refactor: rename SplunkAOMetrics to SplunkAOEvaluators (HYBIM-949)

docs/domain-entity-rename.md

@@ -45,8 +45,8 @@ stream = AgentStream.get(name="prod-traces", project_name="my-project")
 streams = AgentStream.list(project_name="my-project")
 
 # Enable evaluators on the stream
-from splunk_ao.schema.metrics import SplunkAOMetrics
-stream.enable_evaluators([SplunkAOMetrics.correctness, SplunkAOMetrics.completeness])
+from splunk_ao.schema.metrics import SplunkAOEvaluators
+stream.enable_evaluators([SplunkAOEvaluators.correctness, SplunkAOEvaluators.completeness])
 ```
 
 ```python

examples/agent/langgraph-fsi-agent/after/test.py

@@ -15,7 +15,7 @@
 from langchain_core.callbacks import Callbacks
 from langchain_core.messages import HumanMessage
 
-from splunk_ao import SplunkAOMetrics, splunk_ao_context
+from splunk_ao import SplunkAOEvaluators, splunk_ao_context
 from splunk_ao.datasets import create_dataset, get_dataset, delete_dataset
 from splunk_ao.experiments import get_experiment, run_experiment
 from splunk_ao.handlers.langchain import SplunkAOCallback
@@ -108,7 +108,7 @@ def test_run_experiment_with_dataset():
         experiment_name="langgraph-fsi-experiment",
         dataset_name=DATASET_NAME,
         function=send_message_to_supervisor_agent,
-        metrics=[SplunkAOMetrics.action_advancement, SplunkAOMetrics.action_completion, SplunkAOMetrics.tool_error_rate, SplunkAOMetrics.tool_selection_quality],
+        metrics=[SplunkAOEvaluators.action_advancement, SplunkAOEvaluators.action_completion, SplunkAOEvaluators.tool_error_rate, SplunkAOEvaluators.tool_selection_quality],
         project=os.getenv("SPLUNK_AO_PROJECT"),
     )
 

examples/chatbot/sample-project-chatbot/anthropic/test.py

@@ -12,7 +12,7 @@
 
 from dotenv import load_dotenv
 
-from splunk_ao import SplunkAOMetrics
+from splunk_ao import SplunkAOEvaluators
 from splunk_ao.datasets import create_dataset, get_dataset
 from splunk_ao.experiments import get_experiment, run_experiment
 
@@ -75,8 +75,8 @@ def test_run_experiment_with_dataset():
         dataset_name="simple-chatbot-unit-test-dataset",
         function=chat_with_llm,
         metrics=[
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.instruction_adherence,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.instruction_adherence,
         ],
         project=os.getenv("SPLUNK_AO_PROJECT"),
     )

examples/chatbot/sample-project-chatbot/azure-inference/test.py

@@ -12,7 +12,7 @@
 
 from dotenv import load_dotenv
 
-from splunk_ao import SplunkAOMetrics
+from splunk_ao import SplunkAOEvaluators
 from splunk_ao.datasets import create_dataset, get_dataset
 from splunk_ao.experiments import get_experiment, run_experiment
 
@@ -75,8 +75,8 @@ def test_run_experiment_with_dataset():
         dataset_name="simple-chatbot-unit-test-dataset",
         function=chat_with_llm,
         metrics=[
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.instruction_adherence,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.instruction_adherence,
         ],
         project=os.getenv("SPLUNK_AO_PROJECT"),
     )

examples/chatbot/sample-project-chatbot/openai-ollama/test.py

@@ -12,7 +12,7 @@
 
 from dotenv import load_dotenv
 
-from splunk_ao import SplunkAOMetrics
+from splunk_ao import SplunkAOEvaluators
 from splunk_ao.datasets import create_dataset, get_dataset
 from splunk_ao.experiments import get_experiment, run_experiment
 
@@ -75,8 +75,8 @@ def test_run_experiment_with_dataset():
         dataset_name="simple-chatbot-unit-test-dataset",
         function=chat_with_llm,
         metrics=[
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.instruction_adherence,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.instruction_adherence,
         ],
         project=os.getenv("SPLUNK_AO_PROJECT"),
     )

examples/experiments/multi-turn/README.md

@@ -61,13 +61,13 @@ The `METRIC_NAME` variable in this script cites a session-level metric.
 
 Pre-defined session-level metrics include:
 
-- `SplunkAOMetrics.conversation_quality`
-- `SplunkAOMetrics.action_completion`
-- `SplunkAOMetrics.action_advancement`
-- `SplunkAOMetrics.agent_efficiency`
-- `SplunkAOMetrics.context_adherence`
-- `SplunkAOMetrics.context_relevance`
-- `SplunkAOMetrics.tool_error_rate`
+- `SplunkAOEvaluators.conversation_quality`
+- `SplunkAOEvaluators.action_completion`
+- `SplunkAOEvaluators.action_advancement`
+- `SplunkAOEvaluators.agent_efficiency`
+- `SplunkAOEvaluators.context_adherence`
+- `SplunkAOEvaluators.context_relevance`
+- `SplunkAOEvaluators.tool_error_rate`
 
 Related documentation: [Metrics Comparison](https://agent-observability-docs.splunk.com/concepts/metrics/metric-comparison)
 

examples/experiments/multi-turn/basic-example.py

@@ -1,15 +1,15 @@
 import os
 import time
 
-from splunk_ao import SplunkAOMetrics, splunk_ao_context
+from splunk_ao import SplunkAOEvaluators, splunk_ao_context
 from splunk_ao.experiments import create_experiment
 from splunk_ao.projects import create_project, get_project
 from splunk_ao.resources.models import MetricSuccess
 from splunk_ao.search import get_sessions
 from splunk_ao.utils.metrics import create_metric_configs
 
 # Provide the name of a session-level metric
-METRIC_NAME = SplunkAOMetrics.conversation_quality
+METRIC_NAME = SplunkAOEvaluators.conversation_quality
 
 # example custom metric name (must be set up in advance)
 # METRIC_NAME = "multi-turn-session-test-metric-apples"

examples/experiments/rag-and-tools/experiment.py

@@ -1,6 +1,6 @@
 import os
 
-from splunk_ao import SplunkAOMetrics
+from splunk_ao import SplunkAOEvaluators
 from splunk_ao.experiments import run_experiment
 
 from app import get_users_horoscope
@@ -25,10 +25,10 @@ def main():
         dataset=dataset,
         function=get_users_horoscope,
         metrics=[
-            SplunkAOMetrics.tool_error_rate,
-            SplunkAOMetrics.tool_selection_quality,
-            SplunkAOMetrics.chunk_attribution_utilization,
-            SplunkAOMetrics.context_adherence,
+            SplunkAOEvaluators.tool_error_rate,
+            SplunkAOEvaluators.tool_selection_quality,
+            SplunkAOEvaluators.chunk_attribution_utilization,
+            SplunkAOEvaluators.context_adherence,
         ],
         project=os.environ["SPLUNK_AO_PROJECT"],
     )

examples/experiments/upload_experiment/README.md

@@ -117,12 +117,12 @@ Edit `dataset.json` with your own evaluation data. The example uses space missio
 In `upload_existing_results.py`, modify the `metrics` parameter in `upload_experiment()`:
 
 ```python
-from splunk_ao.schema.metrics import SplunkAOMetrics
+from splunk_ao.schema.metrics import SplunkAOEvaluators
 
 custom_metrics = [
-    SplunkAOMetrics.ground_truth_adherence,
-    SplunkAOMetrics.context_adherence,
-    SplunkAOMetrics.correctness,
+    SplunkAOEvaluators.ground_truth_adherence,
+    SplunkAOEvaluators.context_adherence,
+    SplunkAOEvaluators.correctness,
     # Add any other Splunk AO metrics you want
 ]
 

examples/experiments/upload_experiment/upload_existing_results.py

@@ -32,7 +32,7 @@
 # Splunk AO imports
 from splunk_ao.datasets import create_dataset, get_dataset
 from splunk_ao.experiments import run_experiment
-from splunk_ao.schema.metrics import SplunkAOMetrics
+from splunk_ao.schema.metrics import SplunkAOEvaluators
 from splunk_ao import splunk_ao_context
 
 
@@ -239,11 +239,11 @@ def upload_experiment(
     # Use default metrics if none provided
     if metrics is None:
         metrics = [
-            SplunkAOMetrics.ground_truth_adherence,
-            SplunkAOMetrics.context_adherence,
-            SplunkAOMetrics.chunk_attribution_utilization,
-            SplunkAOMetrics.completeness,
-            SplunkAOMetrics.correctness,
+            SplunkAOEvaluators.ground_truth_adherence,
+            SplunkAOEvaluators.context_adherence,
+            SplunkAOEvaluators.chunk_attribution_utilization,
+            SplunkAOEvaluators.completeness,
+            SplunkAOEvaluators.correctness,
         ]
 
     # Run experiment with your data

splunk-ao-migration-tool/README.md

@@ -196,12 +196,12 @@ All sub-module paths follow the same rename pattern:
 | Old | New |
 |-----|-----|
 | `GalileoMetric` | `SplunkAOMetric` |
-| `GalileoMetrics` | `SplunkAOMetrics` |
+| `GalileoMetrics` | `SplunkAOEvaluators` |
 | `GalileoScorers` | **Removed** (see §5.2) |
 
 ```diff
 - from galileo import GalileoMetric, GalileoMetrics
-+ from splunk_ao import SplunkAOMetric, SplunkAOMetrics
++ from splunk_ao import SplunkAOMetric, SplunkAOEvaluators
 ```
 
 ### 3.4 Handlers & Middleware
@@ -330,14 +330,14 @@ The following symbols from `galileo` are **not available** in `splunk-ao`:
 
 ### 5.2 `GalileoScorers` Removed
 
-The `GalileoScorers` enum has been removed entirely. Migrate to `SplunkAOMetrics`:
+The `GalileoScorers` enum has been removed entirely. Migrate to `SplunkAOEvaluators`:
 
 ```diff
 - from galileo.schema.metrics import GalileoScorers
-+ from splunk_ao.schema.metrics import SplunkAOMetrics
++ from splunk_ao.schema.metrics import SplunkAOEvaluators
 
 - scorer = GalileoScorers.completeness
-+ scorer = SplunkAOMetrics.completeness
++ scorer = SplunkAOEvaluators.completeness
 ```
 
 ---
@@ -441,8 +441,8 @@ The following are **unchanged** between galileo and splunk-ao and require no mig
 - [ ] Rename `GalileoLoggerException` → `SplunkAOLoggerException`
 - [ ] Rename `GalileoFutureError` → `SplunkAOFutureError`
 - [ ] Rename `GalileoMetric` → `SplunkAOMetric`
-- [ ] Rename `GalileoMetrics` → `SplunkAOMetrics`
-- [ ] Replace `GalileoScorers` with `SplunkAOMetrics`
+- [ ] Rename `GalileoMetrics` → `SplunkAOEvaluators`
+- [ ] Replace `GalileoScorers` with `SplunkAOEvaluators`
 - [ ] Rename `GalileoAgentControlBridge` → `SplunkAOAgentControlBridge`
 - [ ] Rename all `GALILEO_*` environment variables to `SPLUNK_AO_*`
 - [ ] Update `.env`, `.env.example`, CI/CD secrets, and deployment configs

src/splunk_ao/__init__.py

@@ -67,7 +67,7 @@
 from splunk_ao.provider import AnthropicProvider, AzureProvider, BedrockProvider, OpenAIProvider, Provider
 from splunk_ao.resources.models.document import Document
 from splunk_ao.schema.message import Message
-from splunk_ao.schema.metrics import SplunkAOMetrics
+from splunk_ao.schema.metrics import SplunkAOEvaluators
 from splunk_ao.shared.base import SyncState
 from splunk_ao.shared.exceptions import (
     AmbiguousConfigurationError,
@@ -149,7 +149,7 @@
     "SplunkAOFutureError",
     "SplunkAOLogger",
     "SplunkAOLoggerException",
-    "SplunkAOMetrics",
+    "SplunkAOEvaluators",
     "StepType",
     "StepWithChildSpans",
     "SyncState",

src/splunk_ao/agent_stream.py

@@ -21,7 +21,7 @@
 from splunk_ao.resources.models.log_records_available_columns_response import LogRecordsAvailableColumnsResponse
 from splunk_ao.resources.types import Unset
 from splunk_ao.schema.filters import FilterType
-from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOEvaluators
 from splunk_ao.search import RecordType, Search
 from splunk_ao.shared.base import StateManagementMixin, SyncState
 from splunk_ao.shared.exceptions import ValidationError
@@ -78,10 +78,10 @@ class AgentStream(StateManagementMixin):
         agent_stream = project.create_agent_stream(name="Production Logs")
 
         # Enable metrics on the log stream
-        from splunk_ao.schema.metrics import SplunkAOMetrics
+        from splunk_ao.schema.metrics import SplunkAOEvaluators
         local_metrics = log_stream.enable_evaluators([
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.completeness,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.completeness,
             "context_relevance"
         ])
 
@@ -441,7 +441,7 @@ def get_metrics(self) -> builtins.list[str]:
         return metric_names
 
     def set_metrics(
-        self, metrics: builtins.list[SplunkAOMetrics | Metric | LocalMetricConfig | str]
+        self, metrics: builtins.list[SplunkAOEvaluators | Metric | LocalMetricConfig | str]
     ) -> builtins.list[LocalMetricConfig]:
         """
         Set (replace) the metrics on this log stream.
@@ -451,7 +451,7 @@ def set_metrics(
 
         Args:
             metrics: List of metrics to set. Supports:
-                - SplunkAOMetrics enum values (e.g., SplunkAOMetrics.correctness)
+                - SplunkAOEvaluators enum values (e.g., SplunkAOEvaluators.correctness)
                 - Metric objects (including from Metric.get(id="..."))
                 - LocalMetricConfig objects for custom scoring functions
                 - String names of built-in metrics