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/524-597.md

@@ -0,0 +1,177 @@
+# MON 89034 SEED BLEND
+
+- EPA Reg No: **524-597**
+- 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 (0.0056%); Bacillus thuringiensis Cry2Ab2 protein and the genetic material necessary (vector PV-ZMIR245) for its production in corn (0.0055%)
+- Label accepted: 2018-07-05
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000524-00597-20180705.pdf
+
+---
+UNITED STATES ENVIRONMENTAL PROTECTION AGENCY 
+WASHINGTON, D.C. 20460 
+OFFICE OF CHEMICAL SAFETY 
+AND POLLUTION PREVENTION 
+July 5, 2018 
+David Chi 
+Regulatory Affairs Manager 
+Monsanto Company 
+800 North Lindbergh Blvd. 
+St. Louis, Missouri 63167 
+Subject: Non-PRIA (Pesticide Registration Improvement Act) Labeling Amendment – 
+• Make minor changes to designations for the active and inactive ingredients;
+• Add fall armyworm (S. frugiperda) as a target pest;
+• Make minor changes to the Directions for Use;
+• Remove Genuity® VT Double PRO® RIB Complete® as an Alternate Brand 
+Name;
+• Remove VT Double PRO® RIB Complete® Corn Blend as an Alternate Brand 
+Name;
+• Correct the name of Crockett County in the list of cotton-growing areas. 
+Product Name: MON 89034 Seed Blend 
+EPA Registration Number: 524-597 
+Application Date: 3/29/2018 
+OPP Decision Number: 542194 
+Dear Mr. Chi: 
+In an application dated March 29, 2018, you notified the U.S. Environmental Protection Agency (EPA) 
+that you requested to make minor changes to designations for the active and inactive ingredients, add 
+fall armyworm (S. frugiperda) as a target pest, make minor changes to the Directions for Use, and 
+correct the name of Crockett County in the list of cotton-growing areas. Subsequently, the EPA 
+determined that the actions requested do not fall under the scope of Pesticide Registration Notice 98-10 
+and therefore converted the notification to a non-PRIA amendment (OPP Decision No. 542194). The 
+amended labeling referred to above, submitted in connection with registration under the Federal 
+Insecticide, Fungicide, and Rodenticide Act (FIFRA), as amended, is acceptable. 
+Additionally, the alternate brand names Genuity® VT Double PRO® RIB Complete® and VT Double 
+PRO® RIB Complete® Corn Blend have been removed from the registration, and our records have been 
+updated accordingly. 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.
+
+Page 2 of 2 
+EPA Reg. No. 524-597 
+OPP Decision Nos. 542194 
+A stam
+ped copy of your labeling is enclosed for your records. This labeling supersedes all previously 
+accepted labeling. You must submit one (1) copy of the final printed labeling before you release this 
+product for shipment with the new 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 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. 
+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 Matt Weiner by phone at 703-347-0333 or via email at 
+weiner.matthew@epa.gov. 
+Sincerely, 
+A
+l a n R eynolds, Team Leader 
+E
+m e r g i n g T e chnologies Branch 
+Biopesticides and Pollution 
+ Prevention Division (7511P) 
+Office of Pesticide Programs 
+Enclosure
+
+Plant-Incorporated Protectant Label
+MON 89034 Seed Blend
+Lepidopteran-Protected Corn
+(OECD Unique Identifier MON-89Ø34-3)
+Active Ingredients:
+Bacillus thuringiensis Cry1A.105 protein and the genetic material (vector PV-ZMIR245)
+necessary for its production in MON 89034 (OECD Unique Identifier: MON-89 Ø34-3)
+ ”
+Bacillus thuringiensis Cry2Ab2 protein and the genetic material (vector PV-ZMIR245)
+necessary for its production in MON 89034 (OECD Unique Identifier: MON-89 Ø34-3)
+ ”
+* Percentage (wt/wt) on a dry weight basis whole plant (forage)
+The MON 89034 seed with this refuge configuration contains 95% MON 89034 mi xed
+with 5% non-B.t. corn within a single lot of seed.
+KEEP OUT OF REACH OF CHILDREN
+CAUTION
+NET CONTENTS__________
+EPA Registration No. 524-597
+EPA Establishment No. 524-MO-002
+Monsanto Company
+800 North Lindbergh Blvd.
+St. Louis, Missouri 63167
+07/05/2018
+524-597
+
+DIRECTIONS FOR USE
+It is a violation of Federal law to use this product in any manner inconsiste nt with its
+labeling. Information regarding co mmercial production as specified in t he terms and
+conditions of this registration must b e included in the Technology Use Gui de and/or
+Insect Resistance Management (IRM) Grower Guide.
+MON 89034 can be used to protect corn plants from leaf, stalk, and ear damage caused
+by corn borers.
+Refuge Requirements
+A refuge must consist of corn hybrids that do not contain B.t. technologies for the control
+of corn borers. This product achieves the required refuge as the refuge is i nterspersed
+within the field and occurs only by planting a licensed seed-mixture conta ining
+MON 89034 or MON 89034 stacked with other non-PIP technologies, with a mini mum
+of 5% non-PIP seed. This refuge configuration complies with refuge requir ements only
+in the U.S. Corn Belt.
+The sufficiency of this refuge configuration is defined by geography, and ultimately is
+based on insect presence and species. The seed mix refuge option for MON 89034
+complies with refuge requirements only in the U.S. Corn Belt.
+The 95/5% MON 89034 seed mix product may be planted in cotton growing areas:
+however, planting the 95/5% MON 89034 seed mix in cotton growing areas stil l requires
+planting an additional 20% structured refuge (block, strips, or border) a sd e f i n e df o r
+MON 89034 EPA registration 524-575. The interspersed refuge option for
+MON 89034 does not alone comply with refuge requirements in cotton growing
+areas.
+Cotton-growing areas include the following states: Alabama, Arkansas, G eorgia, Florida,
+Louisiana, North Carolina, Missis sippi, South Carolina, Oklahoma (only the counties of
+Beckham, Caddo, Comanche, Custer, Greer, Harmon, Jackson, Kay, Kiowa, Ti llman, and
+Washita), Tennessee (only the coun ties of Carroll, Chester, Crockett, Dy er, Fayette,
+Franklin, Gibson, Hardeman, Hardin, Haywood, Lake, Lauderdale, Lincoln , Madison,
+Obion, Rutherford, Shelby, and Tipton), Texas (except the counties of Car son, Dallam,
+Hansford, Hartley, Hutchinson, Lipscomb, Moore, Ochiltree, Roberts, an d Sherman),
+Virginia (only the counties of Dinwiddie, Franklin City, Greensville, Is le of Wight,
+Northampton, Southampton, Suffolk City, Surrey, and Sussex), and Missou ri (only the
+counties of Dunklin, New Madrid, P emiscot, Scott, and Stoddard).
+
+The seed mix (interspersed) refuge option under this registration is limi ted to planting
+specifically licensed seed corn of MON 89034 and MON 89034 stacks with non- PIP
+corn.
+With this option, the field containing an interspersed refuge may be treat ed with labeled
+insecticides to control additional cor n pests, including larval or adult lepidopteran pests,
+because both the MON 89034 and refuge are treated in the same manner. Insect icide
+treatments for control of European co rn borer, corn earworm, southwester n corn borer,
+southern cornstalk borer, sugarcane borer, fall armyworm, lesser cornst alk borer, and
+stalk borer may be applied only if economic thresholds are reached for one o r more of
+these target pests. Economic thresholds will be determined using methods recommended
+by local or regional professionals (e.g., Extension Service agents, crop consultants).
+Microbial B.t. insecticides must not be applied to the field containing a seed mix
+interspersed refuge.
+Corn Insects Controlled or Suppressed
+European corn borer Ostrinia nubilalis
+Southwestern corn borer Diatraea grandiosella
+Southern cornstalk borer Diatraea crambidoides
+Corn earworm Helicoverpa zea
+Fall armyworm Spodoptera frugiperda
+Stalk borer Papaipema nebris
+Lesser cornstalk borer Elasmopalpus lignosellus
+Sugarcane borer Diatraea saccharalis
+Sales of corn hybrids that contain Monsanto’s B.t. corn plant-incorporated protectant
+must be accompanied by a grower guide which includes information on planti ng,
+production and insect resistance management and notes that routine appli cations of
+insecticides to control these insects are usually unnecessary when corn c ontaining the B.t.
+proteins is planted.
+This plant-incorporated protectant (PIP) may be combined through conven tional breeding
+with other registered plant-incorporated protectants that are similarl y approved for use in
+combination, through conventional br eeding, with other registered plan t-incorporated
+protectants to produce inbred corn lines and hybrid corn varieties with co mbined
+pesticidal traits.
+MON 89034 Seed Blend is a product of Monsanto’s research program offering u nique
+genetic characteristics for specific grower needs and may be protected by one or more of
+the following U.S. patents that can be found at http://www.monsantotechn ology.com