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/524-627.md

@@ -0,0 +1,132 @@
+# MON 87751 X MON 87701
+
+- EPA Reg No: **524-627**
+- Registrant: BAYER CROPSCIENCE, LLC
+- Signal word: Caution
+- Active ingredients: Bacillus thuringiensis Cry1A.105 protein and the genetic material  (Vector PV-GMIR1316) necessary for production in Mon 87751 soybean (0.00057%); Bacillus thuringiensis Cry2Ab2 protein and the genetic material  (Vector PV-GMIR1316) necessary for production in Mon 87751 soybean (0.00059%); Bacillus thuringiensis Cry1Ac protein and the genetic material (vector PV-GHBK04) necessary for its production in MON 88702 x MON 15985 x COT102 cotton (0.0011%)
+- Label accepted: 2016-04-06
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000524-00627-20160406.pdf
+
+---
+U.S. ENVIRONMENTAL PROTECTION AGENCY 
+Office of Pesticide Programs 
+Biopesticides and Pollution 
+Prevention Division (7511P) 
+1200 Pennsylvania Ave., NW 
+Washington, D.C. 20460
+EPA Reg. Number:
+524-627 
+Date of Issuance:
+April 6, 2016 
+NOTICE OF PESTICIDE: 
+ x Registration 
+___ Reregistration 
+(under FIFRA, as amended) 
+Term of Issuance: Unconditional 
+Name of Pesticide Product: 
+MON 87751 x MON 87701 
+Name and Address of Registrant (include ZIP Code): 
+Monsanto Company 
+800 North Lindbergh Blvd. 
+St. Louis, MO 63167 
+Note: Changes in labeling differing in substance from that accepted in connection with this registration must be submitted to and accepted by the 
+Biopesticides and Pollution Prevention Division prior to use of the label in commerce. In any correspondence on this product always refer to the above 
+EPA registration number. 
+On the basis of information furnished by the registrant, the above named pesticide is hereby registered/reregistered under the Federal Insecticide, Fungicide and 
+Rodenticide Act. Registration is in no way to be construed as an endorsement or recommendation of this product by the Agency. In order to protect health and the 
+environment, the Administrator, on his motion, may at any time suspend or cancel the registration of a pesticide in accordance with the Act. The acceptance of any 
+name in connection with the registration of a product under this Act is not to be construed as giving the registrant a right to exclusive use of the name or to its use if 
+it has been covered by others. 
+This registration does not eliminate the need for continual reassessment of the pesticide. If EPA determines 
+at any time, that additional data are required to maintain in effect an existing registration, the Agency will 
+require submission of such data under section 3(c)(2)(B) of FIFRA. 
+This product is unconditionally registered in accordance with FIFRA section 3(c)(5) and is subject to the 
+following terms: 
+1) The subject registration is limited to a combined yearly total of 20,000 acres or less in the U.S. with no
+more than 1,000 acres per county per year (per municipio in Puerto Rico) for breeding purposes,
+agronomic testing, and producing seed in the United States.
+2) Monsanto must submit reports on IRM monitoring and remedial action plans to EPA annually by August
+31
+st each year.
+3) Upon request, Monsanto must provide EPA by January 31st each year annual reports on the acreage
+where MON 87751 x MON 87701 has been grown by States and territory.
+Signature of Approving Official:
+Alan Reynolds, Team
+ Leader 
+Microbial Pesticide Branch 
+Biopesticides and Pollution Prevention Division 
+Date: 
+April 6, 2016 
+EPA Form 8570-6
+
+Page 2 of 2
+OPP Decision No. 506547 
+4)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 containing MON 87751 x MON 87701 may be sold as grain.
+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. A 
+stamped copy of your labeling is enclosed for your records. Please also note that the record for this 
+product currently contains the following acceptable Confidential Statement of Formula (CSF):
+• Basic CSF dated 06/22/2015
+If you have any questions, please contact Jennifer Wingeart of my team by phone at (703) 347-0100 or 
+via email at wingeart.jennifer@epa.gov. 
+Sincerely, 
+Alan Reynolds, Team Leader 
+Microbial Pesticides Branch 
+Biopesticides and Pollution 
+Prevention Division (7511P) 
+Enclosure (stamped label)
+
+Monsanto Company SY259-15E1 Page 1 of 2 
+Plant-Incorporated Protectant Label 
+MON 87751 × MON 87701 
+Lepidopteran-Protected Soybean 
+(OECD Unique Identifier MON-87751-7 × MON-877Ø1-2) 
+Active Ingredients: 
+Bacillus thuringiensis Cry1A.105 protein and the genetic mate rial necessary for its production 
+(vector PV-GMIR13196) in MON 87751 × MON 87701 soybean (OECD Unique Identifier 
+MON-87751-7 × MON-877Ø1-2) .................................................................... ≤0.00057%* 
+Bacillus thuringiensis Cry2Ab2 protein and the genetic mate rial necessary for its production 
+(vector PV-GMIR13196) in MON 87751 × MON 87701 soybean (OECD Unique Identifier 
+MON-87751-7 × MON-877Ø1-2) .................................................................... ≤0.00059%* 
+Bacillus thuringiensis Cry1Ac protein and the genetic material necessary for its production 
+(vector PV-GMIR9) in MON 87751 × MON 87701 soybean (OECD Unique Identifier MON-
+87751-7 × MON-877Ø1-2) ................................................................................. ≤0.0011%* 
+* Maximum percent (wt/wt) of dry grain.
+KEEP OUT OF REACH OF CHILDREN 
+CAUTION 
+Ne
+t Contents __________ 
+EPA Registration Number 524-627 
+EPA Establishment Number 524-MO-002 
+Monsanto Company 
+800 North Lindbergh Blvd. 
+St. Louis, Missouri 63167 
+04/06/2016
+524-627
+
+Monsanto Company SY259-15E1 Page 2 of 2 
+DIRECTIONS FOR USE 
+It is a violation of federal law to use this product in a manner inconsistent with its labeling. 
+Seed containing this pesticide product may only be planted for the purposes of agronomic 
+evaluation, seed increase and production in bree ding nurseries as specified in the terms and 
+conditions of this registration and on the labelin g. Commercial plantings of this product for the 
+purposes of grain production and controlling insect pests are prohibited. 
+MON 87751 × MON 87701 soybean may be combined through conventional breeding with other 
+registered plant incorporated protectants that are similarly approved for use in combination, 
+through conventional breeding, with other register ed plant-incorporated protectants to produce 
+soybean varieties with combined pesticidal traits. 
+Soybean has been transformed to express Bacillus thuringiensis Cry1A.105, Cry2Ab2 and 
+Cry1Ac proteins for the control of the following lepidopteran soybean pests: 
+Soybean velvetbean caterpillar Anticarsia gemmatalis 
+Soybean looper Chrysodeixis includens 
+Soybean axil borer Crocidosema aporema
+Sunflower looper Rachiplusia nu
+Corn earworm Helicoverpa zea 
+Fall armyworm Spodoptera frugiperda 
+Plants that contain the pesticide product may be grown on 20,000 acres or less in total per year in 
+the U.S. with no more than 1,000 acres per county per year (per municipio in Puerto Rico). 
+Harvested seed should 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 87751 × MON 87701 
+may be sold as grain. 
+There are no refuge requirements for planting MON 87751 × MON 87701 Soybean.