Feature proposal: inherited recursion-depth budget for Agent.as_tool delegation
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
调研方向
Start with Agent.as_tool() in src/agents/agent.py, then trace how nested calls create Runner.run() and Runner.run_streamed() executions and how their turn limits are resolved. Review the existing runtime governance discussion #2775 and per-agent max_turns request #551 before deciding whether the proposed inherited depth limit fits the SDK. Done means maintainers settle the scope and semantics, including concurrent task inheritance and resumed workflows.
由索引模型根据 Issue 内容生成。
描述
Summary
I would like to propose an opt-in, inherited delegation-depth limit for Agent.as_tool() to help applications bound recursive or multi-agent delegation trees.
This is not a claim of a security vulnerability or a defect in max_turns. I understand that max_turns limits an individual Runner.run(), and a nested agent tool starts another run. The motivation is to offer an explicit SDK-side safety primitive when applications require a depth limit over a delegation chain, rather than just each run.
Reproduced behavior (no API access)
I ran a fully offline agents.testing.ScriptedModel test against public main commit cd26bbbc52847845fde73b9952b51e62e2bcbdc0 (v0.24.0 source) using distinct call IDs and a deliberately finite, four-delegation script.
- Outer
Runner.run(..., max_turns=1) - Recursive
Agent.as_tool(..., max_turns=1) - Unmodified SDK: 5 model calls occur before the outer run raises
MaxTurnsExceeded. This is consistent with per-run limits. - Candidate guard with
max_agent_tool_depth=1: 2 model calls occur; the next nested agent tool fails before starting another child run, including through streaming.
The source boundary is Agent.as_tool() in src/agents/agent.py, where each nested invocation creates its own Runner.run() / Runner.run_streamed() with a separately resolved turn limit.
Proposed narrow, compatible implementation
- Append optional
max_agent_tool_depth: int | None = NonetoAgent.as_tool().Nonepreserves current behavior. - Track active agent-tool depth in an async context using
ContextVar, withfinallyreset. - Propagate a configured limit through other agents'
as_tool()wrappers, even if those descendants do not configure a limit. Children may tighten but cannot relax an inherited bound. - Reject excessive delegation before another child run is started.
- No dependencies, persisted-state changes or wire-protocol changes.
Reproducible public research repository: https://github.com/BlackRonin-coder/openai-agents-recursive-budget-research
It contains the unmodified SDK reproducer, opt-in two-file patch, synthetic tests, and local verification log. The published candidate passed 1,188 relevant tests, 63 skipped, on macOS with Python 3.12.15; Ruff checks and a pristine-source patch-application check passed. I am not claiming comprehensive CI, independent validation or OpenAI endorsement.
Limitations and maintainer questions
This is a nesting-depth limit, not a root-owned cumulative model-turn, token, cost, wall-clock or cross-process execution budget. Application-initiated independent Runner.run() calls are outside this implementation. Further review is needed around concurrent task inheritance and resumed/persisted workflows.
- Would an opt-in inherited agent-tool depth limit be useful as a first-class SDK control?
- Or would you prefer a root-owned, cumulative execution budget with explicit checkpoint/cancellation semantics?
- If there is an existing supported mechanism addressing this exact delegation-depth use case, I would welcome a pointer and will revise or close the proposal.
Related but broader prior art: runtime governance discussions (e.g. #2775), and the existing per-agent max_turns feature request (#551). I did not find a directly equivalent recursive delegation-depth control in the currently indexed issues/PRs. This is offered as independently reproducible engineering research, not a claim of being the first person to explore recursive agent budgets.
Thank you for considering it.
- 主要语言
- Python
- 星标
- 30.4k
- 派生
- 4.9k
- 平均合并
- 15 小时 42 分钟
- 30 天内合并 PR
- 124
环境准备
- 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。
openai/openai-agents-python 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 77/100
openai/openai-agents-python#5451 · 1 条评论 ·
维护者通常 1 天内回复
-
fix(typing): explicitly specialize ToolContext[Any] in ToolFunctionWithToolContext可能重新可做 @AbarnaaSree 于 12 天前认领，目前没有进行中的 PR。 未关闭
难度 1/5 1 小时以内 新手友好度 85/100
openai/openai-agents-python#5387 · 4 条评论 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 53/100
openai/openai-agents-python#5450 ·
维护者通常 1 天内回复
-
function_tool rejects valid arguments when a parameter uses Pydantic strict mode (Enum, date, UUID)可能已有人在做 @Lahari25 于 1 天前认领。 未关闭
难度 3/5 1-2 天 新手友好度 65/100
openai/openai-agents-python#5448 · 2 条评论 ·
维护者通常 1 天内回复
-
难度 3/5 1-2 天 新手友好度 65/100
openai/openai-agents-python#5447 · 3 条评论 ·
维护者通常 1 天内回复
查看 openai/openai-agents-python 的全部 Issue
相似的 Issue
-
bug
难度 1/5 1 小时以内 新手友好度 86/100
awslabs/visual-asset-management-system#937 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 68/100
-
follow-up
难度 2/5 1-3 小时 新手友好度 78/100
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 83/100
维护者通常 3 天内回复
-
难度 2/5 1-3 小时 新手友好度 70/100
维护者通常 2 天内回复