feat: 补齐三个方向的流式工具调用；Anthropic 上游走 x-api-key；禁用模型真正下架
- 流式转换补齐 chat→responses / responses→chat / messages→responses 的工具调用（此前只转文本，SDK 客户端拿不到 tool_calls）；completed 事件携带完整 output 数组 - Anthropic 协议上游同时发 x-api-key（官方 API 不接受 API key 走 Bearer）并透传 anthropic-beta - 请求侧校验模型存在且启用：禁用模型 404 model_not_found，不再只是从 /v1/models 消失、实际照发照扣费；空模型名 400 - 模型在请求中途被删时按 0 记账留痕，不再按硬编码示例价扣用户的钱 - finishUsage 新增一行式请求日志（trace/user/model/channel/tokens/cost/status/latency），记账是异步的，日志是唯一即时排障依据
This commit is contained in:
Sakurasan committed
1 parent
984a31cbc5
commit
d6db0f8162
6 files changed
+485
-31
No files matched your search
@@ -1022,3 +1022,117 @@ func TestMessagesToChatReqToolOrder(t *testing.T) {
|
||||
t.Fatalf("msg[0] missing tool_calls: %s", out)
|
||||
}
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// 流式工具调用：三个此前缺失的方向（chat→responses / responses→chat / messages→responses）
|
||||
|
||||
func TestStreamChatToResponsesToolCall(t *testing.T) {
|
||||
tf := newChatToResponses().line
|
||||
out := feedLines(t, tf, []string{
|
||||
`data: {"id":"chatcmpl-1","object":"chat.completion.chunk","model":"gpt-4o","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}` + "\n\n",
|
||||
`data: {"id":"chatcmpl-1","object":"chat.completion.chunk","model":"gpt-4o","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_9","type":"function","function":{"name":"get_weather","arguments":""}}]},"finish_reason":null}]}` + "\n\n",
|
||||
`data: {"id":"chatcmpl-1","object":"chat.completion.chunk","model":"gpt-4o","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"city\":\"北京\"}"}}]},"finish_reason":null}]}` + "\n\n",
|
||||
`data: {"id":"chatcmpl-1","object":"chat.completion.chunk","model":"gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}` + "\n\n",
|
||||
`data: {"id":"chatcmpl-1","object":"chat.completion.chunk","model":"gpt-4o","choices":[],"usage":{"prompt_tokens":10,"completion_tokens":5}}` + "\n\n",
|
||||
"data: [DONE]\n\n",
|
||||
})
|
||||
if !strings.Contains(out, "event: response.output_item.added") || !strings.Contains(out, `"name":"get_weather"`) {
|
||||
t.Fatalf("missing function_call item added: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, "event: response.function_call_arguments.delta") {
|
||||
t.Fatalf("missing arguments delta: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, "event: response.output_item.done") {
|
||||
t.Fatalf("missing output_item.done: %s", out)
|
||||
}
|
||||
// completed 的 output 数组要携带完整参数，客户端不依赖事件也能拿到最终形态
|
||||
if !strings.Contains(out, `"call_id":"call_9"`) {
|
||||
t.Fatalf("missing call_id: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, `\"city\":\"北京\"`) {
|
||||
t.Fatalf("missing accumulated arguments in completed output: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, `"usage":{"completion_tokens":5,"prompt_tokens":10}`) {
|
||||
t.Fatalf("missing usage in completed: %s", out)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStreamResponsesToChatToolCall(t *testing.T) {
|
||||
tf := newResponsesToChat().line
|
||||
out := feedLines(t, tf, []string{
|
||||
"event: response.created\n",
|
||||
`data: {"type":"response.created","response":{"id":"resp_1","model":"gpt-4o"}}` + "\n\n",
|
||||
"event: response.output_item.added\n",
|
||||
`data: {"type":"response.output_item.added","output_index":1,"item":{"type":"function_call","id":"fc_1","call_id":"call_9","name":"get_weather","arguments":""}}` + "\n\n",
|
||||
"event: response.function_call_arguments.delta\n",
|
||||
`data: {"type":"response.function_call_arguments.delta","item_id":"fc_1","delta":"{\"city\":\"北京\"}"}` + "\n\n",
|
||||
"event: response.completed\n",
|
||||
`data: {"type":"response.completed","response":{"id":"resp_1","status":"completed","usage":{"input_tokens":7,"output_tokens":8}}}` + "\n\n",
|
||||
})
|
||||
if !strings.Contains(out, `"tool_calls"`) || !strings.Contains(out, `"name":"get_weather"`) {
|
||||
t.Fatalf("missing tool_calls chunk: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, `"arguments":"{\"city\":\"北京\"}"`) {
|
||||
t.Fatalf("missing arguments delta chunk: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, `"finish_reason":"tool_calls"`) {
|
||||
t.Fatalf("finish_reason should be tool_calls: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, `"usage":{"input_tokens":7,"output_tokens":8}`) {
|
||||
t.Fatalf("missing usage chunk: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, "data: [DONE]") {
|
||||
t.Fatalf("missing [DONE]: %s", out)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStreamMessagesToResponsesToolCall(t *testing.T) {
|
||||
tf := newMessagesToResponses().line
|
||||
out := feedLines(t, tf, []string{
|
||||
"event: message_start\n",
|
||||
`data: {"type":"message_start","message":{"id":"msg_1","model":"claude-sonnet-5"}}` + "\n\n",
|
||||
"event: content_block_start\n",
|
||||
`data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_1","name":"get_weather"}}` + "\n\n",
|
||||
"event: content_block_delta\n",
|
||||
`data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"city\":\"北京\"}"}}` + "\n\n",
|
||||
"event: content_block_stop\n",
|
||||
`data: {"type":"content_block_stop","index":0}` + "\n\n",
|
||||
"event: message_delta\n",
|
||||
`data: {"type":"message_delta","delta":{"stop_reason":"tool_use"},"usage":{"input_tokens":10,"output_tokens":5}}` + "\n\n",
|
||||
"event: message_stop\n",
|
||||
`data: {"type":"message_stop"}` + "\n\n",
|
||||
})
|
||||
if !strings.Contains(out, "event: response.output_item.added") || !strings.Contains(out, `"call_id":"toolu_1"`) {
|
||||
t.Fatalf("missing function_call item added: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, "event: response.function_call_arguments.delta") {
|
||||
t.Fatalf("missing arguments delta: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, "event: response.output_item.done") {
|
||||
t.Fatalf("missing output_item.done: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, `"call_id":"toolu_1"`) || !strings.Contains(out, `"arguments":"{\"city\":\"北京\"}"`) {
|
||||
t.Fatalf("completed output array missing function_call with full arguments: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, `"usage":{"input_tokens":10,"output_tokens":5}`) {
|
||||
t.Fatalf("missing usage in completed: %s", out)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStreamResponsesToChatTextStillWorks(t *testing.T) {
|
||||
tf := newResponsesToChat().line
|
||||
out := feedLines(t, tf, []string{
|
||||
"event: response.created\n",
|
||||
`data: {"type":"response.created","response":{"id":"resp_1","model":"gpt-4o"}}` + "\n\n",
|
||||
"event: response.output_text.delta\n",
|
||||
`data: {"type":"response.output_text.delta","delta":"hi"}` + "\n\n",
|
||||
"event: response.completed\n",
|
||||
`data: {"type":"response.completed","response":{"id":"resp_1","status":"completed","usage":{"input_tokens":1,"output_tokens":1}}}` + "\n\n",
|
||||
})
|
||||
if !strings.Contains(out, `"content":"hi"`) {
|
||||
t.Fatalf("missing text chunk: %s", out)
|
||||
}
|
||||
if !strings.Contains(out, `"finish_reason":"stop"`) {
|
||||
t.Fatalf("missing finish chunk: %s", out)
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user