dsh-codebase-memory
DSH bundle that bridges the Codebase Memory MCP code knowledge graph into DSH and can keep indexed repositories fresh with an optional debounced filesystem watcher.
111 results
DSH bundle that bridges the Codebase Memory MCP code knowledge graph into DSH and can keep indexed repositories fresh with an optional debounced filesystem watcher.
Recursive Self-Improvement (RSI) engine for DeepSeek Harness: a bounded perceive → integrate → verify → repair → propose loop that keeps a downstream desktop app in sync with the fast-moving upstream harness. AI for AI — DSH maintains DSH.
Codex-style /btw for DeepSeek Harness: ask a side question answered by a conversation-seeded subagent, keeping the answer out of the main context
Agent Skill for DeepSeek Harness (dsh): list.
Let the model render an image into the DSH web chat flow (QQ/WeChat style) via a show_image tool: the message content keeps only the path text, the image never enters model context, and the browser shows the picture inline, scrollable with history.
DSH port of pi-tokensaver: keeps the tokensave semantic graph fresh and teaches the agent to prefer its semantic tools
Opt-in detached watchdog for the DSH Web process with optional snapshot-checked repair and explicit patch restoration.
Long-task gatekeeper for DeepSeek Harness: detects one-shot mammoth requests, asks whether to plan first, and scaffolds plan.md + a capped goal before the agent starts
Keep Think reasoning rows visible and auto-expanded, and always force Chinese thinking and replies. 保持 Think 思考行可见并自动展开,并始终强制中文思考与回复。
Run Claude Code, Codex, Pi, or the built-in loop side by side in one dsh — pick the engine per session, switch without restarting, keep one session store, history, and trace.
Skill usage statistics for DSH: counts every skill invocation across sessions (replay of existing logs + live session/event subscription), detects zombie skills, and helps decide which skills to keep.
Simple memory keeper for DSH: semi-automatic markdown accumulation, layered loading (global/project), cross-project search
OpenCode usage widget for the DeepSeek Harness web sidebar: host-side proxy to the OpenCode usage API (keeps OPENCODE_API_KEY off the page) plus a client-side bars widget.
Vision for text-only DeepSeek Harness agents: delegate image reading to a one-shot subagent on a configurable vision route (MiniMax / Kimi / any OpenAI-compatible provider), keeping image bytes and the vision model's context out of the main session.
Curate tool output before it enters the model's context: keep error/warning lines and head/tail, spill the full text to disk with a pointer. Faster turns, smaller context, sharper attention — for every tool, not just bash.
Minimal-anchored agent preset for DeepSeek Harness: first request keeps the real Minimal tool pair, promotion unlocks the full Standard catalog with a one-shot background-jobs notice
Context compression for small-context models on the DeepSeek Harness Web GUI: one click condenses the whole conversation into a few sentences, opens a fresh session in the same workspace, and re-injects the summary as the first message so a small model keeps working with a clean, compact context.
DeepSeek Harness plugin: switch the current conversation's agent preset (mode) after the model finishes answering, and keep chatting in the same session
Conversational bookkeeping plugin for DeepSeek Harness: record expenses/income by chat, query the ledger, run reports, export CSV/HTML, and track monthly budgets.
DeepSeek Harness plugin: aligns markdown tables in assistant replies right after each turn (surface-replace, replay-safe) and adds a /clear-history command that empties the model-visible conversation while keeping the append-only log.
On-demand vision for text-only LLMs in DeepSeek Harness: keep pasted/attached images in the backend, and let the model call view_image to look at them anytime via any OpenAI-compatible vision endpoint — as if the model were natively multimodal.
DSH plugin that auto-retries failed API requests — when third-party APIs return errors (rate limiting, service unavailable, etc.), intercepts and retries to keep the conversation going. Supports auto/manual mode with configurable status codes and error codes.
Login gate for the DeepSeek Harness web GUI: username/password entry page (DeepSeek style), 12-hour session tokens, slash commands for user management. Background tasks keep running while logged out.
CodeBuddy-style deferred tool loading for DeepSeek Harness: keep tool schemas out of the model context until the model loads them on demand via tool_search / defer_execute_tool.