Files
seed-mcp/.gitea/workflows/refresh.yml
T
justin 84b49d8360 trial data: workflow scrape steps + lessons.md trial-data guide
.gitea/workflows/refresh.yml — add scrape steps for the new trial
sources (agripro_trials, gh_plot_reports) so the monthly cron
refreshes them alongside the variety sources. gh_plot_reports
is the heaviest single source (~4,600 docs @ 1 req/sec ≈ 70 min);
runs late so an earlier failure doesn't waste time before failing.
Commit-message variable count expanded to surface the trial counts.

docs_mcp/lessons.md — new "trial-data" section telling the agent:

- The two surfaces (search_docs = identity, search_trials = perf)
  are complementary; how to route a farmer question to each.
- What's indexed (GH plot reports cross-vendor, AgriPro regional
  PDFs) vs what's not (Bayer per-variety trials, NK yield results,
  Pioneer, university extension trials).
- Recommended workflow: search_trials → identify top performers →
  lookup_variety on each to verify identity → don't fabricate.
- How to read a GH plot report (per-column headers vary by crop:
  corn/soy use Yield/MST/Test Weight, silage uses Ton/Acre +
  Milk + Beef columns).
- Single-data-point caveat: one plot is one cooperator's field;
  look across multiple plots for a robust recommendation.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 15:22:08 -04:00

200 lines
8.6 KiB
YAML

name: Monthly seed catalog refresh
# Runs the full pipeline: scrape all GREEN sources → rebuild indexes
# → push image. Cron'd once a month (1st @ 06:00 UTC). Skip the
# reindex + image-push if the scrape produced no diff against the
# committed corpus.
#
# Seed catalogs move slowly (vendors release new hybrids 1-2x/year
# at field-day timing); monthly cadence is plenty.
#
# Total runtime budget: ~2-3 h end-to-end across all 5 GREEN sources.
# Bayer is the longest (~475 varieties, ~45 min). Beck's PFR is the
# heaviest single-source (~2,089 docs via Sanity GROQ pagination).
on:
schedule:
- cron: "0 6 1 * *" # 1st of each month, 06:00 UTC
workflow_dispatch:
inputs:
force_build:
description: "Rebuild indexes + push image even if corpus is unchanged"
type: boolean
default: false
sources:
description: "Sources to scrape (comma-separated, blank = all GREEN)"
type: string
default: ""
env:
# Self-hosted Gitea registry on the same LAN as the runner.
# CF caps push body at 100 MB, so push via LAN endpoint; pull
# through the public hostname (response bodies aren't capped).
REGISTRY_PUSH: 192.168.0.2:1234
REGISTRY_PULL: git.jpaul.io
IMAGE: ${{ github.repository_owner }}/${{ github.event.repository.name }}
# Embedder pool. Two Ollama instances on the Gitea/runner host
# (one per GPU) + the Windows Ollama. Trashpanda's Ollama is
# production-shared with Drawbar; CI does NOT hit it.
OLLAMA_URL: http://192.168.0.2:11434,http://192.168.0.2:11435,http://192.168.0.125:11434
EMBED_MODEL: nomic-embed-text
PRODUCT_NAME: crop_seed
jobs:
refresh:
runs-on: docker
container:
image: catthehacker/ubuntu:act-latest
steps:
- name: Checkout
uses: actions/checkout@v4
with:
# Full history — required for the digest-history step
# to walk git log. Default fetch-depth: 1 silently
# produces a 0-byte history file.
fetch-depth: 0
- 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
# ---- Phase 1: scrape ---------------------------------------
- name: Scrape Bayer seeds (DEKALB + Asgrow + WestBred)
if: ${{ inputs.sources == '' || contains(inputs.sources, 'bayer_seeds') }}
run: python -m scrape.runner --source bayer_seeds --force
- name: Scrape Golden Harvest
if: ${{ inputs.sources == '' || contains(inputs.sources, 'golden_harvest') }}
run: python -m scrape.runner --source golden_harvest --force
- name: Scrape NK
if: ${{ inputs.sources == '' || contains(inputs.sources, 'nk') }}
run: python -m scrape.runner --source nk --force
- name: Scrape AgriPro
if: ${{ inputs.sources == '' || contains(inputs.sources, 'agripro') }}
run: python -m scrape.runner --source agripro --force
- name: Scrape AgriPro regional trial PDFs
if: ${{ inputs.sources == '' || contains(inputs.sources, 'agripro_trials') }}
run: python -m scrape.runner --source agripro_trials --force
- name: Scrape Golden Harvest plot reports (cross-vendor yield trials)
if: ${{ inputs.sources == '' || contains(inputs.sources, 'gh_plot_reports') }}
# Heaviest single source — ~4,600 docs at 1 req/sec ≈ 70 min.
# Wraps the bulk of CI time; runs late so an earlier failure
# doesn't waste 70 min before failing.
run: python -m scrape.runner --source gh_plot_reports --force
- name: Scrape Beck's PFR research corpus
if: ${{ inputs.sources == '' || contains(inputs.sources, 'becks_pfr') }}
# Deferred (returns 0 cleanly from a stub) — implementation
# pending. Public Sanity GROQ at mc8v24rf.api.sanity.io.
run: python -m scrape.runner --source becks_pfr --force
# ---- Commit corpus changes + retry-on-race -----------------
- name: Commit corpus changes (if any)
id: commit
run: |
git config user.name "seed-mcp-refresh"
git config user.email "actions@jpaul.io"
git add sources.json corpus
if git diff --cached --quiet; then
echo "no corpus changes — skipping reindex and image build"
echo "changed=false" >> "$GITHUB_OUTPUT"
exit 0
fi
echo "changed=true" >> "$GITHUB_OUTPUT"
ts=$(date -u +"%Y-%m-%dT%H:%MZ")
n_bayer=$(find corpus/bayer_seeds -name '*.json' 2>/dev/null | wc -l)
n_gh=$(find corpus/golden_harvest -name '*.json' 2>/dev/null | wc -l)
n_nk=$(find corpus/nk -name '*.json' 2>/dev/null | wc -l)
n_ag=$(find corpus/agripro -name '*.json' 2>/dev/null | wc -l)
n_agt=$(find corpus/agripro_trials -name '*.json' 2>/dev/null | wc -l)
n_ghpr=$(find corpus/gh_plot_reports -name '*.json' 2>/dev/null | wc -l)
n_pfr=$(find corpus/becks_pfr -name '*.json' 2>/dev/null | wc -l)
git commit -m "monthly refresh: ${ts} — bayer=${n_bayer} gh=${n_gh} nk=${n_nk} agripro=${n_ag} ag_trials=${n_agt} gh_plot_reports=${n_ghpr} pfr=${n_pfr}"
attempt=1
while [ $attempt -le 3 ]; do
if git push; then
echo "pushed corpus changes (attempt $attempt)"
break
fi
if [ $attempt -eq 3 ]; then
echo "push still failing after 3 attempts"; exit 1
fi
git fetch origin main
git rebase origin/main || { echo "rebase conflict"; exit 1; }
attempt=$((attempt + 1))
done
# ---- Rebuild Chroma + BM25 ---------------------------------
- name: Rebuild indexes
if: steps.commit.outputs.changed == 'true' || inputs.force_build == true
run: python -m rag.index --rebuild
# ---- Build & push image ------------------------------------
- name: Log in to Gitea container registry
if: steps.commit.outputs.changed == 'true' || inputs.force_build == true
run: echo "${{ secrets.REGISTRY_TOKEN }}" | docker login "${REGISTRY_PUSH}" -u "${{ github.repository_owner }}" --password-stdin
- name: Build & push image
if: steps.commit.outputs.changed == 'true' || inputs.force_build == true
# Tags: :latest (Watchtower target), :<sha12> (rollback pin),
# :corpus-<YYYY.MM.DD> (links image to corpus version so
# Drawbar can pin to a specific seed-catalog snapshot).
run: |
SHA_TAG=$(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}" \
.
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
if: steps.commit.outputs.changed == 'true' || inputs.force_build == true
env:
GITEA_TOKEN: ${{ secrets.REGISTRY_TOKEN }}
run: |
OWNER="${{ github.repository_owner }}"
PKG="${{ github.event.repository.name }}"
BODY=$(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. TODO: issue separate PAT with admin:package
# scope. Until then continue-on-error keeps a failed prune
# from breaking the whole refresh.
if: steps.commit.outputs.changed == 'true' || inputs.force_build == true
continue-on-error: true
env:
GITEA_TOKEN: ${{ secrets.REGISTRY_TOKEN }}
run: |
python scripts/registry_gc.py \
--owner "${{ github.repository_owner }}" \
--package "${{ github.event.repository.name }}" \
--keep-days 180 \
--keep-latest 6