Merge branch 'main' into improvement/speed-up-calculate-node-levels

src/crewai/agent.py

@@ -114,6 +114,7 @@ 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)
@@ -133,11 +134,8 @@ class Agent(BaseAgent):
             self.cache_handler = CacheHandler()
         self.set_cache_handler(self.cache_handler)
 
-    def set_knowledge(self, crew_embedder: Optional[Dict[str, Any]] = None):
+    def _set_knowledge(self):
         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

@@ -351,6 +351,3 @@ 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/cli/constants.py

@@ -216,43 +216,10 @@ MODELS = {
         "watsonx/ibm/granite-3-8b-instruct",
     ],
     "bedrock": [
-        "bedrock/us.amazon.nova-pro-v1:0",
-        "bedrock/us.amazon.nova-micro-v1:0",
-        "bedrock/us.amazon.nova-lite-v1:0",
-        "bedrock/us.anthropic.claude-3-5-sonnet-20240620-v1:0",
-        "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0",
-        "bedrock/us.anthropic.claude-3-5-sonnet-20241022-v2:0",
-        "bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0",
-        "bedrock/us.anthropic.claude-3-sonnet-20240229-v1:0",
-        "bedrock/us.anthropic.claude-3-opus-20240229-v1:0",
-        "bedrock/us.anthropic.claude-3-haiku-20240307-v1:0",
-        "bedrock/us.meta.llama3-2-11b-instruct-v1:0",
-        "bedrock/us.meta.llama3-2-3b-instruct-v1:0",
-        "bedrock/us.meta.llama3-2-90b-instruct-v1:0",
-        "bedrock/us.meta.llama3-2-1b-instruct-v1:0",
-        "bedrock/us.meta.llama3-1-8b-instruct-v1:0",
-        "bedrock/us.meta.llama3-1-70b-instruct-v1:0",
-        "bedrock/us.meta.llama3-3-70b-instruct-v1:0",
-        "bedrock/us.meta.llama3-1-405b-instruct-v1:0",
-        "bedrock/eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
-        "bedrock/eu.anthropic.claude-3-sonnet-20240229-v1:0",
-        "bedrock/eu.anthropic.claude-3-haiku-20240307-v1:0",
-        "bedrock/eu.meta.llama3-2-3b-instruct-v1:0",
-        "bedrock/eu.meta.llama3-2-1b-instruct-v1:0",
-        "bedrock/apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
-        "bedrock/apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
-        "bedrock/apac.anthropic.claude-3-sonnet-20240229-v1:0",
-        "bedrock/apac.anthropic.claude-3-haiku-20240307-v1:0",
-        "bedrock/amazon.nova-pro-v1:0",
-        "bedrock/amazon.nova-micro-v1:0",
-        "bedrock/amazon.nova-lite-v1:0",
         "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0",
-        "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0",
-        "bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0",
-        "bedrock/anthropic.claude-3-7-sonnet-20250219-v1:0",
         "bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
-        "bedrock/anthropic.claude-3-opus-20240229-v1:0",
         "bedrock/anthropic.claude-3-haiku-20240307-v1:0",
+        "bedrock/anthropic.claude-3-opus-20240229-v1:0",
         "bedrock/anthropic.claude-v2:1",
         "bedrock/anthropic.claude-v2",
         "bedrock/anthropic.claude-instant-v1",
@@ -267,6 +234,8 @@ MODELS = {
         "bedrock/ai21.j2-mid-v1",
         "bedrock/ai21.j2-ultra-v1",
         "bedrock/ai21.jamba-instruct-v1:0",
+        "bedrock/meta.llama2-13b-chat-v1",
+        "bedrock/meta.llama2-70b-chat-v1",
         "bedrock/mistral.mistral-7b-instruct-v0:2",
         "bedrock/mistral.mixtral-8x7b-instruct-v0:1",
     ],

src/crewai/crew.py

@@ -600,7 +600,6 @@ 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, timezone
+from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, Optional, Union
 
@@ -34,7 +34,6 @@ 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")
 
@@ -47,8 +46,7 @@ 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,
@@ -56,15 +54,12 @@ 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,
@@ -90,22 +85,19 @@ 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.now(timezone.utc).isoformat(),
-                    json.dumps(state_dict),
-                ),
-            )
+            """, (
+                flow_uuid,
+                method_name,
+                datetime.utcnow().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.
@@ -117,16 +109,13 @@ 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/llm.py

@@ -64,7 +64,6 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "gpt-4-turbo": 128000,
     "o1-preview": 128000,
     "o1-mini": 128000,
-    "o3-mini": 200000,  # Based on official o3-mini specifications
     # gemini
     "gemini-2.0-flash": 1048576,
     "gemini-1.5-pro": 2097152,
@@ -486,23 +485,10 @@ class LLM:
         """
         Returns the context window size, using 75% of the maximum to avoid
         cutting off messages mid-thread.
-
-        Raises:
-            ValueError: If a model's context window size is outside valid bounds (1024-2097152)
         """
         if self.context_window_size != 0:
             return self.context_window_size
 
-        MIN_CONTEXT = 1024
-        MAX_CONTEXT = 2097152  # Current max from gemini-1.5-pro
-
-        # Validate all context window sizes
-        for key, value in LLM_CONTEXT_WINDOW_SIZES.items():
-            if value < MIN_CONTEXT or value > MAX_CONTEXT:
-                raise ValueError(
-                    f"Context window for {key} must be between {MIN_CONTEXT} and {MAX_CONTEXT}"
-                )
-
         self.context_window_size = int(
             DEFAULT_CONTEXT_WINDOW_SIZE * CONTEXT_WINDOW_USAGE_RATIO
         )

src/crewai/utilities/token_counter_callback.py

@@ -30,14 +30,8 @@ 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
-                        and usage.prompt_tokens_details.cached_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_cached_prompt_tokens(
                             usage.prompt_tokens_details.cached_tokens
                         )

tests/llm_test.py

@@ -6,7 +6,7 @@ import pytest
 from pydantic import BaseModel
 
 from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
-from crewai.llm import CONTEXT_WINDOW_USAGE_RATIO, LLM
+from crewai.llm import LLM
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.events.tool_usage_events import ToolExecutionErrorEvent
 from crewai.utilities.token_counter_callback import TokenCalcHandler
@@ -285,23 +285,6 @@ def test_o3_mini_reasoning_effort_medium():
     assert isinstance(result, str)
     assert "Paris" in result
 
-def test_context_window_validation():
-    """Test that context window validation works correctly."""
-    # Test valid window size
-    llm = LLM(model="o3-mini")
-    assert llm.get_context_window_size() == int(200000 * CONTEXT_WINDOW_USAGE_RATIO)
-
-    # Test invalid window size
-    with pytest.raises(ValueError) as excinfo:
-        with patch.dict(
-            "crewai.llm.LLM_CONTEXT_WINDOW_SIZES",
-            {"test-model": 500},  # Below minimum
-            clear=True,
-        ):
-            llm = LLM(model="test-model")
-            llm.get_context_window_size()
-    assert "must be between 1024 and 2097152" in str(excinfo.value)
-
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.fixture