scriptoriumadmin/ReMe
1
0
Fork 0
mirror of https://github.com/agentscope-ai/ReMe.git synced 2026-08-28 05:25:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

refactor(memory): restructure file-based memory components and enhance message handling (#145)

Browse source
This commit is contained in:
jinliyl 2026-03-07 15:22:56 +08:00 • committed by GitHub
parent d0c9d89092
commit 5e08aa48b8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 148 additions and 105 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
README.md
View file

@ -20,7 +20,7 @@
<strong>A memory management toolkit for AI agents — Remember Me, Refine Me.</strong><br>
</p>
> For the older version, please refer to the [0.2.x documentation](docs/README_0_2_x_ZH.md).
> For the older version, please refer to the [0.2.x documentation](docs/README_0_2_x.md).
---
@ -64,17 +64,17 @@ working_dir/
[ReMeLight](reme/reme_light.py) is the core class of the file-based memory system. It provides full memory management
capabilities for AI agents:
| Method | Function | Key components |
|------------------------|--------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `check_context` | 📊 Check context size | [ContextChecker](reme/memory/file_based/component/context_checker.py) — checks whether context exceeds thresholds and splits messages |
| `compact_memory` | 📦 Compact history into summary | [Compactor](reme/memory/file_based/component/compactor.py) — ReActAgent that generates structured context summaries |
| `summary_memory` | 📝 Persist important memory to files | [Summarizer](reme/memory/file_based/component/summarizer.py) — ReActAgent + file tools (`read` / `write` / `edit`) |
| `compact_tool_result` | ✂️ Compact long tool outputs | [ToolResultCompactor](reme/memory/file_based/component/tool_result_compactor.py) — truncates long tool outputs and stores them in `tool_result/` while keeping file references in messages |
| `memory_search` | 🔍 Semantic memory search | [MemorySearch](reme/memory/file_based/tools/memory_search.py) — hybrid retrieval with vectors + BM25 |
| `ReMeInMemoryMemory` | 🗂️ In-session memory class | [ReMeInMemoryMemory](reme/memory/file_based/reme_in_memory_memory.py) — token-aware memory management with summary compression and state serialization |
| `pre_reasoning_hook` | 🔄 Pre-reasoning hook | `compact_tool_result` + `check_context` + `compact_memory` + `summary_memory` (async) |
| `start` | 🚀 Start memory system | Initialize file storage, file watcher, and embedding cache; clean up expired tool result files |
| `close` | 📕 Shutdown and cleanup | Clean up tool result files, stop file watcher, and persist embedding cache |
| Method | Function | Key components |
|-----------------------|--------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `check_context` | 📊 Check context size | [ContextChecker](reme/memory/file_based/components/context_checker.py) — checks whether context exceeds thresholds and splits messages |
| `compact_memory` | 📦 Compact history into summary | [Compactor](reme/memory/file_based/components/compactor.py) — ReActAgent that generates structured context summaries |
| `summary_memory` | 📝 Persist important memory to files | [Summarizer](reme/memory/file_based/components/summarizer.py) — ReActAgent + file tools (`read` / `write` / `edit`) |
| `compact_tool_result` | ✂️ Compact long tool outputs | [ToolResultCompactor](reme/memory/file_based/components/tool_result_compactor.py) — truncates long tool outputs and stores them in `tool_result/` while keeping file references in messages |
| `memory_search` | 🔍 Semantic memory search | [MemorySearch](reme/memory/file_based/tools/memory_search.py) — hybrid retrieval with vectors + BM25 |
| `ReMeInMemoryMemory` | 🗂️ In-session memory class | [ReMeInMemoryMemory](reme/memory/file_based/reme_in_memory_memory.py) — token-aware memory management with summary compression and state serialization |
| `pre_reasoning_hook` | 🔄 Pre-reasoning hook | `compact_tool_result` + `check_context` + `compact_memory` + `summary_memory` (async) |
| `start` | 🚀 Start memory system | Initialize file storage, file watcher, and embedding cache; clean up expired tool result files |
| `close` | 📕 Shutdown and cleanup | Clean up tool result files, stop file watcher, and persist embedding cache |
---
@ -186,7 +186,7 @@ graph LR
CC -->|Exceeds limit| SM[summary_memory<br>Async persistence]
SM -->|ReAct + FileIO| Files[memory/*.md]
Agent -->|Explicit call| Search[memory_search<br>Vector+BM25]
Agent -->|In-session| InMem[ReMeInMemoryMemory<br>Token-aware memory]
Agent -->|In - session| InMem[ReMeInMemoryMemory<br>Token-aware memory]
Files -.->|FileWatcher| Store[(FileStore<br>Vector+FTS index)]
Search --> Store
```
@ -195,7 +195,7 @@ graph LR
#### 1. `check_context` — context checking
[ContextChecker](reme/memory/file_based/component/context_checker.py) uses token counting to determine whether the
[ContextChecker](reme/memory/file_based/components/context_checker.py) uses token counting to determine whether the
context exceeds thresholds and automatically splits messages into a "to compact" group and a "to keep" group.
```mermaid
@ -217,7 +217,7 @@ graph LR
#### 2. `compact_memory` — conversation compaction
[Compactor](reme/memory/file_based/component/compactor.py) uses a ReActAgent to compact conversation history into a *
[Compactor](reme/memory/file_based/components/compactor.py) uses a ReActAgent to compact conversation history into a *
*structured context summary**.
```mermaid
@ -245,7 +245,7 @@ graph LR
#### 3. `summary_memory` — persistent memory
[Summarizer](reme/memory/file_based/component/summarizer.py) uses a **ReAct + file tools** pattern so that the AI can
[Summarizer](reme/memory/file_based/components/summarizer.py) uses a **ReAct + file tools** pattern so that the AI can
decide what to write and where to write it.
```mermaid
@ -271,7 +271,7 @@ graph LR
#### 4. `compact_tool_result` — tool result compaction
[ToolResultCompactor](reme/memory/file_based/component/tool_result_compactor.py) addresses the problem of long tool
[ToolResultCompactor](reme/memory/file_based/components/tool_result_compactor.py) addresses the problem of long tool
outputs bloating the context.
```mermaid
@ -534,7 +534,6 @@ We evaluate ReMe on the BFCL-V3 multi-turn-base task (random split 50 train / 15
For more details on how to reproduce the experiments, see [quickstart.md](benchmark/bfcl/quickstart.md).
## ⭐ Community & support
- **Star & Watch**: Starring helps more agent developers discover ReMe; Watching keeps you up to date with new releases

32
README_ZH.md
View file

@ -60,17 +60,18 @@ working_dir/
[ReMeLight](reme/reme_light.py) 是该记忆系统的核心类，为 AI Agent 提供完整的记忆管理能力：
| 方法 | 功能 | 关键组件 |
|------------------------|--------------|-----------------------------------------------------------------------------------------------------------------------------|
| `check_context` | 📊 检查上下文大小 | [ContextChecker](reme/memory/file_based/component/context_checker.py) — 检查上下文是否超出阈值并拆分Message |
| `compact_memory` | 📦 压缩历史对话为摘要 | [Compactor](reme/memory/file_based/component/compactor.py) — ReActAgent 生成结构化上下文摘要 |
| `summary_memory` | 📝 将重要记忆写入文件 | [Summarizer](reme/memory/file_based/component/summarizer.py) — ReActAgent + 文件工具（read / write / edit） |
| `compact_tool_result` | ✂️ 压缩超长工具输出 | [ToolResultCompactor](reme/memory/file_based/component/tool_result_compactor.py) — 截断超长的工具调用结果并转存到 `tool_result/`，消息中保留文件引用 |
| `memory_search` | 🔍 语义搜索记忆 | [MemorySearch](reme/memory/file_based/tools/memory_search.py) — 向量 + BM25 混合检索 |
| `ReMeInMemoryMemory` | 🗂️ 会话内存类 | [ReMeInMemoryMemory](reme/memory/file_based/reme_in_memory_memory.py) — Token 感知的内存管理，支持压缩摘要和状态序列化 |
| `pre_reasoning_hook` | 🔄 推理前预处理钩子 | compact_tool_result + check_context + compact_memory + summary_memory(async) |
| `start` | 🚀 启动记忆系统 | 初始化文件存储、文件监控、Embedding 缓存；清理过期工具结果文件 |
| `close` | 📕 关闭并清理 | 清理工具结果文件、停止文件监控、保存 Embedding 缓存 |·
| 方法 | 功能 | 关键组件 |
|-----------------------|--------------|------------------------------------------------------------------------------------------------------------------------------|
| `check_context` | 📊 检查上下文大小 | [ContextChecker](reme/memory/file_based/components/context_checker.py) — 检查上下文是否超出阈值并拆分Message |
| `compact_memory` | 📦 压缩历史对话为摘要 | [Compactor](reme/memory/file_based/components/compactor.py) — ReActAgent 生成结构化上下文摘要 |
| `summary_memory` | 📝 将重要记忆写入文件 | [Summarizer](reme/memory/file_based/components/summarizer.py) — ReActAgent + 文件工具（read / write / edit） |
| `compact_tool_result` | ✂️ 压缩超长工具输出 | [ToolResultCompactor](reme/memory/file_based/components/tool_result_compactor.py) — 截断超长的工具调用结果并转存到 `tool_result/`，消息中保留文件引用 |
| `memory_search` | 🔍 语义搜索记忆 | [MemorySearch](reme/memory/file_based/tools/memory_search.py) — 向量 + BM25 混合检索 |
| `ReMeInMemoryMemory` | 🗂️ 会话内存类 | [ReMeInMemoryMemory](reme/memory/file_based/reme_in_memory_memory.py) — Token 感知的内存管理，支持压缩摘要和状态序列化 |
| `pre_reasoning_hook` | 🔄 推理前预处理钩子 | compact_tool_result + check_context + compact_memory + summary_memory(async) |
| `start` | 🚀 启动记忆系统 | 初始化文件存储、文件监控、Embedding 缓存；清理过期工具结果文件 |
| `close` | 📕 关闭并清理 | 清理工具结果文件、停止文件监控、保存 Embedding 缓存 |·
---
### 🚀 快速开始
@ -188,7 +189,7 @@ graph LR
#### 1. check_context — 上下文检查
[ContextChecker](reme/memory/file_based/component/context_checker.py) 基于 Token 计数判断上下文是否超限，自动拆分为「待压缩」和「保留」两组消息。
[ContextChecker](reme/memory/file_based/components/context_checker.py) 基于 Token 计数判断上下文是否超限，自动拆分为「待压缩」和「保留」两组消息。
```mermaid
graph LR
@ -208,7 +209,7 @@ graph LR
#### 2. compact_memory — 对话压缩
[Compactor](reme/memory/file_based/component/compactor.py) 使用 ReActAgent 将历史对话压缩为**结构化上下文摘要**。
[Compactor](reme/memory/file_based/components/compactor.py) 使用 ReActAgent 将历史对话压缩为**结构化上下文摘要**。
```mermaid
graph LR
@ -235,7 +236,7 @@ graph LR
#### 3. summary_memory — 记忆持久化
[Summarizer](reme/memory/file_based/component/summarizer.py) 采用 **ReAct + 文件工具** 模式，让 AI 自主决定写什么、写到哪。
[Summarizer](reme/memory/file_based/components/summarizer.py) 采用 **ReAct + 文件工具** 模式，让 AI 自主决定写什么、写到哪。
```mermaid
graph LR
@ -260,7 +261,7 @@ graph LR
#### 4. compact_tool_result — 工具结果压缩
[ToolResultCompactor](reme/memory/file_based/component/tool_result_compactor.py) 解决工具输出过长导致上下文膨胀的问题。
[ToolResultCompactor](reme/memory/file_based/components/tool_result_compactor.py) 解决工具输出过长导致上下文膨胀的问题。
```mermaid
graph LR
@ -518,7 +519,6 @@ Pass@K 衡量在生成 K 个候选中，至少一个成功完成任务（score=1
关于如何复现实验的更多细节，见 [quickstart.md](benchmark/bfcl/quickstart.md)
## ⭐ 社区与支持
- **Star 与 Watch**：Star 可让更多智能体开发者发现 ReMe；Watch 可助你第一时间获知新版本与特性。

35
reme/core/schema/as_msg_stat.py
View file

@ -26,6 +26,12 @@ class AsBlockStat(BaseModel):
"""Return a short preview of the block content."""
return self.format(_DEFAULT_MAX_BLOCK_TEXT_PREVIEW_LENGTH)
def _truncate(self, text: str, max_length: int) -> str:
"""Simple truncation with ellipsis."""
if len(text) <= max_length:
return text
return text[:max_length] + "..."
# pylint: disable=too-many-return-statements
def format(self, max_length: int = _DEFAULT_MAX_FORMATTER_TEXT_LENGTH, include_thinking: bool = True) -> str:
"""Format block content to string representation.
@ -37,22 +43,25 @@ class AsBlockStat(BaseModel):
Returns:
Formatted string representation of the block.
"""
from ..utils import truncate_text
if self.block_type == "text":
return truncate_text(self.text, max_length) if self.text else ""
if not self.text:
return ""
return f"<text>{self._truncate(self.text, max_length)}</text>"
if self.block_type == "thinking":
if include_thinking and self.text:
return f"<thinking>\n{truncate_text(self.text, max_length)}\n</thinking>"
return ""
if not include_thinking or not self.text:
return ""
return f"<thinking>{self._truncate(self.text, max_length)}</thinking>"
if self.block_type in ("image", "audio", "video"):
return f"[{self.block_type}] {self.media_url}" if self.media_url else f"[{self.block_type}]"
if self.block_type in ("tool_use", "tool_result"):
if self.block_type == "tool_use":
return f" - tool_call={self.tool_name} params={truncate_text(self.tool_input, max_length)}"
else:
output = truncate_text(self.tool_output, max_length)
return f" - tool_result={self.tool_name} output={output}" if output else ""
content = self.media_url if self.media_url else ""
return f"<{self.block_type}>{content}</{self.block_type}>"
if self.block_type == "tool_use":
content = f"{self.tool_name} params={self._truncate(self.tool_input, max_length)}"
return f"<tool_use>{content}</tool_use>"
if self.block_type == "tool_result":
if not self.tool_output:
return ""
content = f"{self.tool_name} output={self._truncate(self.tool_output, max_length)}"
return f"<tool_result>{content}</tool_result>"
return ""

30
reme/memory/file_based/__init__.py
View file

@ -1,29 +1,13 @@
"""File-based Memory Module.
"""File-based Memory Module."""
This module provides memory management components for CoPaw (Cooperative Paw) agents,
including memory formatting, compaction, summarization, and file I/O operations.
Components:
- ReMeInMemoryMemory: Extended InMemoryMemory with bugfixes and summary support
- AsMsgHandler: Handles AgentScope message statistics, formatting, and context checking
- Summarizer: Generates memory summaries using LLM
- Compactor: Compacts memory content to reduce token usage
- ToolResultCompactor: Truncates large tool results and saves full content to files
- ContextChecker: Checks context size and splits messages for compaction
"""
from .as_msg_handler import AsMsgHandler
from .component.compactor import Compactor
from .component.context_checker import ContextChecker
from .component.summarizer import Summarizer
from .component.tool_result_compactor import ToolResultCompactor
from . import components
from . import tools
from . import utils
from .reme_in_memory_memory import ReMeInMemoryMemory
__all__ = [
"AsMsgHandler",
"tools",
"utils",
"components",
"ReMeInMemoryMemory",
"Summarizer",
"Compactor",
"ContextChecker",
"ToolResultCompactor",
]

0
reme/memory/file_based/component/__init__.py
View file

13
reme/memory/file_based/components/__init__.py Normal file
View file

@ -0,0 +1,13 @@
"""components"""
from .compactor import Compactor
from .context_checker import ContextChecker
from .summarizer import Summarizer
from .tool_result_compactor import ToolResultCompactor
__all__ = [
"Compactor",
"Summarizer",
"ContextChecker",
"ToolResultCompactor",
]

5
reme/memory/file_based/component/compactor.py → reme/memory/file_based/components/compactor.py
View file

@ -4,7 +4,7 @@ from agentscope.agent import ReActAgent
from agentscope.message import Msg
from agentscope.token import HuggingFaceTokenCounter
from ..as_msg_handler import AsMsgHandler
from ..utils import AsMsgHandler
from ....core.op import BaseOp
from ....core.utils import get_std_logger
@ -32,10 +32,13 @@ class Compactor(BaseOp):
if not messages:
return ""
before_token_count = self.msg_handler.count_msgs_token(messages)
history_formatted_str: str = self.msg_handler.format_msgs_to_str(
messages=messages,
memory_compact_threshold=self.memory_compact_threshold,
)
after_token_count = self.msg_handler.count_str_token(history_formatted_str)
logger.info(f"Compactor before_token_count={before_token_count} after_token_count={after_token_count}")
if not history_formatted_str:
logger.warning(f"No history to compact. messages={messages}")

0
reme/memory/file_based/component/compactor.yaml → reme/memory/file_based/components/compactor.yaml
View file

15
reme/memory/file_based/component/context_checker.py → reme/memory/file_based/components/context_checker.py
View file

@ -3,7 +3,7 @@
from agentscope.message import Msg
from agentscope.token import HuggingFaceTokenCounter
from ..as_msg_handler import AsMsgHandler
from ..utils import AsMsgHandler
from ....core.op import BaseOp
from ....core.utils import get_std_logger
@ -87,11 +87,12 @@ class ContextChecker(BaseOp):
memory_compact_reserve=self.memory_compact_reserve,
)
logger.info(
f"ContextChecker Result: "
f"to_compact={len(messages_to_compact)}, "
f"to_keep={len(messages_to_keep)}, "
f"is_valid={is_valid}",
)
if messages_to_compact:
logger.info(
f"ContextChecker Result: "
f"to_compact={len(messages_to_compact)}, "
f"to_keep={len(messages_to_keep)}, "
f"is_valid={is_valid}",
)
return messages_to_compact, messages_to_keep, is_valid

5
reme/memory/file_based/component/summarizer.py → reme/memory/file_based/components/summarizer.py
View file

@ -7,7 +7,7 @@ from agentscope.message import Msg
from agentscope.token import HuggingFaceTokenCounter
from agentscope.tool import Toolkit
from ..as_msg_handler import AsMsgHandler
from ..utils import AsMsgHandler
from ....core.op import BaseOp
from ....core.utils import get_std_logger
@ -40,10 +40,13 @@ class Summarizer(BaseOp):
if not messages:
return ""
before_token_count = self.msg_handler.count_msgs_token(messages)
history_formatted_str: str = self.msg_handler.format_msgs_to_str(
messages=messages,
memory_compact_threshold=self.memory_compact_threshold,
)
after_token_count = self.msg_handler.count_str_token(history_formatted_str)
logger.info(f"Summarizer before_token_count={before_token_count} after_token_count={after_token_count}")
if not history_formatted_str:
logger.warning(f"No history to summarize. messages={messages}")

0
reme/memory/file_based/component/summarizer.yaml → reme/memory/file_based/components/summarizer.yaml
View file

0
reme/memory/file_based/component/tool_result_compactor.py → reme/memory/file_based/components/tool_result_compactor.py
View file

2
reme/memory/file_based/reme_in_memory_memory.py
View file

@ -5,7 +5,7 @@ from agentscope.memory import InMemoryMemory
from agentscope.message import Msg
from agentscope.token import HuggingFaceTokenCounter
from .as_msg_handler import AsMsgHandler
from .utils import AsMsgHandler
from ...core.utils import get_std_logger
logger = get_std_logger()

7
reme/memory/file_based/utils/__init__.py Normal file
View file

@ -0,0 +1,7 @@
"""utils"""
from .as_msg_handler import AsMsgHandler
__all__ = [
"AsMsgHandler",
]

33
reme/memory/file_based/as_msg_handler.py → reme/memory/file_based/utils/as_msg_handler.py
View file

@ -5,8 +5,8 @@ import json
from agentscope.message import Msg
from agentscope.token import HuggingFaceTokenCounter
from ...core.schema import AsMsgStat, AsBlockStat
from ...core.utils import get_std_logger
from ....core.schema import AsMsgStat, AsBlockStat
from ....core.utils import get_std_logger
logger = get_std_logger()
@ -111,6 +111,19 @@ class AsMsgHandler:
metadata=message.metadata or {},
)
if not isinstance(message.content, list):
logger.warning(
"Unexpected message.content type %s, expected str or list, returning empty stat.",
type(message.content),
)
return AsMsgStat(
name=message.name or message.role,
role=message.role,
content=blocks,
timestamp=message.timestamp or "",
metadata=message.metadata or {},
)
for block in message.content:
block_type = block.get("type", "unknown")
@ -155,7 +168,7 @@ class AsMsgHandler:
elif block_type == "tool_use":
tool_name = block.get("name", "")
tool_input = block.get("raw_input", "")
tool_input = block.get("input", "")
try:
input_str = json.dumps(tool_input, ensure_ascii=False)
except (TypeError, ValueError):
@ -227,7 +240,8 @@ class AsMsgHandler:
formatted_content = stat.format(include_thinking=include_thinking)
content_token_count = self.count_str_token(formatted_content)
if total_token_count + content_token_count > memory_compact_threshold:
is_latest = i == len(messages) - 1
if not is_latest and total_token_count + content_token_count > memory_compact_threshold:
logger.info(
"Skipping older messages: adding %d tokens would exceed threshold %d (current: %d)",
content_token_count,
@ -236,6 +250,13 @@ class AsMsgHandler:
)
break
if is_latest and content_token_count > memory_compact_threshold:
logger.warning(
"Latest message alone (%d tokens) exceeds threshold %d, including it anyway.",
content_token_count,
memory_compact_threshold,
)
formatted_parts.append(formatted_content)
total_token_count += content_token_count
@ -324,6 +345,10 @@ class AsMsgHandler:
accumulated_tokens = 0
for i in range(len(msg_stats) - 1, -1, -1):
# Skip messages already added as tool_use dependencies to avoid double-counting tokens
if i in keep_indices:
continue
msg, stat = msg_stats[i]
# Check if adding this message would exceed reserve limit

18
reme/reme_light.py
View file

@ -26,16 +26,15 @@ from agentscope.tool import Toolkit, ToolResponse
from .config import ReMeConfigParser
from .core import Application
from .core.utils import get_hf_token_counter, get_std_logger
from .memory.file_based import (
from .memory.file_based import ReMeInMemoryMemory
from .memory.file_based.components import (
Compactor,
ContextChecker,
Summarizer,
ToolResultCompactor,
ReMeInMemoryMemory,
AsMsgHandler,
)
from .memory.file_based import MemorySearch
from .memory.file_based.tools import FileIO
from .memory.file_based.tools import FileIO, MemorySearch
from .memory.file_based.utils import AsMsgHandler
logger = get_std_logger()
@ -487,7 +486,7 @@ class ReMeLight(Application):
- compact_ratio: Compaction threshold ratio
Note:
- Completed/failed/cancelled tasks are cleaned up before adding new ones
- Completed/failed/canceled tasks are cleaned up before adding new ones
- Task results and errors are logged automatically
- Use await_summary_tasks() to wait for all pending tasks to complete
"""
@ -561,7 +560,7 @@ class ReMeLight(Application):
Returns:
tuple[list[Msg], str]: A tuple containing:
- list[Msg]: Messages to keep in context (may be reduced)
- list[Msg]: Messages to keep in context (maybe reduced)
- str: Updated compressed summary incorporating compacted messages
Note:
@ -584,10 +583,11 @@ class ReMeLight(Application):
compact_msgs = messages[:-tool_result_compact_keep_n]
await self.compact_tool_result(compact_msgs)
messages_to_compact, messages_to_keep, is_valid = msg_handler.context_check(
messages_to_compact, messages_to_keep, is_valid = await self.check_context(
messages=messages,
memory_compact_threshold=left_compact_threshold,
memory_compact_reserve=memory_compact_reserve,
token_counter=token_counter,
)
if not messages_to_compact:
@ -626,7 +626,7 @@ class ReMeLight(Application):
Wait for all background summary tasks to complete and collect results.
Blocks until all pending summary tasks in the task list have completed,
cancelled, or failed. Collects status information from each task and
canceled, or failed. Collects status information from each task and
clears the task list after processing.
Returns:

4
tests/light/test_compactor.py
View file

@ -3,7 +3,6 @@
import asyncio
from agentscope.message import Msg
from test_utils import (
get_dash_chat_model,
get_formatter,
@ -11,8 +10,7 @@ from test_utils import (
)
from reme.core.utils import get_std_logger
from reme.memory.file_based import Compactor
from reme.memory.file_based.components import Compactor
logger = get_std_logger()

4
tests/light/test_context_check.py
View file

@ -1,10 +1,10 @@
"""Tests for AsMsgHandler.context_check method."""
from agentscope.message import Msg
from test_utils import get_token_counter
from reme.core.utils import get_std_logger
from reme.memory.file_based.as_msg_handler import AsMsgHandler
from reme.memory.file_based.utils import AsMsgHandler
logger = get_std_logger()

4
tests/light/test_format_msgs_to_str.py
View file

@ -5,10 +5,10 @@
import sys
from agentscope.message import Msg
from test_utils import get_token_counter
from reme.core.utils import get_std_logger
from reme.memory.file_based.as_msg_handler import AsMsgHandler
from reme.memory.file_based.utils import AsMsgHandler
logger = get_std_logger()

4
tests/light/test_summarizer.py
View file

@ -7,16 +7,16 @@ from pathlib import Path
from agentscope.message import Msg
from agentscope.tool import Toolkit
from test_utils import (
get_dash_chat_model,
get_formatter,
get_token_counter,
)
from reme.core.utils import get_std_logger
from reme.memory.file_based import Summarizer
from reme.memory.file_based.components import Summarizer
from reme.memory.file_based.tools import FileIO
logger = get_std_logger()

3
tests/light/test_tool_result_compactor.py
View file

@ -6,8 +6,9 @@ from datetime import datetime, timedelta
from pathlib import Path
from agentscope.message import Msg
from reme.memory.file_based import ToolResultCompactor
from reme.core.utils import is_truncated
from reme.memory.file_based.components import ToolResultCompactor
def create_tool_result_msg(output: str | list, tool_name: str = "test_tool") -> Msg:

2
tests/light/test_tools.py
View file

@ -9,8 +9,8 @@ import tempfile
import pytest
from reme.memory.file_based.tools.shell import Shell
from reme.memory.file_based.tools.file_io import FileIO
from reme.memory.file_based.tools.shell import Shell
from reme.memory.file_based.tools.utils import DEFAULT_MAX_LINES, DEFAULT_MAX_BYTES

2
tests/light/test_utils.py
View file

@ -4,7 +4,7 @@ import os
from agentscope.message import Msg, ThinkingBlock, TextBlock, ToolUseBlock, ToolResultBlock
from reme.memory.file_based import AsMsgHandler
from reme.memory.file_based.utils import AsMsgHandler
def get_token_counter():