1f3625a3e9
Replace the stale "## CodeGraph" example block (NEVER call explore directly / ALWAYS spawn an Explore agent) and the How-It-Works diagram with the validated "answer directly" guidance, and add codegraph_context/trace/explore to the tool table. Interactive A/B (Excalidraw + VS Code, n=3/arm) shows direct codegraph answering beats Explore-agent delegation at every scale: main-session context is ~scale-invariant (~50k), with 0 reads vs 17-26 and ~28% fewer tokens. Record the writeup under docs/benchmarks/answer-directly-vs-explore-agent.md. Docs-only; stays on 0.9.4 (no version bump). Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>