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-soybeans-mi-2024-2419734.md

@@ -0,0 +1,42 @@
+# Soybean yield trial — Michigan, 2024
+
+- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
+- **Crop:** Soybean
+- **State:** Michigan (MI)
+- **Year:** 2024
+- **Plot ID:** 2419734
+- **Cooperator:** Helena Agri-Enterprises Llc
+- **Planted:** 2024-05-08
+- **Harvested:** 2024-10-03
+- **Population:** 138,000 seeds/acre
+- **Row width:** 30"
+- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/mi/2024/2419734
+
+---
+## Results (top-down by rank)
+
+| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
+|---|---|---|---|---|---|---|---|
+| 1 | NK | NK21-C2E3 | Enlist E3 ® | 74.6 | 11.9 | - | $783.30 |
+| 2 | Xitavo | XO | 1632E | 66.9 | 12.7 | - | $702.45 |
+| 3 | Brevant | B214EE | - | 65.3 | 12.1 | - | $685.65 |
+| 4 | Brevant | B164EE | - | 63.1 | 12.2 | - | $662.55 |
+| 5 | Alloy | A22E33 | - | 59.9 | 12.4 | - | $628.95 |
+| 6 | Brevant | B173EE | - | 59.1 | 12.9 | - | $620.55 |
+| 7 | Alloy | A21E34 | - | 58.7 | 12.6 | - | $616.35 |
+| 8 | Alloy | A24E34 | - | 58.3 | 12.0 | - | $612.15 |
+| 9 | NK | NK23-P1E3 | Enlist E3 ® | 58.1 | 12.4 | - | $610.05 |
+| 10 | Xitavo | XO | 2181E | 56.2 | 12.2 | - | $590.10 |
+| 11 | NK | NK16-Z6E3 | Enlist E3 ® | 55.7 | 12.7 | - | $584.85 |
+| 12 | NK | NK19-T8E3S | Enlist E3 ® STS ® | 55.5 | 12.3 | - | $582.75 |
+| 13 | Brevant | B244EE | - | 53.6 | 12.3 | - | $562.80 |
+| 14 | Brevant | B194EE | - | 53.2 | 12.5 | - | $558.60 |
+| 15 | Xitavo | XO | 1761E | 51.7 | 12.4 | - | $542.85 |
+| 16 | Brevant | B224EE | - | 49.4 | 12.1 | - | $518.70 |
+| 17 | Brevant | B202EE | - | 47.5 | 12.5 | - | $498.75 |
+| 18 | NK | NK18-R4E3 | Enlist E3 ® | 46.9 | 13.0 | - | $492.45 |
+| 19 | Xitavo | XO | 2305E | 43.2 | 12.1 | - | $453.60 |
+| 20 | Xitavo | XO | 1971E | 42.6 | 12.5 | - | $447.30 |
+| 21 | Alloy | A19E33 | - | 37.8 | 12.5 | - | $396.90 |
+
+Top 5 by Yield: NK21-C2E3 (NK) 74.6, XO (Xitavo) 66.9, B214EE (Brevant) 65.3, B164EE (Brevant) 63.1, A22E33 (Alloy) 59.9.