플러그인

Edits a message you already sent and re-runs from that point by forking the session, and retries a completed turn, in the DeepSeek Harness Web UI.

Wakes a DSH conversation on demand and hands work to it: pick one or more sessions to auto-wake when DSH starts, give each session its own provider, model and reasoning effort, and let the agent call another conversation with the session_task tool — it wakes that session, delivers the content, waits for it to finish and brings the answer back. Also ships list_sessions and wake_session tools plus a settings page titled 会话唤醒; no QQ or bridge dependency. The three tools are available to every agent and can reach any session in the profile; the auto-wake list is empty by default, a session's boot prompt is delivered at every DSH start, and session_task waits up to 300 seconds by default.

Session trash for DeepSeek Harness: move cold sessions out of the sidebar into a recoverable trash, restore them within the retention window (30 days by default), or delete their logs permanently. A trashed subagent tree moves and restores as a whole, a shared DSH toast offers undo, and the settings page supports search, sorting, multi-select batch restore and emptying the whole trash.

Dispatch a task to a real DSH session by workspace path or session id; results land in a persistent task ledger that can be queried without triggering the model. It serves HTTP on 127.0.0.1:7391 and requires a bearer token it generates on first run (kept in ~/.dsh/relay/token), rejects non-loopback Host and foreign Origin, and stores task results as JSON files under ~/.dsh/relay/tasks; an optional notifyUrl receives each finished result.

Pause or resume the running task from a 28 px button beside the DSH composer: safe pause lets the current step finish, holds the next agent/pre-step boundary, and resumes the same turn without a continuation message; force pause cancels immediately, and the default granularity is configurable in Settings.

Replaces LLM summarization with deterministic text compilation, so compaction makes no model calls and keeps original tokens; elided content stays retrievable through seq pointers. Based on TsFreddie/dsh-compaction-instant.

Edit and resend or regenerate a message you already sent, including while its answer is still streaming: the plugin stops the running turn through the official Session.cancel, waits for the session to go idle (8s cap), then rewinds that message in place the same way dsh-redo does. Command is /relive so it can coexist with dsh-redo.

Adds a Q&A agent preset that answers each new question from a clean context: earlier exchanges leave the model input via a surface replacement, with no extra model call and no summary residue. A /qa follow command and a composer toggle switch to follow-up mode, and /clear archives the session and opens a fresh one under the same preset.

Adds "Delete session (move to recycle bin)" and "Delete session permanently" to every session row's right-click menu, with an in-app recycle bin for restoring or purging entries.

Session-archive layer for DSH. It injects one per-workspace Markdown file into the system prompt on every turn, searches past session transcripts with AND keywords, an optional time window and a workspace filter, and recovers the images and documents those past sessions carried by returning their original local paths or copying them to a chosen directory. It also reports index health: version, entry count, cache usage, frequent sessions and sessions stored in an archive format it does not recognise. Keyword search only, no embedding service.

A patched build of ranxianglei/billion-context (MIT) with the author's model-request accelerator folded in: verified snapshot reuse, parent-session inheritance for forks, outbound request-body compression, and image folding after the first send.

Manual session handoff: when you decide a session has run out of usable context, one click turns its event log into a compact handoff document (goal, done, next, project facts), creates a new session seeded with it and wakes it to continue; the new session can inherit the session-bus name as <name>-handoff. No threshold, no timer, no automatic trigger.

Keeps a root turn open until progressing child agents and the current-turn background jobs it started settle, then asks for one self-contained final answer in that same turn. Idle children that still have parked input do not delay closing. It observes job settlement without consuming job output, never cancels children, and does not decide task success. Verified on DSH 0.2.2-rc.2 only; on any other host version it stays inactive, logs one warning, and turns close natively. Each batch of results that arrives after a reply costs one extra model call; ordinary questions add none.

Checkpoint-and-resume for interrupted runs: when a conversation reaches a key step — two consecutive successful file writes/edits, or one successful test command — it appends a lightweight record (timestamp, step type, tool, ≤200-char argument summary, result status) to a local JSONL file, keeping the newest 50 and pruning after 24 hours. After DSH restarts, the session_recovery tool lists unfinished sessions and resuming one creates a new session whose system prompt carries only the last three checkpoints (≤500 characters) instead of the full transcript.

Collapse older messages in long conversations and permanently delete sessions you no longer need.

Folds older oversized tool results into spill files and replaces them with short, deterministic stubs at step boundaries, with no LLM call: the stub keeps the first 200 and last 80 characters plus the sequence number, tool name, line/char/size counts and the original file path, and each fold is a real surface replacement accompanied by compaction/prune shadow pricing so token counts stay honest. Triggers on context pressure at 25% of the model window (falling back to 32768 tokens when the window cannot be resolved) or on five accumulated candidates; the last three turns, error results and rich content are never folded. The original is recovered from the session log rather than the spill file, so /folds, /unfold <seq> and /unfold all keep working after spill cleanup; session_fold_recall lets the model fetch a folded result by sequence number or by keyword, and session_fold_diagnose reports the effective settings. /spill-prune removes orphaned spill directories, preview only unless --apply. A Settings page exposes 12 of the 13 options as draft-then-save fields; they are volatile, so saved changes apply without restarting the plugin.

Bookmark a passage or a whole message in a conversation and jump back to it with one click.

Keyboard navigation for the DSH Web GUI: hold Control for 1-9 conversation numbers in the sidebar, Control+Tab to cycle, Control+J to jump to any conversation from a panel that also lists collapsed and not-yet-rendered ones, double-tap Option for clickable hints, and Option+Enter to focus the composer.

Puts a domain bar under the session header — a domain groups skills and tools and toggles as one block, so one click loads or unloads every member. Hovering a chip lists its members (skills, then tools) in a height-capped panel that scrolls. The right end of the bar is a compaction-threshold counter (− 5 +, 100k tokens per step) that rewrites the live compaction engine policies, so the compaction trigger line changes on the next turn without restarting dsh; a degraded fallback turns the number amber and is reported in the snapshot. Settings maintains domains and members with search, skill/tool tabs, all/selected/unselected filters and a copyable AI grouping prompt. Tool removal uses tools.restrict plus a guard; hiding a skill re-registers it with modelInvocable false, so it leaves the model catalog while /name still works. Sessions of another preset are left untouched.

Session archive with tags, notes and per-session metrics, plus a Plan-Do-Check-Act loop over the archived sessions that produces prompt and AGENTS.md rules and re-measures them on later sessions. Runs locally without calling a model.

Cites one specific message from another conversation: the @ menu inserts a chip, and at send time the quoted text is injected as untrusted background; a conversation_history tool also lets the model search and read other sessions of the same workspace. The @ menu searches the indexed sessions of every workspace (only the model tool is limited to the current one), and its HTTP routes (/dsh-message-cite/api/…) are guarded only by a marker header, not by a DSH access check.

Export a DSH session tree (lead plus subagent fleet) to two Markdown files from one frozen snapshot: a readable narrative summary and a complete raw archive. Target directories are checked against the session file policy, and a blocked location falls back to the workspace exports folder.

Adds a "Delete session" item to the sidebar session menu that moves the session transcript directory to the Windows Recycle Bin, or to a plugin trash folder under ~/.dsh/plugin-data when that is unavailable (restorable either way), and deletes its spill files and projection cache in one request, detaching a live session first and cascading to its subagent sessions. A setting switches the confirmation step off so deleting takes one click; duplicate delete items registered by other plugins are collapsed so only one remains.

Adds "Delete conversation" (zh/en) to the sidebar conversation menu. Confirming removes the durable session log under <DSH_HOME>/sessions, drops the id from the workspace registry (sessionIds, pin, archive), detaches a live session before its files go away, and emits api-session/removed so every connected client drops the row.