feat: inline prompt history area — scrollable session messages

The inline prompt now shows the current session's full message
history (user + assistant), scrollable, replacing the single-output
display from the previous commit. The user can scroll back through
prior exchanges in the same notebook's OpenCode session.

Server (opencode_bridge/):
  - New route: GET /opencode-bridge/session-messages?notebook=<path>
    - Resolves notebook to session via SessionManager.peek (no create).
    - If no session: {"messages": []} (no OpenCode call).
    - Else: GET /session/{id}/message on OpenCode Serve, project the
      raw {info, parts}[] into a frontend-friendly {role, content}[].
  - OpenCodeClient.list_session_messages(sid).
  - SessionManager.peek(notebook_path) -> Optional[str] (read without
    creating, to avoid spawning a session just to report emptiness).
  - Wired the new route in setup_route_handlers.

Client (src/):
  - types.ts: OpenCodeMessage { role, content } + OpenCodeMessagesResponse.
  - api/opencode_client.ts: callOpenCodeSessionMessages(notebook, serverSettings).
  - components/opencode_inline_prompt.ts:
    - Replaces the single .opencode-inline-output area with a
      scrollable .opencode-inline-history (max-height 320px, overflow-y
      auto, auto-scrolls to bottom on update).
    - setMessages(messages): renders user messages as plain text,
      assistant messages via marked.parse. No more setOutput/hideOutput.
  - components/opencode_cell_actions.ts:
    - _showPrompt now fires a _refreshHistory(notebookPath) which
      fetches and calls prompt.setMessages.
    - _handleResponse on success also calls _refreshHistory (the new
      assistant message appears as the last item in the history).
    - Cell source is still NOT replaced.
  - api/opencode_client module is mocked in the cell_actions test to
    avoid jsdom network calls.

style/base.css:
  - .opencode-inline-output* rules replaced with .opencode-inline-history
    (max-height 320px, overflow-y auto, border, padding) and
    .opencode-msg / .opencode-msg-user / .opencode-msg-assistant.
  - pre/code/p/h1-3 content styling scoped under .opencode-inline-history.

Tests:
  - pytest 37/37: FakeOpenCodeClient.list_session_messages + 3 new
    session_messages route tests (no session, projects messages, 400).
  - jest 29/29: setMessages renders user/assistant + history area tests.
  - FakeSessionManager.peek (returns None when session_id is falsy).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/__tests__/opencode_cell_actions.spec.ts

@@ -52,6 +52,15 @@ jest.mock('marked', () => ({
   marked: { parse: (md: string) => `<mock>${md}</mock>` }
 }));
 
+// Mock the network-touching API module so jsdom tests don't try to hit
+// a real notebook server (and to keep the refresh-history logic decoupled
+// from the network). The cell_actions tests focus on widget behavior.
+jest.mock('../api/opencode_client', () => ({
+  callOpenCodeEdit: jest.fn(),
+  callOpenCodeProviders: jest.fn(),
+  callOpenCodeSessionMessages: jest.fn().mockResolvedValue({ messages: [] })
+}));
+
 import {
   OpenCodeCellActions,
   setOpenCodeProviders,
@@ -330,17 +339,21 @@ describe('OpenCodeCellActions', () => {
     ).toBeNull();
   });
 
-  it('on a successful response, does NOT replace the cell source (renders to inline output instead)', () => {
+  it('on a successful response, does NOT replace the cell source and triggers a history refresh', () => {
     setOpenCodeProviders(null);
     const cell = makeFakeCell('x = 1');
     const actions = new OpenCodeCellActions(cell);
-    // Click once to create the inline prompt (so setOutput has a target).
+    // Click once to create the inline prompt (so the history refresh
+    // has a target and the cell source check has a baseline).
     Object.defineProperty(actions, 'parent', { value: cell, configurable: true });
     (actions as any).onAfterAttach({} as any);
     const btn = actions.node.querySelector('button') as HTMLButtonElement;
     btn.click();
 
-    // Simulate a successful response.
+    // The history refresh on show is async; spy on _refreshHistory to
+    // confirm it gets called (without depending on the network).
+    const refreshSpy = jest.spyOn(actions as any, '_refreshHistory');
+
     (actions as any)._handleResponse({
       ok: true,
       markdown: '# AI says hi\n\n```python\nprint("hi")\n```',
@@ -350,11 +363,8 @@ describe('OpenCodeCellActions', () => {
 
     // The cell source must remain unchanged.
     expect((cell as any).model.sharedModel.setSource).not.toHaveBeenCalled();
-    // The inline output area is now visible with the rendered markdown.
-    const output = cell.node.querySelector(
-      '.opencode-inline-prompt .opencode-inline-output'
-    ) as HTMLElement;
-    expect(output.style.display).toBe('block');
+    // A history refresh was triggered (to pick up the new assistant msg).
+    expect(refreshSpy).toHaveBeenCalledWith('foo.ipynb');
   });
 });
 
@@ -368,11 +378,12 @@ describe('OpenCodeInlinePrompt', () => {
       providers: null
     });
     expect(prompt.node.querySelector('textarea')).not.toBeNull();
-    // 3 buttons: 发送, 取消, and the output area close (✕).
-    expect(prompt.node.querySelectorAll('button').length).toBe(3);
+    // 2 buttons: 发送 and 取消 (no more output-area close button; the
+    // scrollable history area is the display).
+    expect(prompt.node.querySelectorAll('button').length).toBe(2);
   });
 
-  it('hides the output area by default; setOutput reveals it with rendered markdown', () => {
+  it('renders a history area; setMessages renders user text + assistant markdown and scrolls to bottom', () => {
     const cell = makeFakeCell('x = 1');
     const prompt = new OpenCodeInlinePrompt(cell, {
       onSubmit: jest.fn(),
@@ -380,22 +391,30 @@ describe('OpenCodeInlinePrompt', () => {
       disabled: false,
       providers: null
     });
-    const output = prompt.node.querySelector(
-      '.opencode-inline-prompt .opencode-inline-output'
+    const history = prompt.node.querySelector(
+      '.opencode-inline-prompt .opencode-inline-history'
     ) as HTMLElement;
-    expect(output).not.toBeNull();
-    expect(output.style.display).toBe('none');
+    expect(history).not.toBeNull();
+    // Initially empty (no messages yet).
+    expect(history.children.length).toBe(0);
 
-    prompt.setOutput('# Hello\n\n```python\nx = 1\n```');
-    expect(output.style.display).toBe('block');
-    const content = prompt.node.querySelector(
-      '.opencode-inline-prompt .opencode-inline-output-content'
-    ) as HTMLElement;
-    // marked is mocked to wrap the input in <mock>...</mock>.
-    expect(content.innerHTML).toContain('<mock>');
-    expect(content.innerHTML).toContain('# Hello');
-
-    prompt.hideOutput();
-    expect(output.style.display).toBe('none');
+    prompt.setMessages([
+      { role: 'user', content: 'fix the bug' },
+      {
+        role: 'assistant',
+        content: '# Here you go\n\n```python\nx = 1\n```'
+      }
+    ]);
+    expect(history.children.length).toBe(2);
+    const userMsg = history.querySelector('.opencode-msg-user') as HTMLElement;
+    const asstMsg = history.querySelector('.opencode-msg-assistant') as HTMLElement;
+    expect(userMsg).not.toBeNull();
+    // User messages are plain text (not rendered as HTML).
+    expect(userMsg.textContent).toBe('fix the bug');
+    expect(userMsg.innerHTML).not.toContain('<');
+    // Assistant messages are rendered as markdown via marked (mocked).
+    expect(asstMsg).not.toBeNull();
+    expect(asstMsg.innerHTML).toContain('<mock>');
+    expect(asstMsg.innerHTML).toContain('# Here you go');
   });
 });