Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

Merge remote-tracking branch 'origin/master' into codex/agent-session-jsonl-location

Browse Source 
# Conflicts:
#	docs/config-catalog.md
#	docs/module-graph.md
#	docs/rfc/INDEX.md
#	packages/README.md
#	packages/bash/bash-local/README.md
#	packages/bash/bash/README.md
#	packages/bash/tool-bash/README.md
#	packages/bash/tool-bash/tests/tools.spec.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/examples/acp-demo/src/index.ts
#	packages/examples/acp-demo/tests/acp-agent.spec.ts
#	packages/examples/agent-spine-demo/README.md
#	packages/examples/agent-spine-demo/src/index.ts
#	packages/examples/agent-spine-demo/tests/agent-core.spec.ts
#	packages/examples/stdio-demo/src/index.ts
#	packages/examples/stdio-demo/tests/stdio-agent.spec.ts
#	packages/util/README.md
#	pnpm-lock.yaml
#	tsconfig.build.json
#	tsconfig.json
This commit is contained in:
Yichen Jiang
2026-07-17 18:35:48 +08:00
parent 027af418a2 3412eab518
commit 7d85d3027d
230 changed files with 13315 additions and 453 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/hooks/hooks-codex/README.md
+2 -2
View File
@@ -41,9 +41,9 @@ The hooks themselves run in the agent's session workspace: for the agent-scoped
| 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 |
| `UserPromptSubmit` | `agent/prompt-submit` (waterfall) | `block` (exit 2) → `PromptDecision.block`; additionalContext-only → delegate via `next()` then prepend a separately sourced context to downstream `additionalContexts` |
| `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 (a Code Mode sub-call’s context is dropped by the run_code bridge — see [the pipeline doc](../../../docs/tool-execution-pipeline.md)) |
| `PostToolUse` | `tools/post-execute` (waterfall) | `block` → `block` with feedback; additionalContext-only → delegate via `next()` then prepend a separately sourced context to the downstream decision; Code Mode defers sub-call contexts until the outer `run_code` result |
| `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.