William Valentin 32ac4df20a feat(audio): add smart routing for native vs transcribed audio ...

- Create capabilities.ts with supportsAudioInput() detection
- Gemini, OpenAI, and GitHub Models get native audio passthrough
- Anthropic, Bedrock, Ollama, llama.cpp fall back to Whisper transcription
- routing.ts now checks model capability before deciding to transcribe
- Audio attachments are stripped for non-native models (only transcript text passed)
- Remove deprecated audioConfig from createMessageRouter deps (read from config.audio)

2026-02-11 18:20:10 -08:00

..

local

style: auto-fix ESLint issues (curly braces and formatting)

2026-02-11 10:30:24 -08:00

anthropic.test.ts

feat(models): add tool use support to AnthropicClient

2026-02-05 17:44:00 -08:00

anthropic.ts

feat(audio): add native audio support to type system and model clients

2026-02-11 18:17:33 -08:00

bedrock.test.ts

feat: add Gemini and Bedrock model providers

2026-02-06 16:51:32 -08:00

bedrock.ts

feat(audio): add native audio support to type system and model clients

2026-02-11 18:17:33 -08:00

capabilities.ts

feat(audio): add smart routing for native vs transcribed audio

2026-02-11 18:20:10 -08:00

costs.test.ts

feat: add P2 features — retry policy, prompt templating, usage tracking, tech debt cleanup

2026-02-06 15:12:35 -08:00

costs.ts

feat: implement Tier 3 features — lane queue, credential redaction, token dashboard, xAI, Voyage AI

2026-02-09 10:32:57 -08:00

gemini.test.ts

style: auto-fix ESLint issues (curly braces and formatting)

2026-02-11 10:30:24 -08:00

gemini.ts

feat(audio): add native audio support to type system and model clients

2026-02-11 18:17:33 -08:00

github.ts

feat(audio): add native audio support to type system and model clients

2026-02-11 18:17:33 -08:00

index.ts

feat(audio): add smart routing for native vs transcribed audio

2026-02-11 18:20:10 -08:00

media.test.ts

fix: normalize message roles for local model backends (llama.cpp, Ollama)

2026-02-10 22:04:17 -08:00

media.ts

feat(audio): add native audio support to type system and model clients

2026-02-11 18:17:33 -08:00

openai.test.ts

test: add stopReason edge case tests; update state.json with recent fixes

2026-02-11 09:51:19 -08:00

openai.ts

feat(audio): add native audio support to type system and model clients

2026-02-11 18:17:33 -08:00

retry.test.ts

style: auto-fix ESLint issues (curly braces and formatting)

2026-02-11 10:30:24 -08:00

retry.ts

feat: add log-level system to suppress noisy fallback debug output

2026-02-09 21:23:07 -08:00

router.test.ts

style: auto-fix ESLint issues (curly braces and formatting)

2026-02-11 10:30:24 -08:00

router.ts

style: auto-fix ESLint issues (curly braces and formatting)

2026-02-11 10:30:24 -08:00

types.test.ts

feat: add tool framework foundation (types, registry, executor, shell tool, model types, SOUL.md)

2026-02-05 17:39:40 -08:00

types.ts

feat(audio): add native audio support to type system and model clients

2026-02-11 18:17:33 -08:00