sub2api

mirror of https://github.com/Wei-Shaw/sub2api.git synced 2026-09-24 16:05:44 +08:00

Files

T

stabeyandClaude Opus 4.7 89dffdd2e1 fix(apicompat): emit OpenAI-semantic input_tokens when converting Anthropic to Responses

Anthropic Messages reports input_tokens excluding cache_read/cache_creation, but
OpenAI Responses input_tokens is the total including cached tokens. The reverse
converter passed Anthropic's input_tokens straight through, so client-facing
prompt_tokens/input_tokens were short by the cached count and cache_creation
was dropped entirely.

Fix the non-stream path and the streaming state machine to add cache_read +
cache_creation back into input_tokens, and track CacheCreationInputTokens on
the streaming state. Six downstream paths benefit (Anthropic->Responses,
Anthropic->ChatCompletions, Gemini->ChatCompletions, each sync + stream).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-27 22:36:52 +08:00

cmd

chore: sync VERSION to 0.1.131 [skip ci]

2026-05-26 06:43:49 +00:00

ent

feat(group): 支持自定义 /v1/models 模型列表

2026-05-27 18:00:45 +08:00

internal

fix(apicompat): emit OpenAI-semantic input_tokens when converting Anthropic to Responses

2026-05-27 22:36:52 +08:00

migrations

feat(group): 支持自定义 /v1/models 模型列表