Models & Providers

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.

Codex-style DeepSeek Harness model and reasoning selector with model-advertised effort levels, DSH-native themes, left-clipped radiation effects, and copy-ready reasoning-effort declaration guidance for custom-provider models.

In-process DeepSeek Harness subagent provider that seeds a child with only the last N completed parent turns (fork-lite), leaving official fork untouched.

Tavily web search for DSH: selectable search depth, bounded requests, credential-backed settings and DeepSeek fallback.

Tavily-backed search provider for dsh: registers the `tavily` provider on ctx.web so the web_search tool runs against the Tavily Search API

Sets the DeepSeek flash model's reasoning effort per step — thinking off for short cheap prompts, low for a plain request, high for engineering work — and raises it only on repeated tool failures. The model itself never changes; effort max is opt-in.

DSH plugin: matches a model you declared on a custom gateway to the capability metadata it should have — context window, output cap, reasoning levels and image support — by looking the bare model name up at runtime; the plugin never writes your settings document.

DeepSeek Harness coding-subscription OAuth: SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code, Claude Code. Fixes AUTH API key is invalid, INVALID_REPLAY_STATE, grok-4.6 xhigh, Kimi Bearer vs x-api-key.

Composer polish: the model-select button shows a per-provider brand icon and collapses to icon-only under a narrow composer row (same mechanism as the built-in access-mode button), with a generic fallback icon for unrecognized/new providers.

OpenRouter free-models browser plugin (dual-face): fetch OpenRouter models, filter the free ones (price 0 or :free), list them newest-first in a Settings tab with local search and full model info, and create a ready-to-use DSH model config (settings.yaml

DSH plugin: SearXNG-backed search provider for ctx.web (self-hosted, 1GB-VPS friendly)

IP/domain allowlist web_fetch provider for DeepSeek Harness: lets web_fetch reach allowlisted hosts/IPs freely (incl. proxy fake-IP addresses like 198.18.x.x) while keeping the default public-IP safety check for everything else.

Search and select models in the DeepSeek Harness WebUI with a native settings card.

Model channel manager: several provider/model candidates share one virtual route (roundrobin/<group>) with failover, retry, timeout and cooldown; a settings tab edits providers and groups, runs per-model speed tests and real single-model request tests, and a seven-day health panel aggregates latency, failures and upstream token usage (input, output, cache and reasoning).

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.

dsh web 插件：自动配置模型思考档位与能力，并按 provider+model 记住最后选择的思考档位

Sign in to DeepSeek Harness model providers with a subscription: drives the OAuth flows the harness registers but never exposes.

Use a Claude Pro or Max subscription as a DeepSeek Harness model provider, by driving the Claude Code CLI through the Agent SDK.

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.

A web-search provider for the DeepSeek Harness, fully local no API key needed.

LLM provider plugin for the DeepSeek Harness (dsh): streams Claude through your Claude Code subscription (claude.ai OAuth credentials), no Anthropic API key required.

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.

Per-provider request headers in the DeepSeek Harness Models settings page, with per-conversation ${sessionId} expansion.

Durable provider-neutral Wait, Event, and Delivery runtime for DeepSeek Harness.