Andrew Heard 516f6766bf test(ai): check reasoning in single tool call test (#16999) ...

Move the `.reasoning` transcript check into
`sessionRespondSingleToolCall` and remove
`sessionRespondWithReasoningAndToolCalls`, which used `gemini-3.8-flash`
and often timed out. All Gemini 3 models are reasoning models and
return thought signatures with function calls, so the default
`gemini-3.5-flash-lite` model covers this and the suite makes one fewer
live call per backend.

2026-11-04 13:20:01 -05:00

..

.github/workflows

chore(ci): pin ubuntu versions (#16958)

2026-10-29 12:24:22 -04:00

scripts/typegen

feat(ai): regenerate data models from rev 20261019 (#16960)

2026-10-27 00:47:36 -04:00

Sources

feat(ai): add image input support to GLM (#16895)

2026-10-30 16:57:47 -04:00

Tests

test(ai): check reasoning in single tool call test (#16999)

2026-11-04 13:20:01 -05:00

.gitignore

feat(ai): add Gemini API Swift data model generator (#16879)

2026-10-09 18:35:46 -04:00

Package.swift

test(ai): GeminiLanguageModel integration testing foundation (#16617)

2026-09-07 18:28:37 -04:00