rename availability reasons for clarity (valid_response, rate_limited_platform)

Author: randy-concepcion

src/mlpa/core/completions.py

@@ -272,7 +272,7 @@ async def _read_next_chunk(
                 snapshot=litellm_routing_snapshot,
             )
             result = PrometheusResult.SUCCESS
-            availability_reason = AvailabilityReason.CLEAN_COMPLETION
+            availability_reason = AvailabilityReason.VALID_RESPONSE
     except (GeneratorExit, asyncio.CancelledError):
         # Client went away mid-stream: Starlette tears the generator down by
         # throwing GeneratorExit (or cancelling the task) at the paused
@@ -384,7 +384,7 @@ async def get_completion(authorized_chat_request: AuthorizedChatRequest):
             snapshot=litellm_routing_snapshot,
         )
         result = PrometheusResult.SUCCESS
-        availability_reason = AvailabilityReason.CLEAN_COMPLETION
+        availability_reason = AvailabilityReason.VALID_RESPONSE
         return data
     except HTTPException:
         raise

src/mlpa/core/errors.py

@@ -42,7 +42,7 @@ def availability_reason(self) -> AvailabilityReason:
         if self.reason == PrometheusRejectionReason.RATE_LIMITED:
             if self.error_code == ERROR_CODE_UPSTREAM_RATE_LIMIT_EXCEEDED:
                 return AvailabilityReason.RATE_LIMITED_UPSTREAM
-            return AvailabilityReason.RATE_LIMITED_OWN
+            return AvailabilityReason.RATE_LIMITED_PLATFORM
         return _REJECTION_TO_AVAILABILITY_REASON[self.reason]
 
 

src/mlpa/core/prometheus_metrics.py

@@ -44,11 +44,11 @@ class AvailabilityReason(StrEnum):
     AUTH_SYSTEM_FAILURE = "auth_system_failure"  # failure
 
     # --- completion-stage reasons (recorded inside stream_completion / get_completion) ---
-    CLEAN_COMPLETION = "clean_completion"  # success
+    VALID_RESPONSE = "valid_response"  # success
     UPSTREAM_ERROR = "upstream_error"  # failure
     EMPTY_RESPONSE = "empty_response"  # failure
     BUDGET_EXCEEDED = "budget_exceeded"  # excluded
-    RATE_LIMITED_OWN = "rate_limited_own"  # excluded
+    RATE_LIMITED_PLATFORM = "rate_limited_platform"  # excluded
     RATE_LIMITED_UPSTREAM = "rate_limited_upstream"  # excluded
     PAYLOAD_TOO_LARGE = "payload_too_large"  # excluded
     INVALID_MODEL_NAME = "invalid_model_name"  # excluded
@@ -64,11 +64,11 @@ class AvailabilityReason(StrEnum):
     AvailabilityReason.BLOCKED: AvailabilityOutcome.EXCLUDED,
     AvailabilityReason.PROVISIONING_FAILURE: AvailabilityOutcome.FAILURE,
     AvailabilityReason.AUTH_SYSTEM_FAILURE: AvailabilityOutcome.FAILURE,
-    AvailabilityReason.CLEAN_COMPLETION: AvailabilityOutcome.SUCCESS,
+    AvailabilityReason.VALID_RESPONSE: AvailabilityOutcome.SUCCESS,
     AvailabilityReason.UPSTREAM_ERROR: AvailabilityOutcome.FAILURE,
     AvailabilityReason.EMPTY_RESPONSE: AvailabilityOutcome.FAILURE,
     AvailabilityReason.BUDGET_EXCEEDED: AvailabilityOutcome.EXCLUDED,
-    AvailabilityReason.RATE_LIMITED_OWN: AvailabilityOutcome.EXCLUDED,
+    AvailabilityReason.RATE_LIMITED_PLATFORM: AvailabilityOutcome.EXCLUDED,
     AvailabilityReason.RATE_LIMITED_UPSTREAM: AvailabilityOutcome.EXCLUDED,
     AvailabilityReason.PAYLOAD_TOO_LARGE: AvailabilityOutcome.EXCLUDED,
     AvailabilityReason.INVALID_MODEL_NAME: AvailabilityOutcome.EXCLUDED,

src/tests/unit/test_availability.py

@@ -65,7 +65,7 @@ def test_every_completion_stage_rejection_reason_maps_to_excluded():
         (
             PrometheusRejectionReason.RATE_LIMITED,
             ERROR_CODE_RATE_LIMIT_EXCEEDED,
-            AvailabilityReason.RATE_LIMITED_OWN,
+            AvailabilityReason.RATE_LIMITED_PLATFORM,
         ),
         (
             PrometheusRejectionReason.RATE_LIMITED,

src/tests/unit/test_completions.py

@@ -174,7 +174,7 @@ async def test_get_completion_success(mocker, metrics_spy):
         _availability_count(
             metrics_spy,
             AvailabilityOutcome.SUCCESS,
-            AvailabilityReason.CLEAN_COMPLETION,
+            AvailabilityReason.VALID_RESPONSE,
         )
         == 1
     )
@@ -390,7 +390,7 @@ async def test_stream_completion_success(
         _availability_count(
             metrics_spy,
             AvailabilityOutcome.SUCCESS,
-            AvailabilityReason.CLEAN_COMPLETION,
+            AvailabilityReason.VALID_RESPONSE,
         )
         == 1
     )
@@ -569,7 +569,7 @@ async def test_get_completion_rate_limit_exceeded(mocker, metrics_spy):
         _availability_count(
             metrics_spy,
             AvailabilityOutcome.EXCLUDED,
-            AvailabilityReason.RATE_LIMITED_OWN,
+            AvailabilityReason.RATE_LIMITED_PLATFORM,
         )
         == 1
     )