vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-04 13:50:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Plugins: enforce terminal hook decision semantics for tool/message guards (#54241)

Browse Source 
* Plugins: enforce terminal hook decision policies

* Tests: assert terminal hook behavior in integration paths

* Docs: clarify terminal hook decision semantics

* Docs: add hook guard semantics to plugin guides

* Tests: isolate outbound format label expectations

* changelog

Signed-off-by: joshavant <830519+joshavant@users.noreply.github.com>

---------

Signed-off-by: joshavant <830519+joshavant@users.noreply.github.com>
This commit is contained in:
Josh Avant
2026-03-25 00:11:13 -05:00
committed by GitHub
parent 5a5c5d4cde
commit 10161c2d79
10 changed files with 435 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/concepts/agent-loop.md
View File

@@ -92,6 +92,13 @@ These run inside the agent loop or gateway pipeline:
- **`session_start` / `session_end`**: session lifecycle boundaries.
- **`gateway_start` / `gateway_stop`**: gateway lifecycle events.
Hook decision rules for outbound/tool guards:
- `before_tool_call`: `{ block: true }` is terminal and stops lower-priority handlers.
- `before_tool_call`: `{ block: false }` is a no-op and does not clear a prior block.
- `message_sending`: `{ cancel: true }` is terminal and stops lower-priority handlers.
- `message_sending`: `{ cancel: false }` is a no-op and does not clear a prior cancel.
See [Plugin hooks](/plugins/architecture#provider-runtime-hooks) for the hook API and registration details.
## Streaming + partial replies