Merge branch 'main' into devin/1742244238-fix-issue-2395

update doc SpaceNewsKnowledgeSource code snippet (#2275 )
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2026-01-08 07:38:29 +00:00 · 2025-03-20 12:12:44 -04:00 · 2025-03-20 12:06:21 -04:00 · 2025-03-20 08:21:17 -07:00 · 2025-03-20 09:59:17 -04:00 · 2025-03-20 09:48:11 -04:00
13 changed files with 176 additions and 884 deletions
--- a/docs/concepts/knowledge.mdx
+++ b/docs/concepts/knowledge.mdx
@@ -460,12 +460,12 @@ class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
            data = response.json()
            articles = data.get('results', [])

-            formatted_data = self._format_articles(articles)
+            formatted_data = self.validate_content(articles)
            return {self.api_endpoint: formatted_data}
        except Exception as e:
            raise ValueError(f"Failed to fetch space news: {str(e)}")

-    def _format_articles(self, articles: list) -> str:
+    def validate_content(self, articles: list) -> str:
        """Format articles into readable text."""
        formatted = "Space News Articles:\n\n"
        for article in articles:
--- a/docs/concepts/llms.mdx
+++ b/docs/concepts/llms.mdx
@@ -158,7 +158,11 @@ In this section, you'll find detailed examples that help you select, configure,

  <Accordion title="Anthropic">
    ```toml Code
+    # Required
    ANTHROPIC_API_KEY=sk-ant-...
+
+    # Optional
+    ANTHROPIC_API_BASE=<custom-base-url>
    ```

    Example usage in your CrewAI project:
@@ -250,6 +254,40 @@ In this section, you'll find detailed examples that help you select, configure,
        model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
    )
    ```
+
+    Before using Amazon Bedrock, make sure you have boto3 installed in your environment
+
+    [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html) is a managed service that provides access to multiple foundation models from top AI companies through a unified API, enabling secure and responsible AI application development.
+
+    | Model                   | Context Window       | Best For                                                          |
+    |-------------------------|----------------------|-------------------------------------------------------------------|
+    | Amazon Nova Pro         | Up to 300k tokens    | High-performance, model balancing accuracy, speed, and cost-effectiveness across diverse tasks. |
+    | Amazon Nova Micro       | Up to 128k tokens    | High-performance, cost-effective text-only model optimized for lowest latency responses. |
+    | Amazon Nova Lite        | Up to 300k tokens    | High-performance, affordable multimodal processing for images, video, and text with real-time capabilities. |
+    | Claude 3.7 Sonnet       | Up to 128k tokens    | High-performance, best for complex reasoning, coding & AI agents |
+    | Claude 3.5 Sonnet v2    | Up to 200k tokens    | State-of-the-art model specialized in software engineering, agentic capabilities, and computer interaction at optimized cost. |
+    | Claude 3.5 Sonnet       | Up to 200k tokens    | High-performance model delivering superior intelligence and reasoning across diverse tasks with optimal speed-cost balance. |
+    | Claude 3.5 Haiku        | Up to 200k tokens    | Fast, compact multimodal model optimized for quick responses and seamless human-like interactions |
+    | Claude 3 Sonnet         | Up to 200k tokens    | Multimodal model balancing intelligence and speed for high-volume deployments. |
+    | Claude 3 Haiku          | Up to 200k tokens    | Compact, high-speed multimodal model optimized for quick responses and natural conversational interactions |
+    | Claude 3 Opus           | Up to 200k tokens    | Most advanced multimodal model excelling at complex tasks with human-like reasoning and superior contextual understanding. |
+    | Claude 2.1              | Up to 200k tokens    | Enhanced version with expanded context window, improved reliability, and reduced hallucinations for long-form and RAG applications |
+    | Claude                  | Up to 100k tokens    | Versatile model excelling in sophisticated dialogue, creative content, and precise instruction following. |
+    | Claude Instant          | Up to 100k tokens    | Fast, cost-effective model for everyday tasks like dialogue, analysis, summarization, and document Q&A |
+    | Llama 3.1 405B Instruct | Up to 128k tokens    | Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks. |
+    | Llama 3.1 70B Instruct  | Up to 128k tokens    | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
+    | Llama 3.1 8B Instruct   | Up to 128k tokens    | Advanced state-of-the-art model with language understanding, superior reasoning, and text generation. |
+    | Llama 3 70B Instruct    | Up to 8k tokens      | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
+    | Llama 3 8B Instruct     | Up to 8k tokens      | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
+    | Titan Text G1 - Lite    | Up to 4k tokens      | Lightweight, cost-effective model optimized for English tasks and fine-tuning with focus on summarization and content generation. |
+    | Titan Text G1 - Express | Up to 8k tokens      | Versatile model for general language tasks, chat, and RAG applications with support for English and 100+ languages. |
+    | Cohere Command          | Up to 4k tokens      | Model specialized in following user commands and delivering practical enterprise solutions. |
+    | Jurassic-2 Mid          | Up to 8,191 tokens   | Cost-effective model balancing quality and affordability for diverse language tasks like Q&A, summarization, and content generation. |
+    | Jurassic-2 Ultra        | Up to 8,191 tokens   | Model for advanced text generation and comprehension, excelling in complex tasks like analysis and content creation. |
+    | Jamba-Instruct          | Up to 256k tokens    | Model with extended context window optimized for cost-effective text generation, summarization, and Q&A. |
+    | Mistral 7B Instruct     | Up to 32k tokens     | This LLM follows instructions, completes requests, and generates creative text. |
+    | Mistral 8x7B Instruct   | Up to 32k tokens     | An MOE LLM that follows instructions, completes requests, and generates creative text. |
+
  </Accordion>
  
  <Accordion title="Amazon SageMaker">
--- a/docs/concepts/memory.mdx
+++ b/docs/concepts/memory.mdx
@@ -60,7 +60,8 @@ my_crew = Crew(
 ```python Code
 from crewai import Crew, Process
 from crewai.memory import LongTermMemory, ShortTermMemory, EntityMemory
-from crewai.memory.storage import LTMSQLiteStorage, RAGStorage
+from crewai.memory.storage.rag_storage import RAGStorage
+from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
 from typing import List, Optional

 # Assemble your crew with memory capabilities
@@ -119,7 +120,7 @@ Example using environment variables:
 import os
 from crewai import Crew
 from crewai.memory import LongTermMemory
-from crewai.memory.storage import LTMSQLiteStorage
+from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage

 # Configure storage path using environment variable
 storage_path = os.getenv("CREWAI_STORAGE_DIR", "./storage")
@@ -148,7 +149,7 @@ crew = Crew(memory=True)  # Uses default storage locations
 ```python
 from crewai import Crew
 from crewai.memory import LongTermMemory
-from crewai.memory.storage import LTMSQLiteStorage
+from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage

 # Configure custom storage paths
 crew = Crew(
--- a/docs/guides/advanced/customizing-prompts.mdx
+++ b/docs/guides/advanced/customizing-prompts.mdx
@@ -1,4 +1,5 @@
---title: Customizing Prompts
+---
+title: Customizing Prompts
 description: Dive deeper into low-level prompt customization for CrewAI, enabling super custom and complex use cases for different models and languages.
 icon: message-pen
 ---
--- a/src/crewai/crew.py
+++ b/src/crewai/crew.py
@@ -1,5 +1,4 @@
 import asyncio
-import concurrent.futures
 import json
 import re
 import uuid
@@ -7,7 +6,7 @@ import warnings
 from concurrent.futures import Future
 from copy import copy as shallow_copy
 from hashlib import md5
-from typing import Any, Callable, Dict, List, Optional, Sequence, Set, Tuple, Union
+from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union

 from pydantic import (
    UUID4,
@@ -708,65 +707,6 @@ class Crew(BaseModel):
        self.usage_metrics = total_usage_metrics
        self._task_output_handler.reset()
        return results
-        
-    def kickoff_for_each_parallel(self, inputs: Sequence[Dict[str, Any]], max_workers: Optional[int] = None) -> List[CrewOutput]:
-        """Executes the Crew's workflow for each input in the list in parallel using ThreadPoolExecutor.
-        
-        Args:
-            inputs: Sequence of input dictionaries to be passed to each crew execution.
-            max_workers: Maximum number of worker threads to use. If None, uses the default
-                        ThreadPoolExecutor behavior (typically min(32, os.cpu_count() + 4)).
-        
-        Returns:
-            List of CrewOutput objects, one for each input.
-        """
-        from concurrent.futures import ThreadPoolExecutor, as_completed
-        
-        if not isinstance(inputs, (list, tuple)):
-            raise TypeError(f"Inputs must be a list of dictionaries. Received {type(inputs).__name__} instead.")
-        
-        if not inputs:
-            return []
-        
-        results: List[CrewOutput] = []
-        
-        # Initialize the parent crew's usage metrics
-        total_usage_metrics = UsageMetrics()
-        
-        # Create a copy of the crew for each input to avoid state conflicts
-        crew_copies = [self.copy() for _ in inputs]
-        
-        # Execute each crew in parallel
-        try:
-            with ThreadPoolExecutor(max_workers=max_workers) as executor:
-                # Submit all tasks to the executor
-                future_to_crew = {
-                    executor.submit(crew_copies[i].kickoff, inputs[i]): i 
-                    for i in range(len(inputs))
-                }
-                
-                # Process results as they complete
-                for future in as_completed(future_to_crew):
-                    crew_index = future_to_crew[future]
-                    try:
-                        output = future.result()
-                        results.append(output)
-                        
-                        # Aggregate usage metrics
-                        if crew_copies[crew_index].usage_metrics:
-                            total_usage_metrics.add_usage_metrics(crew_copies[crew_index].usage_metrics)
-                    except Exception as exc:
-                        # Re-raise the exception to maintain consistent behavior with kickoff_for_each
-                        raise exc
-        finally:
-            # Clean up to assist garbage collection
-            crew_copies.clear()
-        
-        # Set the aggregated metrics on the parent crew
-        self.usage_metrics = total_usage_metrics
-        self._task_output_handler.reset()
-        
-        return results

    def _handle_crew_planning(self):
        """Handles the Crew planning."""
--- a/src/crewai/task.py
+++ b/src/crewai/task.py
@@ -19,6 +19,8 @@ from typing import (
    Tuple,
    Type,
    Union,
+    get_args,
+    get_origin,
 )

 from pydantic import (
@@ -178,15 +180,29 @@ class Task(BaseModel):
        """
        if v is not None:
            sig = inspect.signature(v)
-            if len(sig.parameters) != 1:
+            positional_args = [
+                param
+                for param in sig.parameters.values()
+                if param.default is inspect.Parameter.empty
+            ]
+            if len(positional_args) != 1:
                raise ValueError("Guardrail function must accept exactly one parameter")

            # Check return annotation if present, but don't require it
            return_annotation = sig.return_annotation
            if return_annotation != inspect.Signature.empty:
+
+                return_annotation_args = get_args(return_annotation)
                if not (
-                    return_annotation == Tuple[bool, Any]
-                    or str(return_annotation) == "Tuple[bool, Any]"
+                    get_origin(return_annotation) is tuple
+                    and len(return_annotation_args) == 2
+                    and return_annotation_args[0] is bool
+                    and (
+                        return_annotation_args[1] is Any
+                        or return_annotation_args[1] is str
+                        or return_annotation_args[1] is TaskOutput
+                        or return_annotation_args[1] == Union[str, TaskOutput]
+                    )
                ):
                    raise ValueError(
                        "If return type is annotated, it must be Tuple[bool, Any]"
--- a/src/crewai/utilities/events/crewai_event_bus.py
+++ b/src/crewai/utilities/events/crewai_event_bus.py
@@ -67,15 +67,12 @@ class CrewAIEventsBus:
            source: The object emitting the event
            event: The event instance to emit
        """
-        event_type = type(event)
-        if event_type in self._handlers:
-            for handler in self._handlers[event_type]:
-                handler(source, event)
-        self._signal.send(source, event=event)
+        for event_type, handlers in self._handlers.items():
+            if isinstance(event, event_type):
+                for handler in handlers:
+                    handler(source, event)

-    def clear_handlers(self) -> None:
-        """Clear all registered event handlers - useful for testing"""
-        self._handlers.clear()
+        self._signal.send(source, event=event)

    def register_handler(
        self, event_type: Type[EventTypes], handler: Callable[[Any, EventTypes], None]
--- a/tests/cassettes/test_kickoff_for_each_parallel_max_workers.yaml
+++ b/tests/cassettes/test_kickoff_for_each_parallel_max_workers.yaml
@@ -1,254 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "system", "content": "You are dog Researcher. You
-      have a lot of experience with dog.\nYour personal goal is: Express hot takes
-      on dog.\nTo give my best complete final answer to the task respond using the
-      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
-      Your final answer must be the great and the most complete as possible, it must
-      be outcome described.\n\nI MUST use these formats, my job depends on it!"},
-      {"role": "user", "content": "\nCurrent Task: Give me an analysis around dog.\n\nThis
-      is the expected 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-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '914'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
-        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
-      sk-proj-********************************************************************************************************************************************************sLcA.
-      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
-      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
-      \"invalid_api_key\"\n    }\n}\n"
-    headers:
-      CF-RAY:
-      - 922e88ad5d8d2805-SEA
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '414'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Wed, 19 Mar 2025 17:01:49 GMT
-      Server:
-      - cloudflare
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      vary:
-      - Origin
-      x-request-id:
-      - req_9f1aa8c42b31f8139e80f67a71b11af3
-    http_version: HTTP/1.1
-    status_code: 401
- request:
-    body: '{"messages": [{"role": "system", "content": "You are apple Researcher.
-      You have a lot of experience with apple.\nYour personal goal is: Express hot
-      takes on apple.\nTo give my best complete final answer to the task respond using
-      the exact following format:\n\nThought: I now can give a great answer\nFinal
-      Answer: Your final answer must be the great and the most complete as possible,
-      it must be outcome described.\n\nI MUST use these formats, my job depends on
-      it!"}, {"role": "user", "content": "\nCurrent Task: Give me an analysis around
-      apple.\n\nThis is the expected criteria for your final answer: 1 bullet point
-      about apple 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-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '924'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
-        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
-      sk-proj-********************************************************************************************************************************************************sLcA.
-      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
-      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
-      \"invalid_api_key\"\n    }\n}\n"
-    headers:
-      CF-RAY:
-      - 922e88adcdfe2805-SEA
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '414'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Wed, 19 Mar 2025 17:01:49 GMT
-      Server:
-      - cloudflare
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      vary:
-      - Origin
-      x-request-id:
-      - req_2a94d77754a61f5f38f74f0648bf38af
-    http_version: HTTP/1.1
-    status_code: 401
- 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
-      on cat.\nTo give my best complete final answer to the task respond using the
-      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
-      Your final answer must be the great and the most complete as possible, it must
-      be outcome described.\n\nI MUST use these formats, my job depends on it!"},
-      {"role": "user", "content": "\nCurrent Task: Give me an analysis around cat.\n\nThis
-      is the expected 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-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '914'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
-        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
-      sk-proj-********************************************************************************************************************************************************sLcA.
-      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
-      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
-      \"invalid_api_key\"\n    }\n}\n"
-    headers:
-      CF-RAY:
-      - 922e88adabe3f8d9-SEA
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '414'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Wed, 19 Mar 2025 17:01:49 GMT
-      Server:
-      - cloudflare
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      vary:
-      - Origin
-      x-request-id:
-      - req_e06cdb71cffc47ee28b267ed083c3a6b
-    http_version: HTTP/1.1
-    status_code: 401
-version: 1
--- a/tests/cassettes/test_kickoff_for_each_parallel_multiple_inputs.yaml
+++ b/tests/cassettes/test_kickoff_for_each_parallel_multiple_inputs.yaml
@@ -1,254 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "system", "content": "You are dog Researcher. You
-      have a lot of experience with dog.\nYour personal goal is: Express hot takes
-      on dog.\nTo give my best complete final answer to the task respond using the
-      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
-      Your final answer must be the great and the most complete as possible, it must
-      be outcome described.\n\nI MUST use these formats, my job depends on it!"},
-      {"role": "user", "content": "\nCurrent Task: Give me an analysis around dog.\n\nThis
-      is the expected 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-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '914'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
-        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
-      sk-proj-********************************************************************************************************************************************************sLcA.
-      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
-      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
-      \"invalid_api_key\"\n    }\n}\n"
-    headers:
-      CF-RAY:
-      - 922e88a8e9432805-SEA
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '414'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Wed, 19 Mar 2025 17:01:48 GMT
-      Server:
-      - cloudflare
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      vary:
-      - Origin
-      x-request-id:
-      - req_d00f966d049ee99fde6e9e7bf652afa2
-    http_version: HTTP/1.1
-    status_code: 401
- request:
-    body: '{"messages": [{"role": "system", "content": "You are apple Researcher.
-      You have a lot of experience with apple.\nYour personal goal is: Express hot
-      takes on apple.\nTo give my best complete final answer to the task respond using
-      the exact following format:\n\nThought: I now can give a great answer\nFinal
-      Answer: Your final answer must be the great and the most complete as possible,
-      it must be outcome described.\n\nI MUST use these formats, my job depends on
-      it!"}, {"role": "user", "content": "\nCurrent Task: Give me an analysis around
-      apple.\n\nThis is the expected criteria for your final answer: 1 bullet point
-      about apple 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-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '924'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
-        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
-      sk-proj-********************************************************************************************************************************************************sLcA.
-      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
-      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
-      \"invalid_api_key\"\n    }\n}\n"
-    headers:
-      CF-RAY:
-      - 922e88a91a59c4c8-SEA
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '414'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Wed, 19 Mar 2025 17:01:48 GMT
-      Server:
-      - cloudflare
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      vary:
-      - Origin
-      x-request-id:
-      - req_6e9a5fd1d83c6eac8070b4e9b9b94f10
-    http_version: HTTP/1.1
-    status_code: 401
- 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
-      on cat.\nTo give my best complete final answer to the task respond using the
-      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
-      Your final answer must be the great and the most complete as possible, it must
-      be outcome described.\n\nI MUST use these formats, my job depends on it!"},
-      {"role": "user", "content": "\nCurrent Task: Give me an analysis around cat.\n\nThis
-      is the expected 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-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '914'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
-        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
-      sk-proj-********************************************************************************************************************************************************sLcA.
-      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
-      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
-      \"invalid_api_key\"\n    }\n}\n"
-    headers:
-      CF-RAY:
-      - 922e88a91f2ef8d9-SEA
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '414'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Wed, 19 Mar 2025 17:01:48 GMT
-      Server:
-      - cloudflare
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      vary:
-      - Origin
-      x-request-id:
-      - req_d0ddaee2449c771a230de2b6362c8d99
-    http_version: HTTP/1.1
-    status_code: 401
-version: 1
--- a/tests/cassettes/test_kickoff_for_each_parallel_single_input.yaml
+++ b/tests/cassettes/test_kickoff_for_each_parallel_single_input.yaml
@@ -1,89 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "system", "content": "You are dog Researcher. You
-      have a lot of experience with dog.\nYour personal goal is: Express hot takes
-      on dog.\nTo give my best complete final answer to the task respond using the
-      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
-      Your final answer must be the great and the most complete as possible, it must
-      be outcome described.\n\nI MUST use these formats, my job depends on it!"},
-      {"role": "user", "content": "\nCurrent Task: Give me an analysis around dog.\n\nThis
-      is the expected 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-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '914'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
-      sk-proj-********************************************************************************************************************************************************sLcA.
-      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
-      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
-      \"invalid_api_key\"\n    }\n}\n"
-    headers:
-      CF-RAY:
-      - 922e88a1b9ef2805-SEA
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '414'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Wed, 19 Mar 2025 17:01:47 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
-        path=/; expires=Wed, 19-Mar-25 17:31:47 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      vary:
-      - Origin
-      x-request-id:
-      - req_5980db57b01be333b0f977bb03a15bca
-    http_version: HTTP/1.1
-    status_code: 401
-version: 1
--- a/tests/task_test.py
+++ b/tests/task_test.py
@@ -3,6 +3,8 @@
 import hashlib
 import json
 import os
+from functools import partial
+from typing import Tuple, Union
 from unittest.mock import MagicMock, patch

 import pytest
@@ -215,6 +217,75 @@ def test_multiple_output_type_error():
        )


+def test_guardrail_type_error():
+    desc = "Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting."
+    expected_output = "Bullet point list of 5 interesting ideas."
+    # Lambda function
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=lambda x: (True, x),
+    )
+
+    # Function
+    def guardrail_fn(x: TaskOutput) -> tuple[bool, TaskOutput]:
+        return (True, x)
+
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=guardrail_fn,
+    )
+
+    class Object:
+        def guardrail_fn(self, x: TaskOutput) -> tuple[bool, TaskOutput]:
+            return (True, x)
+
+        @classmethod
+        def guardrail_class_fn(cls, x: TaskOutput) -> tuple[bool, str]:
+            return (True, x)
+
+        @staticmethod
+        def guardrail_static_fn(x: TaskOutput) -> tuple[bool, Union[str, TaskOutput]]:
+            return (True, x)
+
+    obj = Object()
+    # Method
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=obj.guardrail_fn,
+    )
+    # Class method
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=Object.guardrail_class_fn,
+    )
+    # Static method
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=Object.guardrail_static_fn,
+    )
+
+    def error_fn(x: TaskOutput, y: bool) -> Tuple[bool, TaskOutput]:
+        return (y, x)
+
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=partial(error_fn, y=True),
+    )
+
+    with pytest.raises(ValidationError):
+        Task(
+            description=desc,
+            expected_output=expected_output,
+            guardrail=error_fn,
+        )
+
+
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_output_pydantic_sequential():
    class ScoreOutput(BaseModel):
--- a/tests/test_kickoff_for_each_parallel.py
+++ b/tests/test_kickoff_for_each_parallel.py
@@ -1,209 +0,0 @@
-"""Test for the kickoff_for_each_parallel method in Crew class."""
-
-import concurrent.futures
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from crewai.agent import Agent
-from crewai.crew import Crew
-from crewai.crews.crew_output import CrewOutput
-from crewai.task import Task
-
-
-def test_kickoff_for_each_parallel_single_input():
-    """Tests if kickoff_for_each_parallel works with a single input."""
-    
-    inputs = [{"topic": "dog"}]
-    
-    agent = Agent(
-        role="{topic} Researcher",
-        goal="Express hot takes on {topic}.",
-        backstory="You have a lot of experience with {topic}.",
-    )
-    
-    task = Task(
-        description="Give me an analysis around {topic}.",
-        expected_output="1 bullet point about {topic} that's under 15 words.",
-        agent=agent,
-    )
-    
-    crew = Crew(agents=[agent], tasks=[task])
-    
-    # Mock the kickoff method to avoid API calls
-    expected_output = CrewOutput(raw="Dogs are loyal companions.")
-    with patch.object(Crew, "kickoff", return_value=expected_output):
-        results = crew.kickoff_for_each_parallel(inputs=inputs)
-        
-        assert len(results) == 1
-        assert results[0].raw == "Dogs are loyal companions."
-
-
-def test_kickoff_for_each_parallel_multiple_inputs():
-    """Tests if kickoff_for_each_parallel works with multiple inputs."""
-    
-    inputs = [
-        {"topic": "dog"},
-        {"topic": "cat"},
-        {"topic": "apple"},
-    ]
-    
-    agent = Agent(
-        role="{topic} Researcher",
-        goal="Express hot takes on {topic}.",
-        backstory="You have a lot of experience with {topic}.",
-    )
-    
-    task = Task(
-        description="Give me an analysis around {topic}.",
-        expected_output="1 bullet point about {topic} that's under 15 words.",
-        agent=agent,
-    )
-    
-    crew = Crew(agents=[agent], tasks=[task])
-    
-    # Mock the kickoff method to avoid API calls
-    expected_outputs = [
-        CrewOutput(raw="Dogs are loyal companions."),
-        CrewOutput(raw="Cats are independent pets."),
-        CrewOutput(raw="Apples are nutritious fruits."),
-    ]
-    
-    with patch.object(Crew, "copy") as mock_copy:
-        # Setup mock crew copies
-        crew_copies = []
-        for i in range(len(inputs)):
-            crew_copy = MagicMock()
-            crew_copy.kickoff.return_value = expected_outputs[i]
-            crew_copies.append(crew_copy)
-        mock_copy.side_effect = crew_copies
-        
-        results = crew.kickoff_for_each_parallel(inputs=inputs)
-        
-        assert len(results) == len(inputs)
-        # Since ThreadPoolExecutor returns results in completion order, not input order,
-        # we just check that all expected outputs are in the results
-        result_texts = [result.raw for result in results]
-        expected_texts = [output.raw for output in expected_outputs]
-        for expected_text in expected_texts:
-            assert expected_text in result_texts
-
-
-def test_kickoff_for_each_parallel_empty_input():
-    """Tests if kickoff_for_each_parallel handles an empty input list."""
-    agent = Agent(
-        role="{topic} Researcher",
-        goal="Express hot takes on {topic}.",
-        backstory="You have a lot of experience with {topic}.",
-    )
-    
-    task = Task(
-        description="Give me an analysis around {topic}.",
-        expected_output="1 bullet point about {topic} that's under 15 words.",
-        agent=agent,
-    )
-    
-    crew = Crew(agents=[agent], tasks=[task])
-    results = crew.kickoff_for_each_parallel(inputs=[])
-    assert results == []
-
-
-def test_kickoff_for_each_parallel_invalid_input():
-    """Tests if kickoff_for_each_parallel raises TypeError for invalid input types."""
-    
-    agent = Agent(
-        role="{topic} Researcher",
-        goal="Express hot takes on {topic}.",
-        backstory="You have a lot of experience with {topic}.",
-    )
-    
-    task = Task(
-        description="Give me an analysis around {topic}.",
-        expected_output="1 bullet point about {topic} that's under 15 words.",
-        agent=agent,
-    )
-    
-    crew = Crew(agents=[agent], tasks=[task])
-    
-    # No need to mock here since we're testing input validation which happens before any API calls
-    with pytest.raises(TypeError):
-        # Pass a string instead of a list
-        crew.kickoff_for_each_parallel("invalid input")
-
-
-def test_kickoff_for_each_parallel_error_handling():
-    """Tests error handling in kickoff_for_each_parallel when kickoff raises an error."""
-    
-    inputs = [
-        {"topic": "dog"},
-        {"topic": "cat"},
-        {"topic": "apple"},
-    ]
-    
-    agent = Agent(
-        role="{topic} Researcher",
-        goal="Express hot takes on {topic}.",
-        backstory="You have a lot of experience with {topic}.",
-    )
-    
-    task = Task(
-        description="Give me an analysis around {topic}.",
-        expected_output="1 bullet point about {topic} that's under 15 words.",
-        agent=agent,
-    )
-    
-    crew = Crew(agents=[agent], tasks=[task])
-    
-    with patch.object(Crew, "copy") as mock_copy:
-        # Setup mock crew copies
-        crew_copies = []
-        for i in range(len(inputs)):
-            crew_copy = MagicMock()
-            # Make the third crew copy raise an exception
-            if i == 2:
-                crew_copy.kickoff.side_effect = Exception("Simulated kickoff error")
-            else:
-                crew_copy.kickoff.return_value = f"Output for {inputs[i]['topic']}"
-            crew_copies.append(crew_copy)
-        mock_copy.side_effect = crew_copies
-        
-        with pytest.raises(Exception, match="Simulated kickoff error"):
-            crew.kickoff_for_each_parallel(inputs=inputs)
-
-
-def test_kickoff_for_each_parallel_max_workers():
-    """Tests if kickoff_for_each_parallel respects the max_workers parameter."""
-    
-    inputs = [
-        {"topic": "dog"},
-        {"topic": "cat"},
-        {"topic": "apple"},
-    ]
-    
-    agent = Agent(
-        role="{topic} Researcher",
-        goal="Express hot takes on {topic}.",
-        backstory="You have a lot of experience with {topic}.",
-    )
-    
-    task = Task(
-        description="Give me an analysis around {topic}.",
-        expected_output="1 bullet point about {topic} that's under 15 words.",
-        agent=agent,
-    )
-    
-    crew = Crew(agents=[agent], tasks=[task])
-    
-    # Mock both ThreadPoolExecutor and crew.copy to avoid API calls
-    with patch.object(concurrent.futures, "ThreadPoolExecutor", wraps=concurrent.futures.ThreadPoolExecutor) as mock_executor:
-        with patch.object(Crew, "copy") as mock_copy:
-            # Setup mock crew copies
-            crew_copies = []
-            for _ in range(len(inputs)):
-                crew_copy = MagicMock()
-                crew_copy.kickoff.return_value = CrewOutput(raw="Test output")
-                crew_copies.append(crew_copy)
-            mock_copy.side_effect = crew_copies
-            
-            crew.kickoff_for_each_parallel(inputs=inputs, max_workers=2)
-            mock_executor.assert_called_once_with(max_workers=2)
--- a/tests/utilities/events/test_crewai_event_bus.py
+++ b/tests/utilities/events/test_crewai_event_bus.py
@@ -0,0 +1,34 @@
+from unittest.mock import Mock
+
+from crewai.utilities.events.base_events import CrewEvent
+from crewai.utilities.events.crewai_event_bus import crewai_event_bus
+
+
+class TestEvent(CrewEvent):
+    pass
+
+
+def test_specific_event_handler():
+    mock_handler = Mock()
+
+    @crewai_event_bus.on(TestEvent)
+    def handler(source, event):
+        mock_handler(source, event)
+
+    event = TestEvent(type="test_event")
+    crewai_event_bus.emit("source_object", event)
+
+    mock_handler.assert_called_once_with("source_object", event)
+
+
+def test_wildcard_event_handler():
+    mock_handler = Mock()
+
+    @crewai_event_bus.on(CrewEvent)
+    def handler(source, event):
+        mock_handler(source, event)
+
+    event = TestEvent(type="test_event")
+    crewai_event_bus.emit("source_object", event)
+
+    mock_handler.assert_called_once_with("source_object", event)
Author	SHA1	Message	Date
Brandon Hancock (bhancock_ai)	282461d13a	Merge branch 'main' into devin/1742244238-fix-issue-2395	2025-03-20 12:12:44 -04:00
Amine Saihi	f8f9df6d1d	update doc SpaceNewsKnowledgeSource code snippet (#2275 ) Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>	2025-03-20 12:06:21 -04:00
João Moura	6e94edb777	TYPO	2025-03-20 08:21:17 -07:00
Vini Brasil	bbe896d48c	Support wildcard handling in `emit()` (#2424 ) * Support wildcard handling in `emit()` Change `emit()` to call handlers registered for parent classes using `isinstance()`. Ensures that base event handlers receive derived events. * Fix failing test * Remove unused variable	2025-03-20 09:59:17 -04:00
Seyed Mostafa Meshkati	9298054436	docs: add base_url env for anthropic llm example (#2204 ) Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>	2025-03-20 09:48:11 -04:00
Fernando Galves	90b7937796	Update documentation (#2199 ) * Update llms.mdx Update Amazon Bedrock section with more information about the foundation models available. * Update llms.mdx fix the description of Amazon Bedrock section * Update llms.mdx Remove the incorrect </tab> tag * Update llms.mdx Add Claude 3.7 Sonnet to the Amazon Bedrock list --------- Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>	2025-03-20 09:42:23 -04:00
elda27	520933b4c5	Fix: More comfortable validation #2177 (#2178 ) * Fix: More confortable validation * Fix: union type support --------- Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>	2025-03-20 09:28:31 -04:00
Devin AI	6e359ae9ee	Fix incorrect import statement in memory examples documentation (fixes #2395 ) Co-Authored-By: Joe Moura <joao@crewai.com>	2025-03-17 20:46:32 +00:00