teknium1 70aaa774be fix(opencode-go): emit Kimi reasoning_effort, match KimiProfile shape ... The Kimi K2 branch added in the prior commit only emitted extra_body.thinking and dropped reasoning_effort entirely. KimiProfile (api.moonshot.ai/v1) sends both fields, and OpenCode Go proxies to the same Moonshot backend. Mirror that shape on the Go path so /reasoning effort actually reaches Kimi. - low/medium/high pass through verbatim - xhigh/max clamp to high (Moonshot's max supported value) - minimal / unknown effort → omit reasoning_effort, keep thinking on - disabled / no config → unchanged - DeepSeek branch unchanged		2026-05-23 02:20:28 -07:00
..
browser
image_gen	refactor(image_gen): port FAL backend to plugins/image_gen/fal	2026-05-22 04:10:45 -07:00
memory
model_providers	fix(opencode-go): emit Kimi reasoning_effort, match KimiProfile shape	2026-05-23 02:20:28 -07:00
video_gen
web	test: use subprocesses for each test file (#29016)	2026-05-21 16:40:04 +05:30
__init__.py
test_achievements_plugin.py	test: use subprocesses for each test file (#29016)	2026-05-21 16:40:04 +05:30
test_disk_cleanup_plugin.py
test_google_meet_audio.py
test_google_meet_node.py
test_google_meet_plugin.py
test_google_meet_realtime.py
test_kanban_dashboard_plugin.py	fix(kanban-dashboard): restore implementations dropped during salvages (#28481)	2026-05-18 21:54:56 -07:00
test_kanban_worker_runs.py
test_langfuse_plugin.py
test_retaindb_plugin.py
test_teams_pipeline_plugin.py