Plugins

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

Chat recovery for DSH: edit the last finished user message and explicitly retry failed turns, both via session-fork branches that leave the original conversation untouched.

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

Undo/redo & rollback system for DSH: every config change is auto-snapshotted; undo/redo/restore to any version from the WebUI or the offline CLI/GUI tools (works even when DSH fails to boot).

Claude Code-style auto-memory, natively: typed memory files (user/feedback/project/reference) with a MEMORY.md index auto-injected into the system prompt (zero footprint when empty); memory_write/read/list/delete follow Claude Code write rules (dedupe-and-update, absolute dates, cross-links); workspace-scoped and user-scoped layers, cross-process file locking with orphan-lock recovery, plain Markdown on disk, no external services, no embeddings.

Execution maze for DSH sessions: the agent's real path — main advance, failed or dead-end detours, backtracks, request retries and subagent branches — drawn on one wall-clock timeline, with three tracks under each lane sharing that axis (tool-call density, token pulse, context pressure) and a deterministic analysis panel below it (tool result matrix, failure-recovery chains, duration distribution); watch it grow live in a session tab, or upload up to 5 session logs for a same-axis compare.

Manage archived chats with search, preview, restore, workspace bulk archiving, and a Recycle Bin.

One-command backup & restore of DSH user data with a visual Settings panel: scheduled auto-backup, sha256 verification, hardened restore with auto-rollback, typed sub-backups (--types), credential redaction into a local vault, GitHub sync for cross-machine moves, and an out-of-process rescue channel for when the host won't boot. /backup doctor checks and repairs corrupt session logs from a known-good backup; migrate-check predicts which sessions a host upgrade would break (frozen event-list rules, filename mismatch, legacy credentials); the credential sentinel preserves pre-migration copies before the host rewrites them; smart backup snapshots before host upgrades and quarantines corrupt logs before rotation; /backup check-update and /backup update report and install new releases (snapshotting first), and it spans DSH 0.1.1-rc.2 through 0.2.0-rc.1, including 0.2.0's install-time peer gate. macOS/Linux/Windows.

Visual multi-agent DAG workflows for DeepSeek Harness with live execution, restart recovery, and Feishu integration.

Synchronizes DSH profiles and local plugin source archives through WebDAV and S3-compatible storage, with encrypted snapshots, conflict-aware recovery, and explicit self-updates.

Git worktree Session Targets with isolated task sessions, Ready for Review, reversible Local Preview, human-confirmed delivery, environment retention and recovery, and same-session iteration.

Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness — continuable children, durable session recovery, per-role product permissions, and delegation with a permission ceiling.

Harness-neutral reliability infrastructure for AI coding agents: reversible destructive actions, pre-emission redaction, recovery evidence, and a shared Decision Protocol with optional native adapters.

Workflow One - Visual AI workflow orchestrator for DeepSeek Harness (dsh): multi-agent DAGs, live execution, recovery, and Feishu integration (single-package edition)

Restart recovery for DeepSeek Harness web: after a crash or restart, an interrupted agent turn continues automatically (host-side agent/created listener, no browser timing races).

Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Keeps a pool of API keys per provider with auto-created clone routes, switches to the next key on quota or rate-limit errors, probes cooled keys for recovery, and exposes the pools, cooldown and switch codes in a Settings section.

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Modular frontier execution discipline for DSH: evidence-first routing across 26 skills, Manus-style file planning, verification gates, fail-streak recovery, and an interactive web dashboard.

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

Session deep links, full session export (markdown/JSON), approved cross-session messaging with pairing, and team roster, rotation and recovery tools for multi-session work.