Make provider readiness follow the selected model - #1074
Open
koko3tallah wants to merge 2 commits into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #918.
The early TUI check currently evaluates Anthropic before the switchboard has resolved the model, then the runner trusts that cached result. That can stop an OpenAI-only run because Anthropic happens to be degraded.
This keeps the early infrastructure checks, but moves provider gating to the point immediately after the final run binding is resolved. The fresh check targets the exact vendor API component selected by the model:
Claude API (api.anthropic.com)ResponsesOnly a confirmed component outage blocks an interactive run. Degraded status, missing components, and status-page request failures stay advisory. CI and headless runs keep the existing advisory behavior.
Coverage includes the original cache seam: a stored TUI result does not prevent an OpenAI binding from receiving a fresh OpenAI provider check.
Verified with:
pnpm test(1,755 tests)pnpm buildpnpm fix