Skip to content

fix(evals): centralize .env creation guidance for all agent runs#125

Merged
frederikprijck merged 1 commit into
mainfrom
fix/quickstart-env-prompt-wording
Jul 20, 2026
Merged

fix(evals): centralize .env creation guidance for all agent runs#125
frederikprijck merged 1 commit into
mainfrom
fix/quickstart-env-prompt-wording

Conversation

@frederikprijck

@frederikprijck frederikprijck commented Jul 20, 2026

Copy link
Copy Markdown
Member

What

Moves the .env no-permission-prompt guidance out of the eight individual quickstart PROMPT.md files and into the central AGENT_GUIDANCE string, 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 .env would have to copy it again.

writeAgentGuidance() already injects AGENT_GUIDANCE into 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 .env intent 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):

    If the task requires environment variables (e.g. .env or .env.local files), create those files directly — do not pause to ask for permission to create them.

  • Remove the now-redundant per-prompt lines from the eight quickstart PROMPT.md files.

  • Add a test asserting the guidance carries the .env no-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 L3 notContainsInSource grader.

Notes

No frontmatter schema change, so no docs/ADDING_EVALS.md update required.

@coderabbitai

coderabbitai Bot commented Jul 20, 2026

Copy link
Copy Markdown

Review Change Stack

📝 Walkthrough

Walkthrough

Updated FastAPI, Flask, and Nuxt quickstart prompts to store and load Auth0 configuration from environment files and create those files without confirmation.

Changes

Quickstart environment configuration

Layer / File(s) Summary
Environment-file configuration guidance
apps/auth0-evals/src/evals/quickstarts/{fastapi,flask,nuxt}/PROMPT.md
Quickstart instructions now specify storing Auth0 credentials in .env or .env.local files, loading them from environment variables, and creating the files directly without confirmation.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Suggested reviewers: sanchitmehtagit

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly reflects the main change: consolidating .env creation guidance across the eval quickstart prompts.
✨ Finishing Touches
📝 Generate docstrings
  • Create stacked PR
  • Commit on current branch
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch fix/quickstart-env-prompt-wording

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.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

📥 Commits

Reviewing files that changed from the base of the PR and between 3e91dfe and f6886a5.

📒 Files selected for processing (3)
  • apps/auth0-evals/src/evals/quickstarts/fastapi/PROMPT.md
  • apps/auth0-evals/src/evals/quickstarts/flask/PROMPT.md
  • apps/auth0-evals/src/evals/quickstarts/nuxt/PROMPT.md

Comment thread apps/auth0-evals/src/evals/quickstarts/nuxt/PROMPT.md Outdated
@frederikprijck
frederikprijck force-pushed the fix/quickstart-env-prompt-wording branch from 2746b98 to f0e6bc1 Compare July 20, 2026 10:27
@frederikprijck frederikprijck changed the title fix(evals): reword .env instruction in quickstart prompts fix(evals): clarify .env creation in quickstart prompts Jul 20, 2026
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
frederikprijck force-pushed the fix/quickstart-env-prompt-wording branch from f0e6bc1 to 19b0a1e Compare July 20, 2026 14:25
@frederikprijck frederikprijck changed the title fix(evals): clarify .env creation in quickstart prompts fix(evals): centralize .env creation guidance for all agent runs Jul 20, 2026
@frederikprijck
frederikprijck merged commit d36e460 into main Jul 20, 2026
6 checks passed
@frederikprijck
frederikprijck deleted the fix/quickstart-env-prompt-wording branch July 20, 2026 14:27
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants