feat: ensure previous event and trigger event are passed

- noted race condition within the vcr package

conftest.py

@@ -1,6 +1,7 @@
 """Pytest configuration for crewAI workspace."""
 
 from collections.abc import Generator
+import gzip
 import os
 from pathlib import Path
 import tempfile
@@ -31,6 +32,21 @@ def cleanup_event_handlers() -> Generator[None, Any, None]:
         pass
 
 
+@pytest.fixture(autouse=True, scope="function")
+def reset_event_state() -> None:
+    """Reset event system state before each test for isolation."""
+    from crewai.events.base_events import reset_emission_counter
+    from crewai.events.event_context import (
+        EventContextConfig,
+        _event_context_config,
+        _event_id_stack,
+    )
+
+    reset_emission_counter()
+    _event_id_stack.set(())
+    _event_context_config.set(EventContextConfig())
+
+
 @pytest.fixture(autouse=True, scope="function")
 def setup_test_environment() -> Generator[None, Any, None]:
     """Setup test environment for crewAI workspace."""
@@ -138,9 +154,14 @@ def _filter_request_headers(request: Request) -> Request:  # type: ignore[no-any
 
 def _filter_response_headers(response: dict[str, Any]) -> dict[str, Any]:
     """Filter sensitive headers from response before recording."""
-    # Remove Content-Encoding to prevent decompression issues on replay
+
     for encoding_header in ["Content-Encoding", "content-encoding"]:
-        response["headers"].pop(encoding_header, None)
+        if encoding_header in response["headers"]:
+            encoding = response["headers"].pop(encoding_header)
+            if encoding and encoding[0] == "gzip":
+                body = response.get("body", {}).get("string", b"")
+                if isinstance(body, bytes) and body.startswith(b"\x1f\x8b"):
+                    response["body"]["string"] = gzip.decompress(body).decode("utf-8")
 
     for header_name, replacement in HEADERS_TO_FILTER.items():
         for variant in [header_name, header_name.upper(), header_name.title()]:

lib/crewai/src/crewai/a2a/types.py

@@ -14,15 +14,25 @@ from typing import (
 from pydantic import BeforeValidator, HttpUrl, TypeAdapter
 from typing_extensions import NotRequired
 
-from crewai.a2a.updates import (
-    PollingConfig,
-    PollingHandler,
-    PushNotificationConfig,
-    PushNotificationHandler,
-    StreamingConfig,
-    StreamingHandler,
-    UpdateConfig,
-)
+
+try:
+    from crewai.a2a.updates import (
+        PollingConfig,
+        PollingHandler,
+        PushNotificationConfig,
+        PushNotificationHandler,
+        StreamingConfig,
+        StreamingHandler,
+        UpdateConfig,
+    )
+except ImportError:
+    PollingConfig = Any  # type: ignore[misc,assignment]
+    PollingHandler = Any  # type: ignore[misc,assignment]
+    PushNotificationConfig = Any  # type: ignore[misc,assignment]
+    PushNotificationHandler = Any  # type: ignore[misc,assignment]
+    StreamingConfig = Any  # type: ignore[misc,assignment]
+    StreamingHandler = Any  # type: ignore[misc,assignment]
+    UpdateConfig = Any  # type: ignore[misc,assignment]
 
 
 TransportType = Literal["JSONRPC", "GRPC", "HTTP+JSON"]

lib/crewai/src/crewai/a2a/utils/delegation.py

@@ -251,30 +251,48 @@ async def aexecute_a2a_delegation(
     if turn_number is None:
         turn_number = len([m for m in conversation_history if m.role == Role.user]) + 1
 
-    result = await _aexecute_a2a_delegation_impl(
-        endpoint=endpoint,
-        auth=auth,
-        timeout=timeout,
-        task_description=task_description,
-        context=context,
-        context_id=context_id,
-        task_id=task_id,
-        reference_task_ids=reference_task_ids,
-        metadata=metadata,
-        extensions=extensions,
-        conversation_history=conversation_history,
-        is_multiturn=is_multiturn,
-        turn_number=turn_number,
-        agent_branch=agent_branch,
-        agent_id=agent_id,
-        agent_role=agent_role,
-        response_model=response_model,
-        updates=updates,
-        transport_protocol=transport_protocol,
-        from_task=from_task,
-        from_agent=from_agent,
-        skill_id=skill_id,
-    )
+    try:
+        result = await _aexecute_a2a_delegation_impl(
+            endpoint=endpoint,
+            auth=auth,
+            timeout=timeout,
+            task_description=task_description,
+            context=context,
+            context_id=context_id,
+            task_id=task_id,
+            reference_task_ids=reference_task_ids,
+            metadata=metadata,
+            extensions=extensions,
+            conversation_history=conversation_history,
+            is_multiturn=is_multiturn,
+            turn_number=turn_number,
+            agent_branch=agent_branch,
+            agent_id=agent_id,
+            agent_role=agent_role,
+            response_model=response_model,
+            updates=updates,
+            transport_protocol=transport_protocol,
+            from_task=from_task,
+            from_agent=from_agent,
+            skill_id=skill_id,
+        )
+    except Exception as e:
+        crewai_event_bus.emit(
+            agent_branch,
+            A2ADelegationCompletedEvent(
+                status="failed",
+                result=None,
+                error=str(e),
+                context_id=context_id,
+                is_multiturn=is_multiturn,
+                endpoint=endpoint,
+                metadata=metadata,
+                extensions=list(extensions.keys()) if extensions else None,
+                from_task=from_task,
+                from_agent=from_agent,
+            ),
+        )
+        raise
 
     agent_card_data: dict[str, Any] = result.get("agent_card") or {}
     crewai_event_bus.emit(

lib/crewai/src/crewai/agent/core.py

@@ -14,7 +14,14 @@ from typing import (
 )
 from urllib.parse import urlparse
 
-from pydantic import BaseModel, Field, InstanceOf, PrivateAttr, model_validator
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    PrivateAttr,
+    model_validator,
+)
 from typing_extensions import Self
 
 from crewai.agent.utils import (
@@ -46,6 +53,7 @@ from crewai.events.types.knowledge_events import (
 )
 from crewai.events.types.memory_events import (
     MemoryRetrievalCompletedEvent,
+    MemoryRetrievalFailedEvent,
     MemoryRetrievalStartedEvent,
 )
 from crewai.experimental.agent_executor import AgentExecutor
@@ -85,17 +93,10 @@ from crewai.utilities.token_counter_callback import TokenCalcHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
 
-try:
-    from crewai.a2a.config import A2AClientConfig, A2AConfig, A2AServerConfig
-except ImportError:
-    A2AClientConfig = Any
-    A2AConfig = Any
-    A2AServerConfig = Any
-
-
 if TYPE_CHECKING:
     from crewai_tools import CodeInterpreterTool
 
+    from crewai.a2a.config import A2AClientConfig, A2AConfig, A2AServerConfig
     from crewai.agents.agent_builder.base_agent import PlatformAppOrAction
     from crewai.task import Task
     from crewai.tools.base_tool import BaseTool
@@ -141,6 +142,8 @@ class Agent(BaseAgent):
             mcps: List of MCP server references for tool integration.
     """
 
+    model_config = ConfigDict()
+
     _times_executed: int = PrivateAttr(default=0)
     _mcp_clients: list[Any] = PrivateAttr(default_factory=list)
     _last_messages: list[LLMMessage] = PrivateAttr(default_factory=list)
@@ -354,30 +357,43 @@ class Agent(BaseAgent):
             )
 
             start_time = time.time()
+            memory = ""
 
-            contextual_memory = ContextualMemory(
-                self.crew._short_term_memory,
-                self.crew._long_term_memory,
-                self.crew._entity_memory,
-                self.crew._external_memory,
-                agent=self,
-                task=task,
-            )
-            memory = contextual_memory.build_context_for_task(task, context or "")
-            if memory.strip() != "":
-                task_prompt += self.i18n.slice("memory").format(memory=memory)
+            try:
+                contextual_memory = ContextualMemory(
+                    self.crew._short_term_memory,
+                    self.crew._long_term_memory,
+                    self.crew._entity_memory,
+                    self.crew._external_memory,
+                    agent=self,
+                    task=task,
+                )
+                memory = contextual_memory.build_context_for_task(task, context or "")
+                if memory.strip() != "":
+                    task_prompt += self.i18n.slice("memory").format(memory=memory)
 
-            crewai_event_bus.emit(
-                self,
-                event=MemoryRetrievalCompletedEvent(
-                    task_id=str(task.id) if task else None,
-                    memory_content=memory,
-                    retrieval_time_ms=(time.time() - start_time) * 1000,
-                    source_type="agent",
-                    from_agent=self,
-                    from_task=task,
-                ),
-            )
+                crewai_event_bus.emit(
+                    self,
+                    event=MemoryRetrievalCompletedEvent(
+                        task_id=str(task.id) if task else None,
+                        memory_content=memory,
+                        retrieval_time_ms=(time.time() - start_time) * 1000,
+                        source_type="agent",
+                        from_agent=self,
+                        from_task=task,
+                    ),
+                )
+            except Exception as e:
+                crewai_event_bus.emit(
+                    self,
+                    event=MemoryRetrievalFailedEvent(
+                        task_id=str(task.id) if task else None,
+                        source_type="agent",
+                        from_agent=self,
+                        from_task=task,
+                        error=str(e),
+                    ),
+                )
 
         knowledge_config = get_knowledge_config(self)
         task_prompt = handle_knowledge_retrieval(
@@ -563,32 +579,45 @@ class Agent(BaseAgent):
             )
 
             start_time = time.time()
+            memory = ""
 
-            contextual_memory = ContextualMemory(
-                self.crew._short_term_memory,
-                self.crew._long_term_memory,
-                self.crew._entity_memory,
-                self.crew._external_memory,
-                agent=self,
-                task=task,
-            )
-            memory = await contextual_memory.abuild_context_for_task(
-                task, context or ""
-            )
-            if memory.strip() != "":
-                task_prompt += self.i18n.slice("memory").format(memory=memory)
+            try:
+                contextual_memory = ContextualMemory(
+                    self.crew._short_term_memory,
+                    self.crew._long_term_memory,
+                    self.crew._entity_memory,
+                    self.crew._external_memory,
+                    agent=self,
+                    task=task,
+                )
+                memory = await contextual_memory.abuild_context_for_task(
+                    task, context or ""
+                )
+                if memory.strip() != "":
+                    task_prompt += self.i18n.slice("memory").format(memory=memory)
 
-            crewai_event_bus.emit(
-                self,
-                event=MemoryRetrievalCompletedEvent(
-                    task_id=str(task.id) if task else None,
-                    memory_content=memory,
-                    retrieval_time_ms=(time.time() - start_time) * 1000,
-                    source_type="agent",
-                    from_agent=self,
-                    from_task=task,
-                ),
-            )
+                crewai_event_bus.emit(
+                    self,
+                    event=MemoryRetrievalCompletedEvent(
+                        task_id=str(task.id) if task else None,
+                        memory_content=memory,
+                        retrieval_time_ms=(time.time() - start_time) * 1000,
+                        source_type="agent",
+                        from_agent=self,
+                        from_task=task,
+                    ),
+                )
+            except Exception as e:
+                crewai_event_bus.emit(
+                    self,
+                    event=MemoryRetrievalFailedEvent(
+                        task_id=str(task.id) if task else None,
+                        source_type="agent",
+                        from_agent=self,
+                        from_task=task,
+                        error=str(e),
+                    ),
+                )
 
         knowledge_config = get_knowledge_config(self)
         task_prompt = await ahandle_knowledge_retrieval(
@@ -2039,3 +2068,22 @@ class Agent(BaseAgent):
                 ),
             )
             raise
+
+
+# Rebuild Agent model to resolve A2A type forward references
+try:
+    from crewai.a2a.config import (
+        A2AClientConfig as _A2AClientConfig,
+        A2AConfig as _A2AConfig,
+        A2AServerConfig as _A2AServerConfig,
+    )
+
+    Agent.model_rebuild(
+        _types_namespace={
+            "A2AConfig": _A2AConfig,
+            "A2AClientConfig": _A2AClientConfig,
+            "A2AServerConfig": _A2AServerConfig,
+        }
+    )
+except ImportError:
+    pass

lib/crewai/src/crewai/crews/utils.py

@@ -189,9 +189,15 @@ def prepare_kickoff(crew: Crew, inputs: dict[str, Any] | None) -> dict[str, Any]
     Returns:
         The potentially modified inputs dictionary after before callbacks.
     """
+    from crewai.events.base_events import reset_emission_counter
     from crewai.events.event_bus import crewai_event_bus
+    from crewai.events.event_context import get_current_parent_id, reset_last_event_id
     from crewai.events.types.crew_events import CrewKickoffStartedEvent
 
+    if get_current_parent_id() is None:
+        reset_emission_counter()
+        reset_last_event_id()
+
     for before_callback in crew.before_kickoff_callbacks:
         if inputs is None:
             inputs = {}

lib/crewai/src/crewai/events/__init__.py

@@ -75,6 +75,7 @@ from crewai.events.types.memory_events import (
     MemoryQueryFailedEvent,
     MemoryQueryStartedEvent,
     MemoryRetrievalCompletedEvent,
+    MemoryRetrievalFailedEvent,
     MemoryRetrievalStartedEvent,
     MemorySaveCompletedEvent,
     MemorySaveFailedEvent,
@@ -174,6 +175,7 @@ __all__ = [
     "MemoryQueryFailedEvent",
     "MemoryQueryStartedEvent",
     "MemoryRetrievalCompletedEvent",
+    "MemoryRetrievalFailedEvent",
     "MemoryRetrievalStartedEvent",
     "MemorySaveCompletedEvent",
     "MemorySaveFailedEvent",

lib/crewai/src/crewai/events/base_events.py

@@ -1,9 +1,46 @@
+from collections.abc import Iterator
+import contextvars
 from datetime import datetime, timezone
+import itertools
 from typing import Any
+import uuid
 
 from pydantic import BaseModel, Field
 
-from crewai.utilities.serialization import to_serializable
+from crewai.utilities.serialization import Serializable, to_serializable
+
+
+_emission_counter: contextvars.ContextVar[Iterator[int]] = contextvars.ContextVar(
+    "_emission_counter"
+)
+
+
+def _get_or_create_counter() -> Iterator[int]:
+    """Get the emission counter for the current context, creating if needed."""
+    try:
+        return _emission_counter.get()
+    except LookupError:
+        counter: Iterator[int] = itertools.count(start=1)
+        _emission_counter.set(counter)
+        return counter
+
+
+def get_next_emission_sequence() -> int:
+    """Get the next emission sequence number.
+
+    Returns:
+        The next sequence number.
+    """
+    return next(_get_or_create_counter())
+
+
+def reset_emission_counter() -> None:
+    """Reset the emission sequence counter to 1.
+
+    Resets for the current context only.
+    """
+    counter: Iterator[int] = itertools.count(start=1)
+    _emission_counter.set(counter)
 
 
 class BaseEvent(BaseModel):
@@ -22,7 +59,13 @@ class BaseEvent(BaseModel):
     agent_id: str | None = None
     agent_role: str | None = None
 
-    def to_json(self, exclude: set[str] | None = None):
+    event_id: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    parent_event_id: str | None = None
+    previous_event_id: str | None = None
+    triggered_by_event_id: str | None = None
+    emission_sequence: int | None = None
+
+    def to_json(self, exclude: set[str] | None = None) -> Serializable:
         """
         Converts the event to a JSON-serializable dictionary.
 
@@ -34,13 +77,13 @@ class BaseEvent(BaseModel):
         """
         return to_serializable(self, exclude=exclude)
 
-    def _set_task_params(self, data: dict[str, Any]):
+    def _set_task_params(self, data: dict[str, Any]) -> None:
         if "from_task" in data and (task := data["from_task"]):
             self.task_id = str(task.id)
             self.task_name = task.name or task.description
             self.from_task = None
 
-    def _set_agent_params(self, data: dict[str, Any]):
+    def _set_agent_params(self, data: dict[str, Any]) -> None:
         task = data.get("from_task", None)
         agent = task.agent if task else data.get("from_agent", None)
 

lib/crewai/src/crewai/events/event_bus.py

@@ -16,8 +16,22 @@ from typing import Any, Final, ParamSpec, TypeVar
 
 from typing_extensions import Self
 
-from crewai.events.base_events import BaseEvent
+from crewai.events.base_events import BaseEvent, get_next_emission_sequence
 from crewai.events.depends import Depends
+from crewai.events.event_context import (
+    SCOPE_ENDING_EVENTS,
+    SCOPE_STARTING_EVENTS,
+    VALID_EVENT_PAIRS,
+    get_current_parent_id,
+    get_enclosing_parent_id,
+    get_last_event_id,
+    get_triggering_event_id,
+    handle_empty_pop,
+    handle_mismatch,
+    pop_event_scope,
+    push_event_scope,
+    set_last_event_id,
+)
 from crewai.events.handler_graph import build_execution_plan
 from crewai.events.types.event_bus_types import (
     AsyncHandler,
@@ -69,6 +83,8 @@ class CrewAIEventsBus:
     _execution_plan_cache: dict[type[BaseEvent], ExecutionPlan]
     _console: ConsoleFormatter
     _shutting_down: bool
+    _pending_futures: set[Future[Any]]
+    _futures_lock: threading.Lock
 
     def __new__(cls) -> Self:
         """Create or return the singleton instance.
@@ -91,6 +107,8 @@ class CrewAIEventsBus:
         """
         self._shutting_down = False
         self._rwlock = RWLock()
+        self._pending_futures: set[Future[Any]] = set()
+        self._futures_lock = threading.Lock()
         self._sync_handlers: dict[type[BaseEvent], SyncHandlerSet] = {}
         self._async_handlers: dict[type[BaseEvent], AsyncHandlerSet] = {}
         self._handler_dependencies: dict[
@@ -111,6 +129,25 @@ class CrewAIEventsBus:
         )
         self._loop_thread.start()
 
+    def _track_future(self, future: Future[Any]) -> Future[Any]:
+        """Track a future and set up automatic cleanup when it completes.
+
+        Args:
+            future: The future to track
+
+        Returns:
+            The same future for chaining
+        """
+        with self._futures_lock:
+            self._pending_futures.add(future)
+
+        def _cleanup(f: Future[Any]) -> None:
+            with self._futures_lock:
+                self._pending_futures.discard(f)
+
+        future.add_done_callback(_cleanup)
+        return future
+
     def _run_loop(self) -> None:
         """Run the background async event loop."""
         asyncio.set_event_loop(self._loop)
@@ -326,6 +363,28 @@ class CrewAIEventsBus:
             ...     await asyncio.wrap_future(future)  # In async test
             ...     # or future.result(timeout=5.0) in sync code
         """
+        event.previous_event_id = get_last_event_id()
+        event.triggered_by_event_id = get_triggering_event_id()
+        event.emission_sequence = get_next_emission_sequence()
+        if event.parent_event_id is None:
+            event_type_name = event.type
+            if event_type_name in SCOPE_ENDING_EVENTS:
+                event.parent_event_id = get_enclosing_parent_id()
+                popped = pop_event_scope()
+                if popped is None:
+                    handle_empty_pop(event_type_name)
+                else:
+                    _, popped_type = popped
+                    expected_start = VALID_EVENT_PAIRS.get(event_type_name)
+                    if expected_start and popped_type and popped_type != expected_start:
+                        handle_mismatch(event_type_name, popped_type, expected_start)
+            elif event_type_name in SCOPE_STARTING_EVENTS:
+                event.parent_event_id = get_current_parent_id()
+                push_event_scope(event.event_id, event_type_name)
+            else:
+                event.parent_event_id = get_current_parent_id()
+
+        set_last_event_id(event.event_id)
         event_type = type(event)
 
         with self._rwlock.r_locked():
@@ -339,9 +398,11 @@ class CrewAIEventsBus:
             async_handlers = self._async_handlers.get(event_type, frozenset())
 
         if has_dependencies:
-            return asyncio.run_coroutine_threadsafe(
-                self._emit_with_dependencies(source, event),
-                self._loop,
+            return self._track_future(
+                asyncio.run_coroutine_threadsafe(
+                    self._emit_with_dependencies(source, event),
+                    self._loop,
+                )
             )
 
         if sync_handlers:
@@ -353,16 +414,53 @@ class CrewAIEventsBus:
                     ctx.run, self._call_handlers, source, event, sync_handlers
                 )
                 if not async_handlers:
-                    return sync_future
+                    return self._track_future(sync_future)
 
         if async_handlers:
-            return asyncio.run_coroutine_threadsafe(
-                self._acall_handlers(source, event, async_handlers),
-                self._loop,
+            return self._track_future(
+                asyncio.run_coroutine_threadsafe(
+                    self._acall_handlers(source, event, async_handlers),
+                    self._loop,
+                )
             )
 
         return None
 
+    def flush(self, timeout: float | None = 30.0) -> bool:
+        """Block until all pending event handlers complete.
+
+        This method waits for all futures from previously emitted events to
+        finish executing. Useful at the end of operations (like kickoff) to
+        ensure all event handlers have completed before returning.
+
+        Args:
+            timeout: Maximum time in seconds to wait for handlers to complete.
+                    Defaults to 30 seconds. Pass None to wait indefinitely.
+
+        Returns:
+            True if all handlers completed, False if timeout occurred.
+        """
+        with self._futures_lock:
+            futures_to_wait = list(self._pending_futures)
+
+        if not futures_to_wait:
+            return True
+
+        from concurrent.futures import wait as wait_futures
+
+        done, not_done = wait_futures(futures_to_wait, timeout=timeout)
+
+        # Check for exceptions in completed futures
+        errors = [
+            future.exception() for future in done if future.exception() is not None
+        ]
+        for error in errors:
+            self._console.print(
+                f"[CrewAIEventsBus] Handler exception during flush: {error}"
+            )
+
+        return len(not_done) == 0
+
     async def aemit(self, source: Any, event: BaseEvent) -> None:
         """Asynchronously emit an event to registered async handlers.
 
@@ -464,6 +562,9 @@ class CrewAIEventsBus:
             wait: If True, wait for all pending tasks to complete before stopping.
                   If False, cancel all pending tasks immediately.
         """
+        if wait:
+            self.flush()
+
         with self._rwlock.w_locked():
             self._shutting_down = True
             loop = getattr(self, "_loop", None)

lib/crewai/src/crewai/events/event_context.py

@@ -0,0 +1,334 @@
+"""Event context management for parent-child relationship tracking."""
+
+from collections.abc import Generator
+from contextlib import contextmanager
+import contextvars
+from dataclasses import dataclass
+from enum import Enum
+
+from crewai.events.utils.console_formatter import ConsoleFormatter
+
+
+class MismatchBehavior(Enum):
+    """Behavior when event pairs don't match."""
+
+    WARN = "warn"
+    RAISE = "raise"
+    SILENT = "silent"
+
+
+@dataclass
+class EventContextConfig:
+    """Configuration for event context behavior."""
+
+    max_stack_depth: int = 100
+    mismatch_behavior: MismatchBehavior = MismatchBehavior.WARN
+    empty_pop_behavior: MismatchBehavior = MismatchBehavior.WARN
+
+
+class StackDepthExceededError(Exception):
+    """Raised when stack depth limit is exceeded."""
+
+
+class EventPairingError(Exception):
+    """Raised when event pairs don't match."""
+
+
+class EmptyStackError(Exception):
+    """Raised when popping from empty stack."""
+
+
+_event_id_stack: contextvars.ContextVar[tuple[tuple[str, str], ...]] = (
+    contextvars.ContextVar("_event_id_stack", default=())
+)
+
+_event_context_config: contextvars.ContextVar[EventContextConfig | None] = (
+    contextvars.ContextVar("_event_context_config", default=None)
+)
+
+_last_event_id: contextvars.ContextVar[str | None] = contextvars.ContextVar(
+    "_last_event_id", default=None
+)
+
+_triggering_event_id: contextvars.ContextVar[str | None] = contextvars.ContextVar(
+    "_triggering_event_id", default=None
+)
+
+_default_config = EventContextConfig()
+
+_console = ConsoleFormatter()
+
+
+def get_current_parent_id() -> str | None:
+    """Get the current parent event ID from the stack."""
+    stack = _event_id_stack.get()
+    return stack[-1][0] if stack else None
+
+
+def get_enclosing_parent_id() -> str | None:
+    """Get the parent of the current scope (stack[-2])."""
+    stack = _event_id_stack.get()
+    return stack[-2][0] if len(stack) >= 2 else None
+
+
+def get_last_event_id() -> str | None:
+    """Get the ID of the last emitted event for linear chain tracking.
+
+    Returns:
+        The event_id of the previously emitted event, or None if no event yet.
+    """
+    return _last_event_id.get()
+
+
+def reset_last_event_id() -> None:
+    """Reset the last event ID to None.
+
+    Should be called at the start of a new flow or when resetting event state.
+    """
+    _last_event_id.set(None)
+
+
+def set_last_event_id(event_id: str) -> None:
+    """Set the ID of the last emitted event.
+
+    Args:
+        event_id: The event_id to set as the last emitted event.
+    """
+    _last_event_id.set(event_id)
+
+
+def get_triggering_event_id() -> str | None:
+    """Get the ID of the event that triggered the current execution.
+
+    Returns:
+        The event_id of the triggering event, or None if not in a triggered context.
+    """
+    return _triggering_event_id.get()
+
+
+def set_triggering_event_id(event_id: str | None) -> None:
+    """Set the ID of the triggering event for causal chain tracking.
+
+    Args:
+        event_id: The event_id that triggered the current execution, or None.
+    """
+    _triggering_event_id.set(event_id)
+
+
+@contextmanager
+def triggered_by_scope(event_id: str) -> Generator[None, None, None]:
+    """Context manager to set the triggering event ID for causal chain tracking.
+
+    All events emitted within this context will have their triggered_by_event_id
+    set to the provided event_id.
+
+    Args:
+        event_id: The event_id that triggered the current execution.
+    """
+    previous = _triggering_event_id.get()
+    _triggering_event_id.set(event_id)
+    try:
+        yield
+    finally:
+        _triggering_event_id.set(previous)
+
+
+def push_event_scope(event_id: str, event_type: str = "") -> None:
+    """Push an event ID and type onto the scope stack."""
+    config = _event_context_config.get() or _default_config
+    stack = _event_id_stack.get()
+
+    if 0 < config.max_stack_depth <= len(stack):
+        raise StackDepthExceededError(
+            f"Event stack depth limit ({config.max_stack_depth}) exceeded. "
+            f"This usually indicates missing ending events."
+        )
+
+    _event_id_stack.set((*stack, (event_id, event_type)))
+
+
+def pop_event_scope() -> tuple[str, str] | None:
+    """Pop an event entry from the scope stack."""
+    stack = _event_id_stack.get()
+    if not stack:
+        return None
+    _event_id_stack.set(stack[:-1])
+    return stack[-1]
+
+
+def handle_empty_pop(event_type_name: str) -> None:
+    """Handle a pop attempt on an empty stack."""
+    config = _event_context_config.get() or _default_config
+    msg = (
+        f"Ending event '{event_type_name}' emitted with empty scope stack. "
+        "Missing starting event?"
+    )
+
+    if config.empty_pop_behavior == MismatchBehavior.RAISE:
+        raise EmptyStackError(msg)
+    if config.empty_pop_behavior == MismatchBehavior.WARN:
+        _console.print(f"[CrewAIEventsBus] Warning: {msg}")
+
+
+def handle_mismatch(
+    event_type_name: str,
+    popped_type: str,
+    expected_start: str,
+) -> None:
+    """Handle a mismatched event pair."""
+    config = _event_context_config.get() or _default_config
+    msg = (
+        f"Event pairing mismatch. '{event_type_name}' closed '{popped_type}' "
+        f"(expected '{expected_start}')"
+    )
+
+    if config.mismatch_behavior == MismatchBehavior.RAISE:
+        raise EventPairingError(msg)
+    if config.mismatch_behavior == MismatchBehavior.WARN:
+        _console.print(f"[CrewAIEventsBus] Warning: {msg}")
+
+
+@contextmanager
+def event_scope(event_id: str, event_type: str = "") -> Generator[None, None, None]:
+    """Context manager to establish a parent event scope."""
+    stack = _event_id_stack.get()
+    already_on_stack = any(entry[0] == event_id for entry in stack)
+    if not already_on_stack:
+        push_event_scope(event_id, event_type)
+    try:
+        yield
+    finally:
+        if not already_on_stack:
+            pop_event_scope()
+
+
+SCOPE_STARTING_EVENTS: frozenset[str] = frozenset(
+    {
+        "flow_started",
+        "method_execution_started",
+        "crew_kickoff_started",
+        "crew_train_started",
+        "crew_test_started",
+        "agent_execution_started",
+        "agent_evaluation_started",
+        "lite_agent_execution_started",
+        "task_started",
+        "llm_call_started",
+        "llm_guardrail_started",
+        "tool_usage_started",
+        "mcp_connection_started",
+        "mcp_tool_execution_started",
+        "memory_retrieval_started",
+        "memory_save_started",
+        "memory_query_started",
+        "knowledge_query_started",
+        "knowledge_search_query_started",
+        "a2a_delegation_started",
+        "a2a_conversation_started",
+        "a2a_server_task_started",
+        "a2a_parallel_delegation_started",
+        "agent_reasoning_started",
+    }
+)
+
+SCOPE_ENDING_EVENTS: frozenset[str] = frozenset(
+    {
+        "flow_finished",
+        "flow_paused",
+        "method_execution_finished",
+        "method_execution_failed",
+        "method_execution_paused",
+        "crew_kickoff_completed",
+        "crew_kickoff_failed",
+        "crew_train_completed",
+        "crew_train_failed",
+        "crew_test_completed",
+        "crew_test_failed",
+        "agent_execution_completed",
+        "agent_execution_error",
+        "agent_evaluation_completed",
+        "agent_evaluation_failed",
+        "lite_agent_execution_completed",
+        "lite_agent_execution_error",
+        "task_completed",
+        "task_failed",
+        "llm_call_completed",
+        "llm_call_failed",
+        "llm_guardrail_completed",
+        "llm_guardrail_failed",
+        "tool_usage_finished",
+        "tool_usage_error",
+        "mcp_connection_completed",
+        "mcp_connection_failed",
+        "mcp_tool_execution_completed",
+        "mcp_tool_execution_failed",
+        "memory_retrieval_completed",
+        "memory_retrieval_failed",
+        "memory_save_completed",
+        "memory_save_failed",
+        "memory_query_completed",
+        "memory_query_failed",
+        "knowledge_query_completed",
+        "knowledge_query_failed",
+        "knowledge_search_query_completed",
+        "knowledge_search_query_failed",
+        "a2a_delegation_completed",
+        "a2a_conversation_completed",
+        "a2a_server_task_completed",
+        "a2a_server_task_canceled",
+        "a2a_server_task_failed",
+        "a2a_parallel_delegation_completed",
+        "agent_reasoning_completed",
+        "agent_reasoning_failed",
+    }
+)
+
+VALID_EVENT_PAIRS: dict[str, str] = {
+    "flow_finished": "flow_started",
+    "flow_paused": "flow_started",
+    "method_execution_finished": "method_execution_started",
+    "method_execution_failed": "method_execution_started",
+    "method_execution_paused": "method_execution_started",
+    "crew_kickoff_completed": "crew_kickoff_started",
+    "crew_kickoff_failed": "crew_kickoff_started",
+    "crew_train_completed": "crew_train_started",
+    "crew_train_failed": "crew_train_started",
+    "crew_test_completed": "crew_test_started",
+    "crew_test_failed": "crew_test_started",
+    "agent_execution_completed": "agent_execution_started",
+    "agent_execution_error": "agent_execution_started",
+    "agent_evaluation_completed": "agent_evaluation_started",
+    "agent_evaluation_failed": "agent_evaluation_started",
+    "lite_agent_execution_completed": "lite_agent_execution_started",
+    "lite_agent_execution_error": "lite_agent_execution_started",
+    "task_completed": "task_started",
+    "task_failed": "task_started",
+    "llm_call_completed": "llm_call_started",
+    "llm_call_failed": "llm_call_started",
+    "llm_guardrail_completed": "llm_guardrail_started",
+    "llm_guardrail_failed": "llm_guardrail_started",
+    "tool_usage_finished": "tool_usage_started",
+    "tool_usage_error": "tool_usage_started",
+    "mcp_connection_completed": "mcp_connection_started",
+    "mcp_connection_failed": "mcp_connection_started",
+    "mcp_tool_execution_completed": "mcp_tool_execution_started",
+    "mcp_tool_execution_failed": "mcp_tool_execution_started",
+    "memory_retrieval_completed": "memory_retrieval_started",
+    "memory_retrieval_failed": "memory_retrieval_started",
+    "memory_save_completed": "memory_save_started",
+    "memory_save_failed": "memory_save_started",
+    "memory_query_completed": "memory_query_started",
+    "memory_query_failed": "memory_query_started",
+    "knowledge_query_completed": "knowledge_query_started",
+    "knowledge_query_failed": "knowledge_query_started",
+    "knowledge_search_query_completed": "knowledge_search_query_started",
+    "knowledge_search_query_failed": "knowledge_search_query_started",
+    "a2a_delegation_completed": "a2a_delegation_started",
+    "a2a_conversation_completed": "a2a_conversation_started",
+    "a2a_server_task_completed": "a2a_server_task_started",
+    "a2a_server_task_canceled": "a2a_server_task_started",
+    "a2a_server_task_failed": "a2a_server_task_started",
+    "a2a_parallel_delegation_completed": "a2a_parallel_delegation_started",
+    "agent_reasoning_completed": "agent_reasoning_started",
+    "agent_reasoning_failed": "agent_reasoning_started",
+}

lib/crewai/src/crewai/events/event_types.py

@@ -79,6 +79,7 @@ from crewai.events.types.memory_events import (
     MemoryQueryFailedEvent,
     MemoryQueryStartedEvent,
     MemoryRetrievalCompletedEvent,
+    MemoryRetrievalFailedEvent,
     MemoryRetrievalStartedEvent,
     MemorySaveCompletedEvent,
     MemorySaveFailedEvent,
@@ -173,6 +174,7 @@ EventTypes = (
     | MemoryQueryFailedEvent
     | MemoryRetrievalStartedEvent
     | MemoryRetrievalCompletedEvent
+    | MemoryRetrievalFailedEvent
     | MCPConnectionStartedEvent
     | MCPConnectionCompletedEvent
     | MCPConnectionFailedEvent

lib/crewai/src/crewai/events/listeners/tracing/trace_batch_manager.py

@@ -267,9 +267,12 @@ class TraceBatchManager:
 
         sorted_events = sorted(
             self.event_buffer,
-            key=lambda e: e.timestamp
-            if hasattr(e, "timestamp") and e.timestamp
-            else "",
+            key=lambda e: (
+                e.emission_sequence
+                if e.emission_sequence is not None
+                else float("inf"),
+                e.timestamp if hasattr(e, "timestamp") and e.timestamp else "",
+            ),
         )
 
         self.current_batch.events = sorted_events

lib/crewai/src/crewai/events/listeners/tracing/trace_listener.py

@@ -9,6 +9,7 @@ from typing_extensions import Self
 from crewai.cli.authentication.token import AuthError, get_auth_token
 from crewai.cli.version import get_crewai_version
 from crewai.events.base_event_listener import BaseEventListener
+from crewai.events.base_events import BaseEvent
 from crewai.events.event_bus import CrewAIEventsBus
 from crewai.events.listeners.tracing.first_time_trace_handler import (
     FirstTimeTraceHandler,
@@ -616,7 +617,7 @@ class TraceCollectionListener(BaseEventListener):
             if self.batch_manager.is_batch_initialized():
                 self.batch_manager.finalize_batch()
 
-    def _initialize_crew_batch(self, source: Any, event: Any) -> None:
+    def _initialize_crew_batch(self, source: Any, event: BaseEvent) -> None:
         """Initialize trace batch.
 
         Args:
@@ -626,7 +627,7 @@ class TraceCollectionListener(BaseEventListener):
         user_context = self._get_user_context()
         execution_metadata = {
             "crew_name": getattr(event, "crew_name", "Unknown Crew"),
-            "execution_start": event.timestamp if hasattr(event, "timestamp") else None,
+            "execution_start": event.timestamp,
             "crewai_version": get_crewai_version(),
         }
 
@@ -635,7 +636,7 @@ class TraceCollectionListener(BaseEventListener):
 
         self._initialize_batch(user_context, execution_metadata)
 
-    def _initialize_flow_batch(self, source: Any, event: Any) -> None:
+    def _initialize_flow_batch(self, source: Any, event: BaseEvent) -> None:
         """Initialize trace batch for Flow execution.
 
         Args:
@@ -645,7 +646,7 @@ class TraceCollectionListener(BaseEventListener):
         user_context = self._get_user_context()
         execution_metadata = {
             "flow_name": getattr(event, "flow_name", "Unknown Flow"),
-            "execution_start": event.timestamp if hasattr(event, "timestamp") else None,
+            "execution_start": event.timestamp,
             "crewai_version": get_crewai_version(),
             "execution_type": "flow",
         }
@@ -714,18 +715,18 @@ class TraceCollectionListener(BaseEventListener):
             self.batch_manager.end_event_processing()
 
     def _create_trace_event(
-        self, event_type: str, source: Any, event: Any
+        self, event_type: str, source: Any, event: BaseEvent
     ) -> TraceEvent:
-        """Create a trace event"""
-        if hasattr(event, "timestamp") and event.timestamp:
-            trace_event = TraceEvent(
-                type=event_type,
-                timestamp=event.timestamp.isoformat(),
-            )
-        else:
-            trace_event = TraceEvent(
-                type=event_type,
-            )
+        """Create a trace event with ordering information."""
+        trace_event = TraceEvent(
+            type=event_type,
+            timestamp=event.timestamp.isoformat() if event.timestamp else "",
+            event_id=event.event_id,
+            emission_sequence=event.emission_sequence,
+            parent_event_id=event.parent_event_id,
+            previous_event_id=event.previous_event_id,
+            triggered_by_event_id=event.triggered_by_event_id,
+        )
 
         trace_event.event_data = self._build_event_data(event_type, event, source)
 
@@ -778,10 +779,8 @@ class TraceCollectionListener(BaseEventListener):
             }
         if event_type == "llm_call_started":
             event_data = safe_serialize_to_dict(event)
-            event_data["task_name"] = (
-                event.task_name or event.task_description
-                if hasattr(event, "task_name") and event.task_name
-                else None
+            event_data["task_name"] = event.task_name or getattr(
+                event, "task_description", None
             )
             return event_data
         if event_type == "llm_call_completed":

lib/crewai/src/crewai/events/listeners/tracing/types.py

@@ -15,5 +15,10 @@ class TraceEvent:
     type: str = ""
     event_data: dict[str, Any] = field(default_factory=dict)
 
+    emission_sequence: int | None = None
+    parent_event_id: str | None = None
+    previous_event_id: str | None = None
+    triggered_by_event_id: str | None = None
+
     def to_dict(self) -> dict[str, Any]:
         return asdict(self)

lib/crewai/src/crewai/events/types/memory_events.py

@@ -14,7 +14,7 @@ class MemoryBaseEvent(BaseEvent):
     agent_role: str | None = None
     agent_id: str | None = None
 
-    def __init__(self, **data):
+    def __init__(self, **data: Any) -> None:
         super().__init__(**data)
         self._set_agent_params(data)
         self._set_task_params(data)
@@ -93,3 +93,11 @@ class MemoryRetrievalCompletedEvent(MemoryBaseEvent):
     task_id: str | None = None
     memory_content: str
     retrieval_time_ms: float
+
+
+class MemoryRetrievalFailedEvent(MemoryBaseEvent):
+    """Event emitted when memory retrieval for a task prompt fails."""
+
+    type: str = "memory_retrieval_failed"
+    task_id: str | None = None
+    error: str

lib/crewai/src/crewai/flow/flow.py

@@ -31,7 +31,13 @@ from pydantic import BaseModel, Field, ValidationError
 from rich.console import Console
 from rich.panel import Panel
 
+from crewai.events.base_events import reset_emission_counter
 from crewai.events.event_bus import crewai_event_bus
+from crewai.events.event_context import (
+    get_current_parent_id,
+    reset_last_event_id,
+    triggered_by_scope,
+)
 from crewai.events.listeners.tracing.trace_listener import (
     TraceCollectionListener,
 )
@@ -753,6 +759,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
         racing_listeners: frozenset[FlowMethodName],
         other_listeners: list[FlowMethodName],
         result: Any,
+        triggering_event_id: str | None = None,
     ) -> None:
         """Execute racing listeners with first-wins semantics.
 
@@ -764,10 +771,11 @@ class Flow(Generic[T], metaclass=FlowMeta):
             racing_listeners: Set of listener names that race for an OR condition.
             other_listeners: Other listeners to execute in parallel (not racing).
             result: The result from the triggering method.
+            triggering_event_id: The event_id of the event that triggered these listeners.
         """
         racing_tasks = [
             asyncio.create_task(
-                self._execute_single_listener(name, result),
+                self._execute_single_listener(name, result, triggering_event_id),
                 name=str(name),
             )
             for name in racing_listeners
@@ -775,7 +783,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
         other_tasks = [
             asyncio.create_task(
-                self._execute_single_listener(name, result),
+                self._execute_single_listener(name, result, triggering_event_id),
                 name=str(name),
             )
             for name in other_listeners
@@ -1557,6 +1565,10 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 if filtered_inputs:
                     self._initialize_state(filtered_inputs)
 
+            if get_current_parent_id() is None:
+                reset_emission_counter()
+                reset_last_event_id()
+
             # Emit FlowStartedEvent and log the start of the flow.
             if not self.suppress_flow_events:
                 future = crewai_event_bus.emit(
@@ -1736,12 +1748,14 @@ class Flow(Generic[T], metaclass=FlowMeta):
         method = self._methods[start_method_name]
         enhanced_method = self._inject_trigger_payload_for_start_method(method)
 
-        result = await self._execute_method(start_method_name, enhanced_method)
+        result, finished_event_id = await self._execute_method(
+            start_method_name, enhanced_method
+        )
 
         # If start method is a router, use its result as an additional trigger
         if start_method_name in self._routers and result is not None:
             # Execute listeners for the start method name first
-            await self._execute_listeners(start_method_name, result)
+            await self._execute_listeners(start_method_name, result, finished_event_id)
             # Then execute listeners for the router result (e.g., "approved")
             router_result_trigger = FlowMethodName(str(result))
             listeners_for_result = self._find_triggered_methods(
@@ -1765,16 +1779,21 @@ class Flow(Generic[T], metaclass=FlowMeta):
                         if name not in racing_members
                     ]
                     await self._execute_racing_listeners(
-                        racing_members, other_listeners, listener_result
+                        racing_members,
+                        other_listeners,
+                        listener_result,
+                        finished_event_id,
                     )
                 else:
                     tasks = [
-                        self._execute_single_listener(listener_name, listener_result)
+                        self._execute_single_listener(
+                            listener_name, listener_result, finished_event_id
+                        )
                         for listener_name in listeners_for_result
                     ]
                     await asyncio.gather(*tasks)
         else:
-            await self._execute_listeners(start_method_name, result)
+            await self._execute_listeners(start_method_name, result, finished_event_id)
 
     def _inject_trigger_payload_for_start_method(
         self, original_method: Callable[..., Any]
@@ -1818,7 +1837,14 @@ class Flow(Generic[T], metaclass=FlowMeta):
         method: Callable[..., Any],
         *args: Any,
         **kwargs: Any,
-    ) -> Any:
+    ) -> tuple[Any, str | None]:
+        """Execute a method and emit events.
+
+        Returns:
+            A tuple of (result, finished_event_id) where finished_event_id is
+            the event_id of the MethodExecutionFinishedEvent, or None if events
+            are suppressed.
+        """
         try:
             dumped_params = {f"_{i}": arg for i, arg in enumerate(args)} | (
                 kwargs or {}
@@ -1859,21 +1885,21 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
             self._completed_methods.add(method_name)
 
+            finished_event_id: str | None = None
             if not self.suppress_flow_events:
-                future = crewai_event_bus.emit(
-                    self,
-                    MethodExecutionFinishedEvent(
-                        type="method_execution_finished",
-                        method_name=method_name,
-                        flow_name=self.name or self.__class__.__name__,
-                        state=self._copy_and_serialize_state(),
-                        result=result,
-                    ),
+                finished_event = MethodExecutionFinishedEvent(
+                    type="method_execution_finished",
+                    method_name=method_name,
+                    flow_name=self.name or self.__class__.__name__,
+                    state=self._copy_and_serialize_state(),
+                    result=result,
                 )
+                finished_event_id = finished_event.event_id
+                future = crewai_event_bus.emit(self, finished_event)
                 if future:
                     self._event_futures.append(future)
 
-            return result
+            return result, finished_event_id
         except Exception as e:
             # Check if this is a HumanFeedbackPending exception (paused, not failed)
             from crewai.flow.async_feedback.types import HumanFeedbackPending
@@ -1927,7 +1953,10 @@ class Flow(Generic[T], metaclass=FlowMeta):
             return state_copy
 
     async def _execute_listeners(
-        self, trigger_method: FlowMethodName, result: Any
+        self,
+        trigger_method: FlowMethodName,
+        result: Any,
+        triggering_event_id: str | None = None,
     ) -> None:
         """Executes all listeners and routers triggered by a method completion.
 
@@ -1938,6 +1967,8 @@ class Flow(Generic[T], metaclass=FlowMeta):
         Args:
             trigger_method: The name of the method that triggered these listeners.
             result: The result from the triggering method, passed to listeners that accept parameters.
+            triggering_event_id: The event_id of the MethodExecutionFinishedEvent that
+                triggered these listeners, used for causal chain tracking.
 
         Note:
             - Routers are executed sequentially to maintain flow control
@@ -1952,6 +1983,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
         ] = {}  # Map outcome -> HumanFeedbackResult
         current_trigger = trigger_method
         current_result = result  # Track the result to pass to each router
+        current_triggering_event_id = triggering_event_id
 
         while True:
             routers_triggered = self._find_triggered_methods(
@@ -1965,7 +1997,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 router_input = router_result_to_feedback.get(
                     str(current_trigger), current_result
                 )
-                await self._execute_single_listener(router_name, router_input)
+                current_triggering_event_id = await self._execute_single_listener(
+                    router_name, router_input, current_triggering_event_id
+                )
                 # After executing router, the router's result is the path
                 router_result = (
                     self._method_outputs[-1] if self._method_outputs else None
@@ -2008,12 +2042,15 @@ class Flow(Generic[T], metaclass=FlowMeta):
                             if name not in racing_members
                         ]
                         await self._execute_racing_listeners(
-                            racing_members, other_listeners, listener_result
+                            racing_members,
+                            other_listeners,
+                            listener_result,
+                            triggering_event_id,
                         )
                     else:
                         tasks = [
                             self._execute_single_listener(
-                                listener_name, listener_result
+                                listener_name, listener_result, triggering_event_id
                             )
                             for listener_name in listeners_triggered
                         ]
@@ -2192,8 +2229,11 @@ class Flow(Generic[T], metaclass=FlowMeta):
         return triggered
 
     async def _execute_single_listener(
-        self, listener_name: FlowMethodName, result: Any
-    ) -> None:
+        self,
+        listener_name: FlowMethodName,
+        result: Any,
+        triggering_event_id: str | None = None,
+    ) -> str | None:
         """Executes a single listener method with proper event handling.
 
         This internal method manages the execution of an individual listener,
@@ -2202,6 +2242,12 @@ class Flow(Generic[T], metaclass=FlowMeta):
         Args:
             listener_name: The name of the listener method to execute.
             result: The result from the triggering method, which may be passed to the listener if it accepts parameters.
+            triggering_event_id: The event_id of the event that triggered this listener,
+                used for causal chain tracking.
+
+        Returns:
+            The event_id of the MethodExecutionFinishedEvent emitted by this listener,
+            or None if events are suppressed.
 
         Note:
             - Inspects method signature to determine if it accepts the trigger result
@@ -2227,7 +2273,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
                         ):
                             # This conditional start was executed, continue its chain
                             await self._execute_start_method(start_method_name)
-                return
+                return None
             # For cyclic flows, clear from completed to allow re-execution
             self._completed_methods.discard(listener_name)
             # Also clear from fired OR listeners for cyclic flows
@@ -2240,15 +2286,30 @@ class Flow(Generic[T], metaclass=FlowMeta):
             params = list(sig.parameters.values())
             method_params = [p for p in params if p.name != "self"]
 
-            if method_params:
-                listener_result = await self._execute_method(
-                    listener_name, method, result
-                )
+            if triggering_event_id:
+                with triggered_by_scope(triggering_event_id):
+                    if method_params:
+                        listener_result, finished_event_id = await self._execute_method(
+                            listener_name, method, result
+                        )
+                    else:
+                        listener_result, finished_event_id = await self._execute_method(
+                            listener_name, method
+                        )
             else:
-                listener_result = await self._execute_method(listener_name, method)
+                if method_params:
+                    listener_result, finished_event_id = await self._execute_method(
+                        listener_name, method, result
+                    )
+                else:
+                    listener_result, finished_event_id = await self._execute_method(
+                        listener_name, method
+                    )
 
             # Execute listeners (and possibly routers) of this listener
-            await self._execute_listeners(listener_name, listener_result)
+            await self._execute_listeners(
+                listener_name, listener_result, finished_event_id
+            )
 
             # If this listener is also a router (e.g., has @human_feedback with emit),
             # we need to trigger listeners for the router result as well
@@ -2275,15 +2336,22 @@ class Flow(Generic[T], metaclass=FlowMeta):
                             if name not in racing_members
                         ]
                         await self._execute_racing_listeners(
-                            racing_members, other_listeners, feedback_result
+                            racing_members,
+                            other_listeners,
+                            feedback_result,
+                            finished_event_id,
                         )
                     else:
                         tasks = [
-                            self._execute_single_listener(name, feedback_result)
+                            self._execute_single_listener(
+                                name, feedback_result, finished_event_id
+                            )
                             for name in listeners_for_result
                         ]
                         await asyncio.gather(*tasks)
 
+            return finished_event_id
+
         except Exception as e:
             # Don't log HumanFeedbackPending as an error - it's expected control flow
             from crewai.flow.async_feedback.types import HumanFeedbackPending

lib/crewai/src/crewai/llms/providers/azure/completion.py

@@ -124,11 +124,8 @@ class AzureCompletion(BaseLLM):
         )
 
         self.api_key = api_key or os.getenv("AZURE_API_KEY")
-        # Support both 'endpoint' and 'base_url' parameters for consistency with other providers
-        base_url = kwargs.get("base_url")
         self.endpoint = (
             endpoint
-            or base_url
             or os.getenv("AZURE_ENDPOINT")
             or os.getenv("AZURE_OPENAI_ENDPOINT")
             or os.getenv("AZURE_API_BASE")
@@ -173,44 +170,11 @@ class AzureCompletion(BaseLLM):
             prefix in model.lower() for prefix in ["gpt-", "o1-", "text-"]
         )
 
-        # Azure OpenAI endpoints use openai.azure.com domain and require deployment path
-        # Other Azure AI endpoints (cognitiveservices.azure.com, etc.) are also valid
         self.is_azure_openai_endpoint = (
             "openai.azure.com" in self.endpoint
             and "/openai/deployments/" in self.endpoint
         )
 
-        # Check if this is any Azure endpoint (for proper API handling)
-        self.is_azure_endpoint = self._is_azure_endpoint(self.endpoint)
-
-    @staticmethod
-    def _is_azure_endpoint(endpoint: str) -> bool:
-        """Check if the endpoint is an Azure endpoint.
-
-        Azure endpoints can have various domain formats:
-        - openai.azure.com (Azure OpenAI Service)
-        - cognitiveservices.azure.com (Azure AI Services / Cognitive Services)
-        - services.ai.azure.com (Azure AI Services)
-        - Other *.azure.com domains
-
-        Args:
-            endpoint: The endpoint URL to check
-
-        Returns:
-            True if the endpoint is an Azure endpoint, False otherwise
-        """
-        azure_domains = [
-            "openai.azure.com",
-            "cognitiveservices.azure.com",
-            "services.ai.azure.com",
-        ]
-        # Check for known Azure domains
-        for domain in azure_domains:
-            if domain in endpoint:
-                return True
-        # Also check for generic .azure.com pattern (e.g., cservices.azure.com)
-        return ".azure.com" in endpoint
-
     @staticmethod
     def _validate_and_fix_endpoint(endpoint: str, model: str) -> str:
         """Validate and fix Azure endpoint URL format.
@@ -218,9 +182,6 @@ class AzureCompletion(BaseLLM):
         Azure OpenAI endpoints should be in the format:
         https://<resource-name>.openai.azure.com/openai/deployments/<deployment-name>
 
-        Other Azure AI endpoints (cognitiveservices.azure.com, etc.) are used as-is
-        since they may have different URL structures.
-
         Args:
             endpoint: The endpoint URL
             model: The model/deployment name
@@ -228,8 +189,6 @@ class AzureCompletion(BaseLLM):
         Returns:
             Validated and potentially corrected endpoint URL
         """
-        # Only auto-construct deployment path for Azure OpenAI endpoints (openai.azure.com)
-        # Other Azure endpoints (cognitiveservices.azure.com, etc.) should be used as-is
         if "openai.azure.com" in endpoint and "/openai/deployments/" not in endpoint:
             endpoint = endpoint.rstrip("/")
 

lib/crewai/src/crewai/tools/tool_usage.py

@@ -241,6 +241,9 @@ class ToolUsage:
                 if self.task:
                     self.task.increment_tools_errors()
 
+        started_at = time.time()
+        started_event_emitted = False
+
         if self.agent:
             event_data = {
                 "agent_key": self.agent.key,
@@ -258,151 +261,162 @@ class ToolUsage:
                 event_data["task_name"] = self.task.name or self.task.description
                 event_data["task_id"] = str(self.task.id)
             crewai_event_bus.emit(self, ToolUsageStartedEvent(**event_data))
+            started_event_emitted = True
 
-        started_at = time.time()
         from_cache = False
         result = None  # type: ignore
+        should_retry = False
+        available_tool = None
 
-        if self.tools_handler and self.tools_handler.cache:
-            input_str = ""
-            if calling.arguments:
-                if isinstance(calling.arguments, dict):
-                    input_str = json.dumps(calling.arguments)
-                else:
-                    input_str = str(calling.arguments)
+        try:
+            if self.tools_handler and self.tools_handler.cache:
+                input_str = ""
+                if calling.arguments:
+                    if isinstance(calling.arguments, dict):
+                        input_str = json.dumps(calling.arguments)
+                    else:
+                        input_str = str(calling.arguments)
 
-            result = self.tools_handler.cache.read(
-                tool=calling.tool_name, input=input_str
-            )  # type: ignore
-            from_cache = result is not None
+                result = self.tools_handler.cache.read(
+                    tool=calling.tool_name, input=input_str
+                )  # type: ignore
+                from_cache = result is not None
 
-        available_tool = next(
-            (
-                available_tool
-                for available_tool in self.tools
-                if available_tool.name == tool.name
-            ),
-            None,
-        )
+            available_tool = next(
+                (
+                    available_tool
+                    for available_tool in self.tools
+                    if available_tool.name == tool.name
+                ),
+                None,
+            )
 
-        usage_limit_error = self._check_usage_limit(available_tool, tool.name)
-        if usage_limit_error:
-            try:
+            usage_limit_error = self._check_usage_limit(available_tool, tool.name)
+            if usage_limit_error:
                 result = usage_limit_error
                 self._telemetry.tool_usage_error(llm=self.function_calling_llm)
-                return self._format_result(result=result)
-            except Exception:
-                if self.task:
-                    self.task.increment_tools_errors()
-
-        if result is None:
-            try:
-                if calling.tool_name in [
-                    "Delegate work to coworker",
-                    "Ask question to coworker",
-                ]:
-                    coworker = (
-                        calling.arguments.get("coworker") if calling.arguments else None
-                    )
-                    if self.task:
-                        self.task.increment_delegations(coworker)
-
-                if calling.arguments:
-                    try:
-                        acceptable_args = tool.args_schema.model_json_schema()[
-                            "properties"
-                        ].keys()
-                        arguments = {
-                            k: v
-                            for k, v in calling.arguments.items()
-                            if k in acceptable_args
-                        }
-                        arguments = self._add_fingerprint_metadata(arguments)
-                        result = await tool.ainvoke(input=arguments)
-                    except Exception:
-                        arguments = calling.arguments
-                        arguments = self._add_fingerprint_metadata(arguments)
-                        result = await tool.ainvoke(input=arguments)
-                else:
-                    arguments = self._add_fingerprint_metadata({})
-                    result = await tool.ainvoke(input=arguments)
-            except Exception as e:
-                self.on_tool_error(tool=tool, tool_calling=calling, e=e)
-                self._run_attempts += 1
-                if self._run_attempts > self._max_parsing_attempts:
-                    self._telemetry.tool_usage_error(llm=self.function_calling_llm)
-                    error_message = self._i18n.errors("tool_usage_exception").format(
-                        error=e, tool=tool.name, tool_inputs=tool.description
-                    )
-                    error = ToolUsageError(
-                        f"\n{error_message}.\nMoving on then. {self._i18n.slice('format').format(tool_names=self.tools_names)}"
-                    ).message
-                    if self.task:
-                        self.task.increment_tools_errors()
-                    if self.agent and self.agent.verbose:
-                        self._printer.print(
-                            content=f"\n\n{error_message}\n", color="red"
+                result = self._format_result(result=result)
+                # Don't return early - fall through to finally block
+            elif result is None:
+                try:
+                    if calling.tool_name in [
+                        "Delegate work to coworker",
+                        "Ask question to coworker",
+                    ]:
+                        coworker = (
+                            calling.arguments.get("coworker")
+                            if calling.arguments
+                            else None
                         )
-                    return error
+                        if self.task:
+                            self.task.increment_delegations(coworker)
 
-                if self.task:
-                    self.task.increment_tools_errors()
-                return await self.ause(calling=calling, tool_string=tool_string)
+                    if calling.arguments:
+                        try:
+                            acceptable_args = tool.args_schema.model_json_schema()[
+                                "properties"
+                            ].keys()
+                            arguments = {
+                                k: v
+                                for k, v in calling.arguments.items()
+                                if k in acceptable_args
+                            }
+                            arguments = self._add_fingerprint_metadata(arguments)
+                            result = await tool.ainvoke(input=arguments)
+                        except Exception:
+                            arguments = calling.arguments
+                            arguments = self._add_fingerprint_metadata(arguments)
+                            result = await tool.ainvoke(input=arguments)
+                    else:
+                        arguments = self._add_fingerprint_metadata({})
+                        result = await tool.ainvoke(input=arguments)
 
-            if self.tools_handler:
-                should_cache = True
-                if (
-                    hasattr(available_tool, "cache_function")
-                    and available_tool.cache_function
-                ):
-                    should_cache = available_tool.cache_function(
-                        calling.arguments, result
+                    if self.tools_handler:
+                        should_cache = True
+                        if (
+                            hasattr(available_tool, "cache_function")
+                            and available_tool.cache_function
+                        ):
+                            should_cache = available_tool.cache_function(
+                                calling.arguments, result
+                            )
+
+                        self.tools_handler.on_tool_use(
+                            calling=calling, output=result, should_cache=should_cache
+                        )
+
+                    self._telemetry.tool_usage(
+                        llm=self.function_calling_llm,
+                        tool_name=tool.name,
+                        attempts=self._run_attempts,
                     )
+                    result = self._format_result(result=result)
+                    data = {
+                        "result": result,
+                        "tool_name": tool.name,
+                        "tool_args": calling.arguments,
+                    }
 
-                self.tools_handler.on_tool_use(
-                    calling=calling, output=result, should_cache=should_cache
+                    if (
+                        hasattr(available_tool, "result_as_answer")
+                        and available_tool.result_as_answer
+                    ):
+                        result_as_answer = available_tool.result_as_answer
+                        data["result_as_answer"] = result_as_answer
+
+                    if self.agent and hasattr(self.agent, "tools_results"):
+                        self.agent.tools_results.append(data)
+
+                    if available_tool and hasattr(
+                        available_tool, "current_usage_count"
+                    ):
+                        available_tool.current_usage_count += 1
+                        if (
+                            hasattr(available_tool, "max_usage_count")
+                            and available_tool.max_usage_count is not None
+                        ):
+                            self._printer.print(
+                                content=f"Tool '{available_tool.name}' usage: {available_tool.current_usage_count}/{available_tool.max_usage_count}",
+                                color="blue",
+                            )
+
+                except Exception as e:
+                    self.on_tool_error(tool=tool, tool_calling=calling, e=e)
+                    self._run_attempts += 1
+                    if self._run_attempts > self._max_parsing_attempts:
+                        self._telemetry.tool_usage_error(llm=self.function_calling_llm)
+                        error_message = self._i18n.errors(
+                            "tool_usage_exception"
+                        ).format(error=e, tool=tool.name, tool_inputs=tool.description)
+                        result = ToolUsageError(
+                            f"\n{error_message}.\nMoving on then. {self._i18n.slice('format').format(tool_names=self.tools_names)}"
+                        ).message
+                        if self.task:
+                            self.task.increment_tools_errors()
+                        if self.agent and self.agent.verbose:
+                            self._printer.print(
+                                content=f"\n\n{error_message}\n", color="red"
+                            )
+                    else:
+                        if self.task:
+                            self.task.increment_tools_errors()
+                        should_retry = True
+            else:
+                result = self._format_result(result=result)
+
+        finally:
+            if started_event_emitted:
+                self.on_tool_use_finished(
+                    tool=tool,
+                    tool_calling=calling,
+                    from_cache=from_cache,
+                    started_at=started_at,
+                    result=result,
                 )
 
-        self._telemetry.tool_usage(
-            llm=self.function_calling_llm,
-            tool_name=tool.name,
-            attempts=self._run_attempts,
-        )
-        result = self._format_result(result=result)
-        data = {
-            "result": result,
-            "tool_name": tool.name,
-            "tool_args": calling.arguments,
-        }
-
-        self.on_tool_use_finished(
-            tool=tool,
-            tool_calling=calling,
-            from_cache=from_cache,
-            started_at=started_at,
-            result=result,
-        )
-
-        if (
-            hasattr(available_tool, "result_as_answer")
-            and available_tool.result_as_answer  # type: ignore
-        ):
-            result_as_answer = available_tool.result_as_answer  # type: ignore
-            data["result_as_answer"] = result_as_answer  # type: ignore
-
-        if self.agent and hasattr(self.agent, "tools_results"):
-            self.agent.tools_results.append(data)
-
-        if available_tool and hasattr(available_tool, "current_usage_count"):
-            available_tool.current_usage_count += 1
-            if (
-                hasattr(available_tool, "max_usage_count")
-                and available_tool.max_usage_count is not None
-            ):
-                self._printer.print(
-                    content=f"Tool '{available_tool.name}' usage: {available_tool.current_usage_count}/{available_tool.max_usage_count}",
-                    color="blue",
-                )
+        # Handle retry after finally block ensures finished event was emitted
+        if should_retry:
+            return await self.ause(calling=calling, tool_string=tool_string)
 
         return result
 
@@ -412,6 +426,7 @@ class ToolUsage:
         tool: CrewStructuredTool,
         calling: ToolCalling | InstructorToolCalling,
     ) -> str:
+        # Repeated usage check happens before event emission - safe to return early
         if self._check_tool_repeated_usage(calling=calling):
             try:
                 result = self._i18n.errors("task_repeated_usage").format(
@@ -428,6 +443,9 @@ class ToolUsage:
                 if self.task:
                     self.task.increment_tools_errors()
 
+        started_at = time.time()
+        started_event_emitted = False
+
         if self.agent:
             event_data = {
                 "agent_key": self.agent.key,
@@ -446,155 +464,162 @@ class ToolUsage:
                 event_data["task_name"] = self.task.name or self.task.description
                 event_data["task_id"] = str(self.task.id)
             crewai_event_bus.emit(self, ToolUsageStartedEvent(**event_data))
+            started_event_emitted = True
 
-        started_at = time.time()
         from_cache = False
         result = None  # type: ignore
+        should_retry = False
+        available_tool = None
 
-        if self.tools_handler and self.tools_handler.cache:
-            input_str = ""
-            if calling.arguments:
-                if isinstance(calling.arguments, dict):
-                    import json
+        try:
+            if self.tools_handler and self.tools_handler.cache:
+                input_str = ""
+                if calling.arguments:
+                    if isinstance(calling.arguments, dict):
+                        input_str = json.dumps(calling.arguments)
+                    else:
+                        input_str = str(calling.arguments)
 
-                    input_str = json.dumps(calling.arguments)
-                else:
-                    input_str = str(calling.arguments)
+                result = self.tools_handler.cache.read(
+                    tool=calling.tool_name, input=input_str
+                )  # type: ignore
+                from_cache = result is not None
 
-            result = self.tools_handler.cache.read(
-                tool=calling.tool_name, input=input_str
-            )  # type: ignore
-            from_cache = result is not None
+            available_tool = next(
+                (
+                    available_tool
+                    for available_tool in self.tools
+                    if available_tool.name == tool.name
+                ),
+                None,
+            )
 
-        available_tool = next(
-            (
-                available_tool
-                for available_tool in self.tools
-                if available_tool.name == tool.name
-            ),
-            None,
-        )
-
-        usage_limit_error = self._check_usage_limit(available_tool, tool.name)
-        if usage_limit_error:
-            try:
+            usage_limit_error = self._check_usage_limit(available_tool, tool.name)
+            if usage_limit_error:
                 result = usage_limit_error
                 self._telemetry.tool_usage_error(llm=self.function_calling_llm)
-                return self._format_result(result=result)
-            except Exception:
-                if self.task:
-                    self.task.increment_tools_errors()
-
-        if result is None:
-            try:
-                if calling.tool_name in [
-                    "Delegate work to coworker",
-                    "Ask question to coworker",
-                ]:
-                    coworker = (
-                        calling.arguments.get("coworker") if calling.arguments else None
-                    )
-                    if self.task:
-                        self.task.increment_delegations(coworker)
-
-                if calling.arguments:
-                    try:
-                        acceptable_args = tool.args_schema.model_json_schema()[
-                            "properties"
-                        ].keys()
-                        arguments = {
-                            k: v
-                            for k, v in calling.arguments.items()
-                            if k in acceptable_args
-                        }
-                        # Add fingerprint metadata if available
-                        arguments = self._add_fingerprint_metadata(arguments)
-                        result = tool.invoke(input=arguments)
-                    except Exception:
-                        arguments = calling.arguments
-                        # Add fingerprint metadata if available
-                        arguments = self._add_fingerprint_metadata(arguments)
-                        result = tool.invoke(input=arguments)
-                else:
-                    # Add fingerprint metadata even to empty arguments
-                    arguments = self._add_fingerprint_metadata({})
-                    result = tool.invoke(input=arguments)
-            except Exception as e:
-                self.on_tool_error(tool=tool, tool_calling=calling, e=e)
-                self._run_attempts += 1
-                if self._run_attempts > self._max_parsing_attempts:
-                    self._telemetry.tool_usage_error(llm=self.function_calling_llm)
-                    error_message = self._i18n.errors("tool_usage_exception").format(
-                        error=e, tool=tool.name, tool_inputs=tool.description
-                    )
-                    error = ToolUsageError(
-                        f"\n{error_message}.\nMoving on then. {self._i18n.slice('format').format(tool_names=self.tools_names)}"
-                    ).message
-                    if self.task:
-                        self.task.increment_tools_errors()
-                    if self.agent and self.agent.verbose:
-                        self._printer.print(
-                            content=f"\n\n{error_message}\n", color="red"
+                result = self._format_result(result=result)
+                # Don't return early - fall through to finally block
+            elif result is None:
+                try:
+                    if calling.tool_name in [
+                        "Delegate work to coworker",
+                        "Ask question to coworker",
+                    ]:
+                        coworker = (
+                            calling.arguments.get("coworker")
+                            if calling.arguments
+                            else None
                         )
-                    return error
+                        if self.task:
+                            self.task.increment_delegations(coworker)
 
-                if self.task:
-                    self.task.increment_tools_errors()
-                return self.use(calling=calling, tool_string=tool_string)
+                    if calling.arguments:
+                        try:
+                            acceptable_args = tool.args_schema.model_json_schema()[
+                                "properties"
+                            ].keys()
+                            arguments = {
+                                k: v
+                                for k, v in calling.arguments.items()
+                                if k in acceptable_args
+                            }
+                            arguments = self._add_fingerprint_metadata(arguments)
+                            result = tool.invoke(input=arguments)
+                        except Exception:
+                            arguments = calling.arguments
+                            arguments = self._add_fingerprint_metadata(arguments)
+                            result = tool.invoke(input=arguments)
+                    else:
+                        arguments = self._add_fingerprint_metadata({})
+                        result = tool.invoke(input=arguments)
 
-            if self.tools_handler:
-                should_cache = True
-                if (
-                    hasattr(available_tool, "cache_function")
-                    and available_tool.cache_function
-                ):
-                    should_cache = available_tool.cache_function(
-                        calling.arguments, result
+                    if self.tools_handler:
+                        should_cache = True
+                        if (
+                            hasattr(available_tool, "cache_function")
+                            and available_tool.cache_function
+                        ):
+                            should_cache = available_tool.cache_function(
+                                calling.arguments, result
+                            )
+
+                        self.tools_handler.on_tool_use(
+                            calling=calling, output=result, should_cache=should_cache
+                        )
+
+                    self._telemetry.tool_usage(
+                        llm=self.function_calling_llm,
+                        tool_name=tool.name,
+                        attempts=self._run_attempts,
                     )
+                    result = self._format_result(result=result)
+                    data = {
+                        "result": result,
+                        "tool_name": tool.name,
+                        "tool_args": calling.arguments,
+                    }
 
-                self.tools_handler.on_tool_use(
-                    calling=calling, output=result, should_cache=should_cache
+                    if (
+                        hasattr(available_tool, "result_as_answer")
+                        and available_tool.result_as_answer
+                    ):
+                        result_as_answer = available_tool.result_as_answer
+                        data["result_as_answer"] = result_as_answer
+
+                    if self.agent and hasattr(self.agent, "tools_results"):
+                        self.agent.tools_results.append(data)
+
+                    if available_tool and hasattr(
+                        available_tool, "current_usage_count"
+                    ):
+                        available_tool.current_usage_count += 1
+                        if (
+                            hasattr(available_tool, "max_usage_count")
+                            and available_tool.max_usage_count is not None
+                        ):
+                            self._printer.print(
+                                content=f"Tool '{available_tool.name}' usage: {available_tool.current_usage_count}/{available_tool.max_usage_count}",
+                                color="blue",
+                            )
+
+                except Exception as e:
+                    self.on_tool_error(tool=tool, tool_calling=calling, e=e)
+                    self._run_attempts += 1
+                    if self._run_attempts > self._max_parsing_attempts:
+                        self._telemetry.tool_usage_error(llm=self.function_calling_llm)
+                        error_message = self._i18n.errors(
+                            "tool_usage_exception"
+                        ).format(error=e, tool=tool.name, tool_inputs=tool.description)
+                        result = ToolUsageError(
+                            f"\n{error_message}.\nMoving on then. {self._i18n.slice('format').format(tool_names=self.tools_names)}"
+                        ).message
+                        if self.task:
+                            self.task.increment_tools_errors()
+                        if self.agent and self.agent.verbose:
+                            self._printer.print(
+                                content=f"\n\n{error_message}\n", color="red"
+                            )
+                    else:
+                        if self.task:
+                            self.task.increment_tools_errors()
+                        should_retry = True
+            else:
+                result = self._format_result(result=result)
+
+        finally:
+            if started_event_emitted:
+                self.on_tool_use_finished(
+                    tool=tool,
+                    tool_calling=calling,
+                    from_cache=from_cache,
+                    started_at=started_at,
+                    result=result,
                 )
-        self._telemetry.tool_usage(
-            llm=self.function_calling_llm,
-            tool_name=tool.name,
-            attempts=self._run_attempts,
-        )
-        result = self._format_result(result=result)
-        data = {
-            "result": result,
-            "tool_name": tool.name,
-            "tool_args": calling.arguments,
-        }
 
-        self.on_tool_use_finished(
-            tool=tool,
-            tool_calling=calling,
-            from_cache=from_cache,
-            started_at=started_at,
-            result=result,
-        )
-
-        if (
-            hasattr(available_tool, "result_as_answer")
-            and available_tool.result_as_answer  # type: ignore # Item "None" of "Any | None" has no attribute "cache_function"
-        ):
-            result_as_answer = available_tool.result_as_answer  # type: ignore # Item "None" of "Any | None" has no attribute "result_as_answer"
-            data["result_as_answer"] = result_as_answer  # type: ignore
-
-        if self.agent and hasattr(self.agent, "tools_results"):
-            self.agent.tools_results.append(data)
-
-        if available_tool and hasattr(available_tool, "current_usage_count"):
-            available_tool.current_usage_count += 1
-            if (
-                hasattr(available_tool, "max_usage_count")
-                and available_tool.max_usage_count is not None
-            ):
-                self._printer.print(
-                    content=f"Tool '{available_tool.name}' usage: {available_tool.current_usage_count}/{available_tool.max_usage_count}",
-                    color="blue",
-                )
+        # Handle retry after finally block ensures finished event was emitted
+        if should_retry:
+            return self.use(calling=calling, tool_string=tool_string)
 
         return result
 

lib/crewai/tests/cassettes/events/TestAgentEventOrdering.test_agent_events_have_event_ids.yaml

@@ -0,0 +1,118 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Helper. You help.\nYour
+      personal goal is: Help with tasks\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: Say ''done''
+      and nothing else.\n\nThis is the expected criteria for your final answer: The
+      word done.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '794'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D087GaV1OkB4Yos5MqLYqRSpLLZkV\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768923570,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: done\",\n        \"refusal\": null,\n        \"annotations\": []\n
+        \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 159,\n    \"completion_tokens\":
+        14,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 15:39:30 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '446'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '472'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestAgentEventOrdering.test_llm_events_have_parent.yaml

@@ -0,0 +1,118 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Helper. You help.\nYour
+      personal goal is: Help with tasks\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: Say ''hi''
+      and nothing else.\n\nThis is the expected criteria for your final answer: The
+      word hi.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '790'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D087HNU70QfEltqUwIaR3WflNQJMq\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768923571,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: hi\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 159,\n    \"completion_tokens\": 14,\n
+        \   \"total_tokens\": 173,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 15:39:31 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '401'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '429'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestCrewEventOrdering.test_crew_completed_after_started.yaml

@@ -0,0 +1,118 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Responder. You give short
+      answers.\nYour personal goal is: Respond briefly\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: Say
+      ''yes'' and nothing else.\n\nThis is the expected criteria for your final answer:
+      The word yes.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '809'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D0876LY6Tp1gWmwQ5f2A6EsqdbLOK\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768923560,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: yes\",\n        \"refusal\": null,\n        \"annotations\": []\n
+        \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 161,\n    \"completion_tokens\":
+        14,\n    \"total_tokens\": 175,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 15:39:21 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '519'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '758'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestCrewEventOrdering.test_crew_events_have_event_ids.yaml

@@ -0,0 +1,118 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Responder. You give short
+      answers.\nYour personal goal is: Respond briefly\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: Say
+      ''hello'' and nothing else.\n\nThis is the expected criteria for your final
+      answer: The word hello.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '813'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D0874asFandwADBjb4DfArsTUyu8K\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768923558,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: hello\",\n        \"refusal\": null,\n        \"annotations\": []\n
+        \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 161,\n    \"completion_tokens\":
+        14,\n    \"total_tokens\": 175,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 15:39:18 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '478'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '497'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestCrewEventOrdering.test_task_parent_is_crew.yaml

@@ -0,0 +1,118 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Responder. You give short
+      answers.\nYour personal goal is: Respond briefly\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: Say
+      ''ok'' and nothing else.\n\nThis is the expected criteria for your final answer:
+      The word ok.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '807'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D0875A6FEJ2ZFKVHohoJdbBgKEMNx\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768923559,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: ok\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 161,\n    \"completion_tokens\": 14,\n
+        \   \"total_tokens\": 175,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 15:39:19 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '406'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '439'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestFlowWithCrewEventOrdering.test_crew_parent_is_method.yaml

@@ -0,0 +1,118 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Worker. You work.\nYour
+      personal goal is: Do work\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: Say ''go'' and nothing
+      else.\n\nThis is the expected criteria for your final answer: The word go.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '782'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - async:asyncio
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D09c91Qh5LJ73NLwFrcRhThK7zNKS\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768929329,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: go\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 158,\n    \"completion_tokens\": 14,\n
+        \   \"total_tokens\": 172,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 17:15:30 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '521'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '781'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestFlowWithCrewEventOrdering.test_flow_events_have_ids.yaml

@@ -0,0 +1,118 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Worker. You work.\nYour
+      personal goal is: Do work\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: Say ''complete''
+      and nothing else.\n\nThis is the expected criteria for your final answer: The
+      word complete.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '794'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - async:asyncio
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D09bYGfIe5pA04mBGuMO94KLyKhry\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768929292,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: complete\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 158,\n    \"completion_tokens\":
+        14,\n    \"total_tokens\": 172,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 17:14:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '436'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '660'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestFlowWithCrewEventOrdering.test_method_parent_is_flow.yaml

@@ -0,0 +1,118 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Worker. You work.\nYour
+      personal goal is: Do work\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: Say ''ready'' and
+      nothing else.\n\nThis is the expected criteria for your final answer: The word
+      ready.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '788'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - async:asyncio
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D09cBIfuX53tF9rWbEKXXIr20uzSv\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768929331,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: ready\",\n        \"refusal\": null,\n        \"annotations\": []\n
+        \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 158,\n    \"completion_tokens\":
+        14,\n    \"total_tokens\": 172,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 17:15:32 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '517'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '1841'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestFlowWithMultipleCrewsEventOrdering.test_second_crew_after_first.yaml

@@ -0,0 +1,234 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are First. You go first.\nYour
+      personal goal is: Be first\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: Say ''a'' and nothing
+      else.\n\nThis is the expected criteria for your final answer: The letter a.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '786'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - async:asyncio
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D09rkgXjWfa1XwICCnLAVV3LXFlUZ\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768930296,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: a\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 159,\n    \"completion_tokens\": 14,\n
+        \   \"total_tokens\": 173,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 17:31:37 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '418'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '443'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Second. You go second.\nYour
+      personal goal is: Be second\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: Say ''b'' and nothing
+      else.\n\nThis is the expected criteria for your final answer: The letter b.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '789'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - async:asyncio
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D09rlVUPgS5haPGYgA4RmW9EfPArd\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768930297,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: b\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 159,\n    \"completion_tokens\": 14,\n
+        \   \"total_tokens\": 173,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 17:31:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '345'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '658'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestFlowWithMultipleCrewsEventOrdering.test_tasks_have_correct_crew_parents.yaml

@@ -0,0 +1,234 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Alpha. You are alpha.\nYour
+      personal goal is: Do alpha work\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: Say ''alpha''
+      and nothing else.\n\nThis is the expected criteria for your final answer: The
+      word alpha.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '798'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - async:asyncio
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D09ri7edf1TcYqD0vAkS3IjNkai3V\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768930294,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: alpha\",\n        \"refusal\": null,\n        \"annotations\": []\n
+        \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 160,\n    \"completion_tokens\":
+        14,\n    \"total_tokens\": 174,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 17:31:34 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '491'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '513'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Beta. You are beta.\nYour
+      personal goal is: Do beta work\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: Say ''beta''
+      and nothing else.\n\nThis is the expected criteria for your final answer: The
+      word beta.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '793'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - async:asyncio
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D09rj5wiKmsX5P72qH0GEKL5pQEq6\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768930295,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: beta\",\n        \"refusal\": null,\n        \"annotations\": []\n
+        \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+        \ ],\n  \"usage\": {\n    \"prompt_tokens\": 160,\n    \"completion_tokens\":
+        14,\n    \"total_tokens\": 174,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 17:31:35 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '506'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '741'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/events/TestFlowWithMultipleCrewsEventOrdering.test_two_crews_have_different_ids.yaml

@@ -0,0 +1,234 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are First. You go first.\nYour
+      personal goal is: Be first\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: Say ''1'' and nothing
+      else.\n\nThis is the expected criteria for your final answer: The number 1.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '786'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - async:asyncio
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D09rmoYXlYGqmDh0Ca3r9xunjmE7k\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768930298,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: 1\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 160,\n    \"completion_tokens\": 15,\n
+        \   \"total_tokens\": 175,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 17:31:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '387'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '403'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Second. You go second.\nYour
+      personal goal is: Be second\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: Say ''2'' and nothing
+      else.\n\nThis is the expected criteria for your final answer: The number 2.\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-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '789'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - async:asyncio
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D09rnDNZsxICQvSZrx5rlgMdc2Tbp\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1768930299,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+        Answer: 2\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
+        \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        \ \"usage\": {\n    \"prompt_tokens\": 160,\n    \"completion_tokens\": 15,\n
+        \   \"total_tokens\": 175,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 20 Jan 2026 17:31:39 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '560'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '581'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/events/test_event_context.py

@@ -0,0 +1,180 @@
+"""Tests for event context management."""
+
+import pytest
+
+from crewai.events.event_context import (
+    SCOPE_ENDING_EVENTS,
+    SCOPE_STARTING_EVENTS,
+    VALID_EVENT_PAIRS,
+    EmptyStackError,
+    EventPairingError,
+    MismatchBehavior,
+    StackDepthExceededError,
+    _event_context_config,
+    EventContextConfig,
+    get_current_parent_id,
+    get_enclosing_parent_id,
+    get_last_event_id,
+    get_triggering_event_id,
+    handle_empty_pop,
+    handle_mismatch,
+    pop_event_scope,
+    push_event_scope,
+    reset_last_event_id,
+    set_last_event_id,
+    set_triggering_event_id,
+    triggered_by_scope,
+)
+
+
+class TestStackOperations:
+    """Tests for stack push/pop operations."""
+
+    def test_empty_stack_returns_none(self) -> None:
+        assert get_current_parent_id() is None
+        assert get_enclosing_parent_id() is None
+
+    def test_push_and_get_parent(self) -> None:
+        push_event_scope("event-1", "task_started")
+        assert get_current_parent_id() == "event-1"
+
+    def test_nested_push(self) -> None:
+        push_event_scope("event-1", "crew_kickoff_started")
+        push_event_scope("event-2", "task_started")
+        assert get_current_parent_id() == "event-2"
+        assert get_enclosing_parent_id() == "event-1"
+
+    def test_pop_restores_parent(self) -> None:
+        push_event_scope("event-1", "crew_kickoff_started")
+        push_event_scope("event-2", "task_started")
+        popped = pop_event_scope()
+        assert popped == ("event-2", "task_started")
+        assert get_current_parent_id() == "event-1"
+
+    def test_pop_empty_stack_returns_none(self) -> None:
+        assert pop_event_scope() is None
+
+
+class TestStackDepthLimit:
+    """Tests for stack depth limit."""
+
+    def test_depth_limit_exceeded_raises(self) -> None:
+        _event_context_config.set(EventContextConfig(max_stack_depth=3))
+
+        push_event_scope("event-1", "type-1")
+        push_event_scope("event-2", "type-2")
+        push_event_scope("event-3", "type-3")
+
+        with pytest.raises(StackDepthExceededError):
+            push_event_scope("event-4", "type-4")
+
+
+class TestMismatchHandling:
+    """Tests for mismatch behavior."""
+
+    def test_handle_mismatch_raises_when_configured(self) -> None:
+        _event_context_config.set(
+            EventContextConfig(mismatch_behavior=MismatchBehavior.RAISE)
+        )
+
+        with pytest.raises(EventPairingError):
+            handle_mismatch("task_completed", "llm_call_started", "task_started")
+
+    def test_handle_empty_pop_raises_when_configured(self) -> None:
+        _event_context_config.set(
+            EventContextConfig(empty_pop_behavior=MismatchBehavior.RAISE)
+        )
+
+        with pytest.raises(EmptyStackError):
+            handle_empty_pop("task_completed")
+
+
+class TestEventTypeSets:
+    """Tests for event type set completeness."""
+
+    def test_all_ending_events_have_pairs(self) -> None:
+        for ending_event in SCOPE_ENDING_EVENTS:
+            assert ending_event in VALID_EVENT_PAIRS
+
+    def test_all_pairs_reference_starting_events(self) -> None:
+        for ending_event, starting_event in VALID_EVENT_PAIRS.items():
+            assert starting_event in SCOPE_STARTING_EVENTS
+
+    def test_starting_and_ending_are_disjoint(self) -> None:
+        overlap = SCOPE_STARTING_EVENTS & SCOPE_ENDING_EVENTS
+        assert not overlap
+
+
+class TestLastEventIdTracking:
+    """Tests for linear chain event ID tracking."""
+
+    def test_initial_last_event_id_is_none(self) -> None:
+        reset_last_event_id()
+        assert get_last_event_id() is None
+
+    def test_set_and_get_last_event_id(self) -> None:
+        reset_last_event_id()
+        set_last_event_id("event-123")
+        assert get_last_event_id() == "event-123"
+
+    def test_reset_clears_last_event_id(self) -> None:
+        set_last_event_id("event-123")
+        reset_last_event_id()
+        assert get_last_event_id() is None
+
+    def test_overwrite_last_event_id(self) -> None:
+        reset_last_event_id()
+        set_last_event_id("event-1")
+        set_last_event_id("event-2")
+        assert get_last_event_id() == "event-2"
+
+
+class TestTriggeringEventIdTracking:
+    """Tests for causal chain event ID tracking."""
+
+    def test_initial_triggering_event_id_is_none(self) -> None:
+        set_triggering_event_id(None)
+        assert get_triggering_event_id() is None
+
+    def test_set_and_get_triggering_event_id(self) -> None:
+        set_triggering_event_id("trigger-123")
+        assert get_triggering_event_id() == "trigger-123"
+        set_triggering_event_id(None)
+
+    def test_set_none_clears_triggering_event_id(self) -> None:
+        set_triggering_event_id("trigger-123")
+        set_triggering_event_id(None)
+        assert get_triggering_event_id() is None
+
+
+class TestTriggeredByScope:
+    """Tests for triggered_by_scope context manager."""
+
+    def test_scope_sets_triggering_id(self) -> None:
+        set_triggering_event_id(None)
+        with triggered_by_scope("trigger-456"):
+            assert get_triggering_event_id() == "trigger-456"
+
+    def test_scope_restores_previous_value(self) -> None:
+        set_triggering_event_id(None)
+        with triggered_by_scope("trigger-456"):
+            pass
+        assert get_triggering_event_id() is None
+
+    def test_nested_scopes(self) -> None:
+        set_triggering_event_id(None)
+        with triggered_by_scope("outer"):
+            assert get_triggering_event_id() == "outer"
+            with triggered_by_scope("inner"):
+                assert get_triggering_event_id() == "inner"
+            assert get_triggering_event_id() == "outer"
+        assert get_triggering_event_id() is None
+
+    def test_scope_restores_on_exception(self) -> None:
+        set_triggering_event_id(None)
+        try:
+            with triggered_by_scope("trigger-789"):
+                raise ValueError("test error")
+        except ValueError:
+            pass
+        assert get_triggering_event_id() is None

lib/crewai/tests/llms/azure/test_azure.py

@@ -1215,177 +1215,3 @@ def test_azure_streaming_returns_usage_metrics():
     assert result.token_usage.prompt_tokens > 0
     assert result.token_usage.completion_tokens > 0
     assert result.token_usage.successful_requests >= 1
-
-
-def test_azure_cognitive_services_endpoint():
-    """
-    Test that Azure Cognitive Services endpoints (cognitiveservices.azure.com) are supported.
-    This addresses GitHub issue #4260 where non-openai.azure.com endpoints were not working.
-    """
-    from crewai.llms.providers.azure.completion import AzureCompletion
-
-    with patch.dict(os.environ, {
-        "AZURE_API_KEY": "test-key",
-        "AZURE_ENDPOINT": "https://my-resource.cognitiveservices.azure.com"
-    }):
-        llm = LLM(model="azure/gpt-4")
-
-        assert isinstance(llm, AzureCompletion)
-        # Cognitive Services endpoints should NOT have deployment path auto-constructed
-        assert llm.endpoint == "https://my-resource.cognitiveservices.azure.com"
-        # Should be recognized as an Azure endpoint
-        assert llm.is_azure_endpoint == True
-        # But NOT as an Azure OpenAI endpoint (different URL structure)
-        assert llm.is_azure_openai_endpoint == False
-
-
-def test_azure_ai_services_endpoint():
-    """
-    Test that Azure AI Services endpoints (services.ai.azure.com) are supported.
-    """
-    from crewai.llms.providers.azure.completion import AzureCompletion
-
-    with patch.dict(os.environ, {
-        "AZURE_API_KEY": "test-key",
-        "AZURE_ENDPOINT": "https://my-resource.services.ai.azure.com"
-    }):
-        llm = LLM(model="azure/gpt-4")
-
-        assert isinstance(llm, AzureCompletion)
-        assert llm.endpoint == "https://my-resource.services.ai.azure.com"
-        assert llm.is_azure_endpoint == True
-        assert llm.is_azure_openai_endpoint == False
-
-
-def test_azure_generic_azure_com_endpoint():
-    """
-    Test that generic .azure.com endpoints are supported (e.g., cservices.azure.com).
-    This addresses the specific case from GitHub issue #4260.
-    """
-    from crewai.llms.providers.azure.completion import AzureCompletion
-
-    with patch.dict(os.environ, {
-        "AZURE_API_KEY": "test-key",
-        "AZURE_ENDPOINT": "https://my-resource.cservices.azure.com"
-    }):
-        llm = LLM(model="azure/gpt-4")
-
-        assert isinstance(llm, AzureCompletion)
-        assert llm.endpoint == "https://my-resource.cservices.azure.com"
-        assert llm.is_azure_endpoint == True
-        assert llm.is_azure_openai_endpoint == False
-
-
-def test_azure_is_azure_endpoint_detection():
-    """
-    Test the _is_azure_endpoint static method for various endpoint formats.
-    """
-    from crewai.llms.providers.azure.completion import AzureCompletion
-
-    # Azure OpenAI endpoints
-    assert AzureCompletion._is_azure_endpoint("https://my-resource.openai.azure.com") == True
-    assert AzureCompletion._is_azure_endpoint("https://my-resource.openai.azure.com/openai/deployments/gpt-4") == True
-
-    # Azure Cognitive Services endpoints
-    assert AzureCompletion._is_azure_endpoint("https://my-resource.cognitiveservices.azure.com") == True
-
-    # Azure AI Services endpoints
-    assert AzureCompletion._is_azure_endpoint("https://my-resource.services.ai.azure.com") == True
-
-    # Generic .azure.com endpoints (like cservices.azure.com from issue #4260)
-    assert AzureCompletion._is_azure_endpoint("https://my-resource.cservices.azure.com") == True
-
-    # Azure AI Inference endpoint
-    assert AzureCompletion._is_azure_endpoint("https://models.inference.ai.azure.com") == True
-
-    # Non-Azure endpoints should return False
-    assert AzureCompletion._is_azure_endpoint("https://api.openai.com") == False
-    assert AzureCompletion._is_azure_endpoint("https://example.com") == False
-
-
-def test_azure_base_url_parameter_support():
-    """
-    Test that the base_url parameter is supported as an alias for endpoint.
-    This provides consistency with other LLM providers.
-    """
-    from crewai.llms.providers.azure.completion import AzureCompletion
-
-    # Test with base_url parameter directly
-    llm = AzureCompletion(
-        model="gpt-4",
-        api_key="test-key",
-        base_url="https://my-resource.cognitiveservices.azure.com"
-    )
-
-    assert llm.endpoint == "https://my-resource.cognitiveservices.azure.com"
-    assert llm.is_azure_endpoint == True
-
-
-def test_azure_endpoint_takes_precedence_over_base_url():
-    """
-    Test that explicit endpoint parameter takes precedence over base_url.
-    """
-    from crewai.llms.providers.azure.completion import AzureCompletion
-
-    llm = AzureCompletion(
-        model="gpt-4",
-        api_key="test-key",
-        endpoint="https://explicit-endpoint.openai.azure.com",
-        base_url="https://base-url-endpoint.cognitiveservices.azure.com"
-    )
-
-    # endpoint should take precedence
-    assert "explicit-endpoint.openai.azure.com" in llm.endpoint
-
-
-def test_azure_non_openai_endpoint_model_parameter_included():
-    """
-    Test that model parameter IS included for non-Azure OpenAI endpoints.
-    This is important for Cognitive Services and other Azure AI endpoints.
-    """
-    from crewai.llms.providers.azure.completion import AzureCompletion
-
-    with patch.dict(os.environ, {
-        "AZURE_API_KEY": "test-key",
-        "AZURE_ENDPOINT": "https://my-resource.cognitiveservices.azure.com"
-    }):
-        llm = LLM(model="azure/gpt-4")
-
-        params = llm._prepare_completion_params(
-            messages=[{"role": "user", "content": "test"}]
-        )
-
-        # Model parameter should be included for non-Azure OpenAI endpoints
-        assert "model" in params
-        assert params["model"] == "gpt-4"
-
-
-def test_azure_validate_and_fix_endpoint_only_modifies_openai_azure():
-    """
-    Test that _validate_and_fix_endpoint only auto-constructs deployment path
-    for openai.azure.com endpoints, not for other Azure endpoints.
-    """
-    from crewai.llms.providers.azure.completion import AzureCompletion
-
-    # Azure OpenAI endpoint should have deployment path auto-constructed
-    result = AzureCompletion._validate_and_fix_endpoint(
-        "https://my-resource.openai.azure.com",
-        "gpt-4"
-    )
-    assert "/openai/deployments/gpt-4" in result
-
-    # Cognitive Services endpoint should NOT be modified
-    result = AzureCompletion._validate_and_fix_endpoint(
-        "https://my-resource.cognitiveservices.azure.com",
-        "gpt-4"
-    )
-    assert result == "https://my-resource.cognitiveservices.azure.com"
-    assert "/openai/deployments/" not in result
-
-    # Generic Azure endpoint should NOT be modified
-    result = AzureCompletion._validate_and_fix_endpoint(
-        "https://my-resource.cservices.azure.com",
-        "gpt-4"
-    )
-    assert result == "https://my-resource.cservices.azure.com"
-    assert "/openai/deployments/" not in result

lib/crewai/tests/memory/test_external_memory.py

@@ -304,6 +304,11 @@ def test_external_memory_search_events(
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": None,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "query": "test value",
         "limit": 3,
         "score_threshold": 0.35,
@@ -321,6 +326,11 @@ def test_external_memory_search_events(
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": ANY,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "query": "test value",
         "results": [],
         "limit": 3,
@@ -376,6 +386,11 @@ def test_external_memory_save_events(
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": None,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "value": "saving value",
         "metadata": {"task": "test_task"},
     }
@@ -392,6 +407,11 @@ def test_external_memory_save_events(
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": ANY,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "value": "saving value",
         "metadata": {"task": "test_task"},
         "save_time_ms": ANY,

lib/crewai/tests/memory/test_long_term_memory.py

@@ -70,6 +70,11 @@ def test_long_term_memory_save_events(long_term_memory):
         "from_agent": None,
         "agent_role": "test_agent",
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": None,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "value": "test_task",
         "metadata": {"task": "test_task", "quality": 0.5},
     }
@@ -85,6 +90,11 @@ def test_long_term_memory_save_events(long_term_memory):
         "from_agent": None,
         "agent_role": "test_agent",
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": None,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "value": "test_task",
         "metadata": {
             "task": "test_task",
@@ -139,6 +149,11 @@ def test_long_term_memory_search_events(long_term_memory):
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": None,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "query": "test query",
         "limit": 5,
         "score_threshold": None,
@@ -156,6 +171,11 @@ def test_long_term_memory_search_events(long_term_memory):
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": ANY,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "query": "test query",
         "results": None,
         "limit": 5,

lib/crewai/tests/memory/test_short_term_memory.py

@@ -81,6 +81,11 @@ def test_short_term_memory_search_events(short_term_memory):
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": None,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "query": "test value",
         "limit": 3,
         "score_threshold": 0.35,
@@ -98,6 +103,11 @@ def test_short_term_memory_search_events(short_term_memory):
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": None,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "query": "test value",
         "results": [],
         "limit": 3,
@@ -150,6 +160,11 @@ def test_short_term_memory_save_events(short_term_memory):
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": None,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "value": "test value",
         "metadata": {"task": "test_task"},
     }
@@ -166,6 +181,11 @@ def test_short_term_memory_save_events(short_term_memory):
         "from_agent": None,
         "agent_role": None,
         "agent_id": None,
+        "event_id": ANY,
+        "parent_event_id": None,
+        "previous_event_id": ANY,
+        "triggered_by_event_id": None,
+        "emission_sequence": ANY,
         "value": "test value",
         "metadata": {"task": "test_task"},
         "save_time_ms": ANY,

lib/crewai/tests/test_flow.py

@@ -1204,7 +1204,8 @@ def test_complex_and_or_branching():
 
 
     # Final should be after both 2a and 2b
-    assert execution_order[-1] == "final"
+    # Note: we don't assert final is last because branch_1c has no downstream
+    # dependencies and can complete after final due to parallel execution
     assert execution_order.index("final") > execution_order.index("branch_2a")
     assert execution_order.index("final") > execution_order.index("branch_2b")