Plugins

Plugin web DeepSeek Harness : bouton de solde dans l'en-tête (à gauche du journal de session natif), menu déroulant avec le solde du compte, l'usage de modèle + de tokens par session en direct et des estimations de coût au tarif officiel ; se masque automatiquement sur la page de réglages.

Extension d'assistant d'apprentissage pour DeepSeek Harness (dsh) : tutorat DeepTutor pour votre agent — explications approfondies, questions d'auto-évaluation, parcours d'apprentissage, recherche dans une base de connaissances personnelle (RAG) et archivage de notes (HTTP/WS en priorité, repli CLI ; s'adapte automatiquement au local/distant).

Observabilité Langfuse pour DeepSeek Harness : exporte les journaux de session en traces OpenTelemetry (conventions sémantiques GenAI) vers l'endpoint OTLP de Langfuse.

Sonneries de fin de tâche par espace de travail, plus des sons d'alerte pour l'approbation, les questions, la revue de plan, le blocage d'objectif et l'échec de tâche, avec synthèse intégrée, voix (TTS) et audio personnalisé.

Falsification-driven correction loop for agent sessions: risky work commits an evidence-checkable claim first, deterministic gates verify it, falsified claims force mutually exclusive replacement hypotheses with discriminating experiments, and every event lands in an append-only evidence ledger.

A DSH Web plugin that turns chat sessions into editable mind maps, with Markdown, Mermaid, PlantUML, XMind text, and TODO exports.

DeepSeek Harness plugin: multi-key pool with automatic quota failover and a usage dashboard for the OpenCode Go plan

LAN P2P Collaboration Plugin.局域网内协同插件

Sidebar meters for DeepSeek Harness Web: a DeepSeek account balance bar (orange, with a low-balance alarm) and a conversation context-usage bar (blue), rendered above the plugin store with a hover detail popover.

Show the DeepSeek account balance below the conversation in the web UI. · 在对话下方显示 DeepSeek 账户余额。

Composable working, reasoning, quality, and human-reviewed self-evolution controls for DeepSeek Harness Web.

Composable working, reasoning, and quality controls for DeepSeek Harness Web.

DSH web plugin: sidebar notification panel with per-scene sounds (plan / done / ask / fail) for every finished turn, custom sound uploads, and system notifications while the tab is hidden.

Token usage dashboard, provider balances, and subscription quotas for the dsh web GUI

DeepSeek Harness plugin: live account balance/quota panel for every configured LLM provider (sidebar widget, configurable refresh interval)

Ambient UI for DeepSeek Harness Web: a glassmorphism balance/token floating widget plus a pixel-art agent-trail animation.

Cost tracking plugin for the DeepSeek Harness Web GUI — snapshot-anchored per-turn pricing, account balance, and live cost estimates.

DSH plugin: visible cost/balance stats pill below the composer, with settings page and one-click reset. Fixed fork-level issues of dsh-cost-balance (slot id collision, missing ctx, invisible 5px bar).

The DeepSeek time-of-use meter for dsh: what this session cost, which tariff is running, when it flips, and the account balance behind it — one line under the composer.

Complete LAN/remote access for the Web UI: 0.0.0.0 binding, crypto.randomUUID polyfill, token gate (401 login page + WebSocket interception, loopback exempt), privileged-fence and settings-persistence exemptions, and an idempotent installer with upgrade recovery.

OS-level system notifications for the dsh web GUI: popups when a turn finishes or the agent needs your approval, answer, or plan review while the page is in the background.

Specialized in Git branch and status handling: a Git status drawer on the right edge of the DSH web UI with a commit DAG lane graph, uncommitted changes and stash rows, inline diffs, right-click branch/tag actions, and one-click fetch from all remotes.

Long-task orchestration loop: Codex plans/scores/reviews, DeepSeek executes, Kimi supplements (vision acceptance, summarization, cross-check).

Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.