mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-09-07 18:18:00 +00:00
Calcium-Ion
0ed497f066
* 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
28 lines
1.1 KiB
Go
28 lines
1.1 KiB
Go
// Package reasoning re-exports the pure model-name effort-suffix helpers,
|
|
// which moved to the conversion kit (relaykit/relayconvert/reasoning) as part
|
|
// of the relaykit extraction. Host code keeps importing this path unchanged.
|
|
package reasoning
|
|
|
|
import (
|
|
kitreasoning "github.com/QuantumNous/new-api/relaykit/relayconvert/reasoning"
|
|
"github.com/QuantumNous/new-api/setting/model_setting"
|
|
)
|
|
|
|
var (
|
|
EffortSuffixes = kitreasoning.EffortSuffixes
|
|
OpenAIEffortSuffixes = kitreasoning.OpenAIEffortSuffixes
|
|
DeepSeekV4EffortSuffixes = kitreasoning.DeepSeekV4EffortSuffixes
|
|
)
|
|
|
|
var (
|
|
TrimEffortSuffixWithSuffixes = kitreasoning.TrimEffortSuffixWithSuffixes
|
|
ParseDeepSeekV4ThinkingSuffix = kitreasoning.ParseDeepSeekV4ThinkingSuffix
|
|
TrimGeminiThinkingSuffix = kitreasoning.TrimGeminiThinkingSuffix
|
|
)
|
|
|
|
// ParseOpenAIReasoningEffortFromModelSuffix applies the host effort-tail
|
|
// whitelist so real model IDs such as qwen-max are not treated as aliases.
|
|
func ParseOpenAIReasoningEffortFromModelSuffix(modelName string) (string, string) {
|
|
return kitreasoning.ParseOpenAIReasoningEffortFromModelSuffix(modelName, model_setting.ShouldPreserveEffortTail)
|
|
}
|