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-2024-2452449.md

@@ -0,0 +1,40 @@
+# Soybean yield trial — Michigan, 2024
+
+- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
+- **Crop:** Soybean
+- **State:** Michigan (MI)
+- **Year:** 2024
+- **Plot ID:** 2452449
+- **Cooperator:** Michigan State University - Ingham Cnty Late
+- **Planted:** 2024-05-20
+- **Harvested:** 2024-10-24
+- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/mi/2024/2452449
+
+---
+## Results (top-down by rank)
+
+| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
+|---|---|---|---|---|---|---|---|
+| 1 | NK | NK26-M6E3 | Enlist E3 ® | 72.6 | - | - | $762.30 |
+| 2 | M | & | W Seeds 31E33 | 70.0 | - | - | $735.00 |
+| 3 | Golden Harvest | GH2922E3 | Enlist E3 ® | 69.9 | - | - | $733.95 |
+| 4 | Xitavo | XO | 2832E | 69.8 | - | - | $732.90 |
+| 5 | Wyckoff | Hybrids | W2895E3 | 68.6 | - | - | $720.30 |
+| 6 | Xitavo | XO | 2985E | 68.1 | - | - | $715.05 |
+| 7 | Xitavo | XO | 2865E | 67.9 | - | - | $712.95 |
+| 8 | Wyckoff | Hybrids | W2790E3 | 67.8 | - | - | $711.90 |
+| 9 | M | & | W Seeds 29E65 | 67.7 | - | - | $710.85 |
+| 10 | NK | NK30-A9E3 | Enlist E3 ® | 67.3 | - | - | $706.65 |
+| 11 | Golden Harvest | GH3035E3 | Enlist E3 ® | 66.9 | - | - | $702.45 |
+| 12 | Wyckoff | Hybrids | W2980E3 | 66.4 | - | - | $697.20 |
+| 13 | Golden Harvest | GH2925XF | XtendFlex ® | 65.9 | - | - | $691.95 |
+| 13 | Xitavo | XO | 3014E | 65.9 | - | - | $691.95 |
+| 15 | Wyckoff | Hybrids | W3190E3 | 65.3 | - | - | $685.65 |
+| 16 | Golden Harvest | GH2814E3S | Enlist E3 ® STS ® | 64.1 | - | - | $673.05 |
+| 17 | MCIA | MCIA | 2820 LL/GT | 63.1 | - | - | $662.55 |
+| 18 | Wyckoff | Hybrids | W3085E3 | 60.2 | - | - | $632.10 |
+| 18 | Xitavo | XO | 3224E | 60.2 | - | - | $632.10 |
+| 20 | Xitavo | XO | 3105E | 55.7 | - | - | $584.85 |
+| 21 | Michigan | State | E21326GTHO | 53.5 | - | - | $561.75 |
+
+Top 5 by Yield: NK26-M6E3 (NK) 72.6, & (M) 70.0, GH2922E3 (Golden Harvest) 69.9, XO (Xitavo) 69.8, Hybrids (Wyckoff) 68.6.