188 results
AI auto-management channel for GitHub repositories - a DeepSeek Harness community plugin (bundle) that lets an agent manage repos, issues, pull requests, branches, files, labels, topics, tags, releases, and search through the GitHub REST API, with a Web settings card and a live master switch.
Maestro Review — pluggable ReviewProvider (GitLab/GitHub) + orchestrator for automated MR review
Read-only model request concurrency monitoring for DeepSeek Harness
X-ray for your DeepSeek Harness — diagnostics for what's actually loaded, why, and what it costs: per-plugin context-tax attribution, per-request token ledger, skill catalog pricing, dependency cascades.
Offline DeepSeek request, tool-loop, reasoning_content, and SSE diagnostics for DSH
Global model command palette and provider/model configuration panel for DeepSeek Harness, with selective request retries, OpenRouter free-model import, loopback relays, online capacity presets, and optional media tools.
DSH web plugin: per-model thinking-intensity tiers, provider default reasoning, modalities, gateway compat switches and static custom request headers for custom llm-pi-ai providers, edited inside the official Models settings card. 模型能力：思考强度档位 / 默认思考强度 / 支持模态 / 兼容开关 / 静态自定义请求头。
Secret-scrubbing guard plugin: irreversible regex redaction of secrets before session-log persistence and model requests
Per-provider concurrency gate for DeepSeek Harness LLM requests
Provider request metadata minimization extension for DeepSeek Harness
DSH web plugin: cross-session token usage, request count, and optional cost analytics (ctx.tokenUsageStats), with a self-contained dashboard page and a sidebar footer entry.
Runtime-switchable outbound proxy for the DeepSeek Harness: hot-reload HTTP(S)/SOCKS5 routing for every global-fetch request via a settings section.
DSH-Desktop LLM provider plugin for Command Code with model catalog sync, request retry, multi-credential support, and a settings UI.
DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.
DeepSeek Harness plugin: pick configured model providers, and when a model fails with a model-related error the request automatically falls through the provider group's models (then the next selected provider) until one works, so the unfinished task keeps going. Adds its own Settings tab.
Issue-to-PR 可验证交付链：项目配置 → 11 阶段流水线 → 人工复核 → PR 说明（DSH 全局插件）
Mobile UI fixes for the DeepSeek Harness web profile: a restart row, input-modality switches, a narrow-screen drawer and settings tabs, a full-width model menu, a stuck-request network chip, a scrollable question region, a throttled reaction to streaming message storms, a guarded subagent-catalog refresh, click-to-open lineage chips, a narrow-header collector sheet, and a throttled session-list render under background streaming load.
DSH Skill MCP Manager for DeepSeek Harness Desktop: manage MCP servers and Skills from Settings, publish compact capability descriptions, and progressively load each MCP server's tools only into the requesting session. Dual-face dsh plugin, no DSH source changes.
Keeps Charm Hyper requests under the gateway's 10 MiB body cap: replaces the oldest images with placeholders (newest survive) before sending, and retries with a tighter projection when the gateway still rejects the body.
DeepSeek Harness plugin (in development): reports what changed in your authored pull requests since your last check — merged, closed, or gone stale.
DeepSeek Harness plugin: Sign in with Claude Pro/Max (no Anthropic API key). Also caps Anthropic request images at 2000px and slims /compact so a 1M context can still summarize.
DSH Web UI plugin: automatically sends a localized continue prompt when a request is interrupted by network errors or other non-human causes
Automatic review of sandbox escalation requests for DeepSeek Harness, plus an /approve slash command for manually approving auto-denied actions (Codex Guardian-style)
Safe restart execution for DeepSeek Harness: request validation, checkpoint gating, restart locking, graceful shutdown, crash-loop breaking and an external supervisor. It never decides when to restart.