mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Python: [Durabletask] Update feature-durabletask-python branch with main (#3068)
* 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> * Remove from feature branch * Remove ollama changes --------- Signed-off-by: dependabot[bot] <support@github.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>
This commit is contained in:
Laveesh Rohra
committed by
GitHub
Unverified
GitHub
parent
a02527f00a
commit
a5b36dc379
@@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) Microsoft Corporation.
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE
|
||||
@@ -0,0 +1,19 @@
|
||||
# Get Started with Microsoft Agent Framework Bedrock
|
||||
|
||||
Install the provider package:
|
||||
|
||||
```bash
|
||||
pip install agent-framework-bedrock --pre
|
||||
```
|
||||
|
||||
## Bedrock Integration
|
||||
|
||||
The Bedrock integration enables Microsoft Agent Framework applications to call Amazon Bedrock models with familiar chat abstractions, including tool/function calling when you attach tools through `ChatOptions`.
|
||||
|
||||
### Basic Usage Example
|
||||
|
||||
See the [Bedrock sample script](samples/bedrock_sample.py) for a runnable end-to-end script that:
|
||||
|
||||
- Loads credentials from the `BEDROCK_*` environment variables
|
||||
- Instantiates `BedrockChatClient`
|
||||
- Sends a simple conversation turn and prints the response
|
||||
@@ -0,0 +1,15 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
import importlib.metadata
|
||||
|
||||
from ._chat_client import BedrockChatClient
|
||||
|
||||
try:
|
||||
__version__ = importlib.metadata.version(__name__)
|
||||
except importlib.metadata.PackageNotFoundError:
|
||||
__version__ = "0.0.0"
|
||||
|
||||
__all__ = [
|
||||
"BedrockChatClient",
|
||||
"__version__",
|
||||
]
|
||||
@@ -0,0 +1,527 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
from collections import deque
|
||||
from collections.abc import AsyncIterable, MutableMapping, MutableSequence, Sequence
|
||||
from typing import Any, ClassVar
|
||||
from uuid import uuid4
|
||||
|
||||
from agent_framework import (
|
||||
AGENT_FRAMEWORK_USER_AGENT,
|
||||
AIFunction,
|
||||
BaseChatClient,
|
||||
ChatMessage,
|
||||
ChatOptions,
|
||||
ChatResponse,
|
||||
ChatResponseUpdate,
|
||||
Contents,
|
||||
FinishReason,
|
||||
FunctionCallContent,
|
||||
FunctionResultContent,
|
||||
Role,
|
||||
TextContent,
|
||||
ToolProtocol,
|
||||
UsageContent,
|
||||
UsageDetails,
|
||||
get_logger,
|
||||
prepare_function_call_results,
|
||||
use_chat_middleware,
|
||||
use_function_invocation,
|
||||
)
|
||||
from agent_framework._pydantic import AFBaseSettings
|
||||
from agent_framework.exceptions import ServiceInitializationError, ServiceInvalidResponseError
|
||||
from agent_framework.observability import use_instrumentation
|
||||
from boto3.session import Session as Boto3Session
|
||||
from botocore.client import BaseClient
|
||||
from botocore.config import Config as BotoConfig
|
||||
from pydantic import SecretStr, ValidationError
|
||||
|
||||
logger = get_logger("agent_framework.bedrock")
|
||||
|
||||
DEFAULT_REGION = "us-east-1"
|
||||
DEFAULT_MAX_TOKENS = 1024
|
||||
|
||||
ROLE_MAP: dict[Role, str] = {
|
||||
Role.USER: "user",
|
||||
Role.ASSISTANT: "assistant",
|
||||
Role.SYSTEM: "user",
|
||||
Role.TOOL: "user",
|
||||
}
|
||||
|
||||
FINISH_REASON_MAP: dict[str, FinishReason] = {
|
||||
"end_turn": FinishReason.STOP,
|
||||
"stop_sequence": FinishReason.STOP,
|
||||
"max_tokens": FinishReason.LENGTH,
|
||||
"length": FinishReason.LENGTH,
|
||||
"content_filtered": FinishReason.CONTENT_FILTER,
|
||||
"tool_use": FinishReason.TOOL_CALLS,
|
||||
}
|
||||
|
||||
|
||||
class BedrockSettings(AFBaseSettings):
|
||||
"""Bedrock configuration settings pulled from environment variables or .env files."""
|
||||
|
||||
env_prefix: ClassVar[str] = "BEDROCK_"
|
||||
|
||||
region: str = DEFAULT_REGION
|
||||
chat_model_id: str | None = None
|
||||
access_key: SecretStr | None = None
|
||||
secret_key: SecretStr | None = None
|
||||
session_token: SecretStr | None = None
|
||||
|
||||
|
||||
@use_function_invocation
|
||||
@use_instrumentation
|
||||
@use_chat_middleware
|
||||
class BedrockChatClient(BaseChatClient):
|
||||
"""Async chat client for Amazon Bedrock's Converse API."""
|
||||
|
||||
OTEL_PROVIDER_NAME: ClassVar[str] = "aws.bedrock" # type: ignore[reportIncompatibleVariableOverride, misc]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
region: str | None = None,
|
||||
model_id: str | None = None,
|
||||
access_key: str | None = None,
|
||||
secret_key: str | None = None,
|
||||
session_token: str | None = None,
|
||||
client: BaseClient | None = None,
|
||||
boto3_session: Boto3Session | None = None,
|
||||
env_file_path: str | None = None,
|
||||
env_file_encoding: str | None = None,
|
||||
**kwargs: Any,
|
||||
) -> None:
|
||||
"""Create a Bedrock chat client and load AWS credentials.
|
||||
|
||||
Args:
|
||||
region: Region to send Bedrock requests to; falls back to BEDROCK_REGION.
|
||||
model_id: Default model identifier; falls back to BEDROCK_CHAT_MODEL_ID.
|
||||
access_key: Optional AWS access key for manual credential injection.
|
||||
secret_key: Optional AWS secret key paired with ``access_key``.
|
||||
session_token: Optional AWS session token for temporary credentials.
|
||||
client: Preconfigured Bedrock runtime client; when omitted a boto3 session is created.
|
||||
boto3_session: Custom boto3 session used to build the runtime client if provided.
|
||||
env_file_path: Optional .env file path used by ``BedrockSettings`` to load defaults.
|
||||
env_file_encoding: Encoding for the optional .env file.
|
||||
kwargs: Additional arguments forwarded to ``BaseChatClient``.
|
||||
"""
|
||||
try:
|
||||
settings = BedrockSettings(
|
||||
region=region,
|
||||
chat_model_id=model_id,
|
||||
access_key=access_key, # type: ignore[arg-type]
|
||||
secret_key=secret_key, # type: ignore[arg-type]
|
||||
session_token=session_token, # type: ignore[arg-type]
|
||||
env_file_path=env_file_path,
|
||||
env_file_encoding=env_file_encoding,
|
||||
)
|
||||
except ValidationError as ex:
|
||||
raise ServiceInitializationError("Failed to initialize Bedrock settings.", ex) from ex
|
||||
|
||||
if client is None:
|
||||
session = boto3_session or self._create_session(settings)
|
||||
client = session.client(
|
||||
"bedrock-runtime",
|
||||
region_name=settings.region,
|
||||
config=BotoConfig(user_agent_extra=AGENT_FRAMEWORK_USER_AGENT),
|
||||
)
|
||||
|
||||
super().__init__(**kwargs)
|
||||
self._bedrock_client = client
|
||||
self.model_id = settings.chat_model_id
|
||||
self.region = settings.region
|
||||
|
||||
@staticmethod
|
||||
def _create_session(settings: BedrockSettings) -> Boto3Session:
|
||||
session_kwargs: dict[str, Any] = {"region_name": settings.region or DEFAULT_REGION}
|
||||
if settings.access_key and settings.secret_key:
|
||||
session_kwargs["aws_access_key_id"] = settings.access_key.get_secret_value()
|
||||
session_kwargs["aws_secret_access_key"] = settings.secret_key.get_secret_value()
|
||||
if settings.session_token:
|
||||
session_kwargs["aws_session_token"] = settings.session_token.get_secret_value()
|
||||
return Boto3Session(**session_kwargs)
|
||||
|
||||
async def _inner_get_response(
|
||||
self,
|
||||
*,
|
||||
messages: MutableSequence[ChatMessage],
|
||||
chat_options: ChatOptions,
|
||||
**kwargs: Any,
|
||||
) -> ChatResponse:
|
||||
request = self._build_converse_request(messages, chat_options, **kwargs)
|
||||
raw_response = await asyncio.to_thread(self._bedrock_client.converse, **request)
|
||||
return self._process_converse_response(raw_response)
|
||||
|
||||
async def _inner_get_streaming_response(
|
||||
self,
|
||||
*,
|
||||
messages: MutableSequence[ChatMessage],
|
||||
chat_options: ChatOptions,
|
||||
**kwargs: Any,
|
||||
) -> AsyncIterable[ChatResponseUpdate]:
|
||||
response = await self._inner_get_response(messages=messages, chat_options=chat_options, **kwargs)
|
||||
contents = list(response.messages[0].contents if response.messages else [])
|
||||
if response.usage_details:
|
||||
contents.append(UsageContent(details=response.usage_details))
|
||||
yield ChatResponseUpdate(
|
||||
response_id=response.response_id,
|
||||
contents=contents,
|
||||
model_id=response.model_id,
|
||||
finish_reason=response.finish_reason,
|
||||
raw_representation=response.raw_representation,
|
||||
)
|
||||
|
||||
def _build_converse_request(
|
||||
self,
|
||||
messages: MutableSequence[ChatMessage],
|
||||
chat_options: ChatOptions,
|
||||
**kwargs: Any,
|
||||
) -> dict[str, Any]:
|
||||
model_id = chat_options.model_id or self.model_id
|
||||
if not model_id:
|
||||
raise ServiceInitializationError(
|
||||
"Bedrock model_id is required. Set via chat options or BEDROCK_CHAT_MODEL_ID environment variable."
|
||||
)
|
||||
|
||||
system_prompts, conversation = self._prepare_bedrock_messages(messages)
|
||||
if not conversation:
|
||||
raise ServiceInitializationError("At least one non-system message is required for Bedrock requests.")
|
||||
|
||||
payload: dict[str, Any] = {
|
||||
"modelId": model_id,
|
||||
"messages": conversation,
|
||||
}
|
||||
if system_prompts:
|
||||
payload["system"] = system_prompts
|
||||
|
||||
inference_config: dict[str, Any] = {}
|
||||
inference_config["maxTokens"] = (
|
||||
chat_options.max_tokens if chat_options.max_tokens is not None else DEFAULT_MAX_TOKENS
|
||||
)
|
||||
if chat_options.temperature is not None:
|
||||
inference_config["temperature"] = chat_options.temperature
|
||||
if chat_options.top_p is not None:
|
||||
inference_config["topP"] = chat_options.top_p
|
||||
if chat_options.stop is not None:
|
||||
inference_config["stopSequences"] = chat_options.stop
|
||||
if inference_config:
|
||||
payload["inferenceConfig"] = inference_config
|
||||
|
||||
tool_config = self._convert_tools_to_bedrock_config(chat_options.tools)
|
||||
if tool_choice := self._convert_tool_choice(chat_options.tool_choice):
|
||||
if tool_config is None:
|
||||
tool_config = {}
|
||||
tool_config["toolChoice"] = tool_choice
|
||||
if tool_config:
|
||||
payload["toolConfig"] = tool_config
|
||||
|
||||
if chat_options.additional_properties:
|
||||
payload.update(chat_options.additional_properties)
|
||||
if kwargs:
|
||||
payload.update(kwargs)
|
||||
return payload
|
||||
|
||||
def _prepare_bedrock_messages(
|
||||
self, messages: Sequence[ChatMessage]
|
||||
) -> tuple[list[dict[str, str]], list[dict[str, Any]]]:
|
||||
prompts: list[dict[str, str]] = []
|
||||
conversation: list[dict[str, Any]] = []
|
||||
pending_tool_use_ids: deque[str] = deque()
|
||||
for message in messages:
|
||||
if message.role == Role.SYSTEM:
|
||||
text_value = message.text
|
||||
if text_value:
|
||||
prompts.append({"text": text_value})
|
||||
continue
|
||||
|
||||
content_blocks = self._convert_message_to_content_blocks(message)
|
||||
if not content_blocks:
|
||||
continue
|
||||
|
||||
role = ROLE_MAP.get(message.role, "user")
|
||||
if role == "assistant":
|
||||
pending_tool_use_ids = deque(
|
||||
block["toolUse"]["toolUseId"]
|
||||
for block in content_blocks
|
||||
if isinstance(block, MutableMapping) and "toolUse" in block
|
||||
)
|
||||
elif message.role == Role.TOOL:
|
||||
content_blocks = self._align_tool_results_with_pending(content_blocks, pending_tool_use_ids)
|
||||
pending_tool_use_ids.clear()
|
||||
if not content_blocks:
|
||||
continue
|
||||
else:
|
||||
pending_tool_use_ids.clear()
|
||||
|
||||
conversation.append({"role": role, "content": content_blocks})
|
||||
|
||||
return prompts, conversation
|
||||
|
||||
def _align_tool_results_with_pending(
|
||||
self, content_blocks: list[dict[str, Any]], pending_tool_use_ids: deque[str]
|
||||
) -> list[dict[str, Any]]:
|
||||
if not content_blocks:
|
||||
return content_blocks
|
||||
if not pending_tool_use_ids:
|
||||
# No pending tool calls; drop toolResult blocks to avoid Bedrock validation errors
|
||||
return [
|
||||
block for block in content_blocks if not (isinstance(block, MutableMapping) and "toolResult" in block)
|
||||
]
|
||||
|
||||
aligned_blocks: list[dict[str, Any]] = []
|
||||
pending = deque(pending_tool_use_ids)
|
||||
for block in content_blocks:
|
||||
if not isinstance(block, MutableMapping):
|
||||
aligned_blocks.append(block)
|
||||
continue
|
||||
tool_result = block.get("toolResult")
|
||||
if not tool_result:
|
||||
aligned_blocks.append(block)
|
||||
continue
|
||||
if not pending:
|
||||
logger.debug("Dropping extra tool result block due to missing pending tool uses: %s", block)
|
||||
continue
|
||||
tool_use_id = tool_result.get("toolUseId")
|
||||
if tool_use_id:
|
||||
try:
|
||||
pending.remove(tool_use_id)
|
||||
except ValueError:
|
||||
logger.debug("Tool result references unknown toolUseId '%s'. Dropping block.", tool_use_id)
|
||||
continue
|
||||
else:
|
||||
tool_result["toolUseId"] = pending.popleft()
|
||||
aligned_blocks.append(block)
|
||||
|
||||
return aligned_blocks
|
||||
|
||||
def _convert_message_to_content_blocks(self, message: ChatMessage) -> list[dict[str, Any]]:
|
||||
blocks: list[dict[str, Any]] = []
|
||||
for content in message.contents:
|
||||
block = self._convert_content_to_bedrock_block(content)
|
||||
if block is None:
|
||||
logger.debug("Skipping unsupported content type for Bedrock: %s", type(content))
|
||||
continue
|
||||
blocks.append(block)
|
||||
return blocks
|
||||
|
||||
def _convert_content_to_bedrock_block(self, content: Contents) -> dict[str, Any] | None:
|
||||
if isinstance(content, TextContent):
|
||||
return {"text": content.text}
|
||||
if isinstance(content, FunctionCallContent):
|
||||
arguments = content.parse_arguments() or {}
|
||||
return {
|
||||
"toolUse": {
|
||||
"toolUseId": content.call_id or self._generate_tool_call_id(),
|
||||
"name": content.name,
|
||||
"input": arguments,
|
||||
}
|
||||
}
|
||||
if isinstance(content, FunctionResultContent):
|
||||
tool_result_block = {
|
||||
"toolResult": {
|
||||
"toolUseId": content.call_id,
|
||||
"content": self._convert_tool_result_to_blocks(content.result),
|
||||
"status": "error" if content.exception else "success",
|
||||
}
|
||||
}
|
||||
if content.exception:
|
||||
tool_result = tool_result_block["toolResult"]
|
||||
existing_content = tool_result.get("content")
|
||||
content_list: list[dict[str, Any]]
|
||||
if isinstance(existing_content, list):
|
||||
content_list = existing_content
|
||||
else:
|
||||
content_list = []
|
||||
tool_result["content"] = content_list
|
||||
content_list.append({"text": str(content.exception)})
|
||||
return tool_result_block
|
||||
return None
|
||||
|
||||
def _convert_tool_result_to_blocks(self, result: Any) -> list[dict[str, Any]]:
|
||||
prepared_result = prepare_function_call_results(result)
|
||||
try:
|
||||
parsed_result = json.loads(prepared_result)
|
||||
except json.JSONDecodeError:
|
||||
return [{"text": prepared_result}]
|
||||
|
||||
return self._convert_prepared_tool_result_to_blocks(parsed_result)
|
||||
|
||||
def _convert_prepared_tool_result_to_blocks(self, value: Any) -> list[dict[str, Any]]:
|
||||
if isinstance(value, list):
|
||||
blocks: list[dict[str, Any]] = []
|
||||
for item in value:
|
||||
blocks.extend(self._convert_prepared_tool_result_to_blocks(item))
|
||||
return blocks or [{"text": ""}]
|
||||
return [self._normalize_tool_result_value(value)]
|
||||
|
||||
def _normalize_tool_result_value(self, value: Any) -> dict[str, Any]:
|
||||
if isinstance(value, dict):
|
||||
return {"json": value}
|
||||
if isinstance(value, (list, tuple)):
|
||||
return {"json": list(value)}
|
||||
if isinstance(value, str):
|
||||
return {"text": value}
|
||||
if isinstance(value, (int, float, bool)) or value is None:
|
||||
return {"json": value}
|
||||
if isinstance(value, TextContent) and getattr(value, "text", None):
|
||||
return {"text": value.text}
|
||||
if hasattr(value, "to_dict"):
|
||||
try:
|
||||
return {"json": value.to_dict()} # type: ignore[call-arg]
|
||||
except Exception: # pragma: no cover - defensive
|
||||
return {"text": str(value)}
|
||||
return {"text": str(value)}
|
||||
|
||||
def _convert_tools_to_bedrock_config(
|
||||
self, tools: list[ToolProtocol | MutableMapping[str, Any]] | None
|
||||
) -> dict[str, Any] | None:
|
||||
if not tools:
|
||||
return None
|
||||
converted: list[dict[str, Any]] = []
|
||||
for tool in tools:
|
||||
if isinstance(tool, MutableMapping):
|
||||
converted.append(dict(tool))
|
||||
continue
|
||||
if isinstance(tool, AIFunction):
|
||||
converted.append({
|
||||
"toolSpec": {
|
||||
"name": tool.name,
|
||||
"description": tool.description or "",
|
||||
"inputSchema": {"json": tool.parameters()},
|
||||
}
|
||||
})
|
||||
continue
|
||||
logger.debug("Ignoring unsupported tool type for Bedrock: %s", type(tool))
|
||||
return {"tools": converted} if converted else None
|
||||
|
||||
def _convert_tool_choice(self, tool_choice: Any) -> dict[str, Any] | None:
|
||||
if not tool_choice:
|
||||
return None
|
||||
mode = tool_choice.mode if hasattr(tool_choice, "mode") else str(tool_choice)
|
||||
required_name = getattr(tool_choice, "required_function_name", None)
|
||||
match mode:
|
||||
case "auto":
|
||||
return {"auto": {}}
|
||||
case "none":
|
||||
return {"none": {}}
|
||||
case "required":
|
||||
if required_name:
|
||||
return {"tool": {"name": required_name}}
|
||||
return {"any": {}}
|
||||
case _:
|
||||
logger.debug("Unsupported tool choice mode for Bedrock: %s", mode)
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def _generate_tool_call_id() -> str:
|
||||
return f"tool-call-{uuid4().hex}"
|
||||
|
||||
def _process_converse_response(self, response: dict[str, Any]) -> ChatResponse:
|
||||
output = response.get("output", {})
|
||||
message = output.get("message", {})
|
||||
content_blocks = message.get("content", []) or []
|
||||
contents = self._parse_message_contents(content_blocks)
|
||||
chat_message = ChatMessage(role=Role.ASSISTANT, contents=contents, raw_representation=message)
|
||||
usage_details = self._parse_usage(response.get("usage") or output.get("usage"))
|
||||
finish_reason = self._map_finish_reason(output.get("completionReason") or response.get("stopReason"))
|
||||
response_id = response.get("responseId") or message.get("id")
|
||||
model_id = response.get("modelId") or output.get("modelId") or self.model_id
|
||||
return ChatResponse(
|
||||
response_id=response_id,
|
||||
messages=[chat_message],
|
||||
usage_details=usage_details,
|
||||
model_id=model_id,
|
||||
finish_reason=finish_reason,
|
||||
raw_representation=response,
|
||||
)
|
||||
|
||||
def _parse_usage(self, usage: dict[str, Any] | None) -> UsageDetails | None:
|
||||
if not usage:
|
||||
return None
|
||||
details = UsageDetails()
|
||||
if (input_tokens := usage.get("inputTokens")) is not None:
|
||||
details.input_token_count = input_tokens
|
||||
if (output_tokens := usage.get("outputTokens")) is not None:
|
||||
details.output_token_count = output_tokens
|
||||
if (total_tokens := usage.get("totalTokens")) is not None:
|
||||
details.additional_counts["bedrock.total_tokens"] = total_tokens
|
||||
return details
|
||||
|
||||
def _parse_message_contents(self, content_blocks: Sequence[MutableMapping[str, Any]]) -> list[Any]:
|
||||
contents: list[Any] = []
|
||||
for block in content_blocks:
|
||||
if text_value := block.get("text"):
|
||||
contents.append(TextContent(text=text_value, raw_representation=block))
|
||||
continue
|
||||
if (json_value := block.get("json")) is not None:
|
||||
contents.append(TextContent(text=json.dumps(json_value), raw_representation=block))
|
||||
continue
|
||||
tool_use = block.get("toolUse")
|
||||
if isinstance(tool_use, MutableMapping):
|
||||
tool_name = tool_use.get("name")
|
||||
if not tool_name:
|
||||
raise ServiceInvalidResponseError("Bedrock response missing required tool name in toolUse block.")
|
||||
contents.append(
|
||||
FunctionCallContent(
|
||||
call_id=tool_use.get("toolUseId") or self._generate_tool_call_id(),
|
||||
name=tool_name,
|
||||
arguments=tool_use.get("input"),
|
||||
raw_representation=block,
|
||||
)
|
||||
)
|
||||
continue
|
||||
tool_result = block.get("toolResult")
|
||||
if isinstance(tool_result, MutableMapping):
|
||||
status = (tool_result.get("status") or "success").lower()
|
||||
exception = None
|
||||
if status not in {"success", "ok"}:
|
||||
exception = RuntimeError(f"Bedrock tool result status: {status}")
|
||||
result_value = self._convert_bedrock_tool_result_to_value(tool_result.get("content"))
|
||||
contents.append(
|
||||
FunctionResultContent(
|
||||
call_id=tool_result.get("toolUseId") or self._generate_tool_call_id(),
|
||||
result=result_value,
|
||||
exception=exception,
|
||||
raw_representation=block,
|
||||
)
|
||||
)
|
||||
continue
|
||||
logger.debug("Ignoring unsupported Bedrock content block: %s", block)
|
||||
return contents
|
||||
|
||||
def _map_finish_reason(self, reason: str | None) -> FinishReason | None:
|
||||
if not reason:
|
||||
return None
|
||||
return FINISH_REASON_MAP.get(reason.lower())
|
||||
|
||||
def service_url(self) -> str:
|
||||
"""Returns the service URL for the Bedrock runtime in the configured AWS region.
|
||||
|
||||
Returns:
|
||||
str: The Bedrock runtime service URL.
|
||||
"""
|
||||
return f"https://bedrock-runtime.{self.region}.amazonaws.com"
|
||||
|
||||
def _convert_bedrock_tool_result_to_value(self, content: Any) -> Any:
|
||||
if not content:
|
||||
return None
|
||||
if isinstance(content, Sequence) and not isinstance(content, (str, bytes, bytearray)):
|
||||
values: list[Any] = []
|
||||
for item in content:
|
||||
if isinstance(item, MutableMapping):
|
||||
if (text_value := item.get("text")) is not None:
|
||||
values.append(text_value)
|
||||
continue
|
||||
if "json" in item:
|
||||
values.append(item["json"])
|
||||
continue
|
||||
values.append(item)
|
||||
return values[0] if len(values) == 1 else values
|
||||
if isinstance(content, MutableMapping):
|
||||
if (text_value := content.get("text")) is not None:
|
||||
return text_value
|
||||
if "json" in content:
|
||||
return content["json"]
|
||||
return content
|
||||
@@ -0,0 +1,90 @@
|
||||
[project]
|
||||
name = "agent-framework-bedrock"
|
||||
description = "Amazon Bedrock integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b251120"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
urls.release_notes = "https://github.com/microsoft/agent-framework/releases?q=tag%3Apython-1&expanded=true"
|
||||
urls.issues = "https://github.com/microsoft/agent-framework/issues"
|
||||
classifiers = [
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Development Status :: 4 - Beta",
|
||||
"Intended Audience :: Developers",
|
||||
"Programming Language :: Python :: 3",
|
||||
"Programming Language :: Python :: 3.10",
|
||||
"Programming Language :: Python :: 3.11",
|
||||
"Programming Language :: Python :: 3.12",
|
||||
"Programming Language :: Python :: 3.13",
|
||||
"Programming Language :: Python :: 3.14",
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core",
|
||||
"boto3>=1.35.0,<2.0.0",
|
||||
"botocore>=1.35.0,<2.0.0",
|
||||
]
|
||||
|
||||
|
||||
[tool.uv]
|
||||
prerelease = "if-necessary-or-explicit"
|
||||
environments = [
|
||||
"sys_platform == 'darwin'",
|
||||
"sys_platform == 'linux'",
|
||||
"sys_platform == 'win32'"
|
||||
]
|
||||
|
||||
[tool.uv-dynamic-versioning]
|
||||
fallback-version = "0.0.0"
|
||||
|
||||
[tool.pytest.ini_options]
|
||||
testpaths = 'tests'
|
||||
addopts = "-ra -q -r fEX"
|
||||
asyncio_mode = "auto"
|
||||
asyncio_default_fixture_loop_scope = "function"
|
||||
filterwarnings = []
|
||||
timeout = 120
|
||||
|
||||
[tool.ruff]
|
||||
extend = "../../pyproject.toml"
|
||||
|
||||
[tool.coverage.run]
|
||||
omit = [
|
||||
"**/__init__.py"
|
||||
]
|
||||
|
||||
[tool.pyright]
|
||||
extends = "../../pyproject.toml"
|
||||
|
||||
[tool.mypy]
|
||||
plugins = ['pydantic.mypy']
|
||||
strict = true
|
||||
python_version = "3.10"
|
||||
ignore_missing_imports = true
|
||||
disallow_untyped_defs = true
|
||||
no_implicit_optional = true
|
||||
check_untyped_defs = true
|
||||
warn_return_any = true
|
||||
show_error_codes = true
|
||||
warn_unused_ignores = false
|
||||
disallow_incomplete_defs = true
|
||||
disallow_untyped_decorators = true
|
||||
|
||||
[tool.bandit]
|
||||
targets = ["agent_framework_bedrock"]
|
||||
exclude_dirs = ["tests"]
|
||||
|
||||
[tool.poe]
|
||||
executor.type = "uv"
|
||||
include = "../../shared_tasks.toml"
|
||||
|
||||
[tool.poe.tasks]
|
||||
mypy = "mypy --config-file $POE_ROOT/pyproject.toml agent_framework_bedrock"
|
||||
test = "pytest --cov=agent_framework_bedrock --cov-report=term-missing:skip-covered tests"
|
||||
|
||||
[build-system]
|
||||
requires = ["hatchling"]
|
||||
build-backend = "hatchling.build"
|
||||
@@ -0,0 +1,64 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
from collections.abc import Sequence
|
||||
|
||||
from agent_framework import (
|
||||
AgentRunResponse,
|
||||
ChatAgent,
|
||||
FunctionCallContent,
|
||||
FunctionResultContent,
|
||||
Role,
|
||||
TextContent,
|
||||
ToolMode,
|
||||
ai_function,
|
||||
)
|
||||
|
||||
from agent_framework_bedrock import BedrockChatClient
|
||||
|
||||
|
||||
@ai_function
|
||||
def get_weather(city: str) -> dict[str, str]:
|
||||
"""Return a mock forecast for the requested city."""
|
||||
normalized = city.strip() or "New York"
|
||||
return {"city": normalized, "forecast": "72F and sunny"}
|
||||
|
||||
|
||||
async def main() -> None:
|
||||
"""Run the Bedrock sample agent, invoke the weather tool, and log the response."""
|
||||
agent = ChatAgent(
|
||||
chat_client=BedrockChatClient(),
|
||||
instructions="You are a concise travel assistant.",
|
||||
name="BedrockWeatherAgent",
|
||||
tool_choice=ToolMode.AUTO,
|
||||
tools=[get_weather],
|
||||
)
|
||||
|
||||
response = await agent.run("Use the weather tool to check the forecast for new york.")
|
||||
logging.info("\nAssistant reply:", response.text or "<no text returned>")
|
||||
_log_response(response)
|
||||
|
||||
|
||||
def _log_response(response: AgentRunResponse) -> None:
|
||||
logging.info("\nConversation transcript:")
|
||||
for idx, message in enumerate(response.messages, start=1):
|
||||
tag = f"{idx}. {message.role.value if isinstance(message.role, Role) else message.role}"
|
||||
_log_contents(tag, message.contents)
|
||||
|
||||
|
||||
def _log_contents(tag: str, contents: Sequence[object]) -> None:
|
||||
logging.info(f"[{tag}] {len(contents)} content blocks")
|
||||
for idx, content in enumerate(contents, start=1):
|
||||
if isinstance(content, TextContent):
|
||||
logging.info(f" {idx}. text -> {content.text}")
|
||||
elif isinstance(content, FunctionCallContent):
|
||||
logging.info(f" {idx}. tool_call ({content.name}) -> {content.arguments}")
|
||||
elif isinstance(content, FunctionResultContent):
|
||||
logging.info(f" {idx}. tool_result ({content.call_id}) -> {content.result}")
|
||||
else: # pragma: no cover - defensive
|
||||
logging.info(f" {idx}. {content.type}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -0,0 +1,69 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
from typing import Any
|
||||
|
||||
import pytest
|
||||
from agent_framework import ChatMessage, ChatOptions, Role, TextContent
|
||||
from agent_framework.exceptions import ServiceInitializationError
|
||||
|
||||
from agent_framework_bedrock import BedrockChatClient
|
||||
|
||||
|
||||
class _StubBedrockRuntime:
|
||||
def __init__(self) -> None:
|
||||
self.calls: list[dict[str, Any]] = []
|
||||
|
||||
def converse(self, **kwargs: Any) -> dict[str, Any]:
|
||||
self.calls.append(kwargs)
|
||||
return {
|
||||
"modelId": kwargs["modelId"],
|
||||
"responseId": "resp-123",
|
||||
"usage": {"inputTokens": 10, "outputTokens": 5, "totalTokens": 15},
|
||||
"output": {
|
||||
"completionReason": "end_turn",
|
||||
"message": {
|
||||
"id": "msg-1",
|
||||
"role": "assistant",
|
||||
"content": [{"text": "Bedrock says hi"}],
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def test_get_response_invokes_bedrock_runtime() -> None:
|
||||
stub = _StubBedrockRuntime()
|
||||
client = BedrockChatClient(
|
||||
model_id="amazon.titan-text",
|
||||
region="us-west-2",
|
||||
client=stub,
|
||||
)
|
||||
|
||||
messages = [
|
||||
ChatMessage(role=Role.SYSTEM, contents=[TextContent(text="You are concise.")]),
|
||||
ChatMessage(role=Role.USER, contents=[TextContent(text="hello")]),
|
||||
]
|
||||
|
||||
response = asyncio.run(client.get_response(messages=messages, chat_options=ChatOptions(max_tokens=32)))
|
||||
|
||||
assert stub.calls, "Expected the runtime client to be called"
|
||||
payload = stub.calls[0]
|
||||
assert payload["modelId"] == "amazon.titan-text"
|
||||
assert payload["messages"][0]["content"][0]["text"] == "hello"
|
||||
assert response.messages[0].contents[0].text == "Bedrock says hi"
|
||||
assert response.usage_details and response.usage_details.input_token_count == 10
|
||||
|
||||
|
||||
def test_build_request_requires_non_system_messages() -> None:
|
||||
client = BedrockChatClient(
|
||||
model_id="amazon.titan-text",
|
||||
region="us-west-2",
|
||||
client=_StubBedrockRuntime(),
|
||||
)
|
||||
|
||||
messages = [ChatMessage(role=Role.SYSTEM, contents=[TextContent(text="Only system text")])]
|
||||
|
||||
with pytest.raises(ServiceInitializationError):
|
||||
client._build_converse_request(messages, ChatOptions())
|
||||
@@ -0,0 +1,133 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
import pytest
|
||||
from agent_framework import (
|
||||
AIFunction,
|
||||
ChatMessage,
|
||||
ChatOptions,
|
||||
FunctionCallContent,
|
||||
FunctionResultContent,
|
||||
Role,
|
||||
TextContent,
|
||||
ToolMode,
|
||||
)
|
||||
from pydantic import BaseModel
|
||||
|
||||
from agent_framework_bedrock._chat_client import BedrockChatClient, BedrockSettings
|
||||
|
||||
|
||||
class _WeatherArgs(BaseModel):
|
||||
location: str
|
||||
|
||||
|
||||
def _build_client() -> BedrockChatClient:
|
||||
fake_runtime = MagicMock()
|
||||
fake_runtime.converse.return_value = {}
|
||||
return BedrockChatClient(model_id="test-model", client=fake_runtime)
|
||||
|
||||
|
||||
def _dummy_weather(location: str) -> str: # pragma: no cover - helper
|
||||
return f"Weather in {location}"
|
||||
|
||||
|
||||
def test_settings_load_from_environment(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
monkeypatch.setenv("BEDROCK_REGION", "us-west-2")
|
||||
monkeypatch.setenv("BEDROCK_CHAT_MODEL_ID", "anthropic.claude-v2")
|
||||
settings = BedrockSettings()
|
||||
assert settings.region == "us-west-2"
|
||||
assert settings.chat_model_id == "anthropic.claude-v2"
|
||||
|
||||
|
||||
def test_build_request_includes_tool_config() -> None:
|
||||
client = _build_client()
|
||||
|
||||
tool = AIFunction(name="get_weather", description="desc", func=_dummy_weather, input_model=_WeatherArgs)
|
||||
options = ChatOptions(tools=[tool], tool_choice=ToolMode.REQUIRED("get_weather"))
|
||||
messages = [ChatMessage(role=Role.USER, contents=[TextContent(text="hi")])]
|
||||
|
||||
request = client._build_converse_request(messages, options)
|
||||
|
||||
assert request["toolConfig"]["tools"][0]["toolSpec"]["name"] == "get_weather"
|
||||
assert request["toolConfig"]["toolChoice"] == {"tool": {"name": "get_weather"}}
|
||||
|
||||
|
||||
def test_build_request_serializes_tool_history() -> None:
|
||||
client = _build_client()
|
||||
options = ChatOptions()
|
||||
messages = [
|
||||
ChatMessage(role=Role.USER, contents=[TextContent(text="how's weather?")]),
|
||||
ChatMessage(
|
||||
role=Role.ASSISTANT,
|
||||
contents=[FunctionCallContent(call_id="call-1", name="get_weather", arguments='{"location": "SEA"}')],
|
||||
),
|
||||
ChatMessage(
|
||||
role=Role.TOOL,
|
||||
contents=[FunctionResultContent(call_id="call-1", result={"answer": "72F"})],
|
||||
),
|
||||
]
|
||||
|
||||
request = client._build_converse_request(messages, options)
|
||||
assistant_block = request["messages"][1]["content"][0]["toolUse"]
|
||||
result_block = request["messages"][2]["content"][0]["toolResult"]
|
||||
|
||||
assert assistant_block["name"] == "get_weather"
|
||||
assert assistant_block["input"] == {"location": "SEA"}
|
||||
assert result_block["toolUseId"] == "call-1"
|
||||
assert result_block["content"][0]["json"] == {"answer": "72F"}
|
||||
|
||||
|
||||
def test_process_response_parses_tool_use_and_result() -> None:
|
||||
client = _build_client()
|
||||
response = {
|
||||
"modelId": "model",
|
||||
"output": {
|
||||
"message": {
|
||||
"id": "msg-1",
|
||||
"content": [
|
||||
{"toolUse": {"toolUseId": "call-1", "name": "get_weather", "input": {"location": "NYC"}}},
|
||||
{"text": "Calling tool"},
|
||||
],
|
||||
},
|
||||
"completionReason": "tool_use",
|
||||
},
|
||||
}
|
||||
|
||||
chat_response = client._process_converse_response(response)
|
||||
contents = chat_response.messages[0].contents
|
||||
|
||||
assert isinstance(contents[0], FunctionCallContent)
|
||||
assert contents[0].name == "get_weather"
|
||||
assert isinstance(contents[1], TextContent)
|
||||
assert chat_response.finish_reason == client._map_finish_reason("tool_use")
|
||||
|
||||
|
||||
def test_process_response_parses_tool_result() -> None:
|
||||
client = _build_client()
|
||||
response = {
|
||||
"modelId": "model",
|
||||
"output": {
|
||||
"message": {
|
||||
"id": "msg-2",
|
||||
"content": [
|
||||
{
|
||||
"toolResult": {
|
||||
"toolUseId": "call-1",
|
||||
"status": "success",
|
||||
"content": [{"json": {"answer": 42}}],
|
||||
}
|
||||
}
|
||||
],
|
||||
},
|
||||
"completionReason": "end_turn",
|
||||
},
|
||||
}
|
||||
|
||||
chat_response = client._process_converse_response(response)
|
||||
contents = chat_response.messages[0].contents
|
||||
|
||||
assert isinstance(contents[0], FunctionResultContent)
|
||||
assert contents[0].result == {"answer": 42}
|
||||
Reference in New Issue
Block a user