feat(i18n): inject user language into AI agent system prompts
- Add _language_instruction() to deep_agent.py, reads language from core memory - Append language directive to all 4 run_* functions (task/project/checkpoint/note) - Minor fixes: alembic env, route imports, test cleanup
This commit is contained in:
@@ -16,7 +16,7 @@ import re
|
||||
from logging.config import fileConfig
|
||||
|
||||
from alembic import context
|
||||
from sqlalchemy import engine_from_config, pool
|
||||
from sqlalchemy import pool
|
||||
from sqlalchemy.ext.asyncio import create_async_engine
|
||||
|
||||
# Alembic Config object (gives access to alembic.ini values).
|
||||
|
||||
@@ -14,7 +14,7 @@ from __future__ import annotations
|
||||
import asyncio
|
||||
import logging
|
||||
import uuid
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from datetime import datetime, timezone
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@@ -30,7 +30,6 @@ import asyncio
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import uuid
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from typing import Any
|
||||
|
||||
|
||||
@@ -27,6 +27,34 @@ logger = logging.getLogger(__name__)
|
||||
FloatingDomainType = Literal["task", "timeline", "project", "node"]
|
||||
FloatingDomainSection = Literal["task", "timeline", "note"]
|
||||
|
||||
# Mapping of core-memory language values to natural-language names for prompts.
|
||||
_LANGUAGE_NAMES: dict[str, str] = {
|
||||
"en": "English", "it": "Italian", "es": "Spanish",
|
||||
"fr": "French", "de": "German",
|
||||
"english": "English", "italian": "Italian", "italiano": "Italian",
|
||||
"spanish": "Spanish", "español": "Spanish",
|
||||
"french": "French", "français": "French",
|
||||
"german": "German", "deutsch": "German",
|
||||
}
|
||||
|
||||
|
||||
def _language_instruction(context: dict[str, Any]) -> str:
|
||||
"""Return a system-prompt suffix that tells the LLM to respond in the user's language.
|
||||
|
||||
Returns an empty string when the language is English or unknown — saves tokens.
|
||||
"""
|
||||
core = context.get("core_memory") or {}
|
||||
raw = (core.get("language") or "").strip().lower()
|
||||
if not raw:
|
||||
return ""
|
||||
lang = _LANGUAGE_NAMES.get(raw, raw.title()) # best-effort capitalisation
|
||||
if lang.lower() == "english":
|
||||
return ""
|
||||
return (
|
||||
f"\n\nIMPORTANT: Always respond in {lang}. "
|
||||
f"All your output text must be written in {lang}."
|
||||
)
|
||||
|
||||
_HOME_SYSTEM_PROMPT = (
|
||||
"You are the home assistant with direct access to all tools: tasks, projects, notes, timelines, and memory tools. "
|
||||
"Always use tools for factual data retrieval before answering. "
|
||||
@@ -876,6 +904,7 @@ async def run_home(user_id: str, message: str, context: dict[str, Any]) -> str:
|
||||
system_prompt, langfuse_prompt = get_prompt_or_fallback(
|
||||
"home_system", _HOME_SYSTEM_PROMPT
|
||||
)
|
||||
system_prompt += _language_instruction(context)
|
||||
response = await _run_single_agent(
|
||||
user_id=user_id,
|
||||
system_prompt=system_prompt,
|
||||
@@ -893,6 +922,7 @@ async def run_floating(user_id: str, message: str, context: dict[str, Any]) -> t
|
||||
system_prompt, langfuse_prompt = get_prompt_or_fallback(
|
||||
"floating_system", _FLOATING_SYSTEM_PROMPT
|
||||
)
|
||||
system_prompt += _language_instruction(context)
|
||||
response = await _run_single_agent(
|
||||
user_id=user_id,
|
||||
system_prompt=system_prompt,
|
||||
@@ -916,6 +946,7 @@ async def run_home_stream(
|
||||
system_prompt, langfuse_prompt = get_prompt_or_fallback(
|
||||
"home_system", _HOME_SYSTEM_PROMPT
|
||||
)
|
||||
system_prompt += _language_instruction(context)
|
||||
text_chunks: list[str] = []
|
||||
async for event in _run_single_agent_stream(
|
||||
user_id=user_id,
|
||||
@@ -948,6 +979,7 @@ async def run_floating_stream(
|
||||
system_prompt, langfuse_prompt = get_prompt_or_fallback(
|
||||
"floating_system", _FLOATING_SYSTEM_PROMPT
|
||||
)
|
||||
system_prompt += _language_instruction(context)
|
||||
sanitizer = _FloatingStreamSanitizer()
|
||||
emitted_sanitized = False
|
||||
raw_chunks: list[str] = []
|
||||
|
||||
@@ -25,7 +25,7 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import re
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
|
||||
import httpx
|
||||
|
||||
@@ -28,7 +28,6 @@ from datetime import datetime, timezone
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
import pytest_asyncio
|
||||
|
||||
from app.core.agent_runner import (
|
||||
_extract_items_from_content,
|
||||
@@ -597,7 +596,7 @@ async def test_run_cloud_agent_provider_fetch_error():
|
||||
@pytest.mark.asyncio
|
||||
async def test_run_cloud_agent_refreshed_token_persisted():
|
||||
"""When the provider refreshes its token, the new ciphertext is written to DB."""
|
||||
from app.integrations import EmailMessage, encrypt_token
|
||||
from app.integrations import encrypt_token
|
||||
from cryptography.fernet import Fernet as _Fernet
|
||||
|
||||
fernet_key = _Fernet.generate_key().decode()
|
||||
|
||||
@@ -40,7 +40,6 @@ from app.core.agent_runner import (
|
||||
_format_projects,
|
||||
_get_extraction_rules,
|
||||
_get_no_match_behavior,
|
||||
_is_overdue,
|
||||
run_local_agent,
|
||||
)
|
||||
from app.core.device_manager import DeviceConnectionManager
|
||||
|
||||
@@ -21,7 +21,6 @@ import time
|
||||
import uuid
|
||||
from unittest.mock import AsyncMock, patch
|
||||
|
||||
import pytest
|
||||
from fastapi.testclient import TestClient
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
|
||||
@@ -18,13 +18,12 @@ from datetime import datetime, timezone
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
import pytest_asyncio
|
||||
|
||||
from app.core.device_manager import DeviceConnection, DeviceConnectionManager
|
||||
from app.core.device_manager import DeviceConnectionManager
|
||||
from app.db import get_session
|
||||
from app.main import app
|
||||
from app.models import AgentRunLog
|
||||
from tests.conftest import TEST_USER_IDS, auth_header, make_jwt
|
||||
from tests.conftest import TEST_USER_IDS, make_jwt
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Helpers
|
||||
|
||||
@@ -40,11 +40,9 @@ Coverage:
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import uuid
|
||||
from datetime import datetime, timezone
|
||||
from unittest.mock import AsyncMock, MagicMock, Mock, PropertyMock, patch
|
||||
from unittest.mock import AsyncMock, MagicMock, PropertyMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ import pytest_asyncio
|
||||
from cryptography.fernet import Fernet
|
||||
from sqlalchemy import select
|
||||
|
||||
from app.core.memory_middleware import MemoryMiddleware, _PROACTIVE_CONFIDENCE_THRESHOLD
|
||||
from app.core.memory_middleware import MemoryMiddleware
|
||||
from app.db import get_session
|
||||
from app.main import app
|
||||
from app.models import (
|
||||
|
||||
@@ -7,10 +7,9 @@ column is stored as JSON in tests (SQLite-compatible).
|
||||
from __future__ import annotations
|
||||
|
||||
import uuid
|
||||
from datetime import datetime, timezone
|
||||
from datetime import datetime
|
||||
|
||||
import pytest
|
||||
import pytest_asyncio
|
||||
from cryptography.fernet import Fernet
|
||||
from sqlalchemy import select
|
||||
|
||||
|
||||
@@ -12,7 +12,6 @@ from __future__ import annotations
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
import yaml
|
||||
|
||||
from app.core.preprocessors import detect_content_type, preprocess
|
||||
|
||||
Reference in New Issue
Block a user