Skip to content

fix: power-steering incorrectly blocks Q&A/PM sessions with dev checks (#2914)#2916

Closed
rysweet wants to merge 2 commits intomainfrom
fix/2914-power-steering-qa-sessions
Closed

fix: power-steering incorrectly blocks Q&A/PM sessions with dev checks (#2914)#2916
rysweet wants to merge 2 commits intomainfrom
fix/2914-power-steering-qa-sessions

Conversation

@rysweet
Copy link
Owner

@rysweet rysweet commented Mar 7, 2026

Summary

  • Remove INVESTIGATION from workflow_invocation, next_steps, and documentation_updates applicable_session_types — these are dev-specific checks that produce false positives on investigation/PM sessions
  • Add new skill_invocation check: if a <command-name> tag exists in the transcript (user ran a slash command), verify the Skill tool was called for that skill

Problem

During a /pm-architect session (pure PM prioritization), power-steering blocked the session 4-5 times with irrelevant checks like workflow_invocation (demanded dev-orchestrator), next_steps (flagged the prioritized backlog as "remaining work"), and documentation_updates.

Root cause

Three INVESTIGATION blocker checks were designed for development workflows and don't apply to PM/research sessions:

  • workflow_invocation — demands Skill/Read for workflow file, but PM skills don't need dev-orchestrator
  • next_steps — flags project backlogs as incomplete work when the backlog IS the deliverable
  • documentation_updates — demands doc updates for sessions that don't change code

Test plan

  • 49/49 session classification tests pass (1 pre-existing failure excluded)
  • Pre-existing test failures confirmed on main branch (not introduced by this PR)
  • Manual: Run /pm-architect and verify power-steering doesn't block with dev checks
  • Manual: Run /dev and verify skill_invocation check passes when dev-orchestrator is called

🤖 Generated with Claude Code

Ubuntu and others added 2 commits March 7, 2026 16:16
#2914)

- Remove INVESTIGATION from workflow_invocation, next_steps, and
  documentation_updates applicable_session_types — these checks are
  designed for development sessions and produce false positives on
  investigation/PM sessions
- Add new skill_invocation check: if a session starts with a skill
  command (<command-name> tag), verify the Skill tool was actually
  called for that skill. This catches cases where Claude bypasses
  a requested skill without blocking sessions that correctly use skills.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@github-actions
Copy link
Contributor

github-actions bot commented Mar 7, 2026

🤖 Auto-fixed version bump

The version in pyproject.toml has been automatically bumped to the next patch version.

If you need a minor or major version bump instead, please update pyproject.toml manually and push the change.

@rysweet
Copy link
Owner Author

rysweet commented Mar 7, 2026

Closing: merge conflicts with the power_steering_checker package refactor (#2910). The considerations.yaml and checks_workflow.py changes will be reimplemented in a fresh PR against the current package structure. The skill_invocation check is valuable and will be preserved.

@rysweet rysweet closed this Mar 7, 2026
rysweet pushed a commit that referenced this pull request Mar 7, 2026
Detects when a user requests a skill via slash command (<command-name> tag)
but the agent bypasses it and responds directly without invoking the Skill
tool. This was independently valuable work from closed PR #2916 that got
dropped during the stale PR cleanup.

- checks_workflow.py: Add _check_skill_invocation method
- considerations.yaml: Add skill_invocation blocker for DEV/INVESTIGATION/MAINTENANCE
- 12 outside-in tests (Claude + Copilot + edge cases)

Related to #2914

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
rysweet added a commit that referenced this pull request Mar 7, 2026
…2926)

* feat: add skill_invocation power-steering check (extracted from #2916)

Detects when a user requests a skill via slash command (<command-name> tag)
but the agent bypasses it and responds directly without invoking the Skill
tool. This was independently valuable work from closed PR #2916 that got
dropped during the stale PR cleanup.

- checks_workflow.py: Add _check_skill_invocation method
- considerations.yaml: Add skill_invocation blocker for DEV/INVESTIGATION/MAINTENANCE
- 12 outside-in tests (Claude + Copilot + edge cases)

Related to #2914

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* [skip ci] chore: Auto-bump patch version

---------

Co-authored-by: Ubuntu <azureuser@deva.ftnmxvem3frujn3lepas045p5c.xx.internal.cloudapp.net>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant