docs(clients): plan 17 meta scope is the Meta Model API (Muse Spark), not Llama

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-24 06:09:41 +02:00
co-authored by Claude Sonnet 5.5
parent 2674e62c39
commit be485ef3bc
2 changed files with 3 additions and 3 deletions
+1 -1
View File
@@ -4,7 +4,7 @@
namespace molo::example::app {
// Meta Llama API. Stub: the module agent fills this in.
// Meta Model API (Muse Spark and the Muse family). Stub: the module agent fills this in.
void register_ai_meta_demo(fw::Router& router, Services& services) {
(void)router;
(void)services;
+2 -2
View File
@@ -24,7 +24,7 @@ finished module (for example `src/google/runtime`: `calls.cpp` table,
| xai platform | `src/xai/platform` | Voice (realtime WebSocket agent API, TTS, STT), collections and documents, files, management API (API keys, billing, usage, team), API-key info; reuse `src/google/live` `WsClient` for WebSocket |
| anthropic core | `src/anthropic/core` | Messages (create, streaming with every event type, thinking, tools: client tools and server tools such as web search, web fetch, code execution, computer use, bash, text editor, memory, tool search, MCP connector), vision / PDF / documents / citations / search results, prompt caching, structured outputs, Message Batches, token counting, Models, Files, Skills, beta header handling, `AnthropicChatModel : ChatModel` |
| anthropic admin | `src/anthropic/admin` | Admin API (organization, users, invites, workspaces and members, API keys), usage and cost reports (messages, Claude Code), and any public managed-agents / sessions / environments REST surface; admin key is a separate credential |
| meta | `src/meta` | Llama API: chat completions (native and OpenAI-compatible), models, moderations, tool calling, structured output, image understanding, files / uploads if public, speech if public, `LlamaChatModel : ChatModel` |
| meta | `src/meta` | Meta Model API (dev.meta.ai): Muse Spark (Responses-style and any chat/messages endpoints the docs list), tool calling, structured output, reasoning, vision input, Muse Wonder, Muse Image, Muse Voice Transcribe, Segment Anything, Muse Spark Open, Muse Glimmer, models, files / uploads if public, usage and pricing fields, the Muse Code agent surface if it has an API, `MetaChatModel : ChatModel` |
| deepseek | `src/deepseek` | Chat completions (chat and reasoner, `reasoning_content`, tool calls, JSON output), beta: prefix completion and FIM, context caching usage, models, user balance, the Anthropic-compatible endpoint, errors and rate-limit semantics, `DeepseekChatModel : ChatModel` |
## 2. Rules for every package
@@ -71,7 +71,7 @@ finished module (for example `src/google/runtime`: `calls.cpp` table,
Record them under `## Verified live`. Build opt-in live tests gated on
`MOLO_LIVE_NET=1` plus the vendor key (`ANTHROPIC_API_KEY`,
`ANTHROPIC_ADMIN_KEY`, `XAI_API_KEY`, `XAI_MANAGEMENT_KEY`,
`DEEPSEEK_API_KEY`, `LLAMA_API_KEY`, loaded via `llm::Config::get`), with
`DEEPSEEK_API_KEY`, `META_API_KEY` (the docs' own example uses `MODEL_API_KEY`; accept both), loaded via `llm::Config::get`), with
a loud SKIP otherwise. Live tests are read-only (models list, balance,
retrieve) plus at most one smallest-possible completion. Anything that
costs real money (media generation, batches, fine-tuning, long