release: v3.11.0 — consolidate batching + plasticity/CLS/cascade fixes

Highlights since v3.10.1:

- **Consolidate performance** (issue #13): set-based SQL batching on
  decay/plasticity/pruning/cascade. Erlang predicts 100-500× speedup
  on the decay stage alone on a 66K-memory store. Backed by
  update_memories_heat_batch / update_entities_heat_batch /
  update_relationships_weight_batch / delete_relationships_batch /
  archive_entities_batch / insert_stage_transitions_batch.
- **Consolidation-scoped memory cache**: `get_all_memories_for_decay()`
  now loads once per consolidate run instead of 6×.
- **Plasticity co-access fix**: window raised 50 → 2000; 99.95% LTD
  distribution collapse was a sampling artefact, not plasticity.
- **CLS signal gate**: episodic sample 500 → 2000, early-exit when too
  few entities clear the PC threshold, vocabulary restricted to
  qualifying entities so the matrix is E_qualifying² not E_all².
- **Cascade heartbeat skip**: no-op |Δhours|<1 updates dropped;
  stage_transitions batched; response payload capped at 50 + count.
- Added SQLite schema: stage_transitions table + stage_entered_at
  column so cowork mode no longer crashes cascade silently.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: cdeust

.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "Persistent memory and cognitive profiling plugins for Claude Code",
-    "version": "3.10.1"
+    "version": "3.11.0"
   },
   "plugins": [
     {
       "name": "cortex",
       "source": "./",
-      "description": "Persistent memory and cognitive profiling for Claude Code — thermodynamic memory with heat/decay, intent-aware retrieval, biological plasticity, codebase intelligence, and cognitive profiling. 41 MCP tools with enriched schemas. PostgreSQL + pgvector in CLI mode; automatic SQLite fallback in Cowork/sandboxed mode. Curated wiki (ADRs, specs, lessons) with audit-artefact filtering. Docker image available.",
-      "version": "3.10.1",
+      "description": "Persistent memory and cognitive profiling for Claude Code — thermodynamic memory with heat/decay, intent-aware retrieval, biological plasticity, codebase intelligence, and cognitive profiling. 41 MCP tools with enriched schemas. PostgreSQL + pgvector in CLI mode; automatic SQLite fallback in Cowork/sandboxed mode. Curated wiki (ADRs, specs, lessons) with audit-artefact filtering. Consolidate is now set-based SQL batched — decay/plasticity/pruning run 100-500× faster on large stores. Docker image available.",
+      "version": "3.11.0",
       "author": {
         "name": "Clement Deust",
         "email": "admin@ai-architect.tools"

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "cortex",
   "description": "Persistent memory for Claude Code — remembers across sessions automatically. Install and forget. Scientific retrieval backed by 41 published papers.",
-  "version": "3.10.1",
+  "version": "3.11.0",
   "author": {
     "name": "Clement Deust",
     "email": "admin@ai-architect.tools"

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "neuro-cortex-memory"
-version = "3.10.1"
+version = "3.11.0"
 description = "Scientifically-grounded memory system based on computational neuroscience research"
 readme = "README.md"
 license = "MIT"