|
| 1 | +# Async Run Logger (Issue #276) Implementation Plan |
| 2 | + |
| 3 | +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking. |
| 4 | +
|
| 5 | +**Goal:** Stop `FileRunLogger` from blocking the Node event loop by replacing per-entry `appendFileSync` calls with a single append-mode `fs.createWriteStream` per run. |
| 6 | + |
| 7 | +**Architecture:** `packages/runtime-node/src/run-logger.ts` keeps the exact same public `RunLogger` interface (`path`, `console`, `event`, `result`, `error`, `close` — all synchronous signatures). Internally, `FileRunLogger` opens one `WriteStream` with `flags: 'a'` in its constructor, pushes every entry through `stream.write()` (non-blocking; the stream buffers and flushes on the libuv thread pool), and `close()` ends the stream with the final `closed` marker so all buffered entries flush in order. Stream `error` events disable further logging instead of crashing the agent run. Callers (`runFrontAgentTask`, `planFrontAgentTask` in `run.ts`) are untouched. |
| 8 | + |
| 9 | +**Tech Stack:** Node `fs.createWriteStream`, TypeScript, Vitest. |
| 10 | + |
| 11 | +**GitNexus blast radius (recorded before editing):** `gitnexus_impact` on `FileRunLogger` and `createRunLogger` returns **HIGH** risk — direct callers `runFrontAgentTask` and `planFrontAgentTask` (`packages/runtime-node/src/run.ts`), re-export via `packages/runtime-node/src/index.ts`, indirect impact on `createFrontAgentMcpServer` / `startFrontAgentMcpServer` flows. Mitigation: the `RunLogger` interface and entry format are preserved byte-for-byte; only the write mechanism changes. Pending stream writes hold the event loop open, so the CLI's natural exit still flushes the log (no `process.exit` calls exist in `apps/cli/src`). |
| 12 | + |
| 13 | +**Out of scope:** `apps/cli/src/run-logger.ts` is a legacy copy imported only by its own test file (no production import). Issue #276 targets `packages/runtime-node` only; do not touch the CLI copy. |
| 14 | + |
| 15 | +--- |
| 16 | + |
| 17 | +### Task 1: Behavior tests for FileRunLogger file output |
| 18 | + |
| 19 | +**Files:** |
| 20 | +- Modify: `packages/runtime-node/src/run-logger.test.ts` |
| 21 | + |
| 22 | +- [ ] **Step 1: Write the failing tests** |
| 23 | + |
| 24 | +Append to `packages/runtime-node/src/run-logger.test.ts`. Update the imports at the top of the file: |
| 25 | + |
| 26 | +```ts |
| 27 | +import { mkdtempSync, readFileSync, rmSync } from 'node:fs'; |
| 28 | +import { tmpdir } from 'node:os'; |
| 29 | +import { join, resolve } from 'node:path'; |
| 30 | +import type { AgentEvent } from '@frontagent/core'; |
| 31 | +import { afterEach, describe, expect, it, vi } from 'vitest'; |
| 32 | +import { createRunLogger, redactForLog, resolveRunLogPath } from './run-logger.js'; |
| 33 | +``` |
| 34 | + |
| 35 | +Append this suite at the end of the file: |
| 36 | + |
| 37 | +```ts |
| 38 | +describe('createRunLogger (file logger)', () => { |
| 39 | + const tempDirs: string[] = []; |
| 40 | + |
| 41 | + function makeLogger() { |
| 42 | + const dir = mkdtempSync(join(tmpdir(), 'frontagent-runlog-')); |
| 43 | + tempDirs.push(dir); |
| 44 | + const logger = createRunLogger({ |
| 45 | + projectRoot: dir, |
| 46 | + enabled: true, |
| 47 | + logFile: 'run.log', |
| 48 | + task: 'test task', |
| 49 | + provider: 'test-provider', |
| 50 | + model: 'test-model', |
| 51 | + options: {}, |
| 52 | + }); |
| 53 | + if (!logger) throw new Error('expected logger'); |
| 54 | + return logger; |
| 55 | + } |
| 56 | + |
| 57 | + async function readWhenClosed(path: string): Promise<string> { |
| 58 | + await vi.waitFor(() => { |
| 59 | + expect(readFileSync(path, 'utf8')).toContain('closed'); |
| 60 | + }); |
| 61 | + return readFileSync(path, 'utf8'); |
| 62 | + } |
| 63 | + |
| 64 | + afterEach(() => { |
| 65 | + for (const dir of tempDirs.splice(0)) { |
| 66 | + rmSync(dir, { recursive: true, force: true }); |
| 67 | + } |
| 68 | + }); |
| 69 | + |
| 70 | + it('returns null when disabled', () => { |
| 71 | + expect( |
| 72 | + createRunLogger({ |
| 73 | + projectRoot: '/tmp', |
| 74 | + enabled: false, |
| 75 | + task: 't', |
| 76 | + provider: 'p', |
| 77 | + model: 'm', |
| 78 | + options: {}, |
| 79 | + }), |
| 80 | + ).toBeNull(); |
| 81 | + }); |
| 82 | + |
| 83 | + it('flushes header, entries, and close marker to the log file in order', async () => { |
| 84 | + const logger = makeLogger(); |
| 85 | + logger.event({ type: 'stream_token', stepId: 's1', token: 'hello' } as AgentEvent); |
| 86 | + logger.console('warn', ['warned', { apiKey: 'sk-secret' }]); |
| 87 | + logger.result({ success: true } as never); |
| 88 | + logger.error(new Error('boom')); |
| 89 | + logger.close(); |
| 90 | + |
| 91 | + const content = await readWhenClosed(logger.path); |
| 92 | + expect(content).toContain('# FrontAgent Run Log'); |
| 93 | + expect(content).toContain('event.stream_token'); |
| 94 | + expect(content).toContain('"tokenLength": 5'); |
| 95 | + expect(content).toContain('console.warn'); |
| 96 | + expect(content).toContain('[REDACTED]'); |
| 97 | + expect(content).not.toContain('sk-secret'); |
| 98 | + expect(content).toContain('result'); |
| 99 | + expect(content).toContain('boom'); |
| 100 | + expect(content.indexOf('# FrontAgent Run Log')).toBeLessThan(content.indexOf('event.stream_token')); |
| 101 | + expect(content.indexOf('event.stream_token')).toBeLessThan(content.indexOf('console.warn')); |
| 102 | + expect(content.trimEnd().endsWith('closed')).toBe(true); |
| 103 | + }); |
| 104 | + |
| 105 | + it('ignores writes after close and is idempotent on close', async () => { |
| 106 | + const logger = makeLogger(); |
| 107 | + logger.event({ type: 'status_update', label: 'before' } as AgentEvent); |
| 108 | + logger.close(); |
| 109 | + logger.close(); |
| 110 | + logger.event({ type: 'status_update', label: 'after-close' } as AgentEvent); |
| 111 | + logger.console('log', ['after-close-console']); |
| 112 | + |
| 113 | + const content = await readWhenClosed(logger.path); |
| 114 | + expect(content).toContain('before'); |
| 115 | + expect(content).not.toContain('after-close'); |
| 116 | + expect(content.match(/closed/g)).toHaveLength(1); |
| 117 | + }); |
| 118 | + |
| 119 | + it('appends to an existing file instead of truncating', async () => { |
| 120 | + const dir = mkdtempSync(join(tmpdir(), 'frontagent-runlog-')); |
| 121 | + tempDirs.push(dir); |
| 122 | + const path = resolve(dir, 'run.log'); |
| 123 | + const first = createRunLogger({ |
| 124 | + projectRoot: dir, |
| 125 | + enabled: true, |
| 126 | + logFile: 'run.log', |
| 127 | + task: 'first', |
| 128 | + provider: 'p', |
| 129 | + model: 'm', |
| 130 | + options: {}, |
| 131 | + }); |
| 132 | + if (!first) throw new Error('expected logger'); |
| 133 | + first.close(); |
| 134 | + await vi.waitFor(() => { |
| 135 | + expect(readFileSync(path, 'utf8')).toContain('closed'); |
| 136 | + }); |
| 137 | + |
| 138 | + const second = createRunLogger({ |
| 139 | + projectRoot: dir, |
| 140 | + enabled: true, |
| 141 | + logFile: 'run.log', |
| 142 | + task: 'second', |
| 143 | + provider: 'p', |
| 144 | + model: 'm', |
| 145 | + options: {}, |
| 146 | + }); |
| 147 | + if (!second) throw new Error('expected logger'); |
| 148 | + second.close(); |
| 149 | + await vi.waitFor(() => { |
| 150 | + expect((readFileSync(path, 'utf8').match(/closed/g) ?? []).length).toBe(2); |
| 151 | + }); |
| 152 | + |
| 153 | + const content = readFileSync(path, 'utf8'); |
| 154 | + expect(content).toContain('task: first'); |
| 155 | + expect(content).toContain('task: second'); |
| 156 | + }); |
| 157 | +}); |
| 158 | +``` |
| 159 | + |
| 160 | +Note on `task: first` / `task: second`: the header is `stringify(header)` of an object containing `task`, which JSON-stringifies as `"task": "first"`. Use these assertions instead: |
| 161 | + |
| 162 | +```ts |
| 163 | + expect(content).toContain('"task": "first"'); |
| 164 | + expect(content).toContain('"task": "second"'); |
| 165 | +``` |
| 166 | + |
| 167 | +- [ ] **Step 2: Run tests — new ordering/append tests must pass against current sync implementation too (they assert behavior, not mechanism), so verify they pass, then proceed; the refactor in Task 2 must keep them green** |
| 168 | + |
| 169 | +Run: `pnpm vitest run packages/runtime-node/src/run-logger.test.ts` |
| 170 | +Expected: PASS (these tests pin the existing observable contract before the internal change). |
| 171 | + |
| 172 | +- [ ] **Step 3: Commit** |
| 173 | + |
| 174 | +```bash |
| 175 | +git add packages/runtime-node/src/run-logger.test.ts |
| 176 | +git commit -m "test(runtime-node): pin FileRunLogger file output contract before async refactor" |
| 177 | +``` |
| 178 | + |
| 179 | +### Task 2: Replace appendFileSync with a single append-mode WriteStream |
| 180 | + |
| 181 | +**Files:** |
| 182 | +- Modify: `packages/runtime-node/src/run-logger.ts` |
| 183 | + |
| 184 | +- [ ] **Step 1: Update imports** |
| 185 | + |
| 186 | +Replace line 2: |
| 187 | + |
| 188 | +```ts |
| 189 | +import { appendFileSync, mkdirSync } from 'node:fs'; |
| 190 | +``` |
| 191 | + |
| 192 | +with: |
| 193 | + |
| 194 | +```ts |
| 195 | +import { createWriteStream, mkdirSync, type WriteStream } from 'node:fs'; |
| 196 | +``` |
| 197 | + |
| 198 | +- [ ] **Step 2: Rewrite FileRunLogger to write through one stream** |
| 199 | + |
| 200 | +Replace the whole `FileRunLogger` class (lines 119–162) with: |
| 201 | + |
| 202 | +```ts |
| 203 | +class FileRunLogger implements RunLogger { |
| 204 | + private closed = false; |
| 205 | + private readonly stream: WriteStream; |
| 206 | + |
| 207 | + constructor( |
| 208 | + readonly path: string, |
| 209 | + header: Record<string, unknown>, |
| 210 | + ) { |
| 211 | + mkdirSync(dirname(path), { recursive: true }); |
| 212 | + this.stream = createWriteStream(path, { flags: 'a', encoding: 'utf8' }); |
| 213 | + // Disk failures (ENOSPC, EACCES, ...) must not crash the agent run; an |
| 214 | + // unhandled 'error' event on the stream would. Disable further logging instead. |
| 215 | + this.stream.on('error', () => { |
| 216 | + this.closed = true; |
| 217 | + }); |
| 218 | + this.stream.write( |
| 219 | + ['# FrontAgent Run Log', `startedAt: ${timestampForLine()}`, stringify(header), ''].join( |
| 220 | + '\n', |
| 221 | + ), |
| 222 | + ); |
| 223 | + } |
| 224 | + |
| 225 | + private write(kind: string, payload: unknown): void { |
| 226 | + if (this.closed) return; |
| 227 | + this.stream.write(`[${timestampForLine()}] ${kind}\n${stringify(payload)}\n\n`); |
| 228 | + } |
| 229 | + |
| 230 | + console(level: 'log' | 'warn' | 'error', args: unknown[]): void { |
| 231 | + this.write(`console.${level}`, formatConsoleArgs(args)); |
| 232 | + } |
| 233 | + |
| 234 | + event(event: AgentEvent): void { |
| 235 | + this.write(`event.${event.type}`, summarizeEvent(event)); |
| 236 | + } |
| 237 | + |
| 238 | + result(result: AgentExecutionResult): void { |
| 239 | + this.write('result', result); |
| 240 | + } |
| 241 | + |
| 242 | + error(error: unknown): void { |
| 243 | + this.write('error', error); |
| 244 | + } |
| 245 | + |
| 246 | + close(): void { |
| 247 | + if (this.closed) return; |
| 248 | + this.closed = true; |
| 249 | + // end() writes the final marker after all buffered entries, preserving |
| 250 | + // order, then closes the fd. Pending writes keep the event loop alive, |
| 251 | + // so a normal CLI exit still flushes the full log. |
| 252 | + this.stream.end(`[${timestampForLine()}] closed\n`); |
| 253 | + } |
| 254 | +} |
| 255 | +``` |
| 256 | + |
| 257 | +- [ ] **Step 3: Run the focused tests** |
| 258 | + |
| 259 | +Run: `pnpm vitest run packages/runtime-node/src/run-logger.test.ts` |
| 260 | +Expected: PASS (all redaction, path, and new file-logger tests). |
| 261 | + |
| 262 | +- [ ] **Step 4: Run the package tests and type check** |
| 263 | + |
| 264 | +Run: `pnpm vitest run packages/runtime-node && pnpm typecheck` |
| 265 | +Expected: PASS. |
| 266 | + |
| 267 | +- [ ] **Step 5: Commit** |
| 268 | + |
| 269 | +```bash |
| 270 | +git add packages/runtime-node/src/run-logger.ts |
| 271 | +git commit -m "perf(runtime-node): write run log through async WriteStream instead of appendFileSync" |
| 272 | +``` |
| 273 | + |
| 274 | +### Task 3: Optional benchmark evidence for the PR (not committed) |
| 275 | + |
| 276 | +- [ ] **Step 1: Run an ad-hoc latency comparison** |
| 277 | + |
| 278 | +Write `/tmp/runlog-bench.mjs` (do NOT commit): |
| 279 | + |
| 280 | +```js |
| 281 | +import { appendFileSync, createWriteStream, rmSync } from 'node:fs'; |
| 282 | +import { performance } from 'node:perf_hooks'; |
| 283 | + |
| 284 | +const N = 5000; |
| 285 | +const entry = `[2026-06-11T00:00:00.000Z] event.stream_token\n${JSON.stringify({ type: 'stream_token', stepId: 's1', tokenLength: 4 }, null, 2)}\n\n`; |
| 286 | + |
| 287 | +function pctl(samples, p) { |
| 288 | + const s = [...samples].sort((a, b) => a - b); |
| 289 | + return s[Math.min(s.length - 1, Math.floor((p / 100) * s.length))]; |
| 290 | +} |
| 291 | + |
| 292 | +// sync |
| 293 | +{ |
| 294 | + const path = '/tmp/bench-sync.log'; |
| 295 | + rmSync(path, { force: true }); |
| 296 | + const samples = []; |
| 297 | + const t0 = performance.now(); |
| 298 | + for (let i = 0; i < N; i++) { |
| 299 | + const a = performance.now(); |
| 300 | + appendFileSync(path, entry, 'utf8'); |
| 301 | + samples.push(performance.now() - a); |
| 302 | + } |
| 303 | + const total = performance.now() - t0; |
| 304 | + console.log(`appendFileSync: total=${total.toFixed(1)}ms p50=${pctl(samples, 50).toFixed(3)}ms p99=${pctl(samples, 99).toFixed(3)}ms max=${Math.max(...samples).toFixed(3)}ms (per-call event-loop block)`); |
| 305 | +} |
| 306 | + |
| 307 | +// stream |
| 308 | +{ |
| 309 | + const path = '/tmp/bench-stream.log'; |
| 310 | + rmSync(path, { force: true }); |
| 311 | + const stream = createWriteStream(path, { flags: 'a', encoding: 'utf8' }); |
| 312 | + const samples = []; |
| 313 | + const t0 = performance.now(); |
| 314 | + for (let i = 0; i < N; i++) { |
| 315 | + const a = performance.now(); |
| 316 | + stream.write(entry); |
| 317 | + samples.push(performance.now() - a); |
| 318 | + } |
| 319 | + const submitted = performance.now() - t0; |
| 320 | + await new Promise((r) => stream.end(r)); |
| 321 | + const total = performance.now() - t0; |
| 322 | + console.log(`WriteStream: submit=${submitted.toFixed(1)}ms flushTotal=${total.toFixed(1)}ms p50=${pctl(samples, 50).toFixed(3)}ms p99=${pctl(samples, 99).toFixed(3)}ms max=${Math.max(...samples).toFixed(3)}ms (per-call event-loop block)`); |
| 323 | +} |
| 324 | +``` |
| 325 | + |
| 326 | +Run: `node /tmp/runlog-bench.mjs` |
| 327 | +Record the output for the PR description. |
| 328 | + |
| 329 | +### Task 4: Gates and PR |
| 330 | + |
| 331 | +- [ ] **Step 1: Run precommit gate** |
| 332 | + |
| 333 | +Run: `pnpm quality:precommit` |
| 334 | +Expected: PASS. |
| 335 | + |
| 336 | +- [ ] **Step 2: GitNexus detect_changes** |
| 337 | + |
| 338 | +Run `gitnexus_detect_changes()` and confirm only `run-logger.ts` symbols (`FileRunLogger`, its methods) and the test file are affected; affected flows limited to `runFrontAgentTask` / `planFrontAgentTask` logging paths. |
| 339 | + |
| 340 | +- [ ] **Step 3: Open PR to develop** |
| 341 | + |
| 342 | +Use the repo PR template, reference `Closes #276`, include the GitNexus impact summary (HIGH risk, interface preserved) and the benchmark numbers from Task 3. |
0 commit comments