Plugins

Five production-grade DSH tools bundled into one plugin (8 tool slots total): git regression finder (find introducer, recent changes, bisect, blame age), stack-trace decoder with local code context, YAML/ENV/properties config validator with typo suggestions, cross-platform shell escape (POSIX/PowerShell/cmd), and MyBatis Plus SQL static auditor (N+1, missing @Transactional, LIKE leading %, SELECT *, missing WHERE). Zero npm dependencies, all offline; concurrency-safe except the bisect tool (dsh-when-broke). Each sub-plugin is also installable standalone (dsh-when-broke, dsh-stackdecoder, dsh-config-guard, dsh-cmd-shield, dsh-mp-auditor).

Adds a download_file tool that fetches a URL over 16 aria2c connections and falls back to a single stream when aria2 is unavailable. Needs aria2c installed separately; the aria2 channel does not verify TLS certificates.

Release gate for AI answer quality. Two channels: replay an existing VeriScope archive through the original Python quality gate, or run a threshold gate over a Ragas per-row export with Node only — no VeriScope, Python or pandas. Returns PASS, FAIL or REVIEW with source evidence and a re-checkable receipt; supports per-row thresholds and exact decimal comparison. It never re-evaluates and never calls a model, and REVIEW never becomes PASS.

Creates and edits Feishu and Lark cloud content through ten tools - Bitable databases and their records, documents with Markdown converted to native blocks, spreadsheets, wikis, drive files and messages - plus Base V3 dashboard charts and server-side aggregate queries.

Local BM25 auto-recall, a fail-closed write guard, a static doctor and a memory panel for an Engramory markdown store. No network, no daemon and no model calls unless you opt in; recall quality is measured by a reproducible benchmark in the repository.

Notes-backed context compression for DeepSeek Harness: replaces LLM-summarized compaction with a model-written persistent notebook plus recoverable raw history, so the rollover boundary itself costs zero model calls.

Turns a local Markdown vault into two folders the user picks in Settings: a knowledge folder DSH writes notes into, and a memory folder used as the agent's long-term memory with per-turn recall and end-of-turn capture. Pure Markdown with frontmatter, BM25 search, reversible archive, and path isolation that rejects traversal, absolute paths and symlink escapes.

Runs the upstream Headroom compression toolkit (headroom-ai, Apache-2.0) inside DeepSeek Harness over MCP: headroom_compress, headroom_retrieve and headroom_stats are exposed as mcp__headroom__* tools backed by the upstream server, installed on demand by uvx. Compression is lossy but reversible — originals are fetched back by hash from a local CCR store. Also ships a registrar that adds DeepSeek Harness to Headroom's own MCP registry, and a model-header sanitizer for the upstream proxy.

A private memory library for DSH with customizable personas that only records when you ask, storing everything locally in Markdown.

Delete DSH sessions into a restorable recycle bin — subagent sessions follow their parent as one tree, batch archive, restore and purge are supported, and only purge destroys bytes.

Standalone prompt assembly with a source registry, custom text, strategy editing and previews, and per-session strategy snapshots through DSH public hooks.

Deletes a whole conversation from the sidebar session menu, and opens a right-click menu on a chat text selection with Copy, Quote (insert a Markdown quote block into the composer) and Ask: Ask sends the selection plus your question to one reused continuable subagent (label `ask`, found again through the subagent catalog after a restart) and streams the answer into the right sidebar.

Groups the sessions that hand off to each other into one chain in the DSH sidebar — automatic chain detection from the handoff prompt, per-chain numbering, in-place rename, search, drag and multi-select to re-chain, pinning a chain to the top, archiving chains out of the sidebar into a panel-only archive, a per-session context/steps readout, and configurable handoff thresholds that can trigger an automatic handoff (write the next prompt, open a new session, paste it, switch over).

Lists DSH session records and archive caches on a sidebar page, moves deletions into a restorable recycle bin, and refuses sessions written within the last 10 minutes.

Mirrors other coding agents' sessions into DeepSeek Harness as continuable tasks, one workspace per application.

Exposes every model of every provider configured in DeepSeek Harness through one OpenAI-compatible endpoint on a fixed loopback port, with a sidebar page for the base URL, key, port and model ids.

Grok model provider for DeepSeek Harness with model discovery, image and video generation, text-to-speech tools, and durable local media tasks over an OpenAI-compatible gateway.

Connects the MiniMax Code models to DSH - reusing the desktop app's sign-in or signing in on its own - with Anthropic-compatible model access, a live model catalog, the daily check-in that grants the free credits, and a credit balance that follows the model you selected.

Bridge DSH to OpenCode-compatible models via the local OpenCode CLI: native LlmAdapter passthrough, persistent OC sessions with cross-turn tool results, tool mirroring, and a CLI environment check panel. Requires the OpenCode CLI installed locally.

Adds Standard Compute as an OpenAI-compatible model provider through the built-in pi-ai adapter, with its standardcompute router model and two direct model pins; configuration only, no code.

Only the domains you list go through a proxy: add a model host that needs the proxy to be reachable, and web search plus every other request stays on the normal network. Multiple named proxies can serve different domains, with a never-proxy list on top; saved settings apply on the next request without a restart.

Tiers free-channel models into three 1M fallback chains plus a custom chain; orders them by measured throughput, drops models below throughput or error-rate thresholds, and rotates accounts. Requires an OpenAI-compatible gateway (default :8326).

LocalAI provider for language models, embeddings, reranking, speech, and image generation with LocalAI-specific controls in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Jina provider for embeddings and reranking in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.