ModelRouter/internal/lua/adapter_qwen38_test.go

package lua

import (
	"encoding/json"
	"strings"
	"testing"
)

// The fixtures below are REAL responses captured from
// https://discovery-api.intern-ai.org.cn/v1 with qwen3.8-27b — not hand-written
// approximations. Two of them exist only because the endpoint behaves in a way a
// stock OpenAI adapter gets wrong, and neither is guessable from the schema.

// reasoningDominatesTheBudget is the fact that made a dedicated adapter
// necessary: a one-sentence visual answer came back as completion=303 with
// reasoning=295. 97% of the budget went to thinking and only 8 tokens reached
// content. Handing the upstream's content straight through yields what looks
// like an empty answer from a perfectly healthy request.
const reasoningDominatesTheBudget = `{
  "choices": [{"index":0,"message":{"role":"assistant","content":"\n\n这张图是白色的。",
    "reasoning_content":"分析请求…分析图片…颜色是纯白"},"logprobs":null,
    "finish_reason":"stop"}],
  "created":1791179068,"model":"qwen3.8-27b-fp8","object":"chat.completion",
  "usage":{"prompt_tokens":125,"total_tokens":428,"completion_tokens":303,
    "prompt_tokens_details":null,
    "completion_tokens_details":{"reasoning_tokens":295}}
}`

// truncatedReasoningOnly is what a small max_tokens produces: HTTP 200, content
// null, finish_reason "length". It is NOT an upstream failure.
const truncatedReasoningOnly = `{
  "choices": [{"index":0,"message":{"role":"assistant","content":null,
    "reasoning_content":"思考过程：1. **分析请求**…图片的颜色是纯","refusal":null},
    "finish_reason":"length"}],
  "model":"qwen3.8-27b-fp8","object":"chat.completion",
  "usage":{"prompt_tokens":127,"total_tokens":190,"completion_tokens":63}
}`

const qwen38ToolCallResponse = `{
  "choices": [{"index":0,"message":{"role":"assistant","content":"",
    "reasoning_content":"用户询问北京天气。我需要调用 get_weather 函数，参数为城市 \"北京\"。",
    "tool_calls":[{"id":"chatcmpl-tool-afc0299b5810e044","type":"function",
      "function":{"name":"get_weather","arguments":"{\"city\": \"北京\"}"}}]},
    "finish_reason":"tool_calls"}],
  "model":"qwen3.8-27b-fp8",
  "usage":{"prompt_tokens":305,"total_tokens":353,"completion_tokens":48,
    "completion_tokens_details":{"reasoning_tokens":20}}
}`

func qwen38VM(t *testing.T) *VM {
	t.Helper()
	vm := NewVM(freshAdapterDir(t))
	if err := vm.Start(); err != nil {
		t.Fatalf("adapter VM: %v", err)
	}
	t.Cleanup(vm.Stop)
	return vm
}

func qwen38Response(t *testing.T, vm *VM, raw string) map[string]interface{} {
	t.Helper()
	out, err := vm.Transform("qwen38", "transform_response", raw)
	if err != nil {
		t.Fatalf("transform_response: %v", err)
	}
	var m map[string]interface{}
	if err := json.Unmarshal([]byte(out), &m); err != nil {
		t.Fatalf("adapter returned non-JSON: %v\n%s", err, out)
	}
	return m
}

func qwen38Stream(t *testing.T, vm *VM, raw string) map[string]interface{} {
	t.Helper()
	out, err := vm.Transform("qwen38", "transform_stream_chunk", raw)
	if err != nil {
		t.Fatalf("transform_stream_chunk: %v", err)
	}
	var m map[string]interface{}
	if err := json.Unmarshal([]byte(out), &m); err != nil {
		t.Fatalf("adapter returned non-JSON: %v\n%s", err, out)
	}
	return m
}

// TestQwen38KeepsReasoningSeparate is the adapter's reason for existing.
// Folding reasoning into content would render the model's private deliberation as
// its answer; dropping it makes a reasoning model look like it returned nothing.
func TestQwen38KeepsReasoningSeparate(t *testing.T) {
	vm := qwen38VM(t)
	u := qwen38Response(t, vm, reasoningDominatesTheBudget)

	content, _ := u["content"].(string)
	reasoning, _ := u["reasoning_content"].(string)

	if reasoning == "" {
		t.Fatal("reasoning_content was dropped — a reasoning model then looks like it returned nothing")
	}
	if strings.Contains(content, "分析请求") {
		t.Errorf("reasoning was folded into content: %q", content)
	}
	if !strings.Contains(content, "白色的") {
		t.Errorf("content = %q, want the answer text", content)
	}
	if reasoning == content {
		t.Error("content and reasoning_content are identical; they are disjoint upstream")
	}
}

// TestQwen38ReportsTruncationRatherThanFailing: content=null with
// finish_reason="length" is a truncated reasoning response, not a broken
// upstream. Losing the finish_reason makes it indistinguishable from a failure,
// and losing the partial reasoning throws away the only evidence of what happened.
func TestQwen38ReportsTruncationRatherThanFailing(t *testing.T) {
	vm := qwen38VM(t)
	u := qwen38Response(t, vm, truncatedReasoningOnly)

	if u["finish_reason"] != "length" {
		t.Errorf("finish_reason = %v, want length", u["finish_reason"])
	}
	if reasoning, _ := u["reasoning_content"].(string); reasoning == "" {
		t.Error("the partial reasoning was discarded")
	}
	if content, _ := u["content"].(string); content != "" {
		t.Errorf("content = %q, want empty string for a null upstream content", content)
	}
}

// TestQwen38CarriesReasoningTokensWithoutInflatingTotals: reasoning_tokens is a
// SUBSET of completion_tokens. Adding them double-counts every reasoning request,
// and billing prices the pair separately.
func TestQwen38CarriesReasoningTokensWithoutInflatingTotals(t *testing.T) {
	vm := qwen38VM(t)
	u := qwen38Response(t, vm, reasoningDominatesTheBudget)

	tu, ok := u["token_usage"].(map[string]interface{})
	if !ok {
		t.Fatalf("token_usage = %#v", u["token_usage"])
	}
	completion, _ := tu["completion"].(float64)
	total, _ := tu["total"].(float64)

	// The NESTING is the point, not the presence of the field.
	//
	// internal/gateway/chat.go reads reasoning in exactly one place:
	//   resp.TokenUsage.CompletionTokensDetails.ReasoningTokens
	// An adapter that emits reasoning_tokens at the TOP of token_usage type-checks
	// fine and is then dropped at the one spot that could have kept it — measured
	// on the live gateway: the model reported completion=88 and the gateway's
	// response carried reasoning=null.
	//
	// So this asserts the path, not merely that a number appears somewhere.
	det, ok := tu["completion_tokens_details"].(map[string]interface{})
	if !ok {
		t.Fatalf("token_usage has no completion_tokens_details: %#v — chat.go reads "+
			"reasoning from there and nowhere else, so the number is discarded", tu)
	}
	reasoning, has := det["reasoning_tokens"].(float64)
	if !has {
		t.Fatal("completion_tokens_details.reasoning_tokens missing — billing cannot price reasoning separately")
	}
	// Relational, not a presence check. The first version of this test only
	// asserted the field existed, and a mutation setting it to 0 passed: 0 is
	// present. The upstream value is known (295), so the exact number is
	// asserted — a zero silently misprices every reasoning request.
	if reasoning != 295 {
		t.Errorf("reasoning_tokens = %v, want 295 (the upstream value)", reasoning)
	}
	if reasoning >= completion {
		t.Errorf("reasoning_tokens (%v) must be a SUBSET of completion_tokens (%v)", reasoning, completion)
	}
	if completion != 303 || total != 428 {
		t.Errorf("usage was altered: completion=%v total=%v, want 303/428", completion, total)
	}
}

// TestQwen38DecodesToolCallArguments: the upstream sends arguments as a JSON
// STRING, like every other OpenAI-compatible endpoint. Passing it through
// undecoded leaves the caller to parse it.
func TestQwen38DecodesToolCallArguments(t *testing.T) {
	vm := qwen38VM(t)
	u := qwen38Response(t, vm, qwen38ToolCallResponse)

	tcs, ok := u["tool_calls"].([]interface{})
	if !ok || len(tcs) != 1 {
		t.Fatalf("tool_calls = %#v", u["tool_calls"])
	}
	tc, _ := tcs[0].(map[string]interface{})
	if tc["name"] != "get_weather" {
		t.Errorf("name = %v", tc["name"])
	}
	args, ok := tc["arguments"].(map[string]interface{})
	if !ok {
		t.Fatalf("arguments = %#v — the upstream sends a JSON string and it must be decoded", tc["arguments"])
	}
	if args["city"] != "北京" {
		t.Errorf("arguments.city = %v", args["city"])
	}
}

// TestQwen38StreamKeepsReasoningSeparate: measured 20 reasoning chunks against 1
// content chunk on a one-sentence answer. Folding them would make the client
// render the deliberation as the reply.
func TestQwen38StreamKeepsReasoningSeparate(t *testing.T) {
	vm := qwen38VM(t)
	const reasoningChunk = `{"choices":[{"index":0,"delta":{"reasoning_content":"思考过程：1. **分析请求**"},
	  "finish_reason":null}],"model":"qwen3.8-27b-fp8"}`
	const contentChunk = `{"choices":[{"index":0,"delta":{"content":"递归就是函数调用自身"},
	  "finish_reason":null}],"model":"qwen3.8-27b-fp8"}`
	const usageChunk = `{"choices":[],"usage":{"prompt_tokens":64,"total_tokens":132,
	  "completion_tokens":68,"completion_tokens_details":{"reasoning_tokens":62}}}`

	a := qwen38Stream(t, vm, reasoningChunk)
	b := qwen38Stream(t, vm, contentChunk)
	c := qwen38Stream(t, vm, usageChunk)

	if content, mixed := a["content"].(string); mixed && content != "" {
		t.Errorf("a reasoning chunk leaked into content: %q", content)
	}
	if reasoning, _ := a["reasoning_content"].(string); !strings.Contains(reasoning, "思考过程") {
		t.Errorf("reasoning chunk lost its text: %#v", a)
	}
	if content, _ := b["content"].(string); !strings.Contains(content, "递归") {
		t.Errorf("content chunk lost its text: %#v", b)
	}
	if c["usage"] == nil {
		t.Errorf("the terminal usage chunk was dropped: %#v", c)
		return
	}
	u, _ := c["usage"].(map[string]interface{})
	det, _ := u["completion_tokens_details"].(map[string]interface{})
	if det == nil || det["reasoning_tokens"] == nil {
		t.Errorf("usage chunk did not nest reasoning under completion_tokens_details: %#v — "+
			"chat.go reads it there, so a top-level field is discarded", u)
	}
}

// TestQwen38ReportsMediaFailureCode: a remote image URL times out upstream and
// comes back as media_fetch_failed. Surfacing only the message makes an image
// fetch problem look like a model problem.
func TestQwen38ReportsMediaFailureCode(t *testing.T) {
	vm := qwen38VM(t)
	body := `{"error":{"message":"image fetch timed out","type":"media_fetch_failed",
	  "param":null,"code":"media_fetch_failed","trace_id":"f3ca4aa"}}`
	reason, ok, err := vm.TransformError("qwen38", 400, body)
	if err != nil {
		t.Fatalf("TransformError: %v", err)
	}
	if !ok {
		t.Fatal("the media failure was swallowed")
	}
	if !strings.Contains(reason, "image fetch timed out") || !strings.Contains(reason, "media_fetch_failed") {
		t.Errorf("reason = %q; it must carry both the text and the code", reason)
	}
}

// TestQwen38InvalidKeyError: the endpoint answers a bad key with 401 and
// code "invalid_api_key". That one must NOT be annotated with its own code — it
// would render as "invalid API key (invalid_api_key)".
func TestQwen38InvalidKeyError(t *testing.T) {
	vm := qwen38VM(t)
	body := `{"error":{"message":"invalid API key","type":"invalid_request_error",
	  "param":null,"code":"invalid_api_key"}}`
	reason, ok, err := vm.TransformError("qwen38", 401, body)
	if err != nil || !ok {
		t.Fatalf("TransformError: ok=%v err=%v", ok, err)
	}
	if reason != "invalid API key" {
		t.Errorf("reason = %q, want the bare message", reason)
	}
}

// TestQwen38SuppliesReasoningOnToolCallTurns: the upstream requires an assistant
// message carrying tool_calls to echo reasoning_content. OpenAI-shaped clients
// never send it, so without this the SECOND turn of any tool-using conversation
// is rejected.
func TestQwen38SuppliesReasoningOnToolCallTurns(t *testing.T) {
	vm := qwen38VM(t)
	const req = `{"model":"qwen3.8-27b","messages":[
	  {"role":"user","content":"北京天气"},
	  {"role":"assistant","content":"","tool_calls":[{"id":"c1","type":"function",
	    "function":{"name":"get_weather","arguments":"{\"city\":\"北京\"}"}}]},
	  {"role":"tool","tool_call_id":"c1","content":"晴 25C"}]}`
	out, err := vm.Transform("qwen38", "transform_request", req)
	if err != nil {
		t.Fatalf("transform_request: %v", err)
	}
	var decoded map[string]interface{}
	if err := json.Unmarshal([]byte(out), &decoded); err != nil {
		t.Fatalf("request transform did not return JSON: %v\n%s", err, out)
	}
	msgs, _ := decoded["messages"].([]interface{})
	if len(msgs) < 2 {
		t.Fatalf("messages = %#v", decoded["messages"])
	}
	assistant, _ := msgs[1].(map[string]interface{})
	if _, ok := assistant["reasoning_content"]; !ok {
		t.Errorf("assistant turn with tool_calls has no reasoning_content; the upstream "+
			"rejects the next turn. Got %#v", assistant)
	}
}

// TestQwen38PassesImagesThrough: this adapter's job is reasoning handling, not
// media translation. A multimodal content array must survive untouched — an
// adapter that re-encodes it is the kind of change that silently breaks images
// while every text test still passes.
func TestQwen38PassesImagesThrough(t *testing.T) {
	vm := qwen38VM(t)
	const req = `{"model":"qwen3.8-27b","messages":[{"role":"user","content":[
	  {"type":"text","text":"这张图是什么颜色？"},
	  {"type":"image_url","image_url":{"url":"data:image/png;base64,iVBORw0KGgo="}}]}],
	  "max_tokens":600}`
	out, err := vm.Transform("qwen38", "transform_request", req)
	if err != nil {
		t.Fatalf("transform_request: %v", err)
	}
	if !strings.Contains(out, "image_url") || !strings.Contains(out, "data:image/png;base64,") {
		t.Errorf("the image part was lost or rewritten:\n%s", out)
	}
	if strings.Contains(out, "base64,iVBORw0KGgo=") == false {
		t.Errorf("the base64 payload was altered:\n%s", out)
	}
}