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/524-656.md

@@ -0,0 +1,161 @@
+# MON 89034 x MON 810 x MIR162 x MON 87411
+
+- EPA Reg No: **524-656**
+- Registrant: BAYER CROPSCIENCE, LLC
+- Signal word: Caution
+- Active ingredients: Bacillus thuringiensis Cry1A.105 protein and genetic material necessary (vector PV-ZMIR245) for its production in corn (0.0023%); Bacillus thuringiensis Cry2Ab2 protein and the genetic material necessary (vector PV-ZMIR245) for its production in corn (0.0078%); Bacillus thuringiensis Cry1Ab protein and the genetic material (PV-ZMBK07) necessary for its production in corn event MON-00810-6; % dry weight (0.0011%); dsRNA transcript comprising a DvSnf7 inverted repeat sequence derived from western corn rootworm (Diabrotica virgifera) and  the genetic material necessary for its production MON 87411 corn (4.9e-07%); Bacillus thuringiensis Cry3Bb1 protein and the genetic material necessary for its procuction (vector PV -ZMIR10871) in corn event MON 87411 (0.0051%); Bacillus thuringiensis Vip3Aa20 protein encoded by vector pNOV1300 in event MIR162 corn (SYN-IR162-4), % dw (0.0099%)
+- Label accepted: 2022-03-15
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000524-00656-20220315.pdf
+
+---
+UNITED STATES ENVIRONMENTAL PROTECTION AGENCY 
+WASHINGTON, D.C. 20460 
+ 
+ 
+ 
+ 
+ 
+OFFICE OF CHEMICAL SAFETY 
+AND POLLUTION PREVENTION 
+March 15, 2022 
+ 
+ 
+ 
+Edwards Allen, Ph.D. 
+Global Regulatory Manager 
+Bayer U.S.- Crop Science 
+700 Chesterfield Pkwy West 
+Chesterfield, MO 63017 
+ 
+Subject: Non-PRIA (Pesticide Registration Improvement Act) Labeling Amendment – Updates to 
+modify the company name and add the EPA registration number to the label 
+ Product Name: MON 89034 x MON 810 x MIR162 x MON 87411 
+ EPA Registration Number: 524-656 
+ Application Date: January 28, 2022 
+ OPP Case Number: 00338525 
+ 
+Dear Dr. Allen: 
+ 
+The amended labeling referred to above, submitted in connection with registration under the Federal 
+Insecticide, Fungicide, and Rodenticide Act (FIFRA), as amended, is acceptable. 
+ 
+The registrant of this product has been changed from Monsanto Company to Bayer Crop Science, and 
+our records and the product label have been updated accordingly. The registration number for the 
+product has not changed and remains EPA Registration Number 524-656. This approval does not affect 
+any terms or conditions that were previously imposed on this registration. You continue to be subject to 
+existing terms or conditions on your registration and any deadlines connected with them. 
+ 
+A stamped copy of your labeling is enclosed for your records. This labeling supersedes all previously 
+accepted labeling. In accordance with 40 CFR § 152.130(c), you may distribute or sell this product 
+under the previously approved labeling for 18 months from the date of this letter. After 18 months, you 
+may only distribute or sell this product if it bears this new revised labeling or subsequently approved 
+labeling. “To distribute or sell” is defined under FIFRA section 2(gg) and its implementing regulation at 
+40 CFR § 152.3. 
+ 
+Should you wish to add/retain a reference to your company’s website on your label, then please be 
+aware that the website becomes labeling under FIFRA and is subject to review by the U.S. 
+Environmental Protection Agency (EPA). If the website is false or misleading, the product will be 
+considered to be misbranded and sale or distribution of the product is unlawful under FIFRA section 
+12(a)(1)(E). 40 CFR § 156.10(a)(5) lists examples of statements the EPA may consider false or 
+misleading. In addition, regardless of whether a website is referenced on your product’s label, claims 
+made on the website may not substantially differ from those claims approved through the registration 
+process. Therefore, should the EPA find or if it is brought to our attention that a website contains false
+
+Page 2 of 2 
+EPA Reg. No. 524-656 
+OPP Case No. 00338525 
+ 
+or misleading statements or claims substantially differing from the EPA-approved registration, the 
+website will be referred to the EPA’s Office of Enforcement and Compliance Assurance. 
+ 
+Your release for shipment of this product constitutes acceptance of these terms. If these terms are not 
+complied with, this registration will be subject to cancellation in accordance with FIFRA section 6. 
+ 
+If you have any questions, please contact Leslie Paul by phone at (202) 566-1466 or via email at 
+paul.leslie@epa.gov. 
+ 
+ Sincerely, 
+ 
+ 
+ 
+ Alan Reynolds, Team Leader 
+ Emerging Technologies Branch 
+Biopesticides and Pollution 
+ Prevention Division (7511P) 
+Office of Pesticide Programs 
+ 
+ 
+ 
+Enclosure
+
+Plant-Incorporated Protectant Label 
+MON 89034 × MON 810 × MIR162 × MON 87411 
+Insect-Protected, Herbicide-Tolerant Corn 
+(OECD Unique Identifier: MON-89Ø34-3 × MON-ØØ81Ø-6 × SYN-IR162-4 × 
+MON-87411-9) 
+Active Ingredients: 
+Bacillus thuringiensis Cry1A.105 protein and the genetic material (vector PV-ZMIR245) 
+necessary for its production in MON 89034 × MON 810 × MIR162 × MON 87411 corn 
+(Unique Identifier MON-89Ø34-3 × MON-ØØ81Ø-6 × SYN-IR162-4 × MON-87411-9) 
+ ”
+Bacillus thuringiensis Cry2Ab2 protein and the genetic material (vector PV-ZMIR245) 
+necessary for its production in MON 89034 × MON 810 × MIR162 × MON 87411 corn 
+(Unique Identifier MON-89Ø34-3 × MON-ØØ81Ø-6 × SYN-IR162-4 × MON-87411-9) 
+ ”
+Bacillus thuringiensis Cry1Ab protein and the geneti c material (vector PV-ZMCT01) 
+necessary for its production in MON 89034 × MON 810 × MIR162 × MON 87411 corn 
+(Unique Identifier MON-89Ø34-3 × MON-ØØ81Ø-6 × SYN-IR162-4 × MON-87411-9) 
+ ”
+Bacillus thuringiensis Vip3Aa20 protein and the gene tic material (vector pNOV1300) 
+necessary for its production in MON 89034 × MON 810 × MIR162 × MON 87411 corn 
+(Unique Identifier MON-89Ø34-3 × MON-ØØ81Ø-6 × SYN-IR162-4 × MON-87411-9) 
+ ”
+Bacillus thuringiensis Cry3Bb1 protein and the genetic material (vector PV-ZMIR10871) 
+necessary for its production in MON 89034 × MON 810 × MIR162 × MON 87411 corn 
+(Unique Identifier MON-89Ø34-3 × MON-ØØ81Ø-6 × SYN-IR162-4 × MON-87411-9) 
+ ” 
+dsRNA transcript comprising a DvSnf7 inverted repeat sequence derived from Diabrotica 
+virgifera virgifera , and the genetic material (vecto r PV-ZMIR10871) necessary for its 
+production in MON 89034 × MON 810 × MIR162 × MON 87411 corn (Unique Identifier 
+MON-89Ø34-3 × MON-ØØ81Ø-6 × SYN-IR162-4 × MON-87411-9) 
+ ” 
+03/15/2022
+524-656
+
+Other Ingredients:
+PMI (phosphomannose isomerase) protein and the genetic material necessary (vector 
+pNOV1300) for its production in MON 89034 × MON 810 × MIR162 × MON 87411 
+corn (Unique Identifier MON-89Ø34-3 × MON-ØØ81Ø-6 × SYN-IR162-4 × MON-
+  ”
+
+CP4 EPSPS (5-enolpyruvylshikimate-3-phosph ate synthase) protei n and the genetic 
+material (vector PV-ZMIR10871) nece ssary for its production in MON 89034 × 
+MON 810 × MIR162 × MON 87411 corn (Uni que Identifier MON-89Ø34-3 × MON-
+‘‘‘î6<1,5î021”
+
+*Percentage (wt/wt) on a dry weight basis for whole plant (forage).
+
+KEEP OUT OF REACH OF CHILDREN 
+CAUTION 
+EPA Registration No. 524-656 
+EPA Establishment No. 524-MO-002 
+Bayer Crop Science 
+800 North Lindbergh Blvd. 
+St Louis, MO 63167 
+NET CONTENTS__________ 
+DIRECTIONS FOR USE 
+It is a violation of Federal law to use this seed in any manner inconsistent with this 
+labeling. 
+This plant-incorporated protectant (PIP) may be combined through conventional breeding 
+with other registered plant in corporated protectants that are similarly approved for use in 
+combination, through conventional breeding, with other registered plant-incorporated 
+protectants to produce inbred corn lines and hybrid corn varieties with combined 
+pesticidal traits. 
+This product may be used for breeding pur poses, agronomic testing, increasing inbred 
+seed stocks, and producing hybrid seed on up to a total of 20,000 acres per county and up 
+to a combined United States (US) total of 250,000 acres per plant incorporated protectant 
+(PIP) active ingredient per re gistrant per year. Commercial pl antings of this product, for 
+the purposes of grain production and controlling corn insect pests, are prohibited. 
+Harvested seed are not be allowed for sale as commercial seed in the U.S. under the 
+current conditions of this registration but any non-treated seed containing MON 89034 × 
+MON 810 × MIR162 × MON 87411 may be sold as grain.