docker: production image + Gitea Actions for monthly refresh

Dockerfile: self-contained image with corpus + Chroma + BM25 baked
in. Drawbar's compose pulls + runs without volume mounts. Built from
sources.json (labels schema), PRODUCT_NAME=crop_chem by default,
HYBRID_SEARCH=true (always-on for production quality). RERANK_URL +
OLLAMA_URL get set at compose time.

.gitea/workflows/refresh.yml: monthly cron (1st @ 06:00 UTC) does
full scrape → reindex → image push. Scrapes Bayer (~30 min) +
EPA PPLS row-crop filtered (~7h). Skips reindex+push if no corpus
diff. Tags pushed: :latest, :<sha12>, :corpus-<YYYY.MM.DD>.

.gitea/workflows/image-only.yml: on-demand or auto on code-only
pushes to main (paths: docs_mcp/, rag/, scrape/, requirements.txt,
Dockerfile, sources.json). Reindexes from committed corpus, builds
image, pushes. ~10 min vs ~9h full refresh.

.gitignore: corpus/ now COMMITTED (4,159 labels, 265 MB of .md +
sidecars). Lets image-only.yml rebuild indexes without re-scraping.
chroma/ + bm25/ still gitignored (regenerable binary indexes).

.dockerignore: drops venv, eval results, PLAN/README/CLAUDE.md,
deploy/, .git/ — keeps the image lean. corpus + chroma + bm25
explicitly NOT in dockerignore (those go INTO the image).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

corpus/epa_ppls/8033-125.md

@@ -0,0 +1,39 @@
+# TOPSIN M WSB
+
+- EPA Reg No: **8033-125**
+- Registrant: NIPPON SODA CO., LTD.
+- Signal word: Caution
+- Active ingredients: Thiophanate-methyl (70%)
+- Label accepted: 2026-03-18
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/008033-00125-20260318.pdf
+
+---
+March 18, 2026
+SENT BY EMAIL
+Pedro Perdomo
+p.perdomo@nissoamerica.com
+NIPPON SODA CO., LTD.
+Subject: Formulation Notification per Pesticide Registration Notice (PRN) 98-10 - Updating contact
+name and address on the CSFs as well as adding alternate suppliers
+Product Name: TOPSIN M WSB
+Admin Number: 8033-125
+EPA Receipt Date: 12/09/2025
+Action Case Number: 00678193
+Dear Pedro Perdomo:
+The U.S. Environmental Protection Agency is in receipt of your application for notification under Pesticide
+Registration Notice 98-10 for the above referenced product. The EPA has conducted a review of this request
+for its applicability under PRN 98-10 and finds that the action requested falls within the scope of PRN 98-10.
+The Confidential Statements of Formula (CSFs) submitted with this application has or have been stamped
+“Notification” and will be placed in our records. Please note that the record for this product currently contains
+the following acceptable CSFs:
+Basic CSF dated 09/09/2015
+Alternate CSF #1 dated 11/24/2025
+Alternate CSF #2 dated 11/24/2025
+Any CSFs other than those listed above are superseded/no longer valid.
+ If you have questions, please contact Maya Wheeler by telephone at (202) 566-2957 or via email at
+wheeler.maya.b@epa.gov.
+Sincerely,
+Kable Bo Davis, Senior Advisor
+FHB, RD
+Office of Pesticide Programs
+Kable Bo Davis