Plugins

Git panel in the right sidebar plus fifteen agent tools: editor-style diffs, a commit graph across every branch, staging and committing, branch, stash and remote operations, and model-assisted commit messages, pre-commit review and commit splitting.

Extreme LLM-call compression for DeepSeek Harness: title short-circuit, in-flight dedup, 24h replay cache, and batch-merging N parallel requests into 1 upstream call via a `[[TASK n]]`/`[[ANSWER n]]` delimiter protocol - fewer API calls, less spend, same answers.

Auto-pairs brackets and quotes in the DSH chat composer, inserting the closing half with the caret in between; it also wraps selected text with the typed pair and handles brackets committed by an IME.

Aborts a DSH reasoning stream that starts repeating itself instead of letting the turn stall: five rules over the streamed reasoning text (periodic unit, repeated block, repeated line above a share floor, 64-gram density, and a long trailing run of punctuation or whitespace), plus a JSONL fire journal, a Web GUI log panel, and opt-in recovery that retries with a corrective message.

Git repository connector for DeepSeek Harness: saved repo profiles addressed by name, work-copy operations (clone/fetch/pull/push/commit), Gitea/Forgejo/GitHub API tools, keys in the DSH credential center, and per-repo safety flags (TLS bypass, overwrite, force push).

Deep-sea whale-blue reskin for the DSH Web GUI: 14 theme tokens in light and dark, five whale-tail-maid placements, a clock and weather card, and a collapsible hardware readout (CPU, memory, GPU, per-drive temperatures via HWiNFO). No backdrop image is bundled; drop your own in. MIT code, MIT character art.

0 Token Git 提交推送插件，一次调用完成，按 Conventional Commits 为每个变更文件自动生成提交信息并按 type(scope) 拆成多次提交后一次推送到Git，必要时询问打标签。One-call Conventional-Commits git workflow for DeepSeek Harness: survey + one commit per type(scope) + optional tag + push, plus a /git-commit-push sla

Vision understanding + image generation/editing for DeepSeek Harness (read images with Qwen/OpenAI/Anthropic/Gemini, generate and edit with Qwen-Image). A rework of liustack/modlens (MIT). Remove @liustack/modlens first — both register the same vision providers and image interception hooks, so co-installation breaks image reading.

Monitors multi-provider balances, DeepSeek peak/off-peak usage costs, per-session analytics, and configurable spending limits in the DSH sidebar.

One-tap connect Agnes language, image and video models into DSH (off by default), with image recognition and thinking level filled in automatically. After signing in to the Agnes console (re-login uses AGNES_PASSWORD), you can see the quota windows (5-hour requests, weekly requests, daily images, video), account-wide cumulative usage, and a usage pill beside the input box. AgnesCode desktop models can be connected too (Windows only), re-reading the desktop app login when the token expires, with rate-limit hits backing off on their own.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

A read-only git browser for the DeepSeek Harness Web GUI: a right-sidebar page with the session's working-tree changes and commit history, and the diff a click opens beside them. The host half reads the repository through ctx.fs and ctx.subprocess, so a r

Preflight checks for a DeepSeek Harness plugin before submitting it to the community list: verifies the dsh.bundle manifest, cordis.patch.yml wiring, client bundle shape, and peer ranges that silently exclude prerelease harness builds. CLI plus one read-only agent tool.

Ponytail lazy-senior-dev ruleset for DeepSeek Harness: a 7-rung minimal-code ladder (YAGNI, reuse, stdlib, native, installed deps, one line, minimum), six skills (main rules, over-engineering review, repo audit, debt ledger, gain scoreboard, help), a /ponytail session command for lite/full/ultra/off levels, and optional always-on ruleset injection via config. Vendored verbatim from upstream ponytail (MIT), zero tools registered, clean uninstall.

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.

Compact Git status line for DSH Web: the current branch, staged and unstaged line changes, ahead/behind commit counts against upstream, and a clean-worktree marker — placeable in the sidebar footer, the session header, or above/below the composer, with the position switched on the settings page.

Long-form novel writing plugin: each book is a git repository of frontmatter files, with 39 DSH domain tools and a web writing UI. Deep import drafts candidates, AI adoption into canonical assets requires DSH approval, and deterministic continuity checks ship with a report-only benchmark. Independent open source (MIT), not an official DeepSeek product; requires Node >= 24.11.0 and currently targets DSH 0.1.2-rc.1.

A right-sidebar Git panel in the IDEA style — local changes with per-file checkbox commits, a commit tree with per-commit details, branch, remote and stash management, push with a credential fallback, all driven by the plain git CLI.

A GitHub-connected visual git manager for DeepSeek Harness: guided GitHub-Flow steps, commit graph with PR/CI badges, one-click GitHub login, PR and issue management, and structured git tools for the agent. Renamed from gitcompass in 2.0.0.

Live Android device pane next to your DSH conversation: scrcpy-server H.264 streaming (WebCodecs, 30-60 fps), agent tap/swipe/text with auto-screenshot verification, uiautomator element tree with tap coordinates, host-managed recording + logcat debug sessions. FLAG_SECURE pages are detected automatically with a mitigation chain and a tappable text-view fallback. Emulators and USB real phones, human+agent co-operation, session-isolated, loopback-only.

Literature search for DeepSeek Harness: pubmed_search, pubmed_paper and pubmed_related over the official NCBI E-utilities (including elink related-article ranking), plus scholar_search and scholar_cite (MLA/APA/Chicago/Harvard/Vancouver/BibTeX via SerpApi). Both backends return one paper shape, and a settings card configures the API keys, the Scholar backend and the rate/result limits.

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.

Knowledge base with a corrective acquisition loop for DeepSeek Harness: when the agent keeps hitting the same failure, a background worker fetches the web under a rate limit, distills the result into a staging area, and only a two-stage commit makes it recallable — pages without sources are refused.

🫶 DSH-Pet（小齐）—— 住在 DeepSeek Harness 网页终端右下角的 AI Agent 桌宠：随工作状态切换姿态，需要确认时挥手说「快来确认」，任务完成时举手说「任务完成啦」。原生插件、可拖动、可换装，MIT 开源。