Selective, CHANGELOG-driven version bumps for the 2026-06-18 release. Released tier: agent-framework-core and the root agent-framework go to 1.9.0 (minor). Core ships new public APIs (agent-loop middleware, tool-approval middleware and harness integration, shell-tool harness integration, AG-UI thread snapshot persistence, context-provider telemetry) plus two behavioral breaking changes on evolving surfaces: MCP sampling now denies server-initiated requests by default, and the FileAccess tools were aligned with the .NET implementation. These are treated as within-1.x changes because every package caps core at <2; a major bump would require rewriting those caps. The foundry and openai packages go to 1.8.2 (patch, bug fixes only). The root agent-framework-core[all] pin was moved to 1.9.0 in lockstep with core. Release-candidate tier: ag-ui to 1.0.0rc5 and declarative to 1.0.0rc2 for their respective changes. orchestrations is promoted to stable 1.0.0; PACKAGE_STATUS and the README install hint were updated accordingly. Prerelease tier (new Pacific date stamp 260618): anthropic (beta), azure-contentunderstanding (alpha) and foundry-hosting (alpha). No beta cohort bump was applied; only packages with changes this cycle were stamped. Dependency floors: following the established convention, the core floor was raised to >=1.9.0 on every non-core package bumped this cycle, preserving the existing <2 upper bound. Also resolves two pre-existing failures in the dependency-bounds validator that are unrelated to the version bumps. Hosted-environment detection now catches a bare ImportError so optional Foundry hosting probing cannot crash user-agent setup. The harness shell-tool integration, which lazily imports the separate agent-framework-tools package to avoid a circular runtime dependency, is now type-checked and tested in isolated environments via a core dev dependency-group, with the shell-tool tests guarded to skip when that package is absent.
4.7 KiB
Agent Framework Orchestrations
Orchestration patterns for Microsoft Agent Framework. This package provides high-level builders for common multi-agent workflow patterns.
Installation
pip install agent-framework-orchestrations
Orchestration Patterns
SequentialBuilder
Chain agents/executors in sequence, passing conversation context along:
from agent_framework.orchestrations import SequentialBuilder
workflow = SequentialBuilder(participants=[agent1, agent2, agent3]).build()
# Preserve agent1 and agent2 as visible progress, while the default builder output remains Workflow Output.
workflow = SequentialBuilder(
participants=[agent1, agent2, agent3],
intermediate_output_from=[agent1, agent2],
).build()
ConcurrentBuilder
Fan-out to multiple agents in parallel, then aggregate results:
from agent_framework.orchestrations import ConcurrentBuilder
workflow = ConcurrentBuilder(participants=[agent1, agent2, agent3]).build()
HandoffBuilder
Decentralized agent routing where agents decide handoff targets:
from agent_framework.orchestrations import HandoffBuilder
workflow = (
HandoffBuilder()
.participants([triage, billing, support])
.with_start_agent(triage)
.build()
)
GroupChatBuilder
Orchestrator-directed multi-agent conversations:
from agent_framework.orchestrations import GroupChatBuilder
workflow = GroupChatBuilder(
participants=[agent1, agent2],
selection_func=my_selector,
intermediate_output_from=[agent1, agent2],
).build()
MagenticBuilder
Sophisticated multi-agent orchestration using the Magentic One pattern:
from agent_framework.orchestrations import MagenticBuilder
workflow = MagenticBuilder(
participants=[researcher, writer, reviewer],
manager_agent=manager_agent,
intermediate_output_from=[researcher, writer, reviewer],
).build()
Output Selection
Orchestration builders expose Workflow Output selection using participant names. The core rule is that output_from
is an allow-list for Workflow Output, not a routing rule for every other participant output. Unselected participant
payloads are hidden unless intermediate_output_from explicitly selects them as Intermediate Output.
output_fromdesignates participant emissions as Workflow Output (type='output'events).intermediate_output_fromdesignates participant emissions as Intermediate Output (type='intermediate'events).
If neither list is provided, each builder uses its documented default Workflow Output contract. Sequential emits the last participant; Concurrent, GroupChat, and Magentic emit their aggregator/orchestrator/manager output; Handoff emits participants.
| Selection | Workflow Output | Intermediate Output | Hidden payloads |
|---|---|---|---|
| Omit both selections | Builder default Workflow Output contract | None | Builder-specific non-output participant payloads |
output_from="all" |
Every output-capable participant | None | None |
output_from=[writer] |
Only writer |
None | All other participant payloads |
output_from=[writer], intermediate_output_from="all_other" |
Only writer |
Every output-capable participant not selected by output_from |
None |
intermediate_output_from="all_other" |
None, except builder-internal default output executors where applicable | Every output-capable participant | Builder-internal plumbing payloads |
output_from=[], intermediate_output_from="all_other" |
None, except builder-internal default output executors where applicable | Every output-capable participant | Builder-internal plumbing payloads |
output_from=[writer], intermediate_output_from=[researcher, reviewer] |
Only writer |
researcher and reviewer |
Any other participant payloads |
Invalid selections fail at construction or build time:
| Invalid selection | Why it fails |
|---|---|
output_from="all_other" |
"all_other" is only valid for intermediate_output_from |
intermediate_output_from="all" |
"all" is only valid for output_from |
| The same participant in both selections | One payload cannot be both Workflow Output and Intermediate Output |
| Duplicate participant selections | Duplicates are treated as configuration errors |
| Unknown participant selections | Typos and missing participants are rejected |
output_from=[], intermediate_output_from=[] |
Both explicit selections are empty |
When an orchestration is wrapped with workflow.as_agent(), Workflow Output becomes normal response text. Intermediate
Output becomes text_reasoning content so callers can inspect progress without changing .text behavior.
Documentation
For more information, see the Agent Framework documentation.