Per-turn token, cost, and savings capture (FinOps)
Events now carry real per-turn token usage, model id, and cost_usd, replacing the flat per-event cost proxy. Engineering leaders can see actual AI spend per model, how much context-mode saved, and net/ROI.
Highlights
- Real per-model pricing catalog (63 curated models across Anthropic, OpenAI, Google, and other vendors) behind a small no-regex lookup module. Non-Claude models are now priced from their own rates instead of defaulting to Claude pricing.
- Structured cost event (
model_idplus four token counts andcost_usd), replacing the prior string encoding, so the platform persists typed columns. - Per-turn capture across the nine adapters that expose usage: claude-code (session transcript, cursor-gated to avoid double counting), pi, omp, opencode, openclaw, gemini-cli, codex, qwen-code, and kimi. Adapters whose host does not expose usage remain on a clearly labeled estimate.
bytes_avoidedis now forwarded so the platform can attribute context-saving value.
All changes are additive and backward compatible.
Contributors
This release also includes community contributions — thank you:
- @ken-jo — Zed MCP configuration shape correction (#870)
- @ousamabenyounes — omp adapter MCP self-registration on plugin load (#872)
- @NgoQuocViet2001 — Zed configuration documentation sync (#875)