Skip to content
Source
Sign inSign up
TanStack/schemas

serverTools is null with no factSources entry on 66 chat rows; Grok and Gemini tool lists look short #707

Send to my agent
Opentombeckenham opened this issue 2 comments
tombeckenhamcommented

Problem

serverTools is null on 66 chat rows, and none of them has a factSources.serverTools entry. No row has []. A reader cannot tell "this model has no built-in tools" from "not filled yet".

#409 asked for this and is closed, but its acceptance is not met. Snapshot 2026-11-21, GET /v1/models?provider=…&provenance=1, chat rows only.

ProviderChat rowsserverTools null, no factSources entryExamples
openai7019gpt-5-search-api, gpt-audio, gpt-audio-1.5
mistral3216codestral-2508, ministral-14b-2512, glm-5-2
gemini3112antigravity-preview-09-2026, aqa
byteplus2311deepseek-v3-2-251201, glm-4-7-251222, seed-1-6-250615
groq75allam-2-7b, openai/gpt-oss-safeguard-20b
grok73grok-4.3, grok-4.20-multi-agent-0309

Two lists also look short:

  • grok: every filled row has only ["attachment_search"]. #409 says xAI documents web_search and x_search.
  • gemini: the vocabulary across all rows is codeExecution, computerUse, fileSearch, googleMaps, urlContext. Grounding with Google Search is not in it.

Impact

TanStack AI writes each new model's built-in tool list from this field, with no second source and no hand-written list. A null with no entry forces a guess.

Ask

  • When the provider documents no built-in tools for a model, return serverTools: [], or keep null and add factSources.serverTools with derivation: "source-silent" (as #273 does for maxOutput).
  • Check the Grok and Gemini tool lists against the provider docs.

Acceptance

  • Every chat row of the six providers above has serverTools as an array, or a factSources.serverTools entry.
  1. tanstack-source added labelsbug

  2. tombeckenham assignedtombeckenham

  3. tombeckenham linked this to #721

  4. tombeckenham unlinked this from #721

  5. tombeckenham closed this

  6. #721 is merged. It does not close this issue.

    What landed: factSources.serverTools with derivation: "source-silent" on 27 chat rows where the provider's per-model source was read and states no built-in tool (mistral 16, openai 7, gemini 3, byteplus 1), the Gemini "Grounding with Google Search" label is read again, and gemini-flash-latest copies its stated alias target's tools.

    Still neither an array nor an entry: 38 chat rows. Their provider does not state tools per model on the page we read, so calling them source-silent would be false.

    ProviderRowsWhy
    openai (12)gpt-realtime* (10 ids), gpt-live-1, gpt-live-1.1Realtime or Live route supported, model page lists no tools
    gemini (8)antigravity-preview-05-2026, -09-2026, -latest, deep-research-preview-04-2026, deep-research-max-preview-04-2026, gemini-2.5-computer-use-preview-10-2025, gemma-4-26b-a4b-it, gemma-4-31b-itPage has no Capabilities row, or no model page
    byteplus (10)deepseek-v3-2-251201, glm-4-7-251222, gpt-oss-120b-250805, seed-1-6-* (4), seed-1-8-251228, seed-2-0-lite-260228, seed-2-0-mini-260215Not in the Tool use table
    groq (5)allam-2-7b, meta-llama/llama-prompt-guard-2-22m, -86m, openai/gpt-oss-safeguard-20b, qwen/qwen3.8-27bBuilt-in tools page is not exhaustive
    grok (3)grok-4.20-0309-non-reasoning, grok-4.20-multi-agent-0309, grok-4.3Files list says "e.g."

    Sources a parser could read next: Groq's browser-search and code-execution "Supported Models" tables; Gemini's antigravity-agent, deep-research and computer-use guides and the Gemma on Gemini API guide; OpenAI's realtime MCP guide; xAI's multi-agent page (it names doc names, not request type ids, so it needs a mapping the page itself states).

  7. Reopening. #721 was unlinked from this issue before it merged, but the issue closed anyway on merge (most likely the Fixes #707 line still in the PR body on GitHub). 38 chat rows still have neither an array nor an entry: see the table in the comment above.

  8. tombeckenham reopened this

Sign in to join this conversation.