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-ms-2025-2485261.md

@@ -0,0 +1,34 @@
+# Soybean yield trial — Mississippi, 2025
+
+- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
+- **Crop:** Soybean
+- **State:** Mississippi (MS)
+- **Year:** 2025
+- **Plot ID:** 2485261
+- **Cooperator:** Mississippi State University
+- **Planted:** 2025-06-05
+- **Harvested:** 2025-10-14
+- **Population:** 128,000 seeds/acre
+- **Row width:** 30"
+- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/ms/2025/2485261
+
+---
+## Results (top-down by rank)
+
+| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
+|---|---|---|---|---|---|---|---|
+| 1 | NK | NK47-U1XFS | XtendFlex ® STS ® | 28.5 | 11.1 | - | $299.25 |
+| 2 | Innvictis | Seed | Solutions A4862XF | 26.1 | 10.8 | - | $274.05 |
+| 2 | Delta | Grow | DG48XF70STS | 26.1 | 10.9 | - | $274.05 |
+| 4 | Asgrow | AG48XF5 | - | 25.9 | 11.7 | - | $271.95 |
+| 5 | Asgrow | AG43XF5 | - | 25.5 | 11.0 | - | $267.75 |
+| 6 | Great | Heart | Seed GT-4632XFS | 25.0 | 10.5 | - | $262.50 |
+| 6 | Asgrow | AG49XF4 | - | 25.0 | 12.5 | - | $262.50 |
+| 8 | Revere | Seed | Revere 46-F17 | 23.6 | 11.3 | - | $247.80 |
+| 9 | Great | Heart | Seed GT-4867XF | 22.6 | 10.2 | - | $237.30 |
+| 10 | Progeny | P | 4623XF | 22.4 | 10.9 | - | $235.20 |
+| 11 | Asgrow | AG45XF3 | - | 19.5 | 10.4 | - | $204.75 |
+| 12 | Revere | Seed | Revere 47-F77 | 19.3 | 11.4 | - | $202.65 |
+| 13 | Progeny | P | 4848XF | 18.8 | 11.0 | - | $197.40 |
+
+Top 5 by Yield: NK47-U1XFS (NK) 28.5, Seed (Innvictis) 26.1, Grow (Delta) 26.1, AG48XF5 (Asgrow) 25.9, AG43XF5 (Asgrow) 25.5.