플러그인

Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Search, read and write an Outline knowledge base from conversations, with whitelist-guarded approval for every document write.

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.

Audits installed plugin compatibility after a DeepSeek Harness upgrade, repairs or disables incompatible plugins, and keeps an out-of-host supervisor that rescues boot failures or rolls back to the previous host snapshot.

Sanitizes leaked DeepSeek DSML closing tags from model text streams.

Connects DeepSeek Harness to FitMeet through per-user OAuth with 17 tools for people search, gatherings, notifications, personal items, connection feedback, Hall publishing, and direct messages, with preview-and-confirm guards for write actions.

Automatic model-tier routing for DeepSeek Harness: one user instruction enters, one tier decision comes out — complex intent is planned on the strong tier and implemented on the cheap tier, simple intent stays cheap throughout, with a deterministic guard and a TTL escalation fallback.

Crash protection plugin that auto-isolates plugins causing startup crash or hang, with independent watchdog process for total hang recovery.

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

Search, read and write an Outline knowledge base from conversations, with whitelist-guarded approval for every document write.

Install-time patch guard for cross-machine DSH group chat: fixes dsh-weave rc.14 defects (inject crash, random UDP port, 4KB ack frame limit) with four idempotent patches, alongside setup, mechanism and ops docs for the dsh-chat x dsh-weave x dsh-bridge chatroom stack.

Policy plugin that gates kubectl by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.

Service control panel in DSH Web settings: live host info (PID, versions, uptime, memory/CPU trends, active sessions), npm update banner, and a confirm-guarded graceful stop that warns when tasks are running and can wait for them to finish.

Deterministic loop guard: denies a tool call repeated with identical arguments and caps per-agent calls, in code outside the model; incident log lets a parent interrupt a stuck subagent.

Plugin Guard for DeepSeek Harness (DSH): isolate broken plugins so the web UI never goes down, with one-click self-update from npm.

Real-time repetition guard for DeepSeek Harness (DSH): stops model generation when the same string repeats >=10 times in the streamed output. 实时检测 DSH 大模型流式输出中的重复内容，同一字符串重复十次以上立即停止生成。

Mandatory cross-review for design proposals and lessons-learned: auto-detects design doc writes and enqueues them (tier=review) into the task queue, delivers the external reviewer verdict back to the initiating session, and appends approved preventive measures to OPS-GUARDRAILS.md (append-only, conflict-checked).

WebUI panel for the dsh-guardian watchdog: start, stop and inspect two macOS LaunchAgents with status, log tail and explicit failure states.

Neutralize tool calls with invalid JSON arguments on the wire so one malformed model generation cannot brick a session against strict OpenAI-compatible servers.

Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).

Branch-role guard for AI coding agents: configurable integration/preview/production/archive roles, blocking direct push, force-push and delete on protected branches and agent merges into production/archive.

64-entry external CLI catalog with bounded public discovery and guarded package-manager or manual official installation, exposed through DSH tools and a standalone command.

Backs up DSH profiles and mints a desktop "revival coin" that restores the harness after a failed boot or install: a boot guard runs a two-phase health check (HTTP 200 plus client render), marks good boots, isolates or rolls back bad ones, and keeps 3 rotating snapshots. Cross-platform.