chore(ci): fix lint/type issues blocking pipeline

Author: Sakeeb91

app/logging_config.py

@@ -11,7 +11,7 @@
 import logging
 import sys
 from contextvars import ContextVar
-from typing import Any
+from typing import Any, cast
 
 import structlog
 
@@ -50,7 +50,7 @@ def configure_logging(
         logger.info("Application started", version="1.0.0")
     """
     # Shared processors for all log entries
-    shared_processors: list[structlog.types.Processor] = [
+    shared_processors: list[Any] = [
         structlog.contextvars.merge_contextvars,
         structlog.stdlib.add_logger_name,
         structlog.stdlib.add_log_level,
@@ -127,7 +127,7 @@ def get_logger(name: str | None = None) -> structlog.stdlib.BoundLogger:
         logger.info("Processing query", query="SELECT * FROM users")
         logger.error("Query failed", error="Connection timeout", retry_count=3)
     """
-    return structlog.get_logger(name)
+    return cast(structlog.stdlib.BoundLogger, structlog.get_logger(name))
 
 
 class LogContext:

app/middleware.py

@@ -12,7 +12,7 @@
 import time
 import uuid
 from collections.abc import Callable
-from typing import Any
+from typing import Any, cast
 
 from fastapi import FastAPI, HTTPException, Request, Response
 from fastapi.middleware.cors import CORSMiddleware
@@ -69,7 +69,7 @@ async def dispatch(
             # Add request ID to response headers
             response.headers["X-Request-ID"] = request_id
 
-            return response
+            return cast(Response, response)
 
         except Exception as e:
             duration_ms = (time.perf_counter() - start_time) * 1000
@@ -214,8 +214,8 @@ def setup_middleware(app: FastAPI, cors_origins: list[str] | None = None) -> Non
     app.add_middleware(RequestLoggingMiddleware)
 
     # Exception handlers
-    app.add_exception_handler(Text2SQLException, exception_handler)
-    app.add_exception_handler(HTTPException, http_exception_handler)
+    app.add_exception_handler(Text2SQLException, exception_handler)  # type: ignore[arg-type]
+    app.add_exception_handler(HTTPException, http_exception_handler)  # type: ignore[arg-type]
     app.add_exception_handler(Exception, generic_exception_handler)
 
     logger.info(

app/resilience.py

@@ -161,5 +161,5 @@ def compute_backoff_seconds(
     Returns:
         Backoff delay in seconds.
     """
-    delay = base_seconds * (2**attempt)
-    return min(delay, max_seconds)
+    delay = float(base_seconds * (2**attempt))
+    return float(min(delay, max_seconds))

app/security/headers.py

@@ -9,7 +9,7 @@
 """
 
 from collections.abc import Callable
-from typing import Any
+from typing import Any, cast
 
 from fastapi import Request, Response
 from starlette.middleware.base import BaseHTTPMiddleware
@@ -80,4 +80,4 @@ async def dispatch(
         if "X-Powered-By" in response.headers:
             del response.headers["X-Powered-By"]
 
-        return response
+        return cast(Response, response)

app/security/rate_limiting.py

@@ -79,7 +79,9 @@ def setup_rate_limiting(app: FastAPI) -> None:
         >>> setup_rate_limiting(app)
     """
     app.state.limiter = limiter
-    app.add_exception_handler(RateLimitExceeded, _rate_limit_exceeded_handler)
+    app.add_exception_handler(
+        RateLimitExceeded, _rate_limit_exceeded_handler  # type: ignore[arg-type]
+    )
 
     logger.info(
         "rate_limiting_configured",

app/text2sql_engine.py

@@ -853,9 +853,14 @@ async def _run_inference(use_examples: bool) -> InferenceResult:
         for attempt in range(self._max_retries):
             try:
                 use_examples = attempt > 0  # Add examples on retry
-                result = await self._circuit_breaker.run(
-                    lambda use_examples=use_examples: _run_inference(use_examples)
-                )
+                current_use_examples = use_examples
+
+                async def _task(
+                    use_examples: bool = current_use_examples,
+                ) -> InferenceResult:
+                    return await _run_inference(use_examples)
+
+                result = await self._circuit_breaker.run(_task)
 
                 if best_result is None or result.confidence > best_result.confidence:
                     best_result = result

db/executor.py

@@ -248,7 +248,7 @@ async def execute(
             )
 
             result.execution_time_ms = execution_time_ms
-            return result  # type: ignore[no-any-return]
+            return result
 
         except asyncio.TimeoutError as e:
             logger.error(
@@ -274,7 +274,7 @@ async def execute(
                 details={"error": str(e)},
             ) from e
 
-    @retry(  # type: ignore[untyped-decorator]
+    @retry(
         retry=retry_if_exception_type((ConnectionError, OSError)),
         stop=stop_after_attempt(3),
         wait=wait_exponential(multiplier=1, min=2, max=10),

models/inference.py

@@ -266,7 +266,7 @@ async def generate(
 
             # Generate
             with torch.no_grad():
-                outputs = self.model.generate(
+                outputs = self.model.generate(  # type: ignore[operator]
                     **inputs,
                     **config.to_dict(),
                     return_dict_in_generate=True,

models/loader.py

@@ -10,7 +10,7 @@
 
 import gc
 from dataclasses import dataclass
-from typing import Any
+from typing import Any, cast
 
 import torch
 from transformers import (
@@ -290,7 +290,9 @@ async def _load_model(self) -> PreTrainedModel:
 
         # Move to device if not using device_map
         if "device_map" not in load_kwargs:
-            model = model.to(device)
+            model = cast(
+                PreTrainedModel, model.to(device)  # type: ignore[arg-type,assignment]
+            )
 
         # Set to evaluation mode
         model.eval()
@@ -328,7 +330,7 @@ async def warmup(self, sample_text: str = "SELECT * FROM users") -> None:
             inputs = {k: v.to(device) for k, v in inputs.items()}
 
             with torch.no_grad():
-                _ = self._model.generate(
+                _ = self._model.generate(  # type: ignore[operator]
                     **inputs,
                     max_new_tokens=10,
                     do_sample=False,