DAQ: starting exception_handler.py rework

This commit is contained in:
2026-05-22 16:19:59 +02:00
parent 59cb34fd89
commit 85cbc79e45
+192 -82
View File
@@ -1,15 +1,81 @@
from __future__ import annotations
import time
from typing import ClassVar
from aare.common.logger_config import setup_logger
from aare.common.error_codes import AuthErrorCode, DAQErrorCode
logger = setup_logger("aareDAQ")
class TransformationInvalidException(Exception):
def __init__(self, message: str = "Transformation is not implemented"):
super().__init__(message)
class AareException(Exception):
"""Root of the aare exception hierarchy.
Class-level ``critical`` is the default; pass ``critical=...`` to the
constructor of an "optionally critical" subclass to override on a single
raise site.
"""
critical: ClassVar[bool] = False
def __init__(self, *args, critical: bool | None = None, **kwargs):
super().__init__(*args, **kwargs)
if critical is not None:
self.critical = critical
class AutomationError(AareException):
"""Errors that happen during a DAQ operation; route through automation flows."""
class AareUserError(AareException):
"""Bad input / mode misuse; routes through the input-correction flow."""
class AareAuthError(AareException):
"""Authentication / authorization failures; routes through re-auth flow."""
# ---------------------------------------------------------------------------
# Device-family base classes
#
# These exist purely so watchers can match a whole device family via
# ``isinstance(e, TellException)`` etc. Per the plan they are intentionally
# empty -- do not add behavior.
# ---------------------------------------------------------------------------
class TellException(AutomationError):
pass
class SmargonException(AutomationError):
pass
class AerotechException(AutomationError):
pass
class JFJochException(AutomationError):
pass
class BECException(AutomationError):
pass
class BeamlineStateException(AutomationError):
pass
# ---------------------------------------------------------------------------
# Concrete automation exceptions
# ---------------------------------------------------------------------------
class TransformationInvalidException(AutomationError):
def __init__(self, message: str = "Transformation is not implemented", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -17,9 +83,9 @@ class TransformationInvalidException(Exception):
return self.message
class StateTransitionFailed(Exception):
def __init__(self, message: str = "Beamline state transition failed"):
super().__init__(message)
class StateTransitionFailed(BeamlineStateException):
def __init__(self, message: str = "Beamline state transition failed", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -27,9 +93,9 @@ class StateTransitionFailed(Exception):
return self.message
class MaintenanceStateException(Exception):
def __init__(self, message: str = "Beamline is in Maintenance state"):
super().__init__(message)
class MaintenanceStateException(BeamlineStateException):
def __init__(self, message: str = "Beamline is in Maintenance state", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -37,31 +103,33 @@ class MaintenanceStateException(Exception):
return self.message
class DataCollectionException(Exception):
def __init__(self, message: str = "Data collection failed"):
super().__init__(message)
class DataCollectionException(AutomationError):
"""Group parent for data-collection-time exceptions; also raisable directly."""
def __init__(self, message: str = "Data collection failed", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
def __str__(self) -> str:
return self.message
class RasterScanException(Exception):
def __init__(self, message: str = "Data collection failed"):
super().__init__(message)
class RasterScanException(DataCollectionException):
def __init__(self, message: str = "Data collection failed", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
def __str__(self) -> str:
return self.message
class AutoRasterSampleSkipped(Exception):
class AutoRasterSampleSkipped(AutomationError):
"""Raised when automation should skip the current sample because auto-raster is too large."""
class LoopCenteringFailed(Exception):
def __init__(self, message: str = "Loop Centering did not detect a sample"):
super().__init__(message)
class LoopCenteringFailed(AutomationError):
def __init__(self, message: str = "Loop Centering did not detect a sample", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -69,9 +137,11 @@ class LoopCenteringFailed(Exception):
return self.message
class UnmountingFailed(Exception):
def __init__(self, message: str = "A sample was not unmounted"):
super().__init__(message)
class UnmountingFailed(TellException):
"""Sample failed to unmount. Optionally critical via instance flag."""
def __init__(self, message: str = "A sample was not unmounted", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -79,9 +149,14 @@ class UnmountingFailed(Exception):
return self.message
class MountingFailed(Exception):
def __init__(self, message: str = "A sample was not mounted"):
super().__init__(message)
class MountingFailed(TellException):
"""Sample failed to mount. Optionally critical via instance flag.
Absorbs ``TellMountFailedException`` (still present for back-compat during
migration; will be removed in Phase 3)."""
def __init__(self, message: str = "A sample was not mounted", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -89,10 +164,10 @@ class MountingFailed(Exception):
return self.message
class ManualMountException(Exception):
class ManualMountException(AareUserError):
"""Custom exception for manual mounting"""
def __init__(self, message: str = "Manual mounting failed"):
super().__init__(message)
def __init__(self, message: str = "Manual mounting failed", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -100,10 +175,10 @@ class ManualMountException(Exception):
return self.message
class SmartMagnetFaultException(Exception):
class SmartMagnetFaultException(AutomationError):
"""Custom exception for smart magnet fault"""
def __init__(self, message: str = "Smart magnet fault"):
super().__init__(message)
def __init__(self, message: str = "Smart magnet fault", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -111,11 +186,13 @@ class SmartMagnetFaultException(Exception):
return self.message
class TellMountFailedException(Exception):
"""Custom exception for mount failure"""
class TellMountFailedException(TellException):
"""Deprecated -- will be absorbed by MountingFailed in Phase 3.
def __init__(self, message: str = "Tell mount failed"):
super().__init__(message)
Currently kept as a TellException family member for back-compat."""
def __init__(self, message: str = "Tell mount failed", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -123,11 +200,11 @@ class TellMountFailedException(Exception):
return self.message
class TellCommandWhileBusyException(Exception):
class TellCommandWhileBusyException(TellException):
"""Custom exception for trying to move Tell when it is busy"""
def __init__(self, message: str = "Tell is busy"):
super().__init__(message)
def __init__(self, message: str = "Tell is busy", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -135,11 +212,11 @@ class TellCommandWhileBusyException(Exception):
return self.message
class TellConnectionException(Exception):
class TellConnectionException(TellException):
"""Custom exception for connection problems"""
def __init__(self, message: str = "Lost connection to Tell"):
super().__init__(message)
def __init__(self, message: str = "Lost connection to Tell", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -147,9 +224,9 @@ class TellConnectionException(Exception):
return self.message
class WarningTellException(Exception):
def __init__(self, message: str = "Warning error in TELL"):
super().__init__(message)
class WarningTellException(TellException):
def __init__(self, message: str = "Warning error in TELL", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -157,9 +234,9 @@ class WarningTellException(Exception):
return self.message
class CriticalTellException(Exception):
def __init__(self, message: str = "Critical error in TELL"):
super().__init__(message)
class CriticalTellException(TellException):
def __init__(self, message: str = "Critical error in TELL", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -167,9 +244,9 @@ class CriticalTellException(Exception):
return self.message
class AXCFailed(Exception):
def __init__(self, message: str = "Auto X-ray centering failed"):
super().__init__(message)
class AXCFailed(AutomationError):
def __init__(self, message: str = "Auto X-ray centering failed", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -177,9 +254,9 @@ class AXCFailed(Exception):
return self.message
class BeamlineBusyException(Exception):
def __init__(self, message: str = "Beamline is in busy state"):
super().__init__(message)
class BeamlineBusyException(BeamlineStateException):
def __init__(self, message: str = "Beamline is in busy state", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -187,9 +264,9 @@ class BeamlineBusyException(Exception):
return self.message
class BeamlineBusyTimeoutException(Exception):
def __init__(self, message: str = "Beamline busy state expired during operation"):
super().__init__(message)
class BeamlineBusyTimeoutException(BeamlineStateException):
def __init__(self, message: str = "Beamline busy state expired during operation", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -197,9 +274,15 @@ class BeamlineBusyTimeoutException(Exception):
return self.message
class SampleException(Exception):
def __init__(self, message: str = "Sample not found"):
super().__init__(message)
class SampleException(AareUserError):
"""Requested sample could not be located.
NOTE: not listed in the redesign hierarchy (§1.2); parented under
AareUserError pending confirmation -- "sample not found" reads as bad
input rather than a runtime failure."""
def __init__(self, message: str = "Sample not found", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(message, extra={"exception:": Exception})
@@ -207,14 +290,19 @@ class SampleException(Exception):
return self.message
class AuthenticationException(Exception):
# ---------------------------------------------------------------------------
# Auth exceptions
# ---------------------------------------------------------------------------
class AuthenticationException(AareAuthError):
def __init__(self,
message: str = "Authentication failed.",
*,
status_code: int = 401,
headers: dict[str, str] | None = None,
code: AuthErrorCode = AuthErrorCode.AUTHENTICATION_FAILED):
super().__init__(message)
code: AuthErrorCode = AuthErrorCode.AUTHENTICATION_FAILED,
critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
self.status_code = status_code
self.headers = headers
@@ -225,16 +313,18 @@ class AuthenticationException(Exception):
return self.message
class UserRightsException(Exception):
class UserRightsException(AareAuthError):
_last_log_ts_by_message: dict[str, float] = {}
_throttle_window_s = 30.0
def __init__(self,
message: str = "User does not have rights to perform this action.",
*,
status_code: int = 403,
headers: dict[str, str] | None = None,
code: AuthErrorCode = AuthErrorCode.FORBIDDEN):
super().__init__(message)
code: AuthErrorCode = AuthErrorCode.FORBIDDEN,
critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
self.status_code = status_code
self.headers = headers
@@ -250,7 +340,11 @@ class UserRightsException(Exception):
return self.message
class SmargonCommunicationError(Exception):
# ---------------------------------------------------------------------------
# Device communication exceptions
# ---------------------------------------------------------------------------
class SmargonCommunicationError(SmargonException):
"""
Raised when Smargon HTTP communication fails (connection refused, timeout, bad HTTP status, etc).
Keep the original exception in `__cause__` by using `raise ... from e`.
@@ -262,10 +356,11 @@ class SmargonCommunicationError(Exception):
*,
endpoint: str | None = None,
base_url: str | None = None,
operation: str | None = None, # e.g. "GET" / "PUT"
operation: str | None = None,
status_code: int | None = None,
critical: bool | None = None,
):
super().__init__(message)
super().__init__(message, critical=critical)
self.message = message
self.endpoint = endpoint
self.base_url = base_url
@@ -286,7 +381,7 @@ class SmargonCommunicationError(Exception):
return self.message
class TellCommunicationError(Exception):
class TellCommunicationError(TellException):
"""
Raised when TELL HTTP/PShell communication fails (timeouts, connection refused, etc).
Intended to be caught centrally by FastAPI exception handlers.
@@ -298,9 +393,10 @@ class TellCommunicationError(Exception):
*,
endpoint: str | None = None,
base_url: str | None = None,
operation: str | None = None, # e.g. "GET"
operation: str | None = None,
critical: bool | None = None,
):
super().__init__(message)
super().__init__(message, critical=critical)
self.message = message
self.endpoint = endpoint
self.base_url = base_url
@@ -318,7 +414,8 @@ class TellCommunicationError(Exception):
def __str__(self) -> str:
return self.message
class JFJochCommunicationError(Exception):
class JFJochCommunicationError(JFJochException):
"""
Raised when JFJoch HTTP/API communication fails.
Intended for scan-time fallbacks and GUI-visible alerts.
@@ -332,8 +429,9 @@ class JFJochCommunicationError(Exception):
endpoint: str | None = None,
base_url: str | None = None,
status_code: int | None = None,
critical: bool | None = None,
):
super().__init__(message)
super().__init__(message, critical=critical)
self.message = message
self.operation = operation
self.endpoint = endpoint
@@ -353,8 +451,13 @@ class JFJochCommunicationError(Exception):
def __str__(self) -> str:
return self.message
class AareDBCommunicationError(Exception):
"""Raised when AareDB HTTPS communication fails."""
class AareDBCommunicationError(AutomationError):
"""Raised when AareDB HTTPS communication fails.
Default not critical -- DB hiccups don't always halt automation. Raise with
``critical=True`` at call sites where a DB read failure should escalate."""
def __init__(
self,
message: str = "AareDB communication error",
@@ -363,8 +466,9 @@ class AareDBCommunicationError(Exception):
endpoint: str | None = None,
base_url: str | None = None,
status_code: int | None = None,
critical: bool | None = None,
):
super().__init__(message)
super().__init__(message, critical=critical)
self.message = message
self.operation = operation
self.endpoint = endpoint
@@ -384,7 +488,8 @@ class AareDBCommunicationError(Exception):
def __str__(self) -> str:
return self.message
class AerotechCommunicationError(Exception):
class AerotechCommunicationError(AerotechException):
"""
Raised when Aerotech HTTP/API communication fails (connection refused, timeout, bad HTTP status, etc).
Keep the original exception in `__cause__` by using `raise ... from e`.
@@ -398,8 +503,9 @@ class AerotechCommunicationError(Exception):
base_url: str | None = None,
operation: str | None = None,
status_code: int | None = None,
critical: bool | None = None,
):
super().__init__(message)
super().__init__(message, critical=critical)
self.message = message
self.endpoint = endpoint
self.base_url = base_url
@@ -419,9 +525,10 @@ class AerotechCommunicationError(Exception):
def __str__(self) -> str:
return self.message
class MagnetPositionSensorErorr(Exception):
def __init__(self, message: str = "Magnet position sensor error"):
super().__init__(message)
class MagnetPositionSensorErorr(AutomationError):
def __init__(self, message: str = "Magnet position sensor error", *, critical: bool | None = None):
super().__init__(message, critical=critical)
self.message = message
logger.error(
message,
@@ -431,7 +538,8 @@ class MagnetPositionSensorErorr(Exception):
def __str__(self) -> str:
return self.message
class BECCommunicationError(Exception):
class BECCommunicationError(BECException):
def __init__(
self,
message: str = "BEC communication error",
@@ -440,7 +548,9 @@ class BECCommunicationError(Exception):
operation: str | None = None,
endpoint: str | None = None,
base_url: str | None = None,
critical: bool | None = None,
):
super().__init__(message, critical=critical)
self.message = message
self.operation = operation
self.exception = exception