fix: sanitize assistant session text (#1456) (thanks @zerone0x)

Adds sanitization to extractAssistantText in sessions-helpers.ts to
prevent tool call text from leaking to users. Previously, messages
retrieved from chat history via sessions-helpers.ts could expose:

- Minimax XML tool calls (<invoke>...</invoke>)
- Downgraded tool call markers ([Tool Call: name (ID: ...)])
- Thinking tags (<think>...</think>)

This fix:
- Exports the stripping functions from pi-embedded-utils.ts
- Adds a new sanitizeTextContent helper in sessions-helpers.ts
- Updates extractAssistantText to sanitize before returning
- Updates extractMessageText in commands-subagents.ts to sanitize

Fixes #1269

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

src/commands/auth-choice-options.ts

@@ -46,7 +46,7 @@ const AUTH_CHOICE_GROUP_DEFS: {
     value: "anthropic",
     label: "Anthropic",
     hint: "Claude Code CLI + API key",
-    choices: ["claude-cli", "token", "apiKey"],
+    choices: ["token", "claude-cli", "apiKey"],
   },
   {
     value: "minimax",

src/tui/tui.ts

@@ -452,11 +452,16 @@ export async function runTui(opts: TuiOptions) {
     const reasoning = sessionInfo.reasoningLevel ?? "off";
     const reasoningLabel =
       reasoning === "on" ? "reasoning" : reasoning === "stream" ? "reasoning:stream" : null;
-    footer.setText(
+    const footerParts = [
-      theme.dim(
+      `agent ${agentLabel}`,
-        `agent ${agentLabel} | session ${sessionLabel} | ${modelLabel} | think ${think} | verbose ${verbose}${reasoningLabel ? ` | ${reasoningLabel}` : ""} | ${tokens}`,
+      `session ${sessionLabel}`,
-      ),
+      modelLabel,
-    );
+      think !== "off" ? `think ${think}` : null,
+      verbose !== "off" ? `verbose ${verbose}` : null,
+      reasoningLabel,
+      tokens,
+    ].filter(Boolean);
+    footer.setText(theme.dim(footerParts.join(" | ")));
   };
 
   const { openOverlay, closeOverlay } = createOverlayHandlers(tui, editor);