ext/new-api
2
0
Fork 0
mirror of https://github.com/QuantumNous/new-api.git synced 2026-09-11 06:30:21 +00:00
Code Activity

feat(relay): hosted-tool conversion fidelity, reasoning normalization, and billing usage integrity (#7137)

Browse Source 
* feat(relaykit): preserve hosted tools across conversions

- add protocol-neutral hosted-tool DTOs, conversion metadata, and loss policies
- bridge citations, grounding metadata, and hosted-tool stream lifecycles
- document the public conversion behavior and channel policy controls

* refactor(relaykit): normalize reasoning and thinking intent

- centralize provider-neutral reasoning intent, effort, and budget mappings
- parse model suffixes at the host entry boundary while preserving provider-owned tails
- keep adaptive Claude thinking and explicit zero-token compatibility consistent

* fix(billing): preserve authoritative usage across relay hops

- carry native BillingUsage sidecars through direct and streamed protocol bridges
- merge partial and terminal usage monotonically with safe fallback settlement
- retain cache metadata, penultimate usage, and per-call Gemini tool surcharges

* feat(relay): bridge Responses with Claude and Gemini protocols

- add direct request, response, and stream converters across supported relay formats
- expose Claude count_tokens and Chat-to-Responses compatibility endpoints
- carry conversion diagnostics through the host while retaining the curated public goldens

* fix(relay): wire relaykit conversions into host channels

- connect handlers, adaptors, and channel settings to the standalone conversion layer
- keep model mapping, pricing identity, retries, and provider-specific suffix behavior aligned
- ignore local audit artifacts and retain focused public regression coverage
This commit is contained in:
Calcium-Ion
2026-09-01 21:53:35 +08:00
committed by GitHub
parent b7017c251b
commit 0ed497f066
149 changed files with 14729 additions and 3044 deletions
Download Patch File Download Diff File Expand all files Collapse all files
setting/ratio_setting/model_ratio.go
+4 -9
View File
@@ -179,12 +179,10 @@ var defaultModelRatio = map[string]float64{
"gemini-2.5-pro-exp-03-25": 0.625,
"gemini-2.5-pro-preview-03-25": 0.625,
"gemini-2.5-pro": 0.625,
"gemini-2.5-flash-preview-04-17": 0.075,
"gemini-2.5-flash-preview-04-17-thinking": 0.075,
"gemini-2.5-flash-preview-04-17-nothinking": 0.075,
"gemini-2.5-flash-preview-05-20": 0.075,
"gemini-2.5-flash-preview-05-20-thinking": 0.075,
"gemini-2.5-flash-preview-05-20-nothinking": 0.075,
"gemini-2.5-flash-preview-04-17": 0.075,
"gemini-2.5-flash-preview-04-17-thinking": 0.075,
"gemini-2.5-flash-preview-05-20": 0.075,
"gemini-2.5-flash-preview-05-20-thinking": 0.075,
"gemini-2.5-flash-thinking-*": 0.075, // 用于为后续所有2.5 flash thinking budget 模型设置默认倍率
"gemini-2.5-pro-thinking-*": 0.625, // 用于为后续所有2.5 pro thinking budget 模型设置默认倍率
"gemini-2.5-flash-lite-preview-thinking-*": 0.05,
@@ -549,9 +547,6 @@ func getHardcodedCompletionModelRatio(name string) (float64, bool) {
return 8, false
} else if strings.HasPrefix(name, "gemini-2.5-flash") { // 处理不同的flash模型倍率
if strings.HasPrefix(name, "gemini-2.5-flash-preview") {
if strings.HasSuffix(name, "-nothinking") {
return 4, false
}
return 3.5 / 0.15, false
}
if strings.HasPrefix(name, "gemini-2.5-flash-lite") {