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/524-552.md

@@ -0,0 +1,150 @@
+# MON 88017 X MON 810
+
+- EPA Reg No: **524-552**
+- Registrant: BAYER CROPSCIENCE, LLC
+- Signal word: Caution
+- Active ingredients: Bacillus thuringiensis Cry3Bb1 protein and the genetic material necessary (vector ZMIR39) for its production in corn (0.015%); Bacillus thuringiensis Cry1Ab protein and the genetic material (PV-ZMBK07) necessary for its production in corn event MON-00810-6; % dry weight (0.0017%)
+- Label accepted: 2019-02-26
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000524-00552-20190226.pdf
+
+---
+UNITED STATES ENVIRONMENTAL PROTECTION AGENCY 
+ WASHINGTON, D.C. 20460 
+ 
+ 
+ 
+ 
+ 
+OFFICE OF CHEMICAL SAFETY 
+AND POLLUTION PREVENTION 
+ 
+February 26, 2019 
+ 
+ 
+ 
+David J. Chi 
+Regulatory Affairs Manager 
+Monsanto company 
+800 North Lindbergh Blvd. 
+St. Louis, MO 63167 
+ 
+Subject: Labeling Notification pe r Pesticide Registration Notice (PRN) 98-10– Alternative brand 
+ names and/or primary brand names revisions and other minor ch anges 
+ Product Name: MON 88017 x MON 810 
+ EPA Registration Number: 524-552 
+ Application Date: October 17, 2018 
+ OPP Decision Number: 547094 
+ 
+Dear Mr. Chi: 
+ 
+The U.S. Environmental Protection Agency (EPA) is in receipt of your application for notification under 
+Pesticide Registration Notice (PRN) 98-10 for the above referenced product. The Biopesticides and 
+Pollution Prevention Division (BPPD) 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 labeling submitted with this application has been stamped “Notification” and will be placed in our 
+records. You must submit one (1) copy of the final printed labeling with the modifications. 
+ 
+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 the Federal Insecticide, Fungicide, and Rodenticide Act 
+(FIFRA) and is subject to review by the 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 
+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.
+
+Page 2 of 2 
+EPA Reg. No. 524-552 
+OPP Decision No. 547094 
+ 
+If you have any questions, please contact Michael Glikes of my team by phone at (703) 231-6499 or via 
+email at glikes.michael@epa.gov. 
+ 
+ 
+ S i n c e r e l y , 
+ 
+ 
+ 
+ 
+ A l a n R e ynolds, Team Leader 
+ E m e r g i n g T e c hnologies Branch 
+Biopesticides and Pollution 
+Prevention Division (7511P) 
+Office of Pesticide Programs 
+ 
+ 
+ 
+ 
+ 
+ 
+ 
+Enclosure
+
+Monsanto Company CR267-18E1 Page 1 of 2
+Plant-Incorporated Protectant Label
+MON 88017 × MON 810
+Rootworm- and Corn Borer-Protected Corn Seed
+(Alternate Brand Names: YieldGard VT Triple ®)
+(OECD Unique Identifier: MON-88Ø17-3 uMON-ØØ81Ø-6)
+Active Ingredients:
+Bacillus thuringiensis Cry3Bb1 protein and the genetic material necessary for its
+production (Vector ZMIR39) in event MON 88017 corn (OECD Unique Identifie r:
+021‘ ”
+Bacillus thuringiensis Cry1Ab delta-endotoxin and the genetic material necessary for its
+production (Vector PV-ZMCT01) in event MON 810 corn (OECD Unique Identifi er:
+021‘‘‘ ”
+Other Ingredients:
+CP4 EPSPS (5-Enolpyruvylshikimate-3-phosphate synthase) protein and t he genetic
+material necessary for its production (Vector ZMIR39) in event MON 88017 c orn
+(OECD Unique Identifier: MON-88Ø17-3) ............................. ............................”0.007%*
+*Percentage (wt/wt) on a dry weight basis for whole plant (forage).
+KEEP OUT OF REACH OF CHILDREN
+CAUTION
+EPA Registration No. 524-552
+EPA Establishment No. 524-MO-002
+Monsanto Company
+800 North Lindbergh Blvd.
+St. Louis, MO 63167
+NET CONTENTS__________
+®YieldGard VT Triple is a registered trademark of Monsanto Technology, LLC .
+524-552
+02/26/2019
+
+Monsanto Company CR267-18E1 Page 2 of 2
+DIRECTIONS FOR USE
+It is a violation of federal law to use t his product in a manner inconsistent with its labeling.
+Seed containing MON 88017 × MON 810 ma y only be planted for the purposes of
+agronomic evaluation, seed increase and production in breeding nurserie s as specified in the
+terms and conditions of this registra tion and on the labeling. Commercial plantings of this
+product for the purposes of grain production and controlling insect pests are prohibited.
+This plant-incorporated protectan t may be combined through conventiona l breeding with
+other registered plant-incorporated protectants that are similarly app roved for use in
+combination, through conventional b reeding, with other plant-incorpor ated protectants to
+produce inbred corn lines and hybrid cor n varieties with combined pestici dal traits.
+Plants that contain the pesticide product may be grown on 20,000 acres per c ounty and a total
+of 250,000 acres or less in total per year in the U.S.
+Harvested seed are not allowed for sale as commercial seed in the U.S. under the conditions
+of this registration, but any non-treated seed grain containing MON 88017 may be sold as
+grain.
+There are no refuge requirements for planting of MON 88017 × MON 810 Corn.
+CORN INSECTS CONTROLLED OR SUPPRESSED
+Field corn has been genetically transformed to produce the B.t. Cry1Ab and Cry3Bb1
+proteins for the control or suppressi on of the following lepidopteran and coleopteran
+insects, respectively:
+European corn borer ( Ostrinia nubilalis)
+Southwestern corn borer ( Diatraea grandiosella)
+Southern cornstalk borer ( Diatraea crambidoides)
+Sugarcane cornstalk borer ( Diatraea saccharalis)
+Corn earworm (Helicoverpa zea)
+Fall armyworm (Spodoptera frugiperda)
+Stalk borer (Papaipema nebris)
+Western corn rootworm ( Diabrotica virgifera virgifera )
+Northern corn rootworm ( Diabrotica barberi)
+Mexican corn rootworm ( Diabrotica virgifera zeae)
+__________________________
+MON 88017 x MON 810 is a product of Monsanto’s research program offering uni que
+genetic characteristics for specific grower needs and may be protected by one or more
+U.S. Patents found at the following web page: www.monsantotechnology.co m.