Add proactivity features: memory CLI, session pruning, self-repair notifications, slash commands, status diagnostics, context warnings

Closes the proactivity gap with six features:

- Memory CLI (`ironclaw memory search/read/write/tree/status`) for direct workspace access without starting the full agent
- Session pruning background task that evicts idle sessions (configurable TTL, default 7 days)
- Self-repair notifications broadcast recovery results through channel manager instead of silent logging
- `/heartbeat`, `/summarize`, `/suggest` slash commands for manual heartbeat trigger, thread summarization, and next-step suggestions
- `ironclaw status` diagnostics command checking DB, session, secrets, embeddings, WASM tools, channels, heartbeat, and MCP servers
- Context pressure warning that notifies users before auto-compaction fires

Co-Authored-By: Claude Opus 4.6 <[email protected]>

.env.example

@@ -1,5 +1,5 @@
 # Database Configuration
-DATABASE_URL=postgres://near_agent:password@localhost:5432/near_agent
+DATABASE_URL=postgres://ironclaw:password@localhost:5432/ironclaw
 DATABASE_POOL_SIZE=10
 
 # LLM Provider (NEAR AI)
@@ -7,7 +7,7 @@ DATABASE_POOL_SIZE=10
 # Session token is stored in ~/.near-agent/session.json and managed automatically.
 # On first run, the agent will open a browser for OAuth authentication.
 NEARAI_MODEL=claude-3-5-sonnet-20241022
-NEARAI_BASE_URL=https://api.near.ai
+NEARAI_BASE_URL=https://cloud-api.near.ai
 NEARAI_AUTH_URL=https://private.near.ai
 # NEARAI_SESSION_PATH=~/.near-agent/session.json  # optional, default shown
 
@@ -28,7 +28,7 @@ HTTP_PORT=8080
 HTTP_WEBHOOK_SECRET=your-webhook-secret
 
 # Agent Settings
-AGENT_NAME=near-agent
+AGENT_NAME=ironclaw
 AGENT_MAX_PARALLEL_JOBS=5
 AGENT_JOB_TIMEOUT_SECS=3600
 AGENT_STUCK_THRESHOLD_SECS=300
@@ -51,4 +51,4 @@ SAFETY_MAX_OUTPUT_LENGTH=100000
 SAFETY_INJECTION_CHECK_ENABLED=true
 
 # Logging
-RUST_LOG=near_agent=debug,tower_http=debug
+RUST_LOG=ironclaw=debug,tower_http=debug