Plugin

Automatic cross-session GoodMemory recall and writeback for DeepSeek Harness

Self-healing runtime layer: a resource control loop with strategy switching and repair escalation, error-storm and fiber-failure insight, cross-session knowledge carry-over, a self-healing dashboard and 7 tools.

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forget tools behind a human-confirm gate, and global + project-scoped JSON stores that follow your git repo.

Automatic, local-first cross-session memory for DeepSeek Harness: layered Event/Element cards, evidence-gated recall, and expansion back to original turns and tool results.

Scoperta e comunicazione cross-sessione nello stesso runtime per DeepSeek Harness

Deposito di memoria cross-sessione: strumenti remember / recall / forget, iniezione nel prompt per turno e un browser delle voci nella pagina delle impostazioni

DeepSeek Harness 侧边栏用量仪表盘插件：跨会话 token / 模型 / 活动统计、按会话明细与可选时间尺度的用量趋势图。 Usage dashboard plugin for DeepSeek Harness web: cross-session token, model, and activity stats with a per-session table and a windowed trend chart.

Cross-session reference (mention) for DeepSeek Harness: paste @[label](dsh-session:…) into any session — including one in another workspace — and the host resolves and injects the referenced session snapshot via the native session-reference pipeline. Incl

Event-sourced cross-session work ledger: register, track and settle tasks with full audit history, kanban export, and a board digest injected into every model turn.

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.

Cross-session event-cue memory for DeepSeek Harness: auto-extracts task/conversation cues and user language habits from every turn into a persistent global cue bank, then re-injects remembered context on topic-switch detection (keyword or vector matching).

Memoria cross-sessione per il modello: ricerca full-text in tutte le sessioni passate (SQLite FTS5 tramite ctx.sessionQuery) e riporta gli estratti più rilevanti nel contesto corrente