Best DSH Model & LLM Switching Plugins

Enforced pain-point-check guard plugin for DeepSeek Harness: after two non-converged experiments it injects the three questions, denies non-investigative tool calls until answered, and blocks same-direction retries. dsh-plugin

Per-model token cost tracking with configurable cache-hit/miss, output and peak-window pricing, a live session cost bar, and unconfigured-model flags.

Auto-log failed tool calls across native tools, PTC run_code, and inline invocations: dedup and count root causes into a skill so repeated mistakes fade.

Read-only health clinic for the installed DSH plugin set: loader health, dependency integrity, version compatibility, install-script risk, duplicates and patch integrity, delivered as a model tool, a Settings dashboard and JSON reports.

DeepSeek Harness telemetry backend that exports turns, model steps, and tool calls to yiTrace over HTTP.

Runtime-switchable model output styles with Claude Code outputStyles parity: a /style command, per-session persistence over the output_style domain, systemPrompt injection, six built-in styles, custom Markdown/JSON libraries, and a web picker.

Progressive-disclosure MCP gateway that searches large remote catalogs through `mcp_search`, then invokes exact schemas through `mcp_call` with lazy connections and bounded caches.

Model-driven /init command: the agent analyzes the current repo and generates/updates a high-signal AGENTS.md, with a persistent system-prompt reminder to keep it maintained.

Makes Minimal mode work on Windows: supplies the missing win32 process inspector so the persistent Git Bash shell runs, plus a faithful minimal-windows preset and an install-trap doctor (koffi crashes, PS 5.1 fallback, localhost 403).

Docker-isolated real-host lifecycle tests for DSH plugins across install, boot, tool registration, update, uninstall, reinstall, and recovery, with structured evidence.

Zero-touch runtime telemetry for DSH: every session auto-writes task, model tier, tools, failures, duration, status into a human-readable journal with a stats section (pure observer — no tools, no LLM calls, no injection).

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Metadata-first runtime profiler for DSH agents: turn/step traces, model and tool wall-time timelines, provider usage, retries, errors, and live or historical sessions.

DeepSeek Harness plugin: per-process tool-call statistics (not token usage) — tool_stats tool with call counts, error counts, avg durations

Support for the microsandbox backend.

Reusable Markdown prompt profiles for DeepSeek Harness with per-turn model selection, argument substitution, and state restoration. DeepSeek Harness 可复用 Markdown Prompt Profile，支持单轮模型选择、参数替换和状态恢复。

Automatic type-check diagnostics: after the model edits or creates TS files, runs `tsc --noEmit` in the background (debounced per project) and reports errors via the `code_check` tool — grouped by file with line/column, severity and TS error codes, closing the "edit → check → fix" loop.

Plugin compiler with a blueprint registry (scaffold → validate → deploy) exposed as a runtime service, three model tools, and a blueprint-gallery settings page.