LLM/moltbot
1
0
Fork 0
mirror of https://github.com/moltbot/moltbot.git synced 2026-04-23 22:55:24 +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

9
docs/plugins/building-plugins.md
View File

@@ -144,6 +144,15 @@ A single plugin can register any number of capabilities via the `api` object:
For the full registration API, see [SDK Overview](/plugins/sdk-overview#registration-api).
Hook guard semantics to keep in mind:
- `before_tool_call`: `{ block: true }` is terminal and stops lower-priority handlers.
- `before_tool_call`: `{ block: false }` is treated as no decision.
- `message_sending`: `{ cancel: true }` is terminal and stops lower-priority handlers.
- `message_sending`: `{ cancel: false }` is treated as no decision.
See [SDK Overview hook decision semantics](/plugins/sdk-overview#hook-decision-semantics) for details.
## Registering agent tools
Tools are typed functions the LLM can call. They can be required (always