deepseek-harness/packages/hooks/hooks-codex/tests/bridge.spec.ts

218 lines
11 KiB
TypeScript
Raw Normal View History

import { afterEach, describe, expect, it, vi } from 'vitest'
import { chmodSync, existsSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'node:fs'
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { Context } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id # Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00
import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
2026-07-21 03:08:35 +08:00
import { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import type { Agent } from '@deepseek-ai/dsh-agent'
2026-07-14 02:32:35 +08:00
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex'
import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
/**
* Full-loop Codex bridge tests with a mock model, the real loop and bash
* executor, and shell hooks from a temporary config. Covers regex matching,
* block-only decisions, and the five-event subset.
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
*/
const dirs: string[] = []
afterEach(() => { for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true }) })
function configDir(): string {
const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-codex-'))
dirs.push(dir)
return dir
}
function script(dir: string, name: string, body: string): string {
const path = join(dir, name)
writeFileSync(path, body)
chmodSync(path, 0o755)
return path
}
function writeHooks(dir: string, hooks: unknown): void {
writeFileSync(join(dir, 'hooks.json'), JSON.stringify({ hooks }))
}
async function harness(dir: string, adapter: MockAdapter): Promise<Context> {
const ctx = new Context()
await mountAgentLoopTestDependencies(ctx)
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'test-model' })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
2026-07-14 02:32:35 +08:00
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') { dispose(); resolve() }
})
})
}
2026-07-14 02:32:35 +08:00
function events(agent: Agent): SessionEvent[] { return [...agent.session.events] }
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
/** Poll `predicate` until true or the deadline passes (detached hook effects can't be awaited directly). */
async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise<void> {
const deadline = Date.now() + timeout
while (!predicate()) {
if (Date.now() > deadline) throw new Error('waitFor: condition not met before deadline')
await new Promise(r => setTimeout(r, interval))
}
}
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
describe('hooks-codex bridge', () => {
it('a PreToolUse hook (exit 2) denies a tool the regex matcher matches as a substring', async () => {
const dir = configDir()
const deny = script(dir, 'deny.sh', '#!/usr/bin/env bash\necho "codex blocked it" >&2\nexit 2\n')
// Codex regex matcher: "Bash" is /Bash/ — matches the tool name "Bash".
writeHooks(dir, { PreToolUse: [{ matcher: 'Bash', hooks: [{ type: 'command', command: deny }] }] })
const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')])
const ctx = await harness(dir, adapter)
let ran = false
2026-07-21 03:08:35 +08:00
ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } }))
Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id # Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup([{ type: 'text', text: 'run ls' }])
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
await waitForIdle(ctx, agent)
expect(ran).toBe(false)
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('codex blocked it'))).toBe(true)
expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.dialect === 'codex' && e.data.point === 'PreToolUse')).toBe(true)
})
it('a Stop hook (exit 2) forces the turn to continue with the reason as steering', async () => {
const dir = configDir()
// Block once with a marker; until the loop guard lands, an always-blocking
// hook would never let this test finish.
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
const marker = join(dir, 'fired')
const cont = script(dir, 'cont.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\necho "keep going: address the goal" >&2\nexit 2\n`)
writeHooks(dir, { Stop: [{ hooks: [{ type: 'command', command: cont }] }] })
const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')])
const ctx = await harness(dir, adapter)
Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id # Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup([{ type: 'text', text: 'go' }])
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('keep going: address the goal')
})
it('turn cancellation aborts and reaps a running UserPromptSubmit hook before idle', async () => {
const dir = configDir()
const pidFile = join(dir, 'pid')
const marker = join(dir, 'started')
const slow = script(dir, 'slow-prompt.sh', `#!/usr/bin/env bash\necho $$ > "${pidFile}"\ntouch "${marker}"\nsleep 30\n`)
writeHooks(dir, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: slow }] }] })
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.followup([{ type: 'text', text: 'cancel the hook' }])
await waitFor(() => existsSync(marker))
const pid = Number(readFileSync(pidFile, 'utf8').trim())
const idle = agent.whenIdle()
agent.cancel({ kind: 'user' })
await idle
expect(() => process.kill(pid, 0)).toThrow()
expect(adapter.requests).toHaveLength(0)
expect(events(agent).findLast(event => event.type === 'turn/end')).toMatchObject({
data: { reason: { kind: 'aborted' } },
})
expect(events(agent).some(event => event.type === 'hook/result' && event.data.point === 'UserPromptSubmit')).toBe(true)
})
2026-07-14 11:22:53 +08:00
it('only the five bridge-supported Codex events are honored — a SubagentStop entry is ignored', async () => {
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
const dir = configDir()
const s = script(dir, 'x.sh', '#!/usr/bin/env bash\nexit 2\n')
writeHooks(dir, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] })
const adapter = new MockAdapter([textResponse('fine')])
const ctx = await harness(dir, adapter)
Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id # Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup([{ type: 'text', text: 'go' }])
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1)
})
it('a missing config registers no hooks and does not crash', async () => {
const dir = configDir() // no hooks.json written
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(dir, adapter)
Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id # Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup([{ type: 'text', text: 'go' }])
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1)
})
it('disposing the bridge fiber removes its listeners (HMR safety)', async () => {
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
const dir = configDir()
// A leaked listener would let this blocking hook veto the prompt and log an invocation; a
// no-op hook would pass even when leaked.
const deny = script(dir, 'deny.sh', '#!/usr/bin/env bash\nexit 2\n')
writeHooks(dir, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: deny }] }] })
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
const adapter = new MockAdapter([textResponse('ok')])
const ctx = new Context()
await mountAgentLoopTestDependencies(ctx)
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' })
await fiber.dispose()
ctx.llm.registerAdapter(['mock'], adapter)
Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id # Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup([{ type: 'text', text: 'go' }])
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
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
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
})
it('disposing the bridge aborts a still-running SessionStart hook and drains to quiescence', async () => {
const dir = configDir()
const pidFile = join(dir, 'pid')
const marker = join(dir, 'started')
// Record the PID and marker before sleeping past the suite timeout. Disposal must abort the
// tracked process through `runPoint`, not await its natural exit.
const slow = script(dir, 'slow.sh', `#!/usr/bin/env bash\necho $$ > "${pidFile}"\ntouch "${marker}"\nsleep 30\n`)
writeHooks(dir, { SessionStart: [{ hooks: [{ type: 'command', command: slow }] }] })
const ctx = new Context()
await mountAgentLoopTestDependencies(ctx)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' })
ctx.llm.registerAdapter(['mock'], new MockAdapter([]))
const warn = vi.fn()
ctx.logger.warn = warn as never
Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id # Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00
ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // fires agent/session-start
await waitFor(() => existsSync(marker))
const pid = Number(readFileSync(pidFile, 'utf8').trim())
await fiber.dispose()
// Disposal reaches quiescence only after the aborted run settles and the process is reaped, so
// `kill(pid, 0)` must report ESRCH. Untracked fire-and-forget work would remain.
expect(() => process.kill(pid, 0)).toThrow()
// runHook resolves an aborted run as a non-blocking error, so draining must
// not log a rejected continuation.
expect(warn).not.toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed'))
})
feat(hooks): dsh-hooks-claude + dsh-hooks-codex bridges (hooks stack PR-F) The two bridge plugins that run a user's existing Claude Code / Codex hook config on the harness's typed interception seams, built on the shared dsh-hook-protocol library. A bridge is a faithfulness adapter, not a power tool: anything it does a native cordis plugin does more powerfully — the bridge exists only to run UNMODIFIED external hooks. - dsh-hooks-claude: CC dialect. Seven hook points (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop), CC per-event stdin payloads, env + ${CLAUDE_PLUGIN_ROOT}/ ${CLAUDE_PROJECT_DIR} substitution, literal-or-regex matcher. - dsh-hooks-codex: Codex dialect — a deliberate subset. Five hook points, always-regex matcher, snake_case payloads (turn_id/model, no trailing newline), no env/substitution, block-only decisions. Both map the neutral merged outcome onto the seam's typed Decision and stamp an explicit {kind:'plugin'} source on injected context (so it is never mislabeled as a user prompt). Config parse-failure is contained; only command hooks run. updatedInput is logged+warned (input rewrite deferred); the Stop loop-guard is deferred (TODO). Tests: per-file 100% — config-parse unit branches + per-seam mappings end-to-end through the REAL loop + REAL bash + REAL shell scripts (scripted mock model only) + a real-Loader export-shape guard. A keyless ACP snapshot scenario (hook-prompt-block) proves a UserPromptSubmit hook blocks a prompt end-to-end (rejected turn -> ACP cancelled, hook/* events in the log); a with-key e2e (hooks.e2e.ts) proves a PreToolUse hook blocks real bash (verified on disk). The snapshot normalizer now scrubs hook/result.durationMs. RFC: docs/rfc/implemented/feature/2026-06-30-hook-bridges.md
2026-07-01 04:22:00 +08:00
it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/inject/apply', () => {
expect('default' in HooksCodex).toBe(false)
expect(HooksCodex.name).toBe('hooks-codex')
expect(HooksCodex.inject).toEqual(['bash'])
const loader = Object.create(Loader.prototype) as Loader
const unwrapped = loader.unwrapExports(HooksCodex) as Record<string, unknown>
expect(unwrapped).toBe(HooksCodex)
expect(unwrapped.name).toBe('hooks-codex')
expect(unwrapped.inject).toEqual(['bash'])
expect(typeof unwrapped.apply).toBe('function')
})
})