Maurice f6976d5cec fix(assistant): send OpenAI reasoning models on an API key to the Responses API ...

gpt-5.6-sol, gpt-6.1-sol and the other reasoning models refuse function tools
on Chat Completions, so every assistant message on such a model came back as
HTTP 400. An OpenAI connection whose model is from the o-series or GPT-5 and
later now goes through the Responses API, the client a ChatGPT plan already
uses, with the key as its bearer token and no token refresh on a 401. Older
models and the -chat variants stay on Chat Completions.

Closes #2792

2026-10-25 16:55:39 +01:00

..

e2e

fix(assistant): let an admin switch the model of a shared ChatGPT plan

2026-10-25 16:29:31 +01:00

fixtures

feat(ski-routing): plan ski tours on the piste graphs of TREK Places

2026-10-20 21:13:48 +02:00

helpers

feat(assistant): hike, walk and route cards with their lines on the map, and "Plan this"

2026-10-22 21:34:14 +00:00

integration

feat(journey): photo links tell every tab, move between entries, and gain MCP tools

2026-10-24 22:54:45 +02:00

unit

fix(assistant): send OpenAI reasoning models on an API key to the Responses API

2026-10-25 16:55:39 +01:00

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