Plugin

Inspects ONNX models (inputs/outputs, shapes, opset, operators, size) and benchmarks them with ONNX Runtime on the local machine or on a remote target over SSH, reporting average/P50/P95/P99 latency, FPS and the execution provider actually used, with PASS/FAIL gates for FPS, P95 latency and model size. Requires Python 3.10+ with numpy, onnx, onnxruntime, and psutil installed (pip install numpy onnx onnxruntime psutil); remote targets need python3, numpy, and onnxruntime.

Local-first usage analytics for DSH: subscribes to session events and aggregates tool calls, turns, errors, latency and capability usage into daily tables, shown in a sidebar panel (6 KPIs, 14-day trend, top tools, capability breakdown) and served over a fenced local HTTP API with 18 JSON-RPC methods. Zero runtime dependencies, local mode makes no outbound requests, and no message bodies are collected.

Adds a Geek level to the Performance & usage setting: a live reading of the newest request in the composer status row (first-token latency, generation speed, output tokens, total time, amortised speed), and a drawer listing the last ten requests with an average row. Output tokens come from the provider usage; a calibrated character estimate is used only when usage is absent.

Adversarial review gate for tool calls. It hooks `tools/pre-execute`: a local regex pass over destructive commands (`rm -rf`, `git push --force`, `git reset --hard`, `DROP TABLE`, `format`, disk writes) and sensitive paths (`.env`, `id_rsa`, `.ssh`, `.git/`, `$DSH_HOME`) runs first with no latency, and only a hit is escalated to one review-model call that returns allow or deny. Plain reads and ordinary writes never enter that path, so everyday work pays no added delay. Every verdict is shown live in the Web GUI.

Local AI-agent request-log panel: aggregates local logs from atomcode, codebuddy, workbuddy, claude, codex, codearts, gemini, cursor, kimi and dsh, and shows per-round latency, tokens, cache, context and tool calls.

让你更清楚地了解究竟是什么占据了你的等待耗时 ⏱️ DSH 实时时序轨迹与执行过程追踪插件

Manual model probe for DeepSeek Harness: a session-view tab where you pick provider, API type, model and route, then send one real raw HTTP request over openai-completions, openai-responses or anthropic-messages — streaming or not — and read latency, TTFT, HTTP status, token usage and a three-layer diagnosis chain (API request / model response / strict check) on one screen, with errors in plain language.

Adds an http_probe tool for endpoint health checks: status code, latency and key response headers, using HEAD with GET fallback; response bodies are never downloaded.

Model Health panel in Settings: lists every model configured in settings.yaml and batch-tests availability and latency for each.

Dynamic LLM provider gateway latency and health pulse probe for DeepSeek Harness