TanStackOSS
    ai
    fix(anthropic): align #849 max_tokens map and tests with synced model metadata Main's OpenRouter metadata sync (e14586b3e) retired claude-3.x / claude-4 / -fast model ids and added Fable 5 / Sonnet 5, so after rebasing: - ANTHROPIC_MODEL_MAX_OUTPUT_TOKENS again mirrors ANTHROPIC_MODELS exactly (removed retired entries, added claude-fable-5 / claude-sonnet-5). - Tests use current ids (claude-opus-4-8, claude-opus-4-1, claude-sonnet-4-5, claude-opus-4-5 for the 32K ceiling case). - The 'ceiling below the non-streaming limit' test relied on claude-3-haiku's 4K ceiling; no current model sits under 21K, so it now asserts every model in the lineup clamps on the non-streaming path instead. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    nx run-many --targets=build --exclude=examples/**,testing/**
Succeeded
CI Pipeline Execution

nx run-many --targets=build --exclude=examples/**,testing/**

Click to copy
Linux
4 CPU cores
read-write access token used
f54cf0bd853
100%

Cache hits

47 of 47 tasks used cache.

Get faster results

Learn how to enable distribution.

Atomizer enabled

47 groups of tasks optimized.

© 2026 - Nx Cloud

Terms of ServicePrivacy PolicyChangelogStatusDocsContact Nx CloudPricingCompany@NxDevTools