Skip to content

Build and run agents you can see, understand and trust.

fix(schema): remove max_length constraints from SummarySchema fields and increase tool result limit (#1891)

qbc7d804c6054ae
diff --git a/README.md b/README.md
index 7864362a7..0b4e8d87b 100644
--- a/README.md
+++ b/README.md
@@ -73,6 +73,7 @@ rather than constraining them with strict prompts and opinionated orchestrations
## News
<!-- BEGIN NEWS -->
+- **[2026-06] `INTE`:** Mem0 supported. [Example](https://github.com/agentscope-ai/agentscope/tree/main/examples/long_term_memory) | [Docs](https://docs.agentscope.io/v2)
- **[2026-06] `FEAT`:** Agent Team supported. [Example](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent_service) | [Docs](https://docs.agentscope.io/v2/deploy/agent-team)
- **[2026-05] `RELS`:** AgentScope 2.0 released! [Docs](https://docs.agentscope.io/)
<!-- END NEWS -->
diff --git a/README_zh.md b/README_zh.md
index 260d2daa2..36c03e9a4 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -79,6 +79,7 @@ AgentScope 2.0 是一款面向生产、易于使用的智能体框架,提供
## 新闻
<!-- BEGIN NEWS -->
+- **[2026-06] `集成`:** 集成 Mem0 长期记忆。 [Example](https://github.com/agentscope-ai/agentscope/tree/main/examples/long_term_memory) | [Docs](https://docs.agentscope.io/v2)
- **[2026-06] `功能`:** 支持 Agent Team。[样例](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent_service) | [文档](https://docs.agentscope.io/zh/v2/deploy/agent-team)
- **[2026-05] `发布`:** AgentScope 2.0 已发布![文档](https://docs.agentscope.io/)
<!-- END NEWS -->
diff --git a/src/agentscope/agent/_config.py b/src/agentscope/agent/_config.py
index dc85eb3bd..39190cb27 100644
--- a/src/agentscope/agent/_config.py
+++ b/src/agentscope/agent/_config.py
@@ -10,14 +10,12 @@ class SummarySchema(BaseModel):
"""The compressed memory model, used to generate summary of old memories"""
task_overview: str = Field(
- max_length=300,
description=(
"The user's core request and success criteria.\n"
"Any clarifications or constraints they specified"
),
)
current_state: str = Field(
- max_length=300,
description=(
"What has been completed so far.\n"
"File created, modified, or analyzed (with paths if relevant).\n"
@@ -25,7 +23,6 @@ class SummarySchema(BaseModel):
),
)
important_discoveries: str = Field(
- max_length=300,
description=(
"Technical constraints or requirements uncovered.\n"
"Decisions made and their rationale.\n"
@@ -34,7 +31,6 @@ class SummarySchema(BaseModel):
),
)
next_steps: str = Field(
- max_length=200,
description=(
"Specific actions needed to complete the task.\n"
"Any blockers or open questions to resolve.\n"
@@ -42,7 +38,6 @@ class SummarySchema(BaseModel):
),
)
context_to_preserve: str = Field(
- max_length=300,
description=(
"User preferences or style requirements.\n"
"Domain-specific details that aren't obvious.\n"
@@ -116,7 +111,7 @@ class ContextConfig(BaseModel):
tool_result_limit: int = Field(
title="Tool Result Limit",
- default=3000,
+ default=50000,
description=(
"The maximum length of the tool results in tokens. "
"If exceeded, the tool result will be truncated."