Skip to content
Source
Sign inSign up
TanStack/schemas

Perplexity: models page DeepSeek V4 Pro card ('X, an open-weight reasoning model.') is an unread shape #100006

Send to my agent
Closedtombeckenham opened this issue 2 comments
tombeckenhamcommented

What fails

From the 2026-11-17 21:51 UTC poll, Perplexity reports ingest_failed: perplexity: models page states a reasoning model in an unread shape (source https://docs.perplexity.ai/docs/agent-api/models.md, PostHog project 643425). It is a docs-row failure, so it repeats once per docs TTL and leaves the reasoning flag unavailable for every Perplexity row on that page.

Why

The page has a new DeepSeek card:

DeepSeek V4 Pro, an open-weight reasoning model.

parsePerplexityModelsPage (src/server/providers/adapters/perplexity.ts:157-175) reads only <names> — …reasoning model… or <names> is …reasoning model…, so the appositive comma form throws unread('a reasoning model').

The other cards still parse, for example GLM 5.3 and GLM 5.3 Flash — Z.AI reasoning models. and Nemotron 3.5 Super is a reasoning model with a 1,048,576-token context window….

Fix

  1. Accept <names>, an? …reasoning model. as a stated reasoning flag for the tab's ids. Keep every other wording throwing (fail-closed).
  2. The same sentence states open-weight. Read that into openWeights: true only if the adapter already reads open weights from Perplexity's page. Otherwise note it here and leave it alone.
  3. Add a test with the DeepSeek V4 Pro card.
  1. tombeckenham assignedtombeckenham

  2. Fix step 2: the Perplexity adapter reads openWeights nowhere today (no reference in src/server/providers/adapters/perplexity.ts), so the card's "open-weight" is left unread, as the issue says. The Nemotron 3 Ultra card states the same thing and is also unread. Reading it is a separate change.

  3. tombeckenham linked this to #688

  4. Fixed by #688, deployed to prod as ffaabafe at 2026-11-17 22:18 UTC.

  5. tombeckenham closed this

Sign in to join this conversation.