-
Notifications
You must be signed in to change notification settings - Fork 2.4k
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
.NET: Foundry hosting rejects Harness local chat history marker when AllowStoredOutputEnabled is false
.NETUsage: [Issues, PRs], Target: .NetUsage: [Issues, PRs], Target: .NetStatus: Open.#8707 In microsoft/agent-framework;Python: [Feature]: Make public
runandget_responsemethods async in vNextpythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonvnextUsage: [Issues, PRs], Target: breaking-change features deferred to the next major releaseUsage: [Issues, PRs], Target: breaking-change features deferred to the next major releaseStatus: Open.#8703 In microsoft/agent-framework;Python: [Feature]: Move structured response parsing off
.valuein vNextpythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonvnextUsage: [Issues, PRs], Target: breaking-change features deferred to the next major releaseUsage: [Issues, PRs], Target: breaking-change features deferred to the next major releaseStatus: Open.#8704 In microsoft/agent-framework;Python: [Bug]: Mixed approval and Host results give a tool result the user role
pythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonreproducedUsage: [Issues], Target: all issues that can be reproduced by the triage workflowUsage: [Issues], Target: all issues that can be reproduced by the triage workflowworkflowsUsage: [Issues, PRs], Target: WorkflowsUsage: [Issues, PRs], Target: WorkflowsStatus: Open.#8700 In microsoft/agent-framework;Python: [Feature]: Roadmap for AnyIO-backed asyncio and Trio support
.NETUsage: [Issues, PRs], Target: .NetUsage: [Issues, PRs], Target: .NetpythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonStatus: Open.#8698 In microsoft/agent-framework;Python: [Bug]: BedrockChatClient stream=True returns the whole response in one update, so GPT-6 Sol/Luna first text arrives about 3x later
agentsUsage: [Issues, PRs], Target: Single agentUsage: [Issues, PRs], Target: Single agentpythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonreproducedUsage: [Issues], Target: all issues that can be reproduced by the triage workflowUsage: [Issues], Target: all issues that can be reproduced by the triage workflowStatus: Open.#8684 In microsoft/agent-framework;Python: [Bug]: BedrockChatClient drops images from user messages, so GPT-6 Sol/Luna answer without seeing them
agentsUsage: [Issues, PRs], Target: Single agentUsage: [Issues, PRs], Target: Single agentpythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonreproducedUsage: [Issues], Target: all issues that can be reproduced by the triage workflowUsage: [Issues], Target: all issues that can be reproduced by the triage workflowStatus: Open.#8682 In microsoft/agent-framework;Python: [Bug]: filter_values_equal equates booleans with numbers inside sets
agentsUsage: [Issues, PRs], Target: Single agentUsage: [Issues, PRs], Target: Single agentpythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonreproducedUsage: [Issues], Target: all issues that can be reproduced by the triage workflowUsage: [Issues], Target: all issues that can be reproduced by the triage workflowStatus: Open.#8679 In microsoft/agent-framework;Python: [Bug]: BedrockChatClient silently drops guardrailConfig and other Bedrock options, so GPT-6 Sol/Luna reasoning effort can't be set
agentsUsage: [Issues, PRs], Target: Single agentUsage: [Issues, PRs], Target: Single agentpythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonreproducedUsage: [Issues], Target: all issues that can be reproduced by the triage workflowUsage: [Issues], Target: all issues that can be reproduced by the triage workflowStatus: Open.#8678 In microsoft/agent-framework;.NET: [Bug]: AIAgent.RunStreamingAsync does not surface the final image from HostedImageGenerationTool
.NETUsage: [Issues, PRs], Target: .NetUsage: [Issues, PRs], Target: .NetagentsUsage: [Issues, PRs], Target: Single agentUsage: [Issues, PRs], Target: Single agentreproducedUsage: [Issues], Target: all issues that can be reproduced by the triage workflowUsage: [Issues], Target: all issues that can be reproduced by the triage workflowStatus: Open.#8674 In microsoft/agent-framework;Python: [Bug]: LocalShellTool never executes on a self-hosted Foundry agent since openai 1.14.4 - "No tool output found for shell call"
pythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonreproducedUsage: [Issues], Target: all issues that can be reproduced by the triage workflowUsage: [Issues], Target: all issues that can be reproduced by the triage workflowStatus: Open.#8663 In microsoft/agent-framework;Python: [Bug]: Tools with datetime, set or tuple parameters always fail argument validation
agentsUsage: [Issues, PRs], Target: Single agentUsage: [Issues, PRs], Target: Single agentpythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: PythonreproducedUsage: [Issues], Target: all issues that can be reproduced by the triage workflowUsage: [Issues], Target: all issues that can be reproduced by the triage workflowStatus: Open.