chore: sync workflow templates by stranske · Pull Request #272 · stranske/Manager-Database

stranske · 2026-01-10T18:25:15Z

Sync Summary

Files Updated

agents-verifier.yml: Verifier - validates agent work meets acceptance criteria
agents-auto-label.yml: Auto-label - suggests/applies labels based on semantic matching (Phase 5A)
agents-dedup.yml: Duplicate detection - flags similar open issues (Phase 3C)
agents-auto-pilot.yml: Auto-pilot - end-to-end automation orchestrator (format → optimize → agent → verify)
parse_chatgpt_topics.py: Parses ChatGPT conversation into issue topics
error_classifier.js: Classifies CI errors for agent handling
conflict_detector.js: Conflict detector - identifies merge conflicts for targeted resolution
issue_formatter.py: Issue formatter - converts raw text to AGENT_ISSUE_TEMPLATE format
llm_provider.py: LLM provider configuration - GitHub Models and OpenAI client setup

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: 63e90e8d6749 Changes synced from sync-manifest.yml

github-actions · 2026-01-10T18:25:25Z

⚠️ Action Required: Unable to determine source issue for PR #272. The PR title, branch name, or body must contain the issue number (e.g. #123, branch: issue-123, or the hidden marker ).

github-actions · 2026-01-10T18:25:53Z

🤖 Keepalive Loop Status

PR #272 | Agent: Codex | Iteration 0/5

Current State

Metric	Value
Iteration progress	[----------] 0/5
Action	wait (missing-agent-label)
Disposition	skipped (transient)
Gate	success
Tasks	0/12 complete
Keepalive	❌ disabled
Autofix	❌ disabled

🔍 Failure Classification

Copilot

Pull request overview

This PR syncs workflow templates and supporting scripts from the stranske/Workflows repository, updating several agent automation workflows and related tooling. The changes introduce a new comprehensive auto-pilot workflow and update existing workflows for duplicate detection, auto-labeling, and verification.

Changes:

Upgraded default LLM model from gpt-4o-mini to gpt-4o for better evaluation quality
Added new agents-auto-pilot.yml workflow for end-to-end issue automation
Refactored multiple workflows to checkout locally instead of external Workflows repo
Enhanced duplicate detection with stricter similarity thresholds and title-based filtering
Updated auto-label logic to apply only the best matching label to prevent over-labeling

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated 11 comments.

Show a summary per file

File	Description
tools/llm_provider.py	Changed default model to gpt-4o with explanation
scripts/langchain/issue_formatter.py	Added task decomposition functionality with new helper functions
.github/workflows/agents-verifier.yml	Updated default models and descriptions for evaluation
.github/workflows/agents-dedup.yml	Changed to local checkout, raised similarity threshold, added title-based filtering
.github/workflows/agents-auto-pilot.yml	New comprehensive workflow for end-to-end issue automation
.github/workflows/agents-auto-label.yml	Changed to local checkout, refined auto-apply logic
.github/scripts/parse_chatgpt_topics.py	Added admin/dependency keywords to implementation_notes section
.github/scripts/error_classifier.js	Added debug logging for error classification
.github/scripts/conflict_detector.js	Added filtering for automated comments in conflict detection

Copilot · 2026-01-10T18:30:45Z

.github/workflows/agents-dedup.yml

+              # Require at least 40% of words to overlap for a duplicate flag
+              max_words = max(len(title_words_new), len(title_words_match), 1)
+              overlap_ratio = len(shared_words) / max_words
+              if m.score >= 0.95 or overlap_ratio >= 0.4:


The condition on line 143 checks for very high similarity (score >= 0.95) OR title overlap >= 0.4. However, this creates an inconsistency: matches with score >= 0.95 bypass the title overlap requirement entirely. This means issues with 95%+ content similarity but completely different titles (overlap_ratio = 0) would still be flagged as duplicates. Consider if this is the intended behavior or if high-similarity matches should also require some minimum title overlap.

Suggested change

# Require at least 40% of words to overlap for a duplicate flag

max_words = max(len(title_words_new), len(title_words_match), 1)

overlap_ratio = len(shared_words) / max_words

if m.score >= 0.95 or overlap_ratio >= 0.4:

# Require at least 40% of words to overlap for a duplicate flag,

# and ensure even very high-similarity matches have some title overlap.

max_words = max(len(title_words_new), len(title_words_match), 1)

overlap_ratio = len(shared_words) / max_words

if (m.score >= 0.95 and overlap_ratio > 0.0) or overlap_ratio >= 0.4:

Copilot · 2026-01-10T18:30:46Z

.github/workflows/agents-auto-label.yml


      - name: Set up Python
        uses: actions/setup-python@v5
        with:


The Python version was downgraded from 3.12 to 3.11. If this change is intentional for compatibility reasons, it should be documented why. If the codebase or dependencies require Python 3.12 features, this could cause runtime errors.

Suggested change

with:

with:

# Use Python 3.11 intentionally: some dependencies in this workflow (including optional extras)

# are not yet fully compatible with Python 3.12 in our CI environment.

Copilot · 2026-01-10T18:30:46Z

.github/workflows/agents-auto-label.yml

-          repository: stranske/Workflows
-          path: workflows-repo
+      - name: Checkout repository
+        uses: actions/checkout@v4


The checkout action was downgraded from v6 to v4. This is an unusual change as typically actions are upgraded to newer versions. If this is intentional for compatibility, it should be documented. Otherwise, consider keeping v6 which may have security or performance improvements.

Suggested change

uses: actions/checkout@v4

uses: actions/checkout@v6

Copilot · 2026-01-10T18:30:46Z

scripts/langchain/issue_formatter.py

+    if not tasks:
+        return formatted
+
+    from scripts.langchain import task_decomposer


The function attempts to import 'task_decomposer' from 'scripts.langchain', but this module doesn't exist in the repository. This will cause an ImportError at runtime when _apply_task_decomposition is called, breaking the issue formatting functionality.

Suggested change

from scripts.langchain import task_decomposer

try:

from scripts.langchain import task_decomposer

except ImportError:

# Task decomposition is optional; if the module is not available,

# fall back to returning the original formatted text.

return formatted

Copilot · 2026-01-10T18:30:47Z

.github/workflows/agents-auto-label.yml

+              auto_apply = [best_match]
+              # Move other high-confidence matches to suggestions
+              for m in matches[1:]:
+                  if m.score >= auto_threshold and m not in suggestions:


The condition 'm not in suggestions' on line 141 is redundant. The 'suggestions' list (line 132) only contains matches where score < auto_threshold, so any match with score >= auto_threshold will never be in 'suggestions'. The check 'm not in suggestions' will always evaluate to True when 'm.score >= auto_threshold' is True, making the second condition unnecessary.

Suggested change

if m.score >= auto_threshold and m not in suggestions:

if m.score >= auto_threshold:

Copilot · 2026-01-10T18:30:47Z

.github/workflows/agents-dedup.yml

          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          PYTHONPATH: ${{ github.workspace }}/workflows-repo
+          PYTHONPATH: ${{ github.workspace }}


The PYTHONPATH environment variable is set but unused. In line 38 and 83, 'cd workflows-repo' commands were removed but the PYTHONPATH was not removed from line 79. Since the checkout is now local (line 29), this environment variable is unnecessary.

Suggested change

PYTHONPATH: ${{ github.workspace }}

Copilot · 2026-01-10T18:30:48Z

.github/workflows/agents-dedup.yml


      - name: Set up Python
        uses: actions/setup-python@v5
        with:


The Python version was downgraded from 3.12 to 3.11. If this change is intentional for compatibility reasons, it should be documented why. If the codebase or dependencies require Python 3.12 features, this could cause runtime errors.

Suggested change

with:

with:

# Intentionally pinned to Python 3.11 for current dependency/runtime compatibility.

# TODO: Re-evaluate and upgrade to 3.12+ once all dependencies fully support it.

Copilot · 2026-01-10T18:30:48Z

.github/workflows/agents-dedup.yml

-          repository: stranske/Workflows
-          path: workflows-repo
+      - name: Checkout repository
+        uses: actions/checkout@v4


The checkout action was downgraded from v6 to v4. This is an unusual change as typically actions are upgraded to newer versions. If this is intentional for compatibility, it should be documented. Otherwise, consider keeping v6 which may have security or performance improvements.

Suggested change

uses: actions/checkout@v4

uses: actions/checkout@v6

Copilot · 2026-01-10T18:30:48Z

scripts/langchain/issue_formatter.py

+    if not suggestions:
+        return formatted
+
+    from scripts.langchain import issue_optimizer


The function attempts to import 'issue_optimizer' from 'scripts.langchain' and call '_apply_task_decomposition', but this module doesn't exist in the repository. This will cause an ImportError at runtime, breaking the issue formatting functionality.

Copilot · 2026-01-10T18:30:49Z

.github/workflows/agents-verifier.yml

            if (mode === 'compare') {
-              core.setOutput('model', 'gpt-4o');   // GitHub Models - current flagship
-              core.setOutput('model2', 'gpt-5.2'); // OpenAI - GPT-5.2
+              // gpt-5.2 (OpenAI) + Mistral-large (GitHub Models) for cross-provider comparison
+              core.setOutput('model', 'gpt-5.2');
+              core.setOutput('model2', 'Mistral-large-2407');
            } else {
-              core.setOutput('model', '');  // Use default
+              core.setOutput('model', '');  // Use default (gpt-4o)
              core.setOutput('model2', '');
            }
            core.setOutput('provider', '');  // Use default


When compare mode is triggered via label, the model is set to 'gpt-5.2' (an OpenAI model) on line 159, but the provider is set to empty string on line 165, which will use the default 'github-models' provider (line 62). This mismatch will cause the workflow to fail as gpt-5.2 is not available on GitHub Models. The provider should be set to 'openai' when using gpt-5.2, or the logic should be updated to handle cross-provider comparison correctly.

chore: sync workflow templates from Workflows repo

cb5d793

Automated sync from stranske/Workflows Template hash: 63e90e8d6749 Changes synced from sync-manifest.yml

Copilot AI review requested due to automatic review settings January 10, 2026 18:25

stranske added sync Automated sync from Workflows automated Automated sync from Workflows labels Jan 10, 2026

stranske temporarily deployed to agent-standard January 10, 2026 18:25 — with GitHub Actions Inactive

Copilot started reviewing on behalf of stranske January 10, 2026 18:26 View session

Copilot AI reviewed Jan 10, 2026

View reviewed changes

stranske closed this Jan 11, 2026

stranske deleted the sync/workflows-63e90e8d6749 branch January 11, 2026 04:37

-        with:
+        with:
+          # Use Python 3.11 intentionally: some dependencies in this workflow (including optional extras)
+          # are not yet fully compatible with Python 3.12 in our CI environment.

	if m.score >= auto_threshold and m not in suggestions:
	if m.score >= auto_threshold:

-        with:
+        with:
+          # Intentionally pinned to Python 3.11 for current dependency/runtime compatibility.
+          # TODO: Re-evaluate and upgrade to 3.12+ once all dependencies fully support it.

Conversation

stranske commented Jan 10, 2026

Sync Summary

Files Updated

Files Skipped

Review Checklist

Uh oh!

github-actions bot commented Jan 10, 2026

Uh oh!

github-actions bot commented Jan 10, 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!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 10, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

github-actions bot commented Jan 10, 2026 •

edited

Loading