diff --git a/README.md b/README.md index 5c0c521..c988233 100644 --- a/README.md +++ b/README.md @@ -124,7 +124,12 @@ The action-authorization rule is the senior signal: a prompt-level guardrail is ### 4 · Cost — per incident, with a runaway breaker -One incident fans out across four LLM calls plus a Tavily search, so the cost unit is the **whole incident**, not a single call. Per-node token cost and Tavily call cost are summed, logged to the Langfuse trace as `total_cost_usd`, and returned in the API response. Two controls sit on top: the per-account run limit (5) bounds each account's lifetime spend, and a **circuit breaker** aborts any single incident that exceeds `MAX_INCIDENT_USD` before the next LLM call — so a reject→loop-back cycle can't quietly burn money. Average cost per incident is **~$0.02**; the Langfuse cost view is screenshotted in [`docs/cost-per-incident.png`](docs/). +One incident fans out across four LLM calls plus a Tavily search, so the cost unit is the **whole incident**, not a single call. Per-node token cost and Tavily call cost are summed, logged to the Langfuse trace as `total_cost_usd`, and returned in the API response. Two controls sit on top: the per-account run limit (5) bounds each account's lifetime spend, and a **circuit breaker** aborts any single incident that exceeds `MAX_INCIDENT_USD` before the next LLM call — so a reject→loop-back cycle can't quietly burn money. Average cost per incident is **~$0.02**; the Langfuse cost view: + +
+
+
Langfuse — total_cost_usd and per-node LLM/tool breakdown for one incident run