-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #20 from salesforcecli/mdonnalley/agent-testing
feat: implement agent test commands
- Loading branch information
Showing
35 changed files
with
1,226 additions
and
191 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,19 @@ | ||
| # summary | ||
|
|
||
| Get the results of a test evaluation. | ||
|
|
||
| # description | ||
|
|
||
| Provide the AiEvaluation ID to get the results of a test evaluation. | ||
|
|
||
| # flags.job-id.summary | ||
|
|
||
| The AiEvaluation ID. | ||
|
|
||
| # flags.use-most-recent.summary | ||
|
|
||
| Use the job ID of the most recent test evaluation. | ||
|
|
||
| # examples | ||
|
|
||
| - <%= config.bin %> <%= command.id %> --job-id AiEvalId |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,29 @@ | ||
| # summary | ||
|
|
||
| Resume a running test for an Agent. | ||
|
|
||
| # description | ||
|
|
||
| Resume a running test for an Agent, providing the AiEvaluation ID. | ||
|
|
||
| # flags.job-id.summary | ||
|
|
||
| The AiEvaluation ID. | ||
|
|
||
| # flags.use-most-recent.summary | ||
|
|
||
| Use the job ID of the most recent test evaluation. | ||
|
|
||
| # flags.wait.summary | ||
|
|
||
| Number of minutes to wait for the command to complete and display results to the terminal window. | ||
|
|
||
| # flags.wait.description | ||
|
|
||
| If the command continues to run after the wait period, the CLI returns control of the terminal window to you. | ||
|
|
||
| # examples | ||
|
|
||
| - Resume a test for an Agent: | ||
|
|
||
| <%= config.bin %> <%= command.id %> --job-id AiEvalId |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,3 @@ | ||
| # flags.result-format.summary | ||
|
|
||
| Format of the test run results. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,145 @@ | ||
| { | ||
| "$schema": "http://json-schema.org/draft-07/schema#", | ||
| "$ref": "#/definitions/AgentTestResultsResult", | ||
| "definitions": { | ||
| "AgentTestResultsResult": { | ||
| "$ref": "#/definitions/AgentTestDetailsResponse" | ||
| }, | ||
| "AgentTestDetailsResponse": { | ||
| "type": "object", | ||
| "properties": { | ||
| "status": { | ||
| "$ref": "#/definitions/TestStatus" | ||
| }, | ||
| "startTime": { | ||
| "type": "string" | ||
| }, | ||
| "endTime": { | ||
| "type": "string" | ||
| }, | ||
| "errorMessage": { | ||
| "type": "string" | ||
| }, | ||
| "testCases": { | ||
| "type": "array", | ||
| "items": { | ||
| "$ref": "#/definitions/TestCaseResult" | ||
| } | ||
| } | ||
| }, | ||
| "required": ["status", "startTime", "testCases"], | ||
| "additionalProperties": false | ||
| }, | ||
| "TestStatus": { | ||
| "type": "string", | ||
| "enum": ["NEW", "IN_PROGRESS", "COMPLETED", "ERROR"] | ||
| }, | ||
| "TestCaseResult": { | ||
| "type": "object", | ||
| "properties": { | ||
| "status": { | ||
| "$ref": "#/definitions/TestStatus" | ||
| }, | ||
| "number": { | ||
| "type": "string" | ||
| }, | ||
| "startTime": { | ||
| "type": "string" | ||
| }, | ||
| "endTime": { | ||
| "type": "string" | ||
| }, | ||
| "generatedData": { | ||
| "type": "object", | ||
| "properties": { | ||
| "type": { | ||
| "type": "string", | ||
| "const": "AGENT" | ||
| }, | ||
| "actionsSequence": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "outcome": { | ||
| "type": "string", | ||
| "enum": ["Success", "Failure"] | ||
| }, | ||
| "topic": { | ||
| "type": "string" | ||
| }, | ||
| "inputTokensCount": { | ||
| "type": "string" | ||
| }, | ||
| "outputTokensCount": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "required": ["type", "actionsSequence", "outcome", "topic", "inputTokensCount", "outputTokensCount"], | ||
| "additionalProperties": false | ||
| }, | ||
| "expectationResults": { | ||
| "type": "array", | ||
| "items": { | ||
| "type": "object", | ||
| "properties": { | ||
| "name": { | ||
| "type": "string" | ||
| }, | ||
| "actualValue": { | ||
| "type": "string" | ||
| }, | ||
| "expectedValue": { | ||
| "type": "string" | ||
| }, | ||
| "score": { | ||
| "type": "number" | ||
| }, | ||
| "result": { | ||
| "type": "string", | ||
| "enum": ["Passed", "Failed"] | ||
| }, | ||
| "metricLabel": { | ||
| "type": "string", | ||
| "enum": ["Accuracy", "Precision"] | ||
| }, | ||
| "metricExplainability": { | ||
| "type": "string" | ||
| }, | ||
| "status": { | ||
| "$ref": "#/definitions/TestStatus" | ||
| }, | ||
| "startTime": { | ||
| "type": "string" | ||
| }, | ||
| "endTime": { | ||
| "type": "string" | ||
| }, | ||
| "errorCode": { | ||
| "type": "string" | ||
| }, | ||
| "errorMessage": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "required": [ | ||
| "name", | ||
| "actualValue", | ||
| "expectedValue", | ||
| "score", | ||
| "result", | ||
| "metricLabel", | ||
| "metricExplainability", | ||
| "status", | ||
| "startTime" | ||
| ], | ||
| "additionalProperties": false | ||
| } | ||
| } | ||
| }, | ||
| "required": ["status", "number", "startTime", "generatedData", "expectationResults"], | ||
| "additionalProperties": false | ||
| } | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,19 @@ | ||
| { | ||
| "$schema": "http://json-schema.org/draft-07/schema#", | ||
| "$ref": "#/definitions/AgentTestResumeResult", | ||
| "definitions": { | ||
| "AgentTestResumeResult": { | ||
| "type": "object", | ||
| "properties": { | ||
| "aiEvaluationId": { | ||
| "type": "string" | ||
| }, | ||
| "status": { | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "required": ["aiEvaluationId", "status"], | ||
| "additionalProperties": false | ||
| } | ||
| } | ||
| } |
Oops, something went wrong.