feat(ponytail): persona persona boundary + simplification markers

[getappz]

• Persona hardening: 'less work for the same result' framing
• Anti-hallucination: 'NEVER invent APIs that don't exist'
• Persona boundary: 'act the role, never label it'
• Simplification markers: one-line format, delete if longer than code
• Closes ponytail PR audit tickets [ponytail#491] Tighten simplification marker rule: one line, delete if longer than code #77, [ponytail#521] Keep persona out of replies — act the role, don't label it #79

Summary by CodeRabbit

• Chores
  • Updated the built-in assistant guidance to improve response structure and brevity.
  • Added clearer reply constraints, including a “Persona boundary” that prevents referencing internal persona labels.
  • Introduced “Simplification markers” with a standardized single-line comment format for concise omissions/conditional adds.
  • Updated the related unit test to verify the new guidance text is present.

[coderabbitai]

Warning

Review limit reached

@getappz, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 13 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

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 configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 05d1e5d7-2800-4a00-bc91-b50ab72b7ea0

📥 Commits

Reviewing files that changed from the base of the PR and between ca2dddf and 84ad152.

📒 Files selected for processing (1)

• crates/ponytail/src/instructions.rs

📝 Walkthrough

Walkthrough

The PR updates the fallback instructions in crates/ponytail/src/instructions.rs, expanding the opening guidance and adding new persona-boundary and simplification-marker directives. The unit test is updated to assert the new prompt sections.

Changes

Prompt Text Update

Layer / File(s)	Summary
Fallback instructions prompt update crates/ponytail/src/instructions.rs	Opening guidance is expanded, and the prompt adds persona-boundary and simplification-marker directives with the required ponytail: comment format. The unit test checks for the new sections.

Estimated code review effort: 1 (Trivial) | ~5 minutes

Possibly related issues

• [ponytail#491] Tighten simplification marker rule: one line, delete if longer than code #77: Updates the same ponytail: simplification-marker guidance and one-line deletion rule.
• [ponytail#521] Keep persona out of replies — act the role, don't label it #79: Adjusts the same persona-boundary wording in crates/ponytail/src/instructions.rs.
• [ponytail#120] Output formatting rules — no auto-generated signatures, clean commits #59: Changes the same prompt text that constrains persona and output formatting.

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description is missing the required Summary, Test plan, and Notes for reviewers sections from the template.	Rewrite it to follow the template and add a Summary, the test plan checklist, and Notes for reviewers with risk and compatibility notes.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly matches the main change: persona boundary guidance and simplification markers.
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.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch fix/simplification-markers

---

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

[coderabbitai]

🧹 Nitpick comments (1)

crates/ponytail/src/instructions.rs (1)

129-134: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick win

Tests don't cover new persona/marker sections.

The only assertions here ("PONYTAIL MODE ACTIVE", "The ladder") predate this change; nothing verifies the new "Persona boundary" or "Simplification markers" text landed in the generated string.

✅ Suggested test additions

     fn fallback_generates_for_mode() {
         let f = fallback_instructions("full");
         assert!(f.contains("PONYTAIL MODE ACTIVE"));
         assert!(f.contains("The ladder"));
+        assert!(f.contains("Persona boundary"));
+        assert!(f.contains("Simplification markers"));
     }

🤖 Prompt for 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.

In `@crates/ponytail/src/instructions.rs` around lines 129 - 134, The
fallback_instructions test only checks older text and misses the new
persona/marker content. Update fallback_generates_for_mode to assert the
generated string from fallback_instructions("full") also includes the new
"Persona boundary" and "Simplification markers" sections, using the existing
fallback_instructions function and the fallback_generates_for_mode test to
verify the new output lands correctly.

🤖 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.

Nitpick comments:
In `@crates/ponytail/src/instructions.rs`:
- Around line 129-134: The fallback_instructions test only checks older text and
misses the new persona/marker content. Update fallback_generates_for_mode to
assert the generated string from fallback_instructions("full") also includes the
new "Persona boundary" and "Simplification markers" sections, using the existing
fallback_instructions function and the fallback_generates_for_mode test to
verify the new output lands correctly.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 8e6723ac-9221-401c-81af-f3bc2dee920b

📥 Commits

Reviewing files that changed from the base of the PR and between 7af46db and 8f697c0.

📒 Files selected for processing (1)

• crates/ponytail/src/instructions.rs