Files
wehub-resource-sync 23f7624596
ADR-166 MCP Bridge Security Lock / Static-source security lock (push) Failing after 0s
ADR-166 MCP Bridge Security Lock / Compose default binds loopback + Mongo has auth (push) Failing after 2s
CodeQL Advanced / Analyze (rust) (push) Failing after 0s
ADR-166 MCP Bridge Security Lock / plugin-agent-federation bindHost default (push) Failing after 1s
ADR-166 MCP Bridge Security Lock / Runtime behavior — 401 + terminal gate + fail-closed (push) Failing after 4s
business-pods-smoke / smoke (push) Failing after 1s
all-plugins-smoke / smoke-all (push) Failing after 2s
CI/CD Pipeline / Security & Code Quality (push) Failing after 1s
CI/CD Pipeline / Test Suite (ubuntu-latest) (push) Failing after 1s
CI/CD Pipeline / Build & Package (macos-latest) (push) Has been skipped
CI/CD Pipeline / Build & Package (ubuntu-latest) (push) Has been skipped
CI/CD Pipeline / Build & Package (windows-latest) (push) Has been skipped
CI/CD Pipeline / Documentation & Examples (push) Failing after 1s
Clone Tracker (14-day rolling) / Snapshot clones for ruflo ecosystem (push) Failing after 1s
CodeQL Advanced / Analyze (actions) (push) Failing after 1s
CodeQL Advanced / Analyze (javascript-typescript) (push) Failing after 1s
federation-peer-rust / stable-noop (push) Failing after 1s
metaharness-ci / score (push) Failing after 1s
metaharness-ci / router-compat (push) Failing after 0s
metaharness-ci / similarity-tests (push) Failing after 0s
no-agentbbs-smoke / smoke-without-agentbbs (push) Failing after 1s
V3 CI/CD Pipeline / Build V3 (windows-latest) (push) Has been skipped
codex-integration-audit / Codex integration audit (push) Failing after 1s
helpers-manifest-guard / guard (push) Failing after 1s
🔗 Cross-Agent Integration Tests / 🤝 Agent Coordination Tests (push) Has been skipped
🔗 Cross-Agent Integration Tests / 🧠 Memory Sharing Integration (push) Has been skipped
🔗 Cross-Agent Integration Tests / 🛡️ Fault Tolerance Tests (push) Has been skipped
🔗 Cross-Agent Integration Tests / ⚡ Performance Integration Tests (push) Has been skipped
metaharness-ci / mcp-scan (push) Failing after 1s
metaharness-ci / eject-dryrun (push) Failing after 1s
metaharness-ci / metaharness-real-data (push) Failing after 0s
no-cli-optdep-bloat-2561 / guard (push) Failing after 1s
no-metaharness-smoke / smoke-without-metaharness (push) Failing after 1s
no-phantom-agentic-flow-subpath / guard (push) Failing after 1s
🔄 Automated Rollback Manager / 🚨 Failure Detection (push) Failing after 1s
V3 CI/CD Pipeline / Plugin hooks smoke / ubuntu-latest / Node 22 (push) Failing after 1s
V3 CI/CD Pipeline / ruflo-graph-intelligence build + test smoke (#2044, ADR-123) (push) Failing after 1s
CVE Audit Gate / Audit root (critical-blocking) (push) Failing after 2s
cost-tracker-smoke / smoke (push) Failing after 3s
oia-audit-weekly / audit (push) Failing after 2s
ruflo-agent-smoke / ruflo-agent structural smoke (push) Failing after 1s
📊 Status Badges Update / 📊 Update Status Badges (push) Failing after 1s
V3 CI/CD Pipeline / Static regression guards (#2267 YAML + (push) Failing after 1s
V3 CI/CD Pipeline / Test V3 Packages (push) Failing after 0s
V3 CI/CD Pipeline / agent_execute provider routing smoke (#2042) (push) Failing after 0s
CVE Audit Gate / Audit v3 (critical-blocking) (push) Failing after 1s
federation-peer-rust / stable-native (push) Failing after 2s
🔗 Cross-Agent Integration Tests / 🚀 Integration Test Setup (push) Failing after 2s
neural-trader-smoke / runtime-smoke (push) Failing after 1s
V3 CI/CD Pipeline / Build V3 (macos-latest) (push) Has been skipped
V3 CI/CD Pipeline / Build V3 (ubuntu-latest) (push) Has been skipped
V3 CI/CD Pipeline / Type Check V3 (push) Failing after 1s
V3 CI/CD Pipeline / Smoke (no better-sqlite3) / ubuntu-latest / Node 24 (push) Failing after 1s
V3 CI/CD Pipeline / Smoke (no better-sqlite3) / ubuntu-latest / Node 22 (push) Failing after 2s
V3 CI/CD Pipeline / browser rvf create flag smoke (#2015) (push) Failing after 0s
V3 CI/CD Pipeline / Dependency review (#2046) (push) Has been skipped
V3 CI/CD Pipeline / Supply-chain audit (#2046) (push) Failing after 0s
V3 CI/CD Pipeline / witness marker drift smoke (#2021) (push) Failing after 1s
V3 CI/CD Pipeline / neural-trader portfolio CG smoke (#2068, ADR-126 Phase 3) (push) Failing after 1s
V3 CI/CD Pipeline / neural-trader backtest signing smoke (#2068, ADR-126 Phase 4) (push) Failing after 1s
V3 CI/CD Pipeline / kg-extract type-import classification smoke (#2049) (push) Failing after 0s
V3 CI/CD Pipeline / witness verify precondition smoke (#1880) (push) Failing after 2s
V3 CI/CD Pipeline / neural-trader pipeline risk-gate smoke (#2068, ADR-126 Phase 5) (push) Failing after 0s
V3 CI/CD Pipeline / neural-trader feature attribution smoke (#2068, ADR-126 Phase 6) (push) Failing after 0s
V3 CI/CD Pipeline / plugin-registry signature verification smoke (#1922, CWE-347) (push) Failing after 4s
V3 CI/CD Pipeline / memory stats legacy-DB smoke (#2120) (push) Failing after 4s
V3 CI/CD Pipeline / github deprecated actions smoke (#2089, ADR-127 Phase 3) (push) Failing after 1s
V3 CI/CD Pipeline / graph query + pathfinder smoke (ADR-130 P2+P5) (push) Has been skipped
V3 CI/CD Pipeline / graph trajectory hooks smoke (ADR-130 P3) (push) Has been skipped
V3 CI/CD Pipeline / graph plugin adapter smoke (ADR-130 P4) (push) Has been skipped
V3 CI/CD Pipeline / graph benchmark (ADR-130 P6) (push) Has been skipped
V3 CI/CD Pipeline / statusline generator delegation smoke (#2195) (push) Failing after 1s
V3 CI/CD Pipeline / wizard init regression guard (#2206 (push) Failing after 1s
V3 CI/CD Pipeline / memory no-stray-db smoke (ADR-125 P7) (push) Failing after 1s
V3 CI/CD Pipeline / github-safe injection smoke (#2089, ADR-127 Phase 1) (push) Failing after 1s
V3 CI/CD Pipeline / github actions pin smoke (#2089, ADR-127 Phase 1) (push) Failing after 1s
V3 CI/CD Pipeline / github attribution opt-in smoke (#2089, ADR-127 Phase 4) (push) Failing after 1s
V3 CI/CD Pipeline / pre-bash hook safety smoke (#2017) (push) Failing after 1s
V3 CI/CD Pipeline / Memory import smoke / ubuntu-latest (push) Failing after 0s
V3 CI/CD Pipeline / MCP protocol smoke / ubuntu-latest (push) Failing after 2s
V3 CI/CD Pipeline / ruvllm WASM auto-init smoke (#2086) (push) Failing after 4s
V3 CI/CD Pipeline / MCP paired-tool round-trip smoke (#1889) (push) Failing after 1s
V3 CI/CD Pipeline / Plugin package install-safety (#1902/#1903/#1904) (push) Failing after 1s
V3 CI/CD Pipeline / Tool description discoverability (ADR-112) (push) Failing after 3s
V3 CI/CD Pipeline / CLI npx-install smoke (#1147 / (22) (push) Failing after 1s
V3 CI/CD Pipeline / CLI npx-install smoke (#1147 / (24) (push) Failing after 1s
V3 CI/CD Pipeline / Windows hook shim smoke (#2132) / ubuntu-latest (push) Failing after 2s
V3 CI/CD Pipeline / Windows hook execution smoke (#2132) / ubuntu-latest (push) Failing after 1s
V3 CI/CD Pipeline / Windows init hooks smoke (#2132) / ubuntu-latest (push) Failing after 1s
V3 CI/CD Pipeline / Vector-index dimension audit (#1947) (push) Failing after 0s
V3 CI/CD Pipeline / Hook-command install safety (#1921) (push) Failing after 1s
V3 CI/CD Pipeline / ToolOutputGuardrail smoke (ADR-131, (push) Failing after 1s
V3 CI/CD Pipeline / init-bundle invariants smoke (#2095, ADR-128 Phase 5) (push) Failing after 1s
V3 CI/CD Pipeline / wasm provider bridge smoke (ADR-129 P1) (push) Failing after 2s
V3 CI/CD Pipeline / wasm gallery CRUD smoke (ADR-129 P3) (push) Failing after 1s
V3 CI/CD Pipeline / wasm plugin bridge smoke (ADR-129 P4) (push) Failing after 0s
V3 CI/CD Pipeline / wasm compose smoke (ADR-129 P2) (push) Failing after 4s
V3 CI/CD Pipeline / graph schema smoke (ADR-130 P1) (push) Failing after 0s
Validate Marketplace / validate (push) Failing after 1s
🔍 Verification Pipeline / 🚀 Setup Verification (push) Failing after 1s
🔍 Verification Pipeline / 🛡️ Security Verification (push) Has been skipped
🔍 Verification Pipeline / 📝 Code Quality (push) Has been skipped
🔍 Verification Pipeline / 🧪 Test Verification (${{ matrix.os }}, Node ${{ matrix.node }}) (push) Has been skipped
🔍 Verification Pipeline / 🏗️ Build Verification (push) Has been skipped
🔍 Verification Pipeline / 📚 Documentation Verification (push) Has been skipped
CVE Audit Gate / High-severity report (warn only) (push) Has been cancelled
🔄 Automated Rollback Manager / 🔄 Execute Rollback (push) Has been cancelled
🔄 Automated Rollback Manager / ✅ Post-Rollback Verification (push) Has been cancelled
🔄 Automated Rollback Manager / 📊 Rollback Monitoring (push) Has been cancelled
V3 CI/CD Pipeline / Windows init hooks smoke (#2132) / windows-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook execution smoke (#2132) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook execution smoke (#2132) / windows-latest (push) Has been cancelled
🔄 Automated Rollback Manager / ⏳ Manual Rollback Approval (push) Has been cancelled
V3 CI/CD Pipeline / MCP protocol smoke / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Memory import smoke / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook shim smoke (#2132) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook shim smoke (#2132) / windows-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows init hooks smoke (#2132) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Witness verify (signed manifest) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Witness verify (signed manifest) / ubuntu-latest (push) Has been cancelled
V3 CI/CD Pipeline / Witness verify (signed manifest) / windows-latest (push) Has been cancelled
V3 CI/CD Pipeline / Publish to npm (alpha) (push) Has been cancelled
V3 CI/CD Pipeline / Smoke (no better-sqlite3) / macos-latest / Node 22 (push) Has been cancelled
V3 CI/CD Pipeline / Plugin hooks smoke / macos-latest / Node 22 (push) Has been cancelled
CI/CD Pipeline / Deploy & Release (push) Has been cancelled
CI/CD Pipeline / CI Status (push) Has been cancelled
🔗 Cross-Agent Integration Tests / 📊 Integration Test Report (push) Has been cancelled
🔄 Automated Rollback Manager / 🔍 Pre-Rollback Validation (push) Has been cancelled
🔍 Verification Pipeline / ⚡ Performance Verification (push) Has been cancelled
🔍 Verification Pipeline / 📊 Verification Report (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:02:19 +08:00

204 lines
8.8 KiB
TypeScript

/**
* ADR-174 Milestone 2 — `memory distill` CLI surface.
*
* Exercises the CLI command family (run|status|config) built on top of the
* frozen M1 service (`../src/services/memory-distillation.ts`). The service
* itself is proven by `memory-distillation.test.ts`; this file proves the CLI
* wiring: flag → DistillOptions mapping, the ADR-172 fail-fast budget gate,
* the aggressive/conservative presets, and the read-only `status` report.
*/
import { describe, it, expect, beforeAll } from 'vitest';
import { mkdtempSync } from 'node:fs';
import { join } from 'node:path';
import { tmpdir } from 'node:os';
import type { Command, CommandContext } from '../src/types.js';
import { distillCommand, resolveDistillConfig } from '../src/commands/memory-distill.js';
let Database: any;
let haveNative = false;
try { Database = (await import('better-sqlite3')).default; haveNative = true; } catch { haveNative = false; }
/** Same fixture shape as __tests__/memory-distillation.test.ts. */
function seedDb(dbPath: string): void {
const db = new Database(dbPath);
db.exec(`CREATE TABLE memory_entries (
id TEXT PRIMARY KEY, key TEXT, namespace TEXT DEFAULT 'default',
content TEXT, embedding TEXT, status TEXT DEFAULT 'active'
)`);
db.exec(`CREATE TABLE episodes (
id INTEGER PRIMARY KEY AUTOINCREMENT, ts INTEGER DEFAULT 0, session_id TEXT NOT NULL,
task TEXT NOT NULL, input TEXT, output TEXT, critique TEXT, reward REAL DEFAULT 0,
success BOOLEAN DEFAULT 0, latency_ms INTEGER, tokens_used INTEGER, tags TEXT,
metadata JSON, created_at INTEGER DEFAULT 0
)`);
db.exec(`CREATE TABLE reasoning_patterns (
id INTEGER PRIMARY KEY AUTOINCREMENT, ts INTEGER DEFAULT 0, task_type TEXT NOT NULL,
approach TEXT NOT NULL, success_rate REAL NOT NULL DEFAULT 0, uses INTEGER DEFAULT 0,
avg_reward REAL DEFAULT 0, tags TEXT, metadata TEXT
)`);
db.exec(`CREATE TABLE pattern_embeddings (
pattern_id INTEGER PRIMARY KEY, embedding BLOB NOT NULL
)`);
db.exec(`CREATE TABLE causal_edges (
id INTEGER PRIMARY KEY AUTOINCREMENT, from_memory_id INTEGER NOT NULL, from_memory_type TEXT NOT NULL,
to_memory_id INTEGER NOT NULL, to_memory_type TEXT NOT NULL, similarity REAL DEFAULT 0,
confidence REAL DEFAULT 0.5, mechanism TEXT, metadata JSON, created_at INTEGER DEFAULT 0
)`);
const ins = db.prepare('INSERT INTO memory_entries (id, key, namespace, content, embedding) VALUES (?,?,?,?,?)');
const vec = (seed: number) => JSON.stringify(Array.from({ length: 8 }, (_, i) => Math.sin(seed + i)));
ins.run('c1', 'k1', 'commands', 'refactor the auth module in src/auth.ts', vec(1));
ins.run('c2', 'k2', 'commands', 'add validation to src/api/handler.ts', vec(2));
ins.run('c3', 'k3', 'commands', 'optimize the query in src/db/store.ts', vec(3));
ins.run('f1', 'k4', 'feedback', JSON.stringify({ taskId: 'edit-a', success: true }), vec(4));
ins.run('f2', 'k5', 'feedback', JSON.stringify({ taskId: 'edit-b', success: false }), vec(5));
db.close();
}
function countReasoningPatterns(dbPath: string): number {
const db = new Database(dbPath, { readonly: true });
const c = (db.prepare('SELECT COUNT(*) AS c FROM reasoning_patterns').get() as { c: number }).c;
db.close();
return c;
}
function makeCtx(flags: Record<string, unknown>, cwd: string): CommandContext {
return { args: [], flags: { _: [], ...flags }, cwd, interactive: false } as CommandContext;
}
function sub(name: string): Command {
const cmd = distillCommand.subcommands?.find((c) => c.name === name);
if (!cmd?.action) throw new Error(`memory distill ${name} has no action`);
return cmd;
}
describe.skipIf(!haveNative)('memory distill CLI (ADR-174 Milestone 2)', () => {
let workdir: string;
beforeAll(() => { workdir = mkdtempSync(join(tmpdir(), 'distill-cli-')); });
it('registers run, status, and config as subcommands of `memory distill`', () => {
const names = (distillCommand.subcommands ?? []).map((c) => c.name);
expect(names).toEqual(expect.arrayContaining(['run', 'status', 'config']));
});
it('--dry-run makes no writes', async () => {
const dbPath = join(workdir, 'dry.db');
seedDb(dbPath);
const result = await sub('run').action!(makeCtx({ dryRun: true, db: dbPath }, workdir));
expect(result?.success).toBe(true);
const data = result?.data as any;
expect(data.report.patterns).toBeGreaterThan(0);
expect(data.report.dryRun).toBe(true);
expect(countReasoningPatterns(dbPath)).toBe(0); // no writes actually landed
});
it('--namespace scopes the run to the requested namespace(s)', async () => {
const dbPath = join(workdir, 'ns.db');
seedDb(dbPath);
const result = await sub('run').action!(makeCtx({ namespace: 'feedback', db: dbPath }, workdir));
expect(result?.success).toBe(true);
const data = result?.data as any;
expect(data.config.namespaces).toEqual(['feedback']);
expect(data.report.processed).toBe(2); // only the 2 feedback rows
expect(data.report.byProvenance['proxy:structural']).toBeUndefined();
});
it('--judge fable without --budget-usd fails fast (ADR-172 gate)', async () => {
const dbPath = join(workdir, 'fable.db');
seedDb(dbPath);
const result = await sub('run').action!(makeCtx({ judge: 'fable', db: dbPath }, workdir));
expect(result?.success).toBe(false);
expect(result?.exitCode).toBe(1);
expect(countReasoningPatterns(dbPath)).toBe(0); // refused before calling the service
});
it('--judge fable with --budget-usd > 0 passes the gate (service still reserves the tier)', async () => {
const dbPath = join(workdir, 'fable-funded.db');
seedDb(dbPath);
const result = await sub('run').action!(makeCtx({ judge: 'fable', budgetUsd: 2, db: dbPath }, workdir));
expect(result?.success).toBe(true);
const data = result?.data as any;
// The M1 service reserves judge:fable (ADR-172, not enabled here) — CLI must
// surface that as a skip, not silently fall back to structural.
expect(data.report.skipped).toContain('judge:fable');
});
it('--aggressive preset maps to dedup-distance 0.3 / batch-size 500', () => {
const resolved = resolveDistillConfig(makeCtx({ aggressive: true }, workdir));
expect(resolved.ok).toBe(true);
if (resolved.ok) {
expect(resolved.config.dedupDistance).toBe(0.3);
expect(resolved.config.batchSize).toBe(500);
}
});
it('--conservative preset maps to dedup-distance 0.1 / batch-size 100', () => {
const resolved = resolveDistillConfig(makeCtx({ conservative: true }, workdir));
expect(resolved.ok).toBe(true);
if (resolved.ok) {
expect(resolved.config.dedupDistance).toBe(0.1);
expect(resolved.config.batchSize).toBe(100);
}
});
it('rejects --aggressive and --conservative together', () => {
const resolved = resolveDistillConfig(makeCtx({ aggressive: true, conservative: true }, workdir));
expect(resolved.ok).toBe(false);
});
it('explicit --batch-size overrides the --aggressive preset', () => {
const resolved = resolveDistillConfig(makeCtx({ aggressive: true, batchSize: 42 }, workdir));
expect(resolved.ok).toBe(true);
if (resolved.ok) {
expect(resolved.config.batchSize).toBe(42);
expect(resolved.config.dedupDistance).toBe(0.3); // untouched preset value
}
});
it('`config` prints the effective merged config as JSON-serializable data', async () => {
const result = await sub('config').action!(makeCtx({ aggressive: true, db: '/tmp/nonexistent.db' }, workdir));
expect(result?.success).toBe(true);
const data = result?.data as any;
expect(data.dedupDistance).toBe(0.3);
expect(data.batchSize).toBe(500);
expect(data.dbPath).toBe('/tmp/nonexistent.db');
});
it('`status` reports table counts, cursor, and the promote-gate breakdown after a run', async () => {
const dbPath = join(workdir, 'status.db');
seedDb(dbPath);
const runResult = await sub('run').action!(makeCtx({ db: dbPath }, workdir));
expect(runResult?.success).toBe(true);
const statusResult = await sub('status').action!(makeCtx({ db: dbPath }, workdir));
expect(statusResult?.success).toBe(true);
const data = statusResult?.data as any;
expect(data.available).toBe(true);
expect(data.counts.reasoning_patterns).toBeGreaterThan(0);
expect(data.counts.episodes).toBeGreaterThan(0);
expect(data.counts.pattern_embeddings).toBeGreaterThan(0);
expect(data.promoted).toBeGreaterThan(0); // feedback rows promote (ADR-171)
expect(data.proxy).toBeGreaterThan(0); // commands rows never promote
expect(data.cursors.length).toBeGreaterThan(0);
});
it('`status` degrades gracefully when no DB exists at the path', async () => {
const result = await sub('status').action!(makeCtx({ db: join(workdir, 'does-not-exist.db') }, workdir));
expect(result?.success).toBe(true);
const data = result?.data as any;
expect(data.available).toBe(false);
expect(data.reason).toBe('no-db');
});
});