chore: deprecate function_calling_llm field

docs/en/guides/tools/platform-tools-cli.mdx

@@ -1,131 +0,0 @@
----
-title: Platform Tools CLI
-description: Create, publish, and install custom tools on the CrewAI platform using the CLI.
-icon: terminal
-mode: "wide"
----
-
-## Overview
-
-The CrewAI CLI provides commands to manage custom tools on the **CrewAI platform** — a hosted tool registry that lets you share tools within your organization without publishing to PyPI.
-
-| Command | Purpose |
-|---------|---------|
-| `crewai tool create <handle>` | Scaffold a new tool project |
-| `crewai tool publish` | Publish the tool to the CrewAI platform |
-| `crewai tool install <handle>` | Install a platform tool into your crew project |
-
-<Note type="info" title="Platform vs PyPI">
-  These commands manage tools on the **CrewAI platform registry**. If you want to publish a standalone Python package to PyPI instead, see the [Publish Custom Tools to PyPI](/en/guides/tools/publish-custom-tools) guide.
-</Note>
-
-## Prerequisites
-
-- **CrewAI CLI** installed (`pip install crewai`)
-- **Authenticated** with the platform — run `crewai login` first
-
----
-
-## Step 1: Create a Tool Project
-
-Scaffold a new tool project:
-
-```bash
-crewai tool create my_custom_tool
-```
-
-This generates a project structure with the boilerplate you need to start building your tool.
-
-<Tip>
-  The `handle` is the unique identifier for your tool on the platform. Choose something descriptive and specific to what the tool does.
-</Tip>
-
-### Implement Your Tool
-
-Edit the generated tool file to add your logic. The tool follows the standard CrewAI tools contract — you can subclass `BaseTool` or use the `@tool` decorator:
-
-```python
-from crewai.tools import BaseTool
-
-class MyCustomTool(BaseTool):
-    name: str = "My Custom Tool"
-    description: str = "Description of what this tool does — be specific so agents know when to use it."
-
-    def _run(self, argument: str) -> str:
-        # Your tool logic here
-        return "result"
-```
-
-For the full tools API reference (input schemas, caching, async support, error handling), see the [Create Custom Tools](/en/learn/create-custom-tools) guide.
-
----
-
-## Step 2: Publish to the Platform
-
-From your tool project directory, publish it to the CrewAI platform:
-
-```bash
-crewai tool publish
-```
-
-### Options
-
-| Flag | Description |
-|------|-------------|
-| `--force` | Bypass Git remote validations |
-
-Tools are published privately to your organization by default.
-
----
-
-## Step 3: Install a Platform Tool
-
-To install a tool that's been published to the platform:
-
-```bash
-crewai tool install my_custom_tool
-```
-
-Once installed, you can use the tool in your crew like any other tool — assign it to an agent via the `tools` parameter.
-
----
-
-## Full Lifecycle Example
-
-```bash
-# 1. Authenticate with the platform
-crewai login
-
-# 2. Scaffold a new tool
-crewai tool create weather_lookup
-
-# 3. Implement your logic in the generated project
-cd weather_lookup
-# ... edit the tool file ...
-
-# 4. Publish to the platform
-crewai tool publish
-
-# 5. In another project, install and use it
-crewai tool install weather_lookup
-```
-
----
-
-## Platform Tools vs PyPI Packages
-
-| | Platform Tools | PyPI Packages |
-|---|---|---|
-| **Publish** | `crewai tool publish` | `uv build` + `uv publish` |
-| **Registry** | CrewAI platform | PyPI |
-| **Install** | `crewai tool install <handle>` | `pip install <package>` |
-| **Auth** | `crewai login` | PyPI account + token |
-| **Visibility** | Organization-scoped (private) | Always public |
-| **Guide** | This page | [Publish Custom Tools](/en/guides/tools/publish-custom-tools) |
-
----
-
-## Related
-
-- [Create Custom Tools](/en/learn/create-custom-tools) — Python API reference for building tools (BaseTool, @tool decorator)
-- [Publish Custom Tools to PyPI](/en/guides/tools/publish-custom-tools) — package and distribute tools as standalone Python libraries

docs/en/learn/create-custom-tools.mdx

@@ -12,9 +12,7 @@ incorporating the latest functionalities such as tool delegation, error handling
 enabling agents to perform a wide range of actions.
 
 <Tip>
-  **Want to publish your tool to the CrewAI platform?** Use the CLI to scaffold, publish, and share tools directly on the platform — see the [Platform Tools CLI](/en/guides/tools/platform-tools-cli) guide.
-
-  **Prefer publishing to PyPI?** Check out the [Publish Custom Tools](/en/guides/tools/publish-custom-tools) guide to package and distribute your tool as a standalone Python library.
+  **Want to publish your tool for the community?** If you're building a tool that others could benefit from, check out the [Publish Custom Tools](/en/guides/tools/publish-custom-tools) guide to learn how to package and distribute your tool on PyPI.
 </Tip>
 
 ### Subclassing `BaseTool`

lib/crewai/src/crewai/agent/core.py

@@ -220,7 +220,11 @@ class Agent(BaseAgent):
         str | BaseLLM | None,
         BeforeValidator(_validate_llm_ref),
         PlainSerializer(_serialize_llm_ref, return_type=dict | None, when_used="json"),
-    ] = Field(description="Language model that will run the agent.", default=None)
+    ] = Field(
+        description="Language model that will run the agent.",
+        default=None,
+        deprecated="function_calling_llm is deprecated and will be removed in a future release.",
+    )
     system_template: str | None = Field(
         default=None, description="System format for the agent."
     )

lib/crewai/src/crewai/agents/agent_adapters/langgraph/langgraph_adapter.py

@@ -51,7 +51,10 @@ class LangGraphAgentAdapter(BaseAgentAdapter):
     _graph: Any = PrivateAttr(default=None)
     _memory: Any = PrivateAttr(default=None)
     _max_iterations: int = PrivateAttr(default=10)
-    function_calling_llm: Any = Field(default=None)
+    function_calling_llm: Any = Field(
+        default=None,
+        deprecated="function_calling_llm is deprecated and will be removed in a future release.",
+    )
     step_callback: SerializableCallable | None = Field(default=None)
 
     model: str = Field(default="gpt-4o")

lib/crewai/src/crewai/agents/agent_adapters/openai_agents/openai_adapter.py

@@ -60,7 +60,10 @@ class OpenAIAgentAdapter(BaseAgentAdapter):
     _openai_agent: OpenAIAgentProtocol = PrivateAttr()
     _logger: Logger = PrivateAttr(default_factory=Logger)
     _active_thread: str | None = PrivateAttr(default=None)
-    function_calling_llm: Any = Field(default=None)
+    function_calling_llm: Any = Field(
+        default=None,
+        deprecated="function_calling_llm is deprecated and will be removed in a future release.",
+    )
     step_callback: Any = Field(default=None)
     _tool_adapter: OpenAIAgentToolAdapter = PrivateAttr()
     _converter_adapter: OpenAIConverterAdapter = PrivateAttr()

lib/crewai/src/crewai/crew.py

@@ -251,7 +251,11 @@ class Crew(FlowTrackable, BaseModel):
         str | LLM | None,
         BeforeValidator(_validate_llm_ref),
         PlainSerializer(_serialize_llm_ref, return_type=dict | None, when_used="json"),
-    ] = Field(description="Language model that will run the agent.", default=None)
+    ] = Field(
+        description="Language model that will run the agent.",
+        default=None,
+        deprecated="function_calling_llm is deprecated and will be removed in a future release.",
+    )
     config: Json[dict[str, Any]] | dict[str, Any] | None = Field(default=None)
     id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
     share_crew: bool | None = Field(default=False)

lib/crewai/src/crewai/llm.py

@@ -940,6 +940,21 @@ class LLM(BaseLLM):
                 self._track_token_usage_internal(usage_info)
             self._handle_streaming_callbacks(callbacks, usage_info, last_chunk)
 
+            if accumulated_tool_args and not available_functions:
+                tool_calls_list: list[ChatCompletionDeltaToolCall] = [
+                    ChatCompletionDeltaToolCall(
+                        index=idx,
+                        function=Function(
+                            name=tool_arg.function.name,
+                            arguments=tool_arg.function.arguments,
+                        ),
+                    )
+                    for idx, tool_arg in sorted(accumulated_tool_args.items())
+                    if tool_arg.function.name
+                ]
+                if tool_calls_list:
+                    return tool_calls_list
+
             if not tool_calls or not available_functions:
                 if response_model and self.is_litellm:
                     instructor_instance = InternalInstructor(
@@ -1535,8 +1550,7 @@ class LLM(BaseLLM):
             if usage_info:
                 self._track_token_usage_internal(usage_info)
 
-            if accumulated_tool_args and available_functions:
-                # Convert accumulated tool args to ChatCompletionDeltaToolCall objects
+            if accumulated_tool_args:
                 tool_calls_list: list[ChatCompletionDeltaToolCall] = [
                     ChatCompletionDeltaToolCall(
                         index=idx,
@@ -1545,21 +1559,24 @@ class LLM(BaseLLM):
                             arguments=tool_arg.function.arguments,
                         ),
                     )
-                    for idx, tool_arg in accumulated_tool_args.items()
+                    for idx, tool_arg in sorted(accumulated_tool_args.items())
                     if tool_arg.function.name
                 ]
 
                 if tool_calls_list:
-                    result = self._handle_streaming_tool_calls(
-                        tool_calls=tool_calls_list,
-                        accumulated_tool_args=accumulated_tool_args,
-                        available_functions=available_functions,
-                        from_task=from_task,
-                        from_agent=from_agent,
-                        response_id=response_id,
-                    )
-                    if result is not None:
-                        return result
+                    if available_functions:
+                        result = self._handle_streaming_tool_calls(
+                            tool_calls=tool_calls_list,
+                            accumulated_tool_args=accumulated_tool_args,
+                            available_functions=available_functions,
+                            from_task=from_task,
+                            from_agent=from_agent,
+                            response_id=response_id,
+                        )
+                        if result is not None:
+                            return result
+                    else:
+                        return tool_calls_list
 
             usage_dict = self._usage_to_dict(usage_info)
             self._handle_emit_call_events(

lib/crewai/tests/test_llm.py

@@ -624,12 +624,15 @@ def test_handle_streaming_tool_calls_no_available_functions(
         ],
         tools=[get_weather_tool_schema],
     )
-    assert response == ""
+    assert isinstance(response, list)
+    assert len(response) == 1
+    assert response[0].function.name == "get_weather"
+    assert response[0].function.arguments == '{"location":"New York, NY"}'
 
     assert_event_count(
         mock_emit=mock_emit,
         expected_stream_chunk=9,
-        expected_completed_llm_call=1,
+        expected_completed_llm_call=0,
         expected_final_chunk_result='{"location":"New York, NY"}',
     )
 

pyproject.toml

@@ -185,7 +185,7 @@ exclude-newer = "3 days"
 # python-multipart <0.0.27 has GHSA-pp6c-gr5w-3c5g (DoS via unbounded multipart headers).
 # gitpython <3.1.50 has GHSA-mv93-w799-cj2w (config_writer newline injection bypassing the 3.1.49 patch -> RCE via core.hooksPath).
 # urllib3 <2.7.0 has GHSA-qccp-gfcp-xxvc (ProxyManager cross-origin redirect leaks Authorization/Cookie) and GHSA-mf9v-mfxr-j63j (streaming decompression-bomb bypass); force 2.7.0+.
-# langsmith <0.7.31 has GHSA-rr7j-v2q5-chgv (streaming token redaction bypass); force 0.7.31+.
+# langsmith <0.8.0 has GHSA-3644-q5cj-c5c7 (public prompt manifest deserialization, SSRF/secret disclosure); force 0.8.0+.
 # authlib <1.6.11 has GHSA-jj8c-mmj3-mmgv (CSRF bypass in cache-based state storage).
 # litellm 1.83.8+ hard-pins openai==2.24.0, missing openai.types.responses used by crewai;
 # override to >=2.30.0 (the version litellm 1.83.7 used) until upstream relaxes the pin.
@@ -203,7 +203,7 @@ override-dependencies = [
     "uv>=0.11.6,<1",
     "python-multipart>=0.0.27,<1",
     "gitpython>=3.1.50,<4",
-    "langsmith>=0.7.31,<0.8",
+    "langsmith>=0.8.0,<1",
     "authlib>=1.6.11",
 ]
 

uv.lock

@@ -13,7 +13,7 @@ resolution-markers = [
 ]
 
 [options]
-exclude-newer = "2026-05-08T16:33:02.834109Z"
+exclude-newer = "2026-05-12T13:27:48.906744Z"
 exclude-newer-span = "P3D"
 
 [manifest]
@@ -31,7 +31,7 @@ overrides = [
     { name = "gitpython", specifier = ">=3.1.50,<4" },
     { name = "langchain-core", specifier = ">=1.3.3,<2" },
     { name = "langchain-text-splitters", specifier = ">=1.1.2,<2" },
-    { name = "langsmith", specifier = ">=0.7.31,<0.8" },
+    { name = "langsmith", specifier = ">=0.8.0,<1" },
     { name = "onnxruntime", marker = "python_full_version < '3.11'", specifier = "<1.24" },
     { name = "openai", specifier = ">=2.30.0,<3" },
     { name = "pillow", specifier = ">=12.1.1" },
@@ -3888,7 +3888,7 @@ sdist = { url = "https://files.pythonhosted.org/packages/0e/72/a3add0e4eec4eb9e2
 
 [[package]]
 name = "langsmith"
-version = "0.7.32"
+version = "0.8.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "httpx" },
@@ -3901,9 +3901,9 @@ dependencies = [
     { name = "xxhash" },
     { name = "zstandard" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/2f/b4/a0b4a501bee6b8a741ce29f8c48155b132118483cddc6f9247735ddb38fa/langsmith-0.7.32.tar.gz", hash = "sha256:b59b8e106d0e4c4842e158229296086e2aa7c561e3f602acda73d3ad0062e915", size = 1184518, upload-time = "2026-04-15T23:42:41.885Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/de/8a/1e8ea5e8bab2a65fa95bd36229ef38e8723ec46e430e20ca2d953487a7f1/langsmith-0.8.3.tar.gz", hash = "sha256:767ff7a8d136ed42926bf99059ac631dc6883542d6e3104b32e71c7625e1fa05", size = 4460330, upload-time = "2026-05-07T19:56:56.18Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/62/bc/148f98ac7dad73ac5e1b1c985290079cfeeb9ba13d760a24f25002beb2c9/langsmith-0.7.32-py3-none-any.whl", hash = "sha256:e1fde928990c4c52f47dc5132708cec674355d9101723d564183e965f383bf5f", size = 378272, upload-time = "2026-04-15T23:42:39.905Z" },
+    { url = "https://files.pythonhosted.org/packages/98/a9/51e644c1f1dbc3dd7d22dfd6412eab206d538c81e024e4f287373544bdcb/langsmith-0.8.3-py3-none-any.whl", hash = "sha256:b2e40e308222fa0beb2dccee3b4b30bfee9062d7a4f20a3e3e93df3c51a08ab4", size = 399048, upload-time = "2026-05-07T19:56:53.994Z" },
 ]
 
 [[package]]