feat(#93): implement agent spawn via federation

Implements FED-010: Agent Spawn via Federation feature that enables
spawning and managing Claude agents on remote federated Mosaic Stack
instances via COMMAND message type.

Features:
- Federation agent command types (spawn, status, kill)
- FederationAgentService for handling agent operations
- Integration with orchestrator's agent spawner/lifecycle services
- API endpoints for spawning, querying status, and killing agents
- Full command routing through federation COMMAND infrastructure
- Comprehensive test coverage (12/12 tests passing)

Architecture:
- Hub → Spoke: Spawn agents on remote instances
- Command flow: FederationController → FederationAgentService →
  CommandService → Remote Orchestrator
- Response handling: Remote orchestrator returns agent status/results
- Security: Connection validation, signature verification

Files created:
- apps/api/src/federation/types/federation-agent.types.ts
- apps/api/src/federation/federation-agent.service.ts
- apps/api/src/federation/federation-agent.service.spec.ts

Files modified:
- apps/api/src/federation/command.service.ts (agent command routing)
- apps/api/src/federation/federation.controller.ts (agent endpoints)
- apps/api/src/federation/federation.module.ts (service registration)
- apps/orchestrator/src/api/agents/agents.controller.ts (status endpoint)
- apps/orchestrator/src/api/agents/agents.module.ts (lifecycle integration)

Testing:
- 12/12 tests passing for FederationAgentService
- All command service tests passing
- TypeScript compilation successful
- Linting passed

Refs #93

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

docs/SEMANTIC_SEARCH.md

@@ -63,6 +63,7 @@ Get your API key from: https://platform.openai.com/api-keys
 ### OpenAI Model
 
 The default embedding model is `text-embedding-3-small` (1536 dimensions). This provides:
+
 - High quality embeddings
 - Cost-effective pricing
 - Fast generation speed
@@ -76,6 +77,7 @@ The default embedding model is `text-embedding-3-small` (1536 dimensions). This
 Search using vector similarity only.
 
 **Request:**
+
 ```json
 {
   "query": "database performance optimization",
@@ -84,10 +86,12 @@ Search using vector similarity only.
 ```
 
 **Query Parameters:**
+
 - `page` (optional): Page number (default: 1)
 - `limit` (optional): Results per page (default: 20)
 
 **Response:**
+
 ```json
 {
   "data": [
@@ -118,6 +122,7 @@ Search using vector similarity only.
 Combines vector similarity and full-text search using Reciprocal Rank Fusion (RRF).
 
 **Request:**
+
 ```json
 {
   "query": "indexing strategies",
@@ -126,6 +131,7 @@ Combines vector similarity and full-text search using Reciprocal Rank Fusion (RR
 ```
 
 **Benefits of Hybrid Search:**
+
 - Best of both worlds: semantic understanding + keyword matching
 - Better ranking for exact matches
 - Improved recall and precision
@@ -136,10 +142,12 @@ Combines vector similarity and full-text search using Reciprocal Rank Fusion (RR
 **POST** `/api/knowledge/embeddings/batch`
 
 Generate embeddings for all existing entries. Useful for:
+
 - Initial setup after enabling semantic search
 - Regenerating embeddings after model updates
 
 **Request:**
+
 ```json
 {
   "status": "PUBLISHED"
@@ -147,6 +155,7 @@ Generate embeddings for all existing entries. Useful for:
 ```
 
 **Response:**
+
 ```json
 {
   "message": "Generated 42 embeddings out of 45 entries",
@@ -169,6 +178,7 @@ The generation happens asynchronously to avoid blocking API responses.
 ### Content Preparation
 
 Before generating embeddings, content is prepared by:
+
 1. Combining title and content
 2. Weighting title more heavily (appears twice)
 3. This improves semantic matching on titles
@@ -206,6 +216,7 @@ RRF(d) = sum(1 / (k + rank_i))
 ```
 
 Where:
+
 - `d` = document
 - `k` = constant (60 is standard)
 - `rank_i` = rank from source i
@@ -213,6 +224,7 @@ Where:
 **Example:**
 
 Document ranks in two searches:
+
 - Vector search: rank 3
 - Keyword search: rank 1
 
@@ -225,6 +237,7 @@ Higher RRF score = better combined ranking.
 ### Index Parameters
 
 The HNSW index uses:
+
 - `m = 16`: Max connections per layer (balances accuracy/memory)
 - `ef_construction = 64`: Build quality (higher = more accurate, slower build)
 
@@ -237,6 +250,7 @@ The HNSW index uses:
 ### Cost (OpenAI API)
 
 Using `text-embedding-3-small`:
+
 - ~$0.00002 per 1000 tokens
 - Average entry (~500 tokens): $0.00001
 - 10,000 entries: ~$0.10
@@ -253,6 +267,7 @@ pnpm prisma migrate deploy
 ```
 
 This creates:
+
 - `knowledge_embeddings` table
 - Vector index on embeddings
 
@@ -312,6 +327,7 @@ curl -X POST http://localhost:3001/api/knowledge/search/hybrid \
 **Solutions:**
 
 1. Verify index exists and is being used:
+
    ```sql
    EXPLAIN ANALYZE
    SELECT * FROM knowledge_embeddings