Plugins

In-place conversation rewind in the same session window without forking (Claude Code /rewind semantics): a per-message ↶ button cuts the model context back to any user message, with an optional Claude-Code-style file restore from disk-persisted before-backups.

Rewind a DeepSeek Harness conversation and its workspace together, without touching Git: every rewind is a fork, /redo reverses it, and a Rust engine snapshots in milliseconds.

Installs four multi-agent math-research presets for DSH: v2 (probability-driven pipeline with multi-verifier debate), v3 (paper-style Markdown knowledge base with a planner agent and a reusable method library), v4 (persistent self-organizing residents that message and meet), and v5 (a research institute with an academician who decomposes and assigns work, voting researchers, temp workers, group chat and a compare-and-set task board); all four support checkpoint resume, human intervention, and an optional Lean formal-verification switch (off/encourage/require) whose passing proof turns the vote into a fidelity check of the Lean statements.

Visual branch brainstorming that creates an isolated Session for each direction, automates parent, sibling, checkpoint, and return Handoffs, and provides a full tree tab with an optional Better Sidebar view.

Claude Code /rewind for DeepSeek Harness: git-first workspace snapshots before every mutating tool execution, turn-boundary session forks, and a one-shot /rewind command that restores files and forks the session back to a checkpoint.

Carry durable task state across DeepSeek Harness, WorkBuddy, Claude Code and Codex with machine-readable checkpoints and optimistic locking.

DeepSeek Harness bundle registering one skill that turns long-form production (academic papers, industry analysis, business commentary) into a 9-role pipeline: T1 literature / T2 data / T3 case scouts running in parallel, T4 analyst, T5 writer, T6 critical companion, T7 auditor, T8 finalizer run by the coordinator, T9 peer reviewer — across 6 phases with triangular evidence verification, a 23-check M-gate, a G0-G14 audit including a Chinese AI-trace gate, peer-review scoring with journal matching, and 4 human checkpoints. Installs with `dsh plugin add lunheng-article-pipeline` (package.json#dsh.bundle.patch plus a lib/index.js entry that registers the skill); ships role cards for T1-T9, templates and 11 zero-dependency verification scripts, with five-language READMEs.

Browses checkpoints produced by dsh-checkpoint-rewind as a timeline of time nodes and shows per-file line diffs between any two of them, with trace replay from session logs (no snapshot producer needed) and preview-first workspace rollback with single-shot undo, via /diff and /rollback commands, a JSON HTTP API, and a GUI panel.

Engine-enforced guardrails for DeepSeek Harness agent swarms: quality gates reject half-done work, crash-safe checkpoints resume in place — keeps AI teams from breaking, not just running.

Runs AItelier pipelines from DSH over MCP: 39 tools (22 read, 17 write) to generate, run, inspect, edit, export and import multi-step SkillFlow pipelines. The steps execute in AItelier rather than in the DSH session and are polled by run_id, pause at engine-enforced checkpoints answered with answer_checkpoint, and leave per-step traces and step outputs to read afterwards; add_provider / map_model / edit_role point an individual role at a local or cheaper endpoint. Bundles an aitelier-pipelines skill.

Explicit cross-session work state for DeepSeek Harness: goals, decisions and next steps captured automatically from host events or via a model-visible work_state tool, inspectable with /checkpoint.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

TRAE-style conversation rollback — per-turn checkpoints (10-turn sliding window) roll back touched files and truncate model context in place, keeping the same session id. Human-initiated only: a /rollback command or a per-turn Web button (works on interrupted turns too), with a preview listing each affected file and its action — restore, recover, delete, or skip.

Browser patrol & website inspection plugin for DeepSeek Harness (DSH). Teach once, replay deterministic runbooks with managed Chromium, screenshots, credentials, checkpoints and selector recovery.

Multi-language subtitle translation workflow for dsh: SRT/VTT parsing, sentence-level LLM translation, bilingual merge, batched with resumable checkpoints.

Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.

Incremental diff reviewer for DSH: after approving a batch, only new changes since the checkpoint are shown, with a Web review panel and `/review` command that inject feedback back to the agent.

Adds approval-gated Git status, diff, log, commit, branch, and optional checkpoint tools.

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.

Workspace checkpoints per tool call: records every file mutation inside the workspace (excluding .git and node_modules by default), including changes made by shell commands rather than by write/edit, and stores the previous content of each changed path in a content-addressed store kept outside the workspace. Restores have two modes — undo one record, or return to a point in time — with a line-level diff preview, a dry run by default, and a rescue record written before every restore so the restore itself can be undone.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Smart checkpoints, workspace safety guards and instant rollback for DeepSeek Harness.

Session-memory autopilot: watches DSH sessions and extracts OKF entries in-process through the harness LLM (ctx.llm, deepseek-official by default) at idle, commit, compaction and end checkpoints, storing them via the vault MCP server.

Percent-progress scoreboard docked below the todo pill: tracking_write rows with evidence-bound percents, host-captured git checkpoints with before/after deltas, and pursue/align/dismiss actions that reach the agent as instructions.