python-1.0.0rc1
·
178 commits
to main
since this release
[1.0.0rc1] - 2026-02-19
Release candidate for agent-framework-core and agent-framework-azure-ai packages.
Added
- agent-framework-core: Add default in-memory history provider for workflow agents (#3918)
- agent-framework-core: Durable support for workflows (#3630)
Changed
- agent-framework-core: [BREAKING] Scope provider state by
source_idand standardize source IDs (#3995) - agent-framework-core: [BREAKING] Fix chat/agent message typing alignment (#3920)
- agent-framework-core: [BREAKING] Remove
FunctionTool[Any]compatibility shim for schema passthrough (#3907) - agent-framework-core: Inject OpenTelemetry trace context into MCP requests (#3780)
- agent-framework-core: Replace wildcard imports with explicit imports (#3908)
Fixed
- agent-framework-core: Fix hosted MCP tool approval flow for all session/streaming combinations (#4054)
- agent-framework-core: Prevent repeating instructions in continued Responses API conversations (#3909)
- agent-framework-core: Add missing system instruction attribute to
invoke_agentspan (#4012) - agent-framework-core: Fix tool normalization and provider sample consolidation (#3953)
- agent-framework-azure-ai: Warn on unsupported AzureAIClient runtime tool/structured_output overrides (#3919)
- agent-framework-azure-ai-search: Improve Azure AI Search package test coverage (#4019)
- agent-framework-anthropic: Fix Anthropic option conflicts and manager parse retries (#4000)
- agent-framework-anthropic: Track and enforce 85%+ unit test coverage for anthropic package (#3926)
- agent-framework-azurefunctions: Achieve 85%+ unit test coverage for azurefunctions package (#3866)
- samples: Fix workflow, declarative, Redis, Anthropic, GitHub Copilot, Azure AI, MCP, eval, and migration samples (#4055, #4051, #4049, #4046, #4033, #4030, #4027, #4032, #4025, #4021, #4022, #4001)