Initial commit: RECON codebase baseline

Current state of the pipeline code as of 2026-04-14 (Phase 1 scaffolding complete).
Config has new_pipeline.enabled=false and crawler.sites=[] per refactor plan.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

requirements.txt

@@ -0,0 +1,69 @@
+annotated-types==0.7.0
+anyio==4.12.1
+babel==2.18.0
+beautifulsoup4==4.14.3
+blinker==1.9.0
+certifi==2026.1.4
+cffi==2.0.0
+charset-normalizer==3.4.4
+click==8.3.1
+courlan==1.3.2
+cryptography==46.0.5
+dateparser==1.3.0
+Flask==3.1.2
+google-ai-generativelanguage==0.6.15
+google-api-core==2.29.0
+google-api-python-client==2.190.0
+google-auth==2.48.0
+google-auth-httplib2==0.3.0
+google-generativeai==0.8.6
+googleapis-common-protos==1.72.0
+grpcio==1.78.0
+grpcio-status==1.71.2
+h11==0.16.0
+h2==4.3.0
+hpack==4.1.0
+htmldate==1.9.4
+httpcore==1.0.9
+httplib2==0.31.2
+httpx==0.28.1
+hyperframe==6.1.0
+idna==3.11
+itsdangerous==2.2.0
+Jinja2==3.1.6
+jusText==3.0.2
+lxml==6.0.2
+lxml_html_clean==0.4.3
+MarkupSafe==3.0.3
+numpy==2.4.2
+packaging==26.0
+pillow==12.1.1
+portalocker==3.2.0
+proto-plus==1.27.1
+protobuf==5.29.6
+pyasn1==0.6.2
+pyasn1_modules==0.4.2
+pycparser==3.0
+pydantic==2.12.5
+pydantic_core==2.41.5
+pyparsing==3.3.2
+PyPDF2==3.0.1
+pytesseract==0.3.13
+python-dateutil==2.9.0.post0
+pytz==2025.2
+PyYAML==6.0.3
+qdrant-client==1.16.2
+regex==2026.1.15
+requests==2.32.5
+rsa==4.9.1
+six==1.17.0
+soupsieve==2.8.3
+tld==0.13.1
+tqdm==4.67.3
+trafilatura==2.0.0
+typing-inspection==0.4.2
+typing_extensions==4.15.0
+tzlocal==5.3.1
+uritemplate==4.2.0
+urllib3==2.6.3
+Werkzeug==3.1.5