Plugins

Expert-mode agent preset for DeepSeek Harness (v0.6.0, bilingual EN/ZH): a chief coordinator plus 11 domain-expert subagents with automatic task delegation. Features: Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (28% token savings), expert persistence, cross-expert communication protocol, cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance.

Settings card to tune the DSH LLM auto-retry policy (retry count, backoff, jitter) live from Settings → General.

Auto-resumes interrupted DSH turns: sends a queued 「继续」 after turn/end with error, interrupted or max-tokens reasons, with a grace period, cooldown, a consecutive-attempts cap, boot-time scanning and a settings card; it never switches models or providers.