feat: complete audio matrix (Google/Vertex TTS, Google/ElevenLabs STT) (#835)

feat: expose new audio providers (Mistral STT/TTS, Deepgram TTS, xAI TTS) (#834)

feat: bump esperanto to 2.22.0 + Ollama num_ctx override (#833)

fix(api): use configured base_url for OpenAI model discovery (#784)

refactor: move tests from test_bug_fixes.py to proper test modules