Python: [Bug]: A handoff autonomous turn limit of 0 silently becomes the default 50 turns
维护者通常 1 天内回复
评估
这个 Issue 还没有评估数据。
描述
Description
HandoffAgentExecutor.__init__ folds the configured autonomous turn limit through truthiness (python/packages/orchestrations/agent_framework_orchestrations/_handoff.py:282):
self._autonomous_mode_turn_limit = autonomous_mode_turn_limit or _DEFAULT_AUTONOMOUS_TURN_LIMIT
with _DEFAULT_AUTONOMOUS_TURN_LIMIT = 50 (:229), so an explicitly configured 0 is silently replaced by 50. 0 is the natural way for a caller to say "this agent must not continue on its own", and the public builder path makes it reachable without constructing the executor directly: HandoffBuilder.with_autonomous_mode(turn_limits={agent_id: 0}) stores the mapping and build() hands it to the executor unchanged through self._autonomous_mode_turn_limits.get(id, None) (:1210), where the or above then swallows it.
The consumer treats the value as a plain counter bound (:480):
if self._autonomous_mode and self._autonomous_mode_turns < self._autonomous_mode_turn_limit:
With the intended limit of 0 that branch is never taken, so the executor emits request_info as soon as the agent answers without requesting a handoff. With the swallowed 50, the executor instead injects the autonomous prompt and re-runs the agent up to 50 more times first. The docstring describes the default as belonging to the unset case — "Maximum number of autonomous turns before returning control to the user. If not provided, a default turn limit will be used." (:934) — and "not provided" is None, not 0.
The cost is not cosmetic: a caller who asks one agent to stop autonomously gets up to 50 unwanted model calls and 50 unwanted replies before control returns.
Code Sample
Reproduces with the module's existing mock harness, no API keys needed. Added to python/packages/orchestrations/tests/test_handoff.py, right after test_autonomous_mode_resumes_user_input_on_turn_limit:
async def test_autonomous_mode_zero_turn_limit_returns_control_immediately():
"""A turn limit of 0 means no autonomous continuation, not the default turn limit."""
triage_client = MockChatClient(name="triage", handoff_to="worker")
worker_client = MockChatClient(name="worker")
triage: Agent[Any] = Agent(id="triage", name="triage", client=triage_client,
require_per_service_call_history_persistence=True)
worker: Agent[Any] = Agent(id="worker", name="worker", client=worker_client,
require_per_service_call_history_persistence=True)
workflow = (
HandoffBuilder(participants=_as_handoff_agents(triage, worker), termination_condition=lambda _: False)
.with_start_agent(_as_handoff_agent(triage))
.with_autonomous_mode(agents=[worker], turn_limits={resolve_agent_id(worker): 0})
.build()
)
events = await _drain(workflow.run("Start", stream=True))
assert len(worker_client.received_messages) == 1, "A zero turn limit must not grant autonomous turns"
Error Messages / Stack Traces
No exception is raised — the agent just keeps going. The assertion above fails on main:
> assert len(worker_client.received_messages) == 1, "A zero turn limit must not grant autonomous turns"
E AssertionError: A zero turn limit must not grant autonomous turns
E assert 51 == 1
packages\orchestrations\tests\test_handoff.py:1358
51 = the one reply the worker owes the handoff plus the 50 autonomous turns the configured 0 was supposed to forbid.
Package Versions
agent-framework-core: 1.19.0, agent-framework-orchestrations: 1.2.0 (source main @ a91fe668)
Additional Context
HandoffAgentExecutor is the only consumer of turn_limits, and the same truthiness pattern is not used for the other autonomous settings (prompts maps to prompts or {}, which is correct for a container), so replacing the or with an is None check is the whole fix.
#6328 lists "Turn limit = 0 (default limit of 50 applied)" as one of its observations while investigating a separate 49-vs-50 boundary question with live models. This issue isolates only the 0-becomes-default part, which is deterministic and unit-testable; the boundary question in #6328 is unaffected by this and stays open.
- 主要语言
- Python
- 星标
- 14.2k
- 派生
- 2.5k
- 平均合并
- 2 天 9 小时
- 30 天内合并 PR
- 384
环境准备
在浏览器里用你自己的 GitHub 账号启动这个项目的开发容器。
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
microsoft/agent-framework 的其他 Issue
-
Python: [Bug]: A non-positive MCP request timeout silently disables the timeout可能已有人在做 @jpalvarezl 于 6 天前认领。 未关闭python
难度 2/5 1-3 小时 新手友好度 82/100
microsoft/agent-framework#9313 · 已指派 1 人 ·
维护者通常 1 天内回复
-
.NET python triage
难度 1/5 1 小时以内 新手友好度 85/100
microsoft/agent-framework#9092 · 1 条评论 ·
维护者通常 1 天内回复
-
Python: raw-data content mappings lose annotations and attachment metadata可能已有人在做 @moonbox3 于 20 天前认领。 未关闭python triage
难度 2/5 1-3 小时 新手友好度 78/100
microsoft/agent-framework#8632 · 2 条评论 ·
维护者通常 1 天内回复
-
Python: Clarify when to use platform可能已有人在做 @eavanvalkenburg 于 19 天前认领。 未关闭python triage
难度 2/5 1-3 小时 新手友好度 68/100
microsoft/agent-framework#8599 · 1 条评论 ·
维护者通常 1 天内回复
-
.NET compaction documentation
难度 1/5 1 小时以内 新手友好度 82/100
microsoft/agent-framework#4629 · 1 条评论 ·
维护者通常 1 天内回复
查看 microsoft/agent-framework 的全部 Issue
相似的 Issue
-
`image_generation`: `max_retries` is ignored for OpenAI-compatible providers (always 2 retries)可能已有人在做 @ericz7900 今天认领。 未关闭llm translation
难度 2/5 1-3 小时 新手友好度 77/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 72/100
rheeloaded/paperpull#117 ·
维护者通常 1 天内回复
-
bug
难度 2/5 1-3 小时 新手友好度 82/100
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 65/100
agenda-tech-brasil/agenda-tech-brasil#1619 · 1 条评论 ·
-
process
难度 1/5 1-3 小时 新手友好度 76/100
pyrite-wiki/pyrite#1036 ·
维护者通常 1 天内回复