Ilia Breitburg 0eb3010e40 feat(transcription): configurable STT model + OpenRouter provider ...

Add a `transcriptionModel` channel setting and an OpenRouter transcription
backend so voice messages can be transcribed through OpenRouter's
speech-to-text endpoint (e.g. nvidia/parakeet-tdt-0.6b-v3, openai/whisper-1),
alongside the existing Groq/OpenAI Whisper providers.

- schema: add channels.transcriptionModel (None = provider default)
- providers/transcription: extract a shared POST/retry skeleton; add a
  JSON+base64 OpenRouterTranscriptionProvider; make the STT model a
  constructor param on all providers instead of hardcoding it
- channels: route transcriptionProvider="openrouter" and thread the model
  through the manager to each channel
- docs + tests

Only dedicated STT models work on OpenRouter's transcription endpoint;
chat LLMs (e.g. google/gemini-3.5-flash) are rejected there.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-09 04:01:37 +08:00

..

test_ant_ling_provider.py

feat(providers): add Ant Ling support

2026-05-18 22:13:52 +08:00

test_anthropic_long_request_fallback.py

test(provider): tidy Anthropic fallback imports

2026-05-01 23:59:24 +08:00

test_anthropic_merge_consecutive.py

fix(anthropic): also enforce leading-user + empty-array recovery

2026-04-21 01:32:32 +08:00

test_anthropic_stream_idle.py

feat(webui): stream live file edit events

2026-05-18 22:01:33 +08:00

test_anthropic_thinking.py

test(providers): cover reasoning_effort="none" and gemma auto-routing

2026-04-29 15:41:11 +08:00

test_anthropic_tool_result.py

fix: add regression tests for bare-dict coercion, update stale comment

2026-05-30 15:35:04 +08:00

test_azure_openai_provider.py

Remove check from the test

2026-06-05 01:17:34 +08:00

test_bedrock_provider.py

fix(provider): preserve Bedrock tool config for history

2026-05-12 20:59:01 +08:00

test_cached_tokens.py

fix(providers): normalize anthropic cached token usage

2026-04-02 12:51:45 +08:00

test_custom_provider.py

test(provider): cover duplicate streaming tool call ids

2026-05-21 12:28:24 +08:00

test_enforce_role_alternation.py

refactor(agent): tighten comments, extract constant, strengthen edge case test

2026-04-17 16:20:53 +08:00

test_extra_body_config.py

feat: Enhance OpenAI provider configuration with extraBody support and apiType validation

2026-05-25 01:23:36 +08:00

test_extra_query_config.py

feat(providers): add extra_query config for OpenAI-compatible providers

2026-06-09 03:18:14 +08:00

test_github_copilot_routing.py

feat: Add OpenAI API type configuration and update provider settings

2026-05-25 01:23:36 +08:00

test_image_generation.py

test(image): cover dropping null OpenAI image params

2026-06-06 19:35:46 +08:00

test_litellm_kwargs.py

fix(provider): preserve OpenAI-compatible tool call ids

2026-05-24 20:53:14 +08:00

test_llm_response.py

feat(webui): stream live file edit events

2026-05-18 22:01:33 +08:00

test_local_endpoint_detection.py

perf: optimize gateway cold start from ~6.9s to ~460ms (#3918)

2026-05-20 12:02:23 +08:00

test_longcat_provider.py

fix(provider): correct LongCat OpenAI base URL

2026-05-02 01:52:04 +08:00

test_minimax_anthropic_provider.py

docs(providers): explain MiniMax thinking endpoint

2026-04-16 01:00:45 +08:00

test_mistral_provider.py

refactor: replace litellm with native openai + anthropic SDKs

2026-03-25 01:58:48 +08:00

test_novita_provider.py

test(providers): cover Novita gateway fallback

2026-05-21 16:16:32 +08:00

test_openai_codex_provider.py

feat(desktop): polish desktop shell and shared WebUI surfaces (#4195)

2026-06-06 19:49:33 +08:00

test_openai_compat_timeout.py

refactor: preserve cold-start lazy boundaries

2026-05-20 12:02:23 +08:00

test_openai_responses.py

feat(desktop): polish desktop shell and shared WebUI surfaces (#4195)

2026-06-06 19:49:33 +08:00

test_prompt_cache_markers.py

fix(cache): stabilize tool ordering and cache markers for MCP

2026-04-01 17:07:22 +00:00

test_provider_error_metadata.py

fix(providers): surface clear arrearage warning on quota/billing errors (#3006)

2026-05-29 15:31:17 +08:00

test_provider_retry_after_hints.py

fix: robust Retry-After extraction across provider backends

2026-04-02 18:39:24 +00:00

test_provider_retry.py

fix(agent): address session and streaming concurrency bugs

2026-05-28 22:54:46 +08:00

test_provider_sdk_retry_defaults.py

feat(webui): refine output timeline and model controls (#4108)

2026-05-30 23:45:26 +08:00

test_providers_init.py

add native Bedrock Converse provider

2026-05-01 18:52:03 +08:00

test_reasoning_content.py

test: cover empty reasoning_content history preservation

2026-06-08 01:08:27 +08:00

test_responses_circuit_breaker.py

test: Add test to ensure responses API is used regardless of circuit breaker state

2026-05-25 01:23:36 +08:00

test_skywork_provider.py

fix(providers): point Skywork at APIFree agent endpoint

2026-05-20 12:33:03 +08:00

test_stepfun_reasoning.py

fix(provider): gate reasoning-to-content fallback behind spec flag

2026-04-26 20:11:08 +08:00

test_transcription.py

feat(transcription): configurable STT model + OpenRouter provider

2026-06-09 04:01:37 +08:00

test_xiaomi_mimo_thinking.py

refactor(providers): centralize gateway reasoning control

2026-05-21 14:41:50 +08:00