Brummel c5535c0848 Add reasoning_effort to chat request ...

Introduce a new field `reasoning_effort` to the `ChatRequest` struct.
This field, set to "medium" by default, allows tuning LLM reasoning
depth to balance hallucination risk against latency and token cost. This
setting is specifically for Ionos' GPT-OSS reasoning models and is
ignored by other OpenAI-compatible models.

2026-04-30 23:52:40 +02:00

.claude

feat: Add scheduled_tasks.lock file

2026-04-26 14:36:22 +02:00

canary

feat: Add Canary ASR model service and sweep experiments

2026-04-30 14:30:12 +02:00

client-desktop

feat: Add web UI for manual oneliner overrides

2026-04-26 17:17:09 +02:00

docs

feat: Add Canary ASR model service and sweep experiments

2026-04-30 14:30:12 +02:00

doctate-client-core

feat: Add inline oneliner editing

2026-04-26 16:35:14 +02:00

doctate-common

Run audio analysis and Whisper concurrently

2026-04-27 16:18:45 +02:00

experiments

Refactor: Remove unused Whisper variants

2026-04-30 16:56:12 +02:00

scripts

Refactor: Remove unused Whisper variants

2026-04-30 16:56:12 +02:00

server

Add reasoning_effort to chat request

2026-04-30 23:52:40 +02:00

tests/fixtures/dictations

Refactor: Remove unused Whisper variants

2026-04-30 16:56:12 +02:00

watch/wearos

Feat: Add replay-gain to audio playback

2026-04-27 17:08:10 +02:00

whisper

Add section on suppressed tokens for digits

2026-04-28 00:56:05 +02:00

.gitignore

feat(server): split runtime knobs out of .env into settings.toml

2026-04-27 11:21:23 +02:00

Cargo.lock

feat: server-side CSRF token validation

2026-04-22 09:59:17 +02:00

Cargo.toml

feat: Add doctate-client-core crate

2026-04-18 10:03:40 +02:00

CLAUDE.md

Refactor timestamp generation to use helper function

2026-04-27 14:53:35 +02:00

S

Description

No description provided

7.4 MiB

Languages

Rust 74%

Kotlin 12.7%

HTML 4.9%

Python 4.1%

Shell 3.8%

Other 0.5%