Meta Model API (Muse Spark, Muse Wonder) as an AI provider
維護者通常 1 天內回覆
還沒有人認領這個 Issue。
評估
研究方向
Start in apple/TablePro/Models/AI/AIProviderPreset.swift and read the existing Requesty preset and the model fetching and chat streaming paths it uses. Check the Meta API details in the issue, especially the default model and filtering fetched models to chat models. Done when the Meta preset works with authentication, model selection, reasoning, tool calls, and streaming as described.
由索引模型根據 Issue 內容生成。
描述
Problem
Meta's Muse models (Muse Spark, Muse Wonder) are served by the Meta Model API. Using them today means adding a Custom provider and typing the endpoint and model ID by hand.
Proposed solution
Add Meta as an AIProviderPreset (apple/TablePro/Models/AI/AIProviderPreset.swift), next to Requesty. No new AIProviderType case.
API facts from https://dev.meta.ai/docs/:
- Base URL
https://api.meta.ai/v1, OpenAI-compatiblePOST /v1/chat/completions. Preset endpoint ishttps://api.meta.ai. - Auth:
Authorization: Bearer <key>. Keys from https://dev.meta.ai/api-keys/. - Bad, missing or revoked key returns 401 (
invalid_api_key), sorejectsBadKeyWithForbidden: false. 403 means the key lacks access to a model. GET /v1/modelslists models, newest first.- Chat models:
muse-spark-1.3(recommended),muse-spark-1.2,muse-spark-1.1,muse-wonder-1.0(preview). 1,048,576 token context. -contributorvariants are cheaper but Meta may train on the content.reasoning_effortacceptsminimal,low,medium,high,xhigh,max.nonereturns 400. OurReasoningEffortwire values all fit.- Tool calling and SSE streaming are supported.
- Public preview, availability varies by country.
To check while building:
- Default model is
muse-spark-1.3, not the first fetched model. - Fetched list includes non-chat models (
muse-image-1.0,muse-voice-transcribe-1.0,sam-3.1). Keep them out of the chat model picker. - Server accepts
stream_options.include_usage. - Streamed tool-call chunks parse with the current OpenAI-compatible decoder.
Alternatives considered
Custom provider with https://api.meta.ai works if the user knows the model ID. OpenRouter also serves Muse Spark.
- 主要語言
- Swift
- 星號
- 6.2k
- 分支
- 412
- 平均合併
- 3 小時 56 分鐘
- 30 天內合併 PR
- 669
環境準備
這個專案沒有提供開發容器、Dockerfile 或貢獻指南,環境需要你自己搭建:先看它的 README,通用步驟見我們的新手貢獻指南。
從這裡開始
- 先讀完整個 Issue,再讀專案的貢獻指南。
- 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
- Fork 儲存庫,在一個分支上完成修改。
- 送出 Pull Request,並在描述裡引用這個 Issue 編號。
TableProApp/TablePro 的其他 Issue
-
Linux: Remember Password fails silently when there is no default keyring可能已有人在做 @datlechin 今天認領。 未關閉bug platform-linux
難度 2/5 1-3 小時 新手友好度 75/100
TableProApp/TablePro#4098 ·
維護者通常 1 天內回覆
-
bug platform-linux
難度 2/5 1-3 小時 新手友好度 35/100
TableProApp/TablePro#4101 ·
維護者通常 1 天內回覆
-
bug platform-linux
難度 4/5 3-5 天 新手友好度 48/100
TableProApp/TablePro#4099 · 3 則留言 ·
維護者通常 1 天內回覆
-
enhancement platform-macos
難度 5/5 一週以上 新手友好度 25/100
TableProApp/TablePro#4071 ·
維護者通常 1 天內回覆
-
bug
難度 3/5 1-2 天 新手友好度 45/100
TableProApp/TablePro#4037 · 4 則留言 ·
維護者通常 1 天內回覆
查看 TableProApp/TablePro 的全部 Issue
相似的 Issue
-
難度 2/5 1-3 小時 新手友好度 83/100
OneBusAway/vehicle-positions#260 ·
維護者通常 1 天內回覆
-
難度 1/5 1 小時以內 新手友好度 85/100
eliasstravik/herdr-projects#789 · 1 則留言 ·
-
follow-up needs-triage S3: minor
難度 1/5 1-3 小時 新手友好度 85/100
manaflow-ai/cmux#38032 · 1 則留言 ·
維護者通常 1 天內回覆
-
難度 2/5 1-3 小時 新手友好度 67/100
arkavo-org/ArkavoKit#70 ·
維護者通常 1 天內回覆
-
bug
難度 2/5 1-3 小時 新手友好度 70/100
vorssaint/vorssaint-utils#3933 · 1 則留言 ·
維護者通常 2 天內回覆