Repository navigation
Fix failed validation lifecycle retry output - #2046
Merged
Merged
Conversation
Require lifecycle next actions to contain only a backticked Squad command and move retry guidance to a separate field. Cover the malformed output observed in run 34944550565. Refs octodemo/eshop-bradyg-dev#4 Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Contributor
🛫 PR Readiness Check
PR Scope: 🔧 Infrastructure
|
| Status | Check | Details |
|---|---|---|
| ❌ | Single commit | 2 commits — consider squashing before review |
| ✅ | Not in draft | Ready for review |
| ❌ | Branch up to date | dev is 1 commit(s) ahead — rebase recommended |
| ❌ | Copilot review | No Copilot review yet — it may still be processing |
| ✅ | Changeset present | No source files changed — changeset not required |
| ✅ | Scope clean | No .squad/ or docs/proposals/ files |
| ✅ | No merge conflicts | No merge conflicts |
| ❌ | Copilot threads resolved | 1 unresolved Copilot thread(s) — fix and resolve before merging |
| ✅ | CI passing | All checks passing |
Files Changed (5 files, +69 −8)
| File | +/− |
|---|---|
test/gh-aw-lifecycle-upsert.test.ts |
+40 −3 |
test/gh-aw-plan-lifecycle.test.ts |
+7 −0 |
test/gh-aw-quality.test.ts |
+4 −1 |
workflows/shared/squad.md |
+3 −3 |
workflows/squad.md |
+15 −1 |
Total: +69 −8
This check runs automatically on every push. Fix any ❌ items and push again.
See CONTRIBUTING.md and PR Requirements for details.
Contributor
🟡 Impact Analysis — PR #2046Risk tier: 🟡 MEDIUM 📊 Summary
🎯 Risk Factors
📦 Modules Affectedroot (2 files)
tests (3 files)
This report is generated automatically for every PR. See #733 for details. |
Contributor
There was a problem hiding this comment.
Copilot review overview
🟡 Changes recommended
Lifecycle guidance and regression coverage still need updates before approval.
Get a fresh assessment by requesting another Copilot review.
Review tier: Lite
Findings: 1
Open (1)
What changed in this PR
Updates plan validation and lifecycle handling so nonterminal retry actions contain only a /squad command, with separate guidance and regression coverage.
Changes:
- Clarifies validation lifecycle output requirements.
- Tightens shared next-action validation.
- Adds tests for malformed and prose-containing actions.
| File | Description |
|---|---|
workflows/squad.md |
Updates validation lifecycle instructions. |
workflows/shared/squad.md |
Tightens lifecycle next-action validation. |
test/gh-aw-plan-lifecycle.test.ts |
Tests validation prompt requirements. |
test/gh-aw-lifecycle-upsert.test.ts |
Tests invalid lifecycle outputs. |
💡 Configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
| const hasState = /^(?:[-*]\s+)?\*\*(?:Current state|State):\*\*\s+\S+/im.test(body); | ||
| const hasLastCommand = /^(?:[-*]\s+)?\*\*Last command:\*\*\s+`\/squad\b[^`]*`/im.test(body); | ||
| const hasNextCommand = /^(?:[-*]\s+)?\*\*Next (?:action|command|recommended):\*\*\s+`\/squad\b[^`]*`/im.test(body); | ||
| const hasNextCommand = /^(?:[-*]\s+)?\*\*Next (?:action|command|recommended):\*\*\s+`\/squad\b[^`]*`[ \t]*$/im.test(body); |
Raise the authored-source regression budget by 1 KB after the command-only lifecycle next-action contract. The independently enforced ambient prompt budget remains healthy. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
This was referenced Sep 15, 2026
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
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.
Plan validation can correctly fail closed but then lose its lifecycle update because the generated retry action includes explanatory prose in the command field. This reproduces the secondary safe-output failure from octodemo/eshop-bradyg-dev run 34944550565.
This change makes the validation prompt emit a command-only next action and places retry context in a separate guidance field. It also tightens the shared lifecycle writer so nonterminal next actions must consist entirely of a backticked
/squadcommand, with regression coverage for both prose-prefixed and prose-suffixed values.The target run also used a stale Squad installation from before the Fact Checker model fix. After this PR merges,
octodemo/eshop-bradyg-devmust refresh and compile the installed workflows from@devbefore validation is rerun.Validation
gh aw compile: passednpm run build: passedgit diff --check: passed