Repository navigation
fix(accounts): test Claude accounts on Sonnet 5.5, then Opus 5.5, by default - #226
Merged
Merged
Conversation
…default The default Claude test model was claude-sonnet-4-5-20250929, which Anthropic deprecated on 2026-09-30 (retiring 2026-11-30) and which accepts no reasoning effort, so the test dialog of every Anthropic account opened on a model without the effort select. Connection tests now prefer claude-sonnet-5-5 (Anthropic's named replacement), then claude-opus-5-5, and otherwise the first text model of the account's list. That list is now built from mapping keys in a stable order for Anthropic and Gemini API-key accounts, so the fallback no longer depends on map iteration. The same choice applies to batch tests that name no model. Owner decision 2026-10-02. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
After #224, Anthropic accounts still opened the test dialog with no reasoning-effort select. Every Anthropic account's default test model was
claude-sonnet-4-5-20250929, and that model accepts nooutput_config.effort, so the select stays hidden until the admin switches models.Anthropic deprecated
claude-sonnet-4-5-20250929on 2026-09-30 and will retire it on 2026-11-30. Its named replacement isclaude-sonnet-5-5.Change
claude.DefaultTestModelis nowclaude-sonnet-5-5, with the newclaude.DefaultTestModelFallback=claude-opus-5-5as fallback.PickConnectionTestModelwalks the platform's ordered defaults (Sonnet 5.5, then Opus 5.5 for Anthropic and CN-Anthropic) before falling back to the first text model of the account's list.Owner decision 2026-10-02: Sonnet 5.5, then Opus 5.5, then the first text model in a stable order. The select stays hidden for models without effort support.
Verification
Run locally:
go build ./..., andgo veton the changed packages;TestPickConnectionTestModelPrefersClaudeTestModelsInOrder;TestAccountTestPlanAnthropicDefaultFollowsTestModelPreference;TestAccountTestPlanCoreSelectionSmallMatrixandTestAccountTestModelsCarryReasoningOnEveryPlatform.Not run: real model calls.
🤖 Generated with Claude Code