968 results
Codex-style per-session memory for DeepSeek Harness: qualified sessions auto-distill into per-session drafts (rollout_summaries); manual add/change/forget runs only on explicit user request; layered disclosure (summary + registry); idempotent integration watermark. / 一会话一草稿记忆插件：合格会话自动提炼草稿；手动增/改/忘仅在显式请求时执行；分层披露（总纲+注册表）；幂等整合水印。
Safemode profile enforcer: force-restores ~/.dsh/profiles/safemode to a clean whitelist (dsh-base + dsh-web-app) on start and continuously guards it against modification, so `dsh --profile safemode` always boots with zero third-party plugins. No build scripts: the bundle row does all work.
Skill studio for DeepSeek Harness: visualize all agent skills, view/edit their SKILL.md bodies, toggle model/user invocation, and mine session logs to extract reusable personal skills (auto-loadable by the agent) — from the web settings panel (Skill 工作台) and via skillmgr_* / skillmgr_extract_* tools
CodeBuddy (copilot.tencent.com) provider bundle for DeepSeek Harness (dsh): 18 models (DeepSeek, GLM, Kimi, MiniMax, Hunyuan, auto) with adjustable reasoning efforts, CodeBuddy web search / web fetch backends for the stock dsh tools, and a settings card in the Web UI.
DSH 计费统计插件：自动识别模型、实时展示会话/今日/本月消费、余额查询、预算告警，内置 16 家厂商价格目录（DeepSeek/豆包/腾讯混元/阿里千问/OpenAI/Anthropic/Kimi/智谱 等），中英双语
Scan agent skill packages for static security risks. Use for skill audit, security check, prompt-injection review, suspicious scripts, unsafe dependencies, zip package review, and pre-install skill review. Not for runtime monitoring.
DeepSeek Harness plugin exposing the SeismicX earthquake-catalog skill as typed, model-facing tools
Provider health, quota, account usage, and local model usage statistics for DeepSeek Harness
GitHub-only marketplace and guarded lifecycle manager for DeepSeek Harness plugins
Vision-only desktop automation plugin for DeepSeek Harness (fusion refactor)
DSH skill_manage: agent-managed procedural memory. Create/patch/edit/disable/delete skills in ~/.dsh/skills (user scope) or <projectRoot>/.dsh/skills (project scope), with validation, delete guards (agent-created marker, pin, path confinement), disable/enable via disable-model-invocation, and an English trigger-discipline system prompt section. Built on top of skill-filesystem's hot-reload watcher.
DeepSeek Harness (Cordis) plugin: control Alibaba Cloud ECS instances through the local Workbench CLI — list/exec/log/upload/download/diagnose/deploy/session model tools plus a visual settings panel
DSH WebUI capability controls for skills, MCP servers, tools, prompt injections, approvals, and safety guards at session, project, and global levels.
Mochi — natural-language-driven CAE bundle for DeepSeek Harness (CAD → mesh → solve → post-process; CFD via OpenFOAM)
Add a direct no-input continuation control for failed DeepSeek Harness sessions
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.
LLM-as-a-Verifier plugin for DeepSeek Harness: fine-grained logprob-based scoring, pairwise pivot tournaments (best-of-N) and an automatic end-of-turn quality gate.
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
Persistent DeepSeek Harness bundle: MIDI recognize/edit tools (midi_summary, midi_read, midi_write, midi_transpose, midi_quantize, midi_tempo, midi_chords) over @tonejs/midi.
Reliable todo panel for DSH: review dock survives restarts, verifies completion evidence submitted through its own tool (official todo panel stays clean)
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
WeChat Official Account content studio for DeepSeek Harness: anti-homogenization writing methodology, blessing-image visual baseline, gpt-image cover pipeline with OCR acceptance, interaction rules, and the measured xiaolvshu (newspic) draft web API.
鲸蓝戏水：DeepSeek Harness Web GUI 的 macOS 风格皮肤 + 水中鲸鱼动态背景 + 点阵鲸鱼发送按钮（可安装 DSH 插件包）
量化回测与风险指标：规避前视/幸存者偏差、考虑交易成本、walk-forward 分析、风险指标计算。受 wshobson/agents（38k★ MIT）启发。