chore: sync workflow templates by stranske · Pull Request #128 · stranske/Template

stranske · 2026-01-08T03:35:54Z

Sync Summary

Files Updated

agents-verify-to-issue.yml: Verify to issue - creates follow-up issues from verification feedback (Phase 4E)
agents-auto-label.yml: Auto-label - suggests/applies labels based on semantic matching (Phase 5A)
agents-capability-check.yml: Capability check - pre-flight agent feasibility gate (Phase 3A)
agents-decompose.yml: Task decomposition - breaks large issues into sub-tasks (Phase 3B)
agents-dedup.yml: Duplicate detection - flags similar open issues (Phase 3C)
issue_formatter.py: Issue formatter - converts raw text to AGENT_ISSUE_TEMPLATE format

Files Skipped

pr-00-gate.yml: File exists and sync_mode is create_only
ci.yml: File exists and sync_mode is create_only
dependabot.yml: File exists and sync_mode is create_only

Review Checklist

CI passes with updated workflows
No repo-specific customizations were overwritten

Source: stranske/Workflows
Manifest: .github/sync-manifest.yml

Automated sync from stranske/Workflows Template hash: 13e4f1e21f38 Changes synced from sync-manifest.yml

github-actions · 2026-01-08T03:36:18Z

⚠️ Action Required: Unable to determine source issue for PR #128. The PR title, branch name, or body must contain the issue number (e.g. #123, branch: issue-123, or the hidden marker ).

github-actions · 2026-01-08T03:36:28Z

🤖 Keepalive Loop Status

PR #128 | Agent: Codex | Iteration 0/5

Current State

Metric	Value
Iteration progress	[----------] 0/5
Action	wait (missing-agent-label)
Disposition	skipped (transient)
Gate	success
Tasks	0/9 complete
Keepalive	❌ disabled
Autofix	❌ disabled

🔍 Failure Classification

github-actions · 2026-01-08T03:37:02Z

github-actions · 2026-01-08T03:37:03Z

Autofix updated these files:

scripts/langchain/issue_formatter.py

Copilot

Pull request overview

This PR syncs workflow templates from the stranske/Workflows repository, introducing five new agent-based workflows and a minor formatting improvement to issue_formatter.py. The workflows implement various automation features for issue and PR management using LLM-based analysis.

Key Changes:

Added five new agent workflow files implementing issue processing automation (verify-to-issue, auto-label, capability check, decomposition, duplicate detection)
Minor formatting fix in issue_formatter.py adding proper import grouping per PEP 8
All workflows follow consistent patterns using Python scripts embedded via heredoc or -c flag with environment variable passing

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 9 comments.

Show a summary per file

File	Description
scripts/langchain/issue_formatter.py	Adds blank line between third-party and local imports (PEP 8 compliance)
.github/workflows/agents-verify-to-issue.yml	Creates follow-up issues from PR verification feedback via label trigger
.github/workflows/agents-auto-label.yml	Suggests and auto-applies labels using semantic similarity matching
.github/workflows/agents-capability-check.yml	Pre-flight gate checking if agents can complete assigned tasks
.github/workflows/agents-decompose.yml	Breaks down large issues into manageable sub-tasks using LLM
.github/workflows/agents-dedup.yml	Detects and flags potential duplicate issues via embeddings

Copilot · 2026-01-08T03:41:03Z

+
+      - name: Create follow-up issue
+        id: create-issue
+        if: steps.check-merged.outputs.merged == 'true'


When no verification comment is found, the extract step calls core.setFailed() but subsequent steps don't check if extraction was successful. They only check if the PR is merged. This means steps 3-5 will attempt to run even when extraction failed, potentially causing errors when trying to access undefined outputs. Consider adding a check for steps.extract.outcome == 'success' to the conditionals of subsequent steps, or use 'return' to exit early without failing the step.

Suggested change

if: steps.check-merged.outputs.merged == 'true'

if: steps.check-merged.outputs.merged == 'true' && steps.extract.outcome == 'success'

Copilot · 2026-01-08T03:41:03Z

+          with open('../open_issues.json') as f:
+              issues_data = json.load(f)


The file read operation doesn't include error handling. If the file doesn't exist or contains invalid JSON, the workflow will fail with an unclear error. Consider adding a try-except block with a descriptive error message to make debugging easier.

Suggested change

with open('../open_issues.json') as f:

issues_data = json.load(f)

try:

with open('../open_issues.json') as f:

issues_data = json.load(f)

except FileNotFoundError:

print('::warning::open_issues.json not found; skipping duplicate detection')

with open(os.environ['GITHUB_OUTPUT'], 'a') as f:

f.write('has_duplicates=false\n')

sys.exit(0)

except json.JSONDecodeError as e:

print(f'::error::Failed to parse open_issues.json as JSON: {e}')

sys.exit(1)

Copilot · 2026-01-08T03:41:03Z

+          tasks = open('../tasks.md').read()
+          acceptance = open('../acceptance.md').read()


The file read operations don't include error handling. If the files don't exist or contain invalid data, the workflow will fail with an unclear error. Consider adding a try-except block with a descriptive error message to make debugging easier.

Suggested change

tasks = open('../tasks.md').read()

acceptance = open('../acceptance.md').read()

try:

with open('../tasks.md', 'r', encoding='utf-8') as f:

tasks = f.read()

with open('../acceptance.md', 'r', encoding='utf-8') as f:

acceptance = f.read()

except OSError as e:

print(f'::error::Failed to read input files: {e}')

with open(os.environ['GITHUB_OUTPUT'], 'a') as f:

f.write('check_failed=true\n')

sys.exit(1)

Copilot · 2026-01-08T03:41:04Z

+
+permissions:
+  contents: read
+  issues: write


This workflow uses the label_matcher.py script which performs embedding-based similarity matching, but it's missing the 'models: read' permission that other similar workflows (agents-dedup.yml, agents-decompose.yml, agents-capability-check.yml) include. If the embedding provider requires this permission, the workflow may fail. Consider adding 'models: read' to the permissions block for consistency.

Suggested change

issues: write

issues: write

models: read

Copilot · 2026-01-08T03:41:04Z

+              title: '[Follow-up] Address verification concerns from PR #' + prNumber,
+              body: issueBody,
+              labels: ['follow-up', 'agents:optimize']
+            });


The JSON.parse call uses a template literal that directly interpolates step outputs without validation. If the step output contains special characters or malformed JSON, this could cause a runtime error. Consider using process.env with proper error handling instead, similar to how other parts of the workflow handle multi-line content.

Copilot · 2026-01-08T03:41:04Z

+        with:
+          script: |
+            const autoApplyLabels = JSON.parse('${{ steps.match.outputs.auto_apply_labels }}');


The JSON.parse call uses a template literal to directly parse step outputs. If the auto_apply_labels output contains special characters or is malformed, this will cause a runtime error. Consider using a safer parsing approach with try-catch error handling or accessing the value through process.env.

Suggested change

with:

script: |

const autoApplyLabels = JSON.parse('${{ steps.match.outputs.auto_apply_labels }}');

env:

AUTO_APPLY_LABELS: ${{ steps.match.outputs.auto_apply_labels }}

with:

script: |

let autoApplyLabelsRaw = process.env.AUTO_APPLY_LABELS;

let autoApplyLabels;

try {

autoApplyLabels = JSON.parse(autoApplyLabelsRaw || '[]');

} catch (error) {

core.setFailed(`Failed to parse AUTO_APPLY_LABELS: ${error}`);

return;

}

Copilot · 2026-01-08T03:41:04Z

+            const suggestedLabels = JSON.parse('${{ steps.match.outputs.suggested_labels }}');
+            const autoApplied = JSON.parse('${{ steps.match.outputs.auto_apply_labels }}');


The JSON.parse call uses a template literal to directly parse step outputs. If the suggested_labels output contains special characters or is malformed, this will cause a runtime error. Consider using a safer parsing approach with try-catch error handling or accessing the value through process.env.

Copilot · 2026-01-08T03:41:04Z

+          from scripts.langchain.task_decomposer import decompose_task
+
+          # Read issue context
+          context = open('../issue_context.md').read()


The file read operation doesn't include error handling. If the file doesn't exist or contains invalid data, the workflow will fail with an unclear error. Consider adding a try-except block with a descriptive error message to make debugging easier.

Suggested change

context = open('../issue_context.md').read()

try:

with open('../issue_context.md', 'r', encoding='utf-8') as f:

context = f.read()

except Exception as e:

print(f'::error::Failed to read issue context from ../issue_context.md: {e}')

sys.exit(1)

Copilot · 2026-01-08T03:41:05Z

+          with open(os.environ['GITHUB_OUTPUT'], 'a') as f:
+              f.write('check_failed=false\n')
+              f.write(f'recommendation={result.recommendation}\n')
+              f.write(f'blocked_count={len(result.blocked_tasks)}\n')
+              f.write(f'partial_count={len(result.partial_tasks)}\n')
+              f.write(f'result_json={json.dumps(result_dict)}\n')


Writing complex JSON directly to GITHUB_OUTPUT and then parsing it through YAML interpolation could cause issues if the JSON contains special characters that interfere with YAML parsing. Consider using a file-based approach (write to a file, then read from that file) for complex data structures, similar to how duplicates.json and subtasks.md are handled in other workflows.

Suggested change

with open(os.environ['GITHUB_OUTPUT'], 'a') as f:

f.write('check_failed=false\n')

f.write(f'recommendation={result.recommendation}\n')

f.write(f'blocked_count={len(result.blocked_tasks)}\n')

f.write(f'partial_count={len(result.partial_tasks)}\n')

f.write(f'result_json={json.dumps(result_dict)}\n')

# Write full JSON result to a file to avoid complex JSON in GITHUB_OUTPUT

json_path = os.path.join('..', 'capability_result.json')

with open(json_path, 'w') as json_file:

json.dump(result_dict, json_file)

with open(os.environ['GITHUB_OUTPUT'], 'a') as f:

f.write('check_failed=false\n')

f.write(f'recommendation={result.recommendation}\n')

f.write(f'blocked_count={len(result.blocked_tasks)}\n')

f.write(f'partial_count={len(result.partial_tasks)}\n')

f.write(f'result_json_path={os.path.abspath(json_path)}\n')

chore: sync workflow templates from Workflows repo

61abece

Automated sync from stranske/Workflows Template hash: 13e4f1e21f38 Changes synced from sync-manifest.yml

Copilot AI review requested due to automatic review settings January 8, 2026 03:35

stranske added sync Automated sync from Workflows automated Automated sync from Workflows labels Jan 8, 2026

stranske temporarily deployed to agent-standard January 8, 2026 03:35 — with GitHub Actions Inactive

stranske temporarily deployed to agent-standard January 8, 2026 03:36 — with GitHub Actions Inactive

Copilot started reviewing on behalf of stranske January 8, 2026 03:36 View session

github-actions Bot added the autofix Let bots format/lint automatically label Jan 8, 2026

chore(autofix): formatting/lint

b39b77c

github-actions Bot added the autofix:patch Autofix patch available label Jan 8, 2026

github-actions Bot removed the autofix:patch Autofix patch available label Jan 8, 2026

Copilot AI reviewed Jan 8, 2026

View reviewed changes

stranske merged commit 3d4d3fe into main Jan 8, 2026
27 checks passed

stranske deleted the sync/workflows-13e4f1e21f38 branch January 8, 2026 03:45

	if: steps.check-merged.outputs.merged == 'true'
	if: steps.check-merged.outputs.merged == 'true' && steps.extract.outcome == 'success'

		with open('../open_issues.json') as f:
		issues_data = json.load(f)

-          with open('../open_issues.json') as f:
-              issues_data = json.load(f)
+          try:
+              with open('../open_issues.json') as f:
+                  issues_data = json.load(f)
+          except FileNotFoundError:
+              print('::warning::open_issues.json not found; skipping duplicate detection')
+              with open(os.environ['GITHUB_OUTPUT'], 'a') as f:
+                  f.write('has_duplicates=false\n')
+              sys.exit(0)
+          except json.JSONDecodeError as e:
+              print(f'::error::Failed to parse open_issues.json as JSON: {e}')
+              sys.exit(1)

		tasks = open('../tasks.md').read()
		acceptance = open('../acceptance.md').read()

-          tasks = open('../tasks.md').read()
-          acceptance = open('../acceptance.md').read()
+          try:
+              with open('../tasks.md', 'r', encoding='utf-8') as f:
+                  tasks = f.read()
+              with open('../acceptance.md', 'r', encoding='utf-8') as f:
+                  acceptance = f.read()
+          except OSError as e:
+              print(f'::error::Failed to read input files: {e}')
+              with open(os.environ['GITHUB_OUTPUT'], 'a') as f:
+                  f.write('check_failed=true\n')
+              sys.exit(1)

-        with:
-          script: |
-            const autoApplyLabels = JSON.parse('${{ steps.match.outputs.auto_apply_labels }}');
+        env:
+          AUTO_APPLY_LABELS: ${{ steps.match.outputs.auto_apply_labels }}
+        with:
+          script: |
+            let autoApplyLabelsRaw = process.env.AUTO_APPLY_LABELS;
+            let autoApplyLabels;
+            try {
+              autoApplyLabels = JSON.parse(autoApplyLabelsRaw || '[]');
+            } catch (error) {
+              core.setFailed(`Failed to parse AUTO_APPLY_LABELS: ${error}`);
+              return;
+            }

		const suggestedLabels = JSON.parse('${{ steps.match.outputs.suggested_labels }}');
		const autoApplied = JSON.parse('${{ steps.match.outputs.auto_apply_labels }}');

-          context = open('../issue_context.md').read()
+          try:
+              with open('../issue_context.md', 'r', encoding='utf-8') as f:
+                  context = f.read()
+          except Exception as e:
+              print(f'::error::Failed to read issue context from ../issue_context.md: {e}')
+              sys.exit(1)

Conversation

stranske commented Jan 8, 2026

Sync Summary

Files Updated

Files Skipped

Review Checklist

Uh oh!

github-actions Bot commented Jan 8, 2026

Uh oh!

github-actions Bot commented Jan 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🤖 Keepalive Loop Status

Current State

🔍 Failure Classification

Uh oh!

github-actions Bot commented Jan 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Jan 8, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

github-actions Bot commented Jan 8, 2026 •

edited

Loading

github-actions Bot commented Jan 8, 2026 •

edited

Loading