feat: refactor token estimation logic

- 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.
This commit is contained in:
CaIon
2025-12-02 21:34:39 +08:00
parent d3ca454c3b
commit f5b409d74f
26 changed files with 389 additions and 275 deletions

View File

@@ -3,8 +3,9 @@ package constant
type ContextKey string
const (
ContextKeyTokenCountMeta ContextKey = "token_count_meta"
ContextKeyPromptTokens ContextKey = "prompt_tokens"
ContextKeyTokenCountMeta ContextKey = "token_count_meta"
ContextKeyPromptTokens ContextKey = "prompt_tokens"
ContextKeyEstimatedTokens ContextKey = "estimated_tokens"
ContextKeyOriginalModel ContextKey = "original_model"
ContextKeyRequestStartTime ContextKey = "request_start_time"