Commit Graph
3 Commits
Author SHA1 Message Date
Marc-André Bombeck 21af344054 fix(ai): send max_completion_tokens to Azure OpenAI reasoning deployments
An OpenAI-compatible gateway entry pointed at an Azure OpenAI v1 endpoint
was treated as a generic gateway and sent max_tokens and temperature, which
a reasoning deployment refuses with a 400. An Azure v1 endpoint now takes
the api.openai.com contract for a reasoning model, and any gateway that
refuses max_tokens for a model is asked again with max_completion_tokens
and remembers it, which covers deployments named something of their own.

Refs #1304
2026-10-30 17:08:43 +01:00
Marc-André Bombeck a0fa4783c0 fix(ai): keep JSON mode when an endpoint rejects only reasoning_effort
An endpoint that does not know reasoning_effort answers with an unknown
parameter error, which the JSON-mode probe read as a refusal of
response_format and switched that base URL to plain prompts.
2026-10-04 10:48:35 +02:00
Marc-André Bombeck 0c7059804b feat(ai): resolve an OpenAI-compatible gateway as its own provider
The chain gains a seventh entry. It builds the OpenAI client against the
base URL the user saved, with the bearer they saved for it and the model
they named, and it reads none of the OpenAI columns — the pinned
api.openai.com arm stays pinned.

Host policy is the Local provider's, unchanged: a public host always, a
private one only where the operator allowlisted it, which is what a LAN
LiteLLM or vLLM needs. Egress keeps riding safeFetch.

The JSON-mode dialect the Local client learns per endpoint moves into a
shared module and now serves both clients, so a gateway that rejects
response_format is detected once and retried without it.

The entry stays out of the default chain: it can only resolve against a
base URL somebody configured.
2026-07-26 22:27:48 +02:00