Phase 0: branch setup for v2-edge-reliability

chore: harden .gitignore — .claude/, secrets, session artifacts; remove duplicate lines

docs: commit eval summary; clarify critic as LLM-assisted-judge; fix test imports

Phase 14: README

resolve merge: use local RECON codebase

initial commit

Fix sdk_version quotes in README yaml

Fix: remove gradio from requirements.txt - managed by sdk_version in README

Fix HF Spaces: tmp paths for cache and model, preload model at build

Fix: move demo.launch() outside __main__ guard for HF Spaces

Disable SSR mode for HF Spaces compatibility

Remove ragas/datasets/heavy deps - not needed at runtime

Fix Gradio 6 css parameter location

Prevent binary files from being tracked

Prevent binary files from being tracked

Pin Gradio to 6.10.0 matching local version

Remove cached API responses from tracking

Add HF Spaces metadata and project README

Phase 13: HF Spaces deploy ready - verdict logging, clean requirements

Phase 9.1: Cleaned up directory

Phase 9 polish: structured output format, HTML UI components, citation highlighting

Phase 9: Gradio UI, critic debug panel, claim table, session sidebar, MD export

Phase 8: LangGraph state machine, full pipeline, retry loop, session loader

Phase 7: synthesizer agent, claim extraction, session write, MD export

Phase 6: critic agent, 4-verdict taxonomy, contradiction detection, question rewriter

Phase 5: retriever agent, S2 keyword conversion, hybrid scoring, citation graph

Phase 4: planner agent with temporal decomposition and session context

Phase 3: retriever utils, hybrid scoring, DDG+S2 wrappers, disk cache

Phase 2: state schema, SQLite session memory, data dir

Initial commit