@datatamer.ai/agentdev 1.0.6 → 1.0.7

package/skills/auto-ticket-workflow.md

@@ -47,6 +47,27 @@ Instead, all OpenSpec operations are INLINED in this skill:
 - Print errors immediately if they occur
 - NEVER run silently - the user needs to see what's happening
 
+## CRITICAL: Post Intermediate Progress Comments to GitHub
+
+**In addition to printing progress, post intermediate step updates as GitHub issue comments.**
+
+The user wants real-time visibility into what the workflow is doing. Post short progress comments at key intermediate steps — not just at the end of each phase.
+
+**Use this helper pattern to post progress comments:**
+```bash
+gh issue comment <issue-number> -R data-tamer/<repo> --body "🔄 <step description>"
+```
+
+**When to post intermediate comments:**
+- Phase 2: When starting OpenSpec creation, when each artifact is created
+- Phase 3: When starting implementation, when each task starts, when each task completes, when committing
+- Phase 4: When starting local tests, when tests pass/fail
+- Phase 5: When pushing to git, when merging to production, when waiting for CI, when deployment completes
+- Phase 6: When starting production tests, when tests pass/fail
+- Phase 7: Before moving to Done, refresh comments to check for new instructions
+
+**Keep intermediate comments SHORT** (1-2 lines). The phase summary comments at the end of each phase remain as-is for detailed summaries.
+
 ## Check for New Comments Between Phases
 
 **Between every phase transition**, check if new comments have been posted on the ticket:
@@ -231,7 +252,12 @@ openspec status --change "<change-name>" --json
 ```
 Parse the JSON to get `applyRequires` (artifacts needed before implementation).
 
-5. **Create artifacts in sequence:**
+5. **Post progress comment:**
+```bash
+gh issue comment <issue-number> -R data-tamer/<repo> --body "🔄 OpenSpec change \`<change-name>\` created. Building artifacts..."
+```
+
+6. **Create artifacts in sequence:**
 
 For each artifact in dependency order:
 ```bash
@@ -241,11 +267,12 @@ openspec instructions <artifact-id> --change "<change-name>" --json
 - Read the `template` from instructions
 - Read any dependency files for context
 - Create the artifact file following the template structure
+- **Post progress comment:** `gh issue comment <issue-number> -R data-tamer/<repo> --body "🔄 Created artifact: \`<artifact-id>\`"`
 - Print "✓ Created <artifact-id>"
 
 Continue until all `applyRequires` artifacts are complete.
 
-6. **Comment on GitHub issue with OpenSpec status:**
+7. **Comment on GitHub issue with OpenSpec status:**
 ```bash
 gh issue comment <issue-number> -R data-tamer/<repo> --body "## 🔄 Phase 2: OpenSpec Created
 
@@ -290,16 +317,22 @@ This returns context files and task list.
 
 4. **Read context files** listed in `contextFiles` (proposal, specs, design, tasks).
 
-5. **Implement tasks one by one:**
+5. **Post progress comment that implementation is starting:**
+```bash
+gh issue comment <issue-number> -R data-tamer/<repo> --body "🔄 Starting implementation..."
+```
+
+6. **Implement tasks one by one:**
 
 For each pending task in tasks.md:
+- **Post progress comment:** `gh issue comment <issue-number> -R data-tamer/<repo> --body "🔄 Working on: <task description>"`
 - Print "Working on task: <task description>"
 - Make the code changes required
 - Keep changes minimal and focused
 - Mark task complete: `- [ ]` → `- [x]`
 - Print "✓ Task complete"
 
-6. **Commit changes:**
+7. **Commit changes:**
 ```bash
 git add <changed-files>
 git commit -m "fix/feat: <description>
@@ -309,7 +342,7 @@ Fixes #<issue-number>
 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>"
 ```
 
-7. **Comment on GitHub issue with implementation details:**
+8. **Comment on GitHub issue with implementation details:**
 ```bash
 gh issue comment <issue-number> -R data-tamer/<repo> --body "## 🔄 Phase 3: Implementation Complete
 
@@ -328,12 +361,17 @@ Starting local testing...
 
 ### Phase 4: Local Testing
 
-1. Determine which services need restart:
+1. **Post progress comment:**
+```bash
+gh issue comment <issue-number> -R data-tamer/<repo> --body "🔄 Starting local testing..."
+```
+
+2. Determine which services need restart:
    - `data-tamer-dashboard/` → Frontend (hot reload, NO restart needed)
    - `tamer_service/` → `kubectl rollout restart deployment/tamer-datasource-consumer-dev deployment/tamer-message-consumer-dev -n datatamer`
    - `consumer_service/` → `kubectl rollout restart deployment/consumer-service-dev -n datatamer`
 
-2. **Run Playwright headless tests:**
+3. **Run Playwright headless tests:**
 ```bash
 cd /home/riccardo/Documents/apps/datatamer/app/auto-ticket-logs
 node playwright-test.js login        # Test login works
@@ -341,9 +379,9 @@ node playwright-test.js slides       # Test slides feature
 ```
 Screenshots are saved to `/tmp/auto-ticket-screenshots/`
 
-3. If tests fail: Fix issues and re-test (do NOT move to production)
+4. If tests fail: Fix issues and re-test (do NOT move to production)
 
-4. If tests pass: **Comment on GitHub issue:**
+5. If tests pass: **Comment on GitHub issue:**
 ```bash
 gh issue comment <issue-number> -R data-tamer/<repo> --body "## 🔄 Phase 4: Local Testing Passed
 
@@ -359,7 +397,12 @@ All local tests passed. Starting production deployment...
 
 ### Phase 5: Production Deployment
 
-1. **Deploy using git workflow:**
+1. **Post progress comment:**
+```bash
+gh issue comment <issue-number> -R data-tamer/<repo> --body "🔄 Starting production deployment..."
+```
+
+2. **Deploy using git workflow:**
 ```bash
 git push origin master
 git checkout production
@@ -368,17 +411,22 @@ git push origin production
 git checkout master
 ```
 
-2. **Wait for GitHub Actions:**
+3. **Post progress comment:**
+```bash
+gh issue comment <issue-number> -R data-tamer/<repo> --body "🔄 Code pushed to production branch. Waiting for CI..."
+```
+
+4. **Wait for GitHub Actions:**
 ```bash
 gh run watch -R data-tamer/<repo>
 ```
 
-3. **Verify production pods:**
+5. **Verify production pods:**
 ```bash
 ssh root@153.92.127.95 'export KUBECONFIG=/etc/rancher/k3s/k3s.yaml && kubectl get pods -n datatamer | grep <service>'
 ```
 
-4. **Comment on GitHub issue with deployment status:**
+6. **Comment on GitHub issue with deployment status:**
 ```bash
 gh issue comment <issue-number> -R data-tamer/<repo> --body "## 🔄 Phase 5: Production Deployed
 
@@ -406,25 +454,30 @@ gh api graphql -f query='query { node(id: "<item-id>") { ... on ProjectV2Item {
 ```
 Print "✓ Ticket #<number> moved to test (verified)"
 
-2. **Run Playwright tests on production:**
+2. **Post progress comment:**
+```bash
+gh issue comment <issue-number> -R data-tamer/<repo> --body "🔄 Running production tests..."
+```
+
+3. **Run Playwright tests on production:**
 ```bash
 cd /home/riccardo/Documents/apps/datatamer/app/auto-ticket-logs
 node playwright-test.js login --production
 node playwright-test.js slides --production
 ```
 
-3. **Take final screenshot of the feature working:**
+4. **Take final screenshot of the feature working:**
    - Use browser automation (Claude in Chrome MCP) to navigate to the relevant page on production
    - Take a screenshot showing the implemented feature
    - Save to `/tmp/auto-ticket-screenshots/final-<issue-number>.png`
 
-4. **If production tests FAIL:**
+5. **If production tests FAIL:**
    - Comment on issue with failure details
    - Rollback if critical
    - Move ticket back to "Todo" (with verification)
    - Stop workflow
 
-5. **If production tests PASS:**
+6. **If production tests PASS:**
    - **Comment on GitHub issue:**
 ```bash
 gh issue comment <issue-number> -R data-tamer/<repo> --body "## 🔄 Phase 6: Production Testing Passed
@@ -440,7 +493,13 @@ All production tests passed. Completing ticket...
 
 ### Phase 7: Completion
 
-1. **Move ticket to "Done" and VERIFY:**
+1. **CRITICAL: Refresh comments before completing.** Read ALL comments one final time to check for new instructions:
+```bash
+agentdev gh api rest 'repos/data-tamer/<repo>/issues/<issue-number>/comments' | node -e "let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{JSON.parse(d).forEach(c=>console.log('---',c.user.login,c.created_at,'---\n'+c.body+'\n'))})"
+```
+If any new non-bot comment contains instructions to stop, cancel, or change something — DO NOT move to Done. Instead, address the new instructions first.
+
+2. **Move ticket to "Done" and VERIFY:**
 ```bash
 # Move to Done
 gh project item-edit --id <item-id> --project-id PVT_kwDOCJIWbs4AnuSZ \
@@ -452,26 +511,48 @@ gh api graphql -f query='query { node(id: "<item-id>") { ... on ProjectV2Item {
 ```
 Print "✓ Ticket #<number> moved to Done (verified)"
 
-2. **Archive OpenSpec change:**
+3. **Archive OpenSpec change:**
 ```bash
 openspec archive "<change-name>"
 ```
 
-3. **Upload final screenshot to GitHub:**
+4. **Upload final screenshot to GitHub:**
    - Check if screenshot exists at `/tmp/auto-ticket-screenshots/final-<issue-number>.png`
-   - If exists, upload to GitHub using the issue comment with image attachment:
+   - Upload to ImgBB via the agentdev server and include in comment:
 ```bash
-# Upload screenshot as asset and get URL
+# Upload screenshot and get URL
 SCREENSHOT="/tmp/auto-ticket-screenshots/final-<issue-number>.png"
 if [ -f "$SCREENSHOT" ]; then
-  # Create a gist or use GitHub's drag-drop equivalent via API
-  # For now, reference the local screenshot in the comment
-  gh issue comment <issue-number> -R data-tamer/<repo> --body "## Ticket Complete ✅
+  # Convert image to base64
+  BASE64_IMG=$(base64 -w 0 "$SCREENSHOT")
+
+  # Upload via agentdev server API (works for both local and production)
+  AGENTDEV_URL="${AGENTDEV_URL:-http://localhost:3847}"
+  IMAGE_URL=$(curl -s -X POST "$AGENTDEV_URL/api/upload-image" \
+    -H "Content-Type: application/json" \
+    -d "{\"base64\":\"$BASE64_IMG\",\"filename\":\"ticket-$issue-number-final.png\"}" \
+    | jq -r '.url')
+
+  if [ ! -z "$IMAGE_URL" ] && [ "$IMAGE_URL" != "null" ]; then
+    # Post comment with embedded screenshot
+    gh issue comment <issue-number> -R data-tamer/<repo> --body "## Ticket Complete ✅
 
 ### Final Result Screenshot
-![Final Result](https://app.datatamer.ai/screenshot-placeholder.png)
+![Final Result]($IMAGE_URL)
 
-*Screenshot saved locally at: \`$SCREENSHOT\`*
+### Summary
+All phases passed:
+- ✓ OpenSpec created
+- ✓ Implementation complete
+- ✓ Local tests passed
+- ✓ Production deployed
+- ✓ Production tests passed
+
+---
+*Automated by Claude Code Auto-Ticket Workflow*"
+  else
+    echo "⚠️  Screenshot upload failed, posting comment without image"
+    gh issue comment <issue-number> -R data-tamer/<repo> --body "## Ticket Complete ✅
 
 ### Summary
 All phases passed:
@@ -481,17 +562,21 @@ All phases passed:
 - ✓ Production deployed
 - ✓ Production tests passed
 
+*Screenshot saved locally at: \`$SCREENSHOT\`*
+
 ---
 *Automated by Claude Code Auto-Ticket Workflow*"
+  fi
 fi
 ```
 
-   **Alternative: Attach screenshot directly using gh CLI:**
-   - The `gh` CLI doesn't support direct image upload to comments
-   - Instead, use the Read tool to view the screenshot and describe the result in the comment
-   - Or upload to an image hosting service and include the URL
+   **How it works:**
+   - Screenshots are uploaded to ImgBB via the agentdev server's `/api/upload-image` endpoint
+   - The endpoint returns a permanent public URL that works in GitHub comments
+   - No authentication needed (uses server's ImgBB API key)
+   - Works for both local (`http://localhost:3847`) and production (`https://agentdev.datatamer.ai`)
 
-4. **Add completion comment with screenshot description:**
+5. **Add completion comment with screenshot description:**
 
 If screenshot was taken, use the Read tool to view it and include a description of what it shows in the completion comment. The comment should describe:
 - What page/feature is shown
@@ -520,7 +605,7 @@ gh issue comment <issue-number> -R data-tamer/<repo> --body "## Ticket Complete
 *Automated by Claude Code Auto-Ticket Workflow*"
 ```
 
-5. **Close the issue:**
+6. **Close the issue:**
 ```bash
 gh issue close <issue-number> -R data-tamer/<repo> --reason completed
 ```