feat: add a2a liteagent, auth, transport negotiation, and file support

* feat: add server-side auth schemes and protocol extensions

- add server auth scheme base class and implementations (api key, bearer token, basic/digest auth, mtls)
- add server-side extension system for a2a protocol extensions
- add extensions middleware for x-a2a-extensions header management
- add extension validation and registry utilities
- enhance auth utilities with server-side support
- add async intercept method to match client call interceptor protocol
- fix type_checking import to resolve mypy errors with a2aconfig

* feat: add transport negotiation and content type handling

- add transport negotiation logic with fallback support
- add content type parser and encoder utilities
- add transport configuration models (client and server)
- add transport types and enums
- enhance config with transport settings
- add negotiation events for transport and content type

* feat: add a2a delegation support to LiteAgent

* feat: add file input support to a2a delegation and tasks

Introduces handling of file inputs in A2A delegation flows by converting file dictionaries to protocol-compatible parts and propagating them through delegation and task execution functions. Updates include utility functions for file conversion, changes to message construction, and passing input_files through relevant APIs.

* feat: liteagent a2a delegation support to kickoff methods

lib/crewai/src/crewai/a2a/auth/__init__.py

@@ -1,20 +1,36 @@
 """A2A authentication schemas."""
 
-from crewai.a2a.auth.schemas import (
+from crewai.a2a.auth.client_schemes import (
     APIKeyAuth,
+    AuthScheme,
     BearerTokenAuth,
+    ClientAuthScheme,
     HTTPBasicAuth,
     HTTPDigestAuth,
     OAuth2AuthorizationCode,
     OAuth2ClientCredentials,
+    TLSConfig,
+)
+from crewai.a2a.auth.server_schemes import (
+    AuthenticatedUser,
+    OIDCAuth,
+    ServerAuthScheme,
+    SimpleTokenAuth,
 )
 
 
 __all__ = [
     "APIKeyAuth",
+    "AuthScheme",
+    "AuthenticatedUser",
     "BearerTokenAuth",
+    "ClientAuthScheme",
     "HTTPBasicAuth",
     "HTTPDigestAuth",
     "OAuth2AuthorizationCode",
     "OAuth2ClientCredentials",
+    "OIDCAuth",
+    "ServerAuthScheme",
+    "SimpleTokenAuth",
+    "TLSConfig",
 ]

lib/crewai/src/crewai/a2a/auth/client_schemes.py

@@ -0,0 +1,550 @@
+"""Authentication schemes for A2A protocol clients.
+
+Supported authentication methods:
+- Bearer tokens
+- OAuth2 (Client Credentials, Authorization Code)
+- API Keys (header, query, cookie)
+- HTTP Basic authentication
+- HTTP Digest authentication
+- mTLS (mutual TLS) client certificate authentication
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+import asyncio
+import base64
+from collections.abc import Awaitable, Callable, MutableMapping
+from pathlib import Path
+import ssl
+import time
+from typing import TYPE_CHECKING, ClassVar, Literal
+import urllib.parse
+
+import httpx
+from httpx import DigestAuth
+from pydantic import BaseModel, ConfigDict, Field, FilePath, PrivateAttr
+from typing_extensions import deprecated
+
+
+if TYPE_CHECKING:
+    import grpc  # type: ignore[import-untyped]
+
+
+class TLSConfig(BaseModel):
+    """TLS/mTLS configuration for secure client connections.
+
+    Supports mutual TLS (mTLS) where the client presents a certificate to the server,
+    and standard TLS with custom CA verification.
+
+    Attributes:
+        client_cert_path: Path to client certificate file (PEM format) for mTLS.
+        client_key_path: Path to client private key file (PEM format) for mTLS.
+        ca_cert_path: Path to CA certificate bundle for server verification.
+        verify: Whether to verify server certificates. Set False only for development.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    client_cert_path: FilePath | None = Field(
+        default=None,
+        description="Path to client certificate file (PEM format) for mTLS",
+    )
+    client_key_path: FilePath | None = Field(
+        default=None,
+        description="Path to client private key file (PEM format) for mTLS",
+    )
+    ca_cert_path: FilePath | None = Field(
+        default=None,
+        description="Path to CA certificate bundle for server verification",
+    )
+    verify: bool = Field(
+        default=True,
+        description="Whether to verify server certificates. Set False only for development.",
+    )
+
+    def get_httpx_ssl_context(self) -> ssl.SSLContext | bool | str:
+        """Build SSL context for httpx client.
+
+        Returns:
+            SSL context if certificates configured, True for default verification,
+            False if verification disabled, or path to CA bundle.
+        """
+        if not self.verify:
+            return False
+
+        if self.client_cert_path and self.client_key_path:
+            context = ssl.create_default_context()
+
+            if self.ca_cert_path:
+                context.load_verify_locations(cafile=str(self.ca_cert_path))
+
+            context.load_cert_chain(
+                certfile=str(self.client_cert_path),
+                keyfile=str(self.client_key_path),
+            )
+            return context
+
+        if self.ca_cert_path:
+            return str(self.ca_cert_path)
+
+        return True
+
+    def get_grpc_credentials(self) -> grpc.ChannelCredentials | None:  # type: ignore[no-any-unimported]
+        """Build gRPC channel credentials for secure connections.
+
+        Returns:
+            gRPC SSL credentials if certificates configured, None otherwise.
+        """
+        try:
+            import grpc
+        except ImportError:
+            return None
+
+        if not self.verify and not self.client_cert_path:
+            return None
+
+        root_certs: bytes | None = None
+        private_key: bytes | None = None
+        certificate_chain: bytes | None = None
+
+        if self.ca_cert_path:
+            root_certs = Path(self.ca_cert_path).read_bytes()
+
+        if self.client_cert_path and self.client_key_path:
+            private_key = Path(self.client_key_path).read_bytes()
+            certificate_chain = Path(self.client_cert_path).read_bytes()
+
+        return grpc.ssl_channel_credentials(
+            root_certificates=root_certs,
+            private_key=private_key,
+            certificate_chain=certificate_chain,
+        )
+
+
+class ClientAuthScheme(ABC, BaseModel):
+    """Base class for client-side authentication schemes.
+
+    Client auth schemes apply credentials to outgoing requests.
+
+    Attributes:
+        tls: Optional TLS/mTLS configuration for secure connections.
+    """
+
+    tls: TLSConfig | None = Field(
+        default=None,
+        description="TLS/mTLS configuration for secure connections",
+    )
+
+    @abstractmethod
+    async def apply_auth(
+        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
+    ) -> MutableMapping[str, str]:
+        """Apply authentication to request headers.
+
+        Args:
+            client: HTTP client for making auth requests.
+            headers: Current request headers.
+
+        Returns:
+            Updated headers with authentication applied.
+        """
+        ...
+
+
+@deprecated("Use ClientAuthScheme instead", category=FutureWarning)
+class AuthScheme(ClientAuthScheme):
+    """Deprecated: Use ClientAuthScheme instead."""
+
+
+class BearerTokenAuth(ClientAuthScheme):
+    """Bearer token authentication (Authorization: Bearer <token>).
+
+    Attributes:
+        token: Bearer token for authentication.
+    """
+
+    token: str = Field(description="Bearer token")
+
+    async def apply_auth(
+        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
+    ) -> MutableMapping[str, str]:
+        """Apply Bearer token to Authorization header.
+
+        Args:
+            client: HTTP client for making auth requests.
+            headers: Current request headers.
+
+        Returns:
+            Updated headers with Bearer token in Authorization header.
+        """
+        headers["Authorization"] = f"Bearer {self.token}"
+        return headers
+
+
+class HTTPBasicAuth(ClientAuthScheme):
+    """HTTP Basic authentication.
+
+    Attributes:
+        username: Username for Basic authentication.
+        password: Password for Basic authentication.
+    """
+
+    username: str = Field(description="Username")
+    password: str = Field(description="Password")
+
+    async def apply_auth(
+        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
+    ) -> MutableMapping[str, str]:
+        """Apply HTTP Basic authentication.
+
+        Args:
+            client: HTTP client for making auth requests.
+            headers: Current request headers.
+
+        Returns:
+            Updated headers with Basic auth in Authorization header.
+        """
+        credentials = f"{self.username}:{self.password}"
+        encoded = base64.b64encode(credentials.encode()).decode()
+        headers["Authorization"] = f"Basic {encoded}"
+        return headers
+
+
+class HTTPDigestAuth(ClientAuthScheme):
+    """HTTP Digest authentication.
+
+    Note: Uses httpx-auth library for digest implementation.
+
+    Attributes:
+        username: Username for Digest authentication.
+        password: Password for Digest authentication.
+    """
+
+    username: str = Field(description="Username")
+    password: str = Field(description="Password")
+
+    _configured_client_id: int | None = PrivateAttr(default=None)
+
+    async def apply_auth(
+        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
+    ) -> MutableMapping[str, str]:
+        """Digest auth is handled by httpx auth flow, not headers.
+
+        Args:
+            client: HTTP client for making auth requests.
+            headers: Current request headers.
+
+        Returns:
+            Unchanged headers (Digest auth handled by httpx auth flow).
+        """
+        return headers
+
+    def configure_client(self, client: httpx.AsyncClient) -> None:
+        """Configure client with Digest auth.
+
+        Idempotent: Only configures the client once. Subsequent calls on the same
+        client instance are no-ops to prevent overwriting auth configuration.
+
+        Args:
+            client: HTTP client to configure with Digest authentication.
+        """
+        client_id = id(client)
+        if self._configured_client_id == client_id:
+            return
+
+        client.auth = DigestAuth(self.username, self.password)
+        self._configured_client_id = client_id
+
+
+class APIKeyAuth(ClientAuthScheme):
+    """API Key authentication (header, query, or cookie).
+
+    Attributes:
+        api_key: API key value for authentication.
+        location: Where to send the API key (header, query, or cookie).
+        name: Parameter name for the API key (default: X-API-Key).
+    """
+
+    api_key: str = Field(description="API key value")
+    location: Literal["header", "query", "cookie"] = Field(
+        default="header", description="Where to send the API key"
+    )
+    name: str = Field(default="X-API-Key", description="Parameter name for the API key")
+
+    _configured_client_ids: set[int] = PrivateAttr(default_factory=set)
+
+    async def apply_auth(
+        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
+    ) -> MutableMapping[str, str]:
+        """Apply API key authentication.
+
+        Args:
+            client: HTTP client for making auth requests.
+            headers: Current request headers.
+
+        Returns:
+            Updated headers with API key (for header/cookie locations).
+        """
+        if self.location == "header":
+            headers[self.name] = self.api_key
+        elif self.location == "cookie":
+            headers["Cookie"] = f"{self.name}={self.api_key}"
+        return headers
+
+    def configure_client(self, client: httpx.AsyncClient) -> None:
+        """Configure client for query param API keys.
+
+        Idempotent: Only adds the request hook once per client instance.
+        Subsequent calls on the same client are no-ops to prevent hook accumulation.
+
+        Args:
+            client: HTTP client to configure with query param API key hook.
+        """
+        if self.location == "query":
+            client_id = id(client)
+            if client_id in self._configured_client_ids:
+                return
+
+            async def _add_api_key_param(request: httpx.Request) -> None:
+                url = httpx.URL(request.url)
+                request.url = url.copy_add_param(self.name, self.api_key)
+
+            client.event_hooks["request"].append(_add_api_key_param)
+            self._configured_client_ids.add(client_id)
+
+
+class OAuth2ClientCredentials(ClientAuthScheme):
+    """OAuth2 Client Credentials flow authentication.
+
+    Thread-safe implementation with asyncio.Lock to prevent concurrent token fetches
+    when multiple requests share the same auth instance.
+
+    Attributes:
+        token_url: OAuth2 token endpoint URL.
+        client_id: OAuth2 client identifier.
+        client_secret: OAuth2 client secret.
+        scopes: List of required OAuth2 scopes.
+    """
+
+    token_url: str = Field(description="OAuth2 token endpoint")
+    client_id: str = Field(description="OAuth2 client ID")
+    client_secret: str = Field(description="OAuth2 client secret")
+    scopes: list[str] = Field(
+        default_factory=list, description="Required OAuth2 scopes"
+    )
+
+    _access_token: str | None = PrivateAttr(default=None)
+    _token_expires_at: float | None = PrivateAttr(default=None)
+    _lock: asyncio.Lock = PrivateAttr(default_factory=asyncio.Lock)
+
+    async def apply_auth(
+        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
+    ) -> MutableMapping[str, str]:
+        """Apply OAuth2 access token to Authorization header.
+
+        Uses asyncio.Lock to ensure only one coroutine fetches tokens at a time,
+        preventing race conditions when multiple concurrent requests use the same
+        auth instance.
+
+        Args:
+            client: HTTP client for making token requests.
+            headers: Current request headers.
+
+        Returns:
+            Updated headers with OAuth2 access token in Authorization header.
+        """
+        if (
+            self._access_token is None
+            or self._token_expires_at is None
+            or time.time() >= self._token_expires_at
+        ):
+            async with self._lock:
+                if (
+                    self._access_token is None
+                    or self._token_expires_at is None
+                    or time.time() >= self._token_expires_at
+                ):
+                    await self._fetch_token(client)
+
+        if self._access_token:
+            headers["Authorization"] = f"Bearer {self._access_token}"
+
+        return headers
+
+    async def _fetch_token(self, client: httpx.AsyncClient) -> None:
+        """Fetch OAuth2 access token using client credentials flow.
+
+        Args:
+            client: HTTP client for making token request.
+
+        Raises:
+            httpx.HTTPStatusError: If token request fails.
+        """
+        data = {
+            "grant_type": "client_credentials",
+            "client_id": self.client_id,
+            "client_secret": self.client_secret,
+        }
+
+        if self.scopes:
+            data["scope"] = " ".join(self.scopes)
+
+        response = await client.post(self.token_url, data=data)
+        response.raise_for_status()
+
+        token_data = response.json()
+        self._access_token = token_data["access_token"]
+        expires_in = token_data.get("expires_in", 3600)
+        self._token_expires_at = time.time() + expires_in - 60
+
+
+class OAuth2AuthorizationCode(ClientAuthScheme):
+    """OAuth2 Authorization Code flow authentication.
+
+    Thread-safe implementation with asyncio.Lock to prevent concurrent token operations.
+
+    Note: Requires interactive authorization.
+
+    Attributes:
+        authorization_url: OAuth2 authorization endpoint URL.
+        token_url: OAuth2 token endpoint URL.
+        client_id: OAuth2 client identifier.
+        client_secret: OAuth2 client secret.
+        redirect_uri: OAuth2 redirect URI for callback.
+        scopes: List of required OAuth2 scopes.
+    """
+
+    authorization_url: str = Field(description="OAuth2 authorization endpoint")
+    token_url: str = Field(description="OAuth2 token endpoint")
+    client_id: str = Field(description="OAuth2 client ID")
+    client_secret: str = Field(description="OAuth2 client secret")
+    redirect_uri: str = Field(description="OAuth2 redirect URI")
+    scopes: list[str] = Field(
+        default_factory=list, description="Required OAuth2 scopes"
+    )
+
+    _access_token: str | None = PrivateAttr(default=None)
+    _refresh_token: str | None = PrivateAttr(default=None)
+    _token_expires_at: float | None = PrivateAttr(default=None)
+    _authorization_callback: Callable[[str], Awaitable[str]] | None = PrivateAttr(
+        default=None
+    )
+    _lock: asyncio.Lock = PrivateAttr(default_factory=asyncio.Lock)
+
+    def set_authorization_callback(
+        self, callback: Callable[[str], Awaitable[str]] | None
+    ) -> None:
+        """Set callback to handle authorization URL.
+
+        Args:
+            callback: Async function that receives authorization URL and returns auth code.
+        """
+        self._authorization_callback = callback
+
+    async def apply_auth(
+        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
+    ) -> MutableMapping[str, str]:
+        """Apply OAuth2 access token to Authorization header.
+
+        Uses asyncio.Lock to ensure only one coroutine handles token operations
+        (initial fetch or refresh) at a time.
+
+        Args:
+            client: HTTP client for making token requests.
+            headers: Current request headers.
+
+        Returns:
+            Updated headers with OAuth2 access token in Authorization header.
+
+        Raises:
+            ValueError: If authorization callback is not set.
+        """
+        if self._access_token is None:
+            if self._authorization_callback is None:
+                msg = "Authorization callback not set. Use set_authorization_callback()"
+                raise ValueError(msg)
+            async with self._lock:
+                if self._access_token is None:
+                    await self._fetch_initial_token(client)
+        elif self._token_expires_at and time.time() >= self._token_expires_at:
+            async with self._lock:
+                if self._token_expires_at and time.time() >= self._token_expires_at:
+                    await self._refresh_access_token(client)
+
+        if self._access_token:
+            headers["Authorization"] = f"Bearer {self._access_token}"
+
+        return headers
+
+    async def _fetch_initial_token(self, client: httpx.AsyncClient) -> None:
+        """Fetch initial access token using authorization code flow.
+
+        Args:
+            client: HTTP client for making token request.
+
+        Raises:
+            ValueError: If authorization callback is not set.
+            httpx.HTTPStatusError: If token request fails.
+        """
+        params = {
+            "response_type": "code",
+            "client_id": self.client_id,
+            "redirect_uri": self.redirect_uri,
+            "scope": " ".join(self.scopes),
+        }
+        auth_url = f"{self.authorization_url}?{urllib.parse.urlencode(params)}"
+
+        if self._authorization_callback is None:
+            msg = "Authorization callback not set"
+            raise ValueError(msg)
+        auth_code = await self._authorization_callback(auth_url)
+
+        data = {
+            "grant_type": "authorization_code",
+            "code": auth_code,
+            "client_id": self.client_id,
+            "client_secret": self.client_secret,
+            "redirect_uri": self.redirect_uri,
+        }
+
+        response = await client.post(self.token_url, data=data)
+        response.raise_for_status()
+
+        token_data = response.json()
+        self._access_token = token_data["access_token"]
+        self._refresh_token = token_data.get("refresh_token")
+
+        expires_in = token_data.get("expires_in", 3600)
+        self._token_expires_at = time.time() + expires_in - 60
+
+    async def _refresh_access_token(self, client: httpx.AsyncClient) -> None:
+        """Refresh the access token using refresh token.
+
+        Args:
+            client: HTTP client for making token request.
+
+        Raises:
+            httpx.HTTPStatusError: If token refresh request fails.
+        """
+        if not self._refresh_token:
+            await self._fetch_initial_token(client)
+            return
+
+        data = {
+            "grant_type": "refresh_token",
+            "refresh_token": self._refresh_token,
+            "client_id": self.client_id,
+            "client_secret": self.client_secret,
+        }
+
+        response = await client.post(self.token_url, data=data)
+        response.raise_for_status()
+
+        token_data = response.json()
+        self._access_token = token_data["access_token"]
+        if "refresh_token" in token_data:
+            self._refresh_token = token_data["refresh_token"]
+
+        expires_in = token_data.get("expires_in", 3600)
+        self._token_expires_at = time.time() + expires_in - 60

lib/crewai/src/crewai/a2a/auth/schemas.py

@@ -1,392 +1,71 @@
-"""Authentication schemes for A2A protocol agents.
+"""Deprecated: Authentication schemes for A2A protocol agents.
 
-Supported authentication methods:
-- Bearer tokens
-- OAuth2 (Client Credentials, Authorization Code)
-- API Keys (header, query, cookie)
-- HTTP Basic authentication
-- HTTP Digest authentication
+This module is deprecated. Import from crewai.a2a.auth instead:
+- crewai.a2a.auth.ClientAuthScheme (replaces AuthScheme)
+- crewai.a2a.auth.BearerTokenAuth
+- crewai.a2a.auth.HTTPBasicAuth
+- crewai.a2a.auth.HTTPDigestAuth
+- crewai.a2a.auth.APIKeyAuth
+- crewai.a2a.auth.OAuth2ClientCredentials
+- crewai.a2a.auth.OAuth2AuthorizationCode
 """
 
 from __future__ import annotations
 
-from abc import ABC, abstractmethod
-import base64
-from collections.abc import Awaitable, Callable, MutableMapping
-import time
-from typing import Literal
-import urllib.parse
+from typing_extensions import deprecated
 
-import httpx
-from httpx import DigestAuth
-from pydantic import BaseModel, Field, PrivateAttr
+from crewai.a2a.auth.client_schemes import (
+    APIKeyAuth as _APIKeyAuth,
+    BearerTokenAuth as _BearerTokenAuth,
+    ClientAuthScheme as _ClientAuthScheme,
+    HTTPBasicAuth as _HTTPBasicAuth,
+    HTTPDigestAuth as _HTTPDigestAuth,
+    OAuth2AuthorizationCode as _OAuth2AuthorizationCode,
+    OAuth2ClientCredentials as _OAuth2ClientCredentials,
+)
 
 
-class AuthScheme(ABC, BaseModel):
-    """Base class for authentication schemes."""
+@deprecated("Use ClientAuthScheme from crewai.a2a.auth instead", category=FutureWarning)
+class AuthScheme(_ClientAuthScheme):
+    """Deprecated: Use ClientAuthScheme from crewai.a2a.auth instead."""
 
-    @abstractmethod
-    async def apply_auth(
-        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
-    ) -> MutableMapping[str, str]:
-        """Apply authentication to request headers.
 
-        Args:
-            client: HTTP client for making auth requests.
-            headers: Current request headers.
+@deprecated("Import from crewai.a2a.auth instead", category=FutureWarning)
+class BearerTokenAuth(_BearerTokenAuth):
+    """Deprecated: Import from crewai.a2a.auth instead."""
 
-        Returns:
-            Updated headers with authentication applied.
-        """
-        ...
 
+@deprecated("Import from crewai.a2a.auth instead", category=FutureWarning)
+class HTTPBasicAuth(_HTTPBasicAuth):
+    """Deprecated: Import from crewai.a2a.auth instead."""
 
-class BearerTokenAuth(AuthScheme):
-    """Bearer token authentication (Authorization: Bearer <token>).
 
-    Attributes:
-        token: Bearer token for authentication.
-    """
+@deprecated("Import from crewai.a2a.auth instead", category=FutureWarning)
+class HTTPDigestAuth(_HTTPDigestAuth):
+    """Deprecated: Import from crewai.a2a.auth instead."""
 
-    token: str = Field(description="Bearer token")
 
-    async def apply_auth(
-        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
-    ) -> MutableMapping[str, str]:
-        """Apply Bearer token to Authorization header.
+@deprecated("Import from crewai.a2a.auth instead", category=FutureWarning)
+class APIKeyAuth(_APIKeyAuth):
+    """Deprecated: Import from crewai.a2a.auth instead."""
 
-        Args:
-            client: HTTP client for making auth requests.
-            headers: Current request headers.
 
-        Returns:
-            Updated headers with Bearer token in Authorization header.
-        """
-        headers["Authorization"] = f"Bearer {self.token}"
-        return headers
+@deprecated("Import from crewai.a2a.auth instead", category=FutureWarning)
+class OAuth2ClientCredentials(_OAuth2ClientCredentials):
+    """Deprecated: Import from crewai.a2a.auth instead."""
 
 
-class HTTPBasicAuth(AuthScheme):
-    """HTTP Basic authentication.
+@deprecated("Import from crewai.a2a.auth instead", category=FutureWarning)
+class OAuth2AuthorizationCode(_OAuth2AuthorizationCode):
+    """Deprecated: Import from crewai.a2a.auth instead."""
 
-    Attributes:
-        username: Username for Basic authentication.
-        password: Password for Basic authentication.
-    """
 
-    username: str = Field(description="Username")
-    password: str = Field(description="Password")
-
-    async def apply_auth(
-        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
-    ) -> MutableMapping[str, str]:
-        """Apply HTTP Basic authentication.
-
-        Args:
-            client: HTTP client for making auth requests.
-            headers: Current request headers.
-
-        Returns:
-            Updated headers with Basic auth in Authorization header.
-        """
-        credentials = f"{self.username}:{self.password}"
-        encoded = base64.b64encode(credentials.encode()).decode()
-        headers["Authorization"] = f"Basic {encoded}"
-        return headers
-
-
-class HTTPDigestAuth(AuthScheme):
-    """HTTP Digest authentication.
-
-    Note: Uses httpx-auth library for digest implementation.
-
-    Attributes:
-        username: Username for Digest authentication.
-        password: Password for Digest authentication.
-    """
-
-    username: str = Field(description="Username")
-    password: str = Field(description="Password")
-
-    async def apply_auth(
-        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
-    ) -> MutableMapping[str, str]:
-        """Digest auth is handled by httpx auth flow, not headers.
-
-        Args:
-            client: HTTP client for making auth requests.
-            headers: Current request headers.
-
-        Returns:
-            Unchanged headers (Digest auth handled by httpx auth flow).
-        """
-        return headers
-
-    def configure_client(self, client: httpx.AsyncClient) -> None:
-        """Configure client with Digest auth.
-
-        Args:
-            client: HTTP client to configure with Digest authentication.
-        """
-        client.auth = DigestAuth(self.username, self.password)
-
-
-class APIKeyAuth(AuthScheme):
-    """API Key authentication (header, query, or cookie).
-
-    Attributes:
-        api_key: API key value for authentication.
-        location: Where to send the API key (header, query, or cookie).
-        name: Parameter name for the API key (default: X-API-Key).
-    """
-
-    api_key: str = Field(description="API key value")
-    location: Literal["header", "query", "cookie"] = Field(
-        default="header", description="Where to send the API key"
-    )
-    name: str = Field(default="X-API-Key", description="Parameter name for the API key")
-
-    async def apply_auth(
-        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
-    ) -> MutableMapping[str, str]:
-        """Apply API key authentication.
-
-        Args:
-            client: HTTP client for making auth requests.
-            headers: Current request headers.
-
-        Returns:
-            Updated headers with API key (for header/cookie locations).
-        """
-        if self.location == "header":
-            headers[self.name] = self.api_key
-        elif self.location == "cookie":
-            headers["Cookie"] = f"{self.name}={self.api_key}"
-        return headers
-
-    def configure_client(self, client: httpx.AsyncClient) -> None:
-        """Configure client for query param API keys.
-
-        Args:
-            client: HTTP client to configure with query param API key hook.
-        """
-        if self.location == "query":
-
-            async def _add_api_key_param(request: httpx.Request) -> None:
-                url = httpx.URL(request.url)
-                request.url = url.copy_add_param(self.name, self.api_key)
-
-            client.event_hooks["request"].append(_add_api_key_param)
-
-
-class OAuth2ClientCredentials(AuthScheme):
-    """OAuth2 Client Credentials flow authentication.
-
-    Attributes:
-        token_url: OAuth2 token endpoint URL.
-        client_id: OAuth2 client identifier.
-        client_secret: OAuth2 client secret.
-        scopes: List of required OAuth2 scopes.
-    """
-
-    token_url: str = Field(description="OAuth2 token endpoint")
-    client_id: str = Field(description="OAuth2 client ID")
-    client_secret: str = Field(description="OAuth2 client secret")
-    scopes: list[str] = Field(
-        default_factory=list, description="Required OAuth2 scopes"
-    )
-
-    _access_token: str | None = PrivateAttr(default=None)
-    _token_expires_at: float | None = PrivateAttr(default=None)
-
-    async def apply_auth(
-        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
-    ) -> MutableMapping[str, str]:
-        """Apply OAuth2 access token to Authorization header.
-
-        Args:
-            client: HTTP client for making token requests.
-            headers: Current request headers.
-
-        Returns:
-            Updated headers with OAuth2 access token in Authorization header.
-        """
-        if (
-            self._access_token is None
-            or self._token_expires_at is None
-            or time.time() >= self._token_expires_at
-        ):
-            await self._fetch_token(client)
-
-        if self._access_token:
-            headers["Authorization"] = f"Bearer {self._access_token}"
-
-        return headers
-
-    async def _fetch_token(self, client: httpx.AsyncClient) -> None:
-        """Fetch OAuth2 access token using client credentials flow.
-
-        Args:
-            client: HTTP client for making token request.
-
-        Raises:
-            httpx.HTTPStatusError: If token request fails.
-        """
-        data = {
-            "grant_type": "client_credentials",
-            "client_id": self.client_id,
-            "client_secret": self.client_secret,
-        }
-
-        if self.scopes:
-            data["scope"] = " ".join(self.scopes)
-
-        response = await client.post(self.token_url, data=data)
-        response.raise_for_status()
-
-        token_data = response.json()
-        self._access_token = token_data["access_token"]
-        expires_in = token_data.get("expires_in", 3600)
-        self._token_expires_at = time.time() + expires_in - 60
-
-
-class OAuth2AuthorizationCode(AuthScheme):
-    """OAuth2 Authorization Code flow authentication.
-
-    Note: Requires interactive authorization.
-
-    Attributes:
-        authorization_url: OAuth2 authorization endpoint URL.
-        token_url: OAuth2 token endpoint URL.
-        client_id: OAuth2 client identifier.
-        client_secret: OAuth2 client secret.
-        redirect_uri: OAuth2 redirect URI for callback.
-        scopes: List of required OAuth2 scopes.
-    """
-
-    authorization_url: str = Field(description="OAuth2 authorization endpoint")
-    token_url: str = Field(description="OAuth2 token endpoint")
-    client_id: str = Field(description="OAuth2 client ID")
-    client_secret: str = Field(description="OAuth2 client secret")
-    redirect_uri: str = Field(description="OAuth2 redirect URI")
-    scopes: list[str] = Field(
-        default_factory=list, description="Required OAuth2 scopes"
-    )
-
-    _access_token: str | None = PrivateAttr(default=None)
-    _refresh_token: str | None = PrivateAttr(default=None)
-    _token_expires_at: float | None = PrivateAttr(default=None)
-    _authorization_callback: Callable[[str], Awaitable[str]] | None = PrivateAttr(
-        default=None
-    )
-
-    def set_authorization_callback(
-        self, callback: Callable[[str], Awaitable[str]] | None
-    ) -> None:
-        """Set callback to handle authorization URL.
-
-        Args:
-            callback: Async function that receives authorization URL and returns auth code.
-        """
-        self._authorization_callback = callback
-
-    async def apply_auth(
-        self, client: httpx.AsyncClient, headers: MutableMapping[str, str]
-    ) -> MutableMapping[str, str]:
-        """Apply OAuth2 access token to Authorization header.
-
-        Args:
-            client: HTTP client for making token requests.
-            headers: Current request headers.
-
-        Returns:
-            Updated headers with OAuth2 access token in Authorization header.
-
-        Raises:
-            ValueError: If authorization callback is not set.
-        """
-
-        if self._access_token is None:
-            if self._authorization_callback is None:
-                msg = "Authorization callback not set. Use set_authorization_callback()"
-                raise ValueError(msg)
-            await self._fetch_initial_token(client)
-        elif self._token_expires_at and time.time() >= self._token_expires_at:
-            await self._refresh_access_token(client)
-
-        if self._access_token:
-            headers["Authorization"] = f"Bearer {self._access_token}"
-
-        return headers
-
-    async def _fetch_initial_token(self, client: httpx.AsyncClient) -> None:
-        """Fetch initial access token using authorization code flow.
-
-        Args:
-            client: HTTP client for making token request.
-
-        Raises:
-            ValueError: If authorization callback is not set.
-            httpx.HTTPStatusError: If token request fails.
-        """
-        params = {
-            "response_type": "code",
-            "client_id": self.client_id,
-            "redirect_uri": self.redirect_uri,
-            "scope": " ".join(self.scopes),
-        }
-        auth_url = f"{self.authorization_url}?{urllib.parse.urlencode(params)}"
-
-        if self._authorization_callback is None:
-            msg = "Authorization callback not set"
-            raise ValueError(msg)
-        auth_code = await self._authorization_callback(auth_url)
-
-        data = {
-            "grant_type": "authorization_code",
-            "code": auth_code,
-            "client_id": self.client_id,
-            "client_secret": self.client_secret,
-            "redirect_uri": self.redirect_uri,
-        }
-
-        response = await client.post(self.token_url, data=data)
-        response.raise_for_status()
-
-        token_data = response.json()
-        self._access_token = token_data["access_token"]
-        self._refresh_token = token_data.get("refresh_token")
-
-        expires_in = token_data.get("expires_in", 3600)
-        self._token_expires_at = time.time() + expires_in - 60
-
-    async def _refresh_access_token(self, client: httpx.AsyncClient) -> None:
-        """Refresh the access token using refresh token.
-
-        Args:
-            client: HTTP client for making token request.
-
-        Raises:
-            httpx.HTTPStatusError: If token refresh request fails.
-        """
-        if not self._refresh_token:
-            await self._fetch_initial_token(client)
-            return
-
-        data = {
-            "grant_type": "refresh_token",
-            "refresh_token": self._refresh_token,
-            "client_id": self.client_id,
-            "client_secret": self.client_secret,
-        }
-
-        response = await client.post(self.token_url, data=data)
-        response.raise_for_status()
-
-        token_data = response.json()
-        self._access_token = token_data["access_token"]
-        if "refresh_token" in token_data:
-            self._refresh_token = token_data["refresh_token"]
-
-        expires_in = token_data.get("expires_in", 3600)
-        self._token_expires_at = time.time() + expires_in - 60
+__all__ = [
+    "APIKeyAuth",
+    "AuthScheme",
+    "BearerTokenAuth",
+    "HTTPBasicAuth",
+    "HTTPDigestAuth",
+    "OAuth2AuthorizationCode",
+    "OAuth2ClientCredentials",
+]

lib/crewai/src/crewai/a2a/auth/server_schemes.py

@@ -0,0 +1,739 @@
+"""Server-side authentication schemes for A2A protocol.
+
+These schemes validate incoming requests to A2A server endpoints.
+
+Supported authentication methods:
+- Simple token validation with static bearer tokens
+- OpenID Connect with JWT validation using JWKS
+- OAuth2 with JWT validation or token introspection
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+import logging
+import os
+from typing import TYPE_CHECKING, Annotated, Any, ClassVar, Literal
+
+import jwt
+from jwt import PyJWKClient
+from pydantic import (
+    BaseModel,
+    BeforeValidator,
+    ConfigDict,
+    Field,
+    HttpUrl,
+    PrivateAttr,
+    SecretStr,
+    model_validator,
+)
+from typing_extensions import Self
+
+
+if TYPE_CHECKING:
+    from a2a.types import OAuth2SecurityScheme
+
+
+logger = logging.getLogger(__name__)
+
+
+try:
+    from fastapi import HTTPException, status as http_status
+
+    HTTP_401_UNAUTHORIZED = http_status.HTTP_401_UNAUTHORIZED
+    HTTP_500_INTERNAL_SERVER_ERROR = http_status.HTTP_500_INTERNAL_SERVER_ERROR
+    HTTP_503_SERVICE_UNAVAILABLE = http_status.HTTP_503_SERVICE_UNAVAILABLE
+except ImportError:
+
+    class HTTPException(Exception):  # type: ignore[no-redef]  # noqa: N818
+        """Fallback HTTPException when FastAPI is not installed."""
+
+        def __init__(
+            self,
+            status_code: int,
+            detail: str | None = None,
+            headers: dict[str, str] | None = None,
+        ) -> None:
+            self.status_code = status_code
+            self.detail = detail
+            self.headers = headers
+            super().__init__(detail)
+
+    HTTP_401_UNAUTHORIZED = 401
+    HTTP_500_INTERNAL_SERVER_ERROR = 500
+    HTTP_503_SERVICE_UNAVAILABLE = 503
+
+
+def _coerce_secret_str(v: str | SecretStr | None) -> SecretStr | None:
+    """Coerce string to SecretStr."""
+    if v is None or isinstance(v, SecretStr):
+        return v
+    return SecretStr(v)
+
+
+CoercedSecretStr = Annotated[SecretStr, BeforeValidator(_coerce_secret_str)]
+
+JWTAlgorithm = Literal[
+    "RS256",
+    "RS384",
+    "RS512",
+    "ES256",
+    "ES384",
+    "ES512",
+    "PS256",
+    "PS384",
+    "PS512",
+]
+
+
+@dataclass
+class AuthenticatedUser:
+    """Result of successful authentication.
+
+    Attributes:
+        token: The original token that was validated.
+        scheme: Name of the authentication scheme used.
+        claims: JWT claims from OIDC or OAuth2 authentication.
+    """
+
+    token: str
+    scheme: str
+    claims: dict[str, Any] | None = None
+
+
+class ServerAuthScheme(ABC, BaseModel):
+    """Base class for server-side authentication schemes.
+
+    Each scheme validates incoming requests and returns an AuthenticatedUser
+    on success, or raises HTTPException on failure.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    @abstractmethod
+    async def authenticate(self, token: str) -> AuthenticatedUser:
+        """Authenticate the provided token.
+
+        Args:
+            token: The bearer token to authenticate.
+
+        Returns:
+            AuthenticatedUser on successful authentication.
+
+        Raises:
+            HTTPException: If authentication fails.
+        """
+        ...
+
+
+class SimpleTokenAuth(ServerAuthScheme):
+    """Simple bearer token authentication.
+
+    Validates tokens against a configured static token or AUTH_TOKEN env var.
+
+    Attributes:
+        token: Expected token value. Falls back to AUTH_TOKEN env var if not set.
+    """
+
+    token: CoercedSecretStr | None = Field(
+        default=None,
+        description="Expected token. Falls back to AUTH_TOKEN env var.",
+    )
+
+    def _get_expected_token(self) -> str | None:
+        """Get the expected token value."""
+        if self.token:
+            return self.token.get_secret_value()
+        return os.environ.get("AUTH_TOKEN")
+
+    async def authenticate(self, token: str) -> AuthenticatedUser:
+        """Authenticate using simple token comparison.
+
+        Args:
+            token: The bearer token to authenticate.
+
+        Returns:
+            AuthenticatedUser on successful authentication.
+
+        Raises:
+            HTTPException: If authentication fails.
+        """
+        expected = self._get_expected_token()
+
+        if expected is None:
+            logger.warning(
+                "Simple token authentication failed",
+                extra={"reason": "no_token_configured"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Authentication not configured",
+            )
+
+        if token != expected:
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Invalid or missing authentication credentials",
+            )
+
+        return AuthenticatedUser(
+            token=token,
+            scheme="simple_token",
+        )
+
+
+class OIDCAuth(ServerAuthScheme):
+    """OpenID Connect authentication.
+
+    Validates JWTs using JWKS with caching support via PyJWT.
+
+    Attributes:
+        issuer: The OpenID Connect issuer URL.
+        audience: The expected audience claim.
+        jwks_url: Optional explicit JWKS URL. Derived from issuer if not set.
+        algorithms: List of allowed signing algorithms.
+        required_claims: List of claims that must be present in the token.
+        jwks_cache_ttl: TTL for JWKS cache in seconds.
+        clock_skew_seconds: Allowed clock skew for token validation.
+    """
+
+    issuer: HttpUrl = Field(
+        description="OpenID Connect issuer URL (e.g., https://auth.example.com)"
+    )
+    audience: str = Field(description="Expected audience claim (e.g., api://my-agent)")
+    jwks_url: HttpUrl | None = Field(
+        default=None,
+        description="Explicit JWKS URL. Derived from issuer if not set.",
+    )
+    algorithms: list[str] = Field(
+        default_factory=lambda: ["RS256"],
+        description="List of allowed signing algorithms (RS256, ES256, etc.)",
+    )
+    required_claims: list[str] = Field(
+        default_factory=lambda: ["exp", "iat", "iss", "aud", "sub"],
+        description="List of claims that must be present in the token",
+    )
+    jwks_cache_ttl: int = Field(
+        default=3600,
+        description="TTL for JWKS cache in seconds",
+        ge=60,
+    )
+    clock_skew_seconds: float = Field(
+        default=30.0,
+        description="Allowed clock skew for token validation",
+        ge=0.0,
+    )
+
+    _jwk_client: PyJWKClient | None = PrivateAttr(default=None)
+
+    @model_validator(mode="after")
+    def _init_jwk_client(self) -> Self:
+        """Initialize the JWK client after model creation."""
+        jwks_url = (
+            str(self.jwks_url)
+            if self.jwks_url
+            else f"{str(self.issuer).rstrip('/')}/.well-known/jwks.json"
+        )
+        self._jwk_client = PyJWKClient(jwks_url, lifespan=self.jwks_cache_ttl)
+        return self
+
+    async def authenticate(self, token: str) -> AuthenticatedUser:
+        """Authenticate using OIDC JWT validation.
+
+        Args:
+            token: The JWT to authenticate.
+
+        Returns:
+            AuthenticatedUser on successful authentication.
+
+        Raises:
+            HTTPException: If authentication fails.
+        """
+        if self._jwk_client is None:
+            raise HTTPException(
+                status_code=HTTP_500_INTERNAL_SERVER_ERROR,
+                detail="OIDC not initialized",
+            )
+
+        try:
+            signing_key = self._jwk_client.get_signing_key_from_jwt(token)
+
+            claims = jwt.decode(
+                token,
+                signing_key.key,
+                algorithms=self.algorithms,
+                audience=self.audience,
+                issuer=str(self.issuer).rstrip("/"),
+                leeway=self.clock_skew_seconds,
+                options={
+                    "require": self.required_claims,
+                },
+            )
+
+            return AuthenticatedUser(
+                token=token,
+                scheme="oidc",
+                claims=claims,
+            )
+
+        except jwt.ExpiredSignatureError:
+            logger.debug(
+                "OIDC authentication failed",
+                extra={"reason": "token_expired", "scheme": "oidc"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Token has expired",
+            ) from None
+        except jwt.InvalidAudienceError:
+            logger.debug(
+                "OIDC authentication failed",
+                extra={"reason": "invalid_audience", "scheme": "oidc"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Invalid token audience",
+            ) from None
+        except jwt.InvalidIssuerError:
+            logger.debug(
+                "OIDC authentication failed",
+                extra={"reason": "invalid_issuer", "scheme": "oidc"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Invalid token issuer",
+            ) from None
+        except jwt.MissingRequiredClaimError as e:
+            logger.debug(
+                "OIDC authentication failed",
+                extra={"reason": "missing_claim", "claim": e.claim, "scheme": "oidc"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail=f"Missing required claim: {e.claim}",
+            ) from None
+        except jwt.PyJWKClientError as e:
+            logger.error(
+                "OIDC authentication failed",
+                extra={
+                    "reason": "jwks_client_error",
+                    "error": str(e),
+                    "scheme": "oidc",
+                },
+            )
+            raise HTTPException(
+                status_code=HTTP_503_SERVICE_UNAVAILABLE,
+                detail="Unable to fetch signing keys",
+            ) from None
+        except jwt.InvalidTokenError as e:
+            logger.debug(
+                "OIDC authentication failed",
+                extra={"reason": "invalid_token", "error": str(e), "scheme": "oidc"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Invalid or missing authentication credentials",
+            ) from None
+
+
+class OAuth2ServerAuth(ServerAuthScheme):
+    """OAuth2 authentication for A2A server.
+
+    Declares OAuth2 security scheme in AgentCard and validates tokens using
+    either JWKS for JWT tokens or token introspection for opaque tokens.
+
+    This is distinct from OIDCAuth in that it declares an explicit OAuth2SecurityScheme
+    with flows, rather than an OpenIdConnectSecurityScheme with discovery URL.
+
+    Attributes:
+        token_url: OAuth2 token endpoint URL for client_credentials flow.
+        authorization_url: OAuth2 authorization endpoint for authorization_code flow.
+        refresh_url: Optional refresh token endpoint URL.
+        scopes: Available OAuth2 scopes with descriptions.
+        jwks_url: JWKS URL for JWT validation. Required if not using introspection.
+        introspection_url: Token introspection endpoint (RFC 7662). Alternative to JWKS.
+        introspection_client_id: Client ID for introspection endpoint authentication.
+        introspection_client_secret: Client secret for introspection endpoint.
+        audience: Expected audience claim for JWT validation.
+        issuer: Expected issuer claim for JWT validation.
+        algorithms: Allowed JWT signing algorithms.
+        required_claims: Claims that must be present in the token.
+        jwks_cache_ttl: TTL for JWKS cache in seconds.
+        clock_skew_seconds: Allowed clock skew for token validation.
+    """
+
+    token_url: HttpUrl = Field(
+        description="OAuth2 token endpoint URL",
+    )
+    authorization_url: HttpUrl | None = Field(
+        default=None,
+        description="OAuth2 authorization endpoint URL for authorization_code flow",
+    )
+    refresh_url: HttpUrl | None = Field(
+        default=None,
+        description="OAuth2 refresh token endpoint URL",
+    )
+    scopes: dict[str, str] = Field(
+        default_factory=dict,
+        description="Available OAuth2 scopes with descriptions",
+    )
+    jwks_url: HttpUrl | None = Field(
+        default=None,
+        description="JWKS URL for JWT validation. Required if not using introspection.",
+    )
+    introspection_url: HttpUrl | None = Field(
+        default=None,
+        description="Token introspection endpoint (RFC 7662). Alternative to JWKS.",
+    )
+    introspection_client_id: str | None = Field(
+        default=None,
+        description="Client ID for introspection endpoint authentication",
+    )
+    introspection_client_secret: CoercedSecretStr | None = Field(
+        default=None,
+        description="Client secret for introspection endpoint authentication",
+    )
+    audience: str | None = Field(
+        default=None,
+        description="Expected audience claim for JWT validation",
+    )
+    issuer: str | None = Field(
+        default=None,
+        description="Expected issuer claim for JWT validation",
+    )
+    algorithms: list[str] = Field(
+        default_factory=lambda: ["RS256"],
+        description="Allowed JWT signing algorithms",
+    )
+    required_claims: list[str] = Field(
+        default_factory=lambda: ["exp", "iat"],
+        description="Claims that must be present in the token",
+    )
+    jwks_cache_ttl: int = Field(
+        default=3600,
+        description="TTL for JWKS cache in seconds",
+        ge=60,
+    )
+    clock_skew_seconds: float = Field(
+        default=30.0,
+        description="Allowed clock skew for token validation",
+        ge=0.0,
+    )
+
+    _jwk_client: PyJWKClient | None = PrivateAttr(default=None)
+
+    @model_validator(mode="after")
+    def _validate_and_init(self) -> Self:
+        """Validate configuration and initialize JWKS client if needed."""
+        if not self.jwks_url and not self.introspection_url:
+            raise ValueError(
+                "Either jwks_url or introspection_url must be provided for token validation"
+            )
+
+        if self.introspection_url:
+            if not self.introspection_client_id or not self.introspection_client_secret:
+                raise ValueError(
+                    "introspection_client_id and introspection_client_secret are required "
+                    "when using token introspection"
+                )
+
+        if self.jwks_url:
+            self._jwk_client = PyJWKClient(
+                str(self.jwks_url), lifespan=self.jwks_cache_ttl
+            )
+
+        return self
+
+    async def authenticate(self, token: str) -> AuthenticatedUser:
+        """Authenticate using OAuth2 token validation.
+
+        Uses JWKS validation if jwks_url is configured, otherwise falls back
+        to token introspection.
+
+        Args:
+            token: The OAuth2 access token to authenticate.
+
+        Returns:
+            AuthenticatedUser on successful authentication.
+
+        Raises:
+            HTTPException: If authentication fails.
+        """
+        if self._jwk_client:
+            return await self._authenticate_jwt(token)
+        return await self._authenticate_introspection(token)
+
+    async def _authenticate_jwt(self, token: str) -> AuthenticatedUser:
+        """Authenticate using JWKS JWT validation."""
+        if self._jwk_client is None:
+            raise HTTPException(
+                status_code=HTTP_500_INTERNAL_SERVER_ERROR,
+                detail="OAuth2 JWKS not initialized",
+            )
+
+        try:
+            signing_key = self._jwk_client.get_signing_key_from_jwt(token)
+
+            decode_options: dict[str, Any] = {
+                "require": self.required_claims,
+            }
+
+            claims = jwt.decode(
+                token,
+                signing_key.key,
+                algorithms=self.algorithms,
+                audience=self.audience,
+                issuer=self.issuer,
+                leeway=self.clock_skew_seconds,
+                options=decode_options,
+            )
+
+            return AuthenticatedUser(
+                token=token,
+                scheme="oauth2",
+                claims=claims,
+            )
+
+        except jwt.ExpiredSignatureError:
+            logger.debug(
+                "OAuth2 authentication failed",
+                extra={"reason": "token_expired", "scheme": "oauth2"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Token has expired",
+            ) from None
+        except jwt.InvalidAudienceError:
+            logger.debug(
+                "OAuth2 authentication failed",
+                extra={"reason": "invalid_audience", "scheme": "oauth2"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Invalid token audience",
+            ) from None
+        except jwt.InvalidIssuerError:
+            logger.debug(
+                "OAuth2 authentication failed",
+                extra={"reason": "invalid_issuer", "scheme": "oauth2"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Invalid token issuer",
+            ) from None
+        except jwt.MissingRequiredClaimError as e:
+            logger.debug(
+                "OAuth2 authentication failed",
+                extra={"reason": "missing_claim", "claim": e.claim, "scheme": "oauth2"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail=f"Missing required claim: {e.claim}",
+            ) from None
+        except jwt.PyJWKClientError as e:
+            logger.error(
+                "OAuth2 authentication failed",
+                extra={
+                    "reason": "jwks_client_error",
+                    "error": str(e),
+                    "scheme": "oauth2",
+                },
+            )
+            raise HTTPException(
+                status_code=HTTP_503_SERVICE_UNAVAILABLE,
+                detail="Unable to fetch signing keys",
+            ) from None
+        except jwt.InvalidTokenError as e:
+            logger.debug(
+                "OAuth2 authentication failed",
+                extra={"reason": "invalid_token", "error": str(e), "scheme": "oauth2"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Invalid or missing authentication credentials",
+            ) from None
+
+    async def _authenticate_introspection(self, token: str) -> AuthenticatedUser:
+        """Authenticate using OAuth2 token introspection (RFC 7662)."""
+        import httpx
+
+        if not self.introspection_url:
+            raise HTTPException(
+                status_code=HTTP_500_INTERNAL_SERVER_ERROR,
+                detail="OAuth2 introspection not configured",
+            )
+
+        try:
+            async with httpx.AsyncClient() as client:
+                response = await client.post(
+                    str(self.introspection_url),
+                    data={"token": token},
+                    auth=(
+                        self.introspection_client_id or "",
+                        self.introspection_client_secret.get_secret_value()
+                        if self.introspection_client_secret
+                        else "",
+                    ),
+                )
+                response.raise_for_status()
+                introspection_result = response.json()
+
+        except httpx.HTTPStatusError as e:
+            logger.error(
+                "OAuth2 introspection failed",
+                extra={"reason": "http_error", "status_code": e.response.status_code},
+            )
+            raise HTTPException(
+                status_code=HTTP_503_SERVICE_UNAVAILABLE,
+                detail="Token introspection service unavailable",
+            ) from None
+        except Exception as e:
+            logger.error(
+                "OAuth2 introspection failed",
+                extra={"reason": "unexpected_error", "error": str(e)},
+            )
+            raise HTTPException(
+                status_code=HTTP_503_SERVICE_UNAVAILABLE,
+                detail="Token introspection failed",
+            ) from None
+
+        if not introspection_result.get("active", False):
+            logger.debug(
+                "OAuth2 authentication failed",
+                extra={"reason": "token_not_active", "scheme": "oauth2"},
+            )
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Token is not active",
+            )
+
+        return AuthenticatedUser(
+            token=token,
+            scheme="oauth2",
+            claims=introspection_result,
+        )
+
+    def to_security_scheme(self) -> OAuth2SecurityScheme:
+        """Generate OAuth2SecurityScheme for AgentCard declaration.
+
+        Creates an OAuth2SecurityScheme with appropriate flows based on
+        the configured URLs. Includes client_credentials flow if token_url
+        is set, and authorization_code flow if authorization_url is set.
+
+        Returns:
+            OAuth2SecurityScheme suitable for use in AgentCard security_schemes.
+        """
+        from a2a.types import (
+            AuthorizationCodeOAuthFlow,
+            ClientCredentialsOAuthFlow,
+            OAuth2SecurityScheme,
+            OAuthFlows,
+        )
+
+        client_credentials = None
+        authorization_code = None
+
+        if self.token_url:
+            client_credentials = ClientCredentialsOAuthFlow(
+                token_url=str(self.token_url),
+                refresh_url=str(self.refresh_url) if self.refresh_url else None,
+                scopes=self.scopes,
+            )
+
+        if self.authorization_url:
+            authorization_code = AuthorizationCodeOAuthFlow(
+                authorization_url=str(self.authorization_url),
+                token_url=str(self.token_url),
+                refresh_url=str(self.refresh_url) if self.refresh_url else None,
+                scopes=self.scopes,
+            )
+
+        return OAuth2SecurityScheme(
+            flows=OAuthFlows(
+                client_credentials=client_credentials,
+                authorization_code=authorization_code,
+            ),
+            description="OAuth2 authentication",
+        )
+
+
+class APIKeyServerAuth(ServerAuthScheme):
+    """API Key authentication for A2A server.
+
+    Validates requests using an API key in a header, query parameter, or cookie.
+
+    Attributes:
+        name: The name of the API key parameter (default: X-API-Key).
+        location: Where to look for the API key (header, query, or cookie).
+        api_key: The expected API key value.
+    """
+
+    name: str = Field(
+        default="X-API-Key",
+        description="Name of the API key parameter",
+    )
+    location: Literal["header", "query", "cookie"] = Field(
+        default="header",
+        description="Where to look for the API key",
+    )
+    api_key: CoercedSecretStr = Field(
+        description="Expected API key value",
+    )
+
+    async def authenticate(self, token: str) -> AuthenticatedUser:
+        """Authenticate using API key comparison.
+
+        Args:
+            token: The API key to authenticate.
+
+        Returns:
+            AuthenticatedUser on successful authentication.
+
+        Raises:
+            HTTPException: If authentication fails.
+        """
+        if token != self.api_key.get_secret_value():
+            raise HTTPException(
+                status_code=HTTP_401_UNAUTHORIZED,
+                detail="Invalid API key",
+            )
+
+        return AuthenticatedUser(
+            token=token,
+            scheme="api_key",
+        )
+
+
+class MTLSServerAuth(ServerAuthScheme):
+    """Mutual TLS authentication marker for AgentCard declaration.
+
+    This scheme is primarily for AgentCard security_schemes declaration.
+    Actual mTLS verification happens at the TLS/transport layer, not
+    at the application layer via token validation.
+
+    When configured, this signals to clients that the server requires
+    client certificates for authentication.
+    """
+
+    description: str = Field(
+        default="Mutual TLS certificate authentication",
+        description="Description for the security scheme",
+    )
+
+    async def authenticate(self, token: str) -> AuthenticatedUser:
+        """Return authenticated user for mTLS.
+
+        mTLS verification happens at the transport layer before this is called.
+        If we reach this point, the TLS handshake with client cert succeeded.
+
+        Args:
+            token: Certificate subject or identifier (from TLS layer).
+
+        Returns:
+            AuthenticatedUser indicating mTLS authentication.
+        """
+        return AuthenticatedUser(
+            token=token or "mtls-verified",
+            scheme="mtls",
+        )

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

@@ -6,8 +6,10 @@ OAuth2, API keys, and HTTP authentication methods.
 
 import asyncio
 from collections.abc import Awaitable, Callable, MutableMapping
+import hashlib
 import re
-from typing import Final
+import threading
+from typing import Final, Literal, cast
 
 from a2a.client.errors import A2AClientHTTPError
 from a2a.types import (
@@ -18,10 +20,10 @@ from a2a.types import (
 )
 from httpx import AsyncClient, Response
 
-from crewai.a2a.auth.schemas import (
+from crewai.a2a.auth.client_schemes import (
     APIKeyAuth,
-    AuthScheme,
     BearerTokenAuth,
+    ClientAuthScheme,
     HTTPBasicAuth,
     HTTPDigestAuth,
     OAuth2AuthorizationCode,
@@ -29,12 +31,44 @@ from crewai.a2a.auth.schemas import (
 )
 
 
-_auth_store: dict[int, AuthScheme | None] = {}
+class _AuthStore:
+    """Store for authentication schemes with safe concurrent access."""
+
+    def __init__(self) -> None:
+        self._store: dict[str, ClientAuthScheme | None] = {}
+        self._lock = threading.RLock()
+
+    @staticmethod
+    def compute_key(auth_type: str, auth_data: str) -> str:
+        """Compute a collision-resistant key using SHA-256."""
+        content = f"{auth_type}:{auth_data}"
+        return hashlib.sha256(content.encode()).hexdigest()
+
+    def set(self, key: str, auth: ClientAuthScheme | None) -> None:
+        """Store an auth scheme."""
+        with self._lock:
+            self._store[key] = auth
+
+    def get(self, key: str) -> ClientAuthScheme | None:
+        """Retrieve an auth scheme by key."""
+        with self._lock:
+            return self._store.get(key)
+
+    def __setitem__(self, key: str, value: ClientAuthScheme | None) -> None:
+        with self._lock:
+            self._store[key] = value
+
+    def __getitem__(self, key: str) -> ClientAuthScheme | None:
+        with self._lock:
+            return self._store[key]
+
+
+_auth_store = _AuthStore()
 
 _SCHEME_PATTERN: Final[re.Pattern[str]] = re.compile(r"(\w+)\s+(.+?)(?=,\s*\w+\s+|$)")
 _PARAM_PATTERN: Final[re.Pattern[str]] = re.compile(r'(\w+)=(?:"([^"]*)"|([^\s,]+))')
 
-_SCHEME_AUTH_MAPPING: Final[dict[type, tuple[type[AuthScheme], ...]]] = {
+_SCHEME_AUTH_MAPPING: Final[dict[type, tuple[type[ClientAuthScheme], ...]]] = {
     OAuth2SecurityScheme: (
         OAuth2ClientCredentials,
         OAuth2AuthorizationCode,
@@ -43,7 +77,9 @@ _SCHEME_AUTH_MAPPING: Final[dict[type, tuple[type[AuthScheme], ...]]] = {
     APIKeySecurityScheme: (APIKeyAuth,),
 }
 
-_HTTP_SCHEME_MAPPING: Final[dict[str, type[AuthScheme]]] = {
+_HTTPSchemeType = Literal["basic", "digest", "bearer"]
+
+_HTTP_SCHEME_MAPPING: Final[dict[_HTTPSchemeType, type[ClientAuthScheme]]] = {
     "basic": HTTPBasicAuth,
     "digest": HTTPDigestAuth,
     "bearer": BearerTokenAuth,
@@ -51,8 +87,8 @@ _HTTP_SCHEME_MAPPING: Final[dict[str, type[AuthScheme]]] = {
 
 
 def _raise_auth_mismatch(
-    expected_classes: type[AuthScheme] | tuple[type[AuthScheme], ...],
-    provided_auth: AuthScheme,
+    expected_classes: type[ClientAuthScheme] | tuple[type[ClientAuthScheme], ...],
+    provided_auth: ClientAuthScheme,
 ) -> None:
     """Raise authentication mismatch error.
 
@@ -111,7 +147,7 @@ def parse_www_authenticate(header_value: str) -> dict[str, dict[str, str]]:
 
 
 def validate_auth_against_agent_card(
-    agent_card: AgentCard, auth: AuthScheme | None
+    agent_card: AgentCard, auth: ClientAuthScheme | None
 ) -> None:
     """Validate that provided auth matches AgentCard security requirements.
 
@@ -145,7 +181,8 @@ def validate_auth_against_agent_card(
             return
 
         if isinstance(scheme, HTTPAuthSecurityScheme):
-            if required_class := _HTTP_SCHEME_MAPPING.get(scheme.scheme.lower()):
+            scheme_key = cast(_HTTPSchemeType, scheme.scheme.lower())
+            if required_class := _HTTP_SCHEME_MAPPING.get(scheme_key):
                 if not isinstance(auth, required_class):
                     _raise_auth_mismatch(required_class, auth)
             return
@@ -156,7 +193,7 @@ def validate_auth_against_agent_card(
 
 async def retry_on_401(
     request_func: Callable[[], Awaitable[Response]],
-    auth_scheme: AuthScheme | None,
+    auth_scheme: ClientAuthScheme | None,
     client: AsyncClient,
     headers: MutableMapping[str, str],
     max_retries: int = 3,

lib/crewai/src/crewai/a2a/config.py

@@ -5,14 +5,25 @@ This module is separate from experimental.a2a to avoid circular imports.
 
 from __future__ import annotations
 
-from importlib.metadata import version
-from typing import Any, ClassVar, Literal
+from pathlib import Path
+from typing import Any, ClassVar, Literal, cast
+import warnings
 
-from pydantic import BaseModel, ConfigDict, Field
-from typing_extensions import deprecated
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    FilePath,
+    PrivateAttr,
+    SecretStr,
+    model_validator,
+)
+from typing_extensions import Self, deprecated
 
-from crewai.a2a.auth.schemas import AuthScheme
-from crewai.a2a.types import TransportType, Url
+from crewai.a2a.auth.client_schemes import ClientAuthScheme
+from crewai.a2a.auth.server_schemes import ServerAuthScheme
+from crewai.a2a.extensions.base import ValidatedA2AExtension
+from crewai.a2a.types import ProtocolVersion, TransportType, Url
 
 
 try:
@@ -25,16 +36,17 @@ try:
         SecurityScheme,
     )
 
+    from crewai.a2a.extensions.server import ServerExtension
     from crewai.a2a.updates import UpdateConfig
 except ImportError:
-    UpdateConfig = Any
-    AgentCapabilities = Any
-    AgentCardSignature = Any
-    AgentInterface = Any
-    AgentProvider = Any
-    SecurityScheme = Any
-    AgentSkill = Any
-    UpdateConfig = Any  # type: ignore[misc,assignment]
+    UpdateConfig: Any = Any  # type: ignore[no-redef]
+    AgentCapabilities: Any = Any  # type: ignore[no-redef]
+    AgentCardSignature: Any = Any  # type: ignore[no-redef]
+    AgentInterface: Any = Any  # type: ignore[no-redef]
+    AgentProvider: Any = Any  # type: ignore[no-redef]
+    SecurityScheme: Any = Any  # type: ignore[no-redef]
+    AgentSkill: Any = Any  # type: ignore[no-redef]
+    ServerExtension: Any = Any  # type: ignore[no-redef]
 
 
 def _get_default_update_config() -> UpdateConfig:
@@ -43,6 +55,309 @@ def _get_default_update_config() -> UpdateConfig:
     return StreamingConfig()
 
 
+SigningAlgorithm = Literal[
+    "RS256",
+    "RS384",
+    "RS512",
+    "ES256",
+    "ES384",
+    "ES512",
+    "PS256",
+    "PS384",
+    "PS512",
+]
+
+
+class AgentCardSigningConfig(BaseModel):
+    """Configuration for AgentCard JWS signing.
+
+    Provides the private key and algorithm settings for signing AgentCards.
+    Either private_key_path or private_key_pem must be provided, but not both.
+
+    Attributes:
+        private_key_path: Path to a PEM-encoded private key file.
+        private_key_pem: PEM-encoded private key as a secret string.
+        key_id: Optional key identifier for the JWS header (kid claim).
+        algorithm: Signing algorithm (RS256, ES256, PS256, etc.).
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    private_key_path: FilePath | None = Field(
+        default=None,
+        description="Path to PEM-encoded private key file",
+    )
+    private_key_pem: SecretStr | None = Field(
+        default=None,
+        description="PEM-encoded private key",
+    )
+    key_id: str | None = Field(
+        default=None,
+        description="Key identifier for JWS header (kid claim)",
+    )
+    algorithm: SigningAlgorithm = Field(
+        default="RS256",
+        description="Signing algorithm (RS256, ES256, PS256, etc.)",
+    )
+
+    @model_validator(mode="after")
+    def _validate_key_source(self) -> Self:
+        """Ensure exactly one key source is provided."""
+        has_path = self.private_key_path is not None
+        has_pem = self.private_key_pem is not None
+
+        if not has_path and not has_pem:
+            raise ValueError(
+                "Either private_key_path or private_key_pem must be provided"
+            )
+        if has_path and has_pem:
+            raise ValueError(
+                "Only one of private_key_path or private_key_pem should be provided"
+            )
+        return self
+
+    def get_private_key(self) -> str:
+        """Get the private key content.
+
+        Returns:
+            The PEM-encoded private key as a string.
+        """
+        if self.private_key_pem:
+            return self.private_key_pem.get_secret_value()
+        if self.private_key_path:
+            return Path(self.private_key_path).read_text()
+        raise ValueError("No private key configured")
+
+
+class GRPCServerConfig(BaseModel):
+    """gRPC server transport configuration.
+
+    Presence of this config in ServerTransportConfig.grpc enables gRPC transport.
+
+    Attributes:
+        host: Hostname to advertise in agent cards (default: localhost).
+            Use docker service name (e.g., 'web') for docker-compose setups.
+        port: Port for the gRPC server.
+        tls_cert_path: Path to TLS certificate file for gRPC.
+        tls_key_path: Path to TLS private key file for gRPC.
+        max_workers: Maximum number of workers for the gRPC thread pool.
+        reflection_enabled: Whether to enable gRPC reflection for debugging.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    host: str = Field(
+        default="localhost",
+        description="Hostname to advertise in agent cards for gRPC connections",
+    )
+    port: int = Field(
+        default=50051,
+        description="Port for the gRPC server",
+    )
+    tls_cert_path: str | None = Field(
+        default=None,
+        description="Path to TLS certificate file for gRPC",
+    )
+    tls_key_path: str | None = Field(
+        default=None,
+        description="Path to TLS private key file for gRPC",
+    )
+    max_workers: int = Field(
+        default=10,
+        description="Maximum number of workers for the gRPC thread pool",
+    )
+    reflection_enabled: bool = Field(
+        default=False,
+        description="Whether to enable gRPC reflection for debugging",
+    )
+
+
+class GRPCClientConfig(BaseModel):
+    """gRPC client transport configuration.
+
+    Attributes:
+        max_send_message_length: Maximum size for outgoing messages in bytes.
+        max_receive_message_length: Maximum size for incoming messages in bytes.
+        keepalive_time_ms: Time between keepalive pings in milliseconds.
+        keepalive_timeout_ms: Timeout for keepalive ping response in milliseconds.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    max_send_message_length: int | None = Field(
+        default=None,
+        description="Maximum size for outgoing messages in bytes",
+    )
+    max_receive_message_length: int | None = Field(
+        default=None,
+        description="Maximum size for incoming messages in bytes",
+    )
+    keepalive_time_ms: int | None = Field(
+        default=None,
+        description="Time between keepalive pings in milliseconds",
+    )
+    keepalive_timeout_ms: int | None = Field(
+        default=None,
+        description="Timeout for keepalive ping response in milliseconds",
+    )
+
+
+class JSONRPCServerConfig(BaseModel):
+    """JSON-RPC server transport configuration.
+
+    Presence of this config in ServerTransportConfig.jsonrpc enables JSON-RPC transport.
+
+    Attributes:
+        rpc_path: URL path for the JSON-RPC endpoint.
+        agent_card_path: URL path for the agent card endpoint.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    rpc_path: str = Field(
+        default="/a2a",
+        description="URL path for the JSON-RPC endpoint",
+    )
+    agent_card_path: str = Field(
+        default="/.well-known/agent-card.json",
+        description="URL path for the agent card endpoint",
+    )
+
+
+class JSONRPCClientConfig(BaseModel):
+    """JSON-RPC client transport configuration.
+
+    Attributes:
+        max_request_size: Maximum request body size in bytes.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    max_request_size: int | None = Field(
+        default=None,
+        description="Maximum request body size in bytes",
+    )
+
+
+class HTTPJSONConfig(BaseModel):
+    """HTTP+JSON transport configuration.
+
+    Presence of this config in ServerTransportConfig.http_json enables HTTP+JSON transport.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+
+class ServerPushNotificationConfig(BaseModel):
+    """Configuration for outgoing webhook push notifications.
+
+    Controls how the server signs and delivers push notifications to clients.
+
+    Attributes:
+        signature_secret: Shared secret for HMAC-SHA256 signing of outgoing webhooks.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    signature_secret: SecretStr | None = Field(
+        default=None,
+        description="Shared secret for HMAC-SHA256 signing of outgoing push notifications",
+    )
+
+
+class ServerTransportConfig(BaseModel):
+    """Transport configuration for A2A server.
+
+    Groups all transport-related settings including preferred transport
+    and protocol-specific configurations.
+
+    Attributes:
+        preferred: Transport protocol for the preferred endpoint.
+        jsonrpc: JSON-RPC server transport configuration.
+        grpc: gRPC server transport configuration.
+        http_json: HTTP+JSON transport configuration.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    preferred: TransportType = Field(
+        default="JSONRPC",
+        description="Transport protocol for the preferred endpoint",
+    )
+    jsonrpc: JSONRPCServerConfig = Field(
+        default_factory=JSONRPCServerConfig,
+        description="JSON-RPC server transport configuration",
+    )
+    grpc: GRPCServerConfig | None = Field(
+        default=None,
+        description="gRPC server transport configuration",
+    )
+    http_json: HTTPJSONConfig | None = Field(
+        default=None,
+        description="HTTP+JSON transport configuration",
+    )
+
+
+def _migrate_client_transport_fields(
+    transport: ClientTransportConfig,
+    transport_protocol: TransportType | None,
+    supported_transports: list[TransportType] | None,
+) -> None:
+    """Migrate deprecated transport fields to new config."""
+    if transport_protocol is not None:
+        warnings.warn(
+            "transport_protocol is deprecated, use transport=ClientTransportConfig(preferred=...) instead",
+            FutureWarning,
+            stacklevel=5,
+        )
+        object.__setattr__(transport, "preferred", transport_protocol)
+    if supported_transports is not None:
+        warnings.warn(
+            "supported_transports is deprecated, use transport=ClientTransportConfig(supported=...) instead",
+            FutureWarning,
+            stacklevel=5,
+        )
+        object.__setattr__(transport, "supported", supported_transports)
+
+
+class ClientTransportConfig(BaseModel):
+    """Transport configuration for A2A client.
+
+    Groups all client transport-related settings including preferred transport,
+    supported transports for negotiation, and protocol-specific configurations.
+
+    Transport negotiation logic:
+    1. If `preferred` is set and server supports it → use client's preferred
+    2. Otherwise, if server's preferred is in client's `supported` → use server's preferred
+    3. Otherwise, find first match from client's `supported` in server's interfaces
+
+    Attributes:
+        preferred: Client's preferred transport. If set, client preference takes priority.
+        supported: Transports the client can use, in order of preference.
+        jsonrpc: JSON-RPC client transport configuration.
+        grpc: gRPC client transport configuration.
+    """
+
+    model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
+
+    preferred: TransportType | None = Field(
+        default=None,
+        description="Client's preferred transport. If set, takes priority over server preference.",
+    )
+    supported: list[TransportType] = Field(
+        default_factory=lambda: cast(list[TransportType], ["JSONRPC"]),
+        description="Transports the client can use, in order of preference",
+    )
+    jsonrpc: JSONRPCClientConfig = Field(
+        default_factory=JSONRPCClientConfig,
+        description="JSON-RPC client transport configuration",
+    )
+    grpc: GRPCClientConfig = Field(
+        default_factory=GRPCClientConfig,
+        description="gRPC client transport configuration",
+    )
+
+
 @deprecated(
     """
     `crewai.a2a.config.A2AConfig` is deprecated and will be removed in v2.0.0,
@@ -65,13 +380,14 @@ class A2AConfig(BaseModel):
         fail_fast: If True, raise error when agent unreachable; if False, skip and continue.
         trust_remote_completion_status: If True, return A2A agent's result directly when completed.
         updates: Update mechanism config.
-        transport_protocol: A2A transport protocol (grpc, jsonrpc, http+json).
+        client_extensions: Client-side processing hooks for tool injection and prompt augmentation.
+        transport: Transport configuration (preferred, supported transports, gRPC settings).
     """
 
     model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
 
     endpoint: Url = Field(description="A2A agent endpoint URL")
-    auth: AuthScheme | None = Field(
+    auth: ClientAuthScheme | None = Field(
         default=None,
         description="Authentication scheme",
     )
@@ -95,10 +411,48 @@ class A2AConfig(BaseModel):
         default_factory=_get_default_update_config,
         description="Update mechanism config",
     )
-    transport_protocol: Literal["JSONRPC", "GRPC", "HTTP+JSON"] = Field(
-        default="JSONRPC",
-        description="Specified mode of A2A transport protocol",
+    client_extensions: list[ValidatedA2AExtension] = Field(
+        default_factory=list,
+        description="Client-side processing hooks for tool injection and prompt augmentation",
     )
+    transport: ClientTransportConfig = Field(
+        default_factory=ClientTransportConfig,
+        description="Transport configuration (preferred, supported transports, gRPC settings)",
+    )
+    transport_protocol: TransportType | None = Field(
+        default=None,
+        description="Deprecated: Use transport.preferred instead",
+        exclude=True,
+    )
+    supported_transports: list[TransportType] | None = Field(
+        default=None,
+        description="Deprecated: Use transport.supported instead",
+        exclude=True,
+    )
+    use_client_preference: bool | None = Field(
+        default=None,
+        description="Deprecated: Set transport.preferred to enable client preference",
+        exclude=True,
+    )
+    _parallel_delegation: bool = PrivateAttr(default=False)
+
+    @model_validator(mode="after")
+    def _migrate_deprecated_transport_fields(self) -> Self:
+        """Migrate deprecated transport fields to new config."""
+        _migrate_client_transport_fields(
+            self.transport, self.transport_protocol, self.supported_transports
+        )
+        if self.use_client_preference is not None:
+            warnings.warn(
+                "use_client_preference is deprecated, set transport.preferred to enable client preference",
+                FutureWarning,
+                stacklevel=4,
+            )
+            if self.use_client_preference and self.transport.supported:
+                object.__setattr__(
+                    self.transport, "preferred", self.transport.supported[0]
+                )
+        return self
 
 
 class A2AClientConfig(BaseModel):
@@ -114,15 +468,15 @@ class A2AClientConfig(BaseModel):
         trust_remote_completion_status: If True, return A2A agent's result directly when completed.
         updates: Update mechanism config.
         accepted_output_modes: Media types the client can accept in responses.
-        supported_transports: Ordered list of transport protocols the client supports.
-        use_client_preference: Whether to prioritize client transport preferences over server.
-        extensions: Extension URIs the client supports.
+        extensions: Extension URIs the client supports (A2A protocol extensions).
+        client_extensions: Client-side processing hooks for tool injection and prompt augmentation.
+        transport: Transport configuration (preferred, supported transports, gRPC settings).
     """
 
     model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
 
     endpoint: Url = Field(description="A2A agent endpoint URL")
-    auth: AuthScheme | None = Field(
+    auth: ClientAuthScheme | None = Field(
         default=None,
         description="Authentication scheme",
     )
@@ -150,22 +504,37 @@ class A2AClientConfig(BaseModel):
         default_factory=lambda: ["application/json"],
         description="Media types the client can accept in responses",
     )
-    supported_transports: list[str] = Field(
-        default_factory=lambda: ["JSONRPC"],
-        description="Ordered list of transport protocols the client supports",
-    )
-    use_client_preference: bool = Field(
-        default=False,
-        description="Whether to prioritize client transport preferences over server",
-    )
     extensions: list[str] = Field(
         default_factory=list,
         description="Extension URIs the client supports",
     )
-    transport_protocol: Literal["JSONRPC", "GRPC", "HTTP+JSON"] = Field(
-        default="JSONRPC",
-        description="Specified mode of A2A transport protocol",
+    client_extensions: list[ValidatedA2AExtension] = Field(
+        default_factory=list,
+        description="Client-side processing hooks for tool injection and prompt augmentation",
     )
+    transport: ClientTransportConfig = Field(
+        default_factory=ClientTransportConfig,
+        description="Transport configuration (preferred, supported transports, gRPC settings)",
+    )
+    transport_protocol: TransportType | None = Field(
+        default=None,
+        description="Deprecated: Use transport.preferred instead",
+        exclude=True,
+    )
+    supported_transports: list[TransportType] | None = Field(
+        default=None,
+        description="Deprecated: Use transport.supported instead",
+        exclude=True,
+    )
+    _parallel_delegation: bool = PrivateAttr(default=False)
+
+    @model_validator(mode="after")
+    def _migrate_deprecated_transport_fields(self) -> Self:
+        """Migrate deprecated transport fields to new config."""
+        _migrate_client_transport_fields(
+            self.transport, self.transport_protocol, self.supported_transports
+        )
+        return self
 
 
 class A2AServerConfig(BaseModel):
@@ -182,7 +551,6 @@ class A2AServerConfig(BaseModel):
         default_input_modes: Default supported input MIME types.
         default_output_modes: Default supported output MIME types.
         capabilities: Declaration of optional capabilities.
-        preferred_transport: Transport protocol for the preferred endpoint.
         protocol_version: A2A protocol version this agent supports.
         provider: Information about the agent's service provider.
         documentation_url: URL to the agent's documentation.
@@ -192,7 +560,12 @@ class A2AServerConfig(BaseModel):
         security_schemes: Security schemes available to authorize requests.
         supports_authenticated_extended_card: Whether agent provides extended card to authenticated users.
         url: Preferred endpoint URL for the agent.
-        signatures: JSON Web Signatures for the AgentCard.
+        signing_config: Configuration for signing the AgentCard with JWS.
+        signatures: Deprecated. Pre-computed JWS signatures. Use signing_config instead.
+        server_extensions: Server-side A2A protocol extensions with on_request/on_response hooks.
+        push_notifications: Configuration for outgoing push notifications.
+        transport: Transport configuration (preferred transport, gRPC, REST settings).
+        auth: Authentication scheme for A2A endpoints.
     """
 
     model_config: ClassVar[ConfigDict] = ConfigDict(extra="forbid")
@@ -228,12 +601,8 @@ class A2AServerConfig(BaseModel):
         ),
         description="Declaration of optional capabilities supported by the agent",
     )
-    preferred_transport: TransportType = Field(
-        default="JSONRPC",
-        description="Transport protocol for the preferred endpoint",
-    )
-    protocol_version: str = Field(
-        default_factory=lambda: version("a2a-sdk"),
+    protocol_version: ProtocolVersion = Field(
+        default="0.3.0",
         description="A2A protocol version this agent supports",
     )
     provider: AgentProvider | None = Field(
@@ -250,7 +619,7 @@ class A2AServerConfig(BaseModel):
     )
     additional_interfaces: list[AgentInterface] = Field(
         default_factory=list,
-        description="Additional supported interfaces (transport and URL combinations)",
+        description="Additional supported interfaces.",
     )
     security: list[dict[str, list[str]]] = Field(
         default_factory=list,
@@ -268,7 +637,54 @@ class A2AServerConfig(BaseModel):
         default=None,
         description="Preferred endpoint URL for the agent. Set at runtime if not provided.",
     )
-    signatures: list[AgentCardSignature] = Field(
-        default_factory=list,
-        description="JSON Web Signatures for the AgentCard",
+    signing_config: AgentCardSigningConfig | None = Field(
+        default=None,
+        description="Configuration for signing the AgentCard with JWS",
     )
+    signatures: list[AgentCardSignature] | None = Field(
+        default=None,
+        description="Deprecated: Use signing_config instead. Pre-computed JWS signatures for the AgentCard.",
+        exclude=True,
+        deprecated=True,
+    )
+    server_extensions: list[ServerExtension] = Field(
+        default_factory=list,
+        description="Server-side A2A protocol extensions that modify agent behavior",
+    )
+    push_notifications: ServerPushNotificationConfig | None = Field(
+        default=None,
+        description="Configuration for outgoing push notifications",
+    )
+    transport: ServerTransportConfig = Field(
+        default_factory=ServerTransportConfig,
+        description="Transport configuration (preferred transport, gRPC, REST settings)",
+    )
+    preferred_transport: TransportType | None = Field(
+        default=None,
+        description="Deprecated: Use transport.preferred instead",
+        exclude=True,
+        deprecated=True,
+    )
+    auth: ServerAuthScheme | None = Field(
+        default=None,
+        description="Authentication scheme for A2A endpoints. Defaults to SimpleTokenAuth using AUTH_TOKEN env var.",
+    )
+
+    @model_validator(mode="after")
+    def _migrate_deprecated_fields(self) -> Self:
+        """Migrate deprecated fields to new config."""
+        if self.preferred_transport is not None:
+            warnings.warn(
+                "preferred_transport is deprecated, use transport=ServerTransportConfig(preferred=...) instead",
+                FutureWarning,
+                stacklevel=4,
+            )
+            object.__setattr__(self.transport, "preferred", self.preferred_transport)
+        if self.signatures is not None:
+            warnings.warn(
+                "signatures is deprecated, use signing_config=AgentCardSigningConfig(...) instead. "
+                "The signatures field will be removed in v2.0.0.",
+                FutureWarning,
+                stacklevel=4,
+            )
+        return self

lib/crewai/src/crewai/a2a/errors.py

@@ -1,7 +1,491 @@
-"""A2A protocol error types."""
+"""A2A error codes and error response utilities.
+
+This module provides a centralized mapping of all A2A protocol error codes
+as defined in the A2A specification, plus custom CrewAI extensions.
+
+Error codes follow JSON-RPC 2.0 conventions:
+- -32700 to -32600: Standard JSON-RPC errors
+- -32099 to -32000: Server errors (A2A-specific)
+- -32768 to -32100: Reserved for implementation-defined errors
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from enum import IntEnum
+from typing import Any
 
 from a2a.client.errors import A2AClientTimeoutError
 
 
 class A2APollingTimeoutError(A2AClientTimeoutError):
     """Raised when polling exceeds the configured timeout."""
+
+
+class A2AErrorCode(IntEnum):
+    """A2A protocol error codes.
+
+    Codes follow JSON-RPC 2.0 specification with A2A-specific extensions.
+    """
+
+    # JSON-RPC 2.0 Standard Errors (-32700 to -32600)
+    JSON_PARSE_ERROR = -32700
+    """Invalid JSON was received by the server."""
+
+    INVALID_REQUEST = -32600
+    """The JSON sent is not a valid Request object."""
+
+    METHOD_NOT_FOUND = -32601
+    """The method does not exist / is not available."""
+
+    INVALID_PARAMS = -32602
+    """Invalid method parameter(s)."""
+
+    INTERNAL_ERROR = -32603
+    """Internal JSON-RPC error."""
+
+    # A2A-Specific Errors (-32099 to -32000)
+    TASK_NOT_FOUND = -32001
+    """The specified task was not found."""
+
+    TASK_NOT_CANCELABLE = -32002
+    """The task cannot be canceled (already completed/failed)."""
+
+    PUSH_NOTIFICATION_NOT_SUPPORTED = -32003
+    """Push notifications are not supported by this agent."""
+
+    UNSUPPORTED_OPERATION = -32004
+    """The requested operation is not supported."""
+
+    CONTENT_TYPE_NOT_SUPPORTED = -32005
+    """Incompatible content types between client and server."""
+
+    INVALID_AGENT_RESPONSE = -32006
+    """The agent produced an invalid response."""
+
+    # CrewAI Custom Extensions (-32768 to -32100)
+    UNSUPPORTED_VERSION = -32009
+    """The requested A2A protocol version is not supported."""
+
+    UNSUPPORTED_EXTENSION = -32010
+    """Client does not support required protocol extensions."""
+
+    AUTHENTICATION_REQUIRED = -32011
+    """Authentication is required for this operation."""
+
+    AUTHORIZATION_FAILED = -32012
+    """Authorization check failed (insufficient permissions)."""
+
+    RATE_LIMIT_EXCEEDED = -32013
+    """Rate limit exceeded for this client/operation."""
+
+    TASK_TIMEOUT = -32014
+    """Task execution timed out."""
+
+    TRANSPORT_NEGOTIATION_FAILED = -32015
+    """Failed to negotiate a compatible transport protocol."""
+
+    CONTEXT_NOT_FOUND = -32016
+    """The specified context was not found."""
+
+    SKILL_NOT_FOUND = -32017
+    """The specified skill was not found."""
+
+    ARTIFACT_NOT_FOUND = -32018
+    """The specified artifact was not found."""
+
+
+# Error code to default message mapping
+ERROR_MESSAGES: dict[int, str] = {
+    A2AErrorCode.JSON_PARSE_ERROR: "Parse error",
+    A2AErrorCode.INVALID_REQUEST: "Invalid Request",
+    A2AErrorCode.METHOD_NOT_FOUND: "Method not found",
+    A2AErrorCode.INVALID_PARAMS: "Invalid params",
+    A2AErrorCode.INTERNAL_ERROR: "Internal error",
+    A2AErrorCode.TASK_NOT_FOUND: "Task not found",
+    A2AErrorCode.TASK_NOT_CANCELABLE: "Task not cancelable",
+    A2AErrorCode.PUSH_NOTIFICATION_NOT_SUPPORTED: "Push Notification is not supported",
+    A2AErrorCode.UNSUPPORTED_OPERATION: "This operation is not supported",
+    A2AErrorCode.CONTENT_TYPE_NOT_SUPPORTED: "Incompatible content types",
+    A2AErrorCode.INVALID_AGENT_RESPONSE: "Invalid agent response",
+    A2AErrorCode.UNSUPPORTED_VERSION: "Unsupported A2A version",
+    A2AErrorCode.UNSUPPORTED_EXTENSION: "Client does not support required extensions",
+    A2AErrorCode.AUTHENTICATION_REQUIRED: "Authentication required",
+    A2AErrorCode.AUTHORIZATION_FAILED: "Authorization failed",
+    A2AErrorCode.RATE_LIMIT_EXCEEDED: "Rate limit exceeded",
+    A2AErrorCode.TASK_TIMEOUT: "Task execution timed out",
+    A2AErrorCode.TRANSPORT_NEGOTIATION_FAILED: "Transport negotiation failed",
+    A2AErrorCode.CONTEXT_NOT_FOUND: "Context not found",
+    A2AErrorCode.SKILL_NOT_FOUND: "Skill not found",
+    A2AErrorCode.ARTIFACT_NOT_FOUND: "Artifact not found",
+}
+
+
+@dataclass
+class A2AError(Exception):
+    """Base exception for A2A protocol errors.
+
+    Attributes:
+        code: The A2A/JSON-RPC error code.
+        message: Human-readable error message.
+        data: Optional additional error data.
+    """
+
+    code: int
+    message: str | None = None
+    data: Any = None
+
+    def __post_init__(self) -> None:
+        if self.message is None:
+            self.message = ERROR_MESSAGES.get(self.code, "Unknown error")
+        super().__init__(self.message)
+
+    def to_dict(self) -> dict[str, Any]:
+        """Convert to JSON-RPC error object format."""
+        error: dict[str, Any] = {
+            "code": self.code,
+            "message": self.message,
+        }
+        if self.data is not None:
+            error["data"] = self.data
+        return error
+
+    def to_response(self, request_id: str | int | None = None) -> dict[str, Any]:
+        """Convert to full JSON-RPC error response."""
+        return {
+            "jsonrpc": "2.0",
+            "error": self.to_dict(),
+            "id": request_id,
+        }
+
+
+@dataclass
+class JSONParseError(A2AError):
+    """Invalid JSON was received."""
+
+    code: int = field(default=A2AErrorCode.JSON_PARSE_ERROR, init=False)
+
+
+@dataclass
+class InvalidRequestError(A2AError):
+    """The JSON sent is not a valid Request object."""
+
+    code: int = field(default=A2AErrorCode.INVALID_REQUEST, init=False)
+
+
+@dataclass
+class MethodNotFoundError(A2AError):
+    """The method does not exist / is not available."""
+
+    code: int = field(default=A2AErrorCode.METHOD_NOT_FOUND, init=False)
+    method: str | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.method:
+            self.message = f"Method not found: {self.method}"
+        super().__post_init__()
+
+
+@dataclass
+class InvalidParamsError(A2AError):
+    """Invalid method parameter(s)."""
+
+    code: int = field(default=A2AErrorCode.INVALID_PARAMS, init=False)
+    param: str | None = None
+    reason: str | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None:
+            if self.param and self.reason:
+                self.message = f"Invalid parameter '{self.param}': {self.reason}"
+            elif self.param:
+                self.message = f"Invalid parameter: {self.param}"
+        super().__post_init__()
+
+
+@dataclass
+class InternalError(A2AError):
+    """Internal JSON-RPC error."""
+
+    code: int = field(default=A2AErrorCode.INTERNAL_ERROR, init=False)
+
+
+@dataclass
+class TaskNotFoundError(A2AError):
+    """The specified task was not found."""
+
+    code: int = field(default=A2AErrorCode.TASK_NOT_FOUND, init=False)
+    task_id: str | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.task_id:
+            self.message = f"Task not found: {self.task_id}"
+        super().__post_init__()
+
+
+@dataclass
+class TaskNotCancelableError(A2AError):
+    """The task cannot be canceled."""
+
+    code: int = field(default=A2AErrorCode.TASK_NOT_CANCELABLE, init=False)
+    task_id: str | None = None
+    reason: str | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None:
+            if self.task_id and self.reason:
+                self.message = f"Task {self.task_id} cannot be canceled: {self.reason}"
+            elif self.task_id:
+                self.message = f"Task {self.task_id} cannot be canceled"
+        super().__post_init__()
+
+
+@dataclass
+class PushNotificationNotSupportedError(A2AError):
+    """Push notifications are not supported."""
+
+    code: int = field(default=A2AErrorCode.PUSH_NOTIFICATION_NOT_SUPPORTED, init=False)
+
+
+@dataclass
+class UnsupportedOperationError(A2AError):
+    """The requested operation is not supported."""
+
+    code: int = field(default=A2AErrorCode.UNSUPPORTED_OPERATION, init=False)
+    operation: str | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.operation:
+            self.message = f"Operation not supported: {self.operation}"
+        super().__post_init__()
+
+
+@dataclass
+class ContentTypeNotSupportedError(A2AError):
+    """Incompatible content types."""
+
+    code: int = field(default=A2AErrorCode.CONTENT_TYPE_NOT_SUPPORTED, init=False)
+    requested_types: list[str] | None = None
+    supported_types: list[str] | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.requested_types and self.supported_types:
+            self.message = (
+                f"Content type not supported. Requested: {self.requested_types}, "
+                f"Supported: {self.supported_types}"
+            )
+        super().__post_init__()
+
+
+@dataclass
+class InvalidAgentResponseError(A2AError):
+    """The agent produced an invalid response."""
+
+    code: int = field(default=A2AErrorCode.INVALID_AGENT_RESPONSE, init=False)
+
+
+@dataclass
+class UnsupportedVersionError(A2AError):
+    """The requested A2A version is not supported."""
+
+    code: int = field(default=A2AErrorCode.UNSUPPORTED_VERSION, init=False)
+    requested_version: str | None = None
+    supported_versions: list[str] | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.requested_version:
+            msg = f"Unsupported A2A version: {self.requested_version}"
+            if self.supported_versions:
+                msg += f". Supported versions: {', '.join(self.supported_versions)}"
+            self.message = msg
+        super().__post_init__()
+
+
+@dataclass
+class UnsupportedExtensionError(A2AError):
+    """Client does not support required extensions."""
+
+    code: int = field(default=A2AErrorCode.UNSUPPORTED_EXTENSION, init=False)
+    required_extensions: list[str] | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.required_extensions:
+            self.message = f"Client does not support required extensions: {', '.join(self.required_extensions)}"
+        super().__post_init__()
+
+
+@dataclass
+class AuthenticationRequiredError(A2AError):
+    """Authentication is required."""
+
+    code: int = field(default=A2AErrorCode.AUTHENTICATION_REQUIRED, init=False)
+
+
+@dataclass
+class AuthorizationFailedError(A2AError):
+    """Authorization check failed."""
+
+    code: int = field(default=A2AErrorCode.AUTHORIZATION_FAILED, init=False)
+    required_scope: str | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.required_scope:
+            self.message = (
+                f"Authorization failed. Required scope: {self.required_scope}"
+            )
+        super().__post_init__()
+
+
+@dataclass
+class RateLimitExceededError(A2AError):
+    """Rate limit exceeded."""
+
+    code: int = field(default=A2AErrorCode.RATE_LIMIT_EXCEEDED, init=False)
+    retry_after: int | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.retry_after:
+            self.message = (
+                f"Rate limit exceeded. Retry after {self.retry_after} seconds"
+            )
+        if self.retry_after:
+            self.data = {"retry_after": self.retry_after}
+        super().__post_init__()
+
+
+@dataclass
+class TaskTimeoutError(A2AError):
+    """Task execution timed out."""
+
+    code: int = field(default=A2AErrorCode.TASK_TIMEOUT, init=False)
+    task_id: str | None = None
+    timeout_seconds: float | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None:
+            if self.task_id and self.timeout_seconds:
+                self.message = (
+                    f"Task {self.task_id} timed out after {self.timeout_seconds}s"
+                )
+            elif self.task_id:
+                self.message = f"Task {self.task_id} timed out"
+        super().__post_init__()
+
+
+@dataclass
+class TransportNegotiationFailedError(A2AError):
+    """Failed to negotiate a compatible transport protocol."""
+
+    code: int = field(default=A2AErrorCode.TRANSPORT_NEGOTIATION_FAILED, init=False)
+    client_transports: list[str] | None = None
+    server_transports: list[str] | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.client_transports and self.server_transports:
+            self.message = (
+                f"Transport negotiation failed. Client: {self.client_transports}, "
+                f"Server: {self.server_transports}"
+            )
+        super().__post_init__()
+
+
+@dataclass
+class ContextNotFoundError(A2AError):
+    """The specified context was not found."""
+
+    code: int = field(default=A2AErrorCode.CONTEXT_NOT_FOUND, init=False)
+    context_id: str | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.context_id:
+            self.message = f"Context not found: {self.context_id}"
+        super().__post_init__()
+
+
+@dataclass
+class SkillNotFoundError(A2AError):
+    """The specified skill was not found."""
+
+    code: int = field(default=A2AErrorCode.SKILL_NOT_FOUND, init=False)
+    skill_id: str | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.skill_id:
+            self.message = f"Skill not found: {self.skill_id}"
+        super().__post_init__()
+
+
+@dataclass
+class ArtifactNotFoundError(A2AError):
+    """The specified artifact was not found."""
+
+    code: int = field(default=A2AErrorCode.ARTIFACT_NOT_FOUND, init=False)
+    artifact_id: str | None = None
+
+    def __post_init__(self) -> None:
+        if self.message is None and self.artifact_id:
+            self.message = f"Artifact not found: {self.artifact_id}"
+        super().__post_init__()
+
+
+def create_error_response(
+    code: int | A2AErrorCode,
+    message: str | None = None,
+    data: Any = None,
+    request_id: str | int | None = None,
+) -> dict[str, Any]:
+    """Create a JSON-RPC error response.
+
+    Args:
+        code: Error code (A2AErrorCode or int).
+        message: Optional error message (uses default if not provided).
+        data: Optional additional error data.
+        request_id: Request ID for correlation.
+
+    Returns:
+        Dict in JSON-RPC error response format.
+    """
+    error = A2AError(code=int(code), message=message, data=data)
+    return error.to_response(request_id)
+
+
+def is_retryable_error(code: int) -> bool:
+    """Check if an error is potentially retryable.
+
+    Args:
+        code: Error code to check.
+
+    Returns:
+        True if the error might be resolved by retrying.
+    """
+    retryable_codes = {
+        A2AErrorCode.INTERNAL_ERROR,
+        A2AErrorCode.RATE_LIMIT_EXCEEDED,
+        A2AErrorCode.TASK_TIMEOUT,
+    }
+    return code in retryable_codes
+
+
+def is_client_error(code: int) -> bool:
+    """Check if an error is a client-side error.
+
+    Args:
+        code: Error code to check.
+
+    Returns:
+        True if the error is due to client request issues.
+    """
+    client_error_codes = {
+        A2AErrorCode.JSON_PARSE_ERROR,
+        A2AErrorCode.INVALID_REQUEST,
+        A2AErrorCode.METHOD_NOT_FOUND,
+        A2AErrorCode.INVALID_PARAMS,
+        A2AErrorCode.TASK_NOT_FOUND,
+        A2AErrorCode.CONTENT_TYPE_NOT_SUPPORTED,
+        A2AErrorCode.UNSUPPORTED_VERSION,
+        A2AErrorCode.UNSUPPORTED_EXTENSION,
+        A2AErrorCode.CONTEXT_NOT_FOUND,
+        A2AErrorCode.SKILL_NOT_FOUND,
+        A2AErrorCode.ARTIFACT_NOT_FOUND,
+    }
+    return code in client_error_codes

lib/crewai/src/crewai/a2a/extensions/__init__.py

@@ -1,4 +1,37 @@
 """A2A Protocol Extensions for CrewAI.
 
 This module contains extensions to the A2A (Agent-to-Agent) protocol.
+
+**Client-side extensions** (A2AExtension) allow customizing how the A2A wrapper
+processes requests and responses during delegation to remote agents. These provide
+hooks for tool injection, prompt augmentation, and response processing.
+
+**Server-side extensions** (ServerExtension) allow agents to offer additional
+functionality beyond the core A2A specification. Clients activate extensions
+via the X-A2A-Extensions header.
+
+See: https://a2a-protocol.org/latest/topics/extensions/
 """
+
+from crewai.a2a.extensions.base import (
+    A2AExtension,
+    ConversationState,
+    ExtensionRegistry,
+    ValidatedA2AExtension,
+)
+from crewai.a2a.extensions.server import (
+    ExtensionContext,
+    ServerExtension,
+    ServerExtensionRegistry,
+)
+
+
+__all__ = [
+    "A2AExtension",
+    "ConversationState",
+    "ExtensionContext",
+    "ExtensionRegistry",
+    "ServerExtension",
+    "ServerExtensionRegistry",
+    "ValidatedA2AExtension",
+]

lib/crewai/src/crewai/a2a/extensions/base.py

@@ -1,14 +1,20 @@
-"""Base extension interface for A2A wrapper integrations.
+"""Base extension interface for CrewAI A2A wrapper processing hooks.
 
-This module defines the protocol for extending A2A wrapper functionality
-with custom logic for conversation processing, prompt augmentation, and
-agent response handling.
+This module defines the protocol for extending CrewAI's A2A wrapper functionality
+with custom logic for tool injection, prompt augmentation, and response processing.
+
+Note: These are CrewAI-specific processing hooks, NOT A2A protocol extensions.
+A2A protocol extensions are capability declarations using AgentExtension objects
+in AgentCard.capabilities.extensions, activated via the A2A-Extensions HTTP header.
+See: https://a2a-protocol.org/latest/topics/extensions/
 """
 
 from __future__ import annotations
 
 from collections.abc import Sequence
-from typing import TYPE_CHECKING, Any, Protocol
+from typing import TYPE_CHECKING, Annotated, Any, Protocol, runtime_checkable
+
+from pydantic import BeforeValidator
 
 
 if TYPE_CHECKING:
@@ -17,6 +23,20 @@ if TYPE_CHECKING:
     from crewai.agent.core import Agent
 
 
+def _validate_a2a_extension(v: Any) -> Any:
+    """Validate that value implements A2AExtension protocol."""
+    if not isinstance(v, A2AExtension):
+        raise ValueError(
+            f"Value must implement A2AExtension protocol. "
+            f"Got {type(v).__name__} which is missing required methods."
+        )
+    return v
+
+
+ValidatedA2AExtension = Annotated[Any, BeforeValidator(_validate_a2a_extension)]
+
+
+@runtime_checkable
 class ConversationState(Protocol):
     """Protocol for extension-specific conversation state.
 
@@ -33,11 +53,36 @@ class ConversationState(Protocol):
         ...
 
 
+@runtime_checkable
 class A2AExtension(Protocol):
     """Protocol for A2A wrapper extensions.
 
     Extensions can implement this protocol to inject custom logic into
     the A2A conversation flow at various integration points.
+
+    Example:
+        class MyExtension:
+            def inject_tools(self, agent: Agent) -> None:
+                # Add custom tools to the agent
+                pass
+
+            def extract_state_from_history(
+                self, conversation_history: Sequence[Message]
+            ) -> ConversationState | None:
+                # Extract state from conversation
+                return None
+
+            def augment_prompt(
+                self, base_prompt: str, conversation_state: ConversationState | None
+            ) -> str:
+                # Add custom instructions
+                return base_prompt
+
+            def process_response(
+                self, agent_response: Any, conversation_state: ConversationState | None
+            ) -> Any:
+                # Modify response if needed
+                return agent_response
     """
 
     def inject_tools(self, agent: Agent) -> None:

lib/crewai/src/crewai/a2a/extensions/registry.py

@@ -1,34 +1,170 @@
-"""Extension registry factory for A2A configurations.
+"""A2A Protocol extension utilities.
 
-This module provides utilities for creating extension registries from A2A configurations.
+This module provides utilities for working with A2A protocol extensions as
+defined in the A2A specification. Extensions are capability declarations in
+AgentCard.capabilities.extensions using AgentExtension objects, activated
+via the X-A2A-Extensions HTTP header.
+
+See: https://a2a-protocol.org/latest/topics/extensions/
 """
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING
+from typing import Any
 
+from a2a.client.middleware import ClientCallContext, ClientCallInterceptor
+from a2a.extensions.common import (
+    HTTP_EXTENSION_HEADER,
+)
+from a2a.types import AgentCard, AgentExtension
+
+from crewai.a2a.config import A2AClientConfig, A2AConfig
 from crewai.a2a.extensions.base import ExtensionRegistry
 
 
-if TYPE_CHECKING:
-    from crewai.a2a.config import A2AConfig
+def get_extensions_from_config(
+    a2a_config: list[A2AConfig | A2AClientConfig] | A2AConfig | A2AClientConfig,
+) -> list[str]:
+    """Extract extension URIs from A2A configuration.
+
+    Args:
+        a2a_config: A2A configuration (single or list).
+
+    Returns:
+        Deduplicated list of extension URIs from all configs.
+    """
+    configs = a2a_config if isinstance(a2a_config, list) else [a2a_config]
+    seen: set[str] = set()
+    result: list[str] = []
+
+    for config in configs:
+        if not isinstance(config, A2AClientConfig):
+            continue
+        for uri in config.extensions:
+            if uri not in seen:
+                seen.add(uri)
+                result.append(uri)
+
+    return result
+
+
+class ExtensionsMiddleware(ClientCallInterceptor):
+    """Middleware to add X-A2A-Extensions header to requests.
+
+    This middleware adds the extensions header to all outgoing requests,
+    declaring which A2A protocol extensions the client supports.
+    """
+
+    def __init__(self, extensions: list[str]) -> None:
+        """Initialize with extension URIs.
+
+        Args:
+            extensions: List of extension URIs the client supports.
+        """
+        self._extensions = extensions
+
+    async def intercept(
+        self,
+        method_name: str,
+        request_payload: dict[str, Any],
+        http_kwargs: dict[str, Any],
+        agent_card: AgentCard | None,
+        context: ClientCallContext | None,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        """Add extensions header to the request.
+
+        Args:
+            method_name: The A2A method being called.
+            request_payload: The JSON-RPC request payload.
+            http_kwargs: HTTP request kwargs (headers, etc).
+            agent_card: The target agent's card.
+            context: Optional call context.
+
+        Returns:
+            Tuple of (request_payload, modified_http_kwargs).
+        """
+        if self._extensions:
+            headers = http_kwargs.setdefault("headers", {})
+            headers[HTTP_EXTENSION_HEADER] = ",".join(self._extensions)
+        return request_payload, http_kwargs
+
+
+def validate_required_extensions(
+    agent_card: AgentCard,
+    client_extensions: list[str] | None,
+) -> list[AgentExtension]:
+    """Validate that client supports all required extensions from agent.
+
+    Args:
+        agent_card: The agent's card with declared extensions.
+        client_extensions: Extension URIs the client supports.
+
+    Returns:
+        List of unsupported required extensions.
+
+    Raises:
+        None - returns list of unsupported extensions for caller to handle.
+    """
+    unsupported: list[AgentExtension] = []
+    client_set = set(client_extensions or [])
+
+    if not agent_card.capabilities or not agent_card.capabilities.extensions:
+        return unsupported
+
+    unsupported.extend(
+        ext
+        for ext in agent_card.capabilities.extensions
+        if ext.required and ext.uri not in client_set
+    )
+
+    return unsupported
 
 
 def create_extension_registry_from_config(
-    a2a_config: list[A2AConfig] | A2AConfig,
+    a2a_config: list[A2AConfig | A2AClientConfig] | A2AConfig | A2AClientConfig,
 ) -> ExtensionRegistry:
-    """Create an extension registry from A2A configuration.
+    """Create an extension registry from A2A client configuration.
+
+    Extracts client_extensions from each A2AClientConfig and registers them
+    with the ExtensionRegistry. These extensions provide CrewAI-specific
+    processing hooks (tool injection, prompt augmentation, response processing).
+
+    Note: A2A protocol extensions (URI strings sent via X-A2A-Extensions header)
+    are handled separately via get_extensions_from_config() and ExtensionsMiddleware.
 
     Args:
-        a2a_config: A2A configuration (single or list)
+        a2a_config: A2A configuration (single or list).
 
     Returns:
-        Configured extension registry with all applicable extensions
+        Extension registry with all client_extensions registered.
+
+    Example:
+        class LoggingExtension:
+            def inject_tools(self, agent): pass
+            def extract_state_from_history(self, history): return None
+            def augment_prompt(self, prompt, state): return prompt
+            def process_response(self, response, state):
+                print(f"Response: {response}")
+                return response
+
+        config = A2AClientConfig(
+            endpoint="https://agent.example.com",
+            client_extensions=[LoggingExtension()],
+        )
+        registry = create_extension_registry_from_config(config)
     """
     registry = ExtensionRegistry()
     configs = a2a_config if isinstance(a2a_config, list) else [a2a_config]
 
-    for _ in configs:
-        pass
+    seen: set[int] = set()
+
+    for config in configs:
+        if isinstance(config, (A2AConfig, A2AClientConfig)):
+            client_exts = getattr(config, "client_extensions", [])
+            for extension in client_exts:
+                ext_id = id(extension)
+                if ext_id not in seen:
+                    seen.add(ext_id)
+                    registry.register(extension)
 
     return registry

lib/crewai/src/crewai/a2a/extensions/server.py

@@ -0,0 +1,305 @@
+"""A2A protocol server extensions for CrewAI agents.
+
+This module provides the base class and context for implementing A2A protocol
+extensions on the server side. Extensions allow agents to offer additional
+functionality beyond the core A2A specification.
+
+See: https://a2a-protocol.org/latest/topics/extensions/
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass, field
+import logging
+from typing import TYPE_CHECKING, Annotated, Any
+
+from a2a.types import AgentExtension
+from pydantic_core import CoreSchema, core_schema
+
+
+if TYPE_CHECKING:
+    from a2a.server.context import ServerCallContext
+    from pydantic import GetCoreSchemaHandler
+
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class ExtensionContext:
+    """Context passed to extension hooks during request processing.
+
+    Provides access to request metadata, client extensions, and shared state
+    that extensions can read from and write to.
+
+    Attributes:
+        metadata: Request metadata dict, includes extension-namespaced keys.
+        client_extensions: Set of extension URIs the client declared support for.
+        state: Mutable dict for extensions to share data during request lifecycle.
+        server_context: The underlying A2A server call context.
+    """
+
+    metadata: dict[str, Any]
+    client_extensions: set[str]
+    state: dict[str, Any] = field(default_factory=dict)
+    server_context: ServerCallContext | None = None
+
+    def get_extension_metadata(self, uri: str, key: str) -> Any | None:
+        """Get extension-specific metadata value.
+
+        Extension metadata uses namespaced keys in the format:
+        "{extension_uri}/{key}"
+
+        Args:
+            uri: The extension URI.
+            key: The metadata key within the extension namespace.
+
+        Returns:
+            The metadata value, or None if not present.
+        """
+        full_key = f"{uri}/{key}"
+        return self.metadata.get(full_key)
+
+    def set_extension_metadata(self, uri: str, key: str, value: Any) -> None:
+        """Set extension-specific metadata value.
+
+        Args:
+            uri: The extension URI.
+            key: The metadata key within the extension namespace.
+            value: The value to set.
+        """
+        full_key = f"{uri}/{key}"
+        self.metadata[full_key] = value
+
+
+class ServerExtension(ABC):
+    """Base class for A2A protocol server extensions.
+
+    Subclass this to create custom extensions that modify agent behavior
+    when clients activate them. Extensions are identified by URI and can
+    be marked as required.
+
+    Example:
+        class SamplingExtension(ServerExtension):
+            uri = "urn:crewai:ext:sampling/v1"
+            required = True
+
+            def __init__(self, max_tokens: int = 4096):
+                self.max_tokens = max_tokens
+
+            @property
+            def params(self) -> dict[str, Any]:
+                return {"max_tokens": self.max_tokens}
+
+            async def on_request(self, context: ExtensionContext) -> None:
+                limit = context.get_extension_metadata(self.uri, "limit")
+                if limit:
+                    context.state["token_limit"] = int(limit)
+
+            async def on_response(self, context: ExtensionContext, result: Any) -> Any:
+                return result
+    """
+
+    uri: Annotated[str, "Extension URI identifier. Must be unique."]
+    required: Annotated[bool, "Whether clients must support this extension."] = False
+    description: Annotated[
+        str | None, "Human-readable description of the extension."
+    ] = None
+
+    @classmethod
+    def __get_pydantic_core_schema__(
+        cls,
+        _source_type: Any,
+        _handler: GetCoreSchemaHandler,
+    ) -> CoreSchema:
+        """Tell Pydantic how to validate ServerExtension instances."""
+        return core_schema.is_instance_schema(cls)
+
+    @property
+    def params(self) -> dict[str, Any] | None:
+        """Extension parameters to advertise in AgentCard.
+
+        Override this property to expose configuration that clients can read.
+
+        Returns:
+            Dict of parameter names to values, or None.
+        """
+        return None
+
+    def agent_extension(self) -> AgentExtension:
+        """Generate the AgentExtension object for the AgentCard.
+
+        Returns:
+            AgentExtension with this extension's URI, required flag, and params.
+        """
+        return AgentExtension(
+            uri=self.uri,
+            required=self.required if self.required else None,
+            description=self.description,
+            params=self.params,
+        )
+
+    def is_active(self, context: ExtensionContext) -> bool:
+        """Check if this extension is active for the current request.
+
+        An extension is active if the client declared support for it.
+
+        Args:
+            context: The extension context for the current request.
+
+        Returns:
+            True if the client supports this extension.
+        """
+        return self.uri in context.client_extensions
+
+    @abstractmethod
+    async def on_request(self, context: ExtensionContext) -> None:
+        """Called before agent execution if extension is active.
+
+        Use this hook to:
+        - Read extension-specific metadata from the request
+        - Set up state for the execution
+        - Modify execution parameters via context.state
+
+        Args:
+            context: The extension context with request metadata and state.
+        """
+        ...
+
+    @abstractmethod
+    async def on_response(self, context: ExtensionContext, result: Any) -> Any:
+        """Called after agent execution if extension is active.
+
+        Use this hook to:
+        - Modify or enhance the result
+        - Add extension-specific metadata to the response
+        - Clean up any resources
+
+        Args:
+            context: The extension context with request metadata and state.
+            result: The agent execution result.
+
+        Returns:
+            The result, potentially modified.
+        """
+        ...
+
+
+class ServerExtensionRegistry:
+    """Registry for managing server-side A2A protocol extensions.
+
+    Collects extensions and provides methods to generate AgentCapabilities
+    and invoke extension hooks during request processing.
+    """
+
+    def __init__(self, extensions: list[ServerExtension] | None = None) -> None:
+        """Initialize the registry with optional extensions.
+
+        Args:
+            extensions: Initial list of extensions to register.
+        """
+        self._extensions: list[ServerExtension] = list(extensions) if extensions else []
+        self._by_uri: dict[str, ServerExtension] = {
+            ext.uri: ext for ext in self._extensions
+        }
+
+    def register(self, extension: ServerExtension) -> None:
+        """Register an extension.
+
+        Args:
+            extension: The extension to register.
+
+        Raises:
+            ValueError: If an extension with the same URI is already registered.
+        """
+        if extension.uri in self._by_uri:
+            raise ValueError(f"Extension already registered: {extension.uri}")
+        self._extensions.append(extension)
+        self._by_uri[extension.uri] = extension
+
+    def get_agent_extensions(self) -> list[AgentExtension]:
+        """Get AgentExtension objects for all registered extensions.
+
+        Returns:
+            List of AgentExtension objects for the AgentCard.
+        """
+        return [ext.agent_extension() for ext in self._extensions]
+
+    def get_extension(self, uri: str) -> ServerExtension | None:
+        """Get an extension by URI.
+
+        Args:
+            uri: The extension URI.
+
+        Returns:
+            The extension, or None if not found.
+        """
+        return self._by_uri.get(uri)
+
+    @staticmethod
+    def create_context(
+        metadata: dict[str, Any],
+        client_extensions: set[str],
+        server_context: ServerCallContext | None = None,
+    ) -> ExtensionContext:
+        """Create an ExtensionContext for a request.
+
+        Args:
+            metadata: Request metadata dict.
+            client_extensions: Set of extension URIs from client.
+            server_context: Optional server call context.
+
+        Returns:
+            ExtensionContext for use in hooks.
+        """
+        return ExtensionContext(
+            metadata=metadata,
+            client_extensions=client_extensions,
+            server_context=server_context,
+        )
+
+    async def invoke_on_request(self, context: ExtensionContext) -> None:
+        """Invoke on_request hooks for all active extensions.
+
+        Tracks activated extensions and isolates errors from individual hooks.
+
+        Args:
+            context: The extension context for the request.
+        """
+        for extension in self._extensions:
+            if extension.is_active(context):
+                try:
+                    await extension.on_request(context)
+                    if context.server_context is not None:
+                        context.server_context.activated_extensions.add(extension.uri)
+                except Exception:
+                    logger.exception(
+                        "Extension on_request hook failed",
+                        extra={"extension": extension.uri},
+                    )
+
+    async def invoke_on_response(self, context: ExtensionContext, result: Any) -> Any:
+        """Invoke on_response hooks for all active extensions.
+
+        Isolates errors from individual hooks to prevent one failing extension
+        from breaking the entire response.
+
+        Args:
+            context: The extension context for the request.
+            result: The agent execution result.
+
+        Returns:
+            The result after all extensions have processed it.
+        """
+        processed = result
+        for extension in self._extensions:
+            if extension.is_active(context):
+                try:
+                    processed = await extension.on_response(context, processed)
+                except Exception:
+                    logger.exception(
+                        "Extension on_response hook failed",
+                        extra={"extension": extension.uri},
+                    )
+        return processed

lib/crewai/src/crewai/a2a/task_helpers.py

@@ -51,6 +51,13 @@ ACTIONABLE_STATES: frozenset[TaskState] = frozenset(
     }
 )
 
+PENDING_STATES: frozenset[TaskState] = frozenset(
+    {
+        TaskState.submitted,
+        TaskState.working,
+    }
+)
+
 
 class TaskStateResult(TypedDict):
     """Result dictionary from processing A2A task state."""
@@ -272,6 +279,9 @@ def process_task_state(
             history=new_messages,
         )
 
+    if a2a_task.status.state in PENDING_STATES:
+        return None
+
     return None
 
 

lib/crewai/src/crewai/a2a/templates.py

@@ -38,3 +38,18 @@ You MUST now:
 DO NOT send another request - the task is already done.
 </REMOTE_AGENT_STATUS>
 """
+
+REMOTE_AGENT_RESPONSE_NOTICE: Final[str] = """
+<REMOTE_AGENT_STATUS>
+STATUS: RESPONSE_RECEIVED
+The remote agent has responded. Their response is in the conversation history above.
+
+You MUST now:
+1. Set is_a2a=false (the remote task is complete and cannot receive more messages)
+2. Provide YOUR OWN response to the original task based on the information received
+
+IMPORTANT: Your response should be addressed to the USER who gave you the original task.
+Report what the remote agent told you in THIRD PERSON (e.g., "The remote agent said..." or "I learned that...").
+Do NOT address the remote agent directly or use "you" to refer to them.
+</REMOTE_AGENT_STATUS>
+"""

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

@@ -36,6 +36,17 @@ except ImportError:
 
 
 TransportType = Literal["JSONRPC", "GRPC", "HTTP+JSON"]
+ProtocolVersion = Literal[
+    "0.2.0",
+    "0.2.1",
+    "0.2.2",
+    "0.2.3",
+    "0.2.4",
+    "0.2.5",
+    "0.2.6",
+    "0.3.0",
+    "0.4.0",
+]
 
 http_url_adapter: TypeAdapter[HttpUrl] = TypeAdapter(HttpUrl)
 

lib/crewai/src/crewai/a2a/updates/base.py

@@ -2,12 +2,28 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any, Protocol, TypedDict
+from typing import TYPE_CHECKING, Any, NamedTuple, Protocol, TypedDict
 
 from pydantic import GetCoreSchemaHandler
 from pydantic_core import CoreSchema, core_schema
 
 
+class CommonParams(NamedTuple):
+    """Common parameters shared across all update handlers.
+
+    Groups the frequently-passed parameters to reduce duplication.
+    """
+
+    turn_number: int
+    is_multiturn: bool
+    agent_role: str | None
+    endpoint: str
+    a2a_agent_name: str | None
+    context_id: str | None
+    from_task: Any
+    from_agent: Any
+
+
 if TYPE_CHECKING:
     from a2a.client import Client
     from a2a.types import AgentCard, Message, Task
@@ -63,8 +79,8 @@ class PushNotificationResultStore(Protocol):
     @classmethod
     def __get_pydantic_core_schema__(
         cls,
-        source_type: Any,
-        handler: GetCoreSchemaHandler,
+        _source_type: Any,
+        _handler: GetCoreSchemaHandler,
     ) -> CoreSchema:
         return core_schema.any_schema()
 
@@ -130,3 +146,31 @@ class UpdateHandler(Protocol):
             Result dictionary with status, result/error, and history.
         """
         ...
+
+
+def extract_common_params(kwargs: BaseHandlerKwargs) -> CommonParams:
+    """Extract common parameters from handler kwargs.
+
+    Args:
+        kwargs: Handler kwargs dict.
+
+    Returns:
+        CommonParams with extracted values.
+
+    Raises:
+        ValueError: If endpoint is not provided.
+    """
+    endpoint = kwargs.get("endpoint")
+    if endpoint is None:
+        raise ValueError("endpoint is required for update handlers")
+
+    return CommonParams(
+        turn_number=kwargs.get("turn_number", 0),
+        is_multiturn=kwargs.get("is_multiturn", False),
+        agent_role=kwargs.get("agent_role"),
+        endpoint=endpoint,
+        a2a_agent_name=kwargs.get("a2a_agent_name"),
+        context_id=kwargs.get("context_id"),
+        from_task=kwargs.get("from_task"),
+        from_agent=kwargs.get("from_agent"),
+    )

lib/crewai/src/crewai/a2a/updates/polling/handler.py

@@ -94,7 +94,7 @@ async def _poll_task_until_complete(
             A2APollingStatusEvent(
                 task_id=task_id,
                 context_id=effective_context_id,
-                state=str(task.status.state.value) if task.status.state else "unknown",
+                state=str(task.status.state.value),
                 elapsed_seconds=elapsed,
                 poll_count=poll_count,
                 endpoint=endpoint,
@@ -325,7 +325,7 @@ class PollingHandler:
             crewai_event_bus.emit(
                 agent_branch,
                 A2AConnectionErrorEvent(
-                    endpoint=endpoint or "",
+                    endpoint=endpoint,
                     error=str(e),
                     error_type="unexpected_error",
                     a2a_agent_name=a2a_agent_name,

lib/crewai/src/crewai/a2a/updates/push_notifications/config.py

@@ -2,10 +2,30 @@
 
 from __future__ import annotations
 
+from typing import Annotated
+
 from a2a.types import PushNotificationAuthenticationInfo
-from pydantic import AnyHttpUrl, BaseModel, Field
+from pydantic import AnyHttpUrl, BaseModel, BeforeValidator, Field
 
 from crewai.a2a.updates.base import PushNotificationResultStore
+from crewai.a2a.updates.push_notifications.signature import WebhookSignatureConfig
+
+
+def _coerce_signature(
+    value: str | WebhookSignatureConfig | None,
+) -> WebhookSignatureConfig | None:
+    """Convert string secret to WebhookSignatureConfig."""
+    if value is None:
+        return None
+    if isinstance(value, str):
+        return WebhookSignatureConfig.hmac_sha256(secret=value)
+    return value
+
+
+SignatureInput = Annotated[
+    WebhookSignatureConfig | None,
+    BeforeValidator(_coerce_signature),
+]
 
 
 class PushNotificationConfig(BaseModel):
@@ -19,6 +39,8 @@ class PushNotificationConfig(BaseModel):
         timeout: Max seconds to wait for task completion.
         interval: Seconds between result polling attempts.
         result_store: Store for receiving push notification results.
+        signature: HMAC signature config. Pass a string (secret) for defaults,
+            or WebhookSignatureConfig for custom settings.
     """
 
     url: AnyHttpUrl = Field(description="Callback URL for push notifications")
@@ -36,3 +58,8 @@ class PushNotificationConfig(BaseModel):
     result_store: PushNotificationResultStore | None = Field(
         default=None, description="Result store for push notification handling"
     )
+    signature: SignatureInput = Field(
+        default=None,
+        description="HMAC signature config. Pass a string (secret) for simple usage, "
+        "or WebhookSignatureConfig for custom headers/tolerance.",
+    )

lib/crewai/src/crewai/a2a/updates/push_notifications/handler.py

@@ -24,8 +24,10 @@ from crewai.a2a.task_helpers import (
     send_message_and_get_task_id,
 )
 from crewai.a2a.updates.base import (
+    CommonParams,
     PushNotificationHandlerKwargs,
     PushNotificationResultStore,
+    extract_common_params,
 )
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.a2a_events import (
@@ -39,10 +41,81 @@ from crewai.events.types.a2a_events import (
 if TYPE_CHECKING:
     from a2a.types import Task as A2ATask
 
-
 logger = logging.getLogger(__name__)
 
 
+def _handle_push_error(
+    error: Exception,
+    error_msg: str,
+    error_type: str,
+    new_messages: list[Message],
+    agent_branch: Any | None,
+    params: CommonParams,
+    task_id: str | None,
+    status_code: int | None = None,
+) -> TaskStateResult:
+    """Handle push notification errors with consistent event emission.
+
+    Args:
+        error: The exception that occurred.
+        error_msg: Formatted error message for the result.
+        error_type: Type of error for the event.
+        new_messages: List to append error message to.
+        agent_branch: Agent tree branch for events.
+        params: Common handler parameters.
+        task_id: A2A task ID.
+        status_code: HTTP status code if applicable.
+
+    Returns:
+        TaskStateResult with failed status.
+    """
+    error_message = Message(
+        role=Role.agent,
+        message_id=str(uuid.uuid4()),
+        parts=[Part(root=TextPart(text=error_msg))],
+        context_id=params.context_id,
+        task_id=task_id,
+    )
+    new_messages.append(error_message)
+
+    crewai_event_bus.emit(
+        agent_branch,
+        A2AConnectionErrorEvent(
+            endpoint=params.endpoint,
+            error=str(error),
+            error_type=error_type,
+            status_code=status_code,
+            a2a_agent_name=params.a2a_agent_name,
+            operation="push_notification",
+            context_id=params.context_id,
+            task_id=task_id,
+            from_task=params.from_task,
+            from_agent=params.from_agent,
+        ),
+    )
+    crewai_event_bus.emit(
+        agent_branch,
+        A2AResponseReceivedEvent(
+            response=error_msg,
+            turn_number=params.turn_number,
+            context_id=params.context_id,
+            is_multiturn=params.is_multiturn,
+            status="failed",
+            final=True,
+            agent_role=params.agent_role,
+            endpoint=params.endpoint,
+            a2a_agent_name=params.a2a_agent_name,
+            from_task=params.from_task,
+            from_agent=params.from_agent,
+        ),
+    )
+    return TaskStateResult(
+        status=TaskState.failed,
+        error=error_msg,
+        history=new_messages,
+    )
+
+
 async def _wait_for_push_result(
     task_id: str,
     result_store: PushNotificationResultStore,
@@ -126,15 +199,8 @@ class PushNotificationHandler:
         polling_timeout = kwargs.get("polling_timeout", 300.0)
         polling_interval = kwargs.get("polling_interval", 2.0)
         agent_branch = kwargs.get("agent_branch")
-        turn_number = kwargs.get("turn_number", 0)
-        is_multiturn = kwargs.get("is_multiturn", False)
-        agent_role = kwargs.get("agent_role")
-        context_id = kwargs.get("context_id")
         task_id = kwargs.get("task_id")
-        endpoint = kwargs.get("endpoint")
-        a2a_agent_name = kwargs.get("a2a_agent_name")
-        from_task = kwargs.get("from_task")
-        from_agent = kwargs.get("from_agent")
+        params = extract_common_params(kwargs)
 
         if config is None:
             error_msg = (
@@ -143,15 +209,15 @@ class PushNotificationHandler:
             crewai_event_bus.emit(
                 agent_branch,
                 A2AConnectionErrorEvent(
-                    endpoint=endpoint or "",
+                    endpoint=params.endpoint,
                     error=error_msg,
                     error_type="configuration_error",
-                    a2a_agent_name=a2a_agent_name,
+                    a2a_agent_name=params.a2a_agent_name,
                     operation="push_notification",
-                    context_id=context_id,
+                    context_id=params.context_id,
                     task_id=task_id,
-                    from_task=from_task,
-                    from_agent=from_agent,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
                 ),
             )
             return TaskStateResult(
@@ -167,15 +233,15 @@ class PushNotificationHandler:
             crewai_event_bus.emit(
                 agent_branch,
                 A2AConnectionErrorEvent(
-                    endpoint=endpoint or "",
+                    endpoint=params.endpoint,
                     error=error_msg,
                     error_type="configuration_error",
-                    a2a_agent_name=a2a_agent_name,
+                    a2a_agent_name=params.a2a_agent_name,
                     operation="push_notification",
-                    context_id=context_id,
+                    context_id=params.context_id,
                     task_id=task_id,
-                    from_task=from_task,
-                    from_agent=from_agent,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
                 ),
             )
             return TaskStateResult(
@@ -189,14 +255,14 @@ class PushNotificationHandler:
                 event_stream=client.send_message(message),
                 new_messages=new_messages,
                 agent_card=agent_card,
-                turn_number=turn_number,
-                is_multiturn=is_multiturn,
-                agent_role=agent_role,
-                from_task=from_task,
-                from_agent=from_agent,
-                endpoint=endpoint,
-                a2a_agent_name=a2a_agent_name,
-                context_id=context_id,
+                turn_number=params.turn_number,
+                is_multiturn=params.is_multiturn,
+                agent_role=params.agent_role,
+                from_task=params.from_task,
+                from_agent=params.from_agent,
+                endpoint=params.endpoint,
+                a2a_agent_name=params.a2a_agent_name,
+                context_id=params.context_id,
             )
 
             if not isinstance(result_or_task_id, str):
@@ -208,12 +274,12 @@ class PushNotificationHandler:
                 agent_branch,
                 A2APushNotificationRegisteredEvent(
                     task_id=task_id,
-                    context_id=context_id,
+                    context_id=params.context_id,
                     callback_url=str(config.url),
-                    endpoint=endpoint,
-                    a2a_agent_name=a2a_agent_name,
-                    from_task=from_task,
-                    from_agent=from_agent,
+                    endpoint=params.endpoint,
+                    a2a_agent_name=params.a2a_agent_name,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
                 ),
             )
 
@@ -229,11 +295,11 @@ class PushNotificationHandler:
                 timeout=polling_timeout,
                 poll_interval=polling_interval,
                 agent_branch=agent_branch,
-                from_task=from_task,
-                from_agent=from_agent,
-                context_id=context_id,
-                endpoint=endpoint,
-                a2a_agent_name=a2a_agent_name,
+                from_task=params.from_task,
+                from_agent=params.from_agent,
+                context_id=params.context_id,
+                endpoint=params.endpoint,
+                a2a_agent_name=params.a2a_agent_name,
             )
 
             if final_task is None:
@@ -247,13 +313,13 @@ class PushNotificationHandler:
                 a2a_task=final_task,
                 new_messages=new_messages,
                 agent_card=agent_card,
-                turn_number=turn_number,
-                is_multiturn=is_multiturn,
-                agent_role=agent_role,
-                endpoint=endpoint,
-                a2a_agent_name=a2a_agent_name,
-                from_task=from_task,
-                from_agent=from_agent,
+                turn_number=params.turn_number,
+                is_multiturn=params.is_multiturn,
+                agent_role=params.agent_role,
+                endpoint=params.endpoint,
+                a2a_agent_name=params.a2a_agent_name,
+                from_task=params.from_task,
+                from_agent=params.from_agent,
             )
             if result:
                 return result
@@ -265,98 +331,24 @@ class PushNotificationHandler:
             )
 
         except A2AClientHTTPError as e:
-            error_msg = f"HTTP Error {e.status_code}: {e!s}"
-
-            error_message = Message(
-                role=Role.agent,
-                message_id=str(uuid.uuid4()),
-                parts=[Part(root=TextPart(text=error_msg))],
-                context_id=context_id,
+            return _handle_push_error(
+                error=e,
+                error_msg=f"HTTP Error {e.status_code}: {e!s}",
+                error_type="http_error",
+                new_messages=new_messages,
+                agent_branch=agent_branch,
+                params=params,
                 task_id=task_id,
-            )
-            new_messages.append(error_message)
-
-            crewai_event_bus.emit(
-                agent_branch,
-                A2AConnectionErrorEvent(
-                    endpoint=endpoint or "",
-                    error=str(e),
-                    error_type="http_error",
-                    status_code=e.status_code,
-                    a2a_agent_name=a2a_agent_name,
-                    operation="push_notification",
-                    context_id=context_id,
-                    task_id=task_id,
-                    from_task=from_task,
-                    from_agent=from_agent,
-                ),
-            )
-            crewai_event_bus.emit(
-                agent_branch,
-                A2AResponseReceivedEvent(
-                    response=error_msg,
-                    turn_number=turn_number,
-                    context_id=context_id,
-                    is_multiturn=is_multiturn,
-                    status="failed",
-                    final=True,
-                    agent_role=agent_role,
-                    endpoint=endpoint,
-                    a2a_agent_name=a2a_agent_name,
-                    from_task=from_task,
-                    from_agent=from_agent,
-                ),
-            )
-            return TaskStateResult(
-                status=TaskState.failed,
-                error=error_msg,
-                history=new_messages,
+                status_code=e.status_code,
             )
 
         except Exception as e:
-            error_msg = f"Unexpected error during push notification: {e!s}"
-
-            error_message = Message(
-                role=Role.agent,
-                message_id=str(uuid.uuid4()),
-                parts=[Part(root=TextPart(text=error_msg))],
-                context_id=context_id,
+            return _handle_push_error(
+                error=e,
+                error_msg=f"Unexpected error during push notification: {e!s}",
+                error_type="unexpected_error",
+                new_messages=new_messages,
+                agent_branch=agent_branch,
+                params=params,
                 task_id=task_id,
             )
-            new_messages.append(error_message)
-
-            crewai_event_bus.emit(
-                agent_branch,
-                A2AConnectionErrorEvent(
-                    endpoint=endpoint or "",
-                    error=str(e),
-                    error_type="unexpected_error",
-                    a2a_agent_name=a2a_agent_name,
-                    operation="push_notification",
-                    context_id=context_id,
-                    task_id=task_id,
-                    from_task=from_task,
-                    from_agent=from_agent,
-                ),
-            )
-            crewai_event_bus.emit(
-                agent_branch,
-                A2AResponseReceivedEvent(
-                    response=error_msg,
-                    turn_number=turn_number,
-                    context_id=context_id,
-                    is_multiturn=is_multiturn,
-                    status="failed",
-                    final=True,
-                    agent_role=agent_role,
-                    endpoint=endpoint,
-                    a2a_agent_name=a2a_agent_name,
-                    from_task=from_task,
-                    from_agent=from_agent,
-                ),
-            )
-            return TaskStateResult(
-                status=TaskState.failed,
-                error=error_msg,
-                history=new_messages,
-            )

lib/crewai/src/crewai/a2a/updates/push_notifications/signature.py

@@ -0,0 +1,87 @@
+"""Webhook signature configuration for push notifications."""
+
+from __future__ import annotations
+
+from enum import Enum
+import secrets
+
+from pydantic import BaseModel, Field, SecretStr
+
+
+class WebhookSignatureMode(str, Enum):
+    """Signature mode for webhook push notifications."""
+
+    NONE = "none"
+    HMAC_SHA256 = "hmac_sha256"
+
+
+class WebhookSignatureConfig(BaseModel):
+    """Configuration for webhook signature verification.
+
+    Provides cryptographic integrity verification and replay attack protection
+    for A2A push notifications.
+
+    Attributes:
+        mode: Signature mode (none or hmac_sha256).
+        secret: Shared secret for HMAC computation (required for hmac_sha256 mode).
+        timestamp_tolerance_seconds: Max allowed age of timestamps for replay protection.
+        header_name: HTTP header name for the signature.
+        timestamp_header_name: HTTP header name for the timestamp.
+    """
+
+    mode: WebhookSignatureMode = Field(
+        default=WebhookSignatureMode.NONE,
+        description="Signature verification mode",
+    )
+    secret: SecretStr | None = Field(
+        default=None,
+        description="Shared secret for HMAC computation",
+    )
+    timestamp_tolerance_seconds: int = Field(
+        default=300,
+        ge=0,
+        description="Max allowed timestamp age in seconds (5 min default)",
+    )
+    header_name: str = Field(
+        default="X-A2A-Signature",
+        description="HTTP header name for the signature",
+    )
+    timestamp_header_name: str = Field(
+        default="X-A2A-Signature-Timestamp",
+        description="HTTP header name for the timestamp",
+    )
+
+    @classmethod
+    def generate_secret(cls, length: int = 32) -> str:
+        """Generate a cryptographically secure random secret.
+
+        Args:
+            length: Number of random bytes to generate (default 32).
+
+        Returns:
+            URL-safe base64-encoded secret string.
+        """
+        return secrets.token_urlsafe(length)
+
+    @classmethod
+    def hmac_sha256(
+        cls,
+        secret: str | SecretStr,
+        timestamp_tolerance_seconds: int = 300,
+    ) -> WebhookSignatureConfig:
+        """Create an HMAC-SHA256 signature configuration.
+
+        Args:
+            secret: Shared secret for HMAC computation.
+            timestamp_tolerance_seconds: Max allowed timestamp age in seconds.
+
+        Returns:
+            Configured WebhookSignatureConfig for HMAC-SHA256.
+        """
+        if isinstance(secret, str):
+            secret = SecretStr(secret)
+        return cls(
+            mode=WebhookSignatureMode.HMAC_SHA256,
+            secret=secret,
+            timestamp_tolerance_seconds=timestamp_tolerance_seconds,
+        )

lib/crewai/src/crewai/a2a/updates/streaming/handler.py

@@ -2,6 +2,9 @@
 
 from __future__ import annotations
 
+import asyncio
+import logging
+from typing import Final
 import uuid
 
 from a2a.client import Client
@@ -11,7 +14,10 @@ from a2a.types import (
     Message,
     Part,
     Role,
+    Task,
     TaskArtifactUpdateEvent,
+    TaskIdParams,
+    TaskQueryParams,
     TaskState,
     TaskStatusUpdateEvent,
     TextPart,
@@ -24,7 +30,10 @@ from crewai.a2a.task_helpers import (
     TaskStateResult,
     process_task_state,
 )
-from crewai.a2a.updates.base import StreamingHandlerKwargs
+from crewai.a2a.updates.base import StreamingHandlerKwargs, extract_common_params
+from crewai.a2a.updates.streaming.params import (
+    process_status_update,
+)
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.a2a_events import (
     A2AArtifactReceivedEvent,
@@ -35,9 +44,194 @@ from crewai.events.types.a2a_events import (
 )
 
 
+logger = logging.getLogger(__name__)
+
+MAX_RESUBSCRIBE_ATTEMPTS: Final[int] = 3
+RESUBSCRIBE_BACKOFF_BASE: Final[float] = 1.0
+
+
 class StreamingHandler:
     """SSE streaming-based update handler."""
 
+    @staticmethod
+    async def _try_recover_from_interruption(  # type: ignore[misc]
+        client: Client,
+        task_id: str,
+        new_messages: list[Message],
+        agent_card: AgentCard,
+        result_parts: list[str],
+        **kwargs: Unpack[StreamingHandlerKwargs],
+    ) -> TaskStateResult | None:
+        """Attempt to recover from a stream interruption by checking task state.
+
+        If the task completed while we were disconnected, returns the result.
+        If the task is still running, attempts to resubscribe and continue.
+
+        Args:
+            client: A2A client instance.
+            task_id: The task ID to recover.
+            new_messages: List of collected messages.
+            agent_card: The agent card.
+            result_parts: Accumulated result text parts.
+            **kwargs: Handler parameters.
+
+        Returns:
+            TaskStateResult if recovery succeeded (task finished or resubscribe worked).
+            None if recovery not possible (caller should handle failure).
+
+        Note:
+            When None is returned, recovery failed and the original exception should
+            be handled by the caller. All recovery attempts are logged.
+        """
+        params = extract_common_params(kwargs)  # type: ignore[arg-type]
+
+        try:
+            a2a_task: Task = await client.get_task(TaskQueryParams(id=task_id))
+
+            if a2a_task.status.state in TERMINAL_STATES:
+                logger.info(
+                    "Task completed during stream interruption",
+                    extra={"task_id": task_id, "state": str(a2a_task.status.state)},
+                )
+                return process_task_state(
+                    a2a_task=a2a_task,
+                    new_messages=new_messages,
+                    agent_card=agent_card,
+                    turn_number=params.turn_number,
+                    is_multiturn=params.is_multiturn,
+                    agent_role=params.agent_role,
+                    result_parts=result_parts,
+                    endpoint=params.endpoint,
+                    a2a_agent_name=params.a2a_agent_name,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
+                )
+
+            if a2a_task.status.state in ACTIONABLE_STATES:
+                logger.info(
+                    "Task in actionable state during stream interruption",
+                    extra={"task_id": task_id, "state": str(a2a_task.status.state)},
+                )
+                return process_task_state(
+                    a2a_task=a2a_task,
+                    new_messages=new_messages,
+                    agent_card=agent_card,
+                    turn_number=params.turn_number,
+                    is_multiturn=params.is_multiturn,
+                    agent_role=params.agent_role,
+                    result_parts=result_parts,
+                    endpoint=params.endpoint,
+                    a2a_agent_name=params.a2a_agent_name,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
+                    is_final=False,
+                )
+
+            logger.info(
+                "Task still running, attempting resubscribe",
+                extra={"task_id": task_id, "state": str(a2a_task.status.state)},
+            )
+
+            for attempt in range(MAX_RESUBSCRIBE_ATTEMPTS):
+                try:
+                    backoff = RESUBSCRIBE_BACKOFF_BASE * (2**attempt)
+                    if attempt > 0:
+                        await asyncio.sleep(backoff)
+
+                    event_stream = client.resubscribe(TaskIdParams(id=task_id))
+
+                    async for event in event_stream:
+                        if isinstance(event, tuple):
+                            resubscribed_task, update = event
+
+                            is_final_update = (
+                                process_status_update(update, result_parts)
+                                if isinstance(update, TaskStatusUpdateEvent)
+                                else False
+                            )
+
+                            if isinstance(update, TaskArtifactUpdateEvent):
+                                artifact = update.artifact
+                                result_parts.extend(
+                                    part.root.text
+                                    for part in artifact.parts
+                                    if part.root.kind == "text"
+                                )
+
+                            if (
+                                is_final_update
+                                or resubscribed_task.status.state
+                                in TERMINAL_STATES | ACTIONABLE_STATES
+                            ):
+                                return process_task_state(
+                                    a2a_task=resubscribed_task,
+                                    new_messages=new_messages,
+                                    agent_card=agent_card,
+                                    turn_number=params.turn_number,
+                                    is_multiturn=params.is_multiturn,
+                                    agent_role=params.agent_role,
+                                    result_parts=result_parts,
+                                    endpoint=params.endpoint,
+                                    a2a_agent_name=params.a2a_agent_name,
+                                    from_task=params.from_task,
+                                    from_agent=params.from_agent,
+                                    is_final=is_final_update,
+                                )
+
+                        elif isinstance(event, Message):
+                            new_messages.append(event)
+                            result_parts.extend(
+                                part.root.text
+                                for part in event.parts
+                                if part.root.kind == "text"
+                            )
+
+                    final_task = await client.get_task(TaskQueryParams(id=task_id))
+                    return process_task_state(
+                        a2a_task=final_task,
+                        new_messages=new_messages,
+                        agent_card=agent_card,
+                        turn_number=params.turn_number,
+                        is_multiturn=params.is_multiturn,
+                        agent_role=params.agent_role,
+                        result_parts=result_parts,
+                        endpoint=params.endpoint,
+                        a2a_agent_name=params.a2a_agent_name,
+                        from_task=params.from_task,
+                        from_agent=params.from_agent,
+                    )
+
+                except Exception as resubscribe_error:  # noqa: PERF203
+                    logger.warning(
+                        "Resubscribe attempt failed",
+                        extra={
+                            "task_id": task_id,
+                            "attempt": attempt + 1,
+                            "max_attempts": MAX_RESUBSCRIBE_ATTEMPTS,
+                            "error": str(resubscribe_error),
+                        },
+                    )
+                    if attempt == MAX_RESUBSCRIBE_ATTEMPTS - 1:
+                        return None
+
+        except Exception as e:
+            logger.warning(
+                "Failed to recover from stream interruption due to unexpected error",
+                extra={
+                    "task_id": task_id,
+                    "error": str(e),
+                    "error_type": type(e).__name__,
+                },
+                exc_info=True,
+            )
+            return None
+
+        logger.warning(
+            "Recovery exhausted all resubscribe attempts without success",
+            extra={"task_id": task_id, "max_attempts": MAX_RESUBSCRIBE_ATTEMPTS},
+        )
+        return None
+
     @staticmethod
     async def execute(
         client: Client,
@@ -58,42 +252,40 @@ class StreamingHandler:
         Returns:
             Dictionary with status, result/error, and history.
         """
-        context_id = kwargs.get("context_id")
         task_id = kwargs.get("task_id")
-        turn_number = kwargs.get("turn_number", 0)
-        is_multiturn = kwargs.get("is_multiturn", False)
-        agent_role = kwargs.get("agent_role")
-        endpoint = kwargs.get("endpoint")
-        a2a_agent_name = kwargs.get("a2a_agent_name")
-        from_task = kwargs.get("from_task")
-        from_agent = kwargs.get("from_agent")
         agent_branch = kwargs.get("agent_branch")
+        params = extract_common_params(kwargs)
 
         result_parts: list[str] = []
         final_result: TaskStateResult | None = None
         event_stream = client.send_message(message)
         chunk_index = 0
+        current_task_id: str | None = task_id
 
         crewai_event_bus.emit(
             agent_branch,
             A2AStreamingStartedEvent(
                 task_id=task_id,
-                context_id=context_id,
-                endpoint=endpoint or "",
-                a2a_agent_name=a2a_agent_name,
-                turn_number=turn_number,
-                is_multiturn=is_multiturn,
-                agent_role=agent_role,
-                from_task=from_task,
-                from_agent=from_agent,
+                context_id=params.context_id,
+                endpoint=params.endpoint,
+                a2a_agent_name=params.a2a_agent_name,
+                turn_number=params.turn_number,
+                is_multiturn=params.is_multiturn,
+                agent_role=params.agent_role,
+                from_task=params.from_task,
+                from_agent=params.from_agent,
             ),
         )
 
         try:
             async for event in event_stream:
+                if isinstance(event, tuple):
+                    a2a_task, _ = event
+                    current_task_id = a2a_task.id
+
                 if isinstance(event, Message):
                     new_messages.append(event)
-                    message_context_id = event.context_id or context_id
+                    message_context_id = event.context_id or params.context_id
                     for part in event.parts:
                         if part.root.kind == "text":
                             text = part.root.text
@@ -105,12 +297,12 @@ class StreamingHandler:
                                     context_id=message_context_id,
                                     chunk=text,
                                     chunk_index=chunk_index,
-                                    endpoint=endpoint,
-                                    a2a_agent_name=a2a_agent_name,
-                                    turn_number=turn_number,
-                                    is_multiturn=is_multiturn,
-                                    from_task=from_task,
-                                    from_agent=from_agent,
+                                    endpoint=params.endpoint,
+                                    a2a_agent_name=params.a2a_agent_name,
+                                    turn_number=params.turn_number,
+                                    is_multiturn=params.is_multiturn,
+                                    from_task=params.from_task,
+                                    from_agent=params.from_agent,
                                 ),
                             )
                             chunk_index += 1
@@ -128,12 +320,12 @@ class StreamingHandler:
                         artifact_size = None
                         if artifact.parts:
                             artifact_size = sum(
-                                len(p.root.text.encode("utf-8"))
+                                len(p.root.text.encode())
                                 if p.root.kind == "text"
                                 else len(getattr(p.root, "data", b""))
                                 for p in artifact.parts
                             )
-                        effective_context_id = a2a_task.context_id or context_id
+                        effective_context_id = a2a_task.context_id or params.context_id
                         crewai_event_bus.emit(
                             agent_branch,
                             A2AArtifactReceivedEvent(
@@ -147,29 +339,21 @@ class StreamingHandler:
                                 size_bytes=artifact_size,
                                 append=update.append or False,
                                 last_chunk=update.last_chunk or False,
-                                endpoint=endpoint,
-                                a2a_agent_name=a2a_agent_name,
+                                endpoint=params.endpoint,
+                                a2a_agent_name=params.a2a_agent_name,
                                 context_id=effective_context_id,
-                                turn_number=turn_number,
-                                is_multiturn=is_multiturn,
-                                from_task=from_task,
-                                from_agent=from_agent,
+                                turn_number=params.turn_number,
+                                is_multiturn=params.is_multiturn,
+                                from_task=params.from_task,
+                                from_agent=params.from_agent,
                             ),
                         )
 
-                    is_final_update = False
-                    if isinstance(update, TaskStatusUpdateEvent):
-                        is_final_update = update.final
-                        if (
-                            update.status
-                            and update.status.message
-                            and update.status.message.parts
-                        ):
-                            result_parts.extend(
-                                part.root.text
-                                for part in update.status.message.parts
-                                if part.root.kind == "text" and part.root.text
-                            )
+                    is_final_update = (
+                        process_status_update(update, result_parts)
+                        if isinstance(update, TaskStatusUpdateEvent)
+                        else False
+                    )
 
                     if (
                         not is_final_update
@@ -182,27 +366,68 @@ class StreamingHandler:
                         a2a_task=a2a_task,
                         new_messages=new_messages,
                         agent_card=agent_card,
-                        turn_number=turn_number,
-                        is_multiturn=is_multiturn,
-                        agent_role=agent_role,
+                        turn_number=params.turn_number,
+                        is_multiturn=params.is_multiturn,
+                        agent_role=params.agent_role,
                         result_parts=result_parts,
-                        endpoint=endpoint,
-                        a2a_agent_name=a2a_agent_name,
-                        from_task=from_task,
-                        from_agent=from_agent,
+                        endpoint=params.endpoint,
+                        a2a_agent_name=params.a2a_agent_name,
+                        from_task=params.from_task,
+                        from_agent=params.from_agent,
                         is_final=is_final_update,
                     )
                     if final_result:
                         break
 
         except A2AClientHTTPError as e:
+            if current_task_id:
+                logger.info(
+                    "Stream interrupted with HTTP error, attempting recovery",
+                    extra={
+                        "task_id": current_task_id,
+                        "error": str(e),
+                        "status_code": e.status_code,
+                    },
+                )
+                recovery_kwargs = {k: v for k, v in kwargs.items() if k != "task_id"}
+                recovered_result = (
+                    await StreamingHandler._try_recover_from_interruption(
+                        client=client,
+                        task_id=current_task_id,
+                        new_messages=new_messages,
+                        agent_card=agent_card,
+                        result_parts=result_parts,
+                        **recovery_kwargs,
+                    )
+                )
+                if recovered_result:
+                    logger.info(
+                        "Successfully recovered task after HTTP error",
+                        extra={
+                            "task_id": current_task_id,
+                            "status": str(recovered_result.get("status")),
+                        },
+                    )
+                    return recovered_result
+
+                logger.warning(
+                    "Failed to recover from HTTP error, returning failure",
+                    extra={
+                        "task_id": current_task_id,
+                        "status_code": e.status_code,
+                        "original_error": str(e),
+                    },
+                )
+
             error_msg = f"HTTP Error {e.status_code}: {e!s}"
+            error_type = "http_error"
+            status_code = e.status_code
 
             error_message = Message(
                 role=Role.agent,
                 message_id=str(uuid.uuid4()),
                 parts=[Part(root=TextPart(text=error_msg))],
-                context_id=context_id,
+                context_id=params.context_id,
                 task_id=task_id,
             )
             new_messages.append(error_message)
@@ -210,32 +435,118 @@ class StreamingHandler:
             crewai_event_bus.emit(
                 agent_branch,
                 A2AConnectionErrorEvent(
-                    endpoint=endpoint or "",
+                    endpoint=params.endpoint,
                     error=str(e),
-                    error_type="http_error",
-                    status_code=e.status_code,
-                    a2a_agent_name=a2a_agent_name,
+                    error_type=error_type,
+                    status_code=status_code,
+                    a2a_agent_name=params.a2a_agent_name,
                     operation="streaming",
-                    context_id=context_id,
+                    context_id=params.context_id,
                     task_id=task_id,
-                    from_task=from_task,
-                    from_agent=from_agent,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
                 ),
             )
             crewai_event_bus.emit(
                 agent_branch,
                 A2AResponseReceivedEvent(
                     response=error_msg,
-                    turn_number=turn_number,
-                    context_id=context_id,
-                    is_multiturn=is_multiturn,
+                    turn_number=params.turn_number,
+                    context_id=params.context_id,
+                    is_multiturn=params.is_multiturn,
                     status="failed",
                     final=True,
-                    agent_role=agent_role,
-                    endpoint=endpoint,
-                    a2a_agent_name=a2a_agent_name,
-                    from_task=from_task,
-                    from_agent=from_agent,
+                    agent_role=params.agent_role,
+                    endpoint=params.endpoint,
+                    a2a_agent_name=params.a2a_agent_name,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
+                ),
+            )
+            return TaskStateResult(
+                status=TaskState.failed,
+                error=error_msg,
+                history=new_messages,
+            )
+
+        except (asyncio.TimeoutError, asyncio.CancelledError, ConnectionError) as e:
+            error_type = type(e).__name__.lower()
+            if current_task_id:
+                logger.info(
+                    f"Stream interrupted with {error_type}, attempting recovery",
+                    extra={"task_id": current_task_id, "error": str(e)},
+                )
+                recovery_kwargs = {k: v for k, v in kwargs.items() if k != "task_id"}
+                recovered_result = (
+                    await StreamingHandler._try_recover_from_interruption(
+                        client=client,
+                        task_id=current_task_id,
+                        new_messages=new_messages,
+                        agent_card=agent_card,
+                        result_parts=result_parts,
+                        **recovery_kwargs,
+                    )
+                )
+                if recovered_result:
+                    logger.info(
+                        f"Successfully recovered task after {error_type}",
+                        extra={
+                            "task_id": current_task_id,
+                            "status": str(recovered_result.get("status")),
+                        },
+                    )
+                    return recovered_result
+
+                logger.warning(
+                    f"Failed to recover from {error_type}, returning failure",
+                    extra={
+                        "task_id": current_task_id,
+                        "error_type": error_type,
+                        "original_error": str(e),
+                    },
+                )
+
+            error_msg = f"Connection error during streaming: {e!s}"
+            status_code = None
+
+            error_message = Message(
+                role=Role.agent,
+                message_id=str(uuid.uuid4()),
+                parts=[Part(root=TextPart(text=error_msg))],
+                context_id=params.context_id,
+                task_id=task_id,
+            )
+            new_messages.append(error_message)
+
+            crewai_event_bus.emit(
+                agent_branch,
+                A2AConnectionErrorEvent(
+                    endpoint=params.endpoint,
+                    error=str(e),
+                    error_type=error_type,
+                    status_code=status_code,
+                    a2a_agent_name=params.a2a_agent_name,
+                    operation="streaming",
+                    context_id=params.context_id,
+                    task_id=task_id,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
+                ),
+            )
+            crewai_event_bus.emit(
+                agent_branch,
+                A2AResponseReceivedEvent(
+                    response=error_msg,
+                    turn_number=params.turn_number,
+                    context_id=params.context_id,
+                    is_multiturn=params.is_multiturn,
+                    status="failed",
+                    final=True,
+                    agent_role=params.agent_role,
+                    endpoint=params.endpoint,
+                    a2a_agent_name=params.a2a_agent_name,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
                 ),
             )
             return TaskStateResult(
@@ -245,13 +556,23 @@ class StreamingHandler:
             )
 
         except Exception as e:
-            error_msg = f"Unexpected error during streaming: {e!s}"
+            logger.exception(
+                "Unexpected error during streaming",
+                extra={
+                    "task_id": current_task_id,
+                    "error_type": type(e).__name__,
+                    "endpoint": params.endpoint,
+                },
+            )
+            error_msg = f"Unexpected error during streaming: {type(e).__name__}: {e!s}"
+            error_type = "unexpected_error"
+            status_code = None
 
             error_message = Message(
                 role=Role.agent,
                 message_id=str(uuid.uuid4()),
                 parts=[Part(root=TextPart(text=error_msg))],
-                context_id=context_id,
+                context_id=params.context_id,
                 task_id=task_id,
             )
             new_messages.append(error_message)
@@ -259,31 +580,32 @@ class StreamingHandler:
             crewai_event_bus.emit(
                 agent_branch,
                 A2AConnectionErrorEvent(
-                    endpoint=endpoint or "",
+                    endpoint=params.endpoint,
                     error=str(e),
-                    error_type="unexpected_error",
-                    a2a_agent_name=a2a_agent_name,
+                    error_type=error_type,
+                    status_code=status_code,
+                    a2a_agent_name=params.a2a_agent_name,
                     operation="streaming",
-                    context_id=context_id,
+                    context_id=params.context_id,
                     task_id=task_id,
-                    from_task=from_task,
-                    from_agent=from_agent,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
                 ),
             )
             crewai_event_bus.emit(
                 agent_branch,
                 A2AResponseReceivedEvent(
                     response=error_msg,
-                    turn_number=turn_number,
-                    context_id=context_id,
-                    is_multiturn=is_multiturn,
+                    turn_number=params.turn_number,
+                    context_id=params.context_id,
+                    is_multiturn=params.is_multiturn,
                     status="failed",
                     final=True,
-                    agent_role=agent_role,
-                    endpoint=endpoint,
-                    a2a_agent_name=a2a_agent_name,
-                    from_task=from_task,
-                    from_agent=from_agent,
+                    agent_role=params.agent_role,
+                    endpoint=params.endpoint,
+                    a2a_agent_name=params.a2a_agent_name,
+                    from_task=params.from_task,
+                    from_agent=params.from_agent,
                 ),
             )
             return TaskStateResult(
@@ -301,15 +623,15 @@ class StreamingHandler:
                     crewai_event_bus.emit(
                         agent_branch,
                         A2AConnectionErrorEvent(
-                            endpoint=endpoint or "",
+                            endpoint=params.endpoint,
                             error=str(close_error),
                             error_type="stream_close_error",
-                            a2a_agent_name=a2a_agent_name,
+                            a2a_agent_name=params.a2a_agent_name,
                             operation="stream_close",
-                            context_id=context_id,
+                            context_id=params.context_id,
                             task_id=task_id,
-                            from_task=from_task,
-                            from_agent=from_agent,
+                            from_task=params.from_task,
+                            from_agent=params.from_agent,
                         ),
                     )
 

lib/crewai/src/crewai/a2a/updates/streaming/params.py

@@ -0,0 +1,28 @@
+"""Common parameter extraction for streaming handlers."""
+
+from __future__ import annotations
+
+from a2a.types import TaskStatusUpdateEvent
+
+
+def process_status_update(
+    update: TaskStatusUpdateEvent,
+    result_parts: list[str],
+) -> bool:
+    """Process a status update event and extract text parts.
+
+    Args:
+        update: The status update event.
+        result_parts: List to append text parts to (modified in place).
+
+    Returns:
+        True if this is a final update, False otherwise.
+    """
+    is_final = update.final
+    if update.status and update.status.message and update.status.message.parts:
+        result_parts.extend(
+            part.root.text
+            for part in update.status.message.parts
+            if part.root.kind == "text" and part.root.text
+        )
+    return is_final

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

@@ -5,6 +5,7 @@ from __future__ import annotations
 import asyncio
 from collections.abc import MutableMapping
 from functools import lru_cache
+import ssl
 import time
 from types import MethodType
 from typing import TYPE_CHECKING
@@ -15,7 +16,7 @@ from aiocache import cached  # type: ignore[import-untyped]
 from aiocache.serializers import PickleSerializer  # type: ignore[import-untyped]
 import httpx
 
-from crewai.a2a.auth.schemas import APIKeyAuth, HTTPDigestAuth
+from crewai.a2a.auth.client_schemes import APIKeyAuth, HTTPDigestAuth
 from crewai.a2a.auth.utils import (
     _auth_store,
     configure_auth_client,
@@ -32,11 +33,51 @@ from crewai.events.types.a2a_events import (
 
 
 if TYPE_CHECKING:
-    from crewai.a2a.auth.schemas import AuthScheme
+    from crewai.a2a.auth.client_schemes import ClientAuthScheme
     from crewai.agent import Agent
     from crewai.task import Task
 
 
+def _get_tls_verify(auth: ClientAuthScheme | None) -> ssl.SSLContext | bool | str:
+    """Get TLS verify parameter from auth scheme.
+
+    Args:
+        auth: Optional authentication scheme with TLS config.
+
+    Returns:
+        SSL context, CA cert path, True for default verification,
+        or False if verification disabled.
+    """
+    if auth and auth.tls:
+        return auth.tls.get_httpx_ssl_context()
+    return True
+
+
+async def _prepare_auth_headers(
+    auth: ClientAuthScheme | None,
+    timeout: int,
+) -> tuple[MutableMapping[str, str], ssl.SSLContext | bool | str]:
+    """Prepare authentication headers and TLS verification settings.
+
+    Args:
+        auth: Optional authentication scheme.
+        timeout: Request timeout in seconds.
+
+    Returns:
+        Tuple of (headers dict, TLS verify setting).
+    """
+    headers: MutableMapping[str, str] = {}
+    verify = _get_tls_verify(auth)
+    if auth:
+        async with httpx.AsyncClient(
+            timeout=timeout, verify=verify
+        ) as temp_auth_client:
+            if isinstance(auth, (HTTPDigestAuth, APIKeyAuth)):
+                configure_auth_client(auth, temp_auth_client)
+            headers = await auth.apply_auth(temp_auth_client, {})
+    return headers, verify
+
+
 def _get_server_config(agent: Agent) -> A2AServerConfig | None:
     """Get A2AServerConfig from an agent's a2a configuration.
 
@@ -59,7 +100,7 @@ def _get_server_config(agent: Agent) -> A2AServerConfig | None:
 
 def fetch_agent_card(
     endpoint: str,
-    auth: AuthScheme | None = None,
+    auth: ClientAuthScheme | None = None,
     timeout: int = 30,
     use_cache: bool = True,
     cache_ttl: int = 300,
@@ -68,7 +109,7 @@ def fetch_agent_card(
 
     Args:
         endpoint: A2A agent endpoint URL (AgentCard URL).
-        auth: Optional AuthScheme for authentication.
+        auth: Optional ClientAuthScheme for authentication.
         timeout: Request timeout in seconds.
         use_cache: Whether to use caching (default True).
         cache_ttl: Cache TTL in seconds (default 300 = 5 minutes).
@@ -90,10 +131,10 @@ def fetch_agent_card(
                     "_authorization_callback",
                 }
             )
-            auth_hash = hash((type(auth).__name__, auth_data))
+            auth_hash = _auth_store.compute_key(type(auth).__name__, auth_data)
         else:
-            auth_hash = 0
-        _auth_store[auth_hash] = auth
+            auth_hash = _auth_store.compute_key("none", "")
+        _auth_store.set(auth_hash, auth)
         ttl_hash = int(time.time() // cache_ttl)
         return _fetch_agent_card_cached(endpoint, auth_hash, timeout, ttl_hash)
 
@@ -109,7 +150,7 @@ def fetch_agent_card(
 
 async def afetch_agent_card(
     endpoint: str,
-    auth: AuthScheme | None = None,
+    auth: ClientAuthScheme | None = None,
     timeout: int = 30,
     use_cache: bool = True,
 ) -> AgentCard:
@@ -119,7 +160,7 @@ async def afetch_agent_card(
 
     Args:
         endpoint: A2A agent endpoint URL (AgentCard URL).
-        auth: Optional AuthScheme for authentication.
+        auth: Optional ClientAuthScheme for authentication.
         timeout: Request timeout in seconds.
         use_cache: Whether to use caching (default True).
 
@@ -140,10 +181,10 @@ async def afetch_agent_card(
                     "_authorization_callback",
                 }
             )
-            auth_hash = hash((type(auth).__name__, auth_data))
+            auth_hash = _auth_store.compute_key(type(auth).__name__, auth_data)
         else:
-            auth_hash = 0
-        _auth_store[auth_hash] = auth
+            auth_hash = _auth_store.compute_key("none", "")
+        _auth_store.set(auth_hash, auth)
         agent_card: AgentCard = await _afetch_agent_card_cached(
             endpoint, auth_hash, timeout
         )
@@ -155,7 +196,7 @@ async def afetch_agent_card(
 @lru_cache()
 def _fetch_agent_card_cached(
     endpoint: str,
-    auth_hash: int,
+    auth_hash: str,
     timeout: int,
     _ttl_hash: int,
 ) -> AgentCard:
@@ -175,7 +216,7 @@ def _fetch_agent_card_cached(
 @cached(ttl=300, serializer=PickleSerializer())  # type: ignore[untyped-decorator]
 async def _afetch_agent_card_cached(
     endpoint: str,
-    auth_hash: int,
+    auth_hash: str,
     timeout: int,
 ) -> AgentCard:
     """Cached async implementation of AgentCard fetching."""
@@ -185,7 +226,7 @@ async def _afetch_agent_card_cached(
 
 async def _afetch_agent_card_impl(
     endpoint: str,
-    auth: AuthScheme | None,
+    auth: ClientAuthScheme | None,
     timeout: int,
 ) -> AgentCard:
     """Internal async implementation of AgentCard fetching."""
@@ -197,16 +238,17 @@ async def _afetch_agent_card_impl(
     else:
         url_parts = endpoint.split("/", 3)
         base_url = f"{url_parts[0]}//{url_parts[2]}"
-        agent_card_path = f"/{url_parts[3]}" if len(url_parts) > 3 else "/"
+        agent_card_path = (
+            f"/{url_parts[3]}"
+            if len(url_parts) > 3 and url_parts[3]
+            else "/.well-known/agent-card.json"
+        )
 
-    headers: MutableMapping[str, str] = {}
-    if auth:
-        async with httpx.AsyncClient(timeout=timeout) as temp_auth_client:
-            if isinstance(auth, (HTTPDigestAuth, APIKeyAuth)):
-                configure_auth_client(auth, temp_auth_client)
-            headers = await auth.apply_auth(temp_auth_client, {})
+    headers, verify = await _prepare_auth_headers(auth, timeout)
 
-    async with httpx.AsyncClient(timeout=timeout, headers=headers) as temp_client:
+    async with httpx.AsyncClient(
+        timeout=timeout, headers=headers, verify=verify
+    ) as temp_client:
         if auth and isinstance(auth, (HTTPDigestAuth, APIKeyAuth)):
             configure_auth_client(auth, temp_client)
 
@@ -434,6 +476,7 @@ def _agent_to_agent_card(agent: Agent, url: str) -> AgentCard:
     """Generate an A2A AgentCard from an Agent instance.
 
     Uses A2AServerConfig values when available, falling back to agent properties.
+    If signing_config is provided, the card will be signed with JWS.
 
     Args:
         agent: The Agent instance to generate a card for.
@@ -442,6 +485,8 @@ def _agent_to_agent_card(agent: Agent, url: str) -> AgentCard:
     Returns:
         AgentCard describing the agent's capabilities.
     """
+    from crewai.a2a.utils.agent_card_signing import sign_agent_card
+
     server_config = _get_server_config(agent) or A2AServerConfig()
 
     name = server_config.name or agent.role
@@ -472,15 +517,31 @@ def _agent_to_agent_card(agent: Agent, url: str) -> AgentCard:
                 )
             )
 
-    return AgentCard(
+    capabilities = server_config.capabilities
+    if server_config.server_extensions:
+        from crewai.a2a.extensions.server import ServerExtensionRegistry
+
+        registry = ServerExtensionRegistry(server_config.server_extensions)
+        ext_list = registry.get_agent_extensions()
+
+        existing_exts = list(capabilities.extensions) if capabilities.extensions else []
+        existing_uris = {e.uri for e in existing_exts}
+        for ext in ext_list:
+            if ext.uri not in existing_uris:
+                existing_exts.append(ext)
+
+        capabilities = capabilities.model_copy(update={"extensions": existing_exts})
+
+    card = AgentCard(
         name=name,
         description=description,
         url=server_config.url or url,
         version=server_config.version,
-        capabilities=server_config.capabilities,
+        capabilities=capabilities,
         default_input_modes=server_config.default_input_modes,
         default_output_modes=server_config.default_output_modes,
         skills=skills,
+        preferred_transport=server_config.transport.preferred,
         protocol_version=server_config.protocol_version,
         provider=server_config.provider,
         documentation_url=server_config.documentation_url,
@@ -489,9 +550,21 @@ def _agent_to_agent_card(agent: Agent, url: str) -> AgentCard:
         security=server_config.security,
         security_schemes=server_config.security_schemes,
         supports_authenticated_extended_card=server_config.supports_authenticated_extended_card,
-        signatures=server_config.signatures,
     )
 
+    if server_config.signing_config:
+        signature = sign_agent_card(
+            card,
+            private_key=server_config.signing_config.get_private_key(),
+            key_id=server_config.signing_config.key_id,
+            algorithm=server_config.signing_config.algorithm,
+        )
+        card = card.model_copy(update={"signatures": [signature]})
+    elif server_config.signatures:
+        card = card.model_copy(update={"signatures": server_config.signatures})
+
+    return card
+
 
 def inject_a2a_server_methods(agent: Agent) -> None:
     """Inject A2A server methods onto an Agent instance.

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

@@ -0,0 +1,236 @@
+"""AgentCard JWS signing utilities.
+
+This module provides functions for signing and verifying AgentCards using
+JSON Web Signatures (JWS) as per RFC 7515. Signed agent cards allow clients
+to verify the authenticity and integrity of agent card information.
+
+Example:
+    >>> from crewai.a2a.utils.agent_card_signing import sign_agent_card
+    >>> signature = sign_agent_card(agent_card, private_key_pem, key_id="key-1")
+    >>> card_with_sig = card.model_copy(update={"signatures": [signature]})
+"""
+
+from __future__ import annotations
+
+import base64
+import json
+import logging
+from typing import Any, Literal
+
+from a2a.types import AgentCard, AgentCardSignature
+import jwt
+from pydantic import SecretStr
+
+
+logger = logging.getLogger(__name__)
+
+
+SigningAlgorithm = Literal[
+    "RS256", "RS384", "RS512", "ES256", "ES384", "ES512", "PS256", "PS384", "PS512"
+]
+
+
+def _normalize_private_key(private_key: str | bytes | SecretStr) -> bytes:
+    """Normalize private key to bytes format.
+
+    Args:
+        private_key: PEM-encoded private key as string, bytes, or SecretStr.
+
+    Returns:
+        Private key as bytes.
+    """
+    if isinstance(private_key, SecretStr):
+        private_key = private_key.get_secret_value()
+    if isinstance(private_key, str):
+        private_key = private_key.encode()
+    return private_key
+
+
+def _serialize_agent_card(agent_card: AgentCard) -> str:
+    """Serialize AgentCard to canonical JSON for signing.
+
+    Excludes the signatures field to avoid circular reference during signing.
+    Uses sorted keys and compact separators for deterministic output.
+
+    Args:
+        agent_card: The AgentCard to serialize.
+
+    Returns:
+        Canonical JSON string representation.
+    """
+    card_dict = agent_card.model_dump(exclude={"signatures"}, exclude_none=True)
+    return json.dumps(card_dict, sort_keys=True, separators=(",", ":"))
+
+
+def _base64url_encode(data: bytes | str) -> str:
+    """Encode data to URL-safe base64 without padding.
+
+    Args:
+        data: Data to encode.
+
+    Returns:
+        URL-safe base64 encoded string without padding.
+    """
+    if isinstance(data, str):
+        data = data.encode()
+    return base64.urlsafe_b64encode(data).rstrip(b"=").decode("ascii")
+
+
+def sign_agent_card(
+    agent_card: AgentCard,
+    private_key: str | bytes | SecretStr,
+    key_id: str | None = None,
+    algorithm: SigningAlgorithm = "RS256",
+) -> AgentCardSignature:
+    """Sign an AgentCard using JWS (RFC 7515).
+
+    Creates a detached JWS signature for the AgentCard. The signature covers
+    all fields except the signatures field itself.
+
+    Args:
+        agent_card: The AgentCard to sign.
+        private_key: PEM-encoded private key (RSA, EC, or RSA-PSS).
+        key_id: Optional key identifier for the JWS header (kid claim).
+        algorithm: Signing algorithm (RS256, ES256, PS256, etc.).
+
+    Returns:
+        AgentCardSignature with protected header and signature.
+
+    Raises:
+        jwt.exceptions.InvalidKeyError: If the private key is invalid.
+        ValueError: If the algorithm is not supported for the key type.
+
+    Example:
+        >>> signature = sign_agent_card(
+        ...     agent_card,
+        ...     private_key_pem="-----BEGIN PRIVATE KEY-----...",
+        ...     key_id="my-key-id",
+        ... )
+    """
+    key_bytes = _normalize_private_key(private_key)
+    payload = _serialize_agent_card(agent_card)
+
+    protected_header: dict[str, Any] = {"typ": "JWS"}
+    if key_id:
+        protected_header["kid"] = key_id
+
+    jws_token = jwt.api_jws.encode(
+        payload.encode(),
+        key_bytes,
+        algorithm=algorithm,
+        headers=protected_header,
+    )
+
+    parts = jws_token.split(".")
+    protected_b64 = parts[0]
+    signature_b64 = parts[2]
+
+    header: dict[str, Any] | None = None
+    if key_id:
+        header = {"kid": key_id}
+
+    return AgentCardSignature(
+        protected=protected_b64,
+        signature=signature_b64,
+        header=header,
+    )
+
+
+def verify_agent_card_signature(
+    agent_card: AgentCard,
+    signature: AgentCardSignature,
+    public_key: str | bytes,
+    algorithms: list[str] | None = None,
+) -> bool:
+    """Verify an AgentCard JWS signature.
+
+    Validates that the signature was created with the corresponding private key
+    and that the AgentCard content has not been modified.
+
+    Args:
+        agent_card: The AgentCard to verify.
+        signature: The AgentCardSignature to validate.
+        public_key: PEM-encoded public key (RSA, EC, or RSA-PSS).
+        algorithms: List of allowed algorithms. Defaults to common asymmetric algorithms.
+
+    Returns:
+        True if signature is valid, False otherwise.
+
+    Example:
+        >>> is_valid = verify_agent_card_signature(
+        ...     agent_card, signature, public_key_pem="-----BEGIN PUBLIC KEY-----..."
+        ... )
+    """
+    if algorithms is None:
+        algorithms = [
+            "RS256",
+            "RS384",
+            "RS512",
+            "ES256",
+            "ES384",
+            "ES512",
+            "PS256",
+            "PS384",
+            "PS512",
+        ]
+
+    if isinstance(public_key, str):
+        public_key = public_key.encode()
+
+    payload = _serialize_agent_card(agent_card)
+    payload_b64 = _base64url_encode(payload)
+    jws_token = f"{signature.protected}.{payload_b64}.{signature.signature}"
+
+    try:
+        jwt.api_jws.decode(
+            jws_token,
+            public_key,
+            algorithms=algorithms,
+        )
+        return True
+    except jwt.InvalidSignatureError:
+        logger.debug(
+            "AgentCard signature verification failed",
+            extra={"reason": "invalid_signature"},
+        )
+        return False
+    except jwt.DecodeError as e:
+        logger.debug(
+            "AgentCard signature verification failed",
+            extra={"reason": "decode_error", "error": str(e)},
+        )
+        return False
+    except jwt.InvalidAlgorithmError as e:
+        logger.debug(
+            "AgentCard signature verification failed",
+            extra={"reason": "algorithm_error", "error": str(e)},
+        )
+        return False
+
+
+def get_key_id_from_signature(signature: AgentCardSignature) -> str | None:
+    """Extract the key ID (kid) from an AgentCardSignature.
+
+    Checks both the unprotected header and the protected header for the kid claim.
+
+    Args:
+        signature: The AgentCardSignature to extract from.
+
+    Returns:
+        The key ID if present, None otherwise.
+    """
+    if signature.header and "kid" in signature.header:
+        kid: str = signature.header["kid"]
+        return kid
+
+    try:
+        protected = signature.protected
+        padding_needed = 4 - (len(protected) % 4)
+        if padding_needed != 4:
+            protected += "=" * padding_needed
+
+        protected_json = base64.urlsafe_b64decode(protected).decode()
+        protected_header: dict[str, Any] = json.loads(protected_json)
+        return protected_header.get("kid")
+    except (ValueError, json.JSONDecodeError):
+        return None

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

@@ -0,0 +1,339 @@
+"""Content type negotiation for A2A protocol.
+
+This module handles negotiation of input/output MIME types between A2A clients
+and servers based on AgentCard capabilities.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Annotated, Final, Literal, cast
+
+from a2a.types import Part
+
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.a2a_events import A2AContentTypeNegotiatedEvent
+
+
+if TYPE_CHECKING:
+    from a2a.types import AgentCard, AgentSkill
+
+
+TEXT_PLAIN: Literal["text/plain"] = "text/plain"
+APPLICATION_JSON: Literal["application/json"] = "application/json"
+IMAGE_PNG: Literal["image/png"] = "image/png"
+IMAGE_JPEG: Literal["image/jpeg"] = "image/jpeg"
+IMAGE_WILDCARD: Literal["image/*"] = "image/*"
+APPLICATION_PDF: Literal["application/pdf"] = "application/pdf"
+APPLICATION_OCTET_STREAM: Literal["application/octet-stream"] = (
+    "application/octet-stream"
+)
+
+DEFAULT_CLIENT_INPUT_MODES: Final[list[Literal["text/plain", "application/json"]]] = [
+    TEXT_PLAIN,
+    APPLICATION_JSON,
+]
+DEFAULT_CLIENT_OUTPUT_MODES: Final[list[Literal["text/plain", "application/json"]]] = [
+    TEXT_PLAIN,
+    APPLICATION_JSON,
+]
+
+
+@dataclass
+class NegotiatedContentTypes:
+    """Result of content type negotiation."""
+
+    input_modes: Annotated[list[str], "Negotiated input MIME types the client can send"]
+    output_modes: Annotated[
+        list[str], "Negotiated output MIME types the server will produce"
+    ]
+    effective_input_modes: Annotated[list[str], "Server's effective input modes"]
+    effective_output_modes: Annotated[list[str], "Server's effective output modes"]
+    skill_name: Annotated[
+        str | None, "Skill name if negotiation was skill-specific"
+    ] = None
+
+
+class ContentTypeNegotiationError(Exception):
+    """Raised when no compatible content types can be negotiated."""
+
+    def __init__(
+        self,
+        client_input_modes: list[str],
+        client_output_modes: list[str],
+        server_input_modes: list[str],
+        server_output_modes: list[str],
+        direction: str = "both",
+        message: str | None = None,
+    ) -> None:
+        self.client_input_modes = client_input_modes
+        self.client_output_modes = client_output_modes
+        self.server_input_modes = server_input_modes
+        self.server_output_modes = server_output_modes
+        self.direction = direction
+
+        if message is None:
+            if direction == "input":
+                message = (
+                    f"No compatible input content types. "
+                    f"Client supports: {client_input_modes}, "
+                    f"Server accepts: {server_input_modes}"
+                )
+            elif direction == "output":
+                message = (
+                    f"No compatible output content types. "
+                    f"Client accepts: {client_output_modes}, "
+                    f"Server produces: {server_output_modes}"
+                )
+            else:
+                message = (
+                    f"No compatible content types. "
+                    f"Input - Client: {client_input_modes}, Server: {server_input_modes}. "
+                    f"Output - Client: {client_output_modes}, Server: {server_output_modes}"
+                )
+
+        super().__init__(message)
+
+
+def _normalize_mime_type(mime_type: str) -> str:
+    """Normalize MIME type for comparison (lowercase, strip whitespace)."""
+    return mime_type.lower().strip()
+
+
+def _mime_types_compatible(client_type: str, server_type: str) -> bool:
+    """Check if two MIME types are compatible.
+
+    Handles wildcards like image/* matching image/png.
+    """
+    client_normalized = _normalize_mime_type(client_type)
+    server_normalized = _normalize_mime_type(server_type)
+
+    if client_normalized == server_normalized:
+        return True
+
+    if "*" in client_normalized or "*" in server_normalized:
+        client_parts = client_normalized.split("/")
+        server_parts = server_normalized.split("/")
+
+        if len(client_parts) == 2 and len(server_parts) == 2:
+            type_match = (
+                client_parts[0] == server_parts[0]
+                or client_parts[0] == "*"
+                or server_parts[0] == "*"
+            )
+            subtype_match = (
+                client_parts[1] == server_parts[1]
+                or client_parts[1] == "*"
+                or server_parts[1] == "*"
+            )
+            return type_match and subtype_match
+
+    return False
+
+
+def _find_compatible_modes(
+    client_modes: list[str], server_modes: list[str]
+) -> list[str]:
+    """Find compatible MIME types between client and server.
+
+    Returns modes in client preference order.
+    """
+    compatible = []
+    for client_mode in client_modes:
+        for server_mode in server_modes:
+            if _mime_types_compatible(client_mode, server_mode):
+                if "*" in client_mode and "*" not in server_mode:
+                    if server_mode not in compatible:
+                        compatible.append(server_mode)
+                else:
+                    if client_mode not in compatible:
+                        compatible.append(client_mode)
+                break
+    return compatible
+
+
+def _get_effective_modes(
+    agent_card: AgentCard,
+    skill_name: str | None = None,
+) -> tuple[list[str], list[str], AgentSkill | None]:
+    """Get effective input/output modes from agent card.
+
+    If skill_name is provided and the skill has custom modes, those are used.
+    Otherwise, falls back to agent card defaults.
+    """
+    skill: AgentSkill | None = None
+
+    if skill_name and agent_card.skills:
+        for s in agent_card.skills:
+            if s.name == skill_name or s.id == skill_name:
+                skill = s
+                break
+
+    if skill:
+        input_modes = (
+            skill.input_modes if skill.input_modes else agent_card.default_input_modes
+        )
+        output_modes = (
+            skill.output_modes
+            if skill.output_modes
+            else agent_card.default_output_modes
+        )
+    else:
+        input_modes = agent_card.default_input_modes
+        output_modes = agent_card.default_output_modes
+
+    return input_modes, output_modes, skill
+
+
+def negotiate_content_types(
+    agent_card: AgentCard,
+    client_input_modes: list[str] | None = None,
+    client_output_modes: list[str] | None = None,
+    skill_name: str | None = None,
+    emit_event: bool = True,
+    endpoint: str | None = None,
+    a2a_agent_name: str | None = None,
+    strict: bool = False,
+) -> NegotiatedContentTypes:
+    """Negotiate content types between client and server.
+
+    Args:
+        agent_card: The remote agent's card with capability info.
+        client_input_modes: MIME types the client can send. Defaults to text/plain and application/json.
+        client_output_modes: MIME types the client can accept. Defaults to text/plain and application/json.
+        skill_name: Optional skill to use for mode lookup.
+        emit_event: Whether to emit a content type negotiation event.
+        endpoint: Agent endpoint (for event metadata).
+        a2a_agent_name: Agent name (for event metadata).
+        strict: If True, raises error when no compatible types found.
+            If False, returns empty lists for incompatible directions.
+
+    Returns:
+        NegotiatedContentTypes with compatible input and output modes.
+
+    Raises:
+        ContentTypeNegotiationError: If strict=True and no compatible types found.
+    """
+    if client_input_modes is None:
+        client_input_modes = cast(list[str], DEFAULT_CLIENT_INPUT_MODES.copy())
+    if client_output_modes is None:
+        client_output_modes = cast(list[str], DEFAULT_CLIENT_OUTPUT_MODES.copy())
+
+    server_input_modes, server_output_modes, skill = _get_effective_modes(
+        agent_card, skill_name
+    )
+
+    compatible_input = _find_compatible_modes(client_input_modes, server_input_modes)
+    compatible_output = _find_compatible_modes(client_output_modes, server_output_modes)
+
+    if strict:
+        if not compatible_input and not compatible_output:
+            raise ContentTypeNegotiationError(
+                client_input_modes=client_input_modes,
+                client_output_modes=client_output_modes,
+                server_input_modes=server_input_modes,
+                server_output_modes=server_output_modes,
+            )
+        if not compatible_input:
+            raise ContentTypeNegotiationError(
+                client_input_modes=client_input_modes,
+                client_output_modes=client_output_modes,
+                server_input_modes=server_input_modes,
+                server_output_modes=server_output_modes,
+                direction="input",
+            )
+        if not compatible_output:
+            raise ContentTypeNegotiationError(
+                client_input_modes=client_input_modes,
+                client_output_modes=client_output_modes,
+                server_input_modes=server_input_modes,
+                server_output_modes=server_output_modes,
+                direction="output",
+            )
+
+    result = NegotiatedContentTypes(
+        input_modes=compatible_input,
+        output_modes=compatible_output,
+        effective_input_modes=server_input_modes,
+        effective_output_modes=server_output_modes,
+        skill_name=skill.name if skill else None,
+    )
+
+    if emit_event:
+        crewai_event_bus.emit(
+            None,
+            A2AContentTypeNegotiatedEvent(
+                endpoint=endpoint or agent_card.url,
+                a2a_agent_name=a2a_agent_name or agent_card.name,
+                skill_name=skill_name,
+                client_input_modes=client_input_modes,
+                client_output_modes=client_output_modes,
+                server_input_modes=server_input_modes,
+                server_output_modes=server_output_modes,
+                negotiated_input_modes=compatible_input,
+                negotiated_output_modes=compatible_output,
+                negotiation_success=bool(compatible_input and compatible_output),
+            ),
+        )
+
+    return result
+
+
+def validate_content_type(
+    content_type: str,
+    allowed_modes: list[str],
+) -> bool:
+    """Validate that a content type is allowed by a list of modes.
+
+    Args:
+        content_type: The MIME type to validate.
+        allowed_modes: List of allowed MIME types (may include wildcards).
+
+    Returns:
+        True if content_type is compatible with any allowed mode.
+    """
+    for mode in allowed_modes:
+        if _mime_types_compatible(content_type, mode):
+            return True
+    return False
+
+
+def get_part_content_type(part: Part) -> str:
+    """Extract MIME type from an A2A Part.
+
+    Args:
+        part: A Part object containing TextPart, DataPart, or FilePart.
+
+    Returns:
+        The MIME type string for this part.
+    """
+    root = part.root
+    if root.kind == "text":
+        return TEXT_PLAIN
+    if root.kind == "data":
+        return APPLICATION_JSON
+    if root.kind == "file":
+        return root.file.mime_type or APPLICATION_OCTET_STREAM
+    return APPLICATION_OCTET_STREAM
+
+
+def validate_message_parts(
+    parts: list[Part],
+    allowed_modes: list[str],
+) -> list[str]:
+    """Validate that all message parts have allowed content types.
+
+    Args:
+        parts: List of Parts from the incoming message.
+        allowed_modes: List of allowed MIME types (from default_input_modes).
+
+    Returns:
+        List of invalid content types found (empty if all valid).
+    """
+    invalid_types: list[str] = []
+    for part in parts:
+        content_type = get_part_content_type(part)
+        if not validate_content_type(content_type, allowed_modes):
+            if content_type not in invalid_types:
+                invalid_types.append(content_type)
+    return invalid_types

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

@@ -3,14 +3,18 @@
 from __future__ import annotations
 
 import asyncio
-from collections.abc import AsyncIterator, MutableMapping
+import base64
+from collections.abc import AsyncIterator, Callable, MutableMapping
 from contextlib import asynccontextmanager
-from typing import TYPE_CHECKING, Any, Literal
+import logging
+from typing import TYPE_CHECKING, Any, Final, Literal
 import uuid
 
 from a2a.client import Client, ClientConfig, ClientFactory
 from a2a.types import (
     AgentCard,
+    FilePart,
+    FileWithBytes,
     Message,
     Part,
     PushNotificationConfig as A2APushNotificationConfig,
@@ -20,18 +24,24 @@ from a2a.types import (
 import httpx
 from pydantic import BaseModel
 
-from crewai.a2a.auth.schemas import APIKeyAuth, HTTPDigestAuth
+from crewai.a2a.auth.client_schemes import APIKeyAuth, HTTPDigestAuth
 from crewai.a2a.auth.utils import (
     _auth_store,
     configure_auth_client,
     validate_auth_against_agent_card,
 )
+from crewai.a2a.config import ClientTransportConfig, GRPCClientConfig
+from crewai.a2a.extensions.registry import (
+    ExtensionsMiddleware,
+    validate_required_extensions,
+)
 from crewai.a2a.task_helpers import TaskStateResult
 from crewai.a2a.types import (
     HANDLER_REGISTRY,
     HandlerType,
     PartsDict,
     PartsMetadataDict,
+    TransportType,
 )
 from crewai.a2a.updates import (
     PollingConfig,
@@ -39,7 +49,20 @@ from crewai.a2a.updates import (
     StreamingHandler,
     UpdateConfig,
 )
-from crewai.a2a.utils.agent_card import _afetch_agent_card_cached
+from crewai.a2a.utils.agent_card import (
+    _afetch_agent_card_cached,
+    _get_tls_verify,
+    _prepare_auth_headers,
+)
+from crewai.a2a.utils.content_type import (
+    DEFAULT_CLIENT_OUTPUT_MODES,
+    negotiate_content_types,
+)
+from crewai.a2a.utils.transport import (
+    NegotiatedTransport,
+    TransportNegotiationError,
+    negotiate_transport,
+)
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.a2a_events import (
     A2AConversationStartedEvent,
@@ -49,10 +72,48 @@ from crewai.events.types.a2a_events import (
 )
 
 
+logger = logging.getLogger(__name__)
+
+
 if TYPE_CHECKING:
     from a2a.types import Message
 
-    from crewai.a2a.auth.schemas import AuthScheme
+    from crewai.a2a.auth.client_schemes import ClientAuthScheme
+
+
+_DEFAULT_TRANSPORT: Final[TransportType] = "JSONRPC"
+
+
+def _create_file_parts(input_files: dict[str, Any] | None) -> list[Part]:
+    """Convert FileInput dictionary to FilePart objects.
+
+    Args:
+        input_files: Dictionary mapping names to FileInput objects.
+
+    Returns:
+        List of Part objects containing FilePart data.
+    """
+    if not input_files:
+        return []
+
+    try:
+        import crewai_files  # noqa: F401
+    except ImportError:
+        logger.debug("crewai_files not installed, skipping file parts")
+        return []
+
+    parts: list[Part] = []
+    for name, file_input in input_files.items():
+        content_bytes = file_input.read()
+        content_base64 = base64.b64encode(content_bytes).decode()
+        file_with_bytes = FileWithBytes(
+            bytes=content_base64,
+            mimeType=file_input.content_type,
+            name=file_input.filename or name,
+        )
+        parts.append(Part(root=FilePart(file=file_with_bytes)))
+
+    return parts
 
 
 def get_handler(config: UpdateConfig | None) -> HandlerType:
@@ -71,8 +132,7 @@ def get_handler(config: UpdateConfig | None) -> HandlerType:
 
 def execute_a2a_delegation(
     endpoint: str,
-    transport_protocol: Literal["JSONRPC", "GRPC", "HTTP+JSON"],
-    auth: AuthScheme | None,
+    auth: ClientAuthScheme | None,
     timeout: int,
     task_description: str,
     context: str | None = None,
@@ -91,32 +151,24 @@ def execute_a2a_delegation(
     from_task: Any | None = None,
     from_agent: Any | None = None,
     skill_id: str | None = None,
+    client_extensions: list[str] | None = None,
+    transport: ClientTransportConfig | None = None,
+    accepted_output_modes: list[str] | None = None,
+    input_files: dict[str, Any] | None = None,
 ) -> TaskStateResult:
     """Execute a task delegation to a remote A2A agent synchronously.
 
-    This is the sync wrapper around aexecute_a2a_delegation. For async contexts,
-    use aexecute_a2a_delegation directly.
+    WARNING: This function blocks the entire thread by creating and running a new
+    event loop. Prefer using 'await aexecute_a2a_delegation()' in async contexts
+    for better performance and resource efficiency.
+
+    This is a synchronous wrapper around aexecute_a2a_delegation that creates a
+    new event loop to run the async implementation. It is provided for compatibility
+    with synchronous code paths only.
 
     Args:
-        endpoint: A2A agent endpoint URL (AgentCard URL)
-        transport_protocol: Optional A2A transport protocol (grpc, jsonrpc, http+json)
-        auth: Optional AuthScheme for authentication (Bearer, OAuth2, API Key, HTTP Basic/Digest)
-        timeout: Request timeout in seconds
-        task_description: The task to delegate
-        context: Optional context information
-        context_id: Context ID for correlating messages/tasks
-        task_id: Specific task identifier
-        reference_task_ids: List of related task IDs
-        metadata: Additional metadata (external_id, request_id, etc.)
-        extensions: Protocol extensions for custom fields
-        conversation_history: Previous Message objects from conversation
-        agent_id: Agent identifier for logging
-        agent_role: Role of the CrewAI agent delegating the task
-        agent_branch: Optional agent tree branch for logging
-        response_model: Optional Pydantic model for structured outputs
-        turn_number: Optional turn number for multi-turn conversations
-        endpoint: A2A agent endpoint URL.
-        auth: Optional AuthScheme for authentication.
+        endpoint: A2A agent endpoint URL (AgentCard URL).
+        auth: Optional ClientAuthScheme for authentication.
         timeout: Request timeout in seconds.
         task_description: The task to delegate.
         context: Optional context information.
@@ -135,10 +187,27 @@ def execute_a2a_delegation(
         from_task: Optional CrewAI Task object for event metadata.
         from_agent: Optional CrewAI Agent object for event metadata.
         skill_id: Optional skill ID to target a specific agent capability.
+        client_extensions: A2A protocol extension URIs the client supports.
+        transport: Transport configuration (preferred, supported transports, gRPC settings).
+        accepted_output_modes: MIME types the client can accept in responses.
+        input_files: Optional dictionary of files to send to remote agent.
 
     Returns:
         TaskStateResult with status, result/error, history, and agent_card.
+
+    Raises:
+        RuntimeError: If called from an async context with a running event loop.
     """
+    try:
+        asyncio.get_running_loop()
+        raise RuntimeError(
+            "execute_a2a_delegation() cannot be called from an async context. "
+            "Use 'await aexecute_a2a_delegation()' instead."
+        )
+    except RuntimeError as e:
+        if "no running event loop" not in str(e).lower():
+            raise
+
     loop = asyncio.new_event_loop()
     asyncio.set_event_loop(loop)
     try:
@@ -159,12 +228,15 @@ def execute_a2a_delegation(
                 agent_role=agent_role,
                 agent_branch=agent_branch,
                 response_model=response_model,
-                transport_protocol=transport_protocol,
                 turn_number=turn_number,
                 updates=updates,
                 from_task=from_task,
                 from_agent=from_agent,
                 skill_id=skill_id,
+                client_extensions=client_extensions,
+                transport=transport,
+                accepted_output_modes=accepted_output_modes,
+                input_files=input_files,
             )
         )
     finally:
@@ -176,8 +248,7 @@ def execute_a2a_delegation(
 
 async def aexecute_a2a_delegation(
     endpoint: str,
-    transport_protocol: Literal["JSONRPC", "GRPC", "HTTP+JSON"],
-    auth: AuthScheme | None,
+    auth: ClientAuthScheme | None,
     timeout: int,
     task_description: str,
     context: str | None = None,
@@ -196,6 +267,10 @@ async def aexecute_a2a_delegation(
     from_task: Any | None = None,
     from_agent: Any | None = None,
     skill_id: str | None = None,
+    client_extensions: list[str] | None = None,
+    transport: ClientTransportConfig | None = None,
+    accepted_output_modes: list[str] | None = None,
+    input_files: dict[str, Any] | None = None,
 ) -> TaskStateResult:
     """Execute a task delegation to a remote A2A agent asynchronously.
 
@@ -203,25 +278,8 @@ async def aexecute_a2a_delegation(
     in an async context (e.g., with Crew.akickoff() or agent.aexecute_task()).
 
     Args:
-        endpoint: A2A agent endpoint URL
-        transport_protocol: Optional A2A transport protocol (grpc, jsonrpc, http+json)
-        auth: Optional AuthScheme for authentication
-        timeout: Request timeout in seconds
-        task_description: Task to delegate
-        context: Optional context
-        context_id: Context ID for correlation
-        task_id: Specific task identifier
-        reference_task_ids: Related task IDs
-        metadata: Additional metadata
-        extensions: Protocol extensions
-        conversation_history: Previous Message objects
-        turn_number: Current turn number
-        agent_branch: Agent tree branch for logging
-        agent_id: Agent identifier for logging
-        agent_role: Agent role for logging
-        response_model: Optional Pydantic model for structured outputs
         endpoint: A2A agent endpoint URL.
-        auth: Optional AuthScheme for authentication.
+        auth: Optional ClientAuthScheme for authentication.
         timeout: Request timeout in seconds.
         task_description: The task to delegate.
         context: Optional context information.
@@ -240,6 +298,10 @@ async def aexecute_a2a_delegation(
         from_task: Optional CrewAI Task object for event metadata.
         from_agent: Optional CrewAI Agent object for event metadata.
         skill_id: Optional skill ID to target a specific agent capability.
+        client_extensions: A2A protocol extension URIs the client supports.
+        transport: Transport configuration (preferred, supported transports, gRPC settings).
+        accepted_output_modes: MIME types the client can accept in responses.
+        input_files: Optional dictionary of files to send to remote agent.
 
     Returns:
         TaskStateResult with status, result/error, history, and agent_card.
@@ -271,10 +333,13 @@ async def aexecute_a2a_delegation(
             agent_role=agent_role,
             response_model=response_model,
             updates=updates,
-            transport_protocol=transport_protocol,
             from_task=from_task,
             from_agent=from_agent,
             skill_id=skill_id,
+            client_extensions=client_extensions,
+            transport=transport,
+            accepted_output_modes=accepted_output_modes,
+            input_files=input_files,
         )
     except Exception as e:
         crewai_event_bus.emit(
@@ -294,7 +359,7 @@ async def aexecute_a2a_delegation(
         )
         raise
 
-    agent_card_data: dict[str, Any] = result.get("agent_card") or {}
+    agent_card_data = result.get("agent_card")
     crewai_event_bus.emit(
         agent_branch,
         A2ADelegationCompletedEvent(
@@ -306,7 +371,7 @@ async def aexecute_a2a_delegation(
             endpoint=endpoint,
             a2a_agent_name=result.get("a2a_agent_name"),
             agent_card=agent_card_data,
-            provider=agent_card_data.get("provider"),
+            provider=agent_card_data.get("provider") if agent_card_data else None,
             metadata=metadata,
             extensions=list(extensions.keys()) if extensions else None,
             from_task=from_task,
@@ -319,8 +384,7 @@ async def aexecute_a2a_delegation(
 
 async def _aexecute_a2a_delegation_impl(
     endpoint: str,
-    transport_protocol: Literal["JSONRPC", "GRPC", "HTTP+JSON"],
-    auth: AuthScheme | None,
+    auth: ClientAuthScheme | None,
     timeout: int,
     task_description: str,
     context: str | None,
@@ -340,8 +404,14 @@ async def _aexecute_a2a_delegation_impl(
     from_task: Any | None = None,
     from_agent: Any | None = None,
     skill_id: str | None = None,
+    client_extensions: list[str] | None = None,
+    transport: ClientTransportConfig | None = None,
+    accepted_output_modes: list[str] | None = None,
+    input_files: dict[str, Any] | None = None,
 ) -> TaskStateResult:
     """Internal async implementation of A2A delegation."""
+    if transport is None:
+        transport = ClientTransportConfig()
     if auth:
         auth_data = auth.model_dump_json(
             exclude={
@@ -351,22 +421,70 @@ async def _aexecute_a2a_delegation_impl(
                 "_authorization_callback",
             }
         )
-        auth_hash = hash((type(auth).__name__, auth_data))
+        auth_hash = _auth_store.compute_key(type(auth).__name__, auth_data)
     else:
-        auth_hash = 0
-    _auth_store[auth_hash] = auth
+        auth_hash = _auth_store.compute_key("none", endpoint)
+    _auth_store.set(auth_hash, auth)
     agent_card = await _afetch_agent_card_cached(
         endpoint=endpoint, auth_hash=auth_hash, timeout=timeout
     )
 
     validate_auth_against_agent_card(agent_card, auth)
 
-    headers: MutableMapping[str, str] = {}
-    if auth:
-        async with httpx.AsyncClient(timeout=timeout) as temp_auth_client:
-            if isinstance(auth, (HTTPDigestAuth, APIKeyAuth)):
-                configure_auth_client(auth, temp_auth_client)
-            headers = await auth.apply_auth(temp_auth_client, {})
+    unsupported_exts = validate_required_extensions(agent_card, client_extensions)
+    if unsupported_exts:
+        ext_uris = [ext.uri for ext in unsupported_exts]
+        raise ValueError(
+            f"Agent requires extensions not supported by client: {ext_uris}"
+        )
+
+    negotiated: NegotiatedTransport | None = None
+    effective_transport: TransportType = transport.preferred or _DEFAULT_TRANSPORT
+    effective_url = endpoint
+
+    client_transports: list[str] = (
+        list(transport.supported) if transport.supported else [_DEFAULT_TRANSPORT]
+    )
+
+    try:
+        negotiated = negotiate_transport(
+            agent_card=agent_card,
+            client_supported_transports=client_transports,
+            client_preferred_transport=transport.preferred,
+            endpoint=endpoint,
+            a2a_agent_name=agent_card.name,
+        )
+        effective_transport = negotiated.transport  # type: ignore[assignment]
+        effective_url = negotiated.url
+    except TransportNegotiationError as e:
+        logger.warning(
+            "Transport negotiation failed, using fallback",
+            extra={
+                "error": str(e),
+                "fallback_transport": effective_transport,
+                "fallback_url": effective_url,
+                "endpoint": endpoint,
+                "client_transports": client_transports,
+                "server_transports": [
+                    iface.transport for iface in agent_card.additional_interfaces or []
+                ]
+                + [agent_card.preferred_transport or "JSONRPC"],
+            },
+        )
+
+    effective_output_modes = accepted_output_modes or DEFAULT_CLIENT_OUTPUT_MODES.copy()
+
+    content_negotiated = negotiate_content_types(
+        agent_card=agent_card,
+        client_output_modes=accepted_output_modes,
+        skill_name=skill_id,
+        endpoint=endpoint,
+        a2a_agent_name=agent_card.name,
+    )
+    if content_negotiated.output_modes:
+        effective_output_modes = content_negotiated.output_modes
+
+    headers, _ = await _prepare_auth_headers(auth, timeout)
 
     a2a_agent_name = None
     if agent_card.name:
@@ -441,10 +559,13 @@ async def _aexecute_a2a_delegation_impl(
     if skill_id:
         message_metadata["skill_id"] = skill_id
 
+    parts_list: list[Part] = [Part(root=TextPart(**parts))]
+    parts_list.extend(_create_file_parts(input_files))
+
     message = Message(
         role=Role.user,
         message_id=str(uuid.uuid4()),
-        parts=[Part(root=TextPart(**parts))],
+        parts=parts_list,
         context_id=context_id,
         task_id=task_id,
         reference_task_ids=reference_task_ids,
@@ -513,15 +634,22 @@ async def _aexecute_a2a_delegation_impl(
 
     use_streaming = not use_polling and push_config_for_client is None
 
+    client_agent_card = agent_card
+    if effective_url != agent_card.url:
+        client_agent_card = agent_card.model_copy(update={"url": effective_url})
+
     async with _create_a2a_client(
-        agent_card=agent_card,
-        transport_protocol=transport_protocol,
+        agent_card=client_agent_card,
+        transport_protocol=effective_transport,
         timeout=timeout,
         headers=headers,
         streaming=use_streaming,
         auth=auth,
         use_polling=use_polling,
         push_notification_config=push_config_for_client,
+        client_extensions=client_extensions,
+        accepted_output_modes=effective_output_modes,  # type: ignore[arg-type]
+        grpc_config=transport.grpc,
     ) as client:
         result = await handler.execute(
             client=client,
@@ -535,6 +663,245 @@ async def _aexecute_a2a_delegation_impl(
         return result
 
 
+def _normalize_grpc_metadata(
+    metadata: tuple[tuple[str, str], ...] | None,
+) -> tuple[tuple[str, str], ...] | None:
+    """Lowercase all gRPC metadata keys.
+
+    gRPC requires lowercase metadata keys, but some libraries (like the A2A SDK)
+    use mixed-case headers like 'X-A2A-Extensions'. This normalizes them.
+    """
+    if metadata is None:
+        return None
+    return tuple((key.lower(), value) for key, value in metadata)
+
+
+def _create_grpc_interceptors(
+    auth_metadata: list[tuple[str, str]] | None = None,
+) -> list[Any]:
+    """Create gRPC interceptors for metadata normalization and auth injection.
+
+    Args:
+        auth_metadata: Optional auth metadata to inject into all calls.
+            Used for insecure channels that need auth (non-localhost without TLS).
+
+    Returns a list of interceptors that lowercase metadata keys for gRPC
+    compatibility. Must be called after grpc is imported.
+    """
+    import grpc.aio  # type: ignore[import-untyped]
+
+    def _merge_metadata(
+        existing: tuple[tuple[str, str], ...] | None,
+        auth: list[tuple[str, str]] | None,
+    ) -> tuple[tuple[str, str], ...] | None:
+        """Merge existing metadata with auth metadata and normalize keys."""
+        merged: list[tuple[str, str]] = []
+        if existing:
+            merged.extend(existing)
+        if auth:
+            merged.extend(auth)
+        if not merged:
+            return None
+        return tuple((key.lower(), value) for key, value in merged)
+
+    def _inject_metadata(client_call_details: Any) -> Any:
+        """Inject merged metadata into call details."""
+        return client_call_details._replace(
+            metadata=_merge_metadata(client_call_details.metadata, auth_metadata)
+        )
+
+    class MetadataUnaryUnary(grpc.aio.UnaryUnaryClientInterceptor):  # type: ignore[misc,no-any-unimported]
+        """Interceptor for unary-unary calls that injects auth metadata."""
+
+        async def intercept_unary_unary(  # type: ignore[no-untyped-def]
+            self, continuation, client_call_details, request
+        ):
+            """Intercept unary-unary call and inject metadata."""
+            return await continuation(_inject_metadata(client_call_details), request)
+
+    class MetadataUnaryStream(grpc.aio.UnaryStreamClientInterceptor):  # type: ignore[misc,no-any-unimported]
+        """Interceptor for unary-stream calls that injects auth metadata."""
+
+        async def intercept_unary_stream(  # type: ignore[no-untyped-def]
+            self, continuation, client_call_details, request
+        ):
+            """Intercept unary-stream call and inject metadata."""
+            return await continuation(_inject_metadata(client_call_details), request)
+
+    class MetadataStreamUnary(grpc.aio.StreamUnaryClientInterceptor):  # type: ignore[misc,no-any-unimported]
+        """Interceptor for stream-unary calls that injects auth metadata."""
+
+        async def intercept_stream_unary(  # type: ignore[no-untyped-def]
+            self, continuation, client_call_details, request_iterator
+        ):
+            """Intercept stream-unary call and inject metadata."""
+            return await continuation(
+                _inject_metadata(client_call_details), request_iterator
+            )
+
+    class MetadataStreamStream(grpc.aio.StreamStreamClientInterceptor):  # type: ignore[misc,no-any-unimported]
+        """Interceptor for stream-stream calls that injects auth metadata."""
+
+        async def intercept_stream_stream(  # type: ignore[no-untyped-def]
+            self, continuation, client_call_details, request_iterator
+        ):
+            """Intercept stream-stream call and inject metadata."""
+            return await continuation(
+                _inject_metadata(client_call_details), request_iterator
+            )
+
+    return [
+        MetadataUnaryUnary(),
+        MetadataUnaryStream(),
+        MetadataStreamUnary(),
+        MetadataStreamStream(),
+    ]
+
+
+def _create_grpc_channel_factory(
+    grpc_config: GRPCClientConfig,
+    auth: ClientAuthScheme | None = None,
+) -> Callable[[str], Any]:
+    """Create a gRPC channel factory with the given configuration.
+
+    Args:
+        grpc_config: gRPC client configuration with channel options.
+        auth: Optional ClientAuthScheme for TLS and auth configuration.
+
+    Returns:
+        A callable that creates gRPC channels from URLs.
+    """
+    try:
+        import grpc
+    except ImportError as e:
+        raise ImportError(
+            "gRPC transport requires grpcio. Install with: pip install a2a-sdk[grpc]"
+        ) from e
+
+    auth_metadata: list[tuple[str, str]] = []
+
+    if auth is not None:
+        from crewai.a2a.auth.client_schemes import (
+            APIKeyAuth,
+            BearerTokenAuth,
+            HTTPBasicAuth,
+            HTTPDigestAuth,
+            OAuth2AuthorizationCode,
+            OAuth2ClientCredentials,
+        )
+
+        if isinstance(auth, HTTPDigestAuth):
+            raise ValueError(
+                "HTTPDigestAuth is not supported with gRPC transport. "
+                "Digest authentication requires HTTP challenge-response flow. "
+                "Use BearerTokenAuth, HTTPBasicAuth, APIKeyAuth (header), or OAuth2 instead."
+            )
+        if isinstance(auth, APIKeyAuth) and auth.location in ("query", "cookie"):
+            raise ValueError(
+                f"APIKeyAuth with location='{auth.location}' is not supported with gRPC transport. "
+                "gRPC only supports header-based authentication. "
+                "Use APIKeyAuth with location='header' instead."
+            )
+
+        if isinstance(auth, BearerTokenAuth):
+            auth_metadata.append(("authorization", f"Bearer {auth.token}"))
+        elif isinstance(auth, HTTPBasicAuth):
+            import base64
+
+            basic_credentials = f"{auth.username}:{auth.password}"
+            encoded = base64.b64encode(basic_credentials.encode()).decode()
+            auth_metadata.append(("authorization", f"Basic {encoded}"))
+        elif isinstance(auth, APIKeyAuth) and auth.location == "header":
+            header_name = auth.name.lower()
+            auth_metadata.append((header_name, auth.api_key))
+        elif isinstance(auth, (OAuth2ClientCredentials, OAuth2AuthorizationCode)):
+            if auth._access_token:
+                auth_metadata.append(("authorization", f"Bearer {auth._access_token}"))
+
+    def factory(url: str) -> Any:
+        """Create a gRPC channel for the given URL."""
+        target = url
+        use_tls = False
+
+        if url.startswith("grpcs://"):
+            target = url[8:]
+            use_tls = True
+        elif url.startswith("grpc://"):
+            target = url[7:]
+        elif url.startswith("https://"):
+            target = url[8:]
+            use_tls = True
+        elif url.startswith("http://"):
+            target = url[7:]
+
+        options: list[tuple[str, Any]] = []
+        if grpc_config.max_send_message_length is not None:
+            options.append(
+                ("grpc.max_send_message_length", grpc_config.max_send_message_length)
+            )
+        if grpc_config.max_receive_message_length is not None:
+            options.append(
+                (
+                    "grpc.max_receive_message_length",
+                    grpc_config.max_receive_message_length,
+                )
+            )
+        if grpc_config.keepalive_time_ms is not None:
+            options.append(("grpc.keepalive_time_ms", grpc_config.keepalive_time_ms))
+        if grpc_config.keepalive_timeout_ms is not None:
+            options.append(
+                ("grpc.keepalive_timeout_ms", grpc_config.keepalive_timeout_ms)
+            )
+
+        channel_credentials = None
+        if auth and hasattr(auth, "tls") and auth.tls:
+            channel_credentials = auth.tls.get_grpc_credentials()
+        elif use_tls:
+            channel_credentials = grpc.ssl_channel_credentials()
+
+        if channel_credentials and auth_metadata:
+
+            class AuthMetadataPlugin(grpc.AuthMetadataPlugin):  # type: ignore[misc,no-any-unimported]
+                """gRPC auth metadata plugin that adds auth headers as metadata."""
+
+                def __init__(self, metadata: list[tuple[str, str]]) -> None:
+                    self._metadata = tuple(metadata)
+
+                def __call__(  # type: ignore[no-any-unimported]
+                    self,
+                    context: grpc.AuthMetadataContext,
+                    callback: grpc.AuthMetadataPluginCallback,
+                ) -> None:
+                    callback(self._metadata, None)
+
+            call_creds = grpc.metadata_call_credentials(
+                AuthMetadataPlugin(auth_metadata)
+            )
+            credentials = grpc.composite_channel_credentials(
+                channel_credentials, call_creds
+            )
+            interceptors = _create_grpc_interceptors()
+            return grpc.aio.secure_channel(
+                target, credentials, options=options or None, interceptors=interceptors
+            )
+        if channel_credentials:
+            interceptors = _create_grpc_interceptors()
+            return grpc.aio.secure_channel(
+                target,
+                channel_credentials,
+                options=options or None,
+                interceptors=interceptors,
+            )
+        interceptors = _create_grpc_interceptors(
+            auth_metadata=auth_metadata if auth_metadata else None
+        )
+        return grpc.aio.insecure_channel(
+            target, options=options or None, interceptors=interceptors
+        )
+
+    return factory
+
+
 @asynccontextmanager
 async def _create_a2a_client(
     agent_card: AgentCard,
@@ -542,9 +909,12 @@ async def _create_a2a_client(
     timeout: int,
     headers: MutableMapping[str, str],
     streaming: bool,
-    auth: AuthScheme | None = None,
+    auth: ClientAuthScheme | None = None,
     use_polling: bool = False,
     push_notification_config: PushNotificationConfig | None = None,
+    client_extensions: list[str] | None = None,
+    accepted_output_modes: list[str] | None = None,
+    grpc_config: GRPCClientConfig | None = None,
 ) -> AsyncIterator[Client]:
     """Create and configure an A2A client.
 
@@ -554,16 +924,21 @@ async def _create_a2a_client(
         timeout: Request timeout in seconds.
         headers: HTTP headers (already with auth applied).
         streaming: Enable streaming responses.
-        auth: Optional AuthScheme for client configuration.
+        auth: Optional ClientAuthScheme for client configuration.
         use_polling: Enable polling mode.
         push_notification_config: Optional push notification config.
+        client_extensions: A2A protocol extension URIs to declare support for.
+        accepted_output_modes: MIME types the client can accept in responses.
+        grpc_config: Optional gRPC client configuration.
 
     Yields:
         Configured A2A client instance.
     """
+    verify = _get_tls_verify(auth)
     async with httpx.AsyncClient(
         timeout=timeout,
         headers=headers,
+        verify=verify,
     ) as httpx_client:
         if auth and isinstance(auth, (HTTPDigestAuth, APIKeyAuth)):
             configure_auth_client(auth, httpx_client)
@@ -579,15 +954,27 @@ async def _create_a2a_client(
                 )
             )
 
+        grpc_channel_factory = None
+        if transport_protocol == "GRPC":
+            grpc_channel_factory = _create_grpc_channel_factory(
+                grpc_config or GRPCClientConfig(),
+                auth=auth,
+            )
+
         config = ClientConfig(
             httpx_client=httpx_client,
             supported_transports=[transport_protocol],
             streaming=streaming and not use_polling,
             polling=use_polling,
-            accepted_output_modes=["application/json"],
+            accepted_output_modes=accepted_output_modes or DEFAULT_CLIENT_OUTPUT_MODES,  # type: ignore[arg-type]
             push_notification_configs=push_configs,
+            grpc_channel_factory=grpc_channel_factory,
         )
 
         factory = ClientFactory(config)
         client = factory.create(agent_card)
+
+        if client_extensions:
+            await client.add_request_middleware(ExtensionsMiddleware(client_extensions))
+
         yield client

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

@@ -0,0 +1,131 @@
+"""Structured JSON logging utilities for A2A module."""
+
+from __future__ import annotations
+
+from contextvars import ContextVar
+from datetime import datetime, timezone
+import json
+import logging
+from typing import Any
+
+
+_log_context: ContextVar[dict[str, Any] | None] = ContextVar(
+    "log_context", default=None
+)
+
+
+class JSONFormatter(logging.Formatter):
+    """JSON formatter for structured logging.
+
+    Outputs logs as JSON with consistent fields for log aggregators.
+    """
+
+    def format(self, record: logging.LogRecord) -> str:
+        """Format log record as JSON string."""
+        log_data: dict[str, Any] = {
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "level": record.levelname,
+            "logger": record.name,
+            "message": record.getMessage(),
+        }
+
+        if record.exc_info:
+            log_data["exception"] = self.formatException(record.exc_info)
+
+        context = _log_context.get()
+        if context is not None:
+            log_data.update(context)
+
+        if hasattr(record, "task_id"):
+            log_data["task_id"] = record.task_id
+        if hasattr(record, "context_id"):
+            log_data["context_id"] = record.context_id
+        if hasattr(record, "agent"):
+            log_data["agent"] = record.agent
+        if hasattr(record, "endpoint"):
+            log_data["endpoint"] = record.endpoint
+        if hasattr(record, "extension"):
+            log_data["extension"] = record.extension
+        if hasattr(record, "error"):
+            log_data["error"] = record.error
+
+        for key, value in record.__dict__.items():
+            if key.startswith("_") or key in (
+                "name",
+                "msg",
+                "args",
+                "created",
+                "filename",
+                "funcName",
+                "levelname",
+                "levelno",
+                "lineno",
+                "module",
+                "msecs",
+                "pathname",
+                "process",
+                "processName",
+                "relativeCreated",
+                "stack_info",
+                "exc_info",
+                "exc_text",
+                "thread",
+                "threadName",
+                "taskName",
+                "message",
+            ):
+                continue
+            if key not in log_data:
+                log_data[key] = value
+
+        return json.dumps(log_data, default=str)
+
+
+class LogContext:
+    """Context manager for adding fields to all logs within a scope.
+
+    Example:
+        with LogContext(task_id="abc", context_id="xyz"):
+            logger.info("Processing task")  # Includes task_id and context_id
+    """
+
+    def __init__(self, **fields: Any) -> None:
+        self._fields = fields
+        self._token: Any = None
+
+    def __enter__(self) -> LogContext:
+        current = _log_context.get() or {}
+        new_context = {**current, **self._fields}
+        self._token = _log_context.set(new_context)
+        return self
+
+    def __exit__(self, *args: Any) -> None:
+        _log_context.reset(self._token)
+
+
+def configure_json_logging(logger_name: str = "crewai.a2a") -> None:
+    """Configure JSON logging for the A2A module.
+
+    Args:
+        logger_name: Logger name to configure.
+    """
+    logger = logging.getLogger(logger_name)
+
+    for handler in logger.handlers[:]:
+        logger.removeHandler(handler)
+
+    handler = logging.StreamHandler()
+    handler.setFormatter(JSONFormatter())
+    logger.addHandler(handler)
+
+
+def get_logger(name: str) -> logging.Logger:
+    """Get a logger configured for structured JSON output.
+
+    Args:
+        name: Logger name.
+
+    Returns:
+        Configured logger instance.
+    """
+    return logging.getLogger(name)

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

@@ -7,26 +7,40 @@ import base64
 from collections.abc import Callable, Coroutine
 from datetime import datetime
 from functools import wraps
+import json
 import logging
 import os
-from typing import TYPE_CHECKING, Any, ParamSpec, TypeVar, cast
+from typing import TYPE_CHECKING, Any, ParamSpec, TypeVar, TypedDict, cast
 from urllib.parse import urlparse
 
 from a2a.server.agent_execution import RequestContext
 from a2a.server.events import EventQueue
 from a2a.types import (
+    Artifact,
+    FileWithBytes,
+    FileWithUri,
     InternalError,
     InvalidParamsError,
     Message,
+    Part,
     Task as A2ATask,
     TaskState,
     TaskStatus,
     TaskStatusUpdateEvent,
 )
-from a2a.utils import new_agent_text_message, new_text_artifact
+from a2a.utils import (
+    get_data_parts,
+    get_file_parts,
+    new_agent_text_message,
+    new_data_artifact,
+    new_text_artifact,
+)
 from a2a.utils.errors import ServerError
 from aiocache import SimpleMemoryCache, caches  # type: ignore[import-untyped]
+from pydantic import BaseModel
 
+from crewai.a2a.utils.agent_card import _get_server_config
+from crewai.a2a.utils.content_type import validate_message_parts
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.a2a_events import (
     A2AServerTaskCanceledEvent,
@@ -35,9 +49,11 @@ from crewai.events.types.a2a_events import (
     A2AServerTaskStartedEvent,
 )
 from crewai.task import Task
+from crewai.utilities.pydantic_schema_utils import create_model_from_schema
 
 
 if TYPE_CHECKING:
+    from crewai.a2a.extensions.server import ExtensionContext, ServerExtensionRegistry
     from crewai.agent import Agent
 
 
@@ -47,7 +63,17 @@ P = ParamSpec("P")
 T = TypeVar("T")
 
 
-def _parse_redis_url(url: str) -> dict[str, Any]:
+class RedisCacheConfig(TypedDict, total=False):
+    """Configuration for aiocache Redis backend."""
+
+    cache: str
+    endpoint: str
+    port: int
+    db: int
+    password: str
+
+
+def _parse_redis_url(url: str) -> RedisCacheConfig:
     """Parse a Redis URL into aiocache configuration.
 
     Args:
@@ -56,9 +82,8 @@ def _parse_redis_url(url: str) -> dict[str, Any]:
     Returns:
         Configuration dict for aiocache.RedisCache.
     """
-
     parsed = urlparse(url)
-    config: dict[str, Any] = {
+    config: RedisCacheConfig = {
         "cache": "aiocache.RedisCache",
         "endpoint": parsed.hostname or "localhost",
         "port": parsed.port or 6379,
@@ -138,7 +163,10 @@ def cancellable(
                     if message["type"] == "message":
                         return True
             except (OSError, ConnectionError) as e:
-                logger.warning("Cancel watcher error for task_id=%s: %s", task_id, e)
+                logger.warning(
+                    "Cancel watcher Redis error, falling back to polling",
+                    extra={"task_id": task_id, "error": str(e)},
+                )
                 return await poll_for_cancel()
             return False
 
@@ -166,7 +194,98 @@ def cancellable(
     return wrapper
 
 
-@cancellable
+def _convert_a2a_files_to_file_inputs(
+    a2a_files: list[FileWithBytes | FileWithUri],
+) -> dict[str, Any]:
+    """Convert a2a file types to crewai FileInput dict.
+
+    Args:
+        a2a_files: List of FileWithBytes or FileWithUri from a2a SDK.
+
+    Returns:
+        Dictionary mapping file names to FileInput objects.
+    """
+    try:
+        from crewai_files import File, FileBytes
+    except ImportError:
+        logger.debug("crewai_files not installed, returning empty file dict")
+        return {}
+
+    file_dict: dict[str, Any] = {}
+    for idx, a2a_file in enumerate(a2a_files):
+        if isinstance(a2a_file, FileWithBytes):
+            file_bytes = base64.b64decode(a2a_file.bytes)
+            name = a2a_file.name or f"file_{idx}"
+            file_source = FileBytes(data=file_bytes, filename=a2a_file.name)
+            file_dict[name] = File(source=file_source)
+        elif isinstance(a2a_file, FileWithUri):
+            name = a2a_file.name or f"file_{idx}"
+            file_dict[name] = File(source=a2a_file.uri)
+
+    return file_dict
+
+
+def _extract_response_schema(parts: list[Part]) -> dict[str, Any] | None:
+    """Extract response schema from message parts metadata.
+
+    The client may include a JSON schema in TextPart metadata to specify
+    the expected response format (see delegation.py line 463).
+
+    Args:
+        parts: List of message parts.
+
+    Returns:
+        JSON schema dict if found, None otherwise.
+    """
+    for part in parts:
+        if part.root.kind == "text" and part.root.metadata:
+            schema = part.root.metadata.get("schema")
+            if schema and isinstance(schema, dict):
+                return schema  # type: ignore[no-any-return]
+    return None
+
+
+def _create_result_artifact(
+    result: Any,
+    task_id: str,
+) -> Artifact:
+    """Create artifact from task result, using DataPart for structured data.
+
+    Args:
+        result: The task execution result.
+        task_id: The task ID for naming the artifact.
+
+    Returns:
+        Artifact with appropriate part type (DataPart for dict/Pydantic, TextPart for strings).
+    """
+    artifact_name = f"result_{task_id}"
+    if isinstance(result, dict):
+        return new_data_artifact(artifact_name, result)
+    if isinstance(result, BaseModel):
+        return new_data_artifact(artifact_name, result.model_dump())
+    return new_text_artifact(artifact_name, str(result))
+
+
+def _build_task_description(
+    user_message: str,
+    structured_inputs: list[dict[str, Any]],
+) -> str:
+    """Build task description including structured data if present.
+
+    Args:
+        user_message: The original user message text.
+        structured_inputs: List of structured data from DataParts.
+
+    Returns:
+        Task description with structured data appended if present.
+    """
+    if not structured_inputs:
+        return user_message
+
+    structured_json = json.dumps(structured_inputs, indent=2)
+    return f"{user_message}\n\nStructured Data:\n{structured_json}"
+
+
 async def execute(
     agent: Agent,
     context: RequestContext,
@@ -178,15 +297,54 @@ async def execute(
         agent: The CrewAI agent to execute the task.
         context: The A2A request context containing the user's message.
         event_queue: The event queue for sending responses back.
-
-    TODOs:
-        * need to impl both of structured output and file inputs, depends on `file_inputs` for
-          `crewai.task.Task`, pass the below two to Task. both utils in `a2a.utils.parts`
-        * structured outputs ingestion, `structured_inputs = get_data_parts(parts=context.message.parts)`
-        * file inputs ingestion, `file_inputs = get_file_parts(parts=context.message.parts)`
     """
+    await _execute_impl(agent, context, event_queue, None, None)
+
+
+@cancellable
+async def _execute_impl(
+    agent: Agent,
+    context: RequestContext,
+    event_queue: EventQueue,
+    extension_registry: ServerExtensionRegistry | None,
+    extension_context: ExtensionContext | None,
+) -> None:
+    """Internal implementation for task execution with optional extensions."""
+    server_config = _get_server_config(agent)
+    if context.message and context.message.parts and server_config:
+        allowed_modes = server_config.default_input_modes
+        invalid_types = validate_message_parts(context.message.parts, allowed_modes)
+        if invalid_types:
+            raise ServerError(
+                InvalidParamsError(
+                    message=f"Unsupported content type(s): {', '.join(invalid_types)}. "
+                    f"Supported: {', '.join(allowed_modes)}"
+                )
+            )
+
+    if extension_registry and extension_context:
+        await extension_registry.invoke_on_request(extension_context)
 
     user_message = context.get_user_input()
+
+    response_model: type[BaseModel] | None = None
+    structured_inputs: list[dict[str, Any]] = []
+    a2a_files: list[FileWithBytes | FileWithUri] = []
+
+    if context.message and context.message.parts:
+        schema = _extract_response_schema(context.message.parts)
+        if schema:
+            try:
+                response_model = create_model_from_schema(schema)
+            except Exception as e:
+                logger.debug(
+                    "Failed to create response model from schema",
+                    extra={"error": str(e), "schema_title": schema.get("title")},
+                )
+
+        structured_inputs = get_data_parts(context.message.parts)
+        a2a_files = get_file_parts(context.message.parts)
+
     task_id = context.task_id
     context_id = context.context_id
     if task_id is None or context_id is None:
@@ -203,9 +361,11 @@ async def execute(
         raise ServerError(InvalidParamsError(message=msg)) from None
 
     task = Task(
-        description=user_message,
+        description=_build_task_description(user_message, structured_inputs),
         expected_output="Response to the user's request",
         agent=agent,
+        response_model=response_model,
+        input_files=_convert_a2a_files_to_file_inputs(a2a_files),
     )
 
     crewai_event_bus.emit(
@@ -220,6 +380,10 @@ async def execute(
 
     try:
         result = await agent.aexecute_task(task=task, tools=agent.tools)
+        if extension_registry and extension_context:
+            result = await extension_registry.invoke_on_response(
+                extension_context, result
+            )
         result_str = str(result)
         history: list[Message] = [context.message] if context.message else []
         history.append(new_agent_text_message(result_str, context_id, task_id))
@@ -227,8 +391,8 @@ async def execute(
             A2ATask(
                 id=task_id,
                 context_id=context_id,
-                status=TaskStatus(state=TaskState.input_required),
-                artifacts=[new_text_artifact(result_str, f"result_{task_id}")],
+                status=TaskStatus(state=TaskState.completed),
+                artifacts=[_create_result_artifact(result, task_id)],
                 history=history,
             )
         )
@@ -269,6 +433,27 @@ async def execute(
         ) from e
 
 
+async def execute_with_extensions(
+    agent: Agent,
+    context: RequestContext,
+    event_queue: EventQueue,
+    extension_registry: ServerExtensionRegistry,
+    extension_context: ExtensionContext,
+) -> None:
+    """Execute an A2A task with extension hooks.
+
+    Args:
+        agent: The CrewAI agent to execute the task.
+        context: The A2A request context containing the user's message.
+        event_queue: The event queue for sending responses back.
+        extension_registry: Registry of server extensions.
+        extension_context: Context for extension hooks.
+    """
+    await _execute_impl(
+        agent, context, event_queue, extension_registry, extension_context
+    )
+
+
 async def cancel(
     context: RequestContext,
     event_queue: EventQueue,

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

@@ -0,0 +1,215 @@
+"""Transport negotiation utilities for A2A protocol.
+
+This module provides functionality for negotiating the transport protocol
+between an A2A client and server based on their respective capabilities
+and preferences.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Final, Literal
+
+from a2a.types import AgentCard, AgentInterface
+
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.a2a_events import A2ATransportNegotiatedEvent
+
+
+TransportProtocol = Literal["JSONRPC", "GRPC", "HTTP+JSON"]
+NegotiationSource = Literal["client_preferred", "server_preferred", "fallback"]
+
+JSONRPC_TRANSPORT: Literal["JSONRPC"] = "JSONRPC"
+GRPC_TRANSPORT: Literal["GRPC"] = "GRPC"
+HTTP_JSON_TRANSPORT: Literal["HTTP+JSON"] = "HTTP+JSON"
+
+DEFAULT_TRANSPORT_PREFERENCE: Final[list[TransportProtocol]] = [
+    JSONRPC_TRANSPORT,
+    GRPC_TRANSPORT,
+    HTTP_JSON_TRANSPORT,
+]
+
+
+@dataclass
+class NegotiatedTransport:
+    """Result of transport negotiation.
+
+    Attributes:
+        transport: The negotiated transport protocol.
+        url: The URL to use for this transport.
+        source: How the transport was selected ('preferred', 'additional', 'fallback').
+    """
+
+    transport: str
+    url: str
+    source: NegotiationSource
+
+
+class TransportNegotiationError(Exception):
+    """Raised when no compatible transport can be negotiated."""
+
+    def __init__(
+        self,
+        client_transports: list[str],
+        server_transports: list[str],
+        message: str | None = None,
+    ) -> None:
+        """Initialize the error with negotiation details.
+
+        Args:
+            client_transports: Transports supported by the client.
+            server_transports: Transports supported by the server.
+            message: Optional custom error message.
+        """
+        self.client_transports = client_transports
+        self.server_transports = server_transports
+        if message is None:
+            message = (
+                f"No compatible transport found. "
+                f"Client supports: {client_transports}. "
+                f"Server supports: {server_transports}."
+            )
+        super().__init__(message)
+
+
+def _get_server_interfaces(agent_card: AgentCard) -> list[AgentInterface]:
+    """Extract all available interfaces from an AgentCard.
+
+    Creates a unified list of interfaces including the primary URL and
+    any additional interfaces declared by the agent.
+
+    Args:
+        agent_card: The agent's card containing transport information.
+
+    Returns:
+        List of AgentInterface objects representing all available endpoints.
+    """
+    interfaces: list[AgentInterface] = []
+
+    primary_transport = agent_card.preferred_transport or JSONRPC_TRANSPORT
+    interfaces.append(
+        AgentInterface(
+            transport=primary_transport,
+            url=agent_card.url,
+        )
+    )
+
+    if agent_card.additional_interfaces:
+        for interface in agent_card.additional_interfaces:
+            is_duplicate = any(
+                i.url == interface.url and i.transport == interface.transport
+                for i in interfaces
+            )
+            if not is_duplicate:
+                interfaces.append(interface)
+
+    return interfaces
+
+
+def negotiate_transport(
+    agent_card: AgentCard,
+    client_supported_transports: list[str] | None = None,
+    client_preferred_transport: str | None = None,
+    emit_event: bool = True,
+    endpoint: str | None = None,
+    a2a_agent_name: str | None = None,
+) -> NegotiatedTransport:
+    """Negotiate the transport protocol between client and server.
+
+    Compares the client's supported transports with the server's available
+    interfaces to find a compatible transport and URL.
+
+    Negotiation logic:
+    1. If client_preferred_transport is set and server supports it → use it
+    2. Otherwise, if server's preferred is in client's supported → use server's
+    3. Otherwise, find first match from client's supported in server's interfaces
+
+    Args:
+        agent_card: The server's AgentCard with transport information.
+        client_supported_transports: Transports the client can use.
+            Defaults to ["JSONRPC"] if not specified.
+        client_preferred_transport: Client's preferred transport. If set and
+            server supports it, takes priority over server preference.
+        emit_event: Whether to emit a transport negotiation event.
+        endpoint: Original endpoint URL for event metadata.
+        a2a_agent_name: Agent name for event metadata.
+
+    Returns:
+        NegotiatedTransport with the selected transport, URL, and source.
+
+    Raises:
+        TransportNegotiationError: If no compatible transport is found.
+    """
+    if client_supported_transports is None:
+        client_supported_transports = [JSONRPC_TRANSPORT]
+
+    client_transports = [t.upper() for t in client_supported_transports]
+    client_preferred = (
+        client_preferred_transport.upper() if client_preferred_transport else None
+    )
+
+    server_interfaces = _get_server_interfaces(agent_card)
+    server_transports = [i.transport.upper() for i in server_interfaces]
+
+    transport_to_interface: dict[str, AgentInterface] = {}
+    for interface in server_interfaces:
+        transport_upper = interface.transport.upper()
+        if transport_upper not in transport_to_interface:
+            transport_to_interface[transport_upper] = interface
+
+    result: NegotiatedTransport | None = None
+
+    if client_preferred and client_preferred in transport_to_interface:
+        interface = transport_to_interface[client_preferred]
+        result = NegotiatedTransport(
+            transport=interface.transport,
+            url=interface.url,
+            source="client_preferred",
+        )
+    else:
+        server_preferred = (agent_card.preferred_transport or JSONRPC_TRANSPORT).upper()
+        if (
+            server_preferred in client_transports
+            and server_preferred in transport_to_interface
+        ):
+            interface = transport_to_interface[server_preferred]
+            result = NegotiatedTransport(
+                transport=interface.transport,
+                url=interface.url,
+                source="server_preferred",
+            )
+        else:
+            for transport in client_transports:
+                if transport in transport_to_interface:
+                    interface = transport_to_interface[transport]
+                    result = NegotiatedTransport(
+                        transport=interface.transport,
+                        url=interface.url,
+                        source="fallback",
+                    )
+                    break
+
+    if result is None:
+        raise TransportNegotiationError(
+            client_transports=client_transports,
+            server_transports=server_transports,
+        )
+
+    if emit_event:
+        crewai_event_bus.emit(
+            None,
+            A2ATransportNegotiatedEvent(
+                endpoint=endpoint or agent_card.url,
+                a2a_agent_name=a2a_agent_name or agent_card.name,
+                negotiated_transport=result.transport,
+                negotiated_url=result.url,
+                source=result.source,
+                client_supported_transports=client_transports,
+                server_supported_transports=server_transports,
+                server_preferred_transport=agent_card.preferred_transport
+                or JSONRPC_TRANSPORT,
+                client_preferred_transport=client_preferred,
+            ),
+        )
+
+    return result

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

@@ -94,6 +94,12 @@ from crewai.utilities.token_counter_callback import TokenCalcHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
 
+try:
+    from crewai.a2a.types import AgentResponseProtocol
+except ImportError:
+    AgentResponseProtocol = None  # type: ignore[assignment, misc]
+
+
 if TYPE_CHECKING:
     from crewai_files import FileInput
     from crewai_tools import CodeInterpreterTool
@@ -490,9 +496,22 @@ class Agent(BaseAgent):
             self._rpm_controller.stop_rpm_counter()
 
         result = process_tool_results(self, result)
+
+        output_for_event = result
+        if (
+            AgentResponseProtocol is not None
+            and isinstance(result, BaseModel)
+            and isinstance(result, AgentResponseProtocol)
+        ):
+            output_for_event = str(result.message)
+        elif not isinstance(result, str):
+            output_for_event = str(result)
+
         crewai_event_bus.emit(
             self,
-            event=AgentExecutionCompletedEvent(agent=self, task=task, output=result),
+            event=AgentExecutionCompletedEvent(
+                agent=self, task=task, output=output_for_event
+            ),
         )
 
         save_last_messages(self)
@@ -709,9 +728,22 @@ class Agent(BaseAgent):
             self._rpm_controller.stop_rpm_counter()
 
         result = process_tool_results(self, result)
+
+        output_for_event = result
+        if (
+            AgentResponseProtocol is not None
+            and isinstance(result, BaseModel)
+            and isinstance(result, AgentResponseProtocol)
+        ):
+            output_for_event = str(result.message)
+        elif not isinstance(result, str):
+            output_for_event = str(result)
+
         crewai_event_bus.emit(
             self,
-            event=AgentExecutionCompletedEvent(agent=self, task=task, output=result),
+            event=AgentExecutionCompletedEvent(
+                agent=self, task=task, output=output_for_event
+            ),
         )
 
         save_last_messages(self)
@@ -1897,8 +1929,16 @@ class Agent(BaseAgent):
         else:
             usage_metrics = self._token_process.get_summary()
 
+        raw_str = (
+            raw_output
+            if isinstance(raw_output, str)
+            else raw_output.model_dump_json()
+            if isinstance(raw_output, BaseModel)
+            else str(raw_output)
+        )
+
         return LiteAgentOutput(
-            raw=raw_output,
+            raw=raw_str,
             pydantic=formatted_result,
             agent_role=self.role,
             usage_metrics=usage_metrics.model_dump() if usage_metrics else None,
@@ -1967,8 +2007,16 @@ class Agent(BaseAgent):
         else:
             usage_metrics = self._token_process.get_summary()
 
+        raw_str = (
+            raw_output
+            if isinstance(raw_output, str)
+            else raw_output.model_dump_json()
+            if isinstance(raw_output, BaseModel)
+            else str(raw_output)
+        )
+
         return LiteAgentOutput(
-            raw=raw_output,
+            raw=raw_str,
             pydantic=formatted_result,
             agent_role=self.role,
             usage_metrics=usage_metrics.model_dump() if usage_metrics else None,

lib/crewai/src/crewai/events/types/a2a_events.py

@@ -654,3 +654,165 @@ class A2AParallelDelegationCompletedEvent(A2AEventBase):
     success_count: int
     failure_count: int
     results: dict[str, str] | None = None
+
+
+class A2ATransportNegotiatedEvent(A2AEventBase):
+    """Event emitted when transport protocol is negotiated with an A2A agent.
+
+    This event is emitted after comparing client and server transport capabilities
+    to select the optimal transport protocol and endpoint URL.
+
+    Attributes:
+        endpoint: Original A2A agent endpoint URL.
+        a2a_agent_name: Name of the A2A agent from agent card.
+        negotiated_transport: The transport protocol selected (JSONRPC, GRPC, HTTP+JSON).
+        negotiated_url: The URL to use for the selected transport.
+        source: How the transport was selected ('client_preferred', 'server_preferred', 'fallback').
+        client_supported_transports: Transports the client can use.
+        server_supported_transports: Transports the server supports.
+        server_preferred_transport: The server's preferred transport from AgentCard.
+        client_preferred_transport: The client's preferred transport if set.
+        metadata: Custom A2A metadata key-value pairs.
+    """
+
+    type: str = "a2a_transport_negotiated"
+    endpoint: str
+    a2a_agent_name: str | None = None
+    negotiated_transport: str
+    negotiated_url: str
+    source: str
+    client_supported_transports: list[str]
+    server_supported_transports: list[str]
+    server_preferred_transport: str
+    client_preferred_transport: str | None = None
+    metadata: dict[str, Any] | None = None
+
+
+class A2AContentTypeNegotiatedEvent(A2AEventBase):
+    """Event emitted when content types are negotiated with an A2A agent.
+
+    This event is emitted after comparing client and server input/output mode
+    capabilities to determine compatible MIME types for communication.
+
+    Attributes:
+        endpoint: A2A agent endpoint URL.
+        a2a_agent_name: Name of the A2A agent from agent card.
+        skill_name: Skill name if negotiation was skill-specific.
+        client_input_modes: MIME types the client can send.
+        client_output_modes: MIME types the client can accept.
+        server_input_modes: MIME types the server accepts.
+        server_output_modes: MIME types the server produces.
+        negotiated_input_modes: Compatible input MIME types selected.
+        negotiated_output_modes: Compatible output MIME types selected.
+        negotiation_success: Whether compatible types were found for both directions.
+        metadata: Custom A2A metadata key-value pairs.
+    """
+
+    type: str = "a2a_content_type_negotiated"
+    endpoint: str
+    a2a_agent_name: str | None = None
+    skill_name: str | None = None
+    client_input_modes: list[str]
+    client_output_modes: list[str]
+    server_input_modes: list[str]
+    server_output_modes: list[str]
+    negotiated_input_modes: list[str]
+    negotiated_output_modes: list[str]
+    negotiation_success: bool = True
+    metadata: dict[str, Any] | None = None
+
+
+# -----------------------------------------------------------------------------
+# Context Lifecycle Events
+# -----------------------------------------------------------------------------
+
+
+class A2AContextCreatedEvent(A2AEventBase):
+    """Event emitted when an A2A context is created.
+
+    Contexts group related tasks in a conversation or workflow.
+
+    Attributes:
+        context_id: Unique identifier for the context.
+        created_at: Unix timestamp when context was created.
+        metadata: Custom A2A metadata key-value pairs.
+    """
+
+    type: str = "a2a_context_created"
+    context_id: str
+    created_at: float
+    metadata: dict[str, Any] | None = None
+
+
+class A2AContextExpiredEvent(A2AEventBase):
+    """Event emitted when an A2A context expires due to TTL.
+
+    Attributes:
+        context_id: The expired context identifier.
+        created_at: Unix timestamp when context was created.
+        age_seconds: How long the context existed before expiring.
+        task_count: Number of tasks in the context when expired.
+        metadata: Custom A2A metadata key-value pairs.
+    """
+
+    type: str = "a2a_context_expired"
+    context_id: str
+    created_at: float
+    age_seconds: float
+    task_count: int
+    metadata: dict[str, Any] | None = None
+
+
+class A2AContextIdleEvent(A2AEventBase):
+    """Event emitted when an A2A context becomes idle.
+
+    Idle contexts have had no activity for the configured threshold.
+
+    Attributes:
+        context_id: The idle context identifier.
+        idle_seconds: Seconds since last activity.
+        task_count: Number of tasks in the context.
+        metadata: Custom A2A metadata key-value pairs.
+    """
+
+    type: str = "a2a_context_idle"
+    context_id: str
+    idle_seconds: float
+    task_count: int
+    metadata: dict[str, Any] | None = None
+
+
+class A2AContextCompletedEvent(A2AEventBase):
+    """Event emitted when all tasks in an A2A context complete.
+
+    Attributes:
+        context_id: The completed context identifier.
+        total_tasks: Total number of tasks that were in the context.
+        duration_seconds: Total context lifetime in seconds.
+        metadata: Custom A2A metadata key-value pairs.
+    """
+
+    type: str = "a2a_context_completed"
+    context_id: str
+    total_tasks: int
+    duration_seconds: float
+    metadata: dict[str, Any] | None = None
+
+
+class A2AContextPrunedEvent(A2AEventBase):
+    """Event emitted when an A2A context is pruned (deleted).
+
+    Pruning removes the context metadata and optionally associated tasks.
+
+    Attributes:
+        context_id: The pruned context identifier.
+        task_count: Number of tasks that were in the context.
+        age_seconds: How long the context existed before pruning.
+        metadata: Custom A2A metadata key-value pairs.
+    """
+
+    type: str = "a2a_context_pruned"
+    context_id: str
+    task_count: int
+    age_seconds: float
+    metadata: dict[str, Any] | None = None

lib/crewai/src/crewai/experimental/agent_executor.py

@@ -370,6 +370,15 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                 verbose=self.agent.verbose,
             )
 
+            # If response is structured output (BaseModel), store it directly
+            if isinstance(answer, BaseModel):
+                self.state.current_answer = AgentFinish(
+                    thought="",
+                    output=answer,
+                    text=str(answer),
+                )
+                return "parsed"
+
             # Parse the LLM response
             formatted_answer = process_llm_response(answer, self.use_stop_words)
 
@@ -1310,7 +1319,12 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
         Returns:
             Final answer after feedback.
         """
-        human_feedback = self._ask_human_input(formatted_answer.output)
+        output_str = (
+            str(formatted_answer.output)
+            if isinstance(formatted_answer.output, BaseModel)
+            else formatted_answer.output
+        )
+        human_feedback = self._ask_human_input(output_str)
 
         if self._is_training_mode():
             return self._handle_training_feedback(formatted_answer, human_feedback)
@@ -1382,7 +1396,12 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
                 self.state.ask_for_human_input = False
             else:
                 answer = self._process_feedback_iteration(feedback)
-                feedback = self._ask_human_input(answer.output)
+                output_str = (
+                    str(answer.output)
+                    if isinstance(answer.output, BaseModel)
+                    else answer.output
+                )
+                feedback = self._ask_human_input(output_str)
 
         return answer
 

lib/crewai/src/crewai/lite_agent.py

@@ -2,8 +2,10 @@ from __future__ import annotations
 
 import asyncio
 from collections.abc import Callable
+from functools import wraps
 import inspect
 import json
+from types import MethodType
 from typing import (
     TYPE_CHECKING,
     Any,
@@ -30,6 +32,8 @@ from typing_extensions import Self
 if TYPE_CHECKING:
     from crewai_files import FileInput
 
+    from crewai.a2a.config import A2AClientConfig, A2AConfig, A2AServerConfig
+
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
 from crewai.agents.cache.cache_handler import CacheHandler
@@ -84,6 +88,81 @@ from crewai.utilities.tool_utils import execute_tool_and_check_finality
 from crewai.utilities.types import LLMMessage
 
 
+def _kickoff_with_a2a_support(
+    agent: LiteAgent,
+    original_kickoff: Callable[..., LiteAgentOutput],
+    messages: str | list[LLMMessage],
+    response_format: type[BaseModel] | None,
+    input_files: dict[str, FileInput] | None,
+    extension_registry: Any,
+) -> LiteAgentOutput:
+    """Wrap kickoff with A2A delegation using Task adapter.
+
+    Args:
+        agent: The LiteAgent instance.
+        original_kickoff: The original kickoff method.
+        messages: Input messages.
+        response_format: Optional response format.
+        input_files: Optional input files.
+        extension_registry: A2A extension registry.
+
+    Returns:
+        LiteAgentOutput from either local execution or A2A delegation.
+    """
+    from crewai.a2a.utils.response_model import get_a2a_agents_and_response_model
+    from crewai.a2a.wrapper import _execute_task_with_a2a
+    from crewai.task import Task
+
+    a2a_agents, agent_response_model = get_a2a_agents_and_response_model(agent.a2a)
+
+    if not a2a_agents:
+        return original_kickoff(messages, response_format, input_files)
+
+    if isinstance(messages, str):
+        description = messages
+    else:
+        content = next(
+            (m["content"] for m in reversed(messages) if m["role"] == "user"),
+            None,
+        )
+        description = content if isinstance(content, str) else ""
+
+    if not description:
+        return original_kickoff(messages, response_format, input_files)
+
+    fake_task = Task(
+        description=description,
+        agent=agent,
+        expected_output="Result from A2A delegation",
+        input_files=input_files or {},
+    )
+
+    def task_to_kickoff_adapter(
+        self: Any, task: Task, context: str | None, tools: list[Any] | None
+    ) -> str:
+        result = original_kickoff(messages, response_format, input_files)
+        return result.raw
+
+    result_str = _execute_task_with_a2a(
+        self=agent,  # type: ignore[arg-type]
+        a2a_agents=a2a_agents,
+        original_fn=task_to_kickoff_adapter,
+        task=fake_task,
+        agent_response_model=agent_response_model,
+        context=None,
+        tools=None,
+        extension_registry=extension_registry,
+    )
+
+    return LiteAgentOutput(
+        raw=result_str,
+        pydantic=None,
+        agent_role=agent.role,
+        usage_metrics=None,
+        messages=[],
+    )
+
+
 class LiteAgent(FlowTrackable, BaseModel):
     """
     A lightweight agent that can process messages and use tools.
@@ -154,6 +233,17 @@ class LiteAgent(FlowTrackable, BaseModel):
     guardrail_max_retries: int = Field(
         default=3, description="Maximum number of retries when guardrail fails"
     )
+    a2a: (
+        list[A2AConfig | A2AServerConfig | A2AClientConfig]
+        | A2AConfig
+        | A2AServerConfig
+        | A2AClientConfig
+        | None
+    ) = Field(
+        default=None,
+        description="A2A (Agent-to-Agent) configuration for delegating tasks to remote agents. "
+        "Can be a single A2AConfig/A2AClientConfig/A2AServerConfig, or a list of configurations.",
+    )
     tools_results: list[dict[str, Any]] = Field(
         default_factory=list, description="Results of the tools used by the agent."
     )
@@ -209,6 +299,52 @@ class LiteAgent(FlowTrackable, BaseModel):
 
         return self
 
+    @model_validator(mode="after")
+    def setup_a2a_support(self) -> Self:
+        """Setup A2A extensions and server methods if a2a config exists."""
+        if self.a2a:
+            from crewai.a2a.config import A2AClientConfig, A2AConfig
+            from crewai.a2a.extensions.registry import (
+                create_extension_registry_from_config,
+            )
+            from crewai.a2a.utils.agent_card import inject_a2a_server_methods
+
+            configs = self.a2a if isinstance(self.a2a, list) else [self.a2a]
+            client_configs = [
+                config
+                for config in configs
+                if isinstance(config, (A2AConfig, A2AClientConfig))
+            ]
+
+            extension_registry = (
+                create_extension_registry_from_config(client_configs)
+                if client_configs
+                else create_extension_registry_from_config([])
+            )
+            extension_registry.inject_all_tools(self)  # type: ignore[arg-type]
+            inject_a2a_server_methods(self)  # type: ignore[arg-type]
+
+            original_kickoff = self.kickoff
+
+            @wraps(original_kickoff)
+            def kickoff_with_a2a(
+                messages: str | list[LLMMessage],
+                response_format: type[BaseModel] | None = None,
+                input_files: dict[str, FileInput] | None = None,
+            ) -> LiteAgentOutput:
+                return _kickoff_with_a2a_support(
+                    self,
+                    original_kickoff,
+                    messages,
+                    response_format,
+                    input_files,
+                    extension_registry,
+                )
+
+            object.__setattr__(self, "kickoff", MethodType(kickoff_with_a2a, self))
+
+        return self
+
     @model_validator(mode="after")
     def ensure_guardrail_is_callable(self) -> Self:
         if callable(self.guardrail):
@@ -626,7 +762,9 @@ class LiteAgent(FlowTrackable, BaseModel):
                 except Exception as e:
                     raise e
 
-                formatted_answer = process_llm_response(answer, self.use_stop_words)
+                formatted_answer = process_llm_response(
+                    cast(str, answer), self.use_stop_words
+                )
 
                 if isinstance(formatted_answer, AgentAction):
                     try:
@@ -709,3 +847,21 @@ class LiteAgent(FlowTrackable, BaseModel):
     ) -> None:
         """Append a message to the message list with the given role."""
         self._messages.append(format_message_for_llm(text, role=role))
+
+
+try:
+    from crewai.a2a.config import (
+        A2AClientConfig as _A2AClientConfig,
+        A2AConfig as _A2AConfig,
+        A2AServerConfig as _A2AServerConfig,
+    )
+
+    LiteAgent.model_rebuild(
+        _types_namespace={
+            "A2AConfig": _A2AConfig,
+            "A2AClientConfig": _A2AClientConfig,
+            "A2AServerConfig": _A2AServerConfig,
+        }
+    )
+except ImportError:
+    pass

lib/crewai/tests/a2a/test_a2a_integration.py

@@ -104,6 +104,7 @@ class TestA2AStreamingIntegration:
             message=test_message,
             new_messages=new_messages,
             agent_card=agent_card,
+            endpoint=agent_card.url,
         )
 
         assert isinstance(result, dict)
@@ -225,6 +226,7 @@ class TestA2APushNotificationHandler:
             result_store=mock_store,
             polling_timeout=30.0,
             polling_interval=1.0,
+            endpoint=mock_agent_card.url,
         )
 
         mock_store.wait_for_result.assert_called_once_with(
@@ -287,6 +289,7 @@ class TestA2APushNotificationHandler:
             result_store=mock_store,
             polling_timeout=5.0,
             polling_interval=0.5,
+            endpoint=mock_agent_card.url,
         )
 
         assert result["status"] == TaskState.failed
@@ -317,6 +320,7 @@ class TestA2APushNotificationHandler:
             message=test_msg,
             new_messages=new_messages,
             agent_card=mock_agent_card,
+            endpoint=mock_agent_card.url,
         )
 
         assert result["status"] == TaskState.failed

lib/crewai/tests/a2a/utils/test_task.py

@@ -43,6 +43,7 @@ def mock_context() -> MagicMock:
     context.context_id = "test-context-456"
     context.get_user_input.return_value = "Test user message"
     context.message = MagicMock(spec=Message)
+    context.message.parts = []
     context.current_task = None
     return context
 

lib/crewai/tests/agents/test_agent_a2a_kickoff.py

@@ -0,0 +1,217 @@
+"""Tests for Agent.kickoff() with A2A delegation using VCR cassettes."""
+
+from __future__ import annotations
+
+import os
+
+import pytest
+
+from crewai import Agent
+from crewai.a2a.config import A2AClientConfig
+
+
+A2A_TEST_ENDPOINT = os.getenv(
+    "A2A_TEST_ENDPOINT", "http://localhost:9999/.well-known/agent-card.json"
+)
+
+
+class TestAgentA2AKickoff:
+    """Tests for Agent.kickoff() with A2A delegation."""
+
+    @pytest.fixture
+    def researcher_agent(self) -> Agent:
+        """Create a research agent with A2A configuration."""
+        return Agent(
+            role="Research Analyst",
+            goal="Find and analyze information about AI developments",
+            backstory="Expert researcher with access to remote specialized agents",
+            verbose=True,
+            a2a=[
+                A2AClientConfig(
+                    endpoint=A2A_TEST_ENDPOINT,
+                    fail_fast=False,
+                    max_turns=3,  # Limit turns for testing
+                )
+            ],
+        )
+
+    @pytest.mark.skip(reason="VCR cassette matching issue with agent card caching")
+    @pytest.mark.vcr()
+    def test_agent_kickoff_delegates_to_a2a(self, researcher_agent: Agent) -> None:
+        """Test that agent.kickoff() delegates to A2A server."""
+        result = researcher_agent.kickoff(
+            "Use the remote A2A agent to find out what the current time is in New York."
+        )
+
+        assert result is not None
+        assert result.raw is not None
+        assert isinstance(result.raw, str)
+        assert len(result.raw) > 0
+
+    @pytest.mark.skip(reason="VCR cassette matching issue with agent card caching")
+    @pytest.mark.vcr()
+    def test_agent_kickoff_with_calculator_skill(
+        self, researcher_agent: Agent
+    ) -> None:
+        """Test that agent can delegate calculation to A2A server."""
+        result = researcher_agent.kickoff(
+            "Ask the remote A2A agent to calculate 25 times 17."
+        )
+
+        assert result is not None
+        assert result.raw is not None
+        assert "425" in result.raw or "425.0" in result.raw
+
+    @pytest.mark.skip(reason="VCR cassette matching issue with agent card caching")
+    @pytest.mark.vcr()
+    def test_agent_kickoff_with_conversation_skill(
+        self, researcher_agent: Agent
+    ) -> None:
+        """Test that agent can have a conversation with A2A server."""
+        result = researcher_agent.kickoff(
+            "Delegate to the remote A2A agent to explain quantum computing in simple terms."
+        )
+
+        assert result is not None
+        assert result.raw is not None
+        assert isinstance(result.raw, str)
+        assert len(result.raw) > 50  # Should have a meaningful response
+
+    @pytest.mark.vcr()
+    def test_agent_kickoff_returns_lite_agent_output(
+        self, researcher_agent: Agent
+    ) -> None:
+        """Test that kickoff returns LiteAgentOutput with correct structure."""
+        from crewai.lite_agent_output import LiteAgentOutput
+
+        result = researcher_agent.kickoff(
+            "Use the A2A agent to tell me what time it is."
+        )
+
+        assert isinstance(result, LiteAgentOutput)
+        assert result.raw is not None
+        assert result.agent_role == "Research Analyst"
+        assert isinstance(result.messages, list)
+
+    @pytest.mark.skip(reason="VCR cassette matching issue with agent card caching")
+    @pytest.mark.vcr()
+    def test_agent_kickoff_handles_multi_turn_conversation(
+        self, researcher_agent: Agent
+    ) -> None:
+        """Test that agent handles multi-turn A2A conversations."""
+        # This should trigger multiple turns of conversation
+        result = researcher_agent.kickoff(
+            "Ask the remote A2A agent about recent developments in AI agent communication protocols."
+        )
+
+        assert result is not None
+        assert result.raw is not None
+        # The response should contain information about A2A or agent protocols
+        assert isinstance(result.raw, str)
+
+    @pytest.mark.vcr()
+    def test_agent_without_a2a_works_normally(self) -> None:
+        """Test that agent without A2A config works normally."""
+        agent = Agent(
+            role="Simple Assistant",
+            goal="Help with basic tasks",
+            backstory="A helpful assistant",
+            verbose=False,
+        )
+
+        # This should work without A2A delegation
+        result = agent.kickoff("Say hello")
+
+        assert result is not None
+        assert result.raw is not None
+
+    @pytest.mark.vcr()
+    def test_agent_kickoff_with_failed_a2a_endpoint(self) -> None:
+        """Test that agent handles failed A2A connection gracefully."""
+        agent = Agent(
+            role="Research Analyst",
+            goal="Find information",
+            backstory="Expert researcher",
+            verbose=False,
+            a2a=[
+                A2AClientConfig(
+                    endpoint="http://nonexistent:9999/.well-known/agent-card.json",
+                    fail_fast=False,
+                )
+            ],
+        )
+
+        # Should fallback to local LLM when A2A fails
+        result = agent.kickoff("What is 2 + 2?")
+
+        assert result is not None
+        assert result.raw is not None
+
+    @pytest.mark.skip(reason="VCR cassette matching issue with agent card caching")
+    @pytest.mark.vcr()
+    def test_agent_kickoff_with_list_messages(
+        self, researcher_agent: Agent
+    ) -> None:
+        """Test that agent.kickoff() works with list of messages."""
+        messages = [
+            {
+                "role": "user",
+                "content": "Delegate to the A2A agent to find the current time in Tokyo.",
+            },
+        ]
+
+        result = researcher_agent.kickoff(messages)
+
+        assert result is not None
+        assert result.raw is not None
+        assert isinstance(result.raw, str)
+
+
+class TestAgentA2AKickoffAsync:
+    """Tests for async Agent.kickoff_async() with A2A delegation."""
+
+    @pytest.fixture
+    def researcher_agent(self) -> Agent:
+        """Create a research agent with A2A configuration."""
+        return Agent(
+            role="Research Analyst",
+            goal="Find and analyze information",
+            backstory="Expert researcher with access to remote agents",
+            verbose=True,
+            a2a=[
+                A2AClientConfig(
+                    endpoint=A2A_TEST_ENDPOINT,
+                    fail_fast=False,
+                    max_turns=3,
+                )
+            ],
+        )
+
+    @pytest.mark.vcr()
+    @pytest.mark.asyncio
+    async def test_agent_kickoff_async_delegates_to_a2a(
+        self, researcher_agent: Agent
+    ) -> None:
+        """Test that agent.kickoff_async() delegates to A2A server."""
+        result = await researcher_agent.kickoff_async(
+            "Use the remote A2A agent to calculate 10 plus 15."
+        )
+
+        assert result is not None
+        assert result.raw is not None
+        assert isinstance(result.raw, str)
+
+    @pytest.mark.skip(reason="Test assertion needs fixing - not capturing final answer")
+    @pytest.mark.vcr()
+    @pytest.mark.asyncio
+    async def test_agent_kickoff_async_with_calculator(
+        self, researcher_agent: Agent
+    ) -> None:
+        """Test async delegation with calculator skill."""
+        result = await researcher_agent.kickoff_async(
+            "Ask the A2A agent to calculate 100 divided by 4."
+        )
+
+        assert result is not None
+        assert result.raw is not None
+        assert "25" in result.raw or "25.0" in result.raw

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoff.test_agent_kickoff_delegates_to_a2a.yaml

@@ -0,0 +1,665 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Use the remote A2A agent to find out what the current time is in New York.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1385'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPKNZ1miu2xMURPYYcLXdKrlMIh\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808810,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is the current time in New York?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        274,\n    \"completion_tokens\": 40,\n    \"total_tokens\": 314,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:31 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '854'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"869c0693-9e53-40ae-acd0-5823d73c7808","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"5c4fc5ee-97c4-42f9-96a0-f1e1205f0832","parts":[{"kind":"text","text":"What
+      is the current time in New York?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '364'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"869c0693-9e53-40ae-acd0-5823d73c7808\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"0aba73f6-87de-4e43-9a5a-7ebd22f590e3\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"0aca3052-dd0b-4f0e-bc0e-a646b0a86de2\"}}\r\n\r\ndata:
+        {\"id\":\"869c0693-9e53-40ae-acd0-5823d73c7808\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"0aba73f6-87de-4e43-9a5a-7ebd22f590e3\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"0aca3052-dd0b-4f0e-bc0e-a646b0a86de2\"}}\r\n\r\ndata:
+        {\"id\":\"869c0693-9e53-40ae-acd0-5823d73c7808\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"0aba73f6-87de-4e43-9a5a-7ebd22f590e3\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"f70e8fe1-26c9-47e1-9331-1be893e0c5b0\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        get_time] 2026-01-30 16:33:31 EST (America/New_York)\\nThe current time in
+        New York is 4:33 PM EST.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"0aca3052-dd0b-4f0e-bc0e-a646b0a86de2\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:30 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Use the remote A2A agent to find out what the current time is in New York.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1385'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPN7ipYzYuI3Htoj13LNHyic8RB\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808813,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is the current time in New York?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        274,\n    \"completion_tokens\": 40,\n    \"total_tokens\": 314,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:34 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '660'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"7aac6192-3805-4a2f-b9b1-3e281f723f35","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"0a76a4cc-e497-491e-84e0-2a9d35e106b5","parts":[{"kind":"text","text":"What
+      is the current time in New York?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '364'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"7aac6192-3805-4a2f-b9b1-3e281f723f35\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"7a2ffd0b-8d57-4a06-8e61-614cb6132b76\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"a562b802-b554-4dce-93f1-d3b757ab1e93\"}}\r\n\r\ndata:
+        {\"id\":\"7aac6192-3805-4a2f-b9b1-3e281f723f35\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"7a2ffd0b-8d57-4a06-8e61-614cb6132b76\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"a562b802-b554-4dce-93f1-d3b757ab1e93\"}}\r\n\r\ndata:
+        {\"id\":\"7aac6192-3805-4a2f-b9b1-3e281f723f35\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"7a2ffd0b-8d57-4a06-8e61-614cb6132b76\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"9a5678a8-9fdc-47c5-b7fa-061da1bf98e1\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        get_time] 2026-01-30 16:33:34 EST (America/New_York)\\nThe current time in
+        New York is 4:33 PM EST.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"a562b802-b554-4dce-93f1-d3b757ab1e93\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:33 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Use the remote A2A agent to find out what the current time is in New York.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1385'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPQoeD1yHZjR5bbWnq9fMdIPMFu\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808816,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is the current local time in New York?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        274,\n    \"completion_tokens\": 41,\n    \"total_tokens\": 315,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:37 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '684'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"03e755a9-bf97-4c55-bd2f-fbc23e3385ef","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"4c7c5802-a8b0-40ac-bbf4-4ff1cb0b10f3","parts":[{"kind":"text","text":"What
+      is the current local time in New York?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '370'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"03e755a9-bf97-4c55-bd2f-fbc23e3385ef\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"fcef0a1d-ba1d-4703-88a7-0caddb7d8602\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"01abf50f-944a-4814-816c-170e460a542a\"}}\r\n\r\ndata:
+        {\"id\":\"03e755a9-bf97-4c55-bd2f-fbc23e3385ef\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"fcef0a1d-ba1d-4703-88a7-0caddb7d8602\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"01abf50f-944a-4814-816c-170e460a542a\"}}\r\n\r\ndata:
+        {\"id\":\"03e755a9-bf97-4c55-bd2f-fbc23e3385ef\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"fcef0a1d-ba1d-4703-88a7-0caddb7d8602\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"cc32e320-d067-4006-85ad-c3eb988ee0cc\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        get_time] 2026-01-30 16:33:38 EST (America/New_York)\\nThe current local time
+        in New York is 4:33 PM EST on January 30, 2026.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"01abf50f-944a-4814-816c-170e460a542a\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:37 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Use the remote A2A agent to find out what the current time is in New York.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1385'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPUBwXUl9D9xr19IR5ayWaliTQc\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808820,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is the current time in New York?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        274,\n    \"completion_tokens\": 40,\n    \"total_tokens\": 314,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:41 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '844'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: ''
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - localhost:9999
+    method: GET
+    uri: http://localhost:9999/.well-known/agent-card.json
+  response:
+    body:
+      string: '{"capabilities":{"pushNotifications":true,"streaming":true},"defaultInputModes":["text/plain","application/json"],"defaultOutputModes":["text/plain","application/json"],"description":"An
+        AI assistant powered by OpenAI GPT with calculator and time tools. Ask questions,
+        perform calculations, or get the current time in any timezone.","name":"GPT
+        Assistant","preferredTransport":"JSONRPC","protocolVersion":"0.3.0","skills":[{"description":"Have
+        a general conversation with the AI assistant. Ask questions, get explanations,
+        or just chat.","examples":["Hello, how are you?","Explain quantum computing
+        in simple terms","What can you help me with?"],"id":"conversation","name":"General
+        Conversation","tags":["chat","conversation","general"]},{"description":"Perform
+        mathematical calculations including arithmetic, exponents, and more.","examples":["What
+        is 25 * 17?","Calculate 2^10","What''s (100 + 50) / 3?"],"id":"calculator","name":"Calculator","tags":["math","calculator","arithmetic"]},{"description":"Get
+        the current date and time in any timezone.","examples":["What time is it?","What''s
+        the current time in Tokyo?","What''s today''s date in New York?"],"id":"time","name":"Current
+        Time","tags":["time","date","timezone"]}],"url":"http://localhost:9999","version":"1.0.0"}'
+    headers:
+      content-length:
+      - '1272'
+      content-type:
+      - application/json
+      date:
+      - Fri, 30 Jan 2026 21:49:04 GMT
+      server:
+      - uvicorn
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoff.test_agent_kickoff_handles_multi_turn_conversation.yaml

@@ -0,0 +1,744 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Ask the remote A2A agent about recent developments in AI agent communication
+      protocols.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1398'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPVb8R5TRMw6i6NIg1K1QCH37DH\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808821,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Could
+        you provide detailed information on the latest developments and advancements
+        in AI agent communication protocols? I'm particularly interested in new standards,
+        interoperability improvements, and innovative methods adopted recently.\\\",\\\"is_a2a\\\":true}\",\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        271,\n    \"completion_tokens\": 63,\n    \"total_tokens\": 334,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:42 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1076'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"7a3da9c5-2ad7-4334-9cb8-3e45920013f3","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"a3d6ab2f-4e18-4b1c-9a5a-1d326b500dc6","parts":[{"kind":"text","text":"Could
+      you provide detailed information on the latest developments and advancements
+      in AI agent communication protocols? I''m particularly interested in new standards,
+      interoperability improvements, and innovative methods adopted recently."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '564'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"7a3da9c5-2ad7-4334-9cb8-3e45920013f3\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"89db77f5-1399-4c96-827b-2d4bac7f412d\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"4c4fceee-2a1b-4050-a958-56f23e9f5920\"}}\r\n\r\ndata:
+        {\"id\":\"7a3da9c5-2ad7-4334-9cb8-3e45920013f3\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"89db77f5-1399-4c96-827b-2d4bac7f412d\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"4c4fceee-2a1b-4050-a958-56f23e9f5920\"}}\r\n\r\ndata:
+        {\"id\":\"7a3da9c5-2ad7-4334-9cb8-3e45920013f3\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"89db77f5-1399-4c96-827b-2d4bac7f412d\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"b7b4db08-f796-4233-a606-44b65791928b\",\"parts\":[{\"kind\":\"text\",\"text\":\"Recent
+        developments in AI agent communication protocols have focused on enhancing
+        interoperability, establishing new standards, and introducing innovative methods.
+        Here are some key advancements:\\n\\n1. **New Standards**: \\n   - **IEEE
+        P7010**: This is a standard under development that aims to establish ethical
+        guidelines for AI systems, particularly in how they communicate and interact
+        with humans and other systems. \\n   - **W3C's Vocabulary for AI**: The World
+        Wide Web Consortium (W3C) is working on creating vocabularies and protocols
+        to facilitate clearer communication between AI agents across different platforms.\\n\\n2.
+        **Interoperability Improvements**:\\n   - **API Standardization**: Efforts
+        like the OpenAPI Specification (formerly known as Swagger) are being adopted
+        for AI models, allowing better integration and communication between different
+        AI systems and services.\\n   - **Interoperable Frameworks**: Frameworks such
+        as the AI Exchange (a protocol for exchanging AI models and data) are evolving
+        to ensure that different AI systems can work together more effectively, enhancing
+        data sharing and joint operations.\\n\\n3. **Innovative Methods**:\\n   -
+        **Natural Language Understanding (NLU)**: Advances in NLU technologies have
+        made communication more intuitive. AI agents now better grasp context, intent,
+        and sentiment, allowing for more fluid interactions.\\n   - **Multi-agent
+        Systems (MAS)**: Recent research is focusing on improving how multiple AI
+        agents communicate within a shared environment, utilizing protocols that allow
+        for collaborative problem-solving and negotiation.\\n   - **Federated Learning**:
+        This method enhances privacy and security in communications by allowing AI
+        models to learn collaboratively across multiple devices or systems without
+        sharing personal data.\\n\\n4. **Decentralized Protocols**: The emergence
+        of decentralized communication protocols, such as those based on blockchain
+        technology, is enabling AI agents to communicate securely and transparently,
+        fostering trust among users and systems.\\n\\n5. **Research Collaborations**:
+        Initiatives like the Partnership on AI have brought together companies, academia,
+        and civil society to explore best practices in communication protocols that
+        prioritize ethical considerations.\\n\\nOverall, these advancements in standards
+        and protocols are aimed at creating a more interconnected and efficient environment
+        for AI agents, encouraging innovation while addressing ethical and interoperability
+        challenges.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"4c4fceee-2a1b-4050-a958-56f23e9f5920\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:42 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Ask the remote A2A agent about recent developments in AI agent communication
+      protocols.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1398'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPjIHCyZCk5jLwgIGOvDH1NvaPu\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808835,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Could
+        you provide an overview of the recent developments in AI agent communication
+        protocols? Specifically, updates or breakthroughs in how AI agents communicate
+        and coordinate with each other.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        271,\n    \"completion_tokens\": 61,\n    \"total_tokens\": 332,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:57 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1453'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"1fc46982-0250-430d-897b-d12ac939f2ae","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"fdd2c664-4eef-4b15-b62d-1ff72b18faf6","parts":[{"kind":"text","text":"Could
+      you provide an overview of the recent developments in AI agent communication
+      protocols? Specifically, updates or breakthroughs in how AI agents communicate
+      and coordinate with each other."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '520'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"1fc46982-0250-430d-897b-d12ac939f2ae\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"2f12f4df-96b1-41db-9c40-b345b214f107\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"105db7f0-0cc6-43f8-a224-24b6d46c01fb\"}}\r\n\r\ndata:
+        {\"id\":\"1fc46982-0250-430d-897b-d12ac939f2ae\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"2f12f4df-96b1-41db-9c40-b345b214f107\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"105db7f0-0cc6-43f8-a224-24b6d46c01fb\"}}\r\n\r\ndata:
+        {\"id\":\"1fc46982-0250-430d-897b-d12ac939f2ae\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"2f12f4df-96b1-41db-9c40-b345b214f107\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"5a60601d-90f9-452b-8356-9335daa61d6a\",\"parts\":[{\"kind\":\"text\",\"text\":\"Recent
+        developments in AI agent communication protocols have focused on enhancing
+        interoperability, efficiency, and security among AI systems. Key breakthroughs
+        include:\\n\\n1. **Standardization of Protocols**: Efforts such as the IEEE
+        P2870 standard aim to create a unified communication framework that allows
+        different AI agents to interact seamlessly across platforms.\\n\\n2. **Multi-agent
+        Reinforcement Learning (MARL)**: Innovations in MARL enable agents to learn
+        from each other and improve communication strategies, facilitating better
+        coordination in dynamic environments.\\n\\n3. **Natural Language Processing
+        (NLP) Enhancements**: Advancements in NLP have improved how AI agents understand
+        and generate human language, enabling more intuitive communication both with
+        humans and among themselves.\\n\\n4. **Decentralized Communication Frameworks**:
+        Protocols using blockchain technology allow for secure and transparent communication
+        between agents without a central authority, promoting trust and data integrity.\\n\\n5.
+        **Contextual Understanding**: New algorithms enhance AI's ability to maintain
+        context in conversations, allowing agents to communicate more effectively
+        in multi-turn dialogues and complex scenarios.\\n\\n6. **Communication Efficiency**:
+        Research into compressed communication techniques is helping reduce bandwidth
+        usage while maintaining the effectiveness of information exchange between
+        agents. \\n\\nThese advancements are paving the way for more autonomous and
+        collaborative AI systems capable of complex task execution.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"105db7f0-0cc6-43f8-a224-24b6d46c01fb\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:56 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Ask the remote A2A agent about recent developments in AI agent communication
+      protocols.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1398'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPus9YgQVHUbVZ4ytiARJMcg7wS\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808846,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Could
+        you please provide information about the recent developments in AI agent communication
+        protocols?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 271,\n    \"completion_tokens\":
+        46,\n    \"total_tokens\": 317,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:07 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '903'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"b6af80c8-d1de-4149-9093-bac40b337eba","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"8505e288-5d79-4420-88f4-79d8161cd1b5","parts":[{"kind":"text","text":"Could
+      you please provide information about the recent developments in AI agent communication
+      protocols?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '430'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"b6af80c8-d1de-4149-9093-bac40b337eba\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"3fa6f8f9-51c6-417c-8680-732f7de8b0f4\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"d1464f6c-b2b3-4f24-8918-322f152caf74\"}}\r\n\r\ndata:
+        {\"id\":\"b6af80c8-d1de-4149-9093-bac40b337eba\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"3fa6f8f9-51c6-417c-8680-732f7de8b0f4\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"d1464f6c-b2b3-4f24-8918-322f152caf74\"}}\r\n\r\ndata:
+        {\"id\":\"b6af80c8-d1de-4149-9093-bac40b337eba\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"3fa6f8f9-51c6-417c-8680-732f7de8b0f4\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"bd09b7bc-4295-4933-92b9-b2ceeab38aba\",\"parts\":[{\"kind\":\"text\",\"text\":\"Recent
+        developments in AI agent communication protocols have focused on enhancing
+        interoperability, robustness, and security among different AI systems. Key
+        trends include:\\n\\n1. **Standardization Efforts**: Organizations are working
+        towards creating standardized protocols that allow various AI agents to communicate
+        seamlessly, such as the use of IEEE's initiatives.\\n\\n2. **Interoperability
+        Frameworks**: Frameworks such as Agent Communication Language (ACL) and FIPA
+        standards are being updated to support richer interactions among AI systems.\\n\\n3.
+        **Natural Language Processing (NLP) Improvements**: Advances in NLP are enabling
+        agents to understand and generate human-like responses better, allowing for
+        more natural communication.\\n\\n4. **Context Management**: New protocols
+        are incorporating context-awareness so that agents can understand and adjust
+        their responses based on the situational context in which communication occurs.\\n\\n5.
+        **Security Protocol Enhancements**: With rising concerns over data privacy,
+        new communication protocols are integrating stronger security measures, including
+        encryption and authentication methods to protect the exchange of sensitive
+        information.\\n\\n6. **Decentralized Communication**: There's an ongoing exploration
+        into decentralized protocols using blockchain technology to ensure transparency
+        and trust in agent communications.\\n\\nThese advancements are instrumental
+        in creating a more connected and effective network of AI agents capable of
+        cooperating and collaborating across diverse applications and industries.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"d1464f6c-b2b3-4f24-8918-322f152caf74\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:34:07 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Ask the remote A2A agent about recent developments in AI agent communication
+      protocols.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1398'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQ6ybuZARDZhmEoVvSYKa8jh4xN\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808858,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Can
+        you provide the latest information on recent developments in AI agent communication
+        protocols? Specifically, I am interested in new standards, methods, or tools
+        that have emerged to enhance interoperability and efficiency among AI agents.\\\",\\\"is_a2a\\\":true}\",\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        271,\n    \"completion_tokens\": 70,\n    \"total_tokens\": 341,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:19 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1228'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: ''
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - localhost:9999
+    method: GET
+    uri: http://localhost:9999/.well-known/agent-card.json
+  response:
+    body:
+      string: '{"capabilities":{"pushNotifications":true,"streaming":true},"defaultInputModes":["text/plain","application/json"],"defaultOutputModes":["text/plain","application/json"],"description":"An
+        AI assistant powered by OpenAI GPT with calculator and time tools. Ask questions,
+        perform calculations, or get the current time in any timezone.","name":"GPT
+        Assistant","preferredTransport":"JSONRPC","protocolVersion":"0.3.0","skills":[{"description":"Have
+        a general conversation with the AI assistant. Ask questions, get explanations,
+        or just chat.","examples":["Hello, how are you?","Explain quantum computing
+        in simple terms","What can you help me with?"],"id":"conversation","name":"General
+        Conversation","tags":["chat","conversation","general"]},{"description":"Perform
+        mathematical calculations including arithmetic, exponents, and more.","examples":["What
+        is 25 * 17?","Calculate 2^10","What''s (100 + 50) / 3?"],"id":"calculator","name":"Calculator","tags":["math","calculator","arithmetic"]},{"description":"Get
+        the current date and time in any timezone.","examples":["What time is it?","What''s
+        the current time in Tokyo?","What''s today''s date in New York?"],"id":"time","name":"Current
+        Time","tags":["time","date","timezone"]}],"url":"http://localhost:9999","version":"1.0.0"}'
+    headers:
+      content-length:
+      - '1272'
+      content-type:
+      - application/json
+      date:
+      - Fri, 30 Jan 2026 21:49:26 GMT
+      server:
+      - uvicorn
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoff.test_agent_kickoff_returns_lite_agent_output.yaml

@@ -0,0 +1,622 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Use the A2A agent to tell me what time it is.\n\nProvide your complete
+      response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1356'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qP8bKsdUDPFNPsCgA6XfTcDS5RQ\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808798,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        time is it currently?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 269,\n    \"completion_tokens\":
+        37,\n    \"total_tokens\": 306,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:19 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '959'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"bf41cc3b-7d95-4456-af9b-4dc0c1f3837b","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"4ae6375a-3c1f-49fd-8618-6b235be6ea5f","parts":[{"kind":"text","text":"What
+      time is it currently?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '353'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"bf41cc3b-7d95-4456-af9b-4dc0c1f3837b\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"5d428854-df47-4326-aa42-2ca126a4ff08\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"59cef95a-ba9d-486e-b9cb-3ce39dc95c08\"}}\r\n\r\ndata:
+        {\"id\":\"bf41cc3b-7d95-4456-af9b-4dc0c1f3837b\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"5d428854-df47-4326-aa42-2ca126a4ff08\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"59cef95a-ba9d-486e-b9cb-3ce39dc95c08\"}}\r\n\r\ndata:
+        {\"id\":\"bf41cc3b-7d95-4456-af9b-4dc0c1f3837b\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"5d428854-df47-4326-aa42-2ca126a4ff08\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"9d3b99cd-8853-4f78-8a4b-4c82e640a6a8\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        get_time] 2026-01-30 21:33:20 UTC (UTC)\\nThe current time is 21:33:20 UTC
+        on January 30, 2026.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"59cef95a-ba9d-486e-b9cb-3ce39dc95c08\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:19 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Use the A2A agent to tell me what time it is.\n\nProvide your complete
+      response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1356'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPCXrfeCIRc2rGEuz7HncDWi0mt\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808802,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        time is it currently?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 269,\n    \"completion_tokens\":
+        37,\n    \"total_tokens\": 306,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:23 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '762'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"5145c746-1044-4724-9c51-cbcb3f338fbc","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"a4f9ea5b-9ccc-48f2-b5ad-517c0137af72","parts":[{"kind":"text","text":"What
+      time is it currently?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '353'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"5145c746-1044-4724-9c51-cbcb3f338fbc\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"23a29826-dfe4-4c2b-bca2-8c3b69baef39\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"3ef1907c-b2b1-4b3b-a9ca-80678639aa6b\"}}\r\n\r\ndata:
+        {\"id\":\"5145c746-1044-4724-9c51-cbcb3f338fbc\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"23a29826-dfe4-4c2b-bca2-8c3b69baef39\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"3ef1907c-b2b1-4b3b-a9ca-80678639aa6b\"}}\r\n\r\ndata:
+        {\"id\":\"5145c746-1044-4724-9c51-cbcb3f338fbc\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"23a29826-dfe4-4c2b-bca2-8c3b69baef39\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"4fd468de-7e34-4e88-9635-2b13c4acca32\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        get_time] 2026-01-30 21:33:24 UTC (UTC)\\nThe current time is 21:33:24 UTC.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"3ef1907c-b2b1-4b3b-a9ca-80678639aa6b\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:23 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Use the A2A agent to tell me what time it is.\n\nProvide your complete
+      response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1356'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPFhtpO4QMdnHFH73Fum0rpqCi5\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808805,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is the current time?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 269,\n    \"completion_tokens\":
+        37,\n    \"total_tokens\": 306,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:26 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '700'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"fa7576f7-dbfb-4605-ad70-a0ecadf0f1ac","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"ff083812-cb3a-42d3-b410-7941106f68ac","parts":[{"kind":"text","text":"What
+      is the current time?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '352'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"fa7576f7-dbfb-4605-ad70-a0ecadf0f1ac\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"0eb501cf-ef11-4b46-b17d-639fb1a9aa3a\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"a8c1ccbf-6f13-4894-a4d2-d87d0c3b9ffb\"}}\r\n\r\ndata:
+        {\"id\":\"fa7576f7-dbfb-4605-ad70-a0ecadf0f1ac\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"0eb501cf-ef11-4b46-b17d-639fb1a9aa3a\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"a8c1ccbf-6f13-4894-a4d2-d87d0c3b9ffb\"}}\r\n\r\ndata:
+        {\"id\":\"fa7576f7-dbfb-4605-ad70-a0ecadf0f1ac\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"0eb501cf-ef11-4b46-b17d-639fb1a9aa3a\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"2a5368d0-ac8d-4c7c-b272-a711b96bf277\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        get_time] 2026-01-30 21:33:27 UTC (UTC)\\nThe current time is 21:33:27 UTC
+        on January 30, 2026.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"a8c1ccbf-6f13-4894-a4d2-d87d0c3b9ffb\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:26 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Use the A2A agent to tell me what time it is.\n\nProvide your complete
+      response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1356'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qPJqK3Nr9ySPgvb0LGVLS3ZGxGi\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808809,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is the current time?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 269,\n    \"completion_tokens\":
+        37,\n    \"total_tokens\": 306,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:30 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '877'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoff.test_agent_kickoff_with_calculator_skill.yaml

@@ -0,0 +1,662 @@
+interactions:
+- request:
+    body: ''
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - localhost:9999
+    method: GET
+    uri: http://localhost:9999/.well-known/agent-card.json
+  response:
+    body:
+      string: '{"capabilities":{"pushNotifications":true,"streaming":true},"defaultInputModes":["text/plain","application/json"],"defaultOutputModes":["text/plain","application/json"],"description":"An
+        AI assistant powered by OpenAI GPT with calculator and time tools. Ask questions,
+        perform calculations, or get the current time in any timezone.","name":"GPT
+        Assistant","preferredTransport":"JSONRPC","protocolVersion":"0.3.0","skills":[{"description":"Have
+        a general conversation with the AI assistant. Ask questions, get explanations,
+        or just chat.","examples":["Hello, how are you?","Explain quantum computing
+        in simple terms","What can you help me with?"],"id":"conversation","name":"General
+        Conversation","tags":["chat","conversation","general"]},{"description":"Perform
+        mathematical calculations including arithmetic, exponents, and more.","examples":["What
+        is 25 * 17?","Calculate 2^10","What''s (100 + 50) / 3?"],"id":"calculator","name":"Calculator","tags":["math","calculator","arithmetic"]},{"description":"Get
+        the current date and time in any timezone.","examples":["What time is it?","What''s
+        the current time in Tokyo?","What''s today''s date in New York?"],"id":"time","name":"Current
+        Time","tags":["time","date","timezone"]}],"url":"http://localhost:9999","version":"1.0.0"}'
+    headers:
+      content-length:
+      - '1272'
+      content-type:
+      - application/json
+      date:
+      - Fri, 30 Jan 2026 21:33:04 GMT
+      server:
+      - uvicorn
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Ask the remote A2A agent to calculate 25 times 17.\n\nProvide your complete
+      response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1361'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOvSd5OuQsjAaD7aJtOwEXE0l29\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808785,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is 25 times 17?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 270,\n    \"completion_tokens\":
+        39,\n    \"total_tokens\": 309,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:05 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '697'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"ac9d0ac3-5e35-48c7-a2cd-59e2a66966dd","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"1cccc8dc-7253-4bbd-8e32-bed4004181c8","parts":[{"kind":"text","text":"What
+      is 25 times 17?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '347'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"ac9d0ac3-5e35-48c7-a2cd-59e2a66966dd\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"5da04daa-d638-4124-8f65-7a73627679ad\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"837a9eed-eea6-4d12-94e4-545c6869efc6\"}}\r\n\r\ndata:
+        {\"id\":\"ac9d0ac3-5e35-48c7-a2cd-59e2a66966dd\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"5da04daa-d638-4124-8f65-7a73627679ad\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"837a9eed-eea6-4d12-94e4-545c6869efc6\"}}\r\n\r\ndata:
+        {\"id\":\"ac9d0ac3-5e35-48c7-a2cd-59e2a66966dd\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"5da04daa-d638-4124-8f65-7a73627679ad\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"d01e8e15-61d1-4b3d-a356-95d3add99291\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        calculator] 25 * 17 = 425\\n25 times 17 is 425.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"837a9eed-eea6-4d12-94e4-545c6869efc6\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:04 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Ask the remote A2A agent to calculate 25 times 17.\n\nProvide your complete
+      response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1361'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOzCessPAoHkJZsUYJIw48NwJrS\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808789,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Please
+        calculate 25 times 17.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 270,\n    \"completion_tokens\":
+        38,\n    \"total_tokens\": 308,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:10 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '666'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"89e94967-f28d-4639-9c9c-87719483d15d","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"6ef5d359-8604-4520-a539-518e88d75456","parts":[{"kind":"text","text":"Please
+      calculate 25 times 17."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '356'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"89e94967-f28d-4639-9c9c-87719483d15d\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"cdd17068-acc2-462a-9e9d-bf1a2403a432\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"c96047bb-5ddf-410a-a4bd-03c6bcd4457e\"}}\r\n\r\ndata:
+        {\"id\":\"89e94967-f28d-4639-9c9c-87719483d15d\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"cdd17068-acc2-462a-9e9d-bf1a2403a432\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"c96047bb-5ddf-410a-a4bd-03c6bcd4457e\"}}\r\n\r\ndata:
+        {\"id\":\"89e94967-f28d-4639-9c9c-87719483d15d\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"cdd17068-acc2-462a-9e9d-bf1a2403a432\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"4138a4a4-217a-4f99-a6b1-970229a6bedd\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        calculator] 25 * 17 = 425\\nThe result of 25 times 17 is 425.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"c96047bb-5ddf-410a-a4bd-03c6bcd4457e\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:10 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Ask the remote A2A agent to calculate 25 times 17.\n\nProvide your complete
+      response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1361'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qP2eXgsxYsRuFnwu5tCdE8jZyiI\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808792,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Calculate
+        the product of 25 and 17.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        270,\n    \"completion_tokens\": 40,\n    \"total_tokens\": 310,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:13 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '977'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"be0426a2-3de6-44ce-b7de-22b5992b5025","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"2974dcee-5712-40df-aa41-4877f36c4749","parts":[{"kind":"text","text":"Calculate
+      the product of 25 and 17."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '362'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"be0426a2-3de6-44ce-b7de-22b5992b5025\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"f9311c55-c6ef-413a-818b-d0ebeb8466be\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"fd2d5eee-8bd6-4ead-b96b-917782444d10\"}}\r\n\r\ndata:
+        {\"id\":\"be0426a2-3de6-44ce-b7de-22b5992b5025\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"f9311c55-c6ef-413a-818b-d0ebeb8466be\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"fd2d5eee-8bd6-4ead-b96b-917782444d10\"}}\r\n\r\ndata:
+        {\"id\":\"be0426a2-3de6-44ce-b7de-22b5992b5025\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"f9311c55-c6ef-413a-818b-d0ebeb8466be\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"a27f8c49-b5d4-4421-b7cf-9b7455273f34\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        calculator] 25 * 17 = 425\\nThe product of 25 and 17 is 425.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"fd2d5eee-8bd6-4ead-b96b-917782444d10\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:33:13 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Ask the remote A2A agent to calculate 25 times 17.\n\nProvide your complete
+      response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1361'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qP6z5b62nfY2HkvSobGqRaK0JLD\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808796,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Calculate
+        25 times 17.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 270,\n    \"completion_tokens\":
+        37,\n    \"total_tokens\": 307,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:17 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '997'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoff.test_agent_kickoff_with_conversation_skill.yaml

@@ -0,0 +1,669 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Delegate to the remote A2A agent to explain quantum computing in simple
+      terms.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1389'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQLp4DYPeaKABFeQVDKxePblbY7\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808873,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Can
+        you explain quantum computing in simple terms, suitable for someone with no
+        background in the subject?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        271,\n    \"completion_tokens\": 50,\n    \"total_tokens\": 321,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:34 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '834'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"4f421e0d-c7ee-46ad-8c7b-9ff31404beba","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"4b0f91a5-079c-4efe-ba3d-bee5592c67e5","parts":[{"kind":"text","text":"Can
+      you explain quantum computing in simple terms, suitable for someone with no
+      background in the subject?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '433'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"4f421e0d-c7ee-46ad-8c7b-9ff31404beba\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"cdfd9f23-8f2e-4cea-8839-cd52ce0584a7\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"7c223d0c-f144-4bf8-b8d8-1c37efb04232\"}}\r\n\r\ndata:
+        {\"id\":\"4f421e0d-c7ee-46ad-8c7b-9ff31404beba\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"cdfd9f23-8f2e-4cea-8839-cd52ce0584a7\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"7c223d0c-f144-4bf8-b8d8-1c37efb04232\"}}\r\n\r\ndata:
+        {\"id\":\"4f421e0d-c7ee-46ad-8c7b-9ff31404beba\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"cdfd9f23-8f2e-4cea-8839-cd52ce0584a7\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"bdeb2af5-89c3-4368-93bd-f263b3ab40a9\",\"parts\":[{\"kind\":\"text\",\"text\":\"Quantum
+        computing is a new type of computing that uses the principles of quantum mechanics,
+        which is the science that explains how very small particles, like atoms and
+        electrons, behave. \\n\\nIn classical computing, the basic unit of information
+        is a bit, which can be either a 0 or a 1. This is like a light switch that
+        can either be off (0) or on (1). \\n\\nQuantum computing, on the other hand,
+        uses quantum bits or qubits. A qubit can be in a state of 0, 1, or both at
+        the same time due to a phenomenon called superposition. You can think of this
+        as a spinning coin that is both heads and tails while in the air, rather than
+        fixed to one side when it lands. \\n\\nMoreover, qubits can be linked together
+        through another phenomenon called entanglement. This means that the state
+        of one qubit can depend on the state of another, no matter how far apart they
+        are. This allows quantum computers to solve certain problems much more efficiently
+        than classical computers. \\n\\nIn summary, quantum computing harnesses the
+        strange and fascinating behaviors of particles at the quantum level to process
+        information in ways that traditional computers cannot, potentially making
+        them much more powerful for specific tasks, like breaking encryption or simulating
+        complex molecules.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"7c223d0c-f144-4bf8-b8d8-1c37efb04232\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:34:33 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Delegate to the remote A2A agent to explain quantum computing in simple
+      terms.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1389'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQWQTMdXD4Ug72rmgl1eWkm40zL\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808884,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Please
+        explain quantum computing in simple terms suitable for a general audience.\\\",\\\"is_a2a\\\":true}\",\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        271,\n    \"completion_tokens\": 43,\n    \"total_tokens\": 314,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:45 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '714'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"f5ff9e1d-598f-4b68-94ed-e7f2b942c467","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"b4d6f61a-c854-487a-b238-25f03e0a5ef7","parts":[{"kind":"text","text":"Please
+      explain quantum computing in simple terms suitable for a general audience."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '408'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"f5ff9e1d-598f-4b68-94ed-e7f2b942c467\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"93c80ac2-eaef-4eeb-af7a-5aaa15f5b9ad\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"a4288a18-56d4-4270-ad4a-da1efe6cf84b\"}}\r\n\r\ndata:
+        {\"id\":\"f5ff9e1d-598f-4b68-94ed-e7f2b942c467\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"93c80ac2-eaef-4eeb-af7a-5aaa15f5b9ad\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"a4288a18-56d4-4270-ad4a-da1efe6cf84b\"}}\r\n\r\ndata:
+        {\"id\":\"f5ff9e1d-598f-4b68-94ed-e7f2b942c467\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"93c80ac2-eaef-4eeb-af7a-5aaa15f5b9ad\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"c7303248-eebb-48a4-be78-791ac6d11083\",\"parts\":[{\"kind\":\"text\",\"text\":\"Quantum
+        computing is a type of computing that uses the principles of quantum mechanics,
+        which is the science that explains how very small particles, like atoms and
+        photons, behave. Unlike traditional computers that use bits as the smallest
+        unit of data (which can be either 0 or 1), quantum computers use quantum bits
+        or qubits. \\n\\nHere\u2019s a simple breakdown:\\n- **Qubits**: A qubit can
+        be in a state of 0, 1, or both at the same time (thanks to a property called
+        superposition). This allows quantum computers to process a vast amount of
+        possibilities simultaneously.\\n- **Entanglement**: Qubits can also be entangled,
+        meaning the state of one qubit can depend on the state of another, no matter
+        how far apart they are. This creates a powerful link that can improve computing
+        efficiency.\\n- **Quantum Speedup**: Because of superposition and entanglement,
+        quantum computers can solve certain complex problems much faster than traditional
+        computers.\\n\\nIn simple terms, you can think of quantum computing as a new
+        way of doing math and problem-solving that can tackle really difficult tasks
+        much faster than the computers we use today. However, quantum computing is
+        still in its early stages and is not yet widely used for everyday tasks.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"a4288a18-56d4-4270-ad4a-da1efe6cf84b\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:34:44 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Delegate to the remote A2A agent to explain quantum computing in simple
+      terms.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1389'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQhcQzT9KEetchwHOgQTpBYRw7w\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808895,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Please
+        explain quantum computing in simple terms suitable for someone without a technical
+        background.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 271,\n    \"completion_tokens\":
+        45,\n    \"total_tokens\": 316,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:55 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '786'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"10814663-4e33-4777-ac5d-ea9098a690e9","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"a112c8d7-8cf8-47bc-b84d-a7c8d34326d8","parts":[{"kind":"text","text":"Please
+      explain quantum computing in simple terms suitable for someone without a technical
+      background."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '428'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"10814663-4e33-4777-ac5d-ea9098a690e9\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"754dce7b-b2d5-426e-aaf8-3b5aa886984a\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"2745bfc5-138f-4773-ad96-98d463fcbb3e\"}}\r\n\r\ndata:
+        {\"id\":\"10814663-4e33-4777-ac5d-ea9098a690e9\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"754dce7b-b2d5-426e-aaf8-3b5aa886984a\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"2745bfc5-138f-4773-ad96-98d463fcbb3e\"}}\r\n\r\ndata:
+        {\"id\":\"10814663-4e33-4777-ac5d-ea9098a690e9\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"754dce7b-b2d5-426e-aaf8-3b5aa886984a\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"5cfcafcb-5770-4c5a-9724-54dd475a12a1\",\"parts\":[{\"kind\":\"text\",\"text\":\"Quantum
+        computing is a type of computing that uses the principles of quantum mechanics,
+        which is the science that explains how very small particles, like atoms and
+        photons, behave. \\n\\nIn traditional computers, information is processed
+        using bits, which can be either 0 or 1. Think of bits like light switches
+        that can be turned off (0) or on (1). \\n\\nQuantum computers, on the other
+        hand, use quantum bits, or qubits. A qubit can be 0, 1, or both at the same
+        time due to a property called superposition. This means that quantum computers
+        can process a vast amount of information at once compared to regular computers.
+        \\n\\nAnother important concept in quantum computing is entanglement, where
+        qubits become linked in such a way that the state of one qubit can depend
+        on the state of another, no matter how far apart they are. This can lead to
+        faster processing speeds and the ability to solve complex problems more efficiently.
+        \\n\\nIn summary, quantum computing is like a supercharged version of traditional
+        computing that can perform many calculations simultaneously by taking advantage
+        of the quirks of quantum physics.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"2745bfc5-138f-4773-ad96-98d463fcbb3e\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:34:54 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Delegate to the remote A2A agent to explain quantum computing in simple
+      terms.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1389'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQqDYsO5v1fvanhv4G5kXB0YHwW\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808904,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Please
+        explain quantum computing in simple terms.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        271,\n    \"completion_tokens\": 38,\n    \"total_tokens\": 309,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:35:05 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '918'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoff.test_agent_kickoff_with_failed_a2a_endpoint.yaml

@@ -0,0 +1,108 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher\nYour personal goal is: Find information"},{"role":"user","content":"\nCurrent
+      Task: What is 2 + 2?\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '246'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qP75TkGfZcx59AyFhCifB7NeNve\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808797,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"The sum of 2 + 2 is 4.\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        43,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 55,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:18 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1149'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoff.test_agent_kickoff_with_list_messages.yaml

@@ -0,0 +1,623 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Delegate to the A2A agent to find the current time in Tokyo.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1371'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQ7mKtA8Q7mQ8dWafrjQAtMBV7G\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808859,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is the current time in Tokyo?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        270,\n    \"completion_tokens\": 39,\n    \"total_tokens\": 309,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:20 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '1100'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"ef23c1ef-ef7e-4422-8fd0-330f074e5de8","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"f5952732-b12e-40f9-a9e9-9779501d6467","parts":[{"kind":"text","text":"What
+      is the current time in Tokyo?"}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '361'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"ef23c1ef-ef7e-4422-8fd0-330f074e5de8\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"913b5bd8-c755-4e0c-bbd0-fcf11fcdf257\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"eb05446a-6d96-4964-8e94-3f4ffcc612a7\"}}\r\n\r\ndata:
+        {\"id\":\"ef23c1ef-ef7e-4422-8fd0-330f074e5de8\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"913b5bd8-c755-4e0c-bbd0-fcf11fcdf257\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"eb05446a-6d96-4964-8e94-3f4ffcc612a7\"}}\r\n\r\ndata:
+        {\"id\":\"ef23c1ef-ef7e-4422-8fd0-330f074e5de8\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"913b5bd8-c755-4e0c-bbd0-fcf11fcdf257\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"41813b78-0e9a-41a4-bb6c-7176f9d4e5b2\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        get_time] 2026-01-31 06:34:21 JST (Asia/Tokyo)\\nThe current time in Tokyo
+        is 06:34:21 JST on January 31, 2026.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"eb05446a-6d96-4964-8e94-3f4ffcc612a7\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:34:20 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Delegate to the A2A agent to find the current time in Tokyo.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1371'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQBrUkvfrIi9SeEtGbWxFJjum3o\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808863,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Please
+        find the current time in Tokyo and provide it.\\\",\\\"is_a2a\\\":true}\",\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        270,\n    \"completion_tokens\": 41,\n    \"total_tokens\": 311,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:24 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '966'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"dc04364b-9ad9-4ba4-81a8-bae8a71bee8c","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"781be5cc-2c77-4c24-a0af-c9d30609ecd7","parts":[{"kind":"text","text":"Please
+      find the current time in Tokyo and provide it."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '380'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"dc04364b-9ad9-4ba4-81a8-bae8a71bee8c\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"ae6fa54d-f6b0-4c15-b8b0-eb310731bc1a\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"0bda253d-b860-4bd4-9129-691b886e4f8b\"}}\r\n\r\ndata:
+        {\"id\":\"dc04364b-9ad9-4ba4-81a8-bae8a71bee8c\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"ae6fa54d-f6b0-4c15-b8b0-eb310731bc1a\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"0bda253d-b860-4bd4-9129-691b886e4f8b\"}}\r\n\r\ndata:
+        {\"id\":\"dc04364b-9ad9-4ba4-81a8-bae8a71bee8c\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"ae6fa54d-f6b0-4c15-b8b0-eb310731bc1a\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"82eec93e-3c91-44c8-9acb-343454eb8fb8\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        get_time] 2026-01-31 06:34:25 JST (Asia/Tokyo)\\nThe current time in Tokyo
+        is 06:34 AM on January 31, 2026.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"0bda253d-b860-4bd4-9129-691b886e4f8b\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:34:24 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Delegate to the A2A agent to find the current time in Tokyo.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1371'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQGaNP21E5XkyFMtOtKogiqwKnN\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808868,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is the current time in Tokyo? Please provide the current local time there.\\\",\\\"is_a2a\\\":true}\",\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        270,\n    \"completion_tokens\": 46,\n    \"total_tokens\": 316,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:29 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '786'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"06a22a9f-0969-414f-a17b-e3e9d4a3bbef","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"c2ab08c5-ffb1-43e9-9f43-6e8adbaba95b","parts":[{"kind":"text","text":"What
+      is the current time in Tokyo? Please provide the current local time there."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '406'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"06a22a9f-0969-414f-a17b-e3e9d4a3bbef\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"f86582e4-7d3f-448e-ab51-3522667da9a0\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"5b92d2cb-100e-4be5-ba4d-39b320c3dd4f\"}}\r\n\r\ndata:
+        {\"id\":\"06a22a9f-0969-414f-a17b-e3e9d4a3bbef\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"f86582e4-7d3f-448e-ab51-3522667da9a0\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"5b92d2cb-100e-4be5-ba4d-39b320c3dd4f\"}}\r\n\r\ndata:
+        {\"id\":\"06a22a9f-0969-414f-a17b-e3e9d4a3bbef\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"f86582e4-7d3f-448e-ab51-3522667da9a0\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"befc6d8b-3618-410b-910d-614dc6de77fd\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        get_time] 2026-01-31 06:34:30 JST (Asia/Tokyo)\\nThe current local time in
+        Tokyo is 06:34 AM on January 31, 2026.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"5b92d2cb-100e-4be5-ba4d-39b320c3dd4f\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:34:28 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote specialized agents\nYour personal goal is:
+      Find and analyze information about AI developments"},{"role":"user","content":"\nCurrent
+      Task: Delegate to the A2A agent to find the current time in Tokyo.\n\nProvide
+      your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1371'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQKvrKehCGN5jjCKyRqyN6g88gg\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808872,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"What
+        is the current time in Tokyo?\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        270,\n    \"completion_tokens\": 39,\n    \"total_tokens\": 309,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:32 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '742'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoff.test_agent_without_a2a_works_normally.yaml

@@ -0,0 +1,108 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Simple Assistant. A helpful
+      assistant\nYour personal goal is: Help with basic tasks"},{"role":"user","content":"\nCurrent
+      Task: Say hello\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '248'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qQLXvb3qeE7H25yFuZE7lYxOI0j\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808873,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"Hello! How can I assist you today?\",\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        41,\n    \"completion_tokens\": 9,\n    \"total_tokens\": 50,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:34:33 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '358'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoffAsync.test_agent_kickoff_async_delegates_to_a2a.yaml

@@ -0,0 +1,700 @@
+interactions:
+- request:
+    body: ''
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - localhost:9999
+    method: GET
+    uri: http://localhost:9999/.well-known/agent-card.json
+  response:
+    body:
+      string: '{"capabilities":{"pushNotifications":true,"streaming":true},"defaultInputModes":["text/plain","application/json"],"defaultOutputModes":["text/plain","application/json"],"description":"An
+        AI assistant powered by OpenAI GPT with calculator and time tools. Ask questions,
+        perform calculations, or get the current time in any timezone.","name":"GPT
+        Assistant","preferredTransport":"JSONRPC","protocolVersion":"0.3.0","skills":[{"description":"Have
+        a general conversation with the AI assistant. Ask questions, get explanations,
+        or just chat.","examples":["Hello, how are you?","Explain quantum computing
+        in simple terms","What can you help me with?"],"id":"conversation","name":"General
+        Conversation","tags":["chat","conversation","general"]},{"description":"Perform
+        mathematical calculations including arithmetic, exponents, and more.","examples":["What
+        is 25 * 17?","Calculate 2^10","What''s (100 + 50) / 3?"],"id":"calculator","name":"Calculator","tags":["math","calculator","arithmetic"]},{"description":"Get
+        the current date and time in any timezone.","examples":["What time is it?","What''s
+        the current time in Tokyo?","What''s today''s date in New York?"],"id":"time","name":"Current
+        Time","tags":["time","date","timezone"]}],"url":"http://localhost:9999","version":"1.0.0"}'
+    headers:
+      content-length:
+      - '1272'
+      content-type:
+      - application/json
+      date:
+      - Fri, 30 Jan 2026 21:32:36 GMT
+      server:
+      - uvicorn
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote agents\nYour personal goal is: Find and analyze
+      information"},{"role":"user","content":"\nCurrent Task: Use the remote A2A agent
+      to calculate 10 plus 15.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1326'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOTnAG0KogwskyqSSZDRbSOtXHr\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808757,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Calculate
+        the sum of 10 plus 15.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 266,\n    \"completion_tokens\":
+        40,\n    \"total_tokens\": 306,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:32:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '832'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: ''
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - localhost:9999
+    method: GET
+    uri: http://localhost:9999/.well-known/agent-card.json
+  response:
+    body:
+      string: '{"capabilities":{"pushNotifications":true,"streaming":true},"defaultInputModes":["text/plain","application/json"],"defaultOutputModes":["text/plain","application/json"],"description":"An
+        AI assistant powered by OpenAI GPT with calculator and time tools. Ask questions,
+        perform calculations, or get the current time in any timezone.","name":"GPT
+        Assistant","preferredTransport":"JSONRPC","protocolVersion":"0.3.0","skills":[{"description":"Have
+        a general conversation with the AI assistant. Ask questions, get explanations,
+        or just chat.","examples":["Hello, how are you?","Explain quantum computing
+        in simple terms","What can you help me with?"],"id":"conversation","name":"General
+        Conversation","tags":["chat","conversation","general"]},{"description":"Perform
+        mathematical calculations including arithmetic, exponents, and more.","examples":["What
+        is 25 * 17?","Calculate 2^10","What''s (100 + 50) / 3?"],"id":"calculator","name":"Calculator","tags":["math","calculator","arithmetic"]},{"description":"Get
+        the current date and time in any timezone.","examples":["What time is it?","What''s
+        the current time in Tokyo?","What''s today''s date in New York?"],"id":"time","name":"Current
+        Time","tags":["time","date","timezone"]}],"url":"http://localhost:9999","version":"1.0.0"}'
+    headers:
+      content-length:
+      - '1272'
+      content-type:
+      - application/json
+      date:
+      - Fri, 30 Jan 2026 21:32:38 GMT
+      server:
+      - uvicorn
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"11e7f105-5324-4e70-af42-2db3a3e96054","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"8ba087b8-e647-4e46-ba32-d163f2ef3f3b","parts":[{"kind":"text","text":"Calculate
+      the sum of 10 plus 15."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '359'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"11e7f105-5324-4e70-af42-2db3a3e96054\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"2f5791a9-4dd2-4fe1-b637-ef4e8c7d3f78\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"d5371a72-7ad4-4606-889d-040bdaf6dc62\"}}\r\n\r\ndata:
+        {\"id\":\"11e7f105-5324-4e70-af42-2db3a3e96054\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"2f5791a9-4dd2-4fe1-b637-ef4e8c7d3f78\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"d5371a72-7ad4-4606-889d-040bdaf6dc62\"}}\r\n\r\ndata:
+        {\"id\":\"11e7f105-5324-4e70-af42-2db3a3e96054\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"2f5791a9-4dd2-4fe1-b637-ef4e8c7d3f78\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"f9f4cc36-e504-4d2e-8e53-d061427adde6\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        calculator] 10 + 15 = 25\\nThe sum of 10 plus 15 is 25.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"d5371a72-7ad4-4606-889d-040bdaf6dc62\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:32:38 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote agents\nYour personal goal is: Find and analyze
+      information"},{"role":"user","content":"\nCurrent Task: Use the remote A2A agent
+      to calculate 10 plus 15.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1326'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOYv1S9VAwloC7LrWOUABqHUtDO\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808762,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Calculate
+        the sum of 10 plus 15.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 266,\n    \"completion_tokens\":
+        40,\n    \"total_tokens\": 306,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:32:43 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '658'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"93d4ded2-251f-47da-ae7b-2a135ec7cbb9","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"08032897-ffdc-4a5e-8ae9-1124d49bbf01","parts":[{"kind":"text","text":"Calculate
+      the sum of 10 plus 15."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '359'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"93d4ded2-251f-47da-ae7b-2a135ec7cbb9\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"a2b91c10-dc16-4dff-b807-3ea98016ff38\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"2b0861b7-8d94-4325-97ab-aaae42f43581\"}}\r\n\r\ndata:
+        {\"id\":\"93d4ded2-251f-47da-ae7b-2a135ec7cbb9\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"a2b91c10-dc16-4dff-b807-3ea98016ff38\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"2b0861b7-8d94-4325-97ab-aaae42f43581\"}}\r\n\r\ndata:
+        {\"id\":\"93d4ded2-251f-47da-ae7b-2a135ec7cbb9\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"a2b91c10-dc16-4dff-b807-3ea98016ff38\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"e4e420da-aef9-489f-a3ca-39a97930dee8\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        calculator] 10 + 15 = 25\\nThe sum of 10 plus 15 is 25.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"2b0861b7-8d94-4325-97ab-aaae42f43581\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:32:43 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote agents\nYour personal goal is: Find and analyze
+      information"},{"role":"user","content":"\nCurrent Task: Use the remote A2A agent
+      to calculate 10 plus 15.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1326'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOcC0ycRtx6l3V88o2KbMLXk24S\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808766,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Calculate
+        the sum of 10 plus 15.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 266,\n    \"completion_tokens\":
+        40,\n    \"total_tokens\": 306,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:32:47 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '644'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"be92898e-ac10-4bed-a54c-d40e747c85f3","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"0f12aa81-afb8-419b-9d52-b47cc6c21329","parts":[{"kind":"text","text":"Calculate
+      the sum of 10 plus 15."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '359'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"be92898e-ac10-4bed-a54c-d40e747c85f3\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"e13fc32d-ead2-4f01-b852-7fd1b7b73983\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"cdaba0fb-081e-4950-91da-9635c0bd1336\"}}\r\n\r\ndata:
+        {\"id\":\"be92898e-ac10-4bed-a54c-d40e747c85f3\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"e13fc32d-ead2-4f01-b852-7fd1b7b73983\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"cdaba0fb-081e-4950-91da-9635c0bd1336\"}}\r\n\r\ndata:
+        {\"id\":\"be92898e-ac10-4bed-a54c-d40e747c85f3\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"e13fc32d-ead2-4f01-b852-7fd1b7b73983\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"bb905c5a-34c8-4a02-9ba3-5713790e2a00\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        calculator] 10 + 15 = 25\\nThe sum of 10 plus 15 is 25.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"cdaba0fb-081e-4950-91da-9635c0bd1336\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:32:47 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote agents\nYour personal goal is: Find and analyze
+      information"},{"role":"user","content":"\nCurrent Task: Use the remote A2A agent
+      to calculate 10 plus 15.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1326'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOgAECMjCxhfMRaNqRNLVGefrXr\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808770,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Calculate
+        10 plus 15.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 266,\n    \"completion_tokens\":
+        37,\n    \"total_tokens\": 303,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:32:51 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '795'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/cassettes/agents/TestAgentA2AKickoffAsync.test_agent_kickoff_async_with_calculator.yaml

@@ -0,0 +1,616 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote agents\nYour personal goal is: Find and analyze
+      information"},{"role":"user","content":"\nCurrent Task: Ask the A2A agent to
+      calculate 100 divided by 4.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1325'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOhyHELb5GreUumlAiVahTNIN2R\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808771,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Calculate
+        100 divided by 4, please.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        266,\n    \"completion_tokens\": 40,\n    \"total_tokens\": 306,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:32:52 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '685'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"4d72e53a-2c40-42cb-b74a-404a5a798ba6","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"fa5e002d-f81b-4b61-84e6-27f40d0e0240","parts":[{"kind":"text","text":"Calculate
+      100 divided by 4, please."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '362'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"4d72e53a-2c40-42cb-b74a-404a5a798ba6\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"91d26e2b-6c66-45ce-9356-74a0eb634c28\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"151869b9-f640-454a-865d-405413a0859d\"}}\r\n\r\ndata:
+        {\"id\":\"4d72e53a-2c40-42cb-b74a-404a5a798ba6\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"91d26e2b-6c66-45ce-9356-74a0eb634c28\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"151869b9-f640-454a-865d-405413a0859d\"}}\r\n\r\ndata:
+        {\"id\":\"4d72e53a-2c40-42cb-b74a-404a5a798ba6\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"91d26e2b-6c66-45ce-9356-74a0eb634c28\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"3bf24e8a-6a3b-45f1-82eb-7a283a89e0ac\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        calculator] 100 / 4 = 25.0\\nThe result of 100 divided by 4 is 25.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"151869b9-f640-454a-865d-405413a0859d\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:32:51 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote agents\nYour personal goal is: Find and analyze
+      information"},{"role":"user","content":"\nCurrent Task: Ask the A2A agent to
+      calculate 100 divided by 4.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1325'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOmCdZD7rL5Q1syh0ag6AuH5bw3\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808776,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Calculate
+        100 divided by 4.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 266,\n    \"completion_tokens\":
+        38,\n    \"total_tokens\": 304,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:32:57 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '680'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"4ea0d213-a2cd-4d10-9b8c-034cfaa1d678","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"22c5127f-e6d8-4aae-852c-d2d131474e38","parts":[{"kind":"text","text":"Calculate
+      100 divided by 4."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '354'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"4ea0d213-a2cd-4d10-9b8c-034cfaa1d678\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"cba0ab67-9cc6-4afc-a15a-009b0abe4a1c\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"50c44a89-d6bd-4272-92d0-9aef38b35c93\"}}\r\n\r\ndata:
+        {\"id\":\"4ea0d213-a2cd-4d10-9b8c-034cfaa1d678\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"cba0ab67-9cc6-4afc-a15a-009b0abe4a1c\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"50c44a89-d6bd-4272-92d0-9aef38b35c93\"}}\r\n\r\ndata:
+        {\"id\":\"4ea0d213-a2cd-4d10-9b8c-034cfaa1d678\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"cba0ab67-9cc6-4afc-a15a-009b0abe4a1c\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"1d96bb0a-a3b7-4217-a1bc-bdb2658f14b7\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        calculator] 100 / 4 = 25.0\\n100 divided by 4 is 25.0.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"50c44a89-d6bd-4272-92d0-9aef38b35c93\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:32:56 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote agents\nYour personal goal is: Find and analyze
+      information"},{"role":"user","content":"\nCurrent Task: Ask the A2A agent to
+      calculate 100 divided by 4.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1325'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOqMBxYghf1iunoo7hIo23Mmyw0\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808780,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Calculate
+        100 divided by 4.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 266,\n    \"completion_tokens\":
+        38,\n    \"total_tokens\": 304,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:00 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '572'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"id":"217af3be-d6a6-48df-9460-f254481f7da6","jsonrpc":"2.0","method":"message/stream","params":{"configuration":{"acceptedOutputModes":["application/json"],"blocking":true},"message":{"kind":"message","messageId":"2886d1ee-0fc0-4143-98d8-e7a75ade6895","parts":[{"kind":"text","text":"Calculate
+      100 divided by 4."}],"referenceTaskIds":[],"role":"user"}}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*, text/event-stream'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-length:
+      - '354'
+      content-type:
+      - application/json
+      host:
+      - localhost:9999
+    method: POST
+    uri: http://localhost:9999
+  response:
+    body:
+      string: "data: {\"id\":\"217af3be-d6a6-48df-9460-f254481f7da6\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"a3254fcf-baf7-4f46-9767-60156d837a6e\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"submitted\"},\"taskId\":\"2c0e3b76-60f7-4636-934a-2ec41af75ead\"}}\r\n\r\ndata:
+        {\"id\":\"217af3be-d6a6-48df-9460-f254481f7da6\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"a3254fcf-baf7-4f46-9767-60156d837a6e\",\"final\":false,\"kind\":\"status-update\",\"status\":{\"state\":\"working\"},\"taskId\":\"2c0e3b76-60f7-4636-934a-2ec41af75ead\"}}\r\n\r\ndata:
+        {\"id\":\"217af3be-d6a6-48df-9460-f254481f7da6\",\"jsonrpc\":\"2.0\",\"result\":{\"contextId\":\"a3254fcf-baf7-4f46-9767-60156d837a6e\",\"final\":true,\"kind\":\"status-update\",\"status\":{\"message\":{\"kind\":\"message\",\"messageId\":\"b32f6b9c-70b5-4152-9df3-19436e3b655d\",\"parts\":[{\"kind\":\"text\",\"text\":\"[Tool:
+        calculator] 100 / 4 = 25.0\\n100 divided by 4 equals 25.0.\"}],\"role\":\"agent\"},\"state\":\"completed\"},\"taskId\":\"2c0e3b76-60f7-4636-934a-2ec41af75ead\"}}\r\n\r\n"
+    headers:
+      cache-control:
+      - no-store
+      connection:
+      - keep-alive
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Fri, 30 Jan 2026 21:32:59 GMT
+      server:
+      - uvicorn
+      transfer-encoding:
+      - chunked
+      x-accel-buffering:
+      - 'no'
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Research Analyst. Expert
+      researcher with access to remote agents\nYour personal goal is: Find and analyze
+      information"},{"role":"user","content":"\nCurrent Task: Ask the A2A agent to
+      calculate 100 divided by 4.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"a2a_ids":{"description":"A2A
+      agent IDs to delegate to.","items":{"const":"http://localhost:9999/.well-known/agent-card.json","type":"string"},"maxItems":1,"title":"A2A
+      Ids","type":"array"},"message":{"description":"The message content. If is_a2a=true,
+      this is sent to the A2A agent. If is_a2a=false, this is your final answer ending
+      the conversation.","title":"Message","type":"string"},"is_a2a":{"description":"Set
+      to false when the remote agent has answered your question - extract their answer
+      and return it as your final message. Set to true ONLY if you need to ask a NEW,
+      DIFFERENT question. NEVER repeat the same request - if the conversation history
+      shows the agent already answered, set is_a2a=false immediately.","title":"Is
+      A2A","type":"boolean"}},"required":["a2a_ids","message","is_a2a"],"title":"AgentResponse","type":"object","additionalProperties":false},"name":"AgentResponse","strict":true}},"stream":false}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '1325'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.openai.com
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-helper-method:
+      - beta.chat.completions.parse
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D3qOu8lITQt6WBCLcm6bvduIC2xP0\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769808784,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"{\\\"a2a_ids\\\":[\\\"http://localhost:9999/.well-known/agent-card.json\\\"],\\\"message\\\":\\\"Please
+        calculate 100 divided by 4.\\\",\\\"is_a2a\\\":true}\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        266,\n    \"completion_tokens\": 39,\n    \"total_tokens\": 305,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_e01c6f58e1\"\n}\n"
+    headers:
+      CF-RAY:
+      - CF-RAY-XXX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 30 Jan 2026 21:33:04 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      access-control-expose-headers:
+      - ACCESS-CONTROL-XXX
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - OPENAI-ORG-XXX
+      openai-processing-ms:
+      - '934'
+      openai-project:
+      - OPENAI-PROJECT-XXX
+      openai-version:
+      - '2020-10-01'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
+      x-ratelimit-limit-tokens:
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
+      x-ratelimit-remaining-requests:
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
+      x-ratelimit-remaining-tokens:
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
+      x-ratelimit-reset-requests:
+      - X-RATELIMIT-RESET-REQUESTS-XXX
+      x-ratelimit-reset-tokens:
+      - X-RATELIMIT-RESET-TOKENS-XXX
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1