||||
# 3. Generate witness bundle (includes both above + firmware hashes)
|
||||
bash scripts/generate-witness-bundle.sh
|
||||
@@ -172,8 +169,8 @@ bash VERIFY.sh
|
||||
**If the Python proof hash changes** (e.g., numpy/scipy version update):
|
||||
```bash
|
||||
# Regenerate the expected hash, then verify it passes
|
||||
python archive/v1/data/proof/verify.py --generate-hash
|
||||
python archive/v1/data/proof/verify.py
|
||||
python v1/data/proof/verify.py --generate-hash
|
||||
python v1/data/proof/verify.py
|
||||
```
|
||||
|
||||
**Witness bundle contents** (`dist/witness-bundle-ADR028-<sha>.tar.gz`):
|
||||
@@ -186,9 +183,9 @@ python archive/v1/data/proof/verify.py
|
||||
- `VERIFY.sh` — One-command self-verification for recipients
|
||||
|
||||
**Key proof artifacts:**
|
||||
- `archive/v1/data/proof/verify.py` — Trust Kill Switch: feeds reference signal through production pipeline, hashes output
|
||||
- `archive/v1/data/proof/expected_features.sha256` — Published expected hash
|
||||
- `archive/v1/data/proof/sample_csi_data.json` — 1,000 synthetic CSI frames (seed=42)
|
||||
- `v1/data/proof/verify.py` — Trust Kill Switch: feeds reference signal through production pipeline, hashes output
|
||||
- `v1/data/proof/expected_features.sha256` — Published expected hash
|
||||
- `v1/data/proof/sample_csi_data.json` — 1,000 synthetic CSI frames (seed=42)
|
||||
- `docs/WITNESS-LOG-028.md` — 11-step reproducible verification procedure
|
||||
- `docs/adr/ADR-028-esp32-capability-audit.md` — Complete audit record
|
||||
|
||||
@@ -214,13 +211,13 @@ Active feature branch: `ruvsense-full-implementation` (PR #77)
|
||||
- NEVER save to root folder — use the directories below
|
||||
- `docs/adr/` — Architecture Decision Records (43 ADRs)
|
||||
- `docs/ddd/` — Domain-Driven Design models
|
||||
- `v2/crates/` — Rust workspace crates (15 crates)
|
||||
- `v2/crates/wifi-densepose-signal/src/ruvsense/` — RuvSense multistatic modules (14 files)
|
||||
- `v2/crates/wifi-densepose-ruvector/src/viewpoint/` — Cross-viewpoint fusion (5 files)
|
||||
- `v2/crates/wifi-densepose-hardware/src/esp32/` — ESP32 TDM protocol
|
||||
- `rust-port/wifi-densepose-rs/crates/` — Rust workspace crates (15 crates)
|
||||
- `rust-port/wifi-densepose-rs/crates/wifi-densepose-signal/src/ruvsense/` — RuvSense multistatic modules (14 files)
|
||||
- `rust-port/wifi-densepose-rs/crates/wifi-densepose-ruvector/src/viewpoint/` — Cross-viewpoint fusion (5 files)
|
||||
- `rust-port/wifi-densepose-rs/crates/wifi-densepose-hardware/src/esp32/` — ESP32 TDM protocol
|
||||
- `firmware/esp32-csi-node/main/` — ESP32 C firmware (channel hopping, NVS config, TDM)
|
||||
- `archive/v1/src/` — Python source (core, hardware, services, api)
|
||||
- `archive/v1/data/proof/` — Deterministic CSI proof bundles
|
||||
- `v1/src/` — Python source (core, hardware, services, api)
|
||||
- `v1/data/proof/` — Deterministic CSI proof bundles
|
||||
- `.claude-flow/` — Claude Flow coordination state (committed for team sharing)
|
||||
- `.claude/` — Claude Code settings, agents, memory (committed for team sharing)
|
||||
|
||||
@@ -246,7 +243,7 @@ Active feature branch: `ruvsense-full-implementation` (PR #77)
|
||||
Before merging any PR, verify each item applies and is addressed:
|
||||
|
||||
1. **Rust tests pass** — `cargo test --workspace --no-default-features` (1,031+ passed, 0 failed)
|
||||
2. **Python proof passes** — `python archive/v1/data/proof/verify.py` (VERDICT: PASS)
|
||||
2. **Python proof passes** — `python v1/data/proof/verify.py` (VERDICT: PASS)
|
||||
3. **README.md** — Update platform tables, crate descriptions, hardware tables, feature summaries if scope changed
|
||||
4. **CLAUDE.md** — Update crate table, ADR list, module tables, version if scope changed
|
||||
5. **CHANGELOG.md** — Add entry under `[Unreleased]` with what was added/fixed/changed
|
||||
|
||||
@@ -1,50 +0,0 @@
|
||||
# AetherArena ("AA") — The Official Spatial-Intelligence Benchmark
|
||||
|
||||
> **Public leaderboard. Private evaluation split. Open scorer. Signed results.**
|
||||
|
||||
AetherArena is a **standalone, project-agnostic benchmark** for camera-free **spatial intelligence** — pose, presence, occupancy, tracking, and vitals from RF/WiFi (and, over time, mmWave / UWB / radar / lidar / multimodal). It is **not** a single-vendor leaderboard: any team, framework, or sensing modality can enter, and every entrant — including the RuView baseline that donated the seed scorer — is scored by the identical, open, pinned harness.
|
||||
|
||||
Specified in [ADR-149](../docs/adr/ADR-149-public-community-leaderboard-huggingface.md) (Accepted).
|
||||
|
||||
Canonical home: **`ruvnet/aether-arena`** + a Hugging Face Space (deploy pending — see `STATUS`).
|
||||
|
||||
---
|
||||
|
||||
## Why
|
||||
|
||||
WiFi/RF spatial sensing has no shared yardstick — papers self-report against inconsistent splits and metrics, with **no accounting for latency, reproducibility, or privacy leakage**. AA fixes the *measurement*, not just the models: a single deterministic scorer, a private held-out split nobody can train on, and a signed result ledger that can't be silently edited.
|
||||
|
||||
## What gets measured (v0)
|
||||
|
||||
| Category | Metric | Status |
|
||||
|----------|--------|--------|
|
||||
| **Pose** | PCK@0.2 (all / torso), OKS | Ranked |
|
||||
| **Presence** | accuracy, FP/FN | Ranked |
|
||||
| **Edge latency** | p50 / p95 / p99 ms | Ranked |
|
||||
| **Determinism** | proof-hash pass/fail | Ranked (gate) |
|
||||
| Tracking (MOTA) | — | activates when multi-person clips land |
|
||||
| Vitals (BPM err) | — | activates when paired vitals ground truth lands |
|
||||
| **Privacy leakage** | membership-inference ∈ [0,1] | **gated — not ranked** until the attacker ships |
|
||||
| Cross-room | degradation ratio | coming soon |
|
||||
|
||||
The headline rank is the **category metric**; an optional `arena_score = quality × latency_factor × privacy_factor × determinism_gate` is exposed alongside (never instead) so accuracy can't win at any cost. See ADR-149 §2.5.
|
||||
|
||||
## How scoring works
|
||||
|
||||
The scorer is RuView's **already-published** `wifi-densepose-train` acceptance harness (`ruview_metrics` + ADR-145 `ablation`), run in a pinned sandbox. **You submit a model, not predictions** — predictions on data you hold prove nothing. Your model is scored against a **private** MM-Fi held-out split (CC BY-NC 4.0; Wi-Pose excluded for redistribution reasons), and one **signed, append-only** row is written to the results ledger with a determinism proof hash.
|
||||
|
||||
Submission lifecycle: `submitted → validated → quarantined → smoke_scored → full_scored → published` (or `rejected` with a reason). The model only ever runs inside a no-network, read-only-FS sandbox.
|
||||
|
||||
## Submit (when the Space is live)
|
||||
|
||||
1. Write a manifest: [`schema/aa-submission.toml`](schema/aa-submission.toml).
|
||||
2. Push your model artifact (`.safetensors` / `.rvf` / LoRA adapter) + manifest to the Space.
|
||||
3. Watch it move through the lifecycle; your signed row appears on the board.
|
||||
|
||||
## Verify it's fair (you don't have to trust us)
|
||||
|
||||
See [`VERIFY.md`](VERIFY.md) — run the **open scorer** locally on the **public smoke split**, reproduce the determinism hash, and confirm RuView's own entries were scored by the identical path. That five-step check is the launch gate (ADR-149 §7).
|
||||
|
||||
## Neutrality
|
||||
|
||||
AA is a neutral commons. The scorer is open and versioned; any metric change is a public `harness_version` bump that **re-scores all entries**. RuView donated the seed harness and enters as one baseline — it gets no special treatment (ADR-149 §2.8).
|
||||
@@ -1,30 +0,0 @@
|
||||
# AetherArena — Build Status
|
||||
|
||||
Tracks ADR-149 implementation milestones. "Complete" = benchmark **infrastructure** done,
|
||||
tested, CI-gated, deploy-ready, RuView baseline entered, §7 acceptance test passing.
|
||||
Model **SOTA** (e.g. MM-Fi PCK@20 ~72%) is a separate long-running ML effort, blocked on
|
||||
ADR-079 camera-ground-truth collection — *not* an infra-completion blocker.
|
||||
|
||||
| # | Milestone | Status |
|
||||
|---|-----------|--------|
|
||||
| M1 | ADR-149 Accepted + committed | ✅ done |
|
||||
| M2 | Scorer runner (`aa_score_runner`) — **real model scoring** + witness (proof+inputs hash) + **repeatability analysis** | ✅ done — builds `--no-default-features`, determinism gate PASS, repeatable 16/16 |
|
||||
| M3 | CI harness-gate workflow (PR runs scorer + repeatability + real-scoring smoke + ledger verify) | ✅ done — `.github/workflows/aether-arena-harness.yml` |
|
||||
| M4 | Scaffold: README + submission schema + VERIFY (acceptance test) | ✅ done |
|
||||
| M5 | Public smoke split (committed) + private MM-Fi held-out split prep | 🟡 smoke split done (`fixtures/smoke_*.json`); private MM-Fi prep pending |
|
||||
| M6 | HF Space (Gradio) — leaderboard + ledger integrity + submit/verify/about | ✅ deployed → https://huggingface.co/spaces/ruvnet/aether-arena (sandboxed scorer container = later hardening) |
|
||||
| M7 | **Witness ledger chain** — append-only, hash-chained, tamper-evident | ✅ done — `ledger/ledger_tools.py` (seed/append/verify); tamper test fails as designed |
|
||||
| M8 | Public launch | ✅ Space **LIVE** (gradio 5.9.1, serving 200) — **board empty, awaiting first real harness score** (benchmark-first: no seeded numbers) |
|
||||
|
||||
## v0 infrastructure: COMPLETE
|
||||
Implement ✅ · Test ✅ · Deploy to HF ✅ (https://huggingface.co/spaces/ruvnet/aether-arena) · Instructions+Verification ✅ · PR runs the harness ✅ (PR #874, AA harness gate **passed**).
|
||||
Remaining = data + hardening, not infra: private MM-Fi held-out split (M5), sandboxed scorer container (M6), privacy-leakage attacker (gated category), and **model SOTA** (separate ML effort, blocked on ADR-079 — explicitly not an infra exit).
|
||||
|
||||
## Benchmark-first posture (per user direction)
|
||||
- **No placeholder numbers on the board.** The ledger seeds to genesis only; every result is a real scoring-pipeline witness. RuView gets no seeded baseline.
|
||||
- **Witness chain** = `inputs_sha256` (binds witness to exact inputs) + `proof_sha256` (cross-platform-stable score hash) + the append-only hash-chained ledger. Repeatability analysis (`--repeat N`) proves the proof hash is identical across runs.
|
||||
|
||||
## Blockers / decisions needed
|
||||
- **HF deploy (M6)** — token is in GCP Secret Manager (`HUGGINGFACE_API_KEY`); creating the public `ruvnet/aether-arena` Space still wants explicit go.
|
||||
- **MM-Fi is CC BY-NC** → AA must stay non-commercial / legally distinct from the commercial RuView product.
|
||||
- **Private MM-Fi split (M5)** — needs the dataset pulled + a held-out split assembled before real public scoring replaces the smoke fixture.
|
||||
@@ -1,78 +0,0 @@
|
||||
# Verifying AetherArena (you don't have to trust us)
|
||||
|
||||
AA's credibility rests on a stranger being able to reproduce a score and see that the rules are fair. This is the **launch gate** (ADR-149 §7): v0 does not ship until all five checks below pass for someone with no insider access.
|
||||
|
||||
> **Wider context:** this page covers the *leaderboard scorer*. For the whole-platform answer to
|
||||
> "is this real / does it actually work?" — including the deterministic pipeline proof, the
|
||||
> published models + public-benchmark numbers, and the built-in-public development trail — see
|
||||
> [`docs/proof-of-capabilities.md`](../docs/proof-of-capabilities.md).
|
||||
|
||||
## The open scorer
|
||||
|
||||
The scoring engine is a pure-Rust, GPU-free binary: `aa_score_runner` in `wifi-densepose-train`. It runs the real `ruview_metrics` pose-acceptance harness on a fixed fixture and emits a cross-platform-stable SHA-256 **determinism proof**.
|
||||
|
||||
### Reproduce the determinism hash locally
|
||||
|
||||
```bash
|
||||
cd v2
|
||||
# Verify the committed expected hash still matches (this is the CI gate):
|
||||
cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features
|
||||
# → prints the witness (inputs_sha256 + proof_sha256) and "VERDICT: PASS"
|
||||
|
||||
# See the witness row as JSON:
|
||||
cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --json
|
||||
```
|
||||
|
||||
### Witness chain — proof + repeatability analysis
|
||||
|
||||
Every score is a **witness**: `inputs_sha256` (binds it to the exact inputs scored)
|
||||
+ `proof_sha256` (cross-platform-stable hash of the quantised score) + `harness_version`.
|
||||
Witnesses are recorded in an **append-only, hash-chained ledger** (each row references
|
||||
the previous row's hash), so a silent edit to any past row breaks the chain.
|
||||
|
||||
```bash
|
||||
# Repeatability: run the scorer K times, confirm ONE identical proof hash:
|
||||
cd v2
|
||||
cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --repeat 16
|
||||
# → {"repeatability":{"runs":16,"unique_proof_hashes":1,"repeatable":true,...}}
|
||||
|
||||
# Real model scoring (score predictions against an eval split):
|
||||
cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- \
|
||||
--split ../aether-arena/fixtures/smoke_split.json \
|
||||
--pred ../aether-arena/fixtures/smoke_pred.json --json
|
||||
|
||||
# Verify the witness ledger chain is intact (tamper-evident):
|
||||
cd ../aether-arena/ledger && python3 ledger_tools.py verify
|
||||
# → "OK: N rows, chain intact" (edit any row and it reports the broken link)
|
||||
```
|
||||
|
||||
The expected hash is committed at [`fixtures/expected_score.sha256`](fixtures/expected_score.sha256). Same harness version + same fixture → same hash on glibc / MSVC / Apple. If your local run prints `VERDICT: PASS`, you have reproduced the scorer.
|
||||
|
||||
### What happens if the scoring maths changes
|
||||
|
||||
Any edit to `ruview_metrics.rs`, `ablation.rs`, or `aa_score_runner.rs` moves the hash and **fails the CI gate** (`.github/workflows/aether-arena-harness.yml`) until the maintainer regenerates and reviews:
|
||||
|
||||
```bash
|
||||
cargo run -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --generate-hash \
|
||||
> aether-arena/fixtures/expected_score.sha256
|
||||
```
|
||||
|
||||
So a scorer change is always a reviewed, public diff — never silent. That's `harness_version` pinning + `determinism_gate` in action (ADR-149 §2.4–§2.5).
|
||||
|
||||
## The five-step acceptance test (v0 launch gate)
|
||||
|
||||
A stranger must be able to:
|
||||
|
||||
1. **Submit** a model (artifact + `schema/aa-submission.toml`) with no insider help.
|
||||
2. **Get a deterministic score** — same model + same `harness_version` → same numbers.
|
||||
3. **See the signed row** appended to the public results ledger.
|
||||
4. **Rerun the scorer locally** on the public smoke split and reproduce the logic (the command above).
|
||||
5. **Understand why the rank is fair** — private split, open scorer, pinned version, proof hash — from these docs alone.
|
||||
|
||||
If any step fails, v0 is not ready.
|
||||
|
||||
## Current status
|
||||
|
||||
- ✅ Step 4 (rerun the open scorer locally, reproduce the hash) — **works today** via `aa_score_runner`.
|
||||
- ✅ CI harness gate runs the scorer on every PR.
|
||||
- ⏳ Steps 1–3, 5 (HF Space submission flow + signed ledger) — in progress; require the HF Space deploy (needs an HF token / maintainer authorization).
|
||||
@@ -1,87 +0,0 @@
|
||||
# RuView Calibration Service (reference implementation)
|
||||
|
||||
Turn a **shared WiFi-CSI pose base model** into a room-specific one with a **30-second labeled
|
||||
calibration** and a **~11 KB per-room LoRA adapter**. This is the deployable resolution of the
|
||||
cross-subject / cross-environment generalization problem (full study: [ADR-150 §3.3–3.6](../../docs/adr/ADR-150-rf-foundation-encoder.md)).
|
||||
|
||||
## Why
|
||||
|
||||
Zero-shot WiFi pose generalizes poorly to a **new room or new person** — an unseen room can drop a
|
||||
strong model to near-random. But that gap is **not** algorithmically closeable (CORAL, DANN,
|
||||
instance-norm, contrastive foundation-pretraining all failed) and **not** closeable by collecting
|
||||
more subjects (saturates ~64%). It **is** closeable, cheaply, at deployment time: a handful of
|
||||
labeled frames from the actual room pin down its multipath instantly.
|
||||
|
||||
| Deployment case | Zero-shot | + in-room calibration |
|
||||
|-----------------|----------:|----------------------:|
|
||||
| Same room, new person (cross-subject) | 64% | **76%** (200 samples) |
|
||||
| **New room + new person (cross-environment)** | **~10%** | **60% @ 5 samples → 73% @ 200** |
|
||||
|
||||
**Verified demo (this code, source-only base on an unseen MM-Fi room E04):**
|
||||
`zero-shot 3.09% → after 200-sample calibration 74.29%` (+71 pts).
|
||||
|
||||
## How it works
|
||||
|
||||
A frozen shared **base** (transformer + temporal attention pool + skeleton-graph head, the published
|
||||
[`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose)) plus a
|
||||
tiny **LoRA adapter** (rank 8 on the input projection + pose head — **11,200 params ≈ 11 KB int8 /
|
||||
22 KB fp16**) fitted per room. Thousands of room-adapters hang off one base.
|
||||
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
# 1) Capture a short labeled clip in the deployment room -> calib.npz {X:[N,3,114,10], Y:[N,17,2]}
|
||||
# (~100–200 samples recommended; below ~20 the adapter can underperform zero-shot)
|
||||
|
||||
# 2) Fit the per-room adapter (~11 KB):
|
||||
python calibrate.py --base pose_mmfi_best.pt --data calib.npz --out room.adapter.npz
|
||||
|
||||
# 3) Run calibrated inference (base + room adapter):
|
||||
python infer.py --base pose_mmfi_best.pt --adapter room.adapter.npz --data frames.npz --out kp.npy
|
||||
# omit --adapter to run the uncalibrated (zero-shot) base
|
||||
```
|
||||
|
||||
`X` is CSI amplitude `[N, 3 antennas, 114 subcarriers, 10 frames]` (per-sample standardization is
|
||||
applied internally). `Y` is `[N,17,2]` COCO keypoints in `[0,1]`.
|
||||
|
||||
## Calibration budget (measured, rank-8 LoRA, 3 seeds — ADR-150 §3.5)
|
||||
|
||||
| Labeled samples/room | cross-subject | cross-environment |
|
||||
|---------------------:|--------------:|------------------:|
|
||||
| 0 (zero-shot) | 64% | ~10% |
|
||||
| 5 | — | 60% |
|
||||
| 20 | 66% | 66% |
|
||||
| 50 | 70% | 70% |
|
||||
| 200 | 72% | 73% |
|
||||
|
||||
Knee at ~50 samples (~70%); **below ~20 samples the adapter can hurt** (too few to fit reliably).
|
||||
|
||||
## Two models, two producers (not interchangeable)
|
||||
|
||||
Adapters are **model-specific**. There are two calibration producers here:
|
||||
|
||||
| Producer | Target model | Input | Adapter format | Consumer |
|
||||
|----------|--------------|-------|----------------|----------|
|
||||
| `calibrate.py` | MM-Fi **transformer** (`pose_mmfi_best.pt`, 3×114×10) | `[N,3,114,10]` | `.npz` (`proj`/`head` LoRA) | this Python `infer.py` |
|
||||
| `cog_calibrate.py` | cog **conv+MLP** (`pose_v1.safetensors`, 56×20) | `[N,56,20]` | `.safetensors` (`fc1.a`/`fc1.b`/`fc2.a`/`fc2.b`) | Rust `cog-pose-estimation run --adapter` |
|
||||
|
||||
```bash
|
||||
# Produce a cog-format per-room adapter for the deployed Rust pose engine:
|
||||
python cog_calibrate.py --base pose_v1.safetensors --data calib.npz --out room.safetensors
|
||||
# then in the cog runtime:
|
||||
cog-pose-estimation run --config <cfg> --adapter room.safetensors
|
||||
```
|
||||
|
||||
Same LoRA *mechanism* (ADR-150 §3.5), different architecture and key layout — an adapter from one
|
||||
producer will not load into the other model.
|
||||
|
||||
## Notes
|
||||
|
||||
- **Calibration only helps when the base hasn't already seen the room.** The published flagship was
|
||||
trained on MM-Fi `random_split`, so calibrating it on an MM-Fi subject is a near-no-op (it already
|
||||
saw them); for a genuinely new real-world room it is zero-shot and calibration applies. To
|
||||
*reproduce the demo* on a held-out MM-Fi room, train a source-only base (exclude the target
|
||||
environment) — see `ADR-150 §3.6` and the few-shot harness in `aether-arena/staging/`.
|
||||
- Adapter is saved fp16 (~22 KB); quantize to int8 for the ~11 KB on-device form.
|
||||
- Inference is real-time on CPU (the 75 K-param `micro` variant runs in 0.135 ms single-thread x86;
|
||||
see [`docs/benchmarks/wifi-pose-efficiency-frontier.md`](../../docs/benchmarks/wifi-pose-efficiency-frontier.md)).
|
||||
@@ -1,71 +0,0 @@
|
||||
"""RuView per-room calibration — fit a ~11 KB LoRA adapter from a short labeled in-room capture.
|
||||
|
||||
python calibrate.py --base pose_mmfi_best.pt --data room_calib.npz --out room_A.adapter.npz
|
||||
|
||||
`room_calib.npz` must contain `X` [N,3,114,10] CSI amplitude and `Y` [N,17,2] (or [N,34]) keypoints
|
||||
in [0,1] — the labeled calibration samples from the deployment room (~100–200 recommended; ≥20).
|
||||
Outputs a tiny adapter (.npz, ~11 KB) that, loaded over the shared base at inference, recovers
|
||||
SOTA-level pose for that room/person (ADR-150 §3.5–3.6).
|
||||
"""
|
||||
import argparse
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
from model import PoseNet, standardize
|
||||
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--base", required=True, help="base checkpoint (pose_mmfi_best.pt)")
|
||||
ap.add_argument("--data", required=True, help="labeled calibration .npz with X and Y")
|
||||
ap.add_argument("--out", required=True, help="output adapter .npz")
|
||||
ap.add_argument("--rank", type=int, default=8)
|
||||
ap.add_argument("--iters", type=int, default=600)
|
||||
ap.add_argument("--lr", type=float, default=8e-4)
|
||||
ap.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu")
|
||||
a = ap.parse_args()
|
||||
|
||||
z = np.load(a.data)
|
||||
X = torch.tensor(z["X"].astype(np.float32))
|
||||
Y = torch.tensor(z["Y"].reshape(len(z["Y"]), 34).astype(np.float32))
|
||||
n = len(X)
|
||||
if n < 20:
|
||||
print(f"WARNING: only {n} calibration samples — below ~20 the adapter may underperform "
|
||||
f"zero-shot (ADR-150 §3.5). Recommend ~100–200.")
|
||||
dev = a.device
|
||||
|
||||
net = PoseNet().to(dev)
|
||||
net.load_state_dict(torch.load(a.base, map_location=dev), strict=False)
|
||||
net.add_lora(r=a.rank).to(dev)
|
||||
for k, p in net.named_parameters():
|
||||
p.requires_grad = k.endswith(".A") or k.endswith(".B")
|
||||
trainable = [p for p in net.parameters() if p.requires_grad]
|
||||
n_tr = sum(p.numel() for p in trainable)
|
||||
|
||||
Xs = standardize(X.to(dev))
|
||||
Yt = Y.to(dev)
|
||||
opt = torch.optim.AdamW(trainable, lr=a.lr, weight_decay=0.0)
|
||||
lossf = nn.SmoothL1Loss(beta=0.1)
|
||||
bs = min(128, n)
|
||||
net.train()
|
||||
for it in range(a.iters):
|
||||
bi = torch.randint(0, n, (bs,), device=dev)
|
||||
xb = Xs[bi]
|
||||
# light augmentation (subcarrier dropout + noise) — matches training-time regularization
|
||||
m = (torch.rand(xb.shape[0], xb.shape[1], 1, 1, device=dev) > 0.15).float()
|
||||
xb = xb * m + 0.03 * torch.randn_like(xb) * torch.rand(xb.shape[0], 1, 1, 1, device=dev)
|
||||
opt.zero_grad()
|
||||
lossf(net(xb), Yt[bi]).backward()
|
||||
opt.step()
|
||||
|
||||
adapter = net.lora_state()
|
||||
nbytes = sum(v.astype(np.float16).nbytes for v in adapter.values())
|
||||
np.savez(a.out, **{k: v.astype(np.float16) for k, v in adapter.items()},
|
||||
_meta=np.array([a.rank, n, n_tr], dtype=np.int64))
|
||||
print(f"saved {a.out} | rank {a.rank} | {n_tr:,} params | ~{nbytes/1024:.1f} KB fp16 | "
|
||||
f"from {n} labeled samples")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,120 +0,0 @@
|
||||
"""Per-room calibration producer for the cog-pose-estimation **conv+MLP** model
|
||||
(`pose_v1.safetensors`, 56 subcarriers x 20 frames). Companion to `calibrate.py`
|
||||
(which targets the MM-Fi *transformer* model) — different model, different adapter
|
||||
key layout, NOT interchangeable (ADR-150 §3.5).
|
||||
|
||||
Fits a rank-r LoRA on the pose head (fc1, fc2) from a short labeled in-room capture and
|
||||
writes a **safetensors** adapter with keys `fc1.a`/`fc1.b`/`fc2.a`/`fc2.b` (scale baked
|
||||
into `b`) — exactly what `cog-pose-estimation run --adapter <file>` consumes.
|
||||
|
||||
python cog_calibrate.py --base pose_v1.safetensors --data calib.npz --out room.safetensors
|
||||
|
||||
`calib.npz`: `X` [N,56,20] CSI window + `Y` [N,17,2] (or [N,34]) keypoints in [0,1].
|
||||
"""
|
||||
import argparse
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
|
||||
class CogPose(nn.Module):
|
||||
"""Mirrors cog-pose-estimation's PoseNet (Candle) exactly — same safetensors keys."""
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.enc = nn.ModuleDict({
|
||||
"c1": nn.Conv1d(56, 64, 3, padding=1, dilation=1),
|
||||
"c2": nn.Conv1d(64, 128, 3, padding=2, dilation=2),
|
||||
"c3": nn.Conv1d(128, 128, 3, padding=4, dilation=4),
|
||||
})
|
||||
self.head = nn.ModuleDict({"fc1": nn.Linear(128, 256), "fc2": nn.Linear(256, 34)})
|
||||
self.fc1_lora = None
|
||||
self.fc2_lora = None
|
||||
|
||||
def _lora(self, slot, x, y):
|
||||
if slot is None:
|
||||
return y
|
||||
a, b = slot
|
||||
return y + (x @ a) @ b
|
||||
|
||||
def forward(self, x): # x: [B, 56, 20]
|
||||
h = F.relu(self.enc["c1"](x))
|
||||
h = F.relu(self.enc["c2"](h))
|
||||
h = F.relu(self.enc["c3"](h))
|
||||
h = h.mean(2) # [B, 128]
|
||||
z1 = self.head["fc1"](h)
|
||||
z1 = self._lora(self.fc1_lora, h, z1)
|
||||
h1 = F.relu(z1)
|
||||
z2 = self.head["fc2"](h1)
|
||||
z2 = self._lora(self.fc2_lora, h1, z2)
|
||||
return torch.sigmoid(z2) # [B, 34]
|
||||
|
||||
def add_lora(self, r=4):
|
||||
self.fc1_lora = (nn.Parameter(torch.randn(128, r) * 0.02), nn.Parameter(torch.zeros(r, 256)))
|
||||
self.fc2_lora = (nn.Parameter(torch.randn(256, r) * 0.02), nn.Parameter(torch.zeros(r, 34)))
|
||||
for p in (*self.fc1_lora, *self.fc2_lora):
|
||||
self.register_parameter(f"lora_{id(p)}", p)
|
||||
return self
|
||||
|
||||
|
||||
def load_base(net: CogPose, path: str):
|
||||
from safetensors.torch import load_file
|
||||
sd = load_file(path)
|
||||
# remap "enc.c1.weight" -> module dict keys
|
||||
mapped = {}
|
||||
for k, v in sd.items():
|
||||
mapped[k.replace("enc.", "enc.").replace("head.", "head.")] = v
|
||||
net.load_state_dict(mapped, strict=False)
|
||||
return net
|
||||
|
||||
|
||||
def fit(base: str, data: str, out: str, rank: int = 4, iters: int = 400, lr: float = 1e-3):
|
||||
z = np.load(data)
|
||||
X = torch.tensor(z["X"].astype(np.float32)) # [N,56,20]
|
||||
Y = torch.tensor(z["Y"].reshape(len(z["Y"]), 34).astype(np.float32))
|
||||
n = len(X)
|
||||
net = CogPose()
|
||||
load_base(net, base)
|
||||
net.add_lora(rank)
|
||||
for p in net.parameters():
|
||||
p.requires_grad = False
|
||||
lora = [*net.fc1_lora, *net.fc2_lora]
|
||||
for p in lora:
|
||||
p.requires_grad = True
|
||||
opt = torch.optim.AdamW(lora, lr=lr, weight_decay=0.0)
|
||||
lossf = nn.SmoothL1Loss(beta=0.1)
|
||||
bs = min(64, n)
|
||||
net.train()
|
||||
for _ in range(iters):
|
||||
bi = torch.randint(0, n, (bs,))
|
||||
opt.zero_grad()
|
||||
lossf(net(X[bi]), Y[bi]).backward()
|
||||
opt.step()
|
||||
|
||||
alpha = 16.0
|
||||
scale = alpha / rank
|
||||
a1, b1 = net.fc1_lora
|
||||
a2, b2 = net.fc2_lora
|
||||
tensors = {
|
||||
"fc1.a": a1.detach().contiguous(),
|
||||
"fc1.b": (b1.detach() * scale).contiguous(), # bake scale into b
|
||||
"fc2.a": a2.detach().contiguous(),
|
||||
"fc2.b": (b2.detach() * scale).contiguous(),
|
||||
}
|
||||
from safetensors.torch import save_file
|
||||
save_file(tensors, out)
|
||||
return out, sum(p.numel() for p in lora), n
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--base", required=True)
|
||||
ap.add_argument("--data", required=True)
|
||||
ap.add_argument("--out", required=True)
|
||||
ap.add_argument("--rank", type=int, default=4)
|
||||
ap.add_argument("--iters", type=int, default=400)
|
||||
a = ap.parse_args()
|
||||
out, np_, n = fit(a.base, a.data, a.out, a.rank, a.iters)
|
||||
print(f"saved {out} | {np_} LoRA params from {n} samples "
|
||||
f"(keys fc1.a/fc1.b/fc2.a/fc2.b — load with cog-pose-estimation run --adapter)")
|
||||
@@ -1,49 +0,0 @@
|
||||
"""Run calibrated WiFi-CSI pose inference: shared base + a per-room LoRA adapter.
|
||||
|
||||
python infer.py --base pose_mmfi_best.pt --adapter room_A.adapter.npz --data frames.npz
|
||||
|
||||
`frames.npz` contains `X` [N,3,114,10] CSI amplitude. Prints/saves [N,17,2] keypoints in [0,1].
|
||||
Omit --adapter to run the uncalibrated (zero-shot) base. With a room adapter, expect SOTA-level
|
||||
accuracy in that room/person; without one, zero-shot degrades in unseen rooms (ADR-150 §3.6).
|
||||
"""
|
||||
import argparse
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
from model import PoseNet, standardize
|
||||
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--base", required=True)
|
||||
ap.add_argument("--adapter", default=None, help="per-room .adapter.npz (omit for zero-shot)")
|
||||
ap.add_argument("--data", required=True, help=".npz with X [N,3,114,10]")
|
||||
ap.add_argument("--out", default=None, help="optional .npy to save [N,17,2] keypoints")
|
||||
ap.add_argument("--rank", type=int, default=8)
|
||||
ap.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu")
|
||||
a = ap.parse_args()
|
||||
dev = a.device
|
||||
|
||||
net = PoseNet().to(dev)
|
||||
net.load_state_dict(torch.load(a.base, map_location=dev), strict=False)
|
||||
if a.adapter:
|
||||
net.add_lora(r=a.rank).to(dev)
|
||||
z = np.load(a.adapter)
|
||||
net.load_lora({k: z[k].astype(np.float32) for k in z.files if k.endswith(".A") or k.endswith(".B")})
|
||||
net.eval()
|
||||
|
||||
X = torch.tensor(np.load(a.data)["X"].astype(np.float32)).to(dev)
|
||||
Xs = standardize(X)
|
||||
out = []
|
||||
with torch.no_grad():
|
||||
for i in range(0, len(Xs), 4096):
|
||||
out.append(net(Xs[i:i + 4096]).cpu().numpy())
|
||||
kp = np.concatenate(out).reshape(-1, 17, 2)
|
||||
print(f"inferred {len(kp)} frames | adapter={'yes' if a.adapter else 'NONE (zero-shot)'}")
|
||||
if a.out:
|
||||
np.save(a.out, kp)
|
||||
print(f"saved keypoints -> {a.out}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,107 +0,0 @@
|
||||
"""WiFi-CSI pose model + LoRA adapter for the RuView calibration service.
|
||||
|
||||
Architecture matches the published flagship checkpoint
|
||||
[`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose)
|
||||
(`pose_mmfi_best.pt`): transformer encoder + temporal attention pooling + skeleton-graph head.
|
||||
|
||||
The calibration service freezes this base and fits a tiny per-room **LoRA adapter** (rank 8 on the
|
||||
input projection + pose head ≈ 11 KB) from ~100–200 labeled in-room samples. Empirically that lifts
|
||||
cross-subject 64→72% and cross-environment 11→73% (ADR-150 §3.3–3.6).
|
||||
"""
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
# COCO-17 skeleton edges for the graph-refinement head.
|
||||
EDGES = [(0, 1), (0, 2), (1, 3), (2, 4), (5, 6), (5, 7), (7, 9), (6, 8), (8, 10),
|
||||
(5, 11), (6, 12), (11, 12), (11, 13), (13, 15), (12, 14), (14, 16)]
|
||||
_A = np.eye(17, dtype=np.float32)
|
||||
for _i, _j in EDGES:
|
||||
_A[_i, _j] = _A[_j, _i] = 1.0
|
||||
_A = _A / _A.sum(1, keepdims=True)
|
||||
|
||||
|
||||
class LoRA(nn.Module):
|
||||
"""Low-rank adapter wrapping a frozen Linear: y = W·x + (x·A·B)·(alpha/r)."""
|
||||
|
||||
def __init__(self, base: nn.Linear, r: int = 8, alpha: int = 16):
|
||||
super().__init__()
|
||||
self.base = base
|
||||
for p in self.base.parameters():
|
||||
p.requires_grad = False
|
||||
self.A = nn.Parameter(torch.zeros(base.in_features, r))
|
||||
self.B = nn.Parameter(torch.zeros(r, base.out_features))
|
||||
nn.init.normal_(self.A, std=0.02)
|
||||
self.scale = alpha / r
|
||||
|
||||
def forward(self, x):
|
||||
return self.base(x) + (x @ self.A @ self.B) * self.scale
|
||||
|
||||
|
||||
class GR(nn.Module):
|
||||
"""Skeleton-graph refinement: nudges joints toward anatomically consistent positions."""
|
||||
|
||||
def __init__(self, d=256, h=96):
|
||||
super().__init__()
|
||||
self.je = nn.Parameter(torch.randn(17, 32) * 0.02)
|
||||
self.inp = nn.Linear(d + 34, h)
|
||||
self.g1 = nn.Linear(h, h)
|
||||
self.g2 = nn.Linear(h, h)
|
||||
self.out = nn.Linear(h, 2)
|
||||
self.register_buffer("A", torch.tensor(_A))
|
||||
|
||||
def forward(self, z, kp0):
|
||||
B = z.shape[0]
|
||||
f = torch.relu(self.inp(torch.cat(
|
||||
[z.unsqueeze(1).expand(-1, 17, -1), self.je.unsqueeze(0).expand(B, -1, -1), kp0], -1)))
|
||||
f = torch.relu(self.g1(torch.einsum('ij,bjh->bih', self.A, f)))
|
||||
f = torch.relu(self.g2(torch.einsum('ij,bjh->bih', self.A, f)))
|
||||
return kp0 + 0.3 * torch.tanh(self.out(f))
|
||||
|
||||
|
||||
class PoseNet(nn.Module):
|
||||
"""Flagship pose model. Input [B,3,114,10] CSI amplitude (per-sample standardized) -> [B,34]."""
|
||||
|
||||
def __init__(self, na=3, nsc=114, nt=10, d=256, L=4, H=8):
|
||||
super().__init__()
|
||||
self.proj = nn.Linear(na * nsc, d)
|
||||
self.pos = nn.Parameter(torch.randn(1, nt, d) * 0.02)
|
||||
enc = nn.TransformerEncoderLayer(d, H, d * 2, dropout=0.2, batch_first=True, activation='gelu')
|
||||
self.tf = nn.TransformerEncoder(enc, L)
|
||||
self.att = nn.Linear(d, 1)
|
||||
self.head = nn.Sequential(nn.Linear(d, 256), nn.GELU(), nn.Dropout(0.3), nn.Linear(256, 34))
|
||||
self.gr = GR(d)
|
||||
self.na, self.nsc, self.nt = na, nsc, nt
|
||||
|
||||
def forward(self, x):
|
||||
B = x.shape[0]
|
||||
t = x.permute(0, 3, 1, 2).reshape(B, self.nt, self.na * self.nsc)
|
||||
h = self.tf(self.proj(t) + self.pos)
|
||||
w = torch.softmax(self.att(h), 1)
|
||||
z = (h * w).sum(1)
|
||||
kp0 = torch.sigmoid(self.head(z)).reshape(B, 17, 2)
|
||||
return self.gr(z, kp0).reshape(B, 34)
|
||||
|
||||
def add_lora(self, r=8, alpha=16):
|
||||
"""Wrap the input projection + pose head with LoRA adapters (the ~11 KB calibration set)."""
|
||||
self.proj = LoRA(self.proj, r, alpha)
|
||||
self.head[0] = LoRA(self.head[0], r, alpha)
|
||||
self.head[3] = LoRA(self.head[3], r, alpha)
|
||||
return self
|
||||
|
||||
def lora_state(self) -> dict:
|
||||
"""Extract just the LoRA A/B tensors (the per-room adapter to save)."""
|
||||
return {k: v.detach().cpu().numpy() for k, v in self.state_dict().items()
|
||||
if k.endswith(".A") or k.endswith(".B")}
|
||||
|
||||
def load_lora(self, adapter: dict):
|
||||
sd = self.state_dict()
|
||||
for k, v in adapter.items():
|
||||
sd[k] = torch.tensor(v)
|
||||
self.load_state_dict(sd)
|
||||
return self
|
||||
|
||||
|
||||
def standardize(x: torch.Tensor) -> torch.Tensor:
|
||||
"""Per-sample standardization used in training/inference."""
|
||||
return (x - x.mean((1, 2, 3), keepdim=True)) / (x.std((1, 2, 3), keepdim=True) + 1e-6)
|
||||
@@ -1,103 +0,0 @@
|
||||
"""Self-contained regression test for the RuView calibration service.
|
||||
|
||||
Exercises the committed CLI end-to-end on synthetic data (CPU, no GPU, no real checkpoint):
|
||||
build a base -> calibrate.py fits an adapter -> infer.py runs base+adapter -> assert the
|
||||
adapter is small, inference is shape-correct and finite, and the adapter actually changes output.
|
||||
|
||||
Run: python test_calibration.py (or via pytest)
|
||||
"""
|
||||
import json
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
HERE = Path(__file__).parent
|
||||
sys.path.insert(0, str(HERE))
|
||||
from model import PoseNet, standardize # noqa: E402
|
||||
|
||||
|
||||
def _make_base(path: Path):
|
||||
torch.manual_seed(0)
|
||||
net = PoseNet()
|
||||
# Save without the deterministic gr.A buffer (mirrors the published checkpoint;
|
||||
# calibrate.py/infer.py load with strict=False).
|
||||
sd = {k: v for k, v in net.state_dict().items() if k != "gr.A"}
|
||||
torch.save(sd, path)
|
||||
|
||||
|
||||
def _make_data(path: Path, n: int, seed: int):
|
||||
rng = np.random.default_rng(seed)
|
||||
X = rng.standard_normal((n, 3, 114, 10)).astype(np.float32)
|
||||
Y = rng.random((n, 17, 2)).astype(np.float32) # keypoints in [0,1]
|
||||
np.savez(path, X=X, Y=Y)
|
||||
|
||||
|
||||
def _run(*args):
|
||||
r = subprocess.run(
|
||||
[sys.executable, str(HERE / args[0]), *map(str, args[1:])],
|
||||
capture_output=True, text=True,
|
||||
)
|
||||
assert r.returncode == 0, f"{args[0]} failed:\n{r.stdout}\n{r.stderr}"
|
||||
return r.stdout
|
||||
|
||||
|
||||
def test_calibration_end_to_end():
|
||||
with tempfile.TemporaryDirectory() as d:
|
||||
d = Path(d)
|
||||
base = d / "base.pt"
|
||||
calib = d / "calib.npz"
|
||||
frames = d / "frames.npz"
|
||||
adapter = d / "room.adapter.npz"
|
||||
kp = d / "kp.npy"
|
||||
|
||||
_make_base(base)
|
||||
_make_data(calib, n=40, seed=1) # ≥20 → no underfit warning
|
||||
_make_data(frames, n=16, seed=2)
|
||||
|
||||
# 1) calibrate -> adapter
|
||||
out = _run("calibrate.py", "--base", base, "--data", calib, "--out", adapter,
|
||||
"--iters", "50", "--device", "cpu")
|
||||
assert adapter.exists(), "adapter not written"
|
||||
assert "saved" in out.lower()
|
||||
sz = adapter.stat().st_size
|
||||
assert sz < 200_000, f"adapter unexpectedly large ({sz} bytes)"
|
||||
|
||||
# adapter contains the expected LoRA tensors (materialize + close so the
|
||||
# Windows tempdir can be cleaned up — np.load keeps a lazy file handle).
|
||||
with np.load(adapter) as z:
|
||||
keys = [k for k in z.files if k.endswith(".A") or k.endswith(".B")]
|
||||
assert keys, f"adapter has no LoRA tensors: {z.files}"
|
||||
lora = {k: z[k].astype(np.float32) for k in keys}
|
||||
|
||||
# 2) infer with adapter -> keypoints
|
||||
_run("infer.py", "--base", base, "--adapter", adapter, "--data", frames,
|
||||
"--out", kp, "--device", "cpu")
|
||||
out_kp = np.load(kp)
|
||||
assert out_kp.shape == (16, 17, 2), f"bad keypoint shape {out_kp.shape}"
|
||||
assert np.isfinite(out_kp).all(), "non-finite keypoints"
|
||||
assert (out_kp >= 0).all() and (out_kp <= 1).all(), "keypoints out of [0,1]"
|
||||
|
||||
# 3) adapter must actually change the output vs the zero-shot base
|
||||
with np.load(frames) as fz:
|
||||
frames_x = fz["X"][:]
|
||||
net = PoseNet()
|
||||
net.load_state_dict(torch.load(base, map_location="cpu"), strict=False)
|
||||
net.eval()
|
||||
x = standardize(torch.tensor(frames_x))
|
||||
with torch.no_grad():
|
||||
base_kp = net(x).reshape(16, 17, 2).numpy()
|
||||
net.add_lora()
|
||||
net.load_lora(lora)
|
||||
net.eval()
|
||||
with torch.no_grad():
|
||||
cal_kp = net(x).reshape(16, 17, 2).numpy()
|
||||
assert np.abs(base_kp - cal_kp).sum() > 1e-4, "adapter did not change output"
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_calibration_end_to_end()
|
||||
print("PASS: calibration service end-to-end (calibrate -> adapter -> infer)")
|
||||
@@ -1,75 +0,0 @@
|
||||
"""Regression test for the cog-pose adapter producer (cog_calibrate.py).
|
||||
|
||||
Uses the in-repo `pose_v1.safetensors` (skips if absent). Verifies the produced adapter:
|
||||
- has the exact keys/shapes the Rust `cog-pose-estimation --adapter` loader expects,
|
||||
- reduces calibration fit error,
|
||||
- actually changes inference output,
|
||||
- is tiny.
|
||||
Run: python test_cog_calibration.py (or via pytest)
|
||||
"""
|
||||
import os
|
||||
import sys
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
|
||||
HERE = Path(__file__).parent
|
||||
sys.path.insert(0, str(HERE))
|
||||
import cog_calibrate as C # noqa: E402
|
||||
|
||||
BASE = HERE / "../../v2/crates/cog-pose-estimation/cog/artifacts/pose_v1.safetensors"
|
||||
|
||||
|
||||
def test_cog_adapter_producer():
|
||||
if not BASE.exists():
|
||||
print(f"(skip — {BASE} not present)")
|
||||
return
|
||||
from safetensors.torch import load_file
|
||||
|
||||
rng = np.random.default_rng(0)
|
||||
n = 120
|
||||
X = rng.standard_normal((n, 56, 20)).astype("float32")
|
||||
Y = (0.5 + 0.1 * X[:, :34, 0].reshape(n, 34)).clip(0, 1).astype("float32")
|
||||
|
||||
with tempfile.TemporaryDirectory() as d:
|
||||
calib = os.path.join(d, "calib.npz")
|
||||
adapter = os.path.join(d, "room.safetensors")
|
||||
np.savez(calib, X=X, Y=Y)
|
||||
|
||||
net0 = C.CogPose()
|
||||
C.load_base(net0, str(BASE))
|
||||
net0.eval()
|
||||
with torch.no_grad():
|
||||
base_err = F.smooth_l1_loss(net0(torch.tensor(X)), torch.tensor(Y)).item()
|
||||
|
||||
_, nparam, _ = C.fit(str(BASE), calib, adapter, rank=4, iters=400)
|
||||
t = load_file(adapter)
|
||||
|
||||
# exact Rust loader contract: a:[in,r], b:[r,out]
|
||||
assert tuple(t["fc1.a"].shape) == (128, 4)
|
||||
assert tuple(t["fc1.b"].shape) == (4, 256)
|
||||
assert tuple(t["fc2.a"].shape) == (256, 4)
|
||||
assert tuple(t["fc2.b"].shape) == (4, 34)
|
||||
|
||||
net = C.CogPose()
|
||||
C.load_base(net, str(BASE))
|
||||
net.add_lora(4)
|
||||
with torch.no_grad():
|
||||
net.fc1_lora[0].copy_(t["fc1.a"]); net.fc1_lora[1].copy_(t["fc1.b"] / (16 / 4))
|
||||
net.fc2_lora[0].copy_(t["fc2.a"]); net.fc2_lora[1].copy_(t["fc2.b"] / (16 / 4))
|
||||
net.eval()
|
||||
with torch.no_grad():
|
||||
cal_err = F.smooth_l1_loss(net(torch.tensor(X)), torch.tensor(Y)).item()
|
||||
changed = (net0(torch.tensor(X[:8])) - net(torch.tensor(X[:8]))).abs().sum().item()
|
||||
|
||||
assert cal_err < base_err, f"calibration did not reduce error ({base_err} -> {cal_err})"
|
||||
assert changed > 1e-3, "adapter inert"
|
||||
assert nparam < 5000, f"adapter unexpectedly large ({nparam} params)"
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_cog_adapter_producer()
|
||||
print("PASS: cog adapter producer (Rust-loadable format, reduces error, active)")
|
||||
@@ -1 +0,0 @@
|
||||
9c35e541d51f00998691b98948887ebca09b907d8eb29a113f97e792340456ba
|
||||
@@ -1 +0,0 @@
|
||||
{"frames": [{"pred": [[0.4003, 0.2734], [0.5038, 0.4197], [0.2053, 0.4438], [0.4397, 0.685], [0.5796, 0.7645], [0.8001, 0.2195], [0.2789, 0.2833], [0.314, 0.5439], [0.511, 0.2259], [0.6008, 0.46], [0.4837, 0.3879], [0.3475, 0.5597], [0.6569, 0.3575], [0.437, 0.6539], [0.2341, 0.6038], [0.7331, 0.392], [0.5615, 0.4915]]}, {"pred": [[0.4669, 0.6066], [0.6012, 0.7873], [0.4124, 0.5997], [0.2832, 0.281], [0.2732, 0.3635], [0.2503, 0.4848], [0.6827, 0.715], [0.4336, 0.7165], [0.295, 0.3386], [0.5337, 0.3544], [0.4397, 0.5474], [0.5163, 0.5528], [0.7547, 0.6799], [0.4195, 0.4448], [0.2257, 0.2269], [0.384, 0.2176], [0.2419, 0.4332]]}, {"pred": [[0.5585, 0.283], [0.4325, 0.2934], [0.463, 0.4744], [0.4188, 0.3454], [0.215, 0.7565], [0.527, 0.2353], [0.7084, 0.6124], [0.3015, 0.6744], [0.4103, 0.3532], [0.7243, 0.6932], [0.3302, 0.4918], [0.2072, 0.3754], [0.7914, 0.4878], [0.7618, 0.4079], [0.323, 0.3386], [0.7104, 0.4997], [0.2673, 0.6077]]}, {"pred": [[0.6372, 0.4984], [0.4184, 0.6763], [0.4498, 0.7549], [0.2924, 0.303], [0.3069, 0.7022], [0.3954, 0.5098], [0.7836, 0.6071], [0.4733, 0.7114], [0.3407, 0.3793], [0.3408, 0.4678], [0.4156, 0.4911], [0.4525, 0.7519], [0.5117, 0.1985], [0.1893, 0.6784], [0.6281, 0.5346], [0.5175, 0.673], [0.36, 0.3665]]}, {"pred": [[0.5535, 0.6537], [0.568, 0.511], [0.4705, 0.5377], [0.6372, 0.7163], [0.5493, 0.7515], [0.2559, 0.4549], [0.2553, 0.6176], [0.2991, 0.6154], [0.7185, 0.7986], [0.4586, 0.5057], [0.2975, 0.4525], [0.3263, 0.3719], [0.5131, 0.4576], [0.557, 0.5268], [0.6572, 0.7736], [0.2146, 0.6526], [0.4662, 0.7371]]}, {"pred": [[0.2924, 0.7595], [0.2612, 0.2315], [0.2488, 0.7751], [0.2329, 0.7282], [0.4744, 0.4206], [0.3618, 0.267], [0.2477, 0.285], [0.3976, 0.3746], [0.494, 0.2874], [0.3596, 0.2112], [0.3311, 0.4692], [0.6912, 0.4727], [0.4434, 0.5233], [0.4139, 0.7048], [0.425, 0.3937], [0.2326, 0.631], [0.2655, 0.7116]]}, {"pred": [[0.3609, 0.3437], [0.285, 0.486], [0.7734, 0.5468], [0.3657, 0.4093], [0.4728, 0.5019], [0.1866, 0.3545], [0.2172, 0.2028], [0.5613, 0.5238], [0.6252, 0.7205], [0.7998, 0.2954], [0.242, 0.7063], [0.6259, 0.6883], [0.5148, 0.7141], [0.5577, 0.7434], [0.3233, 0.2131], [0.2652, 0.7066], [0.5753, 0.5885]]}, {"pred": [[0.6787, 0.6504], [0.6051, 0.2297], [0.2539, 0.3475], [0.6437, 0.7807], [0.4981, 0.6149], [0.5716, 0.2367], [0.6486, 0.3632], [0.2433, 0.369], [0.6061, 0.3731], [0.4955, 0.2591], [0.7676, 0.7602], [0.6899, 0.7716], [0.3143, 0.7707], [0.3031, 0.4997], [0.7076, 0.5133], [0.3382, 0.7196], [0.2002, 0.4871]]}]}
|
||||
@@ -1 +0,0 @@
|
||||
{"frames": [{"gt": [[0.3943, 0.2905], [0.5215, 0.4194], [0.2225, 0.4602], [0.4547, 0.6961], [0.5765, 0.7686], [0.7858, 0.2279], [0.2866, 0.2707], [0.3084, 0.549], [0.5286, 0.2377], [0.6082, 0.4566], [0.4719, 0.3799], [0.3465, 0.5447], [0.6377, 0.3728], [0.4509, 0.6543], [0.2235, 0.6009], [0.7253, 0.3882], [0.5479, 0.4737]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.4845, 0.5985], [0.5883, 0.7959], [0.4315, 0.6012], [0.3008, 0.2703], [0.2776, 0.3486], [0.2483, 0.4695], [0.6916, 0.7184], [0.4153, 0.7305], [0.3057, 0.3392], [0.5535, 0.3576], [0.4216, 0.5398], [0.5093, 0.5706], [0.7397, 0.668], [0.4354, 0.4394], [0.2373, 0.2404], [0.404, 0.2315], [0.2609, 0.4182]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.5684, 0.2891], [0.4185, 0.2737], [0.4796, 0.4903], [0.4056, 0.3589], [0.2139, 0.7706], [0.5259, 0.2162], [0.718, 0.6177], [0.3002, 0.6632], [0.3978, 0.3338], [0.7116, 0.6836], [0.336, 0.5106], [0.2168, 0.3677], [0.7739, 0.4683], [0.773, 0.4188], [0.318, 0.3226], [0.7043, 0.4877], [0.2509, 0.5964]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.6501, 0.4868], [0.3995, 0.6805], [0.4408, 0.7681], [0.2762, 0.2907], [0.2877, 0.6959], [0.4102, 0.5292], [0.7825, 0.5898], [0.4603, 0.723], [0.3511, 0.3758], [0.3556, 0.4514], [0.4123, 0.4749], [0.4524, 0.7506], [0.5141, 0.2112], [0.2024, 0.6795], [0.6351, 0.5339], [0.5333, 0.6706], [0.3491, 0.3662]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.537, 0.656], [0.5675, 0.5033], [0.4714, 0.52], [0.6195, 0.7259], [0.5357, 0.766], [0.273, 0.4653], [0.2439, 0.6017], [0.2927, 0.6297], [0.7297, 0.7805], [0.439, 0.4924], [0.2969, 0.4589], [0.3174, 0.3911], [0.5324, 0.4643], [0.5744, 0.5074], [0.673, 0.783], [0.2238, 0.6674], [0.4534, 0.7468]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.2896, 0.7515], [0.2537, 0.2345], [0.2434, 0.763], [0.2502, 0.7137], [0.4723, 0.4035], [0.3607, 0.2775], [0.2657, 0.2969], [0.3872, 0.383], [0.5001, 0.3067], [0.3503, 0.2092], [0.3137, 0.4849], [0.6914, 0.4593], [0.4359, 0.504], [0.4056, 0.6994], [0.4428, 0.4085], [0.2424, 0.6445], [0.2507, 0.7048]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.3692, 0.3453], [0.2945, 0.4675], [0.7836, 0.5282], [0.3857, 0.414], [0.4848, 0.5017], [0.203, 0.3585], [0.225, 0.2135], [0.5513, 0.5175], [0.6296, 0.7275], [0.7908, 0.2897], [0.2263, 0.7012], [0.6403, 0.6873], [0.5026, 0.701], [0.5504, 0.7357], [0.338, 0.2187], [0.2629, 0.7015], [0.5757, 0.6084]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.6786, 0.649], [0.5956, 0.2396], [0.2447, 0.3593], [0.6439, 0.7854], [0.4874, 0.6102], [0.5857, 0.2465], [0.6459, 0.3827], [0.2364, 0.3613], [0.6054, 0.3745], [0.4798, 0.2711], [0.7869, 0.7618], [0.6919, 0.7809], [0.3259, 0.7674], [0.285, 0.5144], [0.6921, 0.5052], [0.3388, 0.7386], [0.2022, 0.495]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}]}
|
||||
@@ -1,5 +0,0 @@
|
||||
{"benchmark": "AetherArena", "created": "2026-05-30", "kind": "genesis", "note": "Official Spatial-Intelligence Benchmark \u2014 append-only signed ledger. Entries are real harness scores only; no seeded numbers.", "prev_hash": "0000000000000000000000000000000000000000000000000000000000000000", "row_hash": "940bdc6f0f5dd00f4d89e13a8fa843bab3c9ddf1b8051f426a1701e730249231", "seq": 0, "spec": "ADR-149"}
|
||||
{"abs_gain": "+9.38", "benchmark": "MM-Fi", "category": "pose", "caveat": "Protocol-matched MM-Fi random_split result; NOT solved real-world generalization. Random split has temporal/subject-adjacency effects common to this benchmark family. Leakage-free cross-subject is far lower (~11-27%) and is the real deployment frontier.", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20 (||right_shoulder-left_hip|| norm, 17 COCO kpts)", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer (4L/8H ~2M params, temporal-attention)", "prev_hash": "940bdc6f0f5dd00f4d89e13a8fa843bab3c9ddf1b8051f426a1701e730249231", "protocol": "random_split (ratio=0.8, seed=0)", "rel_gain": "+13.0%", "reproduce": "download MM-Fi -> parse_mmfi_zips.py -> train_tf_torso.py X.npy Y.npy split_random.npy (seed 0)", "row_hash": "76598d8e1320d5248f8cd854a8ffa22a99bd2a2f0e0e7f2d2b1df79af16001d5", "score_pct": 81.63, "scored_at": "2026-05-30", "seq": 1, "sota_ref": "MultiFormer 72.25 (CSI2Pose 68.41)", "submitter": "ruvnet", "tier": "Gold"}
|
||||
{"abs_gain": "+11.34", "benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer + skeleton-graph head + 3-ensemble + TTA", "note": "Best in-domain. Stacks attention-pooling + transformer + skeleton-graph refine + warmup + TTA + 3-model ensemble. Supersedes the 81.63 single-model entry.", "prev_hash": "76598d8e1320d5248f8cd854a8ffa22a99bd2a2f0e0e7f2d2b1df79af16001d5", "protocol": "random_split (0.8, seed 0)", "row_hash": "5780a4bc3e98eb0e30c1ecfa9091e57b280444fa1f21cd5146797e408580e4ab", "score_pct": 83.59, "scored_at": "2026-05-30", "seq": 2, "sota_ref": "MultiFormer 72.25 (CSI2Pose 68.41)", "submitter": "ruvnet", "tier": "Gold"}
|
||||
{"benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer", "note": "Leakage-free generalization to unseen people, shared rooms. Honest deployment-relevant number.", "prev_hash": "5780a4bc3e98eb0e30c1ecfa9091e57b280444fa1f21cd5146797e408580e4ab", "protocol": "cross_subject (official, val=S05,S10,..,S40)", "row_hash": "d989e4e1dbc0182610305fdfbde8b094413b87c913283a46bf41f4afba7a06fd", "score_pct": 64.04, "scored_at": "2026-05-30", "seq": 3, "sota_ref": "(no matched public ref)", "submitter": "ruvnet", "tier": "Silver"}
|
||||
{"benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer + CORAL domain alignment", "note": "The real deployment frontier (new room). CORAL transductive DG (+30% rel over control). Data-bound: MM-Fi has only 3 source rooms.", "prev_hash": "d989e4e1dbc0182610305fdfbde8b094413b87c913283a46bf41f4afba7a06fd", "protocol": "cross_environment (train E01-03 -> test E04, new room)", "row_hash": "bf370487bde88e198c13877956dab3c83766a6a24afef0b78b6ac7aa130bb207", "score_pct": 17.51, "scored_at": "2026-05-30", "seq": 4, "sota_ref": "(hard frontier; control 13.52)", "submitter": "ruvnet", "tier": "Bronze"}
|
||||
@@ -1,100 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""AetherArena append-only, tamper-evident results ledger (ADR-149 §2.3/§2.4).
|
||||
|
||||
Each row is hash-chained to the previous one: ``row_hash = sha256(canonical_row
|
||||
+ prev_hash)``. Any silent edit to an earlier row breaks every subsequent
|
||||
``prev_hash`` link, so the ledger is append-only and verifiable by anyone — no
|
||||
trust in the maintainer required. (Ed25519 row signing is the next hardening;
|
||||
the chain already makes tampering detectable.)
|
||||
|
||||
Usage:
|
||||
python ledger_tools.py seed # (re)build ledger.jsonl with genesis + baseline
|
||||
python ledger_tools.py verify # verify the whole chain -> exit 0 / 1
|
||||
python ledger_tools.py append '<json-row>' # append one scored row
|
||||
"""
|
||||
import hashlib
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
LEDGER = Path(__file__).parent / "ledger.jsonl"
|
||||
GENESIS_PREV = "0" * 64
|
||||
|
||||
|
||||
def canonical(row: dict) -> bytes:
|
||||
# Stable key order, no whitespace -> deterministic bytes for hashing.
|
||||
body = {k: row[k] for k in sorted(row) if k != "row_hash"}
|
||||
return json.dumps(body, separators=(",", ":"), sort_keys=True).encode()
|
||||
|
||||
|
||||
def row_hash(row: dict) -> str:
|
||||
return hashlib.sha256(canonical(row)).hexdigest()
|
||||
|
||||
|
||||
def read_rows() -> list[dict]:
|
||||
if not LEDGER.exists():
|
||||
return []
|
||||
return [json.loads(l) for l in LEDGER.read_text().splitlines() if l.strip()]
|
||||
|
||||
|
||||
def append(entry: dict) -> dict:
|
||||
rows = read_rows()
|
||||
prev = rows[-1]["row_hash"] if rows else GENESIS_PREV
|
||||
entry = dict(entry)
|
||||
entry["seq"] = len(rows)
|
||||
entry["prev_hash"] = prev
|
||||
entry["row_hash"] = row_hash(entry)
|
||||
with LEDGER.open("a") as f:
|
||||
f.write(json.dumps(entry, sort_keys=True) + "\n")
|
||||
return entry
|
||||
|
||||
|
||||
def verify() -> bool:
|
||||
rows = read_rows()
|
||||
prev = GENESIS_PREV
|
||||
for i, r in enumerate(rows):
|
||||
if r.get("seq") != i:
|
||||
print(f"FAIL: row {i} seq mismatch ({r.get('seq')})")
|
||||
return False
|
||||
if r.get("prev_hash") != prev:
|
||||
print(f"FAIL: row {i} prev_hash broken — ledger was edited")
|
||||
return False
|
||||
if r.get("row_hash") != row_hash(r):
|
||||
print(f"FAIL: row {i} row_hash mismatch — row was tampered")
|
||||
return False
|
||||
prev = r["row_hash"]
|
||||
print(f"OK: {len(rows)} rows, chain intact")
|
||||
return True
|
||||
|
||||
|
||||
def seed():
|
||||
"""Rebuild with the genesis row only — an EMPTY board.
|
||||
|
||||
Benchmark-first: no placeholder/hand-entered numbers ever sit on the
|
||||
leaderboard. Every result row is produced by the real scoring pipeline
|
||||
(load model -> run inference -> score against the private eval split ->
|
||||
proof hash). The board starts empty and awaits the first real harness score,
|
||||
including RuView's own — which gets no special seeding.
|
||||
"""
|
||||
if LEDGER.exists():
|
||||
LEDGER.unlink()
|
||||
append({
|
||||
"kind": "genesis",
|
||||
"benchmark": "AetherArena",
|
||||
"spec": "ADR-149",
|
||||
"note": "Official Spatial-Intelligence Benchmark — append-only signed ledger. "
|
||||
"Entries are real harness scores only; no seeded numbers.",
|
||||
"created": "2026-05-30",
|
||||
})
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
cmd = sys.argv[1] if len(sys.argv) > 1 else "verify"
|
||||
if cmd == "seed":
|
||||
seed(); verify()
|
||||
elif cmd == "verify":
|
||||
sys.exit(0 if verify() else 1)
|
||||
elif cmd == "append":
|
||||
print(json.dumps(append(json.loads(sys.argv[2])), indent=2))
|
||||
else:
|
||||
print(__doc__); sys.exit(2)
|
||||
@@ -1,41 +0,0 @@
|
||||
# AetherArena submission manifest (ADR-149 §2.2).
|
||||
# Accompanies a model artifact pushed to the AA Hugging Face Space.
|
||||
# This file is the contract the Space validates before quarantine + scoring.
|
||||
|
||||
[submission]
|
||||
# Free-form display name shown on the leaderboard.
|
||||
name = "my-spatial-model"
|
||||
# Hugging Face repo or URL of the model artifact (.safetensors / .rvf / LoRA adapter).
|
||||
model_ref = "hf://your-org/your-model"
|
||||
# Submitter handle (HF username / org). Used to sign the ledger row.
|
||||
submitter = "your-hf-username"
|
||||
# SPDX license of the submitted model.
|
||||
license = "Apache-2.0"
|
||||
|
||||
[category]
|
||||
# One of: pose | presence | tracking | vitals | multi-task
|
||||
# v0 ranks: pose, presence (tracking/vitals activate when ground truth lands).
|
||||
primary = "pose"
|
||||
|
||||
[input]
|
||||
# Which ADR-145 FeatureSet the model consumes. v0 input is RF/WiFi CSI.
|
||||
# F0 = CSI amplitude/phase F1 = +CIR F2 = +Doppler F3 = +BFLD
|
||||
feature_set = "F0"
|
||||
# Tensor I/O contract so the scorer can feed the model correctly.
|
||||
input_shape = [114, 2] # subcarriers × {amp, phase} (example)
|
||||
output_shape = [17, 2] # 17 keypoints × {x, y} normalised [0,1]
|
||||
# Normalisation expected on the input ("none" | "zscore" | "minmax").
|
||||
normalization = "zscore"
|
||||
|
||||
[runtime]
|
||||
# Inference entrypoint inside the artifact (framework-specific).
|
||||
framework = "candle" # candle | onnx | torch
|
||||
# Optional: target the edge-latency category with a declared device class.
|
||||
device_class = "cpu" # cpu | pi5 | gpu
|
||||
|
||||
# Notes:
|
||||
# - You submit a MODEL, never predictions on data you hold.
|
||||
# - Scoring runs against a PRIVATE MM-Fi held-out split in a no-network,
|
||||
# read-only sandbox. You cannot see the eval data.
|
||||
# - The resulting score is a signed, append-only ledger row carrying a
|
||||
# determinism proof hash and the pinned harness_version.
|
||||
@@ -1,37 +0,0 @@
|
||||
---
|
||||
title: AetherArena — Spatial-Intelligence Benchmark
|
||||
emoji: 📡
|
||||
colorFrom: indigo
|
||||
colorTo: purple
|
||||
sdk: gradio
|
||||
sdk_version: 5.9.1
|
||||
python_version: "3.12"
|
||||
app_file: app.py
|
||||
pinned: true
|
||||
license: cc-by-nc-4.0
|
||||
tags:
|
||||
- benchmark
|
||||
- leaderboard
|
||||
- wifi-sensing
|
||||
- spatial-intelligence
|
||||
- pose-estimation
|
||||
---
|
||||
|
||||
# AetherArena ("AA") — The Official Spatial-Intelligence Benchmark
|
||||
|
||||
> Public leaderboard. Private evaluation split. Open scorer. Signed results.
|
||||
|
||||
The field's standard yardstick for camera-free **spatial intelligence** (pose, presence,
|
||||
occupancy, tracking, vitals) from RF/WiFi and, over time, mmWave / UWB / multimodal.
|
||||
|
||||
- **Project-agnostic** — any team, framework, or modality enters; RuView donated the seed
|
||||
scorer and is scored like everyone else.
|
||||
- **Benchmark-first** — the board starts empty; every row is a real scoring-pipeline
|
||||
**witness** (`inputs_sha256` + `proof_sha256` + `harness_version`) in an append-only,
|
||||
hash-chained, tamper-evident ledger.
|
||||
- **Reproducible** — the scorer is open; reproduce any proof hash + repeatability locally.
|
||||
|
||||
Spec: [ADR-149](https://github.com/ruvnet/RuView/blob/main/docs/adr/ADR-149-public-community-leaderboard-huggingface.md).
|
||||
Source + open scorer: https://github.com/ruvnet/RuView/tree/main/aether-arena
|
||||
|
||||
Non-commercial (CC BY-NC 4.0): the v0 eval split derives from MM-Fi (CC BY-NC); AA is operated non-commercially.
|
||||
@@ -1,161 +0,0 @@
|
||||
"""AetherArena ("AA") — The Official Spatial-Intelligence Benchmark.
|
||||
|
||||
Hugging Face Space (Gradio) — the public face of the benchmark (ADR-149).
|
||||
This Space is the presentation + submission layer; the heavy scoring runs in the
|
||||
pinned RuView harness (CI / scorer container), and results land in the append-only,
|
||||
hash-chained **witness ledger** shown here.
|
||||
|
||||
Benchmark-first: the board starts EMPTY. No seeded or hand-entered numbers — every
|
||||
row is a real scoring-pipeline witness (inputs_sha256 + proof_sha256 + harness_version).
|
||||
"""
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import gradio as gr
|
||||
|
||||
LEDGER = Path(__file__).parent / "ledger.jsonl"
|
||||
GENESIS_PREV = "0" * 64
|
||||
|
||||
|
||||
def _rows():
|
||||
if not LEDGER.exists():
|
||||
return []
|
||||
return [json.loads(l) for l in LEDGER.read_text().splitlines() if l.strip()]
|
||||
|
||||
|
||||
def _canon(row: dict) -> bytes:
|
||||
body = {k: row[k] for k in sorted(row) if k != "row_hash"}
|
||||
return json.dumps(body, separators=(",", ":"), sort_keys=True).encode()
|
||||
|
||||
|
||||
def verify_chain():
|
||||
rows, prev = _rows(), GENESIS_PREV
|
||||
for i, r in enumerate(rows):
|
||||
if r.get("prev_hash") != prev or r.get("row_hash") != hashlib.sha256(_canon(r)).hexdigest():
|
||||
return f"❌ Ledger chain BROKEN at row {i} — tampering detected."
|
||||
prev = r["row_hash"]
|
||||
return f"✅ Witness ledger chain intact — {len(rows)} row(s), append-only."
|
||||
|
||||
|
||||
def leaderboard(category: str):
|
||||
results = [r for r in _rows() if r.get("kind") == "result" and (category == "all" or r.get("category") == category)]
|
||||
if not results:
|
||||
return [["— no entries yet —", "", "", "", "", ""]]
|
||||
results.sort(key=lambda r: r.get("score_pct") or 0, reverse=True)
|
||||
return [[
|
||||
r.get("submitter", "?"),
|
||||
r.get("model_ref", "?"),
|
||||
f"{r.get('benchmark','?')} / {r.get('protocol','?')}",
|
||||
r.get("metric", "?"),
|
||||
f"{r.get('score_pct', 0):.2f}%",
|
||||
f"{r.get('tier','?')} (vs {r.get('sota_ref','?')})",
|
||||
] for r in results]
|
||||
|
||||
|
||||
FOUR_PART = "### Public leaderboard. Private evaluation split. Open scorer. Signed results."
|
||||
|
||||
ABOUT = """
|
||||
**AetherArena** is the official, project-agnostic **Spatial-Intelligence Benchmark** —
|
||||
camera-free pose, presence, occupancy, tracking, and vitals from RF/WiFi (and, over
|
||||
time, mmWave / UWB / radar / multimodal). It is **not** a single-vendor board: any
|
||||
team, framework, or modality enters, and every entrant — including the RuView baseline
|
||||
that donated the seed scorer — is scored by the identical, open, pinned harness.
|
||||
|
||||
The scorer reuses RuView's released `wifi-densepose-train` acceptance harness
|
||||
(`ruview_metrics` + ablation). You submit a **model, not predictions**; it is scored
|
||||
against a **private** MM-Fi held-out split; one **witness** row (inputs hash + proof
|
||||
hash + harness version) is appended to a **hash-chained, tamper-evident ledger**.
|
||||
|
||||
**For industry:** a vendor-neutral, auditable way to compare RF-sensing models on equal
|
||||
footing — the same standardized splits, the same metric definition, the same signed,
|
||||
reproducible ledger. No more "trust our number on our split." Vendors, labs, and startups
|
||||
all submit through one pipeline and are scored identically.
|
||||
|
||||
**Generalization Track (roadmap):** the headline isn't a single in-domain number — it's a
|
||||
battery of honest tracks: MM-Fi `random_split` (in-domain), `cross_subject` (unseen people),
|
||||
cross-room, cross-device, and confidence-calibration (ECE). Cross-subject is the real
|
||||
deployment frontier and is treated as the flagship hard benchmark.
|
||||
|
||||
Spec: ADR-149. v0 ranks **pose, presence, edge-latency, determinism**. Tracking &
|
||||
vitals activate when their ground truth lands; **privacy-leakage** is gated until the
|
||||
membership-inference attacker ships. Source + the open scorer:
|
||||
https://github.com/ruvnet/RuView/tree/main/aether-arena
|
||||
"""
|
||||
|
||||
SUBMIT = """
|
||||
### Submit a model
|
||||
|
||||
1. Write a manifest — [`schema/aa-submission.toml`](https://github.com/ruvnet/RuView/blob/main/aether-arena/schema/aa-submission.toml):
|
||||
declare your model ref, category, the ADR-145 feature set (F0 CSI … F3 BFLD), and the tensor I/O contract.
|
||||
2. Provide your model artifact (`.safetensors` / `.rvf` / LoRA adapter).
|
||||
3. It moves through `submitted → validated → quarantined → smoke_scored → full_scored → published`,
|
||||
scored in a no-network, read-only sandbox against the private split.
|
||||
4. Your signed witness row appears on the leaderboard.
|
||||
|
||||
**You submit a model, never predictions** — predictions on data you hold prove nothing.
|
||||
"""
|
||||
|
||||
VERIFY = """
|
||||
### Verify it's fair (you don't have to trust us)
|
||||
|
||||
The scorer is open and reproducible. Reproduce the determinism proof + repeatability locally:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/ruvnet/RuView && cd RuView/v2
|
||||
# determinism gate (same as CI):
|
||||
cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features
|
||||
# repeatability — N runs, one identical proof hash:
|
||||
cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --repeat 16
|
||||
# verify the append-only witness ledger chain:
|
||||
cd ../aether-arena/ledger && python3 ledger_tools.py verify
|
||||
```
|
||||
|
||||
A stranger must be able to: submit → get a deterministic score → see the signed row →
|
||||
rerun the scorer locally → understand why the rank is fair. That is the launch gate (ADR-149 §7).
|
||||
"""
|
||||
|
||||
with gr.Blocks(title="AetherArena — Spatial-Intelligence Benchmark") as demo:
|
||||
gr.Markdown("# 📡 AetherArena (AA)\n## The Official, Vendor-Neutral Benchmark for WiFi / RF Spatial Sensing")
|
||||
gr.Markdown(FOUR_PART)
|
||||
gr.Markdown(
|
||||
"**An open industry benchmark — for everyone, not any one vendor.** Submit any model, any framework, "
|
||||
"any modality. Every entrant — academic, startup, or incumbent — is scored *identically*: standardized "
|
||||
"protocols (MM-Fi `random_split` / `cross_subject`), matched metrics (torso-PCK@20, the published "
|
||||
"definition), and an auditable, hash-chained **witness ledger** anyone can verify and reproduce.\n\n"
|
||||
"**Why it exists:** WiFi/RF-sensing results are reported with inconsistent splits, metrics, and no "
|
||||
"auditability — so numbers aren't comparable. AetherArena fixes the *measurement*: one protocol, one "
|
||||
"metric, one signed ledger, one-command reproduction. The benchmark is the product; the leaderboard is "
|
||||
"just the scoreboard. (Reference implementation seeded by RuView, ADR-149.)"
|
||||
)
|
||||
chain = gr.Markdown(verify_chain())
|
||||
|
||||
with gr.Tab("🏆 Leaderboard"):
|
||||
gr.Markdown(
|
||||
"### Current standings — MM-Fi WiFi-CSI 2D pose, torso-PCK@20\n"
|
||||
"Ranked, protocol- & metric-matched results. Each row carries its own caveats in the ledger "
|
||||
"(e.g. `random_split` has temporal-adjacency leakage that inflates *all* methods equally — the "
|
||||
"leakage-free `cross_subject` track is the real deployment frontier). **Submit yours — top the board.**"
|
||||
)
|
||||
cat = gr.Dropdown(["all", "pose", "presence"], value="all", label="Category")
|
||||
tbl = gr.Dataframe(
|
||||
headers=["Submitter", "Model", "Benchmark / Protocol", "Metric", "Score", "Tier (vs prior SOTA)"],
|
||||
value=leaderboard("all"), interactive=False, wrap=True,
|
||||
)
|
||||
cat.change(leaderboard, cat, tbl)
|
||||
gr.Markdown(
|
||||
"*Vendor-neutral & benchmark-first: every row is a real, metric- and protocol-matched result — "
|
||||
"no seeded or vendor-favored numbers. Integrity is enforced, not promised: the current top entry's "
|
||||
"score was self-corrected down from an inflated metric (91.86% bbox → 81.63% torso) before it could "
|
||||
"be published. The same scorer and ledger apply to every submitter.*"
|
||||
)
|
||||
|
||||
with gr.Tab("📤 Submit"):
|
||||
gr.Markdown(SUBMIT)
|
||||
with gr.Tab("🔬 Verify"):
|
||||
gr.Markdown(VERIFY)
|
||||
with gr.Tab("ℹ️ About"):
|
||||
gr.Markdown(ABOUT)
|
||||
|
||||
if __name__ == "__main__":
|
||||
demo.launch(server_name="0.0.0.0", server_port=7860)
|
||||
@@ -1,5 +0,0 @@
|
||||
{"benchmark": "AetherArena", "created": "2026-05-30", "kind": "genesis", "note": "Official Spatial-Intelligence Benchmark \u2014 append-only signed ledger. Entries are real harness scores only; no seeded numbers.", "prev_hash": "0000000000000000000000000000000000000000000000000000000000000000", "row_hash": "940bdc6f0f5dd00f4d89e13a8fa843bab3c9ddf1b8051f426a1701e730249231", "seq": 0, "spec": "ADR-149"}
|
||||
{"abs_gain": "+9.38", "benchmark": "MM-Fi", "category": "pose", "caveat": "Protocol-matched MM-Fi random_split result; NOT solved real-world generalization. Random split has temporal/subject-adjacency effects common to this benchmark family. Leakage-free cross-subject is far lower (~11-27%) and is the real deployment frontier.", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20 (||right_shoulder-left_hip|| norm, 17 COCO kpts)", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer (4L/8H ~2M params, temporal-attention)", "prev_hash": "940bdc6f0f5dd00f4d89e13a8fa843bab3c9ddf1b8051f426a1701e730249231", "protocol": "random_split (ratio=0.8, seed=0)", "rel_gain": "+13.0%", "reproduce": "download MM-Fi -> parse_mmfi_zips.py -> train_tf_torso.py X.npy Y.npy split_random.npy (seed 0)", "row_hash": "76598d8e1320d5248f8cd854a8ffa22a99bd2a2f0e0e7f2d2b1df79af16001d5", "score_pct": 81.63, "scored_at": "2026-05-30", "seq": 1, "sota_ref": "MultiFormer 72.25 (CSI2Pose 68.41)", "submitter": "ruvnet", "tier": "Gold"}
|
||||
{"abs_gain": "+11.34", "benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer + skeleton-graph head + 3-ensemble + TTA", "note": "Best in-domain. Stacks attention-pooling + transformer + skeleton-graph refine + warmup + TTA + 3-model ensemble. Supersedes the 81.63 single-model entry.", "prev_hash": "76598d8e1320d5248f8cd854a8ffa22a99bd2a2f0e0e7f2d2b1df79af16001d5", "protocol": "random_split (0.8, seed 0)", "row_hash": "5780a4bc3e98eb0e30c1ecfa9091e57b280444fa1f21cd5146797e408580e4ab", "score_pct": 83.59, "scored_at": "2026-05-30", "seq": 2, "sota_ref": "MultiFormer 72.25 (CSI2Pose 68.41)", "submitter": "ruvnet", "tier": "Gold"}
|
||||
{"benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer", "note": "Leakage-free generalization to unseen people, shared rooms. Honest deployment-relevant number.", "prev_hash": "5780a4bc3e98eb0e30c1ecfa9091e57b280444fa1f21cd5146797e408580e4ab", "protocol": "cross_subject (official, val=S05,S10,..,S40)", "row_hash": "d989e4e1dbc0182610305fdfbde8b094413b87c913283a46bf41f4afba7a06fd", "score_pct": 64.04, "scored_at": "2026-05-30", "seq": 3, "sota_ref": "(no matched public ref)", "submitter": "ruvnet", "tier": "Silver"}
|
||||
{"benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer + CORAL domain alignment", "note": "The real deployment frontier (new room). CORAL transductive DG (+30% rel over control). Data-bound: MM-Fi has only 3 source rooms.", "prev_hash": "d989e4e1dbc0182610305fdfbde8b094413b87c913283a46bf41f4afba7a06fd", "protocol": "cross_environment (train E01-03 -> test E04, new room)", "row_hash": "bf370487bde88e198c13877956dab3c83766a6a24afef0b78b6ac7aa130bb207", "score_pct": 17.51, "scored_at": "2026-05-30", "seq": 4, "sota_ref": "(hard frontier; control 13.52)", "submitter": "ruvnet", "tier": "Bronze"}
|
||||
@@ -1 +0,0 @@
|
||||
gradio==5.9.1
|
||||
@@ -1,74 +0,0 @@
|
||||
# Archive
|
||||
|
||||
Frozen, no-longer-active components of RuView preserved for historical
|
||||
reference, reproducibility, and load-bearing legacy paths the active
|
||||
codebase still depends on.
|
||||
|
||||
## What lives here
|
||||
|
||||
| Path | What it is | Why it's archived | Still load-bearing? |
|
||||
|------|------------|-------------------|---------------------|
|
||||
| `v1/` | Original Python implementation of RuView (CSI processing, hardware adapters, services, FastAPI) | Superseded by the Rust workspace at `v2/`; ~810× slower in benchmarks. Kept rather than deleted because the deterministic proof bundle (`v1/data/proof/`) is part of the pre-merge witness verification process per ADR-011 / ADR-028. | **Yes — for the proof bundle only.** Active code lives in `v2/`. |
|
||||
|
||||
## What "archived" means
|
||||
|
||||
- **Do not add new features here.** New work goes in `v2/`.
|
||||
- **Do not refactor or modernize the archived code beyond what is
|
||||
strictly necessary** to keep the load-bearing paths working. The
|
||||
Python proof bundle is intentionally frozen so that its SHA-256
|
||||
reproducibility holds across releases (per ADR-028's witness
|
||||
verification requirement).
|
||||
- **Bug fixes inside archived code are allowed** when the bug affects a
|
||||
still-load-bearing path (currently: only the Python proof). All
|
||||
other "bugs" in archived code are out-of-scope — they are part of
|
||||
the historical record and any fix would unnecessarily churn the
|
||||
witness hashes.
|
||||
- **CI continues to verify the load-bearing paths.**
|
||||
`.github/workflows/verify-pipeline.yml` runs the Python proof on
|
||||
every push and PR; if you change anything inside `archive/v1/src/`
|
||||
or `archive/v1/data/proof/`, expect the determinism check to flag
|
||||
it.
|
||||
|
||||
## Quick reference for the load-bearing paths
|
||||
|
||||
```bash
|
||||
# Run the deterministic Python proof (must print VERDICT: PASS)
|
||||
python archive/v1/data/proof/verify.py
|
||||
|
||||
# Regenerate the expected hash (only if numpy/scipy version legitimately changed)
|
||||
python archive/v1/data/proof/verify.py --generate-hash
|
||||
|
||||
# Run the full Python test suite (legacy, still maintained)
|
||||
cd archive/v1&& python -m pytest tests/ -x -q
|
||||
```
|
||||
|
||||
## Why we keep `v1/` rather than delete it
|
||||
|
||||
1. **Trust kill-switch.** The proof at `v1/data/proof/verify.py` feeds
|
||||
a known reference signal through the full pipeline and hashes the
|
||||
output. If the active code's behavior drifts, the hash changes and
|
||||
CI fails. This is what stops accidental regression in the science
|
||||
layer of the codebase.
|
||||
|
||||
2. **Witness verification.** ADR-028's witness-bundle process bundles
|
||||
the proof, the rust workspace test results, and firmware hashes
|
||||
into a tarball recipients can self-verify. Removing v1 would break
|
||||
that chain.
|
||||
|
||||
3. **Historical reference.** ADR-011 documents the "no mocks in
|
||||
production code" decision; the original violations and their fixes
|
||||
live in this Python codebase. The ADRs reference these paths.
|
||||
|
||||
If the time comes to retire the proof bundle (e.g., a Rust port of
|
||||
the proof exists and the Python version is no longer canonical), the
|
||||
right move is a single follow-up that simultaneously: ports the
|
||||
witness-bundle process, updates `verify-pipeline.yml`, and either
|
||||
deletes `archive/v1/` or moves it to a separate read-only repository.
|
||||
That decision belongs in its own ADR.
|
||||
|
||||
## See also
|
||||
|
||||
- `docs/adr/ADR-011-python-proof-of-reality-mock-elimination.md`
|
||||
- `docs/adr/ADR-028-esp32-capability-audit.md`
|
||||
- `archive/v1/data/proof/README.md` (if present)
|
||||
- `docs/WITNESS-LOG-028.md`
|
||||
@@ -1,130 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
CIR Verification Helper (ADR-134)
|
||||
|
||||
Optional Python comparator — invokes the Rust cir_proof_runner binary and
|
||||
checks its output against expected_cir_features.sha256.
|
||||
|
||||
Usage:
|
||||
python cir_verify_helper.py # verify against stored hash
|
||||
python cir_verify_helper.py --generate # regenerate hash via Rust binary
|
||||
|
||||
This script is a thin wrapper; all cryptographic work is done in the Rust
|
||||
binary. It exists to integrate the CIR proof step into the Python verify.py
|
||||
flow if needed.
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||
REPO_ROOT = os.path.abspath(os.path.join(SCRIPT_DIR, "..", "..", "..", ".."))
|
||||
|
||||
|
||||
def find_binary() -> str:
|
||||
"""Locate the cir_proof_runner binary."""
|
||||
candidates = [
|
||||
os.path.join(REPO_ROOT, "v2", "target", "release", "cir_proof_runner"),
|
||||
os.path.join(REPO_ROOT, "v2", "target", "release", "cir_proof_runner.exe"),
|
||||
os.path.join(REPO_ROOT, "v2", "target", "debug", "cir_proof_runner"),
|
||||
os.path.join(REPO_ROOT, "v2", "target", "debug", "cir_proof_runner.exe"),
|
||||
]
|
||||
for path in candidates:
|
||||
if os.path.isfile(path):
|
||||
return path
|
||||
return ""
|
||||
|
||||
|
||||
def build_binary() -> bool:
|
||||
"""Build the release binary via cargo."""
|
||||
print("Building cir_proof_runner (release)...")
|
||||
result = subprocess.run(
|
||||
[
|
||||
"cargo", "build",
|
||||
"-p", "wifi-densepose-signal",
|
||||
"--bin", "cir_proof_runner",
|
||||
"--release",
|
||||
"--no-default-features",
|
||||
],
|
||||
cwd=os.path.join(REPO_ROOT, "v2"),
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
print("Build failed:", result.stderr[-2000:])
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def run_generate(binary: str) -> str:
|
||||
"""Run the binary with --generate-hash; return the hex hash."""
|
||||
result = subprocess.run(
|
||||
[binary, "--generate-hash"],
|
||||
cwd=REPO_ROOT,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
print("Error running binary:", result.stderr)
|
||||
return ""
|
||||
return result.stdout.strip()
|
||||
|
||||
|
||||
def run_verify(binary: str) -> bool:
|
||||
"""Run the binary in verify mode; return True on PASS."""
|
||||
result = subprocess.run(
|
||||
[binary],
|
||||
cwd=REPO_ROOT,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
print(result.stdout.strip())
|
||||
if result.stderr.strip():
|
||||
print(result.stderr.strip(), file=sys.stderr)
|
||||
return result.returncode == 0
|
||||
|
||||
|
||||
def main() -> None:
|
||||
parser = argparse.ArgumentParser(description="CIR verification helper (ADR-134)")
|
||||
parser.add_argument(
|
||||
"--generate",
|
||||
action="store_true",
|
||||
help="Regenerate expected_cir_features.sha256 via Rust binary",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--build",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="Build the binary before running (default: use cached binary)",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
binary = find_binary()
|
||||
|
||||
if args.build or not binary:
|
||||
if not build_binary():
|
||||
sys.exit(1)
|
||||
binary = find_binary()
|
||||
|
||||
if not binary:
|
||||
print("ERROR: cir_proof_runner binary not found. Run with --build.")
|
||||
sys.exit(1)
|
||||
|
||||
if args.generate:
|
||||
hash_val = run_generate(binary)
|
||||
if not hash_val:
|
||||
sys.exit(1)
|
||||
hash_file = os.path.join(SCRIPT_DIR, "expected_cir_features.sha256")
|
||||
with open(hash_file, "w") as f:
|
||||
f.write(hash_val + "\n")
|
||||
print(f"Wrote CIR hash to {hash_file}")
|
||||
print(f"Hash: {hash_val}")
|
||||
else:
|
||||
ok = run_verify(binary)
|
||||
sys.exit(0 if ok else 1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1 +0,0 @@
|
||||
d6bce07ecb1648e6936561df44bf4a3bfc17bb0ba5f692646b2301d105b52f67
|
||||
@@ -1 +0,0 @@
|
||||
304d54690af468dc6cbf0f2a1332f109cf187d5e2eab454efd8554cebc45bdeb
|
||||
@@ -1 +0,0 @@
|
||||
f8e76f21a0f9852b70b6d9dd5318239f6b20cbcb4cdd995863263cecdc446f7a
|
||||
Binary file not shown.
@@ -1,7 +0,0 @@
|
||||
"""
|
||||
API routers package
|
||||
"""
|
||||
|
||||
from . import pose, stream, health, auth
|
||||
|
||||
__all__ = ["pose", "stream", "health", "auth"]
|
||||
@@ -1,32 +0,0 @@
|
||||
"""
|
||||
Authentication router for WiFi-DensePose API.
|
||||
Provides logout (token blacklisting) endpoint.
|
||||
"""
|
||||
|
||||
import logging
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import APIRouter, Request, HTTPException, status
|
||||
|
||||
from src.api.middleware.auth import token_blacklist
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/auth", tags=["auth"])
|
||||
|
||||
|
||||
@router.post("/logout")
|
||||
async def logout(request: Request):
|
||||
"""Logout by blacklisting the current Bearer token."""
|
||||
auth_header = request.headers.get("authorization")
|
||||
if not auth_header or not auth_header.startswith("Bearer "):
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_401_UNAUTHORIZED,
|
||||
detail="Missing or invalid Authorization header",
|
||||
)
|
||||
|
||||
token = auth_header.split(" ", 1)[1]
|
||||
token_blacklist.add_token(token)
|
||||
logger.info("Token blacklisted via /auth/logout")
|
||||
|
||||
return {"success": True, "message": "Token revoked"}
|
||||
@@ -1,135 +0,0 @@
|
||||
"""Frame budget benchmark for CSI processing pipeline.
|
||||
|
||||
Verifies that per-frame CSI processing stays within the 50 ms budget
|
||||
required for real-time sensing at 20 FPS.
|
||||
"""
|
||||
|
||||
import time
|
||||
import statistics
|
||||
import pytest
|
||||
import numpy as np
|
||||
|
||||
from src.core.csi_processor import CSIProcessor
|
||||
|
||||
|
||||
def _make_config():
|
||||
return {
|
||||
"sampling_rate": 1000,
|
||||
"window_size": 256,
|
||||
"overlap": 0.5,
|
||||
"noise_threshold": -60,
|
||||
"human_detection_threshold": 0.8,
|
||||
"smoothing_factor": 0.9,
|
||||
"max_history_size": 500,
|
||||
"num_subcarriers": 256,
|
||||
"num_antennas": 3,
|
||||
"doppler_window": 64,
|
||||
}
|
||||
|
||||
|
||||
def _make_csi_data(n_subcarriers=256, n_antennas=3, seed=None):
|
||||
"""Generate a synthetic CSI frame with complex-valued subcarriers."""
|
||||
rng = np.random.default_rng(seed)
|
||||
from unittest.mock import MagicMock
|
||||
csi = MagicMock()
|
||||
csi.amplitude = rng.random((n_antennas, n_subcarriers)).astype(np.float64) * 20.0
|
||||
csi.phase = (rng.random((n_antennas, n_subcarriers)).astype(np.float64) - 0.5) * np.pi * 2
|
||||
csi.frequency = 5.0e9
|
||||
csi.bandwidth = 80e6
|
||||
csi.num_subcarriers = n_subcarriers
|
||||
csi.num_antennas = n_antennas
|
||||
csi.snr = 25.0
|
||||
csi.timestamp = time.time()
|
||||
csi.metadata = {}
|
||||
return csi
|
||||
|
||||
|
||||
class TestSingleFrameBudget:
|
||||
"""Single-frame processing must complete in < 50 ms."""
|
||||
|
||||
def test_single_frame_under_50ms(self):
|
||||
proc = CSIProcessor(config=_make_config())
|
||||
frame = _make_csi_data(seed=42)
|
||||
|
||||
# Warm up
|
||||
proc.preprocess_csi_data(frame)
|
||||
|
||||
start = time.perf_counter()
|
||||
proc.preprocess_csi_data(frame)
|
||||
features = proc.extract_features(frame)
|
||||
if features:
|
||||
proc.detect_human_presence(features)
|
||||
elapsed_ms = (time.perf_counter() - start) * 1000
|
||||
|
||||
assert elapsed_ms < 50, f"Single frame took {elapsed_ms:.1f} ms (budget: 50 ms)"
|
||||
|
||||
|
||||
class TestSustainedFrameBudget:
|
||||
"""Sustained 100-frame processing p95 must be < 50 ms per frame."""
|
||||
|
||||
def test_sustained_100_frames_p95(self):
|
||||
proc = CSIProcessor(config=_make_config())
|
||||
rng = np.random.default_rng(123)
|
||||
n_frames = 100
|
||||
latencies = []
|
||||
|
||||
for i in range(n_frames):
|
||||
frame = _make_csi_data(seed=i)
|
||||
start = time.perf_counter()
|
||||
preprocessed = proc.preprocess_csi_data(frame)
|
||||
features = proc.extract_features(preprocessed)
|
||||
if features:
|
||||
proc.detect_human_presence(features)
|
||||
proc.add_to_history(frame)
|
||||
elapsed_ms = (time.perf_counter() - start) * 1000
|
||||
latencies.append(elapsed_ms)
|
||||
|
||||
p50 = statistics.median(latencies)
|
||||
p95 = sorted(latencies)[int(0.95 * len(latencies))]
|
||||
p99 = sorted(latencies)[int(0.99 * len(latencies))]
|
||||
|
||||
print(f"\n--- Sustained {n_frames}-frame benchmark ---")
|
||||
print(f" p50: {p50:.2f} ms")
|
||||
print(f" p95: {p95:.2f} ms")
|
||||
print(f" p99: {p99:.2f} ms")
|
||||
print(f" min: {min(latencies):.2f} ms")
|
||||
print(f" max: {max(latencies):.2f} ms")
|
||||
|
||||
assert p95 < 50, f"p95 latency {p95:.1f} ms exceeds 50 ms budget"
|
||||
|
||||
|
||||
class TestPipelineWithDoppler:
|
||||
"""Full pipeline including Doppler estimation must stay within budget."""
|
||||
|
||||
def test_doppler_pipeline(self):
|
||||
proc = CSIProcessor(config=_make_config())
|
||||
n_frames = 100
|
||||
latencies = []
|
||||
|
||||
# Fill history first
|
||||
for i in range(20):
|
||||
frame = _make_csi_data(seed=i + 1000)
|
||||
proc.add_to_history(frame)
|
||||
|
||||
for i in range(n_frames):
|
||||
frame = _make_csi_data(seed=i + 2000)
|
||||
start = time.perf_counter()
|
||||
preprocessed = proc.preprocess_csi_data(frame)
|
||||
features = proc.extract_features(preprocessed)
|
||||
if features:
|
||||
proc.detect_human_presence(features)
|
||||
proc.add_to_history(frame)
|
||||
elapsed_ms = (time.perf_counter() - start) * 1000
|
||||
latencies.append(elapsed_ms)
|
||||
|
||||
p50 = statistics.median(latencies)
|
||||
p95 = sorted(latencies)[int(0.95 * len(latencies))]
|
||||
p99 = sorted(latencies)[int(0.99 * len(latencies))]
|
||||
|
||||
print(f"\n--- Doppler pipeline benchmark ({n_frames} frames, 20 warmup) ---")
|
||||
print(f" p50: {p50:.2f} ms")
|
||||
print(f" p95: {p95:.2f} ms")
|
||||
print(f" p99: {p99:.2f} ms")
|
||||
|
||||
# Doppler adds overhead but should still be within budget
|
||||
assert p95 < 50, f"Doppler pipeline p95 {p95:.1f} ms exceeds 50 ms budget"
|
||||
@@ -1,56 +0,0 @@
|
||||
"""Shared fixtures for unit tests."""
|
||||
|
||||
import os
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, AsyncMock, patch
|
||||
|
||||
# Set SECRET_KEY before any settings import
|
||||
os.environ.setdefault("SECRET_KEY", "test-secret-key-for-unit-tests-only")
|
||||
os.environ.setdefault("JWT_SECRET_KEY", "test-secret-key-for-unit-tests-only")
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_settings():
|
||||
"""Create a mock Settings object."""
|
||||
settings = MagicMock()
|
||||
settings.secret_key = "test-secret-key-for-unit-tests-only"
|
||||
settings.jwt_algorithm = "HS256"
|
||||
settings.jwt_expire_hours = 24
|
||||
settings.app_name = "test-app"
|
||||
settings.version = "0.1.0"
|
||||
settings.is_production = False
|
||||
settings.enable_rate_limiting = False
|
||||
settings.enable_authentication = False
|
||||
settings.rate_limit_requests = 100
|
||||
settings.rate_limit_window = 60
|
||||
settings.rate_limit_authenticated_requests = 1000
|
||||
settings.allowed_hosts = ["*"]
|
||||
settings.csi_buffer_size = 100
|
||||
settings.stream_buffer_size = 100
|
||||
settings.mock_hardware = True
|
||||
settings.mock_pose_data = True
|
||||
settings.enable_real_time_processing = False
|
||||
settings.trusted_proxies = ["127.0.0.1"]
|
||||
return settings
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_domain_config():
|
||||
"""Create a mock DomainConfig object."""
|
||||
config = MagicMock()
|
||||
config.pose_estimation = MagicMock()
|
||||
config.streaming = MagicMock()
|
||||
config.hardware = MagicMock()
|
||||
return config
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_redis():
|
||||
"""Provide a mock Redis client."""
|
||||
with patch("redis.Redis") as mock:
|
||||
client = MagicMock()
|
||||
client.ping.return_value = True
|
||||
client.get.return_value = None
|
||||
client.set.return_value = True
|
||||
mock.return_value = client
|
||||
yield client
|
||||
@@ -1,137 +0,0 @@
|
||||
"""Tests for AuthMiddleware and TokenManager."""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
from unittest.mock import MagicMock, AsyncMock, patch
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
|
||||
class TestTokenManager:
|
||||
def test_create_token(self, mock_settings):
|
||||
from src.middleware.auth import TokenManager
|
||||
tm = TokenManager(mock_settings)
|
||||
token = tm.create_access_token({"sub": "user1"})
|
||||
assert isinstance(token, str)
|
||||
assert len(token) > 0
|
||||
|
||||
def test_verify_valid_token(self, mock_settings):
|
||||
from src.middleware.auth import TokenManager
|
||||
tm = TokenManager(mock_settings)
|
||||
token = tm.create_access_token({"sub": "user1", "role": "admin"})
|
||||
payload = tm.verify_token(token)
|
||||
assert payload["sub"] == "user1"
|
||||
assert payload["role"] == "admin"
|
||||
|
||||
def test_verify_invalid_token(self, mock_settings):
|
||||
from src.middleware.auth import TokenManager, AuthenticationError
|
||||
tm = TokenManager(mock_settings)
|
||||
with pytest.raises(AuthenticationError):
|
||||
tm.verify_token("invalid.token.here")
|
||||
|
||||
def test_decode_claims(self, mock_settings):
|
||||
from src.middleware.auth import TokenManager
|
||||
tm = TokenManager(mock_settings)
|
||||
token = tm.create_access_token({"sub": "user1"})
|
||||
claims = tm.decode_token_claims(token)
|
||||
assert claims is not None
|
||||
assert claims["sub"] == "user1"
|
||||
|
||||
def test_decode_claims_invalid(self, mock_settings):
|
||||
from src.middleware.auth import TokenManager
|
||||
tm = TokenManager(mock_settings)
|
||||
claims = tm.decode_token_claims("bad-token")
|
||||
assert claims is None
|
||||
|
||||
def test_token_has_expiry(self, mock_settings):
|
||||
from src.middleware.auth import TokenManager
|
||||
tm = TokenManager(mock_settings)
|
||||
token = tm.create_access_token({"sub": "user1"})
|
||||
payload = tm.verify_token(token)
|
||||
assert "exp" in payload
|
||||
assert "iat" in payload
|
||||
|
||||
|
||||
class TestUserManager:
|
||||
def test_create_user(self):
|
||||
from src.middleware.auth import UserManager
|
||||
um = UserManager()
|
||||
assert um.get_user("nonexistent") is None
|
||||
|
||||
def test_hash_password(self):
|
||||
from src.middleware.auth import UserManager
|
||||
hashed = UserManager.hash_password("secret123")
|
||||
assert hashed != "secret123"
|
||||
assert len(hashed) > 20
|
||||
|
||||
def test_verify_password(self):
|
||||
from src.middleware.auth import UserManager
|
||||
hashed = UserManager.hash_password("secret123")
|
||||
assert UserManager.verify_password("secret123", hashed) is True
|
||||
assert UserManager.verify_password("wrong", hashed) is False
|
||||
|
||||
|
||||
class TestTokenBlacklist:
|
||||
def test_add_and_check(self):
|
||||
from src.api.middleware.auth import TokenBlacklist
|
||||
bl = TokenBlacklist()
|
||||
bl.add_token("tok123")
|
||||
assert bl.is_blacklisted("tok123") is True
|
||||
assert bl.is_blacklisted("tok456") is False
|
||||
|
||||
def test_blacklisted_token_rejected(self, mock_settings):
|
||||
from src.middleware.auth import TokenManager, AuthenticationError
|
||||
from src.api.middleware.auth import token_blacklist
|
||||
|
||||
tm = TokenManager(mock_settings)
|
||||
token = tm.create_access_token({"sub": "user1"})
|
||||
# Token should be valid
|
||||
tm.verify_token(token)
|
||||
# Blacklist it
|
||||
token_blacklist.add_token(token)
|
||||
with pytest.raises(AuthenticationError, match="revoked"):
|
||||
tm.verify_token(token)
|
||||
# Cleanup
|
||||
token_blacklist._blacklisted_tokens.discard(token)
|
||||
|
||||
|
||||
class TestAuthMiddleware:
|
||||
def test_public_paths(self, mock_settings):
|
||||
with patch("src.api.middleware.auth.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.auth import AuthMiddleware
|
||||
app = MagicMock()
|
||||
mw = AuthMiddleware(app)
|
||||
assert mw._is_public_path("/health") is True
|
||||
assert mw._is_public_path("/docs") is True
|
||||
assert mw._is_public_path("/api/v1/pose/analyze") is False
|
||||
|
||||
def test_protected_paths(self, mock_settings):
|
||||
with patch("src.api.middleware.auth.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.auth import AuthMiddleware
|
||||
app = MagicMock()
|
||||
mw = AuthMiddleware(app)
|
||||
assert mw._is_protected_path("/api/v1/pose/analyze") is True
|
||||
assert mw._is_protected_path("/health") is False
|
||||
|
||||
def test_extract_token_from_header(self, mock_settings):
|
||||
with patch("src.api.middleware.auth.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.auth import AuthMiddleware
|
||||
app = MagicMock()
|
||||
mw = AuthMiddleware(app)
|
||||
request = MagicMock()
|
||||
request.headers = {"authorization": "Bearer mytoken123"}
|
||||
request.query_params = {}
|
||||
request.cookies = {}
|
||||
token = mw._extract_token(request)
|
||||
assert token == "mytoken123"
|
||||
|
||||
def test_extract_token_missing(self, mock_settings):
|
||||
with patch("src.api.middleware.auth.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.auth import AuthMiddleware
|
||||
app = MagicMock()
|
||||
mw = AuthMiddleware(app)
|
||||
request = MagicMock()
|
||||
request.headers = {}
|
||||
request.query_params = {}
|
||||
request.cookies = {}
|
||||
token = mw._extract_token(request)
|
||||
assert token is None
|
||||
@@ -1,78 +0,0 @@
|
||||
"""Tests for error handling in the API layer."""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, patch
|
||||
from fastapi.testclient import TestClient
|
||||
|
||||
|
||||
class TestExceptionHandlers:
|
||||
"""Test the exception handlers registered on the FastAPI app."""
|
||||
|
||||
def _get_app(self):
|
||||
"""Import app lazily to avoid side effects."""
|
||||
with patch("src.api.main.get_settings") as mock_gs, \
|
||||
patch("src.api.main.get_domain_config") as mock_gdc, \
|
||||
patch("src.api.main.get_pose_service") as mock_ps, \
|
||||
patch("src.api.main.get_stream_service") as mock_ss, \
|
||||
patch("src.api.main.get_hardware_service") as mock_hs, \
|
||||
patch("src.api.main.connection_manager") as mock_cm, \
|
||||
patch("src.api.main.PoseStreamHandler") as mock_psh:
|
||||
mock_gs.return_value = MagicMock(
|
||||
app_name="test", version="0.1", environment="test",
|
||||
is_production=False, enable_rate_limiting=False,
|
||||
enable_authentication=False, docs_url="/docs",
|
||||
redoc_url="/redoc", openapi_url="/openapi.json",
|
||||
api_prefix="/api/v1",
|
||||
)
|
||||
mock_gs.return_value.get_logging_config.return_value = {
|
||||
"version": 1, "disable_existing_loggers": False,
|
||||
"handlers": {}, "loggers": {},
|
||||
}
|
||||
mock_gs.return_value.get_cors_config.return_value = {
|
||||
"allow_origins": ["*"], "allow_methods": ["*"],
|
||||
"allow_headers": ["*"],
|
||||
}
|
||||
# Re-import to pick up patches
|
||||
import importlib
|
||||
import src.api.main as m
|
||||
importlib.reload(m)
|
||||
return m.app
|
||||
|
||||
|
||||
class TestErrorResponseModel:
|
||||
def test_error_json_structure(self):
|
||||
"""Verify error JSON has code, message, type fields."""
|
||||
error = {
|
||||
"error": {
|
||||
"code": 404,
|
||||
"message": "Not found",
|
||||
"type": "http_error"
|
||||
}
|
||||
}
|
||||
assert error["error"]["code"] == 404
|
||||
assert "message" in error["error"]
|
||||
assert "type" in error["error"]
|
||||
|
||||
def test_validation_error_structure(self):
|
||||
error = {
|
||||
"error": {
|
||||
"code": 422,
|
||||
"message": "Validation error",
|
||||
"type": "validation_error",
|
||||
"details": []
|
||||
}
|
||||
}
|
||||
assert error["error"]["type"] == "validation_error"
|
||||
assert isinstance(error["error"]["details"], list)
|
||||
|
||||
def test_internal_error_masks_details(self):
|
||||
"""In production, internal errors should not leak stack traces."""
|
||||
error = {
|
||||
"error": {
|
||||
"code": 500,
|
||||
"message": "Internal server error",
|
||||
"type": "internal_error"
|
||||
}
|
||||
}
|
||||
assert "traceback" not in str(error)
|
||||
assert error["error"]["message"] == "Internal server error"
|
||||
@@ -1,430 +0,0 @@
|
||||
"""Tests for ESP32BinaryParser (ADR-018 binary frame format)."""
|
||||
|
||||
import asyncio
|
||||
import math
|
||||
import socket
|
||||
import struct
|
||||
import threading
|
||||
import time
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
|
||||
import sys
|
||||
import os
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..', 'src'))
|
||||
|
||||
from hardware.csi_extractor import (
|
||||
ESP32BinaryParser,
|
||||
CSIExtractor,
|
||||
CSIParseError,
|
||||
CSIExtractionError,
|
||||
SyncPacket,
|
||||
SyncPacketParser,
|
||||
)
|
||||
|
||||
# ADR-018 constants
|
||||
MAGIC = 0xC5110001
|
||||
# ADR-110: bytes 18-19 are now PPDU type + flags (used to be `2x` reserved).
|
||||
# Pre-ADR-110 firmware sends zeros for both, which round-trip as
|
||||
# ('ht_legacy', flags=all-false) — fully backwards compatible.
|
||||
HEADER_FMT = '<IBBHIIBBBB'
|
||||
HEADER_SIZE = 20
|
||||
|
||||
|
||||
def build_binary_frame(
|
||||
node_id: int = 1,
|
||||
n_antennas: int = 1,
|
||||
n_subcarriers: int = 4,
|
||||
freq_mhz: int = 2437,
|
||||
sequence: int = 0,
|
||||
rssi: int = -50,
|
||||
noise_floor: int = -90,
|
||||
iq_pairs: list = None,
|
||||
ppdu_byte: int = 0, # ADR-110: default 0 = HT/legacy (pre-ADR-110 behavior)
|
||||
flags_byte: int = 0, # ADR-110: default 0 = no flags set
|
||||
) -> bytes:
|
||||
"""Build an ADR-018 binary frame for testing."""
|
||||
if iq_pairs is None:
|
||||
iq_pairs = [(i % 50, (i * 2) % 50) for i in range(n_antennas * n_subcarriers)]
|
||||
|
||||
rssi_u8 = rssi & 0xFF
|
||||
noise_u8 = noise_floor & 0xFF
|
||||
|
||||
header = struct.pack(
|
||||
HEADER_FMT,
|
||||
MAGIC,
|
||||
node_id,
|
||||
n_antennas,
|
||||
n_subcarriers,
|
||||
freq_mhz,
|
||||
sequence,
|
||||
rssi_u8,
|
||||
noise_u8,
|
||||
ppdu_byte,
|
||||
flags_byte,
|
||||
)
|
||||
|
||||
iq_data = b''
|
||||
for i_val, q_val in iq_pairs:
|
||||
iq_data += struct.pack('<bb', i_val, q_val)
|
||||
|
||||
return header + iq_data
|
||||
|
||||
|
||||
class TestAdr110ByteEncoding:
|
||||
"""ADR-110: byte 18 = PPDU type, byte 19 = flags."""
|
||||
|
||||
def setup_method(self):
|
||||
self.parser = ESP32BinaryParser()
|
||||
|
||||
def test_pre_adr110_zeros_decode_as_ht_legacy(self):
|
||||
"""Pre-ADR-110 firmware sends zeros → must surface as HT/legacy + no flags."""
|
||||
frame = build_binary_frame() # ppdu_byte=0, flags_byte=0 default
|
||||
csi = self.parser.parse(frame)
|
||||
assert csi.metadata['ppdu_type'] == 'ht_legacy'
|
||||
assert csi.metadata['ppdu_type_raw'] == 0
|
||||
assert csi.metadata['he_capable'] is False
|
||||
assert csi.metadata['bw40'] is False
|
||||
assert csi.metadata['stbc'] is False
|
||||
assert csi.metadata['ldpc'] is False
|
||||
assert csi.metadata['ieee802154_sync_valid'] is False
|
||||
|
||||
def test_he_su_decodes(self):
|
||||
frame = build_binary_frame(ppdu_byte=1)
|
||||
csi = self.parser.parse(frame)
|
||||
assert csi.metadata['ppdu_type'] == 'he_su'
|
||||
assert csi.metadata['he_capable'] is True
|
||||
|
||||
def test_he_mu_and_he_tb_decode(self):
|
||||
for byte, expected in [(2, 'he_mu'), (3, 'he_tb')]:
|
||||
csi = self.parser.parse(build_binary_frame(ppdu_byte=byte))
|
||||
assert csi.metadata['ppdu_type'] == expected
|
||||
assert csi.metadata['he_capable'] is True
|
||||
|
||||
def test_unknown_ppdu_byte(self):
|
||||
csi = self.parser.parse(build_binary_frame(ppdu_byte=0xFF))
|
||||
assert csi.metadata['ppdu_type'] == 'unknown'
|
||||
assert csi.metadata['ppdu_type_raw'] == 0xFF
|
||||
assert csi.metadata['he_capable'] is False
|
||||
|
||||
def test_all_flags_set_round_trip(self):
|
||||
# bw40 (0x01) + STBC (0x04) + LDPC (0x08) + 15.4-sync (0x10) = 0x1D
|
||||
csi = self.parser.parse(build_binary_frame(ppdu_byte=1, flags_byte=0x1D))
|
||||
assert csi.metadata['bw40'] is True
|
||||
assert csi.metadata['stbc'] is True
|
||||
assert csi.metadata['ldpc'] is True
|
||||
assert csi.metadata['ieee802154_sync_valid'] is True
|
||||
assert csi.metadata['adr018_flags_raw'] == 0x1D
|
||||
|
||||
|
||||
class TestESP32BinaryParser:
|
||||
"""Tests for ESP32BinaryParser."""
|
||||
|
||||
def setup_method(self):
|
||||
self.parser = ESP32BinaryParser()
|
||||
|
||||
def test_parse_valid_binary_frame(self):
|
||||
"""Parse a well-formed ADR-018 binary frame."""
|
||||
iq = [(3, 4), (0, 10), (5, 12), (7, 0)]
|
||||
frame_bytes = build_binary_frame(
|
||||
node_id=1, n_antennas=1, n_subcarriers=4,
|
||||
freq_mhz=2437, sequence=42, rssi=-50, noise_floor=-90,
|
||||
iq_pairs=iq,
|
||||
)
|
||||
|
||||
result = self.parser.parse(frame_bytes)
|
||||
|
||||
assert result.num_antennas == 1
|
||||
assert result.num_subcarriers == 4
|
||||
assert result.amplitude.shape == (1, 4)
|
||||
assert result.phase.shape == (1, 4)
|
||||
assert result.metadata['node_id'] == 1
|
||||
assert result.metadata['sequence'] == 42
|
||||
assert result.metadata['rssi_dbm'] == -50
|
||||
assert result.metadata['noise_floor_dbm'] == -90
|
||||
assert result.metadata['channel_freq_mhz'] == 2437
|
||||
|
||||
# Check amplitude for I=3, Q=4 -> sqrt(9+16) = 5.0
|
||||
assert abs(result.amplitude[0, 0] - 5.0) < 0.001
|
||||
# I=0, Q=10 -> 10.0
|
||||
assert abs(result.amplitude[0, 1] - 10.0) < 0.001
|
||||
|
||||
def test_parse_frame_too_short(self):
|
||||
"""Reject frames shorter than the 20-byte header."""
|
||||
with pytest.raises(CSIParseError, match="too short"):
|
||||
self.parser.parse(b'\x00' * 10)
|
||||
|
||||
def test_parse_invalid_magic(self):
|
||||
"""Reject frames with wrong magic number."""
|
||||
bad_frame = build_binary_frame()
|
||||
# Corrupt magic
|
||||
bad_frame = b'\xFF\xFF\xFF\xFF' + bad_frame[4:]
|
||||
with pytest.raises(CSIParseError, match="Invalid magic"):
|
||||
self.parser.parse(bad_frame)
|
||||
|
||||
def test_parse_multi_antenna_frame(self):
|
||||
"""Parse a frame with 3 antennas and 4 subcarriers."""
|
||||
n_ant = 3
|
||||
n_sc = 4
|
||||
iq = [(i + 1, i + 2) for i in range(n_ant * n_sc)]
|
||||
|
||||
frame_bytes = build_binary_frame(
|
||||
node_id=5, n_antennas=n_ant, n_subcarriers=n_sc,
|
||||
iq_pairs=iq,
|
||||
)
|
||||
|
||||
result = self.parser.parse(frame_bytes)
|
||||
|
||||
assert result.num_antennas == 3
|
||||
assert result.num_subcarriers == 4
|
||||
assert result.amplitude.shape == (3, 4)
|
||||
assert result.phase.shape == (3, 4)
|
||||
|
||||
def test_udp_read_with_mock_server(self):
|
||||
"""Send a frame via UDP and verify CSIExtractor receives it."""
|
||||
# Find a free port
|
||||
sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
|
||||
sock.bind(('127.0.0.1', 0))
|
||||
port = sock.getsockname()[1]
|
||||
sock.close()
|
||||
|
||||
frame_bytes = build_binary_frame(
|
||||
node_id=3, n_antennas=1, n_subcarriers=4,
|
||||
freq_mhz=2412, sequence=99,
|
||||
)
|
||||
|
||||
config = {
|
||||
'hardware_type': 'esp32',
|
||||
'parser_format': 'binary',
|
||||
'sampling_rate': 100,
|
||||
'buffer_size': 2048,
|
||||
'timeout': 2,
|
||||
'aggregator_host': '127.0.0.1',
|
||||
'aggregator_port': port,
|
||||
}
|
||||
|
||||
extractor = CSIExtractor(config)
|
||||
|
||||
async def run_test():
|
||||
# Connect
|
||||
await extractor.connect()
|
||||
|
||||
# Send frame after a short delay from a background thread
|
||||
def send():
|
||||
time.sleep(0.2)
|
||||
s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
|
||||
s.sendto(frame_bytes, ('127.0.0.1', port))
|
||||
s.close()
|
||||
|
||||
sender = threading.Thread(target=send, daemon=True)
|
||||
sender.start()
|
||||
|
||||
result = await extractor.extract_csi()
|
||||
sender.join(timeout=2)
|
||||
|
||||
assert result.metadata['node_id'] == 3
|
||||
assert result.metadata['sequence'] == 99
|
||||
assert result.num_subcarriers == 4
|
||||
|
||||
await extractor.disconnect()
|
||||
|
||||
asyncio.run(run_test())
|
||||
|
||||
def test_udp_timeout(self):
|
||||
"""Verify timeout when no UDP server is sending data."""
|
||||
# Find a free port (nothing will send to it)
|
||||
sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
|
||||
sock.bind(('127.0.0.1', 0))
|
||||
port = sock.getsockname()[1]
|
||||
sock.close()
|
||||
|
||||
config = {
|
||||
'hardware_type': 'esp32',
|
||||
'parser_format': 'binary',
|
||||
'sampling_rate': 100,
|
||||
'buffer_size': 2048,
|
||||
'timeout': 0.5,
|
||||
'retry_attempts': 1,
|
||||
'aggregator_host': '127.0.0.1',
|
||||
'aggregator_port': port,
|
||||
}
|
||||
|
||||
extractor = CSIExtractor(config)
|
||||
|
||||
async def run_test():
|
||||
await extractor.connect()
|
||||
with pytest.raises(CSIExtractionError, match="timed out"):
|
||||
await extractor.extract_csi()
|
||||
await extractor.disconnect()
|
||||
|
||||
asyncio.run(run_test())
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# ADR-110 §A0.12 — SyncPacket / SyncPacketParser tests (firmware v0.6.9+)
|
||||
# ============================================================================
|
||||
|
||||
SYNC_MAGIC = 0xC511A110
|
||||
SYNC_SIZE = 32
|
||||
SYNC_FMT = '<IBBBBQQI4x'
|
||||
|
||||
|
||||
def build_sync_packet(
|
||||
node_id: int = 9,
|
||||
proto_ver: int = 1,
|
||||
is_leader: bool = False,
|
||||
is_valid: bool = True,
|
||||
smoothed_used: bool = True,
|
||||
local_us: int = 28798450,
|
||||
epoch_us: int = 27634885,
|
||||
sequence: int = 20,
|
||||
) -> bytes:
|
||||
flags = 0
|
||||
if is_leader: flags |= 0x01
|
||||
if is_valid: flags |= 0x02
|
||||
if smoothed_used: flags |= 0x04
|
||||
return struct.pack(
|
||||
SYNC_FMT,
|
||||
SYNC_MAGIC,
|
||||
node_id, proto_ver, flags, 0,
|
||||
local_us, epoch_us, sequence,
|
||||
)
|
||||
|
||||
|
||||
class TestSyncPacketParser:
|
||||
"""ADR-110 §A0.12: 32-byte UDP sync packet (magic 0xC511A110)."""
|
||||
|
||||
def test_follower_typical_packet_roundtrips(self):
|
||||
"""Match the COM9-witnessed sync-pkt #1 byte-for-byte."""
|
||||
raw = build_sync_packet(
|
||||
node_id=9, is_leader=False, is_valid=True, smoothed_used=True,
|
||||
local_us=28798450, epoch_us=27634885, sequence=20,
|
||||
)
|
||||
assert len(raw) == SYNC_SIZE
|
||||
pkt = SyncPacketParser.parse(raw)
|
||||
assert isinstance(pkt, SyncPacket)
|
||||
assert pkt.node_id == 9
|
||||
assert pkt.proto_ver == 1
|
||||
assert pkt.is_leader is False
|
||||
assert pkt.is_valid is True
|
||||
assert pkt.smoothed_used is True
|
||||
assert pkt.local_us == 28798450
|
||||
assert pkt.epoch_us == 27634885
|
||||
assert pkt.sequence == 20
|
||||
# The 1.16-second boot delta from §A0.10 should be recoverable
|
||||
assert pkt.local_us - pkt.epoch_us == 1163565
|
||||
|
||||
def test_leader_packet_has_local_close_to_epoch(self):
|
||||
"""COM12 (leader) had flags=0x03 and epoch ≈ local."""
|
||||
raw = build_sync_packet(
|
||||
node_id=12, is_leader=True, is_valid=True, smoothed_used=False,
|
||||
local_us=28864932, epoch_us=28864939, sequence=20,
|
||||
)
|
||||
pkt = SyncPacketParser.parse(raw)
|
||||
assert pkt.node_id == 12
|
||||
assert pkt.is_leader is True
|
||||
assert pkt.is_valid is True
|
||||
assert pkt.smoothed_used is False
|
||||
assert pkt.flags_raw == 0x03
|
||||
assert pkt.local_us - pkt.epoch_us == -7 # leader has zero offset
|
||||
|
||||
def test_magic_mismatch_raises(self):
|
||||
"""A non-sync datagram must not silently decode."""
|
||||
raw = bytearray(build_sync_packet())
|
||||
raw[0] = 0x01 # corrupt magic low byte
|
||||
with pytest.raises(CSIParseError, match="magic mismatch"):
|
||||
SyncPacketParser.parse(bytes(raw))
|
||||
|
||||
def test_short_packet_raises(self):
|
||||
"""Below 32 bytes must error early, not silently truncate."""
|
||||
raw = build_sync_packet()[:16]
|
||||
with pytest.raises(CSIParseError, match="too short"):
|
||||
SyncPacketParser.parse(raw)
|
||||
|
||||
def test_all_flag_combinations(self):
|
||||
"""Each flag bit decodes independently."""
|
||||
for is_leader in (False, True):
|
||||
for is_valid in (False, True):
|
||||
for smoothed_used in (False, True):
|
||||
raw = build_sync_packet(
|
||||
is_leader=is_leader,
|
||||
is_valid=is_valid,
|
||||
smoothed_used=smoothed_used,
|
||||
)
|
||||
pkt = SyncPacketParser.parse(raw)
|
||||
assert pkt.is_leader == is_leader
|
||||
assert pkt.is_valid == is_valid
|
||||
assert pkt.smoothed_used == smoothed_used
|
||||
|
||||
def test_dispatch_distinguishes_csi_from_sync(self):
|
||||
"""A host can pick CSI vs sync by leading magic."""
|
||||
csi_magic = struct.unpack_from('<I', build_binary_frame(), 0)[0]
|
||||
sync_magic = struct.unpack_from('<I', build_sync_packet(), 0)[0]
|
||||
assert csi_magic == ESP32BinaryParser.MAGIC
|
||||
assert sync_magic == SyncPacketParser.MAGIC
|
||||
assert csi_magic != sync_magic
|
||||
|
||||
def test_apply_to_local_recovers_epoch_at_sync_point(self):
|
||||
"""ADR-110 iter 26 — Python parity with Rust's `apply_to_local`.
|
||||
At local_at_frame == sync.local_us, the recovered mesh time must
|
||||
equal sync.epoch_us exactly."""
|
||||
pkt = SyncPacketParser.parse(build_sync_packet(
|
||||
local_us=28_798_450, epoch_us=27_634_885, sequence=20,
|
||||
))
|
||||
assert pkt.apply_to_local(pkt.local_us) == pkt.epoch_us
|
||||
assert pkt.local_minus_epoch_us() == 1_163_565 # §A0.10's bench number
|
||||
|
||||
def test_apply_to_local_preserves_inter_frame_delta(self):
|
||||
"""A frame arriving 5 s after the sync packet on the follower's
|
||||
local clock must produce a mesh time exactly 5 s after sync.epoch_us."""
|
||||
pkt = SyncPacketParser.parse(build_sync_packet(
|
||||
local_us=28_798_450, epoch_us=27_634_885, sequence=20,
|
||||
))
|
||||
local_at_frame = pkt.local_us + 5_000_000
|
||||
assert pkt.apply_to_local(local_at_frame) == pkt.epoch_us + 5_000_000
|
||||
|
||||
def test_mesh_aligned_us_for_sequence_matches_rust(self):
|
||||
"""Cross-language parity with Rust's
|
||||
`end_to_end_sync_decode_then_frame_mesh_recovery` test —
|
||||
100 frames after sync.sequence at 20 fps = sync.epoch_us + 5 s."""
|
||||
pkt = SyncPacketParser.parse(build_sync_packet(
|
||||
local_us=28_798_450, epoch_us=27_634_885, sequence=20,
|
||||
))
|
||||
mesh = pkt.mesh_aligned_us_for_sequence(120, 20.0)
|
||||
assert mesh == pkt.epoch_us + 5_000_000
|
||||
# Both paths (apply_to_local + interpolation) must agree
|
||||
local_at = pkt.local_us + 5_000_000
|
||||
assert pkt.apply_to_local(local_at) == mesh
|
||||
|
||||
def test_canonical_wire_bytes_match_rust_decoder(self):
|
||||
"""ADR-110 iter 21 — cross-language wire-format conformance gate.
|
||||
|
||||
These exact bytes also appear pinned in the Rust hardware crate's
|
||||
`canonical_wire_bytes_match_python_decoder` test (same field
|
||||
values, encoded by Rust's `SyncPacket::to_bytes`). If Python's
|
||||
hardcoded hex stops matching what Rust produces from the equivalent
|
||||
SyncPacket struct, ONE of the decoders has drifted from the wire.
|
||||
|
||||
Canonical packet: COM9 sync-pkt #1 from §A0.12 live capture.
|
||||
"""
|
||||
canonical = bytes.fromhex(
|
||||
"10a111c509010600" # magic LE + node=9 + ver=1 + flags=0x06 + reserved
|
||||
"f26db70100000000" # local_us = 28_798_450 (LE u64)
|
||||
"c5aca50100000000" # epoch_us = 27_634_885 (LE u64)
|
||||
"1400000000000000" # sequence = 20 (LE u32) + 4 reserved bytes
|
||||
)
|
||||
assert len(canonical) == SyncPacketParser.SIZE == 32
|
||||
|
||||
pkt = SyncPacketParser.parse(canonical)
|
||||
assert pkt.node_id == 9
|
||||
assert pkt.proto_ver == 1
|
||||
assert pkt.flags_raw == 0x06
|
||||
assert pkt.is_leader is False
|
||||
assert pkt.is_valid is True
|
||||
assert pkt.smoothed_used is True
|
||||
assert pkt.local_us == 28_798_450
|
||||
assert pkt.epoch_us == 27_634_885
|
||||
assert pkt.sequence == 20
|
||||
# Recovered offset matches §A0.10's measured 1.16-second boot delta.
|
||||
assert pkt.local_us - pkt.epoch_us == 1_163_565
|
||||
@@ -1,65 +0,0 @@
|
||||
"""Tests for HardwareService."""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, AsyncMock, patch
|
||||
|
||||
|
||||
class TestHardwareServiceInit:
|
||||
def test_init(self, mock_settings, mock_domain_config):
|
||||
mock_settings.mock_hardware = True
|
||||
with patch("src.services.hardware_service.RouterInterface"):
|
||||
from src.services.hardware_service import HardwareService
|
||||
svc = HardwareService(mock_settings, mock_domain_config)
|
||||
assert svc.is_running is False
|
||||
assert svc.stats["total_samples"] == 0
|
||||
assert svc.stats["connected_routers"] == 0
|
||||
|
||||
def test_stats_defaults(self, mock_settings, mock_domain_config):
|
||||
mock_settings.mock_hardware = True
|
||||
with patch("src.services.hardware_service.RouterInterface"):
|
||||
from src.services.hardware_service import HardwareService
|
||||
svc = HardwareService(mock_settings, mock_domain_config)
|
||||
assert svc.stats["successful_samples"] == 0
|
||||
assert svc.stats["failed_samples"] == 0
|
||||
assert svc.stats["last_sample_time"] is None
|
||||
|
||||
|
||||
class TestHardwareServiceLifecycle:
|
||||
@pytest.mark.asyncio
|
||||
async def test_start(self, mock_settings, mock_domain_config):
|
||||
mock_settings.mock_hardware = True
|
||||
with patch("src.services.hardware_service.RouterInterface"):
|
||||
from src.services.hardware_service import HardwareService
|
||||
svc = HardwareService(mock_settings, mock_domain_config)
|
||||
svc._initialize_routers = AsyncMock()
|
||||
svc._monitoring_loop = AsyncMock()
|
||||
await svc.start()
|
||||
assert svc.is_running is True
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_double_start_idempotent(self, mock_settings, mock_domain_config):
|
||||
mock_settings.mock_hardware = True
|
||||
with patch("src.services.hardware_service.RouterInterface"):
|
||||
from src.services.hardware_service import HardwareService
|
||||
svc = HardwareService(mock_settings, mock_domain_config)
|
||||
svc._initialize_routers = AsyncMock()
|
||||
svc._monitoring_loop = AsyncMock()
|
||||
await svc.start()
|
||||
await svc.start() # idempotent
|
||||
assert svc.is_running is True
|
||||
|
||||
|
||||
class TestHardwareServiceRouter:
|
||||
def test_no_routers_on_init(self, mock_settings, mock_domain_config):
|
||||
mock_settings.mock_hardware = True
|
||||
with patch("src.services.hardware_service.RouterInterface"):
|
||||
from src.services.hardware_service import HardwareService
|
||||
svc = HardwareService(mock_settings, mock_domain_config)
|
||||
assert len(svc.router_interfaces) == 0
|
||||
|
||||
def test_max_recent_samples(self, mock_settings, mock_domain_config):
|
||||
mock_settings.mock_hardware = True
|
||||
with patch("src.services.hardware_service.RouterInterface"):
|
||||
from src.services.hardware_service import HardwareService
|
||||
svc = HardwareService(mock_settings, mock_domain_config)
|
||||
assert svc.max_recent_samples == 1000
|
||||
@@ -1,67 +0,0 @@
|
||||
"""Tests for HealthCheckService."""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
|
||||
class TestHealthCheckServiceInit:
|
||||
def test_init(self, mock_settings):
|
||||
from src.services.health_check import HealthCheckService
|
||||
svc = HealthCheckService(mock_settings)
|
||||
assert svc._initialized is False
|
||||
assert svc._running is False
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_initialize(self, mock_settings):
|
||||
from src.services.health_check import HealthCheckService
|
||||
svc = HealthCheckService(mock_settings)
|
||||
await svc.initialize()
|
||||
assert svc._initialized is True
|
||||
assert "api" in svc._services
|
||||
assert "database" in svc._services
|
||||
assert "hardware" in svc._services
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_double_initialize(self, mock_settings):
|
||||
from src.services.health_check import HealthCheckService
|
||||
svc = HealthCheckService(mock_settings)
|
||||
await svc.initialize()
|
||||
await svc.initialize() # idempotent
|
||||
assert svc._initialized is True
|
||||
|
||||
|
||||
class TestHealthCheckAggregation:
|
||||
@pytest.mark.asyncio
|
||||
async def test_services_registered(self, mock_settings):
|
||||
from src.services.health_check import HealthCheckService, HealthStatus
|
||||
svc = HealthCheckService(mock_settings)
|
||||
await svc.initialize()
|
||||
assert len(svc._services) == 6
|
||||
for name, sh in svc._services.items():
|
||||
assert sh.status == HealthStatus.UNKNOWN
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_service_names(self, mock_settings):
|
||||
from src.services.health_check import HealthCheckService
|
||||
svc = HealthCheckService(mock_settings)
|
||||
await svc.initialize()
|
||||
expected = {"api", "database", "redis", "hardware", "pose", "stream"}
|
||||
assert set(svc._services.keys()) == expected
|
||||
|
||||
|
||||
class TestHealthStatus:
|
||||
def test_enum_values(self):
|
||||
from src.services.health_check import HealthStatus
|
||||
assert HealthStatus.HEALTHY.value == "healthy"
|
||||
assert HealthStatus.DEGRADED.value == "degraded"
|
||||
assert HealthStatus.UNHEALTHY.value == "unhealthy"
|
||||
assert HealthStatus.UNKNOWN.value == "unknown"
|
||||
|
||||
|
||||
class TestHealthCheck:
|
||||
def test_health_check_dataclass(self):
|
||||
from src.services.health_check import HealthCheck, HealthStatus
|
||||
hc = HealthCheck(name="test", status=HealthStatus.HEALTHY, message="ok")
|
||||
assert hc.name == "test"
|
||||
assert hc.status == HealthStatus.HEALTHY
|
||||
assert hc.duration_ms == 0.0
|
||||
@@ -1,70 +0,0 @@
|
||||
"""Tests for MetricsService."""
|
||||
|
||||
import pytest
|
||||
from datetime import timedelta
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
|
||||
class TestMetricSeries:
|
||||
def test_add_point(self):
|
||||
from src.services.metrics import MetricSeries
|
||||
ms = MetricSeries(name="test", description="desc", unit="ms")
|
||||
ms.add_point(42.0)
|
||||
assert len(ms.points) == 1
|
||||
assert ms.points[0].value == 42.0
|
||||
|
||||
def test_get_latest(self):
|
||||
from src.services.metrics import MetricSeries
|
||||
ms = MetricSeries(name="test", description="desc", unit="ms")
|
||||
ms.add_point(1.0)
|
||||
ms.add_point(2.0)
|
||||
latest = ms.get_latest()
|
||||
assert latest is not None
|
||||
assert latest.value == 2.0
|
||||
|
||||
def test_get_latest_empty(self):
|
||||
from src.services.metrics import MetricSeries
|
||||
ms = MetricSeries(name="test", description="desc", unit="ms")
|
||||
assert ms.get_latest() is None
|
||||
|
||||
def test_get_average(self):
|
||||
from src.services.metrics import MetricSeries
|
||||
ms = MetricSeries(name="test", description="desc", unit="ms")
|
||||
for v in [10.0, 20.0, 30.0]:
|
||||
ms.add_point(v)
|
||||
avg = ms.get_average(timedelta(minutes=5))
|
||||
assert avg == pytest.approx(20.0)
|
||||
|
||||
def test_get_average_empty(self):
|
||||
from src.services.metrics import MetricSeries
|
||||
ms = MetricSeries(name="test", description="desc", unit="ms")
|
||||
assert ms.get_average(timedelta(minutes=5)) is None
|
||||
|
||||
def test_get_max(self):
|
||||
from src.services.metrics import MetricSeries
|
||||
ms = MetricSeries(name="test", description="desc", unit="ms")
|
||||
for v in [10.0, 50.0, 30.0]:
|
||||
ms.add_point(v)
|
||||
mx = ms.get_max(timedelta(minutes=5))
|
||||
assert mx == 50.0
|
||||
|
||||
def test_labels(self):
|
||||
from src.services.metrics import MetricSeries
|
||||
ms = MetricSeries(name="test", description="desc", unit="ms")
|
||||
ms.add_point(1.0, {"region": "us-east"})
|
||||
assert ms.points[0].labels["region"] == "us-east"
|
||||
|
||||
def test_maxlen(self):
|
||||
from src.services.metrics import MetricSeries
|
||||
ms = MetricSeries(name="test", description="desc", unit="ms")
|
||||
for i in range(1100):
|
||||
ms.add_point(float(i))
|
||||
assert len(ms.points) == 1000
|
||||
|
||||
|
||||
class TestMetricsService:
|
||||
def test_init(self, mock_settings):
|
||||
with patch("src.services.metrics.psutil"):
|
||||
from src.services.metrics import MetricsService
|
||||
svc = MetricsService(mock_settings)
|
||||
assert svc._metrics is not None
|
||||
@@ -1,73 +0,0 @@
|
||||
"""Tests for PoseService."""
|
||||
|
||||
import pytest
|
||||
import asyncio
|
||||
from unittest.mock import MagicMock, AsyncMock, patch
|
||||
from datetime import datetime
|
||||
|
||||
|
||||
class TestPoseServiceInit:
|
||||
def test_init_sets_defaults(self, mock_settings, mock_domain_config):
|
||||
with patch.dict("sys.modules", {
|
||||
"torch": MagicMock(),
|
||||
"src.models.densepose_head": MagicMock(),
|
||||
"src.models.modality_translation": MagicMock(),
|
||||
}):
|
||||
from src.services.pose_service import PoseService
|
||||
svc = PoseService(mock_settings, mock_domain_config)
|
||||
assert svc.is_initialized is False
|
||||
assert svc.is_running is False
|
||||
assert svc.stats["total_processed"] == 0
|
||||
|
||||
def test_stats_are_zero_on_init(self, mock_settings, mock_domain_config):
|
||||
with patch.dict("sys.modules", {
|
||||
"torch": MagicMock(),
|
||||
"src.models.densepose_head": MagicMock(),
|
||||
"src.models.modality_translation": MagicMock(),
|
||||
}):
|
||||
from src.services.pose_service import PoseService
|
||||
svc = PoseService(mock_settings, mock_domain_config)
|
||||
assert svc.stats["successful_detections"] == 0
|
||||
assert svc.stats["failed_detections"] == 0
|
||||
assert svc.stats["average_confidence"] == 0.0
|
||||
|
||||
|
||||
class TestPoseServiceLifecycle:
|
||||
@pytest.mark.asyncio
|
||||
async def test_initialize_sets_flag(self, mock_settings, mock_domain_config):
|
||||
with patch.dict("sys.modules", {
|
||||
"torch": MagicMock(),
|
||||
"src.models.densepose_head": MagicMock(),
|
||||
"src.models.modality_translation": MagicMock(),
|
||||
}):
|
||||
from src.services.pose_service import PoseService
|
||||
svc = PoseService(mock_settings, mock_domain_config)
|
||||
await svc.initialize()
|
||||
assert svc.is_initialized is True
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_start_stop(self, mock_settings, mock_domain_config):
|
||||
with patch.dict("sys.modules", {
|
||||
"torch": MagicMock(),
|
||||
"src.models.densepose_head": MagicMock(),
|
||||
"src.models.modality_translation": MagicMock(),
|
||||
}):
|
||||
from src.services.pose_service import PoseService
|
||||
svc = PoseService(mock_settings, mock_domain_config)
|
||||
await svc.initialize()
|
||||
await svc.start()
|
||||
assert svc.is_running is True
|
||||
await svc.stop()
|
||||
assert svc.is_running is False
|
||||
|
||||
|
||||
class TestPoseServiceStats:
|
||||
def test_initial_classification(self, mock_settings, mock_domain_config):
|
||||
with patch.dict("sys.modules", {
|
||||
"torch": MagicMock(),
|
||||
"src.models.densepose_head": MagicMock(),
|
||||
"src.models.modality_translation": MagicMock(),
|
||||
}):
|
||||
from src.services.pose_service import PoseService
|
||||
svc = PoseService(mock_settings, mock_domain_config)
|
||||
assert svc.last_error is None
|
||||
@@ -1,62 +0,0 @@
|
||||
"""Tests for rate limiting middleware."""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, AsyncMock, patch
|
||||
|
||||
|
||||
class TestRateLimitMiddleware:
|
||||
def test_init(self, mock_settings):
|
||||
with patch("src.api.middleware.rate_limit.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.rate_limit import RateLimitMiddleware
|
||||
app = MagicMock()
|
||||
mw = RateLimitMiddleware(app)
|
||||
assert "anonymous" in mw.rate_limits
|
||||
assert "authenticated" in mw.rate_limits
|
||||
assert "admin" in mw.rate_limits
|
||||
|
||||
def test_exempt_paths(self, mock_settings):
|
||||
with patch("src.api.middleware.rate_limit.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.rate_limit import RateLimitMiddleware
|
||||
app = MagicMock()
|
||||
mw = RateLimitMiddleware(app)
|
||||
assert "/health" in mw.exempt_paths
|
||||
assert "/metrics" in mw.exempt_paths
|
||||
|
||||
def test_is_exempt(self, mock_settings):
|
||||
with patch("src.api.middleware.rate_limit.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.rate_limit import RateLimitMiddleware
|
||||
app = MagicMock()
|
||||
mw = RateLimitMiddleware(app)
|
||||
assert mw._is_exempt_path("/health") is True
|
||||
assert mw._is_exempt_path("/api/v1/pose/current") is False
|
||||
|
||||
def test_path_specific_limits(self, mock_settings):
|
||||
with patch("src.api.middleware.rate_limit.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.rate_limit import RateLimitMiddleware
|
||||
app = MagicMock()
|
||||
mw = RateLimitMiddleware(app)
|
||||
assert "/api/v1/pose/current" in mw.path_limits
|
||||
assert mw.path_limits["/api/v1/pose/current"]["requests"] == 60
|
||||
|
||||
def test_trusted_proxies_not_blocked(self, mock_settings):
|
||||
with patch("src.api.middleware.rate_limit.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.rate_limit import RateLimitMiddleware
|
||||
app = MagicMock()
|
||||
mw = RateLimitMiddleware(app)
|
||||
assert not mw._is_client_blocked("new-client-id")
|
||||
|
||||
|
||||
class TestRateLimitConfig:
|
||||
def test_anonymous_limit(self, mock_settings):
|
||||
with patch("src.api.middleware.rate_limit.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.rate_limit import RateLimitMiddleware
|
||||
app = MagicMock()
|
||||
mw = RateLimitMiddleware(app)
|
||||
assert mw.rate_limits["anonymous"]["burst"] == 10
|
||||
|
||||
def test_admin_limit(self, mock_settings):
|
||||
with patch("src.api.middleware.rate_limit.get_settings", return_value=mock_settings):
|
||||
from src.api.middleware.rate_limit import RateLimitMiddleware
|
||||
app = MagicMock()
|
||||
mw = RateLimitMiddleware(app)
|
||||
assert mw.rate_limits["admin"]["requests"] == 10000
|
||||
@@ -1,68 +0,0 @@
|
||||
"""Tests for StreamService."""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, AsyncMock, patch
|
||||
|
||||
|
||||
class TestStreamServiceLifecycle:
|
||||
def test_init(self, mock_settings, mock_domain_config):
|
||||
from src.services.stream_service import StreamService
|
||||
svc = StreamService(mock_settings, mock_domain_config)
|
||||
assert svc.is_running is False
|
||||
assert len(svc.connections) == 0
|
||||
assert svc.stats["active_connections"] == 0
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_initialize(self, mock_settings, mock_domain_config):
|
||||
from src.services.stream_service import StreamService
|
||||
svc = StreamService(mock_settings, mock_domain_config)
|
||||
await svc.initialize()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_start(self, mock_settings, mock_domain_config):
|
||||
mock_settings.enable_real_time_processing = False
|
||||
from src.services.stream_service import StreamService
|
||||
svc = StreamService(mock_settings, mock_domain_config)
|
||||
await svc.start()
|
||||
assert svc.is_running is True
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_stop(self, mock_settings, mock_domain_config):
|
||||
mock_settings.enable_real_time_processing = False
|
||||
from src.services.stream_service import StreamService
|
||||
svc = StreamService(mock_settings, mock_domain_config)
|
||||
await svc.start()
|
||||
await svc.stop()
|
||||
assert svc.is_running is False
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_double_start(self, mock_settings, mock_domain_config):
|
||||
mock_settings.enable_real_time_processing = False
|
||||
from src.services.stream_service import StreamService
|
||||
svc = StreamService(mock_settings, mock_domain_config)
|
||||
await svc.start()
|
||||
await svc.start() # should be idempotent
|
||||
assert svc.is_running is True
|
||||
|
||||
|
||||
class TestStreamServiceConnections:
|
||||
def test_no_connections_on_init(self, mock_settings, mock_domain_config):
|
||||
from src.services.stream_service import StreamService
|
||||
svc = StreamService(mock_settings, mock_domain_config)
|
||||
assert svc.stats["total_connections"] == 0
|
||||
assert svc.stats["messages_sent"] == 0
|
||||
|
||||
def test_buffer_sizes(self, mock_settings, mock_domain_config):
|
||||
mock_settings.stream_buffer_size = 50
|
||||
from src.services.stream_service import StreamService
|
||||
svc = StreamService(mock_settings, mock_domain_config)
|
||||
assert svc.pose_buffer.maxlen == 50
|
||||
assert svc.csi_buffer.maxlen == 50
|
||||
|
||||
|
||||
class TestStreamServiceBroadcast:
|
||||
def test_stats_messages_failed_init_zero(self, mock_settings, mock_domain_config):
|
||||
from src.services.stream_service import StreamService
|
||||
svc = StreamService(mock_settings, mock_domain_config)
|
||||
assert svc.stats["messages_failed"] == 0
|
||||
assert svc.stats["data_points_streamed"] == 0
|
||||
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 1.9 MiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.2 MiB |
File diff suppressed because one or more lines are too long
@@ -1,26 +0,0 @@
|
||||
# Upstream clone (WiFlow-STD, DY2434) -- never commit third-party code/weights
|
||||
upstream/
|
||||
|
||||
# Local python env
|
||||
.venv/
|
||||
|
||||
# Downloaded data / artifacts
|
||||
data/
|
||||
downloads/
|
||||
*.pth
|
||||
*.pt
|
||||
*.npy
|
||||
*.npz
|
||||
*.zip
|
||||
*.mat
|
||||
*.safetensors
|
||||
results/parity_fixture.json
|
||||
__pycache__/
|
||||
*.onnx
|
||||
|
||||
# Committed ground truth: corruption masks for the pristine Kaggle download.
|
||||
# remote/clean_v2.py zeroes the corrupted source windows IN PLACE, so these
|
||||
# masks CANNOT be regenerated from a cleaned copy (generate_corruption_masks.py
|
||||
# documents the criteria and reproduces them only from a fresh download).
|
||||
!results/nan_windows_mask.npy
|
||||
!results/big_windows_mask.npy
|
||||
@@ -1,486 +0,0 @@
|
||||
# WiFlow-STD (DY2434) Benchmark Results — ADR-152 §2.2
|
||||
|
||||
Upstream: <https://github.com/DY2434/WiFlow-WiFi-Pose-Estimation-with-Spatio-Temporal-Decoupling>
|
||||
pinned at `06899d29` (2026-04-05), Apache-2.0. Dataset: Kaggle `kaka2434/wiflow-dataset`
|
||||
(12.8 GB archive → 15.5 GB extracted; 360,000 windows of 540×20 CSI + 15-keypoint 2D labels).
|
||||
|
||||
Published claims (README "Setting 1"): PCK@20 97.25%, PCK@30 98.63%, PCK@40 99.16%,
|
||||
PCK@50 99.48%, MPJPE 0.007 m, 2.23M params, 0.07 GFLOPs.
|
||||
|
||||
## Measurement (a): their model on their data
|
||||
|
||||
### Artifact verification (MEASURED, 2026-06-10, this repo `eval_repro.py`)
|
||||
|
||||
| Check | Result |
|
||||
|---|---|
|
||||
| Parameter count | **2,225,042 (2.23M) — matches claim** |
|
||||
| FLOPs (torch profiler, batch 1) | ~0.055 GFLOPs — consistent with 0.07B claim |
|
||||
| CPU latency (Windows box, torch 2.12 CPU) | 13.2 ms/window @ batch 1 (76/s); 2.48 ms/sample @ batch 64 (403/s) |
|
||||
| Checkpoint load | `weights_only=True` (no pickle code execution) |
|
||||
|
||||
### Released checkpoint does NOT reproduce the claims — REFUTED as shipped
|
||||
|
||||
Running the released `best_pose_model.pth` through the released code on the released
|
||||
dataset with the released split procedure (seed-42 file-level 70/15/15; 54,000 test
|
||||
samples) yields:
|
||||
|
||||
| Metric | Published | Measured (shipped checkpoint) |
|
||||
|---|---|---|
|
||||
| PCK@20 | 97.25% | **0.08%** |
|
||||
| PCK@30 | 98.63% | 0.78% |
|
||||
| PCK@40 | 99.16% | 5.53% |
|
||||
| PCK@50 | 99.48% | 15.42% |
|
||||
| MPJPE | 0.007 | **NaN** (dataset contains NaN CSI windows) |
|
||||
|
||||
Raw output: `results/repro_a.json`.
|
||||
|
||||
Diagnostics (on 2,000 NaN-free windows from the first files of the dataset, i.e.
|
||||
mostly would-be *training* data — so this is not a split mismatch):
|
||||
|
||||
- Predictions correlate with targets (Pearson r ≈ 0.76) — the checkpoint is a trained
|
||||
model, but in a **different keypoint normalization/order** than the released data.
|
||||
- Best-case post-hoc global per-axis affine correction: PCK@20 ≈ 20%.
|
||||
- Best-case per-keypoint affine correction (15×2 fitted transforms — generous
|
||||
cheating): PCK@20 ≈ 72%, still far below 97.25%.
|
||||
- Pred↔target keypoint correspondence matrix is degenerate (multiple predicted
|
||||
keypoints best-match the same target joint) — keypoint convention mismatch.
|
||||
|
||||
### Reproducibility defects in the released artifacts
|
||||
|
||||
1. `models/__init__.py` imports `TemporalConvNet`, which `models/tcn.py` does not
|
||||
define — **the published code does not import/run as-is**.
|
||||
2. The released root checkpoint uses pre-rename module names (`att.*`, `final_conv.*`)
|
||||
vs the published code (`attention.*`, `decoder.*`) — same shapes/param count, but
|
||||
confirms the checkpoint predates the published code.
|
||||
3. The second shipped checkpoint (`cross_dataset_test/WiFlow/best_pose_model.pth`) is
|
||||
a **different architecture** (342-channel input = MM-Fi layout, 3 TCN layers,
|
||||
3-channel/3D decoder) — not usable on their own dataset.
|
||||
4. `run.py` ignores `--data_dir` and hardcodes `../preprocessed_csi_data`.
|
||||
5. The released dataset's final 13 files (indices 487–499; 9,072 windows, 2.52%)
|
||||
are corrupted: NaN values plus garbage amplitudes up to 3.4e38 (float32 max) in
|
||||
data that is otherwise [0,1]-normalized. Upstream code has no NaN/inf handling;
|
||||
training as published on this download diverges — the first corrupted batch
|
||||
overflows fp16 autocast and permanently poisons BatchNorm running statistics
|
||||
(GradScaler step-skipping does not protect BN). The authors' training curves
|
||||
show normal convergence, so their local data evidently differed from the
|
||||
Kaggle upload. Window masks: `results/nan_windows_mask.npy`,
|
||||
`results/big_windows_mask.npy`.
|
||||
|
||||
### Reproducing the corruption masks
|
||||
|
||||
The two mask files (9,070 NaN/Inf windows, 9,072 with |amplitude| > 1.5;
|
||||
union 9,072, all in dataset files 487–499) are **committed ground truth**
|
||||
(gitignore-negated, ~352 KB each). They can only be regenerated from a
|
||||
**pristine** Kaggle download: `remote/clean_v2.py` repairs the dataset by
|
||||
zeroing the corrupted windows in place, after which the corruption evidence
|
||||
is gone and a rescan returns all-False. `generate_corruption_masks.py`
|
||||
re-derives them (chunked scan, criteria: any non-finite value OR
|
||||
max |finite| > 1.5 per 540×20 window) and refuses to write all-False masks,
|
||||
which indicate a cleaned copy. Verified 2026-06-11: a regeneration from the
|
||||
local pristine download is bit-identical to the committed masks.
|
||||
|
||||
### Retraining result (MEASURED, 2026-06-10): claims APPROXIMATELY REPRODUCED
|
||||
|
||||
Since the shipped checkpoint is unusable, measurement (a) fell back to retraining
|
||||
with upstream code + defaults (seed 42, batch 64, early-stopped at epoch 41 of 50,
|
||||
best epoch 36, ~75 s/epoch) on ruvultra (RTX 5080). Deviations, all forced and
|
||||
documented: one-line fix for defect (1); torch 2.x+cu128 instead of pinned 2.3.1
|
||||
(Blackwell sm_120 unsupported); the 9,072 corrupted windows (defect 5) zeroed
|
||||
entirely — without this the published pipeline produces NaN from epoch 1 (observed).
|
||||
Scripts mirrored in `remote/`; raw metrics in `results/eval_retrained.json`.
|
||||
|
||||
| Metric | Published | Retrained (full test, 54,000) | Retrained (corruption-free, 52,560) |
|
||||
|---|---|---|---|
|
||||
| PCK@20 | 97.25% | **96.09%** | **96.61%** |
|
||||
| PCK@30 | 98.63% | 97.89% | 98.23% |
|
||||
| PCK@40 | 99.16% | 98.58% | 98.79% |
|
||||
| PCK@50 | 99.48% | 98.99% | 99.11% |
|
||||
| MPJPE | 0.007 | 0.0098 | 0.0094 |
|
||||
|
||||
Within ~0.6–1.2 PCK points of every published figure (single run, corrupted train
|
||||
windows zeroed, different torch/GPU). **Verdict: the accuracy claims are credible
|
||||
and approximately reproducible — but only after repairing the released dataset and
|
||||
code.** Val best: PCK@20 96.99%, MPJPE 0.0086 (epoch 36).
|
||||
|
||||
One more defect found during the run:
|
||||
|
||||
6. `train.py` calls `plot_training_history`, which is not defined anywhere — the
|
||||
built-in post-training test evaluation is unreachable as published (crashes
|
||||
with NameError after training completes).
|
||||
|
||||
## ADR-152 §2.2 citation rule
|
||||
|
||||
Evidence grade for the WiFlow-STD accuracy claims after measurement (a):
|
||||
**MEASURED-EQUIVALENT (96.1–96.6% PCK@20 reproduced by retraining; shipped
|
||||
checkpoint REFUTED; dataset/code require repairs)**. RuView docs may cite
|
||||
"~96% PCK@20 (our reproduction)" — still **not comparable** to our 17-keypoint
|
||||
ESP32 numbers (different hardware, 5 subjects, in-domain random split,
|
||||
15 keypoints).
|
||||
|
||||
## Edge optimization (measured)
|
||||
|
||||
ADR-152 "optimize beyond SOTA" track, 2026-06-10, this Windows box (Windows 11,
|
||||
16 torch threads, torch 2.12.0+cpu, onnxruntime 1.26.0). Subject: the retrained
|
||||
checkpoint `results/retrained_best_pose_model.pth` (2,225,042 fp32 params).
|
||||
Scripts: `quantize_bench.py`, `onnx_bench.py`, `eval_ort_accuracy.py`.
|
||||
Raw numbers: `results/edge_optimization.json`.
|
||||
|
||||
Accuracy is on a **10,000-window seed-42 random subset** of the corruption-free
|
||||
test split (same seed-42 file-level 70/15/15 split as `eval_repro.py`; 54,000
|
||||
test windows, 1,440 corrupted excluded via `results/nan_windows_mask.npy` |
|
||||
`results/big_windows_mask.npy`, leaving 52,560; subset drawn with
|
||||
`np.random.default_rng(42)`). The fp32 subset PCK@20 (96.68%) matches the full
|
||||
clean-test figure (96.61%), so the subset is representative.
|
||||
|
||||
Latency is CPU ms/window, median of repeated runs, 3 interleaved repetitions
|
||||
per variant (medians below; run-to-run spread on this box is large, roughly
|
||||
±20-40% at batch 1 — reps are in the JSON).
|
||||
|
||||
| Variant | Disk size | Batch 1 (ms/win) | Batch 64 (ms/win) | PCK@20 | PCK@50 | MPJPE |
|
||||
|---|---|---|---|---|---|---|
|
||||
| torch fp32 (baseline) | 9.07 MB | 11.0 | 2.27 | 96.68% | 99.15% | 0.00936 |
|
||||
| torch fp16 (`.half()`) | **4.58 MB** | 24.3 | 2.42 | 96.68% | 99.15% | 0.00946 |
|
||||
| torch int8 dynamic | 9.07 MB (unchanged) | 15.6 | 2.06 | 96.68% (identical) | 99.15% | 0.00936 |
|
||||
| ONNX fp32 (onnxruntime) | 8.97 MB | **3.2** | **2.0** | 96.68% | 99.15% | 0.00936 |
|
||||
| ONNX int8 (ORT dynamic, supplementary) | **2.44 MB** | 6.5 | 5.8 | 96.52% | 99.15% | 0.01108 |
|
||||
|
||||
Findings:
|
||||
|
||||
- **torch dynamic INT8 quantizes nothing on this model.** The architecture has
|
||||
**zero `nn.Linear` layers** — it is entirely Conv1d (21) + Conv2d (22) +
|
||||
BatchNorm. `torch.ao.quantization.quantize_dynamic` (requested over
|
||||
`{Linear, Conv1d, Conv2d}`) converted **0 modules / 0.0% of params**: dynamic
|
||||
quantization only has kernels for Linear/RNN-family modules and silently
|
||||
skips convolutions. The "int8" model is bit-identical to fp32 (same outputs,
|
||||
same 9.07 MB). Conv quantization would require static (PTQ) quantization
|
||||
with calibration — out of scope here; the ORT dynamic path below is the
|
||||
honest int8 datapoint.
|
||||
- **fp16 halves size for free accuracy-wise** (PCK@20 −0.005 pt, MPJPE
|
||||
+0.0001) but is *slower* on CPU at batch 1 (~2.2×) — torch CPU fp16 conv
|
||||
kernels are emulated. fp16 is a storage/transport format here, not a CPU
|
||||
runtime win.
|
||||
- **ONNX Runtime is the real batch-1 latency win: ~3.4× faster than torch**
|
||||
(3.2 vs 11.0 ms/window) at identical accuracy (parity 2.4e-7).
|
||||
|
||||
### Verdict on the paper's "~2.2 MB int8" claim
|
||||
|
||||
**Plausible but not free, and unreachable by the obvious PyTorch route.**
|
||||
2,225,042 params × 1 byte ≈ 2.2 MB assumes *every* parameter quantizes.
|
||||
PyTorch dynamic quantization — the one-liner most readers would reach for —
|
||||
yields **9.07 MB (0% quantized)** because the model has no Linear layers.
|
||||
ONNX Runtime dynamic quantization, which does have int8 conv weight support,
|
||||
gets **2.44 MB** (close to the claim; the overhead is BatchNorm params/buffers
|
||||
and quantization scales kept in fp32) at a measurable accuracy cost:
|
||||
PCK@20 96.68 → 96.52% (−0.16 pt) and MPJPE 0.00936 → 0.01108 (+18%), and
|
||||
~2× slower inference than ONNX fp32 (ConvInteger kernels). The paper does not
|
||||
state a method or an int8 accuracy; treat "2.2 MB" as a weight-arithmetic
|
||||
estimate, achievable in practice only via conv-capable quantization toolchains
|
||||
and with a small accuracy penalty.
|
||||
|
||||
### ONNX export status
|
||||
|
||||
**Works.** Exported via the TorchScript exporter (`dynamo=False`), opset 17,
|
||||
with a dynamic batch axis — `results/retrained_fp32_dynamic.onnx` (8.97 MB),
|
||||
verified to run at batch 1/2/64. The axial attention's
|
||||
`view(N*W, C, H)` reshape traced correctly (sizes recorded as graph ops, not
|
||||
baked constants). The dynamo exporter also captures the graph but crashed on
|
||||
this box writing a ✅ to a cp1252 console (cosmetic Windows encoding issue, not
|
||||
a model blocker). Parity vs torch on the stored fixture
|
||||
(`results/parity_fixture.npz`, batch 2, seed 42): **max abs diff 2.4e-7 —
|
||||
PASS** (< 1e-4). ORT-quantized int8 model: `results/retrained_int8_ort_dynamic.onnx`.
|
||||
|
||||
### Static PTQ (calibrated) — follow-up
|
||||
|
||||
Follow-up to the dynamic-int8 row above (2026-06-10, same box, onnxruntime
|
||||
1.26.0): ONNX Runtime **static** post-training quantization
|
||||
(`quantize_static`, QDQ format, per-channel int8 weights + int8 activations)
|
||||
of the same fp32 export, calibrated on **corruption-free TRAINING-split
|
||||
windows only** (seed-42 file-level split, same masks; 1,000 windows for
|
||||
MinMax, 512 for the histogram calibrators; never test windows). Scopes:
|
||||
"conv-only" (`op_types_to_quantize=["Conv"]` — the attention path exports as
|
||||
Einsum/Softmax, which ORT never quantizes anyway, so "all-ops" additionally
|
||||
quantizes the elementwise Mul/Sigmoid/Add/AveragePool glue). Accuracy on the
|
||||
identical 10k-window seed-42 corruption-free test subset; latency median of
|
||||
3 interleaved reps (fp32/dynamic re-benched in-session as references).
|
||||
Script: `static_ptq_bench.py`; raw: `results/edge_optimization.json`
|
||||
(`onnx_static_ptq`).
|
||||
|
||||
| Variant | Disk size | Batch 1 (ms/win) | Batch 64 (ms/win) | PCK@20 | PCK@50 | MPJPE |
|
||||
|---|---|---|---|---|---|---|
|
||||
| ONNX fp32 (reference) | 8.97 MB | 2.5 | 1.9 | 96.68% | 99.15% | 0.00936 |
|
||||
| ORT dynamic int8 (baseline) | **2.44 MB** | 5.7 | 4.6 | 96.52% | 99.15% | 0.01108 |
|
||||
| static QDQ **Percentile(99.99) conv-only** | 2.53 MB | 5.3 | 4.7 | 96.61% | 99.16% | **0.01031** |
|
||||
| static QDQ MinMax conv-only | 2.53 MB | 5.2 | 3.3 | **96.63%** | 99.19% | 0.01084 |
|
||||
| static QDQ Entropy conv-only | 2.53 MB | 5.2 | 3.1 | 96.60% | 99.19% | 0.01078 |
|
||||
| static QDQ MinMax all-ops | 2.60 MB | 6.5 | 3.9 | 95.45% | 99.14% | 0.01486 |
|
||||
| static QDQ Entropy all-ops | 2.60 MB | 5.7 | 4.1 | 95.30% | 99.13% | 0.01510 |
|
||||
| static QDQ Percentile all-ops | 2.60 MB | 5.3 | 4.3 | 96.39% | 99.17% | 0.01218 |
|
||||
|
||||
**Verdict: static PTQ (conv-only) is the new best int8 point on accuracy —
|
||||
but only modestly, and it does not fix int8's latency penalty.**
|
||||
|
||||
- **Accuracy: beats dynamic.** All three conv-only calibrations land at
|
||||
PCK@20 96.60–96.63% (vs dynamic 96.52%, fp32 96.68% — recovers ~⅔ of the
|
||||
dynamic gap) and MPJPE 0.0103–0.0108 (vs dynamic 0.01108). Best MPJPE:
|
||||
Percentile conv-only, +10% over fp32 instead of dynamic's +18%.
|
||||
- **Size: slightly worse.** 2.53 MB vs 2.44 MB (+3.6%) — QDQ nodes and
|
||||
per-channel scales cost a little; BatchNorm stays fp32 in both (the 12 BNs
|
||||
follow Slice/Einsum/Reshape, never Conv, so they cannot be folded).
|
||||
- **Latency: a wash vs dynamic, still ~2× slower than ONNX fp32 at batch 1.**
|
||||
Batch-1 medians 5.2–5.3 vs dynamic 5.7 ms/win in-session — within this
|
||||
box's ±20–40% noise. Batch 64 leans static (3.1–3.3 for MinMax/Entropy
|
||||
conv-only vs 4.6), same caveat.
|
||||
- **All-ops QDQ is strictly worse**: up to −1.4 pt PCK@20 and +60% MPJPE for
|
||||
zero size/latency benefit — int8 activations through the elementwise glue
|
||||
around the attention blocks is where the damage is. Conv-only is the right
|
||||
scope.
|
||||
- Negative result worth recording: **Entropy calibration is a no-op here** —
|
||||
on an identical calibration set it selects full-range thresholds
|
||||
bit-identical to MinMax (all 247 scales equal; verified on a 64-window
|
||||
smoke set). Also, ORT 1.26's `CalibMaxIntermediateOutputs` raises a
|
||||
spurious "No data is collected" when the batch count divides the chunk
|
||||
size (worked around in the script).
|
||||
|
||||
Deployment guidance: need speed → ONNX fp32 (3.2 ms b1). Need int8 weights
|
||||
for size → static QDQ conv-only (Percentile or MinMax,
|
||||
`results/retrained_int8_static_percentile_conv.onnx`), which strictly
|
||||
dominates dynamic int8 on accuracy at ~equal latency and +0.09 MB.
|
||||
|
||||
## Efficiency sweep (MEASURED, overnight 2026-06-10/11)
|
||||
|
||||
ADR-152 beyond-SOTA track: compact purpose-built variants of the WiFlow-STD
|
||||
architecture, trained from scratch on the same cleaned dataset, identical
|
||||
seed-42 file-level split, loss and protocol as the measurement-(a) reference
|
||||
(fp32, batch 64, ≤50 epochs, patience 5; RTX 5080, ~22–29 min/variant).
|
||||
Variant transforms are pure channel/group/stride scalings of an
|
||||
architecture-exact parameterized model (validated: reproduces 2,225,042 params
|
||||
at the reference config). Scripts: `remote/sweep/`; raw:
|
||||
`results/efficiency_sweep.jsonl`; checkpoints `results/{half,quarter,tiny}_best.pth`
|
||||
(gitignored).
|
||||
|
||||
| Variant | Params | vs 2.23M | Clean-test PCK@20 | PCK@50 | MPJPE | Best epoch |
|
||||
|---|---|---|---|---|---|---|
|
||||
| full (reference, meas. a) | 2,225,042 | 1× | 96.61% | 99.11% | 0.0094 | 36 |
|
||||
| **half** | **843,834** | **0.38×** | **96.62%** | **99.47%** | **0.00898** | 23 |
|
||||
| quarter | 338,600 | 0.15× | 96.05% | 99.43% | 0.00928 | 50 |
|
||||
| tiny | 56,290 | 0.025× | 94.11% | 99.36% | 0.0125 | 47 |
|
||||
|
||||
Findings:
|
||||
|
||||
- **The half model (843k params) strictly dominates the full reference** on
|
||||
this dataset — equal PCK@20, better PCK@50 and MPJPE, converges in fewer
|
||||
epochs. The published 2.23M architecture is over-parameterized for its own
|
||||
benchmark.
|
||||
- **tiny (56k params, 1/39.5) holds 94.11% PCK@20** — a ~220 KB fp32 /
|
||||
~60 KB int8-class model in reach of severely constrained edge targets,
|
||||
at −2.5 pt from the full reference.
|
||||
- Caveats: in-domain (5-subject random-file split) like every number on this
|
||||
dataset; single run per variant; corruption-free test subset (52,560).
|
||||
Cross-domain behavior of compact variants is untested — ADR-150's evidence
|
||||
says capacity *hurts* cross-subject, so the compact end may generalize no
|
||||
worse, but that is a hypothesis, not a measurement.
|
||||
|
||||
### Compact-variant edge artifacts (MEASURED, 2026-06-11)
|
||||
|
||||
Edge pipeline for the **tiny** checkpoint (56,290 params), same machinery and
|
||||
protocol as the full-model edge rows above (this Windows box, torch
|
||||
2.12.0+cpu, onnxruntime 1.26.0; dynamic-batch opset-17 TorchScript export;
|
||||
static QDQ **Percentile(99.99) conv-only** int8 calibrated on **512**
|
||||
corruption-free TRAIN-split windows; accuracy on the identical 10k-window
|
||||
seed-42 clean test subset; latency = median ms/window over 3 interleaved
|
||||
reps, with the full-model fp32/int8 sessions interleaved as same-session
|
||||
references). Script: `tiny_edge_bench.py`; raw:
|
||||
`results/edge_optimization.json` (`tiny_variant`). Torch-vs-ORT parity on the
|
||||
stored fixture input: **max abs diff 1.5e-7 — PASS** (< 1e-4). The tiny fp32
|
||||
subset PCK@20 (94.11%) matches the full clean-test sweep figure (94.11%)
|
||||
exactly, so the subset remains representative.
|
||||
|
||||
Two forced deviations, both recorded in the JSON:
|
||||
|
||||
1. **Adaptive-pool export rewrite.** tiny's derived stride schedule
|
||||
`[2,1,1,1]` leaves feature width 16, and the TorchScript exporter rejects
|
||||
`AdaptiveAvgPool2d((15,1))` when 15 is not a factor of the input height
|
||||
(the full model never hit this — its width was exactly 15). Since the
|
||||
pool over a fixed-size map is a fixed linear operator, the export wrapper
|
||||
replaces it with `mean(-1)` (W axis, a factor) + a constant averaging
|
||||
matmul using PyTorch's exact bin rule; the parity check (vs the original
|
||||
torch model with the real pool) proves exactness.
|
||||
2. **Calibration count 512, not "~500"**: ORT 1.26's histogram collector
|
||||
`np.asarray()`'s the per-batch maxima, so the calibration count must be a
|
||||
multiple of the 64-window calibration batch or the ragged last batch
|
||||
crashes it (the earlier static-PTQ run dodged this by using exactly 512).
|
||||
|
||||
| Variant | Disk size | Batch 1 (ms/win) | Batch 64 (ms/win) | PCK@20 | PCK@50 | MPJPE |
|
||||
|---|---|---|---|---|---|---|
|
||||
| full ONNX fp32 (same-session ref) | 8.97 MB | 2.27 | 1.42 | 96.68% | 99.15% | 0.00936 |
|
||||
| full static QDQ Percentile conv-only (same-session ref) | 2.53 MB | 5.53 | 3.82 | 96.61% | 99.16% | 0.01031 |
|
||||
| **tiny ONNX fp32** | **0.295 MB** | **0.66** | **0.24** | **94.11%** | 99.37% | 0.01253 |
|
||||
| tiny static QDQ Percentile conv-only | 0.248 MB | 0.85 | 1.03 | 92.68% | 99.33% | 0.01491 |
|
||||
|
||||
(tiny torch `.pth` checkpoint for reference: 0.34 MB on disk; 56,290 fp32
|
||||
params ≈ 225 KB of weights.)
|
||||
|
||||
Findings:
|
||||
|
||||
- **The smallest deployable WiFlow-class model is the tiny ONNX fp32
|
||||
artifact: ~295 KB on disk, 0.66 ms/window batch-1 CPU (~1,500 windows/s),
|
||||
94.1% PCK@20** — 30× smaller and ~3.4× faster (in-session) than the full
|
||||
ONNX fp32 model for −2.6 pt PCK@20.
|
||||
- **int8 is a bad trade at this scale.** Static QDQ conv-only — the recipe
|
||||
that cost the full model only 0.07 pt — costs tiny **−1.43 pt** PCK@20
|
||||
(94.11 → 92.68%) and +19% MPJPE, saves only 47 KB (−16%; QDQ scales and
|
||||
the fp32 BN/attention glue are proportionally larger in a small graph),
|
||||
and is *slower* than tiny fp32 (0.85 vs 0.66 ms b1; 1.03 vs 0.24 ms b64 —
|
||||
QDQ kernel overhead dominates when the convs are this small). A 56k-param
|
||||
model has little redundancy left to absorb weight+activation rounding.
|
||||
- Deployment guidance, compact edition: ship tiny as **ONNX fp32** — at
|
||||
295 KB the int8 size saving solves no real constraint and costs accuracy
|
||||
and speed. If ~250 KB vs ~295 KB ever matters, weight-only quantization
|
||||
would be the thing to try next, not QDQ.
|
||||
|
||||
## Measurement (b): BLOCKED-ON-DATA (attempted 2026-06-10)
|
||||
|
||||
The fine-tune-on-ESP32 measurement stopped at dataset characterization, per the
|
||||
pre-registered stop rule (<2,000 paired windows). Findings (MEASURED):
|
||||
|
||||
- **Only one trainable paired dataset exists**: `ruvultra:~/work/cog-pose-train/paired.jsonl`
|
||||
— 1,077 windows (one subject, one room, one 29.9-min session, single node;
|
||||
CSI [56, 20]; 17 COCO keypoints, MediaPipe confidence mean 0.44 — only 264
|
||||
windows pass ADR-079's own conf>0.5 training filter). Prior measured attempts
|
||||
on this exact set: 0–3% torso-PCK@20 (temporal splits, three independent
|
||||
pipelines). Fine-tuning a 2.23M-param model on ~860 train windows would
|
||||
measure memorization, not transfer.
|
||||
- **The April session behind the old "92.9% PCK@20" claim is lost** (345
|
||||
samples, 35 subcarriers; raw CSI gone from ruvzen/ruvultra/cognitum-v0; only
|
||||
a 69-sample predictions+GT holdout survives at `models/wiflow-real/eval-holdout.jsonl`).
|
||||
- **Forensic recheck of that holdout RETRACTS the 92.9% figure**: the trainer's
|
||||
`pck()` used an absolute 0.2 image-unit threshold (not torso-normalized) and
|
||||
the model output a **constant pose** (pred std 0.0000 across 69 near-static
|
||||
frames; a mean predictor scores 100% under the same protocol). The
|
||||
torso-normalized PCK@20 on the same holdout is 19.1%. This corroborates the
|
||||
2026-05-11 audit retraction (CHANGELOG, PR #535); stale doc citations were
|
||||
removed 2026-06-10 (user-guide, readme-details, ADR-152 §2.1.3). The §2.2
|
||||
no-citation rule now applies to ADR-079 accuracy claims.
|
||||
|
||||
Unblock criteria: a paired collection session of ≥2k windows (≈35+ min at the
|
||||
observed stride; multi-pose, conf>0.5, ideally with the §2.1.3 two-checkerboard
|
||||
calibration), plus a re-baselined our-pipeline number under torso-PCK@20 on the
|
||||
same split. WiFlow-STD assets stand ready on ruvultra (`~/wiflow-std-bench/`).
|
||||
Also worth investigating: ADR-079's protocol predicts ~9k windows per 30 min;
|
||||
the May session under-delivered ~8× (aligner drop rate?).
|
||||
|
||||
## Measurement (b) (MEASURED 2026-06-10/11)
|
||||
|
||||
The data baseline unblocked: the 2026-06-10 22:10–22:40 collection session produced
|
||||
**2,046 paired windows** (`ruvultra:~/wiflow-std-bench/paired-20260610.jsonl`; ONE
|
||||
subject, ONE room, ONE ESP32 node, varied poses: walk/raise/squat/kick/wave/turn/
|
||||
jump/sit; aligner `scripts/align-ground-truth.js`, non-overlapping 20-frame windows
|
||||
~0.42 s; 17 COCO keypoints in normalized [0,1] camera coords; MediaPipe confidence
|
||||
mean 0.802, min 0.692 — all windows pass the conf>0.5 filter). The −4 h timestamp
|
||||
bug and the empty-frame confidence-dilution aligner findings are recorded
|
||||
separately; results only here. Trained on ruvultra (RTX 5080, torch 2.11+cu128,
|
||||
fp32, batch 32, GPU shared with the efficiency sweep). Scripts mirrored in
|
||||
`remote/measb/`; raw metrics + full training curves in `results/measurement_b.json`.
|
||||
|
||||
### Two new aligner/dataset findings (forced deviations, MEASURED)
|
||||
|
||||
1. **`csi_shape` is heterogeneous, not [70, 20]**: 1,347× [70,20], 284× [134,20],
|
||||
243× [26,20], 130× [12,20], 42× [20,20]. The ESP32 stream emits mixed frame
|
||||
types and `extractCsiMatrix` stamps each window's subcarrier count from
|
||||
`window[0].subcarriers`, zero-padding/truncating the other frames — even
|
||||
native-70 windows contain ~20.4% internally zero-padded short frames
|
||||
(subcarriers 40–69 all-zero). Handling: the primary suite ("all 2,046")
|
||||
linearly resamples every frame's subcarrier axis to 70 bins (identity for
|
||||
native-70 frames) so the pre-registered n and split sizes hold; a secondary
|
||||
suite restricts to the 1,347 native [70,20] windows as a homogeneity check.
|
||||
2. **Aligner layout bug**: `extractCsiMatrix` fills `matrix[f * nSc + s]`
|
||||
(frame-major) but declares `shape: [nSc, nFrames]` — the stored shape label is
|
||||
transposed relative to the data. Confirmed by coherent per-frame zero-tails;
|
||||
corrected on load (`reshape(nFrames, nSc).T`).
|
||||
|
||||
### Protocol (pre-registered, followed)
|
||||
|
||||
Temporal split, no shuffling across time: first 70% train (1,432), next 15% val
|
||||
(307), last 15% test (307); seed 42 elsewhere. Model: learned 1×1 Conv1d 70→540
|
||||
adapter prepended to the upstream WiFlow-STD trunk; K=17 via the parameter-free
|
||||
adaptive pool (`AdaptiveAvgPool2d((17,1))` — pretrained weights load strict for
|
||||
any K). CSI normalized by the TRAIN-split p99 amplitude (129.7 all / 130.9
|
||||
native-70), clipped to [0,1]. Three runs, ≤60 epochs, early-stop patience 8 on
|
||||
val MPJPE, AdamW (adapter lr 1e-4; pretrained trunk lr 1e-5, 10× lower; scratch
|
||||
all 1e-4), fp32. Pretrained init = the measurement-(a) **retrained** checkpoint
|
||||
(`upstream/test/best_pose_model.pth`, ~96% PCK@20 on WiFlow data; the
|
||||
`att.`/`final_conv.` key remap from `eval_repro.py` applied defensively — a no-op,
|
||||
that checkpoint already uses post-rename keys). Frozen-trunk run: trunk
|
||||
`requires_grad=False` **and** held in `.eval()` so BatchNorm running stats cannot
|
||||
drift — a pure transfer probe; only the 70→540 adapter (38,340 params) trains.
|
||||
|
||||
PCK is torso-normalized with **torso = ‖l_shoulder(5) − l_hip(11)‖** (upstream
|
||||
`calculate_pck` math — per-frame norm clamped at 0.01, mean over keypoints ×
|
||||
frames — but upstream's `NECK_IDX/PELVIS_IDX = 2, 12` is a 15-keypoint
|
||||
convention; on 17-kp COCO those indices are right_eye/right_hip, so the indices
|
||||
were replaced, not the math). MPJPE is in normalized image units (not meters).
|
||||
|
||||
### Results — primary suite, all 2,046 windows (test = last 307)
|
||||
|
||||
| Run | PCK@10 | PCK@20 | PCK@30 | PCK@40 | PCK@50 | MPJPE | pred std | best ep |
|
||||
|---|---|---|---|---|---|---|---|---|
|
||||
| **mean-pose baseline** (honesty bar) | **73.1%** | **95.9%** | **98.7%** | 99.3% | 99.3% | **0.0148** | 0 (by constr.) | — |
|
||||
| (i) pretrained-init, full fine-tune | 26.0% | 65.0% | 88.0% | 96.4% | 98.9% | 0.0313 | 0.0113 | 58/60 |
|
||||
| (ii) scratch | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 0.2554 | 0.0002 | 4 (stop @13) |
|
||||
| (iii) frozen-trunk (adapter only) | 0.0% | 0.0% | 0.2% | 3.2% | 14.4% | 0.1260 | 0.0073 | 59/60 |
|
||||
|
||||
Secondary suite (native [70,20] windows only, n=1,347, test=202) reproduces the
|
||||
same ordering: mean-baseline 96.0% / pretrained 67.1% / scratch 0.0% /
|
||||
frozen-trunk 0.0% PCK@20 (MPJPE 0.0153 / 0.0318 / 0.2236 / 0.1343) — the
|
||||
subcarrier-resampling choice does not change any conclusion.
|
||||
|
||||
### Interpretation
|
||||
|
||||
- **Did pretraining-transfer happen? Partially — as optimization transfer, not
|
||||
feature transfer, and not past the honesty bar.**
|
||||
- *Pretrained vs scratch*: dramatic (65.0% vs 0.0% PCK@20). The pretrained init
|
||||
is the only configuration that trains at all under the pre-registered budget.
|
||||
- *Frozen-trunk*: near-zero (0.0% PCK@20, 14.4% @50). WiFlow-STD's frozen
|
||||
features do **not** transfer to our ESP32 domain through a linear subcarrier
|
||||
adapter — the pretrained benefit is a well-conditioned initialization (incl.
|
||||
calibrated BN/output scales), not reusable CSI→pose features.
|
||||
- *Everything vs mean-pose baseline*: **no run beats it.** A constant
|
||||
train-mean pose scores 95.9% torso-PCK@20 / 0.0148 MPJPE on this test split,
|
||||
because a single subject in one camera frame barely moves in normalized
|
||||
coordinates. The fine-tuned model is a real, non-constant model
|
||||
(pred std 0.0113 > 0 — passes the constant-pose detector that retracted the
|
||||
old 92.9% figure) but its deviations from the mean hurt: it fits train-period
|
||||
temporal dynamics that do not generalize across the temporal split.
|
||||
- **Verdict for ADR-152 §2.2(b): fine-tuning WiFlow-STD on this dataset does not
|
||||
demonstrate CSI→pose signal beyond the mean pose.** Until a model beats the
|
||||
mean-pose baseline on a temporal split, no PCK number from this line may be
|
||||
cited as pose-estimation capability.
|
||||
|
||||
### Caveats (honest, pre-registered)
|
||||
|
||||
- Single subject, single room, single session (30 min), single ESP32 node —
|
||||
in-domain temporal split only; nothing here speaks to cross-room or
|
||||
cross-subject generalization.
|
||||
- 2k windows vs the 360k-window WiFlow-STD corpus — **NOT comparable** to the
|
||||
~96% in-domain measurement-(a) number, and the published 97.25% even less so.
|
||||
- The scratch run's total collapse (it cannot even reach the mean pose; its
|
||||
output BatchNorm/SiLU head must learn output scale from random init at lr 1e-4)
|
||||
is an optimization outcome under the fixed budget, not proof the architecture
|
||||
cannot learn from scratch — the pretrained-vs-scratch gap partially reflects
|
||||
this conditioning advantage.
|
||||
- Mixed-subcarrier frames (finding 1) mean even the "clean" windows carry ~20%
|
||||
zero-padded frames; collection-side frame-type filtering should precede the
|
||||
next session.
|
||||
- Mean-baseline PCK is inflated by low pose variance relative to torso size
|
||||
(~0.2–0.3 image units); PCK@10 (73.1%) shows the same ceiling effect at a
|
||||
stricter threshold — the bar is the bar, but a livelier dataset would lower it.
|
||||
|
||||
## Pending
|
||||
|
||||
- (b) fine-tune on our ESP32 17-keypoint eval set — **MEASURED 2026-06-10/11**,
|
||||
see above: no run beats the mean-pose baseline; pretraining transfers as
|
||||
optimization aid only.
|
||||
- (c) our internal WiFlow on their dataset (15-keypoint subset mapping) — also
|
||||
affected: there is currently no validated internal pose model to compare
|
||||
(the 92.9% artifact is retracted; the MM-Fi SOTA models in ADR-150 §3 are a
|
||||
different input domain).
|
||||
@@ -1,200 +0,0 @@
|
||||
"""Shared infrastructure for the LOCAL wiflow-std benchmark scripts (ADR-152).
|
||||
|
||||
This module is the single canonical implementation of the helpers that were
|
||||
previously copy-pasted across eval_repro.py / quantize_bench.py /
|
||||
onnx_bench.py / eval_ort_accuracy.py / export_to_safetensors.py:
|
||||
|
||||
- ``import_upstream()`` -- sys.path setup + the models-package stub that
|
||||
works around the upstream import bug, plus the >1GB np.load mmap patch
|
||||
- ``install_np_load_mmap_patch()`` -- the mmap patch on its own
|
||||
- ``remap_legacy_keys()`` / ``load_remapped_state()`` -- checkpoint
|
||||
key remap for the pre-rename released checkpoint
|
||||
- ``load_wiflow_model()`` -- WiFlowPoseModel from a checkpoint, eval mode
|
||||
- ``set_seed()`` -- mirrors upstream run.py seeding exactly
|
||||
- ``evaluate()`` -- THE canonical batch-weighted PCK/MPJPE evaluation loop
|
||||
(thresholds 0.1-0.5, upstream utils/metrics.py math); accepts either a
|
||||
torch nn.Module or an onnxruntime InferenceSession
|
||||
|
||||
The scripts under remote/ deploy to ruvultra as standalone single files and
|
||||
therefore intentionally inline private copies of these helpers; when editing
|
||||
them, treat this module as the reference implementation and keep the copies
|
||||
in sync.
|
||||
"""
|
||||
|
||||
import os
|
||||
import random
|
||||
import sys
|
||||
import time
|
||||
import types
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
HERE = os.path.dirname(os.path.abspath(__file__))
|
||||
UPSTREAM = os.path.join(HERE, "upstream")
|
||||
RESULTS = os.path.join(HERE, "results")
|
||||
|
||||
DEFAULT_THRESHOLDS = (0.1, 0.2, 0.3, 0.4, 0.5)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# >1GB np.load mmap patch
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# csi_windows.npy is ~13 GB; mmap large arrays instead of loading into RAM
|
||||
# (loading it eagerly needs ~15 GB).
|
||||
_np_load = np.load
|
||||
|
||||
|
||||
def _np_load_mmap(path, *a, **kw):
|
||||
if (isinstance(path, str) and path.endswith(".npy")
|
||||
and os.path.getsize(path) > 1 << 30 and "mmap_mode" not in kw):
|
||||
kw["mmap_mode"] = "r"
|
||||
return _np_load(path, *a, **kw)
|
||||
|
||||
|
||||
def install_np_load_mmap_patch():
|
||||
"""Globally patch np.load so .npy files >1GB are mmap'd read-only.
|
||||
|
||||
Idempotent. Patching the numpy module attribute is equivalent to the
|
||||
historical ``upstream_dataset.np.load = _np_load_mmap`` (dataset.np IS
|
||||
the numpy module), but works regardless of import order.
|
||||
"""
|
||||
np.load = _np_load_mmap
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# upstream import shim
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def import_upstream(mmap_patch=True):
|
||||
"""Make the upstream WiFlow-STD clone importable; returns its path.
|
||||
|
||||
Upstream bug: models/__init__.py imports TemporalConvNet, which
|
||||
models/tcn.py does not define -- the package fails to import as
|
||||
published. Register a stub package so the broken __init__ never
|
||||
executes; submodules (models.pose_model etc.) still resolve via
|
||||
__path__. Idempotent.
|
||||
"""
|
||||
if UPSTREAM not in sys.path:
|
||||
sys.path.insert(0, UPSTREAM)
|
||||
if "models" not in sys.modules:
|
||||
_models_pkg = types.ModuleType("models")
|
||||
_models_pkg.__path__ = [os.path.join(UPSTREAM, "models")]
|
||||
sys.modules["models"] = _models_pkg
|
||||
if mmap_patch:
|
||||
install_np_load_mmap_patch()
|
||||
return UPSTREAM
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# checkpoint loading
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# The released checkpoint predates the published code: modules were renamed
|
||||
# att -> attention, final_conv -> decoder (param count identical, 2.23M).
|
||||
LEGACY_RENAMES = {"att.": "attention.", "final_conv.": "decoder."}
|
||||
|
||||
|
||||
def remap_legacy_keys(state):
|
||||
"""Remap pre-rename state_dict keys; no-op for already-new-style keys."""
|
||||
return {next((new + k[len(old):] for old, new in LEGACY_RENAMES.items()
|
||||
if k.startswith(old)), k): v
|
||||
for k, v in state.items()}
|
||||
|
||||
|
||||
def load_remapped_state(path, map_location="cpu"):
|
||||
"""torch.load (weights_only) + legacy key remap."""
|
||||
state = torch.load(path, map_location=map_location, weights_only=True)
|
||||
return remap_legacy_keys(state)
|
||||
|
||||
|
||||
def load_wiflow_model(checkpoint, map_location="cpu", dropout=0.5):
|
||||
"""Full-size WiFlowPoseModel from a checkpoint, strict load, eval mode."""
|
||||
import_upstream()
|
||||
from models.pose_model import WiFlowPoseModel
|
||||
model = WiFlowPoseModel(dropout=dropout)
|
||||
model.load_state_dict(load_remapped_state(checkpoint, map_location),
|
||||
strict=True)
|
||||
model.eval()
|
||||
return model
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# seeding
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def set_seed(seed=42):
|
||||
# mirror upstream run.py exactly
|
||||
random.seed(seed)
|
||||
np.random.seed(seed)
|
||||
torch.manual_seed(seed)
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.manual_seed(seed)
|
||||
torch.cuda.manual_seed_all(seed)
|
||||
torch.backends.cudnn.deterministic = True
|
||||
torch.backends.cudnn.benchmark = False
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# THE canonical evaluation loop
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def evaluate(model, loader, device=None, dtype=None, label="",
|
||||
thresholds=DEFAULT_THRESHOLDS, progress_every=50):
|
||||
"""Batch-weighted PCK/MPJPE over a DataLoader (upstream metrics math).
|
||||
|
||||
``model`` may be a torch nn.Module (optionally evaluated on ``device``
|
||||
with inputs cast to ``dtype``) or an onnxruntime InferenceSession.
|
||||
Per-threshold PCK values are independent in upstream calculate_pck, so
|
||||
evaluating a superset of thresholds never changes any individual value.
|
||||
|
||||
Returns {"samples", "mpjpe", "pck@10".."pck@50", "wall_seconds"}.
|
||||
"""
|
||||
import_upstream()
|
||||
from utils.metrics import calculate_mpjpe, calculate_pck
|
||||
|
||||
is_ort = hasattr(model, "get_inputs") # onnxruntime InferenceSession
|
||||
if is_ort:
|
||||
inp = model.get_inputs()[0].name
|
||||
|
||||
def forward(bx):
|
||||
return torch.from_numpy(model.run(None, {inp: bx.numpy()})[0])
|
||||
else:
|
||||
model.eval()
|
||||
|
||||
def forward(bx):
|
||||
if device is not None:
|
||||
bx = bx.to(device)
|
||||
if dtype is not None:
|
||||
bx = bx.to(dtype)
|
||||
return model(bx).float()
|
||||
|
||||
thresholds = list(thresholds)
|
||||
totals = {t: 0.0 for t in thresholds}
|
||||
total_mpe, n = 0.0, 0
|
||||
t0 = time.time()
|
||||
with torch.no_grad():
|
||||
for batch_idx, (bx, by) in enumerate(loader):
|
||||
out = forward(bx)
|
||||
if device is not None and not is_ort:
|
||||
by = by.to(device)
|
||||
mpe = calculate_mpjpe(out, by)
|
||||
pck = calculate_pck(out, by, thresholds=thresholds)
|
||||
bs = by.size(0)
|
||||
total_mpe += mpe * bs
|
||||
for t in totals:
|
||||
totals[t] += pck[t] * bs
|
||||
n += bs
|
||||
if batch_idx % progress_every == 0:
|
||||
tag = f"[{label}] " if label else ""
|
||||
pck20 = totals.get(0.2)
|
||||
pck20_str = f"pck20={pck20 / n:.4f} " if pck20 is not None else ""
|
||||
print(f" {tag}batch {batch_idx}: n={n} {pck20_str}"
|
||||
f"mpjpe={total_mpe / n:.4f} ({time.time() - t0:.0f}s)",
|
||||
flush=True)
|
||||
return {
|
||||
"samples": n,
|
||||
"mpjpe": total_mpe / n,
|
||||
**{f"pck@{int(t * 100)}": totals[t] / n for t in thresholds},
|
||||
"wall_seconds": time.time() - t0,
|
||||
}
|
||||
@@ -1,67 +0,0 @@
|
||||
"""ADR-152 edge optimization: accuracy of the ONNX fp32 and ORT-dynamic-int8
|
||||
models on the same corruption-free 10k test subset used by quantize_bench.py.
|
||||
|
||||
The torch dynamic-int8 path quantizes nothing (no nn.Linear in the model), so
|
||||
the only real int8 datapoint for the paper's "~2.2 MB int8" claim is the
|
||||
onnxruntime dynamically quantized model -- this script measures what that
|
||||
quantization costs in PCK/MPJPE.
|
||||
|
||||
Usage:
|
||||
.venv/Scripts/python.exe eval_ort_accuracy.py \
|
||||
--data-dir <preprocessed_csi_data> [--subset 10000]
|
||||
|
||||
Writes/merges into results/edge_optimization.json under key "onnx_accuracy".
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
HERE = os.path.dirname(os.path.abspath(__file__))
|
||||
sys.path.insert(0, HERE)
|
||||
|
||||
from _bench_common import RESULTS, evaluate # noqa: E402
|
||||
from quantize_bench import build_test_subset # noqa: E402 (sets up upstream imports)
|
||||
|
||||
|
||||
def evaluate_ort(sess, loader, label):
|
||||
"""ORT-session evaluation via the canonical _bench_common.evaluate loop."""
|
||||
return evaluate(sess, loader, label=label)
|
||||
|
||||
|
||||
def main():
|
||||
import onnxruntime as ort
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--data-dir", default=os.path.join(
|
||||
os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
|
||||
"wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
|
||||
parser.add_argument("--subset", type=int, default=10000)
|
||||
parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
|
||||
args = parser.parse_args()
|
||||
|
||||
loader, _n_clean = build_test_subset(args.data_dir, args.subset)
|
||||
results = {}
|
||||
for label, fname in (("onnx_fp32", "retrained_fp32_dynamic.onnx"),
|
||||
("onnx_int8_ort_dynamic", "retrained_int8_ort_dynamic.onnx")):
|
||||
path = os.path.join(RESULTS, fname)
|
||||
if not os.path.exists(path):
|
||||
results[label] = {"error": f"{fname} not found; run onnx_bench.py first"}
|
||||
continue
|
||||
sess = ort.InferenceSession(path, providers=["CPUExecutionProvider"])
|
||||
print(f"=== accuracy: {label} ({fname}) ===")
|
||||
results[label] = evaluate_ort(sess, loader, label)
|
||||
print(json.dumps(results[label], indent=2))
|
||||
|
||||
merged = {}
|
||||
if os.path.exists(args.out):
|
||||
with open(args.out) as f:
|
||||
merged = json.load(f)
|
||||
merged["onnx_accuracy"] = results
|
||||
with open(args.out, "w") as f:
|
||||
json.dump(merged, f, indent=2)
|
||||
print(f"wrote {args.out}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,102 +0,0 @@
|
||||
"""ADR-152 §2.2 measurement (a): reproduce WiFlow-STD (DY2434) published test metrics.
|
||||
|
||||
Runs the released pretrained checkpoint (upstream/best_pose_model.pth) against the
|
||||
released Kaggle dataset (kaka2434/wiflow-dataset) using the upstream code path:
|
||||
identical dataset class, identical file-level 70/15/15 split at seed 42, identical
|
||||
PCK/MPJPE implementations (utils/metrics.py).
|
||||
|
||||
Published claims (README, "Setting 1 random split"):
|
||||
PCK@20 97.25% | PCK@30 98.63% | PCK@40 99.16% | PCK@50 99.48% | MPJPE 0.007 m
|
||||
|
||||
Usage:
|
||||
.venv/Scripts/python.exe eval_repro.py --data-dir <dir containing csi_windows.npy>
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
import torch
|
||||
from torch.utils.data import DataLoader
|
||||
|
||||
from _bench_common import (UPSTREAM, evaluate, import_upstream,
|
||||
load_remapped_state, set_seed)
|
||||
|
||||
import_upstream() # sys.path + models stub + >1GB np.load mmap patch
|
||||
|
||||
from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders # noqa: E402
|
||||
from models.pose_model import WiFlowPoseModel # noqa: E402
|
||||
|
||||
|
||||
def find_data_dir(root):
|
||||
for dirpath, _dirnames, filenames in os.walk(root):
|
||||
if "csi_windows.npy" in filenames:
|
||||
return dirpath
|
||||
return None
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--data-dir", required=True,
|
||||
help="Directory containing csi_windows.npy (searched recursively)")
|
||||
parser.add_argument("--checkpoint", default=os.path.join(UPSTREAM, "best_pose_model.pth"))
|
||||
parser.add_argument("--batch-size", type=int, default=64)
|
||||
parser.add_argument("--out", default=os.path.join(os.path.dirname(os.path.abspath(__file__)),
|
||||
"results", "repro_a.json"))
|
||||
args = parser.parse_args()
|
||||
|
||||
data_dir = args.data_dir
|
||||
if not os.path.exists(os.path.join(data_dir, "csi_windows.npy")):
|
||||
located = find_data_dir(data_dir)
|
||||
if located is None:
|
||||
sys.exit(f"csi_windows.npy not found under {data_dir}")
|
||||
data_dir = located
|
||||
print(f"data dir: {data_dir}")
|
||||
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
print(f"device: {device}, torch {torch.__version__}")
|
||||
|
||||
set_seed(42)
|
||||
|
||||
dataset = PreprocessedCSIKeypointsDataset(
|
||||
data_dir=data_dir, keypoint_scale=1000.0, enable_temporal_clean=True)
|
||||
|
||||
# split must match upstream: file-level shuffle at random_seed=42, 70/15/15
|
||||
_train_loader, _val_loader, test_loader = create_preprocessed_train_val_test_loaders(
|
||||
dataset=dataset, batch_size=args.batch_size, num_workers=0, random_seed=42)
|
||||
|
||||
model = WiFlowPoseModel(dropout=0.5).to(device)
|
||||
# released checkpoint predates the published code: modules were renamed
|
||||
# att -> attention, final_conv -> decoder (param count identical, 2.23M)
|
||||
state = load_remapped_state(args.checkpoint, map_location=device)
|
||||
model.load_state_dict(state, strict=True)
|
||||
n_params = sum(p.numel() for p in model.parameters())
|
||||
print(f"checkpoint: {args.checkpoint} ({n_params/1e6:.2f}M params)")
|
||||
|
||||
# upstream also evaluates with drop_last=True; we report the full test set
|
||||
# (drop_last=False) and the drop_last variant for exact comparability
|
||||
results = {"published": {"pck@20": 0.9725, "pck@30": 0.9863, "pck@40": 0.9916,
|
||||
"pck@50": 0.9948, "mpjpe": 0.007},
|
||||
"params_millions": n_params / 1e6,
|
||||
"data_dir": data_dir,
|
||||
"device": str(device)}
|
||||
|
||||
print("=== test set (full, drop_last=False) ===")
|
||||
results["test_full"] = evaluate(model, test_loader, device=device)
|
||||
print(json.dumps(results["test_full"], indent=2))
|
||||
|
||||
test_loader_dl = DataLoader(test_loader.dataset, batch_size=args.batch_size,
|
||||
shuffle=False, drop_last=True)
|
||||
print("=== test set (drop_last=True, as upstream train.py) ===")
|
||||
results["test_drop_last"] = evaluate(model, test_loader_dl, device=device)
|
||||
print(json.dumps(results["test_drop_last"], indent=2))
|
||||
|
||||
os.makedirs(os.path.dirname(args.out), exist_ok=True)
|
||||
with open(args.out, "w") as f:
|
||||
json.dump(results, f, indent=2)
|
||||
print(f"wrote {args.out}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,174 +0,0 @@
|
||||
"""ADR-152 §2.2: export the retrained WiFlow-STD PyTorch checkpoint to
|
||||
safetensors with tch-rs (VarStore) variable names, plus a numerical-parity
|
||||
fixture for the Rust port.
|
||||
|
||||
Outputs (all under results/, gitignored):
|
||||
retrained_wiflow_std.safetensors -- 248 f32 tensors named exactly as the
|
||||
Rust WiFlowStdModel VarStore expects
|
||||
(see wiflow_std/model.rs
|
||||
`dump_variable_names` for the
|
||||
authoritative name dump)
|
||||
parity_fixture.npz -- deterministic input (seed 42,
|
||||
shape (2, 540, 20), uniform [0,1]) and
|
||||
the Python model's eval-mode output
|
||||
parity_fixture.json -- same data as flattened f32 lists, for
|
||||
the dependency-free Rust test
|
||||
(tests/test_wiflow_std_parity.rs)
|
||||
|
||||
PyTorch -> tch key mapping (derived from the VarStore dump, not guessed):
|
||||
|
||||
tcn.network.{i}.conv1_group.weight -> tcn{i}.conv1_group.weight
|
||||
tcn.network.{i}.bn*_{group,pw}.<leaf> -> tcn{i}.bn*_{group,pw}.<leaf>
|
||||
tcn.network.{i}.downsample.0.weight -> tcn{i}.ds_conv.weight
|
||||
tcn.network.{i}.downsample.1.<leaf> -> tcn{i}.ds_bn.<leaf>
|
||||
up.block.{0,1,4,5,8,9}.<leaf> -> conv_in.{conv1,bn1,conv2,bn2,conv3,bn3}.<leaf>
|
||||
up.downsample.{0,1}.<leaf> -> conv_in.{ds_conv,ds_bn}.<leaf>
|
||||
residual_blocks.{i}.block.{...}.<leaf> -> conv{i}.{conv1..bn3}.<leaf>
|
||||
residual_blocks.{i}.downsample.{0,1} -> conv{i}.{ds_conv,ds_bn}
|
||||
attention.{width,height}_axis.qkv_transform.weight
|
||||
-> attention.{width,height}.qkv.weight
|
||||
attention.{width,height}_axis.bn_* -> attention.{width,height}.bn_*
|
||||
decoder.{0,1,3,4}.<leaf> -> {dec_conv1,dec_bn1,dec_conv2,dec_bn2}.<leaf>
|
||||
*.num_batches_tracked -> dropped (tch BatchNorm has no such buffer)
|
||||
|
||||
Legacy upstream names (att. -> attention., final_conv. -> decoder.) are
|
||||
remapped first, exactly as eval_repro.py does for the released checkpoint.
|
||||
|
||||
Usage:
|
||||
.venv/Scripts/python.exe export_to_safetensors.py
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from safetensors.torch import save_file
|
||||
|
||||
from _bench_common import RESULTS, import_upstream, remap_legacy_keys
|
||||
|
||||
import_upstream() # sys.path + models stub
|
||||
|
||||
from models.pose_model import WiFlowPoseModel # noqa: E402
|
||||
|
||||
CHECKPOINT = os.path.join(RESULTS, "retrained_best_pose_model.pth")
|
||||
|
||||
# Sequential index -> tch sub-name inside one ConvBlock1/AsymmetricConvBlock:
|
||||
# [Conv2d(0), BN(1), SiLU(2), Dropout2d(3), Conv2d(4), BN(5), SiLU(6),
|
||||
# Dropout2d(7), Conv2d(8), BN(9)]
|
||||
_BLOCK_IDX = {"0": "conv1", "1": "bn1", "4": "conv2", "5": "bn2",
|
||||
"8": "conv3", "9": "bn3"}
|
||||
_DS_IDX = {"0": "ds_conv", "1": "ds_bn"}
|
||||
_DECODER_IDX = {"0": "dec_conv1", "1": "dec_bn1", "3": "dec_conv2",
|
||||
"4": "dec_bn2"}
|
||||
|
||||
|
||||
def _conv_block(new_prefix: str, rest: str) -> str:
|
||||
m = re.fullmatch(r"block\.(\d+)\.(.+)", rest)
|
||||
if m:
|
||||
return f"{new_prefix}.{_BLOCK_IDX[m.group(1)]}.{m.group(2)}"
|
||||
m = re.fullmatch(r"downsample\.(\d+)\.(.+)", rest)
|
||||
if m:
|
||||
return f"{new_prefix}.{_DS_IDX[m.group(1)]}.{m.group(2)}"
|
||||
raise KeyError(f"unmapped conv-block key: {new_prefix} / {rest}")
|
||||
|
||||
|
||||
def map_key(key: str) -> str:
|
||||
"""Map one PyTorch state_dict key to the tch VarStore name."""
|
||||
m = re.fullmatch(r"tcn\.network\.(\d+)\.(.+)", key)
|
||||
if m:
|
||||
i, rest = m.groups()
|
||||
rest = (rest.replace("downsample.0.", "ds_conv.")
|
||||
.replace("downsample.1.", "ds_bn."))
|
||||
return f"tcn{i}.{rest}"
|
||||
|
||||
m = re.fullmatch(r"up\.(.+)", key)
|
||||
if m:
|
||||
return _conv_block("conv_in", m.group(1))
|
||||
|
||||
m = re.fullmatch(r"residual_blocks\.(\d+)\.(.+)", key)
|
||||
if m:
|
||||
return _conv_block(f"conv{m.group(1)}", m.group(2))
|
||||
|
||||
m = re.fullmatch(r"attention\.(width|height)_axis\.(.+)", key)
|
||||
if m:
|
||||
axis, rest = m.groups()
|
||||
rest = rest.replace("qkv_transform.", "qkv.")
|
||||
return f"attention.{axis}.{rest}"
|
||||
|
||||
m = re.fullmatch(r"decoder\.(\d+)\.(.+)", key)
|
||||
if m:
|
||||
return f"{_DECODER_IDX[m.group(1)]}.{m.group(2)}"
|
||||
|
||||
raise KeyError(f"unmapped checkpoint key: {key}")
|
||||
|
||||
|
||||
def main():
|
||||
state = torch.load(CHECKPOINT, map_location="cpu", weights_only=True)
|
||||
if not isinstance(state, dict) or "tcn.network.0.conv1_group.weight" not in {
|
||||
k for k in state
|
||||
} | {k.replace("att.", "attention.") for k in state}:
|
||||
# tolerate trainer wrappers like {"model_state_dict": ...}
|
||||
for wrapper in ("model_state_dict", "state_dict", "model"):
|
||||
if isinstance(state, dict) and wrapper in state:
|
||||
state = state[wrapper]
|
||||
break
|
||||
|
||||
# Legacy upstream names predate the published code (_bench_common).
|
||||
state = remap_legacy_keys(state)
|
||||
|
||||
mapped = {}
|
||||
dropped = 0
|
||||
for k, v in state.items():
|
||||
if k.endswith("num_batches_tracked"):
|
||||
dropped += 1
|
||||
continue
|
||||
tch_key = map_key(k)
|
||||
if tch_key in mapped:
|
||||
raise KeyError(f"duplicate mapped key: {k} -> {tch_key}")
|
||||
mapped[tch_key] = v.detach().to(torch.float32).contiguous()
|
||||
|
||||
n_params = sum(v.numel() for k, v in mapped.items()
|
||||
if "running_" not in k)
|
||||
print(f"checkpoint tensors: {len(state)} "
|
||||
f"(dropped {dropped} num_batches_tracked)")
|
||||
print(f"mapped tensors: {len(mapped)}, "
|
||||
f"non-buffer params: {n_params/1e6:.6f}M")
|
||||
assert len(mapped) == 248, f"expected 248 tch variables, got {len(mapped)}"
|
||||
assert n_params == 2_225_042, f"param count mismatch: {n_params}"
|
||||
|
||||
st_path = os.path.join(RESULTS, "retrained_wiflow_std.safetensors")
|
||||
save_file(mapped, st_path)
|
||||
print(f"wrote {st_path}")
|
||||
|
||||
# ---- parity fixture --------------------------------------------------
|
||||
model = WiFlowPoseModel(dropout=0.5)
|
||||
model.load_state_dict(state, strict=True)
|
||||
model.eval()
|
||||
|
||||
gen = torch.Generator().manual_seed(42)
|
||||
x = torch.rand(2, 540, 20, generator=gen, dtype=torch.float32)
|
||||
with torch.no_grad():
|
||||
y = model(x)
|
||||
print(f"fixture input {tuple(x.shape)} -> output {tuple(y.shape)}, "
|
||||
f"output range [{y.min().item():.6f}, {y.max().item():.6f}]")
|
||||
|
||||
np.savez(os.path.join(RESULTS, "parity_fixture.npz"),
|
||||
input=x.numpy(), output=y.numpy())
|
||||
fixture = {
|
||||
"seed": 42,
|
||||
"input_shape": list(x.shape),
|
||||
"input": x.flatten().tolist(),
|
||||
"output_shape": list(y.shape),
|
||||
"output": y.flatten().tolist(),
|
||||
}
|
||||
json_path = os.path.join(RESULTS, "parity_fixture.json")
|
||||
with open(json_path, "w") as f:
|
||||
json.dump(fixture, f)
|
||||
print(f"wrote {os.path.join(RESULTS, 'parity_fixture.npz')}")
|
||||
print(f"wrote {json_path}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,148 +0,0 @@
|
||||
"""Regenerate results/nan_windows_mask.npy + results/big_windows_mask.npy by
|
||||
scanning a PRISTINE kagglehub download of the WiFlow-STD dataset
|
||||
(kaka2434/wiflow-dataset v1, csi_windows.npy, 360,000 windows of 540x20).
|
||||
|
||||
============================ READ THIS FIRST ===============================
|
||||
This script MUST be run against an UNCLEANED copy of the dataset.
|
||||
|
||||
remote/clean_v2.py (and its predecessor clean_nan.py) repair the dataset by
|
||||
zeroing the corrupted windows IN PLACE, with no backup. A cleaned copy
|
||||
contains no non-finite values and no out-of-range amplitudes, so on a cleaned
|
||||
copy this scan produces ALL-FALSE masks -- silently wrong ground truth. The
|
||||
script errors out loudly in that case (see the sanity check in main()).
|
||||
|
||||
That irreversibility is exactly why the two committed mask files under
|
||||
results/ (gitignore-negated) are the canonical ground truth: once a download
|
||||
has been cleaned, the masks can NEVER be regenerated from it. Only run this
|
||||
on a fresh `kagglehub.dataset_download("kaka2434/wiflow-dataset")`.
|
||||
============================================================================
|
||||
|
||||
Criteria (per window; mirrors the original 2026-06-10 scan and the
|
||||
remote/clean_v2.py repair criteria):
|
||||
|
||||
nan mask: any non-finite value (NaN/Inf) anywhere in the 540x20 window
|
||||
big mask: max |finite value| > 1.5 (the data is otherwise [0,1]-normalized;
|
||||
the corrupted files contain garbage up to 3.4e38, float32 max)
|
||||
|
||||
Expected result on the pristine Kaggle download (RESULTS.md defect 5):
|
||||
nan: 9,070 True | big: 9,072 True | union: 9,072 -- all windows in dataset
|
||||
files 487-499 (the final 13 files), window indices 350,922-359,999.
|
||||
|
||||
Usage:
|
||||
PYTHONUTF8=1 .venv/Scripts/python.exe generate_corruption_masks.py \
|
||||
[--data-dir <dir containing csi_windows.npy>] [--out-dir results]
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
|
||||
import numpy as np
|
||||
|
||||
HERE = os.path.dirname(os.path.abspath(__file__))
|
||||
RESULTS = os.path.join(HERE, "results")
|
||||
|
||||
EXPECTED = {"nan": 9070, "big": 9072, "union": 9072,
|
||||
"files": (487, 499), "windows": (350922, 359999)}
|
||||
|
||||
|
||||
def scan(csi_path, chunk=4000):
|
||||
"""Chunked scan of the (mmap'd) windows array; returns (nan_mask, big_mask)."""
|
||||
csi = np.load(csi_path, mmap_mode="r")
|
||||
n = len(csi)
|
||||
nan_mask = np.zeros(n, dtype=bool)
|
||||
big_mask = np.zeros(n, dtype=bool)
|
||||
for i in range(0, n, chunk):
|
||||
block = np.asarray(csi[i:i + chunk])
|
||||
finite = np.isfinite(block)
|
||||
nan_mask[i:i + chunk] = (~finite).any(axis=(1, 2))
|
||||
big_mask[i:i + chunk] = (
|
||||
np.abs(np.where(finite, block, 0)).max(axis=(1, 2)) > 1.5)
|
||||
if (i // chunk) % 10 == 0:
|
||||
print(f" scanned {min(i + chunk, n):,}/{n:,} windows "
|
||||
f"(nan={int(nan_mask.sum()):,} big={int(big_mask.sum()):,})",
|
||||
flush=True)
|
||||
return nan_mask, big_mask
|
||||
|
||||
|
||||
def describe_files(data_dir, mask):
|
||||
"""Map marked windows to dataset file indices via window_info.npz."""
|
||||
info = os.path.join(data_dir, "window_info.npz")
|
||||
if not os.path.exists(info):
|
||||
return None
|
||||
w2f = np.load(info)["window_to_file"]
|
||||
return np.unique(w2f[mask])
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Regenerate the corruption masks from a PRISTINE "
|
||||
"(uncleaned) kagglehub download. See module docstring.")
|
||||
parser.add_argument("--data-dir", default=os.path.join(
|
||||
os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
|
||||
"wiflow-dataset", "versions", "1", "preprocessed_csi_data"),
|
||||
help="Directory containing csi_windows.npy (PRISTINE copy)")
|
||||
parser.add_argument("--out-dir", default=RESULTS,
|
||||
help="Where to write the two .npy masks")
|
||||
parser.add_argument("--chunk", type=int, default=4000,
|
||||
help="Windows per scan chunk (memory/speed tradeoff)")
|
||||
args = parser.parse_args()
|
||||
|
||||
csi_path = os.path.join(args.data_dir, "csi_windows.npy")
|
||||
if not os.path.exists(csi_path):
|
||||
sys.exit(f"csi_windows.npy not found in {args.data_dir}")
|
||||
|
||||
print(f"scanning {csi_path} (chunk={args.chunk}) ...")
|
||||
nan_mask, big_mask = scan(csi_path, args.chunk)
|
||||
union = nan_mask | big_mask
|
||||
print(f"nan: {int(nan_mask.sum()):,} | big: {int(big_mask.sum()):,} | "
|
||||
f"union: {int(union.sum()):,} of {len(union):,} windows")
|
||||
|
||||
# ---- sanity check: an all-False result means a CLEANED copy ------------
|
||||
if not union.any():
|
||||
sys.exit(
|
||||
"ERROR: scan found ZERO corrupted windows.\n"
|
||||
"\n"
|
||||
"The pristine Kaggle download (kaka2434/wiflow-dataset v1) is "
|
||||
"known to contain\n"
|
||||
"9,072 corrupted windows (NaN/Inf + amplitudes up to 3.4e38) in "
|
||||
"dataset files\n"
|
||||
"487-499 (RESULTS.md, reproducibility defect 5). Finding none "
|
||||
"means this copy\n"
|
||||
"has almost certainly already been repaired by remote/clean_v2.py "
|
||||
"(or clean_nan.py),\n"
|
||||
"which zeroes the corrupted windows IN PLACE -- after that the "
|
||||
"corruption evidence\n"
|
||||
"is gone and the masks CANNOT be regenerated from this copy.\n"
|
||||
"\n"
|
||||
"Refusing to overwrite the committed ground-truth masks with "
|
||||
"all-False ones.\n"
|
||||
"Re-download the dataset (kagglehub.dataset_download("
|
||||
"'kaka2434/wiflow-dataset'))\n"
|
||||
"and point --data-dir at the fresh, uncleaned copy.")
|
||||
|
||||
files = describe_files(args.data_dir, union)
|
||||
if files is not None:
|
||||
print(f"marked windows span dataset files {files.min()}-{files.max()}: "
|
||||
f"{files.tolist()}")
|
||||
lo, hi = EXPECTED["files"]
|
||||
if files.min() != lo or files.max() != hi:
|
||||
print(f"WARNING: expected marked files exactly {lo}-{hi} "
|
||||
f"(the pristine v1 download); got {files.min()}-{files.max()}. "
|
||||
f"Different dataset version, or a partially cleaned copy?")
|
||||
for name, mask, exp in (("nan", nan_mask, EXPECTED["nan"]),
|
||||
("big", big_mask, EXPECTED["big"])):
|
||||
if int(mask.sum()) != exp:
|
||||
print(f"WARNING: {name} mask has {int(mask.sum()):,} True windows; "
|
||||
f"the pristine v1 download yields {exp:,}.")
|
||||
|
||||
os.makedirs(args.out_dir, exist_ok=True)
|
||||
for name, mask in (("nan_windows_mask.npy", nan_mask),
|
||||
("big_windows_mask.npy", big_mask)):
|
||||
out = os.path.join(args.out_dir, name)
|
||||
np.save(out, mask)
|
||||
print(f"wrote {out} ({int(mask.sum()):,} True)")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,220 +0,0 @@
|
||||
"""ADR-152 edge optimization: ONNX export + onnxruntime CPU benchmark for the
|
||||
retrained WiFlow-STD checkpoint.
|
||||
|
||||
- Exports fp32 to ONNX. The axial attention reshapes with python ints taken
|
||||
from tensor.size() (view(N*W, C, H)), so a traced graph bakes the batch
|
||||
size; we first try a dynamic-batch export and verify it actually works at
|
||||
batch sizes 1/2/64 -- if not, we fall back to fixed-batch exports.
|
||||
- Verifies output parity vs torch on the stored fixture
|
||||
(results/parity_fixture.npz, batch 2, seed 42): max abs diff < 1e-4.
|
||||
- Measures onnxruntime CPU latency at batch 1 and 64 (median of N runs).
|
||||
- Supplementary: onnxruntime dynamic int8 quantization of the exported model
|
||||
(weight size datapoint for the paper's "~2.2 MB int8" claim).
|
||||
|
||||
Usage:
|
||||
.venv/Scripts/python.exe onnx_bench.py
|
||||
|
||||
Writes/merges into results/edge_optimization.json under key "onnx".
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import platform
|
||||
import statistics
|
||||
import time
|
||||
import traceback
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
from _bench_common import RESULTS, import_upstream, load_wiflow_model
|
||||
|
||||
import_upstream() # sys.path + models stub + >1GB np.load mmap patch
|
||||
|
||||
CHECKPOINT = os.path.join(RESULTS, "retrained_best_pose_model.pth")
|
||||
OUT_JSON = os.path.join(RESULTS, "edge_optimization.json")
|
||||
|
||||
|
||||
def load_fp32_model():
|
||||
return load_wiflow_model(CHECKPOINT)
|
||||
|
||||
|
||||
def try_export(model, path, batch, dynamic, opset=17):
|
||||
"""Returns (ok, exporter_used, error)."""
|
||||
x = torch.rand(batch, 540, 20)
|
||||
attempts = []
|
||||
if dynamic:
|
||||
attempts.append(("dynamo", dict(dynamo=True,
|
||||
dynamic_shapes={"x": {0: "batch"}})))
|
||||
attempts.append(("torchscript", dict(dynamo=False,
|
||||
dynamic_axes={"input": {0: "batch"},
|
||||
"output": {0: "batch"}})))
|
||||
else:
|
||||
attempts.append(("torchscript", dict(dynamo=False)))
|
||||
attempts.append(("dynamo", dict(dynamo=True)))
|
||||
last_err = None
|
||||
for name, kw in attempts:
|
||||
try:
|
||||
with torch.no_grad():
|
||||
torch.onnx.export(model, (x,), path, opset_version=opset,
|
||||
input_names=["input"], output_names=["output"],
|
||||
**kw)
|
||||
return True, name, None
|
||||
except Exception as e: # noqa: BLE001
|
||||
last_err = f"{name}: {type(e).__name__}: {e}"
|
||||
traceback.print_exc()
|
||||
return False, None, last_err
|
||||
|
||||
|
||||
def ort_session(path):
|
||||
import onnxruntime as ort
|
||||
return ort.InferenceSession(path, providers=["CPUExecutionProvider"])
|
||||
|
||||
|
||||
def ort_run(sess, x):
|
||||
inp = sess.get_inputs()[0].name
|
||||
return sess.run(None, {inp: x})[0]
|
||||
|
||||
|
||||
def bench_ort(sess, batch, n_runs):
|
||||
rng = np.random.default_rng(123)
|
||||
x = rng.random((batch, 540, 20), dtype=np.float32)
|
||||
for _ in range(max(5, n_runs // 10)):
|
||||
ort_run(sess, x)
|
||||
times = []
|
||||
for _ in range(n_runs):
|
||||
t0 = time.perf_counter()
|
||||
ort_run(sess, x)
|
||||
times.append(time.perf_counter() - t0)
|
||||
med = statistics.median(times)
|
||||
return {
|
||||
"batch_size": batch,
|
||||
"runs": n_runs,
|
||||
"median_ms_per_batch": med * 1e3,
|
||||
"median_ms_per_window": med * 1e3 / batch,
|
||||
"windows_per_second": batch / med,
|
||||
}
|
||||
|
||||
|
||||
def main():
|
||||
import argparse
|
||||
parser = argparse.ArgumentParser(
|
||||
description="ONNX export + onnxruntime CPU benchmark for the "
|
||||
"retrained WiFlow-STD checkpoint (no options; see "
|
||||
"module docstring). NB: the published "
|
||||
"retrained_fp32_dynamic.onnx came from the TorchScript "
|
||||
"exporter; on newer torch the dynamo attempt may succeed "
|
||||
"first and produce a different (external-data) artifact.")
|
||||
parser.parse_args()
|
||||
|
||||
import onnxruntime
|
||||
model = load_fp32_model()
|
||||
results = {
|
||||
"env": {
|
||||
"torch": torch.__version__,
|
||||
"onnxruntime": onnxruntime.__version__,
|
||||
"platform": platform.platform(),
|
||||
},
|
||||
}
|
||||
|
||||
fixture = np.load(os.path.join(RESULTS, "parity_fixture.npz"))
|
||||
fx, fy = fixture["input"], fixture["output"] # (2,540,20) -> (2,15,2)
|
||||
|
||||
# ---- export: dynamic batch first, fall back to fixed --------------------
|
||||
dyn_path = os.path.join(RESULTS, "retrained_fp32_dynamic.onnx")
|
||||
ok, exporter, err = try_export(model, dyn_path, batch=2, dynamic=True)
|
||||
dynamic_works = False
|
||||
if ok:
|
||||
# verify the dynamic graph really runs at other batch sizes
|
||||
try:
|
||||
sess = ort_session(dyn_path)
|
||||
for b in (1, 2, 64):
|
||||
y = ort_run(sess, np.zeros((b, 540, 20), dtype=np.float32))
|
||||
assert y.shape == (b, 15, 2), y.shape
|
||||
dynamic_works = True
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f"dynamic-batch model does not generalize: {e}")
|
||||
|
||||
sessions = {}
|
||||
if dynamic_works:
|
||||
results["export"] = {"mode": "dynamic-batch", "exporter": exporter,
|
||||
"file": os.path.basename(dyn_path),
|
||||
"size_mb": os.path.getsize(dyn_path) / 1e6}
|
||||
sess = ort_session(dyn_path)
|
||||
sessions = {1: sess, 2: sess, 64: sess}
|
||||
print(f"dynamic-batch export OK via {exporter}")
|
||||
else:
|
||||
results["export"] = {"mode": "fixed-batch", "fallback_reason": err,
|
||||
"files": {}}
|
||||
for b in (1, 2, 64):
|
||||
p = os.path.join(RESULTS, f"retrained_fp32_b{b}.onnx")
|
||||
ok, exporter, err = try_export(model, p, batch=b, dynamic=False)
|
||||
if not ok:
|
||||
results["export"]["files"][str(b)] = {"error": err}
|
||||
print(f"EXPORT FAILED at batch {b}: {err}")
|
||||
continue
|
||||
results["export"]["files"][str(b)] = {
|
||||
"exporter": exporter, "file": os.path.basename(p),
|
||||
"size_mb": os.path.getsize(p) / 1e6}
|
||||
sessions[b] = ort_session(p)
|
||||
print(f"fixed-batch {b} export OK via {exporter}")
|
||||
|
||||
# ---- parity vs torch on the fixture -------------------------------------
|
||||
if 2 in sessions:
|
||||
y_ort = ort_run(sessions[2], fx)
|
||||
with torch.no_grad():
|
||||
y_torch = model(torch.from_numpy(fx)).numpy()
|
||||
results["parity"] = {
|
||||
"fixture": "results/parity_fixture.npz (batch 2, seed 42)",
|
||||
"max_abs_diff_vs_stored_fixture": float(np.abs(y_ort - fy).max()),
|
||||
"max_abs_diff_vs_torch_now": float(np.abs(y_ort - y_torch).max()),
|
||||
"pass_lt_1e-4": bool(np.abs(y_ort - y_torch).max() < 1e-4),
|
||||
}
|
||||
print("parity:", json.dumps(results["parity"], indent=2))
|
||||
|
||||
# ---- latency -------------------------------------------------------------
|
||||
results["latency"] = {}
|
||||
if 1 in sessions:
|
||||
results["latency"]["batch1"] = bench_ort(sessions[1], 1, 100)
|
||||
print(f"ORT batch 1: {results['latency']['batch1']['median_ms_per_window']:.2f} ms/window")
|
||||
if 64 in sessions:
|
||||
results["latency"]["batch64"] = bench_ort(sessions[64], 64, 30)
|
||||
print(f"ORT batch 64: {results['latency']['batch64']['median_ms_per_window']:.3f} ms/window")
|
||||
|
||||
# ---- supplementary: ORT dynamic int8 (size datapoint for the 2.2MB claim)
|
||||
src = (dyn_path if dynamic_works
|
||||
else os.path.join(RESULTS, "retrained_fp32_b1.onnx"))
|
||||
if os.path.exists(src):
|
||||
try:
|
||||
from onnxruntime.quantization import QuantType, quantize_dynamic
|
||||
q_path = os.path.join(RESULTS, "retrained_int8_ort_dynamic.onnx")
|
||||
quantize_dynamic(src, q_path, weight_type=QuantType.QInt8)
|
||||
entry = {"file": os.path.basename(q_path),
|
||||
"size_mb": os.path.getsize(q_path) / 1e6}
|
||||
try:
|
||||
qs = ort_session(q_path)
|
||||
yq = ort_run(qs, fx[:1] if not dynamic_works else fx)
|
||||
ref = fy[:1] if not dynamic_works else fy
|
||||
entry["runs"] = True
|
||||
entry["max_abs_diff_vs_fp32_fixture"] = float(np.abs(yq - ref).max())
|
||||
except Exception as e: # noqa: BLE001
|
||||
entry["runs"] = False
|
||||
entry["run_error"] = f"{type(e).__name__}: {e}"
|
||||
results["ort_int8_dynamic_supplementary"] = entry
|
||||
print("ORT int8:", json.dumps(entry, indent=2))
|
||||
except Exception as e: # noqa: BLE001
|
||||
results["ort_int8_dynamic_supplementary"] = {
|
||||
"error": f"{type(e).__name__}: {e}"}
|
||||
|
||||
merged = {}
|
||||
if os.path.exists(OUT_JSON):
|
||||
with open(OUT_JSON) as f:
|
||||
merged = json.load(f)
|
||||
merged["onnx"] = results
|
||||
with open(OUT_JSON, "w") as f:
|
||||
json.dump(merged, f, indent=2)
|
||||
print(f"wrote {OUT_JSON}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,228 +0,0 @@
|
||||
"""ADR-152 "optimize beyond SOTA": edge-optimization benchmark for the
|
||||
retrained WiFlow-STD checkpoint (results/retrained_best_pose_model.pth,
|
||||
~96% PCK@20, fp32 params 2,225,042).
|
||||
|
||||
Measures, for fp32 / fp16 / dynamic-int8 torch variants:
|
||||
(a) serialized state_dict size on disk,
|
||||
(b) CPU inference latency per window at batch 1 and batch 64
|
||||
(median of repeated runs, this Windows box),
|
||||
(c) accuracy (PCK@20/50 + MPJPE, upstream metrics) on a corruption-free
|
||||
random subset of the seed-42 file-level 70/15/15 test split
|
||||
(same split as eval_repro.py; corrupted windows 487-499 excluded via
|
||||
results/nan_windows_mask.npy | results/big_windows_mask.npy).
|
||||
|
||||
Also verifies the paper's "~2.2 MB int8" size claim: reports which layer
|
||||
types torch dynamic quantization actually converts (the model contains NO
|
||||
nn.Linear -- it is Conv1d/Conv2d/BatchNorm only) and the real on-disk size.
|
||||
|
||||
Usage:
|
||||
.venv/Scripts/python.exe quantize_bench.py \
|
||||
--data-dir C:/Users/ruv/.cache/kagglehub/datasets/kaka2434/wiflow-dataset/versions/1/preprocessed_csi_data \
|
||||
[--subset 10000] [--skip-accuracy]
|
||||
|
||||
Writes/merges into results/edge_optimization.json under key "torch".
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import platform
|
||||
import statistics
|
||||
import time
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torch.utils.data import DataLoader
|
||||
|
||||
from _bench_common import HERE, RESULTS, evaluate, import_upstream, load_wiflow_model
|
||||
|
||||
import_upstream() # sys.path + models stub + >1GB np.load mmap patch
|
||||
|
||||
from dataset import ( # noqa: E402
|
||||
PreprocessedCSIKeypointsDataset,
|
||||
create_preprocessed_train_val_test_loaders,
|
||||
)
|
||||
|
||||
CHECKPOINT = os.path.join(RESULTS, "retrained_best_pose_model.pth")
|
||||
|
||||
|
||||
def load_fp32_model():
|
||||
# legacy upstream key remap inside is a harmless no-op on this checkpoint
|
||||
return load_wiflow_model(CHECKPOINT)
|
||||
|
||||
|
||||
def state_dict_size_bytes(model, path):
|
||||
torch.save(model.state_dict(), path)
|
||||
return os.path.getsize(path)
|
||||
|
||||
|
||||
def bench_latency(model, batch_size, n_runs, dtype=torch.float32):
|
||||
gen = torch.Generator().manual_seed(123)
|
||||
x = torch.rand(batch_size, 540, 20, generator=gen).to(dtype)
|
||||
with torch.no_grad():
|
||||
for _ in range(max(5, n_runs // 10)): # warmup
|
||||
model(x)
|
||||
times = []
|
||||
for _ in range(n_runs):
|
||||
t0 = time.perf_counter()
|
||||
model(x)
|
||||
times.append(time.perf_counter() - t0)
|
||||
med = statistics.median(times)
|
||||
return {
|
||||
"batch_size": batch_size,
|
||||
"runs": n_runs,
|
||||
"median_ms_per_batch": med * 1e3,
|
||||
"median_ms_per_window": med * 1e3 / batch_size,
|
||||
"windows_per_second": batch_size / med,
|
||||
}
|
||||
|
||||
|
||||
def build_test_subset(data_dir, subset_size, batch_size=64):
|
||||
"""Seed-42 file-level 70/15/15 test split (exactly as eval_repro.py),
|
||||
minus corrupted windows, then a seed-42 random subset."""
|
||||
dataset = PreprocessedCSIKeypointsDataset(
|
||||
data_dir=data_dir, keypoint_scale=1000.0, enable_temporal_clean=True)
|
||||
_tr, _va, test_loader = create_preprocessed_train_val_test_loaders(
|
||||
dataset=dataset, batch_size=batch_size, num_workers=0, random_seed=42)
|
||||
test_indices = np.asarray(test_loader.dataset.indices)
|
||||
|
||||
corrupted = (np.load(os.path.join(RESULTS, "nan_windows_mask.npy"))
|
||||
| np.load(os.path.join(RESULTS, "big_windows_mask.npy")))
|
||||
clean = test_indices[~corrupted[test_indices]]
|
||||
print(f"test split: {len(test_indices)} windows, "
|
||||
f"{len(test_indices) - len(clean)} corrupted excluded, "
|
||||
f"{len(clean)} clean")
|
||||
|
||||
if subset_size and subset_size < len(clean):
|
||||
rng = np.random.default_rng(42)
|
||||
clean = np.sort(rng.choice(clean, size=subset_size, replace=False))
|
||||
subset = torch.utils.data.Subset(dataset, clean.tolist())
|
||||
loader = DataLoader(subset, batch_size=batch_size, shuffle=False,
|
||||
num_workers=0)
|
||||
return loader, len(clean)
|
||||
|
||||
|
||||
def quantize_int8_dynamic(fp32_model):
|
||||
"""torch.ao.quantization.quantize_dynamic on Linear/Conv where supported.
|
||||
Returns (model, report) where report documents what actually quantized."""
|
||||
qmodel = torch.ao.quantization.quantize_dynamic(
|
||||
fp32_model, {nn.Linear, nn.Conv1d, nn.Conv2d}, dtype=torch.qint8)
|
||||
|
||||
quantized, total_params, quant_params = [], 0, 0
|
||||
for name, mod in qmodel.named_modules():
|
||||
cls = type(mod).__module__ + "." + type(mod).__name__
|
||||
if "quantized" in cls:
|
||||
w = mod.weight() if callable(getattr(mod, "weight", None)) else None
|
||||
numel = w.numel() if w is not None else 0
|
||||
quant_params += numel
|
||||
quantized.append({"module": name, "class": cls, "params": numel})
|
||||
for p in fp32_model.parameters():
|
||||
total_params += p.numel()
|
||||
|
||||
n_linear = sum(isinstance(m, nn.Linear) for m in fp32_model.modules())
|
||||
n_conv1d = sum(isinstance(m, nn.Conv1d) for m in fp32_model.modules())
|
||||
n_conv2d = sum(isinstance(m, nn.Conv2d) for m in fp32_model.modules())
|
||||
report = {
|
||||
"eligible_module_counts": {
|
||||
"nn.Linear": n_linear, "nn.Conv1d": n_conv1d, "nn.Conv2d": n_conv2d},
|
||||
"modules_actually_quantized": quantized,
|
||||
"n_modules_quantized": len(quantized),
|
||||
"params_total": total_params,
|
||||
"params_quantized": quant_params,
|
||||
"params_quantized_fraction": quant_params / total_params,
|
||||
}
|
||||
return qmodel, report
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--data-dir", default=os.path.join(
|
||||
os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
|
||||
"wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
|
||||
parser.add_argument("--subset", type=int, default=10000)
|
||||
parser.add_argument("--runs-b1", type=int, default=100)
|
||||
parser.add_argument("--runs-b64", type=int, default=30)
|
||||
parser.add_argument("--skip-accuracy", action="store_true")
|
||||
parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
|
||||
args = parser.parse_args()
|
||||
|
||||
torch.manual_seed(42)
|
||||
results = {
|
||||
"env": {
|
||||
"torch": torch.__version__,
|
||||
"platform": platform.platform(),
|
||||
"processor": platform.processor(),
|
||||
"num_threads": torch.get_num_threads(),
|
||||
"checkpoint": os.path.relpath(CHECKPOINT, HERE),
|
||||
},
|
||||
"variants": {},
|
||||
}
|
||||
|
||||
# ---- build variants ---------------------------------------------------
|
||||
fp32 = load_fp32_model()
|
||||
n_params = sum(p.numel() for p in fp32.parameters())
|
||||
results["env"]["params"] = n_params
|
||||
print(f"fp32 model: {n_params:,} params")
|
||||
|
||||
fp16 = load_fp32_model().half()
|
||||
|
||||
int8, q_report = quantize_int8_dynamic(load_fp32_model())
|
||||
results["int8_dynamic_quant_report"] = q_report
|
||||
print(f"int8 dynamic: {q_report['n_modules_quantized']} modules quantized, "
|
||||
f"{q_report['params_quantized_fraction']*100:.1f}% of params")
|
||||
|
||||
variants = {
|
||||
"fp32": (fp32, torch.float32, "retrained_fp32_resaved.pth"),
|
||||
"fp16": (fp16, torch.float16, "retrained_fp16.pth"),
|
||||
"int8_dynamic": (int8, torch.float32, "retrained_int8_dynamic.pth"),
|
||||
}
|
||||
|
||||
# ---- (a) size + (b) latency -------------------------------------------
|
||||
for name, (model, dtype, fname) in variants.items():
|
||||
path = os.path.join(RESULTS, fname)
|
||||
size = state_dict_size_bytes(model, path)
|
||||
print(f"\n=== {name}: {size/1e6:.3f} MB on disk ({fname}) ===")
|
||||
lat1 = bench_latency(model, 1, args.runs_b1, dtype)
|
||||
lat64 = bench_latency(model, 64, args.runs_b64, dtype)
|
||||
print(f" batch 1: {lat1['median_ms_per_window']:.2f} ms/window "
|
||||
f"({lat1['windows_per_second']:.0f}/s)")
|
||||
print(f" batch 64: {lat64['median_ms_per_window']:.3f} ms/window "
|
||||
f"({lat64['windows_per_second']:.0f}/s)")
|
||||
results["variants"][name] = {
|
||||
"file": fname,
|
||||
"size_bytes": size,
|
||||
"size_mb": size / 1e6,
|
||||
"latency_batch1": lat1,
|
||||
"latency_batch64": lat64,
|
||||
}
|
||||
|
||||
# ---- (c) accuracy ------------------------------------------------------
|
||||
if not args.skip_accuracy:
|
||||
loader, n_clean = build_test_subset(args.data_dir, args.subset)
|
||||
results["accuracy_subset"] = {
|
||||
"description": "seed-42 file-level 70/15/15 test split, corrupted "
|
||||
"windows (files 487-499) excluded, seed-42 random "
|
||||
"subset",
|
||||
"subset_size": min(args.subset, n_clean) if args.subset else n_clean,
|
||||
"clean_test_total": n_clean,
|
||||
}
|
||||
for name, (model, dtype, _f) in variants.items():
|
||||
print(f"\n=== accuracy: {name} ===")
|
||||
results["variants"][name]["accuracy"] = evaluate(
|
||||
model, loader, dtype=dtype, label=name)
|
||||
print(json.dumps(results["variants"][name]["accuracy"], indent=2))
|
||||
|
||||
# ---- merge into edge_optimization.json ---------------------------------
|
||||
merged = {}
|
||||
if os.path.exists(args.out):
|
||||
with open(args.out) as f:
|
||||
merged = json.load(f)
|
||||
merged["torch"] = results
|
||||
with open(args.out, "w") as f:
|
||||
json.dump(merged, f, indent=2)
|
||||
print(f"\nwrote {args.out}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,14 +0,0 @@
|
||||
import numpy as np, os
|
||||
d = os.path.expanduser('~/wiflow-std-bench/preprocessed_csi_data')
|
||||
csi = np.load(os.path.join(d, 'csi_windows.npy'), mmap_mode='r+')
|
||||
zeroed = 0
|
||||
chunk = 4000
|
||||
for i in range(0, len(csi), chunk):
|
||||
block = csi[i:i+chunk]
|
||||
finite = np.isfinite(block)
|
||||
bad = (~finite).any(axis=(1, 2)) | (np.abs(np.where(finite, block, 0)).max(axis=(1, 2)) > 1.5)
|
||||
if bad.any():
|
||||
block[bad] = 0.0
|
||||
zeroed += int(bad.sum())
|
||||
csi.flush()
|
||||
print(f'zeroed {zeroed} corrupted windows entirely')
|
||||
@@ -1,112 +0,0 @@
|
||||
"""Evaluate the retrained WiFlow-STD checkpoint (ADR-152 §2.2a fallback).
|
||||
|
||||
Scores the model produced by run.py (train_output/best_pose_model.pth or similar)
|
||||
on the seed-42 test split: full test set AND NaN-free subset (excluding windows
|
||||
that were zero-filled by clean_nan.py — file indices 487-499).
|
||||
|
||||
NOTE: deployed to ruvultra (~/wiflow-std-bench) as a standalone single file,
|
||||
so it deliberately inlines its helpers. The reference implementations (upstream
|
||||
import shim, >1GB np.load mmap patch, key-remap loader, canonical evaluate
|
||||
loop) live in benchmarks/wiflow-std/_bench_common.py — keep copies in sync.
|
||||
"""
|
||||
import json, os, random, sys
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch.utils.data import DataLoader, Subset
|
||||
|
||||
# csi_windows.npy is ~13 GB; mmap large arrays instead of eagerly loading
|
||||
# ~15 GB into RAM (same patch as _bench_common._np_load_mmap).
|
||||
_np_load = np.load
|
||||
|
||||
|
||||
def _np_load_mmap(path, *a, **kw):
|
||||
if (isinstance(path, str) and path.endswith('.npy')
|
||||
and os.path.getsize(path) > 1 << 30 and 'mmap_mode' not in kw):
|
||||
kw['mmap_mode'] = 'r'
|
||||
return _np_load(path, *a, **kw)
|
||||
|
||||
|
||||
np.load = _np_load_mmap
|
||||
|
||||
sys.path.insert(0, os.path.expanduser('~/wiflow-std-bench/upstream'))
|
||||
from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders
|
||||
from models.pose_model import WiFlowPoseModel
|
||||
from utils.metrics import calculate_pck, calculate_mpjpe
|
||||
|
||||
|
||||
def find_checkpoint():
|
||||
cands = []
|
||||
for root, _, files in os.walk(os.path.expanduser('~/wiflow-std-bench/train_output')):
|
||||
for f in files:
|
||||
if f.endswith('.pth'):
|
||||
cands.append(os.path.join(root, f))
|
||||
# also upstream/test default output dir
|
||||
for root, _, files in os.walk(os.path.expanduser('~/wiflow-std-bench/upstream')):
|
||||
for f in files:
|
||||
if f.endswith('.pth') and 'best' in f and 'cross_dataset' not in root:
|
||||
p = os.path.join(root, f)
|
||||
if os.path.getmtime(p) > os.path.getmtime(os.path.expanduser('~/wiflow-std-bench/train.log')) - 86400 * 2:
|
||||
cands.append(p)
|
||||
cands = [c for c in cands if not c.endswith('upstream/best_pose_model.pth')]
|
||||
if not cands:
|
||||
sys.exit('no retrained checkpoint found')
|
||||
return max(cands, key=os.path.getmtime)
|
||||
|
||||
|
||||
def evaluate(model, loader, device):
|
||||
model.eval()
|
||||
totals = {t: 0.0 for t in (0.1, 0.2, 0.3, 0.4, 0.5)}
|
||||
total_mpe, n = 0.0, 0
|
||||
with torch.no_grad():
|
||||
for bx, by in loader:
|
||||
bx, by = bx.to(device), by.to(device)
|
||||
out = model(bx)
|
||||
bs = by.size(0)
|
||||
total_mpe += calculate_mpjpe(out, by) * bs
|
||||
pck = calculate_pck(out, by, thresholds=list(totals))
|
||||
for t in totals:
|
||||
totals[t] += pck[t] * bs
|
||||
n += bs
|
||||
return {'samples': n, 'mpjpe': total_mpe / n,
|
||||
**{f'pck@{int(t*100)}': totals[t] / n for t in totals}}
|
||||
|
||||
|
||||
random.seed(42); np.random.seed(42); torch.manual_seed(42)
|
||||
torch.cuda.manual_seed_all(42)
|
||||
torch.backends.cudnn.deterministic = True
|
||||
|
||||
d = os.path.expanduser('~/wiflow-std-bench/preprocessed_csi_data')
|
||||
dataset = PreprocessedCSIKeypointsDataset(data_dir=d, keypoint_scale=1000.0,
|
||||
enable_temporal_clean=True)
|
||||
_, _, test_loader = create_preprocessed_train_val_test_loaders(
|
||||
dataset=dataset, batch_size=256, num_workers=2, random_seed=42)
|
||||
|
||||
device = torch.device('cuda')
|
||||
ckpt = find_checkpoint()
|
||||
print('checkpoint:', ckpt)
|
||||
model = WiFlowPoseModel(dropout=0.5).to(device)
|
||||
state = torch.load(ckpt, map_location=device, weights_only=True)
|
||||
renames = {'att.': 'attention.', 'final_conv.': 'decoder.'}
|
||||
state = {next((new + k[len(old):] for old, new in renames.items()
|
||||
if k.startswith(old)), k): v for k, v in state.items()}
|
||||
model.load_state_dict(state, strict=True)
|
||||
|
||||
results = {'checkpoint': ckpt}
|
||||
print('=== full test set ===')
|
||||
results['test_full'] = evaluate(model, test_loader, device)
|
||||
print(json.dumps(results['test_full'], indent=2))
|
||||
|
||||
# NaN-free subset: exclude windows from corrupted files 487-499
|
||||
test_subset = test_loader.dataset # Subset(dataset, test_indices)
|
||||
w2f = dataset.window_to_file
|
||||
clean_idx = [i for i in test_subset.indices if w2f[i] < 487]
|
||||
print(f'=== NaN-free test subset ({len(clean_idx)} of {len(test_subset.indices)}) ===')
|
||||
clean_loader = DataLoader(Subset(dataset, clean_idx), batch_size=256, shuffle=False)
|
||||
results['test_clean'] = evaluate(model, clean_loader, device)
|
||||
print(json.dumps(results['test_clean'], indent=2))
|
||||
|
||||
out = os.path.expanduser('~/wiflow-std-bench/eval_retrained.json')
|
||||
with open(out, 'w') as f:
|
||||
json.dump(results, f, indent=2)
|
||||
print('wrote', out)
|
||||
@@ -1,374 +0,0 @@
|
||||
"""ADR-152 SS2.2 measurement (b): WiFlow-STD fine-tuned on our fresh ESP32 paired dataset.
|
||||
|
||||
Dataset: ~/wiflow-std-bench/paired-20260610.jsonl -- 2,046 paired windows collected
|
||||
2026-06-10 22:10-22:40 (ONE subject, ONE room, ONE ESP32 node, varied poses).
|
||||
Per record: csi = flat float32 list, csi_shape, kp = 17 COCO [x, y] normalized [0,1]
|
||||
camera coords, conf (MediaPipe mean confidence, all > 0.5 in this set), ts_start/ts_end.
|
||||
Aligner: scripts/align-ground-truth.js, non-overlapping 20-frame windows (~0.42 s each).
|
||||
|
||||
Dataset findings (MEASURED on this file, 2026-06-10):
|
||||
- csi_shape is HETEROGENEOUS, not uniformly [70, 20]: 1,347x [70,20], 284x [134,20],
|
||||
243x [26,20], 130x [12,20], 42x [20,20]. The ESP32 stream emits mixed frame types
|
||||
and the aligner stamps each window's subcarrier count from frame[0]
|
||||
(extractCsiMatrix: nSc = window[0].subcarriers), zero-padding/truncating the rest.
|
||||
Even native-70 windows contain ~20.4% internally zero-padded short frames
|
||||
(subcarriers 40..69 all-zero for those frames).
|
||||
- LAYOUT BUG: the aligner fills matrix[f * nSc + s] (frame-major) but declares
|
||||
shape [nSc, nFrames]. The true layout is (frame, subcarrier); we reshape
|
||||
(nFrames, nSc) and transpose. Confirmed by coherent per-frame zero-tails.
|
||||
- Handling here (primary suite, "all2046"): every frame's subcarrier axis is
|
||||
linearly resampled to 70 bins (np.interp over a normalized index domain;
|
||||
identity for native-70 frames) so the pre-registered n=2,046 and split sizes
|
||||
hold. Secondary suite ("native70") restricts to the 1,347 native [70,20]
|
||||
windows (temporal 70/15/15 of those) as a homogeneity robustness check.
|
||||
|
||||
Pre-registered protocol (followed exactly):
|
||||
1. TEMPORAL split (records are time-sorted; asserted): first 70% train (1,432),
|
||||
next 15% val (307), last 15% test (307). No shuffling across time. Seed 42
|
||||
for everything else.
|
||||
2. Model: upstream WiFlow-STD trunk (WiFlowPoseModel) with a learned 1x1 Conv1d
|
||||
projection 70->540 prepended, and K=17 via the parameter-free adaptive pool
|
||||
(AdaptiveAvgPool2d((17, 1)) instead of (15, 1)) -- pretrained weights load
|
||||
for any K. CSI normalization: divide by the TRAIN-split 99th-percentile
|
||||
amplitude, clip to [0, 1] (documented in output JSON).
|
||||
3. Three runs, <=60 epochs, early-stop patience 8 on val MPJPE, batch 32,
|
||||
AdamW, fp32 (no autocast):
|
||||
(i) pretrained-init: trunk init from upstream/test/best_pose_model.pth
|
||||
(the measurement-(a) retrained checkpoint, ~96% PCK@20 on WiFlow data;
|
||||
key remap att.->attention. / final_conv.->decoder. applied defensively
|
||||
as in eval_repro.py -- a no-op for this checkpoint, which already uses
|
||||
the new names). Discriminative lr: adapter 1e-4, trunk 1e-5.
|
||||
(ii) scratch: same architecture, random init, all params lr 1e-4.
|
||||
(iii) frozen-trunk: pretrained trunk frozen (requires_grad=False AND held in
|
||||
.eval() so BatchNorm running stats cannot drift -- pure transfer probe);
|
||||
only the 70->540 adapter trains, lr 1e-4.
|
||||
4. Metrics on the temporal TEST split: torso-normalized PCK@10/20/30/40/50 and
|
||||
MPJPE. Upstream utils/metrics.py calculate_pck(use_torso_norm=True) hardcodes
|
||||
NECK_IDX/PELVIS_IDX = 2, 12 -- a 15-keypoint convention that is WRONG for our
|
||||
17 COCO keypoints (2 = right_eye, 12 = right_hip). We therefore reimplement the
|
||||
identical math (per-frame norm distance, clamp min 0.01, mean over all
|
||||
keypoints x frames) with torso = ||l_shoulder(5) - l_hip(11)||.
|
||||
Also reported: prediction std across test frames (constant-pose detector;
|
||||
must be > 0) and the mean-pose-predictor baseline (train-split mean pose
|
||||
evaluated on test -- the honesty bar).
|
||||
|
||||
Usage (on ruvultra):
|
||||
nice -n 10 nohup ~/wiflow-std-bench/venv/bin/python train_measb.py > train_measb.log 2>&1 &
|
||||
|
||||
NOTE: deployed to ruvultra as a standalone single file, so it deliberately
|
||||
inlines its helpers. The reference implementations (upstream import shim,
|
||||
np.load mmap patch, key-remap loader, canonical evaluate loop) live in
|
||||
benchmarks/wiflow-std/_bench_common.py — keep copies in sync.
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import sys
|
||||
import time
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
BENCH = os.path.expanduser("~/wiflow-std-bench")
|
||||
UPSTREAM = os.path.join(BENCH, "upstream")
|
||||
MEASB = os.path.join(BENCH, "measb")
|
||||
DATA = os.path.join(BENCH, "paired-20260610.jsonl")
|
||||
CHECKPOINT = os.path.join(UPSTREAM, "test", "best_pose_model.pth")
|
||||
|
||||
sys.path.insert(0, UPSTREAM)
|
||||
|
||||
# Upstream defect (1): models/__init__.py imports a name tcn.py does not define.
|
||||
# Register a stub package so the broken __init__ never executes (as eval_repro.py).
|
||||
import types # noqa: E402
|
||||
|
||||
_models_pkg = types.ModuleType("models")
|
||||
_models_pkg.__path__ = [os.path.join(UPSTREAM, "models")]
|
||||
sys.modules["models"] = _models_pkg
|
||||
|
||||
from models.pose_model import WiFlowPoseModel # noqa: E402
|
||||
|
||||
SEED = 42
|
||||
K = 17
|
||||
N_SUBC = 70
|
||||
TRUNK_IN = 540
|
||||
BATCH = 32 # <= 64 per protocol (GPU shared with the efficiency sweep)
|
||||
MAX_EPOCHS = 60
|
||||
PATIENCE = 8
|
||||
LR_ADAPTER = 1e-4
|
||||
LR_TRUNK_FT = 1e-5 # 10x lower for the pretrained trunk vs the fresh adapter
|
||||
L_SHOULDER, L_HIP = 5, 11
|
||||
THRESHOLDS = (0.1, 0.2, 0.3, 0.4, 0.5)
|
||||
|
||||
|
||||
def set_seed(seed=SEED):
|
||||
random.seed(seed)
|
||||
np.random.seed(seed)
|
||||
torch.manual_seed(seed)
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.manual_seed_all(seed)
|
||||
torch.backends.cudnn.deterministic = True
|
||||
torch.backends.cudnn.benchmark = False
|
||||
|
||||
|
||||
def resample_subcarriers(frame_major, n_out=N_SUBC):
|
||||
"""(nFrames, nSc) -> (nFrames, n_out) by per-frame linear interpolation.
|
||||
|
||||
Identity for nSc == n_out. Normalized index domain [0, 1] on both sides.
|
||||
"""
|
||||
nf, nsc = frame_major.shape
|
||||
if nsc == n_out:
|
||||
return frame_major
|
||||
xi = np.linspace(0.0, 1.0, nsc)
|
||||
xo = np.linspace(0.0, 1.0, n_out)
|
||||
return np.stack([np.interp(xo, xi, frame_major[f]) for f in range(nf)]).astype(np.float32)
|
||||
|
||||
|
||||
def load_dataset():
|
||||
csi, kps, confs, ts, native70 = [], [], [], [], []
|
||||
shape_counts = {}
|
||||
with open(DATA) as f:
|
||||
for line in f:
|
||||
r = json.loads(line)
|
||||
nsc, nf = r["csi_shape"]
|
||||
shape_counts[f"{nsc}x{nf}"] = shape_counts.get(f"{nsc}x{nf}", 0) + 1
|
||||
assert nf == 20, r["csi_shape"]
|
||||
# Aligner layout bug: data is frame-major despite the declared
|
||||
# [nSc, nFrames] shape -- reshape (nFrames, nSc), then resample the
|
||||
# subcarrier axis to 70 and transpose to (70 subcarriers, 20 frames).
|
||||
fm = np.asarray(r["csi"], dtype=np.float32).reshape(nf, nsc)
|
||||
csi.append(resample_subcarriers(fm).T)
|
||||
kp = np.asarray(r["kp"], dtype=np.float32)
|
||||
assert kp.shape == (K, 2), kp.shape
|
||||
kps.append(kp)
|
||||
confs.append(r["conf"])
|
||||
ts.append(r["ts_start"])
|
||||
native70.append(nsc == N_SUBC)
|
||||
assert all(ts[i] <= ts[i + 1] for i in range(len(ts) - 1)), "records not time-sorted"
|
||||
return (np.stack(csi), np.stack(kps), np.asarray(confs, dtype=np.float32),
|
||||
np.asarray(native70), shape_counts, ts[0], ts[-1])
|
||||
|
||||
|
||||
def temporal_split(n):
|
||||
n_train = int(round(n * 0.70))
|
||||
n_val = int(round(n * 0.15))
|
||||
return slice(0, n_train), slice(n_train, n_train + n_val), slice(n_train + n_val, n)
|
||||
|
||||
|
||||
class AdaptedWiFlow(nn.Module):
|
||||
"""1x1 Conv1d adapter 70->540 + upstream WiFlow-STD trunk with K=17 pool head."""
|
||||
|
||||
def __init__(self, k=K, dropout=0.5):
|
||||
super().__init__()
|
||||
self.adapter = nn.Conv1d(N_SUBC, TRUNK_IN, kernel_size=1)
|
||||
nn.init.kaiming_normal_(self.adapter.weight, mode="fan_out", nonlinearity="relu")
|
||||
nn.init.constant_(self.adapter.bias, 0)
|
||||
self.trunk = WiFlowPoseModel(dropout=dropout)
|
||||
# K=17 via the parameter-free adaptive pool: decoder emits [B, 2, 15, 20]
|
||||
# spatial maps; pooling H->17 instead of 15 yields [B, 17, 2] with no new
|
||||
# parameters, so the pretrained state_dict loads strict=True for any K.
|
||||
self.trunk.avg_pool = nn.AdaptiveAvgPool2d((k, 1))
|
||||
|
||||
def forward(self, x):
|
||||
return self.trunk(self.adapter(x))
|
||||
|
||||
|
||||
def load_pretrained_trunk(trunk, path):
|
||||
state = torch.load(path, map_location="cpu", weights_only=True)
|
||||
# Defensive remap as in eval_repro.py (no-op for the retrained checkpoint).
|
||||
renames = {"att.": "attention.", "final_conv.": "decoder."}
|
||||
state = {next((new + k[len(old):] for old, new in renames.items()
|
||||
if k.startswith(old)), k): v
|
||||
for k, v in state.items()}
|
||||
trunk.load_state_dict(state, strict=True)
|
||||
|
||||
|
||||
def pck_torso(pred, target, thresholds=THRESHOLDS):
|
||||
"""Upstream calculate_pck math, torso = l_shoulder(5)<->l_hip(11) for 17-kp COCO."""
|
||||
norm = torch.sqrt(((target[:, L_SHOULDER] - target[:, L_HIP]) ** 2).sum(dim=1))
|
||||
norm = torch.clamp(norm, min=0.01)
|
||||
dist = torch.sqrt(((pred - target) ** 2).sum(dim=2)) / norm.unsqueeze(1)
|
||||
return {f"pck@{int(t * 100)}": (dist <= t).float().mean().item() for t in thresholds}
|
||||
|
||||
|
||||
def mpjpe(pred, target):
|
||||
return torch.sqrt(((pred - target) ** 2).sum(dim=2)).mean().item()
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def predict(model, x, batch=256):
|
||||
model.eval()
|
||||
return torch.cat([model(x[i:i + batch]) for i in range(0, len(x), batch)])
|
||||
|
||||
|
||||
def eval_preds(pred, target):
|
||||
out = pck_torso(pred, target)
|
||||
out["mpjpe"] = mpjpe(pred, target)
|
||||
# Constant-pose detector: std across test frames per coordinate, mean over
|
||||
# the 17x2 coordinates. 0.0 == degenerate constant predictor.
|
||||
out["pred_std"] = pred.std(dim=0).mean().item()
|
||||
return out
|
||||
|
||||
|
||||
def train_run(name, x_tr, y_tr, x_va, y_va, device, pretrained, freeze_trunk,
|
||||
lr_trunk):
|
||||
set_seed(SEED)
|
||||
model = AdaptedWiFlow().to(device)
|
||||
if pretrained:
|
||||
load_pretrained_trunk(model.trunk, CHECKPOINT)
|
||||
if freeze_trunk:
|
||||
for p in model.trunk.parameters():
|
||||
p.requires_grad = False
|
||||
groups = [{"params": model.adapter.parameters(), "lr": LR_ADAPTER}]
|
||||
else:
|
||||
groups = [{"params": model.adapter.parameters(), "lr": LR_ADAPTER},
|
||||
{"params": model.trunk.parameters(), "lr": lr_trunk}]
|
||||
opt = torch.optim.AdamW(groups)
|
||||
loss_fn = nn.MSELoss()
|
||||
|
||||
n = len(x_tr)
|
||||
best_val, best_state, best_epoch, bad = float("inf"), None, -1, 0
|
||||
history = []
|
||||
t0 = time.time()
|
||||
for epoch in range(MAX_EPOCHS):
|
||||
model.train()
|
||||
if freeze_trunk:
|
||||
model.trunk.eval() # keep BatchNorm running stats fixed: pure transfer
|
||||
perm = torch.randperm(n, device=device)
|
||||
ep_loss = 0.0
|
||||
for i in range(0, n, BATCH):
|
||||
idx = perm[i:i + BATCH]
|
||||
opt.zero_grad()
|
||||
loss = loss_fn(model(x_tr[idx]), y_tr[idx])
|
||||
loss.backward()
|
||||
opt.step()
|
||||
ep_loss += loss.item() * len(idx)
|
||||
val_mpjpe = mpjpe(predict(model, x_va), y_va)
|
||||
history.append({"epoch": epoch, "train_mse": ep_loss / n, "val_mpjpe": val_mpjpe})
|
||||
marker = ""
|
||||
if val_mpjpe < best_val:
|
||||
best_val, best_epoch, bad = val_mpjpe, epoch, 0
|
||||
best_state = {k: v.detach().cpu().clone() for k, v in model.state_dict().items()}
|
||||
marker = " *"
|
||||
else:
|
||||
bad += 1
|
||||
print(f"[{name}] epoch {epoch:02d} train_mse {ep_loss / n:.6f} "
|
||||
f"val_mpjpe {val_mpjpe:.5f}{marker}", flush=True)
|
||||
if bad >= PATIENCE:
|
||||
print(f"[{name}] early stop at epoch {epoch} (best {best_epoch})", flush=True)
|
||||
break
|
||||
model.load_state_dict(best_state)
|
||||
torch.save(best_state, os.path.join(MEASB, f"{name}_best.pth"))
|
||||
return model, {"best_epoch": best_epoch, "best_val_mpjpe": best_val,
|
||||
"epochs_run": len(history), "wall_seconds": round(time.time() - t0, 1),
|
||||
"history": history}
|
||||
|
||||
|
||||
def run_suite(tag, csi, kps, device):
|
||||
"""Temporal 70/15/15 split, mean-pose baseline, three training runs."""
|
||||
n = len(csi)
|
||||
tr, va, te = temporal_split(n)
|
||||
print(f"=== suite {tag}: n={n} train={tr.stop} val={va.stop - va.start} "
|
||||
f"test={te.stop - te.start} ===", flush=True)
|
||||
|
||||
# CSI normalization constant from TRAIN split only.
|
||||
train_p99 = float(np.percentile(csi[tr], 99))
|
||||
train_max = float(csi[tr].max())
|
||||
print(f"[{tag}] train p99={train_p99:.3f} max={train_max:.3f} -> /p99, clip [0,1]",
|
||||
flush=True)
|
||||
csi_n = np.clip(csi / train_p99, 0.0, 1.0).astype(np.float32)
|
||||
|
||||
x = torch.from_numpy(csi_n).to(device)
|
||||
y = torch.from_numpy(kps).to(device)
|
||||
x_tr, y_tr = x[tr], y[tr]
|
||||
x_va, y_va = x[va], y[va]
|
||||
x_te, y_te = x[te], y[te]
|
||||
|
||||
suite = {
|
||||
"n_windows": n,
|
||||
"split": {"n_train": int(tr.stop), "n_val": int(va.stop - va.start),
|
||||
"n_test": int(te.stop - te.start)},
|
||||
"csi_norm": {"method": "divide by train-split p99 amplitude, clip [0,1]",
|
||||
"train_p99": train_p99, "train_max": train_max},
|
||||
"runs": {},
|
||||
}
|
||||
|
||||
# Honesty bar: mean-pose predictor fit on TRAIN, evaluated on TEST.
|
||||
mean_pose = y_tr.mean(dim=0, keepdim=True).expand(len(y_te), -1, -1)
|
||||
suite["mean_pose_baseline"] = eval_preds(mean_pose, y_te)
|
||||
suite["mean_pose_baseline"]["note"] = "train-split mean pose; pred_std 0 by construction"
|
||||
print(f"[{tag}] mean-pose baseline:", json.dumps(suite["mean_pose_baseline"]),
|
||||
flush=True)
|
||||
|
||||
configs = [
|
||||
("pretrained", dict(pretrained=True, freeze_trunk=False, lr_trunk=LR_TRUNK_FT)),
|
||||
("scratch", dict(pretrained=False, freeze_trunk=False, lr_trunk=LR_ADAPTER)),
|
||||
("frozen_trunk", dict(pretrained=True, freeze_trunk=True, lr_trunk=0.0)),
|
||||
]
|
||||
for name, cfg in configs:
|
||||
print(f"=== run: {tag}/{name} {cfg} ===", flush=True)
|
||||
model, train_info = train_run(f"{tag}_{name}", x_tr, y_tr, x_va, y_va,
|
||||
device, **cfg)
|
||||
test_metrics = eval_preds(predict(model, x_te), y_te)
|
||||
n_trainable = sum(p.numel() for p in model.parameters() if p.requires_grad)
|
||||
suite["runs"][name] = {"config": cfg, "trainable_params": n_trainable,
|
||||
"train": {k: v for k, v in train_info.items()
|
||||
if k != "history"},
|
||||
"history": train_info["history"],
|
||||
"test": test_metrics}
|
||||
print(f"[{tag}/{name}] TEST:", json.dumps(test_metrics), flush=True)
|
||||
return suite
|
||||
|
||||
|
||||
def main():
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
print(f"device {device}, torch {torch.__version__}", flush=True)
|
||||
set_seed(SEED)
|
||||
|
||||
csi, kps, confs, native70, shape_counts, ts_first, ts_last = load_dataset()
|
||||
print(f"shape distribution: {shape_counts}", flush=True)
|
||||
|
||||
results = {
|
||||
"protocol": {
|
||||
"dataset": DATA, "n_windows": len(csi),
|
||||
"ts_first": ts_first, "ts_last": ts_last,
|
||||
"conf_mean": float(confs.mean()), "conf_min": float(confs.min()),
|
||||
"csi_shape_distribution": shape_counts,
|
||||
"csi_layout_note": "aligner stores frame-major data under a transposed "
|
||||
"[nSc, nFrames] shape label; corrected on load",
|
||||
"csi_resample": "per-frame linear interp of subcarrier axis to 70 bins "
|
||||
"(identity for native-70 frames); native-70 windows still "
|
||||
"contain ~20.4% internally zero-padded short frames",
|
||||
"split": "temporal 70/15/15 (no shuffle across time)",
|
||||
"model": "1x1 Conv1d 70->540 adapter + WiFlowPoseModel trunk, "
|
||||
"AdaptiveAvgPool2d((17,1)) head (parameter-free K=17)",
|
||||
"checkpoint": CHECKPOINT,
|
||||
"checkpoint_note": "measurement-(a) retrained checkpoint (~96% PCK@20 on "
|
||||
"WiFlow data); att./final_conv. remap applied "
|
||||
"defensively (no-op, already new-style keys)",
|
||||
"optimizer": f"AdamW, adapter lr {LR_ADAPTER}, fine-tuned trunk lr "
|
||||
f"{LR_TRUNK_FT} (10x lower), scratch all {LR_ADAPTER}",
|
||||
"batch": BATCH, "max_epochs": MAX_EPOCHS, "patience": PATIENCE,
|
||||
"precision": "fp32", "seed": SEED,
|
||||
"pck": "torso-normalized, torso = ||l_shoulder(5) - l_hip(11)||, "
|
||||
"clamp min 0.01, mean over keypoints x frames "
|
||||
"(upstream math; upstream 2/12 indices are a 15-kp convention)",
|
||||
},
|
||||
# Primary: all 2,046 windows (pre-registered n), subcarrier axis resampled.
|
||||
"all2046": None,
|
||||
# Secondary robustness check: the 1,347 native [70,20] windows only.
|
||||
"native70": None,
|
||||
}
|
||||
|
||||
results["all2046"] = run_suite("all2046", csi, kps, device)
|
||||
results["native70"] = run_suite("native70", csi[native70], kps[native70], device)
|
||||
|
||||
out = os.path.join(MEASB, "measurement_b.json")
|
||||
with open(out, "w") as f:
|
||||
json.dump(results, f, indent=2)
|
||||
print(f"wrote {out}", flush=True)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,33 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -ex
|
||||
cd ~/wiflow-std-bench
|
||||
|
||||
# 1. clone upstream at the pinned commit
|
||||
if [ ! -d upstream ]; then
|
||||
git clone https://github.com/DY2434/WiFlow-WiFi-Pose-Estimation-with-Spatio-Temporal-Decoupling upstream
|
||||
fi
|
||||
cd upstream && git checkout 06899d294a0f44709d601a53e91dbf24759daefb && cd ..
|
||||
|
||||
# 2. documented deviation: fix upstream import bug (TemporalConvNet does not exist)
|
||||
sed -i 's/from .tcn import TemporalConvNet/from .tcn import TemporalBlock/; s/'"'"'TemporalConvNet'"'"'/'"'"'TemporalBlock'"'"'/' upstream/models/__init__.py
|
||||
|
||||
# 3. venv: torch cu128 (RTX 5080 = sm_120 needs >=2.7; their pin 2.3.1 predates Blackwell)
|
||||
if [ ! -d venv ]; then
|
||||
python3 -m venv venv
|
||||
./venv/bin/pip install -q --upgrade pip
|
||||
./venv/bin/pip install -q torch --index-url https://download.pytorch.org/whl/cu128
|
||||
./venv/bin/pip install -q numpy pandas matplotlib seaborn scikit-learn opencv-python-headless scipy tqdm psutil kagglehub
|
||||
fi
|
||||
./venv/bin/python -c "import torch; print(torch.__version__, torch.cuda.is_available(), torch.cuda.get_device_name(0))"
|
||||
|
||||
# 4. dataset via kagglehub (anonymous, public dataset)
|
||||
DS=$(./venv/bin/python -c "import kagglehub; print(kagglehub.dataset_download('kaka2434/wiflow-dataset'))")
|
||||
echo "dataset at: $DS"
|
||||
|
||||
# 5. run.py hardcodes ../preprocessed_csi_data relative to upstream/
|
||||
ln -sfn "$DS/preprocessed_csi_data" ~/wiflow-std-bench/preprocessed_csi_data
|
||||
|
||||
# 6. train with upstream defaults (seed 42 set inside run.py)
|
||||
../venv/bin/python ../clean_nan.py 2>/dev/null || venv/bin/python clean_nan.py
|
||||
cd upstream
|
||||
../venv/bin/python run.py --gpu 0 --batch_size 64 --epochs 50 --output_dir ../train_output
|
||||
@@ -1,332 +0,0 @@
|
||||
"""Configurable compact variants of the WiFlow-STD pose model (ADR-152 efficiency sweep).
|
||||
|
||||
This is a parameterized copy of upstream models/{pose_model,tcn,convnet,attention}.py
|
||||
(DY2434/WiFlow @ 06899d29, Apache-2.0). upstream/ is NOT modified. Deviations from
|
||||
upstream, all forced by shrinking channels and documented per variant in run_sweep.py:
|
||||
|
||||
1. TCN grouped-conv groups: upstream hardcodes groups=20, which does not divide
|
||||
the compact channel counts (e.g. 270, 135, 85). Rule here:
|
||||
- groups_mode='gcd20': per-conv groups = gcd(channels, 20) (== 20 wherever
|
||||
upstream's choice is valid, incl. the 540-ch input conv; falls back to the
|
||||
largest common divisor with 20 otherwise).
|
||||
- groups_mode='depthwise': groups = channels (tiny variant only).
|
||||
2. Conv2d downsampling strides: upstream uses 4 stride-(1,2) blocks because
|
||||
240/2^4 = 15 == n_keypoints. With smaller TCN output widths that would leave
|
||||
<15 rows and AdaptiveAvgPool2d((15,1)) would duplicate rows across keypoints.
|
||||
Rule: halve the width only while the result stays >= 15 (stride-2 blocks
|
||||
first, stride-1 after). Full model: 240 -> 4 halvings = upstream exactly.
|
||||
3. input_pw_groups (tiny only): the dense 540->c pointwise + residual downsample
|
||||
in TCN block 1 cost 2*540*c params (a ~117k floor that alone exceeds the
|
||||
tiny <100k budget). tiny groups these two convs (groups=4; 4 | gcd(540, 68)).
|
||||
4. Decoder mid-channels: upstream 64->32; here c_last -> max(c_last // 2, 4).
|
||||
"""
|
||||
import math
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
|
||||
def tcn_groups(channels: int, mode: str) -> int:
|
||||
if mode == 'depthwise':
|
||||
return channels
|
||||
if mode == 'gcd20':
|
||||
return math.gcd(channels, 20)
|
||||
raise ValueError(mode)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- TCN (copy of tcn.py)
|
||||
class Chomp1d(nn.Module):
|
||||
def __init__(self, chomp_size):
|
||||
super().__init__()
|
||||
self.chomp_size = chomp_size
|
||||
|
||||
def forward(self, x):
|
||||
return x[:, :, :-self.chomp_size].contiguous()
|
||||
|
||||
|
||||
class CompactGroupedTemporalBlock(nn.Module):
|
||||
"""Upstream InnerGroupedTemporalBlock with parameterized groups."""
|
||||
|
||||
def __init__(self, n_inputs, n_outputs, kernel_size, stride, dilation, padding,
|
||||
dropout=0.2, groups_mode='gcd20', pw_groups=1):
|
||||
super().__init__()
|
||||
g_in = tcn_groups(n_inputs, groups_mode)
|
||||
g_out = tcn_groups(n_outputs, groups_mode)
|
||||
self.groups = (g_in, g_out)
|
||||
self.pw_groups = pw_groups
|
||||
|
||||
self.conv1_group = nn.Conv1d(n_inputs, n_inputs, kernel_size, stride=stride,
|
||||
padding=padding, dilation=dilation,
|
||||
groups=g_in, bias=False)
|
||||
self.chomp1 = Chomp1d(padding) if padding > 0 else nn.Identity()
|
||||
self.bn1_group = nn.BatchNorm1d(n_inputs)
|
||||
self.relu1_group = nn.SiLU(inplace=True)
|
||||
|
||||
self.conv1_pw = nn.Conv1d(n_inputs, n_outputs, 1, groups=pw_groups, bias=False)
|
||||
self.bn1_pw = nn.BatchNorm1d(n_outputs)
|
||||
self.relu1_pw = nn.SiLU(inplace=True)
|
||||
self.dropout1 = nn.Dropout(dropout)
|
||||
|
||||
self.conv2_group = nn.Conv1d(n_outputs, n_outputs, kernel_size, stride=1,
|
||||
padding=padding, dilation=dilation,
|
||||
groups=g_out, bias=False)
|
||||
self.chomp2 = Chomp1d(padding) if padding > 0 else nn.Identity()
|
||||
self.bn2_group = nn.BatchNorm1d(n_outputs)
|
||||
self.relu2_group = nn.SiLU(inplace=True)
|
||||
|
||||
self.conv2_pw = nn.Conv1d(n_outputs, n_outputs, 1, bias=False)
|
||||
self.bn2_pw = nn.BatchNorm1d(n_outputs)
|
||||
self.relu2_pw = nn.SiLU(inplace=True)
|
||||
self.dropout2 = nn.Dropout(dropout)
|
||||
|
||||
self.downsample = nn.Sequential(
|
||||
nn.Conv1d(n_inputs, n_outputs, 1, groups=pw_groups, bias=False),
|
||||
nn.BatchNorm1d(n_outputs)
|
||||
) if n_inputs != n_outputs else nn.Identity()
|
||||
|
||||
def forward(self, x):
|
||||
res = self.downsample(x)
|
||||
out = self.conv1_group(x)
|
||||
out = self.chomp1(out)
|
||||
out = self.bn1_group(out)
|
||||
out = self.relu1_group(out)
|
||||
out = self.conv1_pw(out)
|
||||
out = self.bn1_pw(out)
|
||||
out = self.relu1_pw(out)
|
||||
out = self.dropout1(out)
|
||||
out = self.conv2_group(out)
|
||||
out = self.chomp2(out)
|
||||
out = self.bn2_group(out)
|
||||
out = self.relu2_group(out)
|
||||
out = self.conv2_pw(out)
|
||||
out = self.bn2_pw(out)
|
||||
out = self.relu2_pw(out)
|
||||
out = self.dropout2(out)
|
||||
return F.silu(out + res)
|
||||
|
||||
|
||||
class CompactTemporalBlock(nn.Module):
|
||||
def __init__(self, num_inputs, num_channels, kernel_size=3, dropout=0.2,
|
||||
groups_mode='gcd20', input_pw_groups=1):
|
||||
super().__init__()
|
||||
layers = []
|
||||
for i, out_channels in enumerate(num_channels):
|
||||
dilation_size = 2 ** i
|
||||
in_channels = num_inputs if i == 0 else num_channels[i - 1]
|
||||
layers.append(CompactGroupedTemporalBlock(
|
||||
in_channels, out_channels, kernel_size, stride=1,
|
||||
dilation=dilation_size, padding=(kernel_size - 1) * dilation_size,
|
||||
dropout=dropout, groups_mode=groups_mode,
|
||||
pw_groups=input_pw_groups if i == 0 else 1))
|
||||
self.network = nn.Sequential(*layers)
|
||||
|
||||
def forward(self, x):
|
||||
return self.network(x)
|
||||
|
||||
|
||||
# ------------------------------------------------------- Conv2d path (copy of convnet.py)
|
||||
class AsymmetricConvBlock(nn.Module):
|
||||
"""Upstream block with parameterized width stride (upstream: always (1,2))."""
|
||||
|
||||
def __init__(self, in_channels, out_channels, dropout=0.3, stride_w=2):
|
||||
super().__init__()
|
||||
self.block = nn.Sequential(
|
||||
nn.Conv2d(in_channels, out_channels, kernel_size=(1, 3),
|
||||
stride=(1, stride_w), padding=(0, 1)),
|
||||
nn.BatchNorm2d(out_channels),
|
||||
nn.SiLU(inplace=True),
|
||||
nn.Dropout2d(dropout),
|
||||
nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
|
||||
nn.BatchNorm2d(out_channels),
|
||||
nn.SiLU(inplace=True),
|
||||
nn.Dropout2d(dropout),
|
||||
nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
|
||||
nn.BatchNorm2d(out_channels)
|
||||
)
|
||||
self.downsample = nn.Sequential(
|
||||
nn.Conv2d(in_channels, out_channels, kernel_size=1,
|
||||
stride=(1, stride_w), bias=False),
|
||||
nn.BatchNorm2d(out_channels)
|
||||
)
|
||||
self.activation = nn.SiLU(inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
return self.activation(self.block(x) + self.downsample(x))
|
||||
|
||||
|
||||
class ConvBlock1(nn.Module):
|
||||
def __init__(self, in_channels, out_channels, dropout=0.3):
|
||||
super().__init__()
|
||||
self.block = nn.Sequential(
|
||||
nn.Conv2d(in_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
|
||||
nn.BatchNorm2d(out_channels),
|
||||
nn.SiLU(inplace=True),
|
||||
nn.Dropout2d(dropout),
|
||||
nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
|
||||
nn.BatchNorm2d(out_channels),
|
||||
nn.SiLU(inplace=True),
|
||||
nn.Dropout2d(dropout),
|
||||
nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
|
||||
nn.BatchNorm2d(out_channels)
|
||||
)
|
||||
self.downsample = nn.Sequential(
|
||||
nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, bias=False),
|
||||
nn.BatchNorm2d(out_channels)
|
||||
)
|
||||
self.activation = nn.SiLU(inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
return self.activation(self.block(x) + self.downsample(x))
|
||||
|
||||
|
||||
# ----------------------------------------------------- attention (verbatim attention.py)
|
||||
class AxialAttention(nn.Module):
|
||||
def __init__(self, in_planes, out_planes, groups=8, stride=1, bias=False, width=False):
|
||||
assert (in_planes % groups == 0) and (out_planes % groups == 0)
|
||||
super().__init__()
|
||||
self.in_planes = in_planes
|
||||
self.out_planes = out_planes
|
||||
self.groups = groups
|
||||
self.group_planes = out_planes // groups
|
||||
self.stride = stride
|
||||
self.bias = bias
|
||||
self.width = width
|
||||
self.qkv_transform = nn.Conv1d(in_planes, out_planes * 3, kernel_size=1,
|
||||
stride=1, padding=0, bias=False)
|
||||
self.bn_qkv = nn.BatchNorm1d(out_planes * 3)
|
||||
self.bn_similarity = nn.BatchNorm2d(groups)
|
||||
self.bn_output = nn.BatchNorm1d(out_planes)
|
||||
if stride > 1:
|
||||
self.pooling = nn.AvgPool2d(stride, stride=stride)
|
||||
nn.init.normal_(self.qkv_transform.weight.data, 0, math.sqrt(1. / self.in_planes))
|
||||
|
||||
def forward(self, x):
|
||||
if self.width:
|
||||
x = x.permute(0, 2, 1, 3)
|
||||
else:
|
||||
x = x.permute(0, 3, 1, 2)
|
||||
N, W, C, H = x.shape
|
||||
x = x.contiguous().view(N * W, C, H)
|
||||
qkv = self.bn_qkv(self.qkv_transform(x))
|
||||
qkv = qkv.reshape(N * W, 3, self.out_planes, H).permute(1, 0, 2, 3)
|
||||
q, k, v = qkv[0], qkv[1], qkv[2]
|
||||
q = q.reshape(N * W, self.groups, self.group_planes, H)
|
||||
k = k.reshape(N * W, self.groups, self.group_planes, H)
|
||||
v = v.reshape(N * W, self.groups, self.group_planes, H)
|
||||
qk = torch.einsum('bgci, bgcj->bgij', q, k)
|
||||
qk = self.bn_similarity(qk)
|
||||
similarity = F.softmax(qk, dim=-1)
|
||||
sv = torch.einsum('bgij,bgcj->bgci', similarity, v)
|
||||
sv = sv.reshape(N * W, self.out_planes, H)
|
||||
out = self.bn_output(sv)
|
||||
out = out.view(N, W, self.out_planes, H)
|
||||
if self.width:
|
||||
out = out.permute(0, 2, 1, 3)
|
||||
else:
|
||||
out = out.permute(0, 2, 3, 1)
|
||||
if self.stride > 1:
|
||||
out = self.pooling(out)
|
||||
return out
|
||||
|
||||
|
||||
class DualAxialAttention(nn.Module):
|
||||
def __init__(self, in_planes, out_planes, groups=8, stride=1, bias=False):
|
||||
super().__init__()
|
||||
self.width_axis = AxialAttention(in_planes, out_planes, groups, stride, bias, width=True)
|
||||
self.height_axis = AxialAttention(out_planes, out_planes, groups, stride, bias, width=False)
|
||||
|
||||
def forward(self, x):
|
||||
return self.height_axis(self.width_axis(x))
|
||||
|
||||
|
||||
# --------------------------------------------------------------- full model
|
||||
def compute_strides(width: int, n_blocks: int, target: int = 15):
|
||||
"""Halve width while result stays >= target (upstream: 240 -> 4 halvings -> 15)."""
|
||||
strides = []
|
||||
for _ in range(n_blocks):
|
||||
nxt = (width + 1) // 2 # conv k=3 s=2 p=1: out = ceil(in/2)
|
||||
if nxt >= target:
|
||||
strides.append(2)
|
||||
width = nxt
|
||||
else:
|
||||
strides.append(1)
|
||||
return strides, width
|
||||
|
||||
|
||||
class CompactWiFlowPoseModel(nn.Module):
|
||||
"""Parameterized upstream WiFlowPoseModel.
|
||||
|
||||
Upstream config == tcn_channels=[540,440,340,240], conv_channels=[8,16,32,64],
|
||||
attn_groups=8, groups_mode='gcd20' (gcd(c,20)==20 for all upstream channels),
|
||||
input_pw_groups=1 -> identical architecture, 2,225,042 params.
|
||||
"""
|
||||
|
||||
def __init__(self, tcn_channels, conv_channels, attn_groups,
|
||||
groups_mode='gcd20', input_pw_groups=1, dropout=0.3,
|
||||
num_subcarriers=540, num_keypoints=15):
|
||||
super().__init__()
|
||||
self.tcn = CompactTemporalBlock(
|
||||
num_inputs=num_subcarriers, num_channels=tcn_channels, kernel_size=3,
|
||||
dropout=dropout, groups_mode=groups_mode, input_pw_groups=input_pw_groups)
|
||||
|
||||
self.up = ConvBlock1(1, conv_channels[0])
|
||||
|
||||
strides, self.final_width = compute_strides(
|
||||
tcn_channels[-1], len(conv_channels), target=num_keypoints)
|
||||
self.conv_strides = strides
|
||||
self.residual_blocks = nn.ModuleList()
|
||||
in_channels = conv_channels[0]
|
||||
for out_channels, s in zip(conv_channels, strides):
|
||||
self.residual_blocks.append(
|
||||
AsymmetricConvBlock(in_channels, out_channels, stride_w=s))
|
||||
in_channels = out_channels
|
||||
|
||||
c_last = conv_channels[-1]
|
||||
self.attention = DualAxialAttention(c_last, c_last, groups=attn_groups)
|
||||
|
||||
c_mid = max(c_last // 2, 4)
|
||||
self.decoder = nn.Sequential(
|
||||
nn.Conv2d(c_last, c_mid, kernel_size=3, padding=1),
|
||||
nn.BatchNorm2d(c_mid),
|
||||
nn.SiLU(inplace=True),
|
||||
nn.Conv2d(c_mid, 2, kernel_size=1),
|
||||
nn.BatchNorm2d(2),
|
||||
nn.SiLU(inplace=True)
|
||||
)
|
||||
self.avg_pool = nn.AdaptiveAvgPool2d((num_keypoints, 1))
|
||||
self._initialize_weights()
|
||||
|
||||
def _initialize_weights(self):
|
||||
for m in self.modules():
|
||||
if isinstance(m, nn.Conv1d):
|
||||
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
|
||||
if m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, (nn.BatchNorm1d, nn.LayerNorm)):
|
||||
nn.init.constant_(m.weight, 1)
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.Linear):
|
||||
nn.init.xavier_normal_(m.weight)
|
||||
if m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
|
||||
def forward(self, x):
|
||||
# [B, 540, 20]
|
||||
x = self.tcn(x) # [B, C_tcn, 20]
|
||||
x = x.transpose(1, 2).unsqueeze(1) # [B, 1, 20, C_tcn]
|
||||
x = self.up(x)
|
||||
for block in self.residual_blocks:
|
||||
x = block(x) # [B, C_conv, 20, W']
|
||||
x = x.permute(0, 1, 3, 2) # [B, C_conv, W', 20]
|
||||
x = self.attention(x)
|
||||
x = self.decoder(x) # [B, 2, W', 20]
|
||||
x = self.avg_pool(x).squeeze(-1) # [B, 2, 15]
|
||||
return x.transpose(1, 2) # [B, 15, 2]
|
||||
|
||||
|
||||
def describe(model: 'CompactWiFlowPoseModel'):
|
||||
params = sum(p.numel() for p in model.parameters())
|
||||
tcn_g = [blk.groups for blk in model.tcn.network]
|
||||
return {'params': params, 'tcn_groups_per_block': tcn_g,
|
||||
'conv_strides': model.conv_strides, 'final_width': model.final_width}
|
||||
@@ -1,278 +0,0 @@
|
||||
"""WiFlow-STD compact-variant efficiency sweep (ADR-152) — sequential overnight runner.
|
||||
|
||||
Trains compact variants of the upstream WiFlow-STD architecture on the same
|
||||
data/split as the full-size reference retraining (seed 42, file-level 70/15/15,
|
||||
upstream dataset.py) and evaluates PCK@10..50 + MPJPE on the full test split and
|
||||
the corruption-free test subset (file indices < 487).
|
||||
|
||||
Training mirrors upstream run.py/train.py defaults except:
|
||||
- fp32 only (no fp16 autocast / GradScaler — avoids the BN-poisoning trap
|
||||
documented in RESULTS.md defect 5; data on disk is already cleaned).
|
||||
- batch 64 (kept modest: another GPU job may share the 16 GB card tonight).
|
||||
- scheduler + early stopping keyed on val MPJPE (upstream early-stops on val MPE
|
||||
with patience 5; same here).
|
||||
|
||||
Usage:
|
||||
venv/bin/python sweep/run_sweep.py --dry-run # param counts only
|
||||
nohup venv/bin/python sweep/run_sweep.py > sweep/sweep.log 2>&1 &
|
||||
|
||||
Idempotent: variants already present in sweep/results.jsonl are skipped.
|
||||
|
||||
NOTE: deployed to ruvultra (~/wiflow-std-bench/sweep) as a standalone file, so
|
||||
it deliberately inlines its helpers. The reference implementations (upstream
|
||||
import shim, >1GB np.load mmap patch, key-remap loader, canonical evaluate
|
||||
loop) live in benchmarks/wiflow-std/_bench_common.py — keep copies in sync.
|
||||
"""
|
||||
import argparse
|
||||
import copy
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import sys
|
||||
import time
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch.utils.data import DataLoader, Subset
|
||||
|
||||
# csi_windows.npy is ~13 GB; mmap large arrays instead of eagerly loading
|
||||
# ~15 GB into RAM (same patch as _bench_common._np_load_mmap).
|
||||
_np_load = np.load
|
||||
|
||||
|
||||
def _np_load_mmap(path, *a, **kw):
|
||||
if (isinstance(path, str) and path.endswith('.npy')
|
||||
and os.path.getsize(path) > 1 << 30 and 'mmap_mode' not in kw):
|
||||
kw['mmap_mode'] = 'r'
|
||||
return _np_load(path, *a, **kw)
|
||||
|
||||
|
||||
np.load = _np_load_mmap
|
||||
|
||||
BENCH = os.path.expanduser('~/wiflow-std-bench')
|
||||
SWEEP = os.path.join(BENCH, 'sweep')
|
||||
sys.path.insert(0, os.path.join(BENCH, 'upstream'))
|
||||
sys.path.insert(0, SWEEP)
|
||||
|
||||
from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders # noqa: E402
|
||||
from losses.pose_loss import PoseLoss # noqa: E402
|
||||
from utils.metrics import calculate_pck, calculate_mpjpe # noqa: E402
|
||||
from model_compact import CompactWiFlowPoseModel, describe # noqa: E402
|
||||
|
||||
VARIANTS = [
|
||||
# name, tcn_channels, conv_channels, attn_groups, groups_mode, input_pw_groups
|
||||
dict(name='half', tcn=[270, 220, 170, 120], conv=[4, 8, 16, 32], attn_groups=4,
|
||||
groups_mode='gcd20', input_pw_groups=1),
|
||||
dict(name='quarter', tcn=[135, 110, 85, 60], conv=[2, 4, 8, 16], attn_groups=2,
|
||||
groups_mode='gcd20', input_pw_groups=1),
|
||||
dict(name='tiny', tcn=[68, 56, 44, 32], conv=[2, 4, 8, 16], attn_groups=2,
|
||||
groups_mode='depthwise', input_pw_groups=4),
|
||||
]
|
||||
|
||||
BATCH = 64
|
||||
EPOCHS = 50
|
||||
PATIENCE = 5
|
||||
LR = 1e-4
|
||||
WEIGHT_DECAY = 5e-5
|
||||
SEED = 42
|
||||
CORRUPT_FILE_START = 487 # files 487-499 were zero-filled by clean_nan.py
|
||||
|
||||
|
||||
def set_seed(seed=SEED):
|
||||
random.seed(seed)
|
||||
np.random.seed(seed)
|
||||
torch.manual_seed(seed)
|
||||
torch.cuda.manual_seed_all(seed)
|
||||
torch.backends.cudnn.deterministic = True
|
||||
torch.backends.cudnn.benchmark = False
|
||||
|
||||
|
||||
def build_model(v, dropout=0.5):
|
||||
return CompactWiFlowPoseModel(
|
||||
tcn_channels=v['tcn'], conv_channels=v['conv'], attn_groups=v['attn_groups'],
|
||||
groups_mode=v['groups_mode'], input_pw_groups=v['input_pw_groups'],
|
||||
dropout=dropout)
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def evaluate(model, loader, device):
|
||||
model.eval()
|
||||
totals = {t: 0.0 for t in (0.1, 0.2, 0.3, 0.4, 0.5)}
|
||||
total_mpe, n = 0.0, 0
|
||||
for bx, by in loader:
|
||||
bx, by = bx.to(device), by.to(device)
|
||||
out = model(bx)
|
||||
bs = by.size(0)
|
||||
total_mpe += calculate_mpjpe(out, by) * bs
|
||||
pck = calculate_pck(out, by, thresholds=list(totals))
|
||||
for t in totals:
|
||||
totals[t] += pck[t] * bs
|
||||
n += bs
|
||||
return {'samples': n, 'mpjpe': total_mpe / n,
|
||||
**{f'pck@{int(t * 100)}': totals[t] / n for t in totals}}
|
||||
|
||||
|
||||
def train_variant(v, dataset, device):
|
||||
set_seed(SEED)
|
||||
train_loader, val_loader, test_loader = create_preprocessed_train_val_test_loaders(
|
||||
dataset=dataset, batch_size=BATCH, num_workers=2, random_seed=SEED)
|
||||
|
||||
set_seed(SEED) # re-seed after split so init is split-independent
|
||||
model = build_model(v).to(device)
|
||||
info = describe(model)
|
||||
print(f"[{v['name']}] params={info['params']:,} tcn_groups={info['tcn_groups_per_block']} "
|
||||
f"conv_strides={info['conv_strides']} final_width={info['final_width']}", flush=True)
|
||||
|
||||
criterion = PoseLoss(position_weight=1.0, bone_weight=0.2, loss_type='smooth_l1')
|
||||
optimizer = torch.optim.AdamW(model.parameters(), lr=LR, weight_decay=WEIGHT_DECAY,
|
||||
betas=(0.9, 0.999))
|
||||
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(
|
||||
optimizer, mode='min', factor=0.5, patience=3, min_lr=LR / 1000,
|
||||
cooldown=1, threshold=1e-4)
|
||||
|
||||
best_val_mpe = float('inf')
|
||||
best_val_pck20 = 0.0
|
||||
best_epoch = 0
|
||||
best_state = None
|
||||
patience_counter = 0
|
||||
t0 = time.time()
|
||||
error = None
|
||||
epochs_run = 0
|
||||
|
||||
for epoch in range(1, EPOCHS + 1):
|
||||
model.train()
|
||||
ep_loss, nb = 0.0, 0
|
||||
te = time.time()
|
||||
for i, (bx, by) in enumerate(train_loader):
|
||||
bx = bx.to(device, non_blocking=True)
|
||||
by = by.to(device, non_blocking=True)
|
||||
optimizer.zero_grad(set_to_none=True)
|
||||
out = model(bx)
|
||||
loss, _parts = criterion(out, by)
|
||||
if not torch.isfinite(loss):
|
||||
error = f'non-finite loss at epoch {epoch} step {i}'
|
||||
break
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
ep_loss += loss.item()
|
||||
nb += 1
|
||||
if epoch == 1 and i % 500 == 0:
|
||||
print(f"[{v['name']}] e1 step {i}/{len(train_loader)} loss={loss.item():.5f}",
|
||||
flush=True)
|
||||
if error:
|
||||
break
|
||||
epochs_run = epoch
|
||||
|
||||
val = evaluate(model, val_loader, device)
|
||||
scheduler.step(val['mpjpe'])
|
||||
lr_now = optimizer.param_groups[0]['lr']
|
||||
print(f"[{v['name']}] epoch {epoch}/{EPOCHS} train_loss={ep_loss / max(nb, 1):.5f} "
|
||||
f"val_mpjpe={val['mpjpe']:.5f} val_pck20={val['pck@20'] * 100:.2f}% "
|
||||
f"lr={lr_now:.2e} ({time.time() - te:.0f}s)", flush=True)
|
||||
|
||||
if val['mpjpe'] < best_val_mpe:
|
||||
best_val_mpe = val['mpjpe']
|
||||
best_val_pck20 = val['pck@20']
|
||||
best_epoch = epoch
|
||||
best_state = copy.deepcopy(model.state_dict())
|
||||
patience_counter = 0
|
||||
else:
|
||||
patience_counter += 1
|
||||
if patience_counter >= PATIENCE:
|
||||
print(f"[{v['name']}] early stop at epoch {epoch} (best {best_epoch})", flush=True)
|
||||
break
|
||||
|
||||
train_seconds = time.time() - t0
|
||||
result = {
|
||||
'variant': v['name'], 'params': info['params'],
|
||||
'tcn_channels': v['tcn'], 'conv_channels': v['conv'],
|
||||
'attn_groups': v['attn_groups'], 'groups_mode': v['groups_mode'],
|
||||
'input_pw_groups': v['input_pw_groups'],
|
||||
'tcn_groups_per_block': info['tcn_groups_per_block'],
|
||||
'conv_strides': info['conv_strides'], 'final_width': info['final_width'],
|
||||
'batch_size': BATCH, 'max_epochs': EPOCHS, 'patience': PATIENCE,
|
||||
'lr': LR, 'weight_decay': WEIGHT_DECAY, 'seed': SEED, 'precision': 'fp32',
|
||||
'epochs_run': epochs_run, 'best_epoch': best_epoch,
|
||||
'best_val_mpjpe': best_val_mpe if best_state else None,
|
||||
'best_val_pck20': best_val_pck20 if best_state else None,
|
||||
'train_seconds': round(train_seconds, 1),
|
||||
'torch': torch.__version__, 'error': error,
|
||||
'finished_utc': time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime()),
|
||||
}
|
||||
|
||||
if best_state is not None:
|
||||
ckpt = os.path.join(SWEEP, f"{v['name']}_best.pth")
|
||||
torch.save(best_state, ckpt)
|
||||
result['checkpoint'] = ckpt
|
||||
model.load_state_dict(best_state)
|
||||
|
||||
eval_loader = DataLoader(test_loader.dataset, batch_size=256, shuffle=False,
|
||||
num_workers=2)
|
||||
result['test_full'] = evaluate(model, eval_loader, device)
|
||||
|
||||
w2f = dataset.window_to_file
|
||||
clean_idx = [i for i in test_loader.dataset.indices if w2f[i] < CORRUPT_FILE_START]
|
||||
clean_loader = DataLoader(Subset(dataset, clean_idx), batch_size=256,
|
||||
shuffle=False, num_workers=2)
|
||||
result['test_clean'] = evaluate(model, clean_loader, device)
|
||||
print(f"[{v['name']}] TEST clean: pck20={result['test_clean']['pck@20'] * 100:.2f}% "
|
||||
f"mpjpe={result['test_clean']['mpjpe']:.5f} | full: "
|
||||
f"pck20={result['test_full']['pck@20'] * 100:.2f}%", flush=True)
|
||||
return result
|
||||
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument('--dry-run', action='store_true', help='print param counts and exit')
|
||||
args = ap.parse_args()
|
||||
|
||||
if args.dry_run:
|
||||
for v in VARIANTS:
|
||||
m = build_model(v)
|
||||
info = describe(m)
|
||||
x = torch.randn(2, 540, 20)
|
||||
m.eval()
|
||||
y = m(x)
|
||||
print(f"{v['name']:8s} params={info['params']:>9,} "
|
||||
f"tcn={v['tcn']} conv={v['conv']} attn_g={v['attn_groups']} "
|
||||
f"mode={v['groups_mode']} pw_g={v['input_pw_groups']} "
|
||||
f"tcn_groups={info['tcn_groups_per_block']} strides={info['conv_strides']} "
|
||||
f"W'={info['final_width']} out={tuple(y.shape)}")
|
||||
return
|
||||
|
||||
results_path = os.path.join(SWEEP, 'results.jsonl')
|
||||
done = set()
|
||||
if os.path.exists(results_path):
|
||||
with open(results_path) as f:
|
||||
for line in f:
|
||||
try:
|
||||
done.add(json.loads(line)['variant'])
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
device = torch.device('cuda')
|
||||
print(f"torch {torch.__version__} on {torch.cuda.get_device_name(0)}", flush=True)
|
||||
data_dir = os.path.join(BENCH, 'preprocessed_csi_data')
|
||||
dataset = PreprocessedCSIKeypointsDataset(data_dir=data_dir, keypoint_scale=1000.0,
|
||||
enable_temporal_clean=True)
|
||||
|
||||
for v in VARIANTS:
|
||||
if v['name'] in done:
|
||||
print(f"[{v['name']}] already in results.jsonl — skipping", flush=True)
|
||||
continue
|
||||
print(f"\n===== variant: {v['name']} =====", flush=True)
|
||||
try:
|
||||
result = train_variant(v, dataset, device)
|
||||
except Exception as e: # record and move on to next variant
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
result = {'variant': v['name'], 'error': repr(e),
|
||||
'finished_utc': time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())}
|
||||
with open(results_path, 'a') as f:
|
||||
f.write(json.dumps(result) + '\n')
|
||||
f.flush()
|
||||
print('\nSWEEP COMPLETE', flush=True)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Binary file not shown.
@@ -1,772 +0,0 @@
|
||||
{
|
||||
"torch": {
|
||||
"env": {
|
||||
"torch": "2.12.0+cpu",
|
||||
"platform": "Windows-11-10.0.26200-SP0",
|
||||
"processor": "Intel64 Family 6 Model 197 Stepping 2, GenuineIntel",
|
||||
"num_threads": 16,
|
||||
"checkpoint": "results\\retrained_best_pose_model.pth",
|
||||
"params": 2225042
|
||||
},
|
||||
"variants": {
|
||||
"fp32": {
|
||||
"file": "retrained_fp32_resaved.pth",
|
||||
"size_bytes": 9068948,
|
||||
"size_mb": 9.068948,
|
||||
"latency_batch1": {
|
||||
"batch_size": 1,
|
||||
"runs": 100,
|
||||
"median_ms_per_batch": 24.903650000851485,
|
||||
"median_ms_per_window": 24.903650000851485,
|
||||
"windows_per_second": 40.15475642991324
|
||||
},
|
||||
"latency_batch64": {
|
||||
"batch_size": 64,
|
||||
"runs": 30,
|
||||
"median_ms_per_batch": 184.02919999789447,
|
||||
"median_ms_per_window": 2.875456249967101,
|
||||
"windows_per_second": 347.77089723115813
|
||||
},
|
||||
"accuracy": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9668200004577636,
|
||||
"pck@50": 0.9915333324432373,
|
||||
"mpjpe": 0.00936222033649683,
|
||||
"wall_seconds": 37.85407733917236
|
||||
}
|
||||
},
|
||||
"fp16": {
|
||||
"file": "retrained_fp16.pth",
|
||||
"size_bytes": 4580332,
|
||||
"size_mb": 4.580332,
|
||||
"latency_batch1": {
|
||||
"batch_size": 1,
|
||||
"runs": 100,
|
||||
"median_ms_per_batch": 23.936699999467237,
|
||||
"median_ms_per_window": 23.936699999467237,
|
||||
"windows_per_second": 41.776853117691964
|
||||
},
|
||||
"latency_batch64": {
|
||||
"batch_size": 64,
|
||||
"runs": 30,
|
||||
"median_ms_per_batch": 102.32584999903338,
|
||||
"median_ms_per_window": 1.5988414062348966,
|
||||
"windows_per_second": 625.4529036465817
|
||||
},
|
||||
"accuracy": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.966773332977295,
|
||||
"pck@50": 0.9915066654205322,
|
||||
"mpjpe": 0.009460017587244511,
|
||||
"wall_seconds": 21.632277250289917
|
||||
}
|
||||
},
|
||||
"int8_dynamic": {
|
||||
"file": "retrained_int8_dynamic.pth",
|
||||
"size_bytes": 9068948,
|
||||
"size_mb": 9.068948,
|
||||
"latency_batch1": {
|
||||
"batch_size": 1,
|
||||
"runs": 100,
|
||||
"median_ms_per_batch": 18.105350000041653,
|
||||
"median_ms_per_window": 18.105350000041653,
|
||||
"windows_per_second": 55.23229321707117
|
||||
},
|
||||
"latency_batch64": {
|
||||
"batch_size": 64,
|
||||
"runs": 30,
|
||||
"median_ms_per_batch": 168.77549999844632,
|
||||
"median_ms_per_window": 2.6371171874757238,
|
||||
"windows_per_second": 379.20195763359703
|
||||
},
|
||||
"accuracy": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9668200004577636,
|
||||
"pck@50": 0.9915333324432373,
|
||||
"mpjpe": 0.00936222033649683,
|
||||
"wall_seconds": 45.35376596450806
|
||||
}
|
||||
}
|
||||
},
|
||||
"int8_dynamic_quant_report": {
|
||||
"eligible_module_counts": {
|
||||
"nn.Linear": 0,
|
||||
"nn.Conv1d": 21,
|
||||
"nn.Conv2d": 22
|
||||
},
|
||||
"modules_actually_quantized": [],
|
||||
"n_modules_quantized": 0,
|
||||
"params_total": 2225042,
|
||||
"params_quantized": 0,
|
||||
"params_quantized_fraction": 0.0
|
||||
},
|
||||
"accuracy_subset": {
|
||||
"description": "seed-42 file-level 70/15/15 test split, corrupted windows (files 487-499) excluded, seed-42 random subset",
|
||||
"subset_size": 10000,
|
||||
"clean_test_total": 10000
|
||||
}
|
||||
},
|
||||
"onnx": {
|
||||
"env": {
|
||||
"torch": "2.12.0+cpu",
|
||||
"onnxruntime": "1.26.0",
|
||||
"platform": "Windows-11-10.0.26200-SP0"
|
||||
},
|
||||
"export": {
|
||||
"mode": "dynamic-batch",
|
||||
"exporter": "torchscript",
|
||||
"file": "retrained_fp32_dynamic.onnx",
|
||||
"size_mb": 8.971781
|
||||
},
|
||||
"parity": {
|
||||
"fixture": "results/parity_fixture.npz (batch 2, seed 42)",
|
||||
"max_abs_diff_vs_stored_fixture": 2.384185791015625e-07,
|
||||
"max_abs_diff_vs_torch_now": 2.384185791015625e-07,
|
||||
"pass_lt_1e-4": true
|
||||
},
|
||||
"latency": {
|
||||
"batch1": {
|
||||
"batch_size": 1,
|
||||
"runs": 100,
|
||||
"median_ms_per_batch": 2.5410999987798277,
|
||||
"median_ms_per_window": 2.5410999987798277,
|
||||
"windows_per_second": 393.5303610563043
|
||||
},
|
||||
"batch64": {
|
||||
"batch_size": 64,
|
||||
"runs": 30,
|
||||
"median_ms_per_batch": 181.95204999938142,
|
||||
"median_ms_per_window": 2.8430007812403346,
|
||||
"windows_per_second": 351.7410218803118
|
||||
}
|
||||
},
|
||||
"ort_int8_dynamic_supplementary": {
|
||||
"file": "retrained_int8_ort_dynamic.onnx",
|
||||
"size_mb": 2.438794,
|
||||
"runs": true,
|
||||
"max_abs_diff_vs_fp32_fixture": 0.00827130675315857
|
||||
}
|
||||
},
|
||||
"onnx_accuracy": {
|
||||
"onnx_fp32": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9668200004577636,
|
||||
"pck@50": 0.9915333324432373,
|
||||
"mpjpe": 0.00936222568154335,
|
||||
"wall_seconds": 22.34790802001953
|
||||
},
|
||||
"onnx_int8_ort_dynamic": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.965240001964569,
|
||||
"pck@50": 0.9915466655731201,
|
||||
"mpjpe": 0.01108054072111845,
|
||||
"wall_seconds": 55.742953062057495
|
||||
}
|
||||
},
|
||||
"latency_controlled_rerun": {
|
||||
"note": "3 interleaved repetitions per variant, median ms/window; quiet box",
|
||||
"fp32": {
|
||||
"batch1_ms_per_window_median": 10.969150001983508,
|
||||
"batch1_reps": [
|
||||
10.969150001983508,
|
||||
12.646450000829645,
|
||||
10.49820000116597
|
||||
],
|
||||
"batch64_ms_per_window_median": 2.2734187500077496,
|
||||
"batch64_reps": [
|
||||
2.377234374989712,
|
||||
2.124126562478068,
|
||||
2.2734187500077496
|
||||
]
|
||||
},
|
||||
"fp16": {
|
||||
"batch1_ms_per_window_median": 24.313550000442774,
|
||||
"batch1_reps": [
|
||||
25.1078499986761,
|
||||
21.856999999727122,
|
||||
24.313550000442774
|
||||
],
|
||||
"batch64_ms_per_window_median": 2.414695312495496,
|
||||
"batch64_reps": [
|
||||
2.5705156249955508,
|
||||
1.7137437499741281,
|
||||
2.414695312495496
|
||||
]
|
||||
},
|
||||
"int8_dynamic": {
|
||||
"batch1_ms_per_window_median": 15.627150000000256,
|
||||
"batch1_reps": [
|
||||
17.67525000104797,
|
||||
14.627999998992891,
|
||||
15.627150000000256
|
||||
],
|
||||
"batch64_ms_per_window_median": 2.0546906250160646,
|
||||
"batch64_reps": [
|
||||
2.0546906250160646,
|
||||
2.03407343752815,
|
||||
2.9325796875241394
|
||||
]
|
||||
},
|
||||
"onnx_fp32": {
|
||||
"batch1_ms_per_window_median": 3.186650001225644,
|
||||
"batch1_reps": [
|
||||
2.7332500012562377,
|
||||
3.1995500012271805,
|
||||
3.186650001225644
|
||||
],
|
||||
"batch64_ms_per_window_median": 1.9893374999924163,
|
||||
"batch64_reps": [
|
||||
1.5590843750032946,
|
||||
1.9893374999924163,
|
||||
2.2144343749914697
|
||||
]
|
||||
},
|
||||
"onnx_int8_ort_dynamic": {
|
||||
"batch1_ms_per_window_median": 6.50984999811044,
|
||||
"batch1_reps": [
|
||||
6.50984999811044,
|
||||
6.455249998907675,
|
||||
6.789299999581999
|
||||
],
|
||||
"batch64_ms_per_window_median": 5.770093750015803,
|
||||
"batch64_reps": [
|
||||
5.770093750015803,
|
||||
3.912374999970325,
|
||||
7.8067296875019565
|
||||
]
|
||||
}
|
||||
},
|
||||
"onnx_static_ptq": {
|
||||
"env": {
|
||||
"onnxruntime": "1.26.0",
|
||||
"torch": "2.12.0+cpu",
|
||||
"platform": "Windows-11-10.0.26200-SP0",
|
||||
"source_model": "retrained_fp32_dynamic.onnx",
|
||||
"preprocessed_model": {
|
||||
"file": "retrained_fp32_preproc.onnx",
|
||||
"size_mb": 8.981529
|
||||
}
|
||||
},
|
||||
"variants": {
|
||||
"minmax_all": {
|
||||
"file": "retrained_int8_static_minmax_all.onnx",
|
||||
"size_bytes": 2604286,
|
||||
"size_mb": 2.604286,
|
||||
"calibration": {
|
||||
"method": "minmax",
|
||||
"windows": 1000,
|
||||
"percentile": null,
|
||||
"seconds": 5.052440166473389
|
||||
},
|
||||
"scope": "all",
|
||||
"per_channel": true,
|
||||
"activation_type": "QInt8",
|
||||
"weight_type": "QInt8",
|
||||
"node_counts": {
|
||||
"Add": 9,
|
||||
"AveragePool": 1,
|
||||
"BatchNormalization": 12,
|
||||
"Concat": 10,
|
||||
"Conv": 43,
|
||||
"DequantizeLinear": 283,
|
||||
"Einsum": 4,
|
||||
"Gather": 16,
|
||||
"Mul": 39,
|
||||
"QuantizeLinear": 181,
|
||||
"Reshape": 14,
|
||||
"Shape": 2,
|
||||
"Sigmoid": 37,
|
||||
"Slice": 8,
|
||||
"Softmax": 2,
|
||||
"Squeeze": 1,
|
||||
"Transpose": 7,
|
||||
"Unsqueeze": 11
|
||||
},
|
||||
"max_abs_diff_vs_fp32_fixture": 0.015945255756378174,
|
||||
"accuracy": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9545266661643982,
|
||||
"pck@50": 0.9913666645050049,
|
||||
"mpjpe": 0.014860070134699345,
|
||||
"wall_seconds": 43.455235958099365
|
||||
}
|
||||
},
|
||||
"minmax_conv": {
|
||||
"file": "retrained_int8_static_minmax_conv.onnx",
|
||||
"size_bytes": 2527421,
|
||||
"size_mb": 2.527421,
|
||||
"calibration": {
|
||||
"method": "minmax",
|
||||
"windows": 1000,
|
||||
"percentile": null,
|
||||
"seconds": 4.380746126174927
|
||||
},
|
||||
"scope": "conv",
|
||||
"per_channel": true,
|
||||
"activation_type": "QInt8",
|
||||
"weight_type": "QInt8",
|
||||
"node_counts": {
|
||||
"Add": 9,
|
||||
"AveragePool": 1,
|
||||
"BatchNormalization": 12,
|
||||
"Concat": 10,
|
||||
"Conv": 43,
|
||||
"DequantizeLinear": 156,
|
||||
"Einsum": 4,
|
||||
"Gather": 16,
|
||||
"Mul": 39,
|
||||
"QuantizeLinear": 78,
|
||||
"Reshape": 14,
|
||||
"Shape": 2,
|
||||
"Sigmoid": 37,
|
||||
"Slice": 8,
|
||||
"Softmax": 2,
|
||||
"Squeeze": 1,
|
||||
"Transpose": 7,
|
||||
"Unsqueeze": 11
|
||||
},
|
||||
"max_abs_diff_vs_fp32_fixture": 0.010693132877349854,
|
||||
"accuracy": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9663399996757507,
|
||||
"pck@50": 0.9918666641235352,
|
||||
"mpjpe": 0.01084446222037077,
|
||||
"wall_seconds": 35.937947034835815
|
||||
}
|
||||
},
|
||||
"entropy_all": {
|
||||
"file": "retrained_int8_static_entropy_all.onnx",
|
||||
"size_bytes": 2604268,
|
||||
"size_mb": 2.604268,
|
||||
"calibration": {
|
||||
"method": "entropy",
|
||||
"windows": 512,
|
||||
"percentile": null,
|
||||
"seconds": 23.835066318511963
|
||||
},
|
||||
"scope": "all",
|
||||
"per_channel": true,
|
||||
"activation_type": "QInt8",
|
||||
"weight_type": "QInt8",
|
||||
"node_counts": {
|
||||
"Add": 9,
|
||||
"AveragePool": 1,
|
||||
"BatchNormalization": 12,
|
||||
"Concat": 10,
|
||||
"Conv": 43,
|
||||
"DequantizeLinear": 283,
|
||||
"Einsum": 4,
|
||||
"Gather": 16,
|
||||
"Mul": 39,
|
||||
"QuantizeLinear": 181,
|
||||
"Reshape": 14,
|
||||
"Shape": 2,
|
||||
"Sigmoid": 37,
|
||||
"Slice": 8,
|
||||
"Softmax": 2,
|
||||
"Squeeze": 1,
|
||||
"Transpose": 7,
|
||||
"Unsqueeze": 11
|
||||
},
|
||||
"max_abs_diff_vs_fp32_fixture": 0.015280365943908691,
|
||||
"accuracy": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9530466662406921,
|
||||
"pck@50": 0.9912600006103516,
|
||||
"mpjpe": 0.015098519864678382,
|
||||
"wall_seconds": 51.514281034469604
|
||||
}
|
||||
},
|
||||
"entropy_conv": {
|
||||
"file": "retrained_int8_static_entropy_conv.onnx",
|
||||
"size_bytes": 2527403,
|
||||
"size_mb": 2.527403,
|
||||
"calibration": {
|
||||
"method": "entropy",
|
||||
"windows": 512,
|
||||
"percentile": null,
|
||||
"seconds": 9.634419918060303
|
||||
},
|
||||
"scope": "conv",
|
||||
"per_channel": true,
|
||||
"activation_type": "QInt8",
|
||||
"weight_type": "QInt8",
|
||||
"node_counts": {
|
||||
"Add": 9,
|
||||
"AveragePool": 1,
|
||||
"BatchNormalization": 12,
|
||||
"Concat": 10,
|
||||
"Conv": 43,
|
||||
"DequantizeLinear": 156,
|
||||
"Einsum": 4,
|
||||
"Gather": 16,
|
||||
"Mul": 39,
|
||||
"QuantizeLinear": 78,
|
||||
"Reshape": 14,
|
||||
"Shape": 2,
|
||||
"Sigmoid": 37,
|
||||
"Slice": 8,
|
||||
"Softmax": 2,
|
||||
"Squeeze": 1,
|
||||
"Transpose": 7,
|
||||
"Unsqueeze": 11
|
||||
},
|
||||
"max_abs_diff_vs_fp32_fixture": 0.012535125017166138,
|
||||
"accuracy": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9659599989891052,
|
||||
"pck@50": 0.9918666648864746,
|
||||
"mpjpe": 0.010778637571632861,
|
||||
"wall_seconds": 41.01180171966553
|
||||
}
|
||||
},
|
||||
"percentile_all": {
|
||||
"file": "retrained_int8_static_percentile_all.onnx",
|
||||
"size_bytes": 2604052,
|
||||
"size_mb": 2.604052,
|
||||
"calibration": {
|
||||
"method": "percentile",
|
||||
"windows": 512,
|
||||
"percentile": 99.99,
|
||||
"seconds": 20.221954584121704
|
||||
},
|
||||
"scope": "all",
|
||||
"per_channel": true,
|
||||
"activation_type": "QInt8",
|
||||
"weight_type": "QInt8",
|
||||
"node_counts": {
|
||||
"Add": 9,
|
||||
"AveragePool": 1,
|
||||
"BatchNormalization": 12,
|
||||
"Concat": 10,
|
||||
"Conv": 43,
|
||||
"DequantizeLinear": 283,
|
||||
"Einsum": 4,
|
||||
"Gather": 16,
|
||||
"Mul": 39,
|
||||
"QuantizeLinear": 181,
|
||||
"Reshape": 14,
|
||||
"Shape": 2,
|
||||
"Sigmoid": 37,
|
||||
"Slice": 8,
|
||||
"Softmax": 2,
|
||||
"Squeeze": 1,
|
||||
"Transpose": 7,
|
||||
"Unsqueeze": 11
|
||||
},
|
||||
"max_abs_diff_vs_fp32_fixture": 0.017689883708953857,
|
||||
"accuracy": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9639333323478698,
|
||||
"pck@50": 0.9916799991607667,
|
||||
"mpjpe": 0.012176512064039708,
|
||||
"wall_seconds": 49.365190744400024
|
||||
}
|
||||
},
|
||||
"percentile_conv": {
|
||||
"file": "retrained_int8_static_percentile_conv.onnx",
|
||||
"size_bytes": 2527241,
|
||||
"size_mb": 2.527241,
|
||||
"calibration": {
|
||||
"method": "percentile",
|
||||
"windows": 512,
|
||||
"percentile": 99.99,
|
||||
"seconds": 8.223475694656372
|
||||
},
|
||||
"scope": "conv",
|
||||
"per_channel": true,
|
||||
"activation_type": "QInt8",
|
||||
"weight_type": "QInt8",
|
||||
"node_counts": {
|
||||
"Add": 9,
|
||||
"AveragePool": 1,
|
||||
"BatchNormalization": 12,
|
||||
"Concat": 10,
|
||||
"Conv": 43,
|
||||
"DequantizeLinear": 156,
|
||||
"Einsum": 4,
|
||||
"Gather": 16,
|
||||
"Mul": 39,
|
||||
"QuantizeLinear": 78,
|
||||
"Reshape": 14,
|
||||
"Shape": 2,
|
||||
"Sigmoid": 37,
|
||||
"Slice": 8,
|
||||
"Softmax": 2,
|
||||
"Squeeze": 1,
|
||||
"Transpose": 7,
|
||||
"Unsqueeze": 11
|
||||
},
|
||||
"max_abs_diff_vs_fp32_fixture": 0.014725983142852783,
|
||||
"accuracy": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9660599988937378,
|
||||
"pck@50": 0.9916066654205322,
|
||||
"mpjpe": 0.010310938355326652,
|
||||
"wall_seconds": 36.89548587799072
|
||||
}
|
||||
}
|
||||
},
|
||||
"latency": {
|
||||
"note": "3 interleaved repetitions per variant, median ms/window; onnx_fp32 / onnx_int8_ort_dynamic are same-session references",
|
||||
"onnx_fp32": {
|
||||
"batch1_reps": [
|
||||
4.5327999996516155,
|
||||
2.535649999117595,
|
||||
2.167549997466267
|
||||
],
|
||||
"batch64_reps": [
|
||||
1.9354515624740998,
|
||||
2.4948054687854437,
|
||||
1.9334703125082342
|
||||
],
|
||||
"batch1_ms_per_window_median": 2.535649999117595,
|
||||
"batch64_ms_per_window_median": 1.9354515624740998
|
||||
},
|
||||
"onnx_int8_ort_dynamic": {
|
||||
"batch1_reps": [
|
||||
5.698599999959697,
|
||||
5.721350000385428,
|
||||
4.805099997611251
|
||||
],
|
||||
"batch64_reps": [
|
||||
4.096601562508795,
|
||||
4.857628124995017,
|
||||
4.583800000006022
|
||||
],
|
||||
"batch1_ms_per_window_median": 5.698599999959697,
|
||||
"batch64_ms_per_window_median": 4.583800000006022
|
||||
},
|
||||
"entropy_all": {
|
||||
"batch1_reps": [
|
||||
6.444149999879301,
|
||||
5.038299999796436,
|
||||
5.713200000172947
|
||||
],
|
||||
"batch64_reps": [
|
||||
4.149468750028973,
|
||||
3.437125000004926,
|
||||
4.410960937491382
|
||||
],
|
||||
"batch1_ms_per_window_median": 5.713200000172947,
|
||||
"batch64_ms_per_window_median": 4.149468750028973
|
||||
},
|
||||
"entropy_conv": {
|
||||
"batch1_reps": [
|
||||
4.874750000453787,
|
||||
5.169099998965976,
|
||||
5.236699998931726
|
||||
],
|
||||
"batch64_reps": [
|
||||
3.010160156236452,
|
||||
3.1175546875203963,
|
||||
3.516850781238645
|
||||
],
|
||||
"batch1_ms_per_window_median": 5.169099998965976,
|
||||
"batch64_ms_per_window_median": 3.1175546875203963
|
||||
},
|
||||
"percentile_all": {
|
||||
"batch1_reps": [
|
||||
5.184749999898486,
|
||||
5.2898499998264015,
|
||||
5.916899999647285
|
||||
],
|
||||
"batch64_reps": [
|
||||
4.305105468745296,
|
||||
4.460741406262514,
|
||||
4.184502343747454
|
||||
],
|
||||
"batch1_ms_per_window_median": 5.2898499998264015,
|
||||
"batch64_ms_per_window_median": 4.305105468745296
|
||||
},
|
||||
"percentile_conv": {
|
||||
"batch1_reps": [
|
||||
4.916449999655015,
|
||||
7.150899999032845,
|
||||
5.284949998895172
|
||||
],
|
||||
"batch64_reps": [
|
||||
3.855813281262499,
|
||||
4.688969531230214,
|
||||
5.220103124997877
|
||||
],
|
||||
"batch1_ms_per_window_median": 5.284949998895172,
|
||||
"batch64_ms_per_window_median": 4.688969531230214
|
||||
},
|
||||
"minmax_all": {
|
||||
"batch1_reps": [
|
||||
6.463300000177696,
|
||||
7.149449998905766,
|
||||
5.3209000016067876
|
||||
],
|
||||
"batch64_reps": [
|
||||
3.9251343750095202,
|
||||
4.033442187505898,
|
||||
3.428199218745931
|
||||
],
|
||||
"batch1_ms_per_window_median": 6.463300000177696,
|
||||
"batch64_ms_per_window_median": 3.9251343750095202
|
||||
},
|
||||
"minmax_conv": {
|
||||
"batch1_reps": [
|
||||
5.9961499991914025,
|
||||
5.236549999608542,
|
||||
4.854399998293957
|
||||
],
|
||||
"batch64_reps": [
|
||||
4.368359375007458,
|
||||
3.249617187492504,
|
||||
3.0238906249735464
|
||||
],
|
||||
"batch1_ms_per_window_median": 5.236549999608542,
|
||||
"batch64_ms_per_window_median": 3.249617187492504
|
||||
}
|
||||
},
|
||||
"accuracy_subset": {
|
||||
"description": "seed-42 file-level 70/15/15 test split, corrupted windows excluded, seed-42 random subset (same as quantize_bench/eval_ort_accuracy)",
|
||||
"subset_size": 10000
|
||||
}
|
||||
},
|
||||
"tiny_variant": {
|
||||
"env": {
|
||||
"torch": "2.12.0+cpu",
|
||||
"onnxruntime": "1.26.0",
|
||||
"platform": "Windows-11-10.0.26200-SP0",
|
||||
"num_threads": 16,
|
||||
"checkpoint": "results\\tiny_best.pth",
|
||||
"checkpoint_size_bytes": 340555,
|
||||
"params": 56290,
|
||||
"variant_config": {
|
||||
"tcn": [
|
||||
68,
|
||||
56,
|
||||
44,
|
||||
32
|
||||
],
|
||||
"conv": [
|
||||
2,
|
||||
4,
|
||||
8,
|
||||
16
|
||||
],
|
||||
"attn_groups": 2,
|
||||
"groups_mode": "depthwise",
|
||||
"input_pw_groups": 4
|
||||
}
|
||||
},
|
||||
"export": {
|
||||
"mode": "dynamic-batch",
|
||||
"exporter": "torchscript",
|
||||
"opset": 17,
|
||||
"file": "tiny_fp32_dynamic.onnx",
|
||||
"size_bytes": 295279,
|
||||
"size_mb": 0.295279,
|
||||
"verified_batches": [
|
||||
1,
|
||||
2,
|
||||
64
|
||||
],
|
||||
"note": "AdaptiveAvgPool2d((15,1)) replaced at export by an exact mean(-1) + constant averaging matmul (final_width 16 is not a multiple of 15, which the TorchScript exporter rejects); exactness proven by the parity check vs the original torch model"
|
||||
},
|
||||
"parity": {
|
||||
"fixture": "results/parity_fixture.npz input (batch 2, seed 42); reference output recomputed with the tiny torch model",
|
||||
"max_abs_diff_vs_torch": 1.4901161193847656e-07,
|
||||
"pass_lt_1e-4": true
|
||||
},
|
||||
"int8_static_percentile_conv": {
|
||||
"file": "tiny_int8_static_percentile_conv.onnx",
|
||||
"size_bytes": 248278,
|
||||
"size_mb": 0.248278,
|
||||
"calibration": {
|
||||
"method": "percentile",
|
||||
"percentile": 99.99,
|
||||
"windows": 512,
|
||||
"scope": "conv-only TRAIN-split corruption-free",
|
||||
"seconds": 1.5347836017608643
|
||||
},
|
||||
"per_channel": true,
|
||||
"activation_type": "QInt8",
|
||||
"weight_type": "QInt8",
|
||||
"max_abs_diff_vs_fp32_fixture": 0.018491357564926147
|
||||
},
|
||||
"latency": {
|
||||
"note": "3 interleaved repetitions per variant, median ms/window; full-model sessions are same-session references",
|
||||
"tiny_onnx_fp32": {
|
||||
"batch1_reps": [
|
||||
0.6312500008789357,
|
||||
0.6834500018157996,
|
||||
0.6595999984710943
|
||||
],
|
||||
"batch64_reps": [
|
||||
0.37747578119251557,
|
||||
0.24196640623586063,
|
||||
0.2314671875183194
|
||||
],
|
||||
"batch1_ms_per_window_median": 0.6595999984710943,
|
||||
"batch64_ms_per_window_median": 0.24196640623586063
|
||||
},
|
||||
"tiny_onnx_int8_static_percentile_conv": {
|
||||
"batch1_reps": [
|
||||
0.7988500001374632,
|
||||
0.9382499993080273,
|
||||
0.8451000030618161
|
||||
],
|
||||
"batch64_reps": [
|
||||
0.9211476562995813,
|
||||
1.3045390625165965,
|
||||
1.026230468767153
|
||||
],
|
||||
"batch1_ms_per_window_median": 0.8451000030618161,
|
||||
"batch64_ms_per_window_median": 1.026230468767153
|
||||
},
|
||||
"full_onnx_fp32_reference": {
|
||||
"batch1_reps": [
|
||||
2.267249998112675,
|
||||
2.80170000041835,
|
||||
2.132149998942623
|
||||
],
|
||||
"batch64_reps": [
|
||||
1.3050578124875756,
|
||||
1.4244992187855132,
|
||||
1.8014164062947202
|
||||
],
|
||||
"batch1_ms_per_window_median": 2.267249998112675,
|
||||
"batch64_ms_per_window_median": 1.4244992187855132
|
||||
},
|
||||
"full_onnx_int8_static_percentile_conv_reference": {
|
||||
"batch1_reps": [
|
||||
5.529599999135826,
|
||||
4.768399998283712,
|
||||
6.215800000063609
|
||||
],
|
||||
"batch64_reps": [
|
||||
3.815724218725336,
|
||||
3.1025562500417436,
|
||||
4.333318749957016
|
||||
],
|
||||
"batch1_ms_per_window_median": 5.529599999135826,
|
||||
"batch64_ms_per_window_median": 3.815724218725336
|
||||
}
|
||||
},
|
||||
"accuracy_subset": {
|
||||
"description": "seed-42 file-level 70/15/15 test split, corrupted windows excluded, seed-42 random subset (same as quantize_bench/eval_ort_accuracy/static_ptq_bench)",
|
||||
"subset_size": 10000
|
||||
},
|
||||
"accuracy": {
|
||||
"tiny_onnx_fp32": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.941106667804718,
|
||||
"pck@50": 0.99369333152771,
|
||||
"mpjpe": 0.012527281279861927,
|
||||
"wall_seconds": 10.927234888076782
|
||||
},
|
||||
"tiny_onnx_int8_static_percentile_conv": {
|
||||
"samples": 10000,
|
||||
"pck@20": 0.9268133331298828,
|
||||
"pck@50": 0.9932933319091797,
|
||||
"mpjpe": 0.014906252065300942,
|
||||
"wall_seconds": 12.320892333984375
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,3 +0,0 @@
|
||||
{"variant": "half", "params": 843834, "tcn_channels": [270, 220, 170, 120], "conv_channels": [4, 8, 16, 32], "attn_groups": 4, "groups_mode": "gcd20", "input_pw_groups": 1, "tcn_groups_per_block": [[20, 10], [10, 20], [20, 10], [10, 20]], "conv_strides": [2, 2, 2, 1], "final_width": 15, "batch_size": 64, "max_epochs": 50, "patience": 5, "lr": 0.0001, "weight_decay": 5e-05, "seed": 42, "precision": "fp32", "epochs_run": 28, "best_epoch": 23, "best_val_mpjpe": 0.008576328293592842, "best_val_pck20": 0.9690593021534107, "train_seconds": 1346.4, "torch": "2.11.0+cu128", "error": null, "finished_utc": "2026-06-11T03:09:47Z", "checkpoint": "/home/ruvultra/wiflow-std-bench/sweep/half_best.pth", "test_full": {"samples": 54000, "mpjpe": 0.009419974447676428, "pck@10": 0.8740543655289544, "pck@20": 0.9610469643628156, "pck@30": 0.9813556064146537, "pck@40": 0.9896086878246731, "pck@50": 0.9934827546013726}, "test_clean": {"samples": 52560, "mpjpe": 0.008980081718602137, "pck@10": 0.8840944136840205, "pck@20": 0.9662253179869514, "pck@30": 0.9847971080282144, "pck@40": 0.9917795997050618, "pck@50": 0.9946956242600532}}
|
||||
{"variant": "quarter", "params": 338600, "tcn_channels": [135, 110, 85, 60], "conv_channels": [2, 4, 8, 16], "attn_groups": 2, "groups_mode": "gcd20", "input_pw_groups": 1, "tcn_groups_per_block": [[20, 5], [5, 10], [10, 5], [5, 20]], "conv_strides": [2, 2, 1, 1], "final_width": 15, "batch_size": 64, "max_epochs": 50, "patience": 5, "lr": 0.0001, "weight_decay": 5e-05, "seed": 42, "precision": "fp32", "epochs_run": 50, "best_epoch": 50, "best_val_mpjpe": 0.008780752391864856, "best_val_pck20": 0.9672531302240159, "train_seconds": 1754.4, "torch": "2.11.0+cu128", "error": null, "finished_utc": "2026-06-11T03:39:06Z", "checkpoint": "/home/ruvultra/wiflow-std-bench/sweep/quarter_best.pth", "test_full": {"samples": 54000, "mpjpe": 0.009705399298005634, "pck@10": 0.8646123917014511, "pck@20": 0.9553815319449813, "pck@30": 0.979827209190086, "pck@40": 0.9887037501511751, "pck@50": 0.9931309027671814}, "test_clean": {"samples": 52560, "mpjpe": 0.009279253277105465, "pck@10": 0.8742288637923323, "pck@20": 0.9605315079427745, "pck@30": 0.9833016723076865, "pck@40": 0.9908206971631566, "pck@50": 0.9942719799017071}}
|
||||
{"variant": "tiny", "params": 56290, "tcn_channels": [68, 56, 44, 32], "conv_channels": [2, 4, 8, 16], "attn_groups": 2, "groups_mode": "depthwise", "input_pw_groups": 4, "tcn_groups_per_block": [[540, 68], [68, 56], [56, 44], [44, 32]], "conv_strides": [2, 1, 1, 1], "final_width": 16, "batch_size": 64, "max_epochs": 50, "patience": 5, "lr": 0.0001, "weight_decay": 5e-05, "seed": 42, "precision": "fp32", "epochs_run": 50, "best_epoch": 47, "best_val_mpjpe": 0.012602971208592256, "best_val_pck20": 0.9397210340146666, "train_seconds": 1540.1, "torch": "2.11.0+cu128", "error": null, "finished_utc": "2026-06-11T04:04:50Z", "checkpoint": "/home/ruvultra/wiflow-std-bench/sweep/tiny_best.pth", "test_full": {"samples": 54000, "mpjpe": 0.012859782406853305, "pck@10": 0.7640358444319831, "pck@20": 0.9364815320968628, "pck@30": 0.9731568422317505, "pck@40": 0.9866444962642811, "pck@50": 0.992488939108672}, "test_clean": {"samples": 52560, "mpjpe": 0.012502924276904246, "pck@10": 0.770895526488985, "pck@20": 0.9411073559313967, "pck@30": 0.9764840687790962, "pck@40": 0.9886695077067278, "pck@50": 0.9936238432039409}}
|
||||
@@ -1,21 +0,0 @@
|
||||
{
|
||||
"checkpoint": "/home/ruvultra/wiflow-std-bench/upstream/test/best_pose_model.pth",
|
||||
"test_full": {
|
||||
"samples": 54000,
|
||||
"mpjpe": 0.009834060806367133,
|
||||
"pck@10": 0.8686346120127925,
|
||||
"pck@20": 0.9608815324571398,
|
||||
"pck@30": 0.9789111610695168,
|
||||
"pck@40": 0.9857975759682832,
|
||||
"pck@50": 0.9898827553325229
|
||||
},
|
||||
"test_clean": {
|
||||
"samples": 52560,
|
||||
"mpjpe": 0.009432755044379373,
|
||||
"pck@10": 0.876996495807189,
|
||||
"pck@20": 0.9661454100405608,
|
||||
"pck@30": 0.9823453060205306,
|
||||
"pck@40": 0.987909734176537,
|
||||
"pck@50": 0.9911238361167036
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user