- Strip store field from request body for local providers (Ollama, vLLM)
that reject unknown JSON fields with 400 errors
- Add Gemini 3.x model context windows and output token limits
(gemini-3-flash-preview, gemini-3.1-pro-preview, google/ OpenRouter variants)
- Preserve reasoning_content on assistant tool-call message replays
for providers that require it (Kimi k2.5, DeepSeek reasoner)
- Use conservative max_output_tokens fallback (4096/16384) for unknown
3P models to prevent vLLM/Ollama 400 errors from exceeding max_model_len
Consolidates fixes from: #258, #268, #237, #643, #666, #677
Co-authored-by: auriti <auriti@users.noreply.github.com>
Co-authored-by: Gustavo-Falci <Gustavo-Falci@users.noreply.github.com>
Co-authored-by: lttlin <lttlin@users.noreply.github.com>
Co-authored-by: Durannd <Durannd@users.noreply.github.com>
02599e0b6f