test(a2a): add regression tests to verify zero acp references after module rename #10668
Merged
HAL9000
merged 6 commits from 2026-06-17 01:31:27 +00:00
test/v3.6.0/a2a-rename-regression-tests into master
Labels
Clear labels
auto/needs-reevaluation
controller-managed
overdue
auto/blocked-by-deps
auto/ci-timeout
auto/claimed-implementer
auto/claimed-merge
auto/claimed-reviewer
auto/driver-down
auto/invariant-violation
auto/last-attempt-tier-0
auto/last-attempt-tier-1
auto/last-attempt-tier-2
auto/last-attempt-tier-min
Automation Tracking
auto/needs-conflict-resolution
auto/needs-implementer
auto/postmortem
auto/ready-to-merge
auto/restart-throttled
auto/revert
auto/sentinel
auto/stale-inactivity
auto/unstable
Blocked
Needs Feedback
Signed-off: Owner
Signed-off: Scrum Master
Signed-off: Tech Lead
Spike
Controller deferred this PR; awaiting Phase 6+ scope-evaluator or operator re-enablement.
Auto-agents controller manages this PR/issue (see tools/controller/deploy/RUNBOOK.md). Remove this label to abandon controller management.
PR blocked by an open issue dependency. Operator must close the dep (or remove the dependency link) before the merge driver can act. Auto-cleared by merge_drive when no open deps remain.
Most recent merge cycle hit CI timeout. Driver excludes this PR while last merge_cycle row is < 30 min old; label persists thereafter as visible history.
Currently being processed by an implementer worker.
Currently being processed by the merge driver.
Currently being processed by a reviewer worker.
Merge driver heartbeat stale; pipeline halted. Closed automatically on next clean tick.
Detected master commit violating the strict merge invariant. Tracked as an issue (not a PR label); kept here for label completeness.
In-cycle escalation: most recent attempt ran at the Tier 0 slot (`tier-0`). Slot's model defined in .opencode/models/tiers.yaml.
In-cycle escalation: most recent attempt ran at the Tier 1 slot (`tier-1`). Slot's model defined in .opencode/models/tiers.yaml.
In-cycle escalation: most recent attempt ran at the Tier 2 slot (`tier-2`). Slot's model defined in .opencode/models/tiers.yaml. Gated behind IMPLEMENTER_ESCALATION_TIER2_ENABLED.
In-cycle escalation: most recent attempt ran at the Tier -1 slot (`tier-min`). Slot's model defined in .opencode/models/tiers.yaml. Suffix is ``-min`` (not ``--1``) so the Forgejo UI reads naturally.
Tracking issues used by the AI Automation system for agents to communicate and report.
Rebase conflict needs LLM conflict-resolver.
Failing CI needs implementer attention.
Documenting a driver incident or rollback.
Reviewer has APPROVED this PR and no later REQUEST_CHANGES is outstanding. The merge driver requires this label to even consider a PR for merging. Set by the reviewer worker on APPROVE; cleared on REQUEST_CHANGES.
Train repeatedly lost master-tempo races. Driver excludes via merge_cycle until cooldown elapses; label persists as visible history.
Revert PR backing out an invariant violation. Fast-tracked through the merge driver.
Sentinel PR duplicated from upstream into a personal fork by tools/duplicate_prs_to_fork.py for pipeline testing. Lives only in the fork; the canonical pipeline never sees it.
No implementer activity for N days. Flagged for human review. Auto-cleared on next push to head branch.
Repeatedly fails on current master (>= 3 ci-fail-on-rebased-sha releases in 12 h). Excluded from driver until human triage.
A ticket in a blocked state and unable to complete until some other task is completed first.
Bounty
$100
A bounty of $100 for any open-source contributor who provides a MR that solves this issue
Bounty
$1000
A bounty of $1000 for any open-source contributor who provides a MR that solves this issue
Bounty
$10000
A bounty of $10000 for any open-source contributor who provides a MR that solves this issue
Bounty
$20
A bounty of $20 for any open-source contributor who provides a MR that solves this issue
Bounty
$2000
A bounty of $2000 for any open-source contributor who provides a MR that solves this issue
Bounty
$250
A bounty of $250 for any open-source contributor who provides a MR that solves this issue
Bounty
$50
A bounty of $50 for any open-source contributor who provides a MR that solves this issue
Bounty
$500
A bounty of $500 for any open-source contributor who provides a MR that solves this issue
Bounty
$5000
A bounty of $5000 for any open-source contributor who provides a MR that solves this issue
Bounty
$750
A bounty of $750 for any open-source contributor who provides a MR that solves this issue
MoSCoW
Could have
Could have feature in order to satisfy the epic/legendary.
MoSCoW
Must have
Must have feature in order to satisfy the epic/legendary.
MoSCoW
Should have
Should have feature in order to satisfy the epic/legendary.
There are questions in the ticket that can not be completed until the project owner provides clarity.
Points
1
1 man-hours worth of work for an expert with no learning curve.
Points
13
13 man-hours worth of work for an expert with no learning curve.
Points
2
2 man-hours worth of work for an expert with no learning curve.
Points
21
21 man-hours worth of work for an expert with no learning curve.
Points
3
3 man-hours worth of work for an expert with no learning curve.
Points
34
34 man-hours worth of work for an expert with no learning curve.
Points
5
5 man-hours worth of work for an expert with no learning curve.
Points
55
55 man-hours worth of work for an expert with no learning curve.
Points
8
8 man-hours worth of work for an expert with no learning curve.
Points
88
88 man-hours worth of work for an expert with no learning curve.
Priority
Backlog
This ticket has backlogged priority and is not to be worked on yet
Priority
CI Blocker
Critical priority issue that blocks CI/CD pipeline and prevents PR merges
Priority
Critical
The priority is critical
Priority
High
The priority is high
Priority
Low
The priority is low
Priority
Medium
The priority is medium
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.
A ticket for learning a tool or technology that is needed to be able to do future planning and design.
State
Completed
The ticket has been fully implemented, completed, and merged with the source code. This label should only be applied once a ticket is closed.
State
Duplicate
A ticket that represents the same content as an existing ticket.
State
In Progress
A ticket that is actively being developed.
State
In Review
A ticket that has had some code completed to implement but is waiting to pass peer review and is not yet merged in.
State
Paused
This ticket's work started but wasn't finished. It's on hold (likely in a feature branch) and will be resumed later, either due to a blocker or a delay.
State
Unverified
All new tickets start in this state. A developer may set it to show the ticket is unverified. This means we haven't agreed to work on it. It will either move to a verified state or be closed as wontdo.
State
Verified
The issue has been verified by a developer as legitimate. It will be worked on and verified tickets are now considered part of the backlog.
State
Wont Do
This ticket has been decided it wont be done. This may mean the bug has been determined to not be real (cant verify) or the feature is one we have decided we dont want to adopt.
Type
Automation
Any edits or discussion about the AI automated coding system.
Type
Bug
Something that doesnt work as intended.
Type
Discussion
Anytime a ticket represents a discussion about a subject and doesnt fall into one of the other categories.
Type
Documentation
An error or improvement needed in the documentation.
Type
Epic
Any first tier epic. That is, an epic which contains only issues as children and will not have sub-epics.
Type
Feature
Some new functionality not present.
Type
Legendary
A type of Epic which will contain other Epics.
Type
Refactor
A code change that restructures existing code without changing its external behavior.
Type
Support
Someone needs help using the project.
Type
Task
A generic task that doesnt fit into the other type categories.
Type
Testing
Work exclusively focusing on fixing or expanding testing.
Projects
Clear projects
No project
Assignees
aditya (Aditya Chhabra)
aleenaumair (Aleena Umair)
brent.edwards (Brent Edwards)
CoreRasurae (Luis Mendes)
drew (Drew Morris)
eugen.thaci (Eugen Thaci)
freemo (Jeffrey Phillips Freeman)
HAL9000 (HAL 9000)
HAL9001 (HAL9001)
hamza.khyari (Hamza Khyari)
hurui200320 (Rui Hu)
justin.morris
khird (Kyle Hird)
org.cleveragents
Clear assignees
aditya (Aditya Chhabra)
aleenaumair (Aleena Umair)
brent.edwards (Brent Edwards)
CoreRasurae (Luis Mendes)
drew (Drew Morris)
eugen.thaci (Eugen Thaci)
freemo (Jeffrey Phillips Freeman)
HAL9000 (HAL 9000)
HAL9001 (HAL9001)
hamza.khyari (Hamza Khyari)
hurui200320 (Rui Hu)
justin.morris
khird (Kyle Hird)
org.cleveragents
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: cleveragents/cleveragents-core#10668
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Delete Branch "test/v3.6.0/a2a-rename-regression-tests"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Summary
This PR adds comprehensive regression tests to verify that zero ACP references remain after the module rename from ACP to A2A. These tests ensure the migration is complete and all symbols follow the standardized A2A naming convention, preventing any regressions during the ongoing module rename initiative.
Changes
Test Scenarios Added
Behave Scenarios (Import Verification)
Robot Framework Tests (CLI Verification)
Test Coverage
Testing
The following test suites were added and executed:
Issue Reference
Closes #7578
Automated by CleverAgents Bot
Agent: pr-creator
Implementation Attempt — Tier 1: haiku — Success
Fixed the A2A regression test expectations to match the actual module exports. The original test file was expecting symbols like
A2AFacade,ClientFactory,A2AMessage, andEventEmitter, but the actual a2a module exportsA2aLocalFacade,ServerClient,A2aRequest, andA2aEventQueue.Changes made:
Automated by CleverAgents Bot
Supervisor: Implementation | Agent: implementation-worker
Automated by CleverAgents Bot
Supervisor: PR Review | Agent: pr-review-worker
This PR cannot be approved because critical CI checks are failing:
Per company policy, all CI gates (lint, typecheck, security, unit_tests, coverage) must pass before a PR can be approved and merged. Please fix the failing tests and linting issues.
Note: The PR title indicates this is adding regression tests for zero ACP references after module rename. Ensure these tests are passing and that no new linting violations were introduced.
Automated by CleverAgents Bot
Supervisor: PR Review | Agent: pr-review-worker
🌱 Grooming: proceed — PR cleared for processing.
(check
no_duplicates, categoryno_duplicates)PR #10668 adds regression tests (Behave + Robot Framework) to verify zero ACP references after the ACP → A2A module rename. No other open PR combines testing for post-rename verification with identical issue closure (#7578). Related PRs (#10664, #11165) perform the actual rename implementation, not regression testing. The anchor's unique scope (regression test suite + verification focus) distinguishes it from all 397 open PRs.
📋 Estimate: tier 1.
Pure test addition (2 files, +424 LOC) with two active CI failures. Lint gate fails due to ruff format on the new step definitions file (trivial one-command fix). Unit test gate shows 2 Behave scenarios failing with 26 step errors — the "traceback outside scenario" pattern indicates a setup/teardown error in the new Behave environment, requiring debugging of the step definitions and/or environment hooks. Fixing both issues is standard implementer work: apply formatting, then diagnose and correct the Behave context setup problem in the new test code. Multi-file test debugging with framework-specific knowledge needed → tier 1.
15d4757dd7to395724e0fb(attempt #3, tier 1)
🔧 Implementer attempt —
rebased.Pushed 1 commit:
395724e.395724e0fbto79513af899(attempt #4, tier 1)
🔧 Implementer attempt —
rebased.Pushed 1 commit:
79513af.79513af899tobaf8c3103b(attempt #5, tier 1)
🔧 Implementer attempt —
rebased.Pushed 1 commit:
baf8c31.(attempt #6, tier 1)
🔧 Implementer attempt —
resolved.Pushed 1 commit:
750df90.Files touched:
features/steps/a2a_naming_regression_steps.py.750df90920to1bda260320(attempt #7, tier 2)
🔧 Implementer attempt —
rebased.Pushed 1 commit:
1bda260.1bda260320to6e5172338b(attempt #8, tier 2)
🔧 Implementer attempt —
rebased.Pushed 1 commit:
6e51723.(attempt #9, tier 2)
🔧 Implementer attempt —
blocked.Blockers:
e81d1d09fbbut dispatch base was6e5172338b. The implementer pushed from inside the worktree (forbidden by the git contract) OR a third party pushed during the attempt. Re-dispatch will re-prefetch and pick up the new head.🌱 Grooming: proceed — PR cleared for processing.
(check
no_duplicates, categoryno_duplicates)PR #10668 adds regression tests to verify zero ACP references after the ACP→A2A module rename. Topically overlaps with #11165 (which implements the rename), but these are complementary: #11165 executes the rename, #10668 tests that it succeeded. Scanned all 357 open PRs; no other PR tests for the same "zero ACP references" regression condition. Unique testing contribution.
📋 Estimate: tier 1.
Pure test-additive PR: 2 new files (Behave feature file + Robot Framework suite), 452 LOC. Exceeds tier-0 on both the file-count and LOC dimensions, and calibration data shows test-additive work consistently regresses at tier 0. The implementer must write valid Behave step definitions and Robot Framework keywords that actually scan the codebase for ACP references, requiring cross-module awareness of the A2A rename. CI passes, task definition is clear. Standard tier-1 engineering work.
🌱 Grooming: proceed — PR cleared for processing.
(check
no_duplicates, categoryno_duplicates)PR #10668 adds regression tests for ACP→A2A module rename verification. While PR #11165 implements the actual rename, these are complementary not duplicate: #10668 tests the rename's completeness and prevents future regressions, whereas #11165 executes the rename itself. No other open PR targets the same regression test coverage.
📋 Estimate: tier 1.
Purely additive test code: 2 new files, +452/-0 lines covering Behave feature scenarios and Robot Framework test suites. No production code changes. CI passes clean (12/12). However, test-additive work in this codebase has a 0/4 historical hit rate at tier 0 — Behave .feature syntax and Robot Framework format-sensitive content require project-convention awareness (97% coverage threshold, src/test layout, feature file structure) that consistently demands tier-1 capability. Scope is isolated to test files for the ACP→A2A module rename verification; reasoning complexity is low but format and convention correctness push the work above tier 0.
e81d1d09fbtofef91165f4🌱 Grooming: proceed — PR cleared for processing.
(check
no_duplicates, categoryno_duplicates)PR #10668 adds regression tests for the ACP → A2A module rename, verifying zero deprecated ACP references via Behave and Robot Framework test suites. Scanned all 236 open PRs for topical overlap: no other PR addresses A2A rename verification or regression tests for this specific refactor. PR #10992 mentions @a2a tags but concerns BDD tagging enforcement, not rename tests. Conclusion: unique scope, no duplicate.
📋 Estimate: tier 1.
Test-only PR (2 files, +452 LOC) adding Behave and Robot Framework regression tests for ACP→A2A module rename. CI fails on a newly added scenario (
a2a_module_imports_audit.feature:126 Verify test coverage for A2A module imports). Fixing requires reading the new feature file, understanding what the failing step asserts vs. actual codebase state post-rename, and correcting the scenario logic. Cross-file context needed (test file + A2A module structure). Calibration data explicitly flags test-additive work as consistently escalating from tier 0; tier 1 is correct.fef91165f4to0153633b65✅ Approved
Reviewed at commit
0153633.Confidence: high.
Claimed by
merge_drive.py(pid 2202036) until2026-06-17T01:47:33.819565+00:00.This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.
0153633b65to18b4d80627Released by
merge_drive.py(pid 2202036). terminal_state=ci-fail-on-rebased-sha, op_label=auto/needs-implementer(attempt #30, tier 1)
🔧 Implementer attempt —
blocked.Blockers:
b3048f128abut dispatch base was18b4d80627. The implementer pushed from inside the worktree (forbidden by the git contract) OR a third party pushed during the attempt. Re-dispatch will re-prefetch and pick up the new head.(attempt #31, tier 2)
🔧 Implementer attempt —
ci-not-ready.✅ Approved
Reviewed at commit
b3048f1.Confidence: high.
Claimed by
merge_drive.py(pid 2202036) until2026-06-17T03:01:23.158307+00:00.This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.
Approved by the controller reviewer stage (workflow 293).