Skip to content

Add side quest: Diagnosing Common Agent Output Patterns#235

Merged
pelikhan merged 2 commits into
mainfrom
copilot/side-quest-diagnosing-common-agent-output-patterns
Jul 11, 2026
Merged

Add side quest: Diagnosing Common Agent Output Patterns#235
pelikhan merged 2 commits into
mainfrom
copilot/side-quest-diagnosing-common-agent-output-patterns

Conversation

Copilot AI commented Jul 11, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Step 9's troubleshooting table was embedded in a step focused on reading normal output, creating a detour. This extracts and expands it into a dedicated optional side quest.

Changes

New: workshop/side-quest-debug-output.md

  • Quick Log Anatomy Refresher table (all five line types with examples)
  • Five pattern sections — each with a concrete log snippet, root-cause explanation, and specific fix:
    • Long [plan] chains with no [tool] calls
    • [tool] calls returning empty results
    • safe-output: BLOCKED (limit reached)
    • permission denied failures
    • Summary says "done" but nothing written
  • 7-step debugging checklist
  • Return link to Step 9

Updated: workshop/09-understand-output.md

  • Step 4 compressed to a compact 3-column quick-reference table (What you see / Most likely cause / Quick fix)
  • > [!TIP] callout added with an optional link to the side quest

Updated: workshop/README.md

  • New side quest entry inserted in step order under Optional Side Quests, noting it branches from Step 9

Copilot AI linked an issue Jul 11, 2026 that may be closed by this pull request
[side-quest] Add side quest: Diagnosing Common Agent Output Patterns #233
Closed
@pelikhan
Add side quest: Diagnosing Common Agent Output Patterns
0e7f6eb 
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot AI changed the title [WIP] Add side quest: Diagnosing common agent output patterns Add side quest: Diagnosing Common Agent Output Patterns Jul 11, 2026
Copilot AI requested a review from pelikhan July 11, 2026 23:30
@pelikhan pelikhan marked this pull request as ready for review July 11, 2026 23:31
@pelikhan

pelikhan commented Jul 11, 2026

Copy link
Copy Markdown
Contributor

@copilot recommend to use the agentic-workflows skill tone style debug issues

@pelikhan pelikhan merged commit 4a302f9 into main Jul 11, 2026
1 check failed

Copilot AI commented Jul 11, 2026

Copy link
Copy Markdown
Contributor Author

@copilot recommend to use the agentic-workflows skill tone style debug issues

Done in the latest commit. Patterns 3 and 4 now explicitly recommend the agentic-workflows skill in their "What to do" sections — Pattern 3 suggests using it to add the dedup guideline, and Pattern 4 suggests asking it which permissions: scope and safe-outputs: key to use. All five patterns now consistently point learners to the skill when the fix involves changing workflow content.

Copilot stopped work on behalf of pelikhan due to an error July 11, 2026 23:33
The session was cancelled by the user.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@pelikhan pelikhan Awaiting requested review from pelikhan

Assignees

@pelikhan pelikhan

Copilot code review Copilot

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

[side-quest] Add side quest: Diagnosing Common Agent Output Patterns

2 participants

@pelikhan