fix: make search raw output recovery backend-neutral

This commit is contained in:
Dudu-0223
2026-07-10 11:53:02 +08:00
parent 1df9f3a84a
commit 3bb90bd4b6
16 changed files with 136 additions and 107 deletions

View File

@@ -21,7 +21,7 @@ Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi;
- **Spawn per call, no shell state** — every call is a fresh non-login `bash -c` (deterministic; no rc files). All four surveyed tools spawn per call. `XXX(stateful-shell)` in `src/run.ts` records the two proven stateful designs (Claude Code's cwd-only persistence; Codex's PTY exec sessions) for when real workflows demand them.
- **Process-group kills with escalation** — children are spawned `detached` (own process group); kills send SIGTERM to the group, then SIGKILL after the `graceMs` grace (default 3s — OpenCode's escalation; pipelines and subshells die with the parent). ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools.
- **Tail-keep truncation + spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. If the final spill close reports a delayed writeback failure, the executor still returns the tail but withholds the path rather than advertising a possibly incomplete file.
- **Tail-keep truncation + spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. A foreground `BashExecRequest.stdoutMaxBytes` can raise stdout's capture budget for one trusted caller; stderr and background tasks still use `maxOutputBytes`. If the final spill close reports a delayed writeback failure, the executor still returns the tail but withholds the path rather than advertising a possibly incomplete file.
- **Model-friendly env + credential scrub** — `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`), then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. This scrub is the security control that keeps the harness's *ambient* credentials out of a spawned command. A spec's `env` is merged LAST (after the scrub), so a caller's explicit entry — a value it already holds — wins even on a credential-shaped name. The spec's `stdin`, when supplied, is written to the child and closed; with none supplied, fd 0 is `/dev/null` — the exact pre-seam default, so a command that probes stdin's file type is unaffected. Both `env`/`stdin` are set by in-process plugins (the hooks bridges); the model-facing tool doesn't expose them. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
- **Background tasks** — `start()` returns immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), `readOutput()` is incremental with whole-stream byte offsets, and disposal kills everything. The spec's opaque `owner` token is stored on the tracked task and returned by `ownerOf(id)` — the executor never interprets it (the consumer's access policy does), and because it lives with the task here it survives a `tool-bash` HMR reload.

View File

@@ -121,10 +121,13 @@ export class LocalBashExecutor extends BashExecutor {
this.config.maxTimeoutMs,
'bash-local: request.timeoutMs',
)
const stdoutMaxBytes = request.stdoutMaxBytes ?? this.config.maxOutputBytes
assertPositiveFinite('request.stdoutMaxBytes', stdoutMaxBytes)
return {
command: request.command,
workdir: request.workdir ?? this.config.cwd ?? process.cwd(),
timeoutMs,
stdoutMaxBytes,
...request.signal ? { signal: request.signal } : {},
// Carry stdin/env through verbatim — optional, no config default (absent
// means none). env merges AFTER the scrub in run.ts.
@@ -144,7 +147,8 @@ export class LocalBashExecutor extends BashExecutor {
const outcome = await runBash({
command: spec.command,
cwd: spec.workdir,
maxOutputBytes: this.config.maxOutputBytes,
stdoutMaxBytes: spec.stdoutMaxBytes,
stderrMaxBytes: this.config.maxOutputBytes,
graceMs: this.config.graceMs,
signal: d.signal,
stdin: spec.stdin,
@@ -170,7 +174,8 @@ export class LocalBashExecutor extends BashExecutor {
const running = runBash({
command: spec.command,
cwd: spec.workdir,
maxOutputBytes: this.config.maxOutputBytes,
stdoutMaxBytes: this.config.maxOutputBytes,
stderrMaxBytes: this.config.maxOutputBytes,
graceMs: this.config.graceMs,
signal: spec.signal,
stdin: spec.stdin,

View File

@@ -77,8 +77,10 @@ export function childEnv(extra?: Record<string, string>): NodeJS.ProcessEnv {
export interface SpawnSpec {
command: string
cwd: string
/** Per-stream in-memory cap; overflow spills to disk (tail kept in memory). */
maxOutputBytes: number
/** Stdout in-memory cap; overflow spills to disk (tail kept in memory). */
stdoutMaxBytes: number
/** Stderr in-memory cap; overflow spills to disk (tail kept in memory). */
stderrMaxBytes: number
/** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */
graceMs: number
/**
@@ -351,8 +353,8 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
? spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['pipe', 'pipe', 'pipe'], detached: true })
: spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['ignore', 'pipe', 'pipe'], detached: true })
const stdout = new OutputCollector(spec.maxOutputBytes, 'stdout', spillDir)
const stderr = new OutputCollector(spec.maxOutputBytes, 'stderr', spillDir)
const stdout = new OutputCollector(spec.stdoutMaxBytes, 'stdout', spillDir)
const stderr = new OutputCollector(spec.stderrMaxBytes, 'stderr', spillDir)
child.stdout.on('data', (chunk: Buffer) => { stdout.push(chunk) })
child.stderr.on('data', (chunk: Buffer) => { stderr.push(chunk) })

View File

@@ -86,6 +86,23 @@ describe('LocalBashExecutor.run', () => {
const { bash } = await setup()
expect(() => bash.resolve({ command: 'true', timeoutMs: Number.NaN })).toThrow(/request\.timeoutMs/)
expect(() => bash.resolve({ command: 'true', timeoutMs: -1 })).toThrow(/request\.timeoutMs/)
expect(() => bash.resolve({ command: 'true', stdoutMaxBytes: Number.NaN })).toThrow(/request\.stdoutMaxBytes/)
expect(() => bash.resolve({ command: 'true', stdoutMaxBytes: -1 })).toThrow(/request\.stdoutMaxBytes/)
})
it('defaults stdoutMaxBytes to maxOutputBytes and lets foreground callers raise stdout only', async () => {
const { bash } = await setup({ maxOutputBytes: 100 })
expect(bash.resolve({ command: 'true' }).stdoutMaxBytes).toBe(100)
const result = await bash.run(bash.resolve({
command: 'printf "%.0sx" $(seq 1 500); printf "%.0se" $(seq 1 500) >&2',
stdoutMaxBytes: 500,
}))
expect(result.stdout.truncated).toBe(false)
expect(result.stdout.text).toBe('x'.repeat(500))
expect(result.stderr.truncated).toBe(true)
expect(result.stderr.text.length).toBeLessThanOrEqual(100)
})
it('kill escalation uses the configured graceMs (a TERM-trapping task dies by SIGKILL)', async () => {

View File

@@ -26,7 +26,8 @@ function spec(command: string, overrides: Partial<Parameters<typeof runBash>[0]>
return {
command,
cwd: process.cwd(),
maxOutputBytes: 64_000,
stdoutMaxBytes: 64_000,
stderrMaxBytes: 64_000,
graceMs: 3_000,
...overrides,
}
@@ -229,10 +230,24 @@ describe('stdin and extra env (set by in-process plugins)', () => {
})
describe('output truncation and spill', () => {
it('applies stdout and stderr caps independently', async () => {
const result = await runBash(
spec('printf "%.0sx" $(seq 1 500); printf "%.0se" $(seq 1 500) >&2', {
stdoutMaxBytes: 500,
stderrMaxBytes: 100,
}),
{ spillDir },
).done
expect(result.stdout.truncated).toBe(false)
expect(result.stdout.text).toBe('x'.repeat(500))
expect(result.stderr.truncated).toBe(true)
expect(result.stderr.text.length).toBeLessThanOrEqual(100)
})
it('keeps the tail and spills the full stream to disk', async () => {
// 200 numbered lines of ~10 bytes; cap at 500 bytes keeps a late tail.
const result = await runBash(
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }),
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
{ spillDir },
).done
expect(result.stdout.truncated).toBe(true)
@@ -247,7 +262,7 @@ describe('output truncation and spill', () => {
it('does not truncate output exactly at the cap', async () => {
const result = await runBash(
spec('printf "%.0sx" $(seq 1 500)', { maxOutputBytes: 500 }),
spec('printf "%.0sx" $(seq 1 500)', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
{ spillDir },
).done
expect(result.stdout.truncated).toBe(false)
@@ -258,7 +273,7 @@ describe('output truncation and spill', () => {
it('settles with the tail and no spill path when final spill close fails', async () => {
failNextClose.value = true
const result = await runBash(
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }),
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
{ spillDir },
).done
expect(failNextClose.value).toBe(false)
@@ -377,7 +392,7 @@ describe('review fixes: env scrubbing and spill hardening', () => {
it('creates spill files with owner-only permissions and random names', async () => {
const result = await runBash(
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }),
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
{ spillDir },
).done
const path = result.stdout.spillPath!
@@ -388,7 +403,7 @@ describe('review fixes: env scrubbing and spill hardening', () => {
it('defaults spills into a private per-process directory', async () => {
const result = await runBash(
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }),
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
).done
const dir = dirname(result.stdout.spillPath!)
expect(dir).toMatch(/dsh-bash-/)