fix(evals): centralize .env creation guidance for all agent runs#125
Merged
Conversation
📝 WalkthroughWalkthroughUpdated FastAPI, Flask, and Nuxt quickstart prompts to store and load Auth0 configuration from environment files and create those files without confirmation. ChangesQuickstart environment configuration
Estimated code review effort: 1 (Trivial) | ~2 minutes Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@apps/auth0-evals/src/evals/quickstarts/nuxt/PROMPT.md`:
- Line 20: Update the credential-storage instruction in the prompt to require
creating and reading `.env` as the deterministic primary file, without asking
for confirmation; mention `.env.local` only as an explicitly supported fallback
and do not present it as an equivalent default.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: 562376fa-d5d4-4689-9ef3-7e28abfa2bc6
📒 Files selected for processing (3)
apps/auth0-evals/src/evals/quickstarts/fastapi/PROMPT.mdapps/auth0-evals/src/evals/quickstarts/flask/PROMPT.mdapps/auth0-evals/src/evals/quickstarts/nuxt/PROMPT.md
frederikprijck
force-pushed
the
fix/quickstart-env-prompt-wording
branch
from
July 20, 2026 10:27
2746b98 to
f0e6bc1
Compare
The per-prompt line "Do not prompt for permissions to create any .env files" was intended only to stop the agent pausing for a permission prompt, and was duplicated across eight quickstart PROMPT.md files. Move the intent into the central AGENT_GUIDANCE string that writeAgentGuidance() injects into every agent run's context file (CLAUDE.md / GEMINI.md / AGENTS.md / copilot-instructions.md), so the steering reaches all runners and all current and future evals automatically. Remove the now-redundant per-prompt lines. Credential-in-source guidance is intentionally left to the skill.
frederikprijck
force-pushed
the
fix/quickstart-env-prompt-wording
branch
from
July 20, 2026 14:25
f0e6bc1 to
19b0a1e
Compare
sanchitmehtagit
approved these changes
Jul 20, 2026
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.
What
Moves the
.envno-permission-prompt guidance out of the eight individual quickstartPROMPT.mdfiles and into the centralAGENT_GUIDANCEstring, so it reaches every agent run automatically.Why
The line "Do not prompt for permissions to create any .env files" was intended only to stop the agent pausing for a permission (
ask_user) prompt. It was duplicated across eight quickstart prompts (fastapi, flask, nuxt, angular, express, fastify-api, nextjs, vue), and any future eval needing a.envwould have to copy it again.writeAgentGuidance()already injectsAGENT_GUIDANCEinto whichever context file the active runner reads (CLAUDE.md/GEMINI.md/AGENTS.md/.github/copilot-instructions.md) on every agent job — the same mechanism the existing "no documentation files" steering uses. Putting the.envintent there makes it DRY and applies it to all runners and all current/future evals.Change
Add to
AGENT_GUIDANCE(packages/evals-core/src/workspace/workspace.ts):Remove the now-redundant per-prompt lines from the eight quickstart
PROMPT.mdfiles.Add a test asserting the guidance carries the
.envno-permission steering.The credential-in-source concern (agents hardcoding secrets instead of using
.env) is intentionally not covered here — that belongs to the skill, and is enforced independently by the L3notContainsInSourcegrader.Notes
No frontmatter schema change, so no
docs/ADDING_EVALS.mdupdate required.