Skip to content

Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors

docs: update changelog with PRs 1600-1603

diegosouzapw1beb3720570a
diff --git a/CHANGELOG.md b/CHANGELOG.md
index dbb3719f81..cbe526b1d4 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,13 @@
pass per-account `maxConcurrent` caps into runtime credential selection.
- **fix(files):** Avoid loading file content blobs for metadata-only file list, retrieve, delete,
and ownership-check paths.
+- **fix(settings):** Repair OAuth env hydration failures in `/api/system/env/repair` by replacing dynamic imports (#1601).
+- **fix(cli):** Align OpenCode config preview and add multi-model selection support (#1602).
+- **fix(providers):** Navigate to node detail immediately after creating a compatible node to avoid orphaned nodes (#1603).
+
+### ✨ New Features
+
+- **feat(i18n):** Sync keys and complete translations for en and zh-CN locales (#1600).
### 🧪 Tests