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
- Resin lets an agent build standalone LLM inference engines; vLLM and SGLang optimize DeepSeek kernels differently — AccBalanced · 2026-10-27
- Context layout is a cost decision: one memory edit can bust your entire agent prompt cache — dscape · 2026-10-27
- Alchemy adds effect/Workflow support across Durable Objects, Workflows and Lambda Durable Functions — samgoodwin89 · 2026-10-27
- Alchemy's Lambda Web Functions run plain Node web servers on Lambda, no OpenNext needed — samgoodwin89 · 2026-10-27
- Alchemy Domain brings domain-driven design and story testing to Effect backends — samgoodwin89 · 2026-10-27
- Alchemy makes all ~2,850 AWS bindings work from any cloud, not just S3/Lambda/DynamoDB — samgoodwin89 · 2026-10-27