mirror of
https://github.com/fabro-sh/fabro.git
synced 2026-09-14 23:22:51 +00:00
e7740b4acb
Normalize the readable reasoning providers already return into a canonical `ReasoningOutput` and carry it through the `agent.message` run event to storage, SSE, and JSONL. The shape is derived from the final response's canonical message content rather than stored a second time, so there is no duplicate source of truth and retried or replaced streaming buffers never become durable reasoning. OpenAI-compatible `reasoning_details` are now preserved verbatim as an opaque content part; only known readable members are normalized out of them, leaving encrypted entries for a later provider-aware replay phase. This phase is passive: no request parameters change, no capability guessing, and no newly observed provider field is replayed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| src | ||
| tests | ||
| build.rs | ||
| Cargo.toml | ||