457 results
DSH harness bundle/plugin: tolerate OpenAI-compatible providers whose streaming responses omit finish_reason (e.g. the Snowflake Cortex gateway) so turns complete instead of failing with a TRANSPORT error.
Telegram notifications for DeepSeek Harness: ping you when a task finishes or the agent needs your input/approval. DeepSeek Harness 的 Telegram 通知插件。
Two-stage intent and evidence review, deterministic completion gates, and bounded repair for DeepSeek Harness agents
A deterministic piano performance plugin for DSH: shared musical timeline, piano audio engine, visual engine, and DSH-compatible host/browser boundary.
Agent JIT: a compiler/runtime that offloads deterministic execution paths from LLM agent loops.
DSH agent-fleet hygiene audit: credential-file permissions, embedded credentials in git remotes (masked), provider token-prefix literals. Read-only, zero-dependency, deterministic.
System notifications for the DeepSeek Harness web GUI — OS-level popups for finished turns and pending interactions (approvals, questions, plan reviews). · DSH Web 界面系统通知：回合结束、待处理授权/提问/计划审核时弹出系统级提醒。
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.
DeepSeek Harness plugin that bridges to external AI models (Codex, Claude, GPT, ...) for second-opinion code review, adversarial review, and task delegation.
User Message Minimap: a navigation rail for long DeepSeek Harness conversations
Plugin Clinic: read-only health checks for the installed DeepSeek Harness plugin set — loader health, dependency integrity, version compatibility, install-script risk, duplicates, and patch integrity, delivered as a model tool, a Web dashboard, and JSON reports.
A minimal DeepSeek Harness community plugin that adds a callable hello tool
System-level Web Notification when the model finishes a reply in the DeepSeek Harness web GUI
Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.
Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.
Multi-provider image generation and editing tools for DeepSeek Harness
Tick-rail conversation navigator for the DeepSeek Harness web UI — a slim rail with one tick per message you sent, a peak-falloff hover effect, message previews, and click-to-jump.
Memory Standard Protocol (mm) for the DeepSeek Harness: layered MEMORY.md + deterministic budgets + frozen snapshots + cross-agent markdown/URI interop + session-log digestion. Ships as a dsh bundle (tools: mem_read, mem_write, mem_search, mem_budget, mem_digest) and a standalone CLI.
AI 多角色协作开发框架：文件即通信 + 教训库 + 决策日志 + 一致性审计 + 复盘持续优化（REVIEW）。注册 ai_collab_init 工具。
基础训练
Ponytail for DSH — the lazy senior dev. Live intensity switching (off/lite/full/ultra) with a toggle in the composer, injecting a minimal-code ruleset before every step to cut token usage.
Session & token mini dashboard above the sidebar's Settings row for DeepSeek Harness · 侧边栏「设置」上方的会话/token 迷你仪表盘 DSH 插件
Multi-provider quota, balance and Token-cost dashboard for DeepSeek Harness Web, with a draggable widget, usage analytics, local pricing and route diagnostics.
Native DeepSeek Harness LLM adapter for Claude Code / Antigravity CLI subscriptions, plus local Ollama — Claude, Gemini and a free local model in the model picker, no API key