hobokenchicken b0bd1fd143 fix(gemini): ensure conversation starts with user role and add empty message check ...

Gemini API requires the first message to be from the 'user' role.
This commit ensures that:
- If a conversation starts with a 'model' (assistant) role, a placeholder 'user' message is prepended.
- 'tool' results are correctly mapped to 'user' role parts.
- Sequential messages with the same role are merged.
- Empty content requests are prevented in both sync and stream paths.

This fixes 400 Bad Request errors when clients (like opencode) send
message histories that don't match Gemini's strict role requirements.

2026-03-05 08:48:25 -05:00

..

deepseek.rs

fix: deepseek streaming 400 error (remove stream_options.include_usage)

2026-03-03 15:13:30 -05:00

gemini.rs

fix(gemini): ensure conversation starts with user role and add empty message check

2026-03-05 08:48:25 -05:00

grok.rs

feat: add cache token tracking and cache-aware cost calculation

2026-03-02 14:45:21 -05:00

helpers.rs

feat: add cache token tracking and cache-aware cost calculation

2026-03-02 14:45:21 -05:00

mod.rs

feat(providers): model-registry routing + Responses API support and streaming fallbacks for OpenAI/Gemini

2026-03-04 13:36:03 -05:00

ollama.rs

feat: add cache token tracking and cache-aware cost calculation

2026-03-02 14:45:21 -05:00

openai.rs

fix(providers): add registry routing, OpenAI Responses support and Gemini streaming fallbacks; compile fixes

2026-03-04 14:17:30 -05:00