Deep research — tumor immunotherapy survey driven by a Chinese prompt
PASS814sprompt: zhartifact: zh
Prompt (verbatim)
no-interview light-research: 使用 bioresearcher-deep-research 技能,帮我做一个关于肿瘤免疫治疗(tumor immunotherapy)的多方面文献综述并附引用。请用中文撰写报告,引用使用 PMID。
What happened
- Chinese prompt (the WorkBuddy connector's canonical zh example, extended): queried English sources, reported in Chinese.
- Two aspects under light-research: immune checkpoint inhibitors + cell therapy / emerging modalities.
- Objective check asserted Chinese text in the final answer (regex [\u4e00-\u9fff]) — bilingual behavior is verified, not claimed.
Evidence
The evidence below is in Chinese — a true-run output, untranslated.
Objective checks
checks passed: 5/5
| Fan-out mode | Mixed: one direct article_search pass + one Task worker; synthesis in Chinese |
|---|---|
| Provenance | 3380cc6 · opencode 1.18.29 · biomcp@1.1.1 |
Replay
node demos/run-demo.mjs --only agent-deep-research-zh --publish
Manual-run only — this replay spends LLM tokens (real opencode CLI + network).
In the repository: README · transcript · result.json · artifact directory (permalink)