Test Case Set Describer

Automatic generation of descriptive summaries for test case sets. The service analyzes the test case structure, steps, and parameters and writes a concise description back into the TestBench specification.

Endpoint: POST /test-case-set-descriptions

Authorization

The triggering user must hold at least one of the following project roles:

Role	Description
TestManager	Full project management access.
TestDesigner	Specification authoring access.

When authenticating with a JWT token, the token must also grant all of the following API token permissions:

Permission	Description
ReadOwnUserDetails	Read the authenticated user's details.
ReadProjectDetails	Read project metadata.
ReadTovReport	Read test-object-version reports.
ReadCycleReport	Read test cycle reports.
ReadReportingJobDetails	Read reporting job details.
DownloadReportFile	Download report files.
ReadTestThemeTree	Read the test theme tree.
ReadTestCaseSetDetails	Read test case set details.
ModifySpecifications	Write the generated description back to the specification.
ModifySpecManagementInfo	Update specification management metadata.

---

How it works

1. The service retrieves all test case sets from the specified test-object-version (and optional cycle / subtree).
2. For each test case set, it checks that the specification tab is not locked by another user.
3. Items that pass the precheck are processed concurrently in the background:
   • The current description is saved as a backup.
   • A "generation started" marker is written.
   • Test case data (steps, parameters, parameter combinations) is rendered into the prompt template.
   • The prompt is sent to the configured LLM.
   • The AI-generated description is written to the description field of the test structure element specification.
   • If an error occurs, the previous description is restored.

Configuration

Default configuration

# config.toml
[testbench-ai-service.agents.test_case_set_describer]
enabled = true
endpoint_path = "/test-case-set-descriptions"
class_path = "testbench_ai_service.agents.test_case_set_describer.agent.TestCaseSetDescriber"

[testbench-ai-service.agents.test_case_set_describer.prompt]
file = "test_case_set_describer/prompt.yaml"

Agent data

The following variables are generated by the agent and are accessible in prompt templates as {{ agent.<key> }}:

Variable	Type	Description
agent.test_case_set	String	Formatted string representation of the test case set (name, steps, parameters).
agent.parameter_combinations	String	Formatted parameter combination table. May be empty.

Project-specific override

# config.toml
[testbench-ai-service.projects."My Project".agents.test_case_set_describer]
enabled = false

[testbench-ai-service.projects."My Project".agents.test_case_set_describer.prompt]
variant = "Short Description"

Prompt variants

The built-in prompt file (test_case_set_describer/prompt.yaml) ships with the following variants:

Variant	Model	Description
Full Description (default)	gpt-5.5	Generates a structured description with three sections: test objective, key verifications performed, and a summary of each concrete test case. Recommended for full documentation.
Short Description	gpt-5.5	Generates a single-sentence test objective only. Fast and cost-efficient; ideal when a brief label is needed.

See Prompts for details on how to customize or create your own variants.