생산성 도구 · DeepSeek Harness 플러그인 — 26 페이지

DSH 实时思维链锚定监控插件: we/let's/let me 指纹波段检测(spec/mixed/react) + L1温和引导/L2强制重置/L3会话重启分级干预; 左侧栏入口 + 液体毛玻璃浮层 + 变阻器式思考强度条; 独立监控进程 + JSONL 实验日志 + 离线回放/参数校准; 变阻器条可选严肃/「滑动变祖器」梗双皮肤。

Automation-only Agent Client Protocol server for driving DeepSeek Harness agents over JSON-RPC stdio

Remote BFF assembly and Host Agent/Session lookup policy

Agent-preset surfaces: the default for later sessions, this session's seat, and the composition editor

In-app directory browsing surface: the workspace directory-flow owner rendering the host's listing and creation primitives

Native directory-picker surface: the renderless workspace directory-flow occupant driving the host's OS chooser

Session goal surface: GoalBar docked above the composer, read from the goal session projection

Session-header background-job list: live registry state mirrored from session/jobs frames

Model selection: the /model popupSelect over session.models / session.selectModel

Permission surfaces: a new-session default in General settings and a current-session /permission popup over the permissions projection

Sidebar plugin: session multi-level tree, search, grouping, state dots

Durable workflow-run Conversation Node and nested member disclosure for dsh web

Workspace picker plugin: one WorkspacePicker registered into the sidebar and empty-state workspace slots

The dsh one-shot bundle: a direct core Agent/Session runner over dsh-base with no Host, HTTP, or browser layer

SSH remote workspace for DeepSeek Harness: ssh2 connection pool, host settings, and routed bash/fs/search tools

DSH Cordis plugin: hooks the core model-request seam (agent/pre-step + agent/request) to force-compact a session's context and disable thinking per the "强制压缩配置" settings namespace (disableThinking, autoThresholdTokens, retainLatestTokens, turnEndForceCompactionEnabled). When the threshold fires (or /force-compact queues while busy), the latest `retainLatestTokens` of the conversation's surface tokens are KEPT VERBATIM and everything before that cutoff is COMPACTED INTO A SINGLE SUMMARY NODE in one LLM call (original span entries become shadowed/skipped). Also compacts at each turn/end and at each session/flush durability checkpoint. Host half is a pure listener; a web client half registers a settings.section (强制压缩 / Force Compact) that reads and writes the same settings namespace.

FormatForge for DeepSeek Harness: forge any file format (pdf/docx/xlsx/pptx/eml/toml/...) into AI-readable structured data. v3.0.0: 收件箱升级为 SQLite 索引库（元数据/全文检索 trigram/内容去重/会话溯源）+ 宿主右侧栏面板（搜索、预览、重转）+ 只读 API/SSE；顺带修好 ff_result 字段错配。v2.0.2: 拖拽文件夹不再卡死。协议仍为 v1。Thin bundle spawns local Python CLI (`python -m formatforge`) returning protocol JSON; enhancement delegated to current session model via enhance hints.

Orchestrating local agent skills into deterministic workflows. Built by @JiamingShi-JsPhys, Chelate Shell enforces a 4-layer routing architecture for scientific research.

DeepSeek Harness Web 可扩展回答状态宠物框架：支持宠物主题、多会话进度、模型轨迹和工具调用。

DeepSeek Harness plugin: an agent browser with a persistent identity - engine-level fingerprint spoofing, per-profile cookies and passkeys, residential proxy egress.

Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, session/daily/monthly budget caps with threshold alerts (desktop notification + webhook) and alert/block/degrade over-limit policies, built-in carbon footprint estimation and per-model latency benchmarks, a Settings budget tab, and the /budget command

Near-lossless compaction for the DeepSeek Harness — extends BasicCompactionEngine so each <compacted-summary> ends with an Exact Sources locator block (spill files, touched file paths, seq range), making compacted details recoverable via memory_search / read.

Embedded C/C++ firmware development toolbox — 4 agents, 8 skills covering FreeRTOS, ISR, NVM storage, Keil MDK, ARMCLANG, HardFault, state machines, architecture, LVGL patterns, and claim fact-checking. Ships a native DeepSeek Harness (dsh) bundle that injects the session-start gate into the first model step.

Meta-bundle: installs all dsh-memory plugins (CJK search, dedup, hybrid memory index, memory tool, compaction locator, core memory, skill manager + self-evolution) into a DeepSeek Harness profile as one patch layer.