docs(evals): F38 numeric refinements from the repricing verification writeup

docs(evals): findings F35-F38, battery v2 confound corrections, staleness fixes

wip: eval harness + public docs bundle; relocate eval docs into evals/ (#10)

Merge experiment #3: SLM knowledge compaction (Ollama small models, 32k window)

docs: add evals_contributing.md — teammate experiment playbook

docs(evals): F29 — context-compaction maps a boundary where full_history stops winning

Merge experiment #5: context-compaction study (keep-all vs compaction vs retrieve, Gemini 2.5 Flash)

docs(evals): promote GraphRAG result to F28 in the central findings log

Merge experiment #2: GraphRAG vs classical RAG (opt-in retriever + scoped comparison)

feat(evals): single-turn latency finding (F27) + de-confound latency tooling

evals(slm): Axis-A results (3 SLMs x 8 memory presets) + F25, dual-experiment writeup

evals: SLM knowledge-compaction findings (F24) + writeup

compaction study: standalone 2.5-Flash results writeup + report glob fix

feat: add findings on DeepSeek-V4-Flash performance and memory strategies

Refactor telemetry pricing and evaluation reports

graphrag: document the GraphRAG-vs-RAG experiment (methodology, build, run)

evals: add KB-fair recall/citation metrics; record F23

Refine v2 eval plan and memory harness

Make collaborator data-download snippet copy-paste-safe

Add Part C eval variants, LLM judge, and harness fixes

Add evaluation harness for memory/context-management experiments