Exceptions: added handling for tellcommunication and smargon communication errors

src/aare/common/exception_handler.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from aare.common.logger_config import setup_logger
-from aare.common.error_codes import AuthErrorCode
+from aare.common.error_codes import AuthErrorCode, DAQErrorCode
 
 logger = setup_logger("aareDAQ")
 
@@ -64,6 +64,7 @@ class AXCFailed(Exception):
     def __str__(self) -> str:
         return self.message
 
+
 class BeamlineBusyException(Exception):
     def __init__(self, message: str = "Beamline is in busy state"):
         super().__init__(message)
@@ -73,6 +74,7 @@ class BeamlineBusyException(Exception):
     def __str__(self) -> str:
         return self.message
 
+
 class SampleException(Exception):
     def __init__(self, message: str = "Sample not found"):
         super().__init__(message)
@@ -82,6 +84,7 @@ class SampleException(Exception):
     def __str__(self) -> str:
         return self.message
 
+
 class AuthenticationException(Exception):
     def __init__(self,
                  message: str = "Authentication failed.",
@@ -99,6 +102,7 @@ class AuthenticationException(Exception):
     def __str__(self) -> str:
         return self.message
 
+
 class UserRightsException(Exception):
     def __init__(self,
                  message: str = "User does not have rights to perform this action.",
@@ -113,5 +117,74 @@ class UserRightsException(Exception):
         self.code = code
         logger.error(message, extra={"exception:": Exception})
 
+    def __str__(self) -> str:
+        return self.message
+
+
+class SmargonCommunicationError(Exception):
+    """
+    Raised when Smargon HTTP communication fails (connection refused, timeout, bad HTTP status, etc).
+    Keep the original exception in `__cause__` by using `raise ... from e`.
+    """
+
+    def __init__(
+        self,
+        message: str = "Smargon communication error",
+        *,
+        endpoint: str | None = None,
+        base_url: str | None = None,
+        operation: str | None = None,  # e.g. "GET" / "PUT"
+        status_code: int | None = None,
+    ):
+        super().__init__(message)
+        self.message = message
+        self.endpoint = endpoint
+        self.base_url = base_url
+        self.operation = operation
+        self.status_code = status_code
+        logger.error(
+            message,
+            extra={
+                "device": "smargon",
+                "operation": operation,
+                "endpoint": endpoint,
+                "base_url": base_url,
+                "status_code": status_code,
+            },
+        )
+
+    def __str__(self) -> str:
+        return self.message
+
+
+class TellCommunicationError(Exception):
+    """
+    Raised when TELL HTTP/PShell communication fails (timeouts, connection refused, etc).
+    Intended to be caught centrally by FastAPI exception handlers.
+    """
+
+    def __init__(
+        self,
+        message: str = "TELL communication error",
+        *,
+        endpoint: str | None = None,
+        base_url: str | None = None,
+        operation: str | None = None,  # e.g. "GET"
+    ):
+        super().__init__(message)
+        self.message = message
+        self.endpoint = endpoint
+        self.base_url = base_url
+        self.operation = operation
+        logger.error(
+            message,
+            extra={
+                "device": "tell",
+                "operation": operation,
+                "endpoint": endpoint,
+                "base_url": base_url,
+            },
+        )
+
     def __str__(self) -> str:
         return self.message

src/aare/daq/server_exception_handler.py

@@ -16,7 +16,8 @@ from aare.common.exception_handler import (
     BeamlineBusyException,
     AuthenticationException,
     SampleException,
-    UserRightsException
+    UserRightsException,
+    SmargonCommunicationError, TellCommunicationError
 )
 
 logger = setup_logger("aareDAQ")
@@ -116,10 +117,38 @@ def register_exception_handlers(app) -> None:
             content=_error_payload(code="SAMPLE_NOT_FOUND", message=str(exc) or "Sample not found"),
         )
 
+    @app.exception_handler(SmargonCommunicationError)
+    async def smargon_comm_handler(request: Request, exc: SmargonCommunicationError) -> JSONResponse:
+        return JSONResponse(
+            status_code=api_status.HTTP_503_SERVICE_UNAVAILABLE,
+            content=_error_payload(
+                code="SMARGON_UNAVAILABLE",
+                message=str(exc) or "Smargon is unavailable",
+                extra={
+                    "operation": getattr(exc, "operation", None),
+                    "endpoint": getattr(exc, "endpoint", None),
+                },
+            ),
+        )
+
+    @app.exception_handler(TellCommunicationError)
+    async def tell_comm_handler(request: Request, exc: TellCommunicationError) -> JSONResponse:
+        return JSONResponse(
+            status_code=api_status.HTTP_503_SERVICE_UNAVAILABLE,
+            content=_error_payload(
+                code="TELL_UNAVAILABLE",
+                message=str(exc) or "TELL is unavailable",
+                extra={
+                    "operation": getattr(exc, "operation", None),
+                    "endpoint": getattr(exc, "endpoint", None),
+                },
+            ),
+        )
+
     @app.exception_handler(Exception)
     async def unhandled_exception_handler(request: Request, exc: Exception) -> JSONResponse:
         logger.exception("Unhandled server exception")
         return JSONResponse(
             status_code=api_status.HTTP_500_INTERNAL_SERVER_ERROR,
-            content=_error_payload(code="INTERNAL_SERVER_ERROR", message="Internal server error"),
+            content=_error_payload(code="INTERNAL_SERVER_ERROR", message=str(exc) or "Internal server error"),
         )