adevwithpurpose ad672ef822 fix(sse): mark gemini-3.5-flash as thinking-capable ...

The base gemini-3.5-flash entry spread the shared GEMINI_35_FLASH_MODEL_SPEC
constant, which has supportsThinking:false because it is also spread into
several Antigravity flash-tier aliases that reject client-supplied thinking
params. That made the reasoning-routing policy resolve reasoning_effort as
"unsupported" for the base Google AI Studio model, producing a spurious
pre-provider HTTP 400 even though the model supports reasoning (it has an
effort-tier alias gemini-3.5-flash-high).

Set supportsThinking:true as an explicit override on the base
gemini-3.5-flash entry only, leaving the shared spec and the Antigravity
tier aliases unchanged.

Closes #10286

2026-08-15 03:02:39 -03:00

..

_helpers

…

_setup

…

benchmarks

…

boundary

…

e2e

feat(providers): integrate audited free-tier gateways (#9210)

2026-08-12 16:19:25 -03:00

fixtures

fix(radar): refresh entitlement-sensitive state (#9776)

2026-08-10 20:10:12 -03:00

golden-set

…

helpers

…

homolog

…

integration

feat(codex): add OAuth fingerprint convergence modes (#10243)

2026-08-14 00:57:23 -03:00

live

…

llm-security

…

load

…

manual

…

security

…

snapshots

refactor(providers): remove the Puter provider at its owner's request (#10210)

2026-08-12 16:54:50 -03:00

translator

…

unit

fix(sse): mark gemini-3.5-flash as thinking-capable

2026-08-15 03:02:39 -03:00

_cp_mock_hook.mts

…

_cp_mock_module.mts

…

_run_dns_guard_test.sh

…

e2e-tool-calls.sh

…

theoldllm-stress.test.ts

…