Plugins

Route conversation-compaction calls to a chosen summarizer model in the Web settings page, and retry them on a configured fallback model when the primary ends in an error.

dsh 插件，主要解决 remote 开发和 LLM 无限重试

OpenTelemetry (OTLP/HTTP) + Langfuse trace exporter for DeepSeek Harness — GenAI semconv, sanitized before send, batched with retry, off by default.

Routes eight DSH lifecycle events through dedup, quiet hours and digest batching into seven channels. Severity maps to the fields Bark, ntfy, Telegram and webhooks actually support; failed deliveries retry with jittered backoff and survive a restart; per-channel circuit breakers stop hammering a dead endpoint; and a self-check reports a degraded relay instead of going silent.

Scoped, reversible tool-call ID compatibility plugin for DeepSeek Harness

Multi-instance ComfyUI orchestration: probes every configured ComfyUI endpoint for its GPU, free VRAM and queue depth, then dispatches a generation job to the idlest eligible instance. Ships three tools (comfyui_farm_status, comfyui_farm_pick, comfyui_farm_run). An instance is eligible only if it is reachable, has at least the requested free VRAM, and its queue is no deeper than the configured ceiling; eligible instances are ranked by free VRAM minus queue depth times a weight, so an idle shallow queue wins over a busy large one. Zero runtime dependencies. Optional retry on probe failure, because a single timeout across an SSH tunnel is not proof that an instance is down.

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

Requires DSH >= 0.2.0-rc.2 < 0.3.0. Declare any number of LLM providers, each with its own endpoint, credential and per-model parameters (reasoning-effort vocabulary, image input, retry policy), across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats, configured from a settings page.

Global real-time Token HUD for DeepSeek Harness Web: draggable floating window showing live output tok/s, cumulative tokens, and per-session running/retrying status across all DSH sessions.

Recurring task scheduler with an append-only delivery ledger: window-aligned dedup execution, failure/abandoned rows, and same-window retry redelivery.

Replaces the official Models settings page with provider lifecycle management, per-model reasoning effort tiers, retry overrides, drag reorder and upstream model sync.

dsh plugin: bounded retry for gateway network_error failures the stock retry policy cannot classify (e.g. OpenCode Zen finish_reason: network_error)

DSH plugin: connect to MCP servers, discover tools, and register them for direct model invocation with retry logic and statistics

System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.

Configurable model-request retry limit for DeepSeek Harness (Settings → General).

Email reminders from your DSH agent when you are away, with stable SMTP (no 535 retry loop), connect and idle timeouts, and a --check self-test.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.