From f8ce7c3a50c2596d423fd3bafa3da30eca531a02 Mon Sep 17 00:00:00 2001
From: Shane <shane94@hotmail.com>
Date: Fri, 30 Jan 2026 16:36:46 -0600
Subject: [PATCH 1/2] Improve PR agent Gate verification workflow

- Require Gate verification to run via task agent (prevents command substitution)
- Reference verify-tests-fail-without-fix skill by name instead of inline commands
- Add 'Common Gate Mistakes' section with explicit anti-patterns
- Fix ai-summary-comment regex to handle <details> tags with attributes

These changes prevent fabricating dual-direction test results from single runs.
---
 .github/agents/pr.md                          | 39 ++++++++++++++++++-
 .../scripts/post-ai-summary-comment.ps1       |  3 +-
 2 files changed, 39 insertions(+), 3 deletions(-)

diff --git a/.github/agents/pr.md b/.github/agents/pr.md
index 336fcc29310c..b7e60dd46396 100644
--- a/.github/agents/pr.md
+++ b/.github/agents/pr.md
@@ -441,10 +441,31 @@ Tests were already verified to FAIL in Phase 2. Gate is a confirmation step:
 **If starting from a PR (fix exists):**
 Use full verification mode - tests should FAIL without fix, PASS with fix.
 
-```bash
-pwsh .github/skills/verify-tests-fail-without-fix/scripts/verify-tests-fail.ps1 -Platform android -RequireFullVerification
+**🚨 MUST invoke as a task agent** to prevent command substitution:
+
+```markdown
+Invoke the `task` agent with agent_type: "task" and this prompt:
+
+"Invoke the verify-tests-fail-without-fix skill for this PR:
+- Platform: android (or ios)
+- TestFilter: 'IssueXXXXX'
+- RequireFullVerification: true
+
+Wait for FULL completion (5-10+ minutes). The skill does TWO test runs:
+1. Reverts fix → runs tests (should FAIL)
+2. Restores fix → runs tests (should PASS)
+
+Report back:
+1. Did tests FAIL without fix? (Yes/No)
+2. Did tests PASS with fix? (Yes/No)
+3. Final status: VERIFICATION PASSED or VERIFICATION FAILED
+4. Any errors or issues encountered"
 ```
 
+**Why task agent?** Running inline allows substituting commands and fabricating results. Task agent runs in isolation and reports exactly what happened.
+
+**⚠️ Do NOT run Gate verification inline - always use task agent with the skill.**
+
 ### Expected Output (PR with fix)
 
 ```
@@ -493,3 +514,17 @@ pwsh .github/skills/verify-tests-fail-without-fix/scripts/verify-tests-fail.ps1
 - ❌ **Running tests during Pre-Flight** - That's Phase 3
 - ❌ **Not creating state file first** - ALWAYS create state file before gathering context
 - ❌ **Skipping to Phase 4** - Gate MUST pass first
+
+## Common Gate Mistakes
+
+- ❌ **Running Gate verification inline** - Use task agent to prevent command substitution
+- ❌ **Using `BuildAndRunHostApp.ps1` for Gate** - That only runs ONE direction; the skill does TWO runs
+- ❌ **Using manual `dotnet test` commands** - Doesn't revert/restore fix files automatically
+- ❌ **Claiming "fails both ways" from a single test run** - That's fabrication; you need the script's TWO runs
+- ❌ **Not waiting for task agent completion** - Script takes 5-10+ minutes; wait for task to return
+
+**🚨 The verify-tests-fail.ps1 script does TWO test runs automatically:**
+1. Reverts fix → runs tests (should FAIL)
+2. Restores fix → runs tests (should PASS)
+
+Never run Gate inline. Always invoke as task agent.
diff --git a/.github/skills/ai-summary-comment/scripts/post-ai-summary-comment.ps1 b/.github/skills/ai-summary-comment/scripts/post-ai-summary-comment.ps1
index d0748a5a245f..83badb5a3319 100644
--- a/.github/skills/ai-summary-comment/scripts/post-ai-summary-comment.ps1
+++ b/.github/skills/ai-summary-comment/scripts/post-ai-summary-comment.ps1
@@ -289,7 +289,8 @@ function Extract-AllSections {
     $sections = @{}
     
     # Pattern to find all <details><summary><strong>TITLE</strong></summary>...content...</details> blocks
-    $pattern = '(?s)<details>\s*<summary><strong>([^<]+)</strong></summary>(.*?)</details>'
+    # Note: [^>]* handles optional attributes like "open" in <details open>
+    $pattern = '(?s)<details[^>]*>\s*<summary><strong>([^<]+)</strong></summary>(.*?)</details>'
     $matches = [regex]::Matches($StateContent, $pattern)
     
     if ($Debug) {

From 6112c1f4d0358c40506e26cda940cb341cf9304a Mon Sep 17 00:00:00 2001
From: Shane <shane94@hotmail.com>
Date: Fri, 30 Jan 2026 16:45:43 -0600
Subject: [PATCH 2/2] Trim Gate documentation to reference skill instead of
 duplicating

---
 .github/agents/pr.md | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/.github/agents/pr.md b/.github/agents/pr.md
index b7e60dd46396..53e323d82c30 100644
--- a/.github/agents/pr.md
+++ b/.github/agents/pr.md
@@ -451,20 +451,12 @@ Invoke the `task` agent with agent_type: "task" and this prompt:
 - TestFilter: 'IssueXXXXX'
 - RequireFullVerification: true
 
-Wait for FULL completion (5-10+ minutes). The skill does TWO test runs:
-1. Reverts fix → runs tests (should FAIL)
-2. Restores fix → runs tests (should PASS)
-
-Report back:
-1. Did tests FAIL without fix? (Yes/No)
-2. Did tests PASS with fix? (Yes/No)
-3. Final status: VERIFICATION PASSED or VERIFICATION FAILED
-4. Any errors or issues encountered"
+Report back: Did tests FAIL without fix? Did tests PASS with fix? Final status?"
 ```
 
 **Why task agent?** Running inline allows substituting commands and fabricating results. Task agent runs in isolation and reports exactly what happened.
 
-**⚠️ Do NOT run Gate verification inline - always use task agent with the skill.**
+See `.github/skills/verify-tests-fail-without-fix/SKILL.md` for full skill documentation.
 
 ### Expected Output (PR with fix)