Plugins

Watches installed DSH bundles for load failures and dependency drift, brakes repeatedly failing tools, and attributes token cost per message source.

Collects the failures recorded in DSH session logs — tool failures, turn failures and model retries — folds them into one table merged across sessions and sorted by frequency, showing category, source, error code, count, last-seen time and a summary per row. Each row can start a new session draft pre-filled for root-cause analysis or for prevention (sending still needs your confirmation), and ignoring a row only hides it in the panel without deleting logs.

Observation-only audit for DSH Agent Teams that records per-request cache usage and prompt-prefix rewrites to JSONL, with no tool or prompt changes.

Manual context compaction for DSH Agent Teams, adding a scoped compact_context tool and the /compact-agent command.

Let your agent understand your players. Glitchless for DeepSeek Harness: game observability tools over MCP (ranked findings, frame times, errors, where players quit, each game's own dashboard) and skills that add Glitchless to a game in Unity, Godot, Unre

Derivative of cheesehaqi/dsh-qq-onebot-bridge with the same package name, so the two cannot be installed together. Bridges a personal QQ account into DeepSeek Harness over OneBot 11: private and group messages become per-conversation agent sessions and replies are sent back to QQ. Ships a reverse WebSocket server, allowlists (empty = deny all), @ parsing, image and SILK voice handling, and a separate local console on 127.0.0.1:8880 with the decision trace, offline replay, event injection, a read-only preflight and host/Waylay start-stop controls. Needs a separate OneBot v11 implementation (a third-party unofficial QQ client): the default, Waylay, injects into the official Windows QQ.exe (Windows 10/11 x64 only) and is distributed as a separate release archive, not bundled in this repo. botQqAllowed and replayGuardEnabled are edited in DSH Settings > QQ助手, and the replay guard is armed automatically when the logged-in account changes.

Read-only behavior audit for DSH sessions: flags unsafe actions in 8 categories (A–H) with rules for 14 subclasses (the 41-subclass taxonomy file is not shipped, so a built-in 14-subclass fallback is used), anchors every finding to a real event seq, and gives deep links plus the full tool-call / data-access chain of any assistant reply (parameters, results, files read and written, domains, sandbox and approval context). Every finding is drill-downable.

Live architecture map of DeepSeek Harness: renders plugins, services, tools, sessions, models and MCP as a five-layer diagram of 14 component domains, and animates the real tool/model/session call flow as moving dots along the connecting curves.

Ship OpenTelemetry GenAI observability and multi-device cloud state sync from one DSH bundle. It reuses and replaces the standalone @loongsuite/dsh-plugin (traces + metrics for sessions, agent loop, LLM and tool lifecycle; do not install both — disable or remove the upstream plugin first), and adds a WebSocket client that pushes full session event logs (header + snapshotEvents) to a relay you run so different local DSH instances share state. On connect it pulls and rebuilds the other devices' sessions automatically (cross-device resume). The sync client itself has zero third-party runtime dependencies; a small Node.js relay is included in the repo. The local /cloud-sync/* HTTP routes (status, sessions, config, resync, delete) have no origin or loopback check, and the bundled relay accepts unauthenticated connections unless AUTH_TOKEN is set — keep the DSH web port off untrusted networks and run the relay with a token.

Reports DSH session token usage from the local session logs as a host-side tool: totals, input, output and cache-read split, a per-day timeline, usage grouped by day or session and optional cost estimates.

Tells the parent agent when a subagent died from an upstream failure instead of finishing: it listens to agent/error on every agent, waits a short settle delay, and if the child is still not running delivers a followup turn to the parent carrying the child id, the failure and the options the parent has, with a cooldown and a per-child cap so a flapping provider cannot flood the parent.

Read-only observer of native DeepSeek search model calls: appends each call token usage to a JSONL file so accounting plugins can price it. Requests and responses are not modified.

The missing receipt for DeepSeek prefix caching: replays local DSH sessions, prices every call at official peak/off-peak rates, and produces an HTML receipt plus a shareable card.

Token cost monitoring, call-efficiency analysis and reversible tool-output caching for DeepSeek Harness.

检查告警链路：有没有告警、发到哪、有没有把敏感信息一起发出去

会话成本审计：看看一次对话的 token 花在哪、哪一步贵，并把优化建议做成一键可应用的修改。

Shared diagnostic log used by the Claw agent governance plugins (dsh-claw suite).

Registers named Claw agents, isolates them from the official workspace sidebar, and provides settings plus a global new-agent template. Hard deps (install together or single install fails): dsh-claw-policy, dsh-claw-observability, dsh-claw-permissions.

A tiny always-on floating tree of the DSH workspaces, conversations and subagents that are running, waiting on you or on a schedule — live running state, who is waiting for your call, per-row model, scheduled-run countdowns, other local dsh instances with their ports, and local claude/codex CLI processes with their codex subagent threads.

Adds a conversation view that maps which skills, MCP tools and subagents a session actually used, with an attribution tree, a call table and an unused inventory.

Scores each assistant answer on five dimensions plus topic coverage, shows evidence, and turns the weakest dimension into copy-ready prompt advice. Observational only; local by default, with optional Jev review.

Live done/now/next card above the composer while the agent is still working.

Context observability and control for DeepSeek Harness: cross-session token analytics, session-level budget/prompt/tool controls, and optional agent scaffolds. It reuses the official tokenMeter, compaction, systemPrompt, and tools.restrict seams; monitoring is read-only.

Turns declared health readings — source, criterion, verdict — into one read-only verdict; an unreadable source is reported as `unknown`, never as healthy.