perf: faster model resolution, JSON decoding, and request snapshotting

cmd/gomodel/health.go

@@ -2,7 +2,6 @@ package main
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"io"
 	"net"
@@ -11,6 +10,8 @@ import (
 	"strings"
 	"time"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/config"
 )
 

cmd/recordapi/main.go

@@ -9,7 +9,6 @@ package main
 
 import (
 	"bytes"
-	"encoding/json"
 	"flag"
 	"fmt"
 	"io"
@@ -18,6 +17,8 @@ import (
 	"path/filepath"
 	"strings"
 	"time"
+
+	"github.com/goccy/go-json"
 )
 
 const oracleDefaultModel = "openai.gpt-oss-120b"

go.mod

@@ -10,6 +10,7 @@ require (
 	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.53.5
 	github.com/cespare/xxhash/v2 v2.3.0
 	github.com/coder/websocket v1.8.15
+	github.com/goccy/go-json v0.10.6
 	github.com/google/uuid v1.6.0
 	github.com/jackc/pgx/v5 v5.10.0
 	github.com/joho/godotenv v1.5.1

go.sum

@@ -83,6 +83,8 @@ github.com/go-openapi/testify/enable/yaml/v2 v2.4.0 h1:7SgOMTvJkM8yWrQlU8Jm18VeD
 github.com/go-openapi/testify/enable/yaml/v2 v2.4.0/go.mod h1:14iV8jyyQlinc9StD7w1xVPW3CO3q1Gj04Jy//Kw4VM=
 github.com/go-openapi/testify/v2 v2.4.0 h1:8nsPrHVCWkQ4p8h1EsRVymA2XABB4OT40gcvAu+voFM=
 github.com/go-openapi/testify/v2 v2.4.0/go.mod h1:HCPmvFFnheKK2BuwSA0TbbdxJ3I16pjwMkYkP4Ywn54=
+github.com/goccy/go-json v0.10.6 h1:p8HrPJzOakx/mn/bQtjgNjdTcN+/S6FcG2CTtQOrHVU=
+github.com/goccy/go-json v0.10.6/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M=
 github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
 github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
 github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e h1:ijClszYn+mADRFY17kjQEVQ1XRhq2/JR1M3sGqeJoxs=

internal/admin/handler_guardrails.go

@@ -1,11 +1,12 @@
 package admin
 
 import (
-	"encoding/json"
 	"errors"
 	"net/http"
 	"strings"
 
+	"github.com/goccy/go-json"
+
 	"github.com/labstack/echo/v5"
 
 	"gomodel/internal/core"

internal/admin/handler_live.go

@@ -1,13 +1,14 @@
 package admin
 
 import (
-	"encoding/json"
 	"fmt"
 	"net/http"
 	"strconv"
 	"strings"
 	"time"
 
+	"github.com/goccy/go-json"
+
 	"github.com/labstack/echo/v5"
 
 	"gomodel/internal/core"

internal/aliases/batch_preparer.go

@@ -2,10 +2,11 @@ package aliases
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"strings"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/internal/core"
 )
 

internal/anthropicapi/request.go

@@ -2,11 +2,12 @@ package anthropicapi
 
 import (
 	"bytes"
-	"encoding/json"
 	"fmt"
 	"io"
 	"strings"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/internal/core"
 )
 

internal/anthropicapi/response.go

@@ -2,9 +2,10 @@ package anthropicapi
 
 import (
 	"bytes"
-	"encoding/json"
 	"strings"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/internal/core"
 )
 

internal/anthropicapi/stream.go

@@ -3,9 +3,10 @@ package anthropicapi
 import (
 	"bufio"
 	"bytes"
-	"encoding/json"
 	"io"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/internal/streaming"
 )
 

internal/anthropicapi/types.go

@@ -4,7 +4,7 @@
 // independent of which provider ultimately serves the request.
 package anthropicapi
 
-import "encoding/json"
+import "github.com/goccy/go-json"
 
 // MessagesRequest is the Anthropic Messages API request body.
 // System and message content fields are polymorphic on the wire (string or

internal/app/app.go

@@ -4,7 +4,6 @@ package app
 
 import (
 	"context"
-	"encoding/json"
 	"errors"
 	"fmt"
 	"log/slog"
@@ -14,6 +13,8 @@ import (
 	"sync"
 	"time"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/config"
 	"gomodel/internal/admin"
 	"gomodel/internal/admin/dashboard"

internal/auditlog/auditlog.go

@@ -4,10 +4,11 @@ package auditlog
 
 import (
 	"context"
-	"encoding/json"
 	"log/slog"
 	"strings"
 	"time"
+
+	"github.com/goccy/go-json"
 )
 
 // LogStore defines the interface for audit log storage backends.

internal/auditlog/entry_capture.go

@@ -2,12 +2,13 @@ package auditlog
 
 import (
 	"context"
-	"encoding/json"
 	"errors"
 	"net/http"
 	"net/url"
 	"strings"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/internal/core"
 )
 
@@ -211,7 +212,7 @@ func internalJSONAuditHeaders(ctx context.Context, requestID string) http.Header
 		headers.Set(core.UserPathHeaderNameFromContext(ctx), userPath)
 	}
 	if snapshot := core.GetRequestSnapshot(ctx); snapshot != nil {
-		snapshotHeaders := snapshot.GetHeaders()
+		snapshotHeaders := snapshot.HeadersView()
 		for _, key := range []string{"Traceparent", "Tracestate", "Baggage"} {
 			for _, value := range snapshotHeaders[key] {
 				headers.Add(key, value)

internal/auditlog/middleware.go

@@ -8,14 +8,15 @@ import (
 	"context"
 	"crypto/sha256"
 	"encoding/hex"
-	"encoding/json"
 	"io"
 	"net"
 	"net/http"
 	"strings"
 	"time"
 	"unicode/utf8"
 
+	"github.com/goccy/go-json"
+
 	"github.com/andybalholm/brotli"
 	"github.com/google/uuid"
 	"github.com/labstack/echo/v5"

internal/auditlog/reader_postgresql.go

@@ -4,10 +4,11 @@ import (
 	"gomodel/internal/storage/sqlutil"
 
 	"context"
-	"encoding/json"
 	"fmt"
 	"log/slog"
 
+	"github.com/goccy/go-json"
+
 	"github.com/jackc/pgx/v5/pgxpool"
 )
 

internal/auditlog/reader_sqlite.go

@@ -5,11 +5,12 @@ import (
 
 	"context"
 	"database/sql"
-	"encoding/json"
 	"fmt"
 	"log/slog"
 	"sort"
 	"time"
+
+	"github.com/goccy/go-json"
 )
 
 const sqliteTimestampBoundaryLayout = "2006-01-02T15:04:05"

internal/batch/store.go

@@ -3,13 +3,14 @@ package batch
 
 import (
 	"context"
-	"encoding/json"
 	"errors"
 	"fmt"
 	"strconv"
 	"strings"
 	"time"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/internal/core"
 )
 

internal/cache/modelcache/local.go

@@ -2,11 +2,12 @@ package modelcache
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"os"
 	"path/filepath"
 	"sync"
+
+	"github.com/goccy/go-json"
 )
 
 // LocalCache implements Cache using local file storage.

internal/cache/modelcache/modelcache.go

@@ -5,8 +5,9 @@ package modelcache
 
 import (
 	"context"
-	"encoding/json"
 	"time"
+
+	"github.com/goccy/go-json"
 )
 
 // ModelCache represents the cached model data structure.

internal/cache/modelcache/redis.go

@@ -2,11 +2,12 @@ package modelcache
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"log/slog"
 	"time"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/internal/cache"
 )
 

internal/conversationstore/store.go

@@ -4,12 +4,13 @@ package conversationstore
 
 import (
 	"context"
-	"encoding/json"
 	"errors"
 	"fmt"
 	"strings"
 	"time"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/internal/core"
 )
 

internal/conversationstore/store_memory.go

@@ -2,12 +2,13 @@ package conversationstore
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"sort"
 	"sync"
 	"time"
 
+	"github.com/goccy/go-json"
+
 	"gomodel/internal/core"
 )
 

internal/core/audio.go

@@ -1,9 +1,10 @@
 package core
 
 import (
-	"encoding/json"
 	"io"
 	"strings"
+
+	"github.com/goccy/go-json"
 )
 
 // AudioSpeechRequest is an OpenAI-compatible POST /v1/audio/speech

internal/core/batch.go

@@ -1,6 +1,6 @@
 package core
 
-import "encoding/json"
+import "github.com/goccy/go-json"
 
 // BatchRequest is OpenAI-compatible for core fields and extends with inline requests.
 //

internal/core/batch_json.go

@@ -1,6 +1,6 @@
 package core
 
-import "encoding/json"
+import "github.com/goccy/go-json"
 
 func (r *BatchRequest) UnmarshalJSON(data []byte) error {
 	var raw struct {

internal/core/batch_preparation.go

@@ -3,12 +3,13 @@ package core
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"errors"
 	"fmt"
 	"maps"
 	"net/http"
 	"strings"
+
+	"github.com/goccy/go-json"
 )
 
 // BatchPreparationMetadata captures request-scoped batch preprocessing effects

internal/core/chat_content.go

@@ -2,9 +2,10 @@ package core
 
 import (
 	"bytes"
-	"encoding/json"
 	"fmt"
 	"strings"
+
+	"github.com/goccy/go-json"
 )
 
 // ContentPart represents a single OpenAI-compatible multimodal chat content part.

internal/core/chat_json.go

@@ -1,6 +1,6 @@
 package core
 
-import "encoding/json"
+import "github.com/goccy/go-json"
 
 func (r *ChatRequest) UnmarshalJSON(data []byte) error {
 	var raw struct {

internal/core/conversations.go

@@ -2,9 +2,10 @@ package core
 
 import (
 	"bytes"
-	"encoding/json"
 	"fmt"
 	"unicode/utf8"
+
+	"github.com/goccy/go-json"
 )
 
 // ConversationObject is the value of the "object" field on a conversation.