cleveragents/cleveragents-core
4
0
Fork 3
Code Issues 6.0k Pull Requests 115 Actions Packages Projects Releases Wiki Activity

Epic: Subplans & Parallelism #368

New Issue
Open
opened 2026-02-22 23:41:41 +00:00 by freemo · 1 comment
freemo commented 2026-02-22 23:41:41 +00:00
Owner
Copy Link
Copy Source

Background

Covers subplan model, service, execution, merge, checkpoint/rollback hooks, error recovery, and multi-project subplan support.

Expected Behavior

Subplans are modeled, created via service, executed in parallel, and merged back into parent plans. Checkpoint/rollback hooks enable safe recovery, error recovery handles failures gracefully, and multi-project support allows subplans across project boundaries.

Child Issues

Definition of Done

This Epic is complete when all child issues are closed and merged. Subplans execute and merge correctly.

## Background Covers subplan model, service, execution, merge, checkpoint/rollback hooks, error recovery, and multi-project subplan support. ## Expected Behavior Subplans are modeled, created via service, executed in parallel, and merged back into parent plans. Checkpoint/rollback hooks enable safe recovery, error recovery handles failures gracefully, and multi-project support allows subplans across project boundaries. ## Child Issues - #183 - #184 - #186 - #187 - #197 - #198 - #199 ## Definition of Done This Epic is complete when all child issues are closed and merged. Subplans execute and merge correctly.
freemo added this to the v3.4.0 milestone 2026-02-22 23:41:41 +00:00
freemo added the
State
Verified
Type
Epic
Priority
Medium
 labels 2026-02-22 23:41:41 +00:00
freemo added a new dependency 2026-02-22 23:54:23 +00:00
#309 Stage E1: Subplan Model
freemo added a new dependency 2026-02-22 23:54:23 +00:00
#310 test(domain): add subplan model suites
freemo added a new dependency 2026-02-22 23:54:28 +00:00
#377 Legendary: Day 14 Rebaseline Milestones [SUPERSEDED]
freemo removed a dependency 2026-02-23 20:35:54 +00:00
#377 Legendary: Day 14 Rebaseline Milestones [SUPERSEDED]
freemo added a new dependency 2026-02-23 20:35:54 +00:00
#389 Legendary: Context Intelligence & Scaling (M5)
freemo added a new dependency 2026-02-23 20:35:54 +00:00
#183 feat(sandbox): add checkpoint and rollback hooks
freemo added a new dependency 2026-02-23 20:35:54 +00:00
#184 feat(subplan): execute and merge subplans
freemo added a new dependency 2026-02-23 20:35:54 +00:00
#186 feat(plan): add error recovery patterns and CLI hints
freemo added a new dependency 2026-02-23 20:35:54 +00:00
#187 test(e2e): add M4 correction + subplan suites
freemo added a new dependency 2026-02-23 20:35:54 +00:00
#197 feat(service): add subplan service and spawn workflow
freemo added a new dependency 2026-02-23 20:35:54 +00:00
#198 feat(actor): add plan_subplan tool and decision emission
freemo added a new dependency 2026-02-23 20:35:54 +00:00
#199 feat(plan): add multi-project subplan support
freemo added the
Points
34
 label 2026-02-24 03:36:22 +00:00
freemo self-assigned this 2026-02-24 03:37:58 +00:00
freemo commented 2026-04-02 08:10:50 +00:00
Author
Owner
Copy Link
Copy Source

New child issue tracked: #1271 — BUG-HUNT: [boundary] Off-by-one error in subplan retry logic

An off-by-one bug has been discovered in SubplanFailureHandler.should_retry (plan.py:1258). The condition status.attempt_number > config.max_retries should be >=, causing subplans to be retried one extra time beyond max_retries. This child issue has been added to this Epic for tracking.

**New child issue tracked:** #1271 — BUG-HUNT: [boundary] Off-by-one error in subplan retry logic An off-by-one bug has been discovered in `SubplanFailureHandler.should_retry` (`plan.py:1258`). The condition `status.attempt_number > config.max_retries` should be `>=`, causing subplans to be retried one extra time beyond `max_retries`. This child issue has been added to this Epic for tracking.
freemo removed the
Priority
Medium
State
Verified
Type
Epic
 labels 2026-04-03 00:31:20 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
auto/needs-reevaluation
Controller deferred this PR; awaiting Phase 6+ scope-evaluator or operator re-enablement.
 controller-managed
Auto-agents controller manages this PR/issue (see tools/controller/deploy/RUNBOOK.md). Remove this label to abandon controller management.
 overdue
auto/blocked-by-deps
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.
 auto/ci-timeout
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.
 auto/claimed-implementer
Currently being processed by an implementer worker.
 auto/claimed-merge
Currently being processed by the merge driver.
 auto/claimed-reviewer
Currently being processed by a reviewer worker.
 auto/driver-down
Merge driver heartbeat stale; pipeline halted. Closed automatically on next clean tick.
 auto/invariant-violation
Detected master commit violating the strict merge invariant. Tracked as an issue (not a PR label); kept here for label completeness.
 auto/last-attempt-tier-0
In-cycle escalation: most recent attempt ran at the Tier 0 slot (`tier-0`). Slot's model defined in .opencode/models/tiers.yaml.
 auto/last-attempt-tier-1
In-cycle escalation: most recent attempt ran at the Tier 1 slot (`tier-1`). Slot's model defined in .opencode/models/tiers.yaml.
 auto/last-attempt-tier-2
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.
 auto/last-attempt-tier-min
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.
 Automation Tracking
Tracking issues used by the AI Automation system for agents to communicate and report.
 auto/needs-conflict-resolution
Rebase conflict needs LLM conflict-resolver.
 auto/needs-implementer
Failing CI needs implementer attention.
 auto/postmortem
Documenting a driver incident or rollback.
 auto/ready-to-merge
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.
 auto/restart-throttled
Train repeatedly lost master-tempo races. Driver excludes via merge_cycle until cooldown elapses; label persists as visible history.
 auto/revert
Revert PR backing out an invariant violation. Fast-tracked through the merge driver.
 auto/sentinel
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.
 auto/stale-inactivity
No implementer activity for N days. Flagged for human review. Auto-cleared on next push to head branch.
 auto/unstable
Repeatedly fails on current master (>= 3 ci-fail-on-rebased-sha releases in 12 h). Excluded from driver until human triage.
 Blocked
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.
Needs Feedback
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
Signed-off: Owner
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.
 Signed-off: Scrum Master
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.
 Signed-off: Tech Lead
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.
 Spike
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.
No Label
Points
34
Milestone
No items
No Milestone v3.4.0
Projects
Clear projects
No project
Assignees
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 freemo
1 Participants
Notifications
Due Date
No due date set.
Blocks
#389 Legendary: Context Intelligence & Scaling (M5)
cleveragents/cleveragents-core
Depends on
#183 feat(sandbox): add checkpoint and rollback hooks
cleveragents/cleveragents-core
#184 feat(subplan): execute and merge subplans
cleveragents/cleveragents-core
#186 feat(plan): add error recovery patterns and CLI hints
cleveragents/cleveragents-core
#187 test(e2e): add M4 correction + subplan suites
cleveragents/cleveragents-core
#197 feat(service): add subplan service and spawn workflow
cleveragents/cleveragents-core
#198 feat(actor): add plan_subplan tool and decision emission
cleveragents/cleveragents-core
#199 feat(plan): add multi-project subplan support
cleveragents/cleveragents-core
#307 feat(core): add v3 lifecycle models, automation levels, subplan support, and security hardening
cleveragents/cleveragents-core
#308 Traceability: Updated E1.domain commit message to match git log entry (no history rewrite required).
cleveragents/cleveragents-core
#309 Stage E1: Subplan Model
cleveragents/cleveragents-core
#310 test(domain): add subplan model suites
cleveragents/cleveragents-core
#822 bug(plan): checkpoint rollback is simulated — does not execute real git reset
cleveragents/cleveragents-core
#823 bug(plan): subplan spawn creates metadata but does not orchestrate real child plan execution
cleveragents/cleveragents-core
#1207 feat(actors): wire LLM strategize/execute actors to subplan spawning infrastructure
cleveragents/cleveragents-core
#2061 UAT: `SubplanService.spawn()` does not inherit automation profile from parent plan to child plans
cleveragents/cleveragents-core
#2073 Bug: `SubplanService.spawn()` copies parent `definition_of_done` to child plans instead of using spawn entry goal
cleveragents/cleveragents-core
#2074 UAT: `ExecutionMode.DEPENDENCY_ORDERED` is not defined in the specification — undocumented third execution mode added to implementation
cleveragents/cleveragents-core
#2145 TDD: `NamespacedName.validate_namespace()` and `validate_name()` in `plan.py` allow names starting with digits — spec requires names to start with a letter
cleveragents/cleveragents-core
#2147 UAT: `NamespacedName.validate_namespace()` and `validate_name()` in `plan.py` allow names starting with digits — spec requires names to start with a letter
cleveragents/cleveragents-core
#2380 bug(plan): `Plan.can_revert_to()` incorrectly rejects `STRATEGIZE → STRATEGIZE` reversion — errored Strategize plans cannot be restarted
cleveragents/cleveragents-core
#2392 UAT: `PlanLifecycleService.use_action()` stores action invariants as `InvariantSource.ACTION` instead of promoting them to `InvariantSource.PLAN` — runtime sees four-tier chain instead of spec-required three-tier
cleveragents/cleveragents-core
#2454 UAT: `agents plan rollback` `changes_reverted` field is a flat list of path strings instead of spec-required `{file, action}` objects
cleveragents/cleveragents-core
#2864 UAT: `Plan.reversion_count`, `last_completed_step`, and `last_checkpoint_id` are not persisted to the database — plan resume and reversion limits fail after restart
cleveragents/cleveragents-core
#2870 UAT: `Plan.subplan_statuses` and `Plan.subplan_config` are not persisted to the database — subplan orchestration state is lost on restart
cleveragents/cleveragents-core
#3144 UAT: `agents plan rollback` JSON output format does not match spec — multiple field name mismatches and missing fields
cleveragents/cleveragents-core
#3171 UAT: `SubplanService.validate_spawn` incorrectly rejects spawning more subplans than `max_parallel` — should only limit concurrency
cleveragents/cleveragents-core
#3218 bug(checkpoint): `agents plan rollback` does not reset plan processing state to `execute/queued` after sandbox rollback
cleveragents/cleveragents-core
#3270 UAT: `SubplanExecutionService` silently swallows `MergeConflictError` — merge conflicts from parallel subplan results are never surfaced to the user
cleveragents/cleveragents-core
#3274 refactor(agents): extract _create_initial_state and _get_config helpers to eliminate duplicate invocation setup in PlanGenerationGraph and AutoDebugAgent
cleveragents/cleveragents-core
#3326 UAT: `agents plan rollback` does not discard decisions or invalidate child plans after checkpoint — only filesystem is reverted
cleveragents/cleveragents-core
#3327 TDD: UAT: `agents plan rollback` does not discard decisions or invalidate child plans after checkpoint — only filesystem is reverted
cleveragents/cleveragents-core
#3438 UAT: `system/create_checkpoint` built-in tool missing — actors cannot manually create checkpoints
cleveragents/cleveragents-core
#3439 UAT: Automatic checkpoint triggers not implemented — only pre/post execute checkpoints created, not per-tool-write or event-based
cleveragents/cleveragents-core
#3443 UAT: `agents plan rollback` confirmation prompt missing checkpoint label, creation time, and side effects count
cleveragents/cleveragents-core
#3445 UAT: `agents plan rollback` Rich output format doesn't match spec — missing panels, checkpoint label, side effects, and actor state
cleveragents/cleveragents-core
#3561 UAT: `PlanExecutor` has no subplan spawning integration — child plans are never spawned during Execute phase
cleveragents/cleveragents-core
#3563 UAT: `SkeletonCompressor` is stored but never invoked in `ContextAssembler.assemble()` — context inheritance to child plans is broken
cleveragents/cleveragents-core
#3567 bug(subplan): `SubplanService.validate_spawn` incorrectly rejects spawn requests where total entries exceed `max_parallel` — `max_parallel` is a concurrency cap, not a total spawn cap
cleveragents/cleveragents-core
#3725 BUG: [concurrency] Potential for Race Conditions in `_tell_streaming`
cleveragents/cleveragents-core
#3749 UAT: SubplanService.spawn() generates duplicate child plan names when spawning multiple subplans in rapid succession
cleveragents/cleveragents-core
#3754 UAT: Forbidden # type: ignore comments present in decomposition_service.py and decomposition_clustering.py
cleveragents/cleveragents-core
#3819 UAT: `RuntimeExecuteActor.execute()` records stub invocations instead of dispatching real tool calls based on decision content
cleveragents/cleveragents-core
#3935 UAT: `ReactiveEventBus` documented as single-threaded but used as a Singleton in multi-threaded context — race condition risk
cleveragents/cleveragents-core
#3943 UAT: `SubplanExecutionService._execute_with_timeout` creates a new `ThreadPoolExecutor` per subplan call and leaks threads on timeout
cleveragents/cleveragents-core
#3956 UAT: `SubplanService.spawn()` does not inherit `automation_profile` from parent plan — child plans execute without automation behavior context
cleveragents/cleveragents-core
#3959 UAT: `SubplanService.spawn()` does not inherit `execution_environment` and `execution_env_priority` from parent plan — child plans may run in wrong environment
cleveragents/cleveragents-core
#4001 UAT: `SubplanFailureHandler.should_retry()` silently ignores `retry_failed=True` for unknown error types — unknown errors are never retried
cleveragents/cleveragents-core
#4005 UAT: `SubplanMergeService` only supports file-content merging — spec requires resource-type-aware merge strategies (databases, APIs, etc.)
cleveragents/cleveragents-core
#4010 UAT: `SubplanExecutionService._record_attempt()` always sets `was_retried=True` — final failed attempt incorrectly reports a subsequent retry occurred
cleveragents/cleveragents-core
#4027 UAT: `ServiceRetryWiring` and `ErrorRecoveryService` are implemented but not wired into the DI container — retry policies and error recovery are never applied at runtime
cleveragents/cleveragents-core
#4030 UAT: `retry_auto_debug` decorator and `RetryContext` context manager are dead code — defined but never used in production code
cleveragents/cleveragents-core
#4032 UAT: `ErrorPatternService` (Layer 4 Predictive Error Prevention) is not wired into the DI container — predictive guidance is never injected before plan execution
cleveragents/cleveragents-core
#4036 UAT: `PlanExecutor._run_execute_with_stub()` overwrites `plan.error_details` on failure — erases structured error recovery metadata written by `ErrorRecoveryService`
cleveragents/cleveragents-core
#4037 UAT: `agents action create` CLI silently drops invariants, automation_profile, and optional actors (review_actor, estimation_actor, invariant_actor) from YAML config
cleveragents/cleveragents-core
#4039 UAT: `PlanLifecycleService.create_action` missing `apply_actor` and `inputs_schema` parameters — fields defined in YAML schema cannot be persisted
cleveragents/cleveragents-core
Reference: cleveragents/cleveragents-core#368
Delete Branch "%!s()"

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?