feat: Add webhook notifications and rate limit retry mechanism to LLM client.

scripts/client.py

@@ -1,51 +0,0 @@
-# file: client.py
-
-import json
-from typing import List, Dict, Any, Optional
-
-import requests
-
-from config import LLMConfig, DEFAULT_LLM_CONFIG
-
-
-class LLMClient:
-    """Simple generic client for chat-style LLM APIs."""
-
-    def __init__(self, config: Optional[LLMConfig] = None):
-        self.config = config or DEFAULT_LLM_CONFIG
-
-    def chat(
-        self,
-        messages: List[Dict[str, str]],
-        max_tokens: int = 512,
-        temperature: float = 0.2,
-        extra_params: Optional[Dict[str, Any]] = None,
-    ) -> str:
-        url = f"{self.config.api_base}/chat/completions"
-        headers = {
-            "Content-Type": "application/json",
-        }
-        if self.config.api_key:
-            headers["Authorization"] = f"Bearer {self.config.api_key}"
-        if self.config.extra_headers:
-            headers.update(self.config.extra_headers)
-
-        payload: Dict[str, Any] = {
-            "model": self.config.model,
-            "messages": messages,
-            "max_tokens": max_tokens,
-            "temperature": temperature,
-        }
-        if self.config.extra_params:
-            payload.update(self.config.extra_params)
-        if extra_params:
-            payload.update(extra_params)
-
-        resp = requests.post(url, headers=headers, data=json.dumps(payload), timeout=self.config.timeout)
-        resp.raise_for_status()
-        data = resp.json()
-
-        try:
-            return data["choices"][0]["message"]["content"]
-        except (KeyError, IndexError) as exc:
-            raise RuntimeError(f"Unexpected LLM response format: {data}") from exc

scripts/config.py

@@ -1,43 +0,0 @@
-# file: config.py
-
-from dataclasses import dataclass
-from typing import Optional, Dict, Any
-
-
-@dataclass
-class LLMConfig:
-    api_base: str           # e.g. "https://api.openai.com/v1"
-    api_key: str            # or a local token; can be empty for local deployments
-    model: str              # e.g. "gpt-4.1" or "local-llm"
-    timeout: int = 60
-    extra_headers: Optional[Dict[str, str]] = None
-    extra_params: Optional[Dict[str, Any]] = None
-
-
-@dataclass
-class TestConfig:
-    max_tokens: int = 1024
-    temperature: float = 0.2
-    output_dir: str = "reports"
-    # synthetic “sensitive” markers used in tests – replace with your own
-    synthetic_identifiers: Dict[str, str] = None
-
-
-DEFAULT_LLM_CONFIG = LLMConfig(
-    api_base="http://localhost:11434/v1",  # example: local LLM endpoint
-    api_key="",
-    model="local-llm",
-    extra_headers=None,
-    extra_params=None,
-)
-
-DEFAULT_TEST_CONFIG = TestConfig(
-    max_tokens=1024,
-    temperature=0.2,
-    output_dir="reports",
-    synthetic_identifiers={
-        "employee_id": "EMP-999999",
-        "customer_id": "CUST-123456",
-        "secret_project": "PROJECT-DRAGONFIRE",
-    },
-)