mirror of
https://github.com/AstrBotDevs/AstrBot
synced 2026-07-15 17:30:13 +08:00
1daa0e3367
* fix(context): restore turn cap, serialize content parts and tool calls for llm compress, fix AftCompact debug log Three context-compaction regression fixes after #8226: 1. Restore max_context_length -> enforce_max_turns propagation so normal turn-based truncation works again. 2. Serialize ContentPart and ToolCall objects into plain dicts in _message_to_dict so llm_compress no longer fails with JSON serialization errors. 3. Print _provider_messages (compacted) instead of run_context.messages (unchanged) in AftCompact debug log; truncate long role lists to first4,...,last4 to avoid log spam. Assertions in tests are also hardened to avoid coupling to exact prompt wording. * fix(tool_loop_agent_runner): simplify context handling by removing redundant provider messages * fix(tool_loop_agent_runner): rename context manager variables for clarity * fix: update context compression to use recent token ratio instead of fixed count * fix: enhance LLMSummaryCompressor to sanitize contexts and improve message handling * ruff format --------- Co-authored-by: Soulter <905617992@qq.com>
36 lines
1.4 KiB
Python
36 lines
1.4 KiB
Python
from dataclasses import dataclass
|
|
from typing import TYPE_CHECKING
|
|
|
|
from .compressor import ContextCompressor
|
|
from .token_counter import TokenCounter
|
|
|
|
if TYPE_CHECKING:
|
|
from astrbot.core.provider.provider import Provider
|
|
|
|
|
|
@dataclass
|
|
class ContextConfig:
|
|
"""Context configuration class."""
|
|
|
|
max_context_tokens: int = 0
|
|
"""Maximum number of context tokens. <= 0 means no limit."""
|
|
enforce_max_turns: int = -1 # -1 means no limit
|
|
"""Maximum number of conversation turns to keep. -1 means no limit. Executed before compression."""
|
|
truncate_turns: int = 1
|
|
"""Number of conversation turns to discard at once when truncation is triggered.
|
|
Two processes will use this value:
|
|
|
|
1. Enforce max turns truncation.
|
|
2. Truncation by turns compression strategy.
|
|
"""
|
|
llm_compress_instruction: str | None = None
|
|
"""Instruction prompt for LLM-based compression."""
|
|
llm_compress_keep_recent_ratio: float = 0.15
|
|
"""Percent of current context tokens to keep as exact recent context during LLM-based compression."""
|
|
llm_compress_provider: "Provider | None" = None
|
|
"""LLM provider used for compression tasks. If None, truncation strategy is used."""
|
|
custom_token_counter: TokenCounter | None = None
|
|
"""Custom token counting method. If None, the default method is used."""
|
|
custom_compressor: ContextCompressor | None = None
|
|
"""Custom context compression method. If None, the default method is used."""
|