e07c9ec77b
Several weeks of work accumulated without being committed. Grouped here for clarity; see CHANGELOG.md [Unreleased] for the user-facing summary. Highlights ---------- P1 #2 — ISO 639-2/B canonical migration - New Language VO + LanguageRegistry (alfred/domain/shared/knowledge/). - iso_languages.yaml as single source of truth for language codes. - SubtitleKnowledgeBase now delegates lookup to LanguageRegistry; subtitles.yaml only declares subtitle-specific tokens (vostfr, vf, vff, …). - SubtitlePreferences default → ["fre", "eng"]; subtitle filenames written as {iso639_2b}.srt (legacy fr.srt still read via alias). - Scanner: dropped _LANG_KEYWORDS / _SDH_TOKENS / _FORCED_TOKENS / SUBTITLE_EXTENSIONS hardcoded dicts. - Fixed: 'hi' token no longer marks SDH (conflicted with Hindi alias). - Added settings.min_movie_size_bytes (was a module constant). P1 #3 — Release parser unification + data-driven tokenizer - parse_release() is now the single source of truth for release-name parsing. - alfred/knowledge/release/separators.yaml declares the token separators used by the tokenizer (., space, [, ], (, ), _). New conventions can be added without code changes. - Tokenizer now splits on any configured separator instead of name.split('.'). Releases like 'The Father (2020) [1080p] [WEBRip] [5.1] [YTS.MX]' parse via the direct path without sanitization fallback. - Site-tag extraction always runs first; well-formedness only rejects truly forbidden chars. - _parse_season_episode() extended with NxNN / NxNNxNN alt forms. - Removed dead helpers: _sanitize, _normalize. Domain cleanup - Deleted fossil services with zero production callers: alfred/domain/movies/services.py alfred/domain/tv_shows/services.py alfred/domain/subtitles/services.py (replaced by subtitles/services/ package) alfred/domain/subtitles/repositories.py - Split monolithic subtitle services into a package (identifier, matcher, placer, pattern_detector, utils) + dedicated knowledge/ package. - MediaInfo split into dedicated package (alfred/domain/shared/media/: audio, video, subtitle, info, matching). Persistence cleanup - Removed dead JSON repositories (movie/subtitle/tvshow_repository.py). Tests - Major expansion of the test suite organized to mirror the source tree. - Removed obsolete *_edge_cases test files superseded by structured tests. - Suite: 990 passed, 8 skipped. Misc - .gitignore: exclude env_backup/ and *.bak. - Adjustments across agent/llm, app.py, application/filesystem, and infrastructure/filesystem to align with the new domain layout.
100 lines
3.5 KiB
Python
100 lines
3.5 KiB
Python
"""Memory — unified manager for the 3 memory tiers."""
|
|
|
|
import json
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
from .episodic import EpisodicMemory
|
|
from .ltm import LongTermMemory
|
|
from .stm import ShortTermMemory
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class Memory:
|
|
"""
|
|
Unified manager for the 3 memory tiers.
|
|
|
|
Usage:
|
|
memory = Memory("data/memory")
|
|
memory.ltm.workspace.download = "/downloads"
|
|
memory.stm.add_message("user", "Hello")
|
|
memory.episodic.store_search_results("query", results)
|
|
memory.save()
|
|
"""
|
|
|
|
def __init__(self, storage_dir: str = "memory"):
|
|
self.storage_dir = Path(storage_dir)
|
|
self.storage_dir.mkdir(parents=True, exist_ok=True)
|
|
self.ltm_file = self.storage_dir / "ltm.json"
|
|
|
|
self.ltm = self._load_ltm()
|
|
self.stm = ShortTermMemory()
|
|
self.episodic = EpisodicMemory()
|
|
|
|
logger.info(f"Memory initialized (storage: {storage_dir})")
|
|
|
|
def _load_ltm(self) -> LongTermMemory:
|
|
"""Load LTM from disk, or return a fresh instance."""
|
|
if self.ltm_file.exists():
|
|
try:
|
|
data = json.loads(self.ltm_file.read_text(encoding="utf-8"))
|
|
logger.info("LTM loaded from file")
|
|
return LongTermMemory.from_dict(data)
|
|
except (OSError, json.JSONDecodeError) as e:
|
|
logger.warning(f"Could not load LTM: {e}")
|
|
return LongTermMemory()
|
|
|
|
def save(self) -> None:
|
|
"""Persist LTM to disk (STM and Episodic are volatile)."""
|
|
try:
|
|
self.ltm_file.write_text(
|
|
json.dumps(self.ltm.to_dict(), indent=2, ensure_ascii=False),
|
|
encoding="utf-8",
|
|
)
|
|
logger.debug("LTM saved")
|
|
except OSError as e:
|
|
logger.error(f"Failed to save LTM: {e}")
|
|
raise
|
|
|
|
def get_context_for_prompt(self) -> dict:
|
|
"""Snapshot of relevant memory for the system prompt."""
|
|
return {
|
|
"workspace": self.ltm.workspace.as_dict(),
|
|
"library_paths": self.ltm.library_paths.to_dict(),
|
|
"media_preferences": self.ltm.media_preferences.to_dict(),
|
|
"subtitle_preferences": self.ltm.subtitle_preferences.to_dict(),
|
|
"current_workflow": self.stm.workflow.to_dict(),
|
|
"current_topic": self.stm.entities.topic,
|
|
"extracted_entities": self.stm.entities.data,
|
|
"last_search": {
|
|
"query": self.episodic.search_results.last.get("query")
|
|
if self.episodic.search_results.last
|
|
else None,
|
|
"result_count": len(
|
|
self.episodic.search_results.last.get("results", [])
|
|
)
|
|
if self.episodic.search_results.last
|
|
else 0,
|
|
},
|
|
"active_downloads_count": len(self.episodic.downloads.active),
|
|
"pending_question": self.episodic.pending_question is not None,
|
|
"unread_events": len(
|
|
[e for e in self.episodic.events.items if not e.get("read")]
|
|
),
|
|
}
|
|
|
|
def get_full_state(self) -> dict:
|
|
"""Full state dump for debug/API."""
|
|
return {
|
|
"ltm": self.ltm.to_dict(),
|
|
"stm": self.stm.to_dict(),
|
|
"episodic": self.episodic.to_dict(),
|
|
}
|
|
|
|
def clear_session(self) -> None:
|
|
"""Reset volatile memories (STM + Episodic)."""
|
|
self.stm.clear()
|
|
self.episodic.clear()
|
|
logger.info("Session memories cleared")
|