feat: drive reasoning variants from models.dev reasoning_options

Parse the curated reasoning_options field from models.dev api.json and use
its effort values to generate reasoning variants instead of the hardcoded
per-package tables, in both the v1 provider catalog and the v2 catalog plugin.

- core: ModelsDev.ReasoningOption discriminated union (toggle | effort |
  budget_tokens); effort values stay open strings and unknown option types
  are tolerated since api.json is cast, not decoded
- core: ReasoningVariants shared per-package effort encoder used by v1
  ProviderTransform.variants and the v2 ModelsDevPlugin
- core: v2 catalog generates effort variants from reasoning_options;
  curated experimental modes win id collisions; anthropic profile gains
  the effort semantic
- llm: anthropic protocol supports adaptive thinking, lowers effort to
  output_config.effort, and sends the effort-2025-11-24 beta header
- opencode: resolved Provider.Model carries capabilities.reasoningOptions
  (unknown types and null effort values dropped at the mapping boundary);
  config models accept reasoning_options; models without usable effort
  data fall back to the hardcoded tables unchanged

Catalog-wide audit vs live api.json: 2975 models byte-identical, 38 diffs,
all data correcting stale hardcoded effort lists.
This commit is contained in:
Aiden Cline 2026-06-09 17:21:11 -05:00
commit f7dcfc2680
15 changed files with 954 additions and 62 deletions

View file

@ -1816,6 +1816,20 @@ export type ProviderConfig = {
release_date?: string
attachment?: boolean
reasoning?: boolean
reasoning_options?: Array<
| {
type: "toggle"
}
| {
type: "effort"
values: Array<string>
}
| {
type: "budget_tokens"
min?: number
max?: number
}
>
temperature?: boolean
tool_call?: boolean
interleaved?:
@ -2082,6 +2096,20 @@ export type Model = {
capabilities: {
temperature: boolean
reasoning: boolean
reasoningOptions?: Array<
| {
type: "toggle"
}
| {
type: "effort"
values: Array<string>
}
| {
type: "budget_tokens"
min?: number
max?: number
}
>
attachment: boolean
toolcall: boolean
input: {