You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: messages/agent.test.run-eval.md
+16-16Lines changed: 16 additions & 16 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,25 +8,25 @@ Execute rich evaluation tests against an Agentforce agent using the Einstein Eva
8
8
9
9
When you provide a YAML test spec, the command automatically translates test cases into Evaluation API calls and infers the agent name from the spec's `subjectName` field. This means you can use the same test spec with both `sf agent test run` and `sf agent test run-eval`.
10
10
11
-
When you provide a JSON payload, it's sent directly to the API with optional normalization. The normalizer auto-corrects common field name mistakes, converts shorthand references to JSONPath, and injects defaults. Use `--no-normalize` to disable.
11
+
When you provide a JSON payload, it's sent directly to the API with optional normalization. The normalizer auto-corrects common field name mistakes, converts shorthand references to JSONPath, and injects defaults. Use `--no-normalize` to disable this auto-normalization.
12
12
13
-
Supports 8+ evaluator types including topic routing assertions, action invocation checks, string/numeric assertions, semantic similarity scoring, and LLM-based quality ratings.
13
+
Supports 8+ evaluator types, including topic routing assertions, action invocation checks, string/numeric assertions, semantic similarity scoring, and LLM-based quality ratings.
14
14
15
15
# flags.spec.summary
16
16
17
17
Path to test spec file (YAML or JSON). Use `-` for stdin.
18
18
19
-
# flags.agent-api-name.summary
19
+
# flags.api-name.summary
20
20
21
-
Agent DeveloperName to resolve agent_id and agent_version_id. Auto-inferred from YAML spec's subjectName.
21
+
Agent DeveloperName (also called API name) to resolve agent_id and agent_version_id. Auto-inferred from the YAML spec's subjectName.
22
22
23
23
# flags.wait.summary
24
24
25
25
Number of minutes to wait for results.
26
26
27
27
# flags.result-format.summary
28
28
29
-
Output format: human, json, junit, or tap.
29
+
Format of the agent test results.
30
30
31
31
# flags.batch-size.summary
32
32
@@ -38,54 +38,54 @@ Disable auto-normalization of field names and shorthand references.
38
38
39
39
# examples
40
40
41
-
- Run tests from a YAML test spec:
41
+
- Run tests using a YAML test spec on the org with alias "my-org":
0 commit comments