updated README with cost per incident image

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:
+
+<p align="center">
+  <img src="docs/cost-per-incident.png" alt="Langfuse trace showing per-node cost breakdown and total_cost_usd for one incident" width="720"/>
+</p>
+<p align="center"><sub>Langfuse — <code>total_cost_usd</code> and per-node LLM/tool breakdown for one incident run</sub></p>
 
 ### 5 · Durability — survive the human pause and the cold start
 
@@ -433,7 +438,7 @@ make verify     # confirm all imports resolve
 | Slack webhooks | $0 |
 | **Total infrastructure** | **$0/month** |
 
-Anthropic API cost per incident run: **~$0.02** (4 agents × ~500 tokens each at Claude Sonnet pricing), tracked per incident in Langfuse and capped per run by the cost circuit breaker (`MAX_INCIDENT_USD`). See [`docs/cost-per-incident.png`](docs/) for the Langfuse cost view.
+Anthropic API cost per incident run: **~$0.02** (4 agents × ~500 tokens each at Claude Sonnet pricing), tracked per incident in Langfuse and capped per run by the cost circuit breaker (`MAX_INCIDENT_USD`). See [Layer 4 · Cost](#4--cost--per-incident-with-a-runaway-breaker) for the Langfuse trace screenshot.
 
 ---