docs(eval): enforce min-sample gates in canary artifacts and decision log

docs/plans/artifacts/pi_embedded_eval_window_a_2026-02-24.json

@@ -1,5 +1,5 @@
 {
-  "generated_at": "2026-02-24T06:28:12.014Z",
+  "generated_at": "2026-02-24T06:33:31.111Z",
   "event_count": 45,
   "filters": {},
   "options": {
@@ -73,12 +73,12 @@
     },
     "fallback_categories": [
       {
-        "category": "loaded pi module does not expose a supported session factory (expected one of: c",
+        "category": "empty_assistant_text",
         "count": 1,
         "pct": 50
       },
       {
-        "category": "pi agent runtime produced no assistant text",
+        "category": "pi_module_interface",
         "count": 1,
         "pct": 50
       }
@@ -97,6 +97,24 @@
   "gate": {
     "pass": false,
     "criteria": [
+      {
+        "criterion": "Minimum target routes",
+        "pass": true,
+        "actual": "8",
+        "threshold": ">= 8"
+      },
+      {
+        "criterion": "Minimum baseline routes",
+        "pass": true,
+        "actual": "2",
+        "threshold": ">= 2"
+      },
+      {
+        "criterion": "Minimum target external attempts",
+        "pass": true,
+        "actual": "8",
+        "threshold": ">= 8"
+      },
       {
         "criterion": "Completion rate delta (target - baseline)",
         "pass": true,

docs/plans/artifacts/pi_embedded_eval_window_a_2026-02-24.md

@@ -32,8 +32,8 @@
 
 | Category | Count | Percent |
 | --- | ---: | ---: |
-| loaded pi module does not expose a supported session factory (expected one of: c | 1 | 50.00% |
-| pi agent runtime produced no assistant text | 1 | 50.00% |
+| empty_assistant_text | 1 | 50.00% |
+| pi_module_interface | 1 | 50.00% |
 
 ## Top Fallback Reasons
 
@@ -43,6 +43,9 @@
 ## Gate Evaluation
 
 - Gate result: HOLD
+- [x] Minimum target routes: actual=8, threshold=>= 8
+- [x] Minimum baseline routes: actual=2, threshold=>= 2
+- [x] Minimum target external attempts: actual=8, threshold=>= 8
 - [x] Completion rate delta (target - baseline): actual=0.00pp, threshold=>= -2.00pp
 - [ ] P50 latency delta (target - baseline): actual=259ms, threshold=<= 250ms
 - [ ] P95 latency delta (target - baseline): actual=5695ms, threshold=<= 700ms

docs/plans/artifacts/pi_embedded_eval_window_b_2026-02-24_post_fallbacks.json

@@ -1,5 +1,5 @@
 {
-  "generated_at": "2026-02-24T06:30:22.439Z",
+  "generated_at": "2026-02-24T06:33:37.931Z",
   "event_count": 24,
   "filters": {
     "since_ms": 1771913640000
@@ -71,6 +71,24 @@
   "gate": {
     "pass": false,
     "criteria": [
+      {
+        "criterion": "Minimum target routes",
+        "pass": false,
+        "actual": "6",
+        "threshold": ">= 8"
+      },
+      {
+        "criterion": "Minimum baseline routes",
+        "pass": false,
+        "actual": "0",
+        "threshold": ">= 2"
+      },
+      {
+        "criterion": "Minimum target external attempts",
+        "pass": false,
+        "actual": "6",
+        "threshold": ">= 8"
+      },
       {
         "criterion": "Completion rate delta (target - baseline)",
         "pass": false,

docs/plans/artifacts/pi_embedded_eval_window_b_2026-02-24_post_fallbacks.md

@@ -40,6 +40,9 @@
 ## Gate Evaluation
 
 - Gate result: HOLD
+- [ ] Minimum target routes: actual=6, threshold=>= 8
+- [ ] Minimum baseline routes: actual=0, threshold=>= 2
+- [ ] Minimum target external attempts: actual=6, threshold=>= 8
 - [ ] Completion rate delta (target - baseline): actual=n/a, threshold=>= -2.00pp
 - [ ] P50 latency delta (target - baseline): actual=n/a, threshold=<= 250ms
 - [ ] P95 latency delta (target - baseline): actual=n/a, threshold=<= 700ms