estimate batch cost (atomic agents/agent.py) looks up the per-model output price with PRICING.get(model, {}), returning 0.0 for any model not in the hardcoded pricing table. check batch reservation then early-returns when the reservation is <= 0, skipping the batch reservation entirely. That reservation is the only defense against the documented fan-out race where every parallel helper/delegate reads the identical pre-batch on-disk cost total and each passes its individual check even though the collective spend overruns the configured cap.

Impact: an operator running any model not in the pricing table (self-hosted/Ollama/vLLM, a new provider SKU) with cost guardrails + daily cap usd set believes the cap protects them, but a single parallel batch can blow past the cap. The parallel-helper model argument can also be steered to an unknown id. The sibling dream. estimate dream cost does this correctly (PRICING.get(model, fallback pricing())), which makes this a clear defect.

Affected: agent.py ( estimate batch cost / check batch reservation), all versions through 1.0.0.

Fix: use PRICING.get(model, costs. fallback pricing())['output'] (mirror dream/calc cost). Add a conformance test asserting an unknown-model batch reserves > 0 and that an over-cap unknown-model batch raises CostGuardrailBlocked.