diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8d11ea24..a6b75301 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,3 +1,26 @@
+# v0.5.2 (2026-06-17)
+
+## Features
+- **Combo Fusion strategy** — fans the prompt out to all member models in parallel, then a configurable judge model synthesizes one final answer (quorum-grace, anonymized sources, graceful degradation)
+- **Per-combo strategy selector** — pick `fallback` / `round-robin` / `fusion` / `capacity` per combo (replaces the old round-robin toggle), with a judge picker for fusion
+- **Capacity auto-switch** — reorders models per request so images/PDFs route to capable models first
+- **Kiro headless API-key auth** (`ksk_`) + direct `claude↔kiro` route that avoids the lossy OpenAI two-hop pivot
+- **Claude auto-ping** — warms the 5h quota window right after reset so a fresh window starts immediately (per-connection toggle)
+
+## Fixes
+- **Claude 429**: stop hammering the OAuth usage endpoint — cache resetAt, throttle quota refresh to 3 min, cool down after a 429 (chat unaffected)
+- **Usage logs always empty**: missing `await` on `getAdapter()` in `getRecentLogs` made `/api/usage/logs` & `/api/usage/request-logs` return nothing
+- **Executors**: strip params unsupported by the provider/model (drops deprecated `temperature` for claude-opus-4 → Anthropic 400)
+- **Translator**: derive deterministic tool_call ids for gemini/antigravity → OpenAI so function call/response pair correctly (fixes tool-pairing 400s)
+- **Antigravity**: strip `optional` from tool schemas before sending to Gemini
+- **Claude-to-OpenAI**: handle OpenAI-format responses in the non-streaming path (e.g. xiaomi-tokenplan)
+- **Usage views**: show edited connection names consistently across Providers & Quota Tracker
+- **Security**: hardened reverse-proxy local-access trust
+- **Security**: SSRF hardening on web fetch
+
+## Internal
+- Large **open-sse / translator refactor** (~40 commits): unified provider/model registry (LiteLLM-style `models[]` + `kind` field, 100 co-located registry files), single-sourced media/OAuth/refresh/token URLs, registry-based dispatch for usage & token-refresh, DRY translator concerns (buildUsage, encodeDataUri, finishReasonMap, chunkBuilder, reasoningDelta…), ESM-safe registry init, large-file splits, dead-code removal, and golden/no-regression test gates
+
 # v0.4.80 (2026-06-13)
 
 ## Features
diff --git a/cli/package.json b/cli/package.json
index 846d36dc..d75e5125 100644
--- a/cli/package.json
+++ b/cli/package.json
@@ -1,6 +1,6 @@
 {
   "name": "9router",
-  "version": "0.4.80",
+  "version": "0.5.2",
   "description": "9Router CLI - Start and manage 9Router server",
   "bin": {
     "9router": "./cli.js"
diff --git a/package.json b/package.json
index 9211d5ba..17f8380a 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "9router-app",
-  "version": "0.4.80",
+  "version": "0.5.2",
   "description": "9Router web dashboard",
   "private": true,
   "scripts": {
diff --git a/src/app/(dashboard)/dashboard/combos/page.js b/src/app/(dashboard)/dashboard/combos/page.js
index 8902db4e..abfc215c 100644
--- a/src/app/(dashboard)/dashboard/combos/page.js
+++ b/src/app/(dashboard)/dashboard/combos/page.js
@@ -160,11 +160,11 @@ export default function CombosPage() {
           <ul className="text-sm text-text-muted mt-2 flex flex-col gap-1">
             <li><span className="font-medium text-text-main">Fallback</span> — tries models in order (next on failure)</li>
             <li><span className="font-medium text-text-main">Round Robin</span> — rotates models across requests to spread load</li>
-            <li><span className="font-medium text-text-main">Fusion</span> — queries all models in parallel, then a judge synthesizes one answer</li>
-            <li><span className="font-medium text-text-main">Capacity auto-switch</span> — reorders models per request so images/PDFs route to capable models first</li>
+            <li><span className="font-medium text-text-main">Fusion</span> — queries all models in parallel, then a judge synthesizes one answer. Best quality, but costs the most: every request bills all panel models + the judge (N+1 calls)</li>
+            <li><span className="font-medium text-text-main">Capacity auto-switch</span> — sends image/PDF/audio requests to a model that supports them first</li>
           </ul>
         </div>
-        <Button icon="add" onClick={() => setShowCreateModal(true)} className="w-full sm:w-auto">
+        <Button icon="add" onClick={() => setShowCreateModal(true)} className="w-full sm:w-auto whitespace-nowrap">
           Create Combo
         </Button>
       </div>