Merge branch 'main' of github.com:crewAIInc/crewAI into knowledge

.github/workflows/security-checker.yml

@@ -19,5 +19,5 @@ jobs:
         run: pip install bandit
 
       - name: Run Bandit
-        run: bandit -c pyproject.toml -r src/ -lll
+        run: bandit -c pyproject.toml -r src/ -ll
 

docs/concepts/crews.mdx

@@ -22,7 +22,8 @@ A crew in crewAI represents a collaborative group of agents working together to
 | **Max RPM** _(optional)_              | `max_rpm`              | Maximum requests per minute the crew adheres to during execution. Defaults to `None`.                                                                                                                                                                     |
 | **Language** _(optional)_             | `language`             | Language used for the crew, defaults to English.                                                                                                                                                                                                          |
 | **Language File** _(optional)_        | `language_file`        | Path to the language file to be used for the crew.                                                                                                                                                                                                        |
-| **Memory** _(optional)_               | `memory`               | Utilized for storing execution memories (short-term, long-term, entity memory). Defaults to `False`.                                                                                                                                                       |
+| **Memory** _(optional)_               | `memory`               | Utilized for storing execution memories (short-term, long-term, entity memory).                                                                                                                                                                           |
+| **Memory Config** _(optional)_        | `memory_config`        | Configuration for the memory provider to be used by the crew.                                                                                                                                                                                          |
 | **Cache** _(optional)_                | `cache`                | Specifies whether to use a cache for storing the results of tools' execution. Defaults to `True`.                                                                                                                                                          |
 | **Embedder** _(optional)_             | `embedder`             | Configuration for the embedder to be used by the crew. Mostly used by memory for now. Default is `{"provider": "openai"}`.                                                                                                                                                                     |
 | **Full Output** _(optional)_          | `full_output`          | Whether the crew should return the full output with all tasks outputs or just the final output. Defaults to `False`.                                                                                                                                       |

docs/concepts/llms.mdx

@@ -25,7 +25,100 @@ By default, CrewAI uses the `gpt-4o-mini` model. It uses environment variables i
 - `OPENAI_API_BASE`
 - `OPENAI_API_KEY`
 
-### 2. Custom LLM Objects
+### 2. Updating YAML files
+
+You can update the `agents.yml` file to refer to the LLM you want to use:
+
+```yaml Code
+researcher:
+    role: Research Specialist
+    goal: Conduct comprehensive research and analysis to gather relevant information,
+        synthesize findings, and produce well-documented insights.
+    backstory: A dedicated research professional with years of experience in academic
+        investigation, literature review, and data analysis, known for thorough and
+        methodical approaches to complex research questions.
+    verbose: true
+    llm: openai/gpt-4o
+    # llm: azure/gpt-4o-mini
+    # llm: gemini/gemini-pro
+    # llm: anthropic/claude-3-5-sonnet-20240620
+    # llm: bedrock/anthropic.claude-3-sonnet-20240229-v1:0
+    # llm: mistral/mistral-large-latest
+    # llm: ollama/llama3:70b
+    # llm: groq/llama-3.2-90b-vision-preview
+    # llm: watsonx/meta-llama/llama-3-1-70b-instruct
+    # ...
+```
+
+Keep in mind that you will need to set certain ENV vars depending on the model you are
+using to account for the credentials or set a custom LLM object like described below.
+Here are some of the required ENV vars for some of the LLM integrations:
+
+<AccordionGroup>
+    <Accordion title="OpenAI">
+    ```python Code
+    OPENAI_API_KEY=<your-api-key>
+    OPENAI_API_BASE=<optional-custom-base-url>
+    OPENAI_MODEL_NAME=<openai-model-name>
+    OPENAI_ORGANIZATION=<your-org-id>       # OPTIONAL
+    OPENAI_API_BASE=<openaiai-api-base>     # OPTIONAL
+    ```
+    </Accordion>
+
+    <Accordion title="Anthropic">
+    ```python Code
+    ANTHROPIC_API_KEY=<your-api-key>
+    ```
+    </Accordion>
+
+    <Accordion title="Google">
+    ```python Code
+    GEMINI_API_KEY=<your-api-key>
+    ```
+    </Accordion>
+
+    <Accordion title="Azure">
+    ```python Code
+    AZURE_API_KEY=<your-api-key>                    # "my-azure-api-key"
+    AZURE_API_BASE=<your-resource-url>              # "https://example-endpoint.openai.azure.com"
+    AZURE_API_VERSION=<api-version>                 # "2023-05-15"
+    AZURE_AD_TOKEN=<your-azure-ad-token>            # Optional
+    AZURE_API_TYPE=<your-azure-api-type>            # Optional
+    ```
+    </Accordion>
+
+    <Accordion title="AWS Bedrock">
+    ```python Code
+    AWS_ACCESS_KEY_ID=<your-access-key>
+    AWS_SECRET_ACCESS_KEY=<your-secret-key>
+    AWS_DEFAULT_REGION=<your-region>
+    ```
+    </Accordion>
+
+    <Accordion title="Mistral">
+    ```python Code
+    MISTRAL_API_KEY=<your-api-key>
+    ```
+    </Accordion>
+
+    <Accordion title="Groq">
+    ```python Code
+    GROQ_API_KEY=<your-api-key>
+    ```
+    </Accordion>
+
+    <Accordion title="IBM watsonx.ai">
+    ```python Code
+    WATSONX_URL=<your-url>                          # (required) Base URL of your WatsonX instance
+    WATSONX_APIKEY=<your-apikey>                    # (required) IBM cloud API key
+    WATSONX_TOKEN=<your-token>                      # (required) IAM auth token (alternative to APIKEY)
+    WATSONX_PROJECT_ID=<your-project-id>            # (optional) Project ID of your WatsonX instance
+    WATSONX_DEPLOYMENT_SPACE_ID=<your-space-id>     # (optional) ID of deployment space for deployed models
+    ```
+    </Accordion>
+</AccordionGroup>
+
+### 3. Custom LLM Objects
 
 Pass a custom LLM implementation or object from another library.
 
@@ -102,7 +195,7 @@ When configuring an LLM for your agent, you have access to a wide range of param
 
 These are examples of how to configure LLMs for your agent.
 
-<AccordionGroup>    
+<AccordionGroup>
     <Accordion title="OpenAI">
 
     ```python Code
@@ -133,10 +226,10 @@ These are examples of how to configure LLMs for your agent.
         model="cerebras/llama-3.1-70b",
         api_key="your-api-key-here"
     )
-    agent = Agent(llm=llm, ...) 
+    agent = Agent(llm=llm, ...)
     ```
     </Accordion>
- 
+
     <Accordion title="Ollama (Local LLMs)">
 
     CrewAI supports using Ollama for running open-source models locally:
@@ -150,7 +243,7 @@ These are examples of how to configure LLMs for your agent.
 
     agent = Agent(
         llm=LLM(
-            model="ollama/llama3.1", 
+            model="ollama/llama3.1",
             base_url="http://localhost:11434"
         ),
         ...
@@ -164,7 +257,7 @@ These are examples of how to configure LLMs for your agent.
     from crewai import LLM
 
     llm = LLM(
-        model="groq/llama3-8b-8192", 
+        model="groq/llama3-8b-8192",
         api_key="your-api-key-here"
     )
     agent = Agent(llm=llm, ...)
@@ -189,7 +282,7 @@ These are examples of how to configure LLMs for your agent.
     from crewai import LLM
 
     llm = LLM(
-        model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct",  
+        model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct",
         api_key="your-api-key-here"
     )
     agent = Agent(llm=llm, ...)
@@ -224,6 +317,29 @@ These are examples of how to configure LLMs for your agent.
     </Accordion>
 
     <Accordion title="IBM watsonx.ai">
+    You can use IBM Watson by seeting the following ENV vars:
+
+    ```python Code
+    WATSONX_URL=<your-url>
+    WATSONX_APIKEY=<your-apikey>
+    WATSONX_PROJECT_ID=<your-project-id>
+    ```
+
+    You can then define your agents llms by updating the `agents.yml`
+
+    ```yaml Code
+    researcher:
+        role: Research Specialist
+        goal: Conduct comprehensive research and analysis to gather relevant information,
+            synthesize findings, and produce well-documented insights.
+        backstory: A dedicated research professional with years of experience in academic
+            investigation, literature review, and data analysis, known for thorough and
+            methodical approaches to complex research questions.
+        verbose: true
+        llm: watsonx/meta-llama/llama-3-1-70b-instruct
+    ```
+
+    You can also set up agents more dynamically as a base level LLM instance, like bellow:
 
     ```python Code
     from crewai import LLM
@@ -247,7 +363,7 @@ These are examples of how to configure LLMs for your agent.
         api_key="your-api-key-here",
         base_url="your_api_endpoint"
     )
-    agent = Agent(llm=llm, ...) 
+    agent = Agent(llm=llm, ...)
     ```
     </Accordion>
 </AccordionGroup>

docs/concepts/memory.mdx

@@ -18,6 +18,7 @@ reason, and learn from past interactions.
 | **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. |
 | **Entity Memory**    | Captures and organizes information about entities (people, places, concepts) encountered during tasks, facilitating deeper understanding and relationship mapping. Uses `RAG` for storing entity information. |
 | **Contextual Memory**| Maintains the context of interactions by combining `ShortTermMemory`, `LongTermMemory`, and `EntityMemory`, aiding in the coherence and relevance of agent responses over a sequence of tasks or a conversation. |
+| **User Memory**      | Stores user-specific information and preferences, enhancing personalization and user experience. |
 
 ## How Memory Systems Empower Agents
 
@@ -92,6 +93,47 @@ my_crew = Crew(
 )
 ```
 
+## Integrating Mem0 for Enhanced User Memory
+
+[Mem0](https://mem0.ai/) is a self-improving memory layer for LLM applications, enabling personalized AI experiences. 
+
+To include user-specific memory you can get your API key [here](https://app.mem0.ai/dashboard/api-keys) and refer the [docs](https://docs.mem0.ai/platform/quickstart#4-1-create-memories) for adding user preferences.
+
+
+```python Code
+import os
+from crewai import Crew, Process
+from mem0 import MemoryClient
+
+# Set environment variables for Mem0
+os.environ["MEM0_API_KEY"] = "m0-xx"
+
+# Step 1: Record preferences based on past conversation or user input
+client = MemoryClient()
+messages = [
+    {"role": "user", "content": "Hi there! I'm planning a vacation and could use some advice."},
+    {"role": "assistant", "content": "Hello! I'd be happy to help with your vacation planning. What kind of destination do you prefer?"},
+    {"role": "user", "content": "I am more of a beach person than a mountain person."},
+    {"role": "assistant", "content": "That's interesting. Do you like hotels or Airbnb?"},
+    {"role": "user", "content": "I like Airbnb more."},
+]
+client.add(messages, user_id="john")
+
+# Step 2: Create a Crew with User Memory
+
+crew = Crew(
+    agents=[...],
+    tasks=[...],
+    verbose=True,
+    process=Process.sequential,
+    memory=True,
+    memory_config={
+        "provider": "mem0",
+        "config": {"user_id": "john"},
+    },
+)
+```
+
 
 ## Additional Embedding Providers
 

poetry.lock

@@ -1597,12 +1597,12 @@ files = [
 google-auth = ">=2.14.1,<3.0.dev0"
 googleapis-common-protos = ">=1.56.2,<2.0.dev0"
 grpcio = [
-    {version = ">=1.49.1,<2.0dev", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
     {version = ">=1.33.2,<2.0dev", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""},
+    {version = ">=1.49.1,<2.0dev", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
 ]
 grpcio-status = [
-    {version = ">=1.49.1,<2.0.dev0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
     {version = ">=1.33.2,<2.0.dev0", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""},
+    {version = ">=1.49.1,<2.0.dev0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
 ]
 proto-plus = ">=1.22.3,<2.0.0dev"
 protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<6.0.0.dev0"
@@ -4286,8 +4286,8 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
     {version = ">=1.22.4", markers = "python_version < \"3.11\""},
+    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
     {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
 ]
 python-dateutil = ">=2.8.2"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.76.9"
+version = "0.79.4"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<=3.13"
@@ -16,7 +16,7 @@ dependencies = [
     "opentelemetry-exporter-otlp-proto-http>=1.22.0",
     "instructor>=1.3.3",
     "regex>=2024.9.11",
-    "crewai-tools>=0.13.4",
+    "crewai-tools>=0.14.0",
     "click>=8.1.7",
     "python-dotenv>=1.0.0",
     "appdirs>=1.4.4",
@@ -37,7 +37,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools>=0.13.4"]
+tools = ["crewai-tools>=0.14.0"]
 agentops = ["agentops>=0.3.0"]
 fastembed = ["fastembed>=0.4.1"]
 pdfplumber = [
@@ -49,6 +49,7 @@ pandas = [
 openpyxl = [
     "openpyxl>=3.1.5",
 ]
+mem0 = ["mem0ai>=0.1.29"]
 
 [tool.uv]
 dev-dependencies = [
@@ -62,7 +63,7 @@ dev-dependencies = [
     "mkdocs-material-extensions>=1.3.1",
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
-    "crewai-tools>=0.13.4",
+    "crewai-tools>=0.14.0",
     "pytest>=8.0.0",
     "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",

src/crewai/__init__.py

@@ -16,7 +16,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.76.9"
+__version__ = "0.79.4"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/agent.py

@@ -132,6 +132,11 @@ class Agent(BaseAgent):
     @model_validator(mode="after")
     def post_init_setup(self):
         self.agent_ops_agent_name = self.role
+        unnacepted_attributes = [
+            "AWS_ACCESS_KEY_ID",
+            "AWS_SECRET_ACCESS_KEY",
+            "AWS_REGION_NAME",
+        ]
 
         # Handle different cases for self.llm
         if isinstance(self.llm, str):
@@ -155,39 +160,44 @@ class Agent(BaseAgent):
             if api_base:
                 llm_params["base_url"] = api_base
 
+            set_provider = model_name.split("/")[0] if "/" in model_name else "openai"
+
             # Iterate over all environment variables to find matching API keys or use defaults
             for provider, env_vars in ENV_VARS.items():
-                for env_var in env_vars:
+                if provider == set_provider:
-                    # Check if the environment variable is set
+                    for env_var in env_vars:
-                    if "key_name" in env_var:
+                        if env_var["key_name"] in unnacepted_attributes:
-                        env_value = os.environ.get(env_var["key_name"])
+                            continue
-                        if env_value:
+                        # Check if the environment variable is set
-                            # Map key names containing "API_KEY" to "api_key"
+                        if "key_name" in env_var:
-                            key_name = (
+                            env_value = os.environ.get(env_var["key_name"])
-                                "api_key"
+                            if env_value:
-                                if "API_KEY" in env_var["key_name"]
+                                # Map key names containing "API_KEY" to "api_key"
-                                else env_var["key_name"]
+                                key_name = (
-                            )
+                                    "api_key"
-                            # Map key names containing "API_BASE" to "api_base"
+                                    if "API_KEY" in env_var["key_name"]
-                            key_name = (
+                                    else env_var["key_name"]
-                                "api_base"
+                                )
-                                if "API_BASE" in env_var["key_name"]
+                                # Map key names containing "API_BASE" to "api_base"
-                                else key_name
+                                key_name = (
-                            )
+                                    "api_base"
-                            # Map key names containing "API_VERSION" to "api_version"
+                                    if "API_BASE" in env_var["key_name"]
-                            key_name = (
+                                    else key_name
-                                "api_version"
+                                )
-                                if "API_VERSION" in env_var["key_name"]
+                                # Map key names containing "API_VERSION" to "api_version"
-                                else key_name
+                                key_name = (
-                            )
+                                    "api_version"
-                            llm_params[key_name] = env_value
+                                    if "API_VERSION" in env_var["key_name"]
-                    # Check for default values if the environment variable is not set
+                                    else key_name
-                    elif env_var.get("default", False):
+                                )
-                        for key, value in env_var.items():
+                                llm_params[key_name] = env_value
-                            if key not in ["prompt", "key_name", "default"]:
+                        # Check for default values if the environment variable is not set
-                                # Only add default if the key is already set in os.environ
+                        elif env_var.get("default", False):
-                                if key in os.environ:
+                            for key, value in env_var.items():
-                                    llm_params[key] = value
+                                if key not in ["prompt", "key_name", "default"]:
+                                    # Only add default if the key is already set in os.environ
+                                    if key in os.environ:
+                                        llm_params[key] = value
 
             self.llm = LLM(**llm_params)
         else:
@@ -267,9 +277,11 @@ class Agent(BaseAgent):
 
         if self.crew and self.crew.memory:
             contextual_memory = ContextualMemory(
+                self.crew.memory_config,
                 self.crew._short_term_memory,
                 self.crew._long_term_memory,
                 self.crew._entity_memory,
+                self.crew._user_memory,
             )
             memory = contextual_memory.build_context_for_task(task, context)
             if memory.strip() != "":

src/crewai/agents/agent_builder/utilities/base_token_process.py

@@ -4,6 +4,7 @@ from crewai.types.usage_metrics import UsageMetrics
 class TokenProcess:
     total_tokens: int = 0
     prompt_tokens: int = 0
+    cached_prompt_tokens: int = 0
     completion_tokens: int = 0
     successful_requests: int = 0
 
@@ -15,6 +16,9 @@ class TokenProcess:
         self.completion_tokens = self.completion_tokens + tokens
         self.total_tokens = self.total_tokens + tokens
 
+    def sum_cached_prompt_tokens(self, tokens: int):
+        self.cached_prompt_tokens = self.cached_prompt_tokens + tokens
+
     def sum_successful_requests(self, requests: int):
         self.successful_requests = self.successful_requests + requests
 
@@ -22,6 +26,7 @@ class TokenProcess:
         return UsageMetrics(
             total_tokens=self.total_tokens,
             prompt_tokens=self.prompt_tokens,
+            cached_prompt_tokens=self.cached_prompt_tokens,
             completion_tokens=self.completion_tokens,
             successful_requests=self.successful_requests,
         )

src/crewai/agents/crew_agent_executor.py

@@ -145,25 +145,26 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         formatted_answer.result = action_result
                         self._show_logs(formatted_answer)
 
-                        if self.step_callback:
+                    if self.step_callback:
-                            self.step_callback(formatted_answer)
+                        self.step_callback(formatted_answer)
 
-                        if self._should_force_answer():
+                    if self._should_force_answer():
-                            if self.have_forced_answer:
+                        if self.have_forced_answer:
-                                return AgentFinish(
+                            return AgentFinish(
-                                    output=self._i18n.errors(
+                                thought="",
-                                        "force_final_answer_error"
+                                output=self._i18n.errors(
-                                    ).format(formatted_answer.text),
+                                    "force_final_answer_error"
-                                    text=formatted_answer.text,
+                                ).format(formatted_answer.text),
-                                )
+                                text=formatted_answer.text,
-                            else:
+                            )
-                                formatted_answer.text += (
+                        else:
-                                    f'\n{self._i18n.errors("force_final_answer")}'
+                            formatted_answer.text += (
-                                )
+                                f'\n{self._i18n.errors("force_final_answer")}'
-                                self.have_forced_answer = True
+                            )
-                        self.messages.append(
+                            self.have_forced_answer = True
-                            self._format_msg(formatted_answer.text, role="assistant")
+                    self.messages.append(
-                        )
+                        self._format_msg(formatted_answer.text, role="assistant")
+                    )
 
         except OutputParserException as e:
             self.messages.append({"role": "user", "content": e.error})
@@ -332,9 +333,9 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             if self.crew is not None and hasattr(self.crew, "_train_iteration"):
                 train_iteration = self.crew._train_iteration
                 if agent_id in training_data and isinstance(train_iteration, int):
-                    training_data[agent_id][train_iteration][
+                    training_data[agent_id][train_iteration]["improved_output"] = (
-                        "improved_output"
+                        result.output
-                    ] = result.output
+                    )
                     training_handler.save(training_data)
                 else:
                     self._logger.log(
@@ -385,4 +386,5 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         return CrewAgentParser(agent=self.agent).parse(answer)
 
     def _format_msg(self, prompt: str, role: str = "user") -> Dict[str, str]:
+        prompt = prompt.rstrip()
         return {"role": role, "content": prompt}

src/crewai/cli/authentication/main.py

@@ -34,7 +34,9 @@ class AuthenticationCommand:
             "scope": "openid",
             "audience": AUTH0_AUDIENCE,
         }
-        response = requests.post(url=self.DEVICE_CODE_URL, data=device_code_payload)
+        response = requests.post(
+            url=self.DEVICE_CODE_URL, data=device_code_payload, timeout=20
+        )
         response.raise_for_status()
         return response.json()
 
@@ -54,7 +56,7 @@ class AuthenticationCommand:
 
         attempts = 0
         while True and attempts < 5:
-            response = requests.post(self.TOKEN_URL, data=token_payload)
+            response = requests.post(self.TOKEN_URL, data=token_payload, timeout=30)
             token_data = response.json()
 
             if response.status_code == 200:

src/crewai/cli/run_crew.py

@@ -24,7 +24,6 @@ def run_crew() -> None:
             f"Please run `crewai update` to update your pyproject.toml to use uv.",
             fg="red",
         )
-        print()
 
     try:
         subprocess.run(command, capture_output=False, text=True, check=True)

src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.76.9,<1.0.0"
+    "crewai[tools]>=0.79.4,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.76.9,<1.0.0",
+    "crewai[tools]>=0.79.4,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/pipeline/pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = ">=0.76.9,<1.0.0" }
+crewai = { extras = ["tools"], version = ">=0.79.4,<1.0.0" }
 asyncio = "*"
 
 [tool.poetry.scripts]

src/crewai/cli/templates/pipeline_router/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = ["Your Name <you@example.com>"]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.76.9,<1.0.0"
+    "crewai[tools]>=0.79.4,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/tool/pyproject.toml

@@ -5,6 +5,6 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.76.9"
+    "crewai[tools]>=0.79.4"
 ]
 

src/crewai/crew.py

@@ -27,6 +27,7 @@ from crewai.llm import LLM
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
+from crewai.memory.user.user_memory import UserMemory
 from crewai.process import Process
 from crewai.task import Task
 from crewai.tasks.conditional_task import ConditionalTask
@@ -71,6 +72,7 @@ class Crew(BaseModel):
         manager_llm: The language model that will run manager agent.
         manager_agent: Custom agent that will be used as manager.
         memory: Whether the crew should use memory to store memories of it's execution.
+        memory_config: Configuration for the memory to be used for the crew.
         cache: Whether the crew should use a cache to store the results of the tools execution.
         function_calling_llm: The language model that will run the tool calling for all the agents.
         process: The process flow that the crew will follow (e.g., sequential, hierarchical).
@@ -94,6 +96,7 @@ class Crew(BaseModel):
     _short_term_memory: Optional[InstanceOf[ShortTermMemory]] = PrivateAttr()
     _long_term_memory: Optional[InstanceOf[LongTermMemory]] = PrivateAttr()
     _entity_memory: Optional[InstanceOf[EntityMemory]] = PrivateAttr()
+    _user_memory: Optional[InstanceOf[UserMemory]] = PrivateAttr()
     _train: Optional[bool] = PrivateAttr(default=False)
     _train_iteration: Optional[int] = PrivateAttr()
     _inputs: Optional[Dict[str, Any]] = PrivateAttr(default=None)
@@ -114,6 +117,10 @@ class Crew(BaseModel):
         default=False,
         description="Whether the crew should use memory to store memories of it's execution",
     )
+    memory_config: Optional[Dict[str, Any]] = Field(
+        default=None,
+        description="Configuration for the memory to be used for the crew.",
+    )
     short_term_memory: Optional[InstanceOf[ShortTermMemory]] = Field(
         default=None,
         description="An Instance of the ShortTermMemory to be used by the Crew",
@@ -126,7 +133,11 @@ class Crew(BaseModel):
         default=None,
         description="An Instance of the EntityMemory to be used by the Crew",
     )
-    embedder: Optional[Any] = Field(
+    user_memory: Optional[InstanceOf[UserMemory]] = Field(
+        default=None,
+        description="An instance of the UserMemory to be used by the Crew to store/fetch memories of a specific user.",
+    )
+    embedder: Optional[dict] = Field(
         default=None,
         description="Configuration for the embedder to be used for the crew.",
     )
@@ -238,13 +249,22 @@ class Crew(BaseModel):
             self._short_term_memory = (
                 self.short_term_memory
                 if self.short_term_memory
-                else ShortTermMemory(crew=self, embedder_config=self.embedder)
+                else ShortTermMemory(
+                    crew=self,
+                    embedder_config=self.embedder,
+                )
             )
             self._entity_memory = (
                 self.entity_memory
                 if self.entity_memory
                 else EntityMemory(crew=self, embedder_config=self.embedder)
             )
+            if hasattr(self, "memory_config") and self.memory_config is not None:
+                self._user_memory = (
+                    self.user_memory if self.user_memory else UserMemory(crew=self)
+                )
+            else:
+                self._user_memory = None
         return self
 
     @model_validator(mode="after")

src/crewai/llm.py

@@ -118,12 +118,12 @@ class LLM:
 
         litellm.drop_params = True
         litellm.set_verbose = False
-        litellm.callbacks = callbacks
+        self.set_callbacks(callbacks)
 
     def call(self, messages: List[Dict[str, str]], callbacks: List[Any] = []) -> str:
         with suppress_warnings():
             if callbacks and len(callbacks) > 0:
-                litellm.callbacks = callbacks
+                self.set_callbacks(callbacks)
 
             try:
                 params = {
@@ -181,3 +181,15 @@ class LLM:
     def get_context_window_size(self) -> int:
         # Only using 75% of the context window size to avoid cutting the message in the middle
         return int(LLM_CONTEXT_WINDOW_SIZES.get(self.model, 8192) * 0.75)
+
+    def set_callbacks(self, callbacks: List[Any]):
+        callback_types = [type(callback) for callback in callbacks]
+        for callback in litellm.success_callback[:]:
+            if type(callback) in callback_types:
+                litellm.success_callback.remove(callback)
+
+        for callback in litellm._async_success_callback[:]:
+            if type(callback) in callback_types:
+                litellm._async_success_callback.remove(callback)
+
+        litellm.callbacks = callbacks

src/crewai/memory/__init__.py

@@ -1,5 +1,6 @@
 from .entity.entity_memory import EntityMemory
 from .long_term.long_term_memory import LongTermMemory
 from .short_term.short_term_memory import ShortTermMemory
+from .user.user_memory import UserMemory
 
-__all__ = ["EntityMemory", "LongTermMemory", "ShortTermMemory"]
+__all__ = ["UserMemory", "EntityMemory", "LongTermMemory", "ShortTermMemory"]

src/crewai/memory/contextual/contextual_memory.py

@@ -1,13 +1,25 @@
-from typing import Optional
+from typing import Optional, Dict, Any
 
-from crewai.memory import EntityMemory, LongTermMemory, ShortTermMemory
+from crewai.memory import EntityMemory, LongTermMemory, ShortTermMemory, UserMemory
 
 
 class ContextualMemory:
-    def __init__(self, stm: ShortTermMemory, ltm: LongTermMemory, em: EntityMemory):
+    def __init__(
+        self,
+        memory_config: Optional[Dict[str, Any]],
+        stm: ShortTermMemory,
+        ltm: LongTermMemory,
+        em: EntityMemory,
+        um: UserMemory,
+    ):
+        if memory_config is not None:
+            self.memory_provider = memory_config.get("provider")
+        else:
+            self.memory_provider = None
         self.stm = stm
         self.ltm = ltm
         self.em = em
+        self.um = um
 
     def build_context_for_task(self, task, context) -> str:
         """
@@ -23,6 +35,8 @@ class ContextualMemory:
         context.append(self._fetch_ltm_context(task.description))
         context.append(self._fetch_stm_context(query))
         context.append(self._fetch_entity_context(query))
+        if self.memory_provider == "mem0":
+            context.append(self._fetch_user_context(query))
         return "\n".join(filter(None, context))
 
     def _fetch_stm_context(self, query) -> str:
@@ -32,9 +46,11 @@ class ContextualMemory:
         """
         stm_results = self.stm.search(query)
         formatted_results = "\n".join(
-            [f"- {result['context']}" for result in stm_results]
+            [
+                f"- {result['memory'] if self.memory_provider == 'mem0' else result['context']}"
+                for result in stm_results
+            ]
         )
-        print("formatted_results stm", formatted_results)
         return f"Recent Insights:\n{formatted_results}" if stm_results else ""
 
     def _fetch_ltm_context(self, task) -> Optional[str]:
@@ -54,8 +70,6 @@ class ContextualMemory:
         formatted_results = list(dict.fromkeys(formatted_results))
         formatted_results = "\n".join([f"- {result}" for result in formatted_results])  # type: ignore # Incompatible types in assignment (expression has type "str", variable has type "list[str]")
 
-        print("formatted_results ltm", formatted_results)
-
         return f"Historical Data:\n{formatted_results}" if ltm_results else ""
 
     def _fetch_entity_context(self, query) -> str:
@@ -65,7 +79,26 @@ class ContextualMemory:
         """
         em_results = self.em.search(query)
         formatted_results = "\n".join(
-            [f"- {result['context']}" for result in em_results]  # type: ignore #  Invalid index type "str" for "str"; expected type "SupportsIndex | slice"
+            [
+                f"- {result['memory'] if self.memory_provider == 'mem0' else result['context']}"
+                for result in em_results
+            ]  # type: ignore #  Invalid index type "str" for "str"; expected type "SupportsIndex | slice"
         )
-        print("formatted_results em", formatted_results)
         return f"Entities:\n{formatted_results}" if em_results else ""
+
+    def _fetch_user_context(self, query: str) -> str:
+        """
+        Fetches and formats relevant user information from User Memory.
+        Args:
+            query (str): The search query to find relevant user memories.
+        Returns:
+            str: Formatted user memories as bullet points, or an empty string if none found.
+        """
+        user_memories = self.um.search(query)
+        if not user_memories:
+            return ""
+
+        formatted_memories = "\n".join(
+            f"- {result['memory']}" for result in user_memories
+        )
+        return f"User memories/preferences:\n{formatted_memories}"

src/crewai/memory/entity/entity_memory.py

@@ -11,21 +11,43 @@ class EntityMemory(Memory):
     """
 
     def __init__(self, crew=None, embedder_config=None, storage=None):
-        storage = (
+        if hasattr(crew, "memory_config") and crew.memory_config is not None:
-            storage
+            self.memory_provider = crew.memory_config.get("provider")
-            if storage
+        else:
-            else RAGStorage(
+            self.memory_provider = None
-                type="entities",
+
-                allow_reset=True,
+        if self.memory_provider == "mem0":
-                embedder_config=embedder_config,
+            try:
-                crew=crew,
+                from crewai.memory.storage.mem0_storage import Mem0Storage
+            except ImportError:
+                raise ImportError(
+                    "Mem0 is not installed. Please install it with `pip install mem0ai`."
+                )
+            storage = Mem0Storage(type="entities", crew=crew)
+        else:
+            storage = (
+                storage
+                if storage
+                else RAGStorage(
+                    type="entities",
+                    allow_reset=False,
+                    embedder_config=embedder_config,
+                    crew=crew,
+                )
             )
-        )
         super().__init__(storage)
 
     def save(self, item: EntityMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
         """Saves an entity item into the SQLite storage."""
-        data = f"{item.name}({item.type}): {item.description}"
+        if self.memory_provider == "mem0":
+            data = f"""
+            Remember details about the following entity:
+            Name: {item.name}
+            Type: {item.type}
+            Entity Description: {item.description}
+            """
+        else:
+            data = f"{item.name}({item.type}): {item.description}"
         super().save(data, item.metadata)
 
     def reset(self) -> None:

src/crewai/memory/memory.py

@@ -23,5 +23,12 @@ class Memory:
 
         self.storage.save(value, metadata)
 
-    def search(self, query: str) -> List[Dict[str, Any]]:
+    def search(
-        return self.storage.search(query)
+        self,
+        query: str,
+        limit: int = 3,
+        score_threshold: float = 0.35,
+    ) -> List[Any]:
+        return self.storage.search(
+            query=query, limit=limit, score_threshold=score_threshold
+        )

src/crewai/memory/short_term/short_term_memory.py

@@ -14,13 +14,27 @@ class ShortTermMemory(Memory):
     """
 
     def __init__(self, crew=None, embedder_config=None, storage=None):
-        storage = (
+        if hasattr(crew, "memory_config") and crew.memory_config is not None:
-            storage
+            self.memory_provider = crew.memory_config.get("provider")
-            if storage
+        else:
-            else RAGStorage(
+            self.memory_provider = None
-                type="short_term", embedder_config=embedder_config, crew=crew
+
+        if self.memory_provider == "mem0":
+            try:
+                from crewai.memory.storage.mem0_storage import Mem0Storage
+            except ImportError:
+                raise ImportError(
+                    "Mem0 is not installed. Please install it with `pip install mem0ai`."
+                )
+            storage = Mem0Storage(type="short_term", crew=crew)
+        else:
+            storage = (
+                storage
+                if storage
+                else RAGStorage(
+                    type="short_term", embedder_config=embedder_config, crew=crew
+                )
             )
-        )
         super().__init__(storage)
 
     def save(
@@ -30,11 +44,20 @@ class ShortTermMemory(Memory):
         agent: Optional[str] = None,
     ) -> None:
         item = ShortTermMemoryItem(data=value, metadata=metadata, agent=agent)
+        if self.memory_provider == "mem0":
+            item.data = f"Remember the following insights from Agent run: {item.data}"
 
         super().save(value=item.data, metadata=item.metadata, agent=item.agent)
 
-    def search(self, query: str, score_threshold: float = 0.35):
+    def search(
-        return self.storage.search(query=query, score_threshold=score_threshold)  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
+        self,
+        query: str,
+        limit: int = 3,
+        score_threshold: float = 0.35,
+    ):
+        return self.storage.search(
+            query=query, limit=limit, score_threshold=score_threshold
+        )  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
 
     def reset(self) -> None:
         try:

src/crewai/memory/storage/interface.py

@@ -7,8 +7,10 @@ class Storage:
     def save(self, value: Any, metadata: Dict[str, Any]) -> None:
         pass
 
-    def search(self, key: str) -> List[Dict[str, Any]]:  # type: ignore
+    def search(
-        pass
+        self, query: str, limit: int, score_threshold: float
+    ) -> Dict[str, Any] | List[Any]:
+        return {}
 
     def reset(self) -> None:
         pass

src/crewai/memory/storage/kickoff_task_outputs_storage.py

@@ -103,7 +103,7 @@ class KickoffTaskOutputsSQLiteStorage:
                         else value
                     )
 
-                query = f"UPDATE latest_kickoff_task_outputs SET {', '.join(fields)} WHERE task_index = ?"
+                query = f"UPDATE latest_kickoff_task_outputs SET {', '.join(fields)} WHERE task_index = ?"  # nosec
                 values.append(task_index)
 
                 cursor.execute(query, tuple(values))

src/crewai/memory/storage/ltm_sqlite_storage.py

@@ -83,7 +83,7 @@ class LTMSQLiteStorage:
                     WHERE task_description = ?
                     ORDER BY datetime DESC, score ASC
                     LIMIT {latest_n}
-                """,
+                """,  # nosec
                     (task_description,),
                 )
                 rows = cursor.fetchall()

src/crewai/memory/storage/mem0_storage.py

@@ -0,0 +1,104 @@
+import os
+from typing import Any, Dict, List
+
+from mem0 import MemoryClient
+from crewai.memory.storage.interface import Storage
+
+
+class Mem0Storage(Storage):
+    """
+    Extends Storage to handle embedding and searching across entities using Mem0.
+    """
+
+    def __init__(self, type, crew=None):
+        super().__init__()
+
+        if type not in ["user", "short_term", "long_term", "entities"]:
+            raise ValueError("Invalid type for Mem0Storage. Must be 'user' or 'agent'.")
+
+        self.memory_type = type
+        self.crew = crew
+        self.memory_config = crew.memory_config
+
+        # User ID is required for user memory type "user" since it's used as a unique identifier for the user.
+        user_id = self._get_user_id()
+        if type == "user" and not user_id:
+            raise ValueError("User ID is required for user memory type")
+
+        # API key in memory config overrides the environment variable
+        mem0_api_key = self.memory_config.get("config", {}).get("api_key") or os.getenv(
+            "MEM0_API_KEY"
+        )
+        self.memory = MemoryClient(api_key=mem0_api_key)
+
+    def _sanitize_role(self, role: str) -> str:
+        """
+        Sanitizes agent roles to ensure valid directory names.
+        """
+        return role.replace("\n", "").replace(" ", "_").replace("/", "_")
+
+    def save(self, value: Any, metadata: Dict[str, Any]) -> None:
+        user_id = self._get_user_id()
+        agent_name = self._get_agent_name()
+        if self.memory_type == "user":
+            self.memory.add(value, user_id=user_id, metadata={**metadata})
+        elif self.memory_type == "short_term":
+            agent_name = self._get_agent_name()
+            self.memory.add(
+                value, agent_id=agent_name, metadata={"type": "short_term", **metadata}
+            )
+        elif self.memory_type == "long_term":
+            agent_name = self._get_agent_name()
+            self.memory.add(
+                value,
+                agent_id=agent_name,
+                infer=False,
+                metadata={"type": "long_term", **metadata},
+            )
+        elif self.memory_type == "entities":
+            entity_name = None
+            self.memory.add(
+                value, user_id=entity_name, metadata={"type": "entity", **metadata}
+            )
+
+    def search(
+        self,
+        query: str,
+        limit: int = 3,
+        score_threshold: float = 0.35,
+    ) -> List[Any]:
+        params = {"query": query, "limit": limit}
+        if self.memory_type == "user":
+            user_id = self._get_user_id()
+            params["user_id"] = user_id
+        elif self.memory_type == "short_term":
+            agent_name = self._get_agent_name()
+            params["agent_id"] = agent_name
+            params["metadata"] = {"type": "short_term"}
+        elif self.memory_type == "long_term":
+            agent_name = self._get_agent_name()
+            params["agent_id"] = agent_name
+            params["metadata"] = {"type": "long_term"}
+        elif self.memory_type == "entities":
+            agent_name = self._get_agent_name()
+            params["agent_id"] = agent_name
+            params["metadata"] = {"type": "entity"}
+
+        # Discard the filters for now since we create the filters
+        # automatically when the crew is created.
+        results = self.memory.search(**params)
+        return [r for r in results if r["score"] >= score_threshold]
+
+    def _get_user_id(self):
+        if self.memory_type == "user":
+            if hasattr(self, "memory_config") and self.memory_config is not None:
+                return self.memory_config.get("config", {}).get("user_id")
+            else:
+                return None
+        return None
+
+    def _get_agent_name(self):
+        agents = self.crew.agents if self.crew else []
+        agents = [self._sanitize_role(agent.role) for agent in agents]
+        agents = "_".join(agents)
+        return agents

src/crewai/memory/user/user_memory.py

@@ -0,0 +1,45 @@
+from typing import Any, Dict, Optional
+
+from crewai.memory.memory import Memory
+
+
+class UserMemory(Memory):
+    """
+    UserMemory class for handling user memory storage and retrieval.
+    Inherits from the Memory class and utilizes an instance of a class that
+    adheres to the Storage for data storage, specifically working with
+    MemoryItem instances.
+    """
+
+    def __init__(self, crew=None):
+        try:
+            from crewai.memory.storage.mem0_storage import Mem0Storage
+        except ImportError:
+            raise ImportError(
+                "Mem0 is not installed. Please install it with `pip install mem0ai`."
+            )
+        storage = Mem0Storage(type="user", crew=crew)
+        super().__init__(storage)
+
+    def save(
+        self,
+        value,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent: Optional[str] = None,
+    ) -> None:
+        # TODO: Change this function since we want to take care of the case where we save memories for the usr
+        data = f"Remember the details about the user: {value}"
+        super().save(data, metadata)
+
+    def search(
+        self,
+        query: str,
+        limit: int = 3,
+        score_threshold: float = 0.35,
+    ):
+        results = super().search(
+            query=query,
+            limit=limit,
+            score_threshold=score_threshold,
+        )
+        return results

src/crewai/memory/user/user_memory_item.py

@@ -0,0 +1,8 @@
+from typing import Any, Dict, Optional
+
+
+class UserMemoryItem:
+    def __init__(self, data: Any, user: str, metadata: Optional[Dict[str, Any]] = None):
+        self.data = data
+        self.user = user
+        self.metadata = metadata if metadata is not None else {}

src/crewai/types/usage_metrics.py

@@ -8,6 +8,7 @@ class UsageMetrics(BaseModel):
     Attributes:
         total_tokens: Total number of tokens used.
         prompt_tokens: Number of tokens used in prompts.
+        cached_prompt_tokens: Number of cached prompt tokens used.
         completion_tokens: Number of tokens used in completions.
         successful_requests: Number of successful requests made.
     """
@@ -16,6 +17,9 @@ class UsageMetrics(BaseModel):
     prompt_tokens: int = Field(
         default=0, description="Number of tokens used in prompts."
     )
+    cached_prompt_tokens: int = Field(
+        default=0, description="Number of cached prompt tokens used."
+    )
     completion_tokens: int = Field(
         default=0, description="Number of tokens used in completions."
     )
@@ -32,5 +36,6 @@ class UsageMetrics(BaseModel):
         """
         self.total_tokens += usage_metrics.total_tokens
         self.prompt_tokens += usage_metrics.prompt_tokens
+        self.cached_prompt_tokens += usage_metrics.cached_prompt_tokens
         self.completion_tokens += usage_metrics.completion_tokens
         self.successful_requests += usage_metrics.successful_requests

src/crewai/utilities/file_handler.py

@@ -16,7 +16,11 @@ class FileHandler:
 
     def log(self, **kwargs):
         now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-        message = f"{now}: " + ", ".join([f"{key}=\"{value}\"" for key, value in kwargs.items()]) + "\n"
+        message = (
+            f"{now}: "
+            + ", ".join([f'{key}="{value}"' for key, value in kwargs.items()])
+            + "\n"
+        )
         with open(self._path, "a", encoding="utf-8") as file:
             file.write(message + "\n")
 
@@ -63,7 +67,7 @@ class PickleHandler:
 
         with open(self.file_path, "rb") as file:
             try:
-                return pickle.load(file)
+                return pickle.load(file)  # nosec
             except EOFError:
                 return {}  # Return an empty dictionary if the file is empty or corrupted
             except Exception:

src/crewai/utilities/token_counter_callback.py

@@ -1,5 +1,5 @@
 from litellm.integrations.custom_logger import CustomLogger
-
+from litellm.types.utils import Usage
 from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
 
 
@@ -11,8 +11,11 @@ class TokenCalcHandler(CustomLogger):
         if self.token_cost_process is None:
             return
 
+        usage : Usage = response_obj["usage"]
         self.token_cost_process.sum_successful_requests(1)
-        self.token_cost_process.sum_prompt_tokens(response_obj["usage"].prompt_tokens)
+        self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens)
-        self.token_cost_process.sum_completion_tokens(
+        self.token_cost_process.sum_completion_tokens(usage.completion_tokens)
-            response_obj["usage"].completion_tokens
+        if usage.prompt_tokens_details:
-        )
+            self.token_cost_process.sum_cached_prompt_tokens(
+                usage.prompt_tokens_details.cached_tokens
+            )

tests/cassettes/test_crew_kickoff_usage_metrics.yaml

@@ -10,7 +10,8 @@ interactions:
       criteria for your final answer: 1 bullet point about dog that''s under 15 words.\nyou
       MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
       This is VERY important to you, use the tools available and give your best Final
-      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
+      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"], "stream": false}'
     headers:
       accept:
       - application/json
@@ -19,49 +20,50 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '869'
+      - '919'
       content-type:
       - application/json
-      cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.47.0
+      - OpenAI/Python 1.52.1
       x-stainless-arch:
-      - arm64
+      - x64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - Linux
       x-stainless-package-version:
-      - 1.47.0
+      - 1.52.1
       x-stainless-raw-response:
       - 'true'
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.11.9
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-AB7auGDrAVE0iXSBBhySZp3xE8gvP\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1727214164,\n  \"model\": \"gpt-4o-2024-05-13\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA4xSy27bMBC86ysWPEuB7ciV7VuAIkUObQ+59QFhTa0kttQuS9Jx08D/XkhyLAVJ
-      \"assistant\",\n        \"content\": \"I now can give a great answer\\nFinal
+        gV4EaGdnMLPDpwRAmUrtQOkWo+6czW7u41q2t3+cvCvuPvxafSG+58XHTzXlxWeV9gzZ/yAdn1lX
-      Answer: Dogs are unparalleled in loyalty and companionship to humans.\",\n        \"refusal\":
+        WjpnKRrhEdaeMFKvuiyul3m+uV7lA9BJRbanNS5muWSdYZOtFqs8WxTZcnNmt2I0BbWDrwkAwNPw
-      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        7X1yRb/VDhbp86SjELAhtbssASgvtp8oDMGEiBxVOoFaOBIP1u+A5QgaGRrzQIDQ9LYBORzJA3zj
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 175,\n    \"completion_tokens\":
+        W8No4Wb438F7aQKgJ7DyiBb6zMhGOKRA3CJrww10xBEttIQ2toBcgTyQR2vhSNZmezLcXM39eKoP
-      21,\n    \"total_tokens\": 196,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
+        Afub8MHa8/x0CWilcV724Yxf5rVhE9rSEwbhPkyI4tSAnhKA78MhDy9uo5yXzsUyyk/iMHSzHvXU
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
+        1N+Ejo0BqCgR7Yy13aZv6JUVRTQ2zKpQGnVL1USdesNDZWQGJLPUr928pT0mN9z8j/wEaE0uUlU6
+        T5XRLxNPa5765/2vtcuVB8MqPIZIXVkbbsg7b8bHVbuyXm9xs8xXRa2SU/IXAAD//wMAq2ZCBWoD
+        AAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c85f22ddda01cf3-GRU
+      - 8e19bf36db158761-GRU
       Connection:
       - keep-alive
       Content-Encoding:
@@ -69,19 +71,27 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 24 Sep 2024 21:42:44 GMT
+      - Tue, 12 Nov 2024 21:52:04 GMT
       Server:
       - cloudflare
+      Set-Cookie:
+      - __cf_bm=MkvcnvacGpTyn.y0OkFRoFXuAwg4oxjMhViZJTt9mw0-1731448324-1.0.1.1-oekkH_B0xOoPnIFw15LpqFCkZ2cu7VBTJVLDGylan4I67NjX.tlPvOiX9kvtP5Acewi28IE2IwlwtrZWzCH3vw;
+        path=/; expires=Tue, 12-Nov-24 22:22:04 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=4.17346mfw5npZfYNbCx3Vj1VAVPy.tH0Jm2gkTteJ8-1731448324998-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
       - nosniff
       access-control-expose-headers:
       - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
       openai-organization:
-      - crewai-iuxna1
+      - user-tqfegqsiobpvvjmn0giaipdq
       openai-processing-ms:
-      - '349'
+      - '601'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -89,19 +99,20 @@ interactions:
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '30000000'
+      - '200000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '29999792'
+      - '199793'
       x-ratelimit-reset-requests:
-      - 6ms
+      - 8.64s
       x-ratelimit-reset-tokens:
-      - 0s
+      - 62ms
       x-request-id:
-      - req_4c8cd76fdfba7b65e5ce85397b33c22b
+      - req_77fb166b4e272bfd45c37c08d2b93b0c
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "system", "content": "You are cat Researcher. You
       have a lot of experience with cat.\nYour personal goal is: Express hot takes
@@ -113,7 +124,8 @@ interactions:
       criteria for your final answer: 1 bullet point about cat that''s under 15 words.\nyou
       MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
       This is VERY important to you, use the tools available and give your best Final
-      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
+      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"], "stream": false}'
     headers:
       accept:
       - application/json
@@ -122,49 +134,53 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '869'
+      - '919'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
+      - __cf_bm=MkvcnvacGpTyn.y0OkFRoFXuAwg4oxjMhViZJTt9mw0-1731448324-1.0.1.1-oekkH_B0xOoPnIFw15LpqFCkZ2cu7VBTJVLDGylan4I67NjX.tlPvOiX9kvtP5Acewi28IE2IwlwtrZWzCH3vw;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
+        _cfuvid=4.17346mfw5npZfYNbCx3Vj1VAVPy.tH0Jm2gkTteJ8-1731448324998-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.47.0
+      - OpenAI/Python 1.52.1
       x-stainless-arch:
-      - arm64
+      - x64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - Linux
       x-stainless-package-version:
-      - 1.47.0
+      - 1.52.1
       x-stainless-raw-response:
       - 'true'
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.11.9
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-AB7auNbAqjT3rgBX92rhxBLuhaLBj\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1727214164,\n  \"model\": \"gpt-4o-2024-05-13\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA4xSy27bMBC86ysWPFuB7MhN6ltQIGmBnlL00BcEmlxJ21JLhlzFLQL/eyH5IRlt
-      \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        gV4EaGZnMLPLlwxAkVUbUKbVYrrg8rsPsg4P+Orxs9XvPz0U8eP966dS6sdo3wa1GBR++x2NnFRX
-      Answer: Cats are highly independent, agile, and intuitive creatures beloved
+        xnfBoZDnA20iasHBdXlzvSzL2+vVeiQ6b9ENsiZIXvq8I6Z8VazKvLjJl7dHdevJYFIb+JIBALyM
-      by millions worldwide.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+        3yEnW/ypNlAsTkiHKekG1eY8BKCidwOidEqURLOoxUQaz4I8Rn8H7HdgNENDzwgamiE2aE47jABf
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        +Z5YO7gb/zfwRksCHRGGGAHZIg/D1GmXFiBtpGfiBjyDtEgR/I5BMHYJNFvomZ56hIAxedaOhDBd
-      175,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 203,\n    \"completion_tokens_details\":
+        zYNFrPukh+Vw79wR35+bOt+E6LfpyJ/xmphSW0XUyfPQKokPamT3GcC3caP9xZJUiL4LUon/gZzG
-      {\n      \"reasoning_tokens\": 0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
+        I60Pfmo65MSuTqR40W6GF8c7XPpVFkWTS7ObKKNNi3aSTgfUvSU/I7JZ6z/T/M370Jy4+R/7iTAG
+        g6CtQkRL5rLxNBZxeOf/GjtveQys0q8k2FU1cYMxRDq8sjpUxVYXdrkq66XK9tlvAAAA//8DAIjK
+        KzJzAwAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c85f2321c1c1cf3-GRU
+      - 8e19bf3fae118761-GRU
       Connection:
       - keep-alive
       Content-Encoding:
@@ -172,7 +188,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 24 Sep 2024 21:42:45 GMT
+      - Tue, 12 Nov 2024 21:52:05 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -181,10 +197,12 @@ interactions:
       - nosniff
       access-control-expose-headers:
       - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
       openai-organization:
-      - crewai-iuxna1
+      - user-tqfegqsiobpvvjmn0giaipdq
       openai-processing-ms:
-      - '430'
+      - '464'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -192,19 +210,20 @@ interactions:
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '30000000'
+      - '200000'
       x-ratelimit-remaining-requests:
-      - '9999'
+      - '9998'
       x-ratelimit-remaining-tokens:
-      - '29999792'
+      - '199792'
       x-ratelimit-reset-requests:
-      - 6ms
+      - 16.369s
       x-ratelimit-reset-tokens:
-      - 0s
+      - 62ms
       x-request-id:
-      - req_ace859b7d9e83d9fa7753ce23bb03716
+      - req_91706b23d0ef23458ba63ec18304cd28
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "system", "content": "You are apple Researcher.
       You have a lot of experience with apple.\nYour personal goal is: Express hot
@@ -217,7 +236,7 @@ interactions:
       under 15 words.\nyou MUST return the actual complete content as the final answer,
       not a summary.\n\nBegin! This is VERY important to you, use the tools available
       and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
-      "gpt-4o"}'
+      "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
     headers:
       accept:
       - application/json
@@ -226,49 +245,53 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '879'
+      - '929'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
+      - __cf_bm=MkvcnvacGpTyn.y0OkFRoFXuAwg4oxjMhViZJTt9mw0-1731448324-1.0.1.1-oekkH_B0xOoPnIFw15LpqFCkZ2cu7VBTJVLDGylan4I67NjX.tlPvOiX9kvtP5Acewi28IE2IwlwtrZWzCH3vw;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
+        _cfuvid=4.17346mfw5npZfYNbCx3Vj1VAVPy.tH0Jm2gkTteJ8-1731448324998-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.47.0
+      - OpenAI/Python 1.52.1
       x-stainless-arch:
-      - arm64
+      - x64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - MacOS
+      - Linux
       x-stainless-package-version:
-      - 1.47.0
+      - 1.52.1
       x-stainless-raw-response:
       - 'true'
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.11.9
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-AB7avZ0yqY18ukQS7SnLkZydsx72b\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1727214165,\n  \"model\": \"gpt-4o-2024-05-13\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA4xSPW/bMBDd9SsOXLpIgeTITarNS4t26JJubSHQ5IliSh1ZHv0RBP7vhSTHctAU
-      \"assistant\",\n        \"content\": \"I now can give a great answer.\\n\\nFinal
+        6CJQ7909vHd3zxmAsFo0IFQvkxqCKzYPaf1b2/hhW+8PR9N9Kh9W5Zdhjebr4zeRjx1++4gqvXTd
-      Answer: Apples are incredibly versatile, nutritious, and a staple in diets globally.\",\n
+        KD8Eh8l6mmkVUSYcVau726qu729X7ydi8Brd2GZCKmpfDJZssSpXdVHeFdX9ubv3ViGLBr5nAADP
-      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        03f0SRqPooEyf0EGZJYGRXMpAhDRuxERktlykpREvpDKU0KarH8G8gdQksDYPYIEM9oGSXzACPCD
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 175,\n    \"completion_tokens\":
+        PlqSDjbTfwObEBy+Y0Dl+YkTDmApoYkyIUMvoz7IiDmw79L8kqSBMe7HMMAoB4fM7ikHpF6SsmRg
-      25,\n    \"total_tokens\": 200,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
+        xxgBjwGjRVJ4c+00YrdjOU6Lds6d8dMluvMmRL/lM3/BO0uW+zaiZE9jTE4+iIk9ZQA/pxHvXk1N
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
+        hOiHkNrkfyHxtLX1rCeWzS7svEsAkXyS7govq/wNvVZjktbx1ZKEkqpHvbQuG5U7bf0VkV2l/tvN
+        W9pzckvmf+QXQikMCXUbImqrXideyiKOh/+vssuUJ8NiPpO2s2Qwhmjns+tCW25lqatV3VUiO2V/
+        AAAA//8DAPtpFJCEAwAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c85f2369a761cf3-GRU
+      - 8e19bf447ba48761-GRU
       Connection:
       - keep-alive
       Content-Encoding:
@@ -276,7 +299,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 24 Sep 2024 21:42:46 GMT
+      - Tue, 12 Nov 2024 21:52:06 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -285,10 +308,12 @@ interactions:
       - nosniff
       access-control-expose-headers:
       - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
       openai-organization:
-      - crewai-iuxna1
+      - user-tqfegqsiobpvvjmn0giaipdq
       openai-processing-ms:
-      - '389'
+      - '655'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -296,17 +321,18 @@ interactions:
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '30000000'
+      - '200000'
       x-ratelimit-remaining-requests:
-      - '9999'
+      - '9997'
       x-ratelimit-remaining-tokens:
-      - '29999791'
+      - '199791'
       x-ratelimit-reset-requests:
-      - 6ms
+      - 24.239s
       x-ratelimit-reset-tokens:
-      - 0s
+      - 62ms
       x-request-id:
-      - req_0167388f0a7a7f1a1026409834ceb914
+      - req_a228208b0e965ecee334a6947d6c9e7c
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 version: 1

tests/cassettes/test_llm_callback_replacement.yaml

@@ -0,0 +1,205 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "Hello, world!"}], "model": "gpt-4o-mini",
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '101'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xSwWrcMBS8+ytedY6LvWvYZi8lpZSkBJLSQiChGK307FUi66nSc9Ml7L8H2e56
+        l7bQiw8zb8Yzg14yAGG0WINQW8mq8za/+Oqv5MUmXv+8+/Hl3uO3j59u1efreHO+/PAszpKCNo+o
+        +LfqraLOW2RDbqRVQMmYXMvVsqyWy1VVDERHGm2StZ7zivLOOJMvikWVF6u8fDept2QURrGGhwwA
+        4GX4ppxO4y+xhsFrQDqMUbYo1ocjABHIJkTIGE1k6ViczaQix+iG6JdoLb2BS3oGJR1cwSiAHfXA
+        pOXu/bEwYNNHmcK73toJ3x+SWGp9oE2c+APeGGfitg4oI7n018jkxcDuM4DvQ+P+pITwgTrPNdMT
+        umRYlqOdmHeeyfOJY2JpZ3gxjXRqVmtkaWw8GkwoqbaoZ+W8ruy1oSMiO6r8Z5a/eY+1jWv/x34m
+        lELPqGsfUBt12nc+C5ge4b/ODhMPgUXcRcauboxrMfhgxifQ+LrYyEKXi6opRbbPXgEAAP//AwAM
+        DMWoEAMAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e185b2c1b790303-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 12 Nov 2024 17:49:00 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=l.QrRLcNZkML_KSfxjir6YCV35B8GNTitBTNh7cPGc4-1731433740-1.0.1.1-j1ejlmykyoI8yk6i6pQjtPoovGzfxI2f5vG6u0EqodQMjCvhbHfNyN_wmYkeT._BMvFi.zDQ8m_PqEHr8tSdEQ;
+        path=/; expires=Tue, 12-Nov-24 18:19:00 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=jcCDyMK__Fd0V5DMeqt9yXdlKc7Hsw87a1K01pZu9l0-1731433740848-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - user-tqfegqsiobpvvjmn0giaipdq
+      openai-processing-ms:
+      - '322'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '200000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '199978'
+      x-ratelimit-reset-requests:
+      - 8.64s
+      x-ratelimit-reset-tokens:
+      - 6ms
+      x-request-id:
+      - req_037288753767e763a51a04eae757ca84
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "Hello, world from another agent!"}],
+      "model": "gpt-4o-mini", "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '120'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=l.QrRLcNZkML_KSfxjir6YCV35B8GNTitBTNh7cPGc4-1731433740-1.0.1.1-j1ejlmykyoI8yk6i6pQjtPoovGzfxI2f5vG6u0EqodQMjCvhbHfNyN_wmYkeT._BMvFi.zDQ8m_PqEHr8tSdEQ;
+        _cfuvid=jcCDyMK__Fd0V5DMeqt9yXdlKc7Hsw87a1K01pZu9l0-1731433740848-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xSy27bMBC86yu2PFuBZAt14UvRU5MA7aVAEKAIBJpcSUwoLkuu6jiB/z3QI5aM
+        tkAvPMzsDGZ2+ZoACKPFDoRqJKvW2/TLD3+z//oiD8dfL7d339zvW125x9zX90/3mVj1Cto/ouJ3
+        1ZWi1ltkQ26kVUDJ2Lvm201ebDbbIh+IljTaXlZ7TgtKW+NMus7WRZpt0/zTpG7IKIxiBz8TAIDX
+        4e1zOo3PYgfZ6h1pMUZZo9idhwBEINsjQsZoIkvHYjWTihyjG6Jfo7X0Ab4bhcAEipxDxXAw3IB0
+        xA0GkDU6voJrOoCSDm5gNIUjdcCk5fHz0jxg1UXZF3SdtRN+Oqe1VPtA+zjxZ7wyzsSmDCgjuT5Z
+        ZPJiYE8JwMOwle6iqPCBWs8l0xO63jAvRjsx32JBfpxIJpZ2xjfTJi/dSo0sjY2LrQolVYN6Vs4n
+        kJ02tCCSRec/w/zNe+xtXP0/9jOhFHpGXfqA2qjLwvNYwP6n/mvsvOMhsIjHyNiWlXE1Bh/M+E8q
+        X2Z7mel8XVS5SE7JGwAAAP//AwA/cK4yNQMAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e185b31398a0303-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 12 Nov 2024 17:49:02 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - user-tqfegqsiobpvvjmn0giaipdq
+      openai-processing-ms:
+      - '889'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '200000'
+      x-ratelimit-remaining-requests:
+      - '9998'
+      x-ratelimit-remaining-tokens:
+      - '199975'
+      x-ratelimit-reset-requests:
+      - 16.489s
+      x-ratelimit-reset-tokens:
+      - 7ms
+      x-request-id:
+      - req_bde3810b36a4859688e53d1df64bdd20
+    status:
+      code: 200
+      message: OK
+version: 1

tests/crew_test.py

@@ -564,6 +564,7 @@ def test_crew_kickoff_usage_metrics():
         assert result.token_usage.prompt_tokens > 0
         assert result.token_usage.completion_tokens > 0
         assert result.token_usage.successful_requests > 0
+        assert result.token_usage.cached_prompt_tokens == 0
 
 
 def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
@@ -1280,10 +1281,11 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     assert result.raw == "Howdy!"
 
     assert result.token_usage == UsageMetrics(
-        total_tokens=2626,
+        total_tokens=1673,
-        prompt_tokens=2482,
+        prompt_tokens=1562,
-        completion_tokens=144,
+        completion_tokens=111,
-        successful_requests=5,
+        successful_requests=3,
+        cached_prompt_tokens=0
     )
 
 
@@ -1777,26 +1779,22 @@ def test_crew_train_success(
         ]
     )
 
-    crew_training_handler.assert_has_calls(
+    crew_training_handler.assert_any_call("training_data.pkl")
-        [
+    crew_training_handler().load.assert_called()
-            mock.call("training_data.pkl"),
+
-            mock.call().load(),
+    crew_training_handler.assert_any_call("trained_agents_data.pkl")
-            mock.call("trained_agents_data.pkl"),
+    crew_training_handler().load.assert_called()
-            mock.call().save_trained_data(
+
-                agent_id="Researcher",
+    crew_training_handler().save_trained_data.assert_has_calls([
-                trained_data=task_evaluator().evaluate_training_data().model_dump(),
+        mock.call(
-            ),
+            agent_id="Researcher",
-            mock.call("trained_agents_data.pkl"),
+            trained_data=task_evaluator().evaluate_training_data().model_dump(),
-            mock.call().save_trained_data(
+        ),
-                agent_id="Senior Writer",
+        mock.call(
-                trained_data=task_evaluator().evaluate_training_data().model_dump(),
+            agent_id="Senior Writer",
-            ),
+            trained_data=task_evaluator().evaluate_training_data().model_dump(),
-            mock.call(),
+        )
-            mock.call().load(),
+    ])
-            mock.call(),
-            mock.call().load(),
-        ]
-    )
 
 
 def test_crew_train_error():

tests/llm_test.py

@@ -0,0 +1,30 @@
+import pytest
+
+from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
+from crewai.llm import LLM
+from crewai.utilities.token_counter_callback import TokenCalcHandler
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_callback_replacement():
+    llm = LLM(model="gpt-4o-mini")
+
+    calc_handler_1 = TokenCalcHandler(token_cost_process=TokenProcess())
+    calc_handler_2 = TokenCalcHandler(token_cost_process=TokenProcess())
+
+    llm.call(
+        messages=[{"role": "user", "content": "Hello, world!"}],
+        callbacks=[calc_handler_1],
+    )
+    usage_metrics_1 = calc_handler_1.token_cost_process.get_summary()
+
+    llm.call(
+        messages=[{"role": "user", "content": "Hello, world from another agent!"}],
+        callbacks=[calc_handler_2],
+    )
+    usage_metrics_2 = calc_handler_2.token_cost_process.get_summary()
+
+    # The first handler should not have been updated
+    assert usage_metrics_1.successful_requests == 1
+    assert usage_metrics_2.successful_requests == 1
+    assert usage_metrics_1 == calc_handler_1.token_cost_process.get_summary()

tests/memory/cassettes/test_save_and_search_with_provider.yaml

@@ -0,0 +1,270 @@
+interactions:
+- request:
+    body: ''
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      host:
+      - api.mem0.ai
+      user-agent:
+      - python-httpx/0.27.0
+    method: GET
+    uri: https://api.mem0.ai/v1/memories/?user_id=test
+  response:
+    body:
+      string: '[]'
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8b477138bad847b9-BOM
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 17 Aug 2024 06:00:11 GMT
+      NEL:
+      - '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
+      Report-To:
+      - '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v4?s=uuyH2foMJVDpV%2FH52g1q%2FnvXKe3dBKVzvsK0mqmSNezkiszNR9OgrEJfVqmkX%2FlPFRP2sH4zrOuzGo6k%2FjzsjYJczqSWJUZHN2pPujiwnr1E9W%2BdLGKmG6%2FqPrGYAy2SBRWkkJVWsTO3OQ%3D%3D"}],"group":"cf-nel","max_age":604800}'
+      Server:
+      - cloudflare
+      allow:
+      - GET, POST, DELETE, OPTIONS
+      alt-svc:
+      - h3=":443"; ma=86400
+      cross-origin-opener-policy:
+      - same-origin
+      referrer-policy:
+      - same-origin
+      vary:
+      - Accept, origin, Cookie
+      x-content-type-options:
+      - nosniff
+      x-frame-options:
+      - DENY
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"batch": [{"properties": {"python_version": "3.12.4 (v3.12.4:8e8a4baf65,
+      Jun  6 2024, 17:33:18) [Clang 13.0.0 (clang-1300.0.29.30)]", "os": "darwin",
+      "os_version": "Darwin Kernel Version 23.4.0: Wed Feb 21 21:44:54 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6030",
+      "os_release": "23.4.0", "processor": "arm", "machine": "arm64", "function":
+      "mem0.client.main.MemoryClient", "$lib": "posthog-python", "$lib_version": "3.5.0",
+      "$geoip_disable": true}, "timestamp": "2024-08-17T06:00:11.526640+00:00", "context":
+      {}, "distinct_id": "fd411bd3-99a2-42d6-acd7-9fca8ad09580", "event": "client.init"}],
+      "historical_migration": false, "sentAt": "2024-08-17T06:00:11.701621+00:00",
+      "api_key": "phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX"}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '740'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - posthog-python/3.5.0
+    method: POST
+    uri: https://us.i.posthog.com/batch/
+  response:
+    body:
+      string: '{"status":"Ok"}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '15'
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 17 Aug 2024 06:00:12 GMT
+      access-control-allow-credentials:
+      - 'true'
+      server:
+      - envoy
+      vary:
+      - origin, access-control-request-method, access-control-request-headers
+      x-envoy-upstream-service-time:
+      - '69'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "Remember the following insights
+      from Agent run: test value with provider"}], "metadata": {"task": "test_task_provider",
+      "agent": "test_agent_provider"}, "app_id": "Researcher"}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '219'
+      content-type:
+      - application/json
+      host:
+      - api.mem0.ai
+      user-agent:
+      - python-httpx/0.27.0
+    method: POST
+    uri: https://api.mem0.ai/v1/memories/
+  response:
+    body:
+      string: '{"message":"ok"}'
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8b477140282547b9-BOM
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '16'
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 17 Aug 2024 06:00:13 GMT
+      NEL:
+      - '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
+      Report-To:
+      - '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v4?s=FRjJKSk3YxVj03wA7S05H8ts35KnWfqS3wb6Rfy4kVZ4BgXfw7nJbm92wI6vEv5fWcAcHVnOlkJDggs11B01BMuB2k3a9RqlBi0dJNiMuk%2Bgm5xE%2BODMPWJctYNRwQMjNVbteUpS%2Fad8YA%3D%3D"}],"group":"cf-nel","max_age":604800}'
+      Server:
+      - cloudflare
+      allow:
+      - GET, POST, DELETE, OPTIONS
+      alt-svc:
+      - h3=":443"; ma=86400
+      cross-origin-opener-policy:
+      - same-origin
+      referrer-policy:
+      - same-origin
+      vary:
+      - Accept, origin, Cookie
+      x-content-type-options:
+      - nosniff
+      x-frame-options:
+      - DENY
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"query": "test value with provider", "limit": 3, "app_id": "Researcher"}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '73'
+      content-type:
+      - application/json
+      host:
+      - api.mem0.ai
+      user-agent:
+      - python-httpx/0.27.0
+    method: POST
+    uri: https://api.mem0.ai/v1/memories/search/
+  response:
+    body:
+      string: '[]'
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8b47714d083b47b9-BOM
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 17 Aug 2024 06:00:14 GMT
+      NEL:
+      - '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
+      Report-To:
+      - '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v4?s=2DRWL1cdKdMvnE8vx1fPUGeTITOgSGl3N5g84PS6w30GRqpfz79BtSx6REhpnOiFV8kM6KGqln0iCZ5yoHc2jBVVJXhPJhQ5t0uerD9JFnkphjISrJOU1MJjZWneT9PlNABddxvVNCmluA%3D%3D"}],"group":"cf-nel","max_age":604800}'
+      Server:
+      - cloudflare
+      allow:
+      - POST, OPTIONS
+      alt-svc:
+      - h3=":443"; ma=86400
+      cross-origin-opener-policy:
+      - same-origin
+      referrer-policy:
+      - same-origin
+      vary:
+      - Accept, origin, Cookie
+      x-content-type-options:
+      - nosniff
+      x-frame-options:
+      - DENY
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"batch": [{"properties": {"python_version": "3.12.4 (v3.12.4:8e8a4baf65,
+      Jun  6 2024, 17:33:18) [Clang 13.0.0 (clang-1300.0.29.30)]", "os": "darwin",
+      "os_version": "Darwin Kernel Version 23.4.0: Wed Feb 21 21:44:54 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6030",
+      "os_release": "23.4.0", "processor": "arm", "machine": "arm64", "function":
+      "mem0.client.main.MemoryClient", "$lib": "posthog-python", "$lib_version": "3.5.0",
+      "$geoip_disable": true}, "timestamp": "2024-08-17T06:00:13.593952+00:00", "context":
+      {}, "distinct_id": "fd411bd3-99a2-42d6-acd7-9fca8ad09580", "event": "client.add"}],
+      "historical_migration": false, "sentAt": "2024-08-17T06:00:13.858277+00:00",
+      "api_key": "phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX"}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '739'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - posthog-python/3.5.0
+    method: POST
+    uri: https://us.i.posthog.com/batch/
+  response:
+    body:
+      string: '{"status":"Ok"}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '15'
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 17 Aug 2024 06:00:13 GMT
+      access-control-allow-credentials:
+      - 'true'
+      server:
+      - envoy
+      vary:
+      - origin, access-control-request-method, access-control-request-headers
+      x-envoy-upstream-service-time:
+      - '33'
+    status:
+      code: 200
+      message: OK
+version: 1

uv.lock

@@ -604,7 +604,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.76.9"
+version = "0.79.4"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -677,8 +677,8 @@ requires-dist = [
     { name = "auth0-python", specifier = ">=4.7.1" },
     { name = "chromadb", specifier = ">=0.4.24" },
     { name = "click", specifier = ">=8.1.7" },
-    { name = "crewai-tools", specifier = ">=0.13.4" },
+    { name = "crewai-tools", specifier = ">=0.14.0" },
-    { name = "crewai-tools", marker = "extra == 'tools'", specifier = ">=0.13.4" },
+    { name = "crewai-tools", marker = "extra == 'tools'", specifier = ">=0.14.0" },
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
     { name = "json-repair", specifier = ">=0.25.2" },
@@ -704,7 +704,7 @@ requires-dist = [
 [package.metadata.requires-dev]
 dev = [
     { name = "cairosvg", specifier = ">=2.7.1" },
-    { name = "crewai-tools", specifier = ">=0.13.4" },
+    { name = "crewai-tools", specifier = ">=0.14.0" },
     { name = "mkdocs", specifier = ">=1.4.3" },
     { name = "mkdocs-material", specifier = ">=9.5.7" },
     { name = "mkdocs-material-extensions", specifier = ">=1.3.1" },
@@ -723,7 +723,7 @@ dev = [
 
 [[package]]
 name = "crewai-tools"
-version = "0.13.4"
+version = "0.14.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "beautifulsoup4" },
@@ -741,9 +741,9 @@ dependencies = [
     { name = "requests" },
     { name = "selenium" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/64/bd/eff7b633a0b28ff4ed115adde1499e3dcc683e4f0b5c378a4c6f5c0c1bf6/crewai_tools-0.13.4.tar.gz", hash = "sha256:b6ac527633b7018471d892c21ac96bc961a86b6626d996b1ed7d53cd481d4505", size = 816588 }
+sdist = { url = "https://files.pythonhosted.org/packages/9b/6d/4fa91b481b120f83bb58f365203d8aa8564e8ced1035d79f8aedb7d71e2f/crewai_tools-0.14.0.tar.gz", hash = "sha256:510f3a194bcda4fdae4314bd775521964b5f229ddbe451e5d9e0216cae57f4e3", size = 815892 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/6c/40/93cd347d854059cf5e54a81b70f896deea7ad1f03e9c024549eb323c4da5/crewai_tools-0.13.4-py3-none-any.whl", hash = "sha256:eda78fe3c4df57676259d8dd6b2610fa31f89b90909512f15893adb57fb9e825", size = 463703 },
+    { url = "https://files.pythonhosted.org/packages/c8/ed/9f4e64e1507062957b0118085332d38b621c1000874baef2d1c4069bfd97/crewai_tools-0.14.0-py3-none-any.whl", hash = "sha256:0a804a828c29869c3af3253f4fc4c3967a3f80f06dab22e9bbe9526608a31564", size = 462980 },
 ]
 
 [[package]]