Skip to content

t1408.1: Add task-decompose-helper.sh with classify, decompose, and lineage subcommands#2990

Closed
marcusquinn wants to merge 0 commit intomainfrom
feature/task-decompose-helper
Closed

t1408.1: Add task-decompose-helper.sh with classify, decompose, and lineage subcommands#2990
marcusquinn wants to merge 0 commit intomainfrom
feature/task-decompose-helper

Conversation

@marcusquinn
Copy link
Owner

Summary

  • Adds task-decompose-helper.sh — an LLM-powered pre-dispatch step that classifies tasks as atomic (execute directly) or composite (split into subtasks), then decomposes composites into 2-5 independent subtasks with dependency edges
  • Three subcommands: classify (atomic/composite determination), decompose (subtask generation with depends_on edges and time estimates), lineage (ancestor/sibling context formatting for worker prompts)
  • TODO.md-aware: checks for existing subtasks before calling LLM, respects blocked-by: conventions, builds lineage from task ID hierarchy

Design

Prompts adapted from TinyAGI/fractals with aidevops-specific heuristics:

  • Haiku-tier LLM calls (~$0.001/call) for cost efficiency
  • Bias toward atomic at depth 2+ to prevent over-decomposition
  • Max depth guard (default 3) to prevent runaway recursion
  • Structured JSON output for machine consumption by dispatch pipeline

Follows existing patterns from ai-research-helper.sh (API calls) and claim-task-id.sh (TODO.md parsing).

Testing

  • help — displays usage
  • classify --task-id t1408 — detects existing subtasks, returns composite without LLM call
  • decompose --task-id t1408 — returns existing subtasks from TODO.md
  • lineage --task-id t1408.1 — shows parent task + sibling tasks
  • decompose --task "..." --depth 3 --max-depth 3 — max-depth guard returns empty subtasks
  • Error paths: nonexistent task ID, unknown subcommand, no args
  • ShellCheck clean (SC1091 disabled project-wide)

Closes #2984

@github-actions github-actions bot added the enhancement Auto-created from TODO.md tag label Mar 6, 2026
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Mar 6, 2026

Warning

Rate limit exceeded

@marcusquinn has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 6 minutes and 29 seconds before requesting another review.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 88d86e84-5062-485b-bb18-e90d25b4ebbb

📥 Commits

Reviewing files that changed from the base of the PR and between 265d36f and f09d021.

📒 Files selected for processing (1)
  • .agents/scripts/task-decompose-helper.sh
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch feature/task-decompose-helper

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@github-actions
Copy link

github-actions bot commented Mar 6, 2026

🔍 Code Quality Report

�[0;35m[MONITOR]�[0m Code Review Monitoring Report

�[0;34m[INFO]�[0m Latest Quality Status:
SonarCloud: 0 bugs, 0 vulnerabilities, 108 code smells

�[0;34m[INFO]�[0m Recent monitoring activity:
Fri Mar 6 05:40:46 UTC 2026: Code review monitoring started
Fri Mar 6 05:40:47 UTC 2026: SonarCloud - Bugs: 0, Vulnerabilities: 0, Code Smells: 108

📈 Current Quality Metrics

  • BUGS: 0
  • CODE SMELLS: 108
  • VULNERABILITIES: 0

Generated on: Fri Mar 6 05:40:49 UTC 2026


Generated by AI DevOps Framework Code Review Monitoring

@sonarqubecloud
Copy link

sonarqubecloud bot commented Mar 6, 2026

@gemini-code-assist
Copy link

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

@marcusquinn
Copy link
Owner Author

This PR appears orphaned — no active worker process found and no activity for 6+ hours. Flagging for re-dispatch. If work is still in progress, remove the status:orphaned label.

@marcusquinn
Copy link
Owner Author

Conflict Resolution — PR Superseded

This PR's work (t1408.1: task-decompose-helper.sh) was already incorporated into main via PR #2999 (t1408.5), which implemented a complete version of the task decomposition system including the helper script, test suite, and integration docs.

What happened:

  • Rebased feature/task-decompose-helper onto latest origin/main
  • The single commit (f09d0218) conflicted with the version already on main from PR t1408.5: Task decomposition system — helper, tests, and integration docs #2999
  • Resolved by accepting main's version (which supersedes this PR's original implementation)
  • After rebase, the branch had 0 commits ahead of main — GitHub auto-closed the PR as empty

No action needed — the functionality this PR intended to deliver is already live on main via PR #2999.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement Auto-created from TODO.md tag status:orphaned

Projects

None yet

Development

Successfully merging this pull request may close these issues.

t1408.1: Create classify/decompose LLM prompts and helper functions

1 participant