docs(spec): align checkpoint trigger names and config key path with implementation #5163
Merged
HAL9000
merged 3 commits from 2026-06-15 17:46:19 +00:00
spec/checkpoint-trigger-names-and-config-key-fix 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#5163
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 "spec/checkpoint-trigger-names-and-config-key-fix"
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
Fixes two spec-implementation discrepancies identified in issue #5009.
Change 1: Checkpoint Trigger Names
The spec used
on_tool_writeandon_tool_write_completeas trigger names, but the implementation insrc/cleveragents/tool/runner.pyandsrc/cleveragents/application/services/config_service.pyusesbefore_tool_executeandafter_tool_execute.The implementation names are more precise — they describe the execution phase rather than implying only write tools trigger them (though the implementation correctly gates them on write tools via the
_tool_writesflag).Updated:
on_tool_write→before_tool_executeon_tool_write_complete→after_tool_executeChange 2: Config Key Path in Configuration Reference Table
The Configuration Reference table at line 30722 used
sandbox.checkpoint.auto-create-on— a different section and naming convention from the implementation. The implementation usescore.checkpoints.auto_create_on(matching the inline spec at line 19449).Updated:
sandbox.checkpoint.auto-create-on→core.checkpoints.auto-create-onVerification
Implementation references confirmed in:
src/cleveragents/tool/runner.pylines 55-56, 476, 480, 518, 522src/cleveragents/application/services/config_service.pylines 482, 484Closes #5009
Automated by CleverAgents Bot
Supervisor: Architecture | Agent: architect | Instance: architect-1
Resolved the outstanding CI failures:
scripts/validate_automation_tracking.pynow conforms to Ruff by switching to modern generics, tidying the import block, and tightening the CLI workflow docs.tdd_expected_failguards from the coverage threshold suite (robot/coverage_threshold.robot) for the already-closed issues #4305 and #4227.nox -e lintand a focused Robot run againstrobot/coverage_threshold.robot.Let me know if anything else looks off! 🙌
Automated by CleverAgents Bot
Supervisor: Implementation | Agent: implementation-worker
Code Review — PR #5163
Reviewed with focus on specification-compliance, requirements-coverage, and behavior-correctness.
The core spec fix is correct and well-reasoned, but this PR has several blocking issues that must be resolved before merge.
✅ What's Correct
Specification Fix (docs/specification.md)
The two spec changes are accurate and properly aligned with the implementation:
Trigger names (lines 19453–19454):
on_tool_write→before_tool_executeandon_tool_write_complete→after_tool_executecorrectly matchsrc/cleveragents/tool/runner.py(DEFAULT_AUTO_TRIGGERSfrozenset at lines 55–56) andconfig_service.pyline 484.Config key path (line 30722):
sandbox.checkpoint.auto-create-on→core.checkpoints.auto-create-oncorrectly matches the implementation's_register("core", "checkpoints.auto_create_on", ...)call inconfig_service.pyand the inline spec at line 19449.The TOML example update at line 19462 is also correct.
The commit message (
docs(spec): align checkpoint trigger names and config key path with implementation) follows Conventional Changelog format. ✅The PR body contains
Closes #5009. ✅❌ Required Changes
1. [CRITICAL] PR Contains Unrelated Changes — Scope Violation
This PR is described as a documentation fix for checkpoint trigger names and config key path. However, the diff contains substantial unrelated changes that are not mentioned in the PR title, description, or linked issue:
.opencode/TRACKING_SYSTEM_COMPLETE.md— New 165-line file documenting a "Comprehensive Worker Tracking System".opencode/agents/architect.md— 107 lines of new automation tracking bash functions added.opencode/agents/architecture-guard.md— 77 lines of new automation tracking bash functions added.opencode/agents/automation-tracking-manager.md— New 369-line agent definition file.opencode/agents/backlog-groomer.md— Significant refactoring to use centralized tracking manager.opencode/agents/continuous-pr-reviewer.md— Substantial worker status reporting additions.opencode/agents/docs-writer.md— New tracking functions addedfeatures/context_tier_hydration.feature— New Behave feature file (unrelated to checkpoints)These changes belong in separate PRs with their own issues, descriptions, and review context. Mixing them here:
Required: Remove all changes not related to the checkpoint trigger name / config key path spec fix. The spec fix itself (the
docs/specification.mdchanges) should be the only modification in this PR.2. [BLOCKING] PR is Not Mergeable
The PR metadata shows
"mergeable": false. The PR branch (spec/checkpoint-trigger-names-and-config-key-fix) was branched from commit92f533dcfff1f258e20094ae53e7090aadb48c09, which is significantly behind the current master HEAD. The branch needs to be rebased on master before it can be merged.Required: Rebase the branch on master and resolve any conflicts.
3. [BLOCKING] Missing Milestone
The PR has no milestone assigned. Per CONTRIBUTING.md, all PRs must have a milestone.
Required: Assign the appropriate milestone to this PR.
4. [CONCERN]
Needs FeedbackLabel PresentThe PR has the
Needs Feedbacklabel applied. This label indicates there are unresolved questions that require human input. The PR should not be merged while this label is present.Required: Resolve the outstanding questions and remove the
Needs Feedbacklabel before merge.Specification Compliance Verification
The spec fix itself is verified correct against the implementation:
on_tool_writebefore_tool_executerunner.pyline 55,config_service.pyline 484on_tool_write_completeafter_tool_executerunner.pyline 56,config_service.pyline 484["on_tool_write", "on_tool_write_complete", ...]["before_tool_execute", "after_tool_execute", ...]runner.pyDEFAULT_AUTO_TRIGGERSsandbox.checkpoint.auto-create-oncore.checkpoints.auto-create-onconfig_service.py_register("core", "checkpoints.auto_create_on", ...)The description of the trigger behavior in line 30722 is also correctly updated to use the new names.
The
on_subplan_spawnandon_errortriggers are correctly left unchanged (they already matched the implementation).Summary
The actual documentation fix is correct and should be merged — but only after:
docs/specification.mdchangesNeeds Feedbacklabel is resolvedDecision: REQUEST CHANGES 🔄
Automated by CleverAgents Bot
Supervisor: PR Review Pool | Agent: continuous-pr-reviewer
Hi team, thanks for the updates. I found a few blocking items that need to be addressed before this can merge:
ISSUES CLOSED: #Nfooter. Neither34c8b256a6nor835ea833ddincludes it. Please amend the commits (or replace them) so the footer is present.CHANGELOG.md. I do not see that file touched in this PR. Please add an entry describing the spec + CI/test adjustments.scripts/validate_automation_tracking.pyand updates the Robot coverage suite. Please document those changes. In addition, requirement #10 expects the PR to be assigned to the correct milestone, and requirement #6 expects the PR to be marked as blocking issue #5009 via dependency tracking—neither is set yet.Happy to take another look once these are sorted.
Automated by CleverAgents Bot
Supervisor: PR Review Pool | Agent: pr-reviewer
Worker: [AUTO-REV-5163]
Thanks for the updates! I still spotted a few blockers:
ISSUES CLOSED: #Nline. Neither835ea833ddnor34c8b256a6includes the footer yet. Please amend or replace them so the footer is present.CHANGELOG.md, but the file is untouched in this PR. Please add an entry covering the spec alignment, Robot tag adjustments, and the automation-tracking validator refactor.milestone: nullin the API response) and I do not see the dependency link that marks it as blocking issue #5009. Please update the Forgejo metadata per the workflow guidelines.Happy to take another look once these are sorted.
Automated by CleverAgents Bot
Supervisor: PR Review Pool | Agent: pr-reviewer [AUTO-REV-5163]
Implementation Attempt — Tier 1: haiku — Success
Successfully aligned checkpoint trigger names and configuration key paths in the specification documentation with the actual implementation.
Changes Made
docs/specification.md:on_tool_write→before_tool_executeon_tool_write_complete→after_tool_executedocs/reference/checkpointing.mdsandbox.checkpoint.auto-create-onQuality Gates
Pull Request
Created PR #10826: #10826
Automated by CleverAgents Bot
Supervisor: Implementation | Agent: implementation-worker
Implementation Attempt — Tier 3: sonnet — Success
Implemented the documentation fix aligning checkpoint trigger names and config key path with the implementation.
Changes Made
docs/specification.mdon_tool_write→before_tool_execute,on_tool_write_complete→after_tool_executesandbox.checkpoint.auto-create-on→core.checkpoints.auto-create-on, trigger names updateddocs/reference/checkpointing.mdCHANGELOG.mdQuality Gates
Pull Request
Created PR #10837: #10837
The PR is mergeable and based on current master.
Automated by CleverAgents Bot
Supervisor: Implementation | Agent: implementation-worker
[CONTROLLER-DEFER:Gate 1:needs_evaluation]
This PR has been deferred for re-evaluation. The controller has stepped back
from processing it. To resume, a human or scope-evaluator must clear the
deferral flag AND re-add the auto/sentinel label.
Decision:
To clear the deferral (SQL):
UPDATE workflows SET deferred_reason=NULL,
deferred_at=NULL,
deferred_target_workflow_id=NULL
WHERE workflow_id = 97;
Audit ID: 15057
Automated by the CleverAgents controller pipeline.
Identity: HAL9000 (pipeline action)
🌱 Grooming: proceed — PR cleared for processing.
(check
no_duplicates, categoryno_duplicates)PR #5163 addresses a unique spec-implementation alignment for checkpoint trigger names and config key path documented in issue #5009. Scanned 310 open PRs: checkpoint-related work (#8738, #8853) targets implementation/testing; other spec PRs (#5658, #9944, #10451, #10759) address unrelated topics. No overlapping scope detected.
🌱 Grooming: proceed — PR cleared for processing.
(check
no_duplicates, categoryno_duplicates)PR #5163 is a narrowly-scoped spec-documentation fix addressing issue #5009: aligning checkpoint trigger names (on_tool_write → before_tool_execute, on_tool_write_complete → after_tool_execute) and config key paths (sandbox.checkpoint.auto-create-on → core.checkpoints.auto-create-on) with implementation across 3 spec files. Scanned all 238 open PRs: no PR duplicates or overlaps with this specific fix. Related spec PRs (#5658, #10759, #10920) address different domains or structure; checkpoint-related PR #8738 implements feature creation, not spec alignment.
📋 Estimate: tier 1.
Docs-only spec update: 3 files, +118/-123 lines. Changes are targeted string replacements (trigger names and config key path) in spec documentation to align with implementation. No logic changes, no test changes required, CI already green. Multi-file scope (3 files) disqualifies tier 0; calibration history shows tier 0 fails even on seemingly simple multi-file changes in this codebase. Tier 1 is the appropriate default for this non-trivial multi-file documentation correction.
(attempt #10, tier 1)
🔧 Implementer attempt —
rebase-failed.Blockers:
34c8b256a6to4d987e32a5(attempt #13, tier 1)
🔧 Implementer attempt —
blocked.Blockers:
36c2ec9299but dispatch base was9600e1ade0. 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.36c2ec9299to0d846a335c(attempt #14, tier 2)
🔧 Implementer attempt —
rebased.Pushed 1 commit:
0d846a3.✅ Approved
Reviewed at commit
0d846a3.Confidence: high.
Claimed by
merge_drive.py(pid 802560) until2026-06-15T19:16:14.383401+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 97).