Qwen Code’s /learn command now accepts local and URL video input
LaZzyMan · ghdev · 2026-07-22
Qwen Code adds native video input to /learn
This PR extends Qwen Code’s /learn command so it can accept local video files (MP4, WebM, MOV, M4V) and direct HTTP(S) video URLs. The command now checks whether the active model supports video, preserves the video parts through the provider path, and asks the main agent to create exactly one learned skill with a separate timestamped provenance record.
Notable behavior changes:
- YouTube watch pages are rejected with guidance to download the video locally first
- models without video input are blocked before submission
- ordinary text, document, directory, and webpage learning paths stay unchanged
- the generated skill includes a references/source.md file marked source-grounded, not execution-verified
The main goal is to make video transport explicit and keep source-grounded knowledge separate from execution-verified behavior.
More from coding & agent
- Dev builds interactive 3D product experience with GPT-6 Astra + Hyper3D Rodin — nikola_mr64990 · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11