Models & Providers

Adds two-level tabs (provider and model family) to the composer model picker for large catalogs, with configurable family rules.

Model quality testing for DeepSeek Harness Desktop with a question bank, manual and scheduled checks, saved responses, human reviews, and model attribution. Install it into the desktop profile: the shared Go backend is started only by the desktop app, and a web profile can only view an already-running desktop backend.

ModelScope connector: OpenAI-compatible chat models, a Models-page provider entry, and a composer magicube balance while a ModelScope model is selected.

Switches to the next healthy model candidate before the next agent step when the current model has been marked unhealthy.

Lists RouterAI prompt and completion prices for the profile models, highlighting the active one. Requires a model provider whose config key is `routerai`; without it the table shows no data.

Routes model and reasoning effort per turn: a cheap classifier reads each request and picks one of five tiers, a supervisor model re-routes on tool errors and checkpoints, and upgrading to the stronger model waits for confirmation.

Makes DSH's OpenAI Responses calls stateful: after the upstream confirms it stored a response, each turn sends only the newly added input items plus previous_response_id, and a stateless upstream is detected on the first response so every later request falls back to the full history.

Adds a model picker to teammate (continuable subagent) sessions: switch a quota-exhausted teammate to a model that still has quota and let it continue, without rebuilding it or touching the Lead session.

Customize per-provider User-Agent headers and stream idle timeouts, set retry counts and intervals with visible progress, and optionally send bounded continuation messages after retries run out.

Merges your configured, runtime-registered and locally cached models into one panel, probes and minimal-request tests them, pulls each channel's upstream /v1/models catalog, and chains the keepers into named schemes. A virtual ModelPool provider fails over at request time with per-model cooldowns, exponential backoff, image-request avoidance for text-only models, and a 10-minute memory for rejected reasoning levels. Adds a token ledger by day and model with CSV export, and 21 regression probes. Not a fork of dsh-llm-fallbacks.

Gives hand-declared models on custom or relay routes a vendor-matched reasoning-effort picker: detects Claude, GPT, DeepSeek, GLM, Kimi, Qwen, Gemini, Grok, Doubao or MiMo from the model id, display name or endpoint host, fills in only the levels that vendor accepts plus the pi-ai compat fields its request format needs, and writes them into the profile config so the Models page reasoning switch turns on. Models you edit or switch off are left alone, and a Models page card hands them back on request.

Writes one model and reasoning effort into every session at once from a control beside the composer model picker, since the shipped picker only changes the session you are in. Sessions that already match are skipped, subagent sessions follow their parent instead of being written, and the same selection can be pinned as the default for new sessions.

Declares two model routes in the llm-pi-ai settings section — a TLPro gateway and Z.ai's GLM-5.3 endpoint — with per-model context windows, output caps and reasoning-effort ladders, so the stock model picker can select and tune them. Requires your own TLPRO_API_KEY and a Z.ai coding-plan ZAI_API_KEY; the patch replaces the whole llm-pi-ai row config.

Runs one task through several configured models at once — in parallel or as a primary/secondary review — and returns each model's answer plus an aggregated digest.

Ordered model rotation for the DSH model picker: a rate-limited or repeatedly timing-out member hands over to the next one, members that only timed out are retested once, and the DSH platform model is the sticky last resort. Ships a settings page with editable chains and a short-429 in-place retry switch.

Remembers the model used before quitting and restores it as the startup default.

Connect DeepSeek Harness to the local Codex CLI with dynamic model discovery, image input, Harness-owned tools, and read-only ChatGPT plan and quota display.

After user setup, guides native subagents toward model preferences by task type, using native model-selection permissions with no extra routing-model calls.

Signs in to ima.qq.com (Tencent IMA) with a WeChat QR code and runs a localhost OpenAI-compatible relay in front of its SSE chat endpoint, so the four models behind it appear in the picker.

TeleAgent (China Telecom TeleAI "Stellar" agent) model provider for DeepSeek Harness with the working v1 gateway signing: two-round HMAC-SHA256 keyed by the login JWT signature segment, which fixes the 40104 rejections the older local-v1 signing produced. Signs in through a dedicated browser window over the DevTools protocol — the plugin intercepts the login callback the same way the official desktop app does, so nothing has to be copied by hand — and also accepts a pasted token. Ships points balance, daily check-in, an in-composer account chip, and a configurable context window (100K by default, 16K–2M, since the gateway declares no catalogue and the official client ships one shared 100K preset for all three tiers). Cannot be installed alongside anye-99/dsh-codearts-auth: both register the same teleagent provider, and this plugin reuses its credentials and derives its SSE/tool-call parsing from it. It also registers the same teleagent provider as anbulang/dsh-connect-teleagent, so install only one of the two.

Adds a relay_check tool that runs relaycheck against an LLM API relay to detect model swaps, misreported usage, truncated context and injected prompts; keys are read from environment variables.

Switch OpenAI models between Codex-style Responses WebSocket transport and SSE from the composer, inheriting DSH provider settings with an optional priority-tier toggle.

Use Claude models in DeepSeek Harness through Claude subscription accounts.

Google Antigravity model provider based on LiZhenNet/dsh-antigravity, with a multi-account pool added. Do not install it in the same profile as LiZhenNet/dsh-antigravity: both register the same bundle id (dsh-antigravity) and the same npm package name.