feat(agents): add action-hints footer to review, triage, and fix comments by rh-hemartin · Pull Request #2775 · fullsend-ai/fullsend

rh-hemartin · 2026-06-30T08:50:42Z

Summary

Add "Next steps" footer to review comments on request-changes outcomes, showing /fs-fix, /fs-fix <instruction>, push, and /fs-fix-stop
Add "Next steps" footer to triage comments on sufficient action, showing /fs-code and /fs-code <instruction>
Add "Next steps" footer to fix agent summary comments, showing /fs-review, /fs-fix <instruction>, and push
Add test for fix agent footer presence

Test plan

process-fix-result-test.py passes (27 tests)
Deploy to staging, trigger a review with request-changes outcome — verify footer appears
Trigger a triage with sufficient action — verify footer appears
Trigger a fix agent run — verify footer appears
Verify footer does NOT appear on approve, comment, reject, insufficient, duplicate, prerequisites, question outcomes

🤖 Generated with Claude Code

…ents Users receiving agent comments don't know what commands are available. Add contextual "Next steps" footers so available actions are discoverable at the decision point — review (request-changes only), triage (sufficient only), and fix (always). Closes #1789, closes #2493, closes #2494 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Hector Martinez <hemartin@redhat.com>

qodo-code-review · 2026-06-30T08:51:45Z

PR Summary by Qodo

Add contextual “Next steps” footers to review, triage, and fix agent comments

✨ Enhancement 📝 Documentation 🧪 Tests 🕐 20-40 Minutes

AI Description

• Add “Next steps” command hints to review comments for request-changes outcomes.
• Add “Next steps” command hints to triage comments for sufficient actions only.
• Add “Next steps” footer to fix-agent summary comments and cover it with a unit test.

Diagram

graph TD
  User["Developer / Reviewer"] --> Cmds["Slash commands"]
  TriageSpec["triage.md spec"] --> TriageAgent["Triage comment"] --> User
  ReviewSpec["pr-review SKILL.md"] --> ReviewAgent["Review comment"] --> User
  FixScript["process-fix-result.py"] --> FixComment["Fix summary comment"] --> User
  Cmds --> TriageAgent
  Cmds --> ReviewAgent
  Cmds --> FixComment

High-Level Assessment

The following are alternative approaches to this PR:

1. Centralize footer templates in a shared helper

➕ Single source of truth for command text across review/triage/fix outputs
➕ Easier to update commands without missing a prompt/spec location
➖ Requires refactoring wiring between prompt/spec docs and runtime code generation
➖ May be overkill if only fix-agent body is programmatically composed today

2. Link to a canonical “available commands” doc instead of embedding

➕ Keeps comments shorter; avoids repeating command lists
➕ Doc can be updated without changing prompt/spec or code
➖ Lower discoverability at the moment of action (extra click)
➖ Users may ignore links; commands remain less “in your face”

Recommendation: The PR’s approach (contextual, outcome-specific footers) is the best trade-off for discoverability with minimal noise: show hints only when the user is likely to take an action (request-changes / sufficient, and fix summaries). If this pattern expands further, consider centralizing the footer strings in a shared template/helper to avoid drift between specs and runtime rendering.

Files changed (4) +44 / -2

Enhancement (1) +8 / -0

process-fix-result.pyAppend “Next steps” footer to fix-agent summary comments +8/-0

Append “Next steps” footer to fix-agent summary comments
• Updates 'build_summary_body()' to always add a markdown footer describing follow-up actions ('/fs-review', '/fs-fix <instruction>', and pushing commits). Keeps the existing attribution footer intact after the new section.
internal/scaffold/fullsend-repo/scripts/process-fix-result.py

Tests (1) +13 / -0

process-fix-result-test.pyAdd unit test asserting fix-agent footer presence +13/-0

Add unit test asserting fix-agent footer presence
• Introduces a test that builds a fix summary body and asserts the “Next steps” footer and key commands are present. Provides coverage for the newly appended footer behavior.
internal/scaffold/fullsend-repo/scripts/process-fix-result-test.py

Documentation (2) +23 / -2

triage.mdSpecify action-hints footer for 'sufficient' triage comments +8/-0

Specify action-hints footer for 'sufficient' triage comments
• Documents a required “Next steps” footer appended to the triage 'comment' only when 'action' is 'sufficient'. Explicitly instructs omitting the footer for 'insufficient', 'duplicate', 'prerequisites', and 'question'.
internal/scaffold/fullsend-repo/agents/triage.md

SKILL.mdAllow review footer only for 'request-changes' outcomes +15/-2

Allow review footer only for 'request-changes' outcomes
• Refines the review skill guidance to keep review comments footer-free by default, but adds an exception for 'request-changes'. Defines the exact markdown footer content and explicitly omits it for 'approve', 'comment', and 'reject'.
internal/scaffold/fullsend-repo/skills/pr-review/SKILL.md

github-actions · 2026-06-30T08:52:40Z

Site preview

Preview: https://215ca157-site.fullsend-ai.workers.dev

Commit: eb9a565dd3efb2c220615d8eef5428cff454b70e

qodo-code-review · 2026-06-30T08:53:38Z

Code Review by Qodo

🐞 Bugs (0) 📘 Rule violations (0) 📎 Requirement gaps (0)

Great, no issues found!

Qodo reviewed your code and found no material issues that require review

fullsend-ai-review · 2026-06-30T08:54:01Z

🤖 Finished Review · ✅ Success · Started 8:54 AM UTC · Completed 9:04 AM UTC
Commit: eb9a565 · View workflow run →

codecov · 2026-06-30T08:55:17Z

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

fullsend-ai-review · 2026-06-30T09:04:43Z

Review

Findings

Medium

[test-inadequate] internal/scaffold/fullsend-repo/scripts/process-fix-result-test.py:180 — The assertion assertIn('/fs-fix', body) passes via substring match against /fs-fix <your instruction> in the production code. The fix agent footer omits a bare /fs-fix option (without arguments), unlike the PR review footer in SKILL.md which lists both /fs-fix and /fs-fix <your instruction> as separate items. The substring assertion masks this inconsistency — the test passes regardless of whether bare /fs-fix is present.
Remediation: Either add bare /fs-fix to the fix agent footer (consistent with the review footer), or make the assertion precise: assertIn('/fs-fix <your instruction>', body).

Low

[stale-doc] docs/agents/review.md:46 — Documentation describes review outcomes but does not mention the new action-hints footer appended to request-changes outcomes. The footer is a UI convenience rather than a behavior change, so this is minor.
[stale-doc] docs/guides/user/bugfix-workflow.md:93 — Review outcomes section doesn't mention the new action-hints footer.
[pattern-inconsistency] internal/scaffold/fullsend-repo/agents/triage.md:316 — Triage footer placement guidance says "append to the end of the comment field," which is clear enough for the triage context. Minor gap compared to the more detailed placement instructions in SKILL.md.
[design-direction] internal/scaffold/fullsend-repo/agents/triage.md:316 — Conditional footer logic for triage (only for sufficient action) is enforced by agent instructions, not by schema or post-script validation. The fix agent footer is enforced programmatically in process-fix-result.py. This asymmetry is consistent with how other triage behaviors are instruction-driven.

fullsend-ai-review

See the review comment for full details.

fullsend-ai-review · 2026-06-30T09:04:44Z

+        self.assertIn("**Next steps:**", body)
+        self.assertIn("/fs-review", body)
+        self.assertIn("/fs-fix", body)
+


[medium] test-inadequate

The assertion assertIn('/fs-fix', body) passes via substring match against '/fs-fix ' in the production code. The fix agent footer omits a bare '/fs-fix' option, unlike the PR review footer in SKILL.md which lists both. The substring assertion masks this inconsistency.

Suggested fix: Either add bare '/fs-fix' to the fix agent footer (consistent with the review footer), or make the assertion precise: assertIn('/fs-fix ', body).

fullsend-ai-review · 2026-06-30T09:04:44Z

 - Do not present unverified assumptions with certainty. Convey uncertainty when appropriate.
 - Write in second person ("you") addressing the reporter. Do not use first person ("I") — the comment is from the triage system, not an individual.
 - If you include `label_actions`, the pipeline appends your label reason to the comment automatically — do not include label justifications in the `comment` field yourself.
+- **Action hints footer (sufficient action only):** When `action` is `sufficient`, append the following footer to the end of the `comment` field. Omit it for all other actions (`insufficient`, `duplicate`, `prerequisites`, `question`).


[low] pattern-inconsistency

Triage footer placement guidance is adequate but less detailed than SKILL.md's placement instructions.

fullsend-ai-review · 2026-06-30T09:04:44Z

 - Do not present unverified assumptions with certainty. Convey uncertainty when appropriate.
 - Write in second person ("you") addressing the reporter. Do not use first person ("I") — the comment is from the triage system, not an individual.
 - If you include `label_actions`, the pipeline appends your label reason to the comment automatically — do not include label justifications in the `comment` field yourself.
+- **Action hints footer (sufficient action only):** When `action` is `sufficient`, append the following footer to the end of the `comment` field. Omit it for all other actions (`insufficient`, `duplicate`, `prerequisites`, `question`).


[low] design-direction

Conditional footer logic for triage is instruction-driven, not enforced by schema or post-script, unlike the fix agent footer which is programmatic.

github-actions Bot deployed to site-preview June 30, 2026 08:52 View deployment

fullsend-ai-review Bot reviewed Jun 30, 2026

View reviewed changes

fullsend-ai-review Bot added the requires-manual-review Review requires human judgment label Jun 30, 2026

rh-hemartin self-assigned this Jul 1, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat(agents): add action-hints footer to review, triage, and fix comments#2775

feat(agents): add action-hints footer to review, triage, and fix comments#2775
rh-hemartin wants to merge 1 commit into
mainfrom
fix/1789-review-action-hints

rh-hemartin commented Jun 30, 2026

Uh oh!

qodo-code-review Bot commented Jun 30, 2026

Uh oh!

github-actions Bot commented Jun 30, 2026

Uh oh!

qodo-code-review Bot commented Jun 30, 2026

Uh oh!

fullsend-ai-review Bot commented Jun 30, 2026 •

edited

Loading

Uh oh!

codecov Bot commented Jun 30, 2026

Uh oh!

fullsend-ai-review Bot commented Jun 30, 2026

Uh oh!

fullsend-ai-review Bot left a comment

Uh oh!

fullsend-ai-review Bot Jun 30, 2026

Uh oh!

fullsend-ai-review Bot Jun 30, 2026

Uh oh!

fullsend-ai-review Bot Jun 30, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

rh-hemartin commented Jun 30, 2026

Summary

Test plan

Uh oh!

qodo-code-review Bot commented Jun 30, 2026

PR Summary by Qodo

Uh oh!

github-actions Bot commented Jun 30, 2026

Site preview

Uh oh!

qodo-code-review Bot commented Jun 30, 2026

Code Review by Qodo

Great, no issues found!

Uh oh!

fullsend-ai-review Bot commented Jun 30, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

codecov Bot commented Jun 30, 2026

Codecov Report

Uh oh!

fullsend-ai-review Bot commented Jun 30, 2026

Review

Findings

Medium

Low

Uh oh!

fullsend-ai-review Bot left a comment

Choose a reason for hiding this comment

Uh oh!

fullsend-ai-review Bot Jun 30, 2026

Choose a reason for hiding this comment

Uh oh!

fullsend-ai-review Bot Jun 30, 2026

Choose a reason for hiding this comment

Uh oh!

fullsend-ai-review Bot Jun 30, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

fullsend-ai-review Bot commented Jun 30, 2026 •

edited

Loading