You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: .github/aw/create-agentic-workflow.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -304,7 +304,7 @@ safe-outputs:
304
304
---
305
305
306
306
<!-- Edit the file linked below to modify the agent without recompilation. Feel free to move the entire markdown body to that file. -->
307
-
@./agentics/<workflow-id>.md
307
+
{{#runtime-import agentics/<workflow-id>.md}}
308
308
```
309
309
310
310
**Note**: This example omits `workflow_dispatch:` (auto-added by compiler), `timeout-minutes:` (has sensible default), and `engine:` (Copilot is default). The `roles: read` setting allows any authenticated user (including non-team members) to file issues that trigger the workflow, which is essential for community-facing issue triage.
Copy file name to clipboardExpand all lines: .github/aw/update-agentic-workflow.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -322,7 +322,7 @@ If no agentics file exists, edit the markdown body of the workflow file.
322
322
323
323
## Prompt Editing Without Recompilation
324
324
325
-
**Key Feature**: If the workflow uses runtime imports (e.g., `@./agentics/<workflow-id>.md`), you can edit the imported prompt file WITHOUT recompiling the workflow.
325
+
**Key Feature**: If the workflow uses runtime imports (e.g., `{{#runtime-import agentics/<workflow-id>.md}}`), you can edit the imported prompt file WITHOUT recompiling the workflow.
326
326
327
327
**When to use this**:
328
328
- Improving agent instructions
@@ -331,7 +331,7 @@ If no agentics file exists, edit the markdown body of the workflow file.
331
331
- Adding security notices
332
332
333
333
**How to do it**:
334
-
1. Check if the workflow has a runtime import: `@./agentics/<workflow-id>.md`
334
+
1. Check if the workflow has a runtime import: `{{#runtime-import agentics/<workflow-id>.md}}`
335
335
2. If yes, edit that file directly - no compilation needed!
> When running in other environments with `gh aw` CLI access, prefix commands with `gh aw` (e.g., `gh aw compile`).
34
+
>
35
+
> These tools provide the same functionality through the MCP server without requiring GitHub CLI authentication.
35
36
36
37
## Instructions
37
38
@@ -143,7 +144,7 @@ After fixing all errors:
143
144
3. **Refresh Agent and Instruction Files**
144
145
145
146
After successfully upgrading workflows, refresh the agent files and instructions to ensure you have the latest versions:
146
-
- Run `gh aw init` to update all agent files (`.github/agents/*.md`) and instruction files (`.github/aw/github-agentic-workflows.md`)
147
+
- Run `gh aw init --push` to update all agent files (`.github/agents/*.md`) and instruction files (`.github/aw/github-agentic-workflows.md`), then automatically commit and push the changes
147
148
- This ensures that agents and instructions are aligned with the new gh-aw version
148
149
- The command will preserve your existing configuration while updating to the latest templates
149
150
@@ -190,12 +191,12 @@ Upgraded all agentic workflows to gh-aw version [VERSION].
190
191
- ✅ No compilation errors or warnings
191
192
192
193
### Post-Upgrade Steps
193
-
- ✅ Refreshed agent files and instructions with `gh aw init`
194
+
- ✅ Refreshed agent files and instructions with `gh aw init --push`
194
195
195
196
## Files Changed
196
197
- Updated `.md` workflow files: [LIST]
197
198
- Generated `.lock.yml` files: [LIST]
198
-
- Updated agent files: [LIST] (if `gh aw init` was run)
199
+
- Updated agent files: [LIST] (if `gh aw init --push` was run)
0 commit comments