fix: Docker paths, chunker word→char split, and ChatOrchestrator args

Fixed multiple issues preventing the indexer from running:
- Docker COPY paths: companion/ → src/companion/ to match project structure
- pyproject.toml: [tool.hatchling] → [tool.hatch.build.targets.wheel]
- api.py: ChatOrchestrator init params (session_memory instead of http_client)
- chunker.py: Fixed character-based chunking (was word-based, causing 400 errors from Ollama embedding API due to exceeding token limits)
- config.json: Use exact model tag mxbai-embed-large:335m
- docker-compose.yml: Fixed vault mount path

docker-compose.yml

@@ -1,4 +1,4 @@
-version: '3.8'
+version: "3.8"
 
 services:
   companion-api:
@@ -20,7 +20,13 @@ services:
       - companion-network
     restart: unless-stopped
     healthcheck:
-      test: ["CMD", "python", "-c", "import requests; requests.get('http://localhost:7373/health')"]
+      test:
+        [
+          "CMD",
+          "python",
+          "-c",
+          "import requests; requests.get('http://localhost:7373/health')",
+        ]
       interval: 30s
       timeout: 10s
       retries: 3
@@ -34,7 +40,7 @@ services:
     volumes:
       - ./config.json:/app/config.json:ro
       - companion-data:/data
-      - /home/san/KnowledgeVault:/vault:ro  # Mount Obsidian vault as read-only
+      - ./sample-data/Default:/app/sample-data/Default:ro # Mount Obsidian vault as read-only
     environment:
       - COMPANION_CONFIG=/app/config.json
       - COMPANION_DATA_DIR=/data