Плагины

A durable RAG-enhanced long-term memory layer for LLM agents, featuring holographic memory, state-slot conflict detection, and timeline retrieval. Requires Python 3.10+ and this repository's Python dependencies: create a venv and run pip install -e ".\[dev]" in the checkout before enabling the plugin (the bundled installer is a PowerShell script, i.e. Windows).

Stores the agent's long-term memory as plain Markdown in an Obsidian vault — every memory is a .md file with YAML frontmatter that Obsidian indexes natively, so you can read, edit, link and back up it with tools you already use. Nothing is locked in a database. Ships a sidebar panel (tag filter, sort by recency or importance, edit in place), 7 agent tools, three-tier token-budgeted recall, BM25 ranking (no embeddings, no API key, works offline, CJK bigram tokenization), importance decay with archiving (moved to .archive/, never deleted), and optional GitHub Contents API sync. A note containing a secret is refused rather than redacted, because a redacted memory reads as complete while the important part is gone. Zero runtime dependencies; everything comes from the DSH host.

Local three-band memory for DeepSeek Harness: a 24h protection band, query recall and scene replay, injected into sessions without embedding or model calls.

Moves a conversation into another workspace: long-press its sidebar row, drop it on the target workspace, and the session log with its full history is relocated and re-pointed. A plain drag still does the sidebar's own reorder inside one workspace.

Adds a delete row to the menu of an archived conversation only, and after a confirmation removes the session log directory, its projection cache, the archive and pin marks and the workspace booking together.

Windows DSH session manager: recoverable recycle bin, subagent-tree cleanup, workspace file discovery and Explorer highlighting, plus categorized file-path export.

Elides stale, oversized plain-text tool results from the model-visible session surface once the prompt cache goes cold, replacing each with a stub that keeps the tail lines and any error lines, and reports per-request and cumulative savings in the composer footer.

Write each session's summary as a Markdown file in its workspace, with a page to browse, regenerate and delete them.

Side-by-side native chat windows for DSH Web GUI — open several conversations beside the main chat, tile them with one click, minimize into a live status dock, or pop them out into their own browser window.

Material library for dsh: collect a folder, file or note from a conversation, keep it in real folders with tags, browse it Finder-style, reopen the source chat's output in one click. Ships a materials_archive tool plus auto-filing rules: file a task's deliverable once, and every later scheduled run files the new documents by itself.

Session and image management for DSH: a sidebar panel deletes selected sessions together with their on-disk files after DSH has archived them, with multi-select, sub-agent / team-member / whole-family cascade and per-session size; a right-sidebar tab counts a session images and offloads or deletes the selected ones, optionally removing source files and attachment objects from disk.

One settings card that gives every DSH agent mode its own compaction threshold: it registers <mode>-compact-<ratio> preset copies with compaction-basic.thresholdRatio rewritten, re-registers when the value or the selection changes, and can adopt one copy as the default mode (standard > cordis > minimal > ptc).

Archives sessions that have gone unused for longer than a set number of days (5 by default), skipping archived, pinned, and protected ones — a session context-menu item marks a single session as protected, a small shield shows it on the row, and a General settings field changes the threshold.

One read-only index of every local AI-agent session (Codex, Claude Code, DSH, Trae, or any JSONL source) grouped by project, plus an append-only shared board for decisions and handoffs so switching agents leaves no context gap.

Delivers a queued chat message at the next step boundary instead of waiting for the whole turn to end, without aborting the model call already in flight; aborting is an opt-in mode rather than the default.

Read-only monitor for local DSH sessions: live task board, per-session tails, blocking reply wait, Markdown export, and optional IM push via dsh-im. Requires Python 3 with the zstandard package; IM push additionally needs the dsh-im plugin.

Sidebar search across every past Session: literal substring matching that works for Chinese, results grouped per Session with highlighted snippets, and one click to reopen the conversation.

Replaces the built-in compaction provider: at a configurable fraction of the context threshold (85% by default) a detached task summarizes everything up to the previous turn, and the next step boundary commits that held summary as a checkpoint with zero model calls, so the swap itself takes milliseconds. /bcompact \[message] starts the same generation on demand and then sends the message. A settings page sets the trigger ratio, the summarization model, and how many consecutive failures stop background generation until a half-open probe gets through. Subagent sessions, a changed prefix or an expired summary fall back to the built-in synchronous path.

Turns "restarting the host" into one interrupt that many sessions can share. Several sessions queue onto the same restart (8 by default, configurable, joinable at any time including mid-wait); the host is closed once and relaunched once; then each waiting session is woken separately with its own reason and starts running its own work without waiting for the others. Each session decides independently whether to resume, one failed delivery never affects the rest, and a session can drop only itself without cancelling everyone else's restart. Windows desktop only.

One dedicated folder per conversation: archives the transcript, auto-categorizes research output by type once the conversation has been idle for 10 minutes, adds a delete action to the session menu, and permanently removes the folder with the conversation.

Batch session cleanup for DeepSeek Harness — pick a workspace, see which sessions are archived, and permanently delete logs, projection caches and workspace records.

Two triggers (a heartbeat and a log marker) that wake a session and let the agent decide whether to say anything; silence is a reply. Off by default: set sessionId (the target session) and enable it in the profile config, and if replies are forwarded to a chat app the send layer must drop the SILENT marker.

Idle-time context truncation for a single DeepSeek Harness session. After a configurable number of idle hours the older conversation is dropped without a summary, so one long-lived session cannot leak one task into the next; it ships a per-session toggle, a tab next to the chat, and a /truncate command that IM bridges can drive.

Actually delete DSH sessions instead of archiving them (Windows only). Clears all six on-disk locations (transcript, title cache, billion-context SQLite index with VACUUM, workspace registry, cost-meter ledger, bridge logs) with a dry run, a backup, byte-for-byte rollback, and an automatic quit-delete-relaunch flow.