Skip to content

chore: sync actions from gh-aw@v0.80.2#157

Merged
pelikhan merged 1 commit into
mainfrom
sync/gh-aw-v0.80.2
Jun 17, 2026
Merged

chore: sync actions from gh-aw@v0.80.2#157
pelikhan merged 1 commit into
mainfrom
sync/gh-aw-v0.80.2

Conversation

@github-actions

Copy link
Copy Markdown
Contributor

Automated sync of actions from gh-aw at v0.80.2.

@pelikhan pelikhan marked this pull request as ready for review June 17, 2026 03:24
Copilot AI review requested due to automatic review settings June 17, 2026 03:24
@pelikhan pelikhan merged commit 2702b42 into main Jun 17, 2026
7 checks passed
@pelikhan pelikhan deleted the sync/gh-aw-v0.80.2 branch June 17, 2026 03:25

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Syncs safe-outputs prompts and tool schema definitions from gh-aw@v0.80.2, keeping this repo’s agent harness guidance and safe-output tool metadata aligned with upstream.

Changes:

  • Add guidance to trust successful safe-output tool responses (avoid “verifying” writes from the sandbox).
  • Clarify temporary_id wording in the safe-outputs prompt.
  • Refresh safe_outputs_tools.json wording (notably replacing escaped unicode punctuation with literal em dashes) and update the update_release body schema constraints.
Show a summary per file
File Description
setup/md/safe_outputs_prompt.md Updates safe-outputs agent instructions, including new guidance about trusting successful safe-output tool responses.
setup/js/safe_outputs_tools.json Syncs safe-output tool schema descriptions/constraints to match upstream.

Copilot's findings

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

  • Files reviewed: 2/2 changed files
  • Comments generated: 1


**Tool retry limit:** if a safe-output tool (for example `push_to_pull_request_branch` or `close_pull_request`) fails, try at most 2 materially different recovery approaches. If the tool still fails, call `report_incomplete` with the error and the approaches attempted, then continue with other work. Do NOT debug underlying infrastructure after repeated failures.

**Trust successful tool responses.** Safeoutputs records write transactions that are applied after the agent finishes. A successful safe-output tool call means the transaction was accepted for downstream application. Do NOT independently verify the effect via `gh`, `gh api`, or other GitHub read paths from the current sandbox, because those paths will not reflect future safe-output writes.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants