phsl / new-api

fix: Use channel proxy settings for task query scenarios

fix: Try to fix login error "already logged in" issue

fix: sidebar color overlap

fix: fetch upstream models

fix: qwen chat_template_kwargs

fix: regex repeat compile

chore(go): enable greenteagc

feat: zhipu 4v image generations

fix(go.mod): 更新modernc.org/sqlite依赖项版本

fix: Set default to unsupported value for gpt-5 model series requests

Increase token name length limit from 30 to 50

feat: add claude-haiku-4-5-20251001 model support

fix(adaptor): fix reasoning suffix not processing in vertex adapter

- Add model to Claude ModelList
- Add model ratio (0.5, $1/1M input tokens)
- Add completion ratio support (5x, $5/1M output tokens)
- Add cache read ratio (0.1, $0.10/1M tokens)
- Add cache write ratio (1.25, $1.25/1M tokens)

Model specs:
- Context window: 200K tokens
- Max output: 64K tokens
- Release date: October 1, 2025

Increase token name length limit from 30 to 50

feat: gemini 3 thinking level gemini-3-pro-preview-high

feat: refactor token estimation logic

fix: try resolve the high concurrency issue to a single host

- Introduced new OpenAI text models in `common/model.go`.
- Added `IsOpenAITextModel` function to check for OpenAI text models.
- Refactored token estimation methods across various channels to use estimated prompt tokens instead of direct prompt token counts.
- Updated related functions and structures to accommodate the new token estimation approach, enhancing overall token management.

chore: update the relay openapi file