Some OpenRouter reasoning models (e.g. nvidia/nemotron-3-super-120b-a12b:free) emit chain-of-thought into message.content, so even strict prompts like "Reply with exactly: PONG" produce visible reasoning preamble. Add a default model_list entry that sets extra_body.reasoning.exclude=true so OpenRouter strips reasoning server-side, plus a config test and docs note covering the symptom, cause, and per-model tradeoff. No global auto-injection: reasoning visibility stays a per-model choice. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| debug.fr.md | ||
| debug.ja.md | ||
| debug.md | ||
| debug.ms.md | ||
| debug.pt-br.md | ||
| debug.vi.md | ||
| debug.zh.md | ||
| README.md | ||
| troubleshooting.fr.md | ||
| troubleshooting.ja.md | ||
| troubleshooting.md | ||
| troubleshooting.ms.md | ||
| troubleshooting.pt-br.md | ||
| troubleshooting.vi.md | ||
| troubleshooting.zh.md | ||
Operations
Operational docs for debugging, diagnosis, and production troubleshooting.
- Troubleshooting: common failures, symptoms, and recovery steps.
- Debugging PicoClaw: logs, runtime visibility, and debugging workflow.