brent.edwards
d59fa47fd0
CI / lint (push) Has been cancelled
CI / typecheck (push) Has been cancelled
CI / security (push) Has been cancelled
CI / e2e_tests (push) Has been cancelled
CI / integration_tests (push) Has been cancelled
CI / helm (push) Has been cancelled
CI / quality (push) Has been cancelled
CI / build (push) Has been cancelled
CI / unit_tests (push) Has been cancelled
CI / benchmark-publish (push) Has been cancelled
CI / status-check (push) Has been cancelled
CI / coverage (push) Has been cancelled
CI / benchmark-regression (push) Has been cancelled
CI / docker (push) Has been cancelled
Add the missing plan prompt CLI command and wire it through the local A2A facade into PlanLifecycleService so operator guidance can be injected into active execute-phase plans per the specification. The lifecycle flow now validates active state, records user-intervention decisions, and returns structured queue/decision metadata for rich and machine-readable output envelopes across all supported formats. Also stabilize flaky quality gates discovered while implementing #885 by hardening integration helper timeouts, relaxing an overly strict CLI-core timing assertion, defaulting test worker concurrency to serial for determinism, switching ASV to spawn launch mode for runner stability, and documenting the controlled transform sandbox exec/compile path for static security hooks. ISSUES CLOSED: #885 Co-authored-by: Brent E. Edwards <brent.edwards@cleverthis.com> Co-committed-by: Brent E. Edwards <brent.edwards@cleverthis.com>
46 lines
2.2 KiB
Gherkin
46 lines
2.2 KiB
Gherkin
Feature: Plan prompt command
|
|
As a CleverAgents user
|
|
I want to provide guidance to an executing plan
|
|
So that the plan can continue with human-in-the-loop input
|
|
|
|
Scenario: Plan prompt command is discoverable in help
|
|
When I run plan command help
|
|
Then help output should include plan prompt command
|
|
|
|
Scenario: Plan prompt delivers guidance and returns spec envelope in json
|
|
Given a mocked lifecycle service prompt response
|
|
When I run plan prompt with plan id "01HXM8C2ZK4Q7C2B3F2R4VYV6J" and guidance "Use mocks for database tests" in format "json"
|
|
Then the prompt command should succeed
|
|
And lifecycle prompt should be called with plan id "01HXM8C2ZK4Q7C2B3F2R4VYV6J" and guidance "Use mocks for database tests"
|
|
And prompt output envelope should contain command "plan prompt"
|
|
And prompt output envelope should contain status "ok"
|
|
And prompt output data should include queued guidance
|
|
|
|
Scenario Outline: Plan prompt renders successfully across output formats
|
|
Given a mocked lifecycle service prompt response
|
|
When I run plan prompt with plan id "01HXM8C2ZK4Q7C2B3F2R4VYV6J" and guidance "Use mocks for database tests" in format "<format>"
|
|
Then the prompt command should succeed
|
|
And prompt output should include guidance text "Use mocks for database tests"
|
|
|
|
Examples:
|
|
| format |
|
|
| rich |
|
|
| color |
|
|
| table |
|
|
| plain |
|
|
| json |
|
|
| yaml |
|
|
|
|
Scenario: Plan prompt aborts when plan is not in active execute phase
|
|
Given lifecycle service rejects prompt for inactive plan phase
|
|
When I run plan prompt with plan id "01HXM8C2ZK4Q7C2B3F2R4VYV6J" and guidance "Use mocks for database tests" in format "json"
|
|
Then the prompt command should abort
|
|
And prompt output should mention inactive execute phase
|
|
|
|
Scenario: A2A facade routes _cleveragents plan prompt to lifecycle service
|
|
Given an A2A facade with a lifecycle prompt service
|
|
When I dispatch _cleveragents plan prompt for plan "01HXM8C2ZK4Q7C2B3F2R4VYV6J" and guidance "Use mocks for database tests"
|
|
Then facade prompt response should not be a stub
|
|
And facade prompt response should contain plan id "01HXM8C2ZK4Q7C2B3F2R4VYV6J"
|
|
And facade prompt response should contain guidance "Use mocks for database tests"
|