# v0.5.20 (2026-07-07)

## Features
- **Thinking**: per-model thinking level picker on provider page — appends `(level)` suffix to copied model names for forced reasoning effort across all formats (openai, claude, gemini, deepseek, kimi, qwen, zai, minimax, hunyuan, step)
- **RTK**: add JS-native git-log filter (#2423)
- **Caveman**: add targeted upstream-aligned style rules (#2424)
- **i18n**: add Farsi (fa) language support (#2385)

## Fixes
- **Thinking**: strip `(level)` suffix from upstream `body.model` so providers no longer reject requests
- **Translator**: preserve developer instructions in openai-responses conversion (#2434)
- **count_tokens**: count structured Anthropic blocks (#2419)
- **Volcengine-ark**: clamp GLM-5 max_tokens to model output ceiling (#2428)
- **Kimi**: normalize reasoning_effort to backend enum (#2427)
- **Claude**: reconcile max_tokens vs thinking budget and lift per-model ceiling (#2381)
- **Kiro**: deliver system prompt natively, add Opus 4.5/4.7/4.8, tolerate dash version ids (#2366)
- **Headroom**: proxy dashboard through app (#2372)
- **MITM**: recover from stale lock file on server start

open-sse/handlers/chatCore.js

@@ -1,5 +1,6 @@
 import { detectFormat, getTargetFormat, resolveTransport } from "../services/provider.js";
 import { translateRequest } from "../translator/index.js";
+import { stripThinkingSuffix } from "../translator/concerns/thinkingUnified.js";
 import { FORMATS } from "../translator/formats.js";
 import { normalizeClaudePassthrough } from "../translator/formats/claude.js";
 import { COLORS } from "../utils/stream.js";
@@ -123,9 +124,9 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
   let toolNameMap;
   if (passthrough) {
     log?.debug?.("PASSTHROUGH", `${clientTool} → ${provider} | native lossless`);
-    translatedBody = { ...body, model: upstreamModel };
+    translatedBody = { ...body, model: stripThinkingSuffix(upstreamModel) };
     // Normalize newer Cowork/CC beta shapes (adaptive thinking, mid-conversation system) the API rejects
-    if (clientTool === "claude") normalizeClaudePassthrough(translatedBody, upstreamModel);
+    if (clientTool === "claude") normalizeClaudePassthrough(translatedBody, translatedBody.model);
   } else {
     translatedBody = translateRequest(sourceFormat, targetFormat, upstreamModel, body, stream, credentials, provider, reqLogger, stripList, connectionId, clientTool);
     if (!translatedBody) {
@@ -134,7 +135,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
     }
     toolNameMap = translatedBody._toolNameMap;
     delete translatedBody._toolNameMap;
-    translatedBody.model = upstreamModel;
+    translatedBody.model = stripThinkingSuffix(upstreamModel);
   }
 
   // Dedupe duplicate built-in tools when equivalent MCP tools are present (Claude clients only).