feat(memory): add lifecycle hooks and vector memory plugin

Add plugin lifecycle hooks infrastructure:
- before_agent_start: inject context before agent loop
- agent_end: analyze conversation after completion
- 13 hook types total (message, tool, session, gateway hooks)

Memory plugin implementation:
- LanceDB vector storage with OpenAI embeddings
- kind: "memory" to integrate with upstream slot system
- Auto-recall: injects <relevant-memories> when context found
- Auto-capture: stores preferences, decisions, entities
- Rule-based capture filtering with 0.95 similarity dedup
- Tools: memory_recall, memory_store, memory_forget
- CLI: clawdbot ltm list|search|stats

Plugin infrastructure:
- api.on() method for hook registration
- Global hook runner singleton for cross-module access
- Priority ordering and error catching

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/plugins/loader.ts

@@ -8,6 +8,7 @@ import type { GatewayRequestHandler } from "../gateway/server-methods/types.js";
 import { createSubsystemLogger } from "../logging.js";
 import { resolveUserPath } from "../utils.js";
 import { discoverClawdbotPlugins } from "./discovery.js";
+import { initializeGlobalHookRunner } from "./hook-runner-global.js";
 import { createPluginRegistry, type PluginRecord, type PluginRegistry } from "./registry.js";
 import { createPluginRuntime } from "./runtime/index.js";
 import { setActivePluginRegistry } from "./runtime.js";
@@ -271,6 +272,7 @@ function createPluginRecord(params: {
     cliCommands: [],
     services: [],
     httpHandlers: 0,
+    hookCount: 0,
     configSchema: params.configSchema,
     configUiHints: undefined,
     configJsonSchema: undefined,
@@ -521,5 +523,6 @@ export function loadClawdbotPlugins(options: PluginLoadOptions = {}): PluginRegi
     registryCache.set(cacheKey, registry);
   }
   setActivePluginRegistry(registry, cacheKey);
+  initializeGlobalHookRunner(registry);
   return registry;
 }