dsh-record-replay
DeepSeek Harness plugin: model-facing orr_* tools plus the open-record-replay skill for the Open Record/Replay macOS workflow recorder.
52 results
DeepSeek Harness plugin: model-facing orr_* tools plus the open-record-replay skill for the Open Record/Replay macOS workflow recorder.
DSH 插件:全模式工具失败自动实录——把原生工具、PTC(Code Mode) run_code、代码内嵌工具调用的失败按错因去重计数,自动写入 skill 的机器维护区段,越用越少错。Auto-record tool failures from every execution mode into a skill's machine-maintained section (dedup + counts).
dsh web GUI plugin: manage and delete conversation records (whole sessions or individual messages, cascade delete) from the settings page. Dual-face: node half serves /api/session-cleaner routes, browser half registers the settings-page view.
Agentic Control Plane for DeepSeek Harness — check every tool call against your policies before it runs, and keep a durable record of what was allowed and why.
Fully customizable keyboard shortcuts for the DeepSeek Harness WebUI — macOS-first defaults, 34 pre-registered features across session/view/clipboard/model/permission/system groups, one-click recording to add your own bindings, silent permission cycling with color feedback.
View and manage archived sessions in DSH: browse the archive, read full transcripts in a chat-style dialog (turns, reasoning, tool executions), and remove unwanted records. Works on desktop and web.
SSH terminal panel and AI connection manager for DeepSeek Harness: model-driven SSH connections (connect/exec/list/status/disconnect), auto-saved connection records, keep-alive + auto-reconnect, execution mutex, credential-safe auth, and an XShell-style multi-tab terminal panel in the Web GUI.
Real-time chain-of-thought trajectory profiling for DeepSeek Harness: live wording indicators, profile-family judgment, and per-session measurement records
Agent negative-knowledge ledger for DeepSeek Harness: records failed paths with evidence hashes and retry conditions, auto-invalidates on evidence change.
VocoType voice input bridge for DSH Web: mic button + recording panel in the composer, auto-insert recognized text (dedupe, auto-launch/deploy, mtime-optimized polling)
Conversation history recall for DeepSeek Harness: search the original text of every session (like searching chat records) — literal/fuzzy/semantic retrieval, fully local & offline. AI never forgets what you told it.
Per-model hourly token usage for the DeepSeek Harness: automatic recording with a Web GUI dashboard.
Agent Skill for DeepSeek Harness (dsh): list.
DSH bundle plugin: 内容创作与多平台分发 —— 桌面截屏/录屏、Markdown→小红书图文卡片(5 配色 × 4 版式、照片插图、背景图)、dev.to 官方 API 发布、发布前人工审阅(草稿落盘),并挂载 Playwright 与小红书 MCP。
A DeepSeek Harness bundle for local PDF reading, durable paper records, traceable evidence, and cross-paper synthesis.
Leaderless flat agent teams for DeepSeek Harness: cross-window structured task dispatch, recorder service, and web dashboard
Project-scoped AI memory: records pitfalls and user habits per project, injects them into future conversations
Content-addressed conformance proof across recorded DSH ToolRuntime, MCP JSON-RPC and CLI JSON surfaces
Cross-session persistent cost ledger for DeepSeek Harness: logs every LLM token usage to SQLite and exposes record/query/budget tools. Built-in DeepSeek pricing, overridable via config.
Let a local DeepSeek Harness Agent use BailingHub to query data, update records, and run permitted actions in your online store, SaaS, or other admin system.
China hard-tech supply chain intelligence for DeepSeek Harness: signal board, earnings tracker, track record, Q&A via cn-intel MCP
Cross-border counterparty due diligence for DeepSeek Harness — resolve the entity you are actually contracting with, then judge whether the record is fit to rely on.
Adversarial pro/con debate with a neutral judge for DeepSeek Harness: /debate human command, subagent-driven rounds, verdict record, and a web debate card.
DeepSeek Harness 叶子工具正文边界的确定性录制、完整性校验与离线回放插件