agent-launcher-orchestrator

原文涵盖的主题

• agent-launcher — Domain Orchestrator
• The through-line: the session goal
• Routing (deterministic)
• Compile the loop
• Pre-flight gates (hard refusals)
• Hand-off contract
• Forcing-question library (walk one at a time; recommend + cite)
• Tools

Every session starts with a goal — one sentence for one CMA. This orchestrator reads that goal, routes to the right phase, and compiles the goal into a loop or a workflow. Heavy intake stays in the forked context; the parent gets a digest. Inspired by Anthropic's launch-your-agent reference skill (Apache-2.0). This is an independent re-implementation; CMA semantics come from ../../references/cma-primitives.md. State lives at ./my-agent/goal.json (the user's folder). Manage it with goalstate.py (init / set / status / advance) — it also backs the /cs-goal command and the opt-in SessionStart hook. The goal's phase selects the lane; the phase + recurrence selects the loop shape. Run the router, then act on its exit code: | Lane (phase) | Sub-skill | Loop/workflow | |---|---|---| | interview | interview | single-pass workflow | | stage-launch | stage-launch | single-pass workflow | | grade-iterate | grade-iterate | bounded grade→iterate loop | | run-without-you | run-without-you | recurring cron deployment loop | | wrap-up | wrap-up | — | loopcompiler.py emits plan.v1: single-pass, grade-iterate (always with a maxiterations cap 1..20), or cron-loop (optionally nesting a self-grading out

这里只展示节选，请以完整原文和当前要求为准。