lukaszraczylo 5476aefb11 feat(llm): implement native gemini generateContent provider (vision + audio) ...

- Replace stub Vision/Transcribe with real REST implementation
- Endpoint: POST {base}/v1beta/models/{model}:generateContent
- Auth via x-goog-api-key header
- Vision: text part + inline_data per image (mime_type from Image.MediaType)
- Transcribe: transcription prompt + inline_data audio (default audio/wav)
- Model selection: opts.Model > audioModel (transcribe) > c.model
- maxTokens mapped to generationConfig.maxOutputTokens when non-zero
- Add httptest coverage: TestGeminiVision, TestGeminiTranscribe
- Re-enable gemini in tools.go audio capability check

2026-06-07 14:24:16 +01:00

..

server.go

feat(mcp): tool registration and handlers for solve+stealth+detect

2026-06-07 13:26:00 +01:00

tools_test.go

feat(mcp): tool registration and handlers for solve+stealth+detect

2026-06-07 13:26:00 +01:00

tools.go

feat(llm): implement native gemini generateContent provider (vision + audio)

2026-06-07 14:24:16 +01:00