Route Copilot's fast tier to gpt-5.6-luna and unpin capable - #332
Merged
Conversation
Copilot's --model list turns over faster than a release cycle: the capable tier's claude-opus-4.6 is already absent from 1.0.84, so a capable-pinned loop failed to launch. Fast now names gpt-5.6-luna, and capable joins standard in passing no flag so Copilot's own default applies. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01MK7LqRQyrEoJzFoVRCiNSW
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
--model gpt-5.6-luna(loop sessions pinned fast or auto-routed fast, the summary beat rewrite, and the pass board composer).--modelflag, like standard, so Copilot's own default applies.Why
Copilot CLI 1.0.84's accepted id list (
copilot help config) no longer containsclaude-opus-4.6, so a Copilot loop pinned to capable, or a turn-based loop with model auto-select on, launched with an id Copilot rejects. The ids were read off 0.0.410 and the list turns over faster than a release cycle.Test plan
CopilotBackendTestsandSummaryStoreTestsupdated to the new ids and passing (27 tests, exit 0) in a private-DerivedData worktree build🤖 Generated with Claude Code
https://claude.ai/code/session_01MK7LqRQyrEoJzFoVRCiNSW