Merge remote-tracking branch 'origin/master' into simpl-g-hook-contract

# Conflicts:
#	packages/hooks/hook-protocol/src/events.ts
#	packages/hooks/hook-protocol/tests/events.spec.ts
#	packages/hooks/hooks-claude/README.md
#	packages/hooks/hooks-claude/src/index.ts
#	packages/hooks/hooks-codex/README.md
#	packages/hooks/hooks-codex/src/index.ts
This commit is contained in:
Tianyi Cui
2026-07-04 21:08:50 +08:00
115 changed files with 1890 additions and 860 deletions

View File

@@ -17,7 +17,7 @@ Why a shared lib at all: Codex deliberately reimplements a *subset* of the Claud
## Primitives
- **`matchesMatcher(matcher, query, mode)`** — match-all on absent/`''`/`'*'`; `claude` mode treats a pure `[A-Za-z0-9_|]+` pattern as a literal (pipe = exact-match alternation) and anything else as a regex; `codex` mode is always an unanchored regex. An invalid regex matches nothing (never throws).
- **`runHook(bash, hook, options)`** — serialize `options.payload` to the hook's stdin (with a trailing newline iff `options.trailingNewline`), merge `options.env` after the executor's credential scrub (the `dsh-bash` trusted-plugin surface), honor the hook's `timeoutSec` (else `DEFAULT_HOOK_TIMEOUT_MS`, the 10-minute reference default both dialects share), and decode the result (threading `options.expectedEventName` to the codec). Never throws: an executor rejection (infra fault) becomes a `HookOutput` with `exitCode: undefined` (a non-blocking error).
- **`runHook(bash, hook, options)`** — serialize `options.payload` to the hook's stdin (with a trailing newline iff `options.trailingNewline`), merge `options.env` after the executor's credential scrub (the `dsh-bash` trusted-plugin surface), honor the hook's `timeoutSec` (else `options.defaultTimeoutMs` — the bridge owns the default, its config defaulting to the lib's `DEFAULT_HOOK_TIMEOUT_MS` 10-minute reference), and decode the result (threading `options.expectedEventName` to the codec). Never throws: an executor rejection (infra fault) becomes a `HookOutput` with `exitCode: undefined` (a non-blocking error).
- **`parseHookOutput(exitCode, stdout, stderr, expectedEventName?)`** — the exit-code + structured-stdout codec. Exit `0` → parse JSON stdout (lenient: non-JSON is left for the bridge); exit `2` → blocking error, `stderr` is the block reason (surfaced as `decision: 'block'`); other → non-blocking error. `hookSpecificOutput.permissionDecision` (allow/deny/ask) overrides a legacy top-level `decision`; `additionalContext`/`updatedInput`/`systemMessage`/`continue`/`stopReason` are parsed too. The schemas key the `hookSpecificOutput` block by `hookEventName`, so passing `expectedEventName` (the firing event) DISCARDS a block whose `hookEventName` names a different event — or omits it entirely — its event-scoped fields don't take effect (a `PreToolUse` block on a `Stop` hook is malformed, and so is a discriminator-less block that would otherwise apply to any event), while the event-agnostic top-level fields still apply. Pure and total.
- **`mergeHookOutputs(outputs)`** — fold the results of every hook that matched one point: permission precedence **deny > ask > allow**, halt sticky on the first `continue:false`, block reasons joined with `\n\n`, `additionalContext`/`systemMessages` accumulated in order.
@@ -26,7 +26,7 @@ Why a shared lib at all: Codex deliberately reimplements a *subset* of the Claud
Declaration-merged into `SessionEventMap` (log-only, like `compact/*` — NOT a `SurfaceEventType`, no `surfaceOp`):
- `hook/invoked``{ turn, point, dialect, matcher?, handlerId }`: a hook command ran.
- `hook/result``{ turn, point, handlerId, decision, exitCode?, stderrSummary? }`: its outcome, paired by `handlerId`. `appendHookResult` owns the semantics: `decision` is the hook's parsed decision, else `'stop'` on `continue:false`, else `'pass'`; `stderrSummary` is the trimmed stderr truncated to 500 characters (omitted when empty).
- `hook/result``{ turn, point, handlerId, decision, exitCode?, stderrSummary? }`: its outcome, paired by `handlerId`. `appendHookResult` owns the semantics: `decision` is the hook's parsed decision, else `'stop'` on `continue:false`, else `'pass'`; `stderrSummary` is the trimmed stderr truncated to the record's `stderrSummaryMaxChars` (the bridge's config, reference default `DEFAULT_STDERR_SUMMARY_MAX_CHARS` = 500; omitted when empty).
Like every event they must sit inside an open turn. The mid-turn points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn by construction; `SessionStart` gets no `hook/*` record (its injected `context/message` is the durable evidence) — see the hooks RFC.

View File

@@ -43,16 +43,32 @@ export interface HookResultRecord {
* event's semantics live here, in the lib that declares it, not per-bridge.
*/
output: HookOutput
/**
* Character cap for the derived `stderrSummary`. The bound is the bridge's
* to own (its `stderrSummaryMaxChars` config) and is passed in explicitly —
* {@link DEFAULT_STDERR_SUMMARY_MAX_CHARS} is the reference default.
*/
stderrSummaryMaxChars: number
}
/** How many characters of stderr the `hook/result.stderrSummary` field keeps. */
const STDERR_SUMMARY_MAX = 500
/**
* The reference default for {@link HookResultRecord.stderrSummaryMaxChars}
* (both bridges' config default). It lives here, once, next to the truncation
* rule it bounds, so the bridges cannot drift apart on the shared event's
* default cap.
*/
export const DEFAULT_STDERR_SUMMARY_MAX_CHARS = 500
/** Truncate a stderr blob for the `hook/result.stderrSummary` field (`undefined` when empty). */
function summarizeStderr(stderr: string): string | undefined {
/**
* Truncate a hook's stderr for {@link HookResultRecord.stderrSummary}: trimmed,
* `undefined` when empty, cut at `maxChars` with an ellipsis when over. The
* bound is a parameter — like `runHook`'s `defaultTimeoutMs`, each bridge owns
* the config default and passes it in.
*/
export function summarizeStderr(stderr: string, maxChars: number): string | undefined {
const t = stderr.trim()
if (t.length === 0) return undefined
return t.length > STDERR_SUMMARY_MAX ? t.slice(0, STDERR_SUMMARY_MAX) + '…' : t
return t.length > maxChars ? t.slice(0, maxChars) + '…' : t
}
/** Append a `hook/invoked` provenance event to `session`. */
@@ -70,12 +86,13 @@ export function appendHookInvoked(session: Session, invocation: HookInvocation):
* Append a `hook/result` outcome event to `session` (pairs with a prior
* `hook/invoked`). Owns the durable event's semantics: `decision` is the hook's
* parsed decision, else `'stop'` when it asked to halt (`continue: false`),
* else `'pass'`; `stderrSummary` is the trimmed stderr truncated to 500
* characters (omitted when empty); `exitCode` is omitted when the hook never ran.
* else `'pass'`; `stderrSummary` is the trimmed stderr truncated to
* `record.stderrSummaryMaxChars` characters (omitted when empty); `exitCode`
* is omitted when the hook never ran.
*/
export function appendHookResult(session: Session, record: HookResultRecord): void {
const { output } = record
const stderrSummary = summarizeStderr(output.stderr)
const stderrSummary = summarizeStderr(output.stderr, record.stderrSummaryMaxChars)
session.append('hook/result', {
turn: record.turn,
point: record.point,

View File

@@ -36,5 +36,5 @@ export { DEFAULT_HOOK_TIMEOUT_MS, runHook } from './runner.ts'
export type { RunHookOptions } from './runner.ts'
export { mergeHookOutputs } from './merge.ts'
export type { MergedDecision, MergedHookOutcome } from './merge.ts'
export { appendHookInvoked, appendHookResult } from './events.ts'
export { appendHookInvoked, appendHookResult, DEFAULT_STDERR_SUMMARY_MAX_CHARS, summarizeStderr } from './events.ts'
export type { HookInvocation, HookResultRecord } from './events.ts'

View File

@@ -20,8 +20,9 @@ import type { CommandHook, HookOutput } from './types.ts'
/**
* The reference default per-hook timeout, in ms (10 minutes) — the value both
* Claude Code and Codex apply to a hook whose config sets no `timeout`. It
* lives here, once, as the protocol's default; a per-hook {@link CommandHook.timeoutSec}
* is the override surface.
* lives here, once, as the protocol's default; the bridges' `defaultTimeoutMs`
* config defaults to it, and a per-hook {@link CommandHook.timeoutSec} is the
* override surface.
*/
export const DEFAULT_HOOK_TIMEOUT_MS = 600_000
@@ -37,6 +38,12 @@ export interface RunHookOptions {
signal?: AbortSignal
/** Whether to append a trailing newline to the stdin payload (CC yes, Codex no). */
trailingNewline: boolean
/**
* Timeout applied when the hook's config sets no `timeout` of its own. The
* bridge owns the default (its `defaultTimeoutMs` config, reference default
* {@link DEFAULT_HOOK_TIMEOUT_MS}) and passes it in explicitly.
*/
defaultTimeoutMs: number
/**
* The event this hook is firing for (e.g. `'PreToolUse'`). When set, a
* structured `hookSpecificOutput` block whose `hookEventName` names a DIFFERENT
@@ -49,7 +56,7 @@ export interface RunHookOptions {
/**
* Run `hook` via `bash` with `options.payload` serialized to its stdin, then
* decode the result into a {@link HookOutput}. The hook's configured
* `timeoutSec` (wire unit: seconds) overrides {@link DEFAULT_HOOK_TIMEOUT_MS}.
* `timeoutSec` (wire unit: seconds) overrides `options.defaultTimeoutMs`.
* The command runs with the dialect's `env` merged after the executor's
* credential scrub (the trusted-plugin path). NEVER throws: an infrastructure
* failure (the executor rejecting) is surfaced as a {@link HookOutput} with
@@ -61,7 +68,7 @@ export async function runHook(
hook: CommandHook,
options: RunHookOptions,
): Promise<HookOutput> {
const timeoutMs = hook.timeoutSec !== undefined ? hook.timeoutSec * 1000 : DEFAULT_HOOK_TIMEOUT_MS
const timeoutMs = hook.timeoutSec !== undefined ? hook.timeoutSec * 1000 : options.defaultTimeoutMs
const stdin = JSON.stringify(options.payload) + (options.trailingNewline ? '\n' : '')
const request = {

View File

@@ -1,6 +1,6 @@
import { describe, expect, it } from 'vitest'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
import { appendHookInvoked, appendHookResult, type HookOutput } from '@deepseek-ai/dsh-hook-protocol'
import { appendHookInvoked, appendHookResult, summarizeStderr, type HookOutput } from '@deepseek-ai/dsh-hook-protocol'
/** A {@link HookOutput} with the required stream fields defaulted. */
function output(over: Partial<HookOutput> = {}): HookOutput {
@@ -35,7 +35,7 @@ describe('hook/* session events', () => {
const session = new Session(SessionId('s'))
appendHookResult(session, {
turn: 1, point: 'PreToolUse', handlerId: 'h1',
output: output({ exitCode: 2, stderr: 'blocked', decision: 'deny' }),
stderrSummaryMaxChars: 500, output: output({ exitCode: 2, stderr: 'blocked', decision: 'deny' }),
})
const full = [...session.events].find(e => e.type === 'hook/result')
if (full?.type === 'hook/result') {
@@ -46,7 +46,7 @@ describe('hook/* session events', () => {
const session2 = new Session(SessionId('s2'))
appendHookResult(session2, {
turn: 1, point: 'Stop', handlerId: 'h3',
output: output({ exitCode: undefined, decision: 'allow' }),
stderrSummaryMaxChars: 500, output: output({ exitCode: undefined, decision: 'allow' }),
})
const sparse = [...session2.events].find(e => e.type === 'hook/result')
if (sparse?.type === 'hook/result') {
@@ -58,10 +58,10 @@ describe('hook/* session events', () => {
it('the decision falls back to stop on continue:false, else pass', () => {
const session = new Session(SessionId('s'))
appendHookResult(session, { turn: 1, point: 'Stop', handlerId: 'halt', output: output({ continue: false }) })
appendHookResult(session, { turn: 1, point: 'Stop', handlerId: 'noop', output: output() })
appendHookResult(session, { turn: 1, point: 'Stop', handlerId: 'halt', stderrSummaryMaxChars: 500, output: output({ continue: false }) })
appendHookResult(session, { turn: 1, point: 'Stop', handlerId: 'noop', stderrSummaryMaxChars: 500, output: output() })
// An explicit decision wins over the continue:false fallback.
appendHookResult(session, { turn: 1, point: 'Stop', handlerId: 'both', output: output({ continue: false, decision: 'block' }) })
appendHookResult(session, { turn: 1, point: 'Stop', handlerId: 'both', stderrSummaryMaxChars: 500, output: output({ continue: false, decision: 'block' }) })
const decisions = [...session.events]
.filter(e => e.type === 'hook/result')
@@ -73,7 +73,7 @@ describe('hook/* session events', () => {
const session = new Session(SessionId('s'))
appendHookResult(session, {
turn: 1, point: 'PreToolUse', handlerId: 'long',
output: output({ exitCode: 2, stderr: ` ${'x'.repeat(600)} ` }),
stderrSummaryMaxChars: 500, output: output({ exitCode: 2, stderr: ` ${'x'.repeat(600)} ` }),
})
const ev = [...session.events].find(e => e.type === 'hook/result')
if (ev?.type === 'hook/result') {
@@ -85,7 +85,7 @@ describe('hook/* session events', () => {
const session = new Session(SessionId('s'))
appendHookResult(session, {
turn: 1, point: 'PreToolUse', handlerId: 'edge',
output: output({ exitCode: 2, stderr: 'y'.repeat(500) }),
stderrSummaryMaxChars: 500, output: output({ exitCode: 2, stderr: 'y'.repeat(500) }),
})
const ev = [...session.events].find(e => e.type === 'hook/result')
if (ev?.type === 'hook/result') {
@@ -96,7 +96,7 @@ describe('hook/* session events', () => {
it('an invoked/result pair correlates by handlerId', () => {
const session = new Session(SessionId('s'))
appendHookInvoked(session, { turn: 1, point: 'PreToolUse', dialect: 'claude', handlerId: 'pair-1' })
appendHookResult(session, { turn: 1, point: 'PreToolUse', handlerId: 'pair-1', output: output({ decision: 'allow' }) })
appendHookResult(session, { turn: 1, point: 'PreToolUse', handlerId: 'pair-1', stderrSummaryMaxChars: 500, output: output({ decision: 'allow' }) })
const invoked = [...session.events].find(e => e.type === 'hook/invoked')
const result = [...session.events].find(e => e.type === 'hook/result')
@@ -104,3 +104,20 @@ describe('hook/* session events', () => {
expect(result?.type === 'hook/result' && result.data.handlerId).toBe('pair-1')
})
})
describe('summarizeStderr', () => {
it('returns undefined for empty/whitespace stderr', () => {
expect(summarizeStderr('', 500)).toBeUndefined()
expect(summarizeStderr(' \n\t ', 500)).toBeUndefined()
})
it('passes through a summary at or under the cap, trimmed', () => {
expect(summarizeStderr(' blocked: bad tool ', 500)).toBe('blocked: bad tool')
expect(summarizeStderr('abc', 3)).toBe('abc')
})
it('truncates past the cap with an ellipsis', () => {
expect(summarizeStderr('abcdef', 4)).toBe('abcd…')
expect(summarizeStderr('x'.repeat(600), 500)).toBe('x'.repeat(500) + '…')
})
})

View File

@@ -54,6 +54,7 @@ describe('runHook — payload + env + stdin plumbing', () => {
const { bash, specs } = recordingBash(async () => result({ stdout: { text: '', truncated: false } }))
await runHook(bash, { command: 'my-hook.sh' }, {
payload: { hook_event_name: 'PreToolUse', tool_name: 'Bash' },
defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS,
trailingNewline: true,
})
expect(specs[0]!.stdin).toBe(JSON.stringify({ hook_event_name: 'PreToolUse', tool_name: 'Bash' }) + '\n')
@@ -62,14 +63,14 @@ describe('runHook — payload + env + stdin plumbing', () => {
it('omits the trailing newline when trailingNewline is false (Codex)', async () => {
const { bash, specs } = recordingBash(async () => result())
await runHook(bash, { command: 'h' }, { payload: { a: 1 }, trailingNewline: false })
await runHook(bash, { command: 'h' }, { payload: { a: 1 }, defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS, trailingNewline: false })
expect(specs[0]!.stdin).toBe('{"a":1}')
})
it('threads env and cwd into the request', async () => {
const { bash, specs } = recordingBash(async () => result())
await runHook(bash, { command: 'h' }, {
payload: {}, env: { CLAUDE_PROJECT_DIR: '/proj' }, cwd: '/work',
payload: {}, defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS, env: { CLAUDE_PROJECT_DIR: '/proj' }, cwd: '/work',
trailingNewline: true,
})
expect(specs[0]!.env).toEqual({ CLAUDE_PROJECT_DIR: '/proj' })
@@ -78,21 +79,21 @@ describe('runHook — payload + env + stdin plumbing', () => {
it('a per-hook timeoutSec (seconds) overrides the reference default', async () => {
const { bash, specs } = recordingBash(async () => result())
await runHook(bash, { command: 'h', timeoutSec: 3 }, { payload: {}, trailingNewline: true })
await runHook(bash, { command: 'h', timeoutSec: 3 }, { payload: {}, defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS, trailingNewline: true })
expect(specs[0]!.timeoutMs).toBe(3000)
})
it('falls back to DEFAULT_HOOK_TIMEOUT_MS when the hook sets none', async () => {
it('falls back to options.defaultTimeoutMs when the hook sets none', async () => {
const { bash, specs } = recordingBash(async () => result())
await runHook(bash, { command: 'h' }, { payload: {}, trailingNewline: true })
expect(specs[0]!.timeoutMs).toBe(DEFAULT_HOOK_TIMEOUT_MS)
await runHook(bash, { command: 'h' }, { payload: {}, defaultTimeoutMs: 1234, trailingNewline: true })
expect(specs[0]!.timeoutMs).toBe(1234)
expect(DEFAULT_HOOK_TIMEOUT_MS).toBe(600_000) // the CC/Codex reference default (10 minutes)
})
it('passes the abort signal through', async () => {
const controller = new AbortController()
const { bash, specs } = recordingBash(async () => result())
await runHook(bash, { command: 'h' }, { payload: {}, signal: controller.signal, trailingNewline: true })
await runHook(bash, { command: 'h' }, { payload: {}, defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS, signal: controller.signal, trailingNewline: true })
expect(specs[0]!.signal).toBe(controller.signal)
})
})
@@ -102,14 +103,14 @@ describe('runHook — outcome decoding', () => {
const { bash } = recordingBash(async () => result({
exitCode: 0, stdout: { text: JSON.stringify({ decision: 'block', reason: 'no' }), truncated: false },
}))
const output = await runHook(bash, { command: 'h' }, { payload: {}, trailingNewline: true })
const output = await runHook(bash, { command: 'h' }, { payload: {}, defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS, trailingNewline: true })
expect(output.decision).toBe('block')
expect(output.reason).toBe('no')
})
it('a signal death (exitCode null) decodes as undefined exit (non-blocking error)', async () => {
const { bash } = recordingBash(async () => result({ exitCode: null, signal: 'SIGKILL', stderr: { text: 'killed', truncated: false } }))
const output = await runHook(bash, { command: 'h' }, { payload: {}, trailingNewline: true })
const output = await runHook(bash, { command: 'h' }, { payload: {}, defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS, trailingNewline: true })
expect(output.exitCode).toBeUndefined()
expect(output.decision).toBeUndefined()
expect(output.stderr).toBe('killed')
@@ -117,7 +118,7 @@ describe('runHook — outcome decoding', () => {
it('an executor rejection (infra fault) becomes a non-blocking error, never throws', async () => {
const { bash } = recordingBash(async () => { throw new Error('bad workdir: ENOENT') })
const output = await runHook(bash, { command: 'h' }, { payload: {}, trailingNewline: true })
const output = await runHook(bash, { command: 'h' }, { payload: {}, defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS, trailingNewline: true })
expect(output.exitCode).toBeUndefined()
expect(output.stderr).toBe('bad workdir: ENOENT')
expect(output.decision).toBeUndefined()
@@ -125,7 +126,7 @@ describe('runHook — outcome decoding', () => {
it('a non-Error rejection is stringified onto stderr', async () => {
const { bash } = recordingBash(async () => { throw 'plain string fault' })
const output = await runHook(bash, { command: 'h' }, { payload: {}, trailingNewline: true })
const output = await runHook(bash, { command: 'h' }, { payload: {}, defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS, trailingNewline: true })
expect(output.stderr).toBe('plain string fault')
})
@@ -135,7 +136,7 @@ describe('runHook — outcome decoding', () => {
stdout: { text: JSON.stringify({ hookSpecificOutput: { hookEventName: 'PreToolUse', permissionDecision: 'deny' } }), truncated: false },
}))
const output = await runHook(bash, { command: 'h' }, {
payload: {}, trailingNewline: true, expectedEventName: 'Stop',
payload: {}, defaultTimeoutMs: DEFAULT_HOOK_TIMEOUT_MS, trailingNewline: true, expectedEventName: 'Stop',
})
// A PreToolUse block on a Stop hook is malformed → its decision is discarded.
expect(output.hookEventName).toBe('PreToolUse')