Files
ruvnet--RuView/harness/ruview/src/mcp-server.js
T
rUv e6f26e9ac9 docs(adr): deep review of the RuView npm surface — ADR-263/264/265 optimization strategies (#1229)
* docs(adr): deep review of the RuView npm surface — ADR-263/264/265 optimization strategies

ADR-263 — @ruvnet/ruview@0.1.0 harness review (O1–O9):
- HIGH: claim-check CLI fails open on empty input (no --text/--file -> PASS exit 0)
- HIGH: MCP stdio server head-of-line blocking (spawnSync verify/calibrate up to 600s)
- MEASURED: optionalDependencies triple the cold npx install (4 pkgs/620kB/71 files
  vs 1 pkg/172kB/22 files with --omit=optional) for a path that never imports them
- maxBuffer truncation, python -c port interpolation, version drift, duplicate skills,
  guardrail METRIC_TERMS substring false positives ('map'/'F1' — found by dogfooding
  claim-check on these very ADRs), zero CI

ADR-264 — @ruvnet/rvagent@0.1.0 + @ruv/ruview-cli review (O1–O9), verified against
the published registry tarball:
- HIGH: exports.require -> dist/index.cjs which is never built nor published
- MEASURED: 44 dead source-map files = 62,698B of the 188kB unpacked payload
- stdio-only server described as dual-transport; mixed dot/underscore tool names;
  double Zod validation + hand-duplicated advertised schemas; 2-fd leak per training
  job; unbounded body in the unwired HTTP scaffold; dead detectCogBinary candidates;
  ruview bin-name collision

ADR-265 — cross-cutting npm distribution strategy: npm-packages.yml CI matrix
(test + pack-content/size gate + tarball-install smoke test), publish-from-CI-only
with npm provenance, version single-sourcing from package.json, bin/namespace
ownership (ruview bin belongs to @ruvnet/ruview), claim-check on package READMEs.

Docs only — no runtime code changed. Index/CHANGELOG/CLAUDE.md/README counts updated.

Co-Authored-By: claude-flow <ruv@ruv.net>
Claude-Session: https://claude.ai/code/session_01WrGfTGKv1oWZ6iwXZACULz

* fix(npm): implement ADR-263/264/265 — harness fail-closed + async MCP, rvagent packaging/transport/naming, npm CI+provenance gate

ADR-263 (@ruvnet/ruview 0.2.0), O1-O9:
- claim-check fails closed on empty input (CLI exit 2, empty_text tool error)
- MCP stdio server dispatches tools/call asynchronously (promise-based spawn);
  ping answers while a 3s fake verify runs — pinned by new e2e test
- optionalDependencies dropped: cold npx installs exactly 1 package
  (MEASURED: was 4 pkgs/620kB/71 files via npm i in a clean prefix)
- bounded rolling output tails replace spawnSync 1MiB maxBuffer
- node_monitor port passed via sys.argv, never spliced into python -c source
- serverInfo.version read from package.json; resources/prompts stubs
- skills single-sourced: prepack sync script generates .claude/skills/ copies
- which() = memoized dep-free PATH scan
- tools underscore-canonical (ruview_claim_check, ...) + dotted aliases
- guardrail precision: word-boundary map/f1/auc/iou, code-span + F1/O2 label
  scrubbing, quantitative-claims-only; packaging reproducer hints
- 30/30 tests (was 17), incl. concurrency e2e + fail-open regression pins

ADR-264 (@ruvnet/rvagent 0.2.0), O1-O9:
- exports fixed: types-first, phantom dist/index.cjs require target removed
- tarball map-free: 127,704B unpacked / 46 files / 0 maps (MEASURED,
  npm pack --dry-run; was 188kB incl. 44 maps referencing unshipped src)
- Streamable HTTP actually wired behind RVAGENT_HTTP_PORT: one transport +
  one MCP server per session (mcp-session-id routing), 1MiB body cap (413),
  port-aware localhost origin gate; dual-transport description now true
- tools renamed underscore-canonical with dotted router-only aliases
- single Zod validation gate; advertised inputSchema generated from the same
  Zod source (zod-to-json-schema)
- train_count: parent log fds closed (was leaking 2/job); job records
  persisted to <jobsDir>/<id>.json (job_status survives restarts); bounded
  log-tail reads
- detectCogBinary probes its candidates instead of dead-coding them
- version from package.json; @types/express dropped; @types/jest -> 29
- README rewritten to match reality (no phantom subcommands/policy layer)
- 99/99 jest tests (incl. new session/body-cap suite + previously-broken
  manifest suite); stdio handshake + HTTP session flow smoke-tested live

ADR-265 D1-D4:
- .github/workflows/npm-packages.yml: 3-package x Node 20/22 gate — tests,
  version-literal grep (D3), pack-content/size gate, tarball-install smoke
  test (catches the ADR-264 F1 class), README claim-check (D4)
- .github/workflows/ruview-npm-release.yml: publish from CI only with
  npm publish --provenance
- @ruv/ruview-cli bin renamed ruview-cli (ruview bin belongs to
  @ruvnet/ruview); version single-sourced
- ci.yml NODE_VERSION 18 -> 20

ADR statuses updated to Accepted/implemented; harness manifest re-pinned;
ADR-263/264/265 + both package READMEs pass claim-check.

Co-Authored-By: claude-flow <ruv@ruv.net>
Claude-Session: https://claude.ai/code/session_01WrGfTGKv1oWZ6iwXZACULz

* perf(rvagent): lazy-load HTTP transport + memoize generated tool schemas

stdio time-to-first-response ~242ms -> ~189ms (-22%; MEASURED, median of
repeated initialize round-trips against dist/index.js in this container).

- ./http-transport.js now imported lazily inside the RVAGENT_HTTP_PORT
  branch: it chain-loads the MCP SDK streamableHttp module (~48ms MEASURED
  via per-module import() timing) which the default stdio path never uses
- toolInputJsonSchema memoized per tool: schemas are static for the process
  lifetime; under the session-per-server HTTP model every session calls
  tools/list, so stop re-walking the Zod tree each time

No behavior change: 99/99 jest tests; HTTP session flow re-smoke-tested
through the lazy import path (initialize -> 200 + mcp-session-id).

Profiled @ruvnet/ruview too and left it alone: 50ms CLI startup vs ~29ms
bare 'node -e ""' floor on the same box (MEASURED) — already near the
interpreter floor with zero dependencies.

Co-Authored-By: claude-flow <ruv@ruv.net>
Claude-Session: https://claude.ai/code/session_01WrGfTGKv1oWZ6iwXZACULz

* ci(ruview-cli): pass jest --passWithNoTests so the private no-test package doesn't fail the npm-packages matrix

Co-Authored-By: claude-flow <ruv@ruv.net>

* fix(npm): address 10 verified review findings in harness + rvagent before 0.2.0 publish

harness/ruview (@ruvnet/ruview):
- guardrails: digit gate now sees numbers inside code spans; F1-style
  metric tokens followed by ':' or a nearby number are no longer scrubbed
  (fail-open regressions in the honesty gate)
- mcp-server: tools/call requests serialize through a FIFO promise chain
  (hardware/mutating tools never overlap) while ping/tools/list stay
  immediate; stdin close drains in-flight responses before exit
- tools: which() no longer memoizes negative lookups

tools/ruview-mcp (@ruvnet/rvagent):
- index: realpath invoked-directly guard — library import no longer
  connects a stdio transport to the consumer's process
- http-transport: explicit allowedOrigins is exact-match only (localhost
  any-port convenience applies only with no configured allowlist);
  session map gains maxSessions=64 + 5min idle TTL sweep
- train-count: job records persist the child pid and reconcile stale
  'running' status after a server restart (exit-code marker or dead pid)
- config: cog binary candidates ordered by process.arch

.github/workflows/ruview-npm-release.yml: port the full ADR-265 D1 gate
(version-literal check, unpacked-size budget, tarball-install smoke test)
from npm-packages.yml so the publish path enforces what the header claims.

Tests: harness 30→36, rvagent 99→112, all passing.

Co-Authored-By: claude-flow <ruv@ruv.net>

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-07-02 13:11:15 -04:00

108 lines
4.4 KiB
JavaScript

// SPDX-License-Identifier: MIT
// RuView harness — minimal MCP stdio server (JSON-RPC 2.0 over stdin/stdout).
//
// Dependency-free on purpose: a published `npx ruview` must `mcp start` without
// pulling the full MCP SDK. Implements the subset hosts use: `initialize`,
// `tools/list`, `tools/call`, `ping`, empty `resources/list`/`prompts/list`
// stubs, and the `notifications/initialized` ack. Logs go to stderr ONLY —
// stdout is the JSON-RPC channel and must stay clean.
//
// ADR-263 O2: `tools/call` is dispatched asynchronously — a long-running
// verify/calibrate no longer blocks ping/tools/list, so hosts that health-check
// mid-run see a live server. Responses may therefore arrive out of request
// order, which JSON-RPC permits (ids correlate them).
import { createInterface } from 'node:readline';
import { readFileSync } from 'node:fs';
import { listTools, runTool } from './tools.js';
const PROTOCOL_VERSION = '2024-11-05';
// Single-source the version from package.json (ADR-263 O6).
const PKG = JSON.parse(readFileSync(new URL('../package.json', import.meta.url), 'utf8'));
const SERVER_INFO = { name: 'ruview', version: PKG.version };
function send(msg) {
process.stdout.write(JSON.stringify(msg) + '\n');
}
function result(id, res) { send({ jsonrpc: '2.0', id, result: res }); }
function error(id, code, message) { send({ jsonrpc: '2.0', id, error: { code, message } }); }
function log(...a) { process.stderr.write('[ruview-mcp] ' + a.join(' ') + '\n'); }
async function handle(msg) {
const { id, method, params } = msg;
switch (method) {
case 'initialize':
return result(id, {
protocolVersion: PROTOCOL_VERSION,
capabilities: { tools: { listChanged: false } },
serverInfo: SERVER_INFO,
instructions: 'RuView WiFi-sensing operator tools. All results are fail-closed; accuracy claims must pass ruview_claim_check.',
});
case 'notifications/initialized':
case 'initialized':
case 'notifications/cancelled':
return; // notifications — no response
case 'ping':
return result(id, {});
case 'tools/list':
return result(id, { tools: listTools() });
case 'resources/list':
return result(id, { resources: [] });
case 'prompts/list':
return result(id, { prompts: [] });
case 'tools/call': {
const name = params?.name;
const args = params?.arguments || {};
const out = await runTool(name, args);
// MCP content envelope: text block with the JSON, isError reflects ok=false.
return result(id, {
content: [{ type: 'text', text: JSON.stringify(out, null, 2) }],
isError: out && out.ok === false,
});
}
default:
if (id !== undefined) error(id, -32601, `Method not found: ${method}`);
}
}
export function startMcpServer() {
log(`starting v${SERVER_INFO.version} (protocol ${PROTOCOL_VERSION}, ${listTools().length} tools)`);
const rl = createInterface({ input: process.stdin, crlfDelay: Infinity });
// tools/call runs are serialized through a FIFO promise chain: hardware/mutating
// tools (calibrate, serial monitor, flash) must never overlap. ping/tools/list/
// initialize/resources/prompts stay immediate (ADR-263 O2 — a health check must
// answer during a long tool run). `toolChain` also lets stdin-close drain the
// in-flight call so its response is flushed instead of dropped by process.exit.
let toolChain = Promise.resolve();
const dispatch = (msg) => handle(msg).catch((err) => {
if (msg && msg.id !== undefined) error(msg.id, -32603, String(err && err.message || err));
log('handler error:', String(err));
});
rl.on('line', (line) => {
const s = line.trim();
if (!s) return;
let msg;
try { msg = JSON.parse(s); } catch { return log('bad JSON line dropped'); }
if (msg && msg.method === 'tools/call') {
toolChain = toolChain.then(() => dispatch(msg)); // one tool at a time
} else {
dispatch(msg); // health/list/handshake answer immediately, even mid tool run
}
});
rl.on('close', () => {
// Wait for any queued/in-flight tool call to settle (its response written)
// before exiting — fire-and-forget used to race this and drop the response.
toolChain.then(() => {
log('stdin closed — exiting');
const done = () => process.exit(0);
// Pipe writes are async; flush buffered stdout before exit.
if (process.stdout.writableLength) process.stdout.once('drain', done);
else done();
});
});
}