Add Auto permission mode

Claude Code now ships `--permission-mode auto`, where a safety classifier
approves routine actions and blocks risky ones without prompting. Expose it
as a fifth mode between Accept Edits and Bypass: terminals, resumed sessions,
the tab badge, and the scheduler's task runner all map it to the flag.

Headless scheduled runs don't stall in Auto (blocked actions are denied, not
prompted), so the task editor shows a softer note instead of the stall warning.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

HOW-TO-USE.md

@@ -484,9 +484,7 @@ the way they did: one that had Full Permissions on becomes **Bypass**, one that
 **Auto** sits between Accept Edits and Bypass: Claude Code's own classifier reviews each action,
 lets routine work through and blocks things that look risky (such as destructive or
 exfiltrating commands) — no prompts either way. Whether it is available depends on your Claude
-Code account, model and backend (local and OpenAI-compatible backends usually won't
+Code account and model; see Claude Code's documentation on permission modes.
-qualify). When it isn't available, Claude Code quietly starts in its normal prompting mode
-instead.
 
 ### When a change takes effect
 
@@ -504,8 +502,7 @@ instead.
 > Scheduled tasks run headless (`claude -p`) and cannot answer a permission prompt. In any mode
 > other than **Auto** or **Bypass**, a task may simply stop early when Claude Code asks for
 > approval. In **Auto**, actions the classifier blocks are denied and the run carries on without
-> them — but if Auto isn't available for the project's model or backend, Claude Code falls back
+> them. Its run log records which mode it used.
-> to prompting and the task can stall the same way. Its run log records which mode it used.
 
 ---
 
@@ -1360,8 +1357,7 @@ with `--dangerously-skip-permissions`. Because the mode travels into the contain
 environment variable, **stop and start the project** after changing it for the scheduler to see the
 change. Remember that a headless run cannot answer a permission prompt, so in any mode other than
 **Auto** or **Bypass** a task may stop early when Claude Code asks for approval (in Auto, blocked
-actions are denied instead, unless Auto is unavailable and Claude Code falls back to
+actions are denied instead); the run log records the mode
-prompting); the run log records the mode
 that was used.
 
 ### Creating Tasks

app/src/components/projects/home/TaskEditorModal.test.tsx

@@ -165,11 +165,10 @@ describe("TaskEditorModal", () => {
     expect(screen.queryByText(/cannot answer a permission prompt/i)).toBeNull();
   });
 
-  it("tells Auto mode that blocked actions are denied, and warns of the fallback", async () => {
+  it("tells Auto mode that blocked actions are denied, not prompted", async () => {
     await renderEditor(null, { ...baseProject, permission_mode: "auto" });
     expect(screen.queryByText(/cannot answer a permission prompt/i)).toBeNull();
     expect(screen.getByText(/blocks are denied/i)).toBeInTheDocument();
-    expect(screen.getByText(/falls back to prompting/i)).toBeInTheDocument();
   });
 
   it("spells out the stall risk in any non-Bypass mode", async () => {

app/src/components/projects/home/TaskEditorModal.tsx

@@ -302,10 +302,9 @@ export default function TaskEditorModal({ project, task, onClose, onSaved }: Pro
             <strong className="text-[var(--text-primary)]">{modeLabel}</strong>).
           </p>
           {mode === "auto" && (
-            <p className="text-xs text-[var(--warning)]">
+            <p className="text-xs text-[var(--text-secondary)]">
-              In Auto mode, actions the safety classifier blocks are denied and the run carries on
+              In Auto mode nothing prompts: actions the safety classifier blocks are denied and the
-              without them. If Auto isn&rsquo;t available for this project&rsquo;s model or backend,
+              run carries on without them, so check the log if a task seems to have skipped a step.
-              Claude Code falls back to prompting and the task may stall.
             </p>
           )}
           {mode !== "bypass" && mode !== "auto" && (

container/triple-c-task-runner

@@ -61,11 +61,9 @@ TASK_TYPE=$(jq -r '.type' "$TASK_FILE")
 # project's permission setting. Keep this mapping in sync with
 # PermissionMode::cli_args() in app/src-tauri/src/models/project.rs.
 # NOTE: headless `claude -p` runs cannot answer a permission prompt, so any
-# mode other than "bypass" means the task may stop early when Claude Code asks
+# mode other than "bypass" or "auto" means the task may stop early when Claude
-# for permission. In "auto", classifier-blocked actions are denied instead of
+# Code asks for permission. In "auto", actions the classifier blocks are
-# prompted, but if auto mode is unavailable for the session's model/backend,
+# denied rather than prompted, so the run continues without them. Unset or unrecognized values pass no flag (Claude's default).
-# Claude Code falls back to prompting and the same stall applies.
-# Unset or unrecognized values pass no flag (Claude's default).
 PERMISSION_ARGS=()
 case "${TRIPLE_C_PERMISSION_MODE:-}" in
     plan)        PERMISSION_ARGS=(--permission-mode plan) ;;