fix: add models:read permission for GitHub Models API#463
Merged
Conversation
The LLM provider chain uses GitHub Models as primary provider. The GITHUB_TOKEN needs models:read permission to access the API. Without this permission, the API returns 401: 'The models permission is required to access this endpoint' Fixes GitHub Models authentication in analyze_codex_session step.
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
stranske
temporarily deployed
to
agent-high-privilege
GitHub Actions
Inactive
Comprehensive documentation covering: - Provider chain architecture (GitHub Models → OpenAI → Regex) - Workflow integration and outputs - Configuration and permissions - CLI usage and output format - Troubleshooting guide - Development history
Contributor
Automated Status SummaryHead SHA: 3cff333
Coverage Overview
Coverage Trend
Top Coverage Hotspots (lowest coverage)
Updated automatically; will refresh on subsequent CI/Docker completions. Keepalive checklistScope
Tasks
Acceptance criteria
|
stranske
temporarily deployed
to
agent-high-privilege
GitHub Actions
Inactive
Contributor
🤖 Keepalive Loop StatusPR #463 | Agent: Codex | Iteration 0/5 Current State
🔍 Failure Classification| Error type | infrastructure | |
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds the models: read permission to the reusable Codex workflow to enable access to GitHub Models API. The LLM provider chain (introduced in PR #459) uses GitHub Models as the primary AI provider for task completion analysis, which requires this permission to avoid 401 errors when calling the API endpoint.
Key changes:
- Added
models: readpermission to the workflow's permissions block
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| contents: write | ||
| pull-requests: write | ||
| actions: write | ||
| models: read |
There was a problem hiding this comment.
The permission is added without an inline comment explaining its purpose. According to the PR description, the solution includes a comment "# For GitHub Models AI inference". Adding this comment would improve maintainability by clarifying why this permission is needed, especially since the other permissions don't have comments.
Suggested change
| models: read | |
| models: read # For GitHub Models AI inference |
actionlint 1.7.3 doesn't recognize the 'models' permission scope which is a newer GitHub feature for GitHub Models API access. Add ignore pattern to suppress this false positive.
stranske
temporarily deployed
to
agent-high-privilege
GitHub Actions
Inactive
24 tasks
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.
Automated Status Summary
Scope
GITHUB_STEP_SUMMARYoutput so iteration results are visible in the Actions UITasks
agent:codexlabelagents-keepalive-loop.ymlafter agent runbuildStatusBlock()inagents_pr_meta_update_body.jsto acceptagentTypeparameteragentTypeis set (CLI agent): hide workflow table, hide head SHA/required checksagent:*label):<!-- gate-summary: -->comment posting (use step summary instead)<!-- keepalive-round: N -->instruction comments (task appendix replaces this)<!-- keepalive-loop-summary -->to be the single source of truthagent:*label):<!-- gate-summary: -->commentagent_typeoutput to detect job so downstream workflows know the modeagents-pr-meta.ymlto conditionally skip gate summary for CLI agent PRsAcceptance criteria
Head SHA: 0012c71
Latest Runs: ✅ success — Gate
Required: gate: ✅ success