francwa/alfred
1
0
Fork 0
Code Issues 1 Pull Requests 8 Actions Packages Projects Releases Wiki Activity

feat!: migrate to OpenAI native tool calls and fix circular deps (#fuck-gemini)

Browse Source 
- Fix circular dependencies in agent/tools
- Migrate from custom JSON to OpenAI tool calls format
- Add async streaming (step_stream, complete_stream)
- Simplify prompt system and remove token counting
- Add 5 new API endpoints (/health, /v1/models, /api/memory/*)
- Add 3 new tools (get_torrent_by_index, add_torrent_by_index, set_language)
- Fix all 500 tests and add coverage config (80% threshold)
- Add comprehensive docs (README, pytest guide)

BREAKING: LLM interface changed, memory injection via get_memory()
This commit is contained in:
Francwa
2025-12-06 19:11:05 +01:00
parent 2c8cdd3ab1
commit 9ca31e45e0
92 changed files with 7897 additions and 1786 deletions
Download Patch File Download Diff File Expand all files Collapse all files
agent/llm/__init__.py
+10 -2
View File
@@ -1,5 +1,13 @@
"""LLM client module."""
"""LLM clients module."""
from .deepseek import DeepSeekClient
from .exceptions import LLMAPIError, LLMConfigurationError, LLMError
from .ollama import OllamaClient
__all__ = ['DeepSeekClient', 'OllamaClient']
__all__ = [
"DeepSeekClient",
"OllamaClient",
"LLMError",
"LLMAPIError",
"LLMConfigurationError",
]
agent/llm/deepseek.py
+35 -48
View File
@@ -1,48 +1,36 @@
"""DeepSeek LLM client with robust error handling."""
from typing import List, Dict, Any, Optional
import logging
from typing import Any
import requests
from requests.exceptions import RequestException, Timeout, HTTPError
from requests.exceptions import HTTPError, RequestException, Timeout
from ..config import settings
from .exceptions import LLMAPIError, LLMConfigurationError
logger = logging.getLogger(__name__)
class LLMError(Exception):
"""Base exception for LLM-related errors."""
pass
class LLMConfigurationError(LLMError):
"""Raised when LLM is not properly configured."""
pass
class LLMAPIError(LLMError):
"""Raised when LLM API returns an error."""
pass
class DeepSeekClient:
"""Client for interacting with DeepSeek API."""
def __init__(
self,
api_key: Optional[str] = None,
base_url: Optional[str] = None,
model: Optional[str] = None,
timeout: Optional[int] = None,
api_key: str | None = None,
base_url: str | None = None,
model: str | None = None,
timeout: int | None = None,
):
"""
Initialize DeepSeek client.
Args:
api_key: API key for authentication (defaults to settings)
base_url: Base URL for API (defaults to settings)
model: Model name to use (defaults to settings)
timeout: Request timeout in seconds (defaults to settings)
Raises:
LLMConfigurationError: If API key is missing
"""
@@ -50,29 +38,29 @@ class DeepSeekClient:
self.base_url = base_url or settings.deepseek_base_url
self.model = model or settings.model
self.timeout = timeout or settings.request_timeout
if not self.api_key:
raise LLMConfigurationError(
"DeepSeek API key is required. Set DEEPSEEK_API_KEY environment variable."
)
if not self.base_url:
raise LLMConfigurationError(
"DeepSeek base URL is required. Set DEEPSEEK_BASE_URL environment variable."
)
logger.info(f"DeepSeek client initialized with model: {self.model}")
def complete(self, messages: List[Dict[str, Any]]) -> str:
def complete(self, messages: list[dict[str, Any]]) -> str:
"""
Generate a completion from the LLM.
Args:
messages: List of message dicts with 'role' and 'content' keys
Returns:
Generated text response
Raises:
LLMAPIError: If API request fails
ValueError: If messages format is invalid
@@ -80,15 +68,17 @@ class DeepSeekClient:
# Validate messages format
if not messages:
raise ValueError("Messages list cannot be empty")
for msg in messages:
if not isinstance(msg, dict):
raise ValueError(f"Each message must be a dict, got {type(msg)}")
if "role" not in msg or "content" not in msg:
raise ValueError(f"Each message must have 'role' and 'content' keys, got {msg.keys()}")
raise ValueError(
f"Each message must have 'role' and 'content' keys, got {msg.keys()}"
)
if msg["role"] not in ("system", "user", "assistant"):
raise ValueError(f"Invalid role: {msg['role']}")
url = f"{self.base_url}/v1/chat/completions"
headers = {
"Authorization": f"Bearer {self.api_key}",
@@ -99,37 +89,34 @@ class DeepSeekClient:
"messages": messages,
"temperature": settings.temperature,
}
try:
logger.debug(f"Sending request to {url} with {len(messages)} messages")
response = requests.post(
url,
headers=headers,
json=payload,
timeout=self.timeout
url, headers=headers, json=payload, timeout=self.timeout
)
response.raise_for_status()
data = response.json()
# Validate response structure
if "choices" not in data or not data["choices"]:
raise LLMAPIError("Invalid API response: missing 'choices'")
if "message" not in data["choices"][0]:
raise LLMAPIError("Invalid API response: missing 'message' in choice")
if "content" not in data["choices"][0]["message"]:
raise LLMAPIError("Invalid API response: missing 'content' in message")
content = data["choices"][0]["message"]["content"]
logger.debug(f"Received response with {len(content)} characters")
return content
except Timeout as e:
logger.error(f"Request timeout after {self.timeout}s: {e}")
raise LLMAPIError(f"Request timeout after {self.timeout} seconds") from e
except HTTPError as e:
logger.error(f"HTTP error from DeepSeek API: {e}")
if e.response is not None:
@@ -140,11 +127,11 @@ class DeepSeekClient:
error_msg = str(e)
raise LLMAPIError(f"DeepSeek API error: {error_msg}") from e
raise LLMAPIError(f"HTTP error: {e}") from e
except RequestException as e:
logger.error(f"Request failed: {e}")
raise LLMAPIError(f"Failed to connect to DeepSeek API: {e}") from e
except (KeyError, IndexError, TypeError) as e:
logger.error(f"Failed to parse API response: {e}")
raise LLMAPIError(f"Invalid API response format: {e}") from e
agent/llm/exceptions.py
+19
View File
@@ -0,0 +1,19 @@
"""LLM-related exceptions."""
class LLMError(Exception):
"""Base exception for LLM-related errors."""
pass
class LLMConfigurationError(LLMError):
"""Raised when LLM is not properly configured."""
pass
class LLMAPIError(LLMError):
"""Raised when LLM API returns an error."""
pass
agent/llm/ollama.py
+22 -33
View File
@@ -1,31 +1,18 @@
"""Ollama LLM client with robust error handling."""
from typing import List, Dict, Any, Optional
import logging
import os
import requests
from typing import Any
from requests.exceptions import RequestException, Timeout, HTTPError
import requests
from requests.exceptions import HTTPError, RequestException, Timeout
from ..config import settings
from .exceptions import LLMAPIError, LLMConfigurationError
logger = logging.getLogger(__name__)
class LLMError(Exception):
"""Base exception for LLM-related errors."""
pass
class LLMConfigurationError(LLMError):
"""Raised when LLM is not properly configured."""
pass
class LLMAPIError(LLMError):
"""Raised when LLM API returns an error."""
pass
class OllamaClient:
"""
Client for interacting with Ollama API.
@@ -41,10 +28,10 @@ class OllamaClient:
def __init__(
self,
base_url: Optional[str] = None,
model: Optional[str] = None,
timeout: Optional[int] = None,
temperature: Optional[float] = None,
base_url: str | None = None,
model: str | None = None,
timeout: int | None = None,
temperature: float | None = None,
):
"""
Initialize Ollama client.
@@ -58,10 +45,14 @@ class OllamaClient:
Raises:
LLMConfigurationError: If configuration is invalid
"""
self.base_url = base_url or os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
self.base_url = base_url or os.getenv(
"OLLAMA_BASE_URL", "http://localhost:11434"
)
self.model = model or os.getenv("OLLAMA_MODEL", "llama3.2")
self.timeout = timeout or settings.request_timeout
self.temperature = temperature if temperature is not None else settings.temperature
self.temperature = (
temperature if temperature is not None else settings.temperature
)
if not self.base_url:
raise LLMConfigurationError(
@@ -75,7 +66,7 @@ class OllamaClient:
logger.info(f"Ollama client initialized with model: {self.model}")
def complete(self, messages: List[Dict[str, Any]]) -> str:
def complete(self, messages: list[dict[str, Any]]) -> str:
"""
Generate a completion from the LLM.
@@ -97,7 +88,9 @@ class OllamaClient:
if not isinstance(msg, dict):
raise ValueError(f"Each message must be a dict, got {type(msg)}")
if "role" not in msg or "content" not in msg:
raise ValueError(f"Each message must have 'role' and 'content' keys, got {msg.keys()}")
raise ValueError(
f"Each message must have 'role' and 'content' keys, got {msg.keys()}"
)
if msg["role"] not in ("system", "user", "assistant"):
raise ValueError(f"Invalid role: {msg['role']}")
@@ -108,16 +101,12 @@ class OllamaClient:
"stream": False,
"options": {
"temperature": self.temperature,
}
},
}
try:
logger.debug(f"Sending request to {url} with {len(messages)} messages")
response = requests.post(
url,
json=payload,
timeout=self.timeout
)
response = requests.post(url, json=payload, timeout=self.timeout)
response.raise_for_status()
data = response.json()
@@ -156,7 +145,7 @@ class OllamaClient:
logger.error(f"Failed to parse API response: {e}")
raise LLMAPIError(f"Invalid API response format: {e}") from e
def list_models(self) -> List[str]:
def list_models(self) -> list[str]:
"""
List available models in Ollama.