* test(relayconvert): add golden snapshot matrix and relaykit boundary guard Phase 0 of the relaykit extraction plan: pin byte-level output of every registered (from,to) request/response/stream conversion route, and forbid kit-bound packages from growing host-only imports. * wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft Phase 1 in progress: relayconvert now takes context.Context; host media resolver adapts gin.Context back at the service boundary. * refactor(relayconvert): decouple converters from RelayInfo, gin, and settings Phase 1 of the relaykit extraction plan: - converters now depend on convmeta.Meta (implemented by RelayInfo) instead of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move to convmeta with aliases left behind - host settings reach converters via a convmeta.Options snapshot built in RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside the conversion layer - effort-suffix helpers move to service/relayconvert/reasoning (old package forwards); chat-to-responses upgrade policy moves to service (host routing logic, not conversion) - golden conversion matrix unchanged * test(relayconvert): tighten boundary — kit packages now free of gin/setting imports * refactor(dto): drop gin and logger dependencies Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of *gin.Context (Gemini's impl reads query/path off the std request); dto's three logger calls become common.SysError. Boundary test allowlist is now empty — kit-bound packages import no gin/setting/logger/model. * refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common Phase 2 of the relaykit extraction plan: - new service/relayconvert/kitutil holds the pure helpers the kit needs (JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo, pluggable LogInfo/LogError hooks, Debug flag) - dto, types, and all relayconvert packages now use kitutil; their only remaining internal deps are dto/types/constant - common keeps every original symbol (MaskSensitiveInfo delegates to kitutil) so host code is untouched; main.go routes kit logging into common.SysLog/SysError and mirrors DebugEnabled - golden conversion matrix unchanged * refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options Kit packages (dto/types/relayconvert/reasonmap) no longer import constant: - EndpointType and finish-reason values live in types; constant re-exports - the OpenRouter special-case in claude->openai request conversion reads Options.OpenRouterDialect, set by the host from the channel type; InitChannelMeta invalidates the cached snapshot on channel switch * refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap) Phase 3 of the relaykit extraction plan: - new go module github.com/QuantumNous/new-api/relaykit containing dto (minus task family), types, relayconvert (with convmeta/kitutil/reasoning), and reasonmap; host consumes it via require + replace, go.work for dev - task-family dto (task/suno/midjourney/video) stays in the host dto package; dual-consumer host files alias it as taskdto - relaykit builds and tests standalone (GOWORK=off): no host imports, no gin, no DB, no settings - golden conversion matrix unchanged * build(docker): copy relaykit/go.mod before go mod download The local-replace submodule's go.mod must exist inside the build context for the main module graph to resolve. * fix: address relaykit extraction regressions * fix: address relaykit review regressions * docs: document Meta nil receiver contract * fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens The Claude Messages API requires max_tokens (omitting it is a 400 "Field required"), but with a nil Options.Claude.DefaultMaxTokens hook the converters silently emitted a request the upstream is guaranteed to reject. Both OpenAI Chat and Responses → Claude conversions now return sharedclaude.ErrMissingMaxTokens when no path (client value, default hook, thinking-adapter floor) supplied one. Unreachable in the host, which always configures the hook. Host side, claude.default_max_tokens now rejects negative values at the option API before persisting — they would wrap into huge unsigned values during conversion. Zero stays allowed: the current API treats max_tokens: 0 as cache pre-warming. * fix: make Gemini safety settings read path race-free
141 lines
4.2 KiB
Go
141 lines
4.2 KiB
Go
package billingexpr
|
|
|
|
import (
|
|
"fmt"
|
|
"math"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/expr-lang/expr"
|
|
"github.com/expr-lang/expr/vm"
|
|
"github.com/tidwall/gjson"
|
|
)
|
|
|
|
// RunExpr compiles (with cache) and executes an expression string.
|
|
// The environment exposes:
|
|
// - p, c — prompt / completion tokens (auto-excluding separately-priced sub-categories)
|
|
// - len — total input context length for tier conditions (never reduced by sub-category exclusion)
|
|
// - cr, cc, cc1h — cache read / creation / creation-1h tokens
|
|
// - tier(name, value) — trace callback that records which tier matched
|
|
// - max, min, abs, ceil, floor — standard math helpers
|
|
//
|
|
// Returns the resulting float64 quota (before group ratio) and a TraceResult
|
|
// with side-channel info captured by tier() during execution.
|
|
func RunExpr(exprStr string, params TokenParams) (float64, TraceResult, error) {
|
|
return RunExprWithRequest(exprStr, params, RequestInput{})
|
|
}
|
|
|
|
func RunExprWithRequest(exprStr string, params TokenParams, request RequestInput) (float64, TraceResult, error) {
|
|
prog, err := CompileFromCache(exprStr)
|
|
if err != nil {
|
|
return 0, TraceResult{}, err
|
|
}
|
|
return runProgram(prog, params, request)
|
|
}
|
|
|
|
// RunExprByHash is like RunExpr but accepts a pre-computed hash for the cache
|
|
// lookup, avoiding a redundant SHA-256 computation when the caller already
|
|
// holds BillingSnapshot.ExprHash.
|
|
func RunExprByHash(exprStr, hash string, params TokenParams) (float64, TraceResult, error) {
|
|
return RunExprByHashWithRequest(exprStr, hash, params, RequestInput{})
|
|
}
|
|
|
|
func RunExprByHashWithRequest(exprStr, hash string, params TokenParams, request RequestInput) (float64, TraceResult, error) {
|
|
prog, err := CompileFromCacheByHash(exprStr, hash)
|
|
if err != nil {
|
|
return 0, TraceResult{}, err
|
|
}
|
|
return runProgram(prog, params, request)
|
|
}
|
|
|
|
func runProgram(prog *vm.Program, params TokenParams, request RequestInput) (float64, TraceResult, error) {
|
|
trace := TraceResult{}
|
|
headers := normalizeHeaders(request.Headers)
|
|
|
|
env := map[string]interface{}{
|
|
"p": params.P,
|
|
"c": params.C,
|
|
"len": params.Len,
|
|
"cr": params.CR,
|
|
"cc": params.CC,
|
|
"cc1h": params.CC1h,
|
|
"img": params.Img,
|
|
"img_o": params.ImgO,
|
|
"ai": params.AI,
|
|
"ao": params.AO,
|
|
"tier": func(name string, value float64) float64 {
|
|
trace.MatchedTier = name
|
|
trace.Cost = value
|
|
return value
|
|
},
|
|
"header": func(key string) string {
|
|
return headers[strings.ToLower(strings.TrimSpace(key))]
|
|
},
|
|
"param": func(path string) interface{} {
|
|
path = strings.TrimSpace(path)
|
|
if path == "" || len(request.Body) == 0 {
|
|
return nil
|
|
}
|
|
result := gjson.GetBytes(request.Body, path)
|
|
if !result.Exists() {
|
|
return nil
|
|
}
|
|
return result.Value()
|
|
},
|
|
"has": func(source interface{}, substr string) bool {
|
|
if source == nil || substr == "" {
|
|
return false
|
|
}
|
|
return strings.Contains(fmt.Sprint(source), substr)
|
|
},
|
|
"hour": func(tz string) int { return timeInZone(tz).Hour() },
|
|
"minute": func(tz string) int { return timeInZone(tz).Minute() },
|
|
"weekday": func(tz string) int { return int(timeInZone(tz).Weekday()) },
|
|
"month": func(tz string) int { return int(timeInZone(tz).Month()) },
|
|
"day": func(tz string) int { return timeInZone(tz).Day() },
|
|
"max": math.Max,
|
|
"min": math.Min,
|
|
"abs": math.Abs,
|
|
"ceil": math.Ceil,
|
|
"floor": math.Floor,
|
|
}
|
|
|
|
out, err := expr.Run(prog, env)
|
|
if err != nil {
|
|
return 0, trace, fmt.Errorf("expr run error: %w", err)
|
|
}
|
|
f, ok := out.(float64)
|
|
if !ok {
|
|
return 0, trace, fmt.Errorf("expr result is %T, want float64", out)
|
|
}
|
|
return f, trace, nil
|
|
}
|
|
|
|
func timeInZone(tz string) time.Time {
|
|
tz = strings.TrimSpace(tz)
|
|
if tz == "" {
|
|
return time.Now().UTC()
|
|
}
|
|
loc, err := time.LoadLocation(tz)
|
|
if err != nil {
|
|
return time.Now().UTC()
|
|
}
|
|
return time.Now().In(loc)
|
|
}
|
|
|
|
func normalizeHeaders(headers map[string]string) map[string]string {
|
|
if len(headers) == 0 {
|
|
return map[string]string{}
|
|
}
|
|
normalized := make(map[string]string, len(headers))
|
|
for key, value := range headers {
|
|
k := strings.ToLower(strings.TrimSpace(key))
|
|
v := strings.TrimSpace(value)
|
|
if k == "" || v == "" {
|
|
continue
|
|
}
|
|
normalized[k] = v
|
|
}
|
|
return normalized
|
|
}
|