7 Commits

Author	SHA1	Message	Date
William Valentin	0bf69acafe	fix(lint): clear error-level violations across runtime and ui	2026-02-23 16:51:44 -08:00
William Valentin	3d59e5ea9d	Add localhost->127.0.0.1 fallback for transcription fetch	2026-02-22 20:26:38 -08:00
William Valentin	487f26e36d	Harden audio transcription fetch path with retries and timeout	2026-02-22 19:54:58 -08:00
William Valentin	db4e52dd7e	Harden audio transcription arg hydration and add rewrite audit event	2026-02-22 18:56:22 -08:00
William Valentin	948d4ac6d8	chore(lint): burn down remaining warnings to zero	2026-02-15 23:14:21 -08:00
William Valentin	0b44adbaea	fix(audio): add SSRF protection, MIME type fix, and tests for audio-transcribe tool ... - Add URL validation blocking localhost, private IPs, and non-http protocols - Use response Content-Type header instead of hardcoded audio/wav for URL downloads - Add 25 tests covering validation, SSRF, config errors, transcription paths, and error handling Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-11 21:57:45 -08:00
William Valentin	a875bcc4ae	feat(audio): add audio.transcribe tool with Whisper-compatible API support ... - Add createAudioTranscribeTool with OpenAI/Groq/Ollama/llama.cpp provider support - Refactor audio config schema to nested audio.enabled + audio.provider structure - Move audio tool registration to initTools() for conditional enablement - Fix duplication bug in audio-transcribe.ts URL download handler - Support base64 data and URL-based audio input with format detection	2026-02-11 18:13:19 -08:00