chore: remove Qwen support from SDK and internal components

- Deleted `QwenAuthenticator`, internal `qwen_auth`, and `qwen_executor` implementations.
- Removed all Qwen-related OAuth flows, token handling, and execution logic.
- Cleaned up dependencies and references to Qwen across the codebase.
This commit is contained in:
Luis Pater
2026-04-15 12:16:08 +08:00
parent 41ae2c81e7
commit 8fac29631d
30 changed files with 77 additions and 2166 deletions
+1 -1
View File
@@ -128,7 +128,7 @@ type Config struct {
// OAuthModelAlias defines global model name aliases for OAuth/file-backed auth channels.
// These aliases affect both model listing and model routing for supported channels:
// gemini-cli, vertex, aistudio, antigravity, claude, codex, qwen, iflow.
// gemini-cli, vertex, aistudio, antigravity, claude, codex, iflow.
//
// NOTE: This does not apply to existing per-credential model alias features under:
// gemini-api-key, codex-api-key, claude-api-key, openai-compatibility, vertex-api-key, and ampcode.