MiniMax-M2.7 / M3: tool output not propagated between chained tool calls (design_workflow → validate_design)
还没有人认领这个 Issue。
评估
- 难度
- 5/5
- 预计耗时
- 一周以上
- 新手友好度
- 25/100
- Issue 类型
- 缺陷
- 描述清晰度
- 基本清楚
- 活跃度
- 冷清
- 领域
- ai
调研方向
从 harness-test-bench 设置和 smoke_all_tools_2 场景开始，然后检查 Task 2 (task_2_module_design) 及其 design_workflow → validate_design 调用。将 MiniMax-M2.7/M3 与 M2.5 进行比较；完成的标准是链式调用在 schema 有效的 validate_design 请求中收到完全一致的 design_workflow 结果。
由索引模型根据 Issue 内容生成。
描述
Capability area: Agent harness / Tool use
What does M2.7 fail to do for you?
MiniMax-M2.7 fails to produce a valid JSON schema conforming to the validate_design tool definition when chaining from design_workflow.
What would "good" look like in M3?
validate_design receives a valid JSON schema that conforms to the tool's parameter definition — populated from the actual design_workflow result, not reconstructed from model reasoning.
Summary
MiniMax-M2.7 and MiniMax-M3 both fail to propagate tool output across a sequential tool call chain. When design_workflow returns a schema object, both models call the next tool (validate_design) with a schema that does not match the returned output — either reconstructed, incomplete, or structurally invalid against the tool definition.
MiniMax-M2.5 does not reproduce this behavior.
Environment
| Field | Value |
|---|---|
| Models affected | MiniMax-M2.7, MiniMax-M3 |
| Model passing | MiniMax-M2.5 |
| Endpoint | OpenRouter |
| Tool calling | Sequential 2-step chain |
| Observed | 2026-06-17 (UTC+8) |
Expected behavior
design_workflowis called and returns a schema object- The model reads the tool result
validate_designis called withschemaset to the exact object returned in step 1, conforming to the tool's JSON schema definition
Actual behavior
The model calls validate_design with a schema argument that does not match the design_workflow output. The model appears to reconstruct the schema from internal reasoning rather than reading the tool result, producing a value that violates the tool's parameter schema — missing required fields or structurally incorrect.
Benchmark eval output:
issues: ["Validated design is missing fields: project name, client, start date, deadline, owner, budget"]
Tool call sequence observed
1. design_workflow(...)
→ returns: { name, information: [{name, type, ai_hint}, ...], states: [...], ... }
2. validate_design({ schema: <does not match step 1 output, fails tool schema validation> })
→ missing required information fields
Steps to reproduce
We have an open-source MCP tool benchmark that reproduces this consistently:
Repo: https://github.com/Inistate/harness-test-bench
- Clone the repo and follow the setup instructions
- Run the
smoke_all_tools_2scenario againstminimax/MiniMax-M2.7orminimax/MiniMax-M3 - Inspect Task 2 (
task_2_module_design) —validate_designwill be called with a schema that does not conform to the tool's parameter definition - Compare against a passing model (e.g.
minimax/MiniMax-M2.5) running the same scenario
Questions
- Is this a known regression from M2.5?
- Does the model read tool results back into context between sequential calls, or is this not guaranteed?
- Is there a recommended pattern to ensure tool output is forwarded as-is rather than reconstructed?
Workaround
We currently exclude M2.7 and M3 from workflows requiring sequential tool output propagation. A fix at the model level would be preferable.
References
Reproduced across multiple runs in an independent MCP tool benchmark. M2.5 passed consistently. M2.7 scored 3/5 and M3 scored 2/5, with the T2 chain failing on every run for both models.
- 主要语言
- 没有语言数据
- 星标
- 489
- 派生
- 59
- PR 合并指标
- 30 天内没有已合并 PR
环境准备
这个项目没有提供开发容器、Dockerfile 或贡献指南，环境需要你自己搭建：先看它的 README，通用步骤见我们的新手贡献指南。
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。
MiniMax-AI/MiniMax-M3 的其他 Issue
-
难度 1/5 1 小时以内 新手友好度 90/100
MiniMax-AI/MiniMax-M3#34 · 1 个 reaction ·
-
[M2.7 Bug]未关闭bug
难度 4/5 3-5 天 新手友好度 45/100
MiniMax-AI/MiniMax-M3#35 ·
-
enhancement
难度 4/5 3-5 天 新手友好度 45/100
MiniMax-AI/MiniMax-M3#33 ·
-
难度 2/5 1-3 小时 新手友好度 48/100
MiniMax-AI/MiniMax-M3#32 ·
-
bug
难度 4/5 3-5 天 新手友好度 42/100
MiniMax-AI/MiniMax-M3#31 ·
查看 MiniMax-AI/MiniMax-M3 的全部 Issue
相似的 Issue
-
area/sessions comp/tui needs-repro P2 sweeper:risk-session-state type/bug
难度 2/5 1-3 小时 新手友好度 74/100
NousResearch/hermes-agent#127449 · 1 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 88/100
rohitg00/agentmemory#1435 ·
维护者通常 3 天内回复
-
难度 2/5 1-3 小时 新手友好度 85/100
higress-group/higress#4839 ·
维护者通常 1 天内回复
-
.NET triage
难度 2/5 1-3 小时 新手友好度 74/100
microsoft/agent-framework#8811 ·
维护者通常 1 天内回复
-
org:external package:deepagents priority:backlog topic:models topic:multimodal type:feature
难度 2/5 1-3 小时 新手友好度 62/100
langchain-ai/deepagents#6599 ·
维护者通常 1 天内回复