Hass/ha-text-ai
1
0
Fork 0
mirror of https://github.com/smkrv/ha-text-ai.git synced 2026-07-21 22:54:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: Comprehensive v2.4.0 quality pass — 24 review findings + review agent fixes

Browse Source 
Phase A — Critical:
- Remove dual timeout stacking in coordinator._send_to_api
- Add Gemini-specific asyncio.timeout (sync SDK via to_thread)
- Store full text in history for context; cap per-field at 32KB on disk
- Fix instance lookup to match by normalized_name
- Add Bearer/sk-/x-api-key credential sanitization patterns

Phase B — Dead code removal:
- Merge async_ask_question/async_process_question into single method
- Remove dead is_anthropic flag from coordinator and __init__
- Remove unused DEFAULT_TIMEOUT and API_TIMEOUT constants
- Remove redundant _create_history_dir calls
- Consolidate async_check_api to use provider registry

Phase C — Config flow correctness:
- Truncate name before uniqueness check (prevent post-truncation collisions)
- Add async_set_unique_id + _abort_if_unique_id_configured
- Extract shared _build_parameter_schema for ConfigFlow/OptionsFlow dedup

Phase D — UX improvements:
- Optimize history write: serialize from memory, single file write
- Show last 5 history entries in sensor attributes (was 1)
- Return actual error type in ask_question service response
- Add dedicated api_key_required error for provider/endpoint changes
- Pass config_entry to DataUpdateCoordinator (HA 2024.8+)

Phase E — Cleanup:
- Extract _apply_structured_output for OpenAI/DeepSeek dedup
- Reduce ABSOLUTE_MAX_HISTORY_SIZE to 200 with Final annotation
- Remove dead translation keys (queued, invalid_characters)
- Migrate to _attr_has_entity_name = True
- Add from __future__ import annotations to all modules
- Remove redundant api_status sensor attribute
- Add missing translation keys (last_model, last_timestamp, etc.)

Review agent fixes:
- Add archive file cleanup (max 3 archives) to prevent disk exhaustion
- Per-entry storage cap (32KB per field) for history on disk
This commit is contained in:
SMKRV
2026-03-12 02:24:09 +03:00
parent 9cdeb9f417
commit a8a91972ba
13 changed files with 272 additions and 275 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_components/ha_text_ai/__init__.py
+29 -21
View File
@@ -25,7 +25,7 @@ from homeassistant.util import dt as dt_util
from .coordinator import HATextAICoordinator
from .api_client import APIClient
from .utils import safe_log_data, validate_endpoint
from .utils import normalize_name, safe_log_data, validate_endpoint
from .providers import get_default_endpoint, get_default_model, build_auth_headers
from .const import (
DOMAIN,
@@ -38,9 +38,6 @@ from .const import (
CONF_API_TIMEOUT,
CONF_API_PROVIDER,
CONF_CONTEXT_MESSAGES,
API_PROVIDER_ANTHROPIC,
API_PROVIDER_DEEPSEEK,
API_PROVIDER_GEMINI,
DEFAULT_TEMPERATURE,
DEFAULT_MAX_TOKENS,
DEFAULT_REQUEST_INTERVAL,
@@ -87,12 +84,22 @@ SERVICE_SCHEMA_GET_HISTORY = vol.Schema({
})
def get_coordinator_by_instance(hass: HomeAssistant, instance: str) -> HATextAICoordinator:
"""Get coordinator by instance name."""
"""Get coordinator by instance name or normalized name.
Accepts instance_name, normalized_name, or sensor entity_id.
"""
if instance.startswith("sensor."):
instance = instance.replace("sensor.ha_text_ai_", "", 1)
normalized_input = normalize_name(instance)
for entry_id, coord in hass.data[DOMAIN].items():
if isinstance(coord, HATextAICoordinator) and coord.instance_name.lower() == instance.lower():
if not isinstance(coord, HATextAICoordinator):
continue
if (
coord.instance_name.lower() == instance.lower()
or coord.normalized_name == normalized_input
):
return coord
raise HomeAssistantError(f"Instance {instance} not found")
@@ -142,7 +149,8 @@ async def async_setup(hass: HomeAssistant, config: Dict[str, Any]) -> bool:
"question": call.data["question"],
"timestamp": dt_util.utcnow().isoformat(),
"success": False,
"error": "Service call failed"
"error": str(err),
"error_type": type(err).__name__
}
async def async_clear_history(call: ServiceCall) -> None:
@@ -212,21 +220,22 @@ async def async_setup(hass: HomeAssistant, config: Dict[str, Any]) -> bool:
return True
async def async_check_api(session, endpoint: str, headers: dict, provider: str, api_timeout: int = DEFAULT_API_TIMEOUT) -> bool:
"""Check API availability for different providers."""
"""Check API availability using provider registry configuration."""
try:
if provider == API_PROVIDER_GEMINI:
# Gemini API does not support GET /models for validation, just check key presence
if headers.get("Authorization", "").replace("Bearer ", ""):
from .providers import get_provider_config
provider_config = get_provider_config(provider)
check_path = provider_config.get("check_path")
if check_path is None:
# Provider does not support /models check (e.g. Gemini)
auth_header = provider_config["auth_header"]
auth_value = headers.get(auth_header, "").replace(provider_config.get("auth_prefix", ""), "")
if auth_value:
return True
else:
_LOGGER.error("Gemini API key is missing or empty")
_LOGGER.error("API key is missing or empty for %s", provider)
return False
elif provider == API_PROVIDER_ANTHROPIC:
check_url = f"{endpoint}/v1/models"
elif provider == API_PROVIDER_DEEPSEEK:
check_url = f"{endpoint}/models"
else: # OpenAI
check_url = f"{endpoint}/models"
check_url = f"{endpoint}{check_path}"
async with asyncio.timeout(api_timeout):
async with session.get(check_url, headers=headers) as response:
@@ -276,7 +285,6 @@ async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
temperature = config.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)
max_history_size = config.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
context_messages = config.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
is_anthropic = api_provider == API_PROVIDER_ANTHROPIC
headers = build_auth_headers(api_provider, api_key)
@@ -301,11 +309,11 @@ async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
model=model,
update_interval=request_interval,
instance_name=instance_name,
config_entry=entry,
max_tokens=max_tokens,
temperature=temperature,
max_history_size=max_history_size,
context_messages=context_messages,
is_anthropic=is_anthropic,
api_timeout=api_timeout,
)
custom_components/ha_text_ai/api_client.py
+32 -37
View File
@@ -6,6 +6,8 @@ API Client for HA Text AI.
@github: https://github.com/smkrv/ha-text-ai
@source: https://github.com/smkrv/ha-text-ai
"""
from __future__ import annotations
import logging
import asyncio
from typing import Any, Dict, List, Optional
@@ -182,6 +184,30 @@ class APIClient:
_LOGGER.error("API request failed: %s", str(e))
raise HomeAssistantError(f"API request failed: {str(e)}")
@staticmethod
def _apply_structured_output(
payload: Dict[str, Any],
structured_output: bool,
json_schema: Optional[str],
) -> None:
"""Apply OpenAI-compatible structured output to payload in-place."""
if not (structured_output and json_schema):
return
import json
try:
schema = json.loads(json_schema)
payload["response_format"] = {
"type": "json_schema",
"json_schema": {
"name": "structured_response",
"strict": True,
"schema": schema,
},
}
except json.JSONDecodeError as e:
_LOGGER.warning("Invalid JSON schema: %s. Falling back to json_object.", e)
payload["response_format"] = {"type": "json_object"}
async def _create_deepseek_completion(
self,
model: str,
@@ -198,26 +224,9 @@ class APIClient:
"messages": messages,
"temperature": temperature,
"max_tokens": max_tokens,
"stream": False
"stream": False,
}
# Add structured output format if enabled (DeepSeek is OpenAI-compatible)
if structured_output and json_schema:
try:
import json
schema = json.loads(json_schema)
payload["response_format"] = {
"type": "json_schema",
"json_schema": {
"name": "structured_response",
"strict": True,
"schema": schema
}
}
_LOGGER.debug("DeepSeek structured output enabled with schema")
except json.JSONDecodeError as e:
_LOGGER.warning("Invalid JSON schema provided: %s. Falling back to json_object mode.", e)
payload["response_format"] = {"type": "json_object"}
self._apply_structured_output(payload, structured_output, json_schema)
data = await self._make_request(url, payload)
return {
@@ -250,24 +259,7 @@ class APIClient:
"temperature": temperature,
"max_tokens": max_tokens,
}
# Add structured output format if enabled
if structured_output and json_schema:
try:
import json
schema = json.loads(json_schema)
payload["response_format"] = {
"type": "json_schema",
"json_schema": {
"name": "structured_response",
"strict": True,
"schema": schema
}
}
_LOGGER.debug("OpenAI structured output enabled with schema")
except json.JSONDecodeError as e:
_LOGGER.warning("Invalid JSON schema provided: %s. Falling back to json_object mode.", e)
payload["response_format"] = {"type": "json_object"}
self._apply_structured_output(payload, structured_output, json_schema)
data = await self._make_request(url, payload)
return {
@@ -469,6 +461,9 @@ class APIClient:
)
return chat.send_message(last_user_msg)
# Gemini uses sync SDK via to_thread, so needs its own timeout
# (aiohttp ClientTimeout doesn't apply here)
async with asyncio.timeout(self.api_timeout):
response = await asyncio.to_thread(generate_content)
# Extract response text
custom_components/ha_text_ai/config_flow.py
+56 -102
View File
@@ -6,6 +6,8 @@ Config flow for HA text AI integration.
@github: https://github.com/smkrv/ha-text-ai
@source: https://github.com/smkrv/ha-text-ai
"""
from __future__ import annotations
import logging
from typing import Any, Dict, Optional
@@ -61,6 +63,36 @@ from .providers import get_default_endpoint, get_default_model, build_auth_heade
_LOGGER = logging.getLogger(__name__)
def _build_parameter_schema(data: Dict[str, Any]) -> dict:
"""Build shared parameter schema fields used by both ConfigFlow and OptionsFlow."""
return {
vol.Optional(
CONF_TEMPERATURE,
default=data.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE),
): vol.All(vol.Coerce(float), vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)),
vol.Optional(
CONF_MAX_TOKENS,
default=data.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS),
): vol.All(vol.Coerce(int), vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)),
vol.Optional(
CONF_REQUEST_INTERVAL,
default=data.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL),
): vol.All(vol.Coerce(float), vol.Range(min=MIN_REQUEST_INTERVAL)),
vol.Optional(
CONF_API_TIMEOUT,
default=data.get(CONF_API_TIMEOUT, DEFAULT_API_TIMEOUT),
): vol.All(vol.Coerce(int), vol.Range(min=MIN_API_TIMEOUT, max=MAX_API_TIMEOUT)),
vol.Optional(
CONF_CONTEXT_MESSAGES,
default=data.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES),
): vol.All(vol.Coerce(int), vol.Range(min=MIN_CONTEXT_MESSAGES, max=MAX_CONTEXT_MESSAGES)),
vol.Optional(
CONF_MAX_HISTORY_SIZE,
default=data.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY),
): vol.All(vol.Coerce(int), vol.Range(min=MIN_HISTORY_SIZE, max=MAX_HISTORY_SIZE)),
}
class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
"""Handle a config flow for HA text AI."""
@@ -95,42 +127,14 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
) -> vol.Schema:
"""Build provider configuration schema with optional defaults from data."""
defaults = data or {}
return vol.Schema({
schema_dict = {
vol.Required(CONF_NAME, default=defaults.get(CONF_NAME, DEFAULT_INSTANCE_NAME)): str,
vol.Required(CONF_API_KEY): str,
vol.Required(CONF_MODEL, default=defaults.get(CONF_MODEL, get_default_model(self._provider))): str,
vol.Required(CONF_API_ENDPOINT, default=defaults.get(CONF_API_ENDPOINT, get_default_endpoint(self._provider))): str,
vol.Optional(CONF_TEMPERATURE, default=defaults.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)): vol.All(
vol.Coerce(float),
vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
),
vol.Optional(CONF_MAX_TOKENS, default=defaults.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)): vol.All(
vol.Coerce(int),
vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
),
vol.Optional(CONF_REQUEST_INTERVAL, default=defaults.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)): vol.All(
vol.Coerce(float),
vol.Range(min=MIN_REQUEST_INTERVAL)
),
vol.Optional(CONF_API_TIMEOUT, default=defaults.get(CONF_API_TIMEOUT, DEFAULT_API_TIMEOUT)): vol.All(
vol.Coerce(int),
vol.Range(min=MIN_API_TIMEOUT, max=MAX_API_TIMEOUT)
),
vol.Optional(
CONF_CONTEXT_MESSAGES,
default=defaults.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
): vol.All(
vol.Coerce(int),
vol.Range(min=MIN_CONTEXT_MESSAGES, max=MAX_CONTEXT_MESSAGES)
),
vol.Optional(
CONF_MAX_HISTORY_SIZE,
default=defaults.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
): vol.All(
vol.Coerce(int),
vol.Range(min=MIN_HISTORY_SIZE, max=MAX_HISTORY_SIZE)
),
})
}
schema_dict.update(_build_parameter_schema(defaults))
return vol.Schema(schema_dict)
async def async_step_provider(self, user_input: Optional[Dict[str, Any]] = None) -> ConfigFlowResult:
"""Handle provider configuration step."""
@@ -190,35 +194,25 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
return await self._create_entry(input_copy)
def _validate_and_normalize_name(self, name: str) -> str:
"""
Validate and normalize name with detailed error handling.
"""Validate and normalize name.
Truncates before uniqueness check to prevent collisions.
Raises:
ValueError: If name is invalid
Returns:
Normalized name
ValueError: If name is invalid or already exists.
"""
if not name:
if not name or not name.strip():
raise ValueError("empty")
name = name.strip()
normalized = ''.join(
c if c.isalnum() or c in ' _' else '_' # Only allow underscores
for c in name
)
normalized = normalize_name(name.strip())[:50]
normalized = normalized.replace(' ', '_').lower()
if not normalized:
raise ValueError("empty")
for entry in self._async_current_entries():
if entry.data.get(CONF_NAME, "") == normalized:
raise ValueError("name_exists")
normalized = normalized[:50]
if not normalized:
raise ValueError("empty")
return normalized
async def _async_validate_api(self, user_input: Dict[str, Any]) -> bool:
@@ -264,21 +258,21 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
return False
async def _create_entry(self, user_input: Dict[str, Any]) -> ConfigFlowResult:
"""Create the config entry with comprehensive data preservation."""
"""Create the config entry with unique_id deduplication."""
instance_name = user_input[CONF_NAME]
normalized_name = normalize_name(instance_name)
unique_id = f"{DOMAIN}_{normalized_name}_{self._provider}".lower()
unique_id = f"{DOMAIN}_{normalized_name}_{self._provider}"
await self.async_set_unique_id(unique_id)
self._abort_if_unique_id_configured()
default_model = get_default_model(self._provider)
entry_data = {
CONF_API_PROVIDER: self._provider,
CONF_NAME: instance_name,
"normalized_name": normalized_name,
CONF_API_KEY: user_input.get(CONF_API_KEY),
CONF_API_ENDPOINT: user_input.get(CONF_API_ENDPOINT),
"unique_id": unique_id,
CONF_MODEL: user_input.get(CONF_MODEL, default_model),
CONF_TEMPERATURE: user_input.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE),
CONF_MAX_TOKENS: user_input.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS),
@@ -398,7 +392,7 @@ class OptionsFlowHandler(config_entries.OptionsFlow):
stored_endpoint = current_data.get(CONF_API_ENDPOINT, "")
endpoint_changed = endpoint != stored_endpoint
if not api_key and (provider_changed or endpoint_changed):
self._errors["base"] = "invalid_auth"
self._errors["base"] = "api_key_required"
return self.async_show_form(
step_id="settings",
data_schema=self._get_settings_schema(
@@ -464,59 +458,19 @@ class OptionsFlowHandler(config_entries.OptionsFlow):
default_endpoint: str,
default_model: str,
) -> vol.Schema:
"""Build settings schema."""
"""Build settings schema using shared parameter definitions."""
data = user_input or current_data
return vol.Schema({
schema_dict = {
vol.Optional(CONF_API_KEY, default=""): str,
vol.Required(
CONF_API_ENDPOINT,
default=data.get(CONF_API_ENDPOINT, default_endpoint)
default=data.get(CONF_API_ENDPOINT, default_endpoint),
): str,
vol.Required(
CONF_MODEL,
default=data.get(CONF_MODEL, default_model)
default=data.get(CONF_MODEL, default_model),
): str,
vol.Optional(
CONF_TEMPERATURE,
default=data.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)
): vol.All(
vol.Coerce(float),
vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
),
vol.Optional(
CONF_MAX_TOKENS,
default=data.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)
): vol.All(
vol.Coerce(int),
vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
),
vol.Optional(
CONF_REQUEST_INTERVAL,
default=data.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)
): vol.All(
vol.Coerce(float),
vol.Range(min=MIN_REQUEST_INTERVAL)
),
vol.Optional(
CONF_API_TIMEOUT,
default=data.get(CONF_API_TIMEOUT, DEFAULT_API_TIMEOUT)
): vol.All(
vol.Coerce(int),
vol.Range(min=MIN_API_TIMEOUT, max=MAX_API_TIMEOUT)
),
vol.Optional(
CONF_CONTEXT_MESSAGES,
default=data.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
): vol.All(
vol.Coerce(int),
vol.Range(min=MIN_CONTEXT_MESSAGES, max=MAX_CONTEXT_MESSAGES)
),
vol.Optional(
CONF_MAX_HISTORY_SIZE,
default=data.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
): vol.All(
vol.Coerce(int),
vol.Range(min=MIN_HISTORY_SIZE, max=MAX_HISTORY_SIZE)
),
})
}
schema_dict.update(_build_parameter_schema(data))
return vol.Schema(schema_dict)
custom_components/ha_text_ai/const.py
+3 -4
View File
@@ -6,6 +6,8 @@ Constants for the HA text AI integration.
@github: https://github.com/smkrv/ha-text-ai
@source: https://github.com/smkrv/ha-text-ai
"""
from __future__ import annotations
from typing import Final
from homeassistant.const import Platform
@@ -44,12 +46,11 @@ CONF_REQUEST_INTERVAL: Final = "request_interval"
CONF_API_TIMEOUT: Final = "api_timeout"
CONF_INSTANCE: Final = "instance"
CONF_MAX_HISTORY_SIZE: Final = "max_history_size" # Correct constant name
CONF_IS_ANTHROPIC: Final = "is_anthropic"
CONF_CONTEXT_MESSAGES: Final = "context_messages"
CONF_STRUCTURED_OUTPUT: Final = "structured_output"
CONF_JSON_SCHEMA: Final = "json_schema"
ABSOLUTE_MAX_HISTORY_SIZE = 500
ABSOLUTE_MAX_HISTORY_SIZE: Final = 200 # Hard cap; UI allows max MAX_HISTORY_SIZE (100)
MAX_ATTRIBUTE_SIZE = 4 * 1024
MAX_HISTORY_FILE_SIZE = 1 * 1024 * 1024
# Default values
@@ -60,7 +61,6 @@ DEFAULT_GEMINI_MODEL: Final = "gemini-2.0-flash"
DEFAULT_TEMPERATURE: Final = 0.1
DEFAULT_MAX_TOKENS: Final = 1000
DEFAULT_REQUEST_INTERVAL: Final = 1.0
DEFAULT_TIMEOUT: Final = 30
DEFAULT_API_TIMEOUT: Final = 30
DEFAULT_MAX_HISTORY: Final = 50
DEFAULT_NAME: Final = "HA Text AI"
@@ -85,7 +85,6 @@ MIN_API_TIMEOUT: Final = 5
MAX_API_TIMEOUT: Final = 600
# API constants
API_TIMEOUT: Final = 30 # Legacy constant, use CONF_API_TIMEOUT from config
API_RETRY_COUNT: Final = 3
# Service names
custom_components/ha_text_ai/coordinator.py
+8 -23
View File
@@ -14,6 +14,7 @@ import os
from datetime import timedelta
from typing import Any, Dict, List, Optional
from homeassistant.config_entries import ConfigEntry
from homeassistant.core import HomeAssistant
from homeassistant.exceptions import HomeAssistantError
from homeassistant.helpers.update_coordinator import DataUpdateCoordinator
@@ -49,11 +50,11 @@ class HATextAICoordinator(DataUpdateCoordinator):
model: str,
update_interval: int,
instance_name: str,
config_entry: ConfigEntry,
max_tokens: int = DEFAULT_MAX_TOKENS,
temperature: float = DEFAULT_TEMPERATURE,
max_history_size: int = DEFAULT_MAX_HISTORY,
context_messages: int = DEFAULT_CONTEXT_MESSAGES,
is_anthropic: bool = False,
api_timeout: int = DEFAULT_API_TIMEOUT,
) -> None:
"""Initialize coordinator."""
@@ -87,7 +88,6 @@ class HATextAICoordinator(DataUpdateCoordinator):
self.model = model
self.temperature = temperature
self.max_tokens = max_tokens
self.is_anthropic = is_anthropic
self.api_timeout = api_timeout
# Concurrency control
@@ -115,6 +115,7 @@ class HATextAICoordinator(DataUpdateCoordinator):
_LOGGER,
name=instance_name,
update_interval=timedelta(seconds=update_interval),
config_entry=config_entry,
)
self.available = True
@@ -212,23 +213,6 @@ class HATextAICoordinator(DataUpdateCoordinator):
context_messages: Optional[int] = None,
structured_output: bool = False,
json_schema: Optional[str] = None,
) -> dict:
"""Process a question with optional parameters."""
return await self.async_process_question(
question, model, temperature, max_tokens, system_prompt,
context_messages, structured_output, json_schema,
)
async def async_process_question(
self,
question: str,
model: Optional[str] = None,
temperature: Optional[float] = None,
max_tokens: Optional[int] = None,
system_prompt: Optional[str] = None,
context_messages: Optional[int] = None,
structured_output: bool = False,
json_schema: Optional[str] = None,
) -> dict:
"""Process question with context management."""
if self.client is None:
@@ -295,9 +279,12 @@ class HATextAICoordinator(DataUpdateCoordinator):
structured_output: bool = False,
json_schema: Optional[str] = None,
) -> dict:
"""Send request to AI provider and return structured response."""
"""Send request to AI provider and return structured response.
Note: timeout is handled by APIClient via aiohttp ClientTimeout.
No additional asyncio.timeout wrapper to avoid dual timeout stacking.
"""
try:
async with asyncio.timeout(self.api_timeout):
response = await self.client.create(
model=model,
messages=messages,
@@ -339,8 +326,6 @@ class HATextAICoordinator(DataUpdateCoordinator):
"success": True,
}
except asyncio.TimeoutError:
raise HomeAssistantError("Request timed out")
except Exception as err:
_LOGGER.error("Error in API call: %s", err)
raise
custom_components/ha_text_ai/history.py
+61 -64
View File
@@ -28,6 +28,10 @@ from .const import (
TRUNCATION_INDICATOR,
)
# Per-entry storage cap (32KB per field) to prevent disk exhaustion
MAX_STORED_FIELD_SIZE = 32 * 1024
MAX_ARCHIVE_FILES = 3
_LOGGER = logging.getLogger(__name__)
@@ -107,7 +111,6 @@ class HistoryManager:
async def _check_history_directory(self) -> None:
"""Check history directory permissions and writability."""
try:
await self._create_history_dir()
test_file_path = os.path.join(self._history_dir, ".write_test")
await self.hass.async_add_executor_job(
self._sync_test_directory_write, test_file_path
@@ -129,8 +132,6 @@ class HistoryManager:
async def _initialize_history_file(self) -> None:
"""Initialize history file and load existing history."""
try:
await self._create_history_dir()
if await self._file_exists(self._history_file):
async with AsyncFileHandler(self._history_file, "r") as f:
content = await f.read()
@@ -155,71 +156,43 @@ class HistoryManager:
_LOGGER.debug(traceback.format_exc())
async def update_history(self, question: str, response: dict) -> None:
"""Update conversation history with size validation."""
"""Update conversation history.
In-memory history stores full text for context retrieval.
On-disk storage caps per-field size to prevent disk exhaustion.
Display truncation is handled by get_limited_history().
"""
try:
content = response.get("content", "")
history_entry = {
"timestamp": dt_util.utcnow().isoformat(),
"question": self._truncate_text(question, MAX_ATTRIBUTE_SIZE),
"response": self._truncate_text(
response.get("content", ""), MAX_ATTRIBUTE_SIZE
),
"question": question[:MAX_STORED_FIELD_SIZE],
"response": content[:MAX_STORED_FIELD_SIZE],
}
entry_size = len(json.dumps(history_entry).encode("utf-8"))
current_size = await self._check_file_size(self._history_file)
if current_size + entry_size > MAX_HISTORY_FILE_SIZE:
_LOGGER.warning(
"History size limit approaching. Current: %d, Entry: %d, Max: %d",
current_size, entry_size, MAX_HISTORY_FILE_SIZE,
)
await self._rotate_history()
self._conversation_history.append(history_entry)
while len(self._conversation_history) > self.max_history_size:
self._conversation_history.pop(0)
await self._write_history_entry(history_entry)
await self._save_history_to_file()
except Exception as e:
_LOGGER.error("Error updating history: %s", e)
_LOGGER.debug(traceback.format_exc())
async def _write_history_entry(self, entry: dict) -> None:
"""Write history entry with file size checks."""
async def _save_history_to_file(self) -> None:
"""Serialize in-memory history to file with rotation if needed."""
try:
if not await self._file_exists(self._history_dir):
await self._create_history_dir()
data = json.dumps(self._conversation_history, indent=2)
data_size = len(data.encode("utf-8"))
current_size = 0
if await self._file_exists(self._history_file):
current_size = await self.hass.async_add_executor_job(
os.path.getsize, self._history_file
)
entry_size = len(json.dumps(entry).encode("utf-8"))
if current_size + entry_size > MAX_HISTORY_FILE_SIZE:
_LOGGER.warning(
"History file size limit reached. Current: %d, Entry: %d, Max: %d",
current_size, entry_size, MAX_HISTORY_FILE_SIZE,
)
if data_size > MAX_HISTORY_FILE_SIZE:
await self._rotate_history()
history = []
if await self._file_exists(self._history_file):
async with AsyncFileHandler(self._history_file, "r") as f:
content = await f.read()
if content:
history = json.loads(content)
history.append(entry)
if len(history) > self.max_history_size:
history = history[-self.max_history_size :]
async with AsyncFileHandler(self._history_file, "w") as f:
await f.write(json.dumps(history, indent=2))
await f.write(data)
except Exception as e:
_LOGGER.error("Error writing history entry: %s", e)
_LOGGER.error("Error writing history file: %s", e)
_LOGGER.debug(traceback.format_exc())
async def _check_history_size(self) -> None:
@@ -283,10 +256,34 @@ class HistoryManager:
)
_LOGGER.info("History file rotated to: %s", archive_file)
# Clean up old archive files, keep only MAX_ARCHIVE_FILES
await self._cleanup_archives()
except Exception as e:
_LOGGER.error("History rotation failed: %s", e)
_LOGGER.debug(traceback.format_exc())
async def _cleanup_archives(self) -> None:
"""Remove old archive files beyond MAX_ARCHIVE_FILES."""
try:
prefix = f"{self.normalized_name}_history_"
def find_archives():
archives = []
for f in os.listdir(self._history_dir):
if f.startswith(prefix) and f.endswith(".json") and f != os.path.basename(self._history_file):
archives.append(os.path.join(self._history_dir, f))
archives.sort()
return archives
archives = await self.hass.async_add_executor_job(find_archives)
if len(archives) > MAX_ARCHIVE_FILES:
for old_file in archives[:-MAX_ARCHIVE_FILES]:
await self.hass.async_add_executor_job(os.remove, old_file)
_LOGGER.debug("Removed old archive: %s", old_file)
except Exception as e:
_LOGGER.warning("Archive cleanup error: %s", e)
async def _migrate_history_from_txt_to_json(self) -> None:
"""Migrate old .txt history to .json format."""
try:
@@ -424,27 +421,27 @@ class HistoryManager:
_LOGGER.error("Error getting history: %s", e)
return []
def get_limited_history(self) -> Dict[str, Any]:
"""Get limited conversation history showing only last Q&A."""
limited_history = []
def get_limited_history(self, max_display: int = 5) -> Dict[str, Any]:
"""Get limited conversation history for sensor attributes.
if self._conversation_history:
last_entry = self._conversation_history[-1]
limited_entry = {
"timestamp": last_entry["timestamp"],
"question": self._truncate_text(last_entry["question"], 4096),
"response": self._truncate_text(last_entry["response"], 4096),
}
limited_history.append(limited_entry)
history_info = {
"total_entries": len(self._conversation_history),
"displayed_entries": len(limited_history),
Returns last `max_display` entries with truncated text for HA state.
"""
recent = self._conversation_history[-max_display:]
limited_history = [
{
"timestamp": entry["timestamp"],
"question": self._truncate_text(entry["question"], 4096),
"response": self._truncate_text(entry["response"], 4096),
}
for entry in recent
]
return {
"entries": limited_history,
"info": history_info,
"info": {
"total_entries": len(self._conversation_history),
"displayed_entries": len(limited_history),
},
}
@staticmethod
custom_components/ha_text_ai/metrics.py
+4 -1
View File
@@ -123,10 +123,13 @@ class MetricsManager:
await self._save_metrics()
error_msg = str(error)
# Strip URLs, API keys, and query parameters from error messages
# Strip URLs, API keys, tokens, and query parameters from error messages
error_msg = re.sub(r'https?://\S+', '[URL]', error_msg)
error_msg = re.sub(r'[?&]key=[^\s&]+', '?key=***', error_msg)
error_msg = re.sub(r'AIza[A-Za-z0-9_-]+', '***', error_msg)
error_msg = re.sub(r'Bearer\s+\S+', 'Bearer ***', error_msg)
error_msg = re.sub(r'sk-[A-Za-z0-9_-]{20,}', '***', error_msg)
error_msg = re.sub(r'x-api-key:\s*\S+', 'x-api-key: ***', error_msg, flags=re.IGNORECASE)
if len(error_msg) > 256:
error_msg = error_msg[:256] + "..."
custom_components/ha_text_ai/providers.py
+2
View File
@@ -9,6 +9,8 @@ across __init__.py, config_flow.py, and api_client.py.
@github: https://github.com/smkrv/ha-text-ai
@source: https://github.com/smkrv/ha-text-ai
"""
from __future__ import annotations
from typing import Any
from .const import (
custom_components/ha_text_ai/sensor.py
+5 -4
View File
@@ -6,6 +6,8 @@ Sensor platform for HA Text AI.
@github: https://github.com/smkrv/ha-text-ai
@source: https://github.com/smkrv/ha-text-ai
"""
from __future__ import annotations
import logging
import math
from typing import Any, Dict
@@ -42,7 +44,6 @@ from .const import (
ATTR_API_PROVIDER,
ATTR_MODEL,
ATTR_SYSTEM_PROMPT,
ATTR_API_STATUS,
ATTR_RESPONSE,
ATTR_QUESTION,
ATTR_CONVERSATION_HISTORY,
@@ -126,9 +127,10 @@ class HATextAISensor(CoordinatorEntity, SensorEntity):
self._conversation_history = []
self._system_prompt = None
self._attr_name = f"HA Text AI {self._instance_name}"
self._attr_has_entity_name = True
self._attr_name = self._instance_name
self.entity_id = f"sensor.ha_text_ai_{self._normalized_name}"
self._attr_unique_id = f"{config_entry.entry_id}"
self._attr_unique_id = config_entry.entry_id
_LOGGER.debug("Created sensor with entity_id: %s", self.entity_id)
_LOGGER.debug("Sensor name: %s", self._attr_name)
@@ -238,7 +240,6 @@ class HATextAISensor(CoordinatorEntity, SensorEntity):
attributes = {
ATTR_MODEL: self._config_entry.data.get(CONF_MODEL, "Unknown"),
ATTR_API_PROVIDER: self._config_entry.data.get(CONF_API_PROVIDER, "Unknown"),
ATTR_API_STATUS: self._current_state,
ATTR_TOTAL_ERRORS: metrics.get("total_errors", 0),
"instance_name": self._instance_name,
"normalized_name": self._normalized_name,
custom_components/ha_text_ai/strings.json
+20 -3
View File
@@ -42,6 +42,7 @@
"name_exists": "An instance with this name already exists",
"invalid_name": "Invalid instance name",
"invalid_auth": "Authentication failed - check your API key",
"api_key_required": "API key is required when changing provider or endpoint",
"invalid_api_key": "Invalid API key - please verify your credentials",
"cannot_connect": "Failed to connect to API service",
"invalid_model": "Selected model is not available",
@@ -55,7 +56,6 @@
"invalid_instance": "Invalid instance specified",
"unknown": "Unexpected error occurred",
"empty": "Name cannot be empty",
"invalid_characters": "Name can only contain letters, numbers, spaces, underscores and hyphens",
"name_too_long": "Name must be 50 characters or less"
},
"abort": {
@@ -208,8 +208,7 @@
"rate_limited": "Rate Limited",
"maintenance": "Maintenance",
"initializing": "Initializing",
"retrying": "Retrying",
"queued": "Queued"
"retrying": "Retrying"
},
"state_attributes": {
"question": {
@@ -301,6 +300,24 @@
},
"min_latency": {
"name": "Minimum Latency"
},
"last_model": {
"name": "Last Used Model"
},
"last_timestamp": {
"name": "Last Response Time"
},
"instance_name": {
"name": "Instance Name"
},
"normalized_name": {
"name": "Normalized Name"
},
"last_error": {
"name": "Last Error"
},
"conversation_history": {
"name": "Conversation History"
}
}
}
custom_components/ha_text_ai/translations/en.json
+20 -3
View File
@@ -42,6 +42,7 @@
"name_exists": "An instance with this name already exists",
"invalid_name": "Invalid instance name",
"invalid_auth": "Authentication failed - check your API key",
"api_key_required": "API key is required when changing provider or endpoint",
"invalid_api_key": "Invalid API key - please verify your credentials",
"cannot_connect": "Failed to connect to API service",
"invalid_model": "Selected model is not available",
@@ -55,7 +56,6 @@
"invalid_instance": "Invalid instance specified",
"unknown": "Unexpected error occurred",
"empty": "Name cannot be empty",
"invalid_characters": "Name can only contain letters, numbers, spaces, underscores and hyphens",
"name_too_long": "Name must be 50 characters or less"
},
"abort": {
@@ -208,8 +208,7 @@
"rate_limited": "Rate Limited",
"maintenance": "Maintenance",
"initializing": "Initializing",
"retrying": "Retrying",
"queued": "Queued"
"retrying": "Retrying"
},
"state_attributes": {
"question": {
@@ -301,6 +300,24 @@
},
"min_latency": {
"name": "Minimum Latency"
},
"last_model": {
"name": "Last Used Model"
},
"last_timestamp": {
"name": "Last Response Time"
},
"instance_name": {
"name": "Instance Name"
},
"normalized_name": {
"name": "Normalized Name"
},
"last_error": {
"name": "Last Error"
},
"conversation_history": {
"name": "Conversation History"
}
}
}
custom_components/ha_text_ai/translations/ru.json
+20 -3
View File
@@ -42,6 +42,7 @@
"name_exists": "Экземпляр с таким именем уже существует",
"invalid_name": "Недопустимое имя экземпляра",
"invalid_auth": "Ошибка аутентификации - проверьте API-ключ",
"api_key_required": "Необходимо ввести API-ключ при смене провайдера или эндпоинта",
"invalid_api_key": "Недопустимый API-ключ - пожалуйста, проверьте учетные данные",
"cannot_connect": "Не удалось подключиться к сервису API",
"invalid_model": "Выбранная модель недоступна",
@@ -55,7 +56,6 @@
"invalid_instance": "Указан некорректный экземпляр",
"unknown": "Произошла непредвиденная ошибка",
"empty": "Имя не может быть пустым",
"invalid_characters": "Имя может содержать только буквы, цифры, пробелы, подчеркивания и дефисы",
"name_too_long": "Имя должно быть не длиннее 50 символов"
},
"abort": {
@@ -208,8 +208,7 @@
"rate_limited": "Лимит запросов",
"maintenance": "Техническое обслуживание",
"initializing": "Инициализация",
"retrying": "Повторная попытка",
"queued": "В очереди"
"retrying": "Повторная попытка"
},
"state_attributes": {
"question": {
@@ -301,6 +300,24 @@
},
"min_latency": {
"name": "Минимальная задержка"
},
"last_model": {
"name": "Последняя использованная модель"
},
"last_timestamp": {
"name": "Время последнего ответа"
},
"instance_name": {
"name": "Имя экземпляра"
},
"normalized_name": {
"name": "Нормализованное имя"
},
"last_error": {
"name": "Последняя ошибка"
},
"conversation_history": {
"name": "История разговоров"
}
}
}
custom_components/ha_text_ai/utils.py
+2
View File
@@ -6,6 +6,8 @@ Utility functions for HA Text AI integration.
@github: https://github.com/smkrv/ha-text-ai
@source: https://github.com/smkrv/ha-text-ai
"""
from __future__ import annotations
import ipaddress
import socket
from typing import Any