docs(adaptive): document logical response cache keys

docs/configure-plugins/adaptive/response-cache.mdx

@@ -329,10 +329,15 @@ an equivalent provider-native stream. Available saved-token and estimated-cost
 values are reported on the `response_cache` mark, never by editing a buffered
 response body.
 
-## Cache Keys
+## Key Strategies
+
+`key_strategy` selects what counts as "the same request". Strategies never
+share cache entries: changing the strategy starts from an empty keyspace.
+
+### `exact_request` (default)
 
 Two requests hit the same entry when they are the same request after
-normalization, under the default `key_strategy = "exact_request"`:
+normalization:
 
 - The request is decoded to its normalized form and fingerprinted with
   SHA-256, so provider-shaped differences that mean the same thing collapse to
@@ -363,6 +368,23 @@ normalization, under the default `key_strategy = "exact_request"`:
 - Requests containing integers outside the exactly representable RFC 8785
   range (less than `-2^53` or greater than `2^53`) bypass the cache.
 
+### `logical`
+
+Everything keys exactly as `exact_request` except the `tools` array: each tool
+is keyed on its full definition with human-readable `description` text
+removed, and the array is sorted. Rewording a tool description or reordering
+the `tools` array no longer busts the cache; any other change to a tool
+definition — its name, its parameter schema (including constraints such as
+`enum` and `required`), its type, or its settings — still does.
+
+```toml
+[components.config.response_cache]
+key_strategy = "logical"
+```
+
+Use `logical` when prompt-engineering iterations on tool descriptions keep
+invalidating entries whose behavior did not change.
+
 ## Tool-Result Cache
 
 The same `response_cache` section can also cache results from
@@ -478,7 +500,7 @@ cacheable classes and cacheable overrides, plus the default policy.
 | `priority` | `50` | LLM execution intercept priority. Lower values run earlier. |
 | `bypass_rate` | `0.0` | Probability in `[0.0, 1.0]` of running a cacheable call live. A sampled call attempts to refresh the entry when its result is cacheable and the write succeeds. |
 | `cache_nondeterministic` | `false` | Only requests with an explicit numeric `temperature = 0` are eligible. Set `true` to cache and reuse sampled responses. |
-| `key_strategy` | `"exact_request"` | The only supported strategy: reuse requires the same normalized request. |
+| `key_strategy` | `"exact_request"` | What counts as the same request: `"exact_request"` or `"logical"`. Refer to [Key Strategies](#key-strategies). |
 | `header_allowlist` | `[]` | Trusted, non-secret response-affecting headers folded into the key (case-insensitive). A non-empty normalized allowlist policy also partitions the key. Known auth headers are rejected. |
 | `backend.kind` | `"in_memory"` | `"in_memory"`, or `"redis"` (requires building with the `redis-backend` feature). |
 | `backend.config.max_bytes` | 256 MiB | In-memory size budget; the oldest entries are evicted first. |
@@ -518,7 +540,7 @@ Redis capacity and eviction in Redis itself.
 
 - `namespace` is empty or whitespace-only, `ttl_seconds` is `0`, or
   `bypass_rate` is outside `[0.0, 1.0]`.
-- `key_strategy` is not `"exact_request"`.
+- `key_strategy` is neither `"exact_request"` nor `"logical"`.
 - `header_allowlist` names an auth header such as `authorization` or
   `x-api-key`.
 - `in_memory` `max_bytes` is zero or is not an integer.