fix(tokens): 流式统计改用上游真实 usage，图片不再记 token

两处 token 单位错误，均影响 per-model 配额计费：

1. 流式路径的 prompt/completion 只是「字节÷3」估算。
   pumpStream 明明收到了上游最后一帧的真实 usage，却只发给客户端、
   从不回写审计记录，于是配额按估算值扣。生产实测同一请求：
   上游 prompt=37/completion=179 → 记账 27/262，prompt 低估 1.4x、
   completion 高估 1.5x（双向失真）。同模型流式 completion 中位数
   是非流式的 4-27 倍。非流式路径本就用真实值，两路不一致。
   修法：lastUsage 非零时写回 rec.Prompt/rec.Compl，估算降为兜底
   （上游不报 usage 时仍保留原估算行为）。

2. 图片请求把「图片张数」记成 completion_tokens。
   rec.Compl = int64(len(resp.ImageData))，len 是切片长度即张数
   （生产 38 条 image 记录全是 1），且被计入 token 总量。
   图片生成无 token 概念 ⇒ 新增 Req.ImageCount 独立字段，
   Prompt/Compl 归 0；UI 记录表 image 行改显示张数（新增 i18n thImgs）。

顺带补 TestUILocaleKeyParity：此前无人校验 zh/en 键集合一致，
单边加键不会报错，只会显示原始键名。

新增 token_units_test.go（定值上游 6 项），做过变异验证：
回退修复实测复现 stream=16/173 vs chat=44/100、image completion=3。

internal/gateway/chat.go

@@ -957,6 +957,19 @@ func (g *Gateway) pumpStream(w http.ResponseWriter, rec *Req, chunks <-chan type
 	// Final usage chunk (OpenAI standard: empty choices + usage before [DONE]).
 	// Prefer the upstream's exact usage if the stream carried it; fall back to
 	// the gateway's estimate otherwise.
+	// Write the upstream's exact numbers back onto the audit record. Without
+	// this the streamed path kept only the per-chunk byte estimate, so the same
+	// request recorded ~1.4x its real completion tokens (measured: upstream 100,
+	// audit 145) while the non-streaming path recorded 100. Two paths, two
+	// different numbers for one request is a reporting bug, not a rounding one.
+	if lastUsage != nil {
+		if lastUsage.Prompt > 0 {
+			rec.Prompt = int64(lastUsage.Prompt)
+		}
+		if lastUsage.Completion > 0 {
+			rec.Compl = int64(lastUsage.Completion)
+		}
+	}
 	var tut *types.TokenUsage
 	if lastUsage != nil {
 		tut = lastUsage
@@ -1125,7 +1138,10 @@ func (g *Gateway) handleImage(w http.ResponseWriter, r *http.Request) {
 			}
 			rec.OK = true
 			rec.Status = http.StatusOK
-			rec.Compl = int64(len(resp.ImageData))
+			// Image generation has no token concept. Recording len(ImageData)
+			// (the image COUNT) in completion_tokens mislabels image count as
+			// tokens and feeds it into the token totals; leave it 0.
+			rec.ImageCount = len(resp.ImageData)
 			g.writeRec(rec)
 			writeJSON(w, http.StatusOK, types.ImageGenResponse{
 				Created: time.Now().Unix(),
@@ -1174,7 +1190,8 @@ func (g *Gateway) handleImage(w http.ResponseWriter, r *http.Request) {
 	}
 	rec.OK = true
 	rec.Status = http.StatusOK
-	rec.Compl = int64(len(resp.ImageData))
+	// Image generation has no token concept — see the AUTO path above.
+	rec.ImageCount = len(resp.ImageData)
 	g.writeRec(rec)
 	writeJSON(w, http.StatusOK, types.ImageGenResponse{
 		Created: time.Now().Unix(),

internal/gateway/stats.go

@@ -48,6 +48,10 @@ type Req struct {
 	Status int `json:"status"`
 	// Err short error message
 	Err string `json:"error,omitempty"`
+	// ImageCount is how many images an image-generation request produced.
+	// Kept separate from Compl/Prompt: image generation has no token concept,
+	// so counting images as "completion tokens" would corrupt the token totals.
+	ImageCount int `json:"image_count,omitempty"`
 }
 
 // Stat aggregates counters for one dimension row.

internal/gateway/token_units_test.go

@@ -0,0 +1,231 @@
+package gateway
+
+import (
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"llmsproxy/internal/config"
+)
+
+// Token accounting must record TOKENS, not byte estimates and not image
+// counts. These tests pin the two units bugs found on 2026-09-27:
+//
+//  1. streamed chat: rec.Compl was only ever the per-chunk byte estimate
+//     (len(content)/3), even when the upstream sent exact usage on its final
+//     frame. Measured on production traffic: the same model reported a
+//     streamed completion median 4-27x its non-streamed median. Upstream 100
+//     recorded as 145.
+//  2. image generation: rec.Compl was set to len(resp.ImageData) — the image
+//     COUNT — and folded into the token totals.
+//
+// A fake upstream that reports FIXED numbers makes both mismatches
+// unambiguous: any difference between what it reports and what the audit
+// record holds is the gateway's doing.
+
+// fixedUsageUpstream reports prompt=prompt completion=compl on both the
+// streaming and the non-streaming path. The streaming path emits usage on its
+// final frame before [DONE], exactly like OpenAI-compatible upstreams.
+func fixedUsageUpstream(t *testing.T, prompt, compl int, images int) *httptest.Server {
+	t.Helper()
+	return httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]interface{}
+		_ = json.NewDecoder(r.Body).Decode(&body)
+		stream, _ := body["stream"].(bool)
+		usage := fmt.Sprintf(`{"prompt_tokens":%d,"completion_tokens":%d,"total_tokens":%d}`,
+			prompt, compl, prompt+compl)
+
+		// Image generation wire: /v1/images/generations style body.
+		if strings.Contains(r.URL.Path, "image") {
+			w.Header().Set("Content-Type", "application/json")
+			var data []string
+			for i := 0; i < images; i++ {
+				data = append(data, `{"b64_json":"AAAA"}`)
+			}
+			fmt.Fprintf(w, `{"created":1,"data":[%s]}`, strings.Join(data, ","))
+			return
+		}
+
+		if !stream {
+			w.Header().Set("Content-Type", "application/json")
+			fmt.Fprintf(w, `{"model":"m1","choices":[{"message":{"content":"pong pong pong"},
+				"finish_reason":"stop"}],"usage":%s}`, usage)
+			return
+		}
+
+		w.Header().Set("Content-Type", "text/event-stream")
+		w.WriteHeader(200)
+		fl, _ := w.(http.Flusher)
+		send := func(s string) {
+			fmt.Fprintf(w, "data: %s\n\n", s)
+			if fl != nil {
+				fl.Flush()
+			}
+		}
+		// Deliberately verbose payloads: a byte-estimating path records a
+		// number far from `compl`, so the test would catch it.
+		send(`{"model":"m1","choices":[{"delta":{"reasoning_content":"` + strings.Repeat("think ", 40) + `"}}]}`)
+		send(`{"model":"m1","choices":[{"delta":{"content":"` + strings.Repeat("answer ", 40) + `"}}]}`)
+		send(`{"model":"m1","choices":[{"delta":{},"finish_reason":"stop"}]}`)
+		send(`{"model":"m1","choices":[],"usage":` + usage + `}`)
+		send(`[DONE]`)
+	}))
+}
+
+// lastChatRecord returns the most recent audit record whose Type is one of the
+// given types.
+func lastChatRecord(t *testing.T, g *Gateway, types ...string) Req {
+	t.Helper()
+	recs := g.stats.AuditRecords(0, 0, "")
+	want := map[string]bool{}
+	for _, ty := range types {
+		want[ty] = true
+	}
+	for i := len(recs) - 1; i >= 0; i-- {
+		if want[recs[i].Type] {
+			return recs[i]
+		}
+	}
+	t.Fatalf("no audit record of type %v found (have %d records)", types, len(recs))
+	return Req{}
+}
+
+// The streamed path must record the upstream's exact usage, not a byte
+// estimate. Before the fix this recorded 145 for an upstream-reported 100.
+func TestStreamedChatRecordsUpstreamUsage(t *testing.T) {
+	const wantPrompt, wantCompl = 44, 100
+	up := fixedUsageUpstream(t, wantPrompt, wantCompl, 0)
+	defer up.Close()
+	g := newTestGateway(t, config.Source{
+		Name: "up", BaseURL: up.URL, Adapter: "openai",
+		Models: []config.Model{{ID: "m1", Priority: 100}},
+	})
+
+	rr := doReq(t, g, "POST", "/v1/chat/completions",
+		`{"model":"m1","messages":[{"role":"user","content":"hi"}],"stream":true}`)
+	if rr.Code != 200 {
+		t.Fatalf("stream status=%d body=%s", rr.Code, rr.Body.String())
+	}
+
+	rec := lastChatRecord(t, g, "stream")
+	if rec.Prompt != wantPrompt || rec.Compl != wantCompl {
+		t.Errorf("streamed record prompt=%d completion=%d, want %d/%d — the audit "+
+			"must carry the upstream's tokens, not a byte estimate",
+			rec.Prompt, rec.Compl, wantPrompt, wantCompl)
+	}
+}
+
+// Streaming and non-streaming must agree on the same request's tokens. This is
+// the cross-path consistency check: the two paths previously recorded 145 and
+// 100 for one identical upstream usage value.
+func TestStreamedAndNonStreamedAgreeOnTokens(t *testing.T) {
+	const wantPrompt, wantCompl = 44, 100
+	up := fixedUsageUpstream(t, wantPrompt, wantCompl, 0)
+	defer up.Close()
+	g := newTestGateway(t, config.Source{
+		Name: "up", BaseURL: up.URL, Adapter: "openai",
+		Models: []config.Model{{ID: "m1", Priority: 100}},
+	})
+
+	if rr := doReq(t, g, "POST", "/v1/chat/completions",
+		`{"model":"m1","messages":[{"role":"user","content":"hi"}]}`); rr.Code != 200 {
+		t.Fatalf("non-stream status=%d body=%s", rr.Code, rr.Body.String())
+	}
+	if rr := doReq(t, g, "POST", "/v1/chat/completions",
+		`{"model":"m1","messages":[{"role":"user","content":"hi"}],"stream":true}`); rr.Code != 200 {
+		t.Fatalf("stream status=%d body=%s", rr.Code, rr.Body.String())
+	}
+
+	chat, stream := lastChatRecord(t, g, "chat"), lastChatRecord(t, g, "stream")
+	if chat.Prompt != stream.Prompt || chat.Compl != stream.Compl {
+		t.Errorf("chat=%d/%d stream=%d/%d — identical upstream usage must record "+
+			"identically on both paths", chat.Prompt, chat.Compl, stream.Prompt, stream.Compl)
+	}
+}
+
+// A fallback to the byte estimate is still correct WHEN the upstream reports no
+// usage at all. Without this the fix could silently zero out every streamed
+// record from upstreams that omit usage.
+func TestStreamedChatFallsBackToEstimateWithoutUsage(t *testing.T) {
+	up := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "text/event-stream")
+		w.WriteHeader(200)
+		fl, _ := w.(http.Flusher)
+		send := func(s string) {
+			fmt.Fprintf(w, "data: %s\n\n", s)
+			if fl != nil {
+				fl.Flush()
+			}
+		}
+		send(`{"model":"m1","choices":[{"delta":{"content":"` + strings.Repeat("abc ", 60) + `"}}]}`)
+		send(`{"model":"m1","choices":[{"delta":{},"finish_reason":"stop"}]}`)
+		send(`[DONE]`)
+	}))
+	defer up.Close()
+	g := newTestGateway(t, config.Source{
+		Name: "up", BaseURL: up.URL, Adapter: "openai",
+		Models: []config.Model{{ID: "m1", Priority: 100}},
+	})
+
+	if rr := doReq(t, g, "POST", "/v1/chat/completions",
+		`{"model":"m1","messages":[{"role":"user","content":"hi"}],"stream":true}`); rr.Code != 200 {
+		t.Fatalf("status=%d body=%s", rr.Code, rr.Body.String())
+	}
+	rec := lastChatRecord(t, g, "stream")
+	if rec.Compl <= 0 {
+		t.Errorf("completion=%d, want a positive byte-estimate fallback when the "+
+			"upstream reports no usage", rec.Compl)
+	}
+}
+
+// Image generation has no token concept: recording the image COUNT as
+// completion tokens corrupted the token totals. The count is reported
+// separately and must not leak into Prompt/Compl.
+func TestImageGenerationDoesNotRecordTokens(t *testing.T) {
+	up := fixedUsageUpstream(t, 44, 100, 3)
+	defer up.Close()
+	src := config.Source{
+		Name: "up", BaseURL: up.URL, Adapter: "openai",
+		Models: []config.Model{{ID: "img-m", Priority: 100, Kind: "image"}},
+	}
+	g := newTestGateway(t, src)
+
+	rr := doReq(t, g, "POST", "/v1/images/generations",
+		`{"model":"img-m","prompt":"a cat","n":3}`)
+	if rr.Code != 200 {
+		t.Fatalf("image status=%d body=%s", rr.Code, rr.Body.String())
+	}
+
+	rec := lastChatRecord(t, g, "image")
+	if rec.Compl != 0 || rec.Prompt != 0 {
+		t.Errorf("image record prompt=%d completion=%d, want 0/0 — image count is "+
+			"not a token and must not enter the token totals", rec.Prompt, rec.Compl)
+	}
+	if rec.ImageCount != 3 {
+		t.Errorf("image_count=%d, want 3 (the count belongs in its own field)", rec.ImageCount)
+	}
+	// And the aggregate must see zero tokens for it.
+	if got := g.stats.WindowTokens("img-m", "", 3600); got != 0 {
+		t.Errorf("window tokens for an image model = %d, want 0", got)
+	}
+}
+
+// The audit JSON must carry image_count so the WebUI can show images rather
+// than a bogus token figure.
+func TestImageCountSurvivesAuditJSON(t *testing.T) {
+	b, err := json.Marshal(Req{Type: "image", ImageCount: 2, OK: true})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !strings.Contains(string(b), `"image_count":2`) {
+		t.Errorf("audit JSON %s lacks image_count", b)
+	}
+	// Omitempty keeps chat records unchanged.
+	b2, _ := json.Marshal(Req{Type: "chat", Prompt: 1, Compl: 2, OK: true})
+	if strings.Contains(string(b2), "image_count") {
+		t.Errorf("chat record %s should omit image_count", b2)
+	}
+}

internal/gateway/ui/index.html

@@ -984,6 +984,7 @@
           thErr: "失败",
           thPrompt: "输入 Tokens",
           thCompl: "输出 Tokens",
+          thImgs: "张",
           thAvgLat: "平均延迟",
           thMaxLat: "最长延迟",
           thTime: "时间",
@@ -1214,6 +1215,7 @@
           thErr: "Err",
           thPrompt: "Prompt Tokens",
           thCompl: "Completion Tokens",
+          thImgs: "imgs",
           thAvgLat: "Avg latency",
           thMaxLat: "Max latency",
           thTime: "Time",
@@ -2193,7 +2195,7 @@
       <td class="t-tag">${fmtTime(r.time)}</td>
       <td class="num">${r.ok ? `<span class="tag tag-green">${r.status || 200}</span>` : `<span class="tag tag-red" title="${esc(r.error || "")}">${r.status || 500}</span>`}</td>
       <td>${esc(keyNames[r.key] ? keyNames[r.key] + " · " + r.key : r.key)}</td><td class="t-tag">${esc(r.type)}</td><td>${esc(r.model)}</td><td>${esc(r.source || "")}</td>
-      <td class="num">${fmtTok(r.prompt_tokens)}</td><td class="num">${fmtTok(r.completion_tokens)}</td>
+      <td class="num">${fmtTok(r.prompt_tokens)}</td><td class="num">${r.type === "image" ? fmtN(r.image_count || 0) + " " + t("thImgs") : fmtTok(r.completion_tokens)}</td>
       <td class="num">${cacheCell(r)}</td>
       <td class="num">${fmtMs(r.latency_ms)}</td></tr>`;
       }

internal/gateway/ui_contract_test.go

@@ -347,3 +347,60 @@ func cssBlock(src, selector string) (string, bool) {
 	}
 	return src[i : i+j+1], true
 }
+
+// The WebUI ships two locale objects (`zh` and `en`) that every rendered string
+// goes through. A key added to only one of them does not error: t() falls back
+// to `t("key") || "literal"` in some call sites and to the bare key string in
+// others, so the user sees either a hardcoded local string or a raw key name.
+// Nothing in the Go test suite noticed — this was found by hand while adding
+// thImgs. Pin the key sets so a one-sided edit fails here instead of shipping.
+func TestUILocaleKeyParity(t *testing.T) {
+	src := uiSource(t)
+	iZh := strings.Index(src, "zh: {")
+	iEn := strings.Index(src, "en: {")
+	if iZh < 0 || iEn < 0 || iEn < iZh {
+		t.Fatalf("locale blocks not found (zh=%d en=%d)", iZh, iEn)
+	}
+	zh := src[iZh:iEn]
+	en := src[iEn:]
+	// End the EN block at its closing brace, so keys from later objects
+	// (config templates etc.) do not pollute the comparison.
+	if end := strings.Index(en, "\n        },"); end > 0 {
+		en = en[:end]
+	}
+
+	keyRe := regexp.MustCompile(`(?m)^\s*([A-Za-z_][A-Za-z0-9_]*)\s*:`)
+	collect := func(seg string) map[string]bool {
+		m := map[string]bool{}
+		for _, g := range keyRe.FindAllStringSubmatch(seg, -1) {
+			m[g[1]] = true
+		}
+		return m
+	}
+	zk, ek := collect(zh), collect(en)
+	// The locale markers themselves are the two block headers.
+	delete(zk, "zh")
+	delete(ek, "en")
+
+	var missingEN, missingZH []string
+	for k := range zk {
+		if !ek[k] {
+			missingEN = append(missingEN, k)
+		}
+	}
+	for k := range ek {
+		if !zk[k] {
+			missingZH = append(missingZH, k)
+		}
+	}
+	if len(missingEN) > 0 {
+		t.Errorf("translation keys present in zh but missing in en: %v", missingEN)
+	}
+	if len(missingZH) > 0 {
+		t.Errorf("translation keys present in en but missing in zh: %v", missingZH)
+	}
+	if len(zk) < 100 {
+		t.Errorf("only %d zh keys parsed — the block boundary regexp has drifted "+
+			"and this test is no longer checking anything", len(zk))
+	}
+}