.NET: Python: Merge main into feature-durabletask branch (#3385)

* Python: Add factory pattern to concurrent orchestration builder (#2738) * Add factory pattern to concurrent orchestration builder * Update readme * Address AI comments * Fix unit tests * Fix import * Prevent multiple calls to set participants or factories * Add comments * Mitigate warnings * Fix mypy * Address comments * Address Copilot comments * Fix tests * Python: fix: GroupChat ManagerSelectionResponse JSON Schema for OpenAI Structured Outpu… (#2750) * fix: ManagerSelectionResponse JSON Schema for OpenAI Structured Output Strict Mode * refactor: install pre-commit then commit again * Capture file IDs from code interpreter in streaming responses (#2741) * .NET: [BREAKING] Prevent nulls in AIAgent property (#2719) * prevent nulls in AIAgent property * address feedback * code ql sm04598 (#2723) Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * .NET: Add Conversation State Sample (Step05) (#2697) * Initial plan * Add Agent_OpenAI_Step05_Conversation sample for conversation state management Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update Program.cs comment to accurately describe the sample Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update the code to use the ConversationClient more in line with the samples in OpenAI * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Changing sample to use ChatClientAgent and conversationId in GetNewThread --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.7 to 4.0.4.11 (#2777) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.4.11 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.Identity from 1.17.0 to 1.17.1 (#2780) --- updated-dependencies: - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2778) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Python: added more complete parsing for mcp tool arguments (#2756) * added more complete parsing for mcp tool arguments * fixed mypy * added nonlocal model counter, and some fixes * fixes in naming logic * extracted json parsing function, added parametrized test and checked coverage * Python: Updated package versions (#2784) * Updated package versions * Small fix * Bump actions/checkout from 5 to 6 (#2404) Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/checkout dependency-version: '6' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: adds support for labels in edges, fixes rendering of labels in dot a… (#1507) * adds support for labels in edges, fixes rendering of labels in dot and mermaid, adds rendering of labels in edges * Update dotnet/src/Microsoft.Agents.AI.Workflows/Visualization/WorkflowVisualizer.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * escaping edge labels, adding tests for labels containing strange characters that would break the diagram and enabling the previous signature so the API has backwards compatibility. * Unify label in EdgeData * Edge API adjustments, removed useless "sanitizer" * fixed test --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Added custom args and thread object to ai_function kwargs (#2769) * Added an example of using kwargs in ai_function * Added thread object to ai_function kwargs * Updated docs * Small fix * Added thread parameter filtering * Fix WorkflowAgent to include thread convo history. Enable checkpointing. (#2774) * Update OpenAIResponses.yaml to match AgentSchema (#2598) 1. Update `connection` child types -- `kind: ApiKey` to `kind: key` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/apikeyconnection/ 2. Update `outputSchema`'s `PropertySchema` to be `kind` instead of `type` otherwise schema will fail: https://microsoft.github.io/AgentSchema/reference/propertyschema/ * Python: Remove warnings from workflow builder on not using factories (#2808) * Revert concurrent * Fix comments * Python: Filter framework kwargs from MCP tool invocations (#2870) * Filter framework kwargs from MCP tool invocations * Fixes * Python: Fix WorkflowAgent to emit yield_output as agent response (#2866) * Fix WorkflowAgent to emit yield_output as agent response * use raw_representation * Raw representation handling * Python: Use agent description in HandoffBuilder auto-generated tools (#2713) (#2714) ## Summary Enhanced `HandoffBuilder._apply_auto_tools` to use the target agent's description when creating handoff tools, providing more informative tool descriptions for LLMs. ## Changes - Modified `_apply_auto_tools` to extract `description` from `AgentExecutor._agent` when available - Updated iteration to use `.items()` for more efficient dict traversal - Handoff tools now use agent descriptions instead of generic placeholders ## Example Before: "Handoff to the refund_agent agent." After: "You handle refund requests. Ask for order details and process refunds." ## Testing - All handoff tests pass (20/20) - No breaking changes to existing API Fixes #2713 Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * Python: [BREAKING] Observability updates (#2782) * fixes Python: Add env_file_path parameter to setup_observability() similar to AzureOpenAIChatClient Fixes #2186 * WIP on updates using configure_azure_monitor * improved setup and clarity * fixed root .env.example * revert changes * updated files * updated sample * updated zero code * test fixes and fixed links * fix devui * removed planning docs * added enable method and updated readme and samples * clarified docstring * add return annotation * updated naming * update capatilized version * updated readme and some fixes * updated decorator name inline with the rest * feedback from comments addressed * Python: Fix middleware terminate flag to exit function calling loop immediately (#2868) * Fix middleware terminate flag to exit function calling loop immediately * Eliminating duck typing * Improve function exec result handling * Fix race condition * Fix mypy issues * Python: Fix context duplication in handoff workflows when restoring from checkpoint (#2867) * Fix context duplication in handoff workflows when restoring from checkpoint * Address Copilot PR review * .NET: Update to latest Azure.AI.*, OpenAI, and M.E.AI* (#2850) * Update to latest Azure.AI.*, OpenAI, and M.E.AI* Absorb breaking changes in Responses surface area * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/Program.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Using patch to remove the model is necessary, updated the response client to actually use the the ForAgent --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> * Bump actions/download-artifact from 6 to 7 (#2862) Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 6 to 7. - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](https://github.com/actions/download-artifact/compare/v6...v7) --- updated-dependencies: - dependency-name: actions/download-artifact dependency-version: '7' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump actions/cache from 4 to 5 (#2861) Bumps [actions/cache](https://github.com/actions/cache) from 4 to 5. - [Release notes](https://github.com/actions/cache/releases) - [Changelog](https://github.com/actions/cache/blob/main/RELEASES.md) - [Commits](https://github.com/actions/cache/compare/v4...v5) --- updated-dependencies: - dependency-name: actions/cache dependency-version: '5' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump actions/upload-artifact from 5 to 6 (#2860) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 5 to 6. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/upload-artifact dependency-version: '6' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Python : Ollama Connector for Agent Framework (#1104) * Initial Commit for Olama Connector * Added Olama Sample * Add Sample & Fixed Open Telemetry * Fixed Spelling from Olama to Ollama * remove"opentelemetry-semantic-conventions-ai ~=0.4.13" since its handled in a different pr * Added Tool Calling * Finalizing test cases * Adjust samples to be more reliable * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/pyproject.toml Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/tests/test_ollama_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Improved Docstrings & Sample * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Integrate PR Feedback - Divided Streaming and Non-Streaming into independent Methods - Catch Ollama Validation Error - Add OTEL Provider Name - Checked Ollama Messages - Add Usage Statistics * Revert setting, so it can be none * Validate Message formatting between AF and Ollama * Catch Ollama Error and raise a ServiceResponse Error * Fix mypy error * remove .vscode comma * Add Reasoning support & adjust to new structure * Add Ollama Multimodality and Reasoning * Add test cases for reasoning * Add Tests for Error Handling in Ollama Client * Update python/samples/getting_started/multimodal_input/ollama_chat_multimodal.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Integrated Copilot Feedback * Implement first PR Feedback * Adjust Readme files for examples * Adjust argument passing via additional chat options * Implemented PR Feedback * Removing Ollama Package from Core and moving samples * Fix Link & Adding Samples to Main Sample Readme * Fixing Links in Readme * Moved Multimodal and Chat Example * Fixed Link in ChatClient to Ollama * Fix AgentFramework Links in Ollama Project * Fix observability breaking change --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Skip failing IT (#2904) * .NET: Cosmos DB UT Fast Skip (For Non-Configured Local envs) (#2906) * Cosmos DB UT Fast Skip (Non-Configured Local envs) + Long running UT skip in pipeline when no CosmosDB changes happened * Force a CosmosDB source code change to trigger the pipeline * Address possible string boolean mismatch * Add debug * Enabling emulator always when running IT * .NET: Add TTLs to durable agent sessions (#2679) * .NET: Add TTLs to durable agent sessions * Remove unnecessary async * PR feedback: clarify UTC * PR feedback: limit minimum signal delay to <= 5 minutes * PR feedback: Fix TTL disablement * Linter: use auto-property * Fix build break from OpenAI SDK change * Updated CHANGELOG.md * PR feedback * Reduce default TTL to 14 days to work around DTS bug * Python: Update Mem0Provider to use v2 search API `filters` parameter (#2766) * short fix to move id parameters to filters object * added tests * small fix * mem0 dependency update * Updated package versions (#2913) * .NET: Switch to new "Run" method name. (#2843) * Switch to new "RunAgent" method name. * Try to disable false positive naming warning. * Add comment about disabled warnings. * Rename `RunAgent` to just `Run`. * Update CHANGELOG. * Python: Switch to new "run" method name. (#2890) * Switch to `run` method. * Add support for deprecated `run_agent`. * Fix entity method name. * Fix method name and improve tests. * Update comment. * Update Python CHANGELOG. * [BREAKING] Python: Add factory pattern to handoff orchestration builder (#2844) * WIP: Factory pattern to handoff * Add factory pattern to concurrent orchestration builder; Next: tests and sample verification * Add tests and improve comments * Fix mypy * Simplify handoff_simple.py * Simplify handoff_autonoumous.py and bug fix * Update readme * Address Copilot comments * Python: Flow custom kwargs to agents via Workflow SharedState (#2894) * Flow custom kwargs to agents via SharedState * Address Copilot feedback * Improve sample typing * Fix test * Fix Pydantic error when using Literal type for tool params (#2893) * Updated Ollama package version (#2920) * Python: Azure AI Agent with Bing Grounding Citations Sample (#2892) * bing grounding sample with citations * small fix * fix * .NET: Make DelegatingAIAgent abstract (#2797) * Initial plan * Make DelegatingAIAgent abstract Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Added additional arguments for Azure AI agent (#2922) * Python: Correction of MCP image type conversion in _mcp.py (#2901) * Correction of MCP image type conversion in _mcp.py * Added a new overload to the init function of the DataContent() type of the Agent Framework, edited the test case to correctly test the usage of the data and uri fields while using DataContent() * Fixed tests related to the changes of the DataContent type, added testing for both string and byte representations * Pass kwargs into subworkflows (#2923) * Python: Move ollama samples to samples getting started dir (#2921) * Move ollama samples to samples getting started dir * Address feedback * Python: fix: correct BadRequestError when using Pydantic model in response_fo… (#1843) * fix: correct BadRequestError when using Pydantic model in response_format * Fix lint --------- Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> * .NET: [Breaking] Delete display name property (#2758) * delete the AIAgent.DisplayName property * use agent name as a first value for activity display name * Update dotnet/src/Microsoft.Agents.AI.Workflows/Specialized/HandoffAgentExecutor.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: cleanup and refactoring of chat clients (#2937) * refactoring and unifying naming schemes of internal methods of chat clients * set tool_choice to auto * fix for mypy * added note on naming and fix #2951 * fix responses * fixes in azure ai agents client * Python: Workflow add option to visualize internal executors (#2917) * Workflow add option to visualize internal executors * Address Copilot comments * Python: Fixes Run ID and Thread ID casing to align with AG-UI Typescript SDK (#2948) * added camelCase input to run id and thread id aligning with @ag-ui/core * fixed per copilot suggestions * Python: Add workflow cancellation sample (#2732) * Add workflow cancellation sample Add sample demonstrating how to cancel a running workflow using asyncio tasks. Shows both cancellation mid-execution and normal completion paths. Useful for implementing timeouts, graceful shutdown, or A2A executors. * update docstring * .NET: Update Anthropic package to version 12.0.0 (#2914) * Initial plan * Update Anthropic package to version 12.0.0 Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> * Python: Add Azure Managed Redis Support with Credential Provider (#2887) * azure redis support * small fixes * azure managed redis sample * fixes * Bump CommunityToolkit.Aspire.OllamaSharp from 13.0.0-beta.440 to 13.0.0 (#2856) --- updated-dependencies: - dependency-name: CommunityToolkit.Aspire.OllamaSharp dependency-version: 13.0.0 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.11 to 4.0.5 (#2853) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2854) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Fix WorkflowAgent event handling and kwargs forwarding (#2946) * Fix kwargs propagation through workflow.as_agent() * Fix WorkflowAgent to respect AgentExecutor output_response setting * .NET: Use GrpcEntityRunner instead of TaskEntityDispatcher (#2759) * Use GrpcEntityRunner instead of TaskEntityDispatcher * Pin to Durable worker 1.11.0 * Set the invocation result * Update all Durable packages * Update changelog, rename dispatcher to encondedEntityRequest * Python: Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG (#2968) * Bump Py version to 1.0.0b251218 for a release. Update CHANGELOG * update lock * Fix formatting * Fix ChatKit typing * Python: Introducing Foundry Local Chat Clients (#2915) * redo foundry local chat client * fix mypy and spelling * better docstring, updated sample * fixed tests and added tests * small sample update * Updated package versions (#2978) * Python: Added GitHub MCP sample with PAT (#2967) * added github mcp sample with PAT * addressed copilot fixes * env fix * Python: Preserve reasoning blocks with OpenRouter (#2950) * Preserve reasoning blocks with OpenRouter * Put encrypted reasoning in TextReasoningContent * Remove unneccessary change * Fix docs * Support streaming * Fix handling None in TextReasoningContent.text * Python: Added response.created and response.in_progress event process to OpenAIBaseResponseClient (#2975) * added response.created and response.in_progress to include response.id * better doc string * added tests for the new streaming event types * Python: Introducing support for Bedrock-hosted models (Anthropic, Cohere, etc.) (#2610) * Pushing the bedrock related changes to the new branch after addressing the review comments * 2524 Addressed the second round review comments * 2524 Addressed few more minor comments on the PR * resolving the merge conflict * 2524 resolved the uv.lock conflicts * 2524 addressed more comments * 2524 removed the print statement to fix the checks failure * 2524 resolved the CI failure issues * 2524 fixing the CI breaks * 2524 Addressed the review comment * 2524 resolved conflict --------- Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> * .NET: [Durable Agents] Reliable streaming sample (#2942) * .NET: [Durable Agents] Reliable streaming sample * Add automated validation for new sample * Address Copilot PR feedback * Fix typo in README.md about agent definitions (#2634) * Fix typo in README.md about agent definitions * Update agent-samples/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: latency improvements (#3014) * latency improvements * fixed mypy, added coding standards and instructions * slight logic improvement * Python: Updated package versions (#3024) * Updated package versions * Updated changelog * Python: add powerfx safe mode (#3028) * add powerfx safe mode * improved docstring and aligned env_file loading * ensured test uses reset * .NET: [Breaking] Introduce RunCoreAsync/RunCoreStreamingAsync delegation pattern in AIAgent (#2749) * Initial plan * Refactor AIAgent: Make RunAsync and RunStreamingAsync non-abstract, add RunCoreAsync and RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix infinite recursion in test implementations Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Make RunAsync and RunStreamingAsync non-virtual as requested Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix DelegatingAIAgent subclasses to use RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix XML documentation references in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Restore <see cref> tags with proper qualified signatures in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Rollback unnecessary XML documentation changes in AnonymousDelegatingAIAgent Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Remove pragma and update crefs to RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix EntityAgentWrapper to call base.RunCoreAsync/RunCoreStreamingAsync Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * fix compilation issues * fix compilatio issue * fix tests * fix unit tests * fix unit test --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * add issue template and additional labeling (#3006) * fix and extra int test (#3037) * .NET: [BREAKING] Refactor ChatMessageStore methods to be similar to AIContextProvider and add filtering support (#2604) * Refactor ChatMessageStore methods to be similar to AIContextProvider * Fix file encoding * Ensure that AIContextProvider messages area also persisted. * Update formatting and seal context classes * Improve formatting * Remove optional messages from constructor and add unit test * Add ChatMessageStore filtering via a decorator * Update sample and cosmos message store to store AIContextProvider messages in right order. Fix unit tests. * Update Workflowmessage store to use aicontext provider messages. * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Improve xml docs messaging * Address code review comments. * Also notify message store on failure --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * [BREAKING] Remove unused AgentThreadMetadata (#3067) * Remove unused AgentThreadMetadata * Update DurableTask Changelog * Python: Fix AzureAIClient failure when conversation history contains assistant messages (#3076) * Fix AzureAIClient failure when conversation history contains assistant messages * Address PR review feedback: improve docstring and test assertions * Remove redundant cast * Fix: Update OTLP exporter protocol conditions (#3070) * Python: Fix ExecutorInvokedEvent and ExecutorCompletedEvent observability data (#3090) * Fix ExecutorInvokedEvent.data mutation bug * Fix bug related to not yielding output type * .NET: Seal ChatClientAgentThread (#2842) * Initial plan * Seal ChatClientAgentThread class Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * Fix broken strands urls. (#3102) * Fix broken strands urls. * Fix typos * .NET: Fix message ordering inconsistency when using AIContextProvider (#2659) * Initial plan * Fix message ordering inconsistency when using AIContextProvider Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Revert to original message ordering: Input, AIContextProvider, Response Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Reorder messages to ChatClient to match MessageStore order: Existing, Input, AIContextProvider Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Remove redundant test methods as existing tests already verify the behavior Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * fix: tool_choice parameter not being honored when passed to agent.run() (#3095) * sharepoint sample fix (#3108) * Bump versions to 1.0.0b260106 for a release. Update CHANGELOG.md (#3109) * Bump Bedrock version to latest (#3110) * Python: Fix MCP tool result serialization for list[TextContent] (#2523) * Fix MCP tool result serialization for list[TextContent] When MCP tools return results containing list[TextContent], they were incorrectly serialized to object repr strings like: '[<agent_framework._types.TextContent object at 0x...>]' This fix properly extracts text content from list items by: 1. Checking if items have a 'text' attribute (TextContent) 2. Using model_dump() for items that support it 3. Falling back to str() for other types 4. Joining single items as plain text, multiple items as JSON array Fixes #2509 * Address PR review feedback for MCP tool result serialization - Extract serialize_content_result() to shared _utils.py - Fix logic: use texts[0] instead of join for single item - Add type annotation: texts: list[str] = [] - Return empty string for empty list instead of '[]' - Move import json to file top level - Add comprehensive unit tests for serialization * Address PR review feedback: fix type checking and double serialization - Add isinstance(item.text, str) check to ensure text attribute is a string - Fix double-serialization issue by keeping model_dump results as dicts until final json.dumps (removes escaped JSON strings in arrays) - Improve docstring with detailed return value documentation - Add test for non-string text attribute handling - Add tests for list type tool results in _events.py path * Simplify PR: minimal changes to fix MCP tool result serialization Addresses reviewer feedback about excessive refactoring: - Reset _events.py to original structure - Only add import and use serialize_content_result in one location - All review comments addressed in serialize_content_result(): - Added isinstance(item.text, str) check - Use model_dump(mode="json") to avoid double-serialization - Improved docstring with explicit return value documentation - Empty list returns "" instead of "[]" * Refactor: Move MCP TextContent serialization to core prepare_function_call_results Per reviewer feedback, moved the TextContent serialization logic from ag-ui's serialize_content_result to the core package's prepare_function_call_results function. Changes: - Added handling for objects with 'text' attribute (like MCP TextContent) in _prepare_function_call_results_as_dumpable - Removed serialize_content_result from ag-ui/_utils.py - Updated _events.py and _message_adapters.py to use prepare_function_call_results from core package - Updated tests to match the core function's behavior * Fix failing tests for prepare_function_call_results behavior - test_tool_result_with_none: Update expected value to 'null' (JSON serialization of None) - test_tool_result_with_model_dump_objects: Use Pydantic BaseModel instead of plain class * Fix B903 linter error: Convert MockTextContent to dataclass The ruff linter was reporting B903 (class could be dataclass or namedtuple) for the MockTextContent test helper classes. This commit converts them to dataclasses to satisfy the linter check. * Python: Improve DevUI, add Context Inspector view as new tab under traces (#2742) * Improve DevUI, add Context Inspector view as new tab under traces * fix mypy errors * fix: Handle stale MCP connections in DevUI executor MCP tools can become stale when HTTP streaming responses end - the underlying stdio streams close but `is_connected` remains True. This causes subsequent requests to fail with `ClosedResourceError`. Add `_ensure_mcp_connections()` to detect and reconnect stale MCP tools before agent execution. This is a workaround for an upstream Agent Framework issue where connection state isn't properly tracked. Fixes MCP tools failing on second HTTP request in DevUI. fixes #1476 #1515 #2865 * fix #1572 report import dependency errors more clearly * Ensure there is streaming toggle where users can select streaming vs non streaming mode in devui . Fixes .NET: [Python] DevUI tool call rendering in non-streaming mode? * remove unused dead code * improve ux - workflows with agents show a chat component in execution timelien, also ensure magentic final output shows correctly * update ui build * update devui to use instrumentation instead of tracing, other instrumentation and type/instance check fixes * .NET: Seal factory contexts and add non JSO deserialize overloads (#3066) * Seal factory contexts and add non JSO deserialize overloads * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Enable blank issues in issue template configuration Need to re-enable creating blank issues * updated templates (#3106) * updated templates * enabled blank and fixed triage * made language optional and moved to the bottom for features * Python: Streaming sample for azurefunctions (#3057) * Streaming sample for azurefunctions * Fixed links and sample name * Addressed feedback * Addressed feedback * Fixed integration tests * Updated test * Python: fix(azure-ai): Fix response_format handling for structured outputs (#3114) * fix(azure-ai): read response_format from chat_options instead of run_options * refactor: use explicit None checks for response_format * Fix mypy error * Mypy fix * Python: Bump python version to 1.0.0b260107 for a release (#3128) * Bump python version to 1.0.0b260107 for a release * Update changelog * Make A2AAgent public, so that it's concrete implementation methods can be used. (#3119) * .NET: Map additional props <-> A2A metadata (#3137) * map additional props from agent run options to a2a request metadata * small touches * add unit tests for new extension methods * Sort using * add unit test * add additiona unit tests * special case json element to avoid unnecessary serialization * Python: Fix Anthropic streaming response bugs (#3141) * test commit identity * fix(anthropic): fix raw_representation and finish_reason in streaming * lint fix * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.5 to 4.0.5.1 (#2994) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.5.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Bump Anthropic from 12.0.0 to 12.0.1 (#2993) --- updated-dependencies: - dependency-name: Anthropic dependency-version: 12.0.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: [Breaking] Prevent loss of input messages & streamed updates when resuming streaming (#2748) * save input messages and stream updates to the continuation token to be able to use them in the last successful stream resumption call. * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/tests/Microsoft.Agents.AI.UnitTests/ChatClient/ChatClientAgent_BackgroundResponsesTests.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentContinuationToken.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix typo * init continuation token from chat response * remove unnecessary types for source generation * remove check for continuation token passed at initial run * remove check for continuation token pass at initial run * centralize continuation token parsing * update xml comments * use readonly collection instead of enumerable --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * .NET: fix: Expose WorkflowErrorEvent as ErrorContent (#2762) * fix: Expose WorkflowErrorEvent as ErrorContent When hosted using .AsAgent(), Workflows were not exposing inner errors coming as Exceptions (through the WorkflowErrorEvent) The fix is to convert their message to an ErrorContent on the way out, rather than rely on the default "empty update" to collect the raw event. * feat: Add a way to show/suppress exception information * Bump Microsoft.Agents.AI.Workflows from 1.0.0-preview.251125.1 to 1.0.0-preview.251219.1 (#2997) --- updated-dependencies: - dependency-name: Microsoft.Agents.AI.Workflows dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> * .NET: Add Run overloads to expose ChatClientAgentRunOptions in IntelliSense (#3115) * Initial plan * Add ChatClientAgentExtensions for improved discoverability of ChatClientAgentRunOptions Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Address code review feedback - use collection expression syntax Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Apply suggestion from @westey-m * Fix issues with Copilot implementation * Add additional tests for structured output overloads. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: westey-m <164392973+westey-m@users.noreply.github.com> * Python: Add tool call/result content types and update connectors and samples (#2971) * Add new AI content types and image tool support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Add Python content types for tool calls/results and image generation tool support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Address review feedback for tool content and samples Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Tighten image generation typing and sample tools list Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Align image generation output typing Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Handle MCP naming, image options mapping, and connector tool content Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Allow MCP call in function approval request Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Remove raw image_generation tool remapping Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Restore Anthropic tool_use to function calls unless code execution Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix lint issues for hosted file docstring and MCP parsing Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Import ChatResponse types in Anthropic client Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix Anthropics citation type imports and MCP typing for handoff/tools Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Skip lightning tests without agentlightning and fix function call import Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * fix lint on lab package * rebuilt anthropic parsing * redid anthropic parsing * typo * updated parsing and added missing docstrings * fix tests * mypy fixes * second mypy fix * add new class to other samples --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> * Bump Google.GenAI from 0.6.0 to 0.9.0 (#2995) --- updated-dependencies: - dependency-name: Google.GenAI dependency-version: 0.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Bump js-yaml from 4.1.0 to 4.1.1 in /python/packages/devui/frontend (#3123) Bumps [js-yaml](https://github.com/nodeca/js-yaml) from 4.1.0 to 4.1.1. - [Changelog](https://github.com/nodeca/js-yaml/blob/master/CHANGELOG.md) - [Commits](https://github.com/nodeca/js-yaml/compare/4.1.0...4.1.1) --- updated-dependencies: - dependency-name: js-yaml dependency-version: 4.1.1 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Updated package versions (#3144) * .NET: Bump Microsoft.Agents.AI.OpenAI and Microsoft.Extensions.AI.OpenAI (#2996) * Bump Microsoft.Agents.AI.OpenAI and Microsoft.Extensions.AI.OpenAI Bumps Microsoft.Agents.AI.OpenAI from 1.0.0-preview.251125.1 to 1.0.0-preview.251219.1 Bumps Microsoft.Extensions.AI.OpenAI from 10.1.0-preview.1.25608.1 to 10.1.1-preview.1.25612.2 --- updated-dependencies: - dependency-name: Microsoft.Agents.AI.OpenAI dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Extensions.AI.OpenAI dependency-version: 10.1.1-preview.1.25612.2 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Agents.AI.OpenAI dependency-version: 1.0.0-preview.251219.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Microsoft.Extensions.AI.OpenAI dependency-version: 10.1.1-preview.1.25612.2 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Fixed samples --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> * Python: fix(ag-ui): Execute tools with approval_mode, fix shared state, code cleanup (#3079) * fix(ag-ui): execute tools after approval in human-in-the-loop flow * Fix shared state bug * Bug fix finalized * Refactoring to clean up code * Code cleanup * More fixes * More code cleanup * Add version detection in __init__.py to ruff ignore list * Track agent name with updates for workflow agent (#3146) * Python: Fix AzureAIClient tool call bug for AG-UI use (#3148) * Fiz AzureAIClient tool call bug * Address copilot feedback * Python: multiple bug fixes (#3150) * fix Python: kwargs are not passed to _prepare_thread_and_messages in ChatAgent.run Fixes #3118 * fix Python: [Bug]: model_id versus model_deployment_name is confusing in Azure AI Agents Fixes #3147 * add types * fixed type and docstring * fix(anthropic): fix duplicate ToolCallStartEvent in streaming tool calls (#3051) When processing `input_json_delta` events, the Anthropic client was passing the tool name from the previous `tool_use` event. This caused ag-ui's `_handle_function_call_content` to emit a `ToolCallStartEvent` for every streaming chunk (since it triggers on `if content.name:`). This fix changes the behavior to pass an empty string for `name` in `input_json_delta` events, matching OpenAI's behavior where streaming argument chunks have `name=""`. The initial `tool_use` event still provides the tool name, so only one `ToolCallStartEvent` is emitted. Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * .NET: [BREAKING] Change GetNewThread and DeserializeThread to async (#3152) * Change GetNewThread and DeserializeThread plus ChatMessageStore and AIContextProvider Factories to async * Merge fixes * Fix Ollama model env var in documentation (#3156) Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com> * Python: Add Pydantic request model and OpenAPI tags support to AG-UI FastAPI endpoint (#2522) * feat(ag-ui): Add Pydantic request model and OpenAPI tags support - Add AGUIRequest Pydantic model in _types.py with field descriptions - Update add_agent_framework_fastapi_endpoint() to accept tags parameter - Use AGUIRequest model for automatic validation and OpenAPI schema generation - Export AGUIRequest and DEFAULT_TAGS in __init__.py - Update test_endpoint.py to expect 422 for invalid requests - Add tests for OpenAPI schema, default tags, custom tags, and validation Benefits: - Better API documentation with complete request schema in Swagger UI - Automatic request validation with Pydantic - Organized endpoints under 'AG-UI' tag instead of 'default' - Improved developer experience and type safety Fixes #<issue-number> * test(ag-ui): Add test for internal error handling to achieve 100% coverage - Add test_endpoint_internal_error_handling() to cover exception handling code - Mock copy.deepcopy to simulate internal error during default_state processing - Add type: ignore for FastAPI tags parameter (known pyright compatibility issue) - Achieves 100% test coverage for _endpoint.py (previously missing lines 103-105) * .NET: Improve resolving `AITool` from DI (#3175) * remove localagenttoolregistry * also give the factory method API * Python: Fix MCPStreamableHTTPTool to use new streamable_http_client API (#3088) * Fix MCPStreamableHTTPTool to use new streamable_http_client API with proper httpx client cleanup Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Update docstring to reflect new streamable_http_client API usage Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Refactor MCPStreamableHTTPTool to accept optional http_client parameter and delegate client creation to streamable_http_client Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Update mcp package minimum version to 1.24.0 for streamable_http_client API support Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Fix critical bugs: apply headers/timeout/sse_read_timeout when creating httpx client, add version constraint <2, and properly manage client lifecycle Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Simplify implementation: remove headers/timeout/sse_read_timeout params, remove kwargs, remove close() override per feedback Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Add back **kwargs parameter for backward compatibility (accepted but not used) Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * Remove unused httpx import from test file Note: The uv.lock file needs to be updated with 'uv sync' to reflect the mcp version constraint change (>=1.24.0,<2) Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> * cicd fixes * udpated samples with headers examples --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> * azureai direct a2a endpoint support (#3127) * Python: [BREAKING]: removed display_name, renamed context_providers, middleware and AggregateContextProvider (#3139) * removed display_name, renamed context_providers, middleware and AggregateContextProvider * fixes * fixed test * testfix * removed mistakenly put back test * updated new test * rename middlewares to middleware * middleware fixes * Python: MCP Improvements: improved connection loss behavior, pagination for loading and a param to control representation (#3154) * pagination support (#2848) added a parse_tool_result param and connection loss (#2884) * fix #3153 * improved connection handling * improved logic * Python: Add declarative workflow runtime (#2815) * Further support for declarative python workflows * Add tests. Clean up for typing and formatting * Improvements and cleanup * Typing cleanup. Improve docstrings * Proper code in docstrings * Fix malformed code-block directive in docstring * Remove dead links * PR feedback * Address PR feedback * Address PR feedback * Remove sl * Update devui frontend * More cleanup * Fix uv lock * Skip Py 3.14 tests as powerfx doesn't support it * Fix mypy error * Fix for tool calls * Removed stale docstring * Fix lint * Standardize on .NET namespaces. Revert DevUI changes (bring in later) * Implement remaining items for Python declarative support to match dotnet * point URL to agent, not to agentcard (#3176) * Python: [BREAKING]: Introducing Options as TypedDict and Generic (#3140) * WIP typeddict for options * updated all clients and ChatAgents * updated everything * added ADR * fix mypy * proper typevar imports * fixed import * fixed other imports * slight update in the sample * updated from feedback * fixes * fixed missing covariants and test fixes * fixed typing * updated anthropic thinking config * ruff fixes * fixed int tests * fix tests and mypy * updated integration tests * updated docstring and test fix * improved options handling in obser * mypy fix * updated a host of integration tests * fix tests * bedrock fix * [BREAKING] Python: Refactor orchestrations (#3023) * Group chat refactoring Part 1; Next: HIL and handoff * Add agent approval flow; next samples * WIP: samples * WIP: HIL samples * Group chat HIL working; next: handoff * Fix group chat tool approval sample * WIP: refactor handoff; next handoff handling * Handoff done; next handoff samples and concurrent and sequential * Handoff samples, concurrent, and sequential done; next Magentic * WIP: magentic; next test with samples + HIL * Magentic Working; next fix all samples and tests * Fix handoff samples; next tests * WIP: fixing tests; some orchestration as agent samples are failing * Group chat unit tests done * Handoff unit tests done * Remove old orchestration_request_info and fix related tests * Magentic unit tests done * Fix samples * Fix test * Fix test 2 * mypy * Address comments * Update readme * Address comments * Address comments 2 * Replace display name * Python: ADR for create/get agent API (#2618) * ADR for create/get agent API * Updated ADR with implementation options * Small updates * Updated decision outcome section * Updated broken links * Small updates * Fixed merge conflicts * Small fix * Updated decision outcome section * Small fixes * Updated provider naming based on client SDK * Add ignored parameter for CodeQL in workflow (#3204) * Implement IReadOnlyList on InMemoryChatMessageStore (#3205) * .NET: Make ChatMessageStore and AIContextProvider context props settable (#3196) * Make ChatMessageStore and AIContextProvider context props setable * Add validation to preserve non-null requirement of certain properties. * Fix broken tests. * Python: Add dependencies param to ag-ui FastAPI endpoint (#3191) * Add dependencies param to ag-ui FastAPI endpoint * Address Copilot feedback * renamed all (#3207) * Python: ADR for simplified get response (#3098) * ADR for simplified get response * updated some language, added agent option and code comparison * small update in sample * added workflows and expanded some points * changed decision and number * updated with stream=False default * .NET: [Breaking] Rename`AgentRunResponse` and `AgentRunResponseUpdate` classes (#3197) * rename AgentRunResponse and AgentRunResponseUpdate classes - part1 * rename varialbles, parameters, methods and tests * rollback unnecessary changes * .NET: [Breaking] Rename AgentRunResponseEvent and AgentRunUpdateEvent classes (#3214) * rename AgentRunResponseEvent and AgentRunUpdateEvent classes * rollback unnecessary changes * Python: Create/Get Agent API for Azure V2 (#3059) * Added get_agent method to Azure AI V2 * Small fixes * Small fix * Removed AzureAIAgentProvider * Added create_agent method * Small fixes * Fixed code interpreter tool mapping * Added agent provider for V2 client * Updated response format handling * Added provider example * Fixed errors * Update python/samples/getting_started/agents/azure_ai/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Small fix * Updates from merge * Resolved comments * Resolved comments --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: Add more specific exceptions to Workflow (#3188) * Add more specifc workflow exceptions * Fix tests * AI comments * Misc * Python: Added AzureAI sample for downloading code interpreter generated files (#3189) * added azure ai code interpreter file download sample * copilot fix suggestions * function name fixes + readme update * small fix * update package versions (#3223) Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> * Python: fix(core): correct FunctionResultContent ordering in WorkflowAgent.merge_updates (#3168) * fix(core): simplify FunctionResultContent ordering in WorkflowAgent.merge_updates * improve comment * Fix name * fix(workflows): rename WorkflowOutputEvent.source_executor_id to executor_id for API consistency (#3166) * Python: fix(ag-ui): add MCP tool support for AG-UI approval flows (#3212) * add MCP tool support for AG-UI approval flows * use attribute in place of property * Python: Properly configure structured outputs based on new options dict (#3213) * Properly configure structured outputs based on new options dict * Fix mypy * .NET: Merge AgentRunOptions.AdditionalProperties into ChatOptions.AdditionalProperties (#3184) * Merge AgentRunOptions.AdditionalProperties into ChatOptions.AdditionalProperties * Fix namespace and typo. * .NET: Update Google.GenAI to 0.11.0 and remove polyfill implementations (#3232) * Initial plan * Update Google.GenAI to 0.11.0 and remove polyfill files Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * .NET: [BREAKING] Renamed CreateAIAgent/GetAIAgent to AsAIAgent (#3222) * Renamed chat client extension method * Additional renaming * Updated documentation * Fixed tests * Small fix * Small fix * Updated DurableAIAgent and fixed integration tests (#3241) * Python: Create/Get Agent API for Azure V1 (#3192) * Added provider implementation for Azure AI V1 * Small fixes * Fixed OpenAPI example * Fixed local MCP example * Fixed hosted MCP example * Fixed file search sample * Small fixes * Resolved comments * Doc updates * Bump azure-core from 1.37.0 to 1.38.0 in /python (#3209) Bumps [azure-core](https://github.com/Azure/azure-sdk-for-python) from 1.37.0 to 1.38.0. - [Release notes](https://github.com/Azure/azure-sdk-for-python/releases) - [Commits](https://github.com/Azure/azure-sdk-for-python/compare/azure-core_1.37.0...azure-core_1.38.0) --- updated-dependencies: - dependency-name: azure-core dependency-version: 1.38.0 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Python: Create/Get Agent API for OpenAI Assistants (#3208) * Added provider implementation * Added example with response format * Small improvements * Python: (AG-UI) Support service-managed thread on AG-UI (#3136) * added service thread support * set service_thread_id to only supplied_thread_id * uses raw_representation to extract the conversation_id * removed accidental edit * updated test to use raw_representation * resolves copilot review feedback * revert back StubAgent, since not used * removed relative module import * removed hasattr check per PR feedback * Create/Get Agent API - fixes and example improvements (#3246) * .NET Purview Middleware: Improve Background Job Runner Injection (#3256) * Clean up background job dependency injection * Fix xml documentation grammar * Python: [BREAKING] Renamed create_agent to as_agent (#3249) * Renamed create_agent to as_agent * Override for as_agent * Added override * Python: Update package version (#3258) * package version 260116 * removed name tags * Python: Fixed Azure chat client for asynchronous filtering (#3260) * Fixed Azure chat client for asynchronous filtering * Updated test * Python: Fixed use_agent_middleware calling private _normalize_messages (#3264) * Fix use_agent_middleware calling private _normalize_messages * Fixed A2A and Copilot Studio agent * Python: Added rai_config to Azure AI agent creation (#3265) * Add kwargs to create_agent method * Added test for kwargs * Addressed comment * Added doc string * Python: Filter conversation_id when passing kwargs to agent as tool (#3266) * Filter conversation_id when passing kwargs to agent as tool * Small fix * Update python/samples/getting_started/agents/azure_ai/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/samples/getting_started/agents/openai/openai_responses_client_with_agent_as_tool.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/samples/getting_started/agents/azure_ai/azure_ai_with_agent_as_tool.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Bump actions/setup-dotnet from 5.0.1 to 5.1.0 (#3273) Bumps [actions/setup-dotnet](https://github.com/actions/setup-dotnet) from 5.0.1 to 5.1.0. - [Release notes](https://github.com/actions/setup-dotnet/releases) - [Commits](https://github.com/actions/setup-dotnet/compare/v5.0.1...v5.1.0) --- updated-dependencies: - dependency-name: actions/setup-dotnet dependency-version: 5.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Update ignored checks in merge-gatekeeper workflow * Python: [BREAKING] Make response_format validation errors visible to users (#3274) * Make response_format validation errors visible to users * Small fix * Addressed comments * Python: fix(declarative): Fix MCP tool connection not passed from YAML to Azure AI agent creation API (#3248) * fix(declarative): Fix MCP tool connection not passed from YAML * Add samples to README * Fix mypy * Fix mypy again * Address PR comments * fix #3171, ensure proper form rendering for int (#3201) * Bump uv from 0.9.25 to 0.9.26 in /python (#3288) Bumps [uv](https://github.com/astral-sh/uv) from 0.9.25 to 0.9.26. - [Release notes](https://github.com/astral-sh/uv/releases) - [Changelog](https://github.com/astral-sh/uv/blob/main/CHANGELOG.md) - [Commits](https://github.com/astral-sh/uv/compare/0.9.25...0.9.26) --- updated-dependencies: - dependency-name: uv dependency-version: 0.9.26 dependency-type: direct:development update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump ruff from 0.14.11 to 0.14.13 in /python (#3287) Bumps [ruff](https://github.com/astral-sh/ruff) from 0.14.11 to 0.14.13. - [Release notes](https://github.com/astral-sh/ruff/releases) - [Changelog](https://github.com/astral-sh/ruff/blob/main/CHANGELOG.md) - [Commits](https://github.com/astral-sh/ruff/compare/0.14.11...0.14.13) --- updated-dependencies: - dependency-name: ruff dependency-version: 0.14.13 dependency-type: direct:development update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump tar from 7.4.3 to 7.5.3 in /python/packages/devui/frontend (#3267) Bumps [tar](https://github.com/isaacs/node-tar) from 7.4.3 to 7.5.3. - [Release notes](https://github.com/isaacs/node-tar/releases) - [Changelog](https://github.com/isaacs/node-tar/blob/main/CHANGELOG.md) - [Commits](https://github.com/isaacs/node-tar/compare/v7.4.3...v7.5.3) --- updated-dependencies: - dependency-name: tar dependency-version: 7.5.3 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * .NET: Delete sync extension methods for agent (#3291) * Delete sync extension methods for agent * Fix comments and obsolete attribute * Remove more sync methods. * Fix naming and comments. * Fix unit tests * Python: Fix: Add system_instructions to ChatClient LLM span tracing (#3164) * Fix: Add system_instructions to ChatClient LLM span tracing - Add system_instructions parameter to _capture_messages() calls in _trace_get_response() and _trace_get_streaming_response() - Extract instructions from chat_options in kwargs - Add unit tests to verify system_instructions are captured correctly When using ChatClient with ChatOptions.instructions, the OpenTelemetry LLM span was missing system messages in gen_ai.input.messages and the gen_ai.system_instructions attribute was not being set. This fix aligns the ChatClient-level tracing with the Agent-level tracing which already correctly passes system_instructions. Fixes #3163 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Add edge case tests for system_instructions - Add test for empty string instructions (should not set attribute) - Add test for list-type instructions (verify multiple items captured) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Simplify: use options.get('instructions') directly instead of kwargs.get('chat_options') Addresses reviewer feedback: - Removed unnecessary chat_options variable from kwargs - Directly access instructions from the options parameter - Updated tests to use dict syntax for options (TypedDict convention) --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> * Improve PR number handling in workflow (#3302) * Improve PR number handling in workflow Refine PR number extraction and validation method. * Update .github/workflows/python-test-coverage-report.yml Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Fix error message for invalid PR number --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * .NET: Update Microsoft.Extensions.AI.* packages to 10.2.0 (#3211) * Initial plan * Update Microsoft.Extensions.AI.* to 10.2.0 and fix timestamp behavior tests Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> * .NET: Pass AdditionalProperties from parent to child when exposing an agent as a FunctionTool (#3219) * Pass AdditionalProperties from parent to child when exposing an agent as a FunctionTool * Rename variable to improve readability. * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Python: [Breaking] Simplified Content types to a single class with classmethod constructors. (#3252) * ported Content to a new model * fixed linting * fixes * fixed data format handling * fix for 3.10 mypy * fix * fix int test * .NET: Durable Agent samples and automated validation for non-Azure Functions (#3042) * Durable Agent samples and automated validation for non-Azure Functions * Update test projects * fix file encoding * Remove AgentThreadMetadata usage * Absorb breaking change from #3152 * Absorb newer breaking changes (AgentRunResponse --> AgentResponse) * Absorb more breaking changes (see #3222) * Improve integration test reliability (isolated task hubs, etc.) * Fix flakey streaming test --------- Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * Python: fix(core): handle anyio cancel scope errors during MCP connection cleanup (#3277) * fix(core): handle anyio cancel scope errors during MCP connection cleanup * Address Copilot feedback * Python: fix(ag-ui): properly handle json serialize with handoff workflows as agent (#3275) * fix(ag-ui): properly handle json serialize with handoff workflows as agent * Other improvements around handling non-serializable objects * Bump tomli from 2.3.0 to 2.4.0 in /python (#3182) Bumps [tomli](https://github.com/hukkin/tomli) from 2.3.0 to 2.4.0. - [Changelog](https://github.com/hukkin/tomli/blob/master/CHANGELOG.md) - [Commits](https://github.com/hukkin/tomli/compare/2.3.0...2.4.0) --- updated-dependencies: - dependency-name: tomli dependency-version: 2.4.0 dependency-type: direct:development update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * .Net: Fix DebuggerDisplay attribute to reference existing property (#3326) * Initial plan * Fix DebuggerDisplay attribute to use Name instead of DisplayName Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * .NET: Add sample to show multiple AIContextProvider usage (#3284) * Add sample to show multiple AIContextProvider usage * Update comment. * Update messaging in README. * Address PR comments. --------- Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * .NET: Update Conversation Sample to use Conversation Id instead (#3180) * Update Conversation Sample to use conversation Id instead * Remove Run infix * Remove the sync GetAIAgent from sample * Python: Fix local MCP tools with `AzureAIProjectAgentProvider` (#3315) * azureai v2 local mcp fix * addressed copilot comments * .NET: Improve readme for agents V2 (#3285) * Improve readme for agents V2 * Architectural justification * Update dotnet/samples/GettingStarted/FoundryAgents/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Bump pyasn1 from 0.6.1 to 0.6.2 in /python (#3257) Bumps [pyasn1](https://github.com/pyasn1/pyasn1) from 0.6.1 to 0.6.2. - [Release notes](https://github.com/pyasn1/pyasn1/releases) - [Changelog](https://github.com/pyasn1/pyasn1/blob/main/CHANGES.rst) - [Commits](https://github.com/pyasn1/pyasn1/compare/v0.6.1...v0.6.2) --- updated-dependencies: - dependency-name: pyasn1 dependency-version: 0.6.2 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * .NET: Fix DebuggerDisplay attribute in AIAgent.cs to reference existing properties (#2985) * Initial plan * Fix DebuggerDisplay attribute in AIAgent.cs to reference existing properties Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> * Python: feat(anthropic): Add response_format support for structured outputs (#3301) * fix(anthropic): Add response_format support for structured outputs * only use from options * use native way of response format * ruff lint fix * address comment; handle dict * Updated package versions (#3335) * Set min version of dependent azure-ai-projects to 2.0.0b3 (#3347) * Adding feature collections ADR (#3332) * .NET: [Breaking] Allow passing auth token credential to cosmosdb extensions (#3250) * allow passing token credentials to cosmosdb extensions * Update dotnet/src/Microsoft.Agents.AI.CosmosNoSql/CosmosDBWorkflowExtensions.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI.CosmosNoSql/CosmosDBWorkflowExtensions.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/src/Microsoft.Agents.AI.CosmosNoSql/CosmosDBChatExtensions.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix: Subworkflows do not work well with HostAsAgent (#3240) Subworkflows run into issues with Checkpointing and the Chat Protocol: * The concurrency rework made subtle changes in behaviour that introduced a hang when using subworkflows with ChatProtocol and streaming execution. * The ResetAsync() implementation in WorkflowHostExecutor was improperly resetting the joinContext - this was happening on restore checkpoint _after_ the join context was attached when * Subworkflows cannot be used as the start node when hosted AsAgent due to inability to treat Catch-All as a Chat Protocol * Subworkflow ownership issue when used in non-concurrent mode after finishing a run Also fixes: * When ChatMessages are output by executors that are not agents, there is no corresponding AgentResponseUpdate/AgentResponse event Breaking Changes * [BREAKING CHANGE] It is possible to provide the wrong RunId when resuming from CheckpointInfo (even though the data already exists on CheckpointInfo) * Python: .NET: Executor source gen for workflow executor routing (#3131) * Roslyn Source Generators for Workflow Executor Routing. * Update dotnet/src/Microsoft.Agents.AI.Workflows.Generators/ExecutorRouteGenerator.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * WIP. * All fixed up except dangling sends/yields attriutes, working on that next. * Add protocol-only generation for SendsMessage/YieldsOutput attributes * Ensuring collections that can change order are sorted to enable pipeline caching. * Improvents per PR feedback. --------- Co-authored-by: alliscode <bentho@microsoft.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * .NET: Joslat fix sample issue (#3270) * adds support for labels in edges, fixes rendering of labels in dot and mermaid, adds rendering of labels in edges * Update dotnet/src/Microsoft.Agents.AI.Workflows/Visualization/WorkflowVisualizer.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * escaping edge labels, adding tests for labels containing strange characters that would break the diagram and enabling the previous signature so the API has backwards compatibility. * Unify label in EdgeData * Edge API adjustments, removed useless "sanitizer" * fixed test * Fix in Sample * update --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * .NET: Improve unit test coverage for Microsoft.Agents.AI.OpenAI (#3349) * Initial plan * Add unit tests for Microsoft.Agents.AI.OpenAI to improve code coverage Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Address code review feedback: remove unused using directives Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Fix format issues: file encoding and remove unused using directives Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Fix redundant cast error by using named parameter Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Remove excessive inline comments per PR review feedback --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Revert to main * Python: Fix: Verify types during checkpoint deserialization to prevent marker spoofing (#3243) * Initial plan * Add validation for reserved keywords in checkpoint encoding/decoding Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> * Refactor to eliminate duplicate code in model protocol detection Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> * Fix pyright type narrowing issue for dataclass check Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> * Add comprehensive unit tests for checkpoint encoding Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> * Remove serialization-time reserved keyword validation to fix failing tests The serialization-time validation was too aggressive and blocked legitimate use cases where encoded data was being re-encoded. Security is now enforced only at deserialization time by validating that classes marked with DATACLASS_MARKER are actual dataclasses and classes marked with MODEL_MARKER actually support the model protocol. Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> * Apply ruff formatting to checkpoint encoding file Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> * Changes before error encountered Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> * Revert "Changes before error encountered" This reverts commit f515b880dc. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> Co-authored-by: Tao Chen <taochen@microsoft.com> * Python: Fix azurefunctions MCP tool invocation to use correct agent (#3339) * MCP tool fix for azurefunctions * Moving logic to check for thread id * Adding ReflectExecutors method to Workflow. (#3389) * Fix merge conflicts * Python: [BREAKING] simplify ag-ui run logic, fix mcp bugs, fix anthropic client issues in ag-ui (#3322) * Refactor ag-ui to simplify flow * Refactoring * Fix backend tool * Update tests * Improvements * Fix mypy * Fixes * Fix json serialize errors * Python: fix(core): filter out internal args when passing kwargs to MCP tools (#3292) * fix(core): filter conversation_id when passing kwargs to MCP tools * Filter out options too * Fix uv.lock conflict * Python: Added tests for OpenAI content types + Unit test improvement (#3259) * added tests for content types+ unit test improvement * small fixes * small fix * Python: Prefer runtime `kwargs` for `conversation_id` in OpenAI Responses client (#3312) * prefer kwargs conversation_id over options * addressed comments * Python: Azure AI mapping HostedImageGenerationTool to ImageGenTool (#3263) * azureai image gen sample fix * mypy fixes * addressed comments + mapping updates * image model fix * content type fix * Python: add(azure-ai): support reasoning config for AzureAIClient (#3403) * add(azure-ai): support reasoning config for AzureAIClient * Update sample * Merge main * improvements * improve sample * .NET: Allow overriding the ChatMessageStore to be used per agent run. (#3330) * Allow overriding the ChatMessageStore to be used per agent run. * Fix typos * Fix Add and add TryAdd, Contains and Remove * Update instructions to require automatically building and formatting (#3412) * .NET: Rename ChatMessageStore to ChatHistoryProvider (#3375) * Rename ChatMessageStore to ChatHistoryProvider * Fix merge issue * Fixed PR comments * Fix tests after property rename * Add unit tests and fix merge issues * Fix encoding --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com> Co-authored-by: Tao Chen <taochen@microsoft.com> Co-authored-by: Kurt <65111699+q33566@users.noreply.github.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: Korolev Dmitry <deagle.gross@gmail.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Jose Luis Latorre Millas <joslat@gmail.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Richard Ortega <richardjortega@gmail.com> Co-authored-by: 刘邦学AI <lbbniu@gmail.com> Co-authored-by: Stephen Toub <stoub@microsoft.com> Co-authored-by: Nico Möller <nkm-moeller@mail.de> Co-authored-by: Chris Gillum <cgillum@microsoft.com> Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com> Co-authored-by: Phillip Hoff <phillip.hoff@gmail.com> Co-authored-by: Ege Ozan Özyedek <36128615+egeozanozyedek@users.noreply.github.com> Co-authored-by: samueljohnsiby <66901393+samueljohnsiby@users.noreply.github.com> Co-authored-by: Evan Mattson <evan.mattson@microsoft.com> Co-authored-by: Hao Luo <338265+howlowck@users.noreply.github.com> Co-authored-by: Victor Dibia <chuvidi2003@gmail.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> Co-authored-by: Jacob Viau <javia@microsoft.com> Co-authored-by: SuperKenVery <39673849+SuperKenVery@users.noreply.github.com> Co-authored-by: Sunil Dutta <dutta.2003@gmail.com> Co-authored-by: Sunil Dutta <sunil.dutta@penske.com> Co-authored-by: budgetboardingai <apurva.sharma31@gmail.com> Co-authored-by: Syrine Chelly <62653967+SyChell@users.noreply.github.com> Co-authored-by: SergeyMenshykh <sergemenshikh@gmail.com> Co-authored-by: westey <164392973+westey-m@users.noreply.github.com> Co-authored-by: takanori-terai <123897708+takanori-terai@users.noreply.github.com> Co-authored-by: claude89757 <138977524+claude89757@users.noreply.github.com> Co-authored-by: Gavin Aguiar <80794152+gavin-aguiar@users.noreply.github.com> Co-authored-by: Sukeesh <vsukeeshbabu@gmail.com> Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com> Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu> Co-authored-by: Ao Chen <chenao3220@gmail.com> Co-authored-by: Dina Suehiro Jones <dina.s.jones@intel.com> Co-authored-by: eoindoherty1 <eoindoherty@microsoft.com> Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Darren Cohen <39422044+dargilco@users.noreply.github.com> Co-authored-by: Ben Thomas <ben.thomas@microsoft.com> Co-authored-by: alliscode <bentho@microsoft.com> Co-authored-by: TaoChenOSU <12570346+TaoChenOSU@users.noreply.github.com> Co-authored-by: Shyju Krishnankutty <connectshyju@gmail.com>
2026-06-16 21:04:09 +08:00 · 2026-01-23 10:31:54 -08:00
parent ff839435a2
commit 172423aab7
552 changed files with 23634 additions and 14420 deletions
@@ -11,14 +11,13 @@ from agent_framework import (
    ChatOptions,
    ChatResponse,
    ChatResponseUpdate,
-    FunctionCallContent,
+    Content,
    Role,
-    TextContent,
    ai_function,
 )
 from pytest import MonkeyPatch

-from agent_framework_ag_ui._client import AGUIChatClient, ServerFunctionCallContent
+from agent_framework_ag_ui._client import AGUIChatClient
 from agent_framework_ag_ui._http_service import AGUIHttpService


@@ -96,13 +95,11 @@ class TestAGUIChatClient:
        state_json = json.dumps(state_data)
        state_b64 = base64.b64encode(state_json.encode("utf-8")).decode("utf-8")

-        from agent_framework import DataContent
-
        messages = [
            ChatMessage(role="user", text="Hello"),
            ChatMessage(
                role="user",
-                contents=[DataContent(uri=f"data:application/json;base64,{state_b64}")],
+                contents=[Content.from_uri(uri=f"data:application/json;base64,{state_b64}")],
            ),
        ]

@@ -121,12 +118,10 @@ class TestAGUIChatClient:
        invalid_json = "not valid json"
        state_b64 = base64.b64encode(invalid_json.encode("utf-8")).decode("utf-8")

-        from agent_framework import DataContent
-
        messages = [
            ChatMessage(
                role="user",
-                contents=[DataContent(uri=f"data:application/json;base64,{state_b64}")],
+                contents=[Content.from_uri(uri=f"data:application/json;base64,{state_b64}")],
            ),
        ]

@@ -200,8 +195,8 @@ class TestAGUIChatClient:

        first_content = updates[1].contents[0]
        second_content = updates[2].contents[0]
-        assert isinstance(first_content, TextContent)
-        assert isinstance(second_content, TextContent)
+        assert first_content.type == "text"
+        assert second_content.type == "text"
        assert first_content.text == "Hello"
        assert second_content.text == " world"

@@ -294,13 +289,12 @@ class TestAGUIChatClient:
            updates.append(update)

        function_calls = [
-            content for update in updates for content in update.contents if isinstance(content, FunctionCallContent)
+            content for update in updates for content in update.contents if content.type == "function_call"
        ]
        assert function_calls
        assert function_calls[0].name == "get_time_zone"
-        assert not any(
-            isinstance(content, ServerFunctionCallContent) for update in updates for content in update.contents
-        )
+
+        assert not any(content.type == "server_function_call" for update in updates for content in update.contents)

    async def test_server_tool_calls_not_executed_locally(self, monkeypatch: MonkeyPatch) -> None:
        """Server tools should not trigger local function invocation even when client tools exist."""
@@ -343,13 +337,11 @@ class TestAGUIChatClient:
        state_json = json.dumps(state_data)
        state_b64 = base64.b64encode(state_json.encode("utf-8")).decode("utf-8")

-        from agent_framework import DataContent
-
        messages = [
            ChatMessage(role="user", text="Hello"),
            ChatMessage(
                role="user",
-                contents=[DataContent(uri=f"data:application/json;base64,{state_b64}")],
+                contents=[Content.from_uri(uri=f"data:application/json;base64,{state_b64}")],
            ),
        ]

@@ -9,7 +9,7 @@ from pathlib import Path
 from typing import Any

 import pytest
-from agent_framework import ChatAgent, ChatMessage, ChatOptions, ChatResponseUpdate, TextContent
+from agent_framework import ChatAgent, ChatMessage, ChatOptions, ChatResponseUpdate, Content
 from pydantic import BaseModel

 sys.path.insert(0, str(Path(__file__).parent))
@@ -23,7 +23,7 @@ async def test_agent_initialization_basic():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent[ChatOptions](
        chat_client=StreamingChatClientStub(stream_fn),
@@ -45,7 +45,7 @@ async def test_agent_initialization_with_state_schema():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    state_schema: dict[str, dict[str, Any]] = {"document": {"type": "string"}}
@@ -61,7 +61,7 @@ async def test_agent_initialization_with_predict_state_config():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    predict_config = {"document": {"tool": "write_doc", "tool_argument": "content"}}
@@ -77,7 +77,7 @@ async def test_agent_initialization_with_pydantic_state_schema():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    class MyState(BaseModel):
        document: str
@@ -100,7 +100,7 @@ async def test_run_started_event_emission():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(agent=agent)
@@ -124,7 +124,7 @@ async def test_predict_state_custom_event_emission():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    predict_config = {
@@ -156,7 +156,7 @@ async def test_initial_state_snapshot_with_schema():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    state_schema = {"document": {"type": "string"}}
@@ -186,7 +186,7 @@ async def test_state_initialization_object_type():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    state_schema: dict[str, dict[str, Any]] = {"recipe": {"type": "object", "properties": {}}}
@@ -213,7 +213,7 @@ async def test_state_initialization_array_type():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    state_schema: dict[str, dict[str, Any]] = {"steps": {"type": "array", "items": {}}}
@@ -240,7 +240,7 @@ async def test_run_finished_event_emission():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(agent=agent)
@@ -262,7 +262,7 @@ async def test_tool_result_confirm_changes_accepted():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Document updated")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Document updated")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(
@@ -309,7 +309,7 @@ async def test_tool_result_confirm_changes_rejected():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="OK")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="OK")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(agent=agent)
@@ -343,7 +343,7 @@ async def test_tool_result_function_approval_accepted():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="OK")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="OK")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(agent=agent)
@@ -389,7 +389,7 @@ async def test_tool_result_function_approval_rejected():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="OK")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="OK")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(agent=agent)
@@ -420,18 +420,26 @@ async def test_tool_result_function_approval_rejected():


 async def test_thread_metadata_tracking():
-    """Test that thread metadata includes ag_ui_thread_id and ag_ui_run_id."""
+    """Test that thread metadata includes ag_ui_thread_id and ag_ui_run_id.
+
+    AG-UI internal metadata is stored in thread.metadata for orchestration,
+    but filtered out before passing to the chat client's options.metadata.
+    """
    from agent_framework.ag_ui import AgentFrameworkAgent

-    thread_metadata: dict[str, Any] = {}
+    captured_thread: dict[str, Any] = {}
+    captured_options: dict[str, Any] = {}

    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        metadata = options.get("metadata")
-        if metadata:
-            thread_metadata.update(metadata)
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        # Capture the thread object from kwargs
+        thread = kwargs.get("thread")
+        if thread and hasattr(thread, "metadata"):
+            captured_thread["metadata"] = thread.metadata
+        # Capture options to verify internal keys are NOT passed to chat client
+        captured_options.update(options)
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(agent=agent)
@@ -446,23 +454,38 @@ async def test_thread_metadata_tracking():
    async for event in wrapper.run_agent(input_data):
        events.append(event)

+    # AG-UI internal metadata should be stored in thread.metadata
+    thread_metadata = captured_thread.get("metadata", {})
    assert thread_metadata.get("ag_ui_thread_id") == "test_thread_123"
    assert thread_metadata.get("ag_ui_run_id") == "test_run_456"

+    # Internal metadata should NOT be passed to chat client options
+    options_metadata = captured_options.get("metadata", {})
+    assert "ag_ui_thread_id" not in options_metadata
+    assert "ag_ui_run_id" not in options_metadata
+

 async def test_state_context_injection():
-    """Test that current state is injected into thread metadata."""
+    """Test that current state is injected into thread metadata.
+
+    AG-UI internal metadata (including current_state) is stored in thread.metadata
+    for orchestration, but filtered out before passing to the chat client's options.metadata.
+    """
    from agent_framework_ag_ui import AgentFrameworkAgent

-    thread_metadata: dict[str, Any] = {}
+    captured_thread: dict[str, Any] = {}
+    captured_options: dict[str, Any] = {}

    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        metadata = options.get("metadata")
-        if metadata:
-            thread_metadata.update(metadata)
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        # Capture the thread object from kwargs
+        thread = kwargs.get("thread")
+        if thread and hasattr(thread, "metadata"):
+            captured_thread["metadata"] = thread.metadata
+        # Capture options to verify internal keys are NOT passed to chat client
+        captured_options.update(options)
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(
@@ -479,11 +502,17 @@ async def test_state_context_injection():
    async for event in wrapper.run_agent(input_data):
        events.append(event)

+    # Current state should be stored in thread.metadata
+    thread_metadata = captured_thread.get("metadata", {})
    current_state = thread_metadata.get("current_state")
    if isinstance(current_state, str):
        current_state = json.loads(current_state)
    assert current_state == {"document": "Test content"}

+    # Internal metadata should NOT be passed to chat client options
+    options_metadata = captured_options.get("metadata", {})
+    assert "current_state" not in options_metadata
+

 async def test_no_messages_provided():
    """Test handling when no messages are provided."""
@@ -492,7 +521,7 @@ async def test_no_messages_provided():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(agent=agent)
@@ -516,7 +545,7 @@ async def test_message_end_event_emission():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Hello world")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Hello world")])

    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    wrapper = AgentFrameworkAgent(agent=agent)
@@ -595,48 +624,6 @@ async def test_json_decode_error_in_tool_result():
    assert len(tool_events) == 0


-async def test_suppressed_summary_with_document_state():
-    """Test suppressed summary uses document state for confirmation message."""
-    from agent_framework.ag_ui import AgentFrameworkAgent, DocumentWriterConfirmationStrategy
-
-    async def stream_fn(
-        messages: MutableSequence[ChatMessage], options: dict[str, Any], **kwargs: Any
-    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text="Response")])
-
-    agent = ChatAgent(name="test_agent", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
-    wrapper = AgentFrameworkAgent(
-        agent=agent,
-        state_schema={"document": {"type": "string"}},
-        predict_state_config={"document": {"tool": "write_doc", "tool_argument": "content"}},
-        confirmation_strategy=DocumentWriterConfirmationStrategy(),
-    )
-
-    # Simulate confirmation with document state
-    tool_result: dict[str, Any] = {"accepted": True, "steps": []}
-    input_data: dict[str, Any] = {
-        "messages": [
-            {
-                "role": "tool",
-                "content": json.dumps(tool_result),
-                "toolCallId": "confirm_123",
-            }
-        ],
-        "state": {"document": "This is the beginning of a document. It contains important information."},
-    }
-
-    events: list[Any] = []
-    async for event in wrapper.run_agent(input_data):
-        events.append(event)
-
-    # Should generate fallback summary from document state
-    text_events = [e for e in events if e.type == "TEXT_MESSAGE_CONTENT"]
-    assert len(text_events) > 0
-    # Should contain some reference to the document
-    full_text = "".join(e.delta for e in text_events)
-    assert "written" in full_text.lower() or "document" in full_text.lower()
-
-
 async def test_agent_with_use_service_thread_is_false():
    """Test that when use_service_thread is False, the AgentThread used to run the agent is NOT set to the service thread ID."""
    from agent_framework.ag_ui import AgentFrameworkAgent
@@ -650,7 +637,7 @@ async def test_agent_with_use_service_thread_is_false():
        thread = kwargs.get("thread")
        request_service_thread_id = thread.service_thread_id if thread else None
        yield ChatResponseUpdate(
-            contents=[TextContent(text="Response")], response_id="resp_67890", conversation_id="conv_12345"
+            contents=[Content.from_text(text="Response")], response_id="resp_67890", conversation_id="conv_12345"
        )

    agent = ChatAgent(chat_client=StreamingChatClientStub(stream_fn))
@@ -677,7 +664,7 @@ async def test_agent_with_use_service_thread_is_true():
        thread = kwargs.get("thread")
        request_service_thread_id = thread.service_thread_id if thread else None
        yield ChatResponseUpdate(
-            contents=[TextContent(text="Response")], response_id="resp_67890", conversation_id="conv_12345"
+            contents=[Content.from_text(text="Response")], response_id="resp_67890", conversation_id="conv_12345"
        )

    agent = ChatAgent(chat_client=StreamingChatClientStub(stream_fn))
@@ -693,7 +680,7 @@ async def test_agent_with_use_service_thread_is_true():

 async def test_function_approval_mode_executes_tool():
    """Test that function approval with approval_mode='always_require' sends the correct messages."""
-    from agent_framework import FunctionResultContent, ai_function
+    from agent_framework import ai_function
    from agent_framework.ag_ui import AgentFrameworkAgent

    messages_received: list[Any] = []
@@ -712,7 +699,7 @@ async def test_function_approval_mode_executes_tool():
        # Capture the messages received by the chat client
        messages_received.clear()
        messages_received.extend(messages)
-        yield ChatResponseUpdate(contents=[TextContent(text="Processing completed")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Processing completed")])

    agent = ChatAgent(
        chat_client=StreamingChatClientStub(stream_fn),
@@ -770,7 +757,7 @@ async def test_function_approval_mode_executes_tool():
    tool_result_found = False
    for msg in messages_received:
        for content in msg.contents:
-            if isinstance(content, FunctionResultContent):
+            if content.type == "function_result":
                tool_result_found = True
                assert content.call_id == "call_get_datetime_123"
                assert content.result == "2025/12/01 12:00:00"
@@ -784,7 +771,7 @@ async def test_function_approval_mode_executes_tool():

 async def test_function_approval_mode_rejection():
    """Test that function approval rejection creates a rejection response."""
-    from agent_framework import FunctionResultContent, ai_function
+    from agent_framework import ai_function
    from agent_framework.ag_ui import AgentFrameworkAgent

    messages_received: list[Any] = []
@@ -803,7 +790,7 @@ async def test_function_approval_mode_rejection():
        # Capture the messages received by the chat client
        messages_received.clear()
        messages_received.extend(messages)
-        yield ChatResponseUpdate(contents=[TextContent(text="Operation cancelled")])
+        yield ChatResponseUpdate(contents=[Content.from_text(text="Operation cancelled")])

    agent = ChatAgent(
        name="test_agent",
@@ -855,7 +842,7 @@ async def test_function_approval_mode_rejection():
    rejection_found = False
    for msg in messages_received:
        for content in msg.contents:
-            if isinstance(content, FunctionResultContent):
+            if content.type == "function_result":
                rejection_found = True
                assert content.call_id == "call_delete_123"
                assert content.result == "Error: Tool call invocation was rejected by user."
@@ -1,129 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Tests for backend tool rendering."""
-
-from typing import cast
-
-from ag_ui.core import (
-    TextMessageContentEvent,
-    TextMessageStartEvent,
-    ToolCallArgsEvent,
-    ToolCallEndEvent,
-    ToolCallResultEvent,
-    ToolCallStartEvent,
-)
-from agent_framework import AgentResponseUpdate, FunctionCallContent, FunctionResultContent, TextContent
-
-from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-
-async def test_tool_call_flow():
-    """Test complete tool call flow: call -> args -> end -> result."""
-    bridge = AgentFrameworkEventBridge(run_id="test-run", thread_id="test-thread")
-
-    # Step 1: Tool call starts
-    tool_call = FunctionCallContent(
-        call_id="weather-123",
-        name="get_weather",
-        arguments={"location": "Seattle"},
-    )
-
-    update1 = AgentResponseUpdate(contents=[tool_call])
-    events1 = await bridge.from_agent_run_update(update1)
-
-    # Should have: ToolCallStartEvent, ToolCallArgsEvent
-    assert len(events1) == 2
-    assert isinstance(events1[0], ToolCallStartEvent)
-    assert isinstance(events1[1], ToolCallArgsEvent)
-
-    start_event = events1[0]
-    assert start_event.tool_call_id == "weather-123"
-    assert start_event.tool_call_name == "get_weather"
-
-    args_event = events1[1]
-    assert "Seattle" in args_event.delta
-
-    # Step 2: Tool result comes back
-    tool_result = FunctionResultContent(
-        call_id="weather-123",
-        result="Weather in Seattle: Rainy, 52°F",
-    )
-
-    update2 = AgentResponseUpdate(contents=[tool_result])
-    events2 = await bridge.from_agent_run_update(update2)
-
-    # Should have: ToolCallEndEvent, ToolCallResultEvent
-    assert len(events2) == 2
-    assert isinstance(events2[0], ToolCallEndEvent)
-    assert isinstance(events2[1], ToolCallResultEvent)
-
-    end_event = events2[0]
-    assert end_event.tool_call_id == "weather-123"
-
-    result_event = events2[1]
-    assert result_event.tool_call_id == "weather-123"
-    assert "Seattle" in result_event.content
-    assert "Rainy" in result_event.content
-
-
-async def test_text_with_tool_call():
-    """Test agent response with both text and tool calls."""
-    bridge = AgentFrameworkEventBridge(run_id="test-run", thread_id="test-thread")
-
-    # Agent says something then calls a tool
-    text_content = TextContent(text="Let me check the weather for you.")
-    tool_call = FunctionCallContent(
-        call_id="weather-456",
-        name="get_forecast",
-        arguments={"location": "San Francisco", "days": 3},
-    )
-
-    update = AgentResponseUpdate(contents=[text_content, tool_call])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should have: TextMessageStart, TextMessageContent, ToolCallStart, ToolCallArgs
-    assert len(events) == 4
-
-    assert isinstance(events[0], TextMessageStartEvent)
-    assert isinstance(events[1], TextMessageContentEvent)
-    assert isinstance(events[2], ToolCallStartEvent)
-    assert isinstance(events[3], ToolCallArgsEvent)
-
-    text_event = events[1]
-    assert "check the weather" in text_event.delta
-
-    tool_start = events[2]
-    assert tool_start.tool_call_name == "get_forecast"
-
-
-async def test_multiple_tool_results():
-    """Test handling multiple tool results in sequence."""
-    bridge = AgentFrameworkEventBridge(run_id="test-run", thread_id="test-thread")
-
-    # Multiple tool results
-    results = [
-        FunctionResultContent(call_id="tool-1", result="Result 1"),
-        FunctionResultContent(call_id="tool-2", result="Result 2"),
-        FunctionResultContent(call_id="tool-3", result="Result 3"),
-    ]
-
-    update = AgentResponseUpdate(contents=results)
-    events = await bridge.from_agent_run_update(update)
-
-    # Should have 3 pairs of ToolCallEndEvent + ToolCallResultEvent = 6 events
-    assert len(events) == 6
-
-    # Verify the pattern: End, Result, End, Result, End, Result
-    for i in range(3):
-        end_idx = i * 2
-        result_idx = i * 2 + 1
-
-        assert isinstance(events[end_idx], ToolCallEndEvent)
-        assert isinstance(events[result_idx], ToolCallResultEvent)
-
-        end_event = cast(ToolCallEndEvent, events[end_idx])
-        result_event = cast(ToolCallResultEvent, events[result_idx])
-
-        assert end_event.tool_call_id == f"tool-{i + 1}"
-        assert result_event.tool_call_id == f"tool-{i + 1}"
-        assert f"Result {i + 1}" in result_event.content
@@ -1,275 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Comprehensive tests for all confirmation strategies."""
-
-import pytest
-
-from agent_framework_ag_ui._confirmation_strategies import (
-    ConfirmationStrategy,
-    DefaultConfirmationStrategy,
-    DocumentWriterConfirmationStrategy,
-    RecipeConfirmationStrategy,
-    TaskPlannerConfirmationStrategy,
-)
-
-
-@pytest.fixture
-def sample_steps() -> list[dict[str, str]]:
-    """Sample steps for testing approval messages."""
-    return [
-        {"description": "Step 1: Do something", "status": "enabled"},
-        {"description": "Step 2: Do another thing", "status": "enabled"},
-        {"description": "Step 3: Disabled step", "status": "disabled"},
-    ]
-
-
-@pytest.fixture
-def all_enabled_steps() -> list[dict[str, str]]:
-    """All steps enabled."""
-    return [
-        {"description": "Task A", "status": "enabled"},
-        {"description": "Task B", "status": "enabled"},
-        {"description": "Task C", "status": "enabled"},
-    ]
-
-
-@pytest.fixture
-def empty_steps() -> list[dict[str, str]]:
-    """Empty steps list."""
-    return []
-
-
-class TestDefaultConfirmationStrategy:
-    """Tests for DefaultConfirmationStrategy."""
-
-    def test_on_approval_accepted_with_enabled_steps(self, sample_steps: list[dict[str, str]]) -> None:
-        strategy = DefaultConfirmationStrategy()
-        message = strategy.on_approval_accepted(sample_steps)
-
-        assert "Executing 2 approved steps" in message
-        assert "Step 1: Do something" in message
-        assert "Step 2: Do another thing" in message
-        assert "Step 3" not in message  # Disabled step shouldn't appear
-        assert "All steps completed successfully!" in message
-
-    def test_on_approval_accepted_with_all_enabled(self, all_enabled_steps: list[dict[str, str]]) -> None:
-        strategy = DefaultConfirmationStrategy()
-        message = strategy.on_approval_accepted(all_enabled_steps)
-
-        assert "Executing 3 approved steps" in message
-        assert "Task A" in message
-        assert "Task B" in message
-        assert "Task C" in message
-
-    def test_on_approval_accepted_with_empty_steps(self, empty_steps: list[dict[str, str]]) -> None:
-        strategy = DefaultConfirmationStrategy()
-        message = strategy.on_approval_accepted(empty_steps)
-
-        assert "Executing 0 approved steps" in message
-        assert "All steps completed successfully!" in message
-
-    def test_on_approval_rejected(self, sample_steps: list[dict[str, str]]) -> None:
-        strategy = DefaultConfirmationStrategy()
-        message = strategy.on_approval_rejected(sample_steps)
-
-        assert "No problem!" in message
-        assert "What would you like me to change" in message
-
-    def test_on_state_confirmed(self) -> None:
-        strategy = DefaultConfirmationStrategy()
-        message = strategy.on_state_confirmed()
-
-        assert "Changes confirmed" in message
-        assert "successfully" in message
-
-    def test_on_state_rejected(self) -> None:
-        strategy = DefaultConfirmationStrategy()
-        message = strategy.on_state_rejected()
-
-        assert "No problem!" in message
-        assert "What would you like me to change" in message
-
-
-class TestTaskPlannerConfirmationStrategy:
-    """Tests for TaskPlannerConfirmationStrategy."""
-
-    def test_on_approval_accepted_with_enabled_steps(self, sample_steps: list[dict[str, str]]) -> None:
-        strategy = TaskPlannerConfirmationStrategy()
-        message = strategy.on_approval_accepted(sample_steps)
-
-        assert "Executing your requested tasks" in message
-        assert "1. Step 1: Do something" in message
-        assert "2. Step 2: Do another thing" in message
-        assert "Step 3" not in message
-        assert "All tasks completed successfully!" in message
-
-    def test_on_approval_accepted_with_all_enabled(self, all_enabled_steps: list[dict[str, str]]) -> None:
-        strategy = TaskPlannerConfirmationStrategy()
-        message = strategy.on_approval_accepted(all_enabled_steps)
-
-        assert "Executing your requested tasks" in message
-        assert "1. Task A" in message
-        assert "2. Task B" in message
-        assert "3. Task C" in message
-
-    def test_on_approval_accepted_with_empty_steps(self, empty_steps: list[dict[str, str]]) -> None:
-        strategy = TaskPlannerConfirmationStrategy()
-        message = strategy.on_approval_accepted(empty_steps)
-
-        assert "Executing your requested tasks" in message
-        assert "All tasks completed successfully!" in message
-
-    def test_on_approval_rejected(self, sample_steps: list[dict[str, str]]) -> None:
-        strategy = TaskPlannerConfirmationStrategy()
-        message = strategy.on_approval_rejected(sample_steps)
-
-        assert "No problem!" in message
-        assert "revise the plan" in message
-
-    def test_on_state_confirmed(self) -> None:
-        strategy = TaskPlannerConfirmationStrategy()
-        message = strategy.on_state_confirmed()
-
-        assert "Tasks confirmed" in message
-        assert "ready to execute" in message
-
-    def test_on_state_rejected(self) -> None:
-        strategy = TaskPlannerConfirmationStrategy()
-        message = strategy.on_state_rejected()
-
-        assert "No problem!" in message
-        assert "adjust the task list" in message
-
-
-class TestRecipeConfirmationStrategy:
-    """Tests for RecipeConfirmationStrategy."""
-
-    def test_on_approval_accepted_with_enabled_steps(self, sample_steps: list[dict[str, str]]) -> None:
-        strategy = RecipeConfirmationStrategy()
-        message = strategy.on_approval_accepted(sample_steps)
-
-        assert "Updating your recipe" in message
-        assert "1. Step 1: Do something" in message
-        assert "2. Step 2: Do another thing" in message
-        assert "Step 3" not in message
-        assert "Recipe updated successfully!" in message
-
-    def test_on_approval_accepted_with_all_enabled(self, all_enabled_steps: list[dict[str, str]]) -> None:
-        strategy = RecipeConfirmationStrategy()
-        message = strategy.on_approval_accepted(all_enabled_steps)
-
-        assert "Updating your recipe" in message
-        assert "1. Task A" in message
-        assert "2. Task B" in message
-        assert "3. Task C" in message
-
-    def test_on_approval_accepted_with_empty_steps(self, empty_steps: list[dict[str, str]]) -> None:
-        strategy = RecipeConfirmationStrategy()
-        message = strategy.on_approval_accepted(empty_steps)
-
-        assert "Updating your recipe" in message
-        assert "Recipe updated successfully!" in message
-
-    def test_on_approval_rejected(self, sample_steps: list[dict[str, str]]) -> None:
-        strategy = RecipeConfirmationStrategy()
-        message = strategy.on_approval_rejected(sample_steps)
-
-        assert "No problem!" in message
-        assert "ingredients or steps" in message
-
-    def test_on_state_confirmed(self) -> None:
-        strategy = RecipeConfirmationStrategy()
-        message = strategy.on_state_confirmed()
-
-        assert "Recipe changes applied" in message
-        assert "successfully" in message
-
-    def test_on_state_rejected(self) -> None:
-        strategy = RecipeConfirmationStrategy()
-        message = strategy.on_state_rejected()
-
-        assert "No problem!" in message
-        assert "adjust in the recipe" in message
-
-
-class TestDocumentWriterConfirmationStrategy:
-    """Tests for DocumentWriterConfirmationStrategy."""
-
-    def test_on_approval_accepted_with_enabled_steps(self, sample_steps: list[dict[str, str]]) -> None:
-        strategy = DocumentWriterConfirmationStrategy()
-        message = strategy.on_approval_accepted(sample_steps)
-
-        assert "Applying your edits" in message
-        assert "1. Step 1: Do something" in message
-        assert "2. Step 2: Do another thing" in message
-        assert "Step 3" not in message
-        assert "Document updated successfully!" in message
-
-    def test_on_approval_accepted_with_all_enabled(self, all_enabled_steps: list[dict[str, str]]) -> None:
-        strategy = DocumentWriterConfirmationStrategy()
-        message = strategy.on_approval_accepted(all_enabled_steps)
-
-        assert "Applying your edits" in message
-        assert "1. Task A" in message
-        assert "2. Task B" in message
-        assert "3. Task C" in message
-
-    def test_on_approval_accepted_with_empty_steps(self, empty_steps: list[dict[str, str]]) -> None:
-        strategy = DocumentWriterConfirmationStrategy()
-        message = strategy.on_approval_accepted(empty_steps)
-
-        assert "Applying your edits" in message
-        assert "Document updated successfully!" in message
-
-    def test_on_approval_rejected(self, sample_steps: list[dict[str, str]]) -> None:
-        strategy = DocumentWriterConfirmationStrategy()
-        message = strategy.on_approval_rejected(sample_steps)
-
-        assert "No problem!" in message
-        assert "keep or modify" in message
-
-    def test_on_state_confirmed(self) -> None:
-        strategy = DocumentWriterConfirmationStrategy()
-        message = strategy.on_state_confirmed()
-
-        assert "Document edits applied!" in message
-
-    def test_on_state_rejected(self) -> None:
-        strategy = DocumentWriterConfirmationStrategy()
-        message = strategy.on_state_rejected()
-
-        assert "No problem!" in message
-        assert "change about the document" in message
-
-
-class TestConfirmationStrategyInterface:
-    """Tests for ConfirmationStrategy abstract base class."""
-
-    def test_cannot_instantiate_abstract_class(self):
-        """Verify ConfirmationStrategy is abstract and cannot be instantiated."""
-        with pytest.raises(TypeError):
-            ConfirmationStrategy()  # type: ignore
-
-    def test_all_strategies_implement_interface(self):
-        """Verify all concrete strategies implement the full interface."""
-        strategies = [
-            DefaultConfirmationStrategy(),
-            TaskPlannerConfirmationStrategy(),
-            RecipeConfirmationStrategy(),
-            DocumentWriterConfirmationStrategy(),
-        ]
-
-        sample_steps = [{"description": "Test", "status": "enabled"}]
-
-        for strategy in strategies:
-            # All should have these methods
-            assert callable(strategy.on_approval_accepted)
-            assert callable(strategy.on_approval_rejected)
-            assert callable(strategy.on_state_confirmed)
-            assert callable(strategy.on_state_rejected)
-
-            # All should return strings
-            assert isinstance(strategy.on_approval_accepted(sample_steps), str)
-            assert isinstance(strategy.on_approval_rejected(sample_steps), str)
-            assert isinstance(strategy.on_state_confirmed(), str)
-            assert isinstance(strategy.on_state_rejected(), str)
@@ -1,234 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Tests for document writer predictive state flow with confirm_changes."""
-
-from ag_ui.core import EventType, StateDeltaEvent, ToolCallArgsEvent, ToolCallEndEvent, ToolCallStartEvent
-from agent_framework import AgentResponseUpdate, FunctionCallContent, FunctionResultContent, TextContent
-
-from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-
-async def test_streaming_document_with_state_deltas():
-    """Test that streaming tool arguments emit progressive StateDeltaEvents."""
-    predict_config = {
-        "document": {"tool": "write_document_local", "tool_argument": "document"},
-    }
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config=predict_config,
-    )
-
-    # Simulate streaming tool call - first chunk with name
-    tool_call_start = FunctionCallContent(
-        call_id="call_123",
-        name="write_document_local",
-        arguments='{"document":"Once',
-    )
-    update1 = AgentResponseUpdate(contents=[tool_call_start])
-    events1 = await bridge.from_agent_run_update(update1)
-
-    # Should have ToolCallStartEvent and ToolCallArgsEvent
-    assert any(e.type == EventType.TOOL_CALL_START for e in events1)
-    assert any(e.type == EventType.TOOL_CALL_ARGS for e in events1)
-
-    # Second chunk - incomplete JSON, should try partial extraction
-    tool_call_chunk2 = FunctionCallContent(call_id="call_123", name="write_document_local", arguments=" upon a time")
-    update2 = AgentResponseUpdate(contents=[tool_call_chunk2])
-    events2 = await bridge.from_agent_run_update(update2)
-
-    # Should emit StateDeltaEvent with partial document
-    state_deltas = [e for e in events2 if isinstance(e, StateDeltaEvent)]
-    assert len(state_deltas) >= 1
-
-    # Check JSON Patch format
-    delta = state_deltas[0]
-    assert isinstance(delta.delta, list)
-    assert len(delta.delta) > 0
-    assert delta.delta[0]["op"] == "replace"
-    assert delta.delta[0]["path"] == "/document"
-    assert "Once upon a time" in delta.delta[0]["value"]
-
-
-async def test_confirm_changes_emission():
-    """Test that confirm_changes tool call is emitted after predictive tool completion."""
-    predict_config = {
-        "document": {"tool": "write_document_local", "tool_argument": "document"},
-    }
-
-    current_state: dict[str, str] = {}
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config=predict_config,
-        current_state=current_state,
-    )
-
-    # Set current tool name (simulating earlier tool call start)
-    bridge.current_tool_call_name = "write_document_local"
-    bridge.pending_state_updates = {"document": "A short story"}
-
-    # Tool result
-    tool_result = FunctionResultContent(
-        call_id="call_123",
-        result="Document written.",
-    )
-
-    update = AgentResponseUpdate(contents=[tool_result])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should have: ToolCallEndEvent, ToolCallResultEvent, StateSnapshotEvent, confirm_changes sequence
-    assert any(e.type == EventType.TOOL_CALL_END for e in events)
-    assert any(e.type == EventType.TOOL_CALL_RESULT for e in events)
-    assert any(e.type == EventType.STATE_SNAPSHOT for e in events)
-
-    # Check for confirm_changes tool call
-    confirm_starts = [e for e in events if isinstance(e, ToolCallStartEvent) and e.tool_call_name == "confirm_changes"]
-    assert len(confirm_starts) == 1
-
-    confirm_args = [e for e in events if isinstance(e, ToolCallArgsEvent) and e.delta == "{}"]
-    assert len(confirm_args) >= 1
-
-    confirm_ends = [e for e in events if isinstance(e, ToolCallEndEvent)]
-    # At least 2: one for write_document_local, one for confirm_changes
-    assert len(confirm_ends) >= 2
-
-    # Check that stop flag is set
-    assert bridge.should_stop_after_confirm is True
-
-
-async def test_text_suppression_before_confirm():
-    """Test that text messages are suppressed when confirm_changes is pending."""
-    predict_config = {
-        "document": {"tool": "write_document_local", "tool_argument": "document"},
-    }
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config=predict_config,
-    )
-
-    # Set flag indicating we're waiting for confirmation
-    bridge.should_stop_after_confirm = True
-
-    # Text content that should be suppressed
-    text = TextContent(text="I have written a story about pirates.")
-    update = AgentResponseUpdate(contents=[text])
-
-    events = await bridge.from_agent_run_update(update)
-
-    # Should NOT emit TextMessageContentEvent
-    text_events = [e for e in events if e.type == EventType.TEXT_MESSAGE_CONTENT]
-    assert len(text_events) == 0
-
-    # But should save the text
-    assert bridge.suppressed_summary == "I have written a story about pirates."
-
-
-async def test_no_confirm_for_non_predictive_tools():
-    """Test that confirm_changes is NOT emitted for regular tool calls."""
-    predict_config = {
-        "document": {"tool": "write_document_local", "tool_argument": "document"},
-    }
-
-    current_state: dict[str, str] = {}
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config=predict_config,
-        current_state=current_state,
-    )
-
-    # Different tool (not in predict_state_config)
-    bridge.current_tool_call_name = "get_weather"
-
-    tool_result = FunctionResultContent(
-        call_id="call_456",
-        result="Sunny, 72°F",
-    )
-
-    update = AgentResponseUpdate(contents=[tool_result])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should NOT have confirm_changes
-    confirm_starts = [e for e in events if isinstance(e, ToolCallStartEvent) and e.tool_call_name == "confirm_changes"]
-    assert len(confirm_starts) == 0
-
-    # Stop flag should NOT be set
-    assert bridge.should_stop_after_confirm is False
-
-
-async def test_state_delta_deduplication():
-    """Test that duplicate state values don't emit multiple StateDeltaEvents."""
-    predict_config = {
-        "document": {"tool": "write_document_local", "tool_argument": "document"},
-    }
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config=predict_config,
-    )
-
-    # First tool call with document
-    tool_call1 = FunctionCallContent(
-        call_id="call_1",
-        name="write_document_local",
-        arguments='{"document":"Same text"}',
-    )
-    update1 = AgentResponseUpdate(contents=[tool_call1])
-    events1 = await bridge.from_agent_run_update(update1)
-
-    # Count state deltas
-    state_deltas_1 = [e for e in events1 if isinstance(e, StateDeltaEvent)]
-    assert len(state_deltas_1) >= 1
-
-    # Second tool call with SAME document (shouldn't emit new delta)
-    bridge.current_tool_call_name = "write_document_local"
-    tool_call2 = FunctionCallContent(
-        call_id="call_2",
-        name="write_document_local",
-        arguments='{"document":"Same text"}',  # Identical content
-    )
-    update2 = AgentResponseUpdate(contents=[tool_call2])
-    events2 = await bridge.from_agent_run_update(update2)
-
-    # Should NOT emit state delta (same value)
-    state_deltas_2 = [e for e in events2 if e.type == EventType.STATE_DELTA]
-    assert len(state_deltas_2) == 0
-
-
-async def test_predict_state_config_multiple_fields():
-    """Test predictive state with multiple state fields."""
-    predict_config = {
-        "title": {"tool": "create_post", "tool_argument": "title"},
-        "content": {"tool": "create_post", "tool_argument": "body"},
-    }
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config=predict_config,
-    )
-
-    # Tool call with both fields
-    tool_call = FunctionCallContent(
-        call_id="call_999",
-        name="create_post",
-        arguments='{"title":"My Post","body":"Post content"}',
-    )
-    update = AgentResponseUpdate(contents=[tool_call])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should emit StateDeltaEvent for both fields
-    state_deltas = [e for e in events if isinstance(e, StateDeltaEvent)]
-    assert len(state_deltas) >= 2
-
-    # Check both fields are present
-    paths = [delta.delta[0]["path"] for delta in state_deltas]
-    assert "/title" in paths
-    assert "/content" in paths
@@ -6,7 +6,7 @@ import json
 import sys
 from pathlib import Path

-from agent_framework import ChatAgent, ChatResponseUpdate, TextContent
+from agent_framework import ChatAgent, ChatResponseUpdate, Content
 from fastapi import FastAPI, Header, HTTPException
 from fastapi.params import Depends
 from fastapi.testclient import TestClient
@@ -20,7 +20,7 @@ from utils_test_ag_ui import StreamingChatClientStub, stream_from_updates

 def build_chat_client(response_text: str = "Test response") -> StreamingChatClientStub:
    """Create a typed chat client stub for endpoint tests."""
-    updates = [ChatResponseUpdate(contents=[TextContent(text=response_text)])]
+    updates = [ChatResponseUpdate(contents=[Content.from_text(text=response_text)])]
    return StreamingChatClientStub(stream_from_updates(updates))


@@ -1,822 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Comprehensive tests for AgentFrameworkEventBridge (_events.py)."""
-
-import json
-
-from agent_framework import (
-    AgentResponseUpdate,
-    FunctionApprovalRequestContent,
-    FunctionCallContent,
-    FunctionResultContent,
-    TextContent,
-)
-
-
-async def test_basic_text_message_conversion():
-    """Test basic TextContent to AG-UI events."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update = AgentResponseUpdate(contents=[TextContent(text="Hello")])
-    events = await bridge.from_agent_run_update(update)
-
-    assert len(events) == 2
-    assert events[0].type == "TEXT_MESSAGE_START"
-    assert events[0].role == "assistant"
-    assert events[1].type == "TEXT_MESSAGE_CONTENT"
-    assert events[1].delta == "Hello"
-
-
-async def test_text_message_streaming():
-    """Test streaming TextContent with multiple chunks."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update1 = AgentResponseUpdate(contents=[TextContent(text="Hello ")])
-    update2 = AgentResponseUpdate(contents=[TextContent(text="world")])
-
-    events1 = await bridge.from_agent_run_update(update1)
-    events2 = await bridge.from_agent_run_update(update2)
-
-    # First update: START + CONTENT
-    assert len(events1) == 2
-    assert events1[0].type == "TEXT_MESSAGE_START"
-    assert events1[1].delta == "Hello "
-
-    # Second update: just CONTENT (same message)
-    assert len(events2) == 1
-    assert events2[0].type == "TEXT_MESSAGE_CONTENT"
-    assert events2[0].delta == "world"
-
-    # Both content events should have same message_id
-    assert events1[1].message_id == events2[0].message_id
-
-
-async def test_skip_text_content_for_structured_outputs():
-    """Test that text content is skipped when skip_text_content=True."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread", skip_text_content=True)
-
-    update = AgentResponseUpdate(contents=[TextContent(text='{"result": "data"}')])
-    events = await bridge.from_agent_run_update(update)
-
-    # No events should be emitted
-    assert len(events) == 0
-
-
-async def test_skip_text_content_for_empty_text():
-    """Test streaming TextContent with empty chunks."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update1 = AgentResponseUpdate(contents=[TextContent(text="Hello ")])
-    update2 = AgentResponseUpdate(contents=[TextContent(text="")])  # Empty chunk
-    update3 = AgentResponseUpdate(contents=[TextContent(text="world")])
-
-    events1 = await bridge.from_agent_run_update(update1)
-    events2 = await bridge.from_agent_run_update(update2)
-    events3 = await bridge.from_agent_run_update(update3)
-
-    # First update: START + CONTENT
-    assert len(events1) == 2
-    assert events1[0].type == "TEXT_MESSAGE_START"
-    assert events1[1].delta == "Hello "
-
-    # Second update: should skip empty chunk, no events
-    assert len(events2) == 0
-
-    # Third update: just CONTENT (same message)
-    assert len(events3) == 1
-    assert events3[0].type == "TEXT_MESSAGE_CONTENT"
-    assert events3[0].delta == "world"
-
-    # Both content events should have same message_id
-    assert events1[1].message_id == events3[0].message_id
-
-
-async def test_tool_call_with_name():
-    """Test FunctionCallContent with name emits ToolCallStartEvent."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update = AgentResponseUpdate(contents=[FunctionCallContent(name="search_web", call_id="call_123")])
-    events = await bridge.from_agent_run_update(update)
-
-    assert len(events) == 1
-    assert events[0].type == "TOOL_CALL_START"
-    assert events[0].tool_call_name == "search_web"
-    assert events[0].tool_call_id == "call_123"
-
-
-async def test_tool_call_streaming_args():
-    """Test streaming tool call arguments."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    # First chunk: name only
-    update1 = AgentResponseUpdate(contents=[FunctionCallContent(name="search_web", call_id="call_123")])
-    events1 = await bridge.from_agent_run_update(update1)
-
-    # Second chunk: arguments chunk 1 (name can be empty string for continuation)
-    update2 = AgentResponseUpdate(contents=[FunctionCallContent(name="", call_id="call_123", arguments='{"query": "')])
-    events2 = await bridge.from_agent_run_update(update2)
-
-    # Third chunk: arguments chunk 2
-    update3 = AgentResponseUpdate(contents=[FunctionCallContent(name="", call_id="call_123", arguments='AI"}')])
-    events3 = await bridge.from_agent_run_update(update3)
-
-    # First update: ToolCallStartEvent
-    assert len(events1) == 1
-    assert events1[0].type == "TOOL_CALL_START"
-
-    # Second update: ToolCallArgsEvent
-    assert len(events2) == 1
-    assert events2[0].type == "TOOL_CALL_ARGS"
-    assert events2[0].delta == '{"query": "'
-
-    # Third update: ToolCallArgsEvent
-    assert len(events3) == 1
-    assert events3[0].type == "TOOL_CALL_ARGS"
-    assert events3[0].delta == 'AI"}'
-
-    # All should have same tool_call_id
-    assert events1[0].tool_call_id == events2[0].tool_call_id == events3[0].tool_call_id
-
-
-async def test_streaming_tool_call_no_duplicate_start_events():
-    """Test that streaming tool calls emit exactly one ToolCallStartEvent.
-
-    This is a regression test for the Anthropic streaming fix where input_json_delta
-    events were incorrectly passing the tool name, causing duplicate ToolCallStartEvents.
-
-    The correct behavior is:
-    - Initial FunctionCallContent with name -> emits ToolCallStartEvent
-    - Subsequent FunctionCallContent with name="" -> emits only ToolCallArgsEvent
-
-    See: https://github.com/microsoft/agent-framework/pull/3051
-    """
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    # Simulate streaming tool call: first chunk has name, subsequent chunks have name=""
-    update1 = AgentResponseUpdate(contents=[FunctionCallContent(name="get_weather", call_id="call_789")])
-    update2 = AgentResponseUpdate(contents=[FunctionCallContent(name="", call_id="call_789", arguments='{"loc":')])
-    update3 = AgentResponseUpdate(contents=[FunctionCallContent(name="", call_id="call_789", arguments='"SF"}')])
-
-    events1 = await bridge.from_agent_run_update(update1)
-    events2 = await bridge.from_agent_run_update(update2)
-    events3 = await bridge.from_agent_run_update(update3)
-
-    # Count all ToolCallStartEvents - should be exactly 1
-    all_events = events1 + events2 + events3
-    tool_call_start_count = sum(1 for e in all_events if e.type == "TOOL_CALL_START")
-    assert tool_call_start_count == 1, f"Expected 1 ToolCallStartEvent, got {tool_call_start_count}"
-
-    # Verify event types
-    assert events1[0].type == "TOOL_CALL_START"
-    assert events2[0].type == "TOOL_CALL_ARGS"
-    assert events3[0].type == "TOOL_CALL_ARGS"
-
-
-async def test_tool_result_with_dict():
-    """Test FunctionResultContent with dict result."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    result_data = {"status": "success", "count": 42}
-    update = AgentResponseUpdate(contents=[FunctionResultContent(call_id="call_123", result=result_data)])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should emit ToolCallEndEvent + ToolCallResultEvent
-    assert len(events) == 2
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[0].tool_call_id == "call_123"
-
-    assert events[1].type == "TOOL_CALL_RESULT"
-    assert events[1].tool_call_id == "call_123"
-    assert events[1].role == "tool"
-    # Result should be JSON-serialized
-    assert json.loads(events[1].content) == result_data
-
-
-async def test_tool_result_with_string():
-    """Test FunctionResultContent with string result."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update = AgentResponseUpdate(contents=[FunctionResultContent(call_id="call_123", result="Search complete")])
-    events = await bridge.from_agent_run_update(update)
-
-    assert len(events) == 2
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[1].type == "TOOL_CALL_RESULT"
-    assert events[1].content == "Search complete"
-
-
-async def test_tool_result_with_none():
-    """Test FunctionResultContent with None result."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update = AgentResponseUpdate(contents=[FunctionResultContent(call_id="call_123", result=None)])
-    events = await bridge.from_agent_run_update(update)
-
-    assert len(events) == 2
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[1].type == "TOOL_CALL_RESULT"
-    # prepare_function_call_results serializes None as JSON "null"
-    assert events[1].content == "null"
-
-
-async def test_multiple_tool_results_in_sequence():
-    """Test multiple tool results processed sequentially."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update = AgentResponseUpdate(
-        contents=[
-            FunctionResultContent(call_id="call_1", result="Result 1"),
-            FunctionResultContent(call_id="call_2", result="Result 2"),
-        ]
-    )
-    events = await bridge.from_agent_run_update(update)
-
-    # Each result emits: ToolCallEndEvent + ToolCallResultEvent = 4 events total
-    assert len(events) == 4
-    assert events[0].tool_call_id == "call_1"
-    assert events[1].tool_call_id == "call_1"
-    assert events[2].tool_call_id == "call_2"
-    assert events[3].tool_call_id == "call_2"
-
-
-async def test_function_approval_request_basic():
-    """Test FunctionApprovalRequestContent conversion."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    # Set require_confirmation=False to test just the function_approval_request event
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        require_confirmation=False,
-    )
-
-    func_call = FunctionCallContent(
-        call_id="call_123",
-        name="send_email",
-        arguments={"to": "user@example.com", "subject": "Test"},
-    )
-    approval = FunctionApprovalRequestContent(
-        id="approval_001",
-        function_call=func_call,
-    )
-
-    update = AgentResponseUpdate(contents=[approval])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should emit: ToolCallEndEvent + CustomEvent
-    assert len(events) == 2
-
-    # First: ToolCallEndEvent to close the tool call
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[0].tool_call_id == "call_123"
-
-    # Second: CustomEvent with approval details
-    assert events[1].type == "CUSTOM"
-    assert events[1].name == "function_approval_request"
-    assert events[1].value["id"] == "approval_001"
-    assert events[1].value["function_call"]["name"] == "send_email"
-
-
-async def test_empty_predict_state_config():
-    """Test behavior with no predictive state configuration."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={},  # Empty config
-    )
-
-    # Tool call with arguments
-    update = AgentResponseUpdate(
-        contents=[
-            FunctionCallContent(name="write_doc", call_id="call_1", arguments='{"content": "test"}'),
-            FunctionResultContent(call_id="call_1", result="Done"),
-        ]
-    )
-    events = await bridge.from_agent_run_update(update)
-
-    # Should NOT emit StateDeltaEvent or confirm_changes
-    event_types = [e.type for e in events]
-    assert "STATE_DELTA" not in event_types
-    assert "STATE_SNAPSHOT" not in event_types
-
-    # Should have: ToolCallStart, ToolCallArgs, ToolCallEnd, ToolCallResult
-    assert event_types == [
-        "TOOL_CALL_START",
-        "TOOL_CALL_ARGS",
-        "TOOL_CALL_END",
-        "TOOL_CALL_RESULT",
-    ]
-
-
-async def test_tool_not_in_predict_state_config():
-    """Test tool that doesn't match any predict_state_config entry."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={
-            "document": {"tool": "write_document", "tool_argument": "content"},
-        },
-    )
-
-    # Different tool name
-    update = AgentResponseUpdate(
-        contents=[
-            FunctionCallContent(name="search_web", call_id="call_1", arguments='{"query": "AI"}'),
-            FunctionResultContent(call_id="call_1", result="Results"),
-        ]
-    )
-    events = await bridge.from_agent_run_update(update)
-
-    # Should NOT emit StateDeltaEvent or confirm_changes
-    event_types = [e.type for e in events]
-    assert "STATE_DELTA" not in event_types
-    assert "STATE_SNAPSHOT" not in event_types
-
-
-async def test_state_management_tracking():
-    """Test current_state and pending_state_updates tracking."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    initial_state = {"document": ""}
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={
-            "document": {"tool": "write_doc", "tool_argument": "content"},
-        },
-        current_state=initial_state,
-    )
-
-    # Streaming tool call
-    update1 = AgentResponseUpdate(
-        contents=[
-            FunctionCallContent(name="write_doc", call_id="call_1"),
-            FunctionCallContent(name="", call_id="call_1", arguments='{"content": "Hello"}'),
-        ]
-    )
-    await bridge.from_agent_run_update(update1)
-
-    # Check pending_state_updates was populated
-    assert "document" in bridge.pending_state_updates
-    assert bridge.pending_state_updates["document"] == "Hello"
-
-    # Tool result should update current_state
-    update2 = AgentResponseUpdate(contents=[FunctionResultContent(call_id="call_1", result="Done")])
-    await bridge.from_agent_run_update(update2)
-
-    # current_state should be updated
-    assert bridge.current_state["document"] == "Hello"
-
-    # pending_state_updates should be cleared
-    assert len(bridge.pending_state_updates) == 0
-
-
-async def test_wildcard_tool_argument():
-    """Test tool_argument='*' uses all arguments as state value."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={
-            "recipe": {"tool": "create_recipe", "tool_argument": "*"},
-        },
-        current_state={},
-    )
-
-    # Complete tool call with dict arguments
-    update = AgentResponseUpdate(
-        contents=[
-            FunctionCallContent(
-                name="create_recipe",
-                call_id="call_1",
-                arguments={"title": "Pasta", "ingredients": ["pasta", "sauce"]},
-            ),
-            FunctionResultContent(call_id="call_1", result="Created"),
-        ]
-    )
-    events = await bridge.from_agent_run_update(update)
-
-    # Find StateDeltaEvent
-    delta_events = [e for e in events if e.type == "STATE_DELTA"]
-    assert len(delta_events) > 0
-
-    # Value should be the entire arguments dict
-    delta = delta_events[0].delta[0]
-    assert delta["path"] == "/recipe"
-    assert delta["value"] == {"title": "Pasta", "ingredients": ["pasta", "sauce"]}
-
-
-async def test_run_lifecycle_events():
-    """Test RunStartedEvent and RunFinishedEvent creation."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    started = bridge.create_run_started_event()
-    assert started.type == "RUN_STARTED"
-    assert started.run_id == "test_run"
-    assert started.thread_id == "test_thread"
-
-    finished = bridge.create_run_finished_event(result={"status": "complete"})
-    assert finished.type == "RUN_FINISHED"
-    assert finished.run_id == "test_run"
-    assert finished.thread_id == "test_thread"
-    assert finished.result == {"status": "complete"}
-
-
-async def test_message_lifecycle_events():
-    """Test TextMessageStartEvent and TextMessageEndEvent creation."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    start = bridge.create_message_start_event("msg_123", role="assistant")
-    assert start.type == "TEXT_MESSAGE_START"
-    assert start.message_id == "msg_123"
-    assert start.role == "assistant"
-
-    end = bridge.create_message_end_event("msg_123")
-    assert end.type == "TEXT_MESSAGE_END"
-    assert end.message_id == "msg_123"
-
-
-async def test_state_event_creation():
-    """Test StateSnapshotEvent and StateDeltaEvent creation helpers."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    # StateSnapshotEvent
-    snapshot = bridge.create_state_snapshot_event({"document": "content"})
-    assert snapshot.type == "STATE_SNAPSHOT"
-    assert snapshot.snapshot == {"document": "content"}
-
-    # StateDeltaEvent with JSON Patch
-    delta = bridge.create_state_delta_event([{"op": "replace", "path": "/document", "value": "new content"}])
-    assert delta.type == "STATE_DELTA"
-    assert len(delta.delta) == 1
-    assert delta.delta[0]["op"] == "replace"
-    assert delta.delta[0]["path"] == "/document"
-    assert delta.delta[0]["value"] == "new content"
-
-
-async def test_state_snapshot_after_tool_result():
-    """Test StateSnapshotEvent emission after tool result with pending updates."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={
-            "document": {"tool": "write_doc", "tool_argument": "content"},
-        },
-        current_state={"document": ""},
-    )
-
-    # Tool call with streaming args
-    update1 = AgentResponseUpdate(
-        contents=[
-            FunctionCallContent(name="write_doc", call_id="call_1"),
-            FunctionCallContent(name="", call_id="call_1", arguments='{"content": "Test"}'),
-        ]
-    )
-    await bridge.from_agent_run_update(update1)
-
-    # Tool result should trigger StateSnapshotEvent
-    update2 = AgentResponseUpdate(contents=[FunctionResultContent(call_id="call_1", result="Done")])
-    events = await bridge.from_agent_run_update(update2)
-
-    # Should have: ToolCallEnd, ToolCallResult, StateSnapshot, ToolCallStart (confirm_changes), ToolCallArgs, ToolCallEnd
-    snapshot_events = [e for e in events if e.type == "STATE_SNAPSHOT"]
-    assert len(snapshot_events) == 1
-    assert snapshot_events[0].snapshot["document"] == "Test"
-
-
-async def test_message_id_persistence_across_chunks():
-    """Test that message_id persists across multiple text chunks."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    # First chunk
-    update1 = AgentResponseUpdate(contents=[TextContent(text="Hello ")])
-    events1 = await bridge.from_agent_run_update(update1)
-    message_id = events1[0].message_id
-
-    # Second chunk
-    update2 = AgentResponseUpdate(contents=[TextContent(text="world")])
-    events2 = await bridge.from_agent_run_update(update2)
-
-    # Should use same message_id
-    assert events2[0].message_id == message_id
-    assert bridge.current_message_id == message_id
-
-
-async def test_tool_call_id_tracking():
-    """Test tool_call_id tracking across streaming chunks."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    # First chunk with name
-    update1 = AgentResponseUpdate(contents=[FunctionCallContent(name="search", call_id="call_1")])
-    await bridge.from_agent_run_update(update1)
-
-    assert bridge.current_tool_call_id == "call_1"
-    assert bridge.current_tool_call_name == "search"
-
-    # Second chunk with args but no name
-    update2 = AgentResponseUpdate(contents=[FunctionCallContent(name="", call_id="call_1", arguments='{"q":"AI"}')])
-    events2 = await bridge.from_agent_run_update(update2)
-
-    # Should still track same tool call
-    assert bridge.current_tool_call_id == "call_1"
-    assert events2[0].tool_call_id == "call_1"
-
-
-async def test_tool_name_reset_after_result():
-    """Test current_tool_call_name is reset after tool result."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={
-            "document": {"tool": "write_doc", "tool_argument": "content"},
-        },
-    )
-
-    # Tool call
-    update1 = AgentResponseUpdate(
-        contents=[
-            FunctionCallContent(name="write_doc", call_id="call_1"),
-            FunctionCallContent(name="", call_id="call_1", arguments='{"content": "Test"}'),
-        ]
-    )
-    await bridge.from_agent_run_update(update1)
-
-    assert bridge.current_tool_call_name == "write_doc"
-
-    # Tool result with predictive state (should trigger confirm_changes and reset)
-    update2 = AgentResponseUpdate(contents=[FunctionResultContent(call_id="call_1", result="Done")])
-    await bridge.from_agent_run_update(update2)
-
-    # Tool name should be reset
-    assert bridge.current_tool_call_name is None
-
-
-async def test_function_approval_with_wildcard_argument():
-    """Test function approval with wildcard * argument."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={
-            "payload": {"tool": "submit", "tool_argument": "*"},
-        },
-    )
-
-    approval_content = FunctionApprovalRequestContent(
-        id="approval_1",
-        function_call=FunctionCallContent(
-            name="submit", call_id="call_1", arguments='{"key1": "value1", "key2": "value2"}'
-        ),
-    )
-
-    update = AgentResponseUpdate(contents=[approval_content])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should emit StateSnapshotEvent with entire parsed args as value
-    snapshot_events = [e for e in events if e.type == "STATE_SNAPSHOT"]
-    assert len(snapshot_events) == 1
-    assert snapshot_events[0].snapshot["payload"] == {"key1": "value1", "key2": "value2"}
-
-
-async def test_function_approval_missing_argument():
-    """Test function approval when specified argument is not in parsed args."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={
-            "data": {"tool": "process", "tool_argument": "missing_field"},
-        },
-    )
-
-    approval_content = FunctionApprovalRequestContent(
-        id="approval_1",
-        function_call=FunctionCallContent(name="process", call_id="call_1", arguments='{"other_field": "value"}'),
-    )
-
-    update = AgentResponseUpdate(contents=[approval_content])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should not emit StateSnapshotEvent since argument not found
-    snapshot_events = [e for e in events if e.type == "STATE_SNAPSHOT"]
-    assert len(snapshot_events) == 0
-
-
-async def test_empty_predict_state_config_no_deltas():
-    """Test with empty predict_state_config (no predictive updates)."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread", predict_state_config={})
-
-    # Tool call with arguments
-    update = AgentResponseUpdate(
-        contents=[
-            FunctionCallContent(name="search", call_id="call_1"),
-            FunctionCallContent(name="", call_id="call_1", arguments='{"query": "test"}'),
-        ]
-    )
-    events = await bridge.from_agent_run_update(update)
-
-    # Should not emit any StateDeltaEvents
-    delta_events = [e for e in events if e.type == "STATE_DELTA"]
-    assert len(delta_events) == 0
-
-
-async def test_tool_with_no_matching_config():
-    """Test tool call for tool not in predict_state_config."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={"document": {"tool": "write_doc", "tool_argument": "content"}},
-    )
-
-    # Tool call for different tool
-    update = AgentResponseUpdate(
-        contents=[
-            FunctionCallContent(name="search_web", call_id="call_1"),
-            FunctionCallContent(name="", call_id="call_1", arguments='{"query": "test"}'),
-        ]
-    )
-    events = await bridge.from_agent_run_update(update)
-
-    # Should not emit StateDeltaEvents
-    delta_events = [e for e in events if e.type == "STATE_DELTA"]
-    assert len(delta_events) == 0
-
-
-async def test_tool_call_without_name_or_id():
-    """Test handling FunctionCallContent with no name and no call_id."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    # This should not crash but log an error
-    update = AgentResponseUpdate(contents=[FunctionCallContent(name="", call_id="", arguments='{"arg": "val"}')])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should emit ToolCallArgsEvent with generated ID
-    assert len(events) >= 1
-
-
-async def test_state_delta_count_logging():
-    """Test that state delta count increments and logs at intervals."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}},
-    )
-
-    # Emit multiple state deltas with different content each time
-    for i in range(15):
-        update = AgentResponseUpdate(
-            contents=[
-                FunctionCallContent(name="", call_id="call_1", arguments=f'{{"text": "Content variation {i}"}}'),
-            ]
-        )
-        # Set the tool name to match config
-        bridge.current_tool_call_name = "write"
-        await bridge.from_agent_run_update(update)
-
-    # State delta count should have incremented (one per unique state update)
-    assert bridge.state_delta_count >= 1
-
-
-# Tests for list type tool results (MCP tool serialization)
-
-
-async def test_tool_result_with_empty_list():
-    """Test FunctionResultContent with empty list result."""
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update = AgentResponseUpdate(contents=[FunctionResultContent(call_id="call_123", result=[])])
-    events = await bridge.from_agent_run_update(update)
-
-    assert len(events) == 2
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[1].type == "TOOL_CALL_RESULT"
-    # Empty list serializes as JSON empty array
-    assert events[1].content == "[]"
-
-
-async def test_tool_result_with_single_text_content():
-    """Test FunctionResultContent with single TextContent-like item (MCP tool result)."""
-    from dataclasses import dataclass
-
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    @dataclass
-    class MockTextContent:
-        text: str
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update = AgentResponseUpdate(
-        contents=[FunctionResultContent(call_id="call_123", result=[MockTextContent("Hello from MCP tool!")])]
-    )
-    events = await bridge.from_agent_run_update(update)
-
-    assert len(events) == 2
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[1].type == "TOOL_CALL_RESULT"
-    # TextContent text is extracted and serialized as JSON array
-    assert events[1].content == '["Hello from MCP tool!"]'
-
-
-async def test_tool_result_with_multiple_text_contents():
-    """Test FunctionResultContent with multiple TextContent-like items (MCP tool result)."""
-    from dataclasses import dataclass
-
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    @dataclass
-    class MockTextContent:
-        text: str
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update = AgentResponseUpdate(
-        contents=[
-            FunctionResultContent(
-                call_id="call_123",
-                result=[MockTextContent("First result"), MockTextContent("Second result")],
-            )
-        ]
-    )
-    events = await bridge.from_agent_run_update(update)
-
-    assert len(events) == 2
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[1].type == "TOOL_CALL_RESULT"
-    # Multiple TextContent items should return JSON array
-    assert events[1].content == '["First result", "Second result"]'
-
-
-async def test_tool_result_with_model_dump_objects():
-    """Test FunctionResultContent with Pydantic BaseModel objects."""
-    from pydantic import BaseModel
-
-    from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-    class MockModel(BaseModel):
-        value: int
-
-    bridge = AgentFrameworkEventBridge(run_id="test_run", thread_id="test_thread")
-
-    update = AgentResponseUpdate(
-        contents=[FunctionResultContent(call_id="call_123", result=[MockModel(value=1), MockModel(value=2)])]
-    )
-    events = await bridge.from_agent_run_update(update)
-
-    assert len(events) == 2
-    assert events[1].type == "TOOL_CALL_RESULT"
-    # Should be properly serialized JSON array without double escaping
-    assert events[1].content == '[{"value": 1}, {"value": 2}]'
@@ -0,0 +1,502 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Tests for orchestration helper functions."""
+
+from agent_framework import ChatMessage, Content
+
+from agent_framework_ag_ui._orchestration._helpers import (
+    approval_steps,
+    build_safe_metadata,
+    ensure_tool_call_entry,
+    is_state_context_message,
+    is_step_based_approval,
+    latest_approval_response,
+    pending_tool_call_ids,
+    schema_has_steps,
+    select_approval_tool_name,
+    tool_name_for_call_id,
+)
+
+
+class TestPendingToolCallIds:
+    """Tests for pending_tool_call_ids function."""
+
+    def test_empty_messages(self):
+        """Returns empty set for empty messages list."""
+        result = pending_tool_call_ids([])
+        assert result == set()
+
+    def test_no_tool_calls(self):
+        """Returns empty set when no tool calls in messages."""
+        messages = [
+            ChatMessage(role="user", contents=[Content.from_text("Hello")]),
+            ChatMessage(role="assistant", contents=[Content.from_text("Hi there")]),
+        ]
+        result = pending_tool_call_ids(messages)
+        assert result == set()
+
+    def test_pending_tool_call(self):
+        """Returns pending tool call ID when no result exists."""
+        messages = [
+            ChatMessage(
+                role="assistant",
+                contents=[Content.from_function_call(call_id="call_123", name="get_weather", arguments="{}")],
+            ),
+        ]
+        result = pending_tool_call_ids(messages)
+        assert result == {"call_123"}
+
+    def test_resolved_tool_call(self):
+        """Returns empty set when tool call has result."""
+        messages = [
+            ChatMessage(
+                role="assistant",
+                contents=[Content.from_function_call(call_id="call_123", name="get_weather", arguments="{}")],
+            ),
+            ChatMessage(
+                role="tool",
+                contents=[Content.from_function_result(call_id="call_123", result="sunny")],
+            ),
+        ]
+        result = pending_tool_call_ids(messages)
+        assert result == set()
+
+    def test_multiple_tool_calls_some_resolved(self):
+        """Returns only unresolved tool call IDs."""
+        messages = [
+            ChatMessage(
+                role="assistant",
+                contents=[
+                    Content.from_function_call(call_id="call_1", name="tool_a", arguments="{}"),
+                    Content.from_function_call(call_id="call_2", name="tool_b", arguments="{}"),
+                    Content.from_function_call(call_id="call_3", name="tool_c", arguments="{}"),
+                ],
+            ),
+            ChatMessage(
+                role="tool",
+                contents=[Content.from_function_result(call_id="call_1", result="result_a")],
+            ),
+            ChatMessage(
+                role="tool",
+                contents=[Content.from_function_result(call_id="call_3", result="result_c")],
+            ),
+        ]
+        result = pending_tool_call_ids(messages)
+        assert result == {"call_2"}
+
+
+class TestIsStateContextMessage:
+    """Tests for is_state_context_message function."""
+
+    def test_state_context_message(self):
+        """Returns True for state context message."""
+        message = ChatMessage(
+            role="system",
+            contents=[Content.from_text("Current state of the application: {}")],
+        )
+        assert is_state_context_message(message) is True
+
+    def test_non_system_message(self):
+        """Returns False for non-system message."""
+        message = ChatMessage(
+            role="user",
+            contents=[Content.from_text("Current state of the application: {}")],
+        )
+        assert is_state_context_message(message) is False
+
+    def test_system_message_without_state_prefix(self):
+        """Returns False for system message without state prefix."""
+        message = ChatMessage(
+            role="system",
+            contents=[Content.from_text("You are a helpful assistant.")],
+        )
+        assert is_state_context_message(message) is False
+
+    def test_empty_contents(self):
+        """Returns False for message with empty contents."""
+        message = ChatMessage(role="system", contents=[])
+        assert is_state_context_message(message) is False
+
+
+class TestEnsureToolCallEntry:
+    """Tests for ensure_tool_call_entry function."""
+
+    def test_creates_new_entry(self):
+        """Creates new entry when ID not found."""
+        tool_calls_by_id: dict = {}
+        pending_tool_calls: list = []
+
+        entry = ensure_tool_call_entry("call_123", tool_calls_by_id, pending_tool_calls)
+
+        assert entry["id"] == "call_123"
+        assert entry["type"] == "function"
+        assert entry["function"]["name"] == ""
+        assert entry["function"]["arguments"] == ""
+        assert "call_123" in tool_calls_by_id
+        assert len(pending_tool_calls) == 1
+
+    def test_returns_existing_entry(self):
+        """Returns existing entry when ID found."""
+        existing_entry = {
+            "id": "call_123",
+            "type": "function",
+            "function": {"name": "get_weather", "arguments": '{"city": "NYC"}'},
+        }
+        tool_calls_by_id = {"call_123": existing_entry}
+        pending_tool_calls: list = []
+
+        entry = ensure_tool_call_entry("call_123", tool_calls_by_id, pending_tool_calls)
+
+        assert entry is existing_entry
+        assert entry["function"]["name"] == "get_weather"
+        assert len(pending_tool_calls) == 0  # Not added again
+
+
+class TestToolNameForCallId:
+    """Tests for tool_name_for_call_id function."""
+
+    def test_returns_tool_name(self):
+        """Returns tool name for valid entry."""
+        tool_calls_by_id = {
+            "call_123": {
+                "id": "call_123",
+                "function": {"name": "get_weather", "arguments": "{}"},
+            }
+        }
+        result = tool_name_for_call_id(tool_calls_by_id, "call_123")
+        assert result == "get_weather"
+
+    def test_returns_none_for_missing_id(self):
+        """Returns None when ID not found."""
+        tool_calls_by_id: dict = {}
+        result = tool_name_for_call_id(tool_calls_by_id, "call_123")
+        assert result is None
+
+    def test_returns_none_for_missing_function(self):
+        """Returns None when function key missing."""
+        tool_calls_by_id = {"call_123": {"id": "call_123"}}
+        result = tool_name_for_call_id(tool_calls_by_id, "call_123")
+        assert result is None
+
+    def test_returns_none_for_non_dict_function(self):
+        """Returns None when function is not a dict."""
+        tool_calls_by_id = {"call_123": {"id": "call_123", "function": "not_a_dict"}}
+        result = tool_name_for_call_id(tool_calls_by_id, "call_123")
+        assert result is None
+
+    def test_returns_none_for_empty_name(self):
+        """Returns None when name is empty."""
+        tool_calls_by_id = {"call_123": {"id": "call_123", "function": {"name": "", "arguments": "{}"}}}
+        result = tool_name_for_call_id(tool_calls_by_id, "call_123")
+        assert result is None
+
+
+class TestSchemaHasSteps:
+    """Tests for schema_has_steps function."""
+
+    def test_schema_with_steps_array(self):
+        """Returns True when schema has steps array property."""
+        schema = {"properties": {"steps": {"type": "array"}}}
+        assert schema_has_steps(schema) is True
+
+    def test_schema_without_steps(self):
+        """Returns False when schema doesn't have steps."""
+        schema = {"properties": {"name": {"type": "string"}}}
+        assert schema_has_steps(schema) is False
+
+    def test_schema_with_non_array_steps(self):
+        """Returns False when steps is not array type."""
+        schema = {"properties": {"steps": {"type": "string"}}}
+        assert schema_has_steps(schema) is False
+
+    def test_non_dict_schema(self):
+        """Returns False for non-dict schema."""
+        assert schema_has_steps(None) is False
+        assert schema_has_steps("not a dict") is False
+        assert schema_has_steps([]) is False
+
+    def test_missing_properties(self):
+        """Returns False when properties key is missing."""
+        schema = {"type": "object"}
+        assert schema_has_steps(schema) is False
+
+    def test_non_dict_properties(self):
+        """Returns False when properties is not a dict."""
+        schema = {"properties": "not a dict"}
+        assert schema_has_steps(schema) is False
+
+    def test_non_dict_steps(self):
+        """Returns False when steps is not a dict."""
+        schema = {"properties": {"steps": "not a dict"}}
+        assert schema_has_steps(schema) is False
+
+
+class TestSelectApprovalToolName:
+    """Tests for select_approval_tool_name function."""
+
+    def test_none_client_tools(self):
+        """Returns None when client_tools is None."""
+        result = select_approval_tool_name(None)
+        assert result is None
+
+    def test_empty_client_tools(self):
+        """Returns None when client_tools is empty."""
+        result = select_approval_tool_name([])
+        assert result is None
+
+    def test_finds_approval_tool(self):
+        """Returns tool name when tool has steps schema."""
+
+        class MockTool:
+            name = "generate_task_steps"
+
+            def parameters(self):
+                return {"properties": {"steps": {"type": "array"}}}
+
+        result = select_approval_tool_name([MockTool()])
+        assert result == "generate_task_steps"
+
+    def test_skips_tool_without_name(self):
+        """Skips tools without name attribute."""
+
+        class MockToolNoName:
+            def parameters(self):
+                return {"properties": {"steps": {"type": "array"}}}
+
+        result = select_approval_tool_name([MockToolNoName()])
+        assert result is None
+
+    def test_skips_tool_without_parameters_method(self):
+        """Skips tools without callable parameters method."""
+
+        class MockToolNoParams:
+            name = "some_tool"
+            parameters = "not callable"
+
+        result = select_approval_tool_name([MockToolNoParams()])
+        assert result is None
+
+    def test_skips_tool_without_steps_schema(self):
+        """Skips tools that don't have steps in schema."""
+
+        class MockToolNoSteps:
+            name = "other_tool"
+
+            def parameters(self):
+                return {"properties": {"data": {"type": "string"}}}
+
+        result = select_approval_tool_name([MockToolNoSteps()])
+        assert result is None
+
+
+class TestBuildSafeMetadata:
+    """Tests for build_safe_metadata function."""
+
+    def test_none_metadata(self):
+        """Returns empty dict for None metadata."""
+        result = build_safe_metadata(None)
+        assert result == {}
+
+    def test_empty_metadata(self):
+        """Returns empty dict for empty metadata."""
+        result = build_safe_metadata({})
+        assert result == {}
+
+    def test_string_values_under_limit(self):
+        """Preserves string values under 512 chars."""
+        metadata = {"key1": "short value", "key2": "another value"}
+        result = build_safe_metadata(metadata)
+        assert result == metadata
+
+    def test_truncates_long_string_values(self):
+        """Truncates string values over 512 chars."""
+        long_value = "x" * 1000
+        metadata = {"key": long_value}
+        result = build_safe_metadata(metadata)
+        assert len(result["key"]) == 512
+        assert result["key"] == "x" * 512
+
+    def test_non_string_values_serialized(self):
+        """Serializes non-string values to JSON."""
+        metadata = {"count": 42, "items": ["a", "b"]}
+        result = build_safe_metadata(metadata)
+        assert result["count"] == "42"
+        assert result["items"] == '["a", "b"]'
+
+    def test_truncates_serialized_values(self):
+        """Truncates serialized JSON values over 512 chars."""
+        long_list = list(range(200))  # Will serialize to >512 chars
+        metadata = {"data": long_list}
+        result = build_safe_metadata(metadata)
+        assert len(result["data"]) == 512
+
+
+class TestLatestApprovalResponse:
+    """Tests for latest_approval_response function."""
+
+    def test_empty_messages(self):
+        """Returns None for empty messages."""
+        result = latest_approval_response([])
+        assert result is None
+
+    def test_no_approval_response(self):
+        """Returns None when no approval response in last message."""
+        messages = [
+            ChatMessage(role="assistant", contents=[Content.from_text("Hello")]),
+        ]
+        result = latest_approval_response(messages)
+        assert result is None
+
+    def test_finds_approval_response(self):
+        """Returns approval response from last message."""
+        # Create a function call content first
+        fc = Content.from_function_call(call_id="call_123", name="test_tool", arguments="{}")
+        approval_content = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+        )
+        messages = [
+            ChatMessage(role="user", contents=[approval_content]),
+        ]
+        result = latest_approval_response(messages)
+        assert result is approval_content
+
+
+class TestApprovalSteps:
+    """Tests for approval_steps function."""
+
+    def test_steps_from_ag_ui_state_args(self):
+        """Extracts steps from ag_ui_state_args."""
+        fc = Content.from_function_call(call_id="call_123", name="test_tool", arguments="{}")
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+            additional_properties={"ag_ui_state_args": {"steps": [{"id": 1}, {"id": 2}]}},
+        )
+        result = approval_steps(approval)
+        assert result == [{"id": 1}, {"id": 2}]
+
+    def test_steps_from_function_call(self):
+        """Extracts steps from function call arguments."""
+        fc = Content.from_function_call(
+            call_id="call_123",
+            name="test",
+            arguments='{"steps": [{"step": 1}]}',
+        )
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+        )
+        result = approval_steps(approval)
+        assert result == [{"step": 1}]
+
+    def test_empty_steps_when_no_state_args(self):
+        """Returns empty list when no ag_ui_state_args."""
+        fc = Content.from_function_call(call_id="call_123", name="test_tool", arguments="{}")
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+        )
+        result = approval_steps(approval)
+        assert result == []
+
+    def test_empty_steps_when_state_args_not_dict(self):
+        """Returns empty list when ag_ui_state_args is not a dict."""
+        fc = Content.from_function_call(call_id="call_123", name="test_tool", arguments="{}")
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+            additional_properties={"ag_ui_state_args": "not a dict"},
+        )
+        result = approval_steps(approval)
+        assert result == []
+
+    def test_empty_steps_when_steps_not_list(self):
+        """Returns empty list when steps is not a list."""
+        fc = Content.from_function_call(call_id="call_123", name="test_tool", arguments="{}")
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+            additional_properties={"ag_ui_state_args": {"steps": "not a list"}},
+        )
+        result = approval_steps(approval)
+        assert result == []
+
+
+class TestIsStepBasedApproval:
+    """Tests for is_step_based_approval function."""
+
+    def test_returns_true_when_has_steps(self):
+        """Returns True when approval has steps."""
+        fc = Content.from_function_call(call_id="call_123", name="test_tool", arguments="{}")
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+            additional_properties={"ag_ui_state_args": {"steps": [{"id": 1}]}},
+        )
+        result = is_step_based_approval(approval, None)
+        assert result is True
+
+    def test_returns_false_no_steps_no_function_call(self):
+        """Returns False when no steps and no function call."""
+        # Create content directly to have no function_call
+        approval = Content(
+            type="function_approval_response",
+            function_call=None,
+        )
+        result = is_step_based_approval(approval, None)
+        assert result is False
+
+    def test_returns_false_no_predict_config(self):
+        """Returns False when no predict_state_config."""
+        fc = Content.from_function_call(call_id="call_123", name="some_tool", arguments="{}")
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+        )
+        result = is_step_based_approval(approval, None)
+        assert result is False
+
+    def test_returns_true_when_tool_matches_config(self):
+        """Returns True when tool matches predict_state_config with steps."""
+        fc = Content.from_function_call(call_id="call_123", name="generate_steps", arguments="{}")
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+        )
+        config = {"steps": {"tool": "generate_steps", "tool_argument": "steps"}}
+        result = is_step_based_approval(approval, config)
+        assert result is True
+
+    def test_returns_false_when_tool_not_in_config(self):
+        """Returns False when tool not in predict_state_config."""
+        fc = Content.from_function_call(call_id="call_123", name="other_tool", arguments="{}")
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+        )
+        config = {"steps": {"tool": "generate_steps", "tool_argument": "steps"}}
+        result = is_step_based_approval(approval, config)
+        assert result is False
+
+    def test_returns_false_when_tool_arg_not_steps(self):
+        """Returns False when tool_argument is not 'steps'."""
+        fc = Content.from_function_call(call_id="call_123", name="generate_steps", arguments="{}")
+        approval = Content.from_function_approval_response(
+            approved=True,
+            id="approval_123",
+            function_call=fc,
+        )
+        config = {"document": {"tool": "generate_steps", "tool_argument": "content"}}
+        result = is_step_based_approval(approval, config)
+        assert result is False
@@ -1,180 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Tests for human in the loop (function approval requests)."""
-
-from agent_framework import AgentResponseUpdate, FunctionApprovalRequestContent, FunctionCallContent
-
-from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-
-async def test_function_approval_request_emission():
-    """Test that CustomEvent is emitted for FunctionApprovalRequestContent."""
-    # Set require_confirmation=False to test just the function_approval_request event
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        require_confirmation=False,
-    )
-
-    # Create approval request
-    func_call = FunctionCallContent(
-        call_id="call_123",
-        name="send_email",
-        arguments={"to": "user@example.com", "subject": "Test"},
-    )
-    approval_request = FunctionApprovalRequestContent(
-        id="approval_001",
-        function_call=func_call,
-    )
-
-    update = AgentResponseUpdate(contents=[approval_request])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should emit ToolCallEndEvent + CustomEvent for approval request
-    assert len(events) == 2
-
-    # First event: ToolCallEndEvent to close the tool call
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[0].tool_call_id == "call_123"
-
-    # Second event: CustomEvent with approval details
-    event = events[1]
-    assert event.type == "CUSTOM"
-    assert event.name == "function_approval_request"
-    assert event.value["id"] == "approval_001"
-    assert event.value["function_call"]["call_id"] == "call_123"
-    assert event.value["function_call"]["name"] == "send_email"
-    assert event.value["function_call"]["arguments"]["to"] == "user@example.com"
-    assert event.value["function_call"]["arguments"]["subject"] == "Test"
-
-
-async def test_function_approval_request_with_confirm_changes():
-    """Test that confirm_changes is also emitted when require_confirmation=True."""
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        require_confirmation=True,
-    )
-
-    func_call = FunctionCallContent(
-        call_id="call_456",
-        name="delete_file",
-        arguments={"path": "/tmp/test.txt"},
-    )
-    approval_request = FunctionApprovalRequestContent(
-        id="approval_002",
-        function_call=func_call,
-    )
-
-    update = AgentResponseUpdate(contents=[approval_request])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should emit: ToolCallEndEvent, CustomEvent, and confirm_changes (Start, Args, End) = 5 events
-    assert len(events) == 5
-
-    # Check ToolCallEndEvent
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[0].tool_call_id == "call_456"
-
-    # Check function_approval_request CustomEvent
-    assert events[1].type == "CUSTOM"
-    assert events[1].name == "function_approval_request"
-
-    # Check confirm_changes tool call events
-    assert events[2].type == "TOOL_CALL_START"
-    assert events[2].tool_call_name == "confirm_changes"
-    assert events[3].type == "TOOL_CALL_ARGS"
-    # Verify confirm_changes includes function info for Dojo UI
-    import json
-
-    args = json.loads(events[3].delta)
-    assert args["function_name"] == "delete_file"
-    assert args["function_call_id"] == "call_456"
-    assert args["function_arguments"] == {"path": "/tmp/test.txt"}
-    assert args["steps"] == [
-        {
-            "description": "Execute delete_file",
-            "status": "enabled",
-        }
-    ]
-    assert events[4].type == "TOOL_CALL_END"
-
-
-async def test_multiple_approval_requests():
-    """Test handling multiple approval requests in one update."""
-    # Set require_confirmation=False to simplify the test
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-        require_confirmation=False,
-    )
-
-    func_call_1 = FunctionCallContent(
-        call_id="call_1",
-        name="create_event",
-        arguments={"title": "Meeting"},
-    )
-    approval_1 = FunctionApprovalRequestContent(
-        id="approval_1",
-        function_call=func_call_1,
-    )
-
-    func_call_2 = FunctionCallContent(
-        call_id="call_2",
-        name="book_room",
-        arguments={"room": "Conference A"},
-    )
-    approval_2 = FunctionApprovalRequestContent(
-        id="approval_2",
-        function_call=func_call_2,
-    )
-
-    update = AgentResponseUpdate(contents=[approval_1, approval_2])
-    events = await bridge.from_agent_run_update(update)
-
-    # Should emit ToolCallEndEvent + CustomEvent for each approval (4 events total)
-    assert len(events) == 4
-
-    # Events should alternate: End, Custom, End, Custom
-    assert events[0].type == "TOOL_CALL_END"
-    assert events[0].tool_call_id == "call_1"
-
-    assert events[1].type == "CUSTOM"
-    assert events[1].name == "function_approval_request"
-    assert events[1].value["id"] == "approval_1"
-
-    assert events[2].type == "TOOL_CALL_END"
-    assert events[2].tool_call_id == "call_2"
-
-    assert events[3].type == "CUSTOM"
-    assert events[3].name == "function_approval_request"
-    assert events[3].value["id"] == "approval_2"
-
-
-async def test_function_approval_request_sets_stop_flag():
-    """Test that function approval request sets should_stop_after_confirm flag.
-
-    This ensures the orchestrator stops the run after emitting the approval request,
-    allowing the UI to send back an approval response.
-    """
-    bridge = AgentFrameworkEventBridge(
-        run_id="test_run",
-        thread_id="test_thread",
-    )
-
-    assert bridge.should_stop_after_confirm is False
-
-    func_call = FunctionCallContent(
-        call_id="call_stop_test",
-        name="get_datetime",
-        arguments={},
-    )
-    approval_request = FunctionApprovalRequestContent(
-        id="approval_stop_test",
-        function_call=func_call,
-    )
-
-    update = AgentResponseUpdate(contents=[approval_request])
-    await bridge.from_agent_run_update(update)
-
-    assert bridge.should_stop_after_confirm is True
@@ -5,7 +5,7 @@
 import json

 import pytest
-from agent_framework import ChatMessage, FunctionCallContent, FunctionResultContent, Role, TextContent
+from agent_framework import ChatMessage, Content, Role

 from agent_framework_ag_ui._message_adapters import (
    agent_framework_messages_to_agui,
@@ -24,7 +24,7 @@ def sample_agui_message():
@pytest.fixture
 def sample_agent_framework_message():
    """Create a sample Agent Framework message."""
-    return ChatMessage(role=Role.USER, contents=[TextContent(text="Hello")], message_id="msg-123")
+    return ChatMessage(role=Role.USER, contents=[Content.from_text(text="Hello")], message_id="msg-123")


 def test_agui_to_agent_framework_basic(sample_agui_message):
@@ -89,7 +89,7 @@ def test_agui_tool_result_to_agent_framework():
    assert message.role == Role.USER

    assert len(message.contents) == 1
-    assert isinstance(message.contents[0], TextContent)
+    assert message.contents[0].type == "text"
    assert message.contents[0].text == '{"accepted": true, "steps": []}'

    assert message.additional_properties is not None
@@ -141,7 +141,7 @@ def test_agui_tool_approval_updates_tool_call_arguments():

    assert len(messages) == 2
    assistant_msg = messages[0]
-    func_call = next(content for content in assistant_msg.contents if isinstance(content, FunctionCallContent))
+    func_call = next(content for content in assistant_msg.contents if content.type == "function_call")
    assert func_call.arguments == {
        "steps": [
            {"description": "Boil water", "status": "enabled"},
@@ -157,11 +157,9 @@ def test_agui_tool_approval_updates_tool_call_arguments():
        ]
    }

-    from agent_framework import FunctionApprovalResponseContent
-
    approval_msg = messages[1]
    approval_content = next(
-        content for content in approval_msg.contents if isinstance(content, FunctionApprovalResponseContent)
+        content for content in approval_msg.contents if content.type == "function_approval_response"
    )
    assert approval_content.function_call.parse_arguments() == {
        "steps": [
@@ -211,12 +209,9 @@ def test_agui_tool_approval_from_confirm_changes_maps_to_function_call():
    ]

    messages = agui_messages_to_agent_framework(messages_input)
-
-    from agent_framework import FunctionApprovalResponseContent
-
    approval_msg = messages[1]
    approval_content = next(
-        content for content in approval_msg.contents if isinstance(content, FunctionApprovalResponseContent)
+        content for content in approval_msg.contents if content.type == "function_approval_response"
    )

    assert approval_content.function_call.call_id == "call_tool"
@@ -259,12 +254,9 @@ def test_agui_tool_approval_from_confirm_changes_falls_back_to_sibling_call():
    ]

    messages = agui_messages_to_agent_framework(messages_input)
-
-    from agent_framework import FunctionApprovalResponseContent
-
    approval_msg = messages[1]
    approval_content = next(
-        content for content in approval_msg.contents if isinstance(content, FunctionApprovalResponseContent)
+        content for content in approval_msg.contents if content.type == "function_approval_response"
    )

    assert approval_content.function_call.call_id == "call_tool"
@@ -315,12 +307,9 @@ def test_agui_tool_approval_from_generate_task_steps_maps_to_function_call():
    ]

    messages = agui_messages_to_agent_framework(messages_input)
-
-    from agent_framework import FunctionApprovalResponseContent
-
    approval_msg = messages[1]
    approval_content = next(
-        content for content in approval_msg.contents if isinstance(content, FunctionApprovalResponseContent)
+        content for content in approval_msg.contents if content.type == "function_approval_response"
    )

    assert approval_content.function_call.call_id == "call_tool"
@@ -380,15 +369,14 @@ def test_agui_function_approvals():
    assert msg.role == Role.USER
    assert len(msg.contents) == 2

-    from agent_framework import FunctionApprovalResponseContent
-
-    assert isinstance(msg.contents[0], FunctionApprovalResponseContent)
+    assert msg.contents[0].type == "function_approval_response"
    assert msg.contents[0].approved is True
    assert msg.contents[0].id == "approval-1"
    assert msg.contents[0].function_call.name == "search"
    assert msg.contents[0].function_call.call_id == "call-1"

-    assert isinstance(msg.contents[1], FunctionApprovalResponseContent)
+    assert msg.contents[1].type == "function_approval_response"
+    assert msg.contents[1].id == "approval-2"
    assert msg.contents[1].approved is False


@@ -406,7 +394,7 @@ def test_agui_non_string_content():

    assert len(messages) == 1
    assert len(messages[0].contents) == 1
-    assert isinstance(messages[0].contents[0], TextContent)
+    assert messages[0].contents[0].type == "text"
    assert "nested" in messages[0].contents[0].text


@@ -440,9 +428,9 @@ def test_agui_with_tool_calls_to_agent_framework():
    assert msg.role == Role.ASSISTANT
    assert msg.message_id == "msg-789"
    # First content is text, second is the function call
-    assert isinstance(msg.contents[0], TextContent)
+    assert msg.contents[0].type == "text"
    assert msg.contents[0].text == "Calling tool"
-    assert isinstance(msg.contents[1], FunctionCallContent)
+    assert msg.contents[1].type == "function_call"
    assert msg.contents[1].call_id == "call-123"
    assert msg.contents[1].name == "get_weather"
    assert msg.contents[1].arguments == {"location": "Seattle"}
@@ -453,8 +441,8 @@ def test_agent_framework_to_agui_with_tool_calls():
    msg = ChatMessage(
        role=Role.ASSISTANT,
        contents=[
-            TextContent(text="Calling tool"),
-            FunctionCallContent(call_id="call-123", name="search", arguments={"query": "test"}),
+            Content.from_text(text="Calling tool"),
+            Content.from_function_call(call_id="call-123", name="search", arguments={"query": "test"}),
        ],
        message_id="msg-456",
    )
@@ -477,7 +465,7 @@ def test_agent_framework_to_agui_multiple_text_contents():
    """Test concatenating multiple text contents."""
    msg = ChatMessage(
        role=Role.ASSISTANT,
-        contents=[TextContent(text="Part 1 "), TextContent(text="Part 2")],
+        contents=[Content.from_text(text="Part 1 "), Content.from_text(text="Part 2")],
    )

    messages = agent_framework_messages_to_agui([msg])
@@ -488,7 +476,7 @@ def test_agent_framework_to_agui_multiple_text_contents():

 def test_agent_framework_to_agui_no_message_id():
    """Test message without message_id - should auto-generate ID."""
-    msg = ChatMessage(role=Role.USER, contents=[TextContent(text="Hello")])
+    msg = ChatMessage(role=Role.USER, contents=[Content.from_text(text="Hello")])

    messages = agent_framework_messages_to_agui([msg])

@@ -500,7 +488,7 @@ def test_agent_framework_to_agui_no_message_id():

 def test_agent_framework_to_agui_system_role():
    """Test system role conversion."""
-    msg = ChatMessage(role=Role.SYSTEM, contents=[TextContent(text="System")])
+    msg = ChatMessage(role=Role.SYSTEM, contents=[Content.from_text(text="System")])

    messages = agent_framework_messages_to_agui([msg])

@@ -510,7 +498,7 @@ def test_agent_framework_to_agui_system_role():

 def test_extract_text_from_contents():
    """Test extracting text from contents list."""
-    contents = [TextContent(text="Hello "), TextContent(text="World")]
+    contents = [Content.from_text(text="Hello "), Content.from_text(text="World")]

    result = extract_text_from_contents(contents)

@@ -533,7 +521,7 @@ class CustomTextContent:

 def test_extract_text_from_custom_contents():
    """Test extracting text from custom content objects."""
-    contents = [CustomTextContent(text="Custom "), TextContent(text="Mixed")]
+    contents = [CustomTextContent(text="Custom "), Content.from_text(text="Mixed")]

    result = extract_text_from_contents(contents)

@@ -547,7 +535,7 @@ def test_agent_framework_to_agui_function_result_dict():
    """Test converting FunctionResultContent with dict result to AG-UI."""
    msg = ChatMessage(
        role=Role.TOOL,
-        contents=[FunctionResultContent(call_id="call-123", result={"key": "value", "count": 42})],
+        contents=[Content.from_function_result(call_id="call-123", result={"key": "value", "count": 42})],
        message_id="msg-789",
    )

@@ -564,7 +552,7 @@ def test_agent_framework_to_agui_function_result_none():
    """Test converting FunctionResultContent with None result to AG-UI."""
    msg = ChatMessage(
        role=Role.TOOL,
-        contents=[FunctionResultContent(call_id="call-123", result=None)],
+        contents=[Content.from_function_result(call_id="call-123", result=None)],
        message_id="msg-789",
    )

@@ -580,7 +568,7 @@ def test_agent_framework_to_agui_function_result_string():
    """Test converting FunctionResultContent with string result to AG-UI."""
    msg = ChatMessage(
        role=Role.TOOL,
-        contents=[FunctionResultContent(call_id="call-123", result="plain text result")],
+        contents=[Content.from_function_result(call_id="call-123", result="plain text result")],
        message_id="msg-789",
    )

@@ -595,7 +583,7 @@ def test_agent_framework_to_agui_function_result_empty_list():
    """Test converting FunctionResultContent with empty list result to AG-UI."""
    msg = ChatMessage(
        role=Role.TOOL,
-        contents=[FunctionResultContent(call_id="call-123", result=[])],
+        contents=[Content.from_function_result(call_id="call-123", result=[])],
        message_id="msg-789",
    )

@@ -617,7 +605,7 @@ def test_agent_framework_to_agui_function_result_single_text_content():

    msg = ChatMessage(
        role=Role.TOOL,
-        contents=[FunctionResultContent(call_id="call-123", result=[MockTextContent("Hello from MCP!")])],
+        contents=[Content.from_function_result(call_id="call-123", result=[MockTextContent("Hello from MCP!")])],
        message_id="msg-789",
    )

@@ -640,7 +628,7 @@ def test_agent_framework_to_agui_function_result_multiple_text_contents():
    msg = ChatMessage(
        role=Role.TOOL,
        contents=[
-            FunctionResultContent(
+            Content.from_function_result(
                call_id="call-123",
                result=[MockTextContent("First result"), MockTextContent("Second result")],
            )
@@ -654,3 +642,109 @@ def test_agent_framework_to_agui_function_result_multiple_text_contents():
    agui_msg = messages[0]
    # Multiple items should return JSON array
    assert agui_msg["content"] == '["First result", "Second result"]'
+
+
+# Additional tests for better coverage
+
+
+def test_extract_text_from_contents_empty():
+    """Test extracting text from empty contents."""
+    result = extract_text_from_contents([])
+    assert result == ""
+
+
+def test_extract_text_from_contents_multiple():
+    """Test extracting text from multiple text contents."""
+    contents = [
+        Content.from_text("Hello "),
+        Content.from_text("World"),
+    ]
+    result = extract_text_from_contents(contents)
+    assert result == "Hello World"
+
+
+def test_extract_text_from_contents_non_text():
+    """Test extracting text ignores non-text contents."""
+    contents = [
+        Content.from_text("Hello"),
+        Content.from_function_call(call_id="call_1", name="tool", arguments="{}"),
+    ]
+    result = extract_text_from_contents(contents)
+    assert result == "Hello"
+
+
+def test_agui_to_agent_framework_with_tool_calls():
+    """Test converting AG-UI message with tool_calls."""
+    messages = [
+        {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {
+                    "id": "call_123",
+                    "type": "function",
+                    "function": {"name": "get_weather", "arguments": '{"city": "NYC"}'},
+                }
+            ],
+        }
+    ]
+
+    result = agui_messages_to_agent_framework(messages)
+
+    assert len(result) == 1
+    assert len(result[0].contents) == 1
+    assert result[0].contents[0].type == "function_call"
+    assert result[0].contents[0].name == "get_weather"
+
+
+def test_agui_to_agent_framework_tool_result():
+    """Test converting AG-UI tool result message."""
+    messages = [
+        {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {
+                    "id": "call_123",
+                    "type": "function",
+                    "function": {"name": "get_weather", "arguments": "{}"},
+                }
+            ],
+        },
+        {
+            "role": "tool",
+            "content": "Sunny",
+            "toolCallId": "call_123",
+        },
+    ]
+
+    result = agui_messages_to_agent_framework(messages)
+
+    assert len(result) == 2
+    # Second message should be tool result
+    tool_msg = result[1]
+    assert tool_msg.role == Role.TOOL
+    assert tool_msg.contents[0].type == "function_result"
+    assert tool_msg.contents[0].result == "Sunny"
+
+
+def test_agui_messages_to_snapshot_format_empty():
+    """Test converting empty messages to snapshot format."""
+    result = agui_messages_to_snapshot_format([])
+    assert result == []
+
+
+def test_agui_messages_to_snapshot_format_basic():
+    """Test converting messages to snapshot format."""
+    messages = [
+        {"role": "user", "content": "Hello", "id": "msg_1"},
+        {"role": "assistant", "content": "Hi there", "id": "msg_2"},
+    ]
+
+    result = agui_messages_to_snapshot_format(messages)
+
+    assert len(result) == 2
+    assert result[0]["role"] == "user"
+    assert result[0]["content"] == "Hello"
+    assert result[1]["role"] == "assistant"
+    assert result[1]["content"] == "Hi there"
@@ -1,6 +1,6 @@
 # Copyright (c) Microsoft. All rights reserved.

-from agent_framework import ChatMessage, FunctionCallContent, FunctionResultContent, TextContent
+from agent_framework import ChatMessage, Content

 from agent_framework_ag_ui._message_adapters import _deduplicate_messages, _sanitize_tool_history

@@ -10,7 +10,7 @@ def test_sanitize_tool_history_injects_confirm_changes_result() -> None:
        ChatMessage(
            role="assistant",
            contents=[
-                FunctionCallContent(
+                Content.from_function_call(
                    name="confirm_changes",
                    call_id="call_confirm_123",
                    arguments='{"changes": "test"}',
@@ -19,7 +19,7 @@ def test_sanitize_tool_history_injects_confirm_changes_result() -> None:
        ),
        ChatMessage(
            role="user",
-            contents=[TextContent(text='{"accepted": true}')],
+            contents=[Content.from_text(text='{"accepted": true}')],
        ),
    ]

@@ -37,11 +37,11 @@ def test_deduplicate_messages_prefers_non_empty_tool_results() -> None:
    messages = [
        ChatMessage(
            role="tool",
-            contents=[FunctionResultContent(call_id="call1", result="")],
+            contents=[Content.from_function_result(call_id="call1", result="")],
        ),
        ChatMessage(
            role="tool",
-            contents=[FunctionResultContent(call_id="call1", result="result data")],
+            contents=[Content.from_function_result(call_id="call1", result="result data")],
        ),
    ]

@@ -1,307 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Tests for AG-UI orchestrators."""
-
-from collections.abc import AsyncGenerator
-from typing import Any
-from unittest.mock import MagicMock
-
-from ag_ui.core import BaseEvent, RunFinishedEvent
-from agent_framework import (
-    AgentResponseUpdate,
-    AgentThread,
-    BaseChatClient,
-    ChatAgent,
-    ChatResponseUpdate,
-    FunctionInvocationConfiguration,
-    TextContent,
-    ai_function,
-)
-
-from agent_framework_ag_ui._agent import AgentConfig
-from agent_framework_ag_ui._orchestrators import DefaultOrchestrator, ExecutionContext
-
-
-@ai_function
-def server_tool() -> str:
-    """Server-executable tool."""
-    return "server"
-
-
-def _create_mock_chat_agent(
-    tools: list[Any] | None = None,
-    response_format: Any = None,
-    capture_tools: list[Any] | None = None,
-    capture_messages: list[Any] | None = None,
-) -> ChatAgent:
-    """Create a ChatAgent with mocked chat client for testing.
-
-    Args:
-        tools: Tools to configure on the agent.
-        response_format: Response format to configure.
-        capture_tools: If provided, tools passed to run_stream will be appended here.
-        capture_messages: If provided, messages passed to run_stream will be appended here.
-    """
-    mock_chat_client = MagicMock(spec=BaseChatClient)
-    mock_chat_client.function_invocation_configuration = FunctionInvocationConfiguration()
-
-    agent = ChatAgent(
-        chat_client=mock_chat_client,
-        tools=tools or [server_tool],
-        response_format=response_format,
-    )
-
-    # Create a mock run_stream that captures parameters and yields a simple response
-    async def mock_run_stream(
-        messages: list[Any],
-        *,
-        #     thread: AgentThread,
-        #     tools: list[Any] | None = None,
-        #     **kwargs: Any,
-        # ) -> AsyncGenerator[AgentRunResponseUpdate, None]:
-        #     self.seen_tools = tools
-        #     yield AgentRunResponseUpdate(
-        #         contents=[TextContent(text="ok")],
-        #         role="assistant",
-        #         response_id=thread.metadata.get("ag_ui_run_id"),  # type: ignore[attr-defined] (metadata always created in orchestrator)
-        #         raw_representation=ChatResponseUpdate(
-        #             contents=[TextContent(text="ok")],
-        #             conversation_id=thread.metadata.get("ag_ui_thread_id"),  # type: ignore[attr-defined] (metadata always created in orchestrator)
-        #             response_id=thread.metadata.get("ag_ui_run_id"),  # type: ignore[attr-defined] (metadata always created in orchestrator)
-        #         ),
-        #     )
-        thread: AgentThread,
-        tools: list[Any] | None = None,
-        **kwargs: Any,
-    ) -> AsyncGenerator[AgentResponseUpdate, None]:
-        if capture_tools is not None and tools is not None:
-            capture_tools.extend(tools)
-        if capture_messages is not None:
-            capture_messages.extend(messages)
-        yield AgentResponseUpdate(
-            contents=[TextContent(text="ok")],
-            role="assistant",
-            response_id=thread.metadata.get("ag_ui_run_id"),  # type: ignore[attr-defined] (metadata always created in orchestrator)
-            raw_representation=ChatResponseUpdate(
-                contents=[TextContent(text="ok")],
-                conversation_id=thread.metadata.get("ag_ui_thread_id"),  # type: ignore[attr-defined] (metadata always created in orchestrator)
-                response_id=thread.metadata.get("ag_ui_run_id"),  # type: ignore[attr-defined] (metadata always created in orchestrator)
-            ),
-        )
-
-    # Patch the run_stream method
-    agent.run_stream = mock_run_stream  # type: ignore[method-assign]
-
-    return agent
-
-
-async def test_default_orchestrator_merges_client_tools() -> None:
-    """Client tool declarations are merged with server tools before running agent."""
-    captured_tools: list[Any] = []
-    agent = _create_mock_chat_agent(tools=[server_tool], capture_tools=captured_tools)
-    orchestrator = DefaultOrchestrator()
-
-    input_data = {
-        "messages": [
-            {
-                "role": "user",
-                "content": [{"type": "input_text", "text": "Hello"}],
-            }
-        ],
-        "tools": [
-            {
-                "name": "get_weather",
-                "description": "Client weather lookup.",
-                "parameters": {
-                    "type": "object",
-                    "properties": {"location": {"type": "string"}},
-                    "required": ["location"],
-                },
-            }
-        ],
-    }
-
-    context = ExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-
-    events = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    assert len(captured_tools) > 0
-    tool_names = [getattr(tool, "name", "?") for tool in captured_tools]
-    assert "server_tool" in tool_names
-    assert "get_weather" in tool_names
-    assert agent.chat_client.function_invocation_configuration.additional_tools
-
-
-async def test_default_orchestrator_with_camel_case_ids() -> None:
-    """Client tool is able to extract camelCase IDs."""
-    agent = _create_mock_chat_agent()
-    orchestrator = DefaultOrchestrator()
-
-    input_data = {
-        "runId": "test-camelcase-runid",
-        "threadId": "test-camelcase-threadid",
-        "messages": [
-            {
-                "role": "user",
-                "content": [{"type": "input_text", "text": "Hello"}],
-            }
-        ],
-        "tools": [],
-    }
-
-    context = ExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-
-    events = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # assert the last event has the expected run_id and thread_id
-    assert isinstance(events[-1], RunFinishedEvent)
-    last_event = events[-1]
-    assert last_event.run_id == "test-camelcase-runid"
-    assert last_event.thread_id == "test-camelcase-threadid"
-
-
-async def test_default_orchestrator_with_snake_case_ids() -> None:
-    """Client tool is able to extract snake_case IDs."""
-    agent = _create_mock_chat_agent()
-    orchestrator = DefaultOrchestrator()
-
-    input_data = {
-        "run_id": "test-snakecase-runid",
-        "thread_id": "test-snakecase-threadid",
-        "messages": [
-            {
-                "role": "user",
-                "content": [{"type": "input_text", "text": "Hello"}],
-            }
-        ],
-        "tools": [],
-    }
-
-    context = ExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-
-    events: list[BaseEvent] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # assert the last event has the expected run_id and thread_id
-    assert isinstance(events[-1], RunFinishedEvent)
-    last_event = events[-1]
-    assert last_event.run_id == "test-snakecase-runid"
-    assert last_event.thread_id == "test-snakecase-threadid"
-
-
-async def test_state_context_injected_when_tool_call_state_mismatch() -> None:
-    """State context should be injected when current state differs from tool call args."""
-    captured_messages: list[Any] = []
-    agent = _create_mock_chat_agent(tools=[], capture_messages=captured_messages)
-    orchestrator = DefaultOrchestrator()
-
-    tool_recipe = {"title": "Salad", "special_preferences": []}
-    current_recipe = {"title": "Salad", "special_preferences": ["Vegetarian"]}
-
-    input_data = {
-        "state": {"recipe": current_recipe},
-        "messages": [
-            {"role": "system", "content": "Instructions"},
-            {
-                "role": "assistant",
-                "tool_calls": [
-                    {
-                        "id": "call_1",
-                        "type": "function",
-                        "function": {"name": "update_recipe", "arguments": {"recipe": tool_recipe}},
-                    }
-                ],
-            },
-            {"role": "user", "content": "What are the dietary preferences?"},
-        ],
-    }
-
-    context = ExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(
-            state_schema={"recipe": {"type": "object"}},
-            predict_state_config={"recipe": {"tool": "update_recipe", "tool_argument": "recipe"}},
-            require_confirmation=False,
-        ),
-    )
-
-    async for _event in orchestrator.run(context):
-        pass
-
-    assert len(captured_messages) > 0
-    state_messages = []
-    for msg in captured_messages:
-        role_value = msg.role.value if hasattr(msg.role, "value") else str(msg.role)
-        if role_value != "system":
-            continue
-        for content in msg.contents or []:
-            if isinstance(content, TextContent) and content.text.startswith("Current state of the application:"):
-                state_messages.append(content.text)
-    assert state_messages
-    assert "Vegetarian" in state_messages[0]
-
-
-async def test_state_context_not_injected_when_tool_call_matches_state() -> None:
-    """State context should be skipped when tool call args match current state."""
-    captured_messages: list[Any] = []
-    agent = _create_mock_chat_agent(tools=[], capture_messages=captured_messages)
-    orchestrator = DefaultOrchestrator()
-
-    input_data = {
-        "messages": [
-            {"role": "system", "content": "Instructions"},
-            {
-                "role": "assistant",
-                "tool_calls": [
-                    {
-                        "id": "call_1",
-                        "type": "function",
-                        "function": {"name": "update_recipe", "arguments": {"recipe": {}}},
-                    }
-                ],
-            },
-            {"role": "user", "content": "What are the dietary preferences?"},
-        ],
-    }
-
-    context = ExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(
-            state_schema={"recipe": {"type": "object"}},
-            predict_state_config={"recipe": {"tool": "update_recipe", "tool_argument": "recipe"}},
-            require_confirmation=False,
-        ),
-    )
-
-    async for _event in orchestrator.run(context):
-        pass
-
-    assert len(captured_messages) > 0
-    state_messages = []
-    for msg in captured_messages:
-        role_value = msg.role.value if hasattr(msg.role, "value") else str(msg.role)
-        if role_value != "system":
-            continue
-        for content in msg.contents or []:
-            if isinstance(content, TextContent) and content.text.startswith("Current state of the application:"):
-                state_messages.append(content.text)
-    assert not state_messages
@@ -1,878 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Comprehensive tests for orchestrator coverage."""
-
-import sys
-from collections.abc import AsyncGenerator
-from pathlib import Path
-from types import SimpleNamespace
-from typing import Any
-
-from agent_framework import (
-    AgentResponseUpdate,
-    ChatMessage,
-    TextContent,
-    ai_function,
-)
-from pydantic import BaseModel
-
-from agent_framework_ag_ui._agent import AgentConfig
-from agent_framework_ag_ui._orchestrators import DefaultOrchestrator, HumanInTheLoopOrchestrator
-
-sys.path.insert(0, str(Path(__file__).parent))
-from utils_test_ag_ui import StubAgent, TestExecutionContext
-
-
-@ai_function(approval_mode="always_require")
-def approval_tool(param: str) -> str:
-    """Tool requiring approval."""
-    return f"executed: {param}"
-
-
-DEFAULT_OPTIONS: dict[str, Any] = {"tools": [approval_tool], "response_format": None}
-
-
-async def test_human_in_the_loop_json_decode_error() -> None:
-    """Test HumanInTheLoopOrchestrator handles invalid JSON in tool result."""
-    orchestrator = HumanInTheLoopOrchestrator()
-
-    input_data: dict[str, Any] = {
-        "messages": [
-            {
-                "role": "tool",
-                "content": [{"type": "text", "text": "not valid json {"}],
-            }
-        ],
-    }
-
-    messages = [
-        ChatMessage(
-            role="tool",
-            contents=[TextContent(text="not valid json {")],
-            additional_properties={"is_tool_result": True},
-        )
-    ]
-
-    agent = StubAgent(
-        default_options={"tools": [approval_tool], "response_format": None},
-        updates=[AgentResponseUpdate(contents=[TextContent(text="response")], role="assistant")],
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-    context.set_messages(messages, normalize=False)
-
-    assert orchestrator.can_handle(context)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should emit RunErrorEvent for invalid JSON
-    error_events: list[Any] = [e for e in events if e.type == "RUN_ERROR"]
-    assert len(error_events) == 1
-    assert "Invalid tool result format" in error_events[0].message
-
-
-async def test_sanitize_tool_history_confirm_changes() -> None:
-    """Test sanitize_tool_history logic for confirm_changes synthetic result."""
-    from agent_framework import ChatMessage, FunctionCallContent, TextContent
-
-    # Create messages that will trigger confirm_changes synthetic result injection
-    messages = [
-        ChatMessage(
-            role="assistant",
-            contents=[
-                FunctionCallContent(
-                    name="confirm_changes",
-                    call_id="call_confirm_123",
-                    arguments='{"changes": "test"}',
-                )
-            ],
-        ),
-        ChatMessage(
-            role="user",
-            contents=[TextContent(text='{"accepted": true}')],
-        ),
-    ]
-
-    # The sanitize_tool_history function is internal to DefaultOrchestrator.run
-    # We'll test it indirectly by checking the orchestrator processes it correctly
-    orchestrator = DefaultOrchestrator()
-
-    # Use pre-constructed ChatMessage objects to bypass message adapter
-    input_data: dict[str, Any] = {"messages": []}
-
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-    # Override the messages property to use our pre-constructed messages
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Agent should receive synthetic tool result
-    assert len(agent.messages_received) > 0
-    tool_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "tool"
-    ]
-    assert len(tool_messages) == 1
-    assert str(tool_messages[0].contents[0].call_id) == "call_confirm_123"
-    assert tool_messages[0].contents[0].result == "Confirmed"
-
-
-async def test_sanitize_tool_history_orphaned_tool_result() -> None:
-    """Test sanitize_tool_history removes orphaned tool results."""
-    from agent_framework import ChatMessage, FunctionResultContent, TextContent
-
-    # Tool result without preceding assistant tool call
-    messages = [
-        ChatMessage(
-            role="tool",
-            contents=[FunctionResultContent(call_id="orphan_123", result="orphaned data")],
-        ),
-        ChatMessage(
-            role="user",
-            contents=[TextContent(text="Hello")],
-        ),
-    ]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": []}
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Orphaned tool result should be filtered out
-    tool_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "tool"
-    ]
-    assert len(tool_messages) == 0
-
-
-async def test_orphaned_tool_result_sanitization() -> None:
-    """Test that orphaned tool results are filtered out."""
-    orchestrator = DefaultOrchestrator()
-
-    input_data: dict[str, Any] = {
-        "messages": [
-            {
-                "role": "tool",
-                "content": [{"type": "tool_result", "tool_call_id": "orphan_123", "content": "result"}],
-            },
-            {
-                "role": "user",
-                "content": [{"type": "text", "text": "Hello"}],
-            },
-        ],
-    }
-
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Orphaned tool result should be filtered, only user message remains
-    tool_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "tool"
-    ]
-    assert len(tool_messages) == 0
-
-
-async def test_deduplicate_messages_empty_tool_results() -> None:
-    """Test deduplicate_messages prefers non-empty tool results."""
-    from agent_framework import ChatMessage, FunctionCallContent, FunctionResultContent
-
-    messages = [
-        ChatMessage(
-            role="assistant",
-            contents=[FunctionCallContent(name="test_tool", call_id="call_789", arguments="{}")],
-        ),
-        ChatMessage(
-            role="tool",
-            contents=[FunctionResultContent(call_id="call_789", result="")],
-        ),
-        ChatMessage(
-            role="tool",
-            contents=[FunctionResultContent(call_id="call_789", result="real data")],
-        ),
-    ]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": []}
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should have only one tool result with actual data
-    tool_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "tool"
-    ]
-    assert len(tool_messages) == 1
-    assert tool_messages[0].contents[0].result == "real data"
-
-
-async def test_deduplicate_messages_duplicate_assistant_tool_calls() -> None:
-    """Test deduplicate_messages removes duplicate assistant tool call messages."""
-    from agent_framework import ChatMessage, FunctionCallContent, FunctionResultContent
-
-    messages = [
-        ChatMessage(
-            role="assistant",
-            contents=[FunctionCallContent(name="test_tool", call_id="call_abc", arguments="{}")],
-        ),
-        ChatMessage(
-            role="assistant",
-            contents=[FunctionCallContent(name="test_tool", call_id="call_abc", arguments="{}")],
-        ),
-        ChatMessage(
-            role="tool",
-            contents=[FunctionResultContent(call_id="call_abc", result="result")],
-        ),
-    ]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": []}
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should have only one assistant message
-    assistant_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "assistant"
-    ]
-    assert len(assistant_messages) == 1
-
-
-async def test_deduplicate_messages_duplicate_system_messages() -> None:
-    """Test that deduplication logic is invoked for system messages."""
-    from agent_framework import ChatMessage, TextContent
-
-    messages = [
-        ChatMessage(
-            role="system",
-            contents=[TextContent(text="You are a helpful assistant.")],
-        ),
-        ChatMessage(
-            role="system",
-            contents=[TextContent(text="You are a helpful assistant.")],
-        ),
-        ChatMessage(
-            role="user",
-            contents=[TextContent(text="Hello")],
-        ),
-    ]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": []}
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Deduplication uses hash() which may not deduplicate identical content
-    # This test verifies deduplication logic runs without errors
-    system_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "system"
-    ]
-    # At least one system message should be present
-    assert len(system_messages) >= 1
-
-
-async def test_state_context_injection() -> None:
-    """Test state context message injection for first request."""
-    orchestrator = DefaultOrchestrator()
-
-    input_data: dict[str, Any] = {
-        "messages": [
-            {
-                "role": "user",
-                "content": [{"type": "text", "text": "Hello"}],
-            }
-        ],
-        "state": {"items": ["apple", "banana"]},
-    }
-
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(state_schema={"items": {"type": "array"}}),
-    )
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should inject system message with current state
-    system_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "system"
-    ]
-    assert len(system_messages) == 1
-    assert "apple" in system_messages[0].contents[0].text
-    assert "banana" in system_messages[0].contents[0].text
-
-
-async def test_state_context_injection_with_tool_calls_and_input_state() -> None:
-    """Test state context is injected when state is provided, even with tool calls."""
-    from agent_framework import ChatMessage, FunctionCallContent, FunctionResultContent, TextContent
-
-    messages = [
-        ChatMessage(
-            role="assistant",
-            contents=[FunctionCallContent(name="get_weather", call_id="call_xyz", arguments="{}")],
-        ),
-        ChatMessage(
-            role="tool",
-            contents=[FunctionResultContent(call_id="call_xyz", result="sunny")],
-        ),
-        ChatMessage(
-            role="user",
-            contents=[TextContent(text="Thanks")],
-        ),
-    ]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": [], "state": {"weather": "sunny"}}
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(state_schema={"weather": {"type": "string"}}),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should inject state context system message because input state is provided
-    system_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "system"
-    ]
-    assert len(system_messages) == 1
-
-
-async def test_structured_output_processing() -> None:
-    """Test structured output extraction and state update."""
-
-    class RecipeState(BaseModel):
-        ingredients: list[str]
-        message: str
-
-    orchestrator = DefaultOrchestrator()
-
-    input_data: dict[str, Any] = {
-        "messages": [
-            {
-                "role": "user",
-                "content": [{"type": "text", "text": "Add tomato"}],
-            }
-        ],
-    }
-
-    # Agent with structured output
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-        updates=[
-            AgentResponseUpdate(
-                contents=[TextContent(text='{"ingredients": ["tomato"], "message": "Added tomato"}')],
-                role="assistant",
-            )
-        ],
-    )
-    agent.default_options["response_format"] = RecipeState
-
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(state_schema={"ingredients": {"type": "array"}}),
-    )
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should emit StateSnapshotEvent with ingredients
-    state_events: list[Any] = [e for e in events if e.type == "STATE_SNAPSHOT"]
-    assert len(state_events) >= 1
-
-    # Should emit TextMessage with message field
-    text_content_events: list[Any] = [e for e in events if e.type == "TEXT_MESSAGE_CONTENT"]
-    assert len(text_content_events) >= 1
-    assert any("Added tomato" in e.delta for e in text_content_events)
-
-
-async def test_duplicate_client_tools_filtered() -> None:
-    """Test that client tools duplicating server tools are filtered out."""
-
-    @ai_function
-    def get_weather(location: str) -> str:
-        """Get weather for location."""
-        return f"Weather in {location}"
-
-    orchestrator = DefaultOrchestrator()
-
-    input_data: dict[str, Any] = {
-        "messages": [
-            {
-                "role": "user",
-                "content": [{"type": "text", "text": "Hello"}],
-            }
-        ],
-        "tools": [
-            {
-                "name": "get_weather",
-                "description": "Client weather tool.",
-                "parameters": {
-                    "type": "object",
-                    "properties": {"location": {"type": "string"}},
-                    "required": ["location"],
-                },
-            }
-        ],
-    }
-
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    agent.default_options["tools"] = [get_weather]
-
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # tools parameter should not be passed since client tool duplicates server tool
-    assert agent.tools_received is None
-
-
-async def test_unique_client_tools_merged() -> None:
-    """Test that unique client tools are merged with server tools."""
-
-    @ai_function
-    def server_tool() -> str:
-        """Server tool."""
-        return "server"
-
-    orchestrator = DefaultOrchestrator()
-
-    input_data: dict[str, Any] = {
-        "messages": [
-            {
-                "role": "user",
-                "content": [{"type": "text", "text": "Hello"}],
-            }
-        ],
-        "tools": [
-            {
-                "name": "client_tool",
-                "description": "Unique client tool.",
-                "parameters": {
-                    "type": "object",
-                    "properties": {"param": {"type": "string"}},
-                    "required": ["param"],
-                },
-            }
-        ],
-    }
-
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    agent.default_options["tools"] = [server_tool]
-
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # tools parameter should be passed with both server and client tools
-    assert agent.tools_received is not None
-    tool_names = [getattr(tool, "name", None) for tool in agent.tools_received]
-    assert "server_tool" in tool_names
-    assert "client_tool" in tool_names
-
-
-async def test_empty_messages_handling() -> None:
-    """Test orchestrator handles empty message list gracefully."""
-    orchestrator = DefaultOrchestrator()
-
-    input_data: dict[str, Any] = {"messages": []}
-
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should emit run lifecycle events but not call agent
-    assert len(agent.messages_received) == 0
-    run_started = [e for e in events if e.type == "RUN_STARTED"]
-    run_finished = [e for e in events if e.type == "RUN_FINISHED"]
-    assert len(run_started) == 1
-    assert len(run_finished) == 1
-
-
-async def test_all_messages_filtered_handling() -> None:
-    """Test orchestrator handles case where all messages are filtered out."""
-    orchestrator = DefaultOrchestrator()
-
-    input_data: dict[str, Any] = {
-        "messages": [
-            {
-                "role": "tool",
-                "content": [{"type": "tool_result", "tool_call_id": "orphan", "content": "data"}],
-            }
-        ]
-    }
-
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should finish without calling agent
-    assert len(agent.messages_received) == 0
-    run_finished = [e for e in events if e.type == "RUN_FINISHED"]
-    assert len(run_finished) == 1
-
-
-async def test_confirm_changes_with_invalid_json_fallback() -> None:
-    """Test confirm_changes with invalid JSON falls back to normal processing."""
-    from agent_framework import ChatMessage, FunctionCallContent, TextContent
-
-    messages = [
-        ChatMessage(
-            role="assistant",
-            contents=[
-                FunctionCallContent(
-                    name="confirm_changes",
-                    call_id="call_confirm_invalid",
-                    arguments='{"changes": "test"}',
-                )
-            ],
-        ),
-        ChatMessage(
-            role="user",
-            contents=[TextContent(text="invalid json {")],
-        ),
-    ]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": []}
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Invalid JSON should fall back - user message should be included
-    user_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "user"
-    ]
-    assert len(user_messages) == 1
-
-
-async def test_confirm_changes_closes_active_message_before_finish() -> None:
-    """Confirm-changes flow closes any active text message before run finishes."""
-    from ag_ui.core import TextMessageEndEvent, TextMessageStartEvent
-    from agent_framework import FunctionCallContent, FunctionResultContent
-
-    updates = [
-        AgentResponseUpdate(
-            contents=[
-                FunctionCallContent(
-                    name="write_document_local",
-                    call_id="call_1",
-                    arguments='{"document": "Draft"}',
-                )
-            ]
-        ),
-        AgentResponseUpdate(contents=[FunctionResultContent(call_id="call_1", result="Done")]),
-    ]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": [{"role": "user", "content": "Start"}]}
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-        updates=updates,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(
-            predict_state_config={"document": {"tool": "write_document_local", "tool_argument": "document"}},
-            require_confirmation=True,
-        ),
-    )
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    start_events = [e for e in events if isinstance(e, TextMessageStartEvent)]
-    end_events = [e for e in events if isinstance(e, TextMessageEndEvent)]
-    assert len(start_events) == 1
-    assert len(end_events) == 1
-    assert end_events[0].message_id == start_events[0].message_id
-
-    end_index = events.index(end_events[0])
-    finished_index = events.index([e for e in events if e.type == "RUN_FINISHED"][0])
-    assert end_index < finished_index
-
-
-async def test_tool_result_kept_when_call_id_matches() -> None:
-    """Test tool result is kept when call_id matches pending tool calls."""
-    from agent_framework import ChatMessage, FunctionCallContent, FunctionResultContent
-
-    messages = [
-        ChatMessage(
-            role="assistant",
-            contents=[FunctionCallContent(name="get_data", call_id="call_match", arguments="{}")],
-        ),
-        ChatMessage(
-            role="tool",
-            contents=[FunctionResultContent(call_id="call_match", result="data")],
-        ),
-    ]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": []}
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Tool result should be kept
-    tool_messages = [
-        msg
-        for msg in agent.messages_received
-        if (msg.role.value if hasattr(msg.role, "value") else str(msg.role)) == "tool"
-    ]
-    assert len(tool_messages) == 1
-    assert tool_messages[0].contents[0].result == "data"
-
-
-async def test_agent_protocol_fallback_paths() -> None:
-    """Test fallback paths for non-ChatAgent implementations."""
-
-    class CustomAgent:
-        """Custom agent without ChatAgent type."""
-
-        def __init__(self) -> None:
-            self.default_options: dict[str, Any] = {"tools": [], "response_format": None}
-            self.chat_client = SimpleNamespace(function_invocation_configuration=SimpleNamespace())
-            self.messages_received: list[Any] = []
-
-        async def run_stream(
-            self,
-            messages: list[Any],
-            *,
-            thread: Any = None,
-            tools: list[Any] | None = None,
-            **kwargs: Any,
-        ) -> AsyncGenerator[AgentResponseUpdate, None]:
-            self.messages_received = messages
-            yield AgentResponseUpdate(contents=[TextContent(text="response")], role="assistant")
-
-    from agent_framework import ChatMessage, TextContent
-
-    messages = [ChatMessage(role="user", contents=[TextContent(text="Hello")])]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": []}
-    agent = CustomAgent()
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,  # type: ignore
-        config=AgentConfig(),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should work with custom agent implementation
-    assert len(agent.messages_received) > 0
-
-
-async def test_initial_state_snapshot_with_array_schema() -> None:
-    """Test state initialization with array type schema."""
-    from agent_framework import ChatMessage, TextContent
-
-    messages = [ChatMessage(role="user", contents=[TextContent(text="Hello")])]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": [], "state": {}}
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(state_schema={"items": {"type": "array"}}),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Should emit state snapshot with empty array for items
-    state_events: list[Any] = [e for e in events if e.type == "STATE_SNAPSHOT"]
-    assert len(state_events) >= 1
-
-
-async def test_response_format_skip_text_content() -> None:
-    """Test that response_format causes skip_text_content to be set."""
-
-    class OutputModel(BaseModel):
-        result: str
-
-    from agent_framework import ChatMessage, TextContent
-
-    messages = [ChatMessage(role="user", contents=[TextContent(text="Hello")])]
-
-    orchestrator = DefaultOrchestrator()
-    input_data: dict[str, Any] = {"messages": []}
-
-    agent = StubAgent(
-        default_options=DEFAULT_OPTIONS,
-    )
-    agent.default_options["response_format"] = OutputModel
-
-    context = TestExecutionContext(
-        input_data=input_data,
-        agent=agent,
-        config=AgentConfig(),
-    )
-    context.set_messages(messages)
-
-    events: list[Any] = []
-    async for event in orchestrator.run(context):
-        events.append(event)
-
-    # Test passes if no errors occur - verifies response_format code path
-    assert len(events) > 0
@@ -0,0 +1,320 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Tests for predictive state handling."""
+
+from ag_ui.core import StateDeltaEvent
+
+from agent_framework_ag_ui._orchestration._predictive_state import PredictiveStateHandler
+
+
+class TestPredictiveStateHandlerInit:
+    """Tests for PredictiveStateHandler initialization."""
+
+    def test_default_init(self):
+        """Initializes with default values."""
+        handler = PredictiveStateHandler()
+        assert handler.predict_state_config == {}
+        assert handler.current_state == {}
+        assert handler.streaming_tool_args == ""
+        assert handler.last_emitted_state == {}
+        assert handler.state_delta_count == 0
+        assert handler.pending_state_updates == {}
+
+    def test_init_with_config(self):
+        """Initializes with provided config."""
+        config = {"document": {"tool": "write_doc", "tool_argument": "content"}}
+        state = {"document": "initial"}
+        handler = PredictiveStateHandler(predict_state_config=config, current_state=state)
+        assert handler.predict_state_config == config
+        assert handler.current_state == state
+
+
+class TestResetStreaming:
+    """Tests for reset_streaming method."""
+
+    def test_resets_streaming_state(self):
+        """Resets streaming-related state."""
+        handler = PredictiveStateHandler()
+        handler.streaming_tool_args = "some accumulated args"
+        handler.state_delta_count = 5
+
+        handler.reset_streaming()
+
+        assert handler.streaming_tool_args == ""
+        assert handler.state_delta_count == 0
+
+
+class TestExtractStateValue:
+    """Tests for extract_state_value method."""
+
+    def test_no_config(self):
+        """Returns None when no config."""
+        handler = PredictiveStateHandler()
+        result = handler.extract_state_value("some_tool", {"arg": "value"})
+        assert result is None
+
+    def test_no_args(self):
+        """Returns None when args is None."""
+        handler = PredictiveStateHandler(predict_state_config={"key": {"tool": "tool", "tool_argument": "arg"}})
+        result = handler.extract_state_value("tool", None)
+        assert result is None
+
+    def test_empty_args(self):
+        """Returns None when args is empty string."""
+        handler = PredictiveStateHandler(predict_state_config={"key": {"tool": "tool", "tool_argument": "arg"}})
+        result = handler.extract_state_value("tool", "")
+        assert result is None
+
+    def test_tool_not_in_config(self):
+        """Returns None when tool not in config."""
+        handler = PredictiveStateHandler(predict_state_config={"key": {"tool": "other_tool", "tool_argument": "arg"}})
+        result = handler.extract_state_value("some_tool", {"arg": "value"})
+        assert result is None
+
+    def test_extracts_specific_argument(self):
+        """Extracts value from specific tool argument."""
+        handler = PredictiveStateHandler(
+            predict_state_config={"document": {"tool": "write_doc", "tool_argument": "content"}}
+        )
+        result = handler.extract_state_value("write_doc", {"content": "Hello world"})
+        assert result == ("document", "Hello world")
+
+    def test_extracts_with_wildcard(self):
+        """Extracts entire args with * wildcard."""
+        handler = PredictiveStateHandler(predict_state_config={"data": {"tool": "update_data", "tool_argument": "*"}})
+        args = {"key1": "value1", "key2": "value2"}
+        result = handler.extract_state_value("update_data", args)
+        assert result == ("data", args)
+
+    def test_extracts_from_json_string(self):
+        """Extracts value from JSON string args."""
+        handler = PredictiveStateHandler(
+            predict_state_config={"document": {"tool": "write_doc", "tool_argument": "content"}}
+        )
+        result = handler.extract_state_value("write_doc", '{"content": "Hello world"}')
+        assert result == ("document", "Hello world")
+
+    def test_argument_not_in_args(self):
+        """Returns None when tool_argument not in args."""
+        handler = PredictiveStateHandler(
+            predict_state_config={"document": {"tool": "write_doc", "tool_argument": "content"}}
+        )
+        result = handler.extract_state_value("write_doc", {"other": "value"})
+        assert result is None
+
+
+class TestIsPredictiveTool:
+    """Tests for is_predictive_tool method."""
+
+    def test_none_tool_name(self):
+        """Returns False for None tool name."""
+        handler = PredictiveStateHandler(predict_state_config={"key": {"tool": "some_tool", "tool_argument": "arg"}})
+        assert handler.is_predictive_tool(None) is False
+
+    def test_no_config(self):
+        """Returns False when no config."""
+        handler = PredictiveStateHandler()
+        assert handler.is_predictive_tool("some_tool") is False
+
+    def test_tool_in_config(self):
+        """Returns True when tool is in config."""
+        handler = PredictiveStateHandler(predict_state_config={"key": {"tool": "some_tool", "tool_argument": "arg"}})
+        assert handler.is_predictive_tool("some_tool") is True
+
+    def test_tool_not_in_config(self):
+        """Returns False when tool not in config."""
+        handler = PredictiveStateHandler(predict_state_config={"key": {"tool": "other_tool", "tool_argument": "arg"}})
+        assert handler.is_predictive_tool("some_tool") is False
+
+
+class TestEmitStreamingDeltas:
+    """Tests for emit_streaming_deltas method."""
+
+    def test_no_tool_name(self):
+        """Returns empty list for None tool name."""
+        handler = PredictiveStateHandler(predict_state_config={"key": {"tool": "tool", "tool_argument": "arg"}})
+        result = handler.emit_streaming_deltas(None, '{"arg": "value"}')
+        assert result == []
+
+    def test_no_config(self):
+        """Returns empty list when no config."""
+        handler = PredictiveStateHandler()
+        result = handler.emit_streaming_deltas("some_tool", '{"arg": "value"}')
+        assert result == []
+
+    def test_accumulates_args(self):
+        """Accumulates argument chunks."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        handler.emit_streaming_deltas("write", '{"text')
+        handler.emit_streaming_deltas("write", '": "hello')
+        assert handler.streaming_tool_args == '{"text": "hello'
+
+    def test_emits_delta_on_complete_json(self):
+        """Emits delta when JSON is complete."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        events = handler.emit_streaming_deltas("write", '{"text": "hello"}')
+        assert len(events) == 1
+        assert isinstance(events[0], StateDeltaEvent)
+        assert events[0].delta[0]["path"] == "/doc"
+        assert events[0].delta[0]["value"] == "hello"
+        assert events[0].delta[0]["op"] == "replace"
+
+    def test_emits_delta_on_partial_json(self):
+        """Emits delta from partial JSON using regex."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        # First chunk - partial
+        events = handler.emit_streaming_deltas("write", '{"text": "hel')
+        assert len(events) == 1
+        assert events[0].delta[0]["value"] == "hel"
+
+    def test_does_not_emit_duplicate_deltas(self):
+        """Does not emit delta when value unchanged."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        # First emission
+        events1 = handler.emit_streaming_deltas("write", '{"text": "hello"}')
+        assert len(events1) == 1
+
+        # Reset and emit same value again
+        handler.streaming_tool_args = ""
+        events2 = handler.emit_streaming_deltas("write", '{"text": "hello"}')
+        assert len(events2) == 0  # No duplicate
+
+    def test_emits_delta_on_value_change(self):
+        """Emits delta when value changes."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        # First value
+        events1 = handler.emit_streaming_deltas("write", '{"text": "hello"}')
+        assert len(events1) == 1
+
+        # Reset and new value
+        handler.streaming_tool_args = ""
+        events2 = handler.emit_streaming_deltas("write", '{"text": "world"}')
+        assert len(events2) == 1
+        assert events2[0].delta[0]["value"] == "world"
+
+    def test_tracks_pending_updates(self):
+        """Tracks pending state updates."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        handler.emit_streaming_deltas("write", '{"text": "hello"}')
+        assert handler.pending_state_updates == {"doc": "hello"}
+
+
+class TestEmitPartialDeltas:
+    """Tests for _emit_partial_deltas method."""
+
+    def test_unescapes_newlines(self):
+        """Unescapes \\n in partial values."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        handler.streaming_tool_args = '{"text": "line1\\nline2'
+        events = handler._emit_partial_deltas("write")
+        assert len(events) == 1
+        assert events[0].delta[0]["value"] == "line1\nline2"
+
+    def test_handles_escaped_quotes_partially(self):
+        """Handles escaped quotes - regex stops at quote character."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        # The regex pattern [^"]* stops at ANY quote, including escaped ones.
+        # This is expected behavior for partial streaming - the full JSON
+        # will be parsed correctly when complete.
+        handler.streaming_tool_args = '{"text": "say \\"hi'
+        events = handler._emit_partial_deltas("write")
+        assert len(events) == 1
+        # Captures "say \" then the backslash gets converted to empty string
+        # by the replace("\\\\", "\\") first, then replace('\\"', '"')
+        # but since there's no closing quote, we get "say \"
+        # After .replace("\\\\", "\\") -> "say \"
+        # After .replace('\\"', '"') -> "say "  (but actually still "say \" due to order)
+        # The actual result: backslash is preserved since it's not a valid escape sequence
+        assert events[0].delta[0]["value"] == "say \\"
+
+    def test_unescapes_backslashes(self):
+        """Unescapes \\\\ in partial values."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        handler.streaming_tool_args = '{"text": "path\\\\to\\\\file'
+        events = handler._emit_partial_deltas("write")
+        assert len(events) == 1
+        assert events[0].delta[0]["value"] == "path\\to\\file"
+
+
+class TestEmitCompleteDeltas:
+    """Tests for _emit_complete_deltas method."""
+
+    def test_emits_for_matching_tool(self):
+        """Emits delta for tool matching config."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        events = handler._emit_complete_deltas("write", {"text": "content"})
+        assert len(events) == 1
+        assert events[0].delta[0]["value"] == "content"
+
+    def test_skips_non_matching_tool(self):
+        """Skips tools not matching config."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        events = handler._emit_complete_deltas("other_tool", {"text": "content"})
+        assert len(events) == 0
+
+    def test_handles_wildcard_argument(self):
+        """Handles * wildcard for entire args."""
+        handler = PredictiveStateHandler(predict_state_config={"data": {"tool": "update", "tool_argument": "*"}})
+        args = {"key1": "val1", "key2": "val2"}
+        events = handler._emit_complete_deltas("update", args)
+        assert len(events) == 1
+        assert events[0].delta[0]["value"] == args
+
+    def test_skips_missing_argument(self):
+        """Skips when tool_argument not in args."""
+        handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "text"}})
+        events = handler._emit_complete_deltas("write", {"other": "value"})
+        assert len(events) == 0
+
+
+class TestCreateDeltaEvent:
+    """Tests for _create_delta_event method."""
+
+    def test_creates_event(self):
+        """Creates StateDeltaEvent with correct structure."""
+        handler = PredictiveStateHandler()
+        event = handler._create_delta_event("key", "value")
+
+        assert isinstance(event, StateDeltaEvent)
+        assert event.delta[0]["op"] == "replace"
+        assert event.delta[0]["path"] == "/key"
+        assert event.delta[0]["value"] == "value"
+
+    def test_increments_count(self):
+        """Increments state_delta_count."""
+        handler = PredictiveStateHandler()
+        handler._create_delta_event("key", "value")
+        assert handler.state_delta_count == 1
+        handler._create_delta_event("key", "value2")
+        assert handler.state_delta_count == 2
+
+
+class TestApplyPendingUpdates:
+    """Tests for apply_pending_updates method."""
+
+    def test_applies_pending_to_current(self):
+        """Applies pending updates to current state."""
+        handler = PredictiveStateHandler(current_state={"existing": "value"})
+        handler.pending_state_updates = {"doc": "new content", "count": 5}
+
+        handler.apply_pending_updates()
+
+        assert handler.current_state == {"existing": "value", "doc": "new content", "count": 5}
+
+    def test_clears_pending_updates(self):
+        """Clears pending updates after applying."""
+        handler = PredictiveStateHandler()
+        handler.pending_state_updates = {"doc": "content"}
+
+        handler.apply_pending_updates()
+
+        assert handler.pending_state_updates == {}
+
+    def test_overwrites_existing_keys(self):
+        """Overwrites existing keys in current state."""
+        handler = PredictiveStateHandler(current_state={"doc": "old"})
+        handler.pending_state_updates = {"doc": "new"}
+
+        handler.apply_pending_updates()
+
+        assert handler.current_state["doc"] == "new"
@@ -0,0 +1,373 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Tests for _run.py helper functions and FlowState."""
+
+from agent_framework import ChatMessage, Content
+
+from agent_framework_ag_ui._run import (
+    FlowState,
+    _build_safe_metadata,
+    _create_state_context_message,
+    _has_only_tool_calls,
+    _inject_state_context,
+    _should_suppress_intermediate_snapshot,
+)
+
+
+class TestBuildSafeMetadata:
+    """Tests for _build_safe_metadata function."""
+
+    def test_none_metadata(self):
+        """Returns empty dict for None."""
+        result = _build_safe_metadata(None)
+        assert result == {}
+
+    def test_empty_metadata(self):
+        """Returns empty dict for empty dict."""
+        result = _build_safe_metadata({})
+        assert result == {}
+
+    def test_short_string_values(self):
+        """Preserves short string values."""
+        metadata = {"key1": "short", "key2": "value"}
+        result = _build_safe_metadata(metadata)
+        assert result == metadata
+
+    def test_truncates_long_strings(self):
+        """Truncates strings over 512 chars."""
+        long_value = "x" * 1000
+        metadata = {"key": long_value}
+        result = _build_safe_metadata(metadata)
+        assert len(result["key"]) == 512
+
+    def test_serializes_non_strings(self):
+        """Serializes non-string values to JSON."""
+        metadata = {"count": 42, "items": [1, 2, 3]}
+        result = _build_safe_metadata(metadata)
+        assert result["count"] == "42"
+        assert result["items"] == "[1, 2, 3]"
+
+    def test_truncates_serialized_values(self):
+        """Truncates serialized values over 512 chars."""
+        long_list = list(range(200))
+        metadata = {"data": long_list}
+        result = _build_safe_metadata(metadata)
+        assert len(result["data"]) == 512
+
+
+class TestHasOnlyToolCalls:
+    """Tests for _has_only_tool_calls function."""
+
+    def test_only_tool_calls(self):
+        """Returns True when only function_call content."""
+        contents = [
+            Content.from_function_call(call_id="call_1", name="tool1", arguments="{}"),
+        ]
+        assert _has_only_tool_calls(contents) is True
+
+    def test_tool_call_with_text(self):
+        """Returns False when both tool call and text."""
+        contents = [
+            Content.from_text("Some text"),
+            Content.from_function_call(call_id="call_1", name="tool1", arguments="{}"),
+        ]
+        assert _has_only_tool_calls(contents) is False
+
+    def test_only_text(self):
+        """Returns False when only text."""
+        contents = [Content.from_text("Just text")]
+        assert _has_only_tool_calls(contents) is False
+
+    def test_empty_contents(self):
+        """Returns False for empty contents."""
+        assert _has_only_tool_calls([]) is False
+
+    def test_tool_call_with_empty_text(self):
+        """Returns True when text content has empty text."""
+        contents = [
+            Content.from_text(""),
+            Content.from_function_call(call_id="call_1", name="tool1", arguments="{}"),
+        ]
+        assert _has_only_tool_calls(contents) is True
+
+
+class TestShouldSuppressIntermediateSnapshot:
+    """Tests for _should_suppress_intermediate_snapshot function."""
+
+    def test_no_tool_name(self):
+        """Returns False when no tool name."""
+        result = _should_suppress_intermediate_snapshot(
+            None, {"key": {"tool": "write_doc", "tool_argument": "content"}}, False
+        )
+        assert result is False
+
+    def test_no_config(self):
+        """Returns False when no config."""
+        result = _should_suppress_intermediate_snapshot("write_doc", None, False)
+        assert result is False
+
+    def test_confirmation_required(self):
+        """Returns False when confirmation is required."""
+        config = {"key": {"tool": "write_doc", "tool_argument": "content"}}
+        result = _should_suppress_intermediate_snapshot("write_doc", config, True)
+        assert result is False
+
+    def test_tool_not_in_config(self):
+        """Returns False when tool not in config."""
+        config = {"key": {"tool": "other_tool", "tool_argument": "content"}}
+        result = _should_suppress_intermediate_snapshot("write_doc", config, False)
+        assert result is False
+
+    def test_suppresses_predictive_tool(self):
+        """Returns True for predictive tool without confirmation."""
+        config = {"document": {"tool": "write_doc", "tool_argument": "content"}}
+        result = _should_suppress_intermediate_snapshot("write_doc", config, False)
+        assert result is True
+
+
+class TestFlowState:
+    """Tests for FlowState dataclass."""
+
+    def test_default_values(self):
+        """Tests default initialization."""
+        flow = FlowState()
+        assert flow.message_id is None
+        assert flow.tool_call_id is None
+        assert flow.tool_call_name is None
+        assert flow.waiting_for_approval is False
+        assert flow.current_state == {}
+        assert flow.accumulated_text == ""
+        assert flow.pending_tool_calls == []
+        assert flow.tool_calls_by_id == {}
+        assert flow.tool_results == []
+        assert flow.tool_calls_ended == set()
+
+    def test_get_tool_name(self):
+        """Tests get_tool_name method."""
+        flow = FlowState()
+        flow.tool_calls_by_id = {"call_123": {"function": {"name": "get_weather", "arguments": "{}"}}}
+
+        assert flow.get_tool_name("call_123") == "get_weather"
+        assert flow.get_tool_name("nonexistent") is None
+        assert flow.get_tool_name(None) is None
+
+    def test_get_tool_name_empty_name(self):
+        """Tests get_tool_name with empty name."""
+        flow = FlowState()
+        flow.tool_calls_by_id = {"call_123": {"function": {"name": "", "arguments": "{}"}}}
+
+        assert flow.get_tool_name("call_123") is None
+
+    def test_get_pending_without_end(self):
+        """Tests get_pending_without_end method."""
+        flow = FlowState()
+        flow.pending_tool_calls = [
+            {"id": "call_1", "function": {"name": "tool1"}},
+            {"id": "call_2", "function": {"name": "tool2"}},
+            {"id": "call_3", "function": {"name": "tool3"}},
+        ]
+        flow.tool_calls_ended = {"call_1", "call_3"}
+
+        result = flow.get_pending_without_end()
+        assert len(result) == 1
+        assert result[0]["id"] == "call_2"
+
+
+class TestCreateStateContextMessage:
+    """Tests for _create_state_context_message function."""
+
+    def test_no_state(self):
+        """Returns None when no state."""
+        result = _create_state_context_message({}, {"properties": {}})
+        assert result is None
+
+    def test_no_schema(self):
+        """Returns None when no schema."""
+        result = _create_state_context_message({"key": "value"}, {})
+        assert result is None
+
+    def test_creates_message(self):
+        """Creates state context message."""
+        from agent_framework import Role
+
+        state = {"document": "Hello world"}
+        schema = {"properties": {"document": {"type": "string"}}}
+
+        result = _create_state_context_message(state, schema)
+
+        assert result is not None
+        assert result.role == Role.SYSTEM
+        assert len(result.contents) == 1
+        assert "Hello world" in result.contents[0].text
+        assert "Current state" in result.contents[0].text
+
+
+class TestInjectStateContext:
+    """Tests for _inject_state_context function."""
+
+    def test_no_state_message(self):
+        """Returns original messages when no state context needed."""
+        messages = [ChatMessage(role="user", contents=[Content.from_text("Hello")])]
+        result = _inject_state_context(messages, {}, {})
+        assert result == messages
+
+    def test_empty_messages(self):
+        """Returns empty list for empty messages."""
+        result = _inject_state_context([], {"key": "value"}, {"properties": {}})
+        assert result == []
+
+    def test_last_message_not_user(self):
+        """Returns original messages when last message is not from user."""
+        messages = [
+            ChatMessage(role="user", contents=[Content.from_text("Hello")]),
+            ChatMessage(role="assistant", contents=[Content.from_text("Hi")]),
+        ]
+        state = {"key": "value"}
+        schema = {"properties": {"key": {"type": "string"}}}
+
+        result = _inject_state_context(messages, state, schema)
+        assert result == messages
+
+    def test_injects_before_last_user_message(self):
+        """Injects state context before last user message."""
+        from agent_framework import Role
+
+        messages = [
+            ChatMessage(role="system", contents=[Content.from_text("You are helpful")]),
+            ChatMessage(role="user", contents=[Content.from_text("Hello")]),
+        ]
+        state = {"document": "content"}
+        schema = {"properties": {"document": {"type": "string"}}}
+
+        result = _inject_state_context(messages, state, schema)
+
+        assert len(result) == 3
+        # System message first
+        assert result[0].role == Role.SYSTEM
+        assert "helpful" in result[0].contents[0].text
+        # State context second
+        assert result[1].role == Role.SYSTEM
+        assert "Current state" in result[1].contents[0].text
+        # User message last
+        assert result[2].role == Role.USER
+        assert "Hello" in result[2].contents[0].text
+
+
+# Additional tests for _run.py functions
+
+
+def test_emit_text_basic():
+    """Test _emit_text emits correct events."""
+    from agent_framework_ag_ui._run import _emit_text
+
+    flow = FlowState()
+    content = Content.from_text("Hello world")
+
+    events = _emit_text(content, flow)
+
+    assert len(events) == 2  # TextMessageStartEvent + TextMessageContentEvent
+    assert flow.message_id is not None
+    assert flow.accumulated_text == "Hello world"
+
+
+def test_emit_text_skip_empty():
+    """Test _emit_text skips empty text."""
+    from agent_framework_ag_ui._run import _emit_text
+
+    flow = FlowState()
+    content = Content.from_text("")
+
+    events = _emit_text(content, flow)
+
+    assert len(events) == 0
+
+
+def test_emit_text_continues_existing_message():
+    """Test _emit_text continues existing message."""
+    from agent_framework_ag_ui._run import _emit_text
+
+    flow = FlowState()
+    flow.message_id = "existing-id"
+    content = Content.from_text("more text")
+
+    events = _emit_text(content, flow)
+
+    assert len(events) == 1  # Only TextMessageContentEvent, no new start
+    assert flow.message_id == "existing-id"
+
+
+def test_emit_text_skips_when_waiting_for_approval():
+    """Test _emit_text skips when waiting for approval."""
+    from agent_framework_ag_ui._run import _emit_text
+
+    flow = FlowState()
+    flow.waiting_for_approval = True
+    content = Content.from_text("should skip")
+
+    events = _emit_text(content, flow)
+
+    assert len(events) == 0
+
+
+def test_emit_text_skips_when_skip_text_flag():
+    """Test _emit_text skips with skip_text flag."""
+    from agent_framework_ag_ui._run import _emit_text
+
+    flow = FlowState()
+    content = Content.from_text("should skip")
+
+    events = _emit_text(content, flow, skip_text=True)
+
+    assert len(events) == 0
+
+
+def test_emit_tool_call_basic():
+    """Test _emit_tool_call emits correct events."""
+    from agent_framework_ag_ui._run import _emit_tool_call
+
+    flow = FlowState()
+    content = Content.from_function_call(
+        call_id="call_123",
+        name="get_weather",
+        arguments='{"city": "NYC"}',
+    )
+
+    events = _emit_tool_call(content, flow)
+
+    assert len(events) >= 1  # At least ToolCallStartEvent
+    assert flow.tool_call_id == "call_123"
+    assert flow.tool_call_name == "get_weather"
+
+
+def test_emit_tool_call_generates_id():
+    """Test _emit_tool_call generates ID when not provided."""
+    from agent_framework_ag_ui._run import _emit_tool_call
+
+    flow = FlowState()
+    # Create content without call_id
+    content = Content(type="function_call", name="test_tool", arguments="{}")
+
+    events = _emit_tool_call(content, flow)
+
+    assert len(events) >= 1
+    assert flow.tool_call_id is not None  # ID should be generated
+
+
+def test_extract_approved_state_updates_no_handler():
+    """Test _extract_approved_state_updates returns empty with no handler."""
+    from agent_framework_ag_ui._run import _extract_approved_state_updates
+
+    messages = [ChatMessage(role="user", contents=[Content.from_text("Hello")])]
+    result = _extract_approved_state_updates(messages, None)
+    assert result == {}
+
+
+def test_extract_approved_state_updates_no_approval():
+    """Test _extract_approved_state_updates returns empty when no approval content."""
+    from agent_framework_ag_ui._orchestration._predictive_state import PredictiveStateHandler
+    from agent_framework_ag_ui._run import _extract_approved_state_updates
+
+    handler = PredictiveStateHandler(predict_state_config={"doc": {"tool": "write", "tool_argument": "content"}})
+    messages = [ChatMessage(role="user", contents=[Content.from_text("Hello")])]
+    result = _extract_approved_state_updates(messages, handler)
+    assert result == {}
@@ -7,7 +7,7 @@ from pathlib import Path
 from typing import Any

 from ag_ui.core import RunFinishedEvent, RunStartedEvent
-from agent_framework import TextContent
+from agent_framework import Content
 from agent_framework._types import AgentResponseUpdate, ChatResponseUpdate

 sys.path.insert(0, str(Path(__file__).parent))
@@ -20,10 +20,10 @@ async def test_service_thread_id_when_there_are_updates():

    updates: list[AgentResponseUpdate] = [
        AgentResponseUpdate(
-            contents=[TextContent(text="Hello, user!")],
+            contents=[Content.from_text(text="Hello, user!")],
            response_id="resp_67890",
            raw_representation=ChatResponseUpdate(
-                contents=[TextContent(text="Hello, user!")],
+                contents=[Content.from_text(text="Hello, user!")],
                conversation_id="conv_12345",
                response_id="resp_67890",
            ),
@@ -1,108 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Tests for shared state management."""
-
-import sys
-from pathlib import Path
-from typing import Any
-
-import pytest
-from ag_ui.core import StateSnapshotEvent
-from agent_framework import ChatAgent, ChatResponseUpdate, TextContent
-
-from agent_framework_ag_ui._agent import AgentFrameworkAgent
-from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-
-sys.path.insert(0, str(Path(__file__).parent))
-from utils_test_ag_ui import StreamingChatClientStub, stream_from_updates
-
-
-@pytest.fixture
-def mock_agent() -> ChatAgent:
-    """Create a mock agent for testing."""
-    updates = [ChatResponseUpdate(contents=[TextContent(text="Hello!")])]
-    chat_client = StreamingChatClientStub(stream_from_updates(updates))
-    return ChatAgent(name="test_agent", instructions="Test agent", chat_client=chat_client)
-
-
-def test_state_snapshot_event():
-    """Test creating state snapshot events."""
-    bridge = AgentFrameworkEventBridge(run_id="test-run", thread_id="test-thread")
-
-    state = {
-        "recipe": {
-            "name": "Chocolate Chip Cookies",
-            "ingredients": ["flour", "sugar", "chocolate chips"],
-            "instructions": ["Mix ingredients", "Bake at 350°F"],
-            "servings": 24,
-        }
-    }
-
-    event = bridge.create_state_snapshot_event(state)
-
-    assert isinstance(event, StateSnapshotEvent)
-    assert event.snapshot == state
-    assert event.snapshot["recipe"]["name"] == "Chocolate Chip Cookies"
-    assert len(event.snapshot["recipe"]["ingredients"]) == 3
-
-
-def test_state_delta_event():
-    """Test creating state delta events using JSON Patch format."""
-    bridge = AgentFrameworkEventBridge(run_id="test-run", thread_id="test-thread")
-
-    # JSON Patch operations (RFC 6902)
-    delta = [
-        {"op": "add", "path": "/recipe/ingredients/-", "value": "vanilla extract"},
-        {"op": "replace", "path": "/recipe/servings", "value": 30},
-    ]
-
-    event = bridge.create_state_delta_event(delta)
-
-    assert event.delta == delta
-    assert len(event.delta) == 2
-    assert event.delta[0]["op"] == "add"
-    assert event.delta[1]["op"] == "replace"
-
-
-async def test_agent_with_initial_state(mock_agent: ChatAgent) -> None:
-    """Test agent emits state snapshot when initial state provided."""
-    state_schema: dict[str, Any] = {"recipe": {"type": "object", "properties": {"name": {"type": "string"}}}}
-
-    agent = AgentFrameworkAgent(
-        agent=mock_agent,
-        state_schema=state_schema,
-    )
-
-    initial_state = {"recipe": {"name": "Test Recipe"}}
-
-    input_data: dict[str, Any] = {
-        "messages": [{"role": "user", "content": "Hello"}],
-        "state": initial_state,
-    }
-
-    events: list[Any] = []
-    async for event in agent.run_agent(input_data):
-        events.append(event)
-
-    # Should have RunStartedEvent, StateSnapshotEvent, RunFinishedEvent at minimum
-    snapshot_events = [e for e in events if isinstance(e, StateSnapshotEvent)]
-    assert len(snapshot_events) == 1
-    assert snapshot_events[0].snapshot == initial_state
-
-
-async def test_agent_without_state_schema(mock_agent: ChatAgent) -> None:
-    """Test agent doesn't emit state events without state schema."""
-    agent = AgentFrameworkAgent(agent=mock_agent)
-
-    input_data: dict[str, Any] = {
-        "messages": [{"role": "user", "content": "Hello"}],
-        "state": {"some": "state"},
-    }
-
-    events: list[Any] = []
-    async for event in agent.run_agent(input_data):
-        events.append(event)
-
-    # Should NOT have any StateSnapshotEvent
-    snapshot_events = [e for e in events if isinstance(e, StateSnapshotEvent)]
-    assert len(snapshot_events) == 0
@@ -1,51 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-from ag_ui.core import CustomEvent, EventType
-from agent_framework import ChatMessage, TextContent
-
-from agent_framework_ag_ui._events import AgentFrameworkEventBridge
-from agent_framework_ag_ui._orchestration._state_manager import StateManager
-
-
-def test_state_manager_initializes_defaults_and_snapshot() -> None:
-    state_manager = StateManager(
-        state_schema={"items": {"type": "array"}, "metadata": {"type": "object"}},
-        predict_state_config=None,
-        require_confirmation=True,
-    )
-    current_state = state_manager.initialize({"metadata": {"a": 1}})
-    bridge = AgentFrameworkEventBridge(run_id="run", thread_id="thread", current_state=current_state)
-
-    snapshot_event = state_manager.initial_snapshot_event(bridge)
-    assert snapshot_event is not None
-    assert snapshot_event.snapshot["items"] == []
-    assert snapshot_event.snapshot["metadata"] == {"a": 1}
-
-
-def test_state_manager_predict_state_event_shape() -> None:
-    state_manager = StateManager(
-        state_schema=None,
-        predict_state_config={"doc": {"tool": "write_document_local", "tool_argument": "document"}},
-        require_confirmation=True,
-    )
-    predict_event = state_manager.predict_state_event()
-    assert isinstance(predict_event, CustomEvent)
-    assert predict_event.type == EventType.CUSTOM
-    assert predict_event.name == "PredictState"
-    assert predict_event.value[0]["state_key"] == "doc"
-
-
-def test_state_context_only_when_new_user_turn() -> None:
-    state_manager = StateManager(
-        state_schema={"items": {"type": "array"}},
-        predict_state_config=None,
-        require_confirmation=True,
-    )
-    state_manager.initialize({"items": [1]})
-
-    assert state_manager.state_context_message(is_new_user_turn=False, conversation_has_tool_calls=False) is None
-
-    message = state_manager.state_context_message(is_new_user_turn=True, conversation_has_tool_calls=False)
-    assert isinstance(message, ChatMessage)
-    assert isinstance(message.contents[0], TextContent)
-    assert "Current state of the application" in message.contents[0].text
@@ -8,7 +8,7 @@ from collections.abc import AsyncIterator, MutableSequence
 from pathlib import Path
 from typing import Any

-from agent_framework import ChatAgent, ChatMessage, ChatOptions, ChatResponseUpdate, TextContent
+from agent_framework import ChatAgent, ChatMessage, ChatOptions, ChatResponseUpdate, Content
 from pydantic import BaseModel

 sys.path.insert(0, str(Path(__file__).parent))
@@ -43,7 +43,7 @@ async def test_structured_output_with_recipe():
        messages: MutableSequence[ChatMessage], options: ChatOptions, **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
        yield ChatResponseUpdate(
-            contents=[TextContent(text='{"recipe": {"name": "Pasta"}, "message": "Here is your recipe"}')]
+            contents=[Content.from_text(text='{"recipe": {"name": "Pasta"}, "message": "Here is your recipe"}')]
        )

    agent = ChatAgent(name="test", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
@@ -86,7 +86,7 @@ async def test_structured_output_with_steps():
                {"id": "2", "description": "Step 2", "status": "pending"},
            ]
        }
-        yield ChatResponseUpdate(contents=[TextContent(text=json.dumps(steps_data))])
+        yield ChatResponseUpdate(contents=[Content.from_text(text=json.dumps(steps_data))])

    agent = ChatAgent(name="test", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    agent.default_options = ChatOptions(response_format=StepsOutput)
@@ -118,7 +118,7 @@ async def test_structured_output_with_no_schema_match():
    from agent_framework.ag_ui import AgentFrameworkAgent

    updates = [
-        ChatResponseUpdate(contents=[TextContent(text='{"data": {"key": "value"}}')]),
+        ChatResponseUpdate(contents=[Content.from_text(text='{"data": {"key": "value"}}')]),
    ]

    agent = ChatAgent(
@@ -156,7 +156,7 @@ async def test_structured_output_without_schema():
    async def stream_fn(
        messages: MutableSequence[ChatMessage], options: ChatOptions, **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
-        yield ChatResponseUpdate(contents=[TextContent(text='{"data": {"key": "value"}, "info": "processed"}')])
+        yield ChatResponseUpdate(contents=[Content.from_text(text='{"data": {"key": "value"}, "info": "processed"}')])

    agent = ChatAgent(name="test", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    agent.default_options = ChatOptions(response_format=DataOutput)
@@ -185,7 +185,7 @@ async def test_no_structured_output_when_no_response_format():
    """Test that structured output path is skipped when no response_format."""
    from agent_framework.ag_ui import AgentFrameworkAgent

-    updates = [ChatResponseUpdate(contents=[TextContent(text="Regular text")])]
+    updates = [ChatResponseUpdate(contents=[Content.from_text(text="Regular text")])]

    agent = ChatAgent(
        name="test",
@@ -216,7 +216,7 @@ async def test_structured_output_with_message_field():
        messages: MutableSequence[ChatMessage], options: ChatOptions, **kwargs: Any
    ) -> AsyncIterator[ChatResponseUpdate]:
        output_data = {"recipe": {"name": "Salad"}, "message": "Fresh salad recipe ready"}
-        yield ChatResponseUpdate(contents=[TextContent(text=json.dumps(output_data))])
+        yield ChatResponseUpdate(contents=[Content.from_text(text=json.dumps(output_data))])

    agent = ChatAgent(name="test", instructions="Test", chat_client=StreamingChatClientStub(stream_fn))
    agent.default_options = ChatOptions(response_format=RecipeOutput)
@@ -129,3 +129,95 @@ def test_collect_server_tools_with_mcp_tools_via_public_property() -> None:
    assert "regular_tool" in names
    assert "mcp_function" in names
    assert len(tools) == 2
+
+
+# Additional tests for tooling coverage
+
+
+def test_collect_server_tools_no_default_options() -> None:
+    """collect_server_tools returns empty list when agent has no default_options."""
+
+    class MockAgent:
+        pass
+
+    agent = MockAgent()
+    tools = collect_server_tools(agent)
+    assert tools == []
+
+
+def test_register_additional_client_tools_no_tools() -> None:
+    """register_additional_client_tools does nothing with None tools."""
+    mock_chat_client = MagicMock()
+    agent = ChatAgent(chat_client=mock_chat_client)
+
+    # Should not raise
+    register_additional_client_tools(agent, None)
+
+
+def test_register_additional_client_tools_no_chat_client() -> None:
+    """register_additional_client_tools does nothing when agent has no chat_client."""
+    from agent_framework_ag_ui._orchestration._tooling import register_additional_client_tools
+
+    class MockAgent:
+        pass
+
+    agent = MockAgent()
+    tools = [DummyTool("x")]
+
+    # Should not raise
+    register_additional_client_tools(agent, tools)
+
+
+def test_merge_tools_no_client_tools() -> None:
+    """merge_tools returns None when no client tools."""
+    server = [DummyTool("a")]
+    result = merge_tools(server, None)
+    assert result is None
+
+
+def test_merge_tools_all_duplicates() -> None:
+    """merge_tools returns None when all client tools duplicate server tools."""
+    server = [DummyTool("a"), DummyTool("b")]
+    client = [DummyTool("a"), DummyTool("b")]
+    result = merge_tools(server, client)
+    assert result is None
+
+
+def test_merge_tools_empty_server() -> None:
+    """merge_tools works with empty server tools."""
+    server: list = []
+    client = [DummyTool("a"), DummyTool("b")]
+    result = merge_tools(server, client)
+    assert result is not None
+    assert len(result) == 2
+
+
+def test_merge_tools_with_approval_tools_no_client() -> None:
+    """merge_tools returns server tools when they have approval mode even without client tools."""
+
+    class ApprovalTool:
+        def __init__(self, name: str):
+            self.name = name
+            self.approval_mode = "always_require"
+
+    server = [ApprovalTool("write_doc")]
+    result = merge_tools(server, None)
+    assert result is not None
+    assert len(result) == 1
+    assert result[0].name == "write_doc"
+
+
+def test_merge_tools_with_approval_tools_all_duplicates() -> None:
+    """merge_tools returns server tools with approval mode even when client duplicates."""
+
+    class ApprovalTool:
+        def __init__(self, name: str):
+            self.name = name
+            self.approval_mode = "always_require"
+
+    server = [ApprovalTool("write_doc")]
+    client = [DummyTool("write_doc")]  # Same name as server
+    result = merge_tools(server, client)
+    assert result is not None
+    assert len(result) == 1
+    assert result[0].approval_mode == "always_require"
@@ -2,7 +2,7 @@

 """Tests for type definitions in _types.py."""

-from agent_framework_ag_ui._types import AgentState, PredictStateConfig, RunMetadata
+from agent_framework_ag_ui._types import AgentState, AGUIRequest, PredictStateConfig, RunMetadata


 class TestPredictStateConfig:
@@ -143,3 +143,83 @@ class TestAgentState:
        assert len(state["messages"]) == 2
        assert "metadata" in state["messages"][0]
        assert "tool_calls" in state["messages"][1]
+
+
+class TestAGUIRequest:
+    """Test AGUIRequest Pydantic model."""
+
+    def test_agui_request_minimal(self) -> None:
+        """Test creating AGUIRequest with only required fields."""
+        request = AGUIRequest(messages=[{"role": "user", "content": "Hello"}])
+
+        assert len(request.messages) == 1
+        assert request.messages[0]["content"] == "Hello"
+        assert request.run_id is None
+        assert request.thread_id is None
+        assert request.state is None
+        assert request.tools is None
+        assert request.context is None
+        assert request.forwarded_props is None
+        assert request.parent_run_id is None
+
+    def test_agui_request_all_fields(self) -> None:
+        """Test creating AGUIRequest with all fields populated."""
+        request = AGUIRequest(
+            messages=[{"role": "user", "content": "Hello"}],
+            run_id="run-123",
+            thread_id="thread-456",
+            state={"counter": 0},
+            tools=[{"name": "search", "description": "Search tool"}],
+            context=[{"type": "document", "content": "Some context"}],
+            forwarded_props={"custom_key": "custom_value"},
+            parent_run_id="parent-run-789",
+        )
+
+        assert request.run_id == "run-123"
+        assert request.thread_id == "thread-456"
+        assert request.state == {"counter": 0}
+        assert request.tools == [{"name": "search", "description": "Search tool"}]
+        assert request.context == [{"type": "document", "content": "Some context"}]
+        assert request.forwarded_props == {"custom_key": "custom_value"}
+        assert request.parent_run_id == "parent-run-789"
+
+    def test_agui_request_model_dump_excludes_none(self) -> None:
+        """Test that model_dump(exclude_none=True) excludes None fields."""
+        request = AGUIRequest(
+            messages=[{"role": "user", "content": "test"}],
+            tools=[{"name": "my_tool"}],
+            context=[{"id": "ctx1"}],
+        )
+
+        dumped = request.model_dump(exclude_none=True)
+
+        assert "messages" in dumped
+        assert "tools" in dumped
+        assert "context" in dumped
+        assert "run_id" not in dumped
+        assert "thread_id" not in dumped
+        assert "state" not in dumped
+        assert "forwarded_props" not in dumped
+        assert "parent_run_id" not in dumped
+
+    def test_agui_request_model_dump_includes_all_set_fields(self) -> None:
+        """Test that model_dump preserves all explicitly set fields.
+
+        This is critical for the fix - ensuring tools, context, forwarded_props,
+        and parent_run_id are not stripped during request validation.
+        """
+        request = AGUIRequest(
+            messages=[{"role": "user", "content": "test"}],
+            tools=[{"name": "client_tool", "parameters": {"type": "object"}}],
+            context=[{"type": "snippet", "content": "code here"}],
+            forwarded_props={"auth_token": "secret", "user_id": "user-1"},
+            parent_run_id="parent-456",
+        )
+
+        dumped = request.model_dump(exclude_none=True)
+
+        # Verify all fields are preserved (the main bug fix)
+        assert dumped["tools"] == [{"name": "client_tool", "parameters": {"type": "object"}}]
+        assert dumped["context"] == [{"type": "snippet", "content": "code here"}]
+        assert dumped["forwarded_props"] == {"auth_token": "secret", "user_id": "user-1"}
+        assert dumped["parent_run_id"] == "parent-456"
@@ -122,6 +122,20 @@ def test_make_json_safe_model_dump():
    assert result == {"type": "model", "data": "dump"}


+class ToDictObject:
+    """Object with to_dict method (like SerializationMixin)."""
+
+    def to_dict(self):
+        return {"type": "serialization_mixin", "method": "to_dict"}
+
+
+def test_make_json_safe_to_dict():
+    """Test object with to_dict method (SerializationMixin pattern)."""
+    obj = ToDictObject()
+    result = make_json_safe(obj)
+    assert result == {"type": "serialization_mixin", "method": "to_dict"}
+
+
 class DictObject:
    """Object with dict method."""

@@ -203,6 +217,41 @@ def test_make_json_safe_fallback():
    assert isinstance(result, dict)


+def test_make_json_safe_dataclass_with_nested_to_dict_object():
+    """Test dataclass containing a to_dict object (like HandoffAgentUserRequest with AgentResponse).
+
+    This test verifies the fix for the AG-UI JSON serialization error when
+    HandoffAgentUserRequest (a dataclass) contains an AgentResponse (SerializationMixin).
+    """
+
+    class NestedToDictObject:
+        """Simulates SerializationMixin objects like AgentResponse."""
+
+        def __init__(self, contents: list[str]):
+            self.contents = contents
+
+        def to_dict(self):
+            return {"type": "response", "contents": self.contents}
+
+    @dataclass
+    class ContainerDataclass:
+        """Simulates HandoffAgentUserRequest dataclass."""
+
+        response: NestedToDictObject
+
+    obj = ContainerDataclass(response=NestedToDictObject(contents=["hello", "world"]))
+    result = make_json_safe(obj)
+
+    # Verify the nested to_dict object was properly serialized
+    assert result == {"response": {"type": "response", "contents": ["hello", "world"]}}
+
+    # Verify the result is actually JSON serializable
+    import json
+
+    json_str = json.dumps(result)
+    assert json_str is not None
+
+
 def test_convert_tools_to_agui_format_with_ai_function():
    """Test converting AIFunction to AG-UI format."""
    from agent_framework import ai_function
@@ -307,3 +356,173 @@ def test_convert_tools_to_agui_format_with_multiple_tools():
    assert len(result) == 2
    assert result[0]["name"] == "tool1"
    assert result[1]["name"] == "tool2"
+
+
+# Additional tests for utils coverage
+
+
+def test_safe_json_parse_with_dict():
+    """Test safe_json_parse with dict input."""
+    from agent_framework_ag_ui._utils import safe_json_parse
+
+    input_dict = {"key": "value"}
+    result = safe_json_parse(input_dict)
+    assert result == input_dict
+
+
+def test_safe_json_parse_with_json_string():
+    """Test safe_json_parse with JSON string."""
+    from agent_framework_ag_ui._utils import safe_json_parse
+
+    result = safe_json_parse('{"key": "value"}')
+    assert result == {"key": "value"}
+
+
+def test_safe_json_parse_with_invalid_json():
+    """Test safe_json_parse with invalid JSON."""
+    from agent_framework_ag_ui._utils import safe_json_parse
+
+    result = safe_json_parse("not json")
+    assert result is None
+
+
+def test_safe_json_parse_with_non_dict_json():
+    """Test safe_json_parse with JSON that parses to non-dict."""
+    from agent_framework_ag_ui._utils import safe_json_parse
+
+    result = safe_json_parse("[1, 2, 3]")
+    assert result is None
+
+
+def test_safe_json_parse_with_none():
+    """Test safe_json_parse with None input."""
+    from agent_framework_ag_ui._utils import safe_json_parse
+
+    result = safe_json_parse(None)
+    assert result is None
+
+
+def test_get_role_value_with_enum():
+    """Test get_role_value with enum role."""
+    from agent_framework import ChatMessage, Content, Role
+
+    from agent_framework_ag_ui._utils import get_role_value
+
+    message = ChatMessage(role=Role.USER, contents=[Content.from_text("test")])
+    result = get_role_value(message)
+    assert result == "user"
+
+
+def test_get_role_value_with_string():
+    """Test get_role_value with string role."""
+    from agent_framework_ag_ui._utils import get_role_value
+
+    class MockMessage:
+        role = "assistant"
+
+    result = get_role_value(MockMessage())
+    assert result == "assistant"
+
+
+def test_get_role_value_with_none():
+    """Test get_role_value with no role."""
+    from agent_framework_ag_ui._utils import get_role_value
+
+    class MockMessage:
+        pass
+
+    result = get_role_value(MockMessage())
+    assert result == ""
+
+
+def test_normalize_agui_role_developer():
+    """Test normalize_agui_role maps developer to system."""
+    from agent_framework_ag_ui._utils import normalize_agui_role
+
+    assert normalize_agui_role("developer") == "system"
+
+
+def test_normalize_agui_role_valid():
+    """Test normalize_agui_role with valid roles."""
+    from agent_framework_ag_ui._utils import normalize_agui_role
+
+    assert normalize_agui_role("user") == "user"
+    assert normalize_agui_role("assistant") == "assistant"
+    assert normalize_agui_role("system") == "system"
+    assert normalize_agui_role("tool") == "tool"
+
+
+def test_normalize_agui_role_invalid():
+    """Test normalize_agui_role with invalid role defaults to user."""
+    from agent_framework_ag_ui._utils import normalize_agui_role
+
+    assert normalize_agui_role("invalid") == "user"
+    assert normalize_agui_role(123) == "user"
+
+
+def test_extract_state_from_tool_args():
+    """Test extract_state_from_tool_args."""
+    from agent_framework_ag_ui._utils import extract_state_from_tool_args
+
+    # Specific key
+    assert extract_state_from_tool_args({"key": "value"}, "key") == "value"
+
+    # Wildcard
+    args = {"a": 1, "b": 2}
+    assert extract_state_from_tool_args(args, "*") == args
+
+    # Missing key
+    assert extract_state_from_tool_args({"other": "value"}, "key") is None
+
+    # None args
+    assert extract_state_from_tool_args(None, "key") is None
+
+
+def test_convert_agui_tools_to_agent_framework():
+    """Test convert_agui_tools_to_agent_framework."""
+    from agent_framework_ag_ui._utils import convert_agui_tools_to_agent_framework
+
+    agui_tools = [
+        {
+            "name": "test_tool",
+            "description": "A test tool",
+            "parameters": {"type": "object", "properties": {"arg": {"type": "string"}}},
+        }
+    ]
+
+    result = convert_agui_tools_to_agent_framework(agui_tools)
+
+    assert result is not None
+    assert len(result) == 1
+    assert result[0].name == "test_tool"
+    assert result[0].description == "A test tool"
+    assert result[0].declaration_only is True
+
+
+def test_convert_agui_tools_to_agent_framework_none():
+    """Test convert_agui_tools_to_agent_framework with None."""
+    from agent_framework_ag_ui._utils import convert_agui_tools_to_agent_framework
+
+    result = convert_agui_tools_to_agent_framework(None)
+    assert result is None
+
+
+def test_convert_agui_tools_to_agent_framework_empty():
+    """Test convert_agui_tools_to_agent_framework with empty list."""
+    from agent_framework_ag_ui._utils import convert_agui_tools_to_agent_framework
+
+    result = convert_agui_tools_to_agent_framework([])
+    assert result is None
+
+
+def test_make_json_safe_unconvertible():
+    """Test make_json_safe with object that has no standard conversion."""
+
+    class NoConversion:
+        __slots__ = ()  # No __dict__
+
+    from agent_framework_ag_ui._utils import make_json_safe
+
+    result = make_json_safe(NoConversion())
+    # Falls back to str()
+    assert isinstance(result, str)
@@ -16,13 +16,10 @@ from agent_framework import (
    ChatMessage,
    ChatResponse,
    ChatResponseUpdate,
-    TextContent,
+    Content,
 )
 from agent_framework._clients import TOptions_co

-from agent_framework_ag_ui._message_adapters import _deduplicate_messages, _sanitize_tool_history
-from agent_framework_ag_ui._orchestrators import ExecutionContext
-
 if sys.version_info >= (3, 12):
    from typing import override  # type: ignore # pragma: no cover
 else:
@@ -91,7 +88,7 @@ class StubAgent(AgentProtocol):
        self.id = agent_id
        self.name = agent_name
        self.description = "stub agent"
-        self.updates = updates or [AgentResponseUpdate(contents=[TextContent(text="response")], role="assistant")]
+        self.updates = updates or [AgentResponseUpdate(contents=[Content.from_text(text="response")], role="assistant")]
        self.default_options: dict[str, Any] = (
            default_options if isinstance(default_options, dict) else {"tools": None, "response_format": None}
        )
@@ -125,14 +122,3 @@ class StubAgent(AgentProtocol):

    def get_new_thread(self, **kwargs: Any) -> AgentThread:
        return AgentThread()
-
-
-class TestExecutionContext(ExecutionContext):
-    """ExecutionContext helper that allows setting messages for tests."""
-
-    def set_messages(self, messages: list[ChatMessage], *, normalize: bool = True) -> None:
-        if normalize:
-            self._messages = _deduplicate_messages(_sanitize_tool_history(messages))
-        else:
-            self._messages = messages
-        self._snapshot_messages = None