Merge branch 'main' into feat/reasoning

Author: cpsievert

CHANGELOG.md

@@ -11,11 +11,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### New features
 
-* Added new family of functions (`parallel_chat()`, `parallel_chat_text()`, and `parallel_chat_structured()`) for submitting multiple prompts at once with some basic rate limiting toggles. (#188)
-* `ChatOpenAI()` and `ChatAzureOpenAI()` gain access to latest models, built-in tools, image generation, etc. as a result of moving to the new [Responses API](https://platform.openai.com/docs/api-reference/responses). (#192)
 * `ChatOpenAI()`, `ChatAnthropic()`, and `ChatGoogle()` gain a new `reasoning` parameter to easily opt-into, and fully customize, reasoning capabilities. (#202) 
     * A new `ContentThinking` content type was added and captures the "thinking" portion of a reasoning model. (#192)
-* `ChatAnthropic()` and `ChatBedrockAnthropic()` gain new `cache` parameter to control caching. By default it is set to "5m". This should (on average) reduce the cost of your chats. (#215)
+* Added support for built-in provider tools via a new `ToolBuiltIn` class. This enables provider-specific functionality like OpenAI's image generation to be registered and used as tools. Built-in tools pass raw provider definitions directly to the API rather than wrapping Python functions. (#214)
+* `ChatGoogle()` gains basic support for image generation. (#214)
+* `ChatOpenAI()` and `ChatAzureOpenAI()` gain a new `service_tier` parameter to request a specific service tier (e.g., `"flex"` for slower/cheaper or `"priority"` for faster/more expensive). (#204)
+
+### Changes
+
+* The `Chat.get_cost()` method's `options` parameter was renamed to `include`. (#244)
+
+## [0.14.0] - 2025-12-09
+
+### New features
+
+* `ChatOpenAI()` (and `ChatAzureOpenAI()`) gain access to latest models, built-in tools, etc. as a result of moving to the new [Responses API](https://platform.openai.com/docs/api-reference/responses). (#192)
+* Added new family of functions (`parallel_chat()`, `parallel_chat_text()`, and `parallel_chat_structured()`) for submitting multiple prompts at once with some basic rate limiting toggles. (#188)
 * Added support for systematic evaluation via [Inspect AI](https://inspect.aisi.org.uk/). This includes:
     * A new `.export_eval()` method for exporting conversation history as an Inspect eval dataset sample. This supports multi-turn conversations, tool calls, images, PDFs, and structured data.
     * A new `.to_solver()` method for translating chat instances into Inspect solvers that can be used with Inspect's evaluation framework.
@@ -30,12 +41,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Improvements
 
+* `ChatAnthropic()` and `ChatBedrockAnthropic()` now default to Claude Sonnet 4.5.
+* `ChatGroq()` now defaults to llama-3.1-8b-instant.
+* `Chat.chat()`, `Chat.stream()`, and related methods now automatically complete dangling tool requests when a chat is interrupted during a tool call loop, allowing the conversation to be resumed without causing API errors (#230).
 * `content_pdf_file()` and `content_pdf_url()` now include relevant `filename` information. (#199)
 
 ### Bug fixes
 
 * `.set_model_params()` now works correctly for `.*_async()` methods. (#198)
 * `.chat_structured()` results are now included correctly into the multi-turn conversation history. (#203)
+* `ChatAnthropic()` now drops empty assistant turns to avoid API errors when tools return side-effect only results. (#226)
 
 ## [0.13.2] - 2025-10-02
 

chatlas/__init__.py

@@ -10,8 +10,6 @@
 from ._content import (
     ContentToolRequest,
     ContentToolResult,
-    ContentToolResultImage,
-    ContentToolResultResource,
 )
 from ._content_image import content_image_file, content_image_plot, content_image_url
 from ._content_pdf import content_pdf_file, content_pdf_url
@@ -36,8 +34,8 @@
 from ._provider_portkey import ChatPortkey
 from ._provider_snowflake import ChatSnowflake
 from ._tokens import token_usage
-from ._tools import Tool, ToolRejectError
-from ._turn import Turn
+from ._tools import Tool, ToolBuiltIn, ToolRejectError
+from ._turn import AssistantTurn, SystemTurn, Turn, UserTurn
 
 try:
     from ._version import version as __version__
@@ -81,20 +79,20 @@
     "content_pdf_url",
     "ContentToolRequest",
     "ContentToolResult",
-    "ContentToolResultImage",
-    "ContentToolResultResource",
     "interpolate",
     "interpolate_file",
     "Provider",
     "token_usage",
     "Tool",
+    "ToolBuiltIn",
     "ToolRejectError",
     "Turn",
+    "UserTurn",
+    "SystemTurn",
+    "AssistantTurn",
     "types",
 )
 
 # Rebuild content models to resolve forward references to ToolAnnotation
 ContentToolRequest.model_rebuild()
 ContentToolResult.model_rebuild()
-ContentToolResultImage.model_rebuild()
-ContentToolResultResource.model_rebuild()

chatlas/_batch_job.py

@@ -14,7 +14,7 @@
 from ._chat import Chat
 from ._content import Content
 from ._provider import BatchStatus
-from ._turn import Turn, user_turn
+from ._turn import AssistantTurn, Turn, user_turn
 from ._typing_extensions import TypedDict
 
 BatchStage = Literal["submitting", "waiting", "retrieving", "done"]
@@ -223,7 +223,7 @@ def _retrieve(self) -> bool:
         self._save_state()
         return True
 
-    def result_turns(self) -> list[Turn | None]:
+    def result_turns(self) -> list[AssistantTurn | None]:
         turns = []
         for result in self.results:
             turn = self.provider.batch_result_turn(