Plugins

Floating Bilibili video mini-player for DSH — always-on-top window with discover/search/follow-UP channels, auto-playlist, mini & focus modes, persisted watch history and window minimize-to-ball.

DeepSeek Harness plugin: 账户余额 + 会话费用（/balance /cost 命令、deepseek_billing 工具、Web UI 双胶囊），官方价格每 12 小时自动同步

Fail-closed Feishu (Lark) channel bridge: chat with a bot, get dsh agent turns back — with opt-in human-in-the-loop tool approval (Allow/Deny cards before every bash call, fail-closed timeout). Official-Python-SDK-only integration (exact-pinned); deny-by-default allowlist, webhook signature/timestamp/replay verification, per-chat sticky sessions; daily latest-SDK compatibility canary; bilingual docs.

DeepSeek account balance and per-session cost card in the sidebar foot.

Circuit breaker for idle agent turns: watches agent/assistant-stream and cancels a turn that produces only reasoning — no text and no tool call — after 45s, after 80000 reasoning characters, or on a degenerate repetition pattern (exact repeat unit, sentence-template repeat, sparse repeat, or 6-gram density). On trip it injects a continue instruction that requires the next action to be a tool call, and ships 11 regression cases plus per-gate tuning.

Behavior-drift reports for DSH sessions: compares two session logs and reports tool-sequence alignment, tool mix, reasoning volume, timing, retries and file targets, with an optional CI threshold gate. Zero dependencies.

TypeSafe Jev (System One decision model) as the jev_decide tool for DeepSeek Harness: noul, choice and score questions return calibrated probabilities; credentials reuse the DSH credential seam; 429/529 backoff retry built in.

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.

Persistent Endeavour and Challenger peer sessions for DeepSeek Harness that plan, execute sequential tasks, and verify reported results.

Generic workspace base for the dsh harness (local + remote workspace providers with per-workspace routing), with SSH as one concrete provider: bind a server directory as an SSH workspace so the session's file I/O and commands run on that host, manage host

Read assistant replies aloud in DeepSeek Harness: text-to-speech providers with streaming playback.

Zero-config lint feedback loop for JS/TS, Python, Go and Rust: lint_diagnostics / lint_workspace_errors / lint_fix tools driven by the repo's own eslint / biome / ruff / golangci-lint / cargo clippy (auto-detected from config files, repo-local node_modules/.bin resolved first, nothing bundled), plus an auto-injected post-edit findings delta on the harness fs/observed event and a bounded completion gate — edit → lint → auto-repair with one lint_fix call for dsh agents.

SSH workspace and operations for DeepSeek Harness: bind a server directory as a workspace whose fs/subprocess calls route to the remote host via cordis seam replacement, plus web terminal, file transfers, tunnels, cluster runs and host management.

Adds a reasoning-level editor with OpenAI and Anthropic protocol presets (llm-pi-ai), input-modality switches and a 1M/128K context and max-output preset to model rows in Settings.

Remote-control bridge: pair a running dsh web/desktop client with the Happy mobile app by QR code, then remote-control the same harness sessions from the phone (send messages, read replies, approve tool calls, switch models)

Auto-fills reasoning-efforts, context windows, output limits and image modality fields for models from unofficial (custom) providers (with data from models.dev), and provides user experience improvements such as compatibility enhancement and remembering reasoning effort.

Multi-machine, multi-agent orchestration and control plane for DSH: discovers Agents and workspaces across devices, routes tasks by machine, repository, capability, and load to local or remote Agent runtimes, streams progress and results, forwards approvals, and recovers durable tasks after disconnections.

Tender search and bid intelligence in DeepSeek Harness with proposed project search, rule screening, human review and Excel/PDF exports using user-authorized Qichacha MCP.

Zhipu (GLM Coding Plan) web suite as native DSH providers and tools: rebinds the built-in web_search and web_fetch to Zhipu web search and Markdown page reading, optionally registers github_search_doc / github_get_repo_structure / github_read_file repo tools, and adds a settings card with toggles and a credential-ref field.

Aqua glassmorphism theme for the DeepSeek Harness web UI: mica and compatibility modes with adjustable blur and frost, fluid or wallpaper backdrop, background brightness, particle-whale accent, and a master switch that restores the stock UI.

An unofficial Arknights P.R.T.S.-inspired interface theme for DSH Web with appearance presets, accessibility controls, and conversation navigation.

Conversation Flow observability for DeepSeek Harness swarms, with topology, routed-message inspection, HITL pauses, Live follow, and child-session navigation.

Hebrew RTL rendering for the web GUI: per-block direction by dominant script, bidi-safe input fields, and RTL-aware Cmd+Left/Right line navigation.

Live2D companion for DSH: a floating Cubism model with state-driven expressions and mouse tracking; config-driven geometry (size/position from the plugin config); official Haru sample bundled (© Live2D Inc.).