feat(mem0-agent): capture gate, eval harness, and mixed-window fix

- triggers.py: hard-drop rules now filter PER TURN, so a durable fact sitting
  between two progress lines survives instead of being dropped with them. The
  eval harness caught this: 3 mixed-window fixtures were being destroyed
  client-side before the extractor ever saw them.
- widened flag rules for 13 plainly durable windows the gate was missing
  (standing preferences, X-over-Y decisions, stated rules, diagnoses, verified
  procedures); verified procedures moved from aggressive to balanced
- eval/: 56 labeled fixtures from the audited v1 corpus plus offline and live
  runners with a --check regression gate
- un-ignore integrations/mem0-agent/eval (root .gitignore excluded it silently)

Offline scorecard: hard_drop_recall 1.000, extract_recall 1.000,
flag_precision 1.000, 0 misclassified.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.gitignore

@@ -186,6 +186,9 @@ notebooks/*.yaml
 
 # local directories for testing
 eval/
+# ...but the plugin's evaluation harness is source, not local scratch
+!integrations/mem0-agent/eval/
+integrations/mem0-agent/eval/last_report.json
 qdrant_storage/
 .crossnote
 testing.ipynb