pydantic-ai-slim 1.0.15__py3-none-any.whl → 1.0.17__py3-none-any.whl

pydantic_ai/models/anthropic.py

@@ -351,7 +351,7 @@ class AnthropicModel(Model):
 
         return ModelResponse(
             parts=items,
-            usage=_map_usage(response),
+            usage=_map_usage(response, self._provider.name, self._provider.base_url, self._model_name),
             model_name=response.model,
             provider_response_id=response.id,
             provider_name=self._provider.name,
@@ -375,6 +375,7 @@ class AnthropicModel(Model):
             _response=peekable_response,
             _timestamp=_utils.now_utc(),
             _provider_name=self._provider.name,
+            _provider_url=self._provider.base_url,
         )
 
     def _get_tools(self, model_request_parameters: ModelRequestParameters) -> list[BetaToolUnionParam]:
@@ -616,7 +617,13 @@ class AnthropicModel(Model):
         }
 
 
-def _map_usage(message: BetaMessage | BetaRawMessageStartEvent | BetaRawMessageDeltaEvent) -> usage.RequestUsage:
+def _map_usage(
+    message: BetaMessage | BetaRawMessageStartEvent | BetaRawMessageDeltaEvent,
+    provider: str,
+    provider_url: str,
+    model: str,
+    existing_usage: usage.RequestUsage | None = None,
+) -> usage.RequestUsage:
     if isinstance(message, BetaMessage):
         response_usage = message.usage
     elif isinstance(message, BetaRawMessageStartEvent):
@@ -626,24 +633,17 @@ def _map_usage(message: BetaMessage | BetaRawMessageStartEvent | BetaRawMessageD
     else:
         assert_never(message)
 
-    # Store all integer-typed usage values in the details, except 'output_tokens' which is represented exactly by
-    # `response_tokens`
-    details: dict[str, int] = {
+    # In streaming, usage appears in different events.
+    # The values are cumulative, meaning new values should replace existing ones entirely.
+    details: dict[str, int] = (existing_usage.details if existing_usage else {}) | {
         key: value for key, value in response_usage.model_dump().items() if isinstance(value, int)
     }
 
-    # Usage coming from the RawMessageDeltaEvent doesn't have input token data, hence using `get`
-    # Tokens are only counted once between input_tokens, cache_creation_input_tokens, and cache_read_input_tokens
-    # This approach maintains request_tokens as the count of all input tokens, with cached counts as details
-    cache_write_tokens = details.get('cache_creation_input_tokens', 0)
-    cache_read_tokens = details.get('cache_read_input_tokens', 0)
-    request_tokens = details.get('input_tokens', 0) + cache_write_tokens + cache_read_tokens
-
-    return usage.RequestUsage(
-        input_tokens=request_tokens,
-        cache_read_tokens=cache_read_tokens,
-        cache_write_tokens=cache_write_tokens,
-        output_tokens=response_usage.output_tokens,
+    return usage.RequestUsage.extract(
+        dict(model=model, usage=details),
+        provider=provider,
+        provider_url=provider_url,
+        provider_fallback='anthropic',
         details=details,
     )
 
@@ -656,13 +656,14 @@ class AnthropicStreamedResponse(StreamedResponse):
     _response: AsyncIterable[BetaRawMessageStreamEvent]
     _timestamp: datetime
     _provider_name: str
+    _provider_url: str
 
     async def _get_event_iterator(self) -> AsyncIterator[ModelResponseStreamEvent]:  # noqa: C901
         current_block: BetaContentBlock | None = None
 
         async for event in self._response:
             if isinstance(event, BetaRawMessageStartEvent):
-                self._usage = _map_usage(event)
+                self._usage = _map_usage(event, self._provider_name, self._provider_url, self._model_name)
                 self.provider_response_id = event.message.id
 
             elif isinstance(event, BetaRawContentBlockStartEvent):
@@ -743,7 +744,7 @@ class AnthropicStreamedResponse(StreamedResponse):
                     pass
 
             elif isinstance(event, BetaRawMessageDeltaEvent):
-                self._usage = _map_usage(event)
+                self._usage = _map_usage(event, self._provider_name, self._provider_url, self._model_name, self._usage)
                 if raw_finish_reason := event.delta.stop_reason:  # pragma: no branch
                     self.provider_details = {'finish_reason': raw_finish_reason}
                     self.finish_reason = _FINISH_REASON_MAP.get(raw_finish_reason)

pydantic_ai/models/openai.py

@@ -776,6 +776,9 @@ class OpenAIChatModel(Model):
                     image_url: ImageURL = {'url': item.url}
                     if metadata := item.vendor_metadata:
                         image_url['detail'] = metadata.get('detail', 'auto')
+                    if item.force_download:
+                        image_content = await download_item(item, data_format='base64_uri', type_format='extension')
+                        image_url['url'] = image_content['data']
                     content.append(ChatCompletionContentPartImageParam(image_url=image_url, type='image_url'))
                 elif isinstance(item, BinaryContent):
                     if self._is_text_like_media_type(item.media_type):
@@ -1529,11 +1532,16 @@ class OpenAIResponsesModel(Model):
                         raise RuntimeError(f'Unsupported binary content type: {item.media_type}')
                 elif isinstance(item, ImageUrl):
                     detail: Literal['auto', 'low', 'high'] = 'auto'
+                    image_url = item.url
                     if metadata := item.vendor_metadata:
                         detail = cast(Literal['auto', 'low', 'high'], metadata.get('detail', 'auto'))
+                    if item.force_download:
+                        downloaded_item = await download_item(item, data_format='base64_uri', type_format='extension')
+                        image_url = downloaded_item['data']
+
                     content.append(
                         responses.ResponseInputImageParam(
-                            image_url=item.url,
+                            image_url=image_url,
                             type='input_image',
                             detail=detail,
                         )

pydantic_ai/result.py

@@ -67,12 +67,12 @@ class AgentStream(Generic[AgentDepsT, OutputDataT]):
                 except ValidationError:
                     pass
         if self._raw_stream_response.final_result_event is not None:  # pragma: no branch
-            yield await self.validate_response_output(self._raw_stream_response.get())
+            yield await self.validate_response_output(self.response)
 
     async def stream_responses(self, *, debounce_by: float | None = 0.1) -> AsyncIterator[_messages.ModelResponse]:
         """Asynchronously stream the (unvalidated) model responses for the agent."""
         # if the message currently has any parts with content, yield before streaming
-        msg = self._raw_stream_response.get()
+        msg = self.response
         for part in msg.parts:
             if part.has_content():
                 yield msg
@@ -80,7 +80,7 @@ class AgentStream(Generic[AgentDepsT, OutputDataT]):
 
         async with _utils.group_by_temporal(self, debounce_by) as group_iter:
             async for _items in group_iter:
-                yield self._raw_stream_response.get()  # current state of the response
+                yield self.response  # current state of the response
 
     async def stream_text(self, *, delta: bool = False, debounce_by: float | None = 0.1) -> AsyncIterator[str]:
         """Stream the text result as an async iterable.
@@ -136,7 +136,7 @@ class AgentStream(Generic[AgentDepsT, OutputDataT]):
         async for _ in self:
             pass
 
-        return await self.validate_response_output(self._raw_stream_response.get())
+        return await self.validate_response_output(self.response)
 
     async def validate_response_output(
         self, message: _messages.ModelResponse, *, allow_partial: bool = False
@@ -201,7 +201,7 @@ class AgentStream(Generic[AgentDepsT, OutputDataT]):
             # yields tuples of (text_content, part_index)
             # we don't currently make use of the part_index, but in principle this may be useful
             # so we retain it here for now to make possible future refactors simpler
-            msg = self._raw_stream_response.get()
+            msg = self.response
             for i, part in enumerate(msg.parts):
                 if isinstance(part, _messages.TextPart) and part.content:
                     yield part.content, i

pydantic_ai/usage.py

@@ -3,8 +3,9 @@ from __future__ import annotations as _annotations
 import dataclasses
 from copy import copy
 from dataclasses import dataclass, fields
-from typing import Annotated
+from typing import Annotated, Any
 
+from genai_prices.data_snapshot import get_snapshot
 from pydantic import AliasChoices, BeforeValidator, Field
 from typing_extensions import deprecated, overload
 
@@ -120,6 +121,39 @@ class RequestUsage(UsageBase):
         new_usage.incr(other)
         return new_usage
 
+    @classmethod
+    def extract(
+        cls,
+        data: Any,
+        *,
+        provider: str,
+        provider_url: str,
+        provider_fallback: str,
+        api_flavor: str | None = None,
+        details: dict[str, Any] | None = None,
+    ) -> RequestUsage:
+        """Extract usage information from the response data using genai-prices.
+
+        Args:
+            data: The response data from the model API.
+            provider: The actual provider ID
+            provider_url: The provider base_url
+            provider_fallback: The fallback provider ID to use if the actual provider is not found in genai-prices.
+                For example, an OpenAI model should set this to "openai" in case it has an obscure provider ID.
+            api_flavor: The API flavor to use when extracting usage information,
+                e.g. 'chat' or 'responses' for OpenAI.
+            details: Becomes the `details` field on the returned `RequestUsage` for convenience.
+        """
+        details = details or {}
+        for provider_id, provider_api_url in [(None, provider_url), (provider, None), (provider_fallback, None)]:
+            try:
+                provider_obj = get_snapshot().find_provider(None, provider_id, provider_api_url)
+                _model_ref, extracted_usage = provider_obj.extract_usage(data, api_flavor=api_flavor)
+                return cls(**{k: v for k, v in extracted_usage.__dict__.items() if v is not None}, details=details)
+            except Exception:
+                pass
+        return cls(details=details)
+
 
 @dataclass(repr=False, kw_only=True)
 class RunUsage(UsageBase):

{pydantic_ai_slim-1.0.15.dist-info → pydantic_ai_slim-1.0.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pydantic-ai-slim
-Version: 1.0.15
+Version: 1.0.17
 Summary: Agent Framework / shim to use Pydantic with LLMs, slim package
 Project-URL: Homepage, https://github.com/pydantic/pydantic-ai/tree/main/pydantic_ai_slim
 Project-URL: Source, https://github.com/pydantic/pydantic-ai/tree/main/pydantic_ai_slim
@@ -29,11 +29,11 @@ Classifier: Topic :: Internet
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Requires-Dist: exceptiongroup; python_version < '3.11'
-Requires-Dist: genai-prices>=0.0.28
+Requires-Dist: genai-prices>=0.0.30
 Requires-Dist: griffe>=1.3.2
 Requires-Dist: httpx>=0.27
 Requires-Dist: opentelemetry-api>=1.28.0
-Requires-Dist: pydantic-graph==1.0.15
+Requires-Dist: pydantic-graph==1.0.17
 Requires-Dist: pydantic>=2.10
 Requires-Dist: typing-inspection>=0.4.0
 Provides-Extra: a2a
@@ -57,7 +57,7 @@ Requires-Dist: dbos>=1.14.0; extra == 'dbos'
 Provides-Extra: duckduckgo
 Requires-Dist: ddgs>=9.0.0; extra == 'duckduckgo'
 Provides-Extra: evals
-Requires-Dist: pydantic-evals==1.0.15; extra == 'evals'
+Requires-Dist: pydantic-evals==1.0.17; extra == 'evals'
 Provides-Extra: google
 Requires-Dist: google-genai>=1.31.0; extra == 'google'
 Provides-Extra: groq

{pydantic_ai_slim-1.0.15.dist-info → pydantic_ai_slim-1.0.17.dist-info}/RECORD

@@ -1,8 +1,8 @@
 pydantic_ai/__init__.py,sha256=IgLTfgpGwbYsT_d_2wSucOfFyIMl1GH6v-yfkNs_zrM,5149
 pydantic_ai/__main__.py,sha256=Q_zJU15DUA01YtlJ2mnaLCoId2YmgmreVEERGuQT-Y0,132
 pydantic_ai/_a2a.py,sha256=3_pl7JW2yHdu31qLgCrdcTZTqXaJNjAwUV6zavah_w8,12159
-pydantic_ai/_agent_graph.py,sha256=ZzUkx9remZgSdgfMPfBhKtb7ZyRuSfQb-QLESWrHGcU,53965
-pydantic_ai/_cli.py,sha256=HxnWPUkEi_pRJZYZ_s25PkV361uAZY6IpN9ub5yMAzg,13994
+pydantic_ai/_agent_graph.py,sha256=D_Oo_LbPqGwkVAaEAcFFERwrg9pVkxeZ45vtTMhES8M,54230
+pydantic_ai/_cli.py,sha256=iZTCFrpJy3aUZ49nJQ5nw2INFw6gPVQd8EhB0rahVcI,14005
 pydantic_ai/_function_schema.py,sha256=UnDGh7Wh5z70pEaRujXF_hKsSibQdN2ywI6lZGz3LUo,11663
 pydantic_ai/_griffe.py,sha256=BphvTL00FHxsSY56GM-bNyCOdwrpL0T3LbDQITWUK_Q,5280
 pydantic_ai/_instrumentation.py,sha256=3XJxRUT0m2K6NfpAb-JKro4Rpw-8weqQ_ydtufeKVrU,2964
@@ -17,34 +17,34 @@ pydantic_ai/_thinking_part.py,sha256=_0DajGyWPa50WUTPWN1UPfZw0xD8_hHcuSt0T3fgRr0
 pydantic_ai/_tool_manager.py,sha256=se5Fikg4HaiTOnxJ4LFrezktZ2Zfv9a2OH0V9PtFE54,10464
 pydantic_ai/_utils.py,sha256=TBzJ03szJPrmDdqRqKTyhRboTsyP6wppnCCprpZFBMw,16620
 pydantic_ai/ag_ui.py,sha256=X3b4P_IraypCE3r-L2ETIo8G951A1MDdP4P5TQ8Fces,32067
-pydantic_ai/builtin_tools.py,sha256=xtRIlEGUJ9UQzxqsKIXs-KD0awHCxBOvXlZ7CLq5oDM,5666
-pydantic_ai/direct.py,sha256=bSYSA5RyxXQMA4gk6CA6meXRbWv2Mn3IeF8vr6viOXI,15061
+pydantic_ai/builtin_tools.py,sha256=O7wcE18kDdp2DFsxPZdoBrmgreDC6DP9t87nM6TxA34,5751
+pydantic_ai/direct.py,sha256=i5yZ9Tx8IiwXg6Nz9CW4-fyXzxnjP59fsklExCh5sjA,15111
 pydantic_ai/exceptions.py,sha256=zsXZMKf2BJuVsfuHl1fWTkogLU37bd4yq7D6BKHAzVs,4968
-pydantic_ai/format_prompt.py,sha256=Enhe3wn-Fo15DcHM0_XgEOLSBWmNpwWYE4M_2vWw_VI,9565
+pydantic_ai/format_prompt.py,sha256=cLyWO8g77Y4JzqVSikqodXaAfTn6i-k206rNhYTiIsE,9710
 pydantic_ai/mcp.py,sha256=7Ouwepk-p2rOq_Rkv-MSZYyEGJ6FfrJvR7ySghuSLwc,36693
-pydantic_ai/messages.py,sha256=Riay2z3WPgx4VQN-MuXzTfrxqCW8aBSP1CHPjGPNtdo,63393
+pydantic_ai/messages.py,sha256=ZtfMXZBl7w5qOyPuzEaXgyRAiyxQbSulG1zG9IHkiuk,64663
 pydantic_ai/output.py,sha256=q91oqvJ-FqV9GbUUil7WVWbii66SVsVZ54AEm_NWSEo,13002
 pydantic_ai/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pydantic_ai/result.py,sha256=vfRe-s01zBtAZ7f_NoibptI3r80XfAq7CBhpJjgHSpo,26790
+pydantic_ai/result.py,sha256=sVabgrAJXmj96I7NM-w0RBz1rH5x_zZql1V6epei4JU,26700
 pydantic_ai/retries.py,sha256=QM4oDA9DG-Y2qP06fbCp8Dqq8ups40Rr4HYjAOlbNyM,14650
 pydantic_ai/run.py,sha256=dV3zIztC-lfOCKecXg_Mcx2CyOfUbxQC0JbZuPvQhTI,16227
 pydantic_ai/settings.py,sha256=0mr6KudxKKjTG8e3nsv_8vDLxNhu_1-WvefCOzCGSYM,3565
 pydantic_ai/tools.py,sha256=dCecmJtRkF1ioqFYbfT00XGGqzGB4PPO9n6IrHCQtnc,20343
-pydantic_ai/usage.py,sha256=mTKKkXGTdEdka4HqER4i2hE7ULF4CiunGbisjgr38Z8,14102
-pydantic_ai/agent/__init__.py,sha256=gmLwyTsyvL89sYvZR83Ba62A8lKLqTfRBk_KYbYYNQo,64116
-pydantic_ai/agent/abstract.py,sha256=PX6r2g0uzbqQdigb5qeTBdfCEbGy6Djb0haKCCmTLrc,52702
-pydantic_ai/agent/wrapper.py,sha256=xZw0spYA5oZkBc6GMcxV4hoQZSr02LbH9GCKqI3MokI,9734
+pydantic_ai/usage.py,sha256=_xXoPIfpENghWcjBvMj0URXQV6YwHWxxZYma4WZ4vUg,15710
+pydantic_ai/agent/__init__.py,sha256=nScl8k_IK20lcajj4ym9u214bb7sqw5Yu00FxP4HgyI,65395
+pydantic_ai/agent/abstract.py,sha256=69kTaR-ZMEmLJ4tD3oGQS5VuomXtNL8t5mxmPz8Ao50,54587
+pydantic_ai/agent/wrapper.py,sha256=ygwfMq24mGe3pGIK-TtPAy3cV7M8VZJW3ulEHvwNTck,10293
 pydantic_ai/common_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pydantic_ai/common_tools/duckduckgo.py,sha256=1ae_o3zqMGrC6KFqAmuqPwJqQgNBTisuvU2jX9KU8PI,2273
 pydantic_ai/common_tools/tavily.py,sha256=a7p2X03l9GS9B_0mvZZV3jePlCwf2TLNeej62-sPycs,2505
 pydantic_ai/durable_exec/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pydantic_ai/durable_exec/dbos/__init__.py,sha256=H_dT0ERuNCBP0Im8eVGl8F9h7E9Aj87-pvmnLpDelF0,199
-pydantic_ai/durable_exec/dbos/_agent.py,sha256=35PMPRSWwfi98e-p1U-3WRJfz-rXqIBbW_qevbvmdXg,37904
+pydantic_ai/durable_exec/dbos/_agent.py,sha256=5yKDlsMVNKzX3Tth-HC-TAwtEhCUbhL4TBpPCcQ-LJ8,40014
 pydantic_ai/durable_exec/dbos/_mcp_server.py,sha256=cLMCKmXQHqhqnn_E3Nf4IsNFIbqk-V7gnIvpmYeDCSA,2989
 pydantic_ai/durable_exec/dbos/_model.py,sha256=_Cxh0zYFF3cungXiSXpGHmjyBQF7KnksfurV7hMKp-E,5106
 pydantic_ai/durable_exec/dbos/_utils.py,sha256=_aNceFvTcNeqb78sTDYM2TdYph85tbdeLueyXY1lbTA,242
 pydantic_ai/durable_exec/temporal/__init__.py,sha256=XKwy68wfgmjr057nolRwGHTKiadxufpQEGEUprAV09k,5563
-pydantic_ai/durable_exec/temporal/_agent.py,sha256=ayNY1QpoVkgYeyQKSU90bNMoZJgWvJCMI_Ou9Ufq7kU,42557
+pydantic_ai/durable_exec/temporal/_agent.py,sha256=BKbKKo6FM2zx-5ohc9voDyMYONH_8sZwUNypjonWDlA,44458
 pydantic_ai/durable_exec/temporal/_function_toolset.py,sha256=3n_A5uHzygsT88LM105kKuYqwxC1sjI4bOzETeUbT4E,5553
 pydantic_ai/durable_exec/temporal/_logfire.py,sha256=ASd7vb0cd61yESI0mgU2w9SCGxsOegz95HtQjKdlQkE,2472
 pydantic_ai/durable_exec/temporal/_mcp_server.py,sha256=vxfWeI7ZtYyXVgX621rPtG-WOZjlKWnqJhcvR9eBgIo,6014
@@ -55,7 +55,7 @@ pydantic_ai/ext/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pydantic_ai/ext/aci.py,sha256=YWYLXzTQJ6hS7qfgNycA8cRl69gogGgThqEU6II7eMA,2527
 pydantic_ai/ext/langchain.py,sha256=kmbbV3Cx2BiNYEJCZMHVYQquUQD-zG2L_bwDangy0Ww,2317
 pydantic_ai/models/__init__.py,sha256=bZXZRrvQa5xEbv6GLvwmcI39vCZG-y6AxUGres1UtBk,35700
-pydantic_ai/models/anthropic.py,sha256=OYFmejUY6W2DOVyLEaslmUBTznuH96PoZ2mOWNZLJ1Y,38220
+pydantic_ai/models/anthropic.py,sha256=-vW7aoPrELKnJzbooCEhMu8__jY6iqvWdFJbIKeQPa8,38087
 pydantic_ai/models/bedrock.py,sha256=fha8zVZgDFYgDqO5nvBkZ2CEv4GV92yq_YnK4qmD73E,33639
 pydantic_ai/models/cohere.py,sha256=_ccK7XBts1OwD-RP8puU3z425SZ4PeJGts1WFhPjikg,14051
 pydantic_ai/models/fallback.py,sha256=fjQz7qRuxEwC6aFYkglBv-2Z39-6kZ931vs6o7PIti8,5016
@@ -67,7 +67,7 @@ pydantic_ai/models/huggingface.py,sha256=711C0ysjLYKriGfSxPiaF6lqjGcNmIaJaCvAXou
 pydantic_ai/models/instrumented.py,sha256=J8eVTutr3UP1r_wd5sM5c0BIdzkRqT-EGgd2NiF0ssQ,22319
 pydantic_ai/models/mcp_sampling.py,sha256=qY4y4nXbRpNp2QbkfjzWLvF_8KLZGXypz4cc0lYRHXU,3553
 pydantic_ai/models/mistral.py,sha256=fi57hADjYxZw8wEpAcNI6mqY32VG9hHK9GGRQ-9vlZg,33905
-pydantic_ai/models/openai.py,sha256=t-H7Na6Ak7FPApcwn86-Rg_IBCvgBrPwBN-gKSnN_Wg,99216
+pydantic_ai/models/openai.py,sha256=_qU8o9PBwmPmELQz3V8OAjxkKy8gXiKtdG6MKQ7Iq_Y,99708
 pydantic_ai/models/test.py,sha256=5ER66nwZG7Iwm-KkzPo4vwNd3rulzgkpgysu4YcT1W4,20568
 pydantic_ai/models/wrapper.py,sha256=nwh8Gea59blbr1JDKlUnkYICuI9TUubC4qP7iZRRW28,2440
 pydantic_ai/profiles/__init__.py,sha256=UHknN-CYsQexUaxfsgz_J_uSZ9QwistLSuAErQkvbcM,3385
@@ -121,8 +121,8 @@ pydantic_ai/toolsets/prefixed.py,sha256=0KwcDkW8OM36ZUsOLVP5h-Nj2tPq78L3_E2c-1Fb
 pydantic_ai/toolsets/prepared.py,sha256=Zjfz6S8In6PBVxoKFN9sKPN984zO6t0awB7Lnq5KODw,1431
 pydantic_ai/toolsets/renamed.py,sha256=JuLHpi-hYPiSPlaTpN8WiXLiGsywYK0axi2lW2Qs75k,1637
 pydantic_ai/toolsets/wrapper.py,sha256=KRzF1p8dncHbva8CE6Ud-IC5E_aygIHlwH5atXK55k4,1673
-pydantic_ai_slim-1.0.15.dist-info/METADATA,sha256=f2l2aq6lWglum9DIPNIXWcaeHlEl6VSjWe9zl_xiZso,4631
-pydantic_ai_slim-1.0.15.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-pydantic_ai_slim-1.0.15.dist-info/entry_points.txt,sha256=kbKxe2VtDCYS06hsI7P3uZGxcVC08-FPt1rxeiMpIps,50
-pydantic_ai_slim-1.0.15.dist-info/licenses/LICENSE,sha256=vA6Jc482lEyBBuGUfD1pYx-cM7jxvLYOxPidZ30t_PQ,1100
-pydantic_ai_slim-1.0.15.dist-info/RECORD,,
+pydantic_ai_slim-1.0.17.dist-info/METADATA,sha256=-4tDOnbyA9ggeA1T1H-uhYRz0Ab9sKbwqMi3DbFUp0U,4631
+pydantic_ai_slim-1.0.17.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+pydantic_ai_slim-1.0.17.dist-info/entry_points.txt,sha256=kbKxe2VtDCYS06hsI7P3uZGxcVC08-FPt1rxeiMpIps,50
+pydantic_ai_slim-1.0.17.dist-info/licenses/LICENSE,sha256=vA6Jc482lEyBBuGUfD1pYx-cM7jxvLYOxPidZ30t_PQ,1100
+pydantic_ai_slim-1.0.17.dist-info/RECORD,,