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>

.gitea/workflows/image-only.yml

@@ -32,7 +32,9 @@ env:
   REGISTRY_PUSH: 192.168.0.2:1234
   REGISTRY_PULL: git.jpaul.io
   IMAGE: ${{ github.repository_owner }}/${{ github.event.repository.name }}
-  OLLAMA_URL: http://192.168.0.2:11434,http://192.168.0.2:11435,http://192.168.0.125:11434
+  # 4-GPU pool, weighted toward .0.125 (4090). See refresh.yml for the
+  # bench numbers. .0.2:11434 excluded — not GPU-pinned.
+  OLLAMA_URL: http://192.168.0.125:11434,http://192.168.0.125:11434,http://192.168.0.125:11434,http://192.168.0.125:11434,http://192.168.0.2:11436,http://192.168.0.2:11436,http://192.168.0.2:11435,http://localhost:11434
   EMBED_MODEL: nomic-embed-text
   PRODUCT_NAME: crop_seed
 

.gitea/workflows/refresh.yml

@@ -34,10 +34,16 @@ env:
   REGISTRY_PULL: git.jpaul.io
   IMAGE: ${{ github.repository_owner }}/${{ github.event.repository.name }}
 
-  # Embedder pool. Two Ollama instances on the Gitea/runner host
-  # (one per GPU) + the Windows Ollama. Trashpanda's Ollama is
-  # production-shared with Drawbar; CI does NOT hit it.
-  OLLAMA_URL: http://192.168.0.2:11434,http://192.168.0.2:11435,http://192.168.0.125:11434
+  # Embedder pool — 4 GPUs total, with .0.125 (RTX 40-series) listed
+  # multiple times to weight the round-robin scheduler toward the
+  # fastest endpoint. Measured throughput (50-chunk batches on
+  # nomic-embed-text):
+  #   .0.125:11434  (4090)       242 embeds/sec  ← weighted ×4
+  #   .0.2:11436    (GPU-pinned) 108 embeds/sec  ← weighted ×2
+  #   .0.2:11435    (GPU-pinned)  72 embeds/sec  ← weight 1
+  #   localhost (TITAN X)         37 embeds/sec  ← weight 1
+  # NOTE: .0.2:11434 is NOT GPU-pinned — exclude.
+  OLLAMA_URL: http://192.168.0.125:11434,http://192.168.0.125:11434,http://192.168.0.125:11434,http://192.168.0.125:11434,http://192.168.0.2:11436,http://192.168.0.2:11436,http://192.168.0.2:11435,http://localhost:11434
   EMBED_MODEL: nomic-embed-text
 
   PRODUCT_NAME: crop_seed