Skip to content

docs: add Replaying Safe Outputs section to safe-outputs reference #22995

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pelikhan merged 2 commits into from
Mar 25, 2026
Merged

docs: add Replaying Safe Outputs section to safe-outputs reference #22995

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e62a249
Initial plan
Copilot Mar 25, 2026
13993ab
docs: add Replaying Safe Outputs section to safe-outputs reference
Copilot Mar 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/src/content/docs/agent-factory-status.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@ These are experimental agentic workflows used by the GitHub Next team to learn,
| [Agent Container Smoke Test](https://github.com/github/gh-aw/blob/main/.github/workflows/smoke-test-tools.md) | copilot | [![Agent Container Smoke Test](https://github.com/github/gh-aw/actions/workflows/smoke-test-tools.lock.yml/badge.svg)](https://github.com/github/gh-aw/actions/workflows/smoke-test-tools.lock.yml) | - | - |
| [Agent Performance Analyzer - Meta-Orchestrator](https://github.com/github/gh-aw/blob/main/.github/workflows/agent-performance-analyzer.md) | copilot | [![Agent Performance Analyzer - Meta-Orchestrator](https://github.com/github/gh-aw/actions/workflows/agent-performance-analyzer.lock.yml/badge.svg)](https://github.com/github/gh-aw/actions/workflows/agent-performance-analyzer.lock.yml) | - | - |
| [Agent Persona Explorer](https://github.com/github/gh-aw/blob/main/.github/workflows/agent-persona-explorer.md) | copilot | [![Agent Persona Explorer](https://github.com/github/gh-aw/actions/workflows/agent-persona-explorer.lock.yml/badge.svg)](https://github.com/github/gh-aw/actions/workflows/agent-persona-explorer.lock.yml) | - | - |
| [Agentic Observability Kit](https://github.com/github/gh-aw/blob/main/.github/workflows/agentic-observability-kit.md) | copilot | [![Agentic Observability Kit](https://github.com/github/gh-aw/actions/workflows/agentic-observability-kit.lock.yml/badge.svg)](https://github.com/github/gh-aw/actions/workflows/agentic-observability-kit.lock.yml) | - | - |
| [Agentic Workflow Audit Agent](https://github.com/github/gh-aw/blob/main/.github/workflows/audit-workflows.md) | claude | [![Agentic Workflow Audit Agent](https://github.com/github/gh-aw/actions/workflows/audit-workflows.lock.yml/badge.svg)](https://github.com/github/gh-aw/actions/workflows/audit-workflows.lock.yml) | - | - |
| [AI Moderator](https://github.com/github/gh-aw/blob/main/.github/workflows/ai-moderator.md) | codex | [![AI Moderator](https://github.com/github/gh-aw/actions/workflows/ai-moderator.lock.yml/badge.svg)](https://github.com/github/gh-aw/actions/workflows/ai-moderator.lock.yml) | - | - |
| [Archie](https://github.com/github/gh-aw/blob/main/.github/workflows/archie.md) | copilot | [![Archie](https://github.com/github/gh-aw/actions/workflows/archie.lock.yml/badge.svg)](https://github.com/github/gh-aw/actions/workflows/archie.lock.yml) | - | `/archie` |
Expand Down
23 changes: 23 additions & 0 deletions docs/src/content/docs/reference/safe-outputs.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1541,6 +1541,29 @@ To disable staged mode and start creating real resources, remove the `staged: tr

See [Staged Mode](/gh-aw/reference/staged-mode/) for the full guide, including the preview message format, per-type support table, custom message templates, and how to implement staged mode in [custom safe output jobs](/gh-aw/reference/custom-safe-outputs/#staged-mode-support).

## Replaying Safe Outputs

If the `safe_outputs` job fails or is skipped — for example, due to a transient API error, threat detection blocking the output, or a cancelled run — you can replay safe outputs from a previous run using the **Agentic Maintenance** workflow.

> [!NOTE]
> The Agentic Maintenance workflow (`agentics-maintenance.yml`) is generated automatically when any workflow uses the `expires` field in `create-issue`, `create-discussion`, or `create-pull-request` safe outputs.

To replay safe outputs:

1. Go to your repository's **Actions** tab.
2. Select the **Agentic Maintenance** workflow.
3. Click **Run workflow**.
4. Set **Optional maintenance operation** to `safe_outputs`.
5. Set **Run URL or run ID** to the URL or run ID of the previous workflow run:
- Full URL: `https://github.com/OWNER/REPO/actions/runs/12345`
- Run ID only: `12345`
6. Click **Run workflow**.

The `apply_safe_outputs` job downloads the `agent_output.json` artifact from the specified run and applies all safe outputs as if the original run had completed successfully. The job requires admin or maintainer permissions.
Comment on lines +1556 to +1562
Copy link

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

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

The step labels "Optional maintenance operation" / "Run URL or run ID" don’t match the exact input descriptions shown in the generated agentics-maintenance.yml workflow_dispatch UI ("Optional maintenance operation to run" and "Run URL or run ID to replay safe outputs from …"). To avoid user confusion (and to be resilient if the UI wording changes), consider referencing the input names (operation and run_url) or matching the descriptions verbatim.

This issue also appears on line 1562 of the same file.

Suggested change
4. Set **Optional maintenance operation** to `safe_outputs`.
5. Set **Run URL or run ID** to the URL or run ID of the previous workflow run:
- Full URL: `https://github.com/OWNER/REPO/actions/runs/12345`
- Run ID only: `12345`
6. Click **Run workflow**.
The `apply_safe_outputs` job downloads the `agent_output.json` artifact from the specified run and applies all safe outputs as if the original run had completed successfully. The job requires admin or maintainer permissions.
4. In the workflow inputs, set `operation` to `safe_outputs`.
5. Set `run_url` to the URL or run ID of the previous workflow run:
- Full URL: `https://github.com/OWNER/REPO/actions/runs/12345`
- Run ID only: `12345`
6. Click **Run workflow**.
The `apply_safe_outputs` job downloads the `agent_output.json` artifact from the run specified by the `run_url` input and applies all safe outputs as if the original run had completed successfully. The job requires admin or maintainer permissions.

Copilot uses AI. Check for mistakes.

> [!TIP]
> Find the run URL by opening the failed or cancelled run in the **Actions** tab — the URL in your browser's address bar is the run URL.

## Related Documentation

- [Staged Mode](/gh-aw/reference/staged-mode/) - Preview safe output operations without making changes
Expand Down
Loading