Files
ss-tools/backend/alembic/env.py
busya b466ac6211 feat(translate): add translation cache with source_hash dedup + enforce dictionary post-processing
- Add source_hash column (SHA256 of source_text+source_data+dict_hash+config_hash) to TranslationRecord for cache dedup
- Add Alembic migration b1c2d3e4f5a6 for the new column and composite index (source_hash, status)
- Implement _compute_source_hash / _check_translation_cache in executor.py — before LLM call, check if same source+dict+config combo was already translated successfully
- Implement cache-aware routing in _process_batch: full cache hit → skip LLM, partial hit → route to LLM
- Store source_hash on all new TranslationRecord rows for future cache hits
- Strengthen dictionary prompt instructions from 'use when applicable' to 'MUST use — mandatory'
- Add _enforce_dictionary() post-processing: force-replace dictionary terms in LLM output if LLM ignored them
- Fix CRITICAL: use run.dict_snapshot_hash/config_hash (exist on TranslationRun, not TranslationJob)
- Fix MAJOR: verify cached languages cover ALL target_languages before accepting cache hit
- Fix MAJOR: prevent regex back-reference injection in dictionary enforcement (use lambda)
- Fix: add joinedload to cache lookup to avoid N+1 queries
- Fix: remove redundant single-column index (composite index is sufficient)
- Fix(frontend): parse paginated /translate/dictionaries response correctly (result.items)
2026-05-16 00:42:07 +03:00

106 lines
2.7 KiB
Python

import os
import sys
from logging.config import fileConfig
from pathlib import Path
from sqlalchemy import engine_from_config
from sqlalchemy import pool
from alembic import context
# Ensure backend/src is importable
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
# this is the Alembic Config object, which provides
# access to the values within the .ini file in use.
config = context.config
# Allow overriding sqlalchemy.url via DATABASE_URL env var
if "DATABASE_URL" in os.environ:
config.set_main_option("sqlalchemy.url", os.environ["DATABASE_URL"])
# Interpret the config file for Python logging.
# This line sets up loggers basically.
if config.config_file_name is not None:
fileConfig(config.config_file_name)
# add your model's MetaData object here
# for 'autogenerate' support
from src.models.mapping import Base
from src.models.translate import (
TranslationJob,
TranslationRun,
TranslationBatch,
TranslationRecord,
TranslationEvent,
TranslationPreviewSession,
TranslationPreviewRecord,
TerminologyDictionary,
DictionaryEntry,
TranslationSchedule,
TranslationJobDictionary,
MetricSnapshot,
TranslationLanguage,
TranslationPreviewLanguage,
TranslationRunLanguageStats,
)
target_metadata = Base.metadata
# other values from the config, defined by the needs of env.py,
# can be acquired:
# my_important_option = config.get_main_option("my_important_option")
# ... etc.
def run_migrations_offline() -> None:
"""Run migrations in 'offline' mode.
This configures the context with just a URL
and not an Engine, though an Engine is acceptable
here as well. By skipping the Engine creation
we don't even need a DBAPI to be available.
Calls to context.execute() here emit the given string to the
script output.
"""
url = config.get_main_option("sqlalchemy.url")
context.configure(
url=url,
target_metadata=target_metadata,
literal_binds=True,
dialect_opts={"paramstyle": "named"},
)
with context.begin_transaction():
context.run_migrations()
def run_migrations_online() -> None:
"""Run migrations in 'online' mode.
In this scenario we need to create an Engine
and associate a connection with the context.
"""
connectable = engine_from_config(
config.get_section(config.config_ini_section, {}),
prefix="sqlalchemy.",
poolclass=pool.NullPool,
)
with connectable.connect() as connection:
context.configure(
connection=connection, target_metadata=target_metadata
)
with context.begin_transaction():
context.run_migrations()
if context.is_offline_mode():
run_migrations_offline()
else:
run_migrations_online()