Qwen Code adds a separate image-generation model route with PNG safety checks
qqqys · ghdev · 2026-07-23
Qwen Code adds a configurable image-generation route
This PR adds a user-selectable image-only model to Qwen Code, alongside the existing voice and vision auxiliary models. Users can pick it with /model --image, and the CLI invokes an approval-gated image-generation tool that writes verified PNGs as workspace artifacts.
Key implementation details:
- image models are kept separate from the primary chat model and excluded from chat/fast/voice/vision/fallback/subagent selection paths
- the initial transport uses Qwen’s synchronous multimodal image-generation request/response format
- downloads are locked down with HTTPS-only policy, DNS pinning across redirects, bounded response sizes, PNG signature checks, timeout/cancellation handling, redacted errors, and atomic workspace writes
The motivation is to avoid conflating chat and generation protocols while still letting users bring their own endpoint and credentials.
More from coding & agent
- NVIDIA says Nemotron 3 Ultra hit 97.1% on agentic RTL chip-design tasks — NVIDIAAI · 2026-07-27
- Tokyo Agent Forge hackathon shipped production-ready AI agents in one day — DavidBennett__ · 2026-07-27
- Long-running agents will need immutable event logs, this thread argues — sebpaquet · 2026-07-27
- Agentic Data Science in Practice: Agents Write Code but Answer Wrong Questions — hugobowne · 2026-07-27
- A VS Code extension adds Markdown-style highlighting to Alchemy string templates — samgoodwin89 · 2026-07-27
- Claude’s Stripe MCP connector is being called unusable after repeated disconnects — evielync · 2026-07-27