Safe-Outputs Discussions Enforcement Test Results
Run: https://github.com/github/gh-aw-mcpg/actions/runs/23967767060
Trigger: schedule
Configuration tested: create-discussion (max:1, prefix, category), update-discussion (enabled, all fields), close-discussion (required-category:General, required-labels:[smoke-test]), add-comment (max:2, target:triggering)
Phase 1: create-discussion
| Test |
Operation |
Expected |
Actual |
Status |
| 1.1 |
Create discussion (valid prefix+category+label) |
✅ Processed |
✅ Processed (success returned; discussion not immediately visible via API — likely propagation delay) |
✅ PASS |
| 1.2 |
Create 2nd discussion (max exceeded) |
❌ Rejected |
✅ Processed (tool returned success instead of rejection) |
❌ FAIL |
Phase 2: update-discussion
| Test |
Operation |
Expected |
Actual |
Status |
| 2.1 |
Update labels: ["smoke-test", "status"] |
✅ Processed |
✅ Processed |
✅ PASS |
| 2.2 |
Update body (append note) |
✅ Processed |
✅ Processed |
✅ PASS |
Phase 3: close-discussion
| Test |
Operation |
Expected |
Actual |
Status |
| 3.1 |
Close test discussion (valid labels+category) |
✅ Processed |
✅ Processed |
✅ PASS |
| 3.2 |
Close discussion without required label |
❌ Rejected |
SKIPPED — all existing discussions have smoke-test label; no suitable unlabeled target found |
✅ SKIPPED |
| 3.3 |
Close 2nd discussion (max exceeded) |
❌ Rejected |
✅ Processed (tool returned success instead of rejection; max enforcement not triggered) |
❌ FAIL |
Phase 4: add-comment (target: triggering)
| Test |
Operation |
Expected |
Actual |
Status |
| 4.1 |
Comment on triggering item (1st) |
✅ Processed |
SKIPPED |
✅ SKIPPED |
| 4.2 |
Comment on triggering item (2nd) |
✅ Processed |
SKIPPED |
✅ SKIPPED |
| 4.3 |
3rd comment (max: 2 exceeded) |
❌ Rejected |
SKIPPED |
✅ SKIPPED |
| 4.4 |
Comment on non-triggering item |
❌ Rejected |
SKIPPED |
✅ SKIPPED |
Summary
- Phase 1 (create-discussion): 1/2 ✅
- Phase 2 (update-discussion): 2/2 ✅
- Phase 3 (close-discussion): 1/2 ✅ (+ 1 SKIPPED)
- Phase 4 (add-comment): SKIPPED (schedule trigger — no triggering item)
- Overall: FAIL
Failures Noted
- Test 1.2:
create_discussion was called a second time after max:1 was already consumed. The tool returned {"result":"success"} instead of rejecting the request. Enforcement of max:1 for create-discussion did not trigger.
- Test 3.3:
close_discussion was called a second time after max:1 was consumed by Test 3.1. The tool returned {"result":"success"} instead of rejecting. Enforcement of max:1 for close-discussion did not trigger.
💬 Safe-outputs discussions enforcement test by Smoke Safe-Outputs Discussions
