docs: document guideline generation modes and add end-to-end tutorial - #297
docs: document guideline generation modes and add end-to-end tutorial#297evduester wants to merge 2 commits into
Conversation
Consistency guidelines shipped without doc updates, so EVOLVE_GUIDELINES_MODE and its consistency-tuning env vars were undiscoverable anywhere in docs/. Adds a new Enabling Guidelines guide covering both regular and consistency modes, cross-links it from Configuration/Phoenix Sync/Low-Code Tracing, and reorders the Guides nav so tracing precedes sync (traces must exist before they can be synced). Also adds a new tutorial plus a companion example script that walks the full loop: trace an agent, generate guidelines from the trace, then retrieve and inject those guidelines back into a new run. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
|
Warning Review limit reached
Next review available in: 22 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThis change documents guideline generation modes and Phoenix synchronization, adds an end-to-end evolving-agent tutorial, introduces a guideline retrieval example, updates documentation navigation, and ignores the ChangesGuidelines workflow
Repository housekeeping
Estimated code review effort: 2 (Simple) | ~15 minutes Sequence Diagram(s)sequenceDiagram
participant CodeAgent
participant Phoenix
participant Evolve
participant EvolveClient
CodeAgent->>Phoenix: emit traced trajectory
Phoenix->>Evolve: sync trajectory
Evolve->>Evolve: generate guideline entities
EvolveClient->>Evolve: select_guidelines(task)
Evolve-->>EvolveClient: return guideline entities
EvolveClient->>CodeAgent: inject formatted guidelines
Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
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 `@examples/low_code/guidelines_retrieval_demo.py`:
- Around line 77-81: Update the exception handler around agent.run in the
example so agent-run failures propagate as a non-zero process exit status after
reporting the error. Re-raise the caught exception or terminate via SystemExit
chained from the original exception, while preserving the existing error
message.
🪄 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: 4b53f52d-d05d-4f93-983a-0b3e133aeb69
📒 Files selected for processing (10)
.gitignoredocs/guides/configuration.mddocs/guides/extract-trajectories.mddocs/guides/guidelines.mddocs/guides/low-code-tracing.mddocs/guides/phoenix-sync.mddocs/tutorials/guidelines-loop.mddocs/tutorials/index.mdexamples/low_code/guidelines_retrieval_demo.pymkdocs.yaml
|
Checks Summary Last run: 2026-07-28T20:19:46.939Z Mend Unified Agent vulnerability scan found 4 vulnerabilities:
|
agent.run() failures were only printed, so the script exited 0 even when the run failed, hiding real failures from CI/automation. Re-raise as SystemExit, chained from the original exception, so the failure is actually visible in the exit status while keeping the error message. Addresses a CodeRabbit review comment on PR #297. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2 participants
Summary
docs/guides/guidelines.md) coveringEVOLVE_GUIDELINES_MODE(regular/consistency/both) — this was previously undocumented anywhere despite existing in code.EVOLVE_GUIDELINES_MODEenv var indocs/guides/configuration.md.--guidelines-modeflag to the Phoenix Sync guide, and cross-links guides that previously had no links between them (Configuration, Phoenix Sync, Low-Code Tracing, Extract Trajectories).examples/low_code/guidelines_retrieval_demo.py) demonstrating the full loop: trace an agent → generate guidelines → retrieve and inject them back into a new run.Test plan
mkdocs build --strict— only pre-existing, unrelated warnings remain (broken example links in low-code-tracing.md, a stale CLI reference link, a Codex anchor)ruff checkandruff formatSummary by CodeRabbit
Documentation
Examples