googleapis/js-genai v2.29.0 on GitHub

2.29.0 (2026-10-13)

accumulate streaming continuation usage metadata and expose initialPromptTokenCount (dbc961f)
Add continuation_token to the Interactions interaction.status_update event. (a93776c)
Add a CONTINUATION_REQUIRED Interaction status (754f71f)
add billable token counts fields (839ffc2)
Add startOffset/endOffset to Transcription and interimTranscriptTimestampEnabled to RealtimeInputConfig (bdbf156)
Add usage in InteractionStatusUpdate events (8892aea)
automatically consume the continuation token (98637d1)
cli: update Speakeasy generator to v2.948.0, bump CLI to v0.4.2, and apply CLI overlay fixes (22d53ec)

clear intermediate CONTINUATION finishReason in streaming continuation (22706af)
do not record incomplete continuation stream turns in curated chat history (81c3c49)
gemini-api-cli: remove unsupported 2.5 and 1.6 models from Interactions model options and CLI examples (1002720)
js: do not set initial prompt token count for requests that do not use automatic consumption of continuation token (0885fb9)
js: fix streaming continuation edge cases (stale token, AbortError, initialPromptTokenCount) (f3d10a6)
Raise default HTTP timeouts so long-running requests aren't killed client-side (10e850c)
resume streaming generation from the latest checkpoint continuation token on mid-stream errors or cutoffs (625ac2c)
Update EnvironmentConfig.env schema to map keys to EnvVar or string. (8478e12)