docs(api): minor description correction

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 5
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/isaacus%2Fisaacus-46de7b353c33e2b6c139e564caeec9e0462ad714121690f65167a7943e325000.yml
-openapi_spec_hash: 6527287f9709a8741c9cc5b4181d7bb1
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/isaacus%2Fisaacus-c2fccbd5de79f8d02aedb89c4674a7a21988dbb965671d3142196d1f4e98d46e.yml
+openapi_spec_hash: 34ca779f9d68f45b3a0f3be3889994fb
 config_hash: 9040e7359f066240ad536041fb2c5185

src/isaacus/resources/enrichments.py

@@ -71,11 +71,11 @@ def create(
 
           overflow_strategy: The strategy for handling content exceeding the model's maximum input length.
 
-              `auto`, which is the default and recommended setting, currently behaves the same
-              as `chunk`, which intelligently breaks the input up into smaller chunks and then
-              stitches the results back together into a single prediction. In the future
-              `auto` may implement even more sophisticated strategies for handling long
-              contexts such as leveraging chunk overlap and/or a specialized stitching model.
+              `auto`, which is the recommended setting, currently behaves the same as `chunk`,
+              which intelligently breaks the input up into smaller chunks and then stitches
+              the results back together into a single prediction. In the future `auto` may
+              implement even more sophisticated strategies for handling long contexts such as
+              leveraging chunk overlap and/or a specialized stitching model.
 
               `chunk` breaks the input up into smaller chunks that fit within the model's
               context window and then intelligently merges the results into a single
@@ -159,11 +159,11 @@ async def create(
 
           overflow_strategy: The strategy for handling content exceeding the model's maximum input length.
 
-              `auto`, which is the default and recommended setting, currently behaves the same
-              as `chunk`, which intelligently breaks the input up into smaller chunks and then
-              stitches the results back together into a single prediction. In the future
-              `auto` may implement even more sophisticated strategies for handling long
-              contexts such as leveraging chunk overlap and/or a specialized stitching model.
+              `auto`, which is the recommended setting, currently behaves the same as `chunk`,
+              which intelligently breaks the input up into smaller chunks and then stitches
+              the results back together into a single prediction. In the future `auto` may
+              implement even more sophisticated strategies for handling long contexts such as
+              leveraging chunk overlap and/or a specialized stitching model.
 
               `chunk` breaks the input up into smaller chunks that fit within the model's
               context window and then intelligently merges the results into a single

src/isaacus/types/enrichment_create_params.py

@@ -28,11 +28,11 @@ class EnrichmentCreateParams(TypedDict, total=False):
     overflow_strategy: Optional[Literal["auto", "drop_end", "chunk"]]
     """The strategy for handling content exceeding the model's maximum input length.
 
-    `auto`, which is the default and recommended setting, currently behaves the same
-    as `chunk`, which intelligently breaks the input up into smaller chunks and then
-    stitches the results back together into a single prediction. In the future
-    `auto` may implement even more sophisticated strategies for handling long
-    contexts such as leveraging chunk overlap and/or a specialized stitching model.
+    `auto`, which is the recommended setting, currently behaves the same as `chunk`,
+    which intelligently breaks the input up into smaller chunks and then stitches
+    the results back together into a single prediction. In the future `auto` may
+    implement even more sophisticated strategies for handling long contexts such as
+    leveraging chunk overlap and/or a specialized stitching model.
 
     `chunk` breaks the input up into smaller chunks that fit within the model's
     context window and then intelligently merges the results into a single