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-sd-2025-2466663.md

@@ -0,0 +1,45 @@
+# Soybean yield trial — South Dakota, 2025
+
+- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
+- **Crop:** Soybean
+- **State:** South Dakota (SD)
+- **Year:** 2025
+- **Plot ID:** 2466663
+- **Cooperator:** Lake Area Ag
+- **Planted:** 2025-05-13
+- **Harvested:** 2025-10-07
+- **Population:** 130,000 seeds/acre
+- **Row width:** 20"
+- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/sd/2025/2466663
+
+---
+## Results (top-down by rank)
+
+| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
+|---|---|---|---|---|---|---|---|
+| 1 | Pioneer | P13Z28E | - | 70.2 | 10.8 | - | $737.10 |
+| 2 | Golden Harvest | GH0815E3 | Enlist E3 ® | 68.3 | 12.1 | - | $717.15 |
+| 3 | LG Seeds | LGS1585XF | - | 65.7 | 11.2 | - | $689.85 |
+| 4 | Golden Harvest | GH1555XF | XtendFlex ® | 65.6 | 11.3 | - | $688.80 |
+| 5 | Golden Harvest | GH1006XF | XtendFlex ® | 65.5 | 11.4 | - | $687.75 |
+| 5 | Golden Harvest | GH1762XF | XtendFlex ® | 65.5 | 11.5 | - | $687.75 |
+| 7 | Pioneer | P09Z31E | - | 64.8 | 11.2 | - | $680.40 |
+| 8 | Golden Harvest | GH1194E3 | Enlist E3 ® | 64.4 | 11.8 | - | $676.20 |
+| 9 | Pioneer | P16Z25E | - | 64.1 | 11.0 | - | $673.05 |
+| 9 | Pioneer | P14Z08E | - | 64.1 | 11.1 | - | $673.05 |
+| 11 | Jacobsen | J1685E3 | - | 63.8 | 11.5 | - | $669.90 |
+| 11 | LG Seeds | LGS1670E3 | - | 63.8 | 11.5 | - | $669.90 |
+| 13 | LG Seeds | LGS1385XF | - | 63.6 | 11.7 | - | $667.80 |
+| 14 | Golden Harvest | GH1776E3 | Enlist E3 ® | 62.4 | 11.1 | - | $655.20 |
+| 15 | Golden Harvest | GH1534E3S | Enlist E3 ® STS ® | 60.7 | 11.1 | - | $637.35 |
+| 16 | Golden Harvest | GH0936E3 | Enlist E3 ® | 60.4 | 11.6 | - | $634.20 |
+| 17 | LG Seeds | LGS0988XF | - | 60.2 | 11.9 | - | $632.10 |
+| 17 | Golden Harvest | GH1495E3 | Enlist E3 ® | 60.2 | 11.8 | - | $632.10 |
+| 17 | LG Seeds | LGS1660E3 | - | 60.2 | 11.8 | - | $632.10 |
+| 20 | Jacobsen | J0995E3 | - | 58.1 | 12.4 | - | $610.05 |
+| 21 | LG Seeds | LGS1206E3 | - | 57.6 | 11.9 | - | $604.80 |
+| 22 | LG Seeds | LGS1832E3 | - | 57.3 | 11.2 | - | $601.65 |
+| 23 | LG Seeds | LGS1043E3 | - | 56.9 | 11.7 | - | $597.45 |
+| 24 | LG Seeds | LGS1711XF | - | 55.7 | 11.0 | - | $584.85 |
+
+Top 5 by Yield: P13Z28E (Pioneer) 70.2, GH0815E3 (Golden Harvest) 68.3, LGS1585XF (LG Seeds) 65.7, GH1555XF (Golden Harvest) 65.6, GH1006XF (Golden Harvest) 65.5.