Plugins

Requires the Codex CLI installed and `codex login` completed. Consult the OpenAI Codex CLI from DeepSeek Harness with three tools: codex_consult runs Codex in a read-only sandbox, inlines evidence files, verifies the served model and reasoning effort from the Codex rollout file, retries disconnected streams, and records quota before and after the call; codex_quota reports the current 5-hour and weekly quota; codex_calls lists recent calls.

Injects the contents of a .keep-reminder file from the session working directory as a system-reminder, with three modes: once per session, first step of every turn, or every request.

Registers a janitor_scan tool that returns a deterministic, reviewable cleanup plan for session debris (plan docs, scratch scripts) with per-file verdicts and evidence; scan-only, never deletes.

LittleStar Meeting Room: bring AI sessions that cannot see each other into one room — for a meeting, or a game of werewolf. By 插件·2代小星辰 (LittleStar) and 辰启星明; the four-piece game layer (targeted visibility, private chat, concurrent asks, elimination) was contributed by 插件·3代小星辰. Any session can host — set the topic and goal, invite members in order, they speak one at a time, and the meeting closes with written minutes; it also runs games like werewolf. Includes 小白使用指南.md, a beginner guide written by 插件·3代小星辰.

Pick the model your subagents run on — with a reasoning-effort ceiling and an output-token cap — enforced in code on every child DSH starts, whichever tool starts it.

JavaScript orchestration over DeepSeek Harness tools using Node.js VM or QuickJS WebAssembly backends.

Cross-workspace worker fleets: one orchestrating session spawns named worker sessions in other project workspaces, queues or steers tasks into them, watches them in the background via a real host job, and collects their reports. Worker completions deliver themselves to the orchestrator's session rather than needing to be polled, so an idle orchestrator still reacts. Escalations and failed workers deliver by steer when the orchestrator is mid-turn and by queue when it is idle; a turn that ends without a report counts as a failure and the worker is replaced after a configurable limit. The roster persists to disk and each worker session carries a durable title, so a restart neither loses the fleet nor spawns duplicate sessions. Ships five agent presets at full plugin parity with the standard preset.

Meeting rooms for DSH sessions: joining a room grants the right to convene and the duty to attend, and a session belongs to at most one room. Convening forks each participant in with its own completed-turn context and with its tools stripped, a moderator that carries no context chooses the speakers, and every turn is appended to disk as it is spoken. After adjournment each participant receives its own minutes as a user turn and resumes work.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

0.8.6 fixes a startup crash: the host runtime package is an optional peer, never an installed dependency. TypeSafe Jev (System One decision model) wired end to end into DeepSeek Harness (0.8.6). Seven tools: jev_decision (1-25 parallel atomic verdicts in one call; noul/choice/score; typed answers with calibrated confidence; measured median 266-484 ms; verdicts only, never prose), jev_choose (rank 2-10 candidate approaches - fit 0-3 and risk - into an explicit composite with a recommended pick), jev_batch (NEW in 0.8.6: one set of 1-5 judgments over 1-20 texts, one real call per text at bounded concurrency, returning a paste-ready markdown table sortable by a judged dimension; built-in sentiment/priority/intent/pii/spam presets; a failed row is reported as failed with the raw error, never guessed), jev_usage (locally measured usage: calls, tokens, estimated cost, latency median and p95, per-tool mix, rolling windows, projected burn rate, optional local hard budgets, and a declared-balance remainder), jev_overview (session ledger), jev_guard_status (guard counters plus a registrations block that surfaces per-surface registration failures) and jev_verify (frozen 27-question live benchmark at concurrency 6: 96.3%, 26/27). WHAT IS NEW IN 0.8.6 - the ledger survives a restart, the remainder is derived instead of invented, and the plugin can now do batch paperwork. (1) The local ledger persists to $DSH_HOME/jev-usage.json BY DEFAULT, so the cumulative total no longer resets when the host restarts. Two real bugs behind the old silent zero were found and fixed: the ledger path only honoured DSH_HOME (absent inside the host process, so persistence was silently disabled and the file name was null), and save() wrote the still-empty in-memory ring over the history file because it ran before the first load while the debounce window swallowed the follow-up write. (2) Remaining is derived, never invented: TypeSafe exposes no balance endpoint - /v1/usage, /v1/quota, /v1/account, /v1/account/balance, /v1/balance, /v1/credits, /v1/billing, /v1/me, /v1/limits and a dozen more all return 404, and only /v1/models answers, with no balance headers - so the panel shows the remainder as your declared balance (quota.declaredBalanceUsd) minus locally measured spend since quota.balanceSince, and says plainly that it cannot be fetched instead of printing a number. (3) The composer pill re-reads every 20 s instead of every 60 s, so a call you just made shows up while you are still looking at it. (4) The collapsed pill leads with the remainder once you declare a balance, and the cumulative row is renamed when the ledger is on disk. Every tool has an in-conversation structured view; the Settings > Plugins card covers credentials, tool switches, the auto-guard, the dashboard, the prompt section, usage/quota and auto-triage. Honest by design: no API key means an explicit error, never fabricated results; every registration is quarantined so a failure degrades one surface. Tests 38/38 (npm test, ~2.5 s). Client half applies on refresh; server half needs a host restart.

Review-first batch automation for DeepSeek Harness: three reviewed samples, a full preview, one approval, then a safe apply across many files.

DSH 自进化信号源：机械挖掘会话日志（重试簇/工具错误簇/中断回合/Token 浪费）→ 结构化问题工单。dsh-darwin 双插件架构的 B 面，可独立安装当会话体检用。

One MCP tool instead of every schema you own — a lazy capability broker that cuts resident tool context by a measured 94.4%. Search, inspect, enable and call MCP servers and skills on demand.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

DeepSeek Harness plugin for organizing AI discussions into research topics, traceable knowledge cards, and reusable research materials on an interactive graph

A focused end-user QA surface backed by native DeepSeek Harness sessions

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.

One-line scaffold generator for DeepSeek Harness agents and plugins.

Compares existing DSH sessions or runs controlled A/B trials between agent presets, showing aligned timelines, paired metric deltas, explicit success checks, and exportable reports.

Local-first HTML review and annotation workspace for coding agents: opens an isolated copy of a file in a browser editor, collects text edits, format changes and element/area comments, and returns a durable handoff the agent can claim and resolve.

“What should we build next?” There’s a skill for that.

Git-native, auditable long-term memory for AI agents

Evidence-first GitHub research subagent with bounded tools and in-memory request caching.

Self-evolution actuator: consumes problem tickets mined from session logs, synthesizes skill candidates (zero-code tiers by default) behind an eval gate with hold-out canaries, then promotes to project .dsh/skills with human confirm and deterministic rollback.