Assembled context for DeepSeek Harness: a context tree over the session surface with per-node assemble modes (full / key / off), agent-authored presets, and a panel that decides what the model actually sees.
Context compaction for DeepSeek Harness: mind_map and clear_mind agent tools turn selected history into self-written checkpoints, with auditable GUI tombstones and proactive threshold reminders.
DSH (DeepSeek Harness) web plugin: adds a PPT 制作 entry to the composer + menu that kicks off a bundled, self-contained PPT workflow prompt. One menu pick, one short message, no repeated approval prompts.
Context compression for DSH: visually configure summary and recent-context budgets (8k + 16k by default), keep tasks on track, and search full conversation history. Friendly to small-context models.
Map-reduce council of subagents for the DeepSeek Harness: one task fans out to independent members, their findings are deduplicated, verified by a separate panel, and reduced to a quorum report
A persistent office of colleague agents for DeepSeek Harness: ordinary sessions with a roster, channels, direct messages, and delivery that wakes a colleague when something is addressed to it.
Solidify DSH session history step by step: rewrite tool results in place to the facts the model actually kept, so long conversations stop re-sending noise every turn. Costs tokens and time: a ~770-character contract in every request, plus one extra full-context request and round-trip per step when stepSummary is on.
Persistent, model-editable memory/notes store for DeepSeek Harness. Adds memory_set/get/delete/search tools backed by ctx.storageDomain so facts survive across sessions (dsh-plugin).
DeepSeek Harness（DSH）第二大脑载入器：把有硬上限、带时间戳的脑快照（身份＋状态指纹＋未决项＋指针与边界）注入每个新会话；只读、零写入、fail-loud、零依赖。 | Second Brain loader for DSH — a bounded, timestamped snapshot of your local brain in every session prompt; read-only, zero-dependency.
System-1 decision models (Jev/Laya/Kev-class) as the governance layer for an LLM agent context lifecycle: growing association graph over session segments, relevance-gated recall with Trace-as-State ordering, and plan pre-ranking — measured in solve rate, cache hit/miss tokens, cost and latency. DSH plugin + harness-agnostic proxy.
