UniqueSoft/APAW
2
0
Fork 0
Code Issues 15 Pull Requests Actions Packages Projects Releases Wiki Activity

[Improvement] Implement Evaluator-Optimizer Pattern for Code Review Loop #22

New Issue
Closed
opened 2026-04-05 00:49:10 +00:00 by NW · 1 comment
NW commented 2026-04-05 00:49:10 +00:00
Owner
Copy Link

Overview

Formalize the code review loop (code-skeptic to the-fixer) as an evaluator-optimizer pattern with structured iterations and convergence criteria.

Priority: P1

Effort: Low
Impact: High

Current State

Informal review loop:

  • code-skeptic reviews
  • the-fixer fixes
  • Repeat until approved (no limits)

Proposed Solution

max_iterations: 3
convergence_criteria: all_issues_resolved OR max_iterations_reached

iteration_loop:
  - evaluator: code-skeptic
    outputs: [verdict, issues, severity]
  - optimizer: the-fixer
    outputs: [changes, resolution_notes]

Files to Modify

  • .kilo/agents/code-skeptic.md - Add structured output format
  • .kilo/agents/the-fixer.md - Add structured input handling
  • .kilo/agents/orchestrator.md - Add iteration tracking

Expected Outcomes

  • Maximum 3 review iterations
  • Prevents infinite loops
  • Tracks iteration count for evaluator scoring
## Overview Formalize the code review loop (code-skeptic to the-fixer) as an evaluator-optimizer pattern with structured iterations and convergence criteria. ## Priority: P1 **Effort**: Low **Impact**: High ## Current State Informal review loop: - code-skeptic reviews - the-fixer fixes - Repeat until approved (no limits) ## Proposed Solution ```yaml max_iterations: 3 convergence_criteria: all_issues_resolved OR max_iterations_reached iteration_loop: - evaluator: code-skeptic outputs: [verdict, issues, severity] - optimizer: the-fixer outputs: [changes, resolution_notes] ``` ## Files to Modify - `.kilo/agents/code-skeptic.md` - Add structured output format - `.kilo/agents/the-fixer.md` - Add structured input handling - `.kilo/agents/orchestrator.md` - Add iteration tracking ## Expected Outcomes - Maximum 3 review iterations - Prevents infinite loops - Tracks iteration count for evaluator scoring
NW added the priority::hightype::enhancement labels 2026-04-05 00:49:10 +00:00
NW commented 2026-04-05 01:10:11 +00:00
Author
Owner
Copy Link

? Implemented

Evaluator-Optimizer workflow template created: .kilo/workflows/evaluator-optimizer.md

Implementation

  • Structured iteration loop (max 3 iterations)
  • Convergence criteria: all_issues_resolved
  • Evaluator: code-skeptic
  • Optimizer: the-fixer

Benefit

  • Prevents infinite review loops
  • Tracks iteration count for scoring
  • Guarantees convergence

Also Added

  • capability-index.yaml now includes iteration_loops config
  • Maximum iterations enforced per review type

Commit: 348c47f

## ? Implemented Evaluator-Optimizer workflow template created: `.kilo/workflows/evaluator-optimizer.md` ### Implementation - Structured iteration loop (max 3 iterations) - Convergence criteria: all_issues_resolved - Evaluator: code-skeptic - Optimizer: the-fixer ### Benefit - Prevents infinite review loops - Tracks iteration count for scoring - Guarantees convergence ### Also Added - `capability-index.yaml` now includes `iteration_loops` config - Maximum iterations enforced per review type Commit: 348c47f
NW closed this issue 2026-04-05 01:10:18 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agent::agent-architect
Owned by agent-architect
 agent::capability-analyst
Owned by capability-analyst
 agent::code-skeptic
Owned by code-skeptic
 agent::evaluator
Owned by evaluator
 agent::history-miner
Owned by history-miner
 agent::lead-developer
Owned by lead-developer
 agent::orchestrator
Owned by orchestrator
 agent::sdet-engineer
Owned by sdet-engineer
 agent::system-analyst
Owned by system-analyst
 agent::the-fixer
Owned by the-fixer
 budget::exhausted
Token budget exhausted
 budget::sufficient
Token budget sufficient
 budget::warning
Token budget low
 cascade::depth-0
No subagent calls
 cascade::depth-1
1-level subagent calls
 cascade::depth-2
2-level subagent calls
 cascade::depth-exceeded
Depth limit exceeded
 cascade::depth-n
Unlimited subagent calls
 dashboard::frozen
Dashboard feature freeze — no new features until thaw
 evolution::model-change
Model change evolution
 evolution::new-agent
New agent evolution
 evolution::new-skill
New skill evolution
 evolution::new-workflow
New workflow evolution
 evolution::prompt-opt
Prompt optimization evolution
 memory::checkpoint
Checkpoint stored
 memory::fresh
Checkpoint fresh
 memory::recoverable
Checkpoint recoverable
 memory::stale
Checkpoint stale
 permission::evolve-system
Can evolve system
 permission::read-only
Read-only access
 permission::violation
Security violation
 permission::write-code
Can write code
 permission::write-config
Can write config
 phase::awaiting-review
Agent awaits review
 phase::drafting-spec
Agent is drafting specification
 phase::executing
Agent is executing task
 phase::gathering-evidence
Agent is gathering data
 phase::refining-prompt
Agent is refining prompts
 phase::researching
Research phase — gathering evidence and solutions
 phase::verifying
Agent is verifying results
 priority::critical
Critical priority
 priority::high
High priority
 priority::low
Low priority
 priority::medium
Medium priority
 quality::blocked
Blocked by quality
 quality::fail
Quality check failed
 quality::needs-fix
Needs fixes
 quality::pass
Quality check passed
 size::l
Large (4-8 hours)
 size::m
Medium (2-4 hours)
 size::s
Small (1-2 hours)
 size::xl
Extra large (>8 hours)
 size::xs
Extra small (<1 hour)
 status::blocked
Blocked
 status::cancelled
Cancelled
 status::done
Completed
 status::in-progress
Work in progress
 status::new
New issue, not started
 status::planned
Planned for sprint
 status::review
Under review
 status::testing
In testing
 type::bug
Something is broken
 type::chore
Maintenance task
 type::documentation
Documentation
 type::enhancement
Improvement
 type::feature
New feature
 type::refactor
Code refactoring
 type::test
Testing
No Label priority::high type::enhancement
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
NW olilovedani
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: UniqueSoft/APAW#22
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?