ci+deploy: target git.jpaul.io registry, PRODUCT_NAME=hvm

Phase 4/5 — adapt the template workflows to Justin's self-hosted Gitea
+ act_runner setup (see reference_gitea_server memory):

* PUSH via LAN endpoint 192.168.0.2:1234 (bypasses Cloudflare's 100 MB
  request-body cap on the Free plan); PULL via git.jpaul.io.
* buildx with config-inline insecure-registry for the LAN endpoint —
  docker/login-action can't be used there (host daemon rejects HTTP).
  Auth is written into ~/.docker/config.json so buildx reads it
  directly.
* docker/metadata-action labels org.opencontainers.image.source with
  the PUBLIC URL so Gitea auto-links the package; explicit POST to
  /api/v1/packages/.../-/link/{repo} as belt-and-suspenders (201 newly
  linked, 400 already linked, both treated as success).

* deploy/docker-compose.yml: substitute <product> placeholders, point
  image at git.jpaul.io/justin/hvm-docs:latest, set HYBRID_SEARCH=false
  to match the eval winner (bm25+rerank), keep the llama.cpp + jina
  GGUF reranker sidecar as the production target.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

deploy/docker-compose.yml

@@ -1,6 +1,6 @@
 # Hosting stack for a docs MCP server.
 #
-# Replace <product> below with your product name on first deploy.
+# Replace hvm below with your product name on first deploy.
 # Volumes: usage logs are mounted to a host path so they survive
 # Watchtower-driven container recreates.
 #
@@ -10,15 +10,15 @@
 services:
 
   # The MCP server. Watchtower auto-pulls on :latest changes.
-  <product>-docs-mcp:
-    image: <registry>/<owner>/<product>-docs-mcp:latest
-    container_name: <product>-docs-mcp
+  hvm-docs-mcp:
+    image: git.jpaul.io/justin/hvm-docs:latest
+    container_name: hvm-docs-mcp
     restart: unless-stopped
     ports:
       - "8000:8000"
     environment:
-      PRODUCT_NAME: "<product>"
-      PRODUCT_DOCS_URL: "https://docs.example.com"
+      PRODUCT_NAME: "hvm"
+      PRODUCT_DOCS_URL: "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007735en_us"
 
       # Streamable-HTTP transport. Stateless mode is required for
       # production: clients don't lose sessions when Watchtower
@@ -28,19 +28,21 @@ services:
       MCP_PORT: "8000"
 
       # If you run MetaMCP or another gateway in front and reach
-      # this container via its compose DNS name (e.g. <product>-docs-mcp:8000),
+      # this container via its compose DNS name (e.g. hvm-docs-mcp:8000),
       # add that hostname here. "*" disables the rebind check entirely.
-      MCP_ALLOWED_HOSTS: "<product>-docs-mcp,localhost,127.0.0.1"
+      MCP_ALLOWED_HOSTS: "hvm-docs-mcp,localhost,127.0.0.1"
 
       # Phase 6 — reranker sidecar (jina-reranker-v2-base via llama.cpp).
-      RERANK_URL: http://<product>-rerank:8080
+      RERANK_URL: http://hvm-rerank:8080
       RERANK_POOL: "200"
       RERANK_TIMEOUT: "30"
 
-      # Phase 8 — hybrid retrieval (BM25 + dense + RRF). Set true
-      # only after the eval harness shows the dense-only path
-      # missing technical-term queries that BM25 catches.
-      HYBRID_SEARCH: "true"
+      # Phase 8 — hybrid retrieval (BM25 + dense + RRF).
+      # Eval on the HVM corpus (eval/results/baseline.md, 2026-05-22) shows
+      # BM25-default + reranker beats hybrid on every metric (MRR 0.920 vs
+      # 0.875). Leaving HYBRID_SEARCH off so search_docs runs BM25-first +
+      # reranker; dense is the fallback when BM25 finds nothing.
+      HYBRID_SEARCH: "false"
 
       # Phase 10 — usage telemetry.
       USAGE_LOG_DIR: /app/var/logs
@@ -52,9 +54,9 @@ services:
       # DOC_BUG_API_URL: "https://docs-be.example.com/api/feedback"
     volumes:
       # Usage logs persist across container recreates.
-      - ./<product>-docs-mcp-logs:/app/var/logs
+      - ./hvm-docs-mcp-logs:/app/var/logs
     depends_on:
-      - <product>-rerank
+      - hvm-rerank
     labels:
       # Watchtower polls *only* containers with this label set true.
       com.centurylinklabs.watchtower.enable: "true"
@@ -63,9 +65,13 @@ services:
 
   # Reranker sidecar — llama.cpp serving jina-reranker-v2-base.
   # Requires GPU access; adjust runtime/devices for your hardware.
-  <product>-rerank:
+  #
+  # For dev / CPU-only hosts, swap this service for scripts/rerank_server.py
+  # (sentence-transformers ms-marco-MiniLM-L-6-v2). Same /v1/rerank shape,
+  # ~500ms/batch on CPU vs ~50ms on GPU with the jina GGUF.
+  hvm-rerank:
     image: ghcr.io/ggml-org/llama.cpp:server-cuda
-    container_name: <product>-rerank
+    container_name: hvm-rerank
     restart: unless-stopped
     # Mount the GGUF model from the host. Download from huggingface
     # (gguf-org/jina-reranker-v2-base-multilingual-GGUF) first.