Merge branch 'main' into bugfix/fix-type-error-in-token-counter

- Modify `Agent` class to add `set_knowledge` method
- Allow setting embedder from crew-level configuration
- Remove `_set_knowledge` method from initialization
- Update `Crew` class to set agent knowledge during agent setup
- Add default implementation in `BaseAgent` for compatibility

src/crewai/agent.py

@@ -114,7 +114,6 @@ class Agent(BaseAgent):
 
     @model_validator(mode="after")
     def post_init_setup(self):
-        self._set_knowledge()
         self.agent_ops_agent_name = self.role
 
         self.llm = create_llm(self.llm)
@@ -134,8 +133,11 @@ class Agent(BaseAgent):
             self.cache_handler = CacheHandler()
         self.set_cache_handler(self.cache_handler)
 
-    def _set_knowledge(self):
+    def set_knowledge(self, crew_embedder: Optional[Dict[str, Any]] = None):
         try:
+            if self.embedder is None and crew_embedder:
+                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)}"

src/crewai/agents/agent_builder/base_agent.py

@@ -351,3 +351,6 @@ class BaseAgent(ABC, BaseModel):
         if not self._rpm_controller:
             self._rpm_controller = rpm_controller
             self.create_agent_executor()
+
+    def set_knowledge(self, crew_embedder: Optional[Dict[str, Any]] = None):
+        pass

src/crewai/crew.py

@@ -600,6 +600,7 @@ class Crew(BaseModel):
                 agent.i18n = i18n
                 # type: ignore[attr-defined] # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
                 agent.crew = self  # type: ignore[attr-defined]
+                agent.set_knowledge(crew_embedder=self.embedder)
                 # TODO: Create an AgentFunctionCalling protocol for future refactoring
                 if not agent.function_calling_llm:  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
                     agent.function_calling_llm = self.function_calling_llm  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"

src/crewai/flow/persistence/sqlite.py

@@ -4,7 +4,7 @@ SQLite-based implementation of flow state persistence.
 
 import json
 import sqlite3
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any, Dict, Optional, Union
 
@@ -34,6 +34,7 @@ class SQLiteFlowPersistence(FlowPersistence):
             ValueError: If db_path is invalid
         """
         from crewai.utilities.paths import db_storage_path
+
         # Get path from argument or default location
         path = db_path or str(Path(db_storage_path()) / "flow_states.db")
 
@@ -46,7 +47,8 @@ class SQLiteFlowPersistence(FlowPersistence):
     def init_db(self) -> None:
         """Create the necessary tables if they don't exist."""
         with sqlite3.connect(self.db_path) as conn:
-            conn.execute("""
+            conn.execute(
+                """
             CREATE TABLE IF NOT EXISTS flow_states (
                 id INTEGER PRIMARY KEY AUTOINCREMENT,
                 flow_uuid TEXT NOT NULL,
@@ -54,12 +56,15 @@ class SQLiteFlowPersistence(FlowPersistence):
                 timestamp DATETIME NOT NULL,
                 state_json TEXT NOT NULL
             )
-            """)
+            """
+            )
             # Add index for faster UUID lookups
-            conn.execute("""
+            conn.execute(
+                """
             CREATE INDEX IF NOT EXISTS idx_flow_states_uuid
             ON flow_states(flow_uuid)
-            """)
+            """
+            )
 
     def save_state(
         self,
@@ -85,19 +90,22 @@ class SQLiteFlowPersistence(FlowPersistence):
             )
 
         with sqlite3.connect(self.db_path) as conn:
-            conn.execute("""
+            conn.execute(
+                """
             INSERT INTO flow_states (
                 flow_uuid,
                 method_name,
                 timestamp,
                 state_json
             ) VALUES (?, ?, ?, ?)
-            """, (
-                flow_uuid,
-                method_name,
-                datetime.utcnow().isoformat(),
-                json.dumps(state_dict),
-            ))
+            """,
+                (
+                    flow_uuid,
+                    method_name,
+                    datetime.now(timezone.utc).isoformat(),
+                    json.dumps(state_dict),
+                ),
+            )
 
     def load_state(self, flow_uuid: str) -> Optional[Dict[str, Any]]:
         """Load the most recent state for a given flow UUID.
@@ -109,13 +117,16 @@ class SQLiteFlowPersistence(FlowPersistence):
             The most recent state as a dictionary, or None if no state exists
         """
         with sqlite3.connect(self.db_path) as conn:
-            cursor = conn.execute("""
+            cursor = conn.execute(
+                """
             SELECT state_json
             FROM flow_states
             WHERE flow_uuid = ?
             ORDER BY id DESC
             LIMIT 1
-            """, (flow_uuid,))
+            """,
+                (flow_uuid,),
+            )
             row = cursor.fetchone()
 
         if row:

src/crewai/utilities/token_counter_callback.py

@@ -30,8 +30,14 @@ class TokenCalcHandler(CustomLogger):
                     if hasattr(usage, "prompt_tokens"):
                         self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens)
                     if hasattr(usage, "completion_tokens"):
-                        self.token_cost_process.sum_completion_tokens(usage.completion_tokens)
-                    if hasattr(usage, "prompt_tokens_details") and usage.prompt_tokens_details:
+                        self.token_cost_process.sum_completion_tokens(
+                            usage.completion_tokens
+                        )
+                    if (
+                        hasattr(usage, "prompt_tokens_details")
+                        and usage.prompt_tokens_details
+                        and usage.prompt_tokens_details.cached_tokens
+                    ):
                         self.token_cost_process.sum_cached_prompt_tokens(
                             usage.prompt_tokens_details.cached_tokens
                         )