Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion packages/core/src/model-metadata.ts
Original file line number Diff line number Diff line change
Expand Up @@ -433,6 +433,10 @@ const STATIC_MODEL_METADATA: Partial<Record<ProviderType, Record<string, ModelMe
capabilities: { ...REASONING_FUNCTION_CALLING, webSearch: true },
thinkingOptions: { efforts: ['high', 'max'], toggle: true },
},
'deepseek-v4-flash-vision-exp': {
capabilities: { vision: true, ...REASONING_FUNCTION_CALLING, webSearch: true },
thinkingOptions: { efforts: ['high', 'max'], toggle: true },

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[P3] efforts here is ['high', 'max'] but every current upstream source lists low for this model, so the menu will be missing the cheapest effort option.

  • models.dev lists deepseek-v4-flash-vision-exp with toggle + effort values ['low', 'high', 'max'] (last updated 2026-08-21, the release date).
  • The official Thinking Mode guide accepts reasoning_effort: low/high/max.
  • The deepseek-v4-pro entry just below already pins ['low', 'high', 'max'] (lastUpdated 2026-08-13).

The value looks copied from the deepseek-v4-flash sibling above, whose pinned set predates its 0731 refresh (models.dev now lists flash as low/high/max too). Suggested fix: efforts: ['low', 'high', 'max'].

(Separate observation, not for this PR: the deepseek-v4-flash static entry has the same staleness and might deserve its own follow-up so the next model doesn't inherit it.)

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[P2] efforts: ['high', 'max'] is missing 'low'.

Three independent sources agree this model exposes low/high/max: the models.dev entry (refreshed 2026-08-21, toggle plus low/high/max), the official Thinking Mode docs (reasoning_effort accepts low/high/max), and deepseek-v4-pro two entries below, which already pins ['low', 'high', 'max'].

The likely origin is visible in the file: the sibling deepseek-v4-flash entry directly above carries the same ['high', 'max'], which is a stale high-water mark from before the 07-31 refresh. This entry appears to have inherited it.

I am grading this P2 rather than P3, and I want to be explicit that I am raising a colleague's grade. The reasoning: this PR's entire purpose is to add correct metadata for one model. A wrong effort list is not a peripheral nitpick here — it is a defect in the single thing being added, and it is user-visible, since the effort menu simply will not offer low for this model. Merging as-is would ship the exact error the change set out to prevent, and the fix is one array element.

Separately, and explicitly not part of this PR: deepseek-v4-flash above looks stale for the same reason. Worth a follow-up, but please do not widen this PR to cover it.

},
'deepseek-v4-pro': {
capabilities: { ...REASONING_FUNCTION_CALLING, webSearch: true },
lastUpdated: '2026-08-13',
Expand Down Expand Up @@ -578,7 +582,13 @@ const CURATED_CATALOG_FALLBACK_MODELS: Partial<Record<ProviderType, readonly str
'claude-sonnet-4-5-20250929',
],
openai: ['gpt-5.5', 'gpt-5.5-pro', 'gpt-5.4', 'gpt-5.4-mini', 'gpt-5'],
deepseek: ['deepseek-v4-flash', 'deepseek-v4-pro', 'deepseek-reasoner', 'deepseek-chat'],
deepseek: [
'deepseek-v4-flash',
'deepseek-v4-flash-vision-exp',
'deepseek-v4-pro',
'deepseek-reasoner',
'deepseek-chat',
],
google: ['gemini-3.5-flash', 'gemini-3.1-pro-preview', 'gemini-2.5-pro', 'gemini-2.5-flash'],
'zai-coding-plan': ['glm-5.2', 'glm-5.1', 'glm-5-turbo', 'glm-4.7', 'glm-4.5-air'],
MiniMax: ['MiniMax-M3'],
Expand Down