smart context v3 (#1022)

<!-- This is an auto-generated description by cubic. -->

## Summary by cubic
Adds Smart Context v3 with selectable modes (Off, Conservative,
Balanced) and surfaces token savings in chat. Also improves token
estimation by counting per-file tokens when Smart Context is enabled.

- **New Features**
- Smart Context selector in Pro settings with three options.
Conservative is the default when enabled without an explicit choice.
- New setting: proSmartContextOption ("balanced"); undefined implies
Conservative.
- Engine now receives enable_smart_files_context and smart_context_mode.
- Chat shows a DyadTokenSavings card when the message contains
token-savings?original-tokens=...&smart-context-tokens=..., with percent
saved and a tooltip for exact tokens.
- Token estimation uses extracted file contents for accuracy when Pro +
Smart Context is on; otherwise falls back to formatted codebase output.

<!-- End of auto-generated description by cubic. -->

e2e-tests/engine.spec.ts

@@ -2,8 +2,6 @@ import { testSkipIfWindows } from "./helpers/test_helper";
 
 testSkipIfWindows("send message to engine", async ({ po }) => {
   await po.setUpDyadPro();
-  // By default, it's using auto which points to Flash 2.5 and doesn't
-  // use engine.
   await po.selectModel({ provider: "Google", model: "Gemini 2.5 Pro" });
   await po.sendPrompt("[dump] tc=turbo-edits");
 
@@ -11,6 +9,23 @@ testSkipIfWindows("send message to engine", async ({ po }) => {
   await po.snapshotMessages({ replaceDumpPath: true });
 });
 
+testSkipIfWindows(
+  "send message to engine - smart context balanced",
+  async ({ po }) => {
+    await po.setUpDyadPro();
+    const proModesDialog = await po.openProModesDialog({
+      location: "home-chat-input-container",
+    });
+    await proModesDialog.setSmartContextMode("balanced");
+    await proModesDialog.close();
+    await po.selectModel({ provider: "Google", model: "Gemini 2.5 Pro" });
+    await po.sendPrompt("[dump] tc=turbo-edits");
+
+    await po.snapshotServerDump("request");
+    await po.snapshotMessages({ replaceDumpPath: true });
+  },
+);
+
 testSkipIfWindows("send message to engine - openai gpt-4.1", async ({ po }) => {
   await po.setUpDyadPro();
   // By default, it's using auto which points to Flash 2.5 and doesn't
@@ -52,7 +67,7 @@ testSkipIfWindows(
     const proModesDialog = await po.openProModesDialog({
       location: "home-chat-input-container",
     });
-    await proModesDialog.toggleSmartContext();
+    await proModesDialog.setSmartContextMode("off");
     await proModesDialog.close();
     await po.sendPrompt("[dump] tc=turbo-edits");