Alishahryar1 2d2bf3de70 fix: replay reasoning_content for DeepSeek/NIM and expand provider smoke ...

- Add ReasoningReplayMode and top-level reasoning replay in OpenAI conversion
- DeepSeek/NIM request bodies use reasoning_content when thinking is enabled
- NIM retries without reasoning_content on 400 from upstream
- Per-provider smoke models (FCC_SMOKE_MODEL_*) independent of MODEL mapping
- Fix smoke model override parsing for owner/model names with slashes
- Live smoke: reasoning tool continuation uses synthetic thinking+tool history
- Tests and docs updated

2026-04-26 11:02:18 -07:00

..

anthropic

fix: replay reasoning_content for DeepSeek/NIM and expand provider smoke

2026-04-26 11:02:18 -07:00

__init__.py

Architecture refactor: core anthropic, runtime, smoke tiers, remove providers.common

2026-04-24 20:03:14 -07:00

rate_limit.py

Major refactor: API, providers, messaging, and Anthropic protocol

2026-04-26 03:01:14 -07:00