PrismResponseCache class
Caches AI responses by prompt hash so repeated calls don't re-bill.
Keyed by SHA-256 of the prompt + model + temperature. Stores the raw response string and an optional expiry.
final cache = PrismResponseCache();
final key = cache.keyFor(prompt, model: 'gpt-4o-mini');
final cached = cache.get(key);
if (cached != null) return cached;
// …otherwise call the AI and store the response
cache.put(key, response);
Constructors
- PrismResponseCache({int maxEntries = 100})
- Creates a response cache.
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- length → int
-
Number of cached entries.
no setter
- maxEntries → int
-
Maximum number of cached responses. Oldest entries are evicted first.
final
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
clear(
) → void - Clears the cache.
-
get(
String key) → String? -
Returns the cached response for
key, or null if expired or absent. -
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
put(
String key, String response, {Duration? ttl}) → void -
Stores
responseunderkey. -
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited