Added
- Agent-framed live demo.
docs/demo.gifnow shows three real agent sessions —[Claude Code] ❯ Is NBIS a buy?,[Codex] ❯ compare AMD and NVDA,[Antigravity] ❯ should I sell everything…(refused) — against live yfinance data, with the python plumbing hidden. Rendered deterministically fromdocs/demo.tape(charmbracelet/vhs); ademo.ymlworkflow re-renders on tape/renderer changes so the README demo can never drift from the code. - Contract↔eval pinning tests. Synthetic §4a/§4b-shaped answers must score clean through
synthesis_checks, so SKILL.md phrasing and the eval regexes can no longer drift apart silently.
Changed
- §4a leads with the bottom line (direct conditional view before the evidence table); new §4b comparison shape: bottom line → side-by-side table → interpretation by dimension → winner by category (never a universal winner beyond the evidence) → what decides the debate; new Tone section — no hype, no caveat walls, prefer "cannot conclude" over fake precision; SKILL.md opens with the epigraph: "The engine calculates. You think."
Fixed
- Code-review findings #1–#5 (eval/contract drift):
_WATCHmatches §4b's "what decides the debate"; compare intent weighs via per-dimension_COMPARE_TENSION; epigraph scopes no-verbatim-draft tookstatus (never restyle a refusal); §4b ordering clarified; §4a setup re-anchored to report regime/metrics.
🤖 Generated with Claude Code