Repository navigation
Fix Claude subscription fallback to Codex with explicit model settings - #28
Merged
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Claude Code now reports subscription exhaustion as a synthetic assistant API error:
You've hit your session limit. Skillhook classified this as unknown and counted it as agent work, so the configured fallback could not run.Recognise session/weekly limits and exhausted credits, exclude synthetic API notices from the activity guard, and count real assistant/tool activity so an agent that started work is never repeated. Fallback runner entries now also accept
{ runner, model, effort }, allowing Claude to fall back to Codex withgpt-6.1-solandmediuminstead of inheritingopus. Stop revisiting runners to prevent cycles when every account is exhausted. Existing string entries remain compatible.Includes generated schemas, documentation, regression coverage and the 0.10.1 release bump so the runner can install the fix.
Validation:
npm run checkpassed (typecheck, all tests, build, schema and release consistency); release consistency rechecked after the version bump.