Add ProHarvest Seeds: 119 varieties + 161 cross-vendor plot reports

ProHarvest Seeds (independent Corn Belt brand, proharvestseeds.com) exposes
a public, no-auth WordPress REST API — cleaner ingestion than the HTML-only
independents. Two new sources:

- `proharvest` (variety identity, 119 row-crop varieties: 70 corn / 47 soy /
  2 wheat). Enumerated via /wp/v2/seed (seed-type taxonomy), agronomics
  parsed from each /seed/<slug>/ detail page into structured
  characteristics_groups so the ratings actually embed. Mixed scale: disease
  1-9 numeric (9=best, no flip), agronomic/general qualitative, soil HR/R.

- `proharvest_plots` (trials, data_type=trial, 161 plots, 2024+2025). Per-
  cooperator harvest reports via the custom /wp-json/proharvest/v1/plots?y=
  endpoint + PDF table extraction. Many are cross-vendor head-to-head
  (ProHarvest/Apex vs Pioneer/DEKALB/Becks/Channel/Wyffels). Handles ruled
  tables, unruled tables (text fallback; soy drops the Test-Wt column → 4 vs
  5 numerics), and off-template third-party reports (sanity-gated to verbatim
  so junk rows never ship). Image-only PDFs skipped + counted.

- rag/chunk.py: route proharvest_plots through the shared cross-vendor plot
  renderer (structured) / verbatim body (raw_text fallback).
- sources.json + lessons.md (rating-scales, trial-data).
- README/CLAUDE.md corpus inventory brought current (it had drifted: bayer
  931 not 475; ebberts/lg/agrigold were unlisted). New totals: 1,645 variety
  + 6,787 trial records.

robots.txt permissive (only search + /dealer-* disallowed); no ToS
automation clause. CI rebuilds the index from the committed corpus.

docs_mcp/lessons.md

@@ -92,6 +92,16 @@ as Best/Good/Fair/Poor labels which are qualitative.)
 data is publicly available, so most disease/agronomic ratings are
 absent from Beck's records in this corpus.
 
+**ProHarvest Seeds**: **mixed scales** on one record. *Disease
+Tolerance* is `1-9 numeric, 9 = best / most tolerant` (same direction
+as Bayer — no flip; `NA` = not rated). *General Characteristics* and
+*Agronomic Features* are qualitative (`Excellent / Very Good / Good /
+Average`) with a few raw numerics (GDD pollination/black-layer, kernel
+rows). *Soil Adaptability* uses `HR` (highly recommended) / `R`
+(recommended). The single `_scale_direction` line on the record states
+all three. Ebbert's-style independent brand, but ratings ARE parsed
+into structured groups so they're retrievable.
+
 **Always check the chunk's "Rating scale" line or call
 `lookup_variety(source_key)` and look at `_scale_direction` if you
 are unsure.** Cross-vendor comparisons are valid AFTER you've
@@ -275,6 +285,16 @@ The MCP exposes TWO complementary surfaces:
   multi-location wheat performance for Northern Plains / Pacific
   Northwest / Plains regions. Variety + per-location yields
   preserved verbatim.
+- **LG Seeds + AgriGold plot reports** (AgReliant) — additional
+  cross-vendor corn/soy plots (same head-to-head structure as the
+  GH reports).
+- **ProHarvest Seeds plot reports** (corn + soy, 2024+2025) —
+  per-cooperator harvest reports from an independent Corn Belt brand.
+  Many are cross-vendor (ProHarvest / Apex vs Pioneer / DEKALB /
+  Becks / Merschman, etc.). Structured rank/yield/%H2O/test-weight
+  tables where the PDF fits ProHarvest's template; foreign-format
+  third-party reports are kept verbatim (`raw_text`) so the yields
+  are still searchable. Image-only PDFs (no text layer) are skipped.
 
 **Recommended workflow when a farmer asks about performance**: