@nanmicoder/dsh-auto-mode
Sandbox-first automatic permission policy for DeepSeek Harness
68 results
Sandbox-first automatic permission policy for DeepSeek Harness
Declarative Claude Code-style permission rules plus a Codex-style process-level network policy for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), workspace-path, and network-target (domain/ip/port/scheme) matching on the tools/pre-execute waterfall, a built-in local HTTP/CONNECT proxy governing shell subprocess traffic, three network modes mapped onto the official sandbox presets, full session-log audit, HMR rule reload, and a settings page with a rule editor, block counters, and recent interception lists.
Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.
Unified capability management for the DeepSeek Harness: catalog (ctx.capability) + meta_search/meta_invoke + Resident/On-demand/Disabled projection policy + 能力管理 settings tab, in one installable bundle (server + browser).
DSH (DeepSeek Harness) plugin packaging of the Project Blueprint skill — one-command AI coding conventions (AGENTS.md, docs skeleton, CI/CD, git rules, testing policy) with an autonomous discovery engine (7 languages, 15 frameworks, 70+ components, web fallback).
RMB/USD token-billing plugin for DSH web: official-policy auto pricing (incl. peak/off-peak), full coding-plan billing by provider routing, Settings→Cost summary page, per-message ledger, account balance, locale-driven currency display
Closed-loop trajectory policy plane for DeepSeek Harness: task episodes, revision-aware verification debt, benchmark-aware stop control, adaptive effort, and scoped capability control.
Settings UI for DeepSeek Harness (DSH) to edit each model provider's request retryPolicy — mode (normal/always), maxRetries, retryableCodes and exponential-backoff parameters — written to settings.yaml and applied by dsh-llm-retry. 模型重试策略设置:在设置面板中可视化编辑各模型提供方的 API 请求失败重试策略。
Durable bounded context and recall policy for the stock DeepSeek Harness agent loop
See what your AI agent protected: session security receipts, visible data provenance, task boundaries, and tool identity checks for DeepSeek Harness.
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
Whitelist / blacklist / any-error retry policy for DeepSeek Harness, driving DSH's built-in LLM request retry mechanism.
Agentic Control Plane for DeepSeek Harness — check every tool call against your policies before it runs, and keep a durable record of what was allowed and why.
Thin routing policy for DeepSeek Harness: keyword routing, allowlisted model switching, and isolated image generation. / DeepSeek Harness 薄路由策略:关键词路由、白名单模型切换和隔离生图。
Desktop computer use for DeepSeek Harness (DSH): macOS app listing, accessibility-tree window capture, screenshots, and synthesized input — the seam, the local Swift-daemon provider, the computer_use_* tools, the approval policy, and a standalone MCP server in one installable plugin package
DSH Windows default shell policy plugin: probe git-bash/MSYS2, switch bash/pwsh from the plugin config card, register the bash tool and trim the prompt tool surface. DSH Windows 默认 Shell 策略插件:探测 git-bash,配置面板切换 bash/pwsh,动态注册 bash 工具并裁剪提示词工具面
Version management for the dsh Web GUI settings panel: inspect the installed @deepseek-ai/dsh against every npm channel or version line, install or downgrade with one click, roll back instantly from local snapshots, automate the whole cycle with a policy engine (silent auto-update, execution windows, daily checks), and restart the host seamlessly.
Allow, ask, or deny DeepSeek Harness tool calls before execution
DeepSeek Harness plugin for SecurStack security scans, policy checks, doctor diagnostics, and JSON CLI results.
Policy-enforced, evidence-first governed workflows for DeepSeek Harness agents — installable community plugin (governance core + authority provider)
AI approval answerer using the unified ctx.llm route with fail-closed local policy checks
让 DeepSeek Harness 自动重试商汤 429/QUOTA 等瞬时网关故障直到任务完成——启动时给所有 llm-pi-ai provider 热注入加固版 retryPolicy,运行中新增的 provider 也会自动补上,再也不用手动发「继续」。
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
Codex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.