> ## Documentation Index
> Fetch the complete documentation index at: https://infercrane.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Context Passport and Burst Guard

> Durable logical session identity, delegated request survival, and budget-bounded overflow.

# Context Passport and Burst Guard

Context Passport persists bounded logical inference-session identity and best-effort affinity hints:

```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}}
infercrane session create coder-production --ttl 1h
```

Send the returned ID as `X-InferCrane-Context-Passport`. The in-memory route snapshot prefers the hinted
binding or target only while it remains eligible; otherwise ordinary healthy routing wins and the response
reports `X-InferCrane-Affinity: fallback`.

<Warning>
  Context Passport does not store conversation bodies and does not guarantee durable KV state. Logical
  identity survives a worker; engine cache survival does not unless a separately qualified backend provides it.
</Warning>

## Request survival

Request survival is a delegated capability contract. A runtime/backend may claim support only with a named
mechanism and local or real qualification evidence. Plain vLLM does not gain request migration from
InferCrane; unsupported and unknown states fail closed. InferCrane never implements distributed KV or token
migration.

## Burst Guard

Burst Guard combines fresh queue evidence, sustained breach/recovery intervals, qualified external health,
and a hard incremental hourly cost ceiling:

```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}}
infercrane burst coder-production \
  --queue-depth 8 --breaches 3 \
  --external-healthy \
  --incremental-cost-microusd-hour 4000000 \
  --max-incremental-cost-microusd-hour 5000000
```

It requires the existing governed external fallback policy, including privacy acknowledgement and its hard
request/cost budget. Stale signals, unavailable capacity, or cost above policy produce a fail-closed decision.
The evaluator persists evidence; route mutation remains owned by the existing policy controller.