try to unify the collection process to make more seamless

.env

@@ -3,8 +3,10 @@
 QDRANT_URL=http://qdrant:6333
 # QDRANT_API_KEY= # not needed for local
 
-# Default collection used by the MCP server (auto-created if missing)
-# COLLECTION_NAME=my-collection  # Use auto-detected default from .codebase/state.json
+# Single unified collection for seamless cross-repo search
+# Default: "codebase" - all your code in one collection for unified search
+# This enables searching across multiple repos/workspaces without fragmentation
+COLLECTION_NAME=codebase
 
 # Embedding settings (FastEmbed model)
 EMBEDDING_MODEL=BAAI/bge-base-en-v1.5

.env.example

@@ -1,7 +1,9 @@
 # Qdrant connection
 QDRANT_URL=http://localhost:6333
 QDRANT_API_KEY=
-COLLECTION_NAME=my-collection
+# Single unified collection for seamless cross-repo search (default: "codebase")
+# Leave unset or use "codebase" for unified search across all your code
+COLLECTION_NAME=codebase
 
 # Embeddings
 EMBEDDING_MODEL=BAAI/bge-base-en-v1.5

.gitignore

@@ -24,3 +24,5 @@ tests/.codebase/cache.json
 tests/.codebase/state.json
 /scripts/.codebase
 /tests/.codebase
+.claude/settings.local.json
+.mcp.json

Dockerfile

@@ -0,0 +1,38 @@
+# Unified Context-Engine image for Kubernetes deployment
+# Supports multiple roles: memory, indexer, watcher, llamacpp
+FROM python:3.11-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    WORK_ROOTS="/work,/app"
+
+# Install OS dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    git \
+    ca-certificates \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies for all services
+RUN pip install --no-cache-dir --upgrade \
+    qdrant-client \
+    fastembed \
+    watchdog \
+    onnxruntime \
+    tokenizers \
+    tree_sitter \
+    tree_sitter_languages \
+    mcp \
+    fastmcp
+
+# Copy scripts for all services
+COPY scripts /app/scripts
+
+# Create directories
+WORKDIR /work
+
+# Expose all necessary ports
+EXPOSE 8000 8001 8002 8003 18000 18001 18002 18003
+
+# Default to memory server
+CMD ["python", "/app/scripts/mcp_memory_server.py"]

README.md

@@ -40,6 +40,13 @@ INDEX_MICRO_CHUNKS=1 MAX_MICRO_CHUNKS_PER_FILE=200 make reset-dev-dual
 ```
 - Default ports: Memory MCP :8000, Indexer MCP :8001, Qdrant :6333, llama.cpp :8080
 
+**🎯 Seamless Setup Note:**
+- The stack uses a **single unified `codebase` collection** by default
+- All your code goes into one collection for seamless cross-repo search
+- No per-workspace fragmentation - search across everything at once
+- Health checks auto-detect and fix cache/collection sync issues
+- Just run `make reset-dev-dual` on any machine and it works™
+
 ### Make targets: SSE, RMCP, and dual-compat
 - Legacy SSE only (default):
   - Ports: 8000 (/sse), 8001 (/sse)
@@ -96,9 +103,10 @@ INDEX_MICRO_CHUNKS=1 MAX_MICRO_CHUNKS_PER_FILE=200 make reset-dev-dual
    GLM_MODEL=glm-4.6             # Optional, defaults to glm-4.6
    ```
 
-5. **Custom collection name**:
+5. **Collection name** (unified by default):
    ```bash
-   COLLECTION_NAME=my-project    # Defaults to auto-detected repo name
+   COLLECTION_NAME=codebase      # Default: single unified collection for all code
+   # Only change this if you need isolated collections per project
    ```
 
 **After changing `.env`:**
@@ -280,7 +288,7 @@ Ports
 
 | Name | Description | Default |
 |------|-------------|---------|
-| COLLECTION_NAME | Qdrant collection name used by both servers | my-collection |
+| COLLECTION_NAME | Qdrant collection name (unified across all repos) | codebase |
 | REPO_NAME | Logical repo tag stored in payload for filtering | auto-detect from git/folder |
 | HOST_INDEX_PATH | Host path mounted at /work in containers | current repo (.) |
 | QDRANT_URL | Qdrant base URL | container: http://qdrant:6333; local: http://localhost:6333 |
@@ -763,6 +771,50 @@ Notes:
 - Named vector remains aligned with the MCP server (fast-bge-base-en-v1.5). If you change EMBEDDING_MODEL, run `make reindex` to recreate the collection.
 - For very large repos, consider running `make index` on a schedule (or pre-commit) to keep Qdrant warm without full reingestion.
 
+### Multi-repo indexing (unified search)
+
+The stack uses a **single unified `codebase` collection** by default, making multi-repo search seamless:
+
+**Index another repo into the same collection:**
+```bash
+# From your qdrant directory
+make index-here HOST_INDEX_PATH=/path/to/other/repo REPO_NAME=other-repo
+
+# Or with full control:
+HOST_INDEX_PATH=/path/to/other/repo \
+COLLECTION_NAME=codebase \
+REPO_NAME=other-repo \
+docker compose run --rm indexer --root /work
+```
+
+**What happens:**
+- Files from the other repo get indexed into the unified `codebase` collection
+- Each file is tagged with `metadata.repo = "other-repo"` for filtering
+- Search across all repos by default, or filter by specific repo
+
+**Search examples:**
+```bash
+# Search across all indexed repos
+make hybrid QUERY="authentication logic"
+
+# Filter by specific repo
+python scripts/hybrid_search.py \
+  --query "authentication logic" \
+  --repo other-repo
+
+# Filter by repo + language
+python scripts/hybrid_search.py \
+  --query "authentication logic" \
+  --repo other-repo \
+  --language python
+```
+
+**Benefits:**
+- One collection = unified search across all your code
+- No fragmentation or collection management overhead
+- Filter by repo when you need isolation
+- All repos share the same vector space for better semantic search
+
 ### Multi-query re-ranker (no new deps)
 
 - Run a fused query with several phrasings and metadata-aware boosts:
@@ -1296,6 +1348,39 @@ Client tips:
 
 ## Troubleshooting
 
+### Collection Health & Cache Sync
+
+The stack includes automatic health checks that detect and fix cache/collection sync issues:
+
+**Check collection health:**
+```bash
+python scripts/collection_health.py --workspace . --collection codebase
+```
+
+**Auto-heal cache issues:**
+```bash
+python scripts/collection_health.py --workspace . --collection codebase --auto-heal
+```
+
+**What it detects:**
+- Empty collection with cached files (cache thinks files are indexed but they're not)
+- Significant mismatch between cached files and actual collection contents
+- Missing metadata in collection points
+
+**When to use:**
+- After manually deleting collections
+- If searches return no results despite indexing
+- After Qdrant crashes or data loss
+- When switching between collection names
+
+**Automatic healing:**
+- Health checks run automatically on watcher and indexer startup
+- Cache is cleared when sync issues are detected
+- Files are reindexed on next run
+
+### General Issues
+
 - If the MCP servers can’t reach Qdrant, confirm both containers are up: `make ps`.
 - If the SSE port collides, change `FASTMCP_PORT` in `.env` and the mapped port in `docker-compose.yml`.
 - If you customize tool descriptions, restart: `make restart`.
+- If searches return no results, check collection health (see above).

deploy/kubernetes/Makefile

@@ -0,0 +1,199 @@
+# Context-Engine Kubernetes Deployment Makefile
+
+# Configuration
+NAMESPACE ?= context-engine
+IMAGE_REGISTRY ?= context-engine
+IMAGE_TAG ?= latest
+
+# Default target
+.PHONY: help
+help: ## Show this help message
+	@echo "Context-Engine Kubernetes Deployment Commands"
+	@echo ""
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-20s\033[0m %s\n", $$1, $$2}'
+
+# Prerequisites
+.PHONY: check-kubectl
+check-kubectl: ## Check if kubectl is available and cluster is accessible
+	@which kubectl > /dev/null || (echo "kubectl not found. Please install kubectl." && exit 1)
+	@kubectl cluster-info > /dev/null || (echo "Cannot connect to Kubernetes cluster." && exit 1)
+	@echo "✓ Kubernetes connection verified"
+
+# Deployment targets
+.PHONY: deploy
+deploy: check-kubectl ## Deploy all Context-Engine services
+	./deploy.sh --namespace $(NAMESPACE) --registry $(IMAGE_REGISTRY) --tag $(IMAGE_TAG)
+
+.PHONY: deploy-core
+deploy-core: check-kubectl ## Deploy only core services (Qdrant + MCP servers)
+	@echo "Deploying core services..."
+	kubectl apply -f namespace.yaml
+	kubectl apply -f configmap.yaml
+	kubectl apply -f qdrant.yaml
+	kubectl apply -f mcp-memory.yaml
+	kubectl apply -f mcp-indexer.yaml
+
+.PHONY: deploy-full
+deploy-full: check-kubectl ## Deploy all services including optional ones
+	./deploy.sh --namespace $(NAMESPACE) --registry $(IMAGE_REGISTRY) --tag $(IMAGE_TAG) --deploy-ingress
+
+.PHONY: deploy-minimal
+deploy-minimal: check-kubectl ## Deploy minimal setup (skip Llama.cpp and Ingress)
+	./deploy.sh --namespace $(NAMESPACE) --registry $(IMAGE_REGISTRY) --tag $(IMAGE_TAG) --skip-llamacpp
+
+# Kustomize targets
+.PHONY: kustomize-build
+kustomize-build: ## Build manifests with Kustomize
+	kustomize build .
+
+.PHONY: kustomize-apply
+kustomize-apply: check-kubectl ## Apply manifests with Kustomize
+	kustomize build . | kubectl apply -f -
+
+.PHONY: kustomize-delete
+kustomize-delete: check-kubectl ## Delete manifests with Kustomize
+	kustomize build . | kubectl delete -f -
+
+# Management targets
+.PHONY: status
+status: check-kubectl ## Show deployment status
+	@echo "=== Namespace Status ==="
+	kubectl get namespace $(NAMESPACE) || echo "Namespace $(NAMESPACE) not found"
+	@echo ""
+	@echo "=== Pods ==="
+	kubectl get pods -n $(NAMESPACE) -o wide || echo "No pods found"
+	@echo ""
+	@echo "=== Services ==="
+	kubectl get services -n $(NAMESPACE) || echo "No services found"
+	@echo ""
+	@echo "=== Deployments ==="
+	kubectl get deployments -n $(NAMESPACE) || echo "No deployments found"
+	@echo ""
+	@echo "=== StatefulSets ==="
+	kubectl get statefulsets -n $(NAMESPACE) || echo "No statefulsets found"
+	@echo ""
+	@echo "=== PersistentVolumeClaims ==="
+	kubectl get pvc -n $(NAMESPACE) || echo "No PVCs found"
+	@echo ""
+	@echo "=== Jobs ==="
+	kubectl get jobs -n $(NAMESPACE) || echo "No jobs found"
+
+.PHONY: logs
+logs: check-kubectl ## Show logs for all services
+	@echo "=== Qdrant Logs ==="
+	kubectl logs -f statefulset/qdrant -n $(NAMESPACE) --tail=50 || echo "Qdrant logs not available"
+
+.PHONY: logs-service
+logs-service: check-kubectl ## Show logs for specific service (usage: make logs-service SERVICE=mcp-memory)
+	@if [ -z "$(SERVICE)" ]; then echo "Usage: make logs-service SERVICE=<service-name>"; exit 1; fi
+	kubectl logs -f deployment/$(SERVICE) -n $(NAMESPACE) --tail=100 || kubectl logs -f statefulset/$(SERVICE) -n $(NAMESPACE) --tail=100 || kubectl logs -f job/$(SERVICE) -n $(NAMESPACE) --tail=100 || echo "Service $(SERVICE) not found"
+
+.PHONY: shell
+shell: check-kubectl ## Get a shell in a running pod (usage: make shell POD=mcp-memory-xxx)
+	@if [ -z "$(POD)" ]; then echo "Usage: make shell POD=<pod-name>"; echo "Available pods:"; kubectl get pods -n $(NAMESPACE); exit 1; fi
+	kubectl exec -it $(POD) -n $(NAMESPACE) -- /bin/bash || kubectl exec -it $(POD) -n $(NAMESPACE) -- /bin/sh
+
+# Cleanup targets
+.PHONY: cleanup
+cleanup: check-kubectl ## Remove all Context-Engine resources
+	./cleanup.sh --namespace $(NAMESPACE)
+
+.PHONY: clean-force
+clean-force: check-kubectl ## Force cleanup without confirmation
+	./cleanup.sh --namespace $(NAMESPACE) --force
+
+# Development targets
+.PHONY: restart
+restart: check-kubectl ## Restart all deployments
+	kubectl rollout restart deployment -n $(NAMESPACE)
+	kubectl rollout restart statefulset -n $(NAMESPACE)
+
+.PHONY: restart-service
+restart-service: check-kubectl ## Restart specific service (usage: make restart-service SERVICE=mcp-memory)
+	@if [ -z "$(SERVICE)" ]; then echo "Usage: make restart-service SERVICE=<service-name>"; exit 1; fi
+	kubectl rollout restart deployment/$(SERVICE) -n $(NAMESPACE) || kubectl rollout restart statefulset/$(SERVICE) -n $(NAMESPACE)
+
+.PHONY: scale
+scale: check-kubectl ## Scale a deployment (usage: make scale SERVICE=mcp-memory REPLICAS=3)
+	@if [ -z "$(SERVICE)" ] || [ -z "$(REPLICAS)" ]; then echo "Usage: make scale SERVICE=<service-name> REPLICAS=<number>"; exit 1; fi
+	kubectl scale deployment $(SERVICE) -n $(NAMESPACE) --replicas=$(REPLICAS)
+
+# Port forwarding targets
+.PHONY: port-forward
+port-forward: check-kubectl ## Port forward all services
+	@echo "Opening port forwards in background..."
+	@kubectl port-forward -n $(NAMESPACE) service/qdrant 6333:6333 &
+	@kubectl port-forward -n $(NAMESPACE) service/mcp-memory 8000:8000 &
+	@kubectl port-forward -n $(NAMESPACE) service/mcp-indexer 8001:8001 &
+	@echo "Port forwards started. Use 'make stop-port-forward' to stop."
+
+.PHONY: port-forward-service
+port-forward-service: check-kubectl ## Port forward specific service (usage: make port-forward-service SERVICE=qdrant LOCAL=6333 REMOTE=6333)
+	@if [ -z "$(SERVICE)" ] || [ -z "$(LOCAL)" ] || [ -z "$(REMOTE)" ]; then echo "Usage: make port-forward-service SERVICE=<service-name> LOCAL=<local-port> REMOTE=<remote-port>"; exit 1; fi
+	kubectl port-forward -n $(NAMESPACE) service/$(SERVICE) $(LOCAL):$(REMOTE)
+
+.PHONY: stop-port-forward
+stop-port-forward: ## Stop all port forwards
+	pkill -f "kubectl port-forward" || echo "No port forwards found"
+
+# Build and push targets
+.PHONY: build-image
+build-image: ## Build Docker image
+	docker build -t $(IMAGE_REGISTRY)/context-engine:$(IMAGE_TAG) ../../
+
+.PHONY: push-image
+push-image: build-image ## Push Docker image to registry
+	docker push $(IMAGE_REGISTRY)/context-engine:$(IMAGE_TAG)
+
+# Test targets
+.PHONY: test-connection
+test-connection: check-kubectl ## Test connectivity to all services
+	@echo "Testing service connectivity..."
+	@echo "Qdrant:"
+	@kubectl run qdrant-test --image=curlimages/curl --rm -i --restart=Never -n $(NAMESPACE) -- curl -f http://qdrant.$(NAMESPACE).svc.cluster.local:6333/health || echo "Qdrant test failed"
+	@echo "MCP Memory:"
+	@kubectl run memory-test --image=curlimages/curl --rm -i --restart=Never -n $(NAMESPACE) -- curl -f http://mcp-memory.$(NAMESPACE).svc.cluster.local:18000/health || echo "MCP Memory test failed"
+	@echo "MCP Indexer:"
+	@kubectl run indexer-test --image=curlimages/curl --rm -i --restart=Never -n $(NAMESPACE) -- curl -f http://mcp-indexer.$(NAMESPACE).svc.cluster.local:18001/health || echo "MCP Indexer test failed"
+
+# Configuration targets
+.PHONY: show-config
+show-config: ## Show current configuration
+	@echo "Configuration:"
+	@echo "  NAMESPACE: $(NAMESPACE)"
+	@echo "  IMAGE_REGISTRY: $(IMAGE_REGISTRY)"
+	@echo "  IMAGE_TAG: $(IMAGE_TAG)"
+	@echo ""
+	@echo "Quick start commands:"
+	@echo "  make deploy              # Deploy all services"
+	@echo "  make status              # Show deployment status"
+	@echo "  make logs-service SERVICE=mcp-memory  # Show logs"
+	@echo "  make cleanup             # Remove everything"
+
+.PHONY: show-urls
+show-urls: check-kubectl ## Show access URLs for services
+	@echo "Service URLs (via NodePort):"
+	@echo "  Qdrant:           http://<node-ip>:30333"
+	@echo "  MCP Memory (SSE): http://<node-ip>:30800"
+	@echo "  MCP Indexer (SSE): http://<node-ip>:30802"
+	@echo "  MCP Memory (HTTP): http://<node-ip>:30804"
+	@echo "  MCP Indexer (HTTP): http://<node-ip>:30806"
+	@echo "  Llama.cpp:        http://<node-ip>:30808"
+	@echo ""
+	@echo "Service URLs (via port-forward):"
+	@echo "  make port-forward # Then access via localhost ports"
+
+# Advanced targets
+.PHONY: watch-deployment
+watch-deployment: check-kubectl ## Watch deployment progress
+	watch kubectl get pods,services,deployments -n $(NAMESPACE)
+
+.PHONY: describe-service
+describe-service: check-kubectl ## Describe a service (usage: make describe-service SERVICE=mcp-memory)
+	@if [ -z "$(SERVICE)" ]; then echo "Usage: make describe-service SERVICE=<service-name>"; echo "Available services:"; kubectl get services -n $(NAMESPACE); exit 1; fi
+	kubectl describe service $(SERVICE) -n $(NAMESPACE)
+
+.PHONY: events
+events: check-kubectl ## Show recent events
+	kubectl get events -n $(NAMESPACE) --sort-by=.metadata.creationTimestamp
+