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>

opencode_bridge/tests/test_routes.py

@@ -1,5 +1,8 @@
 import json
 
+import pytest
+import tornado.httpclient
+
 
 class FakeOpenCodeClient:
     """Drop-in replacement for OpenCodeClient with recording + canned responses."""
@@ -13,6 +16,18 @@ class FakeOpenCodeClient:
             "info": {"id": "msg-1"},
             "parts": [{"type": "text", "text": "def foo():\n    return 42\n"}],
         }
+        # Canned session-messages list response (list_session_messages).
+        # Default: one user + one assistant message, mixed text parts.
+        self.messages_response = [
+            {
+                "info": {"role": "user", "id": "m1"},
+                "parts": [{"type": "text", "text": "fix the bug"}],
+            },
+            {
+                "info": {"role": "assistant", "id": "m2"},
+                "parts": [{"type": "text", "text": "```python\nx = 1\n```"}],
+            },
+        ]
 
     @property
     def endpoint(self):
@@ -38,6 +53,10 @@ class FakeOpenCodeClient:
         self.calls.append(("delete_session", session_id))
         return True
 
+    async def list_session_messages(self, session_id):
+        self.calls.append(("list_session_messages", session_id))
+        return self.messages_response
+
 
 class FakeSessionManager:
     """Drop-in replacement for SessionManager with recording."""
@@ -50,6 +69,12 @@ class FakeSessionManager:
         self.calls.append(("get_or_create", notebook_path))
         return self._session_id
 
+    def peek(self, notebook_path: str):
+        # Mirror SessionManager.peek: return the session id without
+        # creating one. None means "no session yet" (used by the no-session
+        # test to short-circuit the history route).
+        return self._session_id or None
+
     async def release(self, notebook_path: str) -> bool:
         self.calls.append(("release", notebook_path))
         return True
@@ -177,6 +202,71 @@ async def test_session_list_handler(monkeypatch, jp_fetch):
     assert paths == {"foo.ipynb", "bar.ipynb"}
 
 
+async def test_session_messages_handler_returns_empty_when_no_session(
+    monkeypatch, jp_fetch
+) -> None:
+    # No session registered for this notebook -> handler returns
+    # {"messages": []} WITHOUT calling OpenCodeClient (peek short-circuits).
+    fake = FakeOpenCodeClient()
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+
+    fake_sm = FakeSessionManager(session_id="")
+    monkeypatch.setattr(
+        "opencode_bridge.routes.get_session_manager", lambda h: fake_sm
+    )
+
+    response = await jp_fetch(
+        "opencode-bridge", "session-messages",
+        method="GET",
+        params={"notebook": "fresh.ipynb"},
+    )
+    assert response.code == 200
+    payload = json.loads(response.body)
+    assert payload == {"messages": []}
+    # No OpenCode call was made.
+    assert all(c[0] != "list_session_messages" for c in fake.calls)
+
+
+async def test_session_messages_handler_projects_opencode_messages(
+    monkeypatch, jp_fetch
+) -> None:
+    fake = FakeOpenCodeClient()
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+
+    fake_sm = FakeSessionManager(session_id="fake-session-123")
+    monkeypatch.setattr(
+        "opencode_bridge.routes.get_session_manager", lambda h: fake_sm
+    )
+
+    response = await jp_fetch(
+        "opencode-bridge", "session-messages",
+        method="GET",
+        params={"notebook": "test.ipynb"},
+    )
+    assert response.code == 200
+    payload = json.loads(response.body)
+    assert payload == {
+        "messages": [
+            {"role": "user", "content": "fix the bug"},
+            {"role": "assistant", "content": "```python\nx = 1\n```"},
+        ]
+    }
+    # The OpenCode client was called with the session id from the manager.
+    assert ("list_session_messages", "fake-session-123") in fake.calls
+
+
+async def test_session_messages_handler_requires_notebook(
+    monkeypatch, jp_fetch
+) -> None:
+    fake = FakeOpenCodeClient()
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+    # jp_fetch raises HTTPClientError on 4xx; assert the handler 400s
+    # (the body would contain "missing 'notebook' query parameter").
+    with pytest.raises(tornado.httpclient.HTTPClientError) as exc_info:
+        await jp_fetch("opencode-bridge", "session-messages", method="GET")
+    assert exc_info.value.code == 400
+
+
 async def test_session_release_handler(monkeypatch, jp_fetch):
     fake = FakeOpenCodeClient()
     monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)