Plugins

DSH context insight panel: Context dashboard + /context command + Context browser — one-stop context lifecycle management with categorized composition, content details, evolution trends, compaction/injection events, and stats.

Security-analysis plugin for DeepSeek Harness: 33 tools spanning six security domains, evidence/reporting and toolbox, plus the case lifecycle, routing and tool ledger; a session-bound case workflow with an evidence chain, E-id validation and reproducible findings; 362 on-demand references; three hot-swappable persona profiles; and a four-tab workbench (armor / case / intercept / about) with case-state recovery after context compaction.

Browse Claude Code, DSH and Codex session logs by working directory, with per-turn context composition, token usage, compaction markers and cost estimates.

边做边压 Live Compact. Compress the finished turn in place and keep the prefix cache.

Profile-wide DSH governance and routing with a Web Control Center for responsibility and evidence inspection, plus compaction, scoped semantic memory, safety continuity, and verified delivery; compatible with DSH 0.1.5-rc.1.

DSH session manager: delete with trash/restore/purge, restore archived sessions, recent-activity stats, continue/pause, open log folder, unread markers, fork into a new chat, workspace grouping and sorting, context compaction threshold.

Causal memory for dsh: a zero-dependency MCP stdio bridge that mounts the 17 tools of the causal-memory server under clean names (no mcp__ prefix) — decision → outcome edges with typed relations (caused / enabled / prevented) in a local SQLite store that survives compaction — plus a pinned system-prompt section. Requires the causal-memory server binary on PATH (pip install causal-memory, or a prebuilt release).

边做边压 Live Compact. Compress the finished turn in place and keep the prefix cache.

Keeps a local TinyTitan model server reachable from the harness: refreshes the llm-pi-ai route from the installed models and mounts a compaction backend that does not think.

Floating DSH desktop pet with 12 authored state animations for requests, tools, compaction, archive and prompt enhancement; live context occupancy; a persistent cross-session Lifetime Ledger; per-provider/model totals, hourly trends and 7/30-day views; dark/light theme switching; optional cost estimates (off by default) with a visual price editor and monthly budget alert; client-side skin ZIP import; JSON/CSV usage export; snapshot-only panel reads with background incremental indexing; and opt-in prompt enhancement with editable preview and DSH composer submission.

Token optimization for DeepSeek Harness with searchable MCP tool discovery and lazy loading, configurable compaction controls and status reporting, tool-output reduction, long-text vision summarization, and opt-in conversation archiving with paginated retrieval.

Hosts QQ chats as DeepSeek Harness sessions: one QQ conversation maps to one DSH session that survives restarts, per-speaker tool permissions, three-layer memory with nightly consolidation, optional QQ-number binding that ties openids to QQ numbers so memories survive a bot or AppID change (binding is voluntary, never required, and never guessed from nicknames), four-section personas, context compaction, a ten-page sidebar panel, and a setup wizard that installs the Roost kernel and ai-chat plugin. Anyone in a paired QQ group can chat with the bot by default; only the owner gets the full local toolset.

Per-request thinking budgets, a compaction backend, and a settings tab for the local Qwen3.8 line (llama.cpp or NInfer).

Folds degenerate reasoning loops out of the model-visible history so they are not replayed upstream on the next turn. Detects two shapes — one sentence hammered repeatedly, and short-sentence rotation — and replaces the matched span in place; a companion escape valve aborts a turn that will not stop on its own.

Auto-compaction that writes a handoff note first: as a session approaches a token threshold it asks the model to save a project checkpoint into the workspace, then optionally starts a fresh session seeded with a continue instruction and parks the old one. The note must be written within the current compaction cycle and its conclusions section must actually change, so a stale or merely touched file cannot slip through.

Conversation navigator panel: turn-folded outline of the current session with per-step kind badges (assistant, tool, command, compaction, error), a hover bubble showing the full user question, a minimal mode that hides turn numbers for an all-badge view, keyword filter over user questions and assistant replies, click-to-jump with reading-position tracking, and load-earlier/load-all history paging. Host >= 0.1.2-rc.1; legacy hosts install @legacy/0.2.5.

Terminal-style input history for the web composer: edge-first arrow-key recall with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, and sliding-context awareness; 0.5.0 adds a smart input layer — cross-session snippets (/save, /load), prompt templates with variables, reuse insights, and compaction-summary highlighting.

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log.

Three agent presets in one plugin, each with its own persistent memory file. Enabling it registers 鲸鱼娘Agent预设, 鲸鱼娘活人版Agent预设 and 鲸鱼娘涩涩版Agent预设 in the Agent preset list, so any of them can be picked from the mode dropdown without hand-editing profile config. All three reuse the official minimal composition — a single persistent shell terminal — plus file read/write and glob/grep tools. The first pairs that with a whale-girl companion persona (simplified-Chinese spoken register, addresses the user as 主人, clingy-but-tsundere). The second swaps in a "live person" variant that is allowed to talk back, deflect and be cold, and demotes the sweet tone to a seasoning. The third keeps the original persona but makes being affectionate the stated top behavioral drive, reserved for the user alone and dialed down in group chats. Each preset reads its own memory file (whale-loli.md, whale-loli-v2-live.md and whale-loli-v3-naughty.md) through a distinct prompt variable — whale_memory, whale_memory_v2 and whale_memory_v3 — so the three memories never read or write each other. Conversation compaction is left to the billion-context plugin; this plugin only carries the persona-level rule that compressed summaries count as evidence and that details can be looked up on demand.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Per-session long-term memory for DeepSeek Harness, with memory management, persona settings, and compaction prompts.

Six-layer local memory for dsh: captures turns, stages them through an L2 buffer into DL3 summaries via a staging model, injects a stable memory block each turn and replaces chat history with placeholders. Ships five memory tools and a config page.

Wraps work in named tasks and, once a task closes, folds its whole span of messages into one summary at the next step boundary; the original content can be restored on demand.

Bounded context compaction, session-scoped summary reuse, explicit memory controls, and diagnostic-preserving tool pruning for DeepSeek Harness. Adapted for dsh 0.2.1-rc.2, including the Web preset roster and localized plugin metadata.