gh_plot_reports corpus (4,299 plots) + concurrency + 4-GPU pool

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) <noreply@anthropic.com>

corpus/gh_plot_reports/ghpr-silage-mi-2025-2466193.md

@@ -0,0 +1,35 @@
+# Silage yield trial — Michigan, 2025
+
+- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
+- **Crop:** Silage
+- **State:** Michigan (MI)
+- **Year:** 2025
+- **Plot ID:** 2466193
+- **Cooperator:** Grownorth Ag Llc
+- **Planted:** 2025-06-02
+- **Harvested:** 2025-09-16
+- **Population:** 34,500 seeds/acre
+- **Row width:** 20"
+- **URL:** https://www.goldenharvestseeds.com/silage/plot-report/mi/2025/2466193
+
+---
+## Results (top-down by rank)
+
+| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
+|---|---|---|---|---|---|---|---|---|
+| 1 | XL | 5413Q | - | 21.1 | 2978.0 | 18823.0 | 169.0 | 1284.0 |
+| 2 | Dairyland | Seed | HIDF-4545Q | 20.6 | 3038.0 | 18813.0 | 186.0 | 1277.0 |
+| 3 | Beck's | 6235D1 | - | 20.4 | 3261.0 | 19977.0 | 216.0 | 1310.0 |
+| 4 | XL | 5647V | - | 19.8 | 2870.0 | 17007.0 | 154.0 | 1184.0 |
+| 5 | Enogen | E108K4-DV | - | 19.7 | 3202.0 | 18917.0 | 216.0 | 1263.0 |
+| 5 | Beck's | 6258V4P | - | 19.7 | 2795.0 | 16481.0 | 120.0 | 1146.0 |
+| 7 | Beck's | 5350BR | - | 19.5 | 3226.0 | 18841.0 | 219.0 | 1254.0 |
+| 7 | Beck's | 5054D2 | - | 19.5 | 3180.0 | 18640.0 | 204.0 | 1230.0 |
+| 9 | XL | 6041Q | - | 18.5 | 3103.0 | 17196.0 | 197.0 | 1150.0 |
+| 10 | Dairyland | Seed | DS-4488V | 17.9 | 3162.0 | 16959.0 | 219.0 | 1152.0 |
+| 11 | Enogen | E112S5-D | - | 17.7 | 2757.0 | 14647.0 | 122.0 | 1016.0 |
+| 12 | Enogen | E107C1-D | - | 17.0 | 2744.0 | 14001.0 | 109.0 | 968.0 |
+| 13 | Dairyland | Seed | DS-4510Q | 16.6 | 3047.0 | 15214.0 | 198.0 | 1038.0 |
+| 14 | Enogen | E111V7-D | - | 15.5 | 2756.0 | 12799.0 | 116.0 | 889.0 |
+
+Top 5 by Ton/Acre: 5413Q (XL) 21.1, Seed (Dairyland) 20.6, 6235D1 (Beck's) 20.4, 5647V (XL) 19.8, E108K4-DV (Enogen) 19.7.