Agent
Agent
any_agent.AnyAgent
Bases: ABC
Base abstract class for all agent implementations.
This provides a unified interface for different agent frameworks.
Source code in src/any_agent/frameworks/any_agent.py
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 | |
agent
property
The underlying agent implementation from the framework.
This property is intentionally restricted to maintain framework abstraction and prevent direct dependency on specific agent implementations.
If you need functionality that relies on accessing the underlying agent: 1. Consider if the functionality can be added to the AnyAgent interface 2. Submit a GitHub issue describing your use case 3. Contribute a PR implementing the needed functionality
Raises:
| Type | Description |
|---|---|
NotImplementedError
|
Always raised when this property is accessed |
framework
abstractmethod
property
The Agent Framework used.
__aenter__()
async
__aexit__(exc_type, exc_val, exc_tb)
async
Exit the async context manager and clean up resources.
Source code in src/any_agent/frameworks/any_agent.py
cleanup_async()
async
Clean up resources including MCP client connections.
This should be called when you're done using the agent to ensure all resources are properly released.
Source code in src/any_agent/frameworks/any_agent.py
create(agent_framework, agent_config)
classmethod
Create an agent using the given framework and config.
Source code in src/any_agent/frameworks/any_agent.py
create_async(agent_framework, agent_config)
async
classmethod
Create an agent using the given framework and config.
Source code in src/any_agent/frameworks/any_agent.py
run(prompt, **kwargs)
Run the agent with the given prompt.
run_async(prompt, **kwargs)
async
Run the agent asynchronously with the given prompt.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
prompt
|
str
|
The user prompt to be passed to the agent. |
required |
kwargs
|
Any
|
Will be passed to the underlying runner used by the framework. |
{}
|
Returns:
| Type | Description |
|---|---|
AgentTrace
|
The |
Source code in src/any_agent/frameworks/any_agent.py
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 | |
serve_async(serving_config=None)
async
Serve this agent asynchronously using the protocol defined in the serving_config.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
serving_config
|
MCPServingConfig | A2AServingConfig | None
|
Configuration for serving the agent. If None, uses default A2AServingConfig. Must be an instance of A2AServingConfig or MCPServingConfig. |
None
|
Returns:
| Type | Description |
|---|---|
ServerHandle
|
A ServerHandle instance that provides methods for managing the server lifecycle. |
Raises:
| Type | Description |
|---|---|
ImportError
|
If the |
Example
Source code in src/any_agent/frameworks/any_agent.py
update_output_type_async(output_type)
abstractmethod
async
Update the output type of the agent in-place.
This method allows updating the agent's output type without recreating the entire agent instance, which is more efficient than the current approach of recreating the agent.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
output_type
|
type[BaseModel] | None
|
The new output type to use, or None to remove output type constraint |
required |
Source code in src/any_agent/frameworks/any_agent.py
any_agent.AgentCancel
Bases: ABC, Exception
Abstract base class for control-flow exceptions raised in callbacks.
Within a callback, raise an exception inherited from AgentCancel when you want to intentionally stop agent execution and handle that specific case in your application code.
Unlike regular exceptions (which are wrapped in AgentRunError), AgentCancel subclasses propagate directly to the caller, allowing you to catch them by their specific type.
When to use AgentCancel vs regular exceptions
- Use AgentCancel: When stopping execution is expected behavior (rate limits, safety guardrails, validation failures) and you want to handle it distinctly in your application.
- Use regular exceptions: When something unexpected goes wrong, and you want consistent error handling via AgentRunError.
Example
class StopOnLimit(AgentCancel): pass
class LimitCallsCallback(Callback): def before_tool_execution(self, context, args, *kwargs): if context.shared.get("call_count", 0) > 10: raise StopOnLimit("Exceeded call limit") return context
try: agent.run("prompt") except StopOnLimit as e: # Handle the expected cancellation. print(f"Canceled: {e}") print(f"Collected {len(e.trace.spans)} spans") except AgentRunError as e: # Handle unexpected errors. print(f"Unexpected error: {e.original_exception}")
Source code in src/any_agent/frameworks/any_agent.py
trace
property
Execution trace collected before cancellation.
Returns None if accessed before the framework processes the exception.
any_agent.AgentRunError
Bases: Exception
Wrapper for unexpected exceptions that occur during agent execution.
When an unexpected exception is raised during agent execution (from callbacks, tools, or the underlying framework), it is caught and wrapped in AgentRunError.
Exceptions that inherit from AgentCancel are not wrapped,
they propagate directly to the caller.
AgentRunError ensures:
- The execution trace is preserved - you can inspect what happened
before the error via the
traceproperty. - Consistent error handling - all unexpected errors are wrapped in the same type, regardless of the underlying framework.
- Original exception access - the wrapped exception is available
via
original_exceptionfor debugging.
Example
try: agent.run("prompt") except AgentRunError as e: print(f"Error: {e.original_exception}") print(f"Trace had {len(e.trace.spans)} spans before failure")
Source code in src/any_agent/frameworks/any_agent.py
original_exception
property
The underlying exception that was caught.
trace
property
The execution trace collected up to the point of failure.