Represent tool results as tool-role messages and migrate released wrappers without losing outer own JSON fields, call identity, error state, or writer field order. Refuse nested or wrapper-only information that has no lossless current representation before successor publication. Validate current event relationships directly instead of projecting V4 data back into V3. Keep lifecycle, PTC, title/command, compaction, system-field and retired-syntax checks on catalog restoration and ordinary JSONL opens. The Worker JSON equality helper must inspect own keys so it cannot admit PTC arguments that Node rejects. Keep the source role change, required native admission and consumer fixture updates in one complete review layer. Explain shared-type changes in the persistence record and the native reader rationale in its existing note. Use checked branded fixture identities and discriminant narrowing instead of unknown double casts; fixture values and assertions remain intact. This recomposes the original tool-role work by _Kerman with the independently validated migration and admission repairs by Tianyi Cui. Frozen generations and snapshot input version selection are retained. Co-authored-by: Tianyi Cui <[email protected]>
description, kind
| description | kind |
|---|---|
| The hooks group map: run existing Claude Code and Codex shell-hook configs during agent runs, for users and maintainers navigating the group. | package-group |
packages/hooks
English | 中文
Summary
The hooks group lets agent runs reuse shell hooks written for Claude Code or Codex. Point the matching integration at an existing hooks.json to run supported command hooks when sessions start, prompts arrive, tools run, or runs stop. These hooks can block prompts or tool calls with model-visible messages, add conversation context, or require the run to continue. Choose this group to preserve existing hook configurations; each integration supports only the command-hook subset documented by its source tool.
Table of Contents
Packages
| Package | Role | Shape |
|---|---|---|
hook-protocol |
Shared hook engine both bridges use; never configured directly | library |
hooks-claude-code |
Run your existing Claude Code hooks.json hooks during agent runs |
plugin |
hooks-codex |
Run your existing Codex hooks.json hooks during agent runs |
plugin |
Related documentation
- Interception extension-points Agent Note — the typed-Decision surface the bridges program against.
- Hook bridges Agent Note — the bridge design and its decision mapping.
- Hook protocol library Agent Note — what the shared library owns and why.
Dev Note
Working context for maintainers — click to expand
None.