fix(review-agent): move output schema from pr-review skill to agent definition - #1112
Merged
Conversation
…efinition When the pr-review skill fails to load (e.g. injection scan finding blocks it or skill discovery fails), the agent improvises its output and writes fields outside the strict schema (outcome, summary, prior_review_sha, prior_review_provenance), causing validation failures. Triage and code agents carry their output schema directly in the agent definition, so they produce correct output regardless of skill availability. Align review with that pattern: move the pipeline-mode JSON schema and jq examples from skills/pr-review/SKILL.md into agents/review.md, with an explicit note that additionalProperties: false rejects unknown fields. The skill now delegates to the agent definition for output format details. Assisted-by: Claude claude-sonnet-4-6 <noreply@anthropic.com> Signed-off-by: Ralph Bean <rbean@redhat.com>
Site previewPreview: https://dca8f93f-site.fullsend-ai.workers.dev Commit: |
Merge content from #1111 into this PR: - Escape literal HTML comment patterns in pr-review SKILL.md that trigger fullsend scan context hidden_html_comment findings - Add JSON schema tables (fields, types, constraints, required-per-action) to the agent definition alongside the existing jq examples - Mark schemas/review-result.schema.json as source of truth - Replace inline HTML comment reference in SKILL.md constraints with back-reference to step 6 Supersedes #1111. Signed-off-by: Wayne Sun <gsun@redhat.com>
2 tasks
…elds Remove the paragraph in review.md that duplicated the finding object table. Clarify in SKILL.md that action/pr_number/repo are always required and the per-action table lists additional required fields. Signed-off-by: Wayne Sun <gsun@redhat.com>
ReviewNo findings. |
![fullsend-ai-review[bot]](https://avatars.githubusercontent.com/in/3478501?s=60&v=4){kind=small}
fullsend-ai-review
Bot
added
the
ready-for-merge
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
2 participants
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.
Summary
jqexamples,agent-result.jsonfilename) lived entirely inskills/pr-review/SKILL.md, unlike triage and code agents which carry this in their agent definition filesoutcome,summary,prior_review_sha,prior_review_provenance), causingadditionalProperties: falsevalidation failuresagents/review.mdwith an explicit warning against unknown fields; the skill now delegates to the agent definition for output formatschemas/review-result.schema.jsonmarked as source of truthskills/pr-review/SKILL.mdthat triggeredfullsend scan contexthigh-severityhidden_html_commentfindings (the scanner does line-by-line matching and doesn't respect code fences)Supersedes #1111.
Test plan
fullsend scan contextonskills/pr-review/SKILL.md— cleanagent-result.jsonwhenpr-reviewskill is unavailableagent-result.jsonon next PR review runRefs: fullsend-ai/agents#376