dsh-vlm-bridge
DeepSeek Harness (dsh) bundle plugin: vision_analyze tool lets text-only LLM agents read images via SenseNova VLM, with Schemastery config and single-source credentials
376 results
DeepSeek Harness (dsh) bundle plugin: vision_analyze tool lets text-only LLM agents read images via SenseNova VLM, with Schemastery config and single-source credentials
Git workspace panel for DSH Web: repo discovery, stage/commit like VS Code Source Control, AI-generated commit messages via configurable rules, history graph and diff preview
DSH Web client plugin: card-based new-session configuration wizard (immersive step guide) to prevent silent default configurations
Configurable task-aware model routing bundle for DeepSeek Harness
Configurable conversation statistics row for DeepSeek Harness
Zero-config per-turn git checkpoints for DeepSeek Harness: every completed agent turn in a git workspace becomes one tagged [turnsnap] commit
DSH plugin: route every fetch/http/https request of the DSH process (model endpoints, web search, MCP) through an HTTP proxy. Follows *_proxy environment variables or manual settings; configured from the Web UI (设置 → 网络代理).
User-configurable cost pricing for dsh: per-model list prices and per-day-of-week time segments with price multipliers, edited through a Plugins-settings card
dsh turn-guard plugin: per-step timeout for agent turns. Watches session/event step boundaries; when the agent carries __pluginConfig.turnGuard.stepMs, a step running longer than that limit is cancelled via agent.cancel({kind:'hook'}). No config = no intervention (same as web session).
DSH plugin that bridges the local codebase-memory-mcp knowledge-graph server through the built-in @deepseek-ai/dsh-mcp-client, with a runtime-configurable exe path (settings namespace).
dsh web 插件:自动配置模型思考档位与能力,并按 provider+model 记住最后选择的思考档位
Post-edit diagnostics for DeepSeek Harness: runs configured type-checkers and linters after a successful write/edit and feeds the findings back to the model as tool-result context
Push DeepSeek Harness agent lifecycle notifications to configurable channels
Condition-driven session wake for DeepSeek Harness: durable file and GitHub watches that fire a configured prompt into a target session (cold-wake included), with transition-only dedupe and throttling
First-run health check for DeepSeek Harness (dsh): verifies Node/pnpm/dsh toolchain, profile, API key, workspace and registry config, then prints actionable next steps. Zero runtime dependencies, read-only. CLI + agent-callable quickstart tool.
DeepSeek Harness plugin bundle: graphlint dead-code detection tools for agents (graphlint_query / graphlint_build / graphlint_config + graphlint skill).
Agent harness 配置系统:agents/skills/hooks/rules 四层分工、instincts 持续学习(自动学模式、聚簇成技能)、AgentShield 安全审计(secrets/权限/hook 注入/MCP 风险)、Unified Memory Vault 跨 harness 共享、GateGuard 破坏性命令门卫。受 affaan-m/ECC(185k★ MIT)启发。
One-click Claude Code & Codex hooks for DeepSeek Harness: auto-discovers your existing hooks config and runs it on the harness interception points via the official bridge plugins
Registers a kimi-coding web search provider (api.kimi.com/coding/v1/search) into ctx.web, zero-config via the local kimi-coding credentials.
Image auto-describe provider for the DeepSeek Harness apiproxy admission seam: transcribes pasted images through configurable vision routes (Qwen first, GLM fallback) so text-only session models still receive image prompts.
Seamless image understanding for DeepSeek Harness: lets pure-text models read pasted/dropped images and Feishu/Lark images via a configurable vision model, without touching the host.
DSH 安全启动器:按上次成功配置启动、更新先试运行再采纳、插件先兼容性检查再安装。A DSH plugin for last-good boot config, canary-tested updates, and compatibility-checked plugin installation.
The Agent states: `thinking`, `waiting`, `idle`, and `error` are automatically synced to workled via the MCP protocol. Light‑effect parameters and touch macros can also be configured for the device over MCP.
Configurable MSYS2, UCRT64, and Git Bash executor for DeepSeek Harness