feat: async + SSE message flow with interactive permission/question UI

Replace the synchronous /edit (wait for full markdown response) with an async + SSE flow per demo.html so the user sees text stream in real-time and can interact with permission/question events the agent raises. Backend ------- - EditHandler now calls OpenCode /session/:id/prompt_async and returns immediately with {ok, sessionId, notebookPath}; the LLM reply is no longer embedded in this response. - New GlobalEventHandler proxies OpenCode /global/event as text/event-stream. Server forwards ALL events; the client filters. A too-eager server-side ?session= filter was silently dropping events the client would have accepted, so it was removed. - New PermissionReplyHandler + QuestionReplyHandler forward user replies (once/always/reject and freeform answer) back to OpenCode Serve at /session/:sid/permissions/:permId and /session/:sid/question/:qId/reply. - OpenCodeClient gains send_message_async(), stream_global_events() (async generator over the SSE feed via tornado streaming_callback), reply_permission() and reply_question(). Legacy send_message_sync removed. Frontend -------- - subscribeOpenCodeEvents() opens a fetch+reader SSE client (XSRF token injected from serverSettings); AbortController-backed close() is idempotent. - OpenCodeInlinePrompt.applyEvent() routes events into the streaming UI: text delta -> assistant message (re-rendered as markdown on every delta so the user sees formatted <pre><code> blocks in real-time, not raw fence source); reasoning/tool/permission/question get collapsible details blocks. session.idle resets stream pointers and fires onStreamEnd. - Permission/question blocks render real interactive UI: three buttons (once/always/reject) for permission, a text input + submit for question. Click handlers post through the new API routes and show success/failure status in place. - Centralized idle detection (4 shapes: top-level + payload-nested x {session.idle, session.status/idle}) inside the prompt; cell action reacts via onStreamEnd callback rather than re-parsing event types. - System / workspace / pty / lsp / mcp / installation events AND session-level control events (agent.switched, model.switched, file.edited) are not rendered in the frontend. Tests ----- - 52 backend pytest (was 43) - 58 frontend jest (was 46) design.md section 3 updated for the new async /edit response shape and the new GET /events SSE endpoint. Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-27 17:00:16 +08:00
parent 0bd04a825d
commit 4f8bbaf09f
12 changed files with 2532 additions and 243 deletions
@@ -98,28 +98,30 @@ async def test_auth_absent_when_no_password(base_config: OpenCodeConfig) -> None


@pytest.mark.asyncio
-async def test_send_message_sync_includes_model_when_provider_and_model_given(
+async def test_send_message_async_includes_model_when_provider_and_model_given(
    base_config: OpenCodeConfig,
 ) -> None:
+    """send_message_async posts to /prompt_async with provider/model when both set."""
    client, mock = _make_client(base_config, [(200, {"done": True})])
    parts = [{"type": "text", "text": "hello"}]
-    result = await client.send_message_sync("s1", parts, provider_id="p1", model_id="m1")
-    assert result == {"done": True}
+    result = await client.send_message_async("s1", parts, provider_id="p1", model_id="m1")
+    assert result is None
    call = mock.calls[0]
-    assert call["request"].url == "http://127.0.0.1:4096/session/s1/message"
+    assert call["request"].url == "http://127.0.0.1:4096/session/s1/prompt_async"
+    assert call["request"].method == "POST"
    body = json.loads(call["request"].body.decode("utf-8"))
    assert body["parts"] == parts
    assert body["model"] == {"providerID": "p1", "modelID": "m1"}


@pytest.mark.asyncio
-async def test_send_message_sync_omits_model_when_provider_or_model_missing(
+async def test_send_message_async_omits_model_when_provider_or_model_missing(
    base_config: OpenCodeConfig,
 ) -> None:
    client, mock = _make_client(base_config, [(200, {"done": True})])
    parts = [{"type": "text", "text": "hello"}]
-    result = await client.send_message_sync("s1", parts)
-    assert result == {"done": True}
+    result = await client.send_message_async("s1", parts)
+    assert result is None
    call = mock.calls[0]
    body = json.loads(call["request"].body.decode("utf-8"))
    assert body["parts"] == parts
@@ -127,7 +129,7 @@ async def test_send_message_sync_omits_model_when_provider_or_model_missing(


@pytest.mark.asyncio
-async def test_send_message_sync_includes_system_when_provided() -> None:
+async def test_send_message_async_includes_system_when_provided() -> None:
    """system param is forwarded into the request body when not None."""
    config = OpenCodeConfig(
        url="http://x:1", user="u", password="", request_timeout_seconds=120
@@ -136,7 +138,7 @@ async def test_send_message_sync_includes_system_when_provided() -> None:
    mock.responses.append((200, {"info": {}, "parts": []}))
    client = OpenCodeClient(config, http_client=mock)

-    await client.send_message_sync("sid", [{"type": "text", "text": "hi"}], system="be brief")
+    await client.send_message_async("sid", [{"type": "text", "text": "hi"}], system="be brief")

    assert len(mock.calls) == 1
    body = json.loads(mock.calls[0]["request"].body.decode("utf-8"))
@@ -144,6 +146,83 @@ async def test_send_message_sync_includes_system_when_provided() -> None:
    assert body["parts"] == [{"type": "text", "text": "hi"}]


+@pytest.mark.asyncio
+async def test_stream_global_events_yields_parsed_events(
+    base_config: OpenCodeConfig,
+) -> None:
+    """stream_global_events yields one dict per `data: {...}` SSE block."""
+
+    class _StreamingMock(MockHTTPClient):
+        async def fetch(self, request, **kwargs):
+            self.calls.append({"request": request, "kwargs": kwargs})
+            # Simulate OpenCode's /global/event: three events back-to-back.
+            chunks = [
+                b"data: {\"type\": \"session.next.text.delta\", \"properties\": "
+                b"{\"sessionID\": \"s1\", \"delta\": \"hello \"}}\n\n",
+                b"data: {\"type\": \"session.next.text.delta\", \"properties\": "
+                b"{\"sessionID\": \"s1\", \"delta\": \"world\"}}\n\n",
+                b"data: {\"type\": \"session.idle\", \"properties\": "
+                b"{\"sessionID\": \"s1\"}}\n\n",
+            ]
+            # streaming_callback now lives on the HTTPRequest (per tornado
+            # API — fetch() rejects kwargs when an HTTPRequest is passed).
+            cb = getattr(request, "streaming_callback", None)
+            if cb is not None:
+                for c in chunks:
+                    cb(c)
+            # Empty body, code 200 to terminate normally.
+            return tornado.httpclient.HTTPResponse(
+                request=request,
+                code=200,
+                headers=tornado.httputil.HTTPHeaders(),
+                buffer=BytesIO(b""),
+            )
+
+    mock = _StreamingMock()
+    client = OpenCodeClient(base_config, http_client=mock)
+
+    events = []
+    async for ev in client.stream_global_events():
+        events.append(ev)
+
+    assert len(events) == 3
+    assert events[0]["type"] == "session.next.text.delta"
+    assert events[0]["properties"]["delta"] == "hello "
+    assert events[1]["properties"]["delta"] == "world"
+    assert events[2]["type"] == "session.idle"
+    # Stream used the SSE accept header and no timeout.
+    call = mock.calls[0]
+    assert call["kwargs"] == {"raise_error": False}
+    assert call["request"].method == "GET"
+    assert call["request"].url == "http://127.0.0.1:4096/global/event"
+    assert call["request"].request_timeout == 0
+    assert call["request"].headers.get("Accept") == "text/event-stream"
+    assert call["request"].streaming_callback is not None
+
+
+def test_parse_sse_block_handles_concatenated_data_lines() -> None:
+    """Multi-line `data:` blocks are joined with \n (per SSE spec)."""
+    parsed = OpenCodeClient._parse_sse_block(
+        "data: {\"a\": 1,\ndata:  \"b\": 2}"
+    )
+    assert parsed == {"a": 1, "b": 2}
+
+
+def test_parse_sse_block_ignores_non_data_fields() -> None:
+    parsed = OpenCodeClient._parse_sse_block("event: ping\ndata: {\"k\": \"v\"}\n\n")
+    assert parsed == {"k": "v"}
+
+
+def test_parse_sse_block_returns_none_on_empty() -> None:
+    assert OpenCodeClient._parse_sse_block("") is None
+    assert OpenCodeClient._parse_sse_block("event: ping\n\n") is None
+    assert OpenCodeClient._parse_sse_block(": heartbeat\n\n") is None
+
+
+def test_parse_sse_block_returns_none_on_bad_json() -> None:
+    assert OpenCodeClient._parse_sse_block("data: not-json\n\n") is None
+
+
@pytest.mark.asyncio
 async def test_delete_session_returns_bool_by_status(base_config: OpenCodeConfig) -> None:
    client, mock = _make_client(base_config, [(200, True), (404, False)])
@@ -154,6 +233,39 @@ async def test_delete_session_returns_bool_by_status(base_config: OpenCodeConfig
    assert mock.calls[0]["request"].url == "http://127.0.0.1:4096/session/s1"


+@pytest.mark.asyncio
+async def test_reply_permission_posts_response(base_config: OpenCodeConfig) -> None:
+    """reply_permission forwards the response string to /session/:id/permissions/:permId."""
+    client, mock = _make_client(base_config, [(200, True)])
+    ok = await client.reply_permission("s1", "perm-1", "once")
+    assert ok is True
+    call = mock.calls[0]
+    assert call["request"].url == "http://127.0.0.1:4096/session/s1/permissions/perm-1"
+    assert call["request"].method == "POST"
+    body = json.loads(call["request"].body.decode("utf-8"))
+    assert body == {"response": "once"}
+
+
+@pytest.mark.asyncio
+async def test_reply_permission_returns_false_on_404(
+    base_config: OpenCodeConfig,
+) -> None:
+    client, mock = _make_client(base_config, [(404, False)])
+    assert await client.reply_permission("s1", "perm-1", "reject") is False
+
+
+@pytest.mark.asyncio
+async def test_reply_question_posts_answer(base_config: OpenCodeConfig) -> None:
+    """reply_question forwards the answer to /session/:id/question/:qid/reply."""
+    client, mock = _make_client(base_config, [(200, True)])
+    ok = await client.reply_question("s1", "q-7", "use 3.12")
+    assert ok is True
+    call = mock.calls[0]
+    assert call["request"].url == "http://127.0.0.1:4096/session/s1/question/q-7/reply"
+    body = json.loads(call["request"].body.decode("utf-8"))
+    assert body == {"answer": "use 3.12"}
+
+
@pytest.mark.asyncio
 async def test_non_2xx_response_raises_with_body(base_config: OpenCodeConfig) -> None:
    client, mock = _make_client(base_config, [(500, {"error": "boom"})])
@@ -12,10 +12,6 @@ class FakeOpenCodeClient:
        self.session_id = "fake-session-123"
        self.health_response = {"healthy": True, "version": "0.1.0"}
        self.providers_response = {"providers": [{"id": "anthropic", "models": [{"id": "claude"}]}]}
-        self.message_response = {
-            "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 = [
@@ -45,9 +41,13 @@ class FakeOpenCodeClient:
        self.calls.append(("create_session", title))
        return {"id": self.session_id, "title": title}

-    async def send_message_sync(self, session_id, parts, provider_id=None, model_id=None, system=None):
-        self.calls.append(("send_message_sync", session_id, parts, system))
-        return self.message_response
+    async def send_message_async(
+        self, session_id, parts, provider_id=None, model_id=None, system=None
+    ):
+        self.calls.append(
+            ("send_message_async", session_id, parts, system, provider_id, model_id)
+        )
+        return None

    async def delete_session(self, session_id):
        self.calls.append(("delete_session", session_id))
@@ -57,6 +57,19 @@ class FakeOpenCodeClient:
        self.calls.append(("list_session_messages", session_id))
        return self.messages_response

+    async def reply_permission(self, session_id, permission_id, response):
+        self.calls.append(("reply_permission", session_id, permission_id, response))
+        return True
+
+    async def reply_question(self, session_id, question_id, answer):
+        self.calls.append(("reply_question", session_id, question_id, answer))
+        return True
+
+    async def stream_global_events(self):
+        """Async generator — tests can monkey-patch this to control the stream."""
+        if False:  # pragma: no cover - never executed, just makes this an asyncgen
+            yield {}
+

 class FakeSessionManager:
    """Drop-in replacement for SessionManager with recording."""
@@ -131,6 +144,12 @@ async def test_providers_handler(monkeypatch, jp_fetch):


 async def test_edit_handler(monkeypatch, jp_fetch):
+    """POST /opencode-bridge/edit fires prompt_async and returns sessionId only.
+
+    The async path returns immediately with `{ok, sessionId, notebookPath}` —
+    the actual LLM response is consumed via the /events SSE endpoint, not
+    embedded in this response.
+    """
    fake = FakeOpenCodeClient()
    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)

@@ -159,31 +178,68 @@ async def test_edit_handler(monkeypatch, jp_fetch):
    )
    assert response.code == 200
    payload = json.loads(response.body)
-    assert payload["ok"] is True
-    # Server now returns the AI reply as raw markdown (```fences``` kept
-    # so the frontend marked.parse renders code blocks).
-    assert payload["markdown"] == "def foo():\n    return 42"
-    assert payload["sessionId"] == "fake-session-123"
-    assert payload["notebookPath"] == "test.ipynb"
+    assert payload == {
+        "ok": True,
+        "sessionId": "fake-session-123",
+        "notebookPath": "test.ipynb",
+    }
+    # Async path: no `markdown` field. The LLM reply is consumed via SSE.
+    assert "markdown" not in payload

-    # Session manager was used, not direct create/delete on client
+    # Session manager was used (not direct create/delete on client).
    call_names = [c[0] for c in fake.calls]
    assert "create_session" not in call_names
    assert "delete_session" not in call_names
-    assert "send_message_sync" in call_names
+    assert "send_message_async" in call_names
+    assert "send_message_sync" not in call_names  # legacy sync path is gone

-    # send_message_sync received the session ID from the manager
-    send_call = [c for c in fake.calls if c[0] == "send_message_sync"][0]
+    # send_message_async received the session ID from the manager.
+    send_call = [c for c in fake.calls if c[0] == "send_message_async"][0]
    assert send_call[1] == "fake-session-123"
-    # system prompt was passed (v3+ allows markdown/fences in the reply)
+    # system prompt was passed.
    assert "你是一个代码助手" in send_call[3]

-    # SessionManager.get_or_create was called with the notebook path
+    # SessionManager.get_or_create was called with the notebook path.
    sm_call_names = [c[0] for c in fake_sm.calls]
    assert sm_call_names == ["get_or_create"]
    assert fake_sm.calls[0][1] == "test.ipynb"


+async def test_edit_handler_includes_model_when_provider_and_model_given(
+    monkeypatch, jp_fetch
+):
+    """providerId/modelId are forwarded into the async send body when both set."""
+    fake = FakeOpenCodeClient()
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+    monkeypatch.setattr(
+        "opencode_bridge.routes.get_session_manager",
+        lambda h: FakeSessionManager(),
+    )
+
+    body = json.dumps({
+        "prompt": "x",
+        "context": {
+            "notebookPath": "n.ipynb",
+            "cellId": "c",
+            "language": "python",
+            "cellIndex": 0,
+            "totalCells": 1,
+            "source": "",
+            "previousCode": None,
+            "error": None,
+        },
+        "providerId": "anthropic",
+        "modelId": "claude-sonnet-4-20250514",
+    })
+    response = await jp_fetch("opencode-bridge", "edit", method="POST", body=body)
+    assert response.code == 200
+
+    send_call = [c for c in fake.calls if c[0] == "send_message_async"][0]
+    # (send_message_async, sid, parts, system, provider_id, model_id)
+    assert send_call[4] == "anthropic"
+    assert send_call[5] == "claude-sonnet-4-20250514"
+
+
 async def test_session_list_handler(monkeypatch, jp_fetch):
    fake_sm = FakeSessionManager()
    fake_sm._sessions = {
@@ -287,3 +343,119 @@ async def test_session_release_handler(monkeypatch, jp_fetch):
    assert payload["notebookPath"] == "foo.ipynb"
    assert payload["deleted"] is True
    assert ("release", "foo.ipynb") in fake_sm.calls
+
+
+async def test_permission_reply_forwards_response(monkeypatch, jp_fetch):
+    """POST /opencode-bridge/permissions/:permId?session=:sid forwards to client."""
+    fake = FakeOpenCodeClient()
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+
+    response = await jp_fetch(
+        "opencode-bridge", "permissions", "perm-42",
+        method="POST",
+        params={"session": "ses-1"},
+        body=json.dumps({"response": "once"}),
+    )
+    assert response.code == 200
+    payload = json.loads(response.body)
+    assert payload == {
+        "ok": True,
+        "permissionId": "perm-42",
+        "response": "once",
+    }
+    assert ("reply_permission", "ses-1", "perm-42", "once") in fake.calls
+
+
+async def test_permission_reply_rejects_invalid_response(monkeypatch, jp_fetch):
+    """response must be one of once/always/reject — 400 otherwise."""
+    fake = FakeOpenCodeClient()
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+
+    with pytest.raises(tornado.httpclient.HTTPClientError) as exc_info:
+        await jp_fetch(
+            "opencode-bridge", "permissions", "perm-1",
+            method="POST",
+            params={"session": "ses-1"},
+            body=json.dumps({"response": "yes"}),
+        )
+    assert exc_info.value.code == 400
+    assert "yes" not in fake.calls and fake.calls == []
+
+
+async def test_permission_reply_requires_session(monkeypatch, jp_fetch):
+    """Missing ?session=... is a 400."""
+    fake = FakeOpenCodeClient()
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+    with pytest.raises(tornado.httpclient.HTTPClientError) as exc_info:
+        await jp_fetch(
+            "opencode-bridge", "permissions", "perm-1",
+            method="POST",
+            body=json.dumps({"response": "once"}),
+        )
+    assert exc_info.value.code == 400
+
+
+async def test_question_reply_forwards_answer(monkeypatch, jp_fetch):
+    fake = FakeOpenCodeClient()
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+
+    response = await jp_fetch(
+        "opencode-bridge", "questions", "q-7", "reply",
+        method="POST",
+        params={"session": "ses-2"},
+        body=json.dumps({"answer": "use Python 3.12"}),
+    )
+    assert response.code == 200
+    payload = json.loads(response.body)
+    assert payload == {"ok": True, "questionId": "q-7"}
+    assert ("reply_question", "ses-2", "q-7", "use Python 3.12") in fake.calls
+
+
+async def test_question_reply_rejects_empty_answer(monkeypatch, jp_fetch):
+    fake = FakeOpenCodeClient()
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+    with pytest.raises(tornado.httpclient.HTTPClientError) as exc_info:
+        await jp_fetch(
+            "opencode-bridge", "questions", "q-1", "reply",
+            method="POST",
+            params={"session": "ses-1"},
+            body=json.dumps({"answer": "   "}),
+        )
+    assert exc_info.value.code == 400
+    assert fake.calls == []
+
+
+async def test_global_event_handler_forwards_all_events_unfiltered(
+    monkeypatch, jp_fetch
+):
+    """Server-side SSE proxy must NOT filter by session — it forwards
+    everything so the client can decide. (Previously a too-eager server
+    filter silently dropped events the client would have accepted.)
+
+    We mock stream_global_events to push three events with different
+    sessionID shapes (one matching, one not, one missing). The proxy
+    should pass all three through as data: lines.
+    """
+    fake = FakeOpenCodeClient()
+
+    async def fake_stream():
+        yield {"type": "session.next.text.delta", "properties": {"sessionID": "ses-1", "delta": "A"}}
+        yield {"type": "session.next.text.delta", "properties": {"sessionID": "ses-OTHER", "delta": "B"}}
+        yield {"type": "server.connected", "properties": {}}
+
+    fake.stream_global_events = fake_stream
+    monkeypatch.setattr("opencode_bridge.routes.make_client", lambda h: fake)
+
+    # Use ?session=ses-1 to confirm the param is accepted but doesn't filter.
+    response = await jp_fetch(
+        "opencode-bridge", "events",
+        params={"session": "ses-1"},
+    )
+    assert response.code == 200
+    body = response.body.decode("utf-8")
+    # All three events should appear in the body, regardless of sessionID.
+    assert '"delta": "A"' in body
+    assert '"delta": "B"' in body
+    assert '"server.connected"' in body
+    # The body should use the SSE format: each event as a `data:` line.
+    assert body.count("data: ") == 3