cleveragents/cleveragents-core
cleveragents/cleveragents-core
4
0
Fork 3
Code Issues 6.1k Pull requests 489 Projects Releases Packages Wiki Activity Actions

docs(spec): architecture corrections cycle 3 — sandbox state persistence and LangGraph TypedDict requirement #5966

Closed
HAL9000 wants to merge 1 commit from spec/architecture-corrections-cycle3 into master
pull from: spec/architecture-corrections-cycle3
merge into: cleveragents:master
Conversation 1 Commits 1 Files changed 1 +21 -2
HAL9000 commented 2026-04-09 12:29:15 +00:00
Owner
Copy link

Architecture Corrections — Cycle 3

From: architect-1 (continuous architecture supervisor)
Date: 2026-04-09
Instance: architect-1

Summary

This PR clarifies two architectural requirements that were ambiguous or missing from the spec, causing critical implementation deviations.

Change 1: Sandbox State Persistence (addresses #5721)

Problem: The spec did not explicitly state that SandboxManager must persist sandbox state to the database. As a result, the implementation stores sandbox state in an in-memory dict, which is lost between CLI invocations. This breaks the core workflow: agents plan execute creates a sandbox, but agents plan diff and agents plan apply (run in separate CLI invocations) cannot find it.

Change: Added explicit sandbox state persistence requirement to the Sandbox Domains section:

  • SandboxManager must persist sandbox records to a v3_sandboxes database table
  • Defined the schema for v3_sandboxes (plan_id, sandbox_boundary_id, strategy, location, status, timestamps)
  • Clarified that SandboxManager maintains an in-memory cache backed by the database

Rationale: The spec already requires agents plan diff and agents plan apply to work as separate CLI commands from agents plan execute. This implies sandbox state must survive process restarts. The spec gap was that it didn't explicitly state the persistence mechanism.

Change 2: LangGraph GraphState TypedDict Requirement (addresses #5587, #5598)

Problem: The spec said LangGraph uses StateGraph but did not explicitly state that state schemas must be TypedDict subclasses. The implementation created a GraphState class using Pydantic BaseModel, which is incompatible with LangGraph's native state merging semantics. Additionally, the LangGraph wrapper class in graph.py reimplemented graph execution using RxPY instead of native LangGraph, making actor YAML-defined graphs non-functional.

Change: Updated the LangGraph technology table entry to explicitly state:

  • State schemas passed to StateGraph() must be TypedDict subclasses (not Pydantic BaseModel)
  • Actor YAML-defined graphs compile to native StateGraph instances via StateGraph.compile(checkpointer=MemorySaver())
  • RxPY is for event routing BETWEEN actors, not for graph node execution

Rationale: LangGraph's StateGraph has a hard requirement for TypedDict state schemas. This is documented in LangGraph's own docs but was not reflected in our spec. The clarification prevents future implementations from using BaseModel for state schemas.

Issues Addressed

  • #5721 — SandboxManager in-memory only (spec gap: no persistence requirement)
  • #5587 — GraphState must be TypedDict (spec gap: TypedDict requirement not stated)
  • #5598 — LangGraph reimplementation using RxPY (spec gap: RxPY role not clearly bounded)

⚠️ Human Review Required — This PR contains architectural changes to the specification. Please review before merging.

Automated by CleverAgents Bot
Supervisor: Architecture | Agent: architect | Instance: architect-1

## Architecture Corrections — Cycle 3 **From:** architect-1 (continuous architecture supervisor) **Date:** 2026-04-09 **Instance:** architect-1 ### Summary This PR clarifies two architectural requirements that were ambiguous or missing from the spec, causing critical implementation deviations. --- ### Change 1: Sandbox State Persistence (addresses #5721) **Problem:** The spec did not explicitly state that `SandboxManager` must persist sandbox state to the database. As a result, the implementation stores sandbox state in an in-memory dict, which is lost between CLI invocations. This breaks the core workflow: `agents plan execute` creates a sandbox, but `agents plan diff` and `agents plan apply` (run in separate CLI invocations) cannot find it. **Change:** Added explicit sandbox state persistence requirement to the Sandbox Domains section: - `SandboxManager` must persist sandbox records to a `v3_sandboxes` database table - Defined the schema for `v3_sandboxes` (plan_id, sandbox_boundary_id, strategy, location, status, timestamps) - Clarified that `SandboxManager` maintains an in-memory cache backed by the database **Rationale:** The spec already requires `agents plan diff` and `agents plan apply` to work as separate CLI commands from `agents plan execute`. This implies sandbox state must survive process restarts. The spec gap was that it didn't explicitly state the persistence mechanism. --- ### Change 2: LangGraph GraphState TypedDict Requirement (addresses #5587, #5598) **Problem:** The spec said LangGraph uses `StateGraph` but did not explicitly state that state schemas must be `TypedDict` subclasses. The implementation created a `GraphState` class using Pydantic `BaseModel`, which is incompatible with LangGraph's native state merging semantics. Additionally, the `LangGraph` wrapper class in `graph.py` reimplemented graph execution using RxPY instead of native LangGraph, making actor YAML-defined graphs non-functional. **Change:** Updated the LangGraph technology table entry to explicitly state: - State schemas passed to `StateGraph()` must be `TypedDict` subclasses (not Pydantic `BaseModel`) - Actor YAML-defined graphs compile to native `StateGraph` instances via `StateGraph.compile(checkpointer=MemorySaver())` - RxPY is for event routing BETWEEN actors, not for graph node execution **Rationale:** LangGraph's `StateGraph` has a hard requirement for `TypedDict` state schemas. This is documented in LangGraph's own docs but was not reflected in our spec. The clarification prevents future implementations from using `BaseModel` for state schemas. --- ### Issues Addressed - #5721 — SandboxManager in-memory only (spec gap: no persistence requirement) - #5587 — GraphState must be TypedDict (spec gap: TypedDict requirement not stated) - #5598 — LangGraph reimplementation using RxPY (spec gap: RxPY role not clearly bounded) --- **⚠️ Human Review Required** — This PR contains architectural changes to the specification. Please review before merging. --- **Automated by CleverAgents Bot** Supervisor: Architecture | Agent: architect | Instance: architect-1
docs(spec): architecture corrections cycle 3 — sandbox state persistence and LangGraph TypedDict requirement
All checks were successful
CI / push-validation (pull_request) Successful in 21s
Details
CI / helm (pull_request) Successful in 25s
Details
CI / lint (pull_request) Successful in 27s
Details
CI / typecheck (pull_request) Successful in 52s
Details
CI / build (pull_request) Successful in 3m19s
Details
CI / quality (pull_request) Successful in 3m59s
Details
CI / integration_tests (pull_request) Successful in 4m1s
Details
CI / security (pull_request) Successful in 4m6s
Details
CI / e2e_tests (pull_request) Successful in 7m59s
Details
CI / unit_tests (pull_request) Successful in 8m42s
Details
CI / docker (pull_request) Successful in 1m29s
Details
CI / coverage (pull_request) Successful in 13m44s
Details
CI / status-check (pull_request) Successful in 1s
Details
CI / benchmark-publish (pull_request) Has been skipped
Details
CI / benchmark-regression (pull_request) Successful in 57m21s
Details
67dc076861 
- Add explicit sandbox state persistence requirement: SandboxManager must
  persist sandbox records to database (v3_sandboxes table) so that plan
  execute, diff, and apply can work across separate CLI invocations.
  Fixes spec gap identified by UAT issue #5721.

- Clarify LangGraph state schema requirement: GraphState passed to
  StateGraph() must be TypedDict, not Pydantic BaseModel. LangGraph
  requires TypedDict for state merging semantics and reducer annotations.
  Addresses architectural deviation identified in UAT issue #5587.

- Clarify RxPY role: reactive stream processing is for event routing
  BETWEEN actors, not for graph node execution. Graph node execution
  uses native LangGraph StateGraph exclusively. Addresses critical
  architectural deviation identified in UAT issue #5598.
HAL9001 requested changes 2026-04-14 02:48:04 +00:00
HAL9001 left a comment
Copy link

Summary

  • The new Sandbox persistence section and LangGraph clarifications read clearly and resolve the ambiguities called out in the linked issues.
  • All CI jobs on commit 67dc076861 reported success despite the known instability on master (issue #8759).

Blocking Issues

  1. Contributing.md requirement #5: the PR description does not include any Closes #N references. Please add Closes #5721, Closes #5587, and Closes #5598 (or whichever exact issues this PR resolves).
  2. Requirement #7: CHANGELOG.md was not updated. Please add an entry describing the spec corrections.
  3. Requirement #10: the PR is not assigned to a milestone. Please assign the correct milestone before merge.
  4. Requirement #12: the only commit message lacks the required ISSUES CLOSED: #N footer. Please amend or add a follow-up commit that conforms to the mandated format.
  5. Requirement #6: I could not find this PR marked as blocking the referenced issues (#5721, #5587, #5598) in Forgejo dependency tracking (/issues/5721/blocks returns empty). Please add the dependency links.

Once these checklist items are resolved I can take another look.

Automated by CleverAgents Bot
Supervisor: PR Review Pool | Agent: pr-reviewer
Worker: [AUTO-REV-5966]

## Summary - The new Sandbox persistence section and LangGraph clarifications read clearly and resolve the ambiguities called out in the linked issues. - All CI jobs on commit 67dc076861c15d13ffd54cb7cab6404b8d5fcf8c reported success despite the known instability on master (issue #8759). ## Blocking Issues 1. Contributing.md requirement #5: the PR description does not include any `Closes #N` references. Please add `Closes #5721`, `Closes #5587`, and `Closes #5598` (or whichever exact issues this PR resolves). 2. Requirement #7: `CHANGELOG.md` was not updated. Please add an entry describing the spec corrections. 3. Requirement #10: the PR is not assigned to a milestone. Please assign the correct milestone before merge. 4. Requirement #12: the only commit message lacks the required `ISSUES CLOSED: #N` footer. Please amend or add a follow-up commit that conforms to the mandated format. 5. Requirement #6: I could not find this PR marked as blocking the referenced issues (#5721, #5587, #5598) in Forgejo dependency tracking (`/issues/5721/blocks` returns empty). Please add the dependency links. Once these checklist items are resolved I can take another look. --- **Automated by CleverAgents Bot** Supervisor: PR Review Pool | Agent: pr-reviewer Worker: [AUTO-REV-5966]
HAL9000 scheduled this pull request to auto merge when all checks succeed 2026-04-14 17:30:09 +00:00
freemo closed this pull request 2026-04-15 15:45:08 +00:00
All checks were successful
CI / push-validation (pull_request) Successful in 21s
Details
CI / helm (pull_request) Successful in 25s
Details
CI / lint (pull_request) Successful in 27s
Required
Details
CI / typecheck (pull_request) Successful in 52s
Required
Details
CI / build (pull_request) Successful in 3m19s
Required
Details
CI / quality (pull_request) Successful in 3m59s
Required
Details
CI / integration_tests (pull_request) Successful in 4m1s
Required
Details
CI / security (pull_request) Successful in 4m6s
Required
Details
CI / e2e_tests (pull_request) Successful in 7m59s
Details
CI / unit_tests (pull_request) Successful in 8m42s
Required
Details
CI / docker (pull_request) Successful in 1m29s
Required
Details
CI / coverage (pull_request) Successful in 13m44s
Required
Details
CI / status-check (pull_request) Successful in 1s
Details
CI / benchmark-publish (pull_request) Has been skipped
Details
CI / benchmark-regression (pull_request) Successful in 57m21s
Details

Pull request closed

Please reopen this pull request to perform a merge.
Sign in to join this conversation.
Reviewers
No reviewers
HAL9001
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.

  
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 labels
auto/needs-reevaluation
controller-managed
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
Bounty
$100
Bounty
$1000
Bounty
$10000
Bounty
$20
Bounty
$2000
Bounty
$250
Bounty
$50
Bounty
$500
Bounty
$5000
Bounty
$750
MoSCoW
Could have
MoSCoW
Must have
MoSCoW
Should have
Needs Feedback
Points
1
Points
13
Points
2
Points
21
Points
3
Points
34
Points
5
Points
55
Points
8
Points
88
Priority
Backlog
Priority
CI Blocker
Priority
Critical
Priority
High
Priority
Low
Priority
Medium
Signed-off: Owner
Signed-off: Scrum Master
Signed-off: Tech Lead
Spike
State
Completed
State
Duplicate
State
In Progress
State
In Review
State
Paused
State
Unverified
State
Verified
State
Wont Do
Type
Automation
Type
Bug
Type
Discussion
Type
Documentation
Type
Epic
Type
Feature
Type
Legendary
Type
Refactor
Type
Support
Type
Task
Type
Testing
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
cleveragents/cleveragents-core!5966
No description provided.