Plugins

High-reliability Feishu/Lark bridge for DeepSeek Harness: QR one-click auth, card-based commands and intent-confirmation cards, at-least-once zero-loss outbox, media in/out, /doctor session-log ZIP, and a reusable DSH Web GUI that lands sessions in the right workspace.

One-click prompt enhancement in the composer — rewrites the draft into a structured prompt (role and goal, executable steps, output format, acceptance criteria, edge cases) with before/after preview, fill-back, and undo. Never changes intent, never fabricates requirements.

Adds an optimize button beside the composer that analyzes and rewrites the prompt draft with SSE streaming, conversation-context awareness (template vs intent-polish strategies), an edit-continuity memory chain, undo, and model routing with fallback and a connectivity test.

Auto thinking-effort routing for dsh: a locally fine-tuned 7-question classifier (ModernBERT, 842MB, <1s CPU inference) picks low/high/max for no-intent messages; in-session retries escalate the tier (low to high to max) under exclusion constraints; the judge service fails safe to low if unreachable. A tier chip in the input bar shows the live tier and the last 20 judgments. All inference is local - task text never leaves the machine.

The organ kernel of Agent-Body: plugins organized as one body. Each command is turned into a nerve impulse that deterministically innervates the organ which should handle it and names the capability to use; a heartbeat with a variable interval (faster on alerts, slower when idle) pumps operator directives, proprioception and homeostasis warnings system-wide; reflex arcs fire with zero model calls; failures go through deterministic attribution (missing tool / arguments / permission / timeout / network), a prescription, and a re-check loop, with argument errors never auto-retried. A missing organ is compensated by the one with the highest capability overlap, and tool schemas are gated by the current intent (84.7% measured reduction, reproducible in-repo). This entry is the kernel plugin package inside the agent-body repository.

Windows workspace pre-authorization: adds an explicit full-control DACL ACE (including WRITE_OWNER, required by dsh >=0.1.7 sandbox startup) to user-declared workspace directories, removing the repeated full-access escalation prompt. Grants only on explicit intent — new workspace records or paths added in the plugin settings page; system directories are hard-blocked. Windows only.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.

Old conversation is folded into short summaries by a side model before the window fills (on-disk ledger survives restarts and re-anchors after host compaction), so long sessions stop getting more expensive every turn — one real full-day session: 6 folds replaced 209 old messages and the live context stayed in the tens of thousands of tokens. The session model picks the model per subtask across six pools (economy/mechanical/main/hard/vision/review); or pick Auto and a small intent classifier routes each message itself, switching only past a confidence threshold to keep prompt caches warm. A three-line watermark ends in an automatic four-step handover (fork backup, handover doc, compact, wake) without losing in-flight subagents; /ctx-pause, /ctx-resume and /ctx-handover keep it manual when wanted. Optional Agent Teams mode adds teammates and a shared task board; /vision gives text-only models eyes via the vision pool; tiered verification sends bigger diffs to a tester plus an independent reviewer. Settings UI, READMEs and language preferences cover the same 11 languages. Bundles three skills: read-only MySQL/Redis verification, commit-message generation, and a requirements/design document convention.

Five-layer intent recognition pipeline (rules, pgvector retrieval, Jev scoring, fine-tuned arbitration, LLM fallback) with scenario management UI, PostgreSQL storage and distributable API services.

Read-only DeepSeek web archive tools for DSH: list/download/search sessions, share-list, and a digest tool that compresses the 100-session history into one high-density page with activity bars and topic clusters. Write operations are intentionally not exposed (the web client rate-limits them). Requires the separately installed deepseek-ops Python client (github.com/Panniantong/deepseek-ops, by another author) with QR-code login; set scriptDir to its path.

Composer prompt enhancement for DeepSeek Harness: a button beside the model selector rewrites the draft through one auxiliary LLM call and writes the result back in place, with composer undo left intact; a /prompt-enhance slash command returns the rewritten prompt as a command result line without touching the draft; the enhancement call can be pinned to its own fast provider and model in the profile patch; the rewrite policy is faithful - original intent, language and information are kept, code, commands and paths are preserved verbatim, and nothing is invented or padded with placeholder text.

Java efficient development plugin for DeepSeek Harness providing deterministic auto-fix for .java files, token-saving template intents, and cross-platform JDK/Gradle/Android SDK/FFmpeg/LWJGL/IDEA discovery with persistent caching.

Deep PTC mode is an open-source agent preset for DeepSeek Harness that keeps the built-in PTC tool surface and replaces the persona with a working contract: a DeepSeek identity and unlimited-token-budget instruction so the model does not skip reads, commands or checks to save tokens; planning by estimated size (internal up to 5 minutes, shown without approval up to 20, approval required beyond); and asking about unclear intent instead of guessing. Waiting is limited in code by wrapping the official shell, job and question tools: foreground commands move to background jobs after 30 s (configurable), a steered user message ends the current wait so the model reads it, foreground pauses over 5 s and long timers in run_code are refused, and questions run in timed mode. The mode derives its preset from the official PTC declaration shipped by the installed Harness and inherits upstream composition changes, so an official PTC update — including removed or renamed modules — does not break existing sessions. A settings card selects the preset executor — Automatic, WSL Bash, Windows PowerShell, native Zsh or native Bash.

Adds a ✦ button below the DSH composer that rewrites the current draft into a more complete prompt with a single call to the configured default model, keeping the original intent and language, and replaces the draft in place without sending it.

Chat-driven image-deck workbench for DSH: intent to storyboard script, per-page prompts and AI image generation with page-level revisions, nine design-style presets, and PDF/PPTX export (one full-page image per slide).

Four-tier prompt enhancer for the composer — the system tier always emits a LangGPT-structured system prompt (# Role / Profile / Skills / Rules / Workflows / Initialization), upgrading task drafts into the system prompt of the agent that runs them, while the other tiers rewrite as a light tidy-up, a single paragraph, or a five-section brief; the iterate workbench refines an editable base under an optional requirement, with fill-back and undo. Never changes intent, never invents requirements.

Four-tier prompt enhancer for the composer — a button and a global shortcut rewrite the draft as a light tidy-up, a single paragraph, a five-section brief, or an eight-section system prompt, with a before/after panel, fill-back and undo. Never changes intent, never invents requirements.

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.

Intent fitting for DSH: the agent predicts several directions first, asks a batch of clarifying questions each round, narrows the distribution until one converges, then proposes it for your confirmation. Bottom-right floating panel, local JSONL archive, a

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.

Cadence SKILL (Virtuoso Lisp) assistant for EDA engineers: official-doc-anchored API lookup (3557 entries across 5 IC6.1.8 manuals, signature confidence levels, never invents APIs) plus zero-execution static analysis driven by a lexical depth coordinate system — iterator-safe deletion with position-sensitive copy() protection, printf placeholder/argument reconciliation, in-loop nth O(N^2) detection, deprecated APIs with page refs, dangerous-intent interception and CIW error-log triage. Host half has zero third-party dependencies.

Instantly find DSH settings pages, tabs and rows by keyword, pinyin, intent or AI — and jump straight to them.

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.