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-ne-2025-2466554.md

@@ -0,0 +1,54 @@
+# Soybean yield trial — Nebraska, 2025
+
+- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
+- **Crop:** Soybean
+- **State:** Nebraska (NE)
+- **Year:** 2025
+- **Plot ID:** 2466554
+- **Cooperator:** Pete C Schmit & Sons LTD
+- **Planted:** 2025-05-05
+- **Harvested:** 2025-10-05
+- **Population:** 155,000 seeds/acre
+- **Row width:** 30"
+- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/ne/2025/2466554
+
+---
+## Results (top-down by rank)
+
+| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
+|---|---|---|---|---|---|---|---|
+| 1 | LG Seeds | LGS2685XF | - | 96.0 | 7.8 | - | $1008.00 |
+| 2 | Golden Harvest | GH2626XF | XtendFlex ® | 91.8 | 8.6 | - | $963.90 |
+| 3 | LG Seeds | LGS2334XF | - | 90.7 | 7.6 | - | $952.35 |
+| 4 | LG Seeds | LGS3077XF | - | 90.2 | 7.8 | - | $947.10 |
+| 5 | LG Seeds | Experimental | - | 89.5 | 7.5 | - | $939.75 |
+| 6 | LG Seeds | LGS3320XF | - | 87.4 | 8.8 | - | $917.70 |
+| 7 | LG Seeds | LGS2364XF | - | 87.0 | 7.3 | - | $913.50 |
+| 8 | LG Seeds | LGS2054XF | - | 86.7 | 7.6 | - | $910.35 |
+| 9 | Rob-See-Co | RS2425XF | - | 86.1 | 7.6 | - | $904.05 |
+| 9 | Innotech | IS2625E3 | - | 86.1 | 7.9 | - | $904.05 |
+| 11 | LG Seeds | LGS3000E3 | - | 85.6 | 8.1 | - | $898.80 |
+| 12 | Innotech | IS2330E3 | - | 85.5 | 7.5 | - | $897.75 |
+| 13 | Golden Harvest | GH2406XF | XtendFlex ® | 85.4 | 8.0 | - | $896.70 |
+| 13 | LG Seeds | LGS2850XF | - | 85.4 | 8.0 | - | $896.70 |
+| 15 | Golden Harvest | GH3023XF | XtendFlex ® | 85.2 | 9.2 | - | $894.60 |
+| 16 | LG Seeds | LGS2881E3 | - | 84.2 | 8.9 | - | $884.10 |
+| 17 | Rob-See-Co | RS2135XF | - | 84.0 | 7.5 | - | $882.00 |
+| 18 | Innotech | IS3396E3 | - | 83.9 | 8.9 | - | $880.95 |
+| 19 | Rob-See-Co | RS3437XFS | - | 83.3 | 10.6 | - | $874.65 |
+| 20 | Innotech | IS2566E3S | - | 80.7 | 7.7 | - | $847.35 |
+| 21 | Innotech | IS3188E3S | Enlist E3 ® STS ® | 80.6 | 8.2 | - | $846.30 |
+| 22 | LG Seeds | Experimental | - | 80.1 | 8.1 | - | $841.05 |
+| 22 | Innotech | IS2904E3S | - | 80.1 | 8.1 | - | $841.05 |
+| 24 | LG Seeds | LGS3105XF | - | 79.5 | 8.0 | - | $834.75 |
+| 25 | Innotech | IS2711E3 | - | 79.1 | 7.8 | - | $830.55 |
+| 26 | Rob-See-Co | RS2804XF | - | 79.0 | 8.6 | - | $829.50 |
+| 27 | LG Seeds | LGS2505E3 | - | 77.2 | 8.2 | - | $810.60 |
+| 28 | LG Seeds | LGS2505E3 | - | 77.1 | 8.0 | - | $809.55 |
+| 29 | Rob-See-Co | RS3109XF | - | 75.8 | 8.4 | - | $795.90 |
+| 30 | LG Seeds | LGS3240E3 | - | 74.7 | 8.3 | - | $784.35 |
+| 31 | LG Seeds | LGS2408E3 | - | 73.1 | 8.0 | - | $767.55 |
+| 32 | LG Seeds | LGS2270E3 | - | 72.2 | 7.9 | - | $758.10 |
+| 33 | Golden Harvest | GH3035E3 | Enlist E3 ® | 67.0 | 8.3 | - | $703.50 |
+
+Top 5 by Yield: LGS2685XF (LG Seeds) 96.0, GH2626XF (Golden Harvest) 91.8, LGS2334XF (LG Seeds) 90.7, LGS3077XF (LG Seeds) 90.2, Experimental (LG Seeds) 89.5.