> ## 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.

# Replay and capacity intelligence

> Capture privacy-preserving workload shape and reason from observed capacity evidence.

# Replay and capacity intelligence

Inference Replay records the timing and token-count shape of production traffic without storing prompt
or output bodies. Session, parent-session, and shared-prefix identities are tenant-secret HMACs, not raw
identifiers. A trace records its window, sample count, schema, canonical digest, and evidence class.

```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}}
infercrane replay coder-production --window 24h --max-requests 1000
```

This command only captures persisted observations. It sends no workload and creates no infrastructure.
To approximate the captured mean token sizes and peak concurrency with AIPerf, opt in explicitly:

```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}}
infercrane replay coder-production \
  --execute --acknowledge-cost --revision candidate
```

Execution is an AIPerf approximation, not a reproduction of prompt semantics or exact arrival timing.
The distinction is preserved in output and evidence.

## Capacity intelligence

```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}}
infercrane capacity --window 720h
```

Capacity Intelligence groups this tenant's observed lifecycle attempts by provider adapter, runtime,
compute mode, region, and GPU. It reports sample counts, success rate, normalized capacity/runtime
failures, and p50/p95 operation duration. It does not claim global availability or combine customer data.

## Artifact placement

The artifact cache contract records short-lived provider-native observations (`present`, `prefetching`,
`missing`, or `unknown`). Prefetch requests are durable and idempotent, but execution belongs to the
selected infrastructure adapter. InferCrane does not implement a model CDN or download protocol.

<Warning>
  Cache observations expire after at most 24 hours. Missing or stale evidence must never be treated as a
  cache hit or a readiness guarantee.
</Warning>

## Current boundary

Local qualification proves capture privacy, deterministic digests, tenancy, aggregation, and delegated
prefetch semantics. Real cache behavior and capacity distributions require the consolidated provider
qualification run.