4da2b99bc3
Round-2 Codex review of the round-1 fixes: - (A) The Codex plain-stdout→additionalContext fold (F1) was not gated on exit code, so a NON-clean hook's stdout still injected: a SessionStart `echo stale; exit 2` (an emit — cannot block) wrongly injected "stale", and a UserPromptSubmit `exit 1` (non-blocking error → falls through to context) did too. Gate the fold on `output.exitCode === 0`, matching the codec's own structured-stdout rule. Guard tests for both paths, proven red without the gate. - (B) The Codex "SessionStart no-context no-op" absence test was unsound (a completed turn doesn't prove the detached hook finished). It now touches a marker and waitFor()s it before asserting no context. - (B) Both HMR tests used a no-op `true` hook, so a leaked listener would still pass. They now use a BLOCKING (exit 2) UserPromptSubmit hook and assert the post-dispose turn is NOT blocked and logs no hook/invoked — a leaked listener fails loudly.
@deepseek-ai/dsh-hooks-claude
A cordis plugin that runs a user's existing Claude Code hook config (a hooks.json, or a settings file's hooks key) on the harness's canonical interception seams. It is the CC dialect half of the hooks subsystem: it owns CC's per-event stdin payloads, CC's env + ${CLAUDE_PLUGIN_ROOT}/${CLAUDE_PROJECT_DIR} substitution, and the mapping from a hook's neutral outcome onto the harness's typed Decisions. The dialect-agnostic primitives (matcher, exit-code/stdout codec, ctx.bash execution, most-restrictive merge, the hook/* events) come from @deepseek-ai/dsh-hook-protocol.
A native cordis plugin could do everything this bridge does — more powerfully, with typed returns and no serialization boundary. The bridge exists only to run UNMODIFIED external CC hooks faithfully; anything bespoke should be a native plugin on the same seams (see the interception-seams RFC).
Config
import type { Config } from '@deepseek-ai/dsh-hooks-claude'
const config: Config = {
configPath: '/path/to/hooks.json', // required: a hooks.json or a settings file with a `hooks` key
pluginRoot: '/path/to/plugin', // optional: replaces ${CLAUDE_PLUGIN_ROOT} in command strings
projectDir: '/path/to/project', // optional: replaces ${CLAUDE_PROJECT_DIR} AND set as the hook env var
defaultTimeoutMs: 600_000, // optional: per-hook timeout when a hook sets none (CC default)
}
In a cordis.yml:
- dsh-hooks-claude:
configPath: ./.claude/hooks.json
pluginRoot: ./.claude/plugins/my-plugin
projectDir: .
The config is parsed once at load. A read/parse failure is contained — the bridge logs a warning and registers nothing rather than crashing boot (a typo'd path must not take the agent down). Only type: 'command' hooks run; a prompt/agent/HTTP hook is parsed-and-skipped with a warning.
Hook points → seam Decisions
| CC hook | Harness seam | Mapping |
|---|---|---|
SessionStart |
agent/session-start (emit) |
additionalContext → agent.inject() into the new session (cannot block) |
UserPromptSubmit |
agent/prompt-submit (waterfall) |
deny → PromptDecision.block; additionalContext → allow with context |
PreToolUse |
tools/pre-execute (waterfall) |
deny → PreToolDecision.deny; ask → PreToolDecision.ask |
PostToolUse |
tools/post-execute (waterfall) |
deny → block with feedback; additionalContext → accept with context |
Stop |
agent/turn-continuation (waterfall) |
a blocking Stop hook forces continue, feeding its reason as next-step steering |
SubagentStart |
subagent/start (emit) |
additionalContext → agent.inject() into the live child |
SubagentStop |
subagent/end (emit) |
observe-only |
The matcher subject is the tool name (PreToolUse/PostToolUse), the session source (SessionStart), or the child's agent type (SubagentStart/SubagentStop); UserPromptSubmit/Stop ignore matchers. Multiple file-configured hooks on one point run serially, in config order, and fold most-restrictively (deny > ask > allow, see dsh-hook-protocol); serial keeps each hook's hook/invoked/hook/result pair adjacent in the log, and the fold is order-independent for the decision (see the RFC's "run serially, not concurrently" note).
Context source
Injected context carries an explicit { kind: 'plugin', plugin: 'hooks-claude' } source. agent.inject() defaults a missing source to { kind: 'user' }, which would mislabel plugin context as a user prompt — so the bridge always names itself.
Deferred (faithful-but-degraded)
updatedInput(tool-input rewrite) is logged + warned, not honored — input rewrite is a deferred consistency-design problem (the pre-tool-input-rewrite RFC).- Stop loop-guard. CC breaks an infinite force-continue with
stop_hook_active(true once a Stop hook has fired this run) plus a max-consecutive cap; both are deferred (TODO(stop-loop-guard)). Todaystop_hook_activeis alwaysfalse, so a Stop hook that unconditionally blocks would force-continue every step — a hook author must self-limit until the guard lands.