hkfires 007572b58e fix(util): do not strip thinking suffix on registered models ...

NormalizeThinkingModel now checks ModelSupportsThinking before removing
"-thinking" or "-thinking-<ver>", avoiding accidental parsing of model
names where the suffix is part of the official id (e.g., kimi-k2-thinking,
qwen3-235b-a22b-thinking-2507).

The registry adds ThinkingSupport metadata for several models and
propagates it via ModelInfo (e.g., kimi-k2-thinking, deepseek-r1,
qwen3-235b-a22b-thinking-2507, minimax-m2), enabling accurate detection
of thinking-capable models and correcting base model inference.

2025-12-11 15:52:14 +08:00

..

gemini_thinking.go

feat(util): implement dynamic thinking suffix normalization and refactor budget resolution logic

2025-12-11 03:10:50 +08:00

header_helpers.go

feat(config): support HTTP headers across providers

2025-11-08 20:52:05 +08:00

image.go

feat(registry, executor, util): add support for gemini-2.5-flash-image-preview and improve aspect ratio handling

2025-10-10 01:49:58 +08:00

provider.go

feat: add auto model resolution and model creation timestamp tracking

2025-11-11 20:30:09 +08:00

proxy.go

refactor(proxy): improve SOCKS5 proxy authentication handling

2025-09-30 11:23:39 +08:00

ssh_helper.go

feat(logging): introduce centralized logging with custom format and Gin integration

2025-09-26 00:54:52 +08:00

thinking_suffix.go

fix(util): do not strip thinking suffix on registered models

2025-12-11 15:52:14 +08:00

thinking.go

fix(runtime): validate reasoning effort levels

2025-12-11 12:36:54 +08:00

translator.go

**feat(util): add DeleteKey function and update antigravity executor for Claude model compatibility**

2025-12-05 01:55:45 +08:00

util.go

feat: prefer util.WritablePath() for logs and local storage

2025-10-19 10:19:55 +08:00