jaeminbird 5bd07865a3 fix(anthropic): honor object tool_choice on /v1/messages ...

Anthropic sends tool_choice as an object: {"type": "auto" | "any" |
"none"} or {"type": "tool", "name": ...}. The endpoint only read the
"tool" object, so {"type": "none"} still offered the tools and
{"type": "any"} did not require a call. The object was also forwarded
to the backend unchanged, and the llama.cpp backend turns any object
tool_choice into "required", so even {"type": "auto"} forced a tool
call there. Read the object form, and forward the OpenAI equivalent.

Assisted-by: Claude:claude-opus-5-5
Signed-off-by: jaeminbird <jaeminbird@gmail.com>

2026-10-29 01:27:48 -04:00

..

_index.en.md

feat(chat): local-ai chat is now a terminal agent (#11291)

2026-08-02 09:23:26 +02:00

3d-animation.md

feat(kimodo): Add observability hooks (#12184)

2026-09-22 07:06:32 +00:00

3d-generation.md

feat: Add kimodo.cpp and 3D animation API/UI (#12095)

2026-09-18 06:12:03 +01:00

addons.md

feat(ui): review add-on and backend upgrades before they run (#12948)

2026-10-28 15:10:36 +01:00

agent-actions.md

docs: onboarding overhaul, dedup, and error docs (#7711) (#10895)

2026-07-17 22:08:20 +02:00

agents.md

feat(ui): redesign the web UI around a shared kit and a calm palette (#12526)

2026-10-08 22:03:07 +02:00

api-discovery.md

feat(backends): --disable-backend-install disables backend downloads. (#12754)

2026-10-22 17:58:53 +02:00

audio-classification.md

feat(diarization): return sound events with include_sounds (#12544)

2026-10-07 14:10:45 +02:00

audio-cpp.md

chore: ⬆️ Update 0xShug0/audio.cpp to 96269554d00621fb0fca6b52b58919749eba1c8d (#12598)

2026-10-12 09:35:25 +02:00

audio-diarization.md

feat(diarization): return sound events with include_sounds (#12544)

2026-10-07 14:10:45 +02:00

audio-to-text.md

fix(audio): record transcription usage and traces (#12546)

2026-10-07 16:57:23 +02:00

audio-transform.md

fix(audio): reject incompatible transform streams (#11565)

2026-08-18 09:03:16 +02:00

authentication.md

feat(ui): offer model MCP servers to non-admin chat users (#12660)

2026-10-19 23:43:47 +02:00

backends.md

feat(ui): review add-on and backend upgrades before they run (#12948)

2026-10-28 15:10:36 +01:00

benchmark.md

feat(cli): benchmark configured text models (#12020)

2026-09-13 19:06:43 +02:00

chat-history.md

feat(chat-history): server-side chat history with tombstones (follow-up to #9902) (#12663)

2026-10-19 22:52:07 +02:00

chat.md

feat(chat-history): server-side chat history with tombstones (follow-up to #9902) (#12663)

2026-10-19 22:52:07 +02:00

constrained_grammars.md

feat(api): add text moderation endpoint (#11316)

2026-08-03 18:03:46 +02:00

context-compression.md

feat(chat): add end-to-end context compression (#11556)

2026-08-18 11:31:03 +00:00

decisions.md

fix(backends): flag a llama-cpp backend that predates native decisions (#12733)

2026-10-16 10:41:45 +02:00

diagnostics.md

fix(chat): defer model fallback until after binding (#12621)

2026-10-11 00:26:40 +02:00

distributed_inferencing.md

feat(ui): redesign the web UI around a shared kit and a calm palette (#12526)

2026-10-08 22:03:07 +02:00

distributed-mode.md

fix(proxy): propagate model env and accept direct keys (#12940)

2026-10-27 10:27:45 +01:00

embeddings.md

fix: stop listing the models directory on request paths and cache GGUF header reads (#12683)

2026-10-14 01:06:14 +02:00

face-recognition.md

feat(addons): installable add-ons foundation and the Tables add-on (#12702)

2026-10-22 17:57:19 +02:00

fine-tuning.md

feat(addons): run the add-on owner as its own workload (#12867)

2026-10-24 14:29:39 +02:00

forecast.md

feat(backends): timestral.cpp forecast backend and /v1/forecast API (#12885)

2026-10-24 22:47:04 +02:00

gpt-vision.md

docs: onboarding overhaul, dedup, and error docs (#7711) (#10895)

2026-07-17 22:08:20 +02:00

GPU-acceleration.md

docs: fix 11 dead links in the documentation (#12320)

2026-09-28 08:33:15 +02:00

image-generation.md

feat(images): add ESRGAN upscaling and Studio workflow (#12620)

2026-10-11 00:30:09 +02:00

interleaved-thinking.md

docs: onboarding overhaul, dedup, and error docs (#7711) (#10895)

2026-07-17 22:08:20 +02:00

localai-assistant.md

feat(ui): redesign the web UI around a shared kit and a calm palette (#12526)

2026-10-08 22:03:07 +02:00

mcp.md

feat(agents): per-model output cap for agent job completions

2026-10-25 09:21:58 +00:00

mlx-distributed.md

docs: onboarding overhaul, dedup, and error docs (#7711) (#10895)

2026-07-17 22:08:20 +02:00

model-aliases.md

feat(config): let model aliases carry an opt-in profile block (system prompt, MCP, client tools) (#12661)

2026-10-19 23:42:40 +02:00

model-failover.md

feat(ui): redesign the web UI around a shared kit and a calm palette (#12526)

2026-10-08 22:03:07 +02:00

model-gallery.md

feat(gallery): add Nemotron Bolt E4B variants (#12880)

2026-10-24 23:50:41 +02:00

moderation.md

feat(api): add text moderation endpoint (#11316)

2026-08-03 18:03:46 +02:00

motion.md

feat(motion): add GEM-X backend and duplex streaming API

2026-10-13 08:27:24 +00:00

nemo-speech-cpp.md

[gallery] feat: add Orukeet to the NeMo speech backend (#11998)

2026-09-13 01:51:19 +02:00

object-detection.md

fix(ci): repair nightly backend dep bumps for renamed localai-org repos (#11012)

2026-07-21 09:40:10 +02:00

openai-functions.md

test(vllm): isolate streaming parser fixtures

2026-10-25 08:50:00 +00:00

openai-realtime.md

realtime: announce speakers in transcription-only sessions (#12871)

2026-10-24 00:07:02 +02:00

quantization.md

feat(addons): run the add-on owner as its own workload (#12867)

2026-10-24 14:29:39 +02:00

reranker.md

docs: onboarding overhaul, dedup, and error docs (#7711) (#10895)

2026-07-17 22:08:20 +02:00

rkllm.md

docs: add RKLLM Rockchip NPU integration

2026-09-11 21:49:51 +00:00

runtime-settings.md

feat(galleryop): limit concurrent backend operations (#12888)

2026-10-25 00:26:45 +02:00

stores.md

fix(qdrant-store): warn about non-COSINE metrics and document them

2026-10-13 08:13:55 +00:00

studio.md

feat(addons): add-ons UI direction B: one name, Turn on and Turn off, preview pane (#12858)

2026-10-23 15:25:37 +02:00

tables.md

feat(addons): add-ons UI direction B: one name, Turn on and Turn off, preview pane (#12858)

2026-10-23 15:25:37 +02:00

terminal-agent.md

feat(chat): local-ai chat is now a terminal agent (#11291)

2026-08-02 09:23:26 +02:00

text-generation.md

fix(anthropic): honor object tool_choice on /v1/messages

2026-10-29 01:27:48 -04:00

text-to-audio.md

feat(addons): installable add-ons foundation and the Tables add-on (#12702)

2026-10-22 17:57:19 +02:00

tracing.md

feat(ui): redesign the web UI around a shared kit and a calm palette (#12526)

2026-10-08 22:03:07 +02:00

video-generation.md

stablediffusion-ggml: run MiniMax-H3 video with references and add its gallery entries (#12668)

2026-10-13 17:58:21 +02:00

vllm-cpp.md

chore(vllm-cpp): bump to 967883486 (ABI v30), add hf_overrides and Tev1 entries, fix vllm-cpp gallery installs (#12379)

2026-09-30 20:22:49 +02:00

voice-activity-detection.md

feat(parakeet-cpp): encoder fingerprint for speaker naming, VAD trim and word filter options, pin bump (#12491)

2026-10-05 15:57:16 +02:00

voice-recognition.md

feat(addons): installable add-ons foundation and the Tables add-on (#12702)

2026-10-22 17:57:19 +02:00

whisper-medusa.md

feat(backends): add Whisper-Medusa transcription

2026-09-11 21:48:07 +00:00