feat(triage): add effort-estimation skill on block_auto_promotion - #1079
feat(triage): add effort-estimation skill on block_auto_promotion#1079rh-hemartin wants to merge 2 commits into
Conversation
Replace the single-purpose requires_workflow_changes boolean with a general-purpose block_auto_promotion object (blocked + reason). Workflow file detection now sets blocked=true with a reason; later gates can use the same field without a new post-script path. Keep requires_workflow_changes as a deprecated optional property for one release so lockstep-skewed agent output still validates. When block_auto_promotion is absent, the old boolean still blocks auto-promotion. The post-script appends the reason to the triage comment, sanitizes GHA workflow-command sequences, strips paired line-start fenced code blocks, and uses a held-for-review footer when auto-promotion is blocked. Signed-off-by: Hector Martinez <hemartin@redhat.com>
Add an effort-estimation skill that scores issues on scope, testing, domain knowledge, and risk (1-5 each). When overall effort >= 4, or any single dimension scores 5, the skill sets block_auto_promotion.blocked so the existing post-script gate holds the issue at triaged instead of ready-to-code. Require block_auto_promotion for bug, documentation, and performance categories. Feature, security, and other stay optional because they already route to human review. Closes fullsend-ai/fullsend#2207 Signed-off-by: Hector Martinez <hemartin@redhat.com>
|
🤖 Finished Review · ✅ Success · Started 12:25 PM UTC · Completed 1:07 PM UTC Commit: Runtime: claude · Model: opus → claude-opus-4-6 · Effort: high |
fa3c916 to
361fb43
Compare
|
Risk Assessment: elevated (3/5) DetailsElevated risk driven by large file count touching protected/security-sensitive paths in a high-churn stabilization-phase codebase, offset by the largely additive nature of changes (new eval cases and skill) and modest modifications to existing scripts aligned with a well-scoped feature request. |
ReviewFindingsMedium
Low
|
![fullsend-ai-review[bot]](https://avatars.githubusercontent.com/in/3478501?s=60&v=4){kind=small}
| schema update (`schemas/<agent>-result.schema.json`) to accommodate | ||
| whatever new field the agent uses to expose its conclusions to the | ||
| post-script. Example: the `requires_workflow_changes` flag in triage. | ||
| post-script. Example: the `block_auto_promotion` field in triage. |
There was a problem hiding this comment.
[low] stale-doc
Uses requires_workflow_changes as the canonical example of the 'Agent + scripts' configuration pattern. This PR makes block_auto_promotion the primary mechanism by requiring it for bug/documentation/performance categories via a JSON Schema conditional. The FEATURES.md example now points to the secondary (deprecated-but-still-accepted) field rather than the current one.
Suggested fix: Update the example on line 20 to reference block_auto_promotion instead of requires_workflow_changes.
fullsend-ai-review
Bot
added
the
requires-manual-review
361fb43 to
f09b3d7
Compare
1 participant
Summary
Add the
effort-estimationskill on top of theblock_auto_promotiongate from #1078. High-effort issues (overall >= 4, or any dimension 5) setblocked: truewith a reason; the post-script from #1078 already holds those attriaged.Blocked by #1078. Merge that first. This PR is stacked on
feat/2207-block-auto-promotion; GitHub should retarget it tomainafter #1078 lands and the base branch is deleted.Behavior
effort-estimationskill scores scope, testing, domain knowledge, and risk (1-5 each).block_auto_promotion.Closes fullsend-ai/fullsend#2207
Test plan
bash scripts/post-triage-test.shbash scripts/validate-output-schema-test.shmain