mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-10-06 02:48:22 +00:00
a3bd81bde2
* fix(core): update version number to 0.4.0.1 - Incremented version from 0.4.0.0 to 0.4.0.1 in __init__.py * fix(index): remove stopwords path from tokenizer config and add keyword index repair - Remove stopwords_path from tokenizer config to prevent index forking by install path - Add _sync_keyword_index_from_chunks method to repair keyword index when persisted state mismatches - Implement test for keyword index repair from persisted chunks when missing - Add test to verify tokenizer fingerprint ignores stopwords absolute path - Update version from 0.4.0.1 to 0.4.0.2 * feat(dream): add scan_days parameter to dream extraction process - Add scan_days configuration option to default.yaml with default value of 2 - Implement recent_dates utility function to calculate date ranges for scanning - Modify DreamExtractStep to scan multiple days based on scan_days parameter - Update dream extraction to process files across multiple dates instead of single day - Extend DreamState schema to include dates and scan_days fields - Update DreamTopicsStep to handle multi-day topic processing - Modify finish step to checkpoint files from all scanned dates - Add comprehensive tests for multi-day scanning functionality - Update prompt templates to include scan dates information - Refactor topics writing logic to target specific date rather than current date
95 lines
3.5 KiB
Python
95 lines
3.5 KiB
Python
"""Shared auto-dream schemas."""
|
|
|
|
from typing import Literal
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
BUCKETS: tuple[str, ...] = ("procedure", "personal", "wiki")
|
|
Bucket = Literal["procedure", "personal", "wiki"]
|
|
|
|
|
|
class DreamUnit(BaseModel):
|
|
"""One cross-file memory unit emitted by global extract."""
|
|
|
|
name: str = Field(description="Short kebab-case handle for the abstraction.")
|
|
bucket: str = Field(description="procedure, personal, or wiki; unknown values route to wiki.")
|
|
summary: str = Field(description="Grounded abstraction summary with evidence pointers.")
|
|
paths: list[str] = Field(default_factory=list, description="Workspace-relative source paths.")
|
|
|
|
|
|
class DreamTopic(BaseModel):
|
|
"""One topic candidate emitted by global extract."""
|
|
|
|
title: str = Field(description="Specific user-interest topic title.")
|
|
reason: str = Field(description="Why this topic may interest the user.")
|
|
evidence: str = Field(description="Grounded evidence pointer.")
|
|
keywords: list[str] = Field(default_factory=list, description="Keywords for de-duplication.")
|
|
paths: list[str] = Field(default_factory=list, description="Workspace-relative source paths.")
|
|
|
|
|
|
class DreamExtractOutput(BaseModel):
|
|
"""Structured output for ``dream_extract_step``."""
|
|
|
|
units: list[DreamUnit] = Field(default_factory=list)
|
|
topics: list[DreamTopic] = Field(default_factory=list)
|
|
|
|
|
|
class IntegrateOutcome(BaseModel):
|
|
"""Structured output for one unit integration."""
|
|
|
|
action: Literal["CREATE", "CORROBORATE", "REFINE", "CORRECT"] = Field(description="Write decision.")
|
|
target_path: str = Field(description="Digest path written or edited.")
|
|
note: str = Field(default="", description="Short summary of what landed.")
|
|
|
|
|
|
class TopicSelectionOutput(BaseModel):
|
|
"""Structured output for daily topic selection."""
|
|
|
|
topics: list[DreamTopic] = Field(default_factory=list)
|
|
|
|
|
|
class ProactiveResult(BaseModel):
|
|
"""Result of reading daily interest topics."""
|
|
|
|
date: str = ""
|
|
path: str = ""
|
|
topics: list[dict] = Field(default_factory=list)
|
|
content: str = ""
|
|
skipped: bool = False
|
|
error: str = ""
|
|
summary: str = ""
|
|
|
|
|
|
class DreamState(BaseModel):
|
|
"""Shared state passed across the four dream steps."""
|
|
|
|
date: str = ""
|
|
dates: list[str] = Field(default_factory=list)
|
|
scan_days: int = 2
|
|
hint: str = ""
|
|
daily_dir: str = ""
|
|
workspace: str = ""
|
|
files_scanned: int = 0
|
|
files_unchanged: int = 0
|
|
files_changed: int = 0
|
|
files_deleted: int = 0
|
|
changed_paths: list[str] = Field(default_factory=list)
|
|
unchanged_paths: list[str] = Field(default_factory=list)
|
|
deleted_paths: list[str] = Field(default_factory=list)
|
|
existing: dict[str, float] = Field(default_factory=dict)
|
|
indexed: dict[str, float] = Field(default_factory=dict)
|
|
units: list[dict] = Field(default_factory=list)
|
|
topics: list[dict] = Field(default_factory=list)
|
|
extract_summary: str = ""
|
|
integrate_results: list[dict] = Field(default_factory=list)
|
|
nodes_created: list[str] = Field(default_factory=list)
|
|
nodes_updated: list[str] = Field(default_factory=list)
|
|
failed_units: list[dict] = Field(default_factory=list)
|
|
failed_paths: list[str] = Field(default_factory=list)
|
|
interests_path: str = ""
|
|
interests_paths: list[str] = Field(default_factory=list)
|
|
topics_written: int = 0
|
|
topic_error: str = ""
|
|
checkpoint_paths: list[str] = Field(default_factory=list)
|
|
errors: list[str] = Field(default_factory=list)
|
|
summary: str = ""
|