菜单
Add planners to orxhestra agents for structured reasoning. Covers BasePlanner, PlanReActPlanner, and TaskPlanner.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | agent-planners |
| description | Add planners to orxhestra agents for structured reasoning. Covers BasePlanner, PlanReActPlanner, and TaskPlanner. |
Planners inject planning instructions into the system prompt before each LLM call.
from orxhestra import BasePlanner, ReadonlyContext, LlmRequest, LlmResponse
class MyPlanner(BasePlanner):
def build_planning_instruction(
self, ctx: ReadonlyContext, request: LlmRequest
) -> str | None:
return "Think step by step before acting. Plan before calling tools."
def process_planning_response(
self, ctx: ReadonlyContext, response: LlmResponse
) -> LlmResponse | None:
return None # no post-processing needed
Enforces structured planning tags — the agent must emit /*PLANNING*/ and /*FINAL_ANSWER*/ blocks.
from orxhestra import PlanReActPlanner, LlmAgent
agent = LlmAgent(
name="PlanningAgent",
model=model,
tools=[...],
planner=PlanReActPlanner(),
)
Maintains a task board in ctx.state and injects status into the system prompt. Pairs with ManageTasksTool.
from orxhestra import TaskPlanner, LlmAgent
planner = TaskPlanner()
agent = LlmAgent(
name="ProjectAgent",
model=model,
tools=[planner.get_manage_tasks_tool()],
planner=planner,
instructions=(
"Track your work with manage_tasks. "
"Initialize tasks at the start. Mark each complete when done."
),
)
The agent calls manage_tasks with actions: initialize, list, create, update, complete, remove.
Build orxhestra agent trees from declarative YAML orx files. Covers full schema, models, tools, agents, runner, and server.
Expose orxhestra agents as A2A protocol endpoints or connect to remote A2A agents.
Add callbacks to orxhestra agents for logging, monitoring, and error handling. Covers model and tool callbacks.
Add dynamic skills to orxhestra agents. Covers Skill, InMemorySkillStore, and skill discovery/loading tools.
Stream events from orxhestra agents including token-by-token output, sub-agent events via AgentTool, and Runner streaming.
Create and use tools with orxhestra agents. Covers function_tool, AgentTool, transfer tools, exit_loop, MCP tools, and CallContext.