Python: [BREAKING] Types API Review improvements by eavanvalkenburg · Pull Request #3647 · microsoft/agent-framework

eavanvalkenburg · 2026-02-03T16:05:21Z

Summary

This PR addresses all type-related sub-issues from the Python Single Agent API Review (#3575).

Changes

Replace Role and FinishReason with NewType + Literal

Removed EnumLike metaclass
Replaced Role and FinishReason classes with NewType + Literal
Type hints use RoleLiteral | str for IDE autocomplete while accepting custom values

Simplify ChatResponse/AgentResponse type hints

Changed messages parameter to accept ChatMessage | Sequence[ChatMessage] | None
Removed text parameter and **kwargs from __init__

Remove text parameter from ChatResponseUpdate/AgentResponseUpdate

Removed text parameter (use contents=[Content.from_text(...)] instead)
Removed **kwargs from both classes

Rename from_chat_response_updates

from_chat_response_updates → from_updates on ChatResponse
from_chat_response_generator → from_update_generator on ChatResponse
from_agent_run_response_updates → from_updates on AgentResponse

Remove try_parse_value method

Removed from ChatResponse and AgentResponse
Users should use try/except with .value property instead

Documentation clarification

Added agent_id parameter to AgentResponse and AgentResponseUpdate
Documented that author_name is on ChatMessage objects, not responses

Simplify ChatMessage.init signature

Made contents a positional argument: ChatMessage("role", ["text"])
Auto-convert strings in contents to TextContent
Kept text kwarg for backward compatibility with serialization

Allow Content as input on run/get_response

Updated prepare_messages and normalize_messages to accept Content
Updated type signatures in agents and clients

Breaking Changes

Role and FinishReason are now NewType instead of classes (no .value access)
ChatMessage signature changed: use ChatMessage("role", ["text"]) instead of ChatMessage(role="role", text="text")
try_parse_value removed - use try/except with .value property
text parameter removed from ChatResponseUpdate and AgentResponseUpdate
Method renames: from_chat_response_updates → from_updates, etc.

Closes

Closes #3591
Closes #3592
Closes #3593
Closes #3595
Closes #3596
Closes #3597
Closes #3615
Closes #3618

Testing

All 1639 tests pass
Linting: All checks passed
Type checking: 0 errors, 0 warnings

Copilot

Copilot encountered an error and was unable to review this pull request. You can try again by re-requesting a review.

markwallace-microsoft · 2026-02-03T18:47:02Z

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/a2a/agent_framework_a2a
_agent.py	139	7	94%	351–352, 389–390, 419–421
packages/ag-ui/agent_framework_ag_ui
_client.py	137	10	92%	84–88, 234, 264, 419–421
_event_converters.py	69	0	100%
_message_adapters.py	442	89	79%	64, 74–75, 84–87, 116–117, 120, 124–126, 135–137, 146–157, 159–161, 191, 204–205, 215–216, 253, 256, 258, 261, 264, 280, 297, 319, 350, 355, 366–367, 418, 434–435, 495–498, 500, 506, 514–515, 517, 521–524, 537, 626–629, 631, 696, 731–733, 735–738, 741–742, 744, 750, 753, 755, 758, 760, 766–767, 769
_run.py	432	121	71%	151–158, 301, 320–321, 336–337, 348, 351–352, 354–355, 357–359, 369, 379–382, 386–388, 390, 400, 403–406, 408–409, 412–418, 421–423, 426, 442–444, 451, 457–458, 460–461, 475–481, 492, 505, 507–508, 542–543, 595–597, 609–611, 635, 640–642, 758, 769–770, 777, 824–826, 841, 847, 855, 857, 893–899, 902–905, 907–916, 919, 926–927, 932, 938–940, 953–955
_utils.py	101	3	97%	72, 257, 262
packages/anthropic/agent_framework_anthropic
_chat_client.py	362	150	58%	365, 388, 390, 405, 427–430, 439, 441, 472–476, 478, 480–481, 483, 488–489, 491, 524–525, 534, 536–537, 542, 559–560, 602, 617, 621–622, 638, 647, 649, 653–654, 697–699, 701, 714–715, 722–724, 728–730, 734–737, 748, 750, 772, 782, 804–810, 817–818, 826–827, 835–838, 845–846, 852–853, 859–860, 866, 874–876, 880, 887–888, 894–895, 901–902, 908, 916–919, 926–927, 946, 953–954, 973, 995, 997, 1006–1007, 1013, 1035–1036, 1042–1043, 1052–1062, 1069–1075, 1082–1088, 1095–1104, 1111–1114
packages/azure-ai/agent_framework_azure_ai
_chat_client.py	480	67	86%	376, 637–638, 640, 643, 646, 649–654, 657, 659, 667, 679–681, 685, 688–689, 697–700, 710, 718–721, 723–724, 726–727, 734, 742–743, 751–752, 757–758, 762–769, 774, 777, 785, 791, 799–801, 804, 826–827, 960, 988, 1003, 1124, 1150, 1159, 1168, 1301
_client.py	195	13	93%	345, 347, 396, 425–430, 473, 510, 512, 588
packages/chatkit/agent_framework_chatkit
_converter.py	133	46	65%	115, 120, 168, 170, 340, 393, 395, 414–416, 418, 436, 438, 440, 443, 455, 465, 483, 503–527, 529–531
packages/copilotstudio/agent_framework_copilotstudio
_agent.py	75	4	94%	153–154, 189, 197
packages/core/agent_framework
_agents.py	310	40	87%	456, 855, 858–860, 985–987, 992–994, 1093, 1134, 1136, 1145–1150, 1156, 1158, 1168–1169, 1176, 1178–1179, 1187–1191, 1199–1200, 1202, 1207, 1209, 1243, 1283, 1303
_clients.py	57	4	92%	286, 330, 478, 480
_mcp.py	388	53	86%	111, 173, 182, 245, 253, 274, 364, 431, 466, 468, 472–473, 475–476, 530, 545, 563, 604, 710, 723–728, 750, 771, 774–776, 791–792, 798–800, 819, 828, 831–833, 848–849, 853–857, 874–878, 1018
_middleware.py	404	7	98%	810, 826, 873–874, 1079–1080, 1125
_serialization.py	105	4	96%	516, 532, 542, 610
_threads.py	136	3	97%	343, 474–475
_tools.py	767	76	90%	226, 272, 323, 325, 353, 523, 558–559, 661, 663, 683, 701, 715, 727, 732, 734, 741, 774, 845–847, 888, 913–922, 928–937, 973, 981, 1222, 1559, 1646–1650, 1672–1673, 1789, 1791, 1856, 1948, 1954, 1995–1996, 2009–2010, 2053, 2137, 2175–2176, 2214–2216, 2254–2255, 2265, 2322–2323, 2330–2331
_types.py	877	34	96%	88, 262, 292, 296, 1162, 1182–1183, 1185, 1193, 1230, 1242, 1282, 1621, 1720–1725, 1747, 1881, 1893, 2129, 2138, 2256, 2477, 2762–2764, 2854, 2865–2866, 2872–2873
observability.py	626	76	87%	323, 325–327, 330–332, 337–338, 344–345, 351–352, 359, 361–363, 366–368, 373–374, 380–381, 387–388, 395, 651, 654, 662–663, 666–669, 671, 674–676, 679–680, 708, 710, 721–723, 725–728, 732, 740, 841, 843, 992, 994, 998–1003, 1005, 1008–1012, 1014, 1289, 1614, 1617, 1676, 1850, 2004, 2006
packages/core/agent_framework/_workflows
_agent.py	280	45	83%	61, 69–75, 103–104, 260, 316, 330, 343, 392–395, 401, 407, 411–412, 415–421, 425–426, 495, 502, 508–509, 520, 552, 559, 580, 589, 593, 595–597, 604
_agent_executor.py	171	23	86%	95, 117, 151, 167–168, 219–220, 222–223, 255–257, 265–267, 277–279, 281, 285, 289, 293–294
_base_group_chat_orchestrator.py	170	12	92%	135, 301, 316, 350–352, 356, 375, 436, 480–482
_concurrent.py	187	28	85%	53, 62–63, 71–72, 91–92, 97, 124, 129, 134–135, 141, 163, 173, 180, 347, 350, 378, 434, 446, 485, 487–488, 490, 495, 517, 521
_conversation_state.py	36	5	86%	40, 45, 47, 49, 64
_group_chat.py	285	37	87%	172, 333, 340, 367, 378–379, 385, 390, 406, 433–438, 440, 473–476, 478, 483–487, 648, 653, 667, 748, 754, 799, 819, 915, 934, 953, 963
_handoff.py	382	57	85%	110–111, 113, 142–143, 163–173, 175, 177, 179, 184, 284, 338, 363, 389, 397–398, 412, 461–462, 492, 539–541, 724, 731, 736, 823, 826, 835–838, 848, 853, 860, 866–869, 904, 909, 1106, 1109, 1117, 1135, 1142, 1217
_magentic.py	614	91	85%	68–77, 82, 86–97, 262, 273, 277, 297, 358, 367, 369, 411, 428, 437–438, 440–442, 444, 455, 597, 599, 639, 689, 725–727, 729, 737–740, 744–747, 790, 817–820, 911, 917, 923, 962, 1000, 1029, 1046, 1057, 1111–1112, 1116–1118, 1142, 1163–1164, 1177, 1193, 1215, 1263–1264, 1302–1303, 1459, 1468, 1471, 1476, 1872, 1914, 1929, 1958
_message_utils.py	18	3	83%	22, 33, 37
_orchestration_request_info.py	54	0	100%
_orchestrator_helpers.py	21	2	90%	90–91
_workflow.py	248	17	93%	89, 259–261, 263–264, 282, 310, 411, 688, 722, 727, 730, 749–751, 816
packages/core/agent_framework/openai
_assistants_client.py	274	29	89%	347, 361, 364, 366–367, 370, 373, 376–377, 388, 413, 415, 417, 419, 421, 426, 429, 432, 436, 447, 532, 617, 652, 689–692, 744, 761
_chat_client.py	268	21	92%	181–182, 186, 272, 279, 360–367, 369–372, 382, 467, 504, 520
_responses_client.py	562	64	88%	257, 262, 264–265, 276, 294, 302, 325, 387, 419, 444, 450, 468–469, 491, 496, 552, 566, 583, 596, 651, 730, 735, 739–741, 745–746, 769, 838, 860–861, 876–877, 895–896, 1027–1028, 1044, 1046, 1121–1129, 1177, 1232, 1247, 1283–1284, 1286–1288, 1302–1304, 1314–1315, 1321, 1336
packages/mem0/agent_framework_mem0
_provider.py	83	3	96%	170–171, 174
packages/purview/agent_framework_purview
_middleware.py	93	0	100%
packages/redis/agent_framework_redis
_chat_message_store.py	149	14	90%	199, 232, 322–323, 326, 329, 485, 575–579, 588, 592
_provider.py	188	9	95%	255, 257, 265, 270–271, 274, 329, 386, 398
TOTAL	16255	1918	88%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3929	221 💤	0 ❌	0 🔥	1m 7s ⏱️

- Remove EnumLike metaclass from _types.py - Replace Role class with NewType('Role', str) + RoleLiteral - Replace FinishReason class with NewType('FinishReason', str) + FinishReasonLiteral - Update all usages across codebase to use string literals - Remove .value access patterns (direct string comparison now works) - Add backward compatibility for legacy dict serialization format - Update tests to reflect new string-based types Addresses microsoft#3591, microsoft#3615

- Remove overloads from ChatResponse.__init__ - Remove text parameter from ChatResponse.__init__ - Remove | dict[str, Any] from finish_reason and usage_details params - Remove **kwargs from AgentResponse.__init__ - Both now accept ChatMessage | Sequence[ChatMessage] | None for messages - Update docstrings and examples to reflect changes - Fix tests that were using removed kwargs - Fix Role type hint usage in ag-ui utils

…microsoft#3597) - Remove text parameter from ChatResponseUpdate.__init__ - Remove text parameter from AgentResponseUpdate.__init__ - Remove **kwargs from both update classes - Simplify contents parameter type to Sequence[Content] | None - Update all usages to use contents=[Content.from_text(...)] pattern - Fix imports in test files - Update docstrings and examples

- ChatResponse.from_chat_response_updates → ChatResponse.from_updates - ChatResponse.from_chat_response_generator → ChatResponse.from_update_generator - AgentResponse.from_agent_run_response_updates → AgentResponse.from_updates

…crosoft#3595) - Remove try_parse_value method from ChatResponse - Remove try_parse_value method from AgentResponse - Remove try_parse_value calls from from_updates and from_update_generator methods - Update samples to use try/except with response.value instead - Update tests to use response.value pattern - Users should now use response.value with try/except for safe parsing

…icrosoft#3596) - Add agent_id parameter to AgentResponse class - Document that author_name is on ChatMessage objects, not responses - Update ChatResponse docstring with author_name note - Update AgentResponse docstring with author_name note

- Make contents a positional argument accepting Sequence[Content | str] - Auto-convert strings in contents to TextContent - Remove overloads, keep text kwarg for backward compatibility with serialization - Update _parse_content_list to handle string items - Update all usages across codebase to use new format: ChatMessage("role", ["text"])

- Update prepare_messages and normalize_messages to accept Content - Update type signatures in _agents.py and _clients.py - Add tests for Content input handling

Update all remaining ChatMessage(role=..., text=...) to use new ChatMessage('role', ['text']) signature.

- Fix redis provider: remove .value access on string literals - Fix durabletask ensure_response_format: set _response_format before accessing .value

- Fix ollama _chat_client: remove .value on string literals - Fix ollama _chat_client: rename ai_model_id to model_id - Fix _parse_content_list: skip None values gracefully

…age to 95%

After rebasing on upstream/main which merged PR microsoft#3647 (Types API Review improvements), fix all packages to use the new API: - ChatMessage: Use keyword args (role=, text=, contents=) instead of positional args - Role: Compare using .value attribute since it's now an enum Packages fixed: - ag-ui: Fixed Role value extraction bugs in _message_adapters.py - anthropic: Fixed ChatMessage and Role comparisons in tests - azure-ai: Fixed Role comparison in _client.py - azure-ai-search: Fixed ChatMessage and Role in source/tests - bedrock: Fixed ChatMessage signatures in tests - chatkit: Fixed ChatMessage and Role in source/tests - copilotstudio: Fixed ChatMessage and Role in tests - declarative: Fixed ChatMessage in _executors_agents.py - mem0: Fixed ChatMessage and Role in source/tests - purview: Fixed ChatMessage in source/tests

@overload

* WIP * big update to new ResponseStream model * fixed tests and typing * fixed tests and typing * fixed tools typevar import * fix * mypy fix * mypy fixes and some cleanup * fix missing quoted names * and client * fix imports agui * fix anthropic override * fix agui * fix ag ui * fix import * fix anthropic types * fix mypy * refactoring * updated typing * fix 3.11 * fixes * redid layering of chat clients and agents * redid layering of chat clients and agents * Fix lint, type, and test issues after rebase - Add @overload decorators to AgentProtocol.run() for type compatibility - Add missing docstring params (middleware, function_invocation_configuration) - Fix TODO format (TD002) by adding author tags - Fix broken observability tests from upstream: - Replace non-existent use_instrumentation with direct instantiation - Replace non-existent use_agent_instrumentation with AgentTelemetryLayer mixin - Fix get_streaming_response to use get_response(stream=True) - Add AgentInitializationError import - Update streaming exception tests to match actual behavior * Fix AgentExecutionException import error in test_agents.py - Replace non-existent AgentExecutionException with AgentRunException * Fix test import and asyncio deprecation issues - Add 'tests' to pythonpath in ag-ui pyproject.toml for utils_test_ag_ui import - Replace deprecated asyncio.get_event_loop().run_until_complete with asyncio.run * Fix azure-ai test failures - Update _prepare_options patching to use correct class path - Fix test_to_azure_ai_agent_tools_web_search_missing_connection to clear env vars * Convert ag-ui utils_test_ag_ui.py to conftest.py - Move test utilities to conftest.py for proper pytest discovery - Update all test imports to use conftest instead of utils_test_ag_ui - Remove old utils_test_ag_ui.py file - Revert pythonpath change in pyproject.toml * fix: use relative imports for ag-ui test utilities * fix agui * Rename Bare*Client to Raw*Client and BaseChatClient - Renamed BareChatClient to BaseChatClient (abstract base class) - Renamed BareOpenAIChatClient to RawOpenAIChatClient - Renamed BareOpenAIResponsesClient to RawOpenAIResponsesClient - Renamed BareAzureAIClient to RawAzureAIClient - Added warning docstrings to Raw* classes about layer ordering - Updated README in samples/getting_started/agents/custom with layer docs - Added test for span ordering with function calling * Fix layer ordering: FunctionInvocationLayer before ChatTelemetryLayer This ensures each inner LLM call gets its own telemetry span, resulting in the correct span sequence: chat -> execute_tool -> chat Updated all production clients and test mocks to use correct ordering: - ChatMiddlewareLayer (first) - FunctionInvocationLayer (second) - ChatTelemetryLayer (third) - BaseChatClient/Raw...Client (fourth) * Remove run_stream usage * Fix conversation_id propagation * Python: Add BaseAgent implementation for Claude Agent SDK (#3509) * Added ClaudeAgent implementation * Updated streaming logic * Small updates * Small update * Fixes * Small fix * Naming improvements * Updated imports * Addressed comments * Updated package versions * Update Claude agent connector layering * fix test and plugin * Store function middleware in invocation layer * Fix telemetry streaming and ag-ui tests * Remove legacy ag-ui tests folder * updates * Remove terminate flag from FunctionInvocationContext, use MiddlewareTermination instead - Remove terminate attribute from FunctionInvocationContext - Add result attribute to MiddlewareTermination to carry function results - FunctionMiddlewarePipeline.execute() now lets MiddlewareTermination propagate - _auto_invoke_function captures context.result in exception before re-raising - _try_execute_function_calls catches MiddlewareTermination and sets should_terminate - Fix handoff middleware to append to chat_client.function_middleware directly - Update tests to use raise MiddlewareTermination instead of context.terminate - Add middleware flow documentation in samples/concepts/tools/README.md - Fix ag-ui to use FunctionMiddlewarePipeline instead of removed create_function_middleware_pipeline * fix: remove references to removed terminate flag in purview tests, add type ignore * fix: move _test_utils.py from package to test folder * fix: call get_final_response() to trigger context provider notification in streaming test * fix: correct broken links in tools README * docs: clarify default middleware behavior in summary table * fix: ensure inner stream result hooks are called when using map()/from_awaitable() * Fix mypy type errors * Address PR review comments on observability.py - Remove TODO comment about unconsumed streams, add explanatory note instead - Remove redundant _close_span cleanup hook (already called in _finalize_stream) - Clarify behavior: cleanup hooks run after stream iteration, if stream is not consumed the span remains open until garbage collected * Remove gen_ai.client.operation.duration from span attributes Duration is a metrics-only attribute per OpenTelemetry semantic conventions. It should be recorded to the histogram but not set as a span attribute. * Remove duration from _get_response_attributes, pass directly to _capture_response Duration is a metrics-only attribute. It's now passed directly to _capture_response instead of being included in the attributes dict that gets set on the span. * Remove redundant _close_span cleanup hook in AgentTelemetryLayer _finalize_stream already calls _close_span() in its finally block, so adding it as a separate cleanup hook is redundant. * Use weakref.finalize to close span when stream is garbage collected If a user creates a streaming response but never consumes it, the cleanup hooks won't run. Now we register a weak reference finalizer that will close the span when the stream object is garbage collected, ensuring spans don't leak in this scenario. * Fix _get_finalizers_from_stream to use _result_hooks attribute Renamed function to _get_result_hooks_from_stream and fixed it to look for the _result_hooks attribute which is the correct name in ResponseStream class. * Add missing asyncio import in test_request_info_mixin.py * Fix leftover merge conflict marker in image_generation sample * Update integration tests * Fix integration tests: increase max_iterations from 1 to 2 Tests with tool_choice options require at least 2 iterations: 1. First iteration to get function call and execute the tool 2. Second iteration to get the final text response With max_iterations=1, streaming tests would return early with only the function call/result but no final text content. * Fix duplicate function call error in conversation-based APIs When using conversation_id (for Responses/Assistants APIs), the server already has the function call message from the previous response. We should only send the new function result message, not all messages including the function call which would cause a duplicate ID error. Fix: When conversation_id is set, only send the last message (the tool result) instead of all response.messages. * Add regression test for conversation_id propagation between tool iterations Port test from PR #3664 with updates for new streaming API pattern. Tests that conversation_id is properly updated in options dict during function invocation loop iterations. * Fix tool_choice=required to return after tool execution When tool_choice is 'required', the user's intent is to force exactly one tool call. After the tool executes, return immediately with the function call and result - don't continue to call the model again. This fixes integration tests that were failing with empty text responses because with tool_choice=required, the model would keep returning function calls instead of text. Also adds regression tests for: - conversation_id propagation between tool iterations (from PR #3664) - tool_choice=required returns after tool execution * Document tool_choice behavior in tools README - Add table explaining tool_choice values (auto, none, required) - Explain why tool_choice=required returns immediately after tool execution - Add code example showing the difference between required and auto - Update flow diagram to show the early return path for tool_choice=required * Fix tool_choice=None behavior - don't default to 'auto' Remove the hardcoded default of 'auto' for tool_choice in ChatAgent init. When tool_choice is not specified (None), it will now not be sent to the API, allowing the API's default behavior to be used. Users who want tool_choice='auto' can still explicitly set it either in default_options or at runtime. Fixes #3585 * Fix tool_choice=none should not remove tools In OpenAI Assistants client, tools were not being sent when tool_choice='none'. This was incorrect - tool_choice='none' means the model won't call tools, but tools should still be available in the request (they may be used later in the conversation). Fixes #3585 * Add test for tool_choice=none preserving tools Adds a regression test to ensure that when tool_choice='none' is set but tools are provided, the tools are still sent to the API. This verifies the fix for #3585. * Fix tool_choice=none should not remove tools in all clients Apply the same fix to OpenAI Responses client and Azure AI client: - OpenAI Responses: Remove else block that popped tool_choice/parallel_tool_calls - Azure AI: Remove tool_choice != 'none' check when adding tools When tool_choice='none', the model won't call tools, but tools should still be sent to the API so they're available for future turns. Also update README to clarify tool_choice=required supports multiple tools. Fixes #3585 * Keep tool_choice even when tools is None Move tool_choice processing outside of the 'if tools' block in OpenAI Responses client so tool_choice is sent to the API even when no tools are provided. * Update test to match new parallel_tool_calls behavior Changed test_prepare_options_removes_parallel_tool_calls_when_no_tools to test_prepare_options_preserves_parallel_tool_calls_when_no_tools to reflect that parallel_tool_calls is now preserved even when no tools are present, consistent with the tool_choice behavior. * Fix ChatMessage API and Role enum usage after rebase - Update ChatMessage instantiation to use keyword args (role=, text=, contents=) - Fix Role enum comparisons to use .value for string comparison - Add created_at to AgentResponse in error handling - Fix AgentResponse.from_updates -> from_agent_run_response_updates - Fix DurableAgentStateMessage.from_chat_message to convert Role enum to string - Add Role import where needed * Fix additional ChatMessage API and method name changes - Fix ChatMessage usage in workflow files (use text= instead of contents= for strings) - Fix AgentResponse.from_updates -> from_agent_run_response_updates in workflow files - Fix test files for ChatMessage and Role enum usage * Fix remaining ChatMessage API usage in test files * Fix more ChatMessage and Role API changes in source and test files - Fix ChatMessage in _magentic.py replan method - Fix Role enum comparison in test assertions - Fix remaining test files with old ChatMessage syntax * Fix ChatMessage and Role API changes across packages - Add Role import where missing - Fix ChatMessage signature: positional args to keyword args (role=, text=, contents=) - Fix Role enum comparisons: .role.value instead of .role string - Fix FinishReason enum usage in ag-ui event converters - Rename AgentResponse.from_updates to from_agent_run_response_updates in ag-ui Fixes API compatibility after Types API Review improvements merge * Fix ChatMessage and Role API changes in github_copilot tests * Fix ChatMessage and Role API changes in redis and github_copilot packages - Fix redis provider: Role enum comparison using .value - Fix redis tests: ChatMessage signature and Role comparisons - Fix github_copilot tests: ChatMessage signature and Role comparisons - Update docstring examples in redis chat message store * Fix ChatMessage and Role API changes in devui package - Fix executor: ChatMessage signature change - Fix conversations: Role enum to string conversion in two places - Fix tests: ChatMessage signatures and Role comparisons * Fix ChatMessage and Role API changes in a2a and lab packages - Fix a2a tests: Role comparisons and ChatMessage signatures - Fix lab tau2 source: Role enum comparison in flip_messages, log_messages, sliding_window - Fix lab tau2 tests: ChatMessage signatures and Role comparisons * Remove duplicate test files from ag-ui/tests (tests are in ag_ui_tests) * Fix ChatMessage and Role API changes across packages After rebasing on upstream/main which merged PR #3647 (Types API Review improvements), fix all packages to use the new API: - ChatMessage: Use keyword args (role=, text=, contents=) instead of positional args - Role: Compare using .value attribute since it's now an enum Packages fixed: - ag-ui: Fixed Role value extraction bugs in _message_adapters.py - anthropic: Fixed ChatMessage and Role comparisons in tests - azure-ai: Fixed Role comparison in _client.py - azure-ai-search: Fixed ChatMessage and Role in source/tests - bedrock: Fixed ChatMessage signatures in tests - chatkit: Fixed ChatMessage and Role in source/tests - copilotstudio: Fixed ChatMessage and Role in tests - declarative: Fixed ChatMessage in _executors_agents.py - mem0: Fixed ChatMessage and Role in source/tests - purview: Fixed ChatMessage in source/tests * Fix mypy errors for ChatMessage and Role API changes - durabletask: Use str() fallback in role value extraction - core: Fix ChatMessage in _orchestrator_helpers.py to use keyword args - core: Add type ignore for _conversation_state.py contents deserialization - ag-ui: Fix type ignore comments (call-overload instead of arg-type) - azure-ai-search: Fix get_role_value type hint to accept Any - lab: Move get_role_value to module level with Any type hint * Improve CI test timeout configuration - Increase job timeout from 10 to 15 minutes - Reduce per-test timeout to 60s (was 900s/300s) - Add --timeout_method thread for better timeout handling - Add --timeout-verbose to see which tests are slow - Reduce retries from 3 to 2 and delay from 10s to 5s This ensures individual test timeouts are shorter than the job timeout, providing better visibility when tests hang. With 60s timeout and 2 retries, worst case per test is ~180s. * Fix ChatMessage API usage in docstrings and source - Fix ChatMessage positional args in docstrings: _serialization.py, _threads.py, _middleware.py - Fix ChatMessage in tau2 runner.py - Fix role comparison in _orchestrator_helpers.py to use .value - Fix role comparison in _group_chat.py docstring example - Fix role assertions in test_durable_entities.py to use .value * Revert tool_choice/parallel_tool_calls changes - must be removed when no tools OpenAI API requires tool_choice and parallel_tool_calls to only be present when tools are specified. Restored the logic that removes these options when there are no tools. - Restored check in _chat_client.py to remove tool_choice and parallel_tool_calls when no tools present - Restored same logic in _responses_client.py - Reverted test to expect the correct behavior * fixed issue in tests * fix: resolve merge conflict markers in ag-ui tests * fix: restructure ag-ui tests and fix Role/FinishReason to use string types * fix: streaming function invocation and middleware termination - Refactor streaming function invocation to use get_final_response() on inner streams - Fix MiddlewareTermination to accept result parameter for passing results - Fix _AutoHandoffMiddleware to use MiddlewareTermination instead of context.terminate - Fix AgentMiddlewareLayer.run() to properly forward function/chat middleware - Remove duplicate middleware registration in AgentMiddlewareLayer.__init__ - Fix exception handling in _auto_invoke_function to properly capture termination - Fix mypy errors in core package - Update tests to use stream=True parameter for unified run API * fix all tests command * Refactor integration tests to use pytest fixtures - Merge testutils.py into conftest.py for azurefunctions integration tests - Merge dt_testutils.py into conftest.py for durabletask integration tests - Convert all integration tests to use fixtures instead of direct imports (fixes ModuleNotFoundError with --import-mode=importlib) - Add sample_helper fixture for azurefunctions tests - Add agent_client_factory and orchestration_helper fixtures for durabletask - Integration tests now skip with descriptive messages when services unavailable - Restructure devui tests into tests/devui/ with proper conftest.py - Add test organization guidelines to CODING_STANDARD.md - Remove __init__.py from test directories per pytest best practices * Fix pytest_collection_modifyitems to only skip integration tests The hook was skipping all tests in the test session, not just integration tests. Now it only skips items in the integration_tests directory. * Fix mem0 tests failing on Python 3.13 Use patch.object on the imported module instead of @patch with string path to ensure the mock takes effect regardless of import timing. * fix mem0 * another attempt for mem0 * fix for mem0 * fix mem0 * Increase worker initialization wait time in durabletask tests Increase from 2 to 8 seconds to allow time for: - Python startup and module imports - Azure OpenAI client creation - Agent registration with DTS worker - Worker connection to DTS This helps prevent test failures in CI where the first tests may run before the worker is fully ready to process requests. * Fix streaming test to use ResponseStream with finalizer The _consume_stream method now expects a ResponseStream that can provide a final AgentResponse via get_final_response(). Update the test to use ResponseStream with AgentResponse.from_updates as the finalizer. * Fix MockToolCallingAgent to use new ResponseStream API and update samples * small updates to run_stream to run * fix sub workflow * temp fix for az func test --------- Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>

eavanvalkenburg requested a review from a team as a code owner February 3, 2026 16:05

Copilot AI review requested due to automatic review settings February 3, 2026 16:05

markwallace-microsoft added python lab Agent Framework Lab labels Feb 3, 2026

Copilot AI reviewed Feb 3, 2026

View reviewed changes

markwallace-microsoft added the documentation Improvements or additions to documentation label Feb 3, 2026

dmytrostruk approved these changes Feb 4, 2026

View reviewed changes

eavanvalkenburg changed the title ~~Python: Types API Review improvements~~ Python: [BREAKING] Types API Review improvements Feb 4, 2026

eavanvalkenburg mentioned this pull request Feb 4, 2026

[BREAKING] Python: Rename from_agent_run_response_updates to from_agent_response_updates #3659

Closed

4 tasks

eavanvalkenburg added 14 commits February 4, 2026 09:19

Allow Content as input on run and get_response

af7db9a

- Update prepare_messages and normalize_messages to accept Content - Update type signatures in _agents.py and _clients.py - Add tests for Content input handling

Fix ChatMessage usage across packages and samples

e0a2bb6

Update all remaining ChatMessage(role=..., text=...) to use new ChatMessage('role', ['text']) signature.

Fix Role string usage and response format parsing

b2ab128

- Fix redis provider: remove .value access on string literals - Fix durabletask ensure_response_format: set _response_format before accessing .value

Fix ollama .value and ai_model_id issues, handle None in content list

ee88378

- Fix ollama _chat_client: remove .value on string literals - Fix ollama _chat_client: rename ai_model_id to model_id - Fix _parse_content_list: skip None values gracefully

Fix A2AAgent type signature to include Content

9b05be6

Fix Role/FinishReason NewType dict annotations and improve test cover…

827be5a

…age to 95%

Fix mypy errors for Role/FinishReason NewType usage

4397131

eavanvalkenburg force-pushed the types-api-review-3575 branch from 93d7f47 to 4397131 Compare February 4, 2026 08:21

eavanvalkenburg added 2 commits February 4, 2026 09:30

Fix Role.TOOL and Role.ASSISTANT usage in _orchestrator_helpers.py

2d79b74

Fix Role NewType usage in durabletask _models.py

d46c840

moonbox3 approved these changes Feb 4, 2026

View reviewed changes

eavanvalkenburg added this pull request to the merge queue Feb 4, 2026

Merged via the queue into microsoft:main with commit 838a7fd Feb 4, 2026
35 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Python: [BREAKING] Types API Review improvements#3647

Python: [BREAKING] Types API Review improvements#3647
eavanvalkenburg merged 16 commits intomicrosoft:mainfrom
eavanvalkenburg:types-api-review-3575

eavanvalkenburg commented Feb 3, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

markwallace-microsoft commented Feb 3, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Conversation

eavanvalkenburg commented Feb 3, 2026

Summary

Changes

Replace Role and FinishReason with NewType + Literal

Simplify ChatResponse/AgentResponse type hints

Remove text parameter from ChatResponseUpdate/AgentResponseUpdate

Rename from_chat_response_updates

Remove try_parse_value method

Documentation clarification

Simplify ChatMessage.init signature

Allow Content as input on run/get_response

Breaking Changes

Closes

Testing

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Uh oh!

markwallace-microsoft commented Feb 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Python Unit Test Overview

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

markwallace-microsoft commented Feb 3, 2026 •

edited

Loading