mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-12 20:09:47 +00:00
1298bd4e1b
When `includeReasoning` is active (or `reasoningLevel` falls back to the model default), the agent emits reasoning blocks as separate reply payloads prefixed with "Reasoning:\n". Matrix has no dedicated reasoning lane, so these internal thinking traces leak into the chat as regular user-visible messages. Filter out pure-reasoning payloads (those starting with "Reasoning:\n" or a `<thinking>` tag) before delivery so internal reasoning never reaches the Matrix room. Fixes #24411 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| matrix | ||
| actions.ts | ||
| channel.directory.test.ts | ||
| channel.ts | ||
| config-schema.ts | ||
| directory-live.test.ts | ||
| directory-live.ts | ||
| group-mentions.ts | ||
| onboarding.ts | ||
| outbound.ts | ||
| resolve-targets.test.ts | ||
| resolve-targets.ts | ||
| runtime.ts | ||
| tool-actions.ts | ||
| types.ts | ||