mirror of
https://github.com/ruvnet/ruflo.git
synced 2026-09-14 14:01:28 +08:00
cd8a9c0988
* feat(memory): distillation service — mine memory_entries into intelligence substrate (ADR-174 M0+M1) Root cause the goal-planner surfaced: the daemon's consolidate worker (worker-daemon.ts:1443) is a STUB writing hardcoded zeros — 6000+ commits recorded to memory_entries but never distilled. reasoning_patterns / episodes / pattern_embeddings / causal_edges were all empty (hence 🧠 0%). M0 (safety) + M1 (service): runDistillation() mines memory_entries into episodes → reasoning_patterns (+pattern_embeddings) → causal_edges. - $0: reuses structured-distill.ts extractor + the embeddings already on each row; no LLM, no re-embedding. - Incremental: distill_state rowid cursor per namespace; never rescans. - Non-destructive: only inserts into the empty target tables; never touches memory_entries. Per-batch transactions. - Safe on the just-recovered DB: quick_check gate skips corrupt DBs; better-sqlite3 optional (silent no-op). - Provenance (ADR-171): feedback outcomes = oracle:test-exec (promotable); everything else = proxy:structural (written, NEVER promoted). Measured on a copy of the real 7,900-entry DB: 7,899 → 4,260 patterns (182 promoted, 4,078 proxy), 4,259 embeddings, 4,258 edges; source unchanged; dry-run wrote nothing; 2nd run processed 0. 6 tests green. ADR-174 records the decision, root cause, param surface, self-opt plan, alternatives, rollback. Follow-ups on branch: M2 CLI, M3 daemon (replace the stub), M4 self-optimization, M5 platform default. Co-Authored-By: RuFlo <ruv@ruv.net> * feat(memory): distill CLI, daemon auto-distill, self-optimization (ADR-174 M2+M3+M4) M2 — CLI: 'memory distill run|status|config' consuming the frozen M1 runDistillation. Full param surface: --dry-run, --namespace, --batch-size, --dedup-distance, --max-entries, --since, --budget-usd, --judge (fable gated on budget per ADR-172), --aggressive/--conservative presets, --config, --db. status reports substrate counts + cursor + provenance breakdown; degrades gracefully. 12 tests. M3 — daemon: replaced the runConsolidateWorker STUB (the root cause — it wrote hardcoded zeros) with a real runDistillation call every 30-min tick, bounded to 1000 entries/tick (cursor drains a backlog across ticks, stays well under the 16-min worker timeout). Real DistillReport written to the metrics file. Opt-out via --no-distill / RUFLO_DAEMON_NO_DISTILL and the existing 'daemon enable -w consolidate --disable'. Never throws (corrupt/ skipped surfaced, not fatal). 7 tests. The loop is now self-sustaining. M4 — self-optimization ('ruflo tuning ruflo'): tuneDistillation grid- searches {batchSize, dedupDistance, promoteThreshold} on ISOLATED copies, scored by MRR@10/recall@10 on a rowid-based held-out split (train/held-out disjointness asserted; held-out scored once). Source checksum unchanged. Honest measured result on the real 7.9k-entry corpus: winner batchSize=200 dedupDistance=0.2 promoteThreshold=execution+corroborated, held-out MRR@10 0.753 vs 0.749 baseline — roughly on par (the substrate/training value is the payoff, not raw retrieval uplift; measured-not-marketing). 11 tests. Combined M1+M2+M3+M4: 30 tests green. Co-Authored-By: RuFlo <ruv@ruv.net> * feat(browser): page-agent natural-language intent layer — browser_act (ADR-175) Adds an in-page NL intent tool on top of the selector-based browser tools: browser_act injects page-agent (Alibaba, MIT) into the agent-browser-driven page and runs 'execute(task)' — one natural-language call instead of manual selector orchestration. Verified against the real page-agent@1.11.0 (ESM-only, split @page-agent/* packages) — three load-bearing deviations handled: - import('page-agent') throws 'window is not defined' in Node even when installed → availability probed via require.resolve (path only, no eval), like browser-session-tools.ts. - the injectable IIFE auto-constructs a second PageAgent pointed at Alibaba's PUBLIC test endpoint (data leak on every call) → stripped before injection (stripDemoAutoInit). - execute() returns { success, data, history } → mapped to { result, steps }. Safety + routing: - Optional dependency (~1.11.0) + v3 pnpm-lock regenerated same change; browser_act returns { degraded:true } (never throws) when absent. - LLM routed through this CLI's Tier-3 ladder (OPENROUTER/OLLAMA, OpenAI- compatible); bare ANTHROPIC_API_KEY degrades (wrong API shape). - KEY SAFETY: page-agent runs in page context, so the real key never enters the injected string — startLocalLLMProxy holds it server-side on a loopback http server and injects Authorization itself; page sees 127.0.0.1 + a placeholder. Tests assert no key substring in the injection. - Trajectory → memory namespace 'browser' (feeds ADR-174 distillation). - AIDefence gates returned content (optional; passes through if absent). ADR-175 records the decision, the outer-harness/in-page split, constraints, the 6 follow-on use cases, alternatives, and rollback. 16 tool tests + 145 mcp-client regression tests green; full build clean. Co-Authored-By: RuFlo <ruv@ruv.net> * fix(browser): fail-closed demo-endpoint firewall for page-agent injection The demo auto-connect (page content → Alibaba's public sandbox at page-ag-testing-*.fcapp.run) was only neutralized by a best-effort text strip that fell OPEN — stripDemoAutoInit returned the source unchanged if the DEMO_MODEL marker moved, silently re-enabling the leak on an upstream bundle change. Verified via the real tarball: the demo endpoint lives ONLY in dist/iife/page-agent.demo.js (6 refs); the library core ESM entry is clean (0 refs). So no fork is needed — the leak is a property of the demo bundle, not the library. Fix: findDemoLeak() firewall + DemoLeakError. buildPageAgentInjection now scans the stripped bundle for known demo-endpoint signatures (page-ag-testing, .fcapp.run, DEMO_MODEL) and THROWS if any survive; the browser_act handler catches it and degrades rather than injecting. This is version-independent and fail-CLOSED — a moved/renamed marker can no longer leak, because the guarantee is 'endpoint absent', not 'marker found'. +4 tests (signature detection, clean-bundle pass, moved-marker refusal, clean-bundle injection). 20/20 green. ADR-175 updated with the fork-vs-fix rationale. Co-Authored-By: RuFlo <ruv@ruv.net> * fix(browser): add ADR-112 discoverability guidance to browser_act description CI failed 4 checks (tool-description audit + 3 smoke contracts that run it): browser_act was the 1 tool of 361 without a 'Use when …' guidance signal. The audit regex captures only the FIRST quoted segment of a multi-line description, so the guidance phrase must lead. Reworded to open with 'Use when …' + 'Prefer … over …' + 'pair with …' + 'Falls back …'. Audit now 361/361, exit 0. Co-Authored-By: RuFlo <ruv@ruv.net> * feat(memory): M5 — promote M4 winning distill config as daemon default (ADR-174) The daemon's consolidate worker now runs the M4-tuned config (dedupDistance=0.2, chosen by the self-optimization grid-search on the real corpus). Honest note in code + ADR: held-out MRR@10 0.753 vs 0.749 baseline — on-par, the substrate/training value is the payoff. Overridable per-run via 'memory distill'. Completes ADR-174 M0-M5. Co-Authored-By: RuFlo <ruv@ruv.net> * docs+fix(memory): address ADR-174 review — honest default, edge contract, invariants (ADR-174) Review fixes: - STATUS: Proposed → Accepted (M0-M5 implemented+tested, pending #2570 merge). - TUNED DEFAULT honestly justified: the M4 retrieval delta (0.753 vs 0.749) is a TIE, so dedupDistance=0.2 is sold as COMPRESSION, not retrieval lift — measured 2,723 vs 4,350 patterns (37% fewer) at 11.6ms/batch, 0 violations. Added an explicit promotion rule (retrieval-neutral within 0.002 AND >=15% compression AND <250ms/batch AND 0 proxy violations). - PARAM TABLE / DEFAULT consistency: dedup default is 0.2 everywhere (service, CLI, daemon). Presets now bracket it: --aggressive 0.3 / --conservative 0.1. - CAUSAL_EDGES OVERCLAIM: edges now carry an explicit contract (edge_type=cooccurrence, provenance_tier=proxy:structural, confidence=0.3, promoted=false) with the rule 'may rank retrieval, must NOT justify autonomous action'. Also fixed a latent bug: edges linked epId-1 (assumed consecutive rowids) → now the actual previous episode id. - EMBEDDING 1:1 invariant enforced: a cluster with no parseable vector is skipped, so every pattern has exactly one embedding (was off-by-one on a malformed source vector). - ADR adds operational invariants + audit SQL, business-value framing, and an acceptance test. +2 invariant tests (embedding coverage, edge contract). 32 distill tests green. Co-Authored-By: RuFlo <ruv@ruv.net> * feat(hooks): capture edit/task FAILURES, not just successes (ADR-174) The DB analysis found 898 feedback records — 100% success, 0 failures — because the post-edit/post-task hooks recorded a hardcoded success:true and never inspected the tool outcome. With no negative examples the oracle tier can't teach good-vs-bad, which caps what distillation can learn. Fix: read Claude Code's PostToolUse tool_response and record the REAL outcome. - isToolFailure(hookInput): conservative detector (positive error signal only) — tool_response.is_error / error / success:false, non-zero Bash exit code, or an error string. Exported + unit-tested (5 cases). - Generated hook (helpers-generator.ts) + the shipped .claude/helpers/ hook-handler.cjs both inline it: post-edit → recordEdit(file, !toolFailed), post-task → feedback(!toolFailed) (feedback() already boosts on success / decays on failure — it was just never called with false). - intelligence.cjs recordEdit(file, success) persists success to pending-insights so consolidation/distillation gets the negative example. The distillation JUDGE (memory-distillation.ts judgeFeedback) already maps success:false → reward 0 / not-promoted, so the substrate is failure-ready; this closes the upstream gap that never produced failures. End-to-end: a failed-edit PostToolUse payload now logs '[LEARN] Edit FAILURE recorded' through the actual shipped hook; a success stays '[OK] Edit recorded'. Co-Authored-By: RuFlo <ruv@ruv.net> * feat(init): version-stamped auto-refresh of critical helpers — hook fixes reach all users, no re-init (ADR-174) The propagation gap: Claude Code hooks run the PROJECT-LOCAL .claude/helpers/*.cjs copies, not the npm package — so npx ruflo@latest never updated them, and users didn't know to re-run init. Any hook fix (e.g. the ADR-174 failure-capture change) reached only people who happened to re-init. Fix: stamp the critical helpers (hook-handler.cjs, intelligence.cjs, auto-memory-hook.mjs) with the installed CLI version; on the next CLI command, if a project's stamp is older than the installed version, silently re-copy them. New lightweight src/init/helper-refresh.ts (fs/path/module only at load; lazily imports the heavy generators only on the rare source-unresolvable fallback). Wired AWAITED into index.ts startup so a fast command can't exit before the copy lands — fast path is a stamp read + string compare (sub-ms); the copy runs at most once per version bump. No-op outside a ruflo project (never scaffolds files in an unrelated dir). Skipped for init/update. executeUpgrade also stamps so an explicit upgrade is current. Verified end-to-end: a stale-stamped project with an OLD (no-failure-capture) hook silently upgrades to the toolFailed logic on a plain 'ruflo --help', and a current project is a no-op (a marker file survives). +4 tests. Co-Authored-By: RuFlo <ruv@ruv.net> * feat(security): Ed25519 signed provenance gate for the helper auto-refresh (ADR-174) The auto-refresh copies auto-EXECUTING hook code from the installed package into projects. npm verifies the tarball at install, not the files on disk after — a sibling package's postinstall (or disk tamper) could overwrite the helpers and the refresh would faithfully propagate the malicious code. Fix (fail-closed): every helper is verified against a ruflo-signed manifest before install. - helper-signing.ts: baked RUFLO_HELPERS_PUBKEY + verifyHelpersManifest() (native Ed25519, same primitive as rvfa-signing.ts). Fail-closed — any bad signature / tampered hash / wrong algorithm → null → refuse. - scripts/sign-helpers.mjs: publish-time signer; private key from $RUFLO_HELPERS_SIGNING_KEY, NEVER committed (kept out of the repo tree). Not shipped (scripts/ is narrowed to postinstall.cjs in files). - helper-refresh.writeCriticalHelpers: verifies the signed manifest + every source helper's SHA-256 BEFORE copying anything; a mismatch is refused and the project's existing helpers are left intact. The generator fallback needs no manifest (it's the CLI's own compiled code = trust root). - index.ts warns loudly on a blocked refresh (potential tampering signal). Threat model: closes post-install/on-disk tampering of the helper files; does not defend a wholesale-compromised CLI (which could swap the baked key too — but then it owns the binary you run). A CI test ('hashes match shipped files') fails if a helper changes without re-signing, so a stale manifest can't ship. Verified end-to-end: a tampered shipped helper → refresh REFUSED (blocked, project helper untouched); restored → refresh succeeds. +6 signing tests. Co-Authored-By: RuFlo <ruv@ruv.net> * chore(security): source helper-signing key from GCP Secret Manager sign-helpers.mjs now resolves the private key from GCP Secret Manager (RUFLO_HELPERS_SIGNING_SECRET, via gcloud secrets versions access) as the preferred source for CI/publish, with the local-PEM fallback (RUFLO_HELPERS_SIGNING_KEY) for air-gapped signing. Key never committed. ADR-174 security note updated. Co-Authored-By: RuFlo <ruv@ruv.net>
101 lines
4.5 KiB
JavaScript
101 lines
4.5 KiB
JavaScript
#!/usr/bin/env node
|
|
// tune-distill.mjs — ADR-174 Milestone 4 self-optimization harness
|
|
// ("ruflo tuning ruflo"). Grid-searches the memory-distillation config
|
|
// (batchSize x dedupDistance x promoteThreshold) and prints the grid table +
|
|
// winner + held-out score.
|
|
//
|
|
// Safety: this script NEVER touches the live DB with a write connection. It
|
|
// copies the source DB into its own scratch temp file BEFORE tuneDistillation
|
|
// ever sees a path — defense-in-depth on top of tuneDistillation's own
|
|
// internal per-candidate isolation (which only ever opens further copies of
|
|
// whatever dbPath it's handed).
|
|
//
|
|
// Usage:
|
|
// node scripts/tune-distill.mjs # tune against a copy of .swarm/memory.db
|
|
// node scripts/tune-distill.mjs --db <path> # tune against a copy of a different source db
|
|
// node scripts/tune-distill.mjs --write-config # persist the winner to .claude-flow/distill-tuned.json
|
|
// node scripts/tune-distill.mjs --quick # smaller grid for a fast sanity run
|
|
|
|
import { mkdtempSync, copyFileSync, existsSync, rmSync } from 'node:fs';
|
|
import { fileURLToPath } from 'node:url';
|
|
import { dirname, join, resolve } from 'node:path';
|
|
import { tmpdir } from 'node:os';
|
|
|
|
const SCRIPT_DIR = dirname(fileURLToPath(import.meta.url));
|
|
const CLI_ROOT = resolve(SCRIPT_DIR, '..');
|
|
|
|
const {
|
|
tuneDistillation,
|
|
buildTunedConfigFile,
|
|
writeTunedConfigFile,
|
|
defaultTunedConfigPath,
|
|
} = await import(join(CLI_ROOT, 'dist/src/services/distill-tuning.js'));
|
|
const { defaultMemoryDbPath } = await import(join(CLI_ROOT, 'dist/src/services/memory-distillation.js'));
|
|
|
|
function argValue(flag) {
|
|
const i = process.argv.indexOf(flag);
|
|
return i >= 0 && i + 1 < process.argv.length ? process.argv[i + 1] : undefined;
|
|
}
|
|
|
|
const sourceDb = argValue('--db') ?? defaultMemoryDbPath(process.cwd());
|
|
const writeConfig = process.argv.includes('--write-config');
|
|
const quick = process.argv.includes('--quick');
|
|
|
|
if (!existsSync(sourceDb)) {
|
|
console.error(`tune-distill: no memory DB found at ${sourceDb}`);
|
|
console.error('Pass --db <path> to point at a different source, or run inside a project with .swarm/memory.db');
|
|
process.exit(1);
|
|
}
|
|
|
|
// Defense-in-depth: copy the live DB into a script-owned scratch temp file
|
|
// BEFORE tuneDistillation (or anything else in this process) ever sees the
|
|
// live path. Everything downstream only ever touches this copy — the live
|
|
// path is used exactly once, for fs.copyFileSync.
|
|
const workdir = mkdtempSync(join(tmpdir(), 'tune-distill-'));
|
|
const isolatedCopy = join(workdir, 'source-copy.db');
|
|
copyFileSync(sourceDb, isolatedCopy);
|
|
console.log(`tune-distill: tuning against an isolated copy of ${sourceDb}`);
|
|
console.log(` -> ${isolatedCopy}\n`);
|
|
|
|
try {
|
|
const grid = quick
|
|
? { batchSize: [200], dedupDistance: [0.1, 0.2], promoteThreshold: ['execution-only', 'execution+corroborated'] }
|
|
: undefined; // undefined => tuneDistillation's own ADR-174 default grid
|
|
|
|
const t0 = Date.now();
|
|
const report = await tuneDistillation({ dbPath: isolatedCopy, grid, now: Date.now(), verbose: true });
|
|
const elapsedMs = Date.now() - t0;
|
|
|
|
console.log('\n=== Grid results ===');
|
|
console.log(
|
|
'batchSize | dedupDistance | promoteThreshold | trainMRR@10 | trainRecall@10 | patterns | promoted',
|
|
);
|
|
for (const c of report.candidates) {
|
|
const cfg = c.config;
|
|
const row =
|
|
`${String(cfg.batchSize).padEnd(9)} | ${String(cfg.dedupDistance).padEnd(13)} | ${cfg.promoteThreshold.padEnd(25)} | ` +
|
|
`${c.trainScore.toFixed(4).padEnd(11)} | ${c.trainRecallAt10.toFixed(4).padEnd(14)} | ${String(c.patternCount).padEnd(8)} | ${c.promotedCount}`;
|
|
console.log(row + (c.skipped ? ` [skipped: ${c.skipped}]` : ''));
|
|
}
|
|
|
|
console.log('\n=== Winner (best train MRR@10) ===');
|
|
console.log(JSON.stringify(report.winner, null, 2));
|
|
|
|
console.log('\n=== Held-out (scored once, on the true held-out ~20%) ===');
|
|
console.log(JSON.stringify(report.heldOut, null, 2));
|
|
console.log(`\noverfit flag (held-out >20% worse than train): ${report.overfit}`);
|
|
|
|
console.log('\n=== Provenance ===');
|
|
console.log(JSON.stringify(report.provenance, null, 2));
|
|
console.log(`\nwall time: ${elapsedMs}ms for ${report.candidates.length} grid points`);
|
|
|
|
if (writeConfig) {
|
|
const outPath = defaultTunedConfigPath(process.cwd());
|
|
writeTunedConfigFile(report, outPath);
|
|
console.log(`\nwrote winning config -> ${outPath}`);
|
|
console.log(JSON.stringify(buildTunedConfigFile(report), null, 2));
|
|
}
|
|
} finally {
|
|
rmSync(workdir, { recursive: true, force: true });
|
|
}
|