feat(dashboard): Model Calling 实时监控扩展至全 vendor，修复排队队列长度不可见

CHANGELOG.md

@@ -4,6 +4,11 @@
 
 ## [Unreleased]
 
+- feat(dashboard): Model Calling 实时监控扩展至全 vendor / 全 model（仅 CC 场景），其他 vendor 在 monitor 模式下仅计数不限流，Zhipu 保留 limited 模式 + FIFO 排队；
+- feat(concurrency): 新增 `peak_pending_recent` 最近 10s 排队峰值追踪，瞬时排队释放后前端仍可见"曾排队 N" 余晖徽章；
+- perf(dashboard): Model Calling 轮询间隔由 5000ms 缩短至 1500ms，提升瞬时排队可观测性；
+- refactor(vendors): `ModelConcurrencyLimiter` 重构为 `ModelConcurrencyController`，统一 monitor / limited 双模式抽象（保留旧名别名）；并发控制由 vendor 内部迁移至 executor 层 `track_in_flight` 包裹，行为对所有 vendor 一致；
+
 ## [v0.5.0](https://github.com/ThreeFish-AI/coding-proxy/releases/tag/v0.5.0) - 2026-05-27
 
 > [!IMPORTANT]

src/coding/proxy/routing/executor.py

@@ -689,15 +689,17 @@ async def execute_stream(
                     tier.name, failed_tier_name, session_record, body
                 )
                 body_for_tier = self._prepare_body_for_tier(body, tier, source_vendor)
-                async for chunk in tier.vendor.send_message_stream(
-                    body_for_tier, headers
-                ):
-                    parse_usage_from_chunk(
-                        chunk,
-                        usage,
-                        vendor_label=_VENDOR_PROTOCOL_LABEL_MAP.get(tier.name),
-                    )
-                    yield chunk, tier.name
+                _mapped_model = tier.vendor.map_model(body.get("model", ""))
+                async with tier.vendor.track_in_flight(_mapped_model):
+                    async for chunk in tier.vendor.send_message_stream(
+                        body_for_tier, headers
+                    ):
+                        parse_usage_from_chunk(
+                            chunk,
+                            usage,
+                            vendor_label=_VENDOR_PROTOCOL_LABEL_MAP.get(tier.name),
+                        )
+                        yield chunk, tier.name
 
                 info = self._recorder.build_usage_info(usage)
                 if has_missing_input_usage_signals(info):
@@ -863,7 +865,9 @@ async def execute_message(
                     tier.name, failed_tier_name, session_record, body
                 )
                 body_for_tier = self._prepare_body_for_tier(body, tier, source_vendor)
-                resp = await tier.vendor.send_message(body_for_tier, headers)
+                _mapped_model = tier.vendor.map_model(body.get("model", ""))
+                async with tier.vendor.track_in_flight(_mapped_model):
+                    resp = await tier.vendor.send_message(body_for_tier, headers)
 
                 if resp.status_code < 400:
                     duration = int((time.monotonic() - start) * 1000)

src/coding/proxy/server/dashboard.py

@@ -629,6 +629,10 @@ def _build_favicon() -> bytes:
       background: rgba(251,146,60,.15);
       color: #fb923c;
     }
+    .mc-badge-peak {
+      background: rgba(148,163,184,.12);
+      color: #94a3b8;
+    }
     .mc-badge-active {
       background: rgba(74,222,128,.12);
       color: #4ade80;
@@ -1282,10 +1286,12 @@ def _build_favicon() -> bytes:
       models.push({
         vendor: tier.name,
         model: model,
-        limit: d.limit || 0,
+        mode: d.mode || 'limited',
+        limit: d.limit,
         in_use: d.in_use || 0,
-        available: d.available || 0,
+        available: d.available,
         pending: d.pending || 0,
+        peak_pending_recent: d.peak_pending_recent || 0,
       });
     }
   }
@@ -1298,18 +1304,33 @@ def _build_favicon() -> bytes:
   var html = '<div class="mc-grid">';
   for (var k = 0; k < models.length; k++) {
     var m = models[k];
-    var pct = m.limit > 0 ? Math.round((m.in_use / m.limit) * 100) : 0;
-    var barClass = pct <= 50 ? 'mc-low' : (pct <= 80 ? 'mc-mid' : 'mc-high');
-
-    html += '<div class="mc-model-row">'
-      + '<span class="mc-model-name">' + escapeHtml(m.vendor + '/' + m.model) + '</span>'
-      + '<div class="mc-bar-wrap"><div class="mc-bar-fill ' + barClass + '" style="width:' + pct + '%"></div></div>'
-      + '<div class="mc-stats">'
-      + '<span class="mc-badge mc-badge-active">' + m.in_use
-      + '/<span class="mc-limit-editable" data-tier="' + escapeHtml(m.vendor) + '" data-model="' + escapeHtml(m.model) + '" data-limit="' + m.limit + '" title="点击修改并行度">' + m.limit + '</span></span>'
-      + (m.pending > 0 ? '<span class="mc-badge mc-badge-pending">⏳ ' + m.pending + '</span>' : '')
-      + '</div>'
-      + '</div>';
+
+    if (m.mode === 'monitor') {
+      // monitor 模式：纯计数徽章，无 limit/进度条
+      html += '<div class="mc-model-row">'
+        + '<span class="mc-model-name">' + escapeHtml(m.vendor + '/' + m.model) + '</span>'
+        + '<div class="mc-bar-wrap"></div>'
+        + '<div class="mc-stats">'
+        + '<span class="mc-badge mc-badge-active">' + m.in_use + '</span>'
+        + '</div>'
+        + '</div>';
+    } else {
+      // limited 模式：保留现有渲染（进度条 + limit 编辑）
+      var limit = m.limit || 0;
+      var pct = limit > 0 ? Math.round((m.in_use / limit) * 100) : 0;
+      var barClass = pct <= 50 ? 'mc-low' : (pct <= 80 ? 'mc-mid' : 'mc-high');
+
+      html += '<div class="mc-model-row">'
+        + '<span class="mc-model-name">' + escapeHtml(m.vendor + '/' + m.model) + '</span>'
+        + '<div class="mc-bar-wrap"><div class="mc-bar-fill ' + barClass + '" style="width:' + pct + '%"></div></div>'
+        + '<div class="mc-stats">'
+        + '<span class="mc-badge mc-badge-active">' + m.in_use
+        + '/<span class="mc-limit-editable" data-tier="' + escapeHtml(m.vendor) + '" data-model="' + escapeHtml(m.model) + '" data-limit="' + limit + '" title="点击修改并行度">' + limit + '</span></span>'
+        + (m.pending > 0 ? '<span class="mc-badge mc-badge-pending">⏳ ' + m.pending + '</span>' : '')
+        + (m.pending === 0 && m.peak_pending_recent > 0 ? '<span class="mc-badge mc-badge-peak">🕘 曾排队 ' + m.peak_pending_recent + '</span>' : '')
+        + '</div>'
+        + '</div>';
+    }
   }
   html += '</div>';
   wrap.innerHTML = html;
@@ -1325,7 +1346,7 @@ def _build_favicon() -> bytes:
     }).catch(function() {});
   }
   tick();
-  _mcTimer = setInterval(tick, 5000);
+  _mcTimer = setInterval(tick, 1500);
 }
 function stopModelCallingPoll() {
   if (_mcTimer) { clearInterval(_mcTimer); _mcTimer = null; }

src/coding/proxy/server/routes.py

@@ -254,16 +254,15 @@ async def update_concurrency(request: Request) -> Response:
         for tier in router.tiers:
             if tier.name == tier_name:
                 vendor = tier.vendor
-                update_fn = getattr(vendor, "update_concurrency", None)
-                if update_fn is None:
+                try:
+                    vendor.update_concurrency(model, limit)
+                except ValueError as exc:
                     return json_error_response(
-                        400,
+                        422,
                         error_type="invalid_request_error",
-                        message=f"vendor '{tier_name}' does not support concurrency",
+                        message=str(exc),
                     )
-                try:
-                    update_fn(model, limit)
-                except (ValueError, AttributeError) as exc:
+                except AttributeError as exc:
                     return json_error_response(
                         400, error_type="invalid_request_error", message=str(exc)
                     )

src/coding/proxy/vendors/base.py

@@ -44,6 +44,7 @@
 )
 from ..compat.session_store import CompatSessionRecord
 from ..config.schema import FailoverConfig
+from .concurrency import ModelConcurrencyController
 
 logger = logging.getLogger(__name__)
 
@@ -63,6 +64,8 @@ def __init__(
         self._client: httpx.AsyncClient | None = None
         self._compat_trace: CompatibilityTrace | None = None
         self._compat_session_record: CompatSessionRecord | None = None
+        # 默认 monitor 模式（仅计数不限流）；子类可覆盖为 limited 模式
+        self._concurrency_controller = ModelConcurrencyController(None)
 
     def _get_client(self) -> httpx.AsyncClient:
         if self._client is None or self._client.is_closed:
@@ -246,8 +249,30 @@ def get_diagnostics(self) -> dict[str, Any]:
         diagnostics: dict[str, Any] = {}
         if self._compat_trace is not None:
             diagnostics["compat"] = self._compat_trace.to_dict()
+        concurrency = self._concurrency_controller.get_diagnostics()
+        if concurrency:
+            diagnostics["concurrency"] = concurrency
         return diagnostics
 
+    def track_in_flight(self, mapped_model: str):
+        """返回用于追踪在途请求的异步上下文管理器.
+
+        空 model name 时返回 no-op context（防御性处理）。
+        """
+        if not mapped_model:
+            from contextlib import nullcontext
+
+            return nullcontext()
+        return self._concurrency_controller.track(mapped_model)
+
+    def update_concurrency(self, model: str, limit: int) -> None:
+        """运行时更新指定模型的并发限制.
+
+        默认实现委托给 ``_concurrency_controller.set_limit``。
+        monitor 模式下抛 ``ValueError``。
+        """
+        self._concurrency_controller.set_limit(model, limit)
+
     def should_trigger_failover(
         self, status_code: int, body: dict[str, Any] | None
     ) -> bool: