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
142 lines
5.5 KiB
YAML
142 lines
5.5 KiB
YAML
name: Image rebuild (skip scrape)
|
|
|
|
# Fast path for code-only changes. Skips the scrape and goes straight
|
|
# to: rebuild indexes (from corpus already committed on main) + image
|
|
# build + push. Runtime ~10 min vs ~2-3 h for the full monthly refresh.
|
|
#
|
|
# Use when a PR only changes code/config — anything where the upstream
|
|
# seed catalogs haven't moved but we want the new Python in the
|
|
# running image.
|
|
|
|
on:
|
|
workflow_dispatch:
|
|
push:
|
|
branches:
|
|
- main
|
|
paths:
|
|
- "docs_mcp/**"
|
|
- "rag/**"
|
|
- "scrape/**"
|
|
- "requirements.txt"
|
|
- "Dockerfile"
|
|
- "sources.json"
|
|
|
|
# If multiple pushes land in quick succession, cancel the older one
|
|
# rather than queueing both — each run is non-trivial and the older
|
|
# commit's image just gets overwritten by the newer one anyway.
|
|
concurrency:
|
|
group: image-only
|
|
cancel-in-progress: true
|
|
|
|
env:
|
|
REGISTRY_PUSH: 192.168.0.2:1234
|
|
REGISTRY_PULL: git.jpaul.io
|
|
IMAGE: ${{ github.repository }}
|
|
# 3-GPU LAN pool, weighted toward .0.125 (4090). See refresh.yml for
|
|
# the bench numbers. .0.2:11434 excluded (not GPU-pinned). localhost
|
|
# excluded from CI (runner container has no Ollama on its loopback;
|
|
# works in dev but fails in CI with connection refused).
|
|
OLLAMA_URL: http://192.168.0.125:11434,http://192.168.0.125:11434,http://192.168.0.125:11434,http://192.168.0.125:11434,http://192.168.0.2:11436,http://192.168.0.2:11436,http://192.168.0.2:11435
|
|
EMBED_MODEL: nomic-embed-text
|
|
PRODUCT_NAME: crop_seed
|
|
|
|
jobs:
|
|
build:
|
|
runs-on: docker
|
|
container:
|
|
image: catthehacker/ubuntu:act-latest
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@v4
|
|
with:
|
|
fetch-depth: 0
|
|
|
|
- name: Verify image name resolves
|
|
# ${{ github.event.repository.name }} silently resolves to EMPTY on
|
|
# schedule events (Gitea >=1.27), which built the tag
|
|
# "192.168.0.2:1234/justin/:latest" and failed the build only AFTER
|
|
# the full scrape. IMAGE now comes from github.repository; this step
|
|
# fails in seconds if it ever goes empty again.
|
|
run: |
|
|
echo "IMAGE=${IMAGE}"
|
|
case "${IMAGE}" in
|
|
*/?*) ;;
|
|
*) echo "ERROR: IMAGE did not resolve to owner/repo"; exit 1 ;;
|
|
esac
|
|
|
|
- name: Set up Python
|
|
uses: actions/setup-python@v5
|
|
with:
|
|
python-version: "3.12"
|
|
|
|
- name: Install dependencies
|
|
run: |
|
|
python -m pip install -q --upgrade pip
|
|
python -m pip install -q -r requirements.txt
|
|
|
|
- name: Verify committed corpus is present
|
|
run: |
|
|
test -d corpus || { echo "ERROR: corpus/ missing on this ref"; exit 1; }
|
|
n_md=$(find corpus -name '*.md' | wc -l)
|
|
n_json=$(find corpus -name '*.json' | wc -l)
|
|
echo "corpus: $(du -sh corpus | cut -f1) on disk, ${n_md} .md / ${n_json} .json"
|
|
|
|
- name: Rebuild indexes from committed corpus
|
|
run: python -m rag.index --rebuild
|
|
|
|
- name: Log in to Gitea container registry
|
|
run: echo "${{ secrets.REGISTRY_TOKEN }}" | docker login "${REGISTRY_PUSH}" -u "${{ github.repository_owner }}" --password-stdin
|
|
|
|
- name: Build & push image
|
|
run: |
|
|
SHA_TAG=$(echo "$GITHUB_SHA" | cut -c1-12)
|
|
CORPUS_TAG="corpus-$(date -u +%Y.%m.%d)"
|
|
docker build \
|
|
-t "${REGISTRY_PUSH}/${IMAGE}:latest" \
|
|
-t "${REGISTRY_PUSH}/${IMAGE}:${SHA_TAG}" \
|
|
-t "${REGISTRY_PUSH}/${IMAGE}:${CORPUS_TAG}" \
|
|
.
|
|
# Smoke: the image must at least import its server module before we
|
|
# publish it. mcp 2.x renamed mcp.server.fastmcp -> mcp.server.mcpserver,
|
|
# so an unpinned dep produced a green build that crash-looped in prod
|
|
# for 9 days (2026-09-01 -> 09-10). Import is side-effect-free here
|
|
# (lazy singletons), so this needs no Ollama/Chroma.
|
|
docker run --rm --entrypoint python \
|
|
"${REGISTRY_PUSH}/${IMAGE}:latest" -c "import docs_mcp.server"
|
|
docker push "${REGISTRY_PUSH}/${IMAGE}:latest"
|
|
docker push "${REGISTRY_PUSH}/${IMAGE}:${SHA_TAG}"
|
|
docker push "${REGISTRY_PUSH}/${IMAGE}:${CORPUS_TAG}"
|
|
|
|
- name: Link container package to this repo
|
|
env:
|
|
GITEA_TOKEN: ${{ secrets.REGISTRY_TOKEN }}
|
|
run: |
|
|
OWNER="${{ github.repository_owner }}"
|
|
PKG="${GITHUB_REPOSITORY##*/}"
|
|
BODY=$(mktemp)
|
|
CODE=$(curl -sS -o "$BODY" -w "%{http_code}" -X POST \
|
|
-H "Authorization: token ${GITEA_TOKEN}" \
|
|
"https://${REGISTRY_PULL}/api/v1/packages/${OWNER}/container/${PKG}/-/link/${PKG}")
|
|
echo "link http=$CODE body=$(cat "$BODY")"
|
|
case "$CODE" in
|
|
201) echo "linked package to ${OWNER}/${PKG}" ;;
|
|
400) echo "already linked — ok" ;;
|
|
*) echo "unexpected status $CODE"; exit 1 ;;
|
|
esac
|
|
|
|
- name: Prune old container versions
|
|
# GC requires broader scope than REGISTRY_TOKEN's push perms
|
|
# (HTTP 403 on /packages/.../versions). Non-critical —
|
|
# housekeeping only. Don't fail the whole run.
|
|
# TODO: issue separate PAT with admin:package scope and set
|
|
# as PACKAGES_ADMIN_TOKEN.
|
|
continue-on-error: true
|
|
env:
|
|
GITEA_TOKEN: ${{ secrets.REGISTRY_TOKEN }}
|
|
run: |
|
|
python scripts/registry_gc.py \
|
|
--owner "${{ github.repository_owner }}" \
|
|
--package "${GITHUB_REPOSITORY##*/}" \
|
|
--keep-days 180 \
|
|
--keep-latest 6
|