2
49%
main: 49%

Ran 17 Nov 2025 08:10AM UTC

Files 82

Run time 611min

Badge

Embed ▾

Committed 17 Nov 2025 08:10AM UTC coverage: 49.965% (+0.06%) from 49.909%

Job # a47489b2d5819649e80a12521c32c25cd6afa60b.2

Build Type

push

github

Committed by

web-flow

Commit Message

Fix cached token extraction from Google API responses (#192)

Google's API returns cachedContentTokenCount in the usageMetadata
field for both implicit (automatic) and explicit (CachedContent API)
prompt caching. The provider was not extracting this value, causing
cached_tokens to always report 0 even when caching was active.

This fix extracts cachedContentTokenCount and converts it to the
OpenAI-compatible prompt_tokens_details.cached_tokens format for both
google and google-vertex providers using Gemini models.

Closes #191

Run Details

3572 of 7149 relevant lines covered (49.97%)

14.7 hits per line

agentjido / req_llm / a47489b2d5819649e80a12521c32c25cd6afa60b / 2
49%
main: 49%

README BADGES
x

Markdown

Textile

RDoc

HTML

Rst

Source Files on job a47489b2d5819649e80a12521c32c25cd6afa60b.2

agentjido / req_llm / a47489b2d5819649e80a12521c32c25cd6afa60b / 2 49% main: 49%

README BADGES x

Markdown

Textile

RDoc

HTML

Rst

Source Files on job a47489b2d5819649e80a12521c32c25cd6afa60b.2

agentjido / req_llm / a47489b2d5819649e80a12521c32c25cd6afa60b / 2
49%
main: 49%

README BADGES
x