docs: align evaluator terminology after HYBIM-949 rename

CHANGELOG.md

@@ -19,6 +19,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   `~/.galileo/` on logout/reset is now named `splunk-ao-config.json` (was
   `galileo-python-config.json`). The old file can be deleted or ignored — it is
   never read back and has no effect on authentication or config resolution.
+- **Evaluator terminology alignment in docs and errors**: Updated
+  `SplunkAOEvaluators` docstrings, agent stream/evaluator API docstrings, and
+  user-visible error messages to use evaluator and agent stream vocabulary following
+  the `SplunkAOMetrics` → `SplunkAOEvaluators` rename. Enum values are documented
+  as matching scorer labels via the legacy `/scorers` API paths. The public
+  `metrics=` parameter name is unchanged for API compatibility. Renamed stale
+  `test_galileo_metrics_*` and `test_lookup_by_galileo_metrics_enum` test identifiers.
 
 ## [0.1.1] - 2026-08-03
 

docs/domain-entity-rename.md

@@ -46,7 +46,7 @@ streams = AgentStream.list(project_name="my-project")
 
 # Enable evaluators on the stream
 from splunk_ao.schema.metrics import SplunkAOEvaluators
-stream.enable_evaluators([SplunkAOEvaluators.correctness, SplunkAOEvaluators.completeness])
+stream.set_metrics([SplunkAOEvaluators.correctness, SplunkAOEvaluators.completeness])
 ```
 
 ```python
@@ -187,7 +187,8 @@ from splunk_ao.metrics     import …  →  from splunk_ao.evaluators    import
 project.create_log_stream(…)   →  project.create_agent_stream(…)
 project.list_log_streams(…)    →  project.list_agent_streams(…)
 project.logstreams             →  project.agent_streams
-enable_metrics(…)              →  enable_evaluators(…)
+log_stream.enable_metrics(…)   →  agent_stream.set_metrics(…)
+enable_metrics(…)              →  enable_evaluators(…)   (AgentStreams service / module-level only)
 delete_metric(…)               →  delete_evaluator(…)
 get_metrics(…)                 →  get_evaluators(…)
 create_custom_llm_metric(…)    →  create_custom_llm_evaluator(…)

src/splunk_ao/agent_stream.py

@@ -77,16 +77,16 @@ class AgentStream(StateManagementMixin):
         project = Project.get(name="My AI Project")
         agent_stream = project.create_agent_stream(name="Production Logs")
 
-        # Enable metrics on the log stream
+        # Enable evaluators on the agent stream
         from splunk_ao.schema.metrics import SplunkAOEvaluators
-        local_metrics = log_stream.enable_evaluators([
+        local_evaluators = agent_stream.set_metrics([
             SplunkAOEvaluators.correctness,
             SplunkAOEvaluators.completeness,
             "context_relevance"
         ])
 
-        # Refresh log stream state from API
-        log_stream.refresh()
+        # Refresh agent stream state from API
+        agent_stream.refresh()
     """
 
     created_at: datetime | None
@@ -408,21 +408,21 @@ def refresh(self) -> None:
 
     def get_metrics(self) -> builtins.list[str]:
         """
-        Get the list of metrics currently enabled on this log stream.
+        Get the list of evaluators currently enabled on this agent stream.
 
         Returns
         -------
-            list[str]: List of metric names currently enabled.
+            list[str]: List of evaluator names currently enabled.
 
         Raises
         ------
-            ValueError: If the log stream lacks required id or project_id attributes.
+            ValueError: If the agent stream lacks required id or project_id attributes.
 
         Examples
         --------
             agent_stream = AgentStream.get(name="Production Logs", project_name="My Project")
-            current_metrics = log_stream.get_metrics()
-            print(f"Currently enabled: {current_metrics}")
+            current_evaluators = agent_stream.get_metrics()
+            print(f"Currently enabled: {current_evaluators}")
         """
         logger.info(f"AgentStream.get_metrics: id='{self.id}' - started")
         config = SplunkAOConfig.get()
@@ -444,26 +444,26 @@ def set_metrics(
         self, metrics: builtins.list[SplunkAOEvaluators | Metric | LocalMetricConfig | str]
     ) -> builtins.list[LocalMetricConfig]:
         """
-        Set (replace) the metrics on this log stream.
+        Set (replace) the evaluators on this agent stream.
 
-        This replaces any existing metrics with the new list. Alias for enable_metrics
-        with clearer naming intent.
+        This replaces any existing evaluators with the new list. The ``metrics`` parameter
+        name is retained for API compatibility.
 
         Args:
-            metrics: List of metrics to set. Supports:
+            metrics: List of evaluators to set. Supports:
                 - 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
+                - String names of built-in evaluators
 
         Returns
         -------
-            List[LocalMetricConfig]: Local metric configurations that must be
+            List[LocalMetricConfig]: Local evaluator configurations that must be
                 computed client-side.
 
         Raises
         ------
-            ValueError: If any specified metrics are unknown.
+            ValueError: If any specified evaluators are unknown.
 
         Examples
         --------
@@ -472,7 +472,7 @@ def set_metrics(
             agent_stream = AgentStream.get(name="Production Logs", project_name="My Project")
 
             # Set evaluators (replaces existing)
-            log_stream.set_metrics([
+            agent_stream.set_metrics([
                 Evaluator.metrics.correctness,
                 Evaluator.metrics.completeness,
                 Evaluator.get(id="evaluator-from-console-uuid"),  # From console
@@ -483,7 +483,7 @@ def set_metrics(
             agent_streams_svc = AgentStreams()
             agent_stream = agent_streams_svc.get(name=self.name, project_id=self.project_id)
             if agent_stream is None:
-                raise ValueError(f"Log stream '{self.name}' not found")
+                raise ValueError(f"Agent stream '{self.name}' not found")
             result = agent_stream.enable_evaluators(metrics)
             # Set state to synced after successful operation
             self._set_state(SyncState.SYNCED)