This release includes 3 security fixes for security teams reviewing exposed deployments.
Topics
+10 more
Affected surfaces
Summary
AI summaryUpdates ๐ Improvements & Fixes, ๐ค New Models, and ๐ Security Hardening across a mixed release.
Full changelog
๐ฌ Web Console Improvements
This release adds several visual management capabilities to the Web Console, so more configuration can be done in the UI without editing files:
- Scheduled task management: View, edit, enable/disable, and delete any scheduled task directly in the console. The task list is sorted by enabled status first, then by next run time. Thanks @HnBigVolibear (#2892)
- Knowledge base categories and document management: The knowledge base can now be organized by category, with documents under each category managed in the UI. Thanks @yangziyu-hhh (#2893)
- Multiple custom model providers: Configure multiple OpenAI-compatible providers and switch the active one with a single click, fully compatible with existing configuration. Thanks @kirs-hi (#2877)
- Session renaming: Rename sessions manually to tell parallel tasks apart (#2897)
- Bash streaming output: Long-running Bash commands now stream their progress in real time. Thanks @yangziyu-hhh (#2879)
๐งฌ Self-Evolution Improvements
Building on the Self-Evolution introduced in the previous release, this version refines it further:
- Lower trigger thresholds: The default review thresholds are lowered, so everyday collaboration turns into improvements sooner
- No concurrent reviews: When a single turn runs long, the idle review no longer fires by mistake, avoiding interference with the active conversation
- Better review summary: Refined the summary prompt to keep summaries concise, raise their information density, and output them in the conversation language
Documentation: Self-Evolution
๐ค New Models
- kimi-k2.7-code: Added and set as the default Kimi model, with
kimi-k2.7-code-highspeedalso available - glm-5.2: Added and set as the default GLM model
Documentation: Models Overview
๐ข WeCom Smart-Bot Callback Mode
The WeCom smart-bot channel adds an HTTP callback mode alongside the existing long connection, so deployments that cannot keep a long connection open can still connect reliably:
- Mode switching: Switch between
websocket(long connection) andwebhook(callback) viawecom_bot_mode - Encrypted transport: Callback mode fully supports URL verification, message decryption, and passive-reply encryption
- Stability fixes: Fixed reply interruption, premature stream termination, and temporary image file leaks
Thanks @6vision (#2896 #2869)
Documentation: WeCom Smart Bot
๐ Security Hardening
- Vision tool SSRF protection: Validates the target address before resolving an image URL, blocking requests to internal, loopback, and cloud server metadata endpoints. Thanks @kirs-hi (#2886)
- Web fetch SSRF protection:
web_fetchvalidates the target address before fetching and re-validates every redirect hop, preventing redirects from bypassing the check to reach internal addresses. Thanks @christop (#2900) - Skill install path traversal protection: Validates the path when installing a skill, preventing a malicious skill name from escaping the
skills/directory through path traversal and writing to an unauthorized location. Thanks @kirs-hi (#2886)
๐ Improvements & Fixes
- CLI self-restart: Added the
cow self-restartcommand so the agent can restart its own process - Windows compatibility: Persist the cow CLI directory to the user PATH; fixed
python -clong commands exceeding thecmd.exelength limit; avoid building greenlet from source during install - Custom roles: The role plugin supports customization via standalone prompt files under
roles/*.json. Thanks @sufan721 (#2891) - Stability fixes: Fixed a KeyError on
/canceland an infinite loop in image compression (Thanks @kirs-hi #2888) - Install improvements: Updated the startup script and default config; fixed ASR/TTS defaults, the self-evolution flag, and install hangs
- Vision tool stability: Increased the vision tool timeout and max_tokens
- Memory distillation: Removed the output length cap in deep-dream distillation to avoid truncating a large
MEMORY.md
๐ฆ Upgrade
Source-code deployments can run cow update for a one-click upgrade, or pull the latest code and restart manually. See the Upgrade Guide for details.
Release Date: 2026.06.18 | Full Changelog
Security Fixes
- Vision tool SSRF protection validates target URLs and blocks internal/loopback/cloud metadata endpoints
- Web fetch SSRF protection validates each redirect hop to prevent bypass of URL checks
- Skill install path traversal protection validates installation paths to stop directoryโescape writes
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About chatgpt-on-wechat
CowAgentๆฏๅบไบๅคงๆจกๅ็่ถ ็บงAIๅฉ็๏ผ่ฝไธปๅจๆ่ๅไปปๅก่งๅใ่ฎฟ้ฎๆไฝ็ณป็ปๅๅค้จ่ตๆบใๅ้ ๅๆง่กSkillsใ้่ฟ้ฟๆ่ฎฐๅฟๅ็ฅ่ฏๅบไธๆญๆ้ฟ๏ผๆฏOpenClawๆด่ฝป้ๅไพฟๆทใๅๆถๆฏๆๅพฎไฟกใ้ฃไนฆใ้้ใไผๅพฎใQQใๅ ฌไผๅทใ็ฝ้กต็ญๆฅๅ ฅ๏ผๅฏ้ๆฉOpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI๏ผ่ฝๅค็ๆๆฌใ่ฏญ้ณใๅพ็ๅๆไปถ๏ผๅฏๅฟซ้ๆญๅปบไธชไบบAIๅฉ็ๅไผไธๆฐๅญๅๅทฅใ
Related context
Related tools
Beta — feedback welcome: [email protected]