feat: 实现 executor 流式执行路径及完善 gateway 多格式 plan 构建

- Rust executor 新增流式 plan 支持，覆盖 openai/claude/gemini 的 chat/cli/video 格式
- Gateway 新增 finalize-sync、report-stream 端点及 stream report 模型
- 新增 video sync 操作(create/cancel/remix/delete)的 plan 构建
- 修正 OpenAI Responses(openai:cli) SSE 格式: 添加 event: 行、移除 [DONE] 哨兵
- 统一 OpenAI CLI normalizer 的 ID 生成方法

tests/api/handlers/base/test_cli_event_mixin.py

@@ -0,0 +1,38 @@
+from typing import Any
+
+from src.api.handlers.base.cli_event_mixin import CliEventMixin
+from src.api.handlers.base.stream_context import StreamContext
+
+
+class _DummyCliEventHandler(CliEventMixin):
+    request_id = "req-test"
+
+    def _process_event_data(
+        self,
+        ctx: StreamContext,
+        event_type: str,
+        data: dict[str, Any],
+    ) -> None:
+        del ctx, event_type, data
+
+
+def test_convert_sse_line_drops_done_for_openai_cli() -> None:
+    handler = _DummyCliEventHandler()
+    ctx = StreamContext(model="gpt-test", api_format="openai:cli")
+    ctx.client_api_format = "openai:cli"
+
+    lines, converted = handler._convert_sse_line(ctx, "data: [DONE]", [])
+
+    assert lines == []
+    assert converted == []
+
+
+def test_convert_sse_line_keeps_done_for_openai_chat() -> None:
+    handler = _DummyCliEventHandler()
+    ctx = StreamContext(model="gpt-test", api_format="openai:chat")
+    ctx.client_api_format = "openai:chat"
+
+    lines, converted = handler._convert_sse_line(ctx, "data: [DONE]", [])
+
+    assert lines == ["data: [DONE]"]
+    assert converted == []

tests/api/handlers/base/test_cli_sse_helpers.py

@@ -0,0 +1,32 @@
+import json
+
+from src.api.handlers.base.cli_sse_helpers import _format_converted_events_to_sse
+
+
+def test_format_converted_events_to_sse_uses_event_lines_for_openai_cli() -> None:
+    events = [
+        {
+            "type": "response.output_text.delta",
+            "item_id": "msg_123",
+            "output_index": 0,
+            "content_index": 0,
+            "delta": "Hi",
+            "logprobs": [],
+            "sequence_number": 1,
+        }
+    ]
+
+    lines = _format_converted_events_to_sse(events, "openai:cli")
+
+    assert lines == [
+        "event: response.output_text.delta\n"
+        f"data: {json.dumps(events[0], ensure_ascii=False)}\n"
+    ]
+
+
+def test_format_converted_events_to_sse_keeps_data_only_for_openai_chat() -> None:
+    events = [{"id": "chatcmpl-123", "object": "chat.completion.chunk", "choices": []}]
+
+    lines = _format_converted_events_to_sse(events, "openai:chat")
+
+    assert lines == [f"data: {json.dumps(events[0], ensure_ascii=False)}\n"]

tests/api/handlers/base/test_stream_processor_openai_cli_conversion.py

@@ -0,0 +1,88 @@
+import json
+from typing import Any
+from unittest.mock import AsyncMock
+
+import pytest
+
+from src.api.handlers.base.response_parser import ParsedResponse, ResponseParser, StreamStats
+from src.api.handlers.base.stream_context import StreamContext
+from src.api.handlers.base.stream_processor import StreamProcessor
+from src.core.api_format.conversion import register_default_normalizers
+
+
+class _DummyParser(ResponseParser):
+    def parse_sse_line(self, line: str, stats: StreamStats) -> Any | None:  # noqa: ANN401
+        return None
+
+    def parse_response(self, response: dict[str, Any], status_code: int) -> ParsedResponse:
+        return ParsedResponse(raw_response=response, status_code=status_code)
+
+    def extract_usage_from_response(self, response: dict[str, Any]) -> dict[str, int]:
+        return {}
+
+    def extract_text_content(self, response: dict[str, Any]) -> str:
+        return ""
+
+
+async def _empty_async_iter() -> Any:
+    if False:  # pragma: no cover
+        yield b""
+
+
+@pytest.mark.asyncio
+async def test_create_response_stream_converts_claude_to_openai_cli_with_event_lines() -> None:
+    register_default_normalizers()
+
+    ctx = StreamContext(model="test-model", api_format="openai:cli")
+    ctx.client_api_format = "openai:cli"
+    ctx.provider_api_format = "claude:chat"
+    ctx.needs_conversion = True
+
+    processor = StreamProcessor(request_id="test-request", default_parser=_DummyParser())
+
+    response_ctx = AsyncMock()
+    response_ctx.__aexit__ = AsyncMock(return_value=None)
+
+    message_start = {
+        "type": "message_start",
+        "message": {
+            "id": "msg_1",
+            "type": "message",
+            "role": "assistant",
+            "model": "claude-test",
+            "content": [],
+            "stop_reason": None,
+            "stop_sequence": None,
+        },
+    }
+    content_delta = {
+        "type": "content_block_delta",
+        "index": 0,
+        "delta": {"type": "text_delta", "text": "Hi"},
+    }
+
+    prefetched_chunks = [
+        b"event: message_start\n",
+        f"data: {json.dumps(message_start)}\n".encode("utf-8"),
+        b"\n",
+        f"data: {json.dumps(content_delta)}\n".encode("utf-8"),
+        b"\n",
+    ]
+
+    out = b"".join(
+        [
+            chunk
+            async for chunk in processor.create_response_stream(
+                ctx,
+                byte_iterator=_empty_async_iter(),
+                response_ctx=response_ctx,
+                prefetched_chunks=prefetched_chunks,
+            )
+        ]
+    )
+
+    text = out.decode("utf-8")
+    assert "event: response.output_item.added\n" in text
+    assert "event: response.content_part.added\n" in text
+    assert "event: response.output_text.delta\n" in text
+    assert "data: [DONE]" not in text