add-model
Add a new LLM model to apps/sim/providers/models.ts with specs verified against the provider's live API docs (no hallucination)
simstudioai · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add simstudioai/sim --skill add-model技能说明
name: add-model description: Add a new LLM model to apps/sim/providers/models.ts with specs verified against the provider's live API docs (no hallucination) argument-hint: [docs-url]
Add Model Skill
You add a new model entry to apps/sim/providers/models.ts. Every numeric and capability claim MUST be derived from a live web fetch of the provider's official docs in this session. Marketing emails, training data, and your prior knowledge are not sources of truth — they routinely hallucinate pricing, context windows, and capability lists.
Hard rules (do not skip)
- Live-fetch or refuse. Before writing the entry, you must successfully WebFetch the provider's official models/pricing page in this session. If you cannot reach an authoritative source for any field, mark the field as UNVERIFIED in your report and ask the user before guessing. Never fill in pricing or capabilities from memory.
- Two-source rule for pricing. Cross-check input/output/cached pricing against at least one secondary source (OpenRouter, Artificial Analysis, CloudPrice, mem0, intuitionlabs). If sources disagree, the provider's own docs win — but flag the disagreement.
- Read the code before setting capability flags. Capability flags are dead unless the provider's implementation under
apps/sim/providers/{provider}/actually consumes them (see Consumption Matrix below). Setting a flag the provider ignores is a silent bug. - Cite every fact. Your final report must list the URL each value came from. No URL → not verified.
Your Task
- Identify provider and model id from user args
- Live-fetch official docs + pricing page + capability/parameter pages + at least one secondary source
- Apply the Consumption Matrix to know which capability flags are real
- Read 2-3 sibling entries in
models.tsand match their pattern exactly - Check the repo-side touchpoints that are NOT data-driven (hosted-key billing, tests, provider code)
- Insert the entry, run
bun run lint, print the verification report
Step 1: Live source-of-truth lookup
In priority order — fetch all that exist for the provider:
| Provider | Models index | Pricing | Reasoning/parameter caveats |
|---|---|---|---|
| OpenAI | platform.openai.com/docs/models | openai.com/api/pricing | platform.openai.com/docs/guides/reasoning |
| Anthropic | platform.claude.com/docs/en/about-claude/models/overview | claude.com/pricing (API section) | platform.claude.com/docs/en/build-with-claude/extended-thinking |
| Google (Gemini) | ai.google.dev/gemini-api/docs/models | ai.google.dev/pricing | ai.google.dev/gemini-api/docs/thinking |
| xAI | docs.x.ai/developers/models | docs.x.ai/developers/models (per-model detail page) | docs.x.ai/developers/model-capabilities/text/reasoning |
| Mistral | docs.mistral.ai/getting-started/models/models_overview | mistral.ai/pricing | n/a |
| DeepSeek | api-docs.deepseek.com/quick_start/pricing | same | api-docs.deepseek.com/guides/reasoning_model |
| Groq | console.groq.com/docs/models | groq.com/pricing | n/a |
| Cerebras | inference-docs.cerebras.ai/models | cerebras.ai/pricing | n/a |
Secondary verification (use at least one): openrouter.ai/<provider>/<model>, artificialanalysis.ai/models/<model>, cloudprice.net/models/<provider>-<model>.
Use a precise WebFetch prompt: "Extract for {model_id}: exact model id string, context window in tokens, input price per 1M, cached input price per 1M, output price per 1M, max output tokens, supported reasoning effort levels, accepted parameters (temperature, top_p), release date. Do not fill in fields you cannot find."
Step 2: Consumption Matrix (which provider honors which capability)
| Capability | Honored by | Effect if set elsewhere |
|---|---|---|
temperature | All providers (passed through if set) | Safe but inert on always-reasoning models that reject it |
toolUsageControl | All providers (provider-level, not per-model) | n/a — set on ProviderDefinition, not models |
reasoningEffort | openai/core.ts, azure-openai, xai, deepseek, groq, zai, meta, litellm (each index.ts) | Not read by anthropic/gemini (they use thinking) or by mistral, cerebras, openrouter, fireworks, vertex — re-grep before assuming |
verbosity | openai/core.ts, azure-openai/index.ts only | Dead elsewhere |
thinking | anthropic/core.ts, gemini/core.ts; deepseek, groq, zai, kimi (each index.ts) read the resolved thinkingLevel | Dead elsewhere |
thinking.streamed | Docs generator + getThinkingStreamVisibility (models.ts); anthropic/core.ts uses 'summary' to request display: 'summarized' on agent-events runs | Mandatory on Anthropic-family thinking models (agent-stream-docs:check fails without it); other families fall back to provider defaults |
nativeStructuredOutputs | anthropic/core.ts, bedrock/index.ts (via models.ts supportsNativeStructuredOutputs, which reads the flag) | Dead elsewhere — fireworks/baseten/together/openrouter call their own provider-level supportsNativeStructuredOutputs that ignores the model flag (always on, always off, or OpenRouter API metadata) |
maxOutputTokens | Read by UI + executor for token estimation | Always meaningful — set if provider documents a cap |
computerUse | providers/utils.ts (getComputerUseModels → computerUseModels routing) | Set only on actual computer-use SKUs |
deepResearch | UI flag for routing to deep-research SKUs | Set only on actual deep-research model IDs |
memory: false | Conversation persistence opt-out | Set only when model genuinely cannot maintain history (e.g., deep-research) |
Always re-grep before relying on this table — the codebase moves:
rg "reasoningEffort|reasoning_effort" apps/sim/providers/<provider>/
rg "verbosity" apps/sim/providers/<provider>/
rg "request\.thinking|thinking:" apps/sim/providers/<provider>/
rg "supportsNativeStructuredOutputs|na
阅读完整来源 ↗