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/524-583.md

@@ -0,0 +1,160 @@
+# TC1507 X MON 88017
+
+- EPA Reg No: **524-583**
+- Registrant: BAYER CROPSCIENCE, LLC
+- Signal word: Caution
+- Active ingredients: Bacillus thuringiensis Cry1F protein and the genetic material necessary for its production (plasmid insert PHI8999) in corn (0.0012%); Bacillus thuringiensis Cry3Bb1 protein and the genetic material necessary (vector ZMIR39) for its production in corn (0.0079%)
+- Label accepted: 2021-06-15
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000524-00583-20210615.pdf
+
+---
+UNIT
+ED STATES ENVIRONMENTAL PROTECTION AGENCY 
+WASHINGTON, D.C. 20460 
+OFFICE OF CHEMICAL SAFETY 
+AND POLLUTION PREVENTION 
+June 15, 2021 
+David J. Chi 
+Global Regulatory Manager 
+Bayer – Crop Science 
+Monsanto Company 
+700 Chesterfield Parkway West 
+Chesterfield, Missouri 63017 USA 
+Subject: 
+Non-PRIA (Pesticide Registration Improvement Act) Labeling and Formulation 
+Amendment – Include OECD Unique Identifiers, correct typographical errors, and update 
+label directions 
+Product Name: TC1507 × MON 88017 Insect-Protected, Herbicide-Tolerant Corn 
+EPA Registration Number: 524-583 
+Application Dates: 12/14/2016 and 1/5/2017 
+OPP Case Number: 00074904 
+Dear Mr. Chi: 
+The amended labeling and Confidential Statement of Formula (CSF) referred to above, submitted in 
+connection with registration under the Federal Insecticide, Fungicide, and Rodenticide Act (FIFRA), as 
+amended, are acceptable provided that you comply with the updated terms and conditions as described 
+in this letter. 
+1. Submit and/or cite all data required for registration or registration review of your product when
+the EPA requires all registrants of similar products to submit such data.
+2. The subject registration will be limited to Bacillus thuringiensis Cry1F protein and the genetic
+material necessary for its production (vector PHP8999) in event TC1507 (OECD Unique
+Identifier: DAS-Ø15Ø7-1) and Bacillus thuringiensis Cry3Bb1 protein and the genetic material
+necessary for its production (vector PV-ZMIR39) in event MON 88017 (OECD Unique
+Identifier: MON-88Ø17-3) for use in field corn.
+3. This product may be used for breeding purposes, 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 registrant per year. Commercial plantings of this product, for the purposes
+of grain production and controlling corn insect pests, are prohibited.
+4. This plant-incorporated protectant (PIP) 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 registered plant-incorporated protectants
+to produce inbred corn lines and hybrid corn varieties with combined pesticidal traits.
+
+Page 2 of 2 
+EPA Reg. No. 524-583 
+OPP Case No. 00074904 
+5. Harvested seed are not allowed for sale as commercial seed in the U.S. under the current
+conditions of this registration, but any non-treated seed containing TC1507 x MON 88017 may
+be sold as g
+rain.
+Please no
+te that the record for this product currently contains the following acceptable CSF: 
+ Basic CSF dated 01/05/2017
+Any CSFs o
+ther than that listed above are superseded/no longer valid. 
+A stamped 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 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 
+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,
+Alan Reynolds, Team Leader 
+Emerging 
+Technologies Branch 
+Biopesticides and Pollution 
+ Prevention Division (7511P) 
+Office of Pesticide Programs 
+Enclosure
+
+Monsanto Company CR192-15E1 Page 15 of 84 
+ 
+Plant-Incorporated Protectant Label 
+ 
+TC1507 × MON 88017 
+Insect-Protected, Herbicide-Tolerant Corn 
+(OECD Unique Identifier: DAS- Ø15Ø7-1 × MON-88Ø17-3) 
+ 
+Active Ingredients: 
+Bacillus thuringiensis Cry1F protein and the genetic material necessary (vector 
+PHP8999) for its production in TC1507 × MON 88017 Corn (OECD Unique Identifier: 
+DAS-Ø15Ø7-1 × MON-88Ø17-3) ..................................................................... ≤ 0.0012%* 
+ 
+Bacillus thuringiensis Cry3Bb1 protein and the genetic material necessary (vector PV-
+ZMIR39) for its production in TC1507 × MON 88017 Corn (OECD Unique Identifier: 
+DAS-Ø15Ø7-1 × MON-88Ø17-3) ..................................................................... ≤ 0.0079%* 
+ 
+Other Ingredients: 
+CP4 EPSPS protein (5-enolpyruvylshikimate-3-phosphate synthase) and the genetic 
+material necessary (vector PV-ZMIR39) for its production in TC1507 × MON 88017 
+Corn (OECD Unique Identifier: DAS-Ø15Ø7-1 × MON-88Ø17-3) ................. ≤ 0.0052%* 
+ 
+PAT protein (phosphinothricin acetyl transferase) and the genetic material necessary 
+(vector PHP8999) for its production in TC1507 × MON 88017 Corn (OECD Unique 
+Identifier: DAS-Ø15Ø7-1 × MON-88Ø17-3) .................................................. ≤ 0.00045%* 
+ 
+*Maximum percent (wt/wt) of dry forage 
+ 
+ 
+ 
+KEEP OUT OF REACH OF CHILDREN 
+ 
+CAUTION 
+ 
+ 
+NET CONTENTS_______ 
+ 
+ 
+EPA Registration No. 524-583 
+EPA Establishment No. 524-MO-002 
+ 
+Monsanto Company 
+800 North Lindbergh Blvd. 
+St. Louis, MO 63167 
+ 
+06/15/2021
+524-583
+
+Monsanto Company CR192-15E1 Page 16 of 84 
+DIRECTIONS FOR USE 
+It is a violation of Federal law to use this product in any manner inconsistent with its 
+labeling. 
+This plant-incorporated protectant (PIP) 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 registered plant-incorporated 
+protectants to produce inbred corn lines an d hybrid corn varieties with combined 
+pesticidal traits. 
+This product may be used for breeding purposes, 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 registrant per year . Commercial plantings of this product, for 
+the purposes of grain production and controlling corn insect pests, are prohibited. 
+Harvested seed are not allowed for sale as commercial seed in the U.S. under the current 
+conditions of this registration, but any non-treated seed containing TC1507 × MON 
+88017 may be sold as grain. 
+There are no refuge requirements for planting TC1507 × MON 88017 Corn.