refactor: extract protocol conversion layer into standalone relaykit module (#6369)

* 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

pkg/billingexpr/compile.go

@@ -39,30 +39,30 @@ var (
 
 // compileEnvPrototypeV1 is the v1 type-checking prototype used at compile time.
 var compileEnvPrototypeV1 = map[string]interface{}{
-	"p":    float64(0),
-	"c":    float64(0),
-	"len":  float64(0),
-	"cr":   float64(0),
-	"cc":   float64(0),
-	"cc1h": float64(0),
-	"img":  float64(0),
-	"img_o": float64(0),
-	"ai":   float64(0),
-	"ao":   float64(0),
-	"tier":                   func(string, float64) float64 { return 0 },
-	"header":                 func(string) string { return "" },
-	"param":                  func(string) interface{} { return nil },
-	"has":                    func(interface{}, string) bool { return false },
-	"hour":                   func(string) int { return 0 },
-	"minute":                 func(string) int { return 0 },
-	"weekday":                func(string) int { return 0 },
-	"month":                  func(string) int { return 0 },
-	"day":                    func(string) int { return 0 },
-	"max":                    math.Max,
-	"min":                    math.Min,
-	"abs":                    math.Abs,
-	"ceil":                   math.Ceil,
-	"floor":                  math.Floor,
+	"p":       float64(0),
+	"c":       float64(0),
+	"len":     float64(0),
+	"cr":      float64(0),
+	"cc":      float64(0),
+	"cc1h":    float64(0),
+	"img":     float64(0),
+	"img_o":   float64(0),
+	"ai":      float64(0),
+	"ao":      float64(0),
+	"tier":    func(string, float64) float64 { return 0 },
+	"header":  func(string) string { return "" },
+	"param":   func(string) interface{} { return nil },
+	"has":     func(interface{}, string) bool { return false },
+	"hour":    func(string) int { return 0 },
+	"minute":  func(string) int { return 0 },
+	"weekday": func(string) int { return 0 },
+	"month":   func(string) int { return 0 },
+	"day":     func(string) int { return 0 },
+	"max":     math.Max,
+	"min":     math.Min,
+	"abs":     math.Abs,
+	"ceil":    math.Ceil,
+	"floor":   math.Floor,
 }
 
 func getCompileEnv(version int) map[string]interface{} {

pkg/billingexpr/run.go

@@ -53,16 +53,16 @@ func runProgram(prog *vm.Program, params TokenParams, request RequestInput) (flo
 	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,
+		"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,
+		"ai":    params.AI,
+		"ao":    params.AO,
 		"tier": func(name string, value float64) float64 {
 			trace.MatchedTier = name
 			trace.Cost = value
@@ -94,10 +94,10 @@ func runProgram(prog *vm.Program, params TokenParams, request RequestInput) (flo
 		"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,
+		"min":     math.Min,
+		"abs":     math.Abs,
+		"ceil":    math.Ceil,
+		"floor":   math.Floor,
 	}
 
 	out, err := expr.Run(prog, env)