fix(tracing): stop nagging users who declined tracing (#5665)

- When user explicitly declined tracing, skip the 'Tracing is disabled'
  message instead of showing it on every crew/flow execution
- Add CREWAI_SUPPRESS_TRACING_MESSAGES env var to let users fully
  suppress the message
- Remove duplicate identical if/else branches in all four
  _show_tracing_disabled_message implementations
- Add 24 tests covering suppression via env var, context var, and
  user-declined scenarios

Co-Authored-By: João <joao@crewai.com>

docs/ar/concepts/flows.mdx

@@ -380,6 +380,33 @@ class AnotherFlow(Flow[dict]):
         print("Method-level persisted runs:", self.state["runs"])
 ```
 
+### مفتاح استمرارية مخصص
+
+افتراضيًا، يستخدم `@persist` الحقل `state.id` المُولّد تلقائيًا كمفتاح للاستمرارية. إذا كان لتدفقك معرّف خاص به — مثل `conversation_id` مشترك بين عدة جلسات — يمكنك تمرير الوسيط `key` ليستخدم `@persist` تلك السمة كـ UUID للتدفق:
+
+```python
+from crewai.flow.flow import Flow, listen, start
+from crewai.flow.persistence import persist
+from pydantic import BaseModel
+
+class ConversationState(BaseModel):
+    conversation_id: str
+    turn: int = 0
+
+@persist(key="conversation_id")  # استخدام حقل مخصص كمفتاح للاستمرارية
+class ConversationFlow(Flow[ConversationState]):
+    @start()
+    def begin(self):
+        self.state.turn += 1
+        print(f"Conversation {self.state.conversation_id} turn {self.state.turn}")
+
+# إعادة تشغيل المحادثة بنفس conversation_id يُعيد تحميل الحالة السابقة
+flow = ConversationFlow(conversation_id="user-42")
+flow.kickoff()
+```
+
+يقرأ المزخرف القيمة من `state[key]` للحالات من نوع dict، ومن `getattr(state, key)` للحالات من نوع Pydantic / كائن. إذا كانت السمة المحددة غير موجودة أو قيمتها falsy عند الحفظ، يُطلق `@persist` خطأ `ValueError` مثل `Flow state is missing required persistence key 'conversation_id'`. عند حذف `key`، يظل السلوك الأصلي قائمًا ويُستخدم `state.id`.
+
 ### كيف تعمل
 
 1. **تعريف الحالة الفريد**

docs/ar/concepts/production-architecture.mdx

@@ -146,6 +146,15 @@ class ProductionFlow(Flow[AppState]):
     # ...
 ```
 
+افتراضيًا، يستخدم `@persist` الحقل `state.id` المُولّد تلقائيًا كمفتاح للحالة المحفوظة. إذا كان تطبيقك يمتلك معرّفًا طبيعيًا بالفعل — مثل `conversation_id` يربط عدة تشغيلات بنفس جلسة المستخدم — مرّره كـ `key` ليستخدمه المزخرف كـ UUID للتدفق. يُطلق `ValueError` إذا كانت السمة المحددة غير موجودة أو قيمتها falsy عند الحفظ.
+
+```python
+@persist(key="conversation_id")
+class ProductionFlow(Flow[AppState]):
+    # يجب أن يحتوي AppState على conversation_id؛ استئناف الجلسة يُعيد تحميل الحالة السابقة
+    ...
+```
+
 ## الخلاصة
 
 - **ابدأ بتدفق.**

docs/ar/guides/flows/mastering-flow-state.mdx

@@ -116,6 +116,33 @@ class PersistentCounterFlow(Flow[CounterState]):
         return self.state.value
 ```
 
+### استخدام مفتاح استمرارية مخصص
+
+افتراضيًا، يستخدم `@persist()` الحقل `state.id` المُولّد تلقائيًا كمفتاح للحالة المحفوظة. عندما يكون لمجالك معرّف طبيعي بالفعل — مثل `conversation_id` يربط عدة تشغيلات للتدفق بنفس جلسة المستخدم — مرّره كوسيط `key` ليستخدمه `@persist` كـ UUID للتدفق بدلًا من `id`:
+
+```python
+from crewai.flow.flow import Flow, listen, start
+from crewai.flow.persistence import persist
+from pydantic import BaseModel
+
+class ConversationState(BaseModel):
+    conversation_id: str
+    history: list[str] = []
+
+@persist(key="conversation_id")
+class ConversationFlow(Flow[ConversationState]):
+    @start()
+    def greet(self):
+        self.state.history.append("hello")
+        return self.state.history
+
+# تشغيل ثانٍ بنفس conversation_id يُعيد تحميل الحالة السابقة
+flow = ConversationFlow(conversation_id="user-42")
+flow.kickoff()
+```
+
+بالنسبة للحالات من نوع dict يقرأ `@persist` القيمة من `state[key]`، ولحالات Pydantic / الكائنات يقرأها من `getattr(state, key)`. إذا كانت السمة المحددة غير موجودة أو قيمتها falsy عند حفظ الحالة، يُطلق `@persist` خطأ `ValueError` مثل `Flow state is missing required persistence key 'conversation_id'`، فيظهر الفشل فورًا بدلًا من فقد بيانات الاستمرارية بصمت. استدعاء `@persist()` بدون `key` يحافظ على السلوك الأصلي ويستخدم `state.id`.
+
 ## أنماط حالة متقدمة
 
 ### المنطق الشرطي المبني على الحالة

docs/en/concepts/flows.mdx

@@ -380,6 +380,33 @@ class AnotherFlow(Flow[dict]):
         print("Method-level persisted runs:", self.state["runs"])
 ```
 
+### Custom Persistence Key
+
+By default, `@persist` uses the auto-generated `state.id` field as the persistence key. If your flow models its own identifier — for example a `conversation_id` shared across sessions — you can pass a `key` argument and `@persist` will use that attribute as the flow UUID instead:
+
+```python
+from crewai.flow.flow import Flow, listen, start
+from crewai.flow.persistence import persist
+from pydantic import BaseModel
+
+class ConversationState(BaseModel):
+    conversation_id: str
+    turn: int = 0
+
+@persist(key="conversation_id")  # Use a custom field as the persistence key
+class ConversationFlow(Flow[ConversationState]):
+    @start()
+    def begin(self):
+        self.state.turn += 1
+        print(f"Conversation {self.state.conversation_id} turn {self.state.turn}")
+
+# Resuming the same conversation reloads its prior state by conversation_id
+flow = ConversationFlow(conversation_id="user-42")
+flow.kickoff()
+```
+
+The decorator reads the value at `state[key]` for dict states, or `getattr(state, key)` for Pydantic / object states. If the named attribute is missing or falsy at save time, `@persist` raises a `ValueError` such as `Flow state is missing required persistence key 'conversation_id'`. When `key` is omitted, the existing behavior is preserved and `state.id` is used.
+
 ### How It Works
 
 1. **Unique State Identification**

docs/en/concepts/production-architecture.mdx

@@ -146,6 +146,15 @@ class ProductionFlow(Flow[AppState]):
     # ...
 ```
 
+By default `@persist` keys saved state by the auto-generated `state.id`. If your application already has a natural identifier — for example a `conversation_id` that ties multiple runs to the same user session — pass it as `key` and the decorator will use that attribute as the flow UUID. A `ValueError` is raised if the named attribute is missing or falsy at save time.
+
+```python
+@persist(key="conversation_id")
+class ProductionFlow(Flow[AppState]):
+    # AppState must expose conversation_id; resuming a session reloads its prior state
+    ...
+```
+
 ## Summary
 
 - **Start with a Flow.**

docs/en/guides/flows/mastering-flow-state.mdx

@@ -346,6 +346,33 @@ class SelectivePersistFlow(Flow):
         return f"Complete with count {self.state['count']}"
 ```
 
+#### Using a Custom Persistence Key
+
+By default, `@persist()` keys persisted state by the flow's auto-generated `state.id`. When your domain already has a natural identifier — for example a `conversation_id` that ties multiple flow runs to the same user session — pass it as the `key` argument and `@persist` will use that attribute as the flow UUID instead of `id`:
+
+```python
+from crewai.flow.flow import Flow, listen, start
+from crewai.flow.persistence import persist
+from pydantic import BaseModel
+
+class ConversationState(BaseModel):
+    conversation_id: str
+    history: list[str] = []
+
+@persist(key="conversation_id")
+class ConversationFlow(Flow[ConversationState]):
+    @start()
+    def greet(self):
+        self.state.history.append("hello")
+        return self.state.history
+
+# A second run with the same conversation_id reloads the prior state
+flow = ConversationFlow(conversation_id="user-42")
+flow.kickoff()
+```
+
+For dict-based states `@persist` reads `state[key]`, and for Pydantic / object states it reads `getattr(state, key)`. If the named attribute is missing or falsy when state is being saved, `@persist` raises a `ValueError` like `Flow state is missing required persistence key 'conversation_id'`, so the failure surfaces immediately rather than silently dropping persisted data. Calling `@persist()` without `key` keeps the original behavior of using `state.id`.
+
 
 ## Advanced State Patterns
 

docs/ko/concepts/flows.mdx

@@ -373,6 +373,33 @@ class AnotherFlow(Flow[dict]):
         print("Method-level persisted runs:", self.state["runs"])
 ```
 
+### 사용자 지정 영속성 키
+
+기본적으로 `@persist`는 자동 생성된 `state.id` 필드를 영속성 키로 사용합니다. 여러 세션에 걸쳐 공유되는 `conversation_id`처럼 플로우에 자체 식별자가 있는 경우, `key` 인자를 전달하면 `@persist`가 해당 속성을 플로우 UUID로 사용합니다:
+
+```python
+from crewai.flow.flow import Flow, listen, start
+from crewai.flow.persistence import persist
+from pydantic import BaseModel
+
+class ConversationState(BaseModel):
+    conversation_id: str
+    turn: int = 0
+
+@persist(key="conversation_id")  # 사용자 지정 필드를 영속성 키로 사용
+class ConversationFlow(Flow[ConversationState]):
+    @start()
+    def begin(self):
+        self.state.turn += 1
+        print(f"Conversation {self.state.conversation_id} turn {self.state.turn}")
+
+# 동일한 conversation_id로 다시 실행하면 이전 상태가 다시 로드됩니다
+flow = ConversationFlow(conversation_id="user-42")
+flow.kickoff()
+```
+
+이 데코레이터는 dict 상태의 경우 `state[key]`에서, Pydantic / 객체 상태의 경우 `getattr(state, key)`에서 값을 읽습니다. 저장 시점에 지정된 속성이 없거나 falsy 값이면, `@persist`는 `Flow state is missing required persistence key 'conversation_id'`와 같은 `ValueError`를 발생시킵니다. `key`를 생략하면 기존 동작이 유지되어 `state.id`가 사용됩니다.
+
 ### 작동 방식
 
 1. **고유 상태 식별**

docs/ko/concepts/production-architecture.mdx

@@ -146,6 +146,15 @@ class ProductionFlow(Flow[AppState]):
     # ...
 ```
 
+기본적으로 `@persist`는 자동 생성된 `state.id`를 저장된 상태의 키로 사용합니다. 애플리케이션에 이미 자연스러운 식별자가 있는 경우 — 예를 들어 같은 사용자 세션에 속한 여러 실행을 묶는 `conversation_id` — `key`로 전달하면 데코레이터가 해당 속성을 플로우 UUID로 사용합니다. 저장 시점에 지정된 속성이 없거나 falsy 값이면 `ValueError`가 발생합니다.
+
+```python
+@persist(key="conversation_id")
+class ProductionFlow(Flow[AppState]):
+    # AppState는 conversation_id를 노출해야 합니다; 세션을 재개하면 이전 상태가 다시 로드됩니다
+    ...
+```
+
 ## 요약
 
 - **Flow로 시작하세요.**

docs/ko/guides/flows/mastering-flow-state.mdx

@@ -346,6 +346,33 @@ class SelectivePersistFlow(Flow):
         return f"Complete with count {self.state['count']}"
 ```
 
+#### 사용자 지정 영속성 키 사용하기
+
+기본적으로 `@persist()`는 자동 생성된 `state.id`를 영속 상태의 키로 사용합니다. 도메인에 이미 자연스러운 식별자가 있는 경우 — 예를 들어 같은 사용자 세션에 속한 여러 플로우 실행을 묶는 `conversation_id` — `key` 인자로 전달하면 `@persist`는 `id` 대신 해당 속성을 플로우 UUID로 사용합니다:
+
+```python
+from crewai.flow.flow import Flow, listen, start
+from crewai.flow.persistence import persist
+from pydantic import BaseModel
+
+class ConversationState(BaseModel):
+    conversation_id: str
+    history: list[str] = []
+
+@persist(key="conversation_id")
+class ConversationFlow(Flow[ConversationState]):
+    @start()
+    def greet(self):
+        self.state.history.append("hello")
+        return self.state.history
+
+# 동일한 conversation_id로 두 번째 실행 시 이전 상태가 다시 로드됩니다
+flow = ConversationFlow(conversation_id="user-42")
+flow.kickoff()
+```
+
+dict 기반 상태의 경우 `@persist`는 `state[key]`를 읽고, Pydantic / 객체 상태의 경우 `getattr(state, key)`를 읽습니다. 상태가 저장될 때 지정된 속성이 없거나 falsy 값이면 `@persist`는 `Flow state is missing required persistence key 'conversation_id'`와 같은 `ValueError`를 발생시켜, 영속 데이터가 조용히 손실되는 대신 즉시 실패가 드러나도록 합니다. `key` 없이 `@persist()`를 호출하면 기존 동작대로 `state.id`가 사용됩니다.
+
 ## 고급 상태 패턴
 
 ### 상태 기반 조건부 로직

docs/pt-BR/concepts/flows.mdx

@@ -193,6 +193,33 @@ Para um controle mais granular, você pode aplicar @persist em métodos específ
 # (O código não é traduzido)
 ```
 
+### Chave de Persistência Personalizada
+
+Por padrão, `@persist` usa o campo `state.id` gerado automaticamente como chave de persistência. Se o seu flow já possui um identificador natural — por exemplo um `conversation_id` compartilhado entre sessões — você pode passar o argumento `key` e `@persist` usará esse atributo como UUID do flow:
+
+```python
+from crewai.flow.flow import Flow, listen, start
+from crewai.flow.persistence import persist
+from pydantic import BaseModel
+
+class ConversationState(BaseModel):
+    conversation_id: str
+    turn: int = 0
+
+@persist(key="conversation_id")  # Usa um campo personalizado como chave de persistência
+class ConversationFlow(Flow[ConversationState]):
+    @start()
+    def begin(self):
+        self.state.turn += 1
+        print(f"Conversa {self.state.conversation_id} turno {self.state.turn}")
+
+# Retomar a mesma conversa recarrega o estado anterior pelo conversation_id
+flow = ConversationFlow(conversation_id="user-42")
+flow.kickoff()
+```
+
+O decorador lê o valor em `state[key]` para estados do tipo dicionário ou `getattr(state, key)` para estados Pydantic / objetos. Se o atributo informado estiver ausente ou for *falsy* no momento de salvar, `@persist` lança um `ValueError` como `Flow state is missing required persistence key 'conversation_id'`. Quando `key` é omitido, o comportamento original é preservado e `state.id` continua sendo usado.
+
 ### Como Funciona
 
 1. **Identificação Única do Estado**

docs/pt-BR/concepts/production-architecture.mdx

@@ -146,6 +146,15 @@ class ProductionFlow(Flow[AppState]):
     # ...
 ```
 
+Por padrão, `@persist` usa o `state.id` gerado automaticamente como chave do estado salvo. Se a sua aplicação já tem um identificador natural — por exemplo um `conversation_id` que liga várias execuções à mesma sessão de usuário — passe-o como `key` e o decorador usará esse atributo como UUID do flow. Um `ValueError` é lançado se o atributo informado estiver ausente ou for *falsy* no momento de salvar.
+
+```python
+@persist(key="conversation_id")
+class ProductionFlow(Flow[AppState]):
+    # AppState precisa expor conversation_id; retomar a sessão recarrega o estado anterior
+    ...
+```
+
 ## Resumo
 
 - **Comece com um Flow.**

docs/pt-BR/guides/flows/mastering-flow-state.mdx

@@ -167,6 +167,33 @@ Para mais controle, você pode aplicar `@persist()` em métodos específicos:
 # código não traduzido
 ```
 
+#### Usando uma Chave de Persistência Personalizada
+
+Por padrão, `@persist()` usa o `state.id` gerado automaticamente como chave do estado persistido. Quando seu domínio já possui um identificador natural — por exemplo um `conversation_id` que liga várias execuções do flow à mesma sessão de usuário — passe-o como argumento `key` e `@persist` usará esse atributo como UUID do flow em vez de `id`:
+
+```python
+from crewai.flow.flow import Flow, listen, start
+from crewai.flow.persistence import persist
+from pydantic import BaseModel
+
+class ConversationState(BaseModel):
+    conversation_id: str
+    history: list[str] = []
+
+@persist(key="conversation_id")
+class ConversationFlow(Flow[ConversationState]):
+    @start()
+    def greet(self):
+        self.state.history.append("hello")
+        return self.state.history
+
+# Uma segunda execução com o mesmo conversation_id recarrega o estado anterior
+flow = ConversationFlow(conversation_id="user-42")
+flow.kickoff()
+```
+
+Para estados baseados em dicionário `@persist` lê `state[key]`, e para estados Pydantic / objetos lê `getattr(state, key)`. Se o atributo informado estiver ausente ou for *falsy* no momento em que o estado for salvo, `@persist` lança um `ValueError` como `Flow state is missing required persistence key 'conversation_id'`, fazendo com que a falha apareça imediatamente em vez de descartar silenciosamente os dados persistidos. Chamar `@persist()` sem `key` mantém o comportamento original de usar `state.id`.
+
 ## Padrões Avançados de Estado
 
 ### Lógica Condicional Baseada no Estado

lib/crewai/src/crewai/crew.py

@@ -2272,17 +2272,13 @@ class Crew(FlowTrackable, BaseModel):
         if should_suppress_tracing_messages():
             return
 
+        # Don't nag users who have explicitly declined tracing
+        if has_user_declined_tracing():
+            return
+
         console = Console()
 
-        if has_user_declined_tracing():
-            message = """Info: Tracing is disabled.
-
-To enable tracing, do any one of these:
-• Set tracing=True in your Crew code
-• Set CREWAI_TRACING_ENABLED=true in your project's .env file
-• Run: crewai traces enable"""
-        else:
-            message = """Info: Tracing is disabled.
+        message = """Info: Tracing is disabled.
 
 To enable tracing, do any one of these:
 • Set tracing=True in your Crew code

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

@@ -868,17 +868,13 @@ class TraceCollectionListener(BaseEventListener):
         if should_suppress_tracing_messages():
             return
 
+        # Don't nag users who have explicitly declined tracing
+        if has_user_declined_tracing():
+            return
+
         console = Console()
 
-        if has_user_declined_tracing():
-            message = """Info: Tracing is disabled.
-
-To enable tracing, do any one of these:
-• Set tracing=True in your Crew/Flow code
-• Set CREWAI_TRACING_ENABLED=true in your project's .env file
-• Run: crewai traces enable"""
-        else:
-            message = """Info: Tracing is disabled.
+        message = """Info: Tracing is disabled.
 
 To enable tracing, do any one of these:
 • Set tracing=True in your Crew/Flow code

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

@@ -53,10 +53,19 @@ def set_suppress_tracing_messages(suppress: bool) -> object:
 def should_suppress_tracing_messages() -> bool:
     """Check if tracing messages should be suppressed.
 
+    Checks the context variable first, then falls back to the
+    CREWAI_SUPPRESS_TRACING_MESSAGES environment variable.
+
     Returns:
         True if messages should be suppressed, False otherwise.
     """
-    return _suppress_tracing_messages.get()
+    if _suppress_tracing_messages.get():
+        return True
+    return os.getenv("CREWAI_SUPPRESS_TRACING_MESSAGES", "false").lower() in (
+        "true",
+        "1",
+        "yes",
+    )
 
 
 def should_enable_tracing(*, override: bool | None = None) -> bool:

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

@@ -145,16 +145,12 @@ To update, run: uv sync --upgrade-package crewai"""
         if listener and listener.first_time_handler.is_first_time:
             return
 
-        if not is_tracing_enabled_in_context():
-            if has_user_declined_tracing():
-                message = """Info: Tracing is disabled.
+        # Don't nag users who have explicitly declined tracing
+        if has_user_declined_tracing():
+            return
 
-To enable tracing, do any one of these:
-• Set tracing=True in your Crew/Flow code
-• Set CREWAI_TRACING_ENABLED=true in your project's .env file
-• Run: crewai traces enable"""
-            else:
-                message = """Info: Tracing is disabled.
+        if not is_tracing_enabled_in_context():
+            message = """Info: Tracing is disabled.
 
 To enable tracing, do any one of these:
 • Set tracing=True in your Crew/Flow code

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

@@ -3546,17 +3546,13 @@ class Flow(BaseModel, Generic[T], metaclass=FlowMeta):
         if should_suppress_tracing_messages():
             return
 
+        # Don't nag users who have explicitly declined tracing
+        if has_user_declined_tracing():
+            return
+
         console = Console()
 
-        if has_user_declined_tracing():
-            message = """Info: Tracing is disabled.
-
-To enable tracing, do any one of these:
-• Set tracing=True in your Flow code
-• Set CREWAI_TRACING_ENABLED=true in your project's .env file
-• Run: crewai traces enable"""
-        else:
-            message = """Info: Tracing is disabled.
+        message = """Info: Tracing is disabled.
 
 To enable tracing, do any one of these:
 • Set tracing=True in your Flow code

lib/crewai/src/crewai/flow/persistence/decorators.py

@@ -50,6 +50,7 @@ LOG_MESSAGES: Final[dict[str, str]] = {
     "save_error": "Failed to persist state for method {}: {}",
     "state_missing": "Flow instance has no state",
     "id_missing": "Flow state must have an 'id' field for persistence",
+    "key_missing": "Flow state is missing required persistence key '{}'",
 }
 
 
@@ -63,6 +64,7 @@ class PersistenceDecorator:
         method_name: str,
         persistence_instance: FlowPersistence,
         verbose: bool = False,
+        key: str | None = None,
     ) -> None:
         """Persist flow state with proper error handling and logging.
 
@@ -74,9 +76,12 @@ class PersistenceDecorator:
             method_name: Name of the method that triggered persistence
             persistence_instance: The persistence backend to use
             verbose: Whether to log persistence operations
+            key: Optional state attribute/key to use as the persistence key.
+                When None, falls back to ``state.id``.
 
         Raises:
-            ValueError: If flow has no state or state lacks an ID
+            ValueError: If flow has no state, state lacks an ID, or the
+                requested ``key`` is missing or falsy on state.
             RuntimeError: If state persistence fails
             AttributeError: If flow instance lacks required state attributes
         """
@@ -85,19 +90,22 @@ class PersistenceDecorator:
             if state is None:
                 raise ValueError("Flow instance has no state")
 
+            lookup_key = key if key is not None else "id"
             flow_uuid: str | None = None
             if isinstance(state, dict):
-                flow_uuid = state.get("id")
+                flow_uuid = state.get(lookup_key)
             elif hasattr(state, "_unwrap"):
                 unwrapped = state._unwrap()
                 if isinstance(unwrapped, dict):
-                    flow_uuid = unwrapped.get("id")
+                    flow_uuid = unwrapped.get(lookup_key)
                 else:
-                    flow_uuid = getattr(unwrapped, "id", None)
-            elif isinstance(state, BaseModel) or hasattr(state, "id"):
-                flow_uuid = getattr(state, "id", None)
+                    flow_uuid = getattr(unwrapped, lookup_key, None)
+            elif isinstance(state, BaseModel) or hasattr(state, lookup_key):
+                flow_uuid = getattr(state, lookup_key, None)
 
             if not flow_uuid:
+                if key is not None:
+                    raise ValueError(LOG_MESSAGES["key_missing"].format(key))
                 raise ValueError("Flow state must have an 'id' field for persistence")
 
             # Log state saving only if verbose is True
@@ -127,7 +135,7 @@ class PersistenceDecorator:
             logger.error(error_msg)
             raise ValueError(error_msg) from e
         except (TypeError, ValueError) as e:
-            error_msg = LOG_MESSAGES["id_missing"]
+            error_msg = str(e) or LOG_MESSAGES["id_missing"]
             if verbose:
                 PRINTER.print(error_msg, color="red")
             logger.error(error_msg)
@@ -135,7 +143,9 @@ class PersistenceDecorator:
 
 
 def persist(
-    persistence: FlowPersistence | None = None, verbose: bool = False
+    persistence: FlowPersistence | None = None,
+    verbose: bool = False,
+    key: str | None = None,
 ) -> Callable[[type | Callable[..., T]], type | Callable[..., T]]:
     """Decorator to persist flow state.
 
@@ -148,12 +158,16 @@ def persist(
         persistence: Optional FlowPersistence implementation to use.
                     If not provided, uses SQLiteFlowPersistence.
         verbose: Whether to log persistence operations. Defaults to False.
+        key: Optional name of the state attribute (for Pydantic/object states)
+            or dict key (for dict states) to use as the persistence key. When
+            ``None`` (default) the decorator falls back to ``state.id``.
 
     Returns:
         A decorator that can be applied to either a class or method
 
     Raises:
-        ValueError: If the flow state doesn't have an 'id' field
+        ValueError: If the flow state doesn't have an 'id' field, or the
+            specified ``key`` is missing or falsy on state.
         RuntimeError: If state persistence fails
 
     Example:
@@ -162,6 +176,10 @@ def persist(
             @start()
             def begin(self):
                 pass
+
+        @persist(key="conversation_id")  # Custom persistence key
+        class MyFlow(Flow[MyState]):
+            ...
     """
 
     def decorator(target: type | Callable[..., T]) -> type | Callable[..., T]:
@@ -207,7 +225,7 @@ def persist(
                         ) -> Any:
                             result = await original_method(self, *args, **kwargs)
                             PersistenceDecorator.persist_state(
-                                self, method_name, actual_persistence, verbose
+                                self, method_name, actual_persistence, verbose, key
                             )
                             return result
 
@@ -237,7 +255,7 @@ def persist(
                         def method_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
                             result = original_method(self, *args, **kwargs)
                             PersistenceDecorator.persist_state(
-                                self, method_name, actual_persistence, verbose
+                                self, method_name, actual_persistence, verbose, key
                             )
                             return result
 
@@ -276,7 +294,7 @@ def persist(
                 else:
                     result = method_coro
                 PersistenceDecorator.persist_state(
-                    flow_instance, method.__name__, actual_persistence, verbose
+                    flow_instance, method.__name__, actual_persistence, verbose, key
                 )
                 return cast(T, result)
 
@@ -295,7 +313,7 @@ def persist(
         def method_sync_wrapper(flow_instance: Any, *args: Any, **kwargs: Any) -> T:
             result = method(flow_instance, *args, **kwargs)
             PersistenceDecorator.persist_state(
-                flow_instance, method.__name__, actual_persistence, verbose
+                flow_instance, method.__name__, actual_persistence, verbose, key
             )
             return result
 

lib/crewai/src/crewai/llm.py

@@ -1160,7 +1160,7 @@ class LLM(BaseLLM):
                 call_type=LLMCallType.LLM_CALL,
                 from_task=from_task,
                 from_agent=from_agent,
-                messages=params["messages"],
+                messages=messages,
                 usage=None,
             )
             return structured_response
@@ -1316,7 +1316,7 @@ class LLM(BaseLLM):
                 call_type=LLMCallType.LLM_CALL,
                 from_task=from_task,
                 from_agent=from_agent,
-                messages=params["messages"],
+                messages=messages,
                 usage=None,
             )
             return structured_response

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

@@ -88,9 +88,24 @@ class AzureCompletion(BaseLLM):
     response_format: type[BaseModel] | None = None
     is_openai_model: bool = False
     is_azure_openai_endpoint: bool = False
+    credential_scopes: list[str] | None = None
+
+    # Responses API settings
+    api: Literal["completions", "responses"] = "completions"
+    reasoning_effort: str | None = None
+    instructions: str | None = None
+    store: bool | None = None
+    previous_response_id: str | None = None
+    include: list[str] | None = None
+    builtin_tools: list[str] | None = None
+    parse_tool_outputs: bool = False
+    auto_chain: bool = False
+    auto_chain_reasoning: bool = False
+    max_completion_tokens: int | None = None
 
     _client: Any = PrivateAttr(default=None)
     _async_client: Any = PrivateAttr(default=None)
+    _responses_delegate: Any = PrivateAttr(default=None)
 
     @model_validator(mode="before")
     @classmethod
@@ -115,6 +130,10 @@ class AzureCompletion(BaseLLM):
         data["api_version"] = (
             data.get("api_version") or os.getenv("AZURE_API_VERSION") or "2024-06-01"
         )
+        data["credential_scopes"] = (
+            data.get("credential_scopes")
+            or AzureCompletion._credential_scopes_from_env()
+        )
 
         # Credentials and endpoint are validated lazily in `_init_clients`
         # so the LLM can be constructed before deployment env vars are set.
@@ -140,6 +159,15 @@ class AzureCompletion(BaseLLM):
             hostname == "openai.azure.com" or hostname.endswith(".openai.azure.com")
         ) and "/openai/deployments/" in endpoint
 
+    @staticmethod
+    def _credential_scopes_from_env() -> list[str] | None:
+        """Read ``AZURE_CREDENTIAL_SCOPES`` (comma-separated) into a list."""
+        raw = os.getenv("AZURE_CREDENTIAL_SCOPES")
+        if not raw:
+            return None
+        scopes = [s.strip() for s in raw.split(",") if s.strip()]
+        return scopes or None
+
     @model_validator(mode="after")
     def _init_clients(self) -> AzureCompletion:
         """Eagerly build clients when credentials are available, otherwise
@@ -147,12 +175,89 @@ class AzureCompletion(BaseLLM):
         import time even before deployment env vars are set.
         """
         try:
-            self._client = self._build_sync_client()
-            self._async_client = self._build_async_client()
+            if self.api == "responses":
+                self._init_responses_delegate()
+            else:
+                self._client = self._build_sync_client()
+                self._async_client = self._build_async_client()
         except ValueError:
             pass
         return self
 
+    def _init_responses_delegate(self) -> None:
+        """Create an OpenAICompletion delegate for the Azure OpenAI Responses API.
+
+        The Azure OpenAI Responses API uses the standard OpenAI Python SDK
+        with a base_url pointing to the Azure resource's /openai/v1/ endpoint.
+        """
+        from crewai.llms.providers.openai.completion import OpenAICompletion
+
+        base_url = self._get_responses_base_url()
+
+        delegate_kwargs: dict[str, Any] = {
+            "model": self.model,
+            "api_key": self.api_key,
+            "base_url": base_url,
+            "api": "responses",
+            "provider": "openai",
+            "stream": self.stream,
+        }
+
+        if self.temperature is not None:
+            delegate_kwargs["temperature"] = self.temperature
+        if self.top_p is not None:
+            delegate_kwargs["top_p"] = self.top_p
+        if self.max_tokens is not None:
+            delegate_kwargs["max_tokens"] = self.max_tokens
+        if self.max_completion_tokens is not None:
+            delegate_kwargs["max_completion_tokens"] = self.max_completion_tokens
+        if self.stop:
+            delegate_kwargs["stop"] = self.stop
+        if self.timeout is not None:
+            delegate_kwargs["timeout"] = self.timeout
+        if self.max_retries != 2:
+            delegate_kwargs["max_retries"] = self.max_retries
+        if self.reasoning_effort is not None:
+            delegate_kwargs["reasoning_effort"] = self.reasoning_effort
+        if self.instructions is not None:
+            delegate_kwargs["instructions"] = self.instructions
+        if self.store is not None:
+            delegate_kwargs["store"] = self.store
+        if self.previous_response_id is not None:
+            delegate_kwargs["previous_response_id"] = self.previous_response_id
+        if self.include is not None:
+            delegate_kwargs["include"] = self.include
+        if self.builtin_tools is not None:
+            delegate_kwargs["builtin_tools"] = self.builtin_tools
+        if self.parse_tool_outputs:
+            delegate_kwargs["parse_tool_outputs"] = self.parse_tool_outputs
+        if self.auto_chain:
+            delegate_kwargs["auto_chain"] = self.auto_chain
+        if self.auto_chain_reasoning:
+            delegate_kwargs["auto_chain_reasoning"] = self.auto_chain_reasoning
+        if self.response_format is not None:
+            delegate_kwargs["response_format"] = self.response_format
+        if self.additional_params:
+            delegate_kwargs["additional_params"] = self.additional_params
+
+        self._responses_delegate = OpenAICompletion(**delegate_kwargs)
+
+    def _get_responses_base_url(self) -> str:
+        """Construct the base URL for the Azure OpenAI Responses API.
+
+        Extracts the scheme and host from the configured endpoint and appends
+        the ``/openai/v1/`` path required by the Azure OpenAI Responses API.
+
+        Returns:
+            The Responses API base URL, e.g.
+            ``https://myresource.openai.azure.com/openai/v1/``
+        """
+        if not self.endpoint:
+            raise ValueError("Azure endpoint is required for Responses API")
+        parsed = urlparse(self.endpoint)
+        base = f"{parsed.scheme}://{parsed.netloc}"
+        return f"{base}/openai/v1/"
+
     def _build_sync_client(self) -> Any:
         return ChatCompletionsClient(**self._make_client_kwargs())
 
@@ -188,12 +293,17 @@ class AzureCompletion(BaseLLM):
                 "Azure endpoint is required. Set AZURE_ENDPOINT environment "
                 "variable or pass endpoint parameter."
             )
+        if self.credential_scopes is None:
+            self.credential_scopes = AzureCompletion._credential_scopes_from_env()
+
         client_kwargs: dict[str, Any] = {
             "endpoint": self.endpoint,
             "credential": self._resolve_credential(),
         }
         if self.api_version:
             client_kwargs["api_version"] = self.api_version
+        if self.credential_scopes:
+            client_kwargs["credential_scopes"] = self.credential_scopes
         return client_kwargs
 
     def _resolve_credential(self) -> Any:
@@ -252,6 +362,18 @@ class AzureCompletion(BaseLLM):
             config["presence_penalty"] = self.presence_penalty
         if self.max_tokens is not None:
             config["max_tokens"] = self.max_tokens
+        if self.api != "completions":
+            config["api"] = self.api
+        if self.reasoning_effort is not None:
+            config["reasoning_effort"] = self.reasoning_effort
+        if self.instructions is not None:
+            config["instructions"] = self.instructions
+        if self.store is not None:
+            config["store"] = self.store
+        if self.max_completion_tokens is not None:
+            config["max_completion_tokens"] = self.max_completion_tokens
+        if self.credential_scopes:
+            config["credential_scopes"] = self.credential_scopes
         return config
 
     @staticmethod
@@ -357,10 +479,10 @@ class AzureCompletion(BaseLLM):
         from_agent: Any | None = None,
         response_model: type[BaseModel] | None = None,
     ) -> str | Any:
-        """Call Azure AI Inference chat completions API.
+        """Call Azure AI Inference API.
 
         Args:
-            messages: Input messages for the chat completion
+            messages: Input messages
             tools: List of tool/function definitions
             callbacks: Callback functions (not used in native implementation)
             available_functions: Available functions for tool calling
@@ -369,8 +491,19 @@ class AzureCompletion(BaseLLM):
             response_model: Response model
 
         Returns:
-            Chat completion response or tool call result
+            Completion response or tool call result
         """
+        if self.api == "responses":
+            return self._responses_delegate.call(
+                messages=messages,
+                tools=tools,
+                callbacks=callbacks,
+                available_functions=available_functions,
+                from_task=from_task,
+                from_agent=from_agent,
+                response_model=response_model,
+            )
+
         with llm_call_context():
             try:
                 # Emit call started event
@@ -429,10 +562,10 @@ class AzureCompletion(BaseLLM):
         from_agent: Any | None = None,
         response_model: type[BaseModel] | None = None,
     ) -> str | Any:
-        """Call Azure AI Inference chat completions API asynchronously.
+        """Call Azure AI Inference API asynchronously.
 
         Args:
-            messages: Input messages for the chat completion
+            messages: Input messages
             tools: List of tool/function definitions
             callbacks: Callback functions (not used in native implementation)
             available_functions: Available functions for tool calling
@@ -441,8 +574,19 @@ class AzureCompletion(BaseLLM):
             response_model: Pydantic model for structured output
 
         Returns:
-            Chat completion response or tool call result
+            Completion response or tool call result
         """
+        if self.api == "responses":
+            return await self._responses_delegate.acall(
+                messages=messages,
+                tools=tools,
+                callbacks=callbacks,
+                available_functions=available_functions,
+                from_task=from_task,
+                from_agent=from_agent,
+                response_model=response_model,
+            )
+
         with llm_call_context():
             try:
                 self._emit_call_started_event(
@@ -1178,6 +1322,32 @@ class AzureCompletion(BaseLLM):
             return result
         return {"total_tokens": 0}
 
+    @property
+    def last_response_id(self) -> str | None:
+        """Get the last response ID from Responses API auto-chaining."""
+        if self._responses_delegate is not None:
+            result: str | None = self._responses_delegate.last_response_id
+            return result
+        return None
+
+    @property
+    def last_reasoning_items(self) -> list[Any] | None:
+        """Get the last reasoning items from Responses API auto-chain reasoning."""
+        if self._responses_delegate is not None:
+            result: list[Any] | None = self._responses_delegate.last_reasoning_items
+            return result
+        return None
+
+    def reset_chain(self) -> None:
+        """Reset the Responses API auto-chain state."""
+        if self._responses_delegate is not None:
+            self._responses_delegate.reset_chain()
+
+    def reset_reasoning_chain(self) -> None:
+        """Reset the Responses API reasoning chain state."""
+        if self._responses_delegate is not None:
+            self._responses_delegate.reset_reasoning_chain()
+
     async def aclose(self) -> None:
         """Close the async client and clean up resources.
 

lib/crewai/src/crewai/mcp/tool_resolver.py

@@ -374,6 +374,7 @@ class MCPToolResolver:
                             "MCP connection failed due to event loop cleanup issues. "
                             "This may be due to authentication errors or server unavailability."
                         ) from e
+                    raise
                 except asyncio.CancelledError as e:
                     raise ConnectionError(
                         "MCP connection was cancelled. This may indicate an authentication "
@@ -401,6 +402,13 @@ class MCPToolResolver:
                         filtered_tools.append(tool)
                 tools_list = filtered_tools
 
+            if not tools_list:
+                self._logger.log(
+                    "warning",
+                    f"No tools discovered from MCP server: {server_name}",
+                )
+                return cast(list[BaseTool], []), []
+
             def _client_factory() -> MCPClient:
                 transport, _ = self._create_transport(mcp_config)
                 return MCPClient(

lib/crewai/src/crewai/utilities/internal_instructor.py

@@ -98,7 +98,14 @@ class InternalInstructor(Generic[T]):
         else:
             provider = "openai"  # Default fallback
 
-        return instructor.from_provider(f"{provider}/{model_string}")
+        extra_kwargs: dict[str, Any] = {}
+        if self.llm is not None and not isinstance(self.llm, str):
+            for attr in ("base_url", "api_key"):
+                value = getattr(self.llm, attr, None)
+                if value is not None:
+                    extra_kwargs[attr] = value
+
+        return instructor.from_provider(f"{provider}/{model_string}", **extra_kwargs)
 
     def _extract_provider(self) -> str:
         """Extract provider from LLM model name.

lib/crewai/tests/cassettes/llms/azure/TestAzureResponsesCall.test_call_delegates_to_responses.yaml

@@ -0,0 +1,133 @@
+interactions:
+- request:
+    body: '{"input":[{"role":"user","content":"Say hello in one sentence."}],"model":"gpt-5.2-chat"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '89'
+      content-type:
+      - application/json
+      host:
+      - kkarmakar-ai-eus2.openai.azure.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:
+      - 2.32.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/v1/responses
+  response:
+    body:
+      string: "{\n  \"id\": \"resp_0473c8c2b1c49f8c0069f23d0910e081958ebce72a734935c7\",\n
+        \ \"object\": \"response\",\n  \"created_at\": 1777483017,\n  \"status\":
+        \"completed\",\n  \"background\": false,\n  \"completed_at\": 1777483018,\n
+        \ \"content_filters\": [\n    {\n      \"blocked\": false,\n      \"source_type\":
+        \"prompt\",\n      \"content_filter_raw\": [],\n      \"content_filter_results\":
+        {\n        \"jailbreak\": {\n          \"detected\": false,\n          \"filtered\":
+        false\n        },\n        \"hate\": {\n          \"filtered\": false,\n          \"severity\":
+        \"safe\"\n        },\n        \"sexual\": {\n          \"filtered\": false,\n
+        \         \"severity\": \"safe\"\n        },\n        \"violence\": {\n          \"filtered\":
+        false,\n          \"severity\": \"safe\"\n        },\n        \"self_harm\":
+        {\n          \"filtered\": false,\n          \"severity\": \"safe\"\n        }\n
+        \     },\n      \"content_filter_offsets\": {\n        \"start_offset\": 0,\n
+        \       \"end_offset\": 368,\n        \"check_offset\": 0\n      }\n    },\n
+        \   {\n      \"blocked\": false,\n      \"source_type\": \"completion\",\n
+        \     \"content_filter_raw\": [],\n      \"content_filter_results\": {\n        \"protected_material_code\":
+        {\n          \"detected\": false,\n          \"filtered\": false\n        },\n
+        \       \"protected_material_text\": {\n          \"detected\": false,\n          \"filtered\":
+        false\n        },\n        \"hate\": {\n          \"filtered\": false,\n          \"severity\":
+        \"safe\"\n        },\n        \"sexual\": {\n          \"filtered\": false,\n
+        \         \"severity\": \"safe\"\n        },\n        \"violence\": {\n          \"filtered\":
+        false,\n          \"severity\": \"safe\"\n        },\n        \"self_harm\":
+        {\n          \"filtered\": false,\n          \"severity\": \"safe\"\n        }\n
+        \     },\n      \"content_filter_offsets\": {\n        \"start_offset\": 0,\n
+        \       \"end_offset\": 53,\n        \"check_offset\": 0\n      }\n    }\n
+        \ ],\n  \"error\": null,\n  \"frequency_penalty\": 0.0,\n  \"incomplete_details\":
+        null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"max_tool_calls\":
+        null,\n  \"model\": \"gpt-5.2-chat\",\n  \"output\": [\n    {\n      \"id\":
+        \"rs_0473c8c2b1c49f8c0069f23d09f24481959bcf9fd847a9a475\",\n      \"type\":
+        \"reasoning\",\n      \"summary\": []\n    },\n    {\n      \"id\": \"msg_0473c8c2b1c49f8c0069f23d0a8ccc81958f776ad6016d7edd\",\n
+        \     \"type\": \"message\",\n      \"status\": \"completed\",\n      \"content\":
+        [\n        {\n          \"type\": \"output_text\",\n          \"annotations\":
+        [],\n          \"logprobs\": [],\n          \"text\": \"Hello! \\ud83d\\ude0a\"\n
+        \       }\n      ],\n      \"role\": \"assistant\"\n    }\n  ],\n  \"parallel_tool_calls\":
+        true,\n  \"presence_penalty\": 0.0,\n  \"previous_response_id\": null,\n  \"prompt_cache_key\":
+        null,\n  \"prompt_cache_retention\": null,\n  \"reasoning\": {\n    \"effort\":
+        \"medium\",\n    \"summary\": null\n  },\n  \"safety_identifier\": null,\n
+        \ \"service_tier\": \"default\",\n  \"store\": true,\n  \"temperature\": 1.0,\n
+        \ \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    },\n    \"verbosity\":
+        \"medium\"\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_logprobs\":
+        0,\n  \"top_p\": 0.85,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n
+        \   \"input_tokens\": 12,\n    \"input_tokens_details\": {\n      \"cached_tokens\":
+        0\n    },\n    \"output_tokens\": 22,\n    \"output_tokens_details\": {\n
+        \     \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 34\n  },\n  \"user\":
+        null,\n  \"metadata\": {}\n}"
+    headers:
+      Content-Length:
+      - '3203'
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 29 Apr 2026 17:16:59 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      skip-error-remapping:
+      - 'true'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-is-spilled-over:
+      - 'false'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-abusepenalty-active:
+      - 'False'
+      x-ratelimit-key:
+      - gpt-5.2-chat
+      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-renewalperiod-requests:
+      - '60'
+      x-ratelimit-renewalperiod-tokens:
+      - '60'
+      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/llms/azure/TestAzureResponsesCall.test_call_with_tools_delegates.yaml

@@ -0,0 +1,137 @@
+interactions:
+- request:
+    body: '{"input":[{"role":"user","content":"What is 2 + 2? Be brief."}],"model":"gpt-5.2-chat","tools":[{"type":"web_search_preview"}]}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '127'
+      content-type:
+      - application/json
+      host:
+      - kkarmakar-ai-eus2.openai.azure.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:
+      - 2.32.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/v1/responses
+  response:
+    body:
+      string: "{\n  \"id\": \"resp_0d80ad9adad65fca0069f23d0c904c8194862acae4bd866cf5\",\n
+        \ \"object\": \"response\",\n  \"created_at\": 1777483020,\n  \"status\":
+        \"completed\",\n  \"background\": false,\n  \"completed_at\": 1777483022,\n
+        \ \"content_filters\": [\n    {\n      \"blocked\": false,\n      \"source_type\":
+        \"prompt\",\n      \"content_filter_raw\": [],\n      \"content_filter_results\":
+        {\n        \"jailbreak\": {\n          \"detected\": false,\n          \"filtered\":
+        false\n        },\n        \"hate\": {\n          \"filtered\": false,\n          \"severity\":
+        \"safe\"\n        },\n        \"sexual\": {\n          \"filtered\": false,\n
+        \         \"severity\": \"safe\"\n        },\n        \"violence\": {\n          \"filtered\":
+        false,\n          \"severity\": \"safe\"\n        },\n        \"self_harm\":
+        {\n          \"filtered\": false,\n          \"severity\": \"safe\"\n        }\n
+        \     },\n      \"content_filter_offsets\": {\n        \"start_offset\": 0,\n
+        \       \"end_offset\": 19017,\n        \"check_offset\": 0\n      }\n    },\n
+        \   {\n      \"blocked\": false,\n      \"source_type\": \"completion\",\n
+        \     \"content_filter_raw\": [],\n      \"content_filter_results\": {\n        \"hate\":
+        {\n          \"filtered\": false,\n          \"severity\": \"safe\"\n        },\n
+        \       \"sexual\": {\n          \"filtered\": false,\n          \"severity\":
+        \"safe\"\n        },\n        \"violence\": {\n          \"filtered\": false,\n
+        \         \"severity\": \"safe\"\n        },\n        \"self_harm\": {\n          \"filtered\":
+        false,\n          \"severity\": \"safe\"\n        },\n        \"protected_material_code\":
+        {\n          \"detected\": false,\n          \"filtered\": false\n        },\n
+        \       \"protected_material_text\": {\n          \"detected\": false,\n          \"filtered\":
+        false\n        }\n      },\n      \"content_filter_offsets\": {\n        \"start_offset\":
+        0,\n        \"end_offset\": 889,\n        \"check_offset\": 0\n      }\n    }\n
+        \ ],\n  \"error\": null,\n  \"frequency_penalty\": 0.0,\n  \"incomplete_details\":
+        null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"max_tool_calls\":
+        null,\n  \"model\": \"gpt-5.2-chat\",\n  \"output\": [\n    {\n      \"id\":
+        \"rs_0d80ad9adad65fca0069f23d0d8b8c8194b1a9ab61ddc3420d\",\n      \"type\":
+        \"reasoning\",\n      \"summary\": []\n    },\n    {\n      \"id\": \"msg_0d80ad9adad65fca0069f23d0e262081949c36d6cc1958eeed\",\n
+        \     \"type\": \"message\",\n      \"status\": \"completed\",\n      \"content\":
+        [\n        {\n          \"type\": \"output_text\",\n          \"annotations\":
+        [],\n          \"logprobs\": [],\n          \"text\": \"2 + 2 = 4.\"\n        }\n
+        \     ],\n      \"role\": \"assistant\"\n    }\n  ],\n  \"parallel_tool_calls\":
+        true,\n  \"presence_penalty\": 0.0,\n  \"previous_response_id\": null,\n  \"prompt_cache_key\":
+        null,\n  \"prompt_cache_retention\": null,\n  \"reasoning\": {\n    \"effort\":
+        \"medium\",\n    \"summary\": null\n  },\n  \"safety_identifier\": null,\n
+        \ \"service_tier\": \"default\",\n  \"store\": true,\n  \"temperature\": 1.0,\n
+        \ \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    },\n    \"verbosity\":
+        \"medium\"\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"type\":
+        \"web_search_preview\",\n      \"search_content_types\": [\n        \"text\"\n
+        \     ],\n      \"search_context_size\": \"medium\",\n      \"user_location\":
+        {\n        \"type\": \"approximate\",\n        \"city\": null,\n        \"country\":
+        \"US\",\n        \"region\": null,\n        \"timezone\": null\n      }\n
+        \   }\n  ],\n  \"top_logprobs\": 0,\n  \"top_p\": 0.85,\n  \"truncation\":
+        \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 4312,\n    \"input_tokens_details\":
+        {\n      \"cached_tokens\": 0\n    },\n    \"output_tokens\": 28,\n    \"output_tokens_details\":
+        {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 4340\n  },\n
+        \ \"user\": null,\n  \"metadata\": {}\n}"
+    headers:
+      Content-Length:
+      - '3507'
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 29 Apr 2026 17:17:03 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      skip-error-remapping:
+      - 'true'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-is-spilled-over:
+      - 'false'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-abusepenalty-active:
+      - 'False'
+      x-ratelimit-key:
+      - gpt-5.2-chat
+      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-renewalperiod-requests:
+      - '60'
+      x-ratelimit-renewalperiod-tokens:
+      - '60'
+      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/llms/azure/TestAzureResponsesCall.test_completions_call_unchanged.yaml

@@ -0,0 +1,84 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "Say hello in one sentence."}],
+      "stream": false}'
+    headers:
+      Accept:
+      - application/json
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '90'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      api-key:
+      - X-API-KEY-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-5.2-chat/chat/completions?api-version=2024-02-15-preview
+  response:
+    body:
+      string: "{\"choices\":[{\"content_filter_results\":{\"hate\":{\"filtered\":false,\"severity\":\"safe\"},\"protected_material_code\":{\"detected\":false,\"filtered\":false},\"protected_material_text\":{\"detected\":false,\"filtered\":false},\"self_harm\":{\"filtered\":false,\"severity\":\"safe\"},\"sexual\":{\"filtered\":false,\"severity\":\"safe\"},\"violence\":{\"filtered\":false,\"severity\":\"safe\"}},\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"annotations\":[],\"content\":\"Hello!
+        \U0001F60A\",\"refusal\":null,\"role\":\"assistant\"}}],\"created\":1777483024,\"id\":\"chatcmpl-Da2oyIDHFopG5fmCKbhDiEYG5ciBN\",\"model\":\"gpt-5.2-chat-latest\",\"object\":\"chat.completion\",\"prompt_filter_results\":[{\"prompt_index\":0,\"content_filter_results\":{\"hate\":{\"filtered\":false,\"severity\":\"safe\"},\"jailbreak\":{\"detected\":false,\"filtered\":false},\"self_harm\":{\"filtered\":false,\"severity\":\"safe\"},\"sexual\":{\"filtered\":false,\"severity\":\"safe\"},\"violence\":{\"filtered\":false,\"severity\":\"safe\"}}}],\"service_tier\":\"default\",\"system_fingerprint\":null,\"usage\":{\"completion_tokens\":13,\"completion_tokens_details\":{\"accepted_prediction_tokens\":0,\"audio_tokens\":0,\"reasoning_tokens\":0,\"rejected_prediction_tokens\":0},\"prompt_tokens\":12,\"prompt_tokens_details\":{\"audio_tokens\":0,\"cached_tokens\":0},\"total_tokens\":25}}\n"
+    headers:
+      Content-Length:
+      - '1233'
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 29 Apr 2026 17:17:05 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      azureml-model-session:
+      - AZUREML-MODEL-SESSION-XXX
+      skip-error-remapping:
+      - 'true'
+      x-accel-buffering:
+      - 'no'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-deployment-name:
+      - gpt-5.2-chat
+      x-ms-is-spilled-over:
+      - 'false'
+      x-ms-rai-invoked:
+      - 'true'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-abusepenalty-active:
+      - 'False'
+      x-ratelimit-key:
+      - gpt-5.2-chat
+      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-renewalperiod-requests:
+      - '60'
+      x-ratelimit-renewalperiod-tokens:
+      - '60'
+      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/llms/azure/test_acall_delegates_to_responses.yaml

@@ -0,0 +1,128 @@
+interactions:
+- request:
+    body: '{"input":[{"role":"user","content":"Say hello in one sentence."}],"model":"gpt-5.2-chat"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '89'
+      content-type:
+      - application/json
+      host:
+      - kkarmakar-ai-eus2.openai.azure.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:
+      - 2.32.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.12
+    method: POST
+    uri: https://fake-azure-endpoint.openai.azure.com/openai/v1/responses
+  response:
+    body:
+      string: "{\n  \"id\": \"resp_02861ec017218a520069f23d21dbf88193aa91a73d63d91302\",\n
+        \ \"object\": \"response\",\n  \"created_at\": 1777483041,\n  \"status\":
+        \"completed\",\n  \"background\": false,\n  \"completed_at\": 1777483043,\n
+        \ \"content_filters\": [\n    {\n      \"blocked\": false,\n      \"source_type\":
+        \"prompt\",\n      \"content_filter_raw\": [],\n      \"content_filter_results\":
+        {\n        \"jailbreak\": {\n          \"detected\": false,\n          \"filtered\":
+        false\n        }\n      },\n      \"content_filter_offsets\": {\n        \"start_offset\":
+        0,\n        \"end_offset\": 368,\n        \"check_offset\": 0\n      }\n    },\n
+        \   {\n      \"blocked\": false,\n      \"source_type\": \"completion\",\n
+        \     \"content_filter_raw\": [],\n      \"content_filter_results\": {\n        \"protected_material_text\":
+        {\n          \"detected\": false,\n          \"filtered\": false\n        },\n
+        \       \"protected_material_code\": {\n          \"detected\": false,\n          \"filtered\":
+        false\n        },\n        \"hate\": {\n          \"filtered\": false,\n          \"severity\":
+        \"safe\"\n        },\n        \"sexual\": {\n          \"filtered\": false,\n
+        \         \"severity\": \"safe\"\n        },\n        \"violence\": {\n          \"filtered\":
+        false,\n          \"severity\": \"safe\"\n        },\n        \"self_harm\":
+        {\n          \"filtered\": false,\n          \"severity\": \"safe\"\n        }\n
+        \     },\n      \"content_filter_offsets\": {\n        \"start_offset\": 0,\n
+        \       \"end_offset\": 44,\n        \"check_offset\": 0\n      }\n    }\n
+        \ ],\n  \"error\": null,\n  \"frequency_penalty\": 0.0,\n  \"incomplete_details\":
+        null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"max_tool_calls\":
+        null,\n  \"model\": \"gpt-5.2-chat\",\n  \"output\": [\n    {\n      \"id\":
+        \"rs_02861ec017218a520069f23d2287ac819399dd23b8dd56028e\",\n      \"type\":
+        \"reasoning\",\n      \"summary\": []\n    },\n    {\n      \"id\": \"msg_02861ec017218a520069f23d23082c81939838ab2eebf4e89c\",\n
+        \     \"type\": \"message\",\n      \"status\": \"completed\",\n      \"content\":
+        [\n        {\n          \"type\": \"output_text\",\n          \"annotations\":
+        [],\n          \"logprobs\": [],\n          \"text\": \"Hello! \\ud83d\\udc4b\"\n
+        \       }\n      ],\n      \"role\": \"assistant\"\n    }\n  ],\n  \"parallel_tool_calls\":
+        true,\n  \"presence_penalty\": 0.0,\n  \"previous_response_id\": null,\n  \"prompt_cache_key\":
+        null,\n  \"prompt_cache_retention\": null,\n  \"reasoning\": {\n    \"effort\":
+        \"medium\",\n    \"summary\": null\n  },\n  \"safety_identifier\": null,\n
+        \ \"service_tier\": \"default\",\n  \"store\": true,\n  \"temperature\": 1.0,\n
+        \ \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    },\n    \"verbosity\":
+        \"medium\"\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_logprobs\":
+        0,\n  \"top_p\": 0.85,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n
+        \   \"input_tokens\": 12,\n    \"input_tokens_details\": {\n      \"cached_tokens\":
+        0\n    },\n    \"output_tokens\": 21,\n    \"output_tokens_details\": {\n
+        \     \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 33\n  },\n  \"user\":
+        null,\n  \"metadata\": {}\n}"
+    headers:
+      Content-Length:
+      - '2844'
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 29 Apr 2026 17:17:25 GMT
+      Strict-Transport-Security:
+      - STS-XXX
+      apim-request-id:
+      - APIM-REQUEST-ID-XXX
+      skip-error-remapping:
+      - 'true'
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ms-client-request-id:
+      - X-MS-CLIENT-REQUEST-ID-XXX
+      x-ms-is-spilled-over:
+      - 'false'
+      x-ms-region:
+      - X-MS-REGION-XXX
+      x-ratelimit-abusepenalty-active:
+      - 'False'
+      x-ratelimit-key:
+      - gpt-5.2-chat
+      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-renewalperiod-requests:
+      - '60'
+      x-ratelimit-renewalperiod-tokens:
+      - '60'
+      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/llms/azure/test_azure.py

@@ -1518,3 +1518,120 @@ def test_azure_no_detail_fields():
     assert usage["completion_tokens"] == 30
     assert usage["cached_prompt_tokens"] == 0
     assert usage["reasoning_tokens"] == 0
+
+
+def test_azure_credential_scopes_passed_to_client():
+    """`credential_scopes` constructor arg flows through `_make_client_kwargs`
+    so the underlying ChatCompletionsClient requests tokens for the requested
+    audience (e.g. ``cognitiveservices.azure.com/.default``)."""
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    scopes = ["https://cognitiveservices.azure.com/.default"]
+    with patch.dict(os.environ, {}, clear=True):
+        llm = AzureCompletion(
+            model="gpt-4",
+            api_key="test-key",
+            endpoint="https://test.openai.azure.com",
+            credential_scopes=scopes,
+        )
+        kwargs = llm._make_client_kwargs()
+        assert kwargs["credential_scopes"] == scopes
+
+
+def test_azure_credential_scopes_omitted_by_default():
+    """Without explicit scopes or env var, the kwarg must not be set so the
+    Azure SDK chooses its own default audience."""
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    with patch.dict(os.environ, {}, clear=True):
+        llm = AzureCompletion(
+            model="gpt-4",
+            api_key="test-key",
+            endpoint="https://test.openai.azure.com",
+        )
+        kwargs = llm._make_client_kwargs()
+        assert "credential_scopes" not in kwargs
+
+
+def test_azure_credential_scopes_from_env_comma_separated():
+    """``AZURE_CREDENTIAL_SCOPES`` accepts a comma-separated list. Whitespace
+    around entries is stripped; empty entries are dropped."""
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    with patch.dict(
+        os.environ,
+        {
+            "AZURE_API_KEY": "test-key",
+            "AZURE_ENDPOINT": "https://test.openai.azure.com",
+            "AZURE_CREDENTIAL_SCOPES": " https://cognitiveservices.azure.com/.default , https://other/.default ",
+        },
+        clear=True,
+    ):
+        llm = AzureCompletion(model="gpt-4")
+        assert llm.credential_scopes == [
+            "https://cognitiveservices.azure.com/.default",
+            "https://other/.default",
+        ]
+        kwargs = llm._make_client_kwargs()
+        assert kwargs["credential_scopes"] == llm.credential_scopes
+
+
+def test_azure_credential_scopes_constructor_overrides_env():
+    """A constructor-provided ``credential_scopes`` must win over the env var,
+    matching how endpoint/api_key precedence works elsewhere in this provider."""
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    explicit = ["https://explicit/.default"]
+    with patch.dict(
+        os.environ,
+        {
+            "AZURE_API_KEY": "test-key",
+            "AZURE_ENDPOINT": "https://test.openai.azure.com",
+            "AZURE_CREDENTIAL_SCOPES": "https://env/.default",
+        },
+        clear=True,
+    ):
+        llm = AzureCompletion(model="gpt-4", credential_scopes=explicit)
+        assert llm.credential_scopes == explicit
+
+
+def test_azure_credential_scopes_lazy_env_read():
+    """When the LLM is built before ``AZURE_CREDENTIAL_SCOPES`` is exported
+    (e.g. constructed at module import), the lazy client builder must still
+    pick up the env value — same pattern as the existing api_key/endpoint
+    lazy reads."""
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    with patch.dict(os.environ, {}, clear=True):
+        llm = AzureCompletion(
+            model="gpt-4",
+            api_key="test-key",
+            endpoint="https://test.openai.azure.com",
+        )
+        assert llm.credential_scopes is None
+
+    with patch.dict(
+        os.environ,
+        {"AZURE_CREDENTIAL_SCOPES": "https://late/.default"},
+        clear=True,
+    ):
+        kwargs = llm._make_client_kwargs()
+        assert kwargs["credential_scopes"] == ["https://late/.default"]
+        assert llm.credential_scopes == ["https://late/.default"]
+
+
+def test_azure_credential_scopes_in_to_config_dict():
+    """Config round-trips the scopes so an LLM rebuilt from `to_config_dict`
+    keeps the same audience."""
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    scopes = ["https://cognitiveservices.azure.com/.default"]
+    with patch.dict(os.environ, {}, clear=True):
+        llm = AzureCompletion(
+            model="gpt-4",
+            api_key="test-key",
+            endpoint="https://test.openai.azure.com",
+            credential_scopes=scopes,
+        )
+        config = llm.to_config_dict()
+        assert config["credential_scopes"] == scopes

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

@@ -0,0 +1,395 @@
+"""Tests for Azure OpenAI Responses API support.
+
+Verifies that AzureCompletion with api='responses' correctly delegates
+to OpenAICompletion configured with the Azure OpenAI /openai/v1/ base URL.
+"""
+
+import os
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+
+# ---------------------------------------------------------------------------
+# Fixtures
+# ---------------------------------------------------------------------------
+
+
+@pytest.fixture
+def azure_env():
+    """Set Azure environment variables for tests."""
+    with patch.dict(
+        os.environ,
+        {
+            "AZURE_API_KEY": "test-azure-key",
+            "AZURE_ENDPOINT": "https://myresource.openai.azure.com",
+        },
+    ):
+        yield
+
+
+@pytest.fixture
+def mock_openai_completion():
+    """Mock OpenAICompletion to avoid real client creation.
+
+    Patches at the source module so that the dynamic import inside
+    _init_responses_delegate picks up the mock.
+    """
+    instance = MagicMock()
+    instance.call = MagicMock(return_value="responses-result")
+    instance.acall = AsyncMock(return_value="async-responses-result")
+    instance.last_response_id = "resp_abc123"
+    instance.last_reasoning_items = [{"type": "reasoning"}]
+    instance.reset_chain = MagicMock()
+    instance.reset_reasoning_chain = MagicMock()
+    mock_cls = MagicMock(return_value=instance)
+
+    with patch(
+        "crewai.llms.providers.openai.completion.OpenAICompletion",
+        mock_cls,
+    ):
+        yield mock_cls, instance
+
+
+# ---------------------------------------------------------------------------
+# Helper to build AzureCompletion with api="responses" while mocking imports
+# ---------------------------------------------------------------------------
+
+
+def _create_azure_responses(**overrides):
+    """Create an AzureCompletion(api='responses').
+
+    Must be called inside a context where OpenAICompletion is already mocked
+    (i.e. via the ``mock_openai_completion`` fixture).
+    """
+    from crewai.llms.providers.azure.completion import AzureCompletion
+
+    defaults = {
+        "model": "gpt-4o",
+        "api_key": "test-azure-key",
+        "endpoint": "https://myresource.openai.azure.com",
+        "api": "responses",
+    }
+    defaults.update(overrides)
+    return AzureCompletion(**defaults)
+
+
+# ---------------------------------------------------------------------------
+# Initialization tests
+# ---------------------------------------------------------------------------
+
+
+class TestAzureResponsesInit:
+    """Test initialization with api='responses'."""
+
+    def test_default_api_is_completions(self):
+        """Default api should be 'completions' (existing behaviour)."""
+        from crewai.llms.providers.azure.completion import AzureCompletion
+
+        comp = AzureCompletion(
+            model="gpt-4o",
+            api_key="key",
+            endpoint="https://res.openai.azure.com",
+        )
+        assert comp.api == "completions"
+        assert comp._responses_delegate is None
+
+    def test_responses_api_creates_delegate(self, mock_openai_completion):
+        mock_cls, instance = mock_openai_completion
+        comp = _create_azure_responses()
+
+        assert comp.api == "responses"
+        assert comp._responses_delegate is instance
+        mock_cls.assert_called_once()
+
+    def test_completions_clients_not_created_in_responses_mode(
+        self, mock_openai_completion
+    ):
+        """When api='responses', azure-ai-inference clients should not be created."""
+        _mock_cls, _ = mock_openai_completion
+        comp = _create_azure_responses()
+
+        assert comp._client is None
+        assert comp._async_client is None
+
+    def test_responses_base_url_from_base_endpoint(self, mock_openai_completion):
+        mock_cls, _ = mock_openai_completion
+        _create_azure_responses(
+            endpoint="https://myresource.openai.azure.com",
+        )
+        call_kwargs = mock_cls.call_args[1]
+        assert (
+            call_kwargs["base_url"] == "https://myresource.openai.azure.com/openai/v1/"
+        )
+
+    def test_responses_base_url_strips_deployment_path(self, mock_openai_completion):
+        """Endpoint with /openai/deployments/... should still produce correct base_url."""
+        mock_cls, _ = mock_openai_completion
+        _create_azure_responses(
+            endpoint="https://myresource.openai.azure.com/openai/deployments/gpt-4o",
+        )
+        call_kwargs = mock_cls.call_args[1]
+        assert (
+            call_kwargs["base_url"] == "https://myresource.openai.azure.com/openai/v1/"
+        )
+
+    def test_responses_base_url_preserves_port(self, mock_openai_completion):
+        mock_cls, _ = mock_openai_completion
+        _create_azure_responses(
+            endpoint="https://myresource.openai.azure.com:8443/openai/deployments/gpt-4o",
+        )
+        call_kwargs = mock_cls.call_args[1]
+        assert (
+            call_kwargs["base_url"]
+            == "https://myresource.openai.azure.com:8443/openai/v1/"
+        )
+
+    def test_delegate_receives_model_and_api_key(self, mock_openai_completion):
+        mock_cls, _ = mock_openai_completion
+        _create_azure_responses(
+            model="gpt-4o",
+            api_key="my-key",
+        )
+        call_kwargs = mock_cls.call_args[1]
+        assert call_kwargs["model"] == "gpt-4o"
+        assert call_kwargs["api_key"] == "my-key"
+        assert call_kwargs["api"] == "responses"
+        assert call_kwargs["provider"] == "openai"
+
+    def test_delegate_receives_optional_params(self, mock_openai_completion):
+        mock_cls, _ = mock_openai_completion
+        _create_azure_responses(
+            temperature=0.5,
+            top_p=0.9,
+            max_tokens=1000,
+            max_completion_tokens=800,
+            reasoning_effort="medium",
+            instructions="Be helpful",
+            store=True,
+            previous_response_id="resp_prev",
+            include=["reasoning.encrypted_content"],
+            builtin_tools=["web_search"],
+            parse_tool_outputs=True,
+            auto_chain=True,
+            auto_chain_reasoning=True,
+            stream=True,
+        )
+        call_kwargs = mock_cls.call_args[1]
+        assert call_kwargs["temperature"] == 0.5
+        assert call_kwargs["top_p"] == 0.9
+        assert call_kwargs["max_tokens"] == 1000
+        assert call_kwargs["max_completion_tokens"] == 800
+        assert call_kwargs["reasoning_effort"] == "medium"
+        assert call_kwargs["instructions"] == "Be helpful"
+        assert call_kwargs["store"] is True
+        assert call_kwargs["previous_response_id"] == "resp_prev"
+        assert call_kwargs["include"] == ["reasoning.encrypted_content"]
+        assert call_kwargs["builtin_tools"] == ["web_search"]
+        assert call_kwargs["parse_tool_outputs"] is True
+        assert call_kwargs["auto_chain"] is True
+        assert call_kwargs["auto_chain_reasoning"] is True
+        assert call_kwargs["stream"] is True
+
+    def test_delegate_omits_unset_optional_params(self, mock_openai_completion):
+        """Params left at defaults should not be passed to the delegate."""
+        mock_cls, _ = mock_openai_completion
+        _create_azure_responses()
+        call_kwargs = mock_cls.call_args[1]
+        # These should NOT be in kwargs because they were not set
+        assert "temperature" not in call_kwargs
+        assert "reasoning_effort" not in call_kwargs
+        assert "instructions" not in call_kwargs
+        assert "store" not in call_kwargs
+        assert "max_completion_tokens" not in call_kwargs
+
+
+# ---------------------------------------------------------------------------
+# Call delegation tests (VCR cassette-based)
+# ---------------------------------------------------------------------------
+
+
+class TestAzureResponsesCall:
+    """Test call / acall delegation to the Responses API using VCR cassettes."""
+
+    @pytest.mark.vcr()
+    def test_call_delegates_to_responses(self):
+        from crewai.llm import LLM
+
+        llm = LLM(model="azure/gpt-5.2-chat", api="responses")
+        result = llm.call("Say hello in one sentence.")
+
+        assert isinstance(result, str)
+        assert len(result) > 0
+
+    @pytest.mark.vcr()
+    def test_call_with_tools_delegates(self):
+        from crewai.llm import LLM
+
+        llm = LLM(
+            model="azure/gpt-5.2-chat",
+            api="responses",
+            builtin_tools=["web_search"],
+        )
+        result = llm.call("What is 2 + 2? Be brief.")
+
+        assert isinstance(result, str)
+        assert len(result) > 0
+
+    @pytest.mark.vcr()
+    def test_completions_call_unchanged(self):
+        """Default api='completions' should not use the responses delegate."""
+        from crewai.llm import LLM
+
+        llm = LLM(model="azure/gpt-5.2-chat")
+        result = llm.call("Say hello in one sentence.")
+
+        assert isinstance(result, str)
+        assert len(result) > 0
+
+
+# ---------------------------------------------------------------------------
+# Delegated property & method tests
+# ---------------------------------------------------------------------------
+
+
+class TestAzureResponsesProperties:
+    """Test properties and methods delegated to the responses delegate."""
+
+    def test_last_response_id(self, mock_openai_completion):
+        _mock_cls, _ = mock_openai_completion
+        comp = _create_azure_responses()
+        assert comp.last_response_id == "resp_abc123"
+
+    def test_last_response_id_none_for_completions(self):
+        from crewai.llms.providers.azure.completion import AzureCompletion
+
+        comp = AzureCompletion(
+            model="gpt-4o",
+            api_key="key",
+            endpoint="https://res.openai.azure.com",
+        )
+        assert comp.last_response_id is None
+
+    def test_last_reasoning_items(self, mock_openai_completion):
+        _mock_cls, _ = mock_openai_completion
+        comp = _create_azure_responses()
+        assert comp.last_reasoning_items == [{"type": "reasoning"}]
+
+    def test_reset_chain(self, mock_openai_completion):
+        _mock_cls, instance = mock_openai_completion
+        comp = _create_azure_responses()
+        comp.reset_chain()
+        instance.reset_chain.assert_called_once()
+
+    def test_reset_reasoning_chain(self, mock_openai_completion):
+        _mock_cls, instance = mock_openai_completion
+        comp = _create_azure_responses()
+        comp.reset_reasoning_chain()
+        instance.reset_reasoning_chain.assert_called_once()
+
+    def test_reset_chain_noop_for_completions(self):
+        """reset_chain should not raise when delegate is None."""
+        from crewai.llms.providers.azure.completion import AzureCompletion
+
+        comp = AzureCompletion(
+            model="gpt-4o",
+            api_key="key",
+            endpoint="https://res.openai.azure.com",
+        )
+        comp.reset_chain()  # should not raise
+
+
+# ---------------------------------------------------------------------------
+# Feature-support method tests
+# ---------------------------------------------------------------------------
+
+
+class TestAzureResponsesFeatures:
+    """Test supports_* and config methods."""
+
+    def test_supports_function_calling_responses(self, mock_openai_completion):
+        _mock_cls, _ = mock_openai_completion
+        comp = _create_azure_responses()
+        assert comp.supports_function_calling() is True
+
+    def test_supports_function_calling_completions_openai_model(self):
+        from crewai.llms.providers.azure.completion import AzureCompletion
+
+        comp = AzureCompletion(
+            model="gpt-4o",
+            api_key="key",
+            endpoint="https://res.openai.azure.com",
+        )
+        assert comp.supports_function_calling() is True
+
+    def test_supports_stop_words_false_for_responses(self, mock_openai_completion):
+        _mock_cls, _ = mock_openai_completion
+        comp = _create_azure_responses(model="o4-mini")
+        assert comp.supports_stop_words() is False
+
+    def test_supports_stop_words_true_for_completions_gpt4(self):
+        from crewai.llms.providers.azure.completion import AzureCompletion
+
+        comp = AzureCompletion(
+            model="gpt-4o",
+            api_key="key",
+            endpoint="https://res.openai.azure.com",
+        )
+        assert comp.supports_stop_words() is True
+
+    def test_to_config_dict_includes_responses_fields(self, mock_openai_completion):
+        _mock_cls, _ = mock_openai_completion
+        comp = _create_azure_responses(
+            reasoning_effort="high",
+            instructions="Be concise",
+            store=True,
+            max_completion_tokens=500,
+        )
+        config = comp.to_config_dict()
+        assert config["api"] == "responses"
+        assert config["reasoning_effort"] == "high"
+        assert config["instructions"] == "Be concise"
+        assert config["store"] is True
+        assert config["max_completion_tokens"] == 500
+
+    def test_to_config_dict_omits_api_for_completions(self):
+        from crewai.llms.providers.azure.completion import AzureCompletion
+
+        comp = AzureCompletion(
+            model="gpt-4o",
+            api_key="key",
+            endpoint="https://res.openai.azure.com",
+        )
+        config = comp.to_config_dict()
+        assert "api" not in config
+
+
+# ---------------------------------------------------------------------------
+# LLM factory integration test
+# ---------------------------------------------------------------------------
+
+
+class TestAzureResponsesViaLLMFactory:
+    """Test that the LLM factory passes api='responses' through to AzureCompletion."""
+
+    @pytest.mark.usefixtures("azure_env")
+    def test_llm_factory_passes_api_kwarg(self):
+        """LLM(model='azure/gpt-4o', api='responses') should create AzureCompletion
+        with api='responses' and a delegate."""
+        with (
+            patch(
+                "crewai.llms.providers.openai.completion.OpenAI",
+            ),
+            patch(
+                "crewai.llms.providers.openai.completion.AsyncOpenAI",
+            ),
+        ):
+            from crewai.llm import LLM
+
+            llm = LLM(model="azure/gpt-4o", api="responses")
+
+            from crewai.llms.providers.azure.completion import AzureCompletion
+
+            assert isinstance(llm, AzureCompletion)
+            assert llm.api == "responses"
+            assert llm._responses_delegate is not None

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

@@ -0,0 +1,15 @@
+"""Async tests for Azure OpenAI Responses API support."""
+
+import pytest
+
+
+@pytest.mark.vcr()
+@pytest.mark.asyncio
+async def test_acall_delegates_to_responses():
+    from crewai.llm import LLM
+
+    llm = LLM(model="azure/gpt-5.2-chat", api="responses")
+    result = await llm.acall("Say hello in one sentence.")
+
+    assert isinstance(result, str)
+    assert len(result) > 0

lib/crewai/tests/mcp/test_tool_resolver_native.py

@@ -0,0 +1,99 @@
+"""Tests for MCPToolResolver native (non-AMP) resolution paths."""
+
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+from crewai.agent.core import Agent
+from crewai.mcp.config import MCPServerHTTP
+from crewai.mcp.tool_resolver import MCPToolResolver
+
+
+@pytest.fixture
+def agent():
+    return Agent(
+        role="Test Agent",
+        goal="Test goal",
+        backstory="Test backstory",
+    )
+
+
+@pytest.fixture
+def resolver(agent):
+    return MCPToolResolver(agent=agent, logger=agent._logger)
+
+
+@pytest.fixture
+def http_config():
+    return MCPServerHTTP(url="https://mcp.example.com/api")
+
+
+class TestResolveNativeEmptyTools:
+    @patch("crewai.mcp.tool_resolver.MCPClient")
+    def test_logs_warning_and_returns_empty_when_server_has_no_tools(
+        self, mock_client_class, resolver, http_config
+    ):
+        mock_client = AsyncMock()
+        mock_client.list_tools = AsyncMock(return_value=[])
+        mock_client.connected = False
+        mock_client.connect = AsyncMock()
+        mock_client.disconnect = AsyncMock()
+        mock_client_class.return_value = mock_client
+
+        mock_log = MagicMock()
+        resolver._logger = MagicMock(log=mock_log)
+
+        tools, clients = resolver._resolve_native(http_config)
+
+        assert tools == []
+        assert clients == []
+        warning_calls = [
+            call for call in mock_log.call_args_list if call.args[0] == "warning"
+        ]
+        assert any(
+            "No tools discovered from MCP server" in call.args[1]
+            for call in warning_calls
+        )
+
+    @patch("crewai.mcp.tool_resolver.MCPClient")
+    def test_logs_warning_when_tool_filter_removes_all_tools(
+        self, mock_client_class, resolver
+    ):
+        mock_client = AsyncMock()
+        mock_client.list_tools = AsyncMock(
+            return_value=[{"name": "search", "description": "Search"}]
+        )
+        mock_client.connected = False
+        mock_client.connect = AsyncMock()
+        mock_client.disconnect = AsyncMock()
+        mock_client_class.return_value = mock_client
+
+        config = MCPServerHTTP(
+            url="https://mcp.example.com/api",
+            tool_filter=lambda _tool: False,
+        )
+
+        mock_log = MagicMock()
+        resolver._logger = MagicMock(log=mock_log)
+
+        tools, clients = resolver._resolve_native(config)
+
+        assert tools == []
+        assert clients == []
+        warning_calls = [
+            call for call in mock_log.call_args_list if call.args[0] == "warning"
+        ]
+        assert any(
+            "No tools discovered from MCP server" in call.args[1]
+            for call in warning_calls
+        )
+
+
+class TestResolveNativeRuntimeError:
+    @patch("crewai.mcp.tool_resolver.asyncio.run")
+    def test_unmatched_runtime_error_is_wrapped_not_swallowed(
+        self, mock_asyncio_run, resolver, http_config
+    ):
+        mock_asyncio_run.side_effect = RuntimeError("some other failure")
+
+        with pytest.raises(RuntimeError, match="Failed to get native MCP tools"):
+            resolver._resolve_native(http_config)

lib/crewai/tests/test_flow_persistence.py

@@ -3,6 +3,7 @@
 import os
 from typing import Dict, List
 
+import pytest
 from crewai.flow.flow import Flow, FlowState, listen, start
 from crewai.flow.persistence import persist
 from crewai.flow.persistence.sqlite import SQLiteFlowPersistence
@@ -248,3 +249,69 @@ def test_persistence_with_base_model(tmp_path):
     assert message.type == "text"
     assert message.content == "Hello, World!"
     assert isinstance(flow.state._unwrap(), State)
+
+
+def test_persist_custom_key_with_pydantic_state(tmp_path):
+    """`@persist(key=...)` uses the named attribute on a Pydantic state."""
+    db_path = os.path.join(tmp_path, "test_flows.db")
+    persistence = SQLiteFlowPersistence(db_path)
+
+    class KeyedState(FlowState):
+        conversation_id: str = "conv-42"
+        message: str = ""
+
+    class KeyedFlow(Flow[KeyedState]):
+        @start()
+        @persist(persistence, key="conversation_id")
+        def init_step(self):
+            self.state.message = "hello"
+
+    flow = KeyedFlow(persistence=persistence)
+    flow.kickoff()
+
+    saved_state = persistence.load_state("conv-42")
+    assert saved_state is not None
+    assert saved_state["message"] == "hello"
+    # The default `state.id` lookup must NOT have been used as the key.
+    assert persistence.load_state(flow.state.id) is None
+
+
+def test_persist_custom_key_with_dict_state(tmp_path):
+    """`@persist(key=...)` uses the named key on a dict state."""
+    db_path = os.path.join(tmp_path, "test_flows.db")
+    persistence = SQLiteFlowPersistence(db_path)
+
+    class DictKeyedFlow(Flow[Dict[str, str]]):
+        initial_state = dict()
+
+        @start()
+        @persist(persistence, key="conversation_id")
+        def init_step(self):
+            self.state["conversation_id"] = "conv-dict-7"
+            self.state["message"] = "hi from dict"
+
+    flow = DictKeyedFlow(persistence=persistence)
+    flow.kickoff()
+
+    saved_state = persistence.load_state("conv-dict-7")
+    assert saved_state is not None
+    assert saved_state["message"] == "hi from dict"
+
+
+def test_persist_custom_key_missing_raises(tmp_path):
+    """A missing/falsy custom key must raise a clear ValueError."""
+    db_path = os.path.join(tmp_path, "test_flows.db")
+    persistence = SQLiteFlowPersistence(db_path)
+
+    class MissingKeyFlow(Flow[Dict[str, str]]):
+        initial_state = dict()
+
+        @start()
+        @persist(persistence, key="conversation_id")
+        def init_step(self):
+            # Intentionally do NOT set "conversation_id" on state.
+            self.state["message"] = "no key here"
+
+    flow = MissingKeyFlow(persistence=persistence)
+    with pytest.raises(ValueError, match="conversation_id"):
+        flow.kickoff()

lib/crewai/tests/tracing/test_tracing_message_suppression.py

@@ -0,0 +1,259 @@
+"""Tests for tracing disabled message suppression (issue #5665).
+
+Verifies that:
+- Users who explicitly declined tracing are NOT nagged with the message.
+- The CREWAI_SUPPRESS_TRACING_MESSAGES env var suppresses the message.
+- The message is shown only when tracing is disabled and user hasn't declined.
+"""
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from crewai.events.listeners.tracing.utils import (
+    set_suppress_tracing_messages,
+    should_suppress_tracing_messages,
+)
+
+
+class TestShouldSuppressTracingMessages:
+    """Tests for the should_suppress_tracing_messages utility function."""
+
+    def test_suppress_false_by_default(self):
+        """By default, messages should NOT be suppressed."""
+        token = set_suppress_tracing_messages(False)
+        try:
+            assert should_suppress_tracing_messages() is False
+        finally:
+            from crewai.events.listeners.tracing.utils import (
+                _suppress_tracing_messages,
+            )
+            _suppress_tracing_messages.reset(token)
+
+    def test_suppress_via_context_var(self):
+        """Setting the context var should suppress messages."""
+        token = set_suppress_tracing_messages(True)
+        try:
+            assert should_suppress_tracing_messages() is True
+        finally:
+            from crewai.events.listeners.tracing.utils import (
+                _suppress_tracing_messages,
+            )
+            _suppress_tracing_messages.reset(token)
+
+    @pytest.mark.parametrize("env_value", ["true", "True", "TRUE", "1", "yes", "YES"])
+    def test_suppress_via_env_var(self, env_value, monkeypatch):
+        """CREWAI_SUPPRESS_TRACING_MESSAGES env var should suppress messages."""
+        token = set_suppress_tracing_messages(False)
+        try:
+            monkeypatch.setenv("CREWAI_SUPPRESS_TRACING_MESSAGES", env_value)
+            assert should_suppress_tracing_messages() is True
+        finally:
+            from crewai.events.listeners.tracing.utils import (
+                _suppress_tracing_messages,
+            )
+            _suppress_tracing_messages.reset(token)
+
+    @pytest.mark.parametrize("env_value", ["false", "False", "0", "no", ""])
+    def test_no_suppress_with_falsy_env_var(self, env_value, monkeypatch):
+        """Falsy values for the env var should NOT suppress messages."""
+        token = set_suppress_tracing_messages(False)
+        try:
+            monkeypatch.setenv("CREWAI_SUPPRESS_TRACING_MESSAGES", env_value)
+            assert should_suppress_tracing_messages() is False
+        finally:
+            from crewai.events.listeners.tracing.utils import (
+                _suppress_tracing_messages,
+            )
+            _suppress_tracing_messages.reset(token)
+
+    def test_context_var_takes_precedence_over_env(self, monkeypatch):
+        """Context var set to True should suppress even if env var is false."""
+        token = set_suppress_tracing_messages(True)
+        try:
+            monkeypatch.setenv("CREWAI_SUPPRESS_TRACING_MESSAGES", "false")
+            assert should_suppress_tracing_messages() is True
+        finally:
+            from crewai.events.listeners.tracing.utils import (
+                _suppress_tracing_messages,
+            )
+            _suppress_tracing_messages.reset(token)
+
+
+class TestShowTracingDisabledMessage:
+    """Tests that _show_tracing_disabled_message does not nag declined users."""
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={"first_execution_done": True, "trace_consent": False},
+    )
+    def test_crew_no_message_when_user_declined(self, mock_load):
+        """Crew._show_tracing_disabled_message should not print when user declined."""
+        from crewai.crew import Crew
+
+        with patch("crewai.crew.Console") as MockConsole:
+            Crew._show_tracing_disabled_message()
+            MockConsole.return_value.print.assert_not_called()
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={"first_execution_done": True, "trace_consent": False},
+    )
+    def test_flow_no_message_when_user_declined(self, mock_load):
+        """Flow._show_tracing_disabled_message should not print when user declined."""
+        from crewai.flow.flow import Flow
+
+        with patch("crewai.flow.flow.Console") as MockConsole:
+            Flow._show_tracing_disabled_message()
+            MockConsole.return_value.print.assert_not_called()
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={"first_execution_done": True, "trace_consent": False},
+    )
+    def test_trace_listener_no_message_when_user_declined(self, mock_load):
+        """TraceCollectionListener._show_tracing_disabled_message should not print when user declined."""
+        from crewai.events.listeners.tracing.trace_listener import (
+            TraceCollectionListener,
+        )
+
+        listener = TraceCollectionListener.__new__(TraceCollectionListener)
+        with patch("rich.console.Console") as MockConsole:
+            listener._show_tracing_disabled_message()
+            MockConsole.return_value.print.assert_not_called()
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={},
+    )
+    def test_crew_shows_message_when_user_has_not_decided(self, mock_load):
+        """Crew._show_tracing_disabled_message should print when user hasn't decided yet."""
+        from crewai.crew import Crew
+
+        with patch("crewai.crew.Console") as MockConsole:
+            mock_console_instance = MockConsole.return_value
+            Crew._show_tracing_disabled_message()
+            mock_console_instance.print.assert_called_once()
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={},
+    )
+    def test_crew_no_message_when_suppress_env_set(self, mock_load, monkeypatch):
+        """Crew._show_tracing_disabled_message should not print when env var suppresses."""
+        from crewai.crew import Crew
+
+        monkeypatch.setenv("CREWAI_SUPPRESS_TRACING_MESSAGES", "true")
+        with patch("crewai.crew.Console") as MockConsole:
+            Crew._show_tracing_disabled_message()
+            MockConsole.return_value.print.assert_not_called()
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={},
+    )
+    def test_flow_no_message_when_suppress_env_set(self, mock_load, monkeypatch):
+        """Flow._show_tracing_disabled_message should not print when env var suppresses."""
+        from crewai.flow.flow import Flow
+
+        monkeypatch.setenv("CREWAI_SUPPRESS_TRACING_MESSAGES", "true")
+        with patch("crewai.flow.flow.Console") as MockConsole:
+            Flow._show_tracing_disabled_message()
+            MockConsole.return_value.print.assert_not_called()
+
+
+class TestConsoleFormatterTracingMessage:
+    """Tests for console_formatter._show_tracing_disabled_message_if_needed."""
+
+    def _make_formatter(self):
+        from crewai.events.utils.console_formatter import ConsoleFormatter
+
+        formatter = ConsoleFormatter.__new__(ConsoleFormatter)
+        formatter.console = MagicMock()
+        formatter.verbose = True
+        return formatter
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={"first_execution_done": True, "trace_consent": False},
+    )
+    def test_no_message_when_user_declined(self, mock_load):
+        """Console formatter should not show the message when user declined tracing."""
+        formatter = self._make_formatter()
+
+        with patch(
+            "crewai.events.listeners.tracing.trace_listener.TraceCollectionListener"
+        ) as mock_listener_cls:
+            mock_listener_cls._instance = None
+            formatter._show_tracing_disabled_message_if_needed()
+
+        formatter.console.print.assert_not_called()
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={},
+    )
+    def test_no_message_when_suppress_env_set(self, mock_load, monkeypatch):
+        """Console formatter should not show the message when env var is set."""
+        monkeypatch.setenv("CREWAI_SUPPRESS_TRACING_MESSAGES", "true")
+        formatter = self._make_formatter()
+
+        formatter._show_tracing_disabled_message_if_needed()
+
+        formatter.console.print.assert_not_called()
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={},
+    )
+    @patch(
+        "crewai.events.listeners.tracing.utils.is_tracing_enabled_in_context",
+        return_value=False,
+    )
+    def test_message_shown_when_tracing_disabled_and_not_declined(
+        self, mock_tracing_ctx, mock_load
+    ):
+        """Console formatter should show the message when tracing disabled and user hasn't declined."""
+        from crewai.events.listeners.tracing.trace_listener import (
+            TraceCollectionListener,
+        )
+
+        formatter = self._make_formatter()
+
+        mock_instance = MagicMock()
+        mock_instance.first_time_handler.is_first_time = False
+        original_instance = TraceCollectionListener._instance
+
+        try:
+            TraceCollectionListener._instance = mock_instance  # type: ignore[misc]
+            formatter._show_tracing_disabled_message_if_needed()
+            formatter.console.print.assert_called_once()
+        finally:
+            TraceCollectionListener._instance = original_instance  # type: ignore[misc]
+
+    @patch(
+        "crewai.events.listeners.tracing.utils._load_user_data",
+        return_value={},
+    )
+    @patch(
+        "crewai.events.listeners.tracing.utils.is_tracing_enabled_in_context",
+        return_value=True,
+    )
+    def test_no_message_when_tracing_enabled(self, mock_tracing_ctx, mock_load):
+        """Console formatter should not show the message when tracing is enabled."""
+        from crewai.events.listeners.tracing.trace_listener import (
+            TraceCollectionListener,
+        )
+
+        formatter = self._make_formatter()
+
+        mock_instance = MagicMock()
+        mock_instance.first_time_handler.is_first_time = False
+        original_instance = TraceCollectionListener._instance
+
+        try:
+            TraceCollectionListener._instance = mock_instance  # type: ignore[misc]
+            formatter._show_tracing_disabled_message_if_needed()
+            formatter.console.print.assert_not_called()
+        finally:
+            TraceCollectionListener._instance = original_instance  # type: ignore[misc]

lib/crewai/tests/utilities/test_converter.py

@@ -940,6 +940,8 @@ def test_internal_instructor_real_unsupported_provider() -> None:
     mock_llm.is_litellm = False
     mock_llm.model = "unsupported-model"
     mock_llm.provider = "unsupported"
+    mock_llm.base_url = None
+    mock_llm.api_key = None
 
     # This should raise a ConfigurationError from the real instructor library
     with pytest.raises(Exception) as exc_info:
@@ -952,3 +954,45 @@ def test_internal_instructor_real_unsupported_provider() -> None:
 
     # Verify it's a configuration error about unsupported provider
     assert "Unsupported provider" in str(exc_info.value) or "unsupported" in str(exc_info.value).lower()
+
+
+def test_internal_instructor_forwards_base_url_and_api_key() -> None:
+    """base_url and api_key on the LLM must flow into instructor.from_provider."""
+    from crewai.utilities.internal_instructor import InternalInstructor
+
+    mock_llm = Mock()
+    mock_llm.is_litellm = False
+    mock_llm.model = "gpt-4o"
+    mock_llm.provider = "openai"
+    mock_llm.base_url = "https://custom.example.com/v1"
+    mock_llm.api_key = "sk-custom"
+
+    with patch("instructor.from_provider") as mock_from_provider:
+        mock_from_provider.return_value = Mock()
+
+        InternalInstructor(content="x", model=SimpleModel, llm=mock_llm)
+
+        mock_from_provider.assert_called_once_with(
+            "openai/gpt-4o",
+            base_url="https://custom.example.com/v1",
+            api_key="sk-custom",
+        )
+
+
+def test_internal_instructor_omits_unset_base_url_and_api_key() -> None:
+    """When base_url/api_key are None, they must not be passed to from_provider."""
+    from crewai.utilities.internal_instructor import InternalInstructor
+
+    mock_llm = Mock()
+    mock_llm.is_litellm = False
+    mock_llm.model = "gpt-4o"
+    mock_llm.provider = "openai"
+    mock_llm.base_url = None
+    mock_llm.api_key = None
+
+    with patch("instructor.from_provider") as mock_from_provider:
+        mock_from_provider.return_value = Mock()
+
+        InternalInstructor(content="x", model=SimpleModel, llm=mock_llm)
+
+        mock_from_provider.assert_called_once_with("openai/gpt-4o")