Files
boocode/openspec/changes/domain3-multi-agent/proposal.md
indifferentketchup 6fde7002aa docs: boocode-lift-analysis, openspec change docs, codesight cache, deps
- Add boocode-lift-analysis.md: comprehensive 30-repo lift matrix across 25 domains
- Add openspec/ change docs: domain2-code-intelligence, domain3-multi-agent, impeccable-wave, streaming-codeblocks
- Update .gitignore: .impeccable/, .omo/, bun.lock, DESIGN.md, PRODUCT.md
- Update dependencies in package.json + pnpm-lock.yaml
- Update .codesight/ analysis cache
2026-06-08 03:49:26 +00:00

2.5 KiB

Domain 3 — Multi-Agent Orchestration

Status: Proposed Depends on: v2.7.17-orchestrator, v2.8.13-model-resolution-matcher, v2.8.17-boulder-state

Why

BooCode's conductor runs sequential analysis flows on local Qwen with a static wave scheduler. Each step is a linear dependency chain. This works for simple analysis flows but misses 8 concrete improvements identified in the lift analysis (boocode-lift-analysis.md Domain 3).

DO_WHILE loops, SWITCH branching, FORK_JOIN parallel execution, a formal task state machine, declarative DAGs, parallel batch execution, and a structured phased lifecycle would make the conductor a true multi-agent workflow engine.

What Changes

Phase 1: Flow state machine + branching (high confidence)

  1. Task state machine — Add formal states: SCHEDULED → IN_PROGRESS → COMPLETED/FAILED/TIMED_OUT with retriable flag. Currently steps just have running/completed/failed/cancelled.

  2. DO_WHILE loop step — Re-runs a sub-step until a condition is met. while(condition) guard on step definition.

  3. SWITCH branch step — cases: [{ when: condition, steps: [...] }]. First matching case executes.

  4. FORK_JOIN step — Fans out to N parallel sub-steps and synchronizes at a Join point. All branches must complete before the flow advances.

Phase 2: Declarative DAGs (medium confidence)

  1. JSON DAG format — Optional JSON-based flow definition alongside existing TypeScript Step[] arrays. LLM-friendly, versioned, loadable from disk.

Phase 3: Batch execution + lifecycle (lower confidence)

  1. Parallel batch execution — Independent tasks within a flow run concurrently. Uses existing dispatcher's task queue — launch multiple tasks at once.

  2. Structured phased lifecycle — ticket → research → plan → execute → commit → review as a template flow definition.

Non-Goals

  • No replacement of existing flow engine — additive changes only
  • No Paseo daemon integration (handled by omo-paseo-bridge)
  • No inter-agent messaging (Domain 4)

Capabilities

New Capabilities

  • DO_WHILE step type — repeat sub-steps until condition met
  • SWITCH step type — conditional branching by case
  • FORK_JOIN step type — parallel fan-out with Join sync
  • Retriable task flag — auto-retry failed steps up to N times
  • JSON DAG format — portable flow definitions
  • Phased lifecycle template — ticket-to-review reference flow

Modified Capabilities

  • Step kind: gains 'do_while', 'switch', 'fork_join'
  • Flow runner: wave scheduler handles branching + parallel branches