플러그인

harness에서 로컬 TinyTitan 모델 서버에 접근할 수 있게 유지합니다: 설치된 모델에서 llm-pi-ai 라우트를 새로 고치고, 생각하지 않는 compaction 백엔드를 마운트합니다.

사용자 정의 DSH 모델용 추론 노력 수준 및 하위 에이전트 기본값 구성.

DeepSeek Harness용 라운드별 thinking-level(reasoning_effort) 제어: Auto를 선택하면 최근 도구 호출 기록을 바탕으로 low/high/max를 스케줄하고, 아니면 wire level(off/on/minimal/low/medium/high/xhigh/max)을 수동으로 고정할 수 있다. 사용자 지정 wire 매핑, 모델 인지 capability guard, context-window 프리셋(64K–1M)을 제공하며, 모델별 capability card는 별도 플러그인인 [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions)(dsh-market에서 설치 가능)과 짝을 이뤄, 사용자 지정 OpenAI 호환 게이트웨이(vLLM / LM Studio / 자체 호스팅)가 reasoning을 시험할 수 있게 한다 — card는 llm-pi-ai capabilities를 쓰고, adapter가 wire(compat.thinkingFormat)를 구동하며, 이 플러그인은 takeover list를 자동 유지한다.

llm-pi-ai 모델 제공자를 위한 라이프사이클 관리 UI: 사용자 지정 헤더와 AES-GCM으로 암호화된 API 키를 사용해 제공자를 생성, 편집, 삭제, 활성화, 비활성화합니다. 파킹된 제공자의 제거에 안전한 복원, 일괄 쓰기가 포함된 원격 모델 탐색, 다섯 가지 전략의 스마트 라우팅, 합집합/교집합 컴포지트, 모델별 연결 테스트, 요청 관측 기능을 제공합니다.

Settings의 모델 행에 OpenAI 및 Anthropic 프로토콜 프리셋(llm-pi-ai)이 있는 추론 수준 편집기, 입력 모달리티 토글, 1M/128K 컨텍스트 및 최대 출력 프리셋을 추가합니다.

只填 Key 的服务商预设：50 家渠道为 DSH 一键写入官方 llm-pi-ai 路由与凭据（插件），并可写入腾讯 WorkBuddy、OpenCode（Key 走其 auth.json）与 cc-switch 的配置（CLI）；核心为纯 JS，可被更多应用的外壳复用。

Replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai through a safe-zone download with a one-click enable toggle, and adds provider quota and balance lookups plus a provider management page.

让 DeepSeek Harness 自动重试商汤 429/QUOTA 等瞬时网关故障直到任务完成——启动时给所有 llm-pi-ai provider 热注入加固版 retryPolicy。

DSH Web GUI 모델 능력 구성: '설정 → 모델'의 모델 카탈로그 편집기에서 구성된 각 모델에 대해 이미지 지원 여부와 사고 수준(reasoning efforts)을 직접 설정하고 llm-pi-ai 설정 네임스페이스에 기록합니다.

Make DSH llm-pi-ai opencode routes pass Zen free-tier gate: opencode User-Agent + canonical ses_ session + bash/read tools. Scoped to opencode.ai only.

Declares the OpenCode Go and Command Code route wire protocol and endpoint (so the API address never has to be typed), adds the DeepSeek V4.1 models to the OpenCode Go route and puts them first, completes the Command Code model list from its public catalog, and attaches a per-conversation x-opencode-session header to OpenCode requests (fixes 400 MissingSessionID).

Brings the Codex (ChatGPT Plus/Pro) subscription already signed in on this machine into DSH. It (1) shows the 5-hour and weekly windows with their reset times and the remaining reset credits in a sidebar panel, with one-click reset that consumes a credit; (2) registers the subscription route in llm-pi-ai (openai-codex) when the quota is read, so the Codex models appear in the model picker; (3) refreshes the OAuth access token before expiry and writes it back atomically, so no key has to be replaced by hand; and (4) adds a codex tool that delegates a task to the local Codex agent. No API key has to be entered.

Declares the wire protocol for the opencode-go route so models the installed catalog does not describe resolve, adds the DeepSeek V4.1 models to that route when they are missing, and attaches a per-conversation x-opencode-session header to OpenCode requests.

A full-page console panel opened from the sidebar, with eight tabs: an overview; a session list read from the sessions service (title, directory, running state, updated time, with filters); installed bundles and Loader entries from pluginInventory and pluginManager, with per-bundle enable switches; a plugin market listing public topic:dsh-plugin repositories from the GitHub search API; a model and provider editor that writes the llm-pi-ai settings namespace through remote.settings.mutate (switch a session model, add or edit providers and their model lists, and store API keys via remote.credentials, merging over the stored profile so fields the form does not expose survive an edit); MCP and skills tabs; and a usage tab that reads the host's loopback /api/dsh-usage/overview document. Services are declared through ctx.inject, so a deployment that omits one mounts without the console rather than crashing.

A dsh plugin that replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai, and adds quota/balance lookups plus a provider management UI

Declares per-model reasoning-effort ladders for third-party providers in the llm-pi-ai settings section, so DSH's stock thinking-intensity selector works on models the pi-ai catalog does not describe.

Adds per-route context window and compaction threshold fields to the Models settings page and a vendor-aware thinking-effort picker to the composer, writing llm-pi-ai capacities, reasoningEfforts, and a compaction-basic patch row.

Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.

Provider health dashboard as a Settings page: read-only per-provider status, health (time-decayed from recent errors), thinking capability, max tokens and latest error, sourced from the llm-pi-ai config and the compat-healer error log.

dsh plugin: keep llm-pi-ai provider routes' model lists in step with the pi.dev gateway, written through the official settings seam

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

LLM compatibility auto-healer: detects 400 errors from incorrectly declared model capabilities (thinking/reasoning) on transit/gateway providers, then idempotently patches `llm-pi-ai` config and suppresses thinking on the next request — no restart needed. Full settings UI for every pi-ai compat field.