mirror of
https://github.com/QwenLM/qwen-code.git
synced 2026-09-10 02:29:28 +00:00
e97be6c669
Enabling fork-by-default for every interactive session (#4963) made an omitted `subagent_type` mean a fire-and-forget background fork. A fork's findings never flow back into the parent turn, so any caller that spawns parallel agents and then aggregates their results breaks — the bundled `review`/`simplify` skills, third-party skills, and the model's own delegation. The orchestrator waits forever for results that never arrive; nudged by the periodic todo reminder it can also spin on identical tool calls until DashScope rejects the request with `InternalError.Algo.InvalidParameter: Repetitive tool calls detected` (HTTP 400). Make forking an explicit, deliberate choice and stop steering the model toward it when it needs the results: - Dispatch: `subagent_type: "fork"` selects a fork (interactive only; otherwise general-purpose). Omitting `subagent_type` always resolves to the awaitable general-purpose subagent whose result returns inline — never a fork. `/fork` passes `subagent_type: "fork"` explicitly. - Prompt: drop the "launch parallel forks for research" guidance, reframe the tool description and "When to fork" around "never fork work whose output you need", and stop advertising `fork` in the subagent_type enum (it stays valid via validation for `/fork` and intentional use). - Skills: `review` and `simplify` launch their parallel agents with `subagent_type: "general-purpose"` and are told explicitly not to fork, since they aggregate findings. Forking stays a first-class, default-available feature for genuinely fire-and-forget work — it just isn't the silent default, an enum pick, or something the model is nudged toward when it must read the results. |
||
|---|---|---|
| .. | ||
| design | ||
| developers | ||
| e2e-tests | ||
| plans | ||
| superpowers | ||
| users | ||
| verification/abort-controller-refactor | ||
| _meta.ts | ||
| declarative-agents-port.md | ||
| index.md | ||
| yaml-parser-replacement.md | ||