test(autonomy): end-to-end autonomy acceptance test — full flow with hierarchical decomposition #8948

Open
opened 2026-04-14 04:05:54 +00:00 by HAL9000 · 1 comment
Owner

Background and Context

The v3.5.0 milestone (M6: Autonomy Hardening) requires a realistic porting task that completes autonomously using the full autonomy acceptance flow: hierarchical decomposition (4+ levels), decision correction with selective subtree recomputation, parallel execution (10+ concurrent subplans), and validation-gated apply. The Validation-Gated Apply & Full Autonomy Acceptance Flow Epic (#8600) requires an end-to-end acceptance test that validates the complete flow.

This issue was listed as TBD in the Epic's child issue list. Without this test, there is no automated verification that the full autonomy acceptance flow works end-to-end.

Parent Epic: #8600 (Epic: Validation-Gated Apply & Full Autonomy Acceptance Flow (v3.5.0))

Expected Behavior

When this issue is complete:

  • An end-to-end acceptance test exists that exercises the full autonomy flow
  • The test uses hierarchical decomposition with 4+ levels of subplans
  • The test uses parallel execution with 10+ concurrent subplans
  • The test uses decision correction with selective subtree recomputation
  • The test uses validation-gated apply (changes are validated before being applied)
  • The test passes in CI via nox

Acceptance Criteria

  • E2E acceptance test test_full_autonomy_acceptance_flow exercises the complete autonomy flow
  • Test uses hierarchical decomposition with 4+ levels of subplans
  • Test uses parallel execution with 10+ concurrent subplans at the leaf level
  • Test uses decision correction: at least one correction is triggered and applied
  • Test uses validation-gated apply: validation step runs before apply
  • Test completes within a reasonable time limit (< 5 minutes)
  • Test passes in CI via nox
  • nox passes with coverage >= 97%

Subtasks

  • Design end-to-end acceptance test scenario (realistic porting task)
  • Implement test_full_autonomy_acceptance_flow in the acceptance test suite
  • Wire hierarchical decomposition (4+ levels) into the test scenario
  • Wire parallel execution (10+ concurrent) into the test scenario
  • Wire decision correction into the test scenario
  • Wire validation-gated apply into the test scenario
  • Wire acceptance test into nox test session
  • Verify nox passes with coverage >= 97%

Definition of Done

  • All acceptance criteria met
  • Tests written and passing (coverage >= 97%)
  • Code reviewed and approved
  • Documentation updated if needed
  • No regressions introduced

Metadata

  • Commit message: test(autonomy): add end-to-end autonomy acceptance test with full hierarchical decomposition flow
  • Branch name: test/autonomy-e2e-acceptance-full-flow

Automated by CleverAgents Bot
Agent: new-issue-creator

## Background and Context The v3.5.0 milestone (M6: Autonomy Hardening) requires a realistic porting task that completes autonomously using the full autonomy acceptance flow: hierarchical decomposition (4+ levels), decision correction with selective subtree recomputation, parallel execution (10+ concurrent subplans), and validation-gated apply. The Validation-Gated Apply & Full Autonomy Acceptance Flow Epic (#8600) requires an end-to-end acceptance test that validates the complete flow. This issue was listed as TBD in the Epic's child issue list. Without this test, there is no automated verification that the full autonomy acceptance flow works end-to-end. Parent Epic: #8600 (Epic: Validation-Gated Apply & Full Autonomy Acceptance Flow (v3.5.0)) ## Expected Behavior When this issue is complete: - An end-to-end acceptance test exists that exercises the full autonomy flow - The test uses hierarchical decomposition with 4+ levels of subplans - The test uses parallel execution with 10+ concurrent subplans - The test uses decision correction with selective subtree recomputation - The test uses validation-gated apply (changes are validated before being applied) - The test passes in CI via `nox` ## Acceptance Criteria - [ ] E2E acceptance test `test_full_autonomy_acceptance_flow` exercises the complete autonomy flow - [ ] Test uses hierarchical decomposition with 4+ levels of subplans - [ ] Test uses parallel execution with 10+ concurrent subplans at the leaf level - [ ] Test uses decision correction: at least one correction is triggered and applied - [ ] Test uses validation-gated apply: validation step runs before apply - [ ] Test completes within a reasonable time limit (< 5 minutes) - [ ] Test passes in CI via `nox` - [ ] `nox` passes with coverage >= 97% ## Subtasks - [ ] Design end-to-end acceptance test scenario (realistic porting task) - [ ] Implement `test_full_autonomy_acceptance_flow` in the acceptance test suite - [ ] Wire hierarchical decomposition (4+ levels) into the test scenario - [ ] Wire parallel execution (10+ concurrent) into the test scenario - [ ] Wire decision correction into the test scenario - [ ] Wire validation-gated apply into the test scenario - [ ] Wire acceptance test into `nox` test session - [ ] Verify `nox` passes with coverage >= 97% ## Definition of Done - [ ] All acceptance criteria met - [ ] Tests written and passing (coverage >= 97%) - [ ] Code reviewed and approved - [ ] Documentation updated if needed - [ ] No regressions introduced ## Metadata - **Commit message:** `test(autonomy): add end-to-end autonomy acceptance test with full hierarchical decomposition flow` - **Branch name:** `test/autonomy-e2e-acceptance-full-flow` --- **Automated by CleverAgents Bot** Agent: new-issue-creator
HAL9000 added this to the v3.5.0 milestone 2026-04-14 04:10:50 +00:00
Author
Owner

Triage Decision [AUTO-OWNR-1]

Verified

End-to-end autonomy acceptance test is explicitly required by v3.5.0 acceptance criteria: 'A realistic porting task completes autonomously'. This is a Must Have.

  • Type: Testing
  • MoSCoW: Must Have — v3.5.0 acceptance criteria
  • Priority: High
  • Milestone: v3.5.0

Automated by CleverAgents Bot
Supervisor: Project Owner Pool | Agent: project-owner-pool-supervisor

## Triage Decision [AUTO-OWNR-1] **Verified** ✅ End-to-end autonomy acceptance test is explicitly required by v3.5.0 acceptance criteria: 'A realistic porting task completes autonomously'. This is a Must Have. - **Type:** Testing - **MoSCoW:** Must Have — v3.5.0 acceptance criteria - **Priority:** High - **Milestone:** v3.5.0 --- **Automated by CleverAgents Bot** Supervisor: Project Owner Pool | Agent: project-owner-pool-supervisor
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Reference
cleveragents/cleveragents-core#8948
No description provided.