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

# Trusted Match privacy and context-cache security

> Migrate Context Match caches to AdCP 3.3 evaluation namespaces while preserving the 3.1.22 privacy protections.

> [!WARNING]
>
> AdCP 3.3 adds the `cache_namespace` conformance contract. The experimental
> breaking/security notice published September 13, 2026 had an October 25,
> 2026 notice floor, which has passed. The contract did not ship in 3.2 and is
> not retroactive conformance for 3.1 or 3.2. Published release artifacts remain
> unchanged.

Version 3.1.22 already shipped two emergency privacy/security corrections:

* [#7396](https://github.com/adcontextprotocol/adcp/pull/7396) prohibited
  Context Match embeddings derived from non-public content attributable to
  one user or session, including through an intermediate summary. Keywords
  and summaries require documented privacy reduction.
* [#7397](https://github.com/adcontextprotocol/adcp/pull/7397) replaced
  placement-only response caching with `{provider_id, context_hash}`.

Those emergency protections remain in force. The new evaluation namespace
extends the request partition rather than replacing it.

## Immediate safe operation

An affected implementation MUST bypass or disable cache lookup,
in-flight request coalescing, and insertion until both of these controls are
implemented:

1. Request partitioning by the RFC 8785 JCS/SHA-256 `context_hash`.
2. A trusted `cache_namespace` for result-affecting security and provider
   configuration contexts, with the lifecycle and warm-hit authorization
   controls in the [TMP caching contract](https://docs.adcontextprotocol.org/dist/docs/3.3.0-rc.0/trusted-match/specification.md#caching).

The router-owned inputs include authenticated principal or tenant,
authorization and entitlement revision, active-package generation, endpoint
replacement, provider configuration, and targeting/rules generations.
Bypass caching when the required trusted context or generation cannot be
established, or generation change and invalidation cannot be coordinated.
Never accept a namespace supplied by the caller.

## Cache-key migration

For AdCP 3.3, partition each provider's cache by:

```text theme={null}
{provider_id, cache_namespace, context_hash}
```

Hash the validated provider-forwarded request after removing only `$schema`
and `request_id`; preserve array order and every response-affecting input.
Use RFC 8785 JCS and SHA-256. `provider_id` stays the stable registration
identity, not a rotating generation.

Select the namespace from trusted authentication, authorization, deployment,
and provider-configuration state. It must not contain raw principal or tenant
identifiers, derive from credentials, or incorporate viewer identity, user
tokens, or Identity Match state. Treat namespace mappings, hashes, and cached
responses as sensitive request data; keep them out of logs, metric labels,
and traces.

Capture one evaluation context for lookup, coalescing, outbound endpoint and
authentication selection, provider evaluation, and insertion. Do not relabel
an old in-flight result into a new namespace, insert it after its context
changes, or reuse a generation while old entries or work survive. Authenticate
and authorize the current publisher principal and property before lookup and
again before returning a warm hit.

## Provider-owned model changes

A model change that can affect output is a targeting-configuration change
under the existing `cache_ttl: 0` SHOULD. Providers SHOULD lower their
advertised `cache_ttl` ahead of a planned model deployment that affects output.
Routers are not required to observe internal provider deployments.

A warm entry cached before the change may still be served until its TTL
expires: at most the `cache_ttl` advertised for that entry, 5 minutes by
default and at most 86400 seconds. A later `cache_ttl: 0` cannot evict an
already-cached entry. Lowering TTL ahead of deployment keeps this stale window
short; it does not retroactively shorten an older entry's TTL.

## Validation cases

These cases are router conformance requirements, not a claim that this
specification repository implements a router cache.

| Warm-cache case | Required outcome |
| - | - |
| Same provider and request under two different evaluation namespaces | The second namespace cannot reach the first namespace's entry or in-flight work. |
| Changed request or private data | Recompute the request hash; a changed artifact, signals, geo or package subset cannot reuse the old request's entry. Single-user private derivatives remain prohibited. |
| Changed authorization or entitlement | Authenticate and authorize under current policy on every lookup and warm return; rotate the trusted namespace when the evaluation context changes. A revoked caller cannot receive a warm result. |
| Required trusted namespace cannot be established | Bypass lookup, coalescing and insertion rather than reuse a prior namespace. |
| Internal provider model deployment | Follow the provider TTL policy; an older warm entry may survive only until its original TTL expires. |

## Single-user context migration

Do not forward embeddings derived directly or indirectly from non-public
single-user content. Apply aggregation, thresholding or another documented
privacy-reduction method to keywords and summaries, and remove or reprocess
stored single-user derivatives before using them in new requests. Neither
namespace isolation nor hashing makes prohibited private context safe.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.