sususu 8bd67f3338 feat(kimi): add Kimi K2.8 model definitions, normalization, and temperature guard ...

- Add kimi-k2.8 and kimi-k2.8-code with 1M context, 64k completion tokens, low/high/max thinking, and zero_allowed support to models.json.
- Remap K2.8 aliases (kimi-k2.8, k2.8, kimi-k2.8-code, k2.8-code, and -preview variants) to upstream canonical kimi-for-coding.
- Normalize temperature for Kimi upstream to prevent 400 errors (strict 0.6 for disabled thinking, 1.0 for enabled).
- Align zero_allowed: true across K2.8 and K3 models based on live upstream verification of thinking.type=disabled.
- Add test coverage for model normalization, thinking replay family, temperature stripping, and Claude effort=max preservation.

2026-09-11 17:01:00 +08:00

..

provider

fix(thinking): drop disabled Interactions summaries

2026-07-31 13:40:41 +08:00

apply_codex_usage_test.go

fix(thinking): extract configuration_update reasoning effort in codex usage reporting

2026-09-11 12:15:57 +08:00

apply_configured_api_key_test.go

fix(thinking): respect final summary authority

2026-07-31 13:28:14 +08:00

apply.go

fix(thinking): extract configuration_update reasoning effort in codex usage reporting

2026-09-11 12:15:57 +08:00

convert.go

chore: upgrade CLIProxyAPI dependency to v7 across the project

2026-05-08 11:46:46 +08:00

errors.go

…

kimi_max_clamp_repro_test.go

feat(kimi): add Kimi K2.8 model definitions, normalization, and temperature guard

2026-09-11 17:01:00 +08:00

strip.go

feat(thinking): preserve cross-protocol summary visibility

2026-07-30 21:53:30 +08:00

suffix.go

feat(thinking): add adaptive thinking support for Claude models

2026-03-03 09:05:31 +08:00

summary_test.go

fix(thinking): honor normalized summary payloads

2026-07-31 12:45:13 +08:00

summary.go

fix(thinking): respect final summary authority

2026-07-31 13:28:14 +08:00

text.go

…

types.go

feat(thinking): add xAI provider support with reasoning.effort implementation

2026-05-19 03:09:53 +08:00

validate.go

feat(kimi): implement native thinking object extraction and update reasoning handling

2026-07-17 13:33:44 +08:00