Phase 4-5: deployable container + corpus snapshot + CI fixes

deploy/docker-compose.yml — replace <product>/<registry> placeholders
with concrete values for Drawbar's stack:
- image: git.jpaul.io/justin/seed-mcp:latest (CF tunnel for pulls; CI
  pushes via LAN 192.168.0.2:1234 to avoid 100 MB body cap)
- container_name: seed-mcp
- port 8001:8000 (8001 host-side to not collide with crop-chem-docs
  on 8000)
- PRODUCT_NAME=crop_seed, hybrid search enabled, stateless HTTP
- llama-rerank shared with crop-chem-docs (NOT redefined here —
  expected to already be in Drawbar's parent compose network)
- networks.drawbar-mcp external: true so seed-mcp joins the existing
  cross-MCP shared network

.gitignore — corpus/ is now COMMITTED, not ignored. The monthly
refresh workflow scrapes and commits corpus changes; the image-only
workflow rebuilds indexes from the committed corpus. Allowing the
corpus to flow through git means the :corpus-YYYY.MM.DD image tag
pins to a specific seed-catalog snapshot. chroma/ and bm25/ remain
ignored — those are deterministically derived from corpus.

Initial committed snapshot: 614 varieties.
- bayer_seeds: 475 (DEKALB 288 + Asgrow 102 + WestBred 85)
- golden_harvest: 139 (Syngenta corn + soy; 36 sitemap URLs
  302-redirected = discontinued)

rag/chunk.py — normalize brand and crop to uppercase/lowercase in
Chroma metadata so cross-vendor brand-filter lookups don't break on
casing inconsistency (Bayer stores "DEKALB", Golden Harvest stores
"Golden Harvest"; _build_where uppercases user-supplied brand which
matched the former but not the latter pre-fix). Sidecar JSON keeps
original casing for display.

Stub scrapers (nk, agripro, becks_pfr, becks_products) — change
return code from 2 to 0 so the monthly-refresh CI workflow doesn't
fail on deferred sources. Real implementations will return 0 on
success / 1 on failure when they ship.

Smoke-tested cross-vendor retrieval against the 614-chunk index:
- list_versions shows both vendors with correct facet counts
- broad "corn hybrid 100 RM" query returns both DEKALB and Golden
  Harvest hits in top 5
- brand='Golden Harvest' filter returns 3 GH-only varieties
- variety-code prefilter still works (E085Z5 → top hit on GH)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-25 13:40:05 -04:00
parent 9d4a490731
commit 75f714b454
1235 changed files with 284483 additions and 94 deletions
@@ -0,0 +1,87 @@
# G08R52
- **Vendor:** Syngenta
- **Brand:** Golden Harvest
- **Crop:** Corn
- **Relative maturity:** 108
- **Source:** https://www.goldenharvestseeds.com/products/corn/g08r52
- **Tech sheet (PDF):** https://assets.syngentaebiz.com/pdf/techsheets/G08R52_260310.pdf
- **Rating scale (Golden Harvest):** 1-9 (9 = best)
---
## Positioning
Broadly Adapted Hybrid with Excellent Heat and Moisture Stress Tolerance
## Disease Ratings
| Characteristic | Value |
|---|---|
| Gray Leaf Spot | 5 |
| Northern Corn Leaf Blight | 7 |
| Goss's Wilt | 6 |
| Bacterial Corn Leaf Streak | 6 |
| Southern Corn Leaf Blight | 5 |
| Anthracnose Stalk Rot | 6 |
| Tar Spot | 6 |
| Fusarium Crown Rot | 5 |
| Common Rust | - |
| Southern Rust | 8 |
## Agronomic Characteristics
| Characteristic | Value |
|---|---|
| Emergence | 7 |
| Seeding vigor | 7 |
| Root strength | 8 |
| Stalk strength | 8 |
| Green snap | 6 |
| Stay green | 6 |
| Drydown | 6 |
| TestWeight | 6 |
| Drought | 8 |
## Recommended Management
| Characteristic | Value |
|---|---|
| Continuous corn | ✓ |
| Fungicide response | ✓ |
| High pH soils | ✓ |
| Highly productive soils | ✓ |
| Coarse-textured soils | ✓ |
| Medium-textured soils | ✓ |
| Fine-textured soils | ✓ |
## Plant/Ear Characteristics
| Characteristic | Value |
|---|---|
| Plant height | 5-Moderate |
| Ear placement | 5-Moderate |
| Ear flex | Semi-Flex |
| Cob color | Red |
| Leaf type | Upright |
| Root type | Modified |
## Maturity Info
| Characteristic | Value |
|---|---|
| Relative maturity | 108 |
| Silk RM | 106 |
| Black layer RM | 109 |
| Silk GDU | 1470 |
| Black layer GDU | 2580 |
## Seeding Rates
| Characteristic | Value |
|---|---|
| Yield Environment | Target Seeds / Ac |
| 300 bu/Ac | 38,500 |
| 260 bu/Ac | 36,500 |
| 220 bu/Ac | 34,000 |
| 190 bu/Ac | 32,000 |
| 150 bu/Ac | 30,000 |