merge: integrate origin/master (v0.5.50) into gitea/new_feature

- Resolve conflicts in chatCore handlers: keep apiKey/streamErrorPatterns
  from the details-filters feature, adopt origin's stripContinuityFields,
  customToolNames, cache-inclusive usage accounting, and Responses-API
  SSE→JSON conversion
- Adopt origin's provider usage handlers (codebuddy-intl, qoder creds)
  and modality detection (audio/video inputs)
- Keep requestDetails apiKey column (schema v2) + masked key persistence

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>

open-sse/services/usage/codebuddy-cn.js

@@ -43,17 +43,17 @@ function refillCadence(acc) {
   return "Monthly";
 }
 
-export async function getCodeBuddyCnUsage(accessToken, apiKey, providerSpecificData, proxyOptions = null) {
+async function getCodeBuddyUsage(providerId, accessToken, apiKey, providerSpecificData, proxyOptions = null) {
   const token = accessToken || apiKey;
   if (!token) {
-    return { message: "CodeBuddy CN credential not available." };
+    return { message: `CodeBuddy (${providerId}) credential not available.` };
   }
 
   try {
-    const response = await proxyAwareFetch(U(PROVIDER_ID).url, {
+    const response = await proxyAwareFetch(U(providerId).url, {
       method: "POST",
       headers: {
-        ...(PROVIDERS[PROVIDER_ID]?.headers || {}),
+        ...(PROVIDERS[providerId]?.headers || {}),
         Authorization: `Bearer ${token}`,
         "Content-Type": "application/json",
         Accept: "application/json",
@@ -129,10 +129,18 @@ export async function getCodeBuddyCnUsage(accessToken, apiKey, providerSpecificD
     });
 
     const basePkg = refills[0] || accounts[0] || {};
-    const plan = basePkg.PackageName || basePkg.SubProductName || "CodeBuddy CN";
+    const plan = basePkg.PackageName || basePkg.SubProductName || "CodeBuddy";
 
     return { plan, quotas };
   } catch (error) {
-    return { message: `CodeBuddy CN error: ${error.message}` };
+    return { message: `CodeBuddy (${providerId}) error: ${error.message}` };
   }
 }
+
+export async function getCodeBuddyCnUsage(accessToken, apiKey, providerSpecificData, proxyOptions = null) {
+  return getCodeBuddyUsage(PROVIDER_ID, accessToken, apiKey, providerSpecificData, proxyOptions);
+}
+
+export async function getCodeBuddyIntlUsage(accessToken, apiKey, providerSpecificData, proxyOptions = null) {
+  return getCodeBuddyUsage("codebuddy-intl", accessToken, apiKey, providerSpecificData, proxyOptions);
+}

open-sse/services/usage/google.js

@@ -161,7 +161,9 @@ export async function getAntigravityUsage(accessToken, providerSpecificData, pro
     if (data.models) {
       // Filter only recommended/important models (must match PROVIDER_MODELS ag ids)
       const importantModels = [
-        'gemini-3-flash-agent',
+        'gemini-3.6-flash-high',
+        'gemini-3.6-flash-medium',
+        'gemini-3.6-flash-low',
         'gemini-3.5-flash-low',
         'gemini-3.5-flash-extra-low',
         'gemini-pro-agent',
@@ -169,10 +171,8 @@ export async function getAntigravityUsage(accessToken, providerSpecificData, pro
         'claude-sonnet-4-6',
         'claude-opus-4-6-thinking',
         'gpt-oss-120b-medium',
-        'gemini-3-flash',
         // Image generation models
         'gemini-3.1-flash-image',
-        'gemini-3-pro-image',
       ];
 
       for (const [modelKey, info] of Object.entries(data.models)) {

open-sse/services/usage/grok-cli.js

@@ -91,6 +91,24 @@ function resolvePlan(user, config) {
   return "Grok Build";
 }
 
+// Display only; upstream remains authoritative for access and quota enforcement.
+function planFromAccessToken(accessToken) {
+  try {
+    const payload = JSON.parse(Buffer.from(accessToken.split(".")[1], "base64url"));
+    return {
+      0: "Free",
+      1: "SuperGrok",
+      2: "X Basic",
+      3: "X Premium",
+      4: "X Premium Plus",
+      5: "SuperGrok Heavy",
+      6: "SuperGrok Lite",
+    }[payload.tier] || "";
+  } catch {
+    return "";
+  }
+}
+
 function makeQuota({ used, total, resetAt, unlimited = false }) {
   const safeTotal = Math.max(0, toFiniteNumber(total, 0));
   const safeUsed = Math.max(0, toFiniteNumber(used, 0));
@@ -371,6 +389,7 @@ export async function getGrokCliUsage(accessToken, providerSpecificData = null,
     }
 
     const parsed = parseGrokCliBilling(billing, user);
+    parsed.plan = planFromAccessToken(accessToken) || parsed.plan;
 
     if (!parsed.quotas || Object.keys(parsed.quotas).length === 0) {
       // Paid SuperGrok often returns cap=0 over REST but exposes the shared

open-sse/services/usage/misc.js

@@ -1,5 +1,5 @@
 /**
- * Misc usage handlers (Qwen, iFlow, Ollama, GLM, Vercel AI Gateway, Qoder)
+ * Misc usage handlers (iFlow, Ollama, GLM, Vercel AI Gateway, Qoder)
  */
 
 import { proxyAwareFetch } from "../../utils/proxyFetch.js";
@@ -15,23 +15,6 @@ const GLM_QUOTA_URLS = {
 // Returns { balance: "95.50", total_used: "4.50" } (USD as decimal strings).
 const VERCEL_AI_GATEWAY_CREDITS_URL = U("vercel-ai-gateway").url;
 
-/**
- * Qwen Usage
- */
-export async function getQwenUsage(accessToken, providerSpecificData) {
-  try {
-    const resourceUrl = providerSpecificData?.resourceUrl;
-    if (!resourceUrl) {
-      return { message: "Qwen connected. No resource URL available." };
-    }
-
-    // Qwen may have usage endpoint at resource URL
-    return { message: "Qwen connected. Usage tracked per request." };
-  } catch (error) {
-    return { message: "Unable to fetch Qwen usage." };
-  }
-}
-
 /**
  * iFlow Usage
  */
@@ -46,23 +29,86 @@ export async function getIflowUsage(accessToken) {
 
 /**
  * Ollama Cloud Usage
- * Ollama Cloud uses an API key from ollama.com/settings/keys
- * and has no public usage API — free tier has light usage limits (resets every 5h & 7d).
- * This returns an informational message with the plan details.
+ * GET https://ollama.com/api/usage — session (5h) + weekly (7d) `usage` is a 0..1
+ *   ratio (1.0 = limit reached, e.g. weekly 100% used). No reset timestamp exposed.
+ * POST https://ollama.com/api/me — plan label (fail-open).
+ * Auth: Authorization: Bearer <apiKey>
  */
-export async function getOllamaUsage(accessToken, providerSpecificData) {
+export async function getOllamaUsage(apiKey, providerSpecificData, proxyOptions = null) {
+  if (!apiKey) {
+    return { message: "Ollama Cloud API key not available." };
+  }
+
   try {
-    // Ollama Cloud does not expose a public quota/usage API.
-    // The provider is configured as noAuth with a notice explaining limits.
-    // We return a graceful message so the UI shows a friendly state instead of an error.
-    const plan = providerSpecificData?.plan || "Free";
-    return {
-      plan,
-      message: "Ollama Cloud uses a free tier with light usage limits (resets every 5h & 7d). For detailed usage tracking, visit ollama.com/settings/keys.",
-      quotas: [],
-    };
+    const response = await proxyAwareFetch("https://ollama.com/api/usage", {
+      headers: {
+        Authorization: `Bearer ${apiKey}`,
+        Accept: "application/json",
+      },
+    }, proxyOptions);
+
+    if (response.status === 401 || response.status === 403) {
+      return { message: "Ollama Cloud API key invalid or expired." };
+    }
+
+    if (!response.ok) {
+      return { message: `Ollama Cloud usage API error (${response.status}).` };
+    }
+
+    let data;
+    try {
+      data = await response.json();
+    } catch {
+      return { message: "Ollama Cloud usage response was not JSON." };
+    }
+
+    // Best-effort plan label from /api/me
+    const me = await proxyAwareFetch("https://ollama.com/api/me", {
+      method: "POST",
+      headers: {
+        Authorization: `Bearer ${apiKey}`,
+        Accept: "application/json",
+        "Content-Length": "0",
+      },
+    }, proxyOptions).then((r) => (r.ok ? r.json() : null)).catch(() => null);
+
+    const planRaw = typeof me?.Plan === "string" ? me.Plan : "";
+    const plan = planRaw
+      ? planRaw.charAt(0).toUpperCase() + planRaw.slice(1).toLowerCase()
+      : "Ollama Cloud";
+
+    const limits = data?.limits && typeof data.limits === "object" ? data.limits : {};
+
+    // Ollama `usage` is a 0..1 ratio (1.0 = limit reached). Convert to a 0..100
+    // bar. Do NOT set absolute `remaining` — QuotaTable reads remainingPercentage.
+    function ratioQuota(usageRatio, resetAt = null) {
+      const ratio = Math.max(0, Math.min(1, Number(usageRatio) || 0));
+      const usedPct = Math.round(ratio * 100);
+      return { used: usedPct, total: 100, remainingPercentage: 100 - usedPct, resetAt, unlimited: false };
+    }
+
+    const sessionRaw = limits.session?.usage;
+    const weeklyRaw = limits.weekly?.usage;
+    const sessionNum = Number(sessionRaw);
+    const weeklyNum = Number(weeklyRaw);
+    const hasSession = sessionRaw !== undefined && sessionRaw !== null && !Number.isNaN(sessionNum);
+    const hasWeekly = weeklyRaw !== undefined && weeklyRaw !== null && !Number.isNaN(weeklyNum);
+
+    if (!hasSession && !hasWeekly) {
+      return {
+        plan,
+        message: "Ollama Cloud connected. No usage limits reported.",
+        quotas: {},
+      };
+    }
+
+    const quotas = {};
+    if (hasSession) quotas["Session (5h)"] = ratioQuota(sessionNum);
+    if (hasWeekly) quotas["Weekly (7d)"] = ratioQuota(weeklyNum);
+
+    return { plan, quotas };
   } catch (error) {
-    return { message: "Unable to fetch Ollama Cloud usage." };
+    return { message: `Ollama Cloud error: ${error.message}` };
   }
 }