DRAFT: Feat/OpenAI compatible api #47
Conversation
- Add BuildConfig.ts with AUTOMATED_MODE flag - Bypass OAuth authentication in automated mode - Auto-enable evaluation mode in automated mode - Configure Docker build with ARG support - Allows headless/automated usage without manual configuration
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the ✨ Finishing touches🧪 Generate unit tests
Comment |
Moving this functionality to feat/extend-openai-api branch 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Simple Dockerfile that uses pre-built local files - Uses nginx:alpine for lightweight serving - Designed for local development workflows
|
@codex review |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
Codex Review: Here are some suggestions.
Reply with @codex fix comments to fix any unresolved comments.
About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you open a pull request for review, mark a draft as ready, or comment "@codex review". If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex fix this CI failure" or "@codex address that feedback".
| toolResult = await this.executeToolWithTimeout( | ||
| tool, | ||
| params.input, | ||
| params.timeout || 30000, | ||
| params.timeout || 2700000, |
There was a problem hiding this comment.
[P1] Correct chat/tool default timeouts
The new default timeout constant is 2700000, which equals 45 minutes, while the comment explicitly states “Default 15 minutes for chat” and the tool branch previously defaulted to 30 seconds. This multiplication by 90× means a failed or hanging evaluation may block the UI for three‑quarters of an hour before timing out, which is far longer than either the documented 15 minutes or the prior behaviour. Consider replacing the literal with 900000 for a true 15‑minute chat timeout and restoring a shorter default for regular tools so that broken evaluations fail promptly.
Useful? React with 👍 / 👎.
No description provided.