dsh-markdown-memory
Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section
150 results
Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section
File upload for the DeepSeek Harness web GUI: a folder button, paste, and drag-drop that save files into the session workspace uploads/, with file cards shown alongside image thumbnails.
DSH plugin: import a local folder as a server workspace and sync DSH changes back to local.
dsh plugin: multi-folder workspace — a global linked-folders list (cross-session) plus per-session on-the-fly linking, managed from the Web sidebar.
DeepSeek Harness plugin: adds a folder icon next to the produced-files row that reveals the files in the native file browser (macOS Finder / Linux file manager).
DSH AI-PM 插件:把 pm-scaffold 的 PRD 工作流接入 DeepSeek Harness——agent 侧提供 pipeline 模型工具(init/status/entry/gate/reflow/skill/artifact),GUI 侧提供需求看板与不可绕过的人工确认闸门。
DSH Web client plugin: auto-folds completed-turn process nodes behind a summary row; expand state persists per session+turn
Generate a README.md for DeepSeek Harness (dsh) plugin repositories from package.json + cordis.patch.yml + source layout — deterministic, zero runtime dependencies, read-only by default. CLI + agent-callable readme_forge tool.
DSH web 插件:折叠思考过程直接输出回答内容;在会话输入框上方增加会话活动状态条,展示 Think / Edit / Bash / Read,可展开与收起。 / DSH web plugin: folds the thinking process so answers render directly, and adds a session-activity status bar above the composer showing Think / Edit / Bash / Read, expandable and collapsible.
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
DeepSeek Harness web plugin — upload files and folders straight into the conversation (no workspace copy needed): images attach as real image blocks, text content is written into the composer, folders land under ~/.dsh/uploads by directory structure
Codex-style turn folding: collapse each group of reasoning + tool-call nodes (between visible outputs) into a single disclosure unit
Export a DSH session log as a clean chat log: stream fragments folded into normal messages, every other event kept verbatim. /chat command + browser-download button.
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
In-dsh plugin factory: scaffold, document, and validate DeepSeek Harness plugins (host tools AND client UI) from inside an agent session.
Two-level fold for DeepSeek Harness chat: collapse think+tools as a process, then fold tool rows separately. Official cards stay intact. 聊天主视图两层折叠:过程一层、工具一层,不替换官方卡片。
Virtual session folder grouping, move-to-folder menu, and nested workspace subproject manager for DeepSeek Harness (DSH).
DeepSeek Harness host plugin: serves a configured workspace/media folder over the web server under /media, so any conversation can display local images by referencing http://<host>:<port>/media/<relative-path>.
1-Line AI Agent Generator for DeepSeek Harness (dsh)
Out-of-tree DeepSeek Harness bundle: an executable implementation of the Harness Engineering Methodology (HARNESS-METHODOLOGY-SPEC v1.0) — agent-discipline prompt section + artifact scaffolding tool + compliance audit tool.
Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.
DSH host-only plugin: after every turn, a subagent folds the session's work (messages + tool calls) into a rolling 'major topic - minor topic' outline and renames the session to its current goal + task. No dsh source changes.
Keeps long coding-agent sessions lean: wrap work in named tasks and, when one is done, fold its whole span into a short titled summary. The conversation stays readable, context costs stay low, and every fold's original content can be read back on demand. For DeepSeek Harness.
OpenTelemetry traces backend for the DeepSeek Harness telemetry seam: folds agent session events into OTLP span trees