requirements.txt asked for `mcp[fastmcp]>=1.0.0` with no upper bound.
mcp 2.0.0 (2026-07-28) removed `mcp.server.fastmcp` — renamed FastMCP to
MCPServer under mcp.server.mcpserver — and dropped the [fastmcp] extra.
docs_mcp/server.py:28 still imports the 1.x path.
The 2026-07-01 image predated 2.0.0, so it resolved to 1.x and ran fine.
The 2026-09-01 rebuild resolved to mcp 2.1.1, and the container has been
crash-looping ever since:
File "/app/docs_mcp/server.py", line 28, in <module>
from mcp.server.fastmcp import FastMCP
ModuleNotFoundError: No module named 'mcp.server.fastmcp'
That is nine days of seed-mcp being down for Drawbar's advisor. Same
failure took zerto-docs down on 2026-08-11; crop-chem-docs and
opsramp-docs were pinned then, seed-mcp was missed.
This is a ceiling to restore service, not the destination — the 2.x port
lands separately. It also adds the guard that would have caught this: the
build now runs `python -c "import docs_mcp.server"` inside the freshly
built image and refuses to push if that fails. Import is side-effect-free
(lazy singletons), so the check needs no Ollama or Chroma.
Still unpinned and due to break on their next rebuild: morpheus-docs,
hvm-docs.
Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01FnVuG79cYPcRLTp4pC8ujR
CI was failing on the "Rebuild indexes from committed corpus" step
with httpx.ConnectError [Errno 111] — `localhost:11434` in the
OLLAMA_URL pool resolves to the Gitea Actions runner CONTAINER's
own localhost (no Ollama there), not the host. Fix: drop localhost
from CI's pool; it stays useful for dev runs from the workstation
where the TITAN X serves Ollama on the host loopback.
Final CI pool — 3 LAN endpoints, weighted to .0.125 (4090):
.0.125:11434 ×4 (RTX 40-series, 242 embeds/sec)
.0.2:11436 ×2 (GPU-pinned, 108 embeds/sec)
.0.2:11435 ×1 (GPU-pinned, 72 embeds/sec)
deploy/docker-compose.yml — rewrite to match Drawbar's actual
parent-stack pattern, learned by inspecting how chem-mcp is
deployed on trashpanda:
- Service name `seed-mcp` (matches chem-mcp's pattern). Reached
via docker DNS as `seed-mcp:8080` from drawbar-backend-api.
- Internal-only (no host port), expose 8080 only.
- MCP_PORT=8080 inside container (chem-mcp uses 8080 too).
- OLLAMA_URL via host.docker.internal:11434 (trashpanda's Ollama
runs on the host). extra_hosts maps host-gateway.
- RERANK_URL: http://llama-rerank:8080 — but llama-rerank is on
the default `bridge` network, not drawbar-backend_default,
so chem-mcp's reranker silently fails! Documented patch:
docker network connect drawbar-backend_default llama-rerank
Fixes rerank for BOTH chem-mcp (today: dense-only fallback)
and the new seed-mcp.
- Watchtower label set so CI pushes to :latest auto-deploy.
Documented llama-rerank service block as an alternative for
bringing the sidecar fully into the parent compose stack, with the
ubatch-size flag the seed corpus needs.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
CORPUS — 4,299 GH plot reports added (3,797 written + 502 from the
earlier slow run + 319 sitemap-listed URLs that 404'd as
discontinued). Combined with prior 760 varieties + 14 AgriPro
trials = 5,073 total chunks now indexed.
scrape/sources/gh_plot_reports.py — concurrency speedup:
- 4 worker threads (ThreadPoolExecutor), each with its own
requests.Session for connection-pool efficiency.
- Shared class-level rate limiter (0.25 sec between ANY two
requests across all threads). Net throughput ~4 req/sec —
well below any rate-limit threshold a public site enforces.
- Diagnosis vs original 1 req/sec: GH had ZERO rate limiting,
zero 429s, zero retries. The 1 sec self-throttle was just too
conservative. Bench:
1 worker / 1.0 sec throttle: ~0.4 plots/sec (190 min ETA)
4 workers / 0.25 sec throttle: ~3 plots/sec (~25 min actual)
rag/chunk.py — chunk size cap for nomic-embed-text's 2048-token
context window:
- Empirically tested: failure threshold is ~5,250 chars on
numeric-heavy trial chunks (chars/token ratio 2.4 vs 3.5 for
prose). Cap at 4,500 chars to be safely under at worst-case
2.2 chars/token.
- Applied to BOTH variety and trial chunks. Marked truncated
chunks with metadata.embed_truncated = True; FULL text stays
in the on-disk .md for get_page to return verbatim.
.gitea/workflows/{refresh,image-only}.yml — OLLAMA_URL pool
restructured for the 4 GPU-pinned endpoints. Bench (50-chunk
batches on nomic-embed-text):
.0.125:11434 (RTX 40-series) 242 embeds/sec ← weight ×4
.0.2:11436 (GPU-pinned) 108 embeds/sec ← weight ×2
.0.2:11435 (GPU-pinned) 72 embeds/sec ← weight ×1
localhost (TITAN X) 37 embeds/sec ← weight ×1
Weighting is done by listing the URL multiple times in
OLLAMA_URL since the embedder uses round-robin. .0.2:11434 is
explicitly EXCLUDED — it isn't pinned to a specific GPU.
Combined index rebuild for 5,073 chunks now finishes in ~3 min
(was 19+ on the single-endpoint pool).
Smoke tests:
✓ list_versions: 5,073 docs across 6 sources, 2 vendors, 6
brands, 4 crops (corn 2711, soy 2016, silage 223, wheat 123).
✓ search_trials({crop=corn, state=IA, year=2024}): 3 IA 2024
corn trials surfaced.
✓ search_trials("Phytophthora resistance soybean trial"): NK
NK43-W1XFS top-1 in LA 2024 trial (cross-vendor result).
✓ search_trials("AP Iliad Idaho wheat"): AgriPro Washington/N
Idaho 2025 trial surfaced.
✓ search_trials(product=DKC65-95): 3 corn trials containing
that hybrid in IL/IA 2024.
✓ search_trials(product=NK1701): 3 corn trials in AR/MS 2024.
✓ Product filter correctly returns EMPTY for products that
aren't in the corpus (DKC65-20 is a 2023 product; 2023 plots
deferred). Anti-hallucination contract preserved.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
claudeandClaude Opus 5
justinandClaude Opus 4.7