Skip to content

docs(execute): add tier selection and isolation parameter info#190

Merged
maystudios merged 1 commit intomainfrom
worktree-agent-a58aa641
Mar 25, 2026
Merged

docs(execute): add tier selection and isolation parameter info#190
maystudios merged 1 commit intomainfrom
worktree-agent-a58aa641

Conversation

@maystudios
Copy link
Owner

Summary

  • Adds three sub-bullets under step 5 of templates/commands/maxsim/execute.md documenting Tier 1 worktree isolation defaults, Tier 2 deep competition strategy opt-in, and graceful degradation fallback
  • Brings the §7.2 Parallelism Strategy audit closer to 100% by documenting isolation: "worktree", run_in_background: true, competition_strategy: deep, and CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 requirements
  • Build artifacts (README.md, version.ts, config.json) updated by build scripts

Test plan

  • npx vitest run — 548 tests pass (18 test files)
  • npm run build — TypeScript compiles and assets copy cleanly
  • npm run lint — Biome passes (no errors; pre-existing warnings/infos in unrelated files)

🤖 Generated with Claude Code

…2 parallelism spec

Documents Tier 1 worktree isolation defaults, Tier 2 deep competition strategy opt-in,
and graceful degradation fallback in the execute command's process steps.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Copilot AI review requested due to automatic review settings March 25, 2026 18:33
@maystudios maystudios merged commit caa144e into main Mar 25, 2026
3 checks passed
Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Documentation-focused update clarifying parallel execution tiers (Tier 1 worktree isolation vs Tier 2 Agent Teams) in the /maxsim:execute command docs, plus routine build-script-updated version artifacts.

Changes:

  • Expanded /maxsim:execute docs to mention Tier 1 defaults (isolation: "worktree", run_in_background: true) and Tier 2 opt-in (competition_strategy: deep, Agent Teams env var).
  • Updated CLI README command list and adjusted Planner role description to reflect GitHub-first plan comments.
  • Bumped version artifacts to 5.13.1 (config template + VERSION constant).

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

File Description
templates/templates/config.json Template config version artifact updated to 5.13.1.
templates/commands/maxsim/execute.md Adds Tier selection + isolation/background execution notes to execute command docs.
packages/cli/src/core/version.ts Updates injected VERSION constant to 5.13.1.
packages/cli/README.md Adds loop commands to command table; updates Planner description to match GitHub comment-based plans.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment on lines +30 to +32
- Tier 1 (default): each Agent uses `isolation: "worktree"` and `run_in_background: true`
- Tier 2 (opt-in, `competition_strategy: deep`): Agent Teams with `SendMessage` debate — requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`
- Graceful degradation: if Tier 2 is unavailable, falls back to Tier 1 automatically
Copy link

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The Tier 2 bullets here read like they apply to the general “execute parallel agents within each wave” flow, but in templates/workflows/execute.md Tier selection is described only under the Competitive Implementation (Optional) section (gated by config.execution.competitive_enabled and a critical label). Consider clarifying that Tier 2 (competition_strategy: deep + Agent Teams) is used for competitive/debate mode only, while standard wave execution remains Tier 1 worktree-isolated Agent subagents.

Suggested change
- Tier 1 (default): each Agent uses `isolation: "worktree"` and `run_in_background: true`
- Tier 2 (opt-in, `competition_strategy: deep`): Agent Teams with `SendMessage` debate — requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`
- Graceful degradation: if Tier 2 is unavailable, falls back to Tier 1 automatically
- Tier 1 (standard/default): each wave is executed by `Agent` subagents using `isolation: "worktree"` and `run_in_background: true`
- Tier 2 (competitive/debate mode only; opt-in via `competition_strategy: deep`): Agent Teams with `SendMessage` debate — used only when competitive execution is enabled and a `critical` task is being run, as described in @.claude/maxsim/workflows/execute.md; requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`
- Graceful degradation (competitive path only): if Tier 2 competitive execution is requested but unavailable, fall back to Tier 1 automatically for that work

Copilot uses AI. Check for mistakes.
@github-actions
Copy link
Contributor

🎉 This PR is included in version 5.14.0 🎉

The release is available on:

Your semantic-release bot 📦🚀

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

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants