docs: Add session debrief about test fixes and MCP tool lesson

2026-03-06 00:24:04 -05:00
parent 0b6db4b56c
commit 3376da7761
30 changed files with 874 additions and 1 deletions
--- a/add_ai_status.py
+++ b/add_ai_status.py
@@ -0,0 +1,72 @@
+with open("tests/test_visual_orchestration.py", "r", encoding="utf-8", newline="") as f:
+    content = f.read()
+
+# Add more explicit debug - check ai_status for errors
+content = content.replace(
+    '''# 3. Verify that Tier 1 generates tracks
+    print("[Test] Polling for Tier 1 tracks...")
+    tracks_generated = False
+    for i in range(120):
+        # Check both proposed_tracks AND comms log for tracks
+        mma_status = client.get_mma_status()
+        proposed = mma_status.get("proposed_tracks", [])
+        tier_usage = mma_status.get("mma_tier_usage", {})
+        
+        # Also check the comms log directly
+        session = client.get_session()
+        entries = session.get("session", {}).get("entries", [])
+        
+        # Check for track generation evidence
+        if proposed and len(proposed) > 0:
+            tracks_generated = True
+            print(f"[Test] Tracks found in proposed_tracks after {i}s: {proposed}")
+            break
+        elif tier_usage.get("Tier 1", {}).get("input", 0) > 0:
+            # AI was called, check comms log for track JSON
+            for entry in entries:
+                content = str(entry.get("content", ""))
+                if "track" in content.lower() and ("id" in content or "goal" in content):
+                    tracks_generated = True
+                    print(f"[Test] Tracks found in comms log after {i}s")
+                    break
+        if i % 10 == 0:
+            print(f"[Test] Debug: tier_usage={tier_usage}, proposed={proposed}, entries_count={len(entries)}")
+        time.sleep(1)
+    assert tracks_generated, f"Tier 1 failed to generate tracks within 120 seconds."''',
+    '''# 3. Verify that Tier 1 generates tracks
+    print("[Test] Polling for Tier 1 tracks...")
+    tracks_generated = False
+    for i in range(120):
+        # Check both proposed_tracks AND comms log for tracks
+        mma_status = client.get_mma_status()
+        proposed = mma_status.get("proposed_tracks", [])
+        tier_usage = mma_status.get("mma_tier_usage", {})
+        ai_status = mma_status.get("mma_status", "unknown")
+        
+        # Also check the comms log directly
+        session = client.get_session()
+        entries = session.get("session", {}).get("entries", [])
+        
+        # Check for track generation evidence
+        if proposed and len(proposed) > 0:
+            tracks_generated = True
+            print(f"[Test] Tracks found in proposed_tracks after {i}s: {proposed}")
+            break
+        elif tier_usage.get("Tier 1", {}).get("input", 0) > 0:
+            # AI was called, check comms log for track JSON
+            for entry in entries:
+                content = str(entry.get("content", ""))
+                if "track" in content.lower() and ("id" in content or "goal" in content):
+                    tracks_generated = True
+                    print(f"[Test] Tracks found in comms log after {i}s: {content[:100]}")
+                    break
+        if i % 10 == 0:
+            print(f"[Test] Debug: ai_status={ai_status}, tier_usage={tier_usage}, proposed={proposed}, entries={len(entries)}")
+        time.sleep(1)
+    assert tracks_generated, f"Tier 1 failed to generate tracks within 120 seconds. Status: {ai_status}"''',
+)
+
+with open("tests/test_visual_orchestration.py", "w", encoding="utf-8", newline="") as f:
+    f.write(content)
+
+print("Added ai_status debug")