feat: support CLAUDE_CODE_OAUTH_TOKEN for Claude Code agent #55
+68
−12
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
Allow Claude Pro/Max subscribers to authenticate using their OAuth token instead of requiring a separate ANTHROPIC_API_KEY. When CLAUDE_CODE_OAUTH_TOKEN is set in the environment, it takes precedence over ANTHROPIC_API_KEY for non-AI-Gateway configurations. Closes vercel-labs#54 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Adds support for authenticating the claude-code agent via Claude Code’s OAuth token (CLAUDE_CODE_OAUTH_TOKEN) so Claude Pro/Max users can run evals without an ANTHROPIC_API_KEY, while keeping the AI Gateway path unchanged.
Changes:
- Update
claude-codeagent API key env-var resolution to preferCLAUDE_CODE_OAUTH_TOKEN(direct mode only) when present. - Update sandbox command env passthrough to send
CLAUDE_CODE_OAUTH_TOKENinstead ofANTHROPIC_API_KEYin the OAuth case. - Add a changeset documenting the patch release.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
packages/agent-eval/src/lib/agents/claude-code.ts |
Adds OAuth token selection in getApiKeyEnvVar() and passes OAuth env var into the sandbox for claude runs. |
.changeset/oauth-token-support.md |
Declares a patch release and documents OAuth token support for claude-code auth. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Refactor nested ternary for sandbox env to if/else for readability, add clarifying comment about credential consistency, and add unit tests for getApiKeyEnvVar() precedence (gateway > oauth > direct). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
CLAUDE_CODE_OAUTH_TOKENsupport to theclaude-codeagent, enabling Claude Pro/Max subscription users to run evals without a separateANTHROPIC_API_KEYCLAUDE_CODE_OAUTH_TOKENis set in the environment, it is used for both API key resolution (getApiKeyEnvVar()) and sandbox env passthroughCloses #54
Test plan
npm run buildpassesnpm run lintpassesCLAUDE_CODE_OAUTH_TOKEN(withoutANTHROPIC_API_KEY) and run an eval — agent should authenticate via OAuthANTHROPIC_API_KEY— existing behavior unchangedAI_GATEWAY_API_KEYwithuseVercelAiGateway— AI Gateway path unchanged🤖 Generated with Claude Code