102 results
Task Flow / Execution Graph plugin for DeepSeek Harness (DSH): visualize a single task's full execution — turns, LLM steps, tools, skills, subagents, retries, parallel branches — as an interactive DAG with live updates and trajectory linkage.
Work Continuity for DSH — goal/decisions/checkpoints/next-steps as explicit WorkState, decoupled from generic memory
Token usage dashboard for DeepSeek Harness: cache, context, efficiency, per-step details, and cross-session comparison
dsh-experience-flywheel · DSH 经验飞轮插件 — agent cross-session experience memory + dual-acceptance gates (auto query/inject via agent/pre-step middleware; exit-1 gate scripts)
DSH Web plugin: collapse consecutive tool-use and thinking steps between messages into a single bracketed, expandable item
DeepSeek Harness plugin: the agent publishes a project plan (steps) and a project framework (architecture graph); the browser renders the steps in a right-hand panel and the framework as a downloadable diagram in the center view.
Embedded yiTrace plugin for DeepSeek Harness turns, model steps, and tool calls
Git-backed long-term memory for DeepSeek Harness: a local .mem git repo (single main branch, immutable entries, structured commit messages) with mem_search / mem_read / mem_write / mem_delete / mem_replace tools and fully automatic legacy migration (no CLI needed; the CLI remains for explicit control), auto-managed by the root agent with zero manual steps.
DSH 插件安检机 — install-time static security auditor for DeepSeek Harness plugin bundles. Zero dependencies, zero install scripts, zero build step.
DSH web plugin: two-step inline archive on workspace sidebar rows — one click arms a red confirm, the second archives; archive is no longer buried in the ⋮ menu. · 工作区侧边栏行内两击归档：点一次变红确认，再点即归档，归档不再藏在 ⋮ 菜单里。
A configurable DeepSeek Harness host plugin that silently appends route-specific system-prompt guidance for GPT and DeepSeek steps.
Plug-and-play proteomics analysis bundle for DeepSeek Harness: auto-managed R 4.4 runtime, step-wise traceable pipeline (normalize / PCA / batch / DEA / enrichment / GSEA), cached GO-KEGG annotation backgrounds.
Token usage analytics tab for the dsh web GUI: whole-log projections plus a per-turn/per-step breakdown
Fail-closed per-turn step, tool-call, and provider-token budgets for DeepSeek Harness
Ponytail for DSH — the lazy senior dev. Live intensity switching (off/lite/full/ultra) with a toggle in the composer, injecting a minimal-code ruleset before every step to cut token usage.
DevTools for DeepSeek Harness web: read-only Agent Runtime Trace — turn/step execution timeline, model latency (TTFT/decode), tool-call durations, retries, hook and turn end reasons. Metadata-first, durable events only, zero behavior modification.
DSH plugin: view OBJ/STL/STEP models in the web UI and translate them into a standardized, LLM-readable JSON
Per-turn, per-step LLM cost metering for DeepSeek Harness: a costUsage session projection, a cost line under each message, and an LLM+web price auto-maintenance tool.
DeepSeek Harness 原生插件：让纯文本模型（如 DeepSeek）经 agent/pre-step 劫持 + resolveModelInfo 包装自动识别上传图片（qwen-vl），使纯文本对话也能“看见”图片。
dsh plugin: auto-open the default browser as soon as the dsh web GUI server is listening — one-step startup for `dsh web`
Wide stats footer: removes the max-width clamp on the composer stats line (turns/steps | LLM time | TTFT | cache hit | token counts) so it spans the full composer width, centered
DSH web plugin: a draggable ring-gauge dashboard pinned to the bottom-right that shows live model output speed (tok/s), with an expandable detail panel (per-step exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).
Turn-outline sidebar tab for dsh-better-sidebar: fold a session into user turns (input + tool steps + output) with structured jump-back into the conversation | DSH 轮次轨迹侧边栏：按用户轮次折叠会话（输入+工具步骤+输出），一键定位回对话原位
全局提示注入 / 上下文病毒（context virus）防御插件：tools/pre-execute 扫工具参数、tools/post-execute 扫工具结果、agent/pre-step 扫进入模型前的消息并注入金丝雀守卫、llm/stream 出站消毒；支持 block / quarantine / monitor 三模式、磁盘化可演进病毒库（学习/导入/导出）与审计日志。纯 JS 无原生依赖，profile 层挂载，对所有预设与子代理全局生效。