@@ -1134,6 +1225,74 @@ def _build_favicon() -> bytes:
}).join('');
}
+// ── Model Calling 实时状态 ────────────────────────────────
+function updateModelCalling(status) {
+ var wrap = document.getElementById('model-calling-wrap');
+ if (!wrap) return;
+ var tiers = status.tiers || [];
+
+ // 收集所有带 concurrency 诊断的模型
+ var models = [];
+ for (var i = 0; i < tiers.length; i++) {
+ var tier = tiers[i];
+ var diag = tier.diagnostics || {};
+ var conc = diag.concurrency;
+ if (!conc) continue;
+ var names = Object.keys(conc);
+ for (var j = 0; j < names.length; j++) {
+ var model = names[j];
+ var d = conc[model];
+ models.push({
+ vendor: tier.name,
+ model: model,
+ limit: d.limit || 0,
+ in_use: d.in_use || 0,
+ available: d.available || 0,
+ pending: d.pending || 0,
+ });
+ }
+ }
+
+ if (!models.length) {
+ wrap.innerHTML = '
无活跃模型调用
';
+ return;
+ }
+
+ var html = '
';
+ 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 += '
'
+ + '
' + escapeHtml(m.vendor + '/' + m.model) + ''
+ + '
'
+ + '
'
+ + '' + m.in_use + '/' + m.limit + ''
+ + (m.pending > 0 ? '⏳ ' + m.pending + '' : '')
+ + '
'
+ + '
';
+ }
+ html += '
';
+ wrap.innerHTML = html;
+}
+
+// Model Calling 独立短间隔轮询
+var _mcTimer = null;
+function startModelCallingPoll() {
+ stopModelCallingPoll();
+ function tick() {
+ fetchJSON('/api/status').then(function(status) {
+ updateModelCalling(status);
+ }).catch(function() {});
+ }
+ tick();
+ _mcTimer = setInterval(tick, 5000);
+}
+function stopModelCallingPoll() {
+ if (_mcTimer) { clearInterval(_mcTimer); _mcTimer = null; }
+}
+
// ── 按 tiers 顺序排序 vendor 列表 ─────────────────────────
function sortByTierOrder(vendors, tierOrder) {
if (!tierOrder || !tierOrder.length) return vendors.sort();
@@ -1713,6 +1872,7 @@ def _build_favicon() -> bytes:
updateKPI(summary);
updateVendorStatus(status);
+ updateModelCalling(status);
updateChartTitles(days);
const rows = timeline.rows || [];
@@ -1788,6 +1948,8 @@ def _build_favicon() -> bytes:
currentTab = name;
applyTabState(name);
syncTabUrl(name);
+ // Model Calling 轮询随页签切换启停
+ if (name === 'overview') { startModelCallingPoll(); } else { stopModelCallingPoll(); }
refresh();
}
@@ -1807,6 +1969,7 @@ def _build_favicon() -> bytes:
}).catch(function(){});
refresh(); // 仅加载初始页签的数据
setInterval(refresh, 600000); // 每 10 分钟刷新当前页签
+ if (initial === 'overview') startModelCallingPoll();
})();
diff --git a/src/coding/proxy/vendors/concurrency.py b/src/coding/proxy/vendors/concurrency.py
index b4f4df7..148bb53 100644
--- a/src/coding/proxy/vendors/concurrency.py
+++ b/src/coding/proxy/vendors/concurrency.py
@@ -67,10 +67,15 @@ def get_diagnostics(self) -> dict[str, dict[str, int]]:
limit = self._config.get_limit(model)
# asyncio.Semaphore 内部 _value 表示剩余可用槽位
available = sem._value # noqa: SLF001 — 公开 API 未暴露
+ in_use = max(limit - available, 0)
+ # _waiters 为正在排队等待的协程集合，无等待者时为 None
+ waiters = getattr(sem, "_waiters", None) # noqa: SLF001
+ pending = len(waiters) if waiters else 0
snapshot[model] = {
"limit": limit,
- "in_use": max(limit - available, 0),
+ "in_use": in_use,
"available": max(available, 0),
+ "pending": pending,
}
return snapshot
diff --git a/src/coding/proxy/vendors/zhipu.py b/src/coding/proxy/vendors/zhipu.py
index ff186cd..b6de695 100644
--- a/src/coding/proxy/vendors/zhipu.py
+++ b/src/coding/proxy/vendors/zhipu.py
@@ -206,6 +206,15 @@ async def _maybe_acquire_concurrency_slot(
return None
return await self._concurrency_limiter.acquire(mapped_model)
+ # ── 诊断信息 ─────────────────────────────────────────────
+
+ def get_diagnostics(self) -> dict[str, Any]:
+ """返回供应商运行时诊断信息，包含每模型并发状态."""
+ diagnostics = super().get_diagnostics()
+ if self._concurrency_limiter is not None:
+ diagnostics["concurrency"] = self._concurrency_limiter.get_diagnostics()
+ return diagnostics
+
# ── 延迟计算 ────────────────────────────────────────────
def _compute_retry_delay_from_headers(