Maurice bac968c0bf fix(ai): retry chat requests with reasoning_effort none when a server refuses tools with reasoning ...

Azure AI Foundry reasoning deployments behind an "Own server" connection
reject function tools on /v1/chat/completions at their default reasoning
effort and answer HTTP 400 naming reasoning_effort. The Responses API
switch from #2792 only covers direct OpenAI keys, so the assistant could
not run on these deployments at all.

The chat client still never sends reasoning_effort, so servers that do not
know the field (Ollama, LM Studio, vLLM, OpenRouter) see unchanged
requests. When a request with tools is refused over reasoning_effort, it
goes out once more with reasoning_effort "none", and the rest of the turn
keeps sending it. The refused field is now carried on AiProviderError
instead of only being logged.

Fixes #3043

2026-11-11 21:26:20 +00:00

..

e2e

fix(reservations): keep day_id on partial updates of time-only bookings

2026-11-10 10:05:22 +01:00

fixtures

fix(service-identity): call the dialect self-check's scrypt input inputSha256

2026-10-29 20:04:40 +01:00

helpers

fix(storage): release a deleted journey's photos and a deleted list's images, and keep one bad key from stopping a category

2026-11-05 14:36:22 +01:00

integration

test(vacay): the holiday provider cases live in the existing suites again

2026-11-11 21:06:29 +00:00

unit

fix(ai): retry chat requests with reasoning_effort none when a server refuses tools with reasoning

2026-11-11 21:26:20 +00:00

websocket

style: format server and shared with prettier

2026-10-10 21:23:37 +02:00

build-schema-snapshot.ts

refactor(db): open the database through a DatabaseLifecycle provider

2026-10-08 18:38:28 +02:00

global-setup.ts

refactor(db): open the database through a DatabaseLifecycle provider

2026-10-08 18:38:28 +02:00

setup.console-noise.ts

style: format server and shared with prettier

2026-10-10 21:23:37 +02:00

setup.ts

style: format server and shared with prettier

2026-10-10 21:23:37 +02:00