From 4b7578dee16f563097c89f4aaa00941ea4929e63 Mon Sep 17 00:00:00 2001 From: Eric Hansen Date: Wed, 11 Mar 2026 16:30:50 -0500 Subject: [PATCH] docs: Remove misleading RequestInfoExecutor references Replace references to non-existent RequestInfoExecutor class in MAGENTIC_README.md and STATE_MANAGEMENT.md with accurate RC1 API descriptions. Plan review is handled internally by the orchestrator via enable_plan_review=True and WorkflowEvent(type="request_info"). This addresses the confusion reported in #339 where users attempted to import RequestInfoExecutor based on documentation references. Closes #339 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --- agentic_ai/agents/agent_framework/STATE_MANAGEMENT.md | 2 +- .../agents/agent_framework/multi_agent/MAGENTIC_README.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/agentic_ai/agents/agent_framework/STATE_MANAGEMENT.md b/agentic_ai/agents/agent_framework/STATE_MANAGEMENT.md index f58c4be8b..c4b1d2923 100644 --- a/agentic_ai/agents/agent_framework/STATE_MANAGEMENT.md +++ b/agentic_ai/agents/agent_framework/STATE_MANAGEMENT.md @@ -408,7 +408,7 @@ class SessionMemoryCheckpointStorage(CheckpointStorage): 2. **Team agent** - `MagenticOrchestratorExecutor` automatically snapshots each participant’s `chat_history`. - - Checkpoints include outstanding tool requests (`RequestInfoExecutor` state). + - Checkpoints include outstanding tool requests and plan-review state managed by the orchestrator via `WorkflowEvent(type="request_info")`. - Ensure all custom executors implement `restore_state` to interpret snapshots after schema changes. 3. **Human-in-the-loop** diff --git a/agentic_ai/agents/agent_framework/multi_agent/MAGENTIC_README.md b/agentic_ai/agents/agent_framework/multi_agent/MAGENTIC_README.md index a6641d92c..5f997c725 100644 --- a/agentic_ai/agents/agent_framework/multi_agent/MAGENTIC_README.md +++ b/agentic_ai/agents/agent_framework/multi_agent/MAGENTIC_README.md @@ -128,7 +128,7 @@ When stalling, the manager calls `replan()`, which uses [`ORCHESTRATOR_TASK_LEDG 1. Registers **participants** (`participants()`), each either a `BaseAgent` or another `Executor`. 2. Configures the **manager** (`with_standard_manager()`). 3. Optionally enables **plan review**, **checkpointing**, and **unified callbacks**. -4. Builds a [`Workflow`](reference/agent-framework/python/packages/main/agent_framework/_workflow/_workflow.py) graph: orchestrator (start node), optional `RequestInfoExecutor` for plan review, and bidirectional edges to each agent executor. +4. Builds a [`Workflow`](reference/agent-framework/python/packages/main/agent_framework/_workflow/_workflow.py) graph: orchestrator (start node) with optional plan review enabled via `enable_plan_review=True`, and bidirectional edges to each agent executor. Plan review is handled internally by the orchestrator, which emits `WorkflowEvent(type="request_info")` events containing `MagenticPlanReviewRequest` data. ### 4.2 Workflow Context & State