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

Dockerfile

@@ -28,10 +28,10 @@ COPY --from=builder /app/wheels /wheels
 RUN pip install --no-cache-dir /wheels/*
 
 # Copy application code
-COPY companion/ ./companion/
-COPY companion/forge/ ./companion/forge/
-COPY companion/indexer_daemon/ ./companion/indexer_daemon/
-COPY companion/rag/ ./companion/rag/
+COPY src/companion/ ./companion/
+COPY src/companion/forge/ ./companion/forge/
+COPY src/companion/indexer_daemon/ ./companion/indexer_daemon/
+COPY src/companion/rag/ ./companion/rag/
 
 # Create directories for data
 RUN mkdir -p /data/vectors /data/memory /models