# seed-mcp service block to MERGE into Drawbar's parent compose file
# at /home/justin/drawbar/drawbar-backend/docker-compose.yml on
# trashpanda.
#
# Pattern matches the existing chem-mcp service (crop-chem-docs):
# internal-only, no host port, MCP_PORT=8080 inside container,
# reached via docker DNS as `seed-mcp:8080` from drawbar-backend-api.
# Ollama lives on the host (host.docker.internal); the shared
# llama-rerank sidecar must be attached to drawbar-backend_default
# (see "llama-rerank patch" section below).

services:

  # seed-mcp — 760 variety identity records + 4,313 trial documents.
  # Tools land in the advisor's catalog under the `seed:` prefix via
  # the mcp_client multiplex (same pattern chem-mcp uses).
  seed-mcp:
    image: git.jpaul.io/justin/seed-mcp:latest
    environment:
      MCP_TRANSPORT: streamable-http
      MCP_HOST: 0.0.0.0
      MCP_PORT: "8080"
      # FastMCP DNS-rebinding protection — disabled because we're
      # only reachable on the internal docker network as
      # `seed-mcp:8080`; not published to the host.
      MCP_DISABLE_DNS_REBINDING_PROTECTION: "1"
      PRODUCT_NAME: crop_seed
      # Query-time embeddings via the host's Ollama on :11434
      # (nomic-embed-text). host.docker.internal is mapped below.
      OLLAMA_URL: ${SEED_OLLAMA_URL:-http://host.docker.internal:11434}
      EMBED_MODEL: ${SEED_EMBED_MODEL:-nomic-embed-text}
      # Reranker. Shared llama.cpp sidecar — see "llama-rerank patch"
      # below for the network-attach that makes this resolvable.
      RERANK_URL: ${SEED_RERANK_URL:-http://llama-rerank:8080}
      RERANK_POOL: "50"
      RERANK_TIMEOUT: "30"
      # Hybrid + rerank is the eval-validated config (100% pass, 90%
      # P@1, 0.905 MRR on 21 golden queries; see eval/results/
      # baseline.md). Without rerank, P@1 drops to 62%.
      HYBRID_SEARCH: "true"
      RRF_K: "60"
    extra_hosts:
      - "host.docker.internal:host-gateway"
    expose:
      - "8080"
    restart: unless-stopped
    labels:
      # Watchtower auto-pulls :latest on push from CI. The label is
      # required because the Drawbar stack's watchtower is set to
      # label-mode (WATCHTOWER_LABEL_ENABLE=true).
      com.centurylinklabs.watchtower.enable: "true"


# ─── llama-rerank patch ──────────────────────────────────────────────
#
# As of 2026-05-25, the llama-rerank container is on the default
# Docker `bridge` network — NOT on `drawbar-backend_default` where
# chem-mcp and seed-mcp live. The chem-mcp container's
# RERANK_URL=http://llama-rerank:8080 has been silently failing to
# resolve (returns 167.100.x via public DNS, connection refused),
# falling back to dense-only retrieval. To fix this and unlock
# rerank for BOTH chem-mcp and seed-mcp:
#
#     docker network connect drawbar-backend_default llama-rerank
#
# This is idempotent and survives container restarts as long as the
# llama-rerank container is recreated by Watchtower; if Watchtower
# replaces it, re-run the connect command (or — better — bring
# llama-rerank into the compose stack so the network attachment is
# declarative).
#
# Alternatively, declare llama-rerank as a compose service in this
# parent stack:
#
#     llama-rerank:
#       image: ghcr.io/ggml-org/llama.cpp:server-cuda
#       container_name: llama-rerank
#       restart: unless-stopped
#       volumes:
#         - llama-rerank-cache:/root/.cache/huggingface
#       command: >
#         -hf gpustack/jina-reranker-v2-base-multilingual-GGUF:Q8_0
#         --reranking
#         --host 0.0.0.0 --port 8080
#         --n-gpu-layers 99 --ctx-size 8192
#         --batch-size 4096 --ubatch-size 4096 --parallel 4
#       deploy:
#         resources:
#           reservations:
#             devices:
#               - driver: nvidia
#                 count: 1
#                 capabilities: [gpu]
#       labels:
#         com.centurylinklabs.watchtower.enable: "false"
#       expose:
#         - "8080"
#
# (Watchtower disabled on llama-rerank to avoid surprise model-reload
# downtime; pin the image tag if you want predictability.)
#
# Note: --ubatch-size 4096 is required for the seed-mcp corpus —
# default 512 is too small for the ~600-token trial chunks and
# rejects the whole batch with "input too large to process".

# ─── drawbar-backend-api wiring ──────────────────────────────────────
#
# Add to the drawbar-backend-api `environment:` block so it can call
# seed-mcp alongside chem-mcp:
#
#     SEED_MCP_BASE_URL: ${SEED_MCP_BASE_URL:-http://seed-mcp:8080/mcp}
#
# The advisor's tool multiplex (mcp_client) picks this up and exposes
# the seed-mcp tools under the `seed:` prefix.