fix: remove gpt-5.5 from agent model alias#43229
Merged
Merged
Conversation
…completions) Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot created this pull request from a session on behalf of
pelikhan
July 3, 2026 15:49
View session
pelikhan
marked this pull request as ready for review
July 3, 2026 15:50
Contributor
There was a problem hiding this comment.
Pull request overview
Removes gpt-5.5 from the agent model alias fallback chain so workflows don’t fall back to a model that fails against the Copilot SDK /chat/completions endpoint, reducing hard failures when retries are constrained by AI credit limits.
Changes:
- Updated the built-in
agentalias definition to removegpt-5.5and synced the unit test expectation. - Updated the
BuiltinModelAliasesdoc comment to reflect the newagentchain. - Regenerated workflow/test golden outputs and recompiled workflow lock files to reflect the updated
agentmodel list.
Show a summary per file
| File | Description |
|---|---|
| pkg/workflow/data/model_aliases.json | Removes gpt-5.5 from the agent alias list. |
| pkg/workflow/model_aliases.go | Updates the documented agent alias chain (doc comment). |
| pkg/workflow/model_aliases_test.go | Updates the agent alias assertion to match the new chain. |
| pkg/workflow/testdata/TestWasmGolden_AllEngines/pi.golden | Regenerated golden output reflecting the new agent model list. |
| pkg/workflow/testdata/TestWasmGolden_AllEngines/gemini.golden | Regenerated golden output reflecting the new agent model list. |
| pkg/workflow/testdata/TestWasmGolden_AllEngines/copilot.golden | Regenerated golden output reflecting the new agent model list. |
| pkg/workflow/testdata/TestWasmGolden_AllEngines/codex.golden | Regenerated golden output reflecting the new agent model list. |
| .github/workflows/workflow-health-manager.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/schema-consistency-checker.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/pr-triage-agent.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/poem-bot.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/gpclean.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/daily-regulatory.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/daily-observability-report.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/daily-max-ai-credits-test.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/daily-credit-limit-test.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/daily-compiler-quality.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/daily-cli-tools-tester.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/daily-cache-strategy-analyzer.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/copilot-centralization-optimizer.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/copilot-centralization-drilldown.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/code-simplifier.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/ci-coach.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/agentic-token-optimizer.lock.yml | Recompiled lock file reflecting the new agent model list. |
| .github/workflows/agent-performance-analyzer.lock.yml | Recompiled lock file reflecting the new agent model list. |
Review details
Tip
Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
- Files reviewed: 83/270 changed files
- Comments generated: 1
- Review effort level: Low
| @@ -89,7 +89,7 @@ func loadBuiltinModelAliases() (map[string][]string, error) { | |||
| // - "mini" → haiku, gpt-5-mini, gpt-5-nano, gemini-flash-lite, copilot/raptor*mini* | |||
This was referenced Jul 4, 2026
Contributor
|
🎉 This pull request is included in a new release. Release: |
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.
gpt-5.5does not support the/chat/completionsendpoint used by the Copilot SDK, causingCAPIError: 400failures in any workflow where the agent fallback chain reaches it. When the failure coincides with an exhausted AI credits budget, the harness cannot retry and the job fails hard.Changes
data/model_aliases.json— dropgpt-5.5fromagentalias; chain is nowsonnet-6x → gpt-5.4 → gpt-5.3 → gemini-pro → anymodel_aliases_test.go/model_aliases.go— sync assertion and doc commenttestdata/golden files — regenerated*.lock.yml— recompiled (258 workflows)