Plugin

Connette dsh a un runtime locale SandBase Harness tramite stdio MCP per gestire agenti e sessioni, trasmettere turni, ispezionare artefatti e annullare attività.

Harness di memoria dell’agente a tre livelli: CLAUDE.md L1 sempre attivo, indice L2, scheletro dettagliato L3 con modelli, un gate che blocca le scritture nei file protetti senza un token di approvazione monouso, registrazione degli eventi senza giudizi, distillazione settimanale e una skill di ciclo di esecuzione TDD.

Pilota il tuo agente dsh da WeChat tramite il gateway iLink: trasferimento bidirezionale di contenuti cifrati (casella in ingresso con decifratura automatica + /send), strumento proattivo weixin_send, notifiche di completamento, cambio tra più sessioni e un pannello di stato con log su file.

Automatically retries model failures (drops, timeouts, rate limits, 5xx) in-turn. Retry count, delays, backoff, fallback and more are configurable. Rate-limit backoff is capped and jittered, server retry hints are honored, and optional retry-until-success keeps going within a time ceiling. Every option is editable from the plugin config or the sidebar panel: retry count, initial and max delay, backoff factor and jitter, rate-limit delay window, retry-until-success ceiling, fallback trigger and switch cap, dead-route blacklist TTL, log file. When a route keeps failing it can switch to a pinned, allowlist-filtered, or catalog-picked alternate model route, with a 30-minute dead-route blacklist (auth failure, subscription expired, billing) and a stale-assembly guard that keeps retried requests on the switched route. Ships a right-sidebar panel with live retry state, route labels and incident counters, Chinese and English locale, and memory-only logging by default.

检查日志是否开启、是否记录了该记的、是否留够法定 6 个月

Runs shell scripts on cron or interval schedules inside the host with no model call, logging every run and waking the model only when a script's output changes.

SQLite-backed long-term memory for DeepSeek Harness: add, search, update and archive entries with categories and tags, automatic conversation logging, tiered compression, and a project dimension that scopes retrieval to the current workspace plus global facts.

Event-driven Hypatia memory for DSH: automatic conversation logging via session events, queued background consolidation (span summaries + work-unit extraction) with a dedicated model route, and recall injection — zero per-call model work in the main sessi