mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
9ca31ab193
The emit-shaped hook points (SessionStart, SubagentStart, SubagentStop) run fire-and-forget: no seam awaits the run chain, so disposing a bridge could strand a live hook process and let a late continuation inject into a disposed context. The floating continuation also made the coverage gate racy: the only coverage of the SubagentStart continuation's no-context branch arm rode on an un-awaited .then, and on a loaded CI runner the fork's per-file coverage snapshot beat it — master run 28798191671 failed the 100% branch gate on hooks-claude/src/index.ts at 99.03% (uncovered line 336) with the identical tree passing the PR run three minutes earlier. New shared primitive createDetachedRuns() in dsh-hook-protocol: a bridge tracks each detached run chain, passes the tracker's abort signal to runHook, and registers drain() as its effect disposer — drain aborts still-running hook processes (a kill via the bash seam, not a wait out to the 10-minute default hook timeout), then resolves once every chain has settled. fiber.dispose() resolving now means the bridge's detached work is quiescent (docs/defensive-patterns.md). The subagent marker test disposes the bridge as its sync point, so the formerly racy branch arm is executed deterministically before the file's coverage snapshot; new tests pin abort-on-dispose promptness for both bridges and the tracker's settle/drain contract in hook-protocol.
62 lines
4.7 KiB
Markdown
62 lines
4.7 KiB
Markdown
# @deepseek-ai/dsh-hooks-codex
|
|
|
|
A cordis plugin that runs a user's existing **Codex** `hooks.json` on the harness's canonical interception seams. The **Codex dialect** half of the hooks subsystem. The dialect-agnostic primitives come from [`@deepseek-ai/dsh-hook-protocol`](../hook-protocol/README.md); this bridge owns the Codex-specific payloads, matcher mode, and decision mapping.
|
|
|
|
Codex's hook protocol is a deliberate **subset** of Claude Code's (same `hooks.json` shape):
|
|
|
|
- **Five hook points only:** `PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop` — no subagent / notification / compaction hooks.
|
|
- **Regex-only matchers** (no literal fast path; the matcher is always an unanchored regex).
|
|
- **snake_case stdin payloads** with `turn_id`/`model` extras, written **without** a trailing newline.
|
|
- **No env vars and no command substitution** (a literal `${…}` in a command survives verbatim).
|
|
- **A block-only decision model** — `allow`/`ask` are not honored; a hook can only block, never pre-approve.
|
|
|
|
A native cordis plugin could do everything this bridge does, more powerfully; the bridge exists only to run UNMODIFIED external Codex hooks faithfully (see [the interception-seams RFC](../../../docs/rfc/implemented/feature/2026-06-30-interception-seams.md)).
|
|
|
|
## Config
|
|
|
|
```ts
|
|
import type { Config } from '@deepseek-ai/dsh-hooks-codex'
|
|
const config: Config = {
|
|
configPath: '/path/to/.codex/hooks.json', // required
|
|
model: 'deepseek-v4', // optional: stamped on every payload (Codex includes `model`)
|
|
defaultTimeoutMs: 600_000, // optional: per-hook timeout when a hook sets none
|
|
stderrSummaryMaxChars: 500, // optional: char cap on the hook/result event's persisted stderr summary
|
|
}
|
|
```
|
|
|
|
In a `cordis.yml`:
|
|
|
|
```yaml
|
|
- dsh-hooks-codex:
|
|
configPath: ./.codex/hooks.json
|
|
model: deepseek-v4
|
|
```
|
|
|
|
The config is parsed **once** at load. `configPath` is **process-level** — a relative path resolves against the process launch cwd at load time, not per-session (`TODO(per-session-hook-config)`). A read/parse failure is contained (logs + registers nothing). Only sync `type: 'command'` hooks run — a non-command or `async: true` hook is parsed-and-skipped with a warning. A hook accepts `timeout` or the `timeoutSec` alias; one that sets neither runs under the protocol's reference default (`DEFAULT_HOOK_TIMEOUT_MS` from `dsh-hook-protocol`, 10 minutes). Events outside the five Codex points are dropped at parse.
|
|
|
|
The hooks themselves run in the agent's session workspace: for the agent-scoped points the bridge passes the session's `cwd` as the hook process's working directory, so a hook operates in the user's project tree, not the server launch dir.
|
|
|
|
## Hook points → seam Decisions
|
|
|
|
| Codex hook | Harness seam | Mapping |
|
|
|---|---|---|
|
|
| `SessionStart` | `agent/session-start` (emit) | a plain-stdout hook's output → additionalContext → `agent.inject()` |
|
|
| `UserPromptSubmit` | `agent/prompt-submit` (waterfall) | `block` (exit 2) → `PromptDecision.block`; additionalContext-only → delegate via `next()` then fold context onto the downstream decision |
|
|
| `PreToolUse` | `tools/pre-execute` (waterfall) | `block` → `PreToolDecision.deny` (no `allow`/`ask`) |
|
|
| `PostToolUse` | `tools/post-execute` (waterfall) | `block` → `block` with feedback; additionalContext-only → delegate via `next()` then fold context onto the downstream decision |
|
|
| `Stop` | `agent/turn-continuation` (waterfall) | a blocking Stop hook forces `continue` with the reason as next-step steering |
|
|
|
|
A tool call's payload carries the real `tool_name` (the same value the matcher tests) and Codex's `tool_input: { command }` shape (the `command` arg when present, else `''`). The matcher subject is the tool name (`PreToolUse`/`PostToolUse`) or the session source (`SessionStart`); `UserPromptSubmit`/`Stop` ignore matchers.
|
|
|
|
`SessionStart` — the one emit point — runs detached; each run chain is tracked, and disposing the bridge aborts a still-running hook process, then drains the continuation before the dispose resolves (`createDetachedRuns` in `dsh-hook-protocol`).
|
|
|
|
## Context source
|
|
|
|
Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-codex' }` source (`agent.inject()` would otherwise default it to `{ kind: 'user' }`).
|
|
|
|
## Deferred
|
|
|
|
**Stop loop-guard** (`TODO(stop-loop-guard)`): as in CC, a Stop hook that unconditionally blocks would force-continue every step (`stop_hook_active` is always `false` here); the loop-guard is deferred. A hook author must self-limit until it lands.
|
|
|
|
**`systemMessage`**: a hook's user-facing warning is logged + warned, not surfaced — there is no user-message channel on these seams yet (only model-facing `additionalContext`).
|