Cameron Cordes cab867da60 Serialize /tts/speech with a single permit; 429 when busy ...

The Chatterbox wrapper has no internal lock or cancellation, so concurrent
synth requests contend on the single GPU and abandoned (timed-out) jobs
cascade into stacked slowness. Gate synthesis behind a one-permit semaphore
and fast-fail concurrent requests with 429 instead of queueing.

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

2026-06-03 14:02:56 -04:00

..

apollo_client.rs

EXIF GPS write: POST /image/exif/gps via exiftool

2026-04-28 22:25:40 +00:00

backend.rs

fix: prevent hybrid mode from leaking OpenRouter model to local llamacpp client

2026-05-26 09:55:16 -04:00

clip_client.rs

clip-search: fmt + clippy clamp + test AppState arg

2026-05-15 16:10:52 -04:00

daily_summary_job.rs

…

face_client.rs

style: cargo fmt

2026-04-30 21:16:34 +00:00

handlers.rs

Add reconnectable async chat-turn flow with in-memory TurnRegistry

2026-05-29 19:50:25 -04:00

insight_chat.rs

Exclude inlined image bytes from chat context budget

2026-05-30 11:51:57 -04:00

insight_generator.rs

fix: persist token counts and fix agentic insight_id mapping

2026-05-27 13:47:57 -04:00

llamacpp.rs

Give TTS synthesis its own (longer) request timeout

2026-06-03 10:25:06 -04:00

llm_client.rs

…

mod.rs

Add TTS endpoints backed by Chatterbox via llama-swap

2026-06-02 22:04:42 -04:00

ollama.rs

chore: resolve all clippy warnings and formatting

2026-05-27 13:13:48 -04:00

openrouter.rs

feat(ai): rerank timing + think:false + OpenRouter error detail

2026-04-24 16:19:45 -04:00

sms_client.rs

Add contact name filter to SMS search tool + misc improvements

2026-05-25 21:46:18 -04:00

tts.rs

Serialize /tts/speech with a single permit; 429 when busy

2026-06-03 14:02:56 -04:00

turn_registry.rs

Add reconnectable async chat-turn flow with in-memory TurnRegistry

2026-05-29 19:50:25 -04:00