Correct the sub-agent tool description's working-tree claim

The task tool description and the isolated-run comment both said the
sub-agent unconditionally shares your working tree, which is only
true in the default dispatch mode. Worktree isolation snapshots the
dispatcher's last commit, so uncommitted and untracked changes are
never visible to a sub-agent running in that mode.

Author: TheGreatAxios

src/subagent/run.ts

@@ -205,11 +205,12 @@ export function createSubAgentRunController(
   };
 }
 
-// Spin up an isolated, autonomous agent loop against the same working tree,
-// hand it one task, and return its final report. The sub-agent shares the
-// dispatcher's cwd so its edits land in the real repo, but gets its own posix
-// tool instances and its own git-backed context store so the two loops never
-// trample each other's state.
+// Spin up an isolated, autonomous agent loop, hand it one task, and return
+// its final report. `params.cwd` is either the dispatcher's own cwd (shared
+// mode) or a worktree snapshotted from the dispatcher's last commit
+// (isolated mode, see task-tool.ts's useWorktree) — either way this loop
+// gets its own posix tool instances and its own git-backed context store so
+// the two loops never trample each other's state.
 export async function runSubAgent(params: RunSubAgentParams): Promise<string> {
   return withSubAgentSlot(() => runSubAgentInner(params), {
     reentrant: params.nested === true,

src/subagent/task-tool.ts

@@ -58,7 +58,7 @@ export const TaskToolArgs = type({
 export const taskToolDefinition: ToolDefinition = {
   name: "task",
   description:
-    "Spawn a sub-agent (a short-lived child agent) for one self-contained job. This is not a checklist item — use manage_tasks for your own work list. The sub-agent has the full file, search, and shell toolset, uses this session's permission gate (saved grants and auto mode when eligible; you may be prompted for other consequential actions), and returns a structured report (Summary / Findings / Blockers / Paths). Use it to parallelize exploration (\"map every caller of X\") or hand off a well-scoped implementation so your own context stays focused. Fire several task calls in one turn to run sub-agents in parallel. When launching multiple agents with the same profile, assign each a distinct lens in description and prompt so they do not duplicate work. The sub-agent cannot ask you questions and shares your working tree. Write a clear brief: context = durable background; prompt = actionable goal; goals = optional manage_tasks seeds. Prefer the typed spawn contract so leaves finish without thrashing: intent (explore|implement|review|plan|general), success_criteria (done-when checklist), do_not (scope fence), report_focus (what Findings must cover).",
+    "Spawn a sub-agent (a short-lived child agent) for one self-contained job. This is not a checklist item — use manage_tasks for your own work list. The sub-agent has the full file, search, and shell toolset, uses this session's permission gate (saved grants and auto mode when eligible; you may be prompted for other consequential actions), and returns a structured report (Summary / Findings / Blockers / Paths). Use it to parallelize exploration (\"map every caller of X\") or hand off a well-scoped implementation so your own context stays focused. Fire several task calls in one turn to run sub-agents in parallel. When launching multiple agents with the same profile, assign each a distinct lens in description and prompt so they do not duplicate work. The sub-agent cannot ask you questions. Depending on dispatch configuration it either shares your working tree directly, or runs isolated in its own git worktree snapshotted from your last commit — in the isolated case, any uncommitted or untracked changes in your working tree are excluded. Write a clear brief: context = durable background; prompt = actionable goal; goals = optional manage_tasks seeds. Prefer the typed spawn contract so leaves finish without thrashing: intent (explore|implement|review|plan|general), success_criteria (done-when checklist), do_not (scope fence), report_focus (what Findings must cover).",
   inputSchema: {
     type: "object",
     properties: {