Merge branch 'main' into feat/trace-ui-execution

src/crewai/agent.py

@@ -142,15 +142,13 @@ class Agent(BaseAgent):
                 self.embedder = crew_embedder
 
             if self.knowledge_sources:
-                full_pattern = re.compile(r"[^a-zA-Z0-9\-_\r\n]|(\.\.)")
-                knowledge_agent_name = f"{re.sub(full_pattern, '_', self.role)}"
                 if isinstance(self.knowledge_sources, list) and all(
                     isinstance(k, BaseKnowledgeSource) for k in self.knowledge_sources
                 ):
                     self.knowledge = Knowledge(
                         sources=self.knowledge_sources,
                         embedder=self.embedder,
-                        collection_name=knowledge_agent_name,
+                        collection_name=self.role,
                         storage=self.knowledge_storage or None,
                     )
         except (TypeError, ValueError) as e:

src/crewai/crew.py

@@ -6,9 +6,8 @@ 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, Set, Tuple, TypeVar, Union, cast
+from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union, cast
 
-from langchain_core.tools import BaseTool as LangchainBaseTool
 from pydantic import (
     UUID4,
     BaseModel,
@@ -490,7 +489,7 @@ class Crew(BaseModel):
             task.key for task in self.tasks
         ]
         return md5("|".join(source).encode(), usedforsecurity=False).hexdigest()
-        
+
     @property
     def fingerprint(self) -> Fingerprint:
         """

src/crewai/flow/state_utils.py

@@ -1,4 +1,5 @@
 import json
+import uuid
 from datetime import date, datetime
 from typing import Any, Dict, List, Union
 
@@ -32,7 +33,7 @@ def export_state(flow: Flow) -> dict[str, Serializable]:
 
 
 def to_serializable(
-    obj: Any, max_depth: int = 5, _current_depth: int = 0
+    obj: Any, exclude: set[str] | None = None, max_depth: int = 5, _current_depth: int = 0
 ) -> Serializable:
     """Converts a Python object into a JSON-compatible representation.
 
@@ -42,6 +43,7 @@ def to_serializable(
 
     Args:
         obj (Any): Object to transform.
+        exclude (set[str], optional): Set of keys to exclude from the result.
         max_depth (int, optional): Maximum recursion depth. Defaults to 5.
 
     Returns:
@@ -50,21 +52,39 @@ def to_serializable(
     if _current_depth >= max_depth:
         return repr(obj)
 
+    if exclude is None:
+        exclude = set()
+
     if isinstance(obj, (str, int, float, bool, type(None))):
         return obj
+    elif isinstance(obj, uuid.UUID):
+        return str(obj)
     elif isinstance(obj, (date, datetime)):
         return obj.isoformat()
     elif isinstance(obj, (list, tuple, set)):
-        return [to_serializable(item, max_depth, _current_depth + 1) for item in obj]
+        return [
+            to_serializable(
+                item, max_depth=max_depth, _current_depth=_current_depth + 1
+            )
+            for item in obj
+        ]
     elif isinstance(obj, dict):
         return {
             _to_serializable_key(key): to_serializable(
-                value, max_depth, _current_depth + 1
+                obj=value,
+                exclude=exclude,
+                max_depth=max_depth,
+                _current_depth=_current_depth + 1,
             )
             for key, value in obj.items()
+            if key not in exclude
         }
     elif isinstance(obj, BaseModel):
-        return to_serializable(obj.model_dump(), max_depth, _current_depth + 1)
+        return to_serializable(
+            obj=obj.model_dump(exclude=exclude),
+            max_depth=max_depth,
+            _current_depth=_current_depth + 1,
+        )
     else:
         return repr(obj)
 

src/crewai/knowledge/storage/knowledge_storage.py

@@ -14,6 +14,7 @@ from chromadb.config import Settings
 
 from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
 from crewai.utilities import EmbeddingConfigurator
+from crewai.utilities.chromadb import sanitize_collection_name
 from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
 from crewai.utilities.logger import Logger
 from crewai.utilities.paths import db_storage_path
@@ -99,7 +100,8 @@ class KnowledgeStorage(BaseKnowledgeStorage):
             )
             if self.app:
                 self.collection = self.app.get_or_create_collection(
-                    name=collection_name, embedding_function=self.embedder
+                    name=sanitize_collection_name(collection_name),
+                    embedding_function=self.embedder,
                 )
             else:
                 raise Exception("Vector Database Client not initialized")

src/crewai/utilities/chromadb.py

@@ -0,0 +1,62 @@
+import re
+from typing import Optional
+
+MIN_COLLECTION_LENGTH = 3
+MAX_COLLECTION_LENGTH = 63
+DEFAULT_COLLECTION = "default_collection"
+
+# Compiled regex patterns for better performance
+INVALID_CHARS_PATTERN = re.compile(r"[^a-zA-Z0-9_-]")
+IPV4_PATTERN = re.compile(r"^(\d{1,3}\.){3}\d{1,3}$")
+
+
+def is_ipv4_pattern(name: str) -> bool:
+    """
+    Check if a string matches an IPv4 address pattern.
+
+    Args:
+        name: The string to check
+
+    Returns:
+        True if the string matches an IPv4 pattern, False otherwise
+    """
+    return bool(IPV4_PATTERN.match(name))
+
+
+def sanitize_collection_name(name: Optional[str]) -> str:
+    """
+    Sanitize a collection name to meet ChromaDB requirements:
+    1. 3-63 characters long
+    2. Starts and ends with alphanumeric character
+    3. Contains only alphanumeric characters, underscores, or hyphens
+    4. No consecutive periods
+    5. Not a valid IPv4 address
+
+    Args:
+        name: The original collection name to sanitize
+
+    Returns:
+        A sanitized collection name that meets ChromaDB requirements
+    """
+    if not name:
+        return DEFAULT_COLLECTION
+
+    if is_ipv4_pattern(name):
+        name = f"ip_{name}"
+
+    sanitized = INVALID_CHARS_PATTERN.sub("_", name)
+
+    if not sanitized[0].isalnum():
+        sanitized = "a" + sanitized
+
+    if not sanitized[-1].isalnum():
+        sanitized = sanitized[:-1] + "z"
+
+    if len(sanitized) < MIN_COLLECTION_LENGTH:
+        sanitized = sanitized + "x" * (MIN_COLLECTION_LENGTH - len(sanitized))
+    if len(sanitized) > MAX_COLLECTION_LENGTH:
+        sanitized = sanitized[:MAX_COLLECTION_LENGTH]
+        if not sanitized[-1].isalnum():
+            sanitized = sanitized[:-1] + "z"
+
+    return sanitized

src/crewai/utilities/events/utils/console_formatter.py

@@ -507,9 +507,10 @@ class ConsoleFormatter:
 
         # Remove the thinking status node when complete
         if "Thinking" in str(tool_branch.label):
-            agent_branch.children.remove(tool_branch)
-            self.print(crew_tree)
-            self.print()
+            if tool_branch in agent_branch.children:
+                agent_branch.children.remove(tool_branch)
+                self.print(crew_tree)
+                self.print()
 
     def handle_llm_call_failed(
         self, tool_branch: Optional[Tree], error: str, crew_tree: Optional[Tree]
@@ -587,6 +588,7 @@ class ConsoleFormatter:
             for child in flow_tree.children:
                 if "Running tests" in str(child.label):
                     child.label = Text("✅ Tests completed successfully", style="green")
+                    break
 
             self.print(flow_tree)
             self.print()