feat(release): v2.8.2 — model alias routing fix, log export, 2 merged PRs

- New API: /api/logs/export?hours=24&type=call-logs
- UI: Export button with dropdown on /dashboard/logs page
- Supports export of request-logs, proxy-logs, and call-logs
- Downloads as JSON file with Content-Disposition header

CHANGELOG.md

@@ -4,6 +4,26 @@
 
 ---
 
+## [2.8.2] — 2026-03-19
+
+> Sprint: 2 merged PRs, model aliases routing fix, log export, and issue triage.
+
+### Features
+
+- **Log Export**: New Export button on `/dashboard/logs` with time range dropdown (1h, 6h, 12h, 24h). Downloads JSON of request/proxy/call logs via `/api/logs/export` API (#user-request)
+
+### Bug Fixes
+
+- **Model Aliases Routing** (#472): Settings → Model Aliases now correctly affect provider routing, not just format detection. Previously `resolveModelAlias()` output was only used for `getModelTargetFormat()` but the original model ID was sent to the provider
+- **Stream Flush Usage** (#480): Usage data from the last SSE event in the buffer is now correctly extracted during stream flush (merged from @prakersh)
+
+### Merged PRs
+
+- #480 — Extract usage from remaining buffer in flush handler (@prakersh)
+- #479 — Add missing Codex 5.3/5.4 and Anthropic model ID pricing entries (@prakersh)
+
+---
+
 ## [2.8.1] — 2026-03-19
 
 > Sprint: Five community PRs — streaming call log fixes, Kiro compatibility, cache token analytics, Chinese translation, and configurable tool call IDs.

docs/openapi.yaml

@@ -1,7 +1,7 @@
 openapi: 3.1.0
 info:
   title: OmniRoute API
-  version: 2.8.1
+  version: 2.8.2
   description: |
     OmniRoute is a local-first AI API proxy router. It provides an OpenAI-compatible
     endpoint that routes requests to multiple AI providers with load balancing,

open-sse/handlers/chatCore.ts

@@ -157,10 +157,16 @@ export async function handleChatCore({
   // Detect source format and get target format
   // Model-specific targetFormat takes priority over provider default
 
-  // Apply custom model aliases (Settings → Model Aliases → Pattern→Target) before routing (#315)
+  // Apply custom model aliases (Settings → Model Aliases → Pattern→Target) before routing (#315, #472)
   // Custom aliases take priority over built-in and must be resolved here so the
-  // downstream getModelTargetFormat() lookup uses the correct, aliased model ID.
+  // downstream getModelTargetFormat() lookup AND the actual provider request use
+  // the correct, aliased model ID. Without this, aliases only affect format detection.
   const resolvedModel = resolveModelAlias(model);
+  // Use resolvedModel for all downstream operations (routing, provider requests, logging)
+  const effectiveModel = resolvedModel !== model ? resolvedModel : model;
+  if (resolvedModel !== model) {
+    log?.info?.("ALIAS", `Model alias applied: ${model} → ${resolvedModel}`);
+  }
 
   const alias = PROVIDER_ID_TO_ALIAS[provider] || provider;
   const modelTargetFormat = getModelTargetFormat(alias, resolvedModel);
@@ -367,8 +373,8 @@ export async function handleChatCore({
   delete translatedBody._toolNameMap;
   delete translatedBody._disableToolPrefix;
 
-  // Update model in body
-  translatedBody.model = model;
+  // Update model in body — use resolved alias so the provider gets the correct model ID (#472)
+  translatedBody.model = effectiveModel;
 
   // Strip unsupported parameters for reasoning models (o1, o3, etc.)
   const unsupported = getUnsupportedParams(provider, model);
@@ -397,7 +403,7 @@ export async function handleChatCore({
   const dedupEnabled = shouldDeduplicate(dedupRequestBody);
   const dedupHash = dedupEnabled ? computeRequestHash(dedupRequestBody) : null;
 
-  const executeProviderRequest = async (modelToCall = model, allowDedup = false) => {
+  const executeProviderRequest = async (modelToCall = effectiveModel, allowDedup = false) => {
     const execute = async () => {
       const bodyToSend =
         translatedBody.model === modelToCall
@@ -445,8 +451,8 @@ export async function handleChatCore({
   trackPendingRequest(model, provider, connectionId, true);
 
   // T5: track which models we've tried for intra-family fallback
-  const triedModels = new Set<string>([model]);
-  let currentModel = model;
+  const triedModels = new Set<string>([effectiveModel]);
+  let currentModel = effectiveModel;
 
   // Log start
   appendRequestLog({ model, provider, connectionId, status: "PENDING" }).catch(() => {});
@@ -465,7 +471,7 @@ export async function handleChatCore({
   let finalBody;
 
   try {
-    const result = await executeProviderRequest(model, true);
+    const result = await executeProviderRequest(effectiveModel, true);
 
     providerResponse = result.response;
     providerUrl = result.url;

open-sse/utils/stream.ts

@@ -518,6 +518,33 @@ export function createSSEStream(options: StreamOptions = {}) {
           if (buffer.trim()) {
             const parsed = parseSSELine(buffer.trim());
             if (parsed && !parsed.done) {
+              // Extract usage from remaining buffer — if the usage-bearing event
+              // (e.g. response.completed) is the last SSE line, it ends up here
+              // in the flush handler where extractUsage was not called.
+              // Non-destructive merge: some providers send usage across multiple
+              // events (e.g. prompt_tokens in message_start, completion_tokens
+              // in message_delta). Direct assignment would lose earlier data.
+              const extracted = extractUsage(parsed);
+              if (extracted) {
+                if (!state.usage) {
+                  state.usage = extracted;
+                } else {
+                  if (extracted.prompt_tokens > 0)
+                    state.usage.prompt_tokens = extracted.prompt_tokens;
+                  if (extracted.completion_tokens > 0)
+                    state.usage.completion_tokens = extracted.completion_tokens;
+                  if (extracted.total_tokens > 0) state.usage.total_tokens = extracted.total_tokens;
+                  if (extracted.cache_read_input_tokens > 0)
+                    state.usage.cache_read_input_tokens = extracted.cache_read_input_tokens;
+                  if (extracted.cache_creation_input_tokens > 0)
+                    state.usage.cache_creation_input_tokens = extracted.cache_creation_input_tokens;
+                  if (extracted.cached_tokens > 0)
+                    state.usage.cached_tokens = extracted.cached_tokens;
+                  if (extracted.reasoning_tokens > 0)
+                    state.usage.reasoning_tokens = extracted.reasoning_tokens;
+                }
+              }
+
               const translated = translateResponse(targetFormat, sourceFormat, parsed, state);
 
               // Log OpenAI intermediate chunks

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "2.8.1",
+  "version": "2.8.2",
   "description": "Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.",
   "type": "module",
   "bin": {

src/app/(dashboard)/dashboard/logs/page.tsx

@@ -1,27 +1,135 @@
 "use client";
 
-import { useState } from "react";
+import { useState, useRef, useEffect } from "react";
 import { RequestLoggerV2, ProxyLogger, SegmentedControl } from "@/shared/components";
 import ConsoleLogViewer from "@/shared/components/ConsoleLogViewer";
 import AuditLogTab from "./AuditLogTab";
 import { useTranslations } from "next-intl";
 
+const TIME_RANGES = [
+  { label: "1h", hours: 1 },
+  { label: "6h", hours: 6 },
+  { label: "12h", hours: 12 },
+  { label: "24h", hours: 24 },
+];
+
+const TAB_TO_LOG_TYPE: Record<string, string> = {
+  "request-logs": "request-logs",
+  "proxy-logs": "proxy-logs",
+  "audit-logs": "call-logs",
+  console: "call-logs",
+};
+
 export default function LogsPage() {
   const [activeTab, setActiveTab] = useState("request-logs");
+  const [showExport, setShowExport] = useState(false);
+  const [exporting, setExporting] = useState(false);
+  const dropdownRef = useRef<HTMLDivElement>(null);
   const t = useTranslations("logs");
 
+  useEffect(() => {
+    function handleClickOutside(e: MouseEvent) {
+      if (dropdownRef.current && !dropdownRef.current.contains(e.target as Node)) {
+        setShowExport(false);
+      }
+    }
+    document.addEventListener("mousedown", handleClickOutside);
+    return () => document.removeEventListener("mousedown", handleClickOutside);
+  }, []);
+
+  async function handleExport(hours: number) {
+    setExporting(true);
+    setShowExport(false);
+    try {
+      const logType = TAB_TO_LOG_TYPE[activeTab] || "call-logs";
+      const res = await fetch(`/api/logs/export?hours=${hours}&type=${logType}`);
+      if (!res.ok) throw new Error("Export failed");
+      const blob = await res.blob();
+      const url = URL.createObjectURL(blob);
+      const a = document.createElement("a");
+      a.href = url;
+      a.download = `omniroute-${logType}-${hours}h-${new Date().toISOString().slice(0, 10)}.json`;
+      document.body.appendChild(a);
+      a.click();
+      document.body.removeChild(a);
+      URL.revokeObjectURL(url);
+    } catch (err) {
+      console.error("Export failed:", err);
+    } finally {
+      setExporting(false);
+    }
+  }
+
   return (
     <div className="flex flex-col gap-6">
-      <SegmentedControl
-        options={[
-          { value: "request-logs", label: t("requestLogs") },
-          { value: "proxy-logs", label: t("proxyLogs") },
-          { value: "audit-logs", label: t("auditLog") },
-          { value: "console", label: t("console") },
-        ]}
-        value={activeTab}
-        onChange={setActiveTab}
-      />
+      <div className="flex items-center justify-between gap-4 flex-wrap">
+        <SegmentedControl
+          options={[
+            { value: "request-logs", label: t("requestLogs") },
+            { value: "proxy-logs", label: t("proxyLogs") },
+            { value: "audit-logs", label: t("auditLog") },
+            { value: "console", label: t("console") },
+          ]}
+          value={activeTab}
+          onChange={setActiveTab}
+        />
+
+        <div className="relative" ref={dropdownRef}>
+          <button
+            id="export-logs-btn"
+            onClick={() => setShowExport(!showExport)}
+            disabled={exporting}
+            className="flex items-center gap-2 px-4 py-2 text-sm font-medium rounded-lg
+              bg-[var(--card-bg,#1e1e2e)] border border-[var(--border,#333)]
+              text-[var(--text-secondary,#aaa)] hover:text-[var(--text-primary,#fff)]
+              hover:border-[var(--accent,#7c3aed)] transition-all duration-200
+              disabled:opacity-50 disabled:cursor-not-allowed"
+          >
+            <svg
+              width="16"
+              height="16"
+              viewBox="0 0 16 16"
+              fill="none"
+              stroke="currentColor"
+              strokeWidth="1.5"
+            >
+              <path
+                d="M8 2v8m0 0l-3-3m3 3l3-3M3 12h10"
+                strokeLinecap="round"
+                strokeLinejoin="round"
+              />
+            </svg>
+            {exporting ? "Exporting..." : "Export"}
+          </button>
+
+          {showExport && (
+            <div
+              className="absolute right-0 top-full mt-1 z-50 min-w-[140px] rounded-lg
+                bg-[var(--card-bg,#1e1e2e)] border border-[var(--border,#333)]
+                shadow-xl overflow-hidden animate-in fade-in"
+            >
+              <div className="px-3 py-2 text-xs text-[var(--text-muted,#666)] border-b border-[var(--border,#333)] font-medium">
+                Time Range
+              </div>
+              {TIME_RANGES.map((range) => (
+                <button
+                  key={range.hours}
+                  id={`export-${range.hours}h-btn`}
+                  onClick={() => handleExport(range.hours)}
+                  className="w-full px-3 py-2 text-sm text-left hover:bg-[var(--hover-bg,#2a2a3e)]
+                    text-[var(--text-secondary,#aaa)] hover:text-[var(--text-primary,#fff)]
+                    transition-colors flex items-center justify-between"
+                >
+                  <span>Last {range.label}</span>
+                  <span className="text-xs text-[var(--text-muted,#666)]">
+                    {range.hours === 24 ? "default" : ""}
+                  </span>
+                </button>
+              ))}
+            </div>
+          )}
+        </div>
+      </div>
 
       {/* Content */}
       {activeTab === "request-logs" && <RequestLoggerV2 />}

src/app/api/logs/export/route.ts

@@ -0,0 +1,58 @@
+import { getDbInstance } from "@/lib/db/core";
+
+/**
+ * GET /api/logs/export — export logs as JSON
+ * Query params: ?hours=24 (1, 6, 12, 24; default 24)
+ *               &type=call-logs|request-logs|proxy-logs (default call-logs)
+ */
+export async function GET(request: Request) {
+  try {
+    const { searchParams } = new URL(request.url);
+    const hours = Math.min(Math.max(parseInt(searchParams.get("hours") || "24") || 24, 1), 168);
+    const logType = searchParams.get("type") || "call-logs";
+
+    const since = new Date(Date.now() - hours * 3600 * 1000).toISOString();
+    const db = getDbInstance();
+
+    let rows: unknown[] = [];
+    let tableName = "";
+
+    if (logType === "call-logs") {
+      tableName = "call_logs";
+      const stmt = db.prepare(
+        "SELECT * FROM call_logs WHERE timestamp >= @since ORDER BY timestamp DESC"
+      );
+      rows = stmt.all({ since });
+    } else if (logType === "request-logs") {
+      tableName = "request_logs";
+      const stmt = db.prepare(
+        "SELECT * FROM request_logs WHERE timestamp >= @since ORDER BY timestamp DESC"
+      );
+      rows = stmt.all({ since });
+    } else if (logType === "proxy-logs") {
+      tableName = "proxy_logs";
+      const stmt = db.prepare(
+        "SELECT * FROM proxy_logs WHERE timestamp >= @since ORDER BY timestamp DESC"
+      );
+      rows = stmt.all({ since });
+    }
+
+    const filename = `omniroute-${tableName}-${hours}h-${new Date().toISOString().slice(0, 10)}.json`;
+
+    return new Response(
+      JSON.stringify({ logs: rows, count: rows.length, hours, type: logType }, null, 2),
+      {
+        status: 200,
+        headers: {
+          "Content-Type": "application/json",
+          "Content-Disposition": `attachment; filename="${filename}"`,
+        },
+      }
+    );
+  } catch (error) {
+    return Response.json(
+      { error: { message: (error as Error).message, type: "server_error" } },
+      { status: 500 }
+    );
+  }
+}

src/shared/constants/pricing.ts

@@ -2,6 +2,47 @@
 // All rates are in dollars per million tokens ($/1M tokens)
 // Based on user-provided pricing for Antigravity models and industry standards for others
 
+// Shared pricing constants to reduce duplication
+const GPT_5_3_CODEX_PRICING = {
+  input: 5.0,
+  output: 20.0,
+  cached: 2.5,
+  reasoning: 30.0,
+  cache_creation: 5.0,
+};
+
+const CLAUDE_OPUS_4_PRICING = {
+  input: 15.0,
+  output: 75.0,
+  cached: 7.5,
+  reasoning: 112.5,
+  cache_creation: 15.0,
+};
+
+const CLAUDE_SONNET_4_PRICING = {
+  input: 3.0,
+  output: 15.0,
+  cached: 1.5,
+  reasoning: 15.0,
+  cache_creation: 3.0,
+};
+
+const CLAUDE_OPUS_46_PRICING = {
+  input: 5.0,
+  output: 25.0,
+  cached: 2.5,
+  reasoning: 37.5,
+  cache_creation: 5.0,
+};
+
+const CLAUDE_SONNET_46_PRICING = {
+  input: 3.0,
+  output: 15.0,
+  cached: 1.5,
+  reasoning: 22.5,
+  cache_creation: 3.0,
+};
+
 export const DEFAULT_PRICING = {
   // OAuth Providers (using aliases)
 
@@ -46,7 +87,14 @@ export const DEFAULT_PRICING = {
 
   // OpenAI Codex (cx)
   cx: {
-    // Issue #334: add gpt5.4
+    // GPT 5.4
+    "gpt-5.4": {
+      input: 5.0,
+      output: 20.0,
+      cached: 2.5,
+      reasoning: 30.0,
+      cache_creation: 5.0,
+    },
     "gpt5.4": {
       input: 5.0,
       output: 20.0,
@@ -54,6 +102,19 @@ export const DEFAULT_PRICING = {
       reasoning: 30.0,
       cache_creation: 5.0,
     },
+    // GPT 5.3 Codex family (all same pricing tier)
+    "gpt-5.3-codex": GPT_5_3_CODEX_PRICING,
+    "gpt-5.3-codex-xhigh": GPT_5_3_CODEX_PRICING,
+    "gpt-5.3-codex-high": GPT_5_3_CODEX_PRICING,
+    "gpt-5.3-codex-low": GPT_5_3_CODEX_PRICING,
+    "gpt-5.3-codex-none": GPT_5_3_CODEX_PRICING,
+    "gpt-5.1-codex-mini-high": {
+      input: 1.5,
+      output: 6.0,
+      cached: 0.75,
+      reasoning: 9.0,
+      cache_creation: 1.5,
+    },
     "gpt-5.2-codex": {
       input: 5.0,
       output: 20.0,
@@ -525,6 +586,15 @@ export const DEFAULT_PRICING = {
       reasoning: 37.5,
       cache_creation: 5.0,
     },
+    // Common model IDs (without dates) used across providers
+    // Intentional duplicates of dot-notation variants (e.g. claude-opus-4.6)
+    // to cover hyphen-notation IDs (claude-opus-4-6) used by some clients
+    "claude-opus-4-6": CLAUDE_OPUS_46_PRICING,
+    "claude-sonnet-4-6": CLAUDE_SONNET_46_PRICING,
+    "claude-opus-4-5-20251101": CLAUDE_OPUS_4_PRICING,
+    "claude-sonnet-4-5-20250929": CLAUDE_SONNET_4_PRICING,
+    "claude-sonnet-4": CLAUDE_SONNET_4_PRICING,
+    "claude-opus-4": CLAUDE_OPUS_4_PRICING,
   },
 
   // Gemini