Qwen Code v0.14 adds cron jobs, planning mode, and remote control from your phone
Qwen Code v0.14.0 through v0.14.2 adds cron jobs, a planning mode, remote control via messaging apps, and a new flagship model with 1M token context.
Qwen Code just released versions 0.14.0 through 0.14.2. The update adds several features across automation, model selection, and output handling.
Like other coding agents, Qwen Code can now receive instructions via Telegram, DingTalk, or WeChat and return results to your server. No SSH access required.
The update also adds cron jobs for scheduling recurring AI tasks on a timer. Among the things it supports:
- Auto-run tests: Run test suites on a set interval without manual triggering.
- Scheduled builds: Pull and build automatically each morning.
- Log monitoring: Check logs on a recurring timer and surface anomalies.
A new /plan mode lets the agent map out all files and steps involved in a task before executing anything. You review the plan and confirm before it touches your codebase.
Qwen Code now also supports Qwen3.6-Plus, Alibaba’s flagship text model with a 1M token context window. It comes with 1,000 free daily requests built into the tool.
The remaining changes cover resource allocation and how the agent surfaces results:
- Sub-agent model selection: Assign different models to sub-agents. Run a heavier model on the main task and a faster one on subtasks.
- Follow-up suggestions: After completing a task the agent surfaces 2-3 suggested next steps. Click to continue without re-prompting.
- Adaptive output tokens: Default output is 8K tokens. The agent escalates to 64K automatically when a response gets truncated.
- Ctrl+O verbosity toggle: Switch between verbose and compact output mid-session.
Qwen Code is Alibaba’s open-source terminal-based coding agent. It reads your codebase, writes and edits files, runs commands, and handles multi-step development tasks from the command line.
Source: Qwen/Github
If you need on-demand GPUs for training, fine-tuning, inference, or running open-source models, give RunPod a try.
- Available hardware: H100, H200, A100, L40S, RTX 4090, RTX 5090, and 30+ more
- Cost: significantly cheaper than AWS or GCP, billed per second, no contracts
- Setup: spins up in under a minute, 30+ regions worldwide
Get the core business tech news delivered straight to your inbox. We track AI, automation, SaaS, and cybersecurity so you don't have to.
Just read what you want, and be done with it.
