Merge remote-tracking branch 'origin/master' into worktree/acp-automation-protocol

# Conflicts:
#	.agents/notes/implemented/architecture/2026-06-14-session-persistence.md
#	.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.md
#	.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md
#	.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md
#	.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md
#	.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md
#	.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md
#	.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md
#	.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md
#	docs/architecture.i18n.yaml
#	docs/cookbook/extension-cookbook.i18n.yaml
#	docs/cookbook/extension-cookbook.md
#	docs/cookbook/extension-cookbook.zh.md
#	docs/core-data-structures/approval.md
#	docs/core-data-structures/user-interaction.md
#	docs/event-producer-consumer.md
#	docs/persistence-catalog.md
#	docs/testing.md
#	docs/tool-catalog.md
#	examples/acp-agent/tests/fixtures/live-mode-switching-2026-07-07.session.jsonl
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl
#	examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
#	packages/goal/tool-goal/README.md
#	packages/ui/acp/README.md
#	packages/ui/acp/acp-feature-support.md
#	packages/ui/acp/src/index.ts
#	packages/ui/acp/tests/bridge.spec.ts
#	packages/ui/acp/tests/dispose.spec.ts
#	packages/ui/acp/tests/edges.spec.ts
#	packages/ui/acp/tests/turns.spec.ts
This commit is contained in:
Tianyi Cui
2026-07-24 23:43:10 +08:00
829 changed files with 23607 additions and 1815 deletions

View File

@@ -27,7 +27,7 @@ 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` (a hook command ran) and `hook/result` (its outcome, paired by `handlerId`, with `appendHookResult` owning the decision rule). Payloads and per-event JSDoc are in the generated [persistence log event catalog](../../../docs/persistence-catalog.md); `stderrSummary` is 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 Agent Note.
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 `user/message` is the durable evidence) — see the hooks Agent Note.
## Model Experience

View File

@@ -97,7 +97,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => {
const adapter = new MockAdapter([textResponse('should not run')])
const ctx = await harness(dir, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'do something' }])
agent.followup([{ type: 'text', text: 'do something' }])
await waitForIdle(ctx, agent)
// The prompt was blocked: model never called, turn ended rejected.
@@ -120,13 +120,13 @@ describe('hooks-claude bridge — UserPromptSubmit', () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(dir, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
// The injected context reached the model and is recorded with the plugin source.
expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('remember: be brief')
const ctxMsg = events(agent).find(e => e.type === 'context/message')
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'hooks-claude' })
const ctxMsg = events(agent).find(e => e.type === 'user/message' && e.data.source.kind !== 'user')
expect(ctxMsg?.type === 'user/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'hooks-claude' })
})
})
@@ -145,7 +145,7 @@ describe('hooks-claude bridge — PreToolUse', () => {
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'danger', description: 'd', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'use danger' }])
agent.followup([{ type: 'text', text: 'use danger' }])
await waitForIdle(ctx, agent)
expect(ran).toBe(false)
@@ -168,7 +168,7 @@ describe('hooks-claude bridge — PreToolUse', () => {
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'safe', description: 's', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ran ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'use safe' }])
agent.followup([{ type: 'text', text: 'use safe' }])
await waitForIdle(ctx, agent)
expect(ran).toBe(true)
@@ -190,7 +190,7 @@ describe('hooks-claude bridge — PostToolUse', () => {
const ctx = await harness(dir, adapter)
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'raw output' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const result = events(agent).find(e => e.type === 'tool/result')
@@ -211,15 +211,15 @@ describe('hooks-claude bridge — PostToolUse', () => {
const ctx = await harness(dir, adapter)
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const log = events(agent)
const resultIdx = log.findIndex(e => e.type === 'tool/result')
const ctxIdx = log.findIndex(e => e.type === 'context/message')
const ctxIdx = log.findIndex(e => e.type === 'user/message' && e.data.source.kind !== 'user')
expect(ctxIdx).toBeGreaterThan(resultIdx) // context appended AFTER the tool result
const ctxMsg = log[ctxIdx]
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.content.some(b => b.type === 'text' && b.text.includes('tool was slow'))).toBe(true)
expect(ctxMsg?.type === 'user/message' && ctxMsg.data.content.some(b => b.type === 'text' && b.text.includes('tool was slow'))).toBe(true)
})
it('a PreToolUse permissionDecision:ask degrades to ask (the tool is gated, not run)', async () => {
@@ -235,7 +235,7 @@ describe('hooks-claude bridge — PostToolUse', () => {
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
// `ask` degrades to deny today (FIXME permissions): the tool does not run and the result is isError.
@@ -262,9 +262,9 @@ describe('hooks-claude bridge — SessionStart', () => {
// session-start fires async (detached .then → agent.inject); wait for the
// injected context/message to actually land before sending, rather than a
// fixed sleep that flakes under load.
await waitFor(() => events(agent).some(e => e.type === 'context/message'
await waitFor(() => events(agent).some(e => e.type === 'user/message'
&& e.data.content.some(b => b.type === 'text' && b.text.includes('project uses tabs'))))
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('project uses tabs')
@@ -357,7 +357,7 @@ describe('hooks-claude bridge — load resilience', () => {
await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' })
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
// The turn ran normally — no hooks, no crash.
expect(adapter.requests).toHaveLength(1)
@@ -379,7 +379,7 @@ describe('hooks-claude bridge — load resilience', () => {
await fiber.dispose()
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone
expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) // no hook ran

View File

@@ -74,7 +74,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} })
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('transcript'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
return {
payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string },
@@ -104,7 +104,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
ctx.logger.warn = warn as never
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(existsSync(marker)).toBe(true) // substituted command ran
})
@@ -120,7 +120,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
let sawArgs: unknown
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
// updatedInput is NOT honored — the tool ran with the ORIGINAL args.
expect((sawArgs as { command?: string }).command).toBe('original')
@@ -136,11 +136,11 @@ export function defineCoverageCases(group: CoverageGroup): void {
const adapter = new MockAdapter([textResponse('ran')])
const ctx = await harness(path, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
// The prompt proceeded unchanged; no context/message injected.
// The prompt proceeded unchanged; no injected context.
expect(adapter.requests).toHaveLength(1)
expect(events(agent).some(e => e.type === 'context/message')).toBe(false)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user')).toBe(false)
})
it('a PreToolUse hook fires for a no-agent direct tool call (no session/turn to record into)', async () => {
@@ -166,7 +166,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter)
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true)
@@ -191,7 +191,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 })
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…')
@@ -207,7 +207,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(path, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('continue please')
@@ -223,7 +223,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(path, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
// A second model request ran → the empty-reason block forced continuation.
expect(adapter.requests).toHaveLength(2)
@@ -271,7 +271,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter)
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const result = events(agent).find(e => e.type === 'tool/result')
expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true)
@@ -285,7 +285,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter)
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const result = events(agent).find(e => e.type === 'tool/result')
expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true)
@@ -314,7 +314,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const adapter = new MockAdapter([textResponse('no')])
const ctx = await harness(path, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const turnEnd = events(agent).findLast(e => e.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind === 'rejected' && turnEnd.data.reason.reason).toContain('blocked by UserPromptSubmit hook')
@@ -329,7 +329,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
// ask (no reason) → degrades to deny with the registry's generic message.
expect(ran).toBe(false)
@@ -344,7 +344,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter)
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0)
@@ -369,7 +369,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') })
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(existsSync(marker)).toBe(true)
})
@@ -384,7 +384,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(ran).toBe(true)
const res = events(agent).find(e => e.type === 'hook/result')
@@ -399,7 +399,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter)
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const result = events(agent).find(e => e.type === 'tool/result')
expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
@@ -418,7 +418,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded
@@ -435,13 +435,13 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter)
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const result = events(agent).find(e => e.type === 'tool/result')
expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true)
// additionalContext also injected (the block + context arm).
expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('context too')))).toBe(true)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('context too')))).toBe(true)
})
it('a PreToolUse hook whose hookSpecificOutput names a DIFFERENT event does NOT deny the tool', async () => {
@@ -455,7 +455,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran
})
@@ -473,9 +473,9 @@ export function defineCoverageCases(group: CoverageGroup): void {
// The factory create() path honors meta.cwd (the plain agentLoop.create() does not).
const { SessionId } = await import('@deepseek-ai/dsh-session')
const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { provider: 'mock', model: 'mock' } })
handle.agent.send([{ type: 'text', text: 'go' }])
handle.agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, handle.agent)
expect(events(handle.agent).some(e => e.type === 'context/message'
expect(events(handle.agent).some(e => e.type === 'user/message'
&& e.data.content.some(b => b.type === 'text' && b.text.includes(`dir=${workspace}`)))).toBe(true)
await handle.dispose()
})
@@ -491,12 +491,12 @@ export function defineCoverageCases(group: CoverageGroup): void {
// A later listener that blocks every prompt (registered AFTER the bridge).
ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
// the downstream block won: the model was never called, no user/message was
// recorded, and the (sole, fully-blocked) prompt closed the turn `rejected`
expect(adapter.requests).toHaveLength(0)
expect(events(agent).some(e => e.type === 'user/message')).toBe(false)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user')).toBe(false)
const turnEnd = events(agent).findLast(e => e.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toMatchObject({ kind: 'rejected', reason: 'policy veto' })
})
@@ -519,7 +519,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
}],
}))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const req = JSON.stringify(adapter.requests[0]!.messages)
expect(req).toContain('from-bridge')
@@ -528,12 +528,12 @@ export function defineCoverageCases(group: CoverageGroup): void {
// the original prompt was replaced by the downstream rewrite
const userMsg = events(agent).find(e => e.type === 'user/message')
expect(userMsg?.type === 'user/message' && userMsg.data.content.some(b => b.type === 'text' && b.text === 'rewritten-prompt')).toBe(true)
const contexts = events(agent).filter(event => event.type === 'context/message')
expect(contexts.map(event => event.type === 'context/message' && event.data.source)).toEqual([
const contexts = events(agent).filter(event => event.type === 'user/message' && event.data.source.kind !== 'user')
expect(contexts.map(event => event.type === 'user/message' && event.data.source)).toEqual([
{ kind: 'plugin', plugin: 'hooks-claude' },
{ kind: 'plugin', plugin: 'policy' },
])
expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
expect(contexts[1]?.type === 'user/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
})
it('folds the bridge PostToolUse context onto a downstream canonical value replacement', async () => {
@@ -547,11 +547,11 @@ export function defineCoverageCases(group: CoverageGroup): void {
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, value: [{ type: 'text' as const, text: 'rewritten-result' }] }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const result = events(agent).find(e => e.type === 'tool/result')
expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true)
expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
})
it('keeps bridge and downstream PostToolUse contexts as separate sourced events', async () => {
@@ -570,15 +570,15 @@ export function defineCoverageCases(group: CoverageGroup): void {
}],
}))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const contexts = events(agent).filter(event => event.type === 'context/message')
expect(contexts.map(event => event.type === 'context/message' && event.data.source)).toEqual([
const contexts = events(agent).filter(event => event.type === 'user/message' && event.data.source.kind !== 'user')
expect(contexts.map(event => event.type === 'user/message' && event.data.source)).toEqual([
{ kind: 'plugin', plugin: 'hooks-claude' },
{ kind: 'plugin', plugin: 'policy' },
])
expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
expect(contexts[1]?.type === 'user/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
})
it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => {
@@ -593,13 +593,13 @@ export function defineCoverageCases(group: CoverageGroup): void {
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const result = events(agent).find(e => e.type === 'tool/result')
expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true)
// the bridge's context still landed (folded onto the block)
expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
})
})
@@ -617,7 +617,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
bash.run = (() => Promise.reject(new Error('executor down')))
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false)
@@ -640,7 +640,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
await waitFor(() => threw)
expect(threw).toBe(true)
agent.inject = original
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1) // loop survived the thrown inject
})
@@ -667,7 +667,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const { SessionId } = await import('@deepseek-ai/dsh-session')
const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', model: 'mock' } })
handle.agent.send([{ type: 'text', text: 'go' }])
handle.agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, handle.agent)
expect(existsSync(marker)).toBe(true) // the marker landed in the SESSION dir
@@ -717,7 +717,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter)
const warn = vi.fn(); ctx.logger.warn = warn as never
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage'))
// Not surfaced: the systemMessage text never reaches the model request.
@@ -736,7 +736,7 @@ export function defineCoverageCases(group: CoverageGroup): void {
const ctx = await harness(path, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// Send immediately — do NOT wait for the session-start inject.
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1) // the turn ran regardless of hook timing
})

View File

@@ -77,7 +77,7 @@ describe('hooks-codex bridge', () => {
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'run ls' }])
agent.followup([{ type: 'text', text: 'run ls' }])
await waitForIdle(ctx, agent)
expect(ran).toBe(false)
@@ -98,7 +98,7 @@ describe('hooks-codex bridge', () => {
const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')])
const ctx = await harness(dir, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(2)
@@ -115,7 +115,7 @@ describe('hooks-codex bridge', () => {
const adapter = new MockAdapter([textResponse('must not run')])
const ctx = await harness(dir, adapter)
const agent = ctx.agentLoop.create(SessionId('cancel-prompt-hook'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'cancel the hook' }])
agent.followup([{ type: 'text', text: 'cancel the hook' }])
await waitFor(() => existsSync(marker))
const pid = Number(readFileSync(pidFile, 'utf8').trim())
@@ -139,7 +139,7 @@ describe('hooks-codex bridge', () => {
const adapter = new MockAdapter([textResponse('fine')])
const ctx = await harness(dir, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1)
})
@@ -149,7 +149,7 @@ describe('hooks-codex bridge', () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(dir, adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1)
})
@@ -169,7 +169,7 @@ describe('hooks-codex bridge', () => {
await fiber.dispose()
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone
expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) // no hook ran

View File

@@ -65,7 +65,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} })
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('transcript'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
return {
payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string | null },
@@ -84,7 +84,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const adapter = new MockAdapter([textResponse('no')])
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(0)
const te = events(agent).findLast(e => e.type === 'turn/end')
expect(te?.type === 'turn/end' && te.data.reason.kind).toBe('rejected')
@@ -96,7 +96,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x')
})
@@ -109,7 +109,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(0)
expect(events(agent).some(e => e.type === 'user/message')).toBe(false)
const te = events(agent).findLast(e => e.type === 'turn/end')
@@ -131,17 +131,17 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
}],
}))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const req = JSON.stringify(adapter.requests[0]!.messages)
expect(req).toContain('from-bridge')
expect(req).toContain('from-downstream')
expect(req).toContain('rewritten-prompt')
const contexts = events(agent).filter(event => event.type === 'context/message')
expect(contexts.map(event => event.type === 'context/message' && event.data.source)).toEqual([
const contexts = events(agent).filter(event => event.type === 'user/message' && event.data.source.kind !== 'user')
expect(contexts.map(event => event.type === 'user/message' && event.data.source)).toEqual([
{ kind: 'plugin', plugin: 'hooks-codex' },
{ kind: 'plugin', plugin: 'policy' },
])
expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
expect(contexts[1]?.type === 'user/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
})
})
@@ -154,10 +154,10 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, value: [{ type: 'text' as const, text: 'rewritten-result' }] }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const result = events(agent).find(e => e.type === 'tool/result')
expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true)
expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
})
it('keeps bridge and downstream PostToolUse contexts as separate sourced events', async () => {
@@ -175,14 +175,14 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
}],
}))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const contexts = events(agent).filter(event => event.type === 'context/message')
expect(contexts.map(event => event.type === 'context/message' && event.data.source)).toEqual([
const contexts = events(agent).filter(event => event.type === 'user/message' && event.data.source.kind !== 'user')
expect(contexts.map(event => event.type === 'user/message' && event.data.source)).toEqual([
{ kind: 'plugin', plugin: 'hooks-codex' },
{ kind: 'plugin', plugin: 'policy' },
])
expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
expect(contexts[1]?.type === 'user/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
})
it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => {
@@ -193,11 +193,11 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const result = events(agent).find(e => e.type === 'tool/result')
expect(result?.type === 'tool/result' && result.data.isError).toBe(true)
expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true)
expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true)
})
it('SessionStart additionalContext is injected for the first request', async () => {
@@ -206,9 +206,9 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
await waitFor(() => events(agent).some(e => e.type === 'context/message'
await waitFor(() => events(agent).some(e => e.type === 'user/message'
&& e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx'))))
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('start-ctx')
})
@@ -219,7 +219,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const r = events(agent).find(e => e.type === 'tool/result')
expect(r?.type === 'tool/result' && r.data.isError).toBe(true)
expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true)
@@ -232,8 +232,8 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true)
})
})
@@ -246,7 +246,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(ran).toBe(true) // clean-exit hook allows; commandOf returned ''
})
@@ -257,7 +257,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0)
expect(res?.type === 'hook/result' && 'stderrSummary' in res.data).toBe(false)
@@ -270,7 +270,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true)
expect(res?.type === 'hook/result' && res.data.stderrSummary?.length).toBe(501) // default 500-char cap + ellipsis
@@ -293,7 +293,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 })
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…')
})
@@ -316,7 +316,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') })
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(existsSync(marker)).toBe(true)
expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook'))
})
@@ -329,7 +329,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(ran).toBe(true)
})
@@ -344,8 +344,8 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
await waitFor(() => existsSync(marker)) // the clean no-output hook has finished
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(events(agent).some(e => e.type === 'context/message')).toBe(false)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user')).toBe(false)
})
it('a throwing SessionStart inject is contained (logged)', async () => {
@@ -370,7 +370,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(ran).toBe(true)
})
@@ -383,7 +383,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded
expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false)
})
@@ -399,7 +399,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded
expect(ran).toBe(true) // NOT honored: the tool still ran (halt is deferred)
@@ -412,7 +412,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const r = events(agent).find(e => e.type === 'tool/result')
expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true)
})
@@ -424,11 +424,11 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const r = events(agent).find(e => e.type === 'tool/result')
expect(r?.type === 'tool/result' && r.data.isError).toBe(true)
expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true)
expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('ctx too')))).toBe(true)
expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('ctx too')))).toBe(true)
})
it('commandOf reads a non-string command arg as an empty command', async () => {
@@ -441,7 +441,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } }
expect(payload.tool_input.command).toBe('')
})
@@ -477,7 +477,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
ctx.bash.run = (() => Promise.reject(new Error('executor down')))
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const res = events(agent).find(e => e.type === 'hook/result')
expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false)
})
@@ -493,7 +493,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook')
})
@@ -506,7 +506,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook')
})
@@ -521,7 +521,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
await waitFor(() => existsSync(marker)) // the exit-2 hook has finished
expect(events(agent).some(e => e.type === 'context/message'
expect(events(agent).some(e => e.type === 'user/message'
&& e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false)
})
@@ -534,7 +534,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran
expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale')
})
@@ -545,9 +545,9 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
await waitFor(() => events(agent).some(e => e.type === 'context/message'
await waitFor(() => events(agent).some(e => e.type === 'user/message'
&& e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble'))))
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('session preamble')
})
@@ -559,7 +559,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(join(d, 'hooks.json'), adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated')
})
@@ -574,7 +574,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
ctx.tools.register(defineContentToolFixture({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } }
expect(payload.tool_name).toBe('shell')
expect(payload.tool_input.command).toBe('ls')
@@ -590,7 +590,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
let ran = false
ctx.tools.register(defineContentToolFixture({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(ran).toBe(false) // the matcher fired → the hook denied the tool
expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true)
})
@@ -602,7 +602,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
const ctx = await harness(join(d, 'hooks.json'), adapter)
const warn = vi.fn(); ctx.logger.warn = warn as never
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent)
expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage'))
expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up')
})
@@ -625,7 +625,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const { SessionId } = await import('@deepseek-ai/dsh-session')
const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', model: 'mock' } })
handle.agent.send([{ type: 'text', text: 'go' }])
handle.agent.followup([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, handle.agent)
expect(existsSync(marker)).toBe(true)
expect(readFileSync(marker, 'utf8').trim().endsWith(sessionDir.split('/').pop()!)).toBe(true)