feat: fork-agent-redesign — 新增 AgentTool fork 参数与 spec 设计文档

为 AgentTool 引入 fork 布尔参数，支持子代理从父对话上下文中 fork 出独立分支，
继承完整历史、系统提示和模型配置。重构 inputSchema 条件逻辑以适配 fork 模式。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

packages/builtin-tools/src/tools/AgentTool/prompt.ts

@@ -82,11 +82,7 @@ export async function getPrompt(
 
 ## When to fork
 
-Fork yourself (omit \`subagent_type\`) when the intermediate tool output isn't worth keeping in your context. The criterion is qualitative \u2014 "will I need this output again" \u2014 not task size.
-- **Research**: fork open-ended questions. If research can be broken into independent questions, launch parallel forks in one message. A fork beats a fresh subagent for this \u2014 it inherits context and shares your cache.
-- **Implementation**: prefer to fork implementation work that requires more than a couple of edits. Do research before jumping to implementation.
-
-Forks are cheap because they share your prompt cache. Don't set \`model\` on a fork \u2014 a different model can't reuse the parent's cache. Pass a short \`name\` (one or two words, lowercase) so the user can see the fork in the teams panel and steer it mid-run.
+When you need to delegate work that benefits from full conversation context (e.g., continuing a multi-file refactor where the child needs the same system prompt and history), use \`fork: true\`. For most tasks, prefer specialized agent types (Explore, Plan, general-purpose).
 
 **Don't peek.** The tool result includes an \`output_file\` path — do not Read or tail it unless the user explicitly asks for a progress check. You get a completion notification; trust it. Reading the transcript mid-flight pulls the fork's tool noise into your context, which defeats the point of forking.
 
@@ -100,14 +96,14 @@ Forks are cheap because they share your prompt cache. Don't set \`model\` on a f
 
 ## Writing the prompt
 
-${forkEnabled ? 'When spawning a fresh agent (with a `subagent_type`), it starts with zero context. ' : ''}Brief the agent like a smart colleague who just walked into the room — it hasn't seen this conversation, doesn't know what you've tried, doesn't understand why this task matters.
+${forkEnabled ? 'When spawning an agent without `fork: true`, it starts with zero context. ' : ''}Brief the agent like a smart colleague who just walked into the room — it hasn't seen this conversation, doesn't know what you've tried, doesn't understand why this task matters.
 - Explain what you're trying to accomplish and why.
 - Describe what you've already learned or ruled out.
 - Give enough context about the surrounding problem that the agent can make judgment calls rather than just following a narrow instruction.
 - If you need a short response, say so ("report in under 200 words").
 - Lookups: hand over the exact command. Investigations: hand over the question — prescribed steps become dead weight when the premise is wrong.
 
-${forkEnabled ? 'For fresh agents, terse' : 'Terse'} command-style prompts produce shallow, generic work.
+${forkEnabled ? 'For non-fork agents, terse' : 'Terse'} command-style prompts produce shallow, generic work.
 
 **Never delegate understanding.** Don't write "based on your findings, fix the bug" or "based on the research, implement it." Those phrases push synthesis onto the agent instead of doing it yourself. Write prompts that prove you understood: include file paths, line numbers, what specifically to change.
 `
@@ -120,6 +116,7 @@ assistant: <thinking>Forking this \u2014 it's a survey question. I want the punc
 ${AGENT_TOOL_NAME}({
   name: "ship-audit",
   description: "Branch ship-readiness audit",
+  fork: true,
   prompt: "Audit what's left before this branch can ship. Check: uncommitted changes, commits ahead of main, whether tests exist, whether the GrowthBook gate is wired up, whether CI-relevant files changed. Report a punch list \u2014 done vs. missing. Under 200 words."
 })
 assistant: Ship-readiness audit running.
@@ -205,11 +202,7 @@ The ${AGENT_TOOL_NAME} tool launches specialized agents (subprocesses) that auto
 
 ${agentListSection}
 
-${
-  forkEnabled
-    ? `When using the ${AGENT_TOOL_NAME} tool, specify a subagent_type to use a specialized agent, or omit it to fork yourself — a fork inherits your full conversation context.`
-    : `When using the ${AGENT_TOOL_NAME} tool, specify a subagent_type parameter to select which agent type to use. If omitted, the general-purpose agent is used.`
-}`
+When using the ${AGENT_TOOL_NAME} tool, specify a subagent_type parameter to select which agent type to use. If omitted, the general-purpose agent is used.${forkEnabled ? ` Set \`fork: true\` to fork from the parent conversation context, inheriting full history and model.` : ''}`
 
   // Coordinator mode gets the slim prompt -- the coordinator system prompt
   // already covers usage notes, examples, and when-not-to-use guidance.
@@ -257,14 +250,13 @@ Usage notes:
 - When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result.${
     // eslint-disable-next-line custom-rules/no-process-env-top-level
     !isEnvTruthy(process.env.CLAUDE_CODE_DISABLE_BACKGROUND_TASKS) &&
-    !isInProcessTeammate() &&
-    !forkEnabled
+    !isInProcessTeammate()
       ? `
 - You can optionally run agents in the background using the run_in_background parameter. When an agent runs in the background, you will be automatically notified when it completes — do NOT sleep, poll, or proactively check on its progress. Continue with other work or respond to the user instead.
 - **Foreground vs background**: Use foreground (default) when you need the agent's results before you can proceed — e.g., research agents whose findings inform your next steps. Use background when you have genuinely independent work to do in parallel.`
       : ''
   }
-- To continue a previously spawned agent, use ${SEND_MESSAGE_TOOL_NAME} with the agent's ID or name as the \`to\` field. The agent resumes with its full context preserved. ${forkEnabled ? 'Each fresh Agent invocation with a subagent_type starts without context — provide a complete task description.' : 'Each Agent invocation starts fresh — provide a complete task description.'}
+- To continue a previously spawned agent, use ${SEND_MESSAGE_TOOL_NAME} with the agent's ID or name as the \`to\` field. The agent resumes with its full context preserved. ${forkEnabled ? 'Each non-fork Agent invocation starts without context — provide a complete task description.' : 'Each Agent invocation starts fresh — provide a complete task description.'}
 - The agent's outputs should generally be trusted
 - Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.)${forkEnabled ? '' : ", since it is not aware of the user's intent"}
 - If the agent description mentions that it should be used proactively, then you should try your best to use it without the user having to ask for it first. Use your judgement.