Plugins

Agent-native API client for DeepSeek Harness: Postman-like debugging UI (request tree with context menus and full keyboard navigation, resizable sidebar, layered auto-generated header preview with per-item suppression and constant secret masking), six api_client_* agent tools sharing the same request core, redaction and audit chain with the human UI, Postman Collection v2.1 import with a migration report, environment variables with SecretRef indirection, and a fail-closed SSRF network policy.

SSH session manager for DeepSeek Harness: saved profiles, agent ssh_run, interactive terminals, and SFTP with secrets kept in the DSH credential center.

Scoped persistent memory for DSH: memory_save/search/replace/remove/list across global, user, project and failure scopes, DSH storage-domain persistence with secret and prompt-injection scanning, session-scope search, retention cleanup, and optional session-start injection; standing context via memory_pin/memory_pins/memory_unpin.

Background security auditor for DeepSeek Harness: scans agent outputs for secret leakage, checks command safety before execution, and surfaces findings in a persistent audit log.

Strongly read-only, secret-aware Oracle second-opinion subagent.

Secret-redacted session handoff with review, auto-start, and brief-only modes.

Uses a GitHub App to report open PRs and the latest Actions run for the current repo without returning secrets.

Safe Git Credential Manager hints for WSL without exposing secrets.

Bidirectional bridge between Hermes Agent and DeepSeek Harness. Hermes dispatches focused tasks via JSON-RPC over POST /mcp/collab (one-shot or continuable, nonce-bound amend, secret-bound consult reply); DSH lets you continue Hermes sessions as native DS

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.

Blocks agents from reading or writing sensitive files (.env, credentials, key material), masks leaked secret-shaped values in tool results, keeps an audit journal, and exposes safe sg_* inspection tools that never print raw values.

Automatic secret redaction in tool results: masks API keys, tokens, JWTs, private keys and configured secrets before the model sees them.

Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".

Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, and secret scanning. Ported in spirit from pi-hermes-memory.

/repro exports a minimal, secret-scrubbed, replayable problem bundle: the session log, failed commands, and Git diff.

Adds dangerous-operation policy checks, output redaction, and a security-review workflow.

Extends the official QQ bot channel (@tencent-connect/dsh-qqbot 0.5.3/0.5.4) in DSH with sticker tools, idle proactive small talk, long-term memory and a Settings → Plugins page. Install is manual: run lib/patch-host.mjs to patch six files in the installed channel (backed up, revertable) and --register it into your profile; you also need a QQ open-platform bot (appId/appSecret) with "receive all messages" enabled by a group admin. The channel access defaults to open (anyone who can message the bot); set access.c2cMode/groupMode to allowlist or disabled before exposing it.

Collects passwords through a card instead of the conversation: terminal prompts, the DSH sidebar browser, and Ego Lite, with multi-field forms and live strength rules.

Restart DSH and find out whether it actually came back. Windows has no external way to make Electron quit cleanly (WM_CLOSE just minimises the window), so this plugin does not pretend: it terminates the host, relaunches it with retries, then polls the host port until it really serves again, and reports the outcome to a local result file plus a QQ message when qq-notify credentials (appId/clientSecret/openid) are configured in the desktop profile. Verified end to end on 2026-11-08.

Agent-asked secrets for DeepSeek Harness: a masked card stores API keys and tokens in the local credential store without them entering the chat, then injects them into one command.

Registers the github-push skill so every session follows one fixed commit-and-push flow, with a pre-flight secret scan, an abuse-resistant retry policy, and local-proxy discovery when github.com is unreachable directly. Runs on Windows only: the push skill uses Windows PowerShell 5.1+ and curl.exe.

WeCom smart bot over the official long connection (Bot ID + Secret, no public callback): persona, sender identity tags, three-layer memory with a forgetting curve, reminders, opt-in proactive chat, owner-only work mode guarded by tools.guard, auto-steer, image input and a wecomSoulBot host service; group chats answer when @-mentioned.

Adds three tools that hand DeepSeek Harness downloads to the Rayburst aria2 engine — rayburst_download, rayburst_wait and rayburst_status. Requires the Rayburst desktop app (aria2-next) installed and running on the same machine; the plugin reads its aria2.conf for the RPC port and secret.

Remote access for DeepSeek Harness: expose this machine's DSH Web GUI through an SSH reverse tunnel and a QR gate — scan and enter. Requires your own Linux server with root SSH access plus nginx, openssl and qrencode; it rewrites that server's nginx config, and the QR link is a one-year login secret, so treat it like a password.