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-al-2024-2465723.md

@@ -0,0 +1,39 @@
+# Soybean yield trial — Alabama, 2024
+
+- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
+- **Crop:** Soybean
+- **State:** Alabama (AL)
+- **Year:** 2024
+- **Plot ID:** 2465723
+- **Cooperator:** Auburn University - Belle Mina MG V
+- **Planted:** 2024-05-21
+- **Harvested:** 2024-10-23
+- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/al/2024/2465723
+
+---
+## Results (top-down by rank)
+
+| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
+|---|---|---|---|---|---|---|---|
+| 1 | Integra | Fortified | Seed XF5834S | 49.0 | - | - | $514.50 |
+| 1 | UniSouth | Genetics | USG 7543XF | 49.0 | - | - | $514.50 |
+| 1 | Innvictis | Seed | Solutions A5813XF | 49.0 | - | - | $514.50 |
+| 4 | Innvictis | Seed | Solutions A5503XF | 48.0 | - | - | $504.00 |
+| 5 | NK | NK54-J9XFS | XtendFlex ® STS ® | 47.0 | - | - | $493.50 |
+| 6 | Progeny | P | 5751XF | 43.0 | - | - | $451.50 |
+| 7 | Asgrow | AG55XF5 | - | 42.0 | - | - | $441.00 |
+| 8 | Asgrow | AG54XF5 | - | 41.0 | - | - | $430.50 |
+| 9 | Innvictis | Seed | Solutions A5284XF | 39.0 | - | - | $409.50 |
+| 10 | Innvictis | Seed | Solutions A5994XF | 38.0 | - | - | $399.00 |
+| 10 | Armor | Seed | Armor 50-F96 | 38.0 | - | - | $399.00 |
+| 12 | NK | NK52-V1XF | XtendFlex ® | 36.0 | - | - | $378.00 |
+| 12 | Mixon | Seed | AGS V5422 | 36.0 | - | - | $378.00 |
+| 12 | Public | Hutchenson | - | 36.0 | - | - | $378.00 |
+| 12 | Innvictis | Seed | Solutions A5124XF | 36.0 | - | - | $378.00 |
+| 12 | Armor | Seed | Armor 54-F34 | 36.0 | - | - | $378.00 |
+| 17 | Progeny | P | 5056XFS | 35.0 | - | - | $367.50 |
+| 18 | DonMario | Seeds | DM59E01S | 34.0 | - | - | $357.00 |
+| 19 | Asgrow | AG50XF5 | - | 32.0 | - | - | $336.00 |
+| 20 | UniSouth | Genetics | USG 7534GT | 28.0 | - | - | $294.00 |
+
+Top 5 by Yield: Fortified (Integra) 49.0, Genetics (UniSouth) 49.0, Seed (Innvictis) 49.0, Seed (Innvictis) 48.0, NK54-J9XFS (NK) 47.0.