mirror of
https://github.com/ruvnet/ruflo.git
synced 2026-09-14 14:01:28 +08:00
495a451cf6
* feat(memory): typed provenance in AgentDB (ADR-323) Corrects and implements the 2026-07-28 dream-cycle research proposal (PR #2804, closed as superseded) for typed memory provenance in AgentDB, addressing MemIR/MemSyco-Bench's "provenance-role collapse" and memory-induced sycophancy findings. The dream-cycle PR's proposed schema change targeted the wrong table (`vector_indexes`, which is per-namespace HNSW index metadata, not per-entry) and its filename collided with the already-merged `ADR-322-metaharness-flywheel-integration.md` (#2817) — both corrected here as ADR-323 against `memory_entries`, the real per-record table. - memory-initializer.ts: `provenance_type` column (user_claim | agent_output | system_observation | tool_result | unknown, default unknown) on `memory_entries`, migrated for existing DBs via `ensureSchemaColumns()`. `storeEntry()`/`searchEntries()` accept and validate `provenanceType`/`provenanceFilter`. - memory-bridge.ts: same wiring for the native better-sqlite3 AgentDB v3 path (`bridgeStoreEntry`/`bridgeSearchEntries`). - commands/memory.ts: `memory store --provenance <type>`, `memory search --provenance-filter <types>` (comma-separated, OR semantics). - mcp-tools/memory-tools.ts + cli-core/mcp-tools/memory-defs.ts: `memory_store`'s `provenance_type` param, `memory_search`'s `provenance_filter` param (kept in sync across both tool-def sets). Found and fixed during implementation: an initial design skipped the RaBitQ/HNSW acceleration paths entirely whenever a provenance filter was requested (neither carries provenance_type on their candidates). This reproducibly crashed the CLI process on exit (a libuv assertion on Windows) after printing correct results. Fixed by never skipping those paths — RaBitQ now fetches provenance_type in its existing per-candidate query, HNSW does one batched (namespace, key) lookup afterward — eliminating the crash across repeated runs. See ADR-323's "Implementation note" for detail. 7 new end-to-end tests (adr-323-memory-provenance.test.ts), including a repeated-run regression guard for the crash. Full existing memory suite re-verified with no regressions (one pre-existing, environment- specific #2558 test failure confirmed identical against unmodified main — better-sqlite3's native bridge is unavailable in this dev environment, unrelated to this change). Closes the follow-up from dream-cycle PR #2804 (closed as superseded). Co-Authored-By: claude-flow <ruv@ruv.net> * fix(memory): enforce provenance across retrieval paths * feat: add agentic policy engine * fix: align Codex MCP integration * fix: keep MetaHarness dependencies optional * fix: declare MetaHarness as optional peers * fix: sync workspace lockfile * fix: document policy tool selection guidance * test: cover governed in-process flywheel * ci: make MetaHarness absence drill deterministic
52 lines
1.9 KiB
JavaScript
52 lines
1.9 KiB
JavaScript
import { performance } from 'node:perf_hooks';
|
|
import { AgenticPolicyEngine, evaluatePolicy } from '../dist/policy/index.js';
|
|
|
|
const iterations = Number(process.env.POLICY_BENCH_ITERATIONS ?? 50_000);
|
|
const request = {
|
|
identity: { id: 'agent:benchmark', type: 'agent', roles: ['developer'] },
|
|
action: { type: 'code.write', resource: 'src/app.ts', environment: 'development' },
|
|
context: {
|
|
envelope: {
|
|
actions: ['code.*'],
|
|
resources: ['src/*'],
|
|
maxConcurrency: 4,
|
|
network: false,
|
|
destructive: false,
|
|
},
|
|
},
|
|
};
|
|
const rules = [
|
|
{ id: 'allow-dev-code', effect: 'allow', actions: ['code.*'], roles: ['developer'], environments: ['development'] },
|
|
{ id: 'deny-prod-write', effect: 'deny', actions: ['code.write'], environments: ['production'], priority: 100 },
|
|
];
|
|
|
|
const pureStarted = performance.now();
|
|
for (let i = 0; i < iterations; i++) evaluatePolicy(request, rules, 'enforce');
|
|
const pureMs = performance.now() - pureStarted;
|
|
|
|
const receiptIterations = Math.min(iterations, 5_000);
|
|
const engine = new AgenticPolicyEngine({ mode: 'enforce', rules });
|
|
const receiptStarted = performance.now();
|
|
for (let i = 0; i < receiptIterations; i++) engine.evaluate({ ...request, requestId: `bench-${i}` });
|
|
const receiptMs = performance.now() - receiptStarted;
|
|
|
|
const report = {
|
|
schema: 'ruflo.policy-benchmark/v1',
|
|
pure: {
|
|
iterations,
|
|
durationMs: Number(pureMs.toFixed(3)),
|
|
opsPerSecond: Math.round(iterations / (pureMs / 1_000)),
|
|
microsPerDecision: Number(((pureMs * 1_000) / iterations).toFixed(3)),
|
|
},
|
|
withReceipts: {
|
|
iterations: receiptIterations,
|
|
durationMs: Number(receiptMs.toFixed(3)),
|
|
opsPerSecond: Math.round(receiptIterations / (receiptMs / 1_000)),
|
|
microsPerDecision: Number(((receiptMs * 1_000) / receiptIterations).toFixed(3)),
|
|
ledgerValid: engine.verifyLedger().valid,
|
|
},
|
|
};
|
|
|
|
console.log(JSON.stringify(report, null, 2));
|
|
if (!report.withReceipts.ledgerValid) process.exitCode = 1;
|