mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-08-28 05:25:04 +00:00
9a6cf2b994
* update * refactor(memory): remove unnecessary type check and update error logging * refactor(core): standardize logger import and update agentscope dependency * fix(memory): disable console output and add logging for summarizer component * feat(core): replace OpenAI token counter with custom ReMe token counter - Replace OpenAITokenCounter with ReMeTokenCounter implementation - Add support for HuggingFace mirror and configurable tokenizer - Register ReMeTokenCounter as default token counter in registry - Update config to use hf backend with Qwen2.5-7B-Instruct model refactor(memory): convert token counting methods to async in message handlers - Change count_str_token, stat_message, count_msgs_token to async methods - Update format_msgs_to_str and context_check to use async token counting - Modify _format_tool_result_output to support async token counting - Adjust all dependent methods to await async token counting calls feat(memory): add dialog persistence to in-memory storage - Implement _append_messages_to_dialog for saving messages to JSONL files - Add dialog_path parameter to ReMeInMemoryMemory constructor - Persist messages to daily JSONL files based on timestamp grouping - Update mark_messages_compressed to save and remove compressed messages - Modify clear_content to persist all messages before clearing memory refactor(ops): update token counter type hints and initialization - Change BaseOp to use HuggingFaceTokenCounter instead of TokenCounterBase - Update type annotations for as_token_counter property and parameters - Remove direct token counter injection from Compactor and ContextChecker - Pass as_token_counter parameter through service context mechanism style(logging): improve error logging with exception details - Replace logger.error with logger.exception in browser control tool - Change logger.error to logger.exception in memory get tool error handling - Add proper exception logging with stack trace information chore(config): add token counter configuration to light YAML - Add as_token_counters section with default hf backend configuration - Configure Qwen/Qwen2.5-7B-Instruct model with mirror support enabled - Set up pretrained_model_name_or_path and use_mirror parameters test(context): update context check tests to async implementation - Convert verify_context_check_invariants to async function - Update context check test methods to use async calls - Change stat_message calls to await async implementation - Modify test_empty_messages and test_below_threshold_returns_all to async * feat(core): implement context checking and memory management features * refactor(core): replace direct loguru import with logger utility function * refactor(reme): remove RuntimeContext dependency and simplify context checking * feat(docs): add raw conversation persistence to ReMe framework
92 lines
3.5 KiB
Python
92 lines
3.5 KiB
Python
"""ContextChecker module for checking context size and splitting messages."""
|
|
|
|
from agentscope.message import Msg
|
|
|
|
from ..utils import AsMsgHandler
|
|
from ....core.op import BaseOp
|
|
from ....core.utils import get_logger
|
|
|
|
logger = get_logger()
|
|
|
|
|
|
class ContextChecker(BaseOp):
|
|
"""
|
|
ContextChecker class for checking context size and splitting messages.
|
|
|
|
This class analyzes conversation messages to determine if the context
|
|
exceeds the specified token threshold and splits messages into two groups:
|
|
those that should be compacted and those to keep in context.
|
|
|
|
Attributes:
|
|
memory_compact_threshold (int): Token count threshold for triggering compaction.
|
|
memory_compact_reserve (int): Token count to reserve for recent messages.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
memory_compact_threshold: int,
|
|
memory_compact_reserve: int = 10000,
|
|
**kwargs,
|
|
):
|
|
"""
|
|
Initialize the ContextChecker.
|
|
|
|
Args:
|
|
memory_compact_threshold (int): Token count threshold for triggering
|
|
compaction. Messages exceeding this threshold will be split.
|
|
memory_compact_reserve (int): Token count to reserve for recent messages
|
|
to keep in context. Defaults to 10000 tokens.
|
|
**kwargs: Additional keyword arguments passed to BaseOp.
|
|
"""
|
|
super().__init__(**kwargs)
|
|
self.memory_compact_threshold: int = memory_compact_threshold
|
|
self.memory_compact_reserve: int = memory_compact_reserve
|
|
assert self.memory_compact_threshold > self.memory_compact_reserve
|
|
|
|
async def execute(self) -> tuple[list[Msg], list[Msg], bool]:
|
|
"""
|
|
Execute context check and split messages.
|
|
|
|
Retrieves messages from context and checks if they exceed the token
|
|
threshold. If so, splits them into messages to compact and messages
|
|
to keep.
|
|
|
|
Context Parameters:
|
|
messages (list[Msg]): List of conversation messages to check.
|
|
Retrieved from self.context.get("messages", []).
|
|
|
|
Returns:
|
|
tuple[list[Msg], list[Msg], bool]: A tuple containing:
|
|
- messages_to_compact (list[Msg]): Older messages that should
|
|
be compacted/summarized.
|
|
- messages_to_keep (list[Msg]): Recent messages to keep in context.
|
|
- is_valid (bool): True if the split is valid (tool calls aligned),
|
|
False if splitting would break conversation integrity.
|
|
|
|
Note:
|
|
- Returns ([], messages, True) if no compaction is needed.
|
|
- Ensures conversation pairs (user-assistant) are not split.
|
|
- is_valid=False indicates tool_use and tool_result are misaligned.
|
|
"""
|
|
messages: list[Msg] = self.context.get("messages", [])
|
|
|
|
if not messages:
|
|
logger.info("ContextChecker: No messages to check.")
|
|
return [], [], True
|
|
|
|
msg_handler = AsMsgHandler(self.as_token_counter)
|
|
messages_to_compact, messages_to_keep, is_valid = await msg_handler.context_check(
|
|
messages=messages,
|
|
memory_compact_threshold=self.memory_compact_threshold,
|
|
memory_compact_reserve=self.memory_compact_reserve,
|
|
)
|
|
|
|
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
|