test(react-ui): disambiguate Max Items locator after adding Max Body Bytes

The Tracing settings panel now has two number inputs. The previous spec
matched 'input[type="number"]' which became ambiguous and triggered a
Playwright strict-mode violation in CI. Switch to getByPlaceholder('100')
for Max Items and add a parallel spec for the new Max Body Bytes field
using getByPlaceholder('65536').

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-7

.gitignore

@@ -77,3 +77,6 @@ local-backends/
 tests/e2e-ui/ui-test-server
 core/http/react-ui/playwright-report/
 core/http/react-ui/test-results/
+
+# Local worktrees
+.worktrees/

backend/cpp/ds4/Makefile

@@ -1,10 +1,10 @@
 # ds4 backend Makefile.
 #
-# Upstream pin lives below as DS4_VERSION?=2606543be7a8c125a32cee37f5d1d85dc78f2fcf
+# Upstream pin lives below as DS4_VERSION?=8d576642c39b9a2d782a80159ba84ef5a81c0b81
 # (.github/bump_deps.sh) can find and update it - matches the
 # llama-cpp / ik-llama-cpp / turboquant convention.
 
-DS4_VERSION?=2606543be7a8c125a32cee37f5d1d85dc78f2fcf
+DS4_VERSION?=8d576642c39b9a2d782a80159ba84ef5a81c0b81
 DS4_REPO?=https://github.com/antirez/ds4
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=ad277572619fcfb6ddd38f4c6437283a4b2b8636
+LLAMA_VERSION?=bb28c1fe246b72276ee1d00ce89306be7b865766
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=5b0267e941cade15bd80089d89838795d9f4baa6
+STABLEDIFFUSION_GGML_VERSION?=3a8788cb7d74f185d6b18688e9563015524ecaf5
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

core/application/startup.go

@@ -552,6 +552,13 @@ func loadRuntimeSettingsFromFile(options *config.ApplicationConfig) {
 			options.TracingMaxItems = *settings.TracingMaxItems
 		}
 	}
+	if settings.TracingMaxBodyBytes != nil {
+		// Allow the on-disk setting to override the CLI/env default. The
+		// startup default is non-zero (see NewApplicationConfig), so a plain
+		// `== 0` guard like the others would never trigger; we instead respect
+		// any value the file specifies. 0 in the file means "uncapped".
+		options.TracingMaxBodyBytes = *settings.TracingMaxBodyBytes
+	}
 
 	// Branding / whitelabeling. There are no env vars for these — the file is
 	// the only source — so apply unconditionally. Without this block a server

core/backend/audio_transform.go

@@ -78,7 +78,7 @@ func ModelAudioTransform(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 
@@ -104,7 +104,7 @@ func ModelAudioTransform(
 			data["sample_rate"] = res.SampleRate
 			data["samples"] = res.Samples
 			data["reference_provided"] = res.ReferenceProvided
-			if snippet := trace.AudioSnippet(dst); snippet != nil {
+			if snippet := trace.AudioSnippet(dst, appConfig.TracingMaxBodyBytes); snippet != nil {
 				maps.Copy(data, snippet)
 			}
 		}

core/backend/detection.go

@@ -35,7 +35,7 @@ func Detection(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 

core/backend/embeddings.go

@@ -67,7 +67,7 @@ func ModelEmbedding(s string, tokens []int, loader *model.ModelLoader, modelConf
 	}
 
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 
 		traceData := map[string]any{
 			"input_text":         trace.TruncateString(s, 1000),

core/backend/face_analyze.go

@@ -32,7 +32,7 @@ func FaceAnalyze(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 

core/backend/face_verify.go

@@ -32,7 +32,7 @@ func FaceVerify(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 

core/backend/image.go

@@ -41,7 +41,7 @@ func ImageGeneration(height, width, step, seed int, positive_prompt, negative_pr
 	}
 
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 
 		traceData := map[string]any{
 			"positive_prompt": positive_prompt,

core/backend/llm.go

@@ -305,7 +305,7 @@ func ModelInference(ctx context.Context, s string, messages schema.Messages, ima
 	}
 
 	if o.EnableTracing {
-		trace.InitBackendTracingIfEnabled(o.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(o.TracingMaxItems, o.TracingMaxBodyBytes)
 
 		traceData := map[string]any{
 			"chat_template":     c.TemplateConfig.Chat,
@@ -316,9 +316,13 @@ func ModelInference(ctx context.Context, s string, messages schema.Messages, ima
 			"audios_count":      len(audios),
 		}
 
+		// Cap the captured fields up front: agent-pool LLM calls embed the
+		// full augmented chat history in messages and the full reply in
+		// response, so without a per-field cap a single trace can dwarf the
+		// rest of the buffer. The cap matches the API-trace body cap.
 		if len(messages) > 0 {
 			if msgJSON, err := json.Marshal(messages); err == nil {
-				traceData["messages"] = string(msgJSON)
+				traceData["messages"] = trace.TruncateToBytes(string(msgJSON), o.TracingMaxBodyBytes)
 			}
 		}
 		if reasoningJSON, err := json.Marshal(c.ReasoningConfig); err == nil {
@@ -337,7 +341,7 @@ func ModelInference(ctx context.Context, s string, messages schema.Messages, ima
 			resp, err := originalFn()
 			duration := time.Since(startTime)
 
-			traceData["response"] = resp.Response
+			traceData["response"] = trace.TruncateToBytes(resp.Response, o.TracingMaxBodyBytes)
 			traceData["token_usage"] = map[string]any{
 				"prompt":     resp.Usage.Prompt,
 				"completion": resp.Usage.Completion,
@@ -359,10 +363,10 @@ func ModelInference(ctx context.Context, s string, messages schema.Messages, ima
 					toolCallCount += len(d.ToolCalls)
 				}
 				if len(contentParts) > 0 {
-					chatDeltasInfo["content"] = strings.Join(contentParts, "")
+					chatDeltasInfo["content"] = trace.TruncateToBytes(strings.Join(contentParts, ""), o.TracingMaxBodyBytes)
 				}
 				if len(reasoningParts) > 0 {
-					chatDeltasInfo["reasoning_content"] = strings.Join(reasoningParts, "")
+					chatDeltasInfo["reasoning_content"] = trace.TruncateToBytes(strings.Join(reasoningParts, ""), o.TracingMaxBodyBytes)
 				}
 				if toolCallCount > 0 {
 					chatDeltasInfo["tool_call_count"] = toolCallCount

core/backend/options.go

@@ -21,7 +21,7 @@ func recordModelLoadFailure(appConfig *config.ApplicationConfig, modelName, back
 	if !appConfig.EnableTracing {
 		return
 	}
-	trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+	trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 	trace.RecordBackendTrace(trace.BackendTrace{
 		Timestamp: time.Now(),
 		Type:      trace.BackendTraceModelLoad,

core/backend/rerank.go

@@ -25,7 +25,7 @@ func Rerank(ctx context.Context, request *proto.RerankRequest, loader *model.Mod
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 

core/backend/soundgeneration.go

@@ -98,7 +98,7 @@ func SoundGeneration(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 

core/backend/tokenize.go

@@ -27,7 +27,7 @@ func ModelTokenize(s string, loader *model.ModelLoader, modelConfig config.Model
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 

core/backend/transcript.go

@@ -76,10 +76,10 @@ func ModelTranscriptionWithOptions(ctx context.Context, req TranscriptionRequest
 	var startTime time.Time
 	var audioSnippet map[string]any
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 		// Capture audio before the backend call — the backend may delete the file.
-		audioSnippet = trace.AudioSnippet(req.Audio)
+		audioSnippet = trace.AudioSnippet(req.Audio, appConfig.TracingMaxBodyBytes)
 	}
 
 	r, err := transcriptionModel.AudioTranscription(ctx, req.toProto(uint32(*modelConfig.Threads)))

core/backend/tts.go

@@ -67,7 +67,7 @@ func ModelTTS(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 
@@ -93,7 +93,7 @@ func ModelTTS(
 			"language": language,
 		}
 		if err == nil && res.Success {
-			if snippet := trace.AudioSnippet(filePath); snippet != nil {
+			if snippet := trace.AudioSnippet(filePath, appConfig.TracingMaxBodyBytes); snippet != nil {
 				maps.Copy(data, snippet)
 			}
 		}
@@ -161,7 +161,7 @@ func ModelTTSStream(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 
@@ -260,7 +260,7 @@ func ModelTTSStream(
 			"streaming": true,
 		}
 		if resultErr == nil && len(snippetPCM) > 0 {
-			if snippet := trace.AudioSnippetFromPCM(snippetPCM, int(sampleRate), totalPCMBytes); snippet != nil {
+			if snippet := trace.AudioSnippetFromPCM(snippetPCM, int(sampleRate), totalPCMBytes, appConfig.TracingMaxBodyBytes); snippet != nil {
 				maps.Copy(data, snippet)
 			}
 		}

core/backend/video.go

@@ -42,7 +42,7 @@ func VideoGeneration(height, width int32, prompt, negativePrompt, startImage, en
 	}
 
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 
 		traceData := map[string]any{
 			"prompt":          prompt,

core/backend/voice_analyze.go

@@ -31,7 +31,7 @@ func VoiceAnalyze(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 

core/backend/voice_embed.go

@@ -34,7 +34,7 @@ func VoiceEmbed(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 

core/backend/voice_verify.go

@@ -32,7 +32,7 @@ func VoiceVerify(
 
 	var startTime time.Time
 	if appConfig.EnableTracing {
-		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
 		startTime = time.Now()
 	}
 

core/cli/run.go

@@ -100,6 +100,7 @@ type RunCMD struct {
 	LoadToMemory                       []string `env:"LOCALAI_LOAD_TO_MEMORY,LOAD_TO_MEMORY" help:"A list of models to load into memory at startup" group:"models"`
 	EnableTracing                      bool     `env:"LOCALAI_ENABLE_TRACING,ENABLE_TRACING" help:"Enable API tracing" group:"api"`
 	TracingMaxItems                    int      `env:"LOCALAI_TRACING_MAX_ITEMS" default:"1024" help:"Maximum number of traces to keep" group:"api"`
+	TracingMaxBodyBytes                int      `env:"LOCALAI_TRACING_MAX_BODY_BYTES" default:"65536" help:"Maximum bytes captured per request/response body in the trace buffer (0 = uncapped). Caps memory growth from chatty endpoints like /embeddings." group:"api"`
 	AgentJobRetentionDays              int      `env:"LOCALAI_AGENT_JOB_RETENTION_DAYS,AGENT_JOB_RETENTION_DAYS" default:"30" help:"Number of days to keep agent job history (default: 30)" group:"api"`
 	OpenResponsesStoreTTL              string   `env:"LOCALAI_OPEN_RESPONSES_STORE_TTL,OPEN_RESPONSES_STORE_TTL" default:"0" help:"TTL for Open Responses store (e.g., 1h, 30m, 0 = no expiration)" group:"api"`
 
@@ -273,6 +274,7 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 		opts = append(opts, config.EnableTracing)
 	}
 	opts = append(opts, config.WithTracingMaxItems(r.TracingMaxItems))
+	opts = append(opts, config.WithTracingMaxBodyBytes(r.TracingMaxBodyBytes))
 
 	token := ""
 	if r.Peer2Peer || r.Peer2PeerToken != "" {

core/config/application_config.go

@@ -21,6 +21,7 @@ type ApplicationConfig struct {
 	Debug                               bool
 	EnableTracing                       bool
 	TracingMaxItems                     int
+	TracingMaxBodyBytes                 int // Per-body cap for captured request/response bodies; 0 disables the cap
 	EnableBackendLogging                bool
 	GeneratedContentDir                 string
 
@@ -187,6 +188,7 @@ func NewApplicationConfig(o ...AppOption) *ApplicationConfig {
 		LRUEvictionRetryInterval: 1 * time.Second,        // Default: 1 second
 		WatchDogInterval:         500 * time.Millisecond, // Default: 500ms
 		TracingMaxItems:          1024,
+		TracingMaxBodyBytes:      64 * 1024, // 64 KiB - caps each request/response body in the trace buffer
 		AgentPool: AgentPoolConfig{
 			Enabled:         true,
 			Timeout:         "5m",
@@ -578,6 +580,12 @@ func WithTracingMaxItems(items int) AppOption {
 	}
 }
 
+func WithTracingMaxBodyBytes(bytes int) AppOption {
+	return func(o *ApplicationConfig) {
+		o.TracingMaxBodyBytes = bytes
+	}
+}
+
 func WithGeneratedContentDir(generatedContentDir string) AppOption {
 	return func(o *ApplicationConfig) {
 		o.GeneratedContentDir = generatedContentDir
@@ -920,6 +928,7 @@ func (o *ApplicationConfig) ToRuntimeSettings() RuntimeSettings {
 	f16 := o.F16
 	debug := o.Debug
 	tracingMaxItems := o.TracingMaxItems
+	tracingMaxBodyBytes := o.TracingMaxBodyBytes
 	enableTracing := o.EnableTracing
 	enableBackendLogging := o.EnableBackendLogging
 	cors := o.CORS
@@ -1008,6 +1017,7 @@ func (o *ApplicationConfig) ToRuntimeSettings() RuntimeSettings {
 		F16:                       &f16,
 		Debug:                     &debug,
 		TracingMaxItems:           &tracingMaxItems,
+		TracingMaxBodyBytes:       &tracingMaxBodyBytes,
 		EnableTracing:             &enableTracing,
 		EnableBackendLogging:      &enableBackendLogging,
 		CORS:                      &cors,
@@ -1146,6 +1156,9 @@ func (o *ApplicationConfig) ApplyRuntimeSettings(settings *RuntimeSettings) (req
 	if settings.TracingMaxItems != nil {
 		o.TracingMaxItems = *settings.TracingMaxItems
 	}
+	if settings.TracingMaxBodyBytes != nil {
+		o.TracingMaxBodyBytes = *settings.TracingMaxBodyBytes
+	}
 	if settings.EnableBackendLogging != nil {
 		o.EnableBackendLogging = *settings.EnableBackendLogging
 	}

core/config/runtime_settings.go

@@ -38,6 +38,7 @@ type RuntimeSettings struct {
 	Debug                *bool `json:"debug,omitempty"`
 	EnableTracing        *bool `json:"enable_tracing,omitempty"`
 	TracingMaxItems      *int  `json:"tracing_max_items,omitempty"`
+	TracingMaxBodyBytes  *int  `json:"tracing_max_body_bytes,omitempty"` // Per-body cap in bytes; 0 disables the cap
 	EnableBackendLogging *bool `json:"enable_backend_logging,omitempty"`
 
 	// Security/CORS settings

core/http/endpoints/openai/chat.go

@@ -73,363 +73,6 @@ func mergeToolCallDeltas(existing []schema.ToolCall, deltas []schema.ToolCall) [
 // @Success 200 {object} schema.OpenAIResponse "Response"
 // @Router /v1/chat/completions [post]
 func ChatEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, evaluator *templates.Evaluator, startupOptions *config.ApplicationConfig, natsClient mcpTools.MCPNATSClient, assistantHolder *mcpTools.LocalAIAssistantHolder) echo.HandlerFunc {
-	process := func(s string, req *schema.OpenAIRequest, config *config.ModelConfig, loader *model.ModelLoader, responses chan schema.OpenAIResponse, extraUsage bool, id string, created int) error {
-		initialMessage := schema.OpenAIResponse{
-			ID:      id,
-			Created: created,
-			Model:   req.Model, // we have to return what the user sent here, due to OpenAI spec.
-			Choices: []schema.Choice{{Delta: &schema.Message{Role: "assistant"}, Index: 0, FinishReason: nil}},
-			Object:  "chat.completion.chunk",
-		}
-		responses <- initialMessage
-
-		// Detect if thinking token is already in prompt or template
-		// When UseTokenizerTemplate is enabled, predInput is empty, so we check the template
-		var template string
-		if config.TemplateConfig.UseTokenizerTemplate {
-			template = config.GetModelTemplate()
-		} else {
-			template = s
-		}
-		thinkingStartToken := reason.DetectThinkingStartToken(template, &config.ReasoningConfig)
-		extractor := reason.NewReasoningExtractor(thinkingStartToken, config.ReasoningConfig)
-
-		_, _, _, err := ComputeChoices(req, s, config, cl, startupOptions, loader, func(s string, c *[]schema.Choice) {}, func(s string, tokenUsage backend.TokenUsage) bool {
-			var reasoningDelta, contentDelta string
-
-			// Always keep the Go-side extractor in sync with raw tokens so it
-			// can serve as fallback for backends without an autoparser (e.g. vLLM).
-			goReasoning, goContent := extractor.ProcessToken(s)
-
-			// When C++ autoparser chat deltas are available, prefer them — they
-			// handle model-specific formats (Gemma 4, etc.) without Go-side tags.
-			// Otherwise fall back to Go-side extraction.
-			if tokenUsage.HasChatDeltaContent() {
-				rawReasoning, cd := tokenUsage.ChatDeltaReasoningAndContent()
-				contentDelta = cd
-				reasoningDelta = extractor.ProcessChatDeltaReasoning(rawReasoning)
-			} else {
-				reasoningDelta = goReasoning
-				contentDelta = goContent
-			}
-
-			usage := schema.OpenAIUsage{
-				PromptTokens:     tokenUsage.Prompt,
-				CompletionTokens: tokenUsage.Completion,
-				TotalTokens:      tokenUsage.Prompt + tokenUsage.Completion,
-			}
-			if extraUsage {
-				usage.TimingTokenGeneration = tokenUsage.TimingTokenGeneration
-				usage.TimingPromptProcessing = tokenUsage.TimingPromptProcessing
-			}
-
-			delta := &schema.Message{}
-			if contentDelta != "" {
-				delta.Content = &contentDelta
-			}
-			if reasoningDelta != "" {
-				delta.Reasoning = &reasoningDelta
-			}
-
-			// Usage rides as a struct field for the consumer to track the
-			// running cumulative — it is stripped before JSON marshal so the
-			// wire chunk stays spec-compliant (no `usage` on intermediate
-			// chunks). The dedicated trailer chunk (when include_usage=true)
-			// carries the final totals.
-			usageForChunk := usage
-			resp := schema.OpenAIResponse{
-				ID:      id,
-				Created: created,
-				Model:   req.Model, // we have to return what the user sent here, due to OpenAI spec.
-				Choices: []schema.Choice{{Delta: delta, Index: 0, FinishReason: nil}},
-				Object:  "chat.completion.chunk",
-				Usage:   &usageForChunk,
-			}
-
-			responses <- resp
-			return true
-		})
-		close(responses)
-		return err
-	}
-	processTools := func(noAction string, prompt string, req *schema.OpenAIRequest, config *config.ModelConfig, loader *model.ModelLoader, responses chan schema.OpenAIResponse, extraUsage bool, id string, created int, textContentToReturn *string) error {
-		// Detect if thinking token is already in prompt or template
-		var template string
-		if config.TemplateConfig.UseTokenizerTemplate {
-			template = config.GetModelTemplate()
-		} else {
-			template = prompt
-		}
-		thinkingStartToken := reason.DetectThinkingStartToken(template, &config.ReasoningConfig)
-		extractor := reason.NewReasoningExtractor(thinkingStartToken, config.ReasoningConfig)
-
-		result := ""
-		lastEmittedCount := 0
-		sentInitialRole := false
-		sentReasoning := false
-		hasChatDeltaToolCalls := false
-		hasChatDeltaContent := false
-
-		_, _, chatDeltas, err := ComputeChoices(req, prompt, config, cl, startupOptions, loader, func(s string, c *[]schema.Choice) {}, func(s string, usage backend.TokenUsage) bool {
-			result += s
-
-			// Track whether ChatDeltas from the C++ autoparser contain
-			// tool calls or content, so the retry decision can account for them.
-			for _, d := range usage.ChatDeltas {
-				if len(d.ToolCalls) > 0 {
-					hasChatDeltaToolCalls = true
-				}
-				if d.Content != "" {
-					hasChatDeltaContent = true
-				}
-			}
-
-			var reasoningDelta, contentDelta string
-
-			goReasoning, goContent := extractor.ProcessToken(s)
-
-			if usage.HasChatDeltaContent() {
-				rawReasoning, cd := usage.ChatDeltaReasoningAndContent()
-				contentDelta = cd
-				reasoningDelta = extractor.ProcessChatDeltaReasoning(rawReasoning)
-			} else {
-				reasoningDelta = goReasoning
-				contentDelta = goContent
-			}
-
-			// Emit reasoning deltas in their own SSE chunks before any tool-call chunks
-			// (OpenAI spec: reasoning and tool_calls never share a delta)
-			if reasoningDelta != "" {
-				responses <- schema.OpenAIResponse{
-					ID:      id,
-					Created: created,
-					Model:   req.Model,
-					Choices: []schema.Choice{{
-						Delta: &schema.Message{Reasoning: &reasoningDelta},
-						Index: 0,
-					}},
-					Object: "chat.completion.chunk",
-				}
-				sentReasoning = true
-			}
-
-			// Stream content deltas (cleaned of reasoning tags) while no tool calls
-			// have been detected. Once the incremental parser finds tool calls,
-			// content stops — per OpenAI spec, content and tool_calls don't mix.
-			if lastEmittedCount == 0 && contentDelta != "" {
-				if !sentInitialRole {
-					responses <- schema.OpenAIResponse{
-						ID: id, Created: created, Model: req.Model,
-						Choices: []schema.Choice{{Delta: &schema.Message{Role: "assistant"}, Index: 0}},
-						Object:  "chat.completion.chunk",
-					}
-					sentInitialRole = true
-				}
-				responses <- schema.OpenAIResponse{
-					ID: id, Created: created, Model: req.Model,
-					Choices: []schema.Choice{{
-						Delta: &schema.Message{Content: &contentDelta},
-						Index: 0,
-					}},
-					Object: "chat.completion.chunk",
-				}
-			}
-
-			// Try incremental XML parsing for streaming support using iterative parser
-			// This allows emitting partial tool calls as they're being generated
-			cleanedResult := functions.CleanupLLMResult(result, config.FunctionsConfig)
-
-			// Determine XML format from config
-			var xmlFormat *functions.XMLToolCallFormat
-			if config.FunctionsConfig.XMLFormat != nil {
-				xmlFormat = config.FunctionsConfig.XMLFormat
-			} else if config.FunctionsConfig.XMLFormatPreset != "" {
-				xmlFormat = functions.GetXMLFormatPreset(config.FunctionsConfig.XMLFormatPreset)
-			}
-
-			// Use iterative parser for streaming (partial parsing enabled)
-			// Try XML parsing first
-			partialResults, parseErr := functions.ParseXMLIterative(cleanedResult, xmlFormat, true)
-			if parseErr == nil && len(partialResults) > 0 {
-				// Emit new XML tool calls that weren't emitted before
-				if len(partialResults) > lastEmittedCount {
-					for i := lastEmittedCount; i < len(partialResults); i++ {
-						toolCall := partialResults[i]
-						initialMessage := schema.OpenAIResponse{
-							ID:      id,
-							Created: created,
-							Model:   req.Model,
-							Choices: []schema.Choice{{
-								Delta: &schema.Message{
-									Role: "assistant",
-									ToolCalls: []schema.ToolCall{
-										{
-											Index: i,
-											ID:    id,
-											Type:  "function",
-											FunctionCall: schema.FunctionCall{
-												Name: toolCall.Name,
-											},
-										},
-									},
-								},
-								Index:        0,
-								FinishReason: nil,
-							}},
-							Object: "chat.completion.chunk",
-						}
-						select {
-						case responses <- initialMessage:
-						default:
-						}
-					}
-					lastEmittedCount = len(partialResults)
-				}
-			} else {
-				// Try JSON tool call parsing for streaming.
-				// Only emit NEW tool calls (same guard as XML parser above).
-				jsonResults, jsonErr := functions.ParseJSONIterative(cleanedResult, true)
-				if jsonErr == nil && len(jsonResults) > lastEmittedCount {
-					for i := lastEmittedCount; i < len(jsonResults); i++ {
-						jsonObj := jsonResults[i]
-						name, ok := jsonObj["name"].(string)
-						if !ok || name == "" {
-							continue
-						}
-						args := "{}"
-						if argsVal, ok := jsonObj["arguments"]; ok {
-							if argsStr, ok := argsVal.(string); ok {
-								args = argsStr
-							} else {
-								argsBytes, _ := json.Marshal(argsVal)
-								args = string(argsBytes)
-							}
-						}
-						initialMessage := schema.OpenAIResponse{
-							ID:      id,
-							Created: created,
-							Model:   req.Model,
-							Choices: []schema.Choice{{
-								Delta: &schema.Message{
-									Role: "assistant",
-									ToolCalls: []schema.ToolCall{
-										{
-											Index: i,
-											ID:    id,
-											Type:  "function",
-											FunctionCall: schema.FunctionCall{
-												Name:      name,
-												Arguments: args,
-											},
-										},
-									},
-								},
-								Index:        0,
-								FinishReason: nil,
-							}},
-							Object: "chat.completion.chunk",
-						}
-						responses <- initialMessage
-					}
-					lastEmittedCount = len(jsonResults)
-				}
-			}
-			return true
-		},
-			func(attempt int) bool {
-				// After streaming completes: check if we got actionable content
-				cleaned := extractor.CleanedContent()
-				// Check for tool calls from chat deltas (will be re-checked after ComputeChoices,
-				// but we need to know here whether to retry).
-				// Also check ChatDelta flags — when the C++ autoparser is active,
-				// tool calls and content are delivered via ChatDeltas while the
-				// raw message is cleared. Without this check, we'd retry
-				// unnecessarily, losing valid results and concatenating output.
-				hasToolCalls := lastEmittedCount > 0 || hasChatDeltaToolCalls
-				hasContent := cleaned != "" || hasChatDeltaContent
-				if !hasContent && !hasToolCalls {
-					xlog.Warn("Streaming: backend produced only reasoning, retrying",
-						"reasoning_len", len(extractor.Reasoning()), "attempt", attempt+1)
-					extractor.ResetAndSuppressReasoning()
-					result = ""
-					lastEmittedCount = 0
-					sentInitialRole = false
-					hasChatDeltaToolCalls = false
-					hasChatDeltaContent = false
-					return true
-				}
-				return false
-			},
-		)
-		if err != nil {
-			return err
-		}
-		// Try using pre-parsed tool calls from C++ autoparser (chat deltas)
-		var functionResults []functions.FuncCallResults
-		var reasoning string
-
-		if deltaToolCalls := functions.ToolCallsFromChatDeltas(chatDeltas); len(deltaToolCalls) > 0 {
-			xlog.Debug("[ChatDeltas] Using pre-parsed tool calls from C++ autoparser", "count", len(deltaToolCalls))
-			functionResults = deltaToolCalls
-			// Use content/reasoning from deltas too
-			*textContentToReturn = functions.ContentFromChatDeltas(chatDeltas)
-			reasoning = functions.ReasoningFromChatDeltas(chatDeltas)
-		} else {
-			// Fallback: parse tool calls from raw text (no chat deltas from backend)
-			xlog.Debug("[ChatDeltas] no pre-parsed tool calls, falling back to Go-side text parsing")
-			reasoning = extractor.Reasoning()
-			cleanedResult := extractor.CleanedContent()
-			*textContentToReturn = functions.ParseTextContent(cleanedResult, config.FunctionsConfig)
-			cleanedResult = functions.CleanupLLMResult(cleanedResult, config.FunctionsConfig)
-			functionResults = functions.ParseFunctionCall(cleanedResult, config.FunctionsConfig)
-		}
-		xlog.Debug("[ChatDeltas] final tool call decision", "tool_calls", len(functionResults), "text_content", *textContentToReturn)
-		// noAction is a sentinel "just answer" pseudo-function — not a real
-		// tool call. Scan the whole slice rather than only index 0 so we
-		// don't drop a real tool call that happens to follow a noAction
-		// entry, and so the default branch isn't entered with only noAction
-		// entries to emit as tool_calls.
-		noActionToRun := !hasRealCall(functionResults, noAction)
-
-		switch {
-		case noActionToRun:
-			// Token-cumulative usage is communicated to the streaming
-			// consumer via the per-token callback's chunk struct (stripped
-			// before wire marshal). The final usage trailer — when the
-			// caller opted in with stream_options.include_usage — is built
-			// by the outer streaming loop, not here.
-			var result string
-			if !sentInitialRole {
-				var hqErr error
-				result, hqErr = handleQuestion(config, functionResults, extractor.CleanedContent(), prompt)
-				if hqErr != nil {
-					xlog.Error("error handling question", "error", hqErr)
-					return hqErr
-				}
-			}
-			for _, chunk := range buildNoActionFinalChunks(
-				id, req.Model, created,
-				sentInitialRole, sentReasoning,
-				result, reasoning,
-			) {
-				responses <- chunk
-			}
-
-		default:
-			for _, chunk := range buildDeferredToolCallChunks(
-				id, req.Model, created,
-				functionResults, lastEmittedCount,
-				sentInitialRole, *textContentToReturn,
-				sentReasoning, reasoning,
-			) {
-				responses <- chunk
-			}
-		}
-
-		close(responses)
-		return err
-	}
-
 	return func(c echo.Context) error {
 		var textContentToReturn string
 		id := uuid.New().String()
@@ -697,17 +340,19 @@ func ChatEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, evaluator
 				}
 
 				responses := make(chan schema.OpenAIResponse)
-				ended := make(chan error, 1)
+				ended := make(chan streamWorkerResult, 1)
 
 				go func() {
 					if !shouldUseFn {
-						ended <- process(predInput, input, config, ml, responses, extraUsage, id, created)
+						u, err := processStream(predInput, input, config, cl, startupOptions, ml, responses, id, created)
+						ended <- streamWorkerResult{usage: u, err: err}
 					} else {
-						ended <- processTools(noActionName, predInput, input, config, ml, responses, extraUsage, id, created, &textContentToReturn)
+						u, err := processStreamWithTools(noActionName, predInput, input, config, cl, startupOptions, ml, responses, id, created, &textContentToReturn)
+						ended <- streamWorkerResult{usage: u, err: err}
 					}
 				}()
 
-				usage := &schema.OpenAIUsage{}
+				var finalUsage backend.TokenUsage
 				toolsCalled := false
 				var collectedToolCalls []schema.ToolCall
 				var collectedContent string
@@ -725,13 +370,6 @@ func ChatEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, evaluator
 							xlog.Debug("No choices in the response, skipping")
 							continue
 						}
-						// Capture the running cumulative usage from this chunk
-						// (when present) so the include_usage trailer can carry
-						// the final totals. Usage is stripped before marshal
-						// below so the wire chunk stays spec-compliant.
-						if ev.Usage != nil {
-							usage = ev.Usage
-						}
 						if len(ev.Choices[0].Delta.ToolCalls) > 0 {
 							toolsCalled = true
 							// Collect and merge tool call deltas for MCP execution
@@ -747,11 +385,6 @@ func ChatEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, evaluator
 								collectedContent += *sp
 							}
 						}
-						// OpenAI streaming spec: intermediate chunks must NOT
-						// carry a `usage` field. Strip the tracking copy
-						// before marshalling — usage is delivered via the
-						// dedicated trailer chunk when include_usage=true.
-						ev.Usage = nil
 						respData, err := json.Marshal(ev)
 						if err != nil {
 							xlog.Debug("Failed to marshal response", "error", err)
@@ -766,15 +399,16 @@ func ChatEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, evaluator
 							return err
 						}
 						c.Response().Flush()
-					case err := <-ended:
-						if err == nil {
+					case res := <-ended:
+						if res.err == nil {
+							finalUsage = res.usage
 							break LOOP
 						}
-						xlog.Error("Stream ended with error", "error", err)
+						xlog.Error("Stream ended with error", "error", res.err)
 
 						errorResp := schema.ErrorResponse{
 							Error: &schema.APIError{
-								Message: err.Error(),
+								Message: res.err.Error(),
 								Type:    "server_error",
 								Code:    "server_error",
 							},
@@ -797,7 +431,10 @@ func ChatEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, evaluator
 				// still trying to send (e.g., after client disconnect). The goroutine
 				// calls close(responses) when done, which terminates the drain.
 				if input.Context.Err() != nil {
-					go func() { for range responses {} }()
+					go func() {
+						for range responses {
+						}
+					}()
 					<-ended
 				}
 
@@ -921,8 +558,16 @@ func ChatEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, evaluator
 				// Trailing usage chunk per OpenAI spec: emit only when the
 				// caller opted in via stream_options.include_usage. Shape:
 				// {"choices":[],"usage":{...},"object":"chat.completion.chunk",...}
-				if input.StreamOptions != nil && input.StreamOptions.IncludeUsage && usage != nil {
-					trailer := streamUsageTrailerJSON(id, input.Model, created, *usage)
+				//
+				// finalUsage is the authoritative TokenUsage returned by the
+				// worker function (process / processTools) via the `ended`
+				// channel. The worker reads it from ComputeChoices' return
+				// value, which is the cumulative count produced by the backend
+				// over the whole prediction. Issue #9927 was caused by the
+				// tools-path worker not surfacing this value at all.
+				if input.StreamOptions != nil && input.StreamOptions.IncludeUsage {
+					trailerUsage := streamUsageFromTokenUsage(finalUsage, extraUsage)
+					trailer := streamUsageTrailerJSON(id, input.Model, created, trailerUsage)
 					_, _ = fmt.Fprintf(c.Response().Writer, "data: %s\n\n", trailer)
 				}
 

core/http/endpoints/openai/chat_emit.go

@@ -4,10 +4,39 @@ import (
 	"encoding/json"
 	"fmt"
 
+	"github.com/mudler/LocalAI/core/backend"
 	"github.com/mudler/LocalAI/core/schema"
 	"github.com/mudler/LocalAI/pkg/functions"
 )
 
+// streamWorkerResult is what the streaming workers (process / processTools)
+// hand back to the outer ChatEndpoint loop through the `ended` channel.
+// Threading the final TokenUsage here, instead of piggy-backing it on the
+// `responses` SSE channel, keeps the SSE channel single-purpose (wire chunks)
+// and gives the trailer emitter a plain Go value to read after LOOP exits.
+// Fix for issue #9927: the previous tools-path worker never surfaced the
+// cumulative token counts at all, so the include_usage trailer reported zeros.
+type streamWorkerResult struct {
+	usage backend.TokenUsage
+	err   error
+}
+
+// streamUsageFromTokenUsage converts the backend's cumulative TokenUsage into
+// the OpenAI-spec OpenAIUsage shape used on the wire. `extraUsage` controls
+// whether the non-standard timing fields are forwarded.
+func streamUsageFromTokenUsage(usage backend.TokenUsage, extraUsage bool) schema.OpenAIUsage {
+	out := schema.OpenAIUsage{
+		PromptTokens:     usage.Prompt,
+		CompletionTokens: usage.Completion,
+		TotalTokens:      usage.Prompt + usage.Completion,
+	}
+	if extraUsage {
+		out.TimingTokenGeneration = usage.TimingTokenGeneration
+		out.TimingPromptProcessing = usage.TimingPromptProcessing
+	}
+	return out
+}
+
 // streamUsageTrailerJSON returns the bytes of the OpenAI-spec trailing usage
 // chunk emitted in streaming completions when the request opts in via
 // `stream_options.include_usage: true`. The shape is:

core/http/endpoints/openai/chat_stream_usage_test.go

@@ -1,10 +1,14 @@
 package openai
 
 import (
+	"context"
 	"encoding/json"
 
+	"github.com/mudler/LocalAI/core/backend"
+	"github.com/mudler/LocalAI/core/config"
 	"github.com/mudler/LocalAI/core/schema"
 	"github.com/mudler/LocalAI/pkg/functions"
+	"github.com/mudler/LocalAI/pkg/model"
 	. "github.com/onsi/ginkgo/v2"
 	. "github.com/onsi/gomega"
 )
@@ -152,6 +156,28 @@ var _ = Describe("streaming usage spec compliance", func() {
 		})
 	})
 
+	Describe("streamUsageFromTokenUsage", func() {
+		It("converts backend TokenUsage to schema OpenAIUsage", func() {
+			tu := backend.TokenUsage{Prompt: 18, Completion: 213}
+			u := streamUsageFromTokenUsage(tu, false)
+			Expect(u.PromptTokens).To(Equal(18))
+			Expect(u.CompletionTokens).To(Equal(213))
+			Expect(u.TotalTokens).To(Equal(231))
+			Expect(u.TimingTokenGeneration).To(BeZero())
+			Expect(u.TimingPromptProcessing).To(BeZero())
+		})
+		It("includes timings when extraUsage is true", func() {
+			tu := backend.TokenUsage{
+				Prompt: 10, Completion: 20,
+				TimingPromptProcessing: 0.5,
+				TimingTokenGeneration:  1.5,
+			}
+			u := streamUsageFromTokenUsage(tu, true)
+			Expect(u.TimingPromptProcessing).To(Equal(0.5))
+			Expect(u.TimingTokenGeneration).To(Equal(1.5))
+		})
+	})
+
 	Describe("OpenAIRequest.StreamOptions", func() {
 		It("parses stream_options.include_usage=true", func() {
 			body := []byte(`{
@@ -177,3 +203,160 @@ var _ = Describe("streaming usage spec compliance", func() {
 		})
 	})
 })
+
+// Functional regression coverage for issue #9927: the streaming workers
+// must surface the cumulative TokenUsage returned by ComputeChoices to
+// their caller. The earlier broken implementations discarded that value
+// (`_, _, chatDeltas, err := ComputeChoices(...)`) and threw away the
+// counts on the floor, so the include_usage trailer always reported
+// zeros when tools were enabled.
+//
+// These tests stub backend.ModelInferenceFunc so the worker exercises the
+// real ComputeChoices → predFunc → LLMResponse pipeline. If a future change
+// drops the TokenUsage somewhere along that path, the assertions on the
+// returned value fail with a concrete count mismatch (e.g. 0 vs 213),
+// not with a "function undefined" compile error.
+var _ = Describe("streaming workers surface final TokenUsage (issue #9927)", func() {
+	var (
+		origInference modelInferenceFunc
+		appCfg        *config.ApplicationConfig
+	)
+
+	BeforeEach(func() {
+		origInference = backend.ModelInferenceFunc
+		appCfg = config.NewApplicationConfig()
+	})
+
+	AfterEach(func() {
+		backend.ModelInferenceFunc = origInference
+	})
+
+	// mockBackendUsage installs a stub backend that yields one LLMResponse
+	// carrying the supplied TokenUsage. ComputeChoices' single-attempt path
+	// copies these counts into the value it returns to the worker.
+	mockBackendUsage := func(usage backend.TokenUsage, response string) {
+		backend.ModelInferenceFunc = func(
+			ctx context.Context, s string, messages schema.Messages,
+			images, videos, audios []string,
+			loader *model.ModelLoader, c *config.ModelConfig, cl *config.ModelConfigLoader,
+			o *config.ApplicationConfig,
+			tokenCallback func(string, backend.TokenUsage) bool,
+			tools, toolChoice string,
+			logprobs, topLogprobs *int,
+			logitBias map[string]float64,
+			metadata map[string]string,
+		) (func() (backend.LLMResponse, error), error) {
+			return func() (backend.LLMResponse, error) {
+				return backend.LLMResponse{
+					Response: response,
+					Usage:    usage,
+				}, nil
+			}, nil
+		}
+	}
+
+	makeReq := func() *schema.OpenAIRequest {
+		ctx, cancel := context.WithCancel(context.Background())
+		req := &schema.OpenAIRequest{
+			Context: ctx,
+			Cancel:  cancel,
+		}
+		req.Model = "test-model" // promoted from BasicModelRequest
+		return req
+	}
+
+	// drainResponses consumes everything the worker pushes onto the channel
+	// so the worker is never blocked on its send. The channel is unbuffered
+	// (matching production), so the drain goroutine must be running before
+	// the worker is called.
+	drainResponses := func(ch <-chan schema.OpenAIResponse) <-chan struct{} {
+		done := make(chan struct{})
+		go func() {
+			for range ch {
+			}
+			close(done)
+		}()
+		return done
+	}
+
+	Describe("processStream (no-tools path)", func() {
+		It("returns the cumulative TokenUsage produced by the backend", func() {
+			mockBackendUsage(backend.TokenUsage{Prompt: 18, Completion: 213}, "Hello there")
+
+			req := makeReq()
+			cfg := &config.ModelConfig{}
+			responses := make(chan schema.OpenAIResponse)
+			done := drainResponses(responses)
+
+			actual, err := processStream("prompt", req, cfg, nil, appCfg, nil, responses, "req-1", 0)
+			<-done
+
+			Expect(err).ToNot(HaveOccurred())
+			Expect(actual.Prompt).To(Equal(18),
+				"prompt tokens must round-trip from backend through processStream")
+			Expect(actual.Completion).To(Equal(213),
+				"completion tokens must round-trip from backend through processStream")
+		})
+
+		It("returns zero TokenUsage when the backend reports zero (negative control)", func() {
+			mockBackendUsage(backend.TokenUsage{}, "x")
+
+			req := makeReq()
+			cfg := &config.ModelConfig{}
+			responses := make(chan schema.OpenAIResponse)
+			done := drainResponses(responses)
+
+			actual, err := processStream("prompt", req, cfg, nil, appCfg, nil, responses, "req-1", 0)
+			<-done
+
+			Expect(err).ToNot(HaveOccurred())
+			Expect(actual.Prompt).To(BeZero())
+			Expect(actual.Completion).To(BeZero())
+		})
+	})
+
+	Describe("processStreamWithTools (tools path)", func() {
+		It("returns the cumulative TokenUsage produced by the backend", func() {
+			// This is the direct regression check for issue #9927: with tools
+			// enabled, the trailer was reporting {0,0,0} because the worker
+			// discarded ComputeChoices' second return value.
+			mockBackendUsage(backend.TokenUsage{Prompt: 18, Completion: 213}, "answer")
+
+			req := makeReq()
+			cfg := &config.ModelConfig{}
+			responses := make(chan schema.OpenAIResponse)
+			done := drainResponses(responses)
+			var textContent string
+
+			actual, err := processStreamWithTools("none", "prompt", req, cfg, nil, appCfg, nil, responses, "req-1", 0, &textContent)
+			<-done
+
+			Expect(err).ToNot(HaveOccurred())
+			Expect(actual.Prompt).To(Equal(18),
+				"prompt tokens must round-trip from backend through processStreamWithTools (issue #9927)")
+			Expect(actual.Completion).To(Equal(213),
+				"completion tokens must round-trip from backend through processStreamWithTools (issue #9927)")
+		})
+
+		It("forwards timing fields when the backend supplies them", func() {
+			mockBackendUsage(backend.TokenUsage{
+				Prompt: 10, Completion: 20,
+				TimingPromptProcessing: 0.5,
+				TimingTokenGeneration:  1.5,
+			}, "answer")
+
+			req := makeReq()
+			cfg := &config.ModelConfig{}
+			responses := make(chan schema.OpenAIResponse)
+			done := drainResponses(responses)
+			var textContent string
+
+			actual, err := processStreamWithTools("none", "prompt", req, cfg, nil, appCfg, nil, responses, "req-1", 0, &textContent)
+			<-done
+
+			Expect(err).ToNot(HaveOccurred())
+			Expect(actual.TimingPromptProcessing).To(Equal(0.5))
+			Expect(actual.TimingTokenGeneration).To(Equal(1.5))
+		})
+	})
+})

core/http/endpoints/openai/chat_stream_workers.go

@@ -0,0 +1,390 @@
+package openai
+
+import (
+	"encoding/json"
+
+	"github.com/mudler/LocalAI/core/backend"
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/schema"
+	"github.com/mudler/LocalAI/pkg/functions"
+	"github.com/mudler/LocalAI/pkg/model"
+	reason "github.com/mudler/LocalAI/pkg/reasoning"
+	"github.com/mudler/xlog"
+)
+
+// processStream is the streaming worker for chat completions with no
+// tool/function calling involved. It pushes SSE-shaped chunks onto
+// `responses` and returns the authoritative cumulative TokenUsage from
+// the prediction so the caller can populate the include_usage trailer
+// without having to peek inside the chunks.
+//
+// The caller owns the `responses` channel and is expected to read from
+// it while this function runs; processStream closes the channel before
+// returning.
+func processStream(
+	s string,
+	req *schema.OpenAIRequest,
+	cfg *config.ModelConfig,
+	cl *config.ModelConfigLoader,
+	startupOptions *config.ApplicationConfig,
+	loader *model.ModelLoader,
+	responses chan schema.OpenAIResponse,
+	id string,
+	created int,
+) (backend.TokenUsage, error) {
+	responses <- schema.OpenAIResponse{
+		ID:      id,
+		Created: created,
+		Model:   req.Model, // we have to return what the user sent here, due to OpenAI spec.
+		Choices: []schema.Choice{{Delta: &schema.Message{Role: "assistant"}, Index: 0, FinishReason: nil}},
+		Object:  "chat.completion.chunk",
+	}
+
+	// Detect if thinking token is already in prompt or template
+	// When UseTokenizerTemplate is enabled, predInput is empty, so we check the template
+	var template string
+	if cfg.TemplateConfig.UseTokenizerTemplate {
+		template = cfg.GetModelTemplate()
+	} else {
+		template = s
+	}
+	thinkingStartToken := reason.DetectThinkingStartToken(template, &cfg.ReasoningConfig)
+	extractor := reason.NewReasoningExtractor(thinkingStartToken, cfg.ReasoningConfig)
+
+	_, finalUsage, _, err := ComputeChoices(req, s, cfg, cl, startupOptions, loader, func(s string, c *[]schema.Choice) {}, func(s string, tokenUsage backend.TokenUsage) bool {
+		var reasoningDelta, contentDelta string
+
+		// Always keep the Go-side extractor in sync with raw tokens so it
+		// can serve as fallback for backends without an autoparser (e.g. vLLM).
+		goReasoning, goContent := extractor.ProcessToken(s)
+
+		// When C++ autoparser chat deltas are available, prefer them: they
+		// handle model-specific formats (Gemma 4, etc.) without Go-side tags.
+		// Otherwise fall back to Go-side extraction.
+		if tokenUsage.HasChatDeltaContent() {
+			rawReasoning, cd := tokenUsage.ChatDeltaReasoningAndContent()
+			contentDelta = cd
+			reasoningDelta = extractor.ProcessChatDeltaReasoning(rawReasoning)
+		} else {
+			reasoningDelta = goReasoning
+			contentDelta = goContent
+		}
+
+		delta := &schema.Message{}
+		if contentDelta != "" {
+			delta.Content = &contentDelta
+		}
+		if reasoningDelta != "" {
+			delta.Reasoning = &reasoningDelta
+		}
+
+		responses <- schema.OpenAIResponse{
+			ID:      id,
+			Created: created,
+			Model:   req.Model, // we have to return what the user sent here, due to OpenAI spec.
+			Choices: []schema.Choice{{Delta: delta, Index: 0, FinishReason: nil}},
+			Object:  "chat.completion.chunk",
+		}
+		return true
+	})
+	close(responses)
+	return finalUsage, err
+}
+
+// processStreamWithTools is the streaming worker for chat completions
+// with tools / function calling. Same contract as processStream: pushes
+// chunks onto `responses`, closes the channel, returns the cumulative
+// TokenUsage.
+//
+// Returning the TokenUsage as a normal Go value (rather than smuggling
+// it on a sentinel chunk) is the fix for issue #9927 — the previous
+// implementation discarded the value from ComputeChoices, so the
+// include_usage trailer reported zeros whenever `tools` was in play.
+func processStreamWithTools(
+	noAction string,
+	prompt string,
+	req *schema.OpenAIRequest,
+	cfg *config.ModelConfig,
+	cl *config.ModelConfigLoader,
+	startupOptions *config.ApplicationConfig,
+	loader *model.ModelLoader,
+	responses chan schema.OpenAIResponse,
+	id string,
+	created int,
+	textContentToReturn *string,
+) (backend.TokenUsage, error) {
+	// Detect if thinking token is already in prompt or template
+	var template string
+	if cfg.TemplateConfig.UseTokenizerTemplate {
+		template = cfg.GetModelTemplate()
+	} else {
+		template = prompt
+	}
+	thinkingStartToken := reason.DetectThinkingStartToken(template, &cfg.ReasoningConfig)
+	extractor := reason.NewReasoningExtractor(thinkingStartToken, cfg.ReasoningConfig)
+
+	result := ""
+	lastEmittedCount := 0
+	sentInitialRole := false
+	sentReasoning := false
+	hasChatDeltaToolCalls := false
+	hasChatDeltaContent := false
+
+	_, finalUsage, chatDeltas, err := ComputeChoices(req, prompt, cfg, cl, startupOptions, loader, func(s string, c *[]schema.Choice) {}, func(s string, usage backend.TokenUsage) bool {
+		result += s
+
+		// Track whether ChatDeltas from the C++ autoparser contain
+		// tool calls or content, so the retry decision can account for them.
+		for _, d := range usage.ChatDeltas {
+			if len(d.ToolCalls) > 0 {
+				hasChatDeltaToolCalls = true
+			}
+			if d.Content != "" {
+				hasChatDeltaContent = true
+			}
+		}
+
+		var reasoningDelta, contentDelta string
+
+		goReasoning, goContent := extractor.ProcessToken(s)
+
+		if usage.HasChatDeltaContent() {
+			rawReasoning, cd := usage.ChatDeltaReasoningAndContent()
+			contentDelta = cd
+			reasoningDelta = extractor.ProcessChatDeltaReasoning(rawReasoning)
+		} else {
+			reasoningDelta = goReasoning
+			contentDelta = goContent
+		}
+
+		// Emit reasoning deltas in their own SSE chunks before any tool-call chunks
+		// (OpenAI spec: reasoning and tool_calls never share a delta)
+		if reasoningDelta != "" {
+			responses <- schema.OpenAIResponse{
+				ID:      id,
+				Created: created,
+				Model:   req.Model,
+				Choices: []schema.Choice{{
+					Delta: &schema.Message{Reasoning: &reasoningDelta},
+					Index: 0,
+				}},
+				Object: "chat.completion.chunk",
+			}
+			sentReasoning = true
+		}
+
+		// Stream content deltas (cleaned of reasoning tags) while no tool calls
+		// have been detected. Once the incremental parser finds tool calls,
+		// content stops: per OpenAI spec, content and tool_calls don't mix.
+		if lastEmittedCount == 0 && contentDelta != "" {
+			if !sentInitialRole {
+				responses <- schema.OpenAIResponse{
+					ID: id, Created: created, Model: req.Model,
+					Choices: []schema.Choice{{Delta: &schema.Message{Role: "assistant"}, Index: 0}},
+					Object:  "chat.completion.chunk",
+				}
+				sentInitialRole = true
+			}
+			responses <- schema.OpenAIResponse{
+				ID: id, Created: created, Model: req.Model,
+				Choices: []schema.Choice{{
+					Delta: &schema.Message{Content: &contentDelta},
+					Index: 0,
+				}},
+				Object: "chat.completion.chunk",
+			}
+		}
+
+		// Try incremental XML parsing for streaming support using iterative parser
+		// This allows emitting partial tool calls as they're being generated
+		cleanedResult := functions.CleanupLLMResult(result, cfg.FunctionsConfig)
+
+		// Determine XML format from config
+		var xmlFormat *functions.XMLToolCallFormat
+		if cfg.FunctionsConfig.XMLFormat != nil {
+			xmlFormat = cfg.FunctionsConfig.XMLFormat
+		} else if cfg.FunctionsConfig.XMLFormatPreset != "" {
+			xmlFormat = functions.GetXMLFormatPreset(cfg.FunctionsConfig.XMLFormatPreset)
+		}
+
+		// Use iterative parser for streaming (partial parsing enabled)
+		// Try XML parsing first
+		partialResults, parseErr := functions.ParseXMLIterative(cleanedResult, xmlFormat, true)
+		if parseErr == nil && len(partialResults) > 0 {
+			// Emit new XML tool calls that weren't emitted before
+			if len(partialResults) > lastEmittedCount {
+				for i := lastEmittedCount; i < len(partialResults); i++ {
+					toolCall := partialResults[i]
+					initialMessage := schema.OpenAIResponse{
+						ID:      id,
+						Created: created,
+						Model:   req.Model,
+						Choices: []schema.Choice{{
+							Delta: &schema.Message{
+								Role: "assistant",
+								ToolCalls: []schema.ToolCall{
+									{
+										Index: i,
+										ID:    id,
+										Type:  "function",
+										FunctionCall: schema.FunctionCall{
+											Name: toolCall.Name,
+										},
+									},
+								},
+							},
+							Index:        0,
+							FinishReason: nil,
+						}},
+						Object: "chat.completion.chunk",
+					}
+					select {
+					case responses <- initialMessage:
+					default:
+					}
+				}
+				lastEmittedCount = len(partialResults)
+			}
+		} else {
+			// Try JSON tool call parsing for streaming.
+			// Only emit NEW tool calls (same guard as XML parser above).
+			jsonResults, jsonErr := functions.ParseJSONIterative(cleanedResult, true)
+			if jsonErr == nil && len(jsonResults) > lastEmittedCount {
+				for i := lastEmittedCount; i < len(jsonResults); i++ {
+					jsonObj := jsonResults[i]
+					name, ok := jsonObj["name"].(string)
+					if !ok || name == "" {
+						continue
+					}
+					args := "{}"
+					if argsVal, ok := jsonObj["arguments"]; ok {
+						if argsStr, ok := argsVal.(string); ok {
+							args = argsStr
+						} else {
+							argsBytes, _ := json.Marshal(argsVal)
+							args = string(argsBytes)
+						}
+					}
+					initialMessage := schema.OpenAIResponse{
+						ID:      id,
+						Created: created,
+						Model:   req.Model,
+						Choices: []schema.Choice{{
+							Delta: &schema.Message{
+								Role: "assistant",
+								ToolCalls: []schema.ToolCall{
+									{
+										Index: i,
+										ID:    id,
+										Type:  "function",
+										FunctionCall: schema.FunctionCall{
+											Name:      name,
+											Arguments: args,
+										},
+									},
+								},
+							},
+							Index:        0,
+							FinishReason: nil,
+						}},
+						Object: "chat.completion.chunk",
+					}
+					responses <- initialMessage
+				}
+				lastEmittedCount = len(jsonResults)
+			}
+		}
+		return true
+	},
+		func(attempt int) bool {
+			// After streaming completes: check if we got actionable content
+			cleaned := extractor.CleanedContent()
+			// Check for tool calls from chat deltas (will be re-checked after ComputeChoices,
+			// but we need to know here whether to retry).
+			// Also check ChatDelta flags: when the C++ autoparser is active,
+			// tool calls and content are delivered via ChatDeltas while the
+			// raw message is cleared. Without this check, we'd retry
+			// unnecessarily, losing valid results and concatenating output.
+			hasToolCalls := lastEmittedCount > 0 || hasChatDeltaToolCalls
+			hasContent := cleaned != "" || hasChatDeltaContent
+			if !hasContent && !hasToolCalls {
+				xlog.Warn("Streaming: backend produced only reasoning, retrying",
+					"reasoning_len", len(extractor.Reasoning()), "attempt", attempt+1)
+				extractor.ResetAndSuppressReasoning()
+				result = ""
+				lastEmittedCount = 0
+				sentInitialRole = false
+				hasChatDeltaToolCalls = false
+				hasChatDeltaContent = false
+				return true
+			}
+			return false
+		},
+	)
+	if err != nil {
+		return finalUsage, err
+	}
+	// Try using pre-parsed tool calls from C++ autoparser (chat deltas)
+	var functionResults []functions.FuncCallResults
+	var reasoning string
+
+	if deltaToolCalls := functions.ToolCallsFromChatDeltas(chatDeltas); len(deltaToolCalls) > 0 {
+		xlog.Debug("[ChatDeltas] Using pre-parsed tool calls from C++ autoparser", "count", len(deltaToolCalls))
+		functionResults = deltaToolCalls
+		// Use content/reasoning from deltas too
+		*textContentToReturn = functions.ContentFromChatDeltas(chatDeltas)
+		reasoning = functions.ReasoningFromChatDeltas(chatDeltas)
+	} else {
+		// Fallback: parse tool calls from raw text (no chat deltas from backend)
+		xlog.Debug("[ChatDeltas] no pre-parsed tool calls, falling back to Go-side text parsing")
+		reasoning = extractor.Reasoning()
+		cleanedResult := extractor.CleanedContent()
+		*textContentToReturn = functions.ParseTextContent(cleanedResult, cfg.FunctionsConfig)
+		cleanedResult = functions.CleanupLLMResult(cleanedResult, cfg.FunctionsConfig)
+		functionResults = functions.ParseFunctionCall(cleanedResult, cfg.FunctionsConfig)
+	}
+	xlog.Debug("[ChatDeltas] final tool call decision", "tool_calls", len(functionResults), "text_content", *textContentToReturn)
+	// noAction is a sentinel "just answer" pseudo-function: not a real
+	// tool call. Scan the whole slice rather than only index 0 so we
+	// don't drop a real tool call that happens to follow a noAction
+	// entry, and so the default branch isn't entered with only noAction
+	// entries to emit as tool_calls.
+	noActionToRun := !hasRealCall(functionResults, noAction)
+
+	switch {
+	case noActionToRun:
+		// The final usage trailer (when the caller opted in with
+		// stream_options.include_usage) is built by the outer streaming
+		// loop from the TokenUsage this function returns, not from any
+		// chunk on the responses channel.
+		var result string
+		if !sentInitialRole {
+			var hqErr error
+			result, hqErr = handleQuestion(cfg, functionResults, extractor.CleanedContent(), prompt)
+			if hqErr != nil {
+				xlog.Error("error handling question", "error", hqErr)
+				return finalUsage, hqErr
+			}
+		}
+		for _, chunk := range buildNoActionFinalChunks(
+			id, req.Model, created,
+			sentInitialRole, sentReasoning,
+			result, reasoning,
+		) {
+			responses <- chunk
+		}
+
+	default:
+		for _, chunk := range buildDeferredToolCallChunks(
+			id, req.Model, created,
+			functionResults, lastEmittedCount,
+			sentInitialRole, *textContentToReturn,
+			sentReasoning, reasoning,
+		) {
+			responses <- chunk
+		}
+	}
+
+	close(responses)
+	return finalUsage, err
+}

core/http/middleware/trace.go

@@ -17,16 +17,20 @@ import (
 )
 
 type APIExchangeRequest struct {
-	Method  string       `json:"method"`
-	Path    string       `json:"path"`
-	Headers *http.Header `json:"headers"`
-	Body    *[]byte      `json:"body"`
+	Method        string       `json:"method"`
+	Path          string       `json:"path"`
+	Headers       *http.Header `json:"headers"`
+	Body          *[]byte      `json:"body"`
+	BodyTruncated bool         `json:"body_truncated,omitempty"`
+	BodyBytes     int          `json:"body_bytes,omitempty"` // original size before truncation
 }
 
 type APIExchangeResponse struct {
-	Status  int          `json:"status"`
-	Headers *http.Header `json:"headers"`
-	Body    *[]byte      `json:"body"`
+	Status        int          `json:"status"`
+	Headers       *http.Header `json:"headers"`
+	Body          *[]byte      `json:"body"`
+	BodyTruncated bool         `json:"body_truncated,omitempty"`
+	BodyBytes     int          `json:"body_bytes,omitempty"` // original size before truncation
 }
 
 type APIExchange struct {
@@ -66,11 +70,29 @@ var doInitializeTracing = sync.OnceFunc(func() {
 
 type bodyWriter struct {
 	http.ResponseWriter
-	body *bytes.Buffer
+	body       *bytes.Buffer
+	maxBytes   int // 0 = unlimited capture
+	truncated  bool
+	totalBytes int // bytes the upstream handler wrote, even past the cap
 }
 
 func (w *bodyWriter) Write(b []byte) (int, error) {
-	w.body.Write(b)
+	// Capture into the trace buffer up to maxBytes, then drop the overflow
+	// so a chatty endpoint can't grow the buffer without bound. The full
+	// payload still flows through to the real client below.
+	w.totalBytes += len(b)
+	if w.maxBytes <= 0 {
+		w.body.Write(b)
+	} else if remain := w.maxBytes - w.body.Len(); remain > 0 {
+		if remain >= len(b) {
+			w.body.Write(b)
+		} else {
+			w.body.Write(b[:remain])
+			w.truncated = true
+		}
+	} else {
+		w.truncated = true
+	}
 	return w.ResponseWriter.Write(b)
 }
 
@@ -80,6 +102,20 @@ func (w *bodyWriter) Flush() {
 	}
 }
 
+// truncateForTrace returns a defensive copy of body capped at maxBytes,
+// and a flag indicating whether the cap forced truncation. maxBytes <= 0
+// disables the cap.
+func truncateForTrace(body []byte, maxBytes int) ([]byte, bool) {
+	if maxBytes <= 0 || len(body) <= maxBytes {
+		out := make([]byte, len(body))
+		copy(out, body)
+		return out, false
+	}
+	out := make([]byte, maxBytes)
+	copy(out, body[:maxBytes])
+	return out, true
+}
+
 func initializeTracing(maxItems int) {
 	tracingMaxItems = maxItems
 	doInitializeTracing()
@@ -134,11 +170,18 @@ func TraceMiddleware(app *application.Application) echo.MiddlewareFunc {
 
 			startTime := time.Now()
 
+			// Cap captured payload size. Without this, /embeddings and
+			// streaming /chat/completions blow the in-memory buffer into the
+			// tens of MB, which then locks the admin Traces UI fetching the
+			// JSON dump faster than the 5s auto-refresh.
+			maxBodyBytes := app.ApplicationConfig().TracingMaxBodyBytes
+
 			// Wrap response writer to capture body
 			resBody := new(bytes.Buffer)
 			mw := &bodyWriter{
 				ResponseWriter: c.Response().Writer,
 				body:           resBody,
+				maxBytes:       maxBodyBytes,
 			}
 			c.Response().Writer = mw
 
@@ -159,8 +202,7 @@ func TraceMiddleware(app *application.Application) echo.MiddlewareFunc {
 			// via any heap-dump-style introspection, and tokens shouldn't
 			// outlive the request that carried them.
 			requestHeaders := redactSensitiveHeaders(c.Request().Header)
-			requestBody := make([]byte, len(body))
-			copy(requestBody, body)
+			requestBody, requestTruncated := truncateForTrace(body, maxBodyBytes)
 			responseHeaders := redactSensitiveHeaders(c.Response().Header())
 			responseBody := make([]byte, resBody.Len())
 			copy(responseBody, resBody.Bytes())
@@ -168,15 +210,19 @@ func TraceMiddleware(app *application.Application) echo.MiddlewareFunc {
 				Timestamp: startTime,
 				Duration:  time.Since(startTime),
 				Request: APIExchangeRequest{
-					Method:  c.Request().Method,
-					Path:    c.Path(),
-					Headers: &requestHeaders,
-					Body:    &requestBody,
+					Method:        c.Request().Method,
+					Path:          c.Path(),
+					Headers:       &requestHeaders,
+					Body:          &requestBody,
+					BodyTruncated: requestTruncated,
+					BodyBytes:     len(body),
 				},
 				Response: APIExchangeResponse{
-					Status:  status,
-					Headers: &responseHeaders,
-					Body:    &responseBody,
+					Status:        status,
+					Headers:       &responseHeaders,
+					Body:          &responseBody,
+					BodyTruncated: mw.truncated,
+					BodyBytes:     mw.totalBytes,
 				},
 			}
 			if handlerErr != nil {

core/http/middleware/trace_body_cap_test.go

@@ -0,0 +1,116 @@
+package middleware
+
+import (
+	"bytes"
+	"net/http/httptest"
+	"strings"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// The trace middleware copies request and response bodies into an in-memory
+// buffer that backs the admin /api/traces endpoint. With no upper bound a
+// chatty workload (embeddings, large completions) trivially produces a
+// multi-MB response that locks the Traces UI in a loading state — fetching
+// and parsing the payload outruns the 5-second auto-refresh. These specs
+// pin the capping contract so future refactors keep both the cap and the
+// passthrough to the real client intact.
+
+var _ = Describe("bodyWriter capping", func() {
+	It("captures the full body when maxBytes is 0 (unlimited)", func() {
+		downstream := httptest.NewRecorder()
+		buf := &bytes.Buffer{}
+		bw := &bodyWriter{ResponseWriter: downstream, body: buf, maxBytes: 0}
+
+		payload := []byte(strings.Repeat("x", 4096))
+		n, err := bw.Write(payload)
+
+		Expect(err).ToNot(HaveOccurred())
+		Expect(n).To(Equal(len(payload)))
+		Expect(buf.Len()).To(Equal(len(payload)))
+		Expect(downstream.Body.Len()).To(Equal(len(payload)))
+		Expect(bw.truncated).To(BeFalse())
+	})
+
+	It("stops appending to the trace buffer once maxBytes is reached but still forwards to the client", func() {
+		downstream := httptest.NewRecorder()
+		buf := &bytes.Buffer{}
+		bw := &bodyWriter{ResponseWriter: downstream, body: buf, maxBytes: 100}
+
+		payload := []byte(strings.Repeat("a", 250))
+		n, err := bw.Write(payload)
+
+		Expect(err).ToNot(HaveOccurred())
+		Expect(n).To(Equal(len(payload)), "Write must return the full byte count so callers see no short write")
+		Expect(buf.Len()).To(Equal(100), "trace buffer should hold exactly maxBytes")
+		Expect(downstream.Body.Len()).To(Equal(len(payload)), "client must still receive every byte")
+		Expect(bw.truncated).To(BeTrue())
+	})
+
+	It("handles a write that straddles the cap by keeping only the leading slice", func() {
+		downstream := httptest.NewRecorder()
+		buf := &bytes.Buffer{}
+		bw := &bodyWriter{ResponseWriter: downstream, body: buf, maxBytes: 10}
+
+		_, err := bw.Write([]byte("12345"))
+		Expect(err).ToNot(HaveOccurred())
+		Expect(bw.truncated).To(BeFalse())
+
+		_, err = bw.Write([]byte("67890ABCDE"))
+		Expect(err).ToNot(HaveOccurred())
+
+		Expect(buf.String()).To(Equal("1234567890"))
+		Expect(downstream.Body.String()).To(Equal("1234567890ABCDE"))
+		Expect(bw.truncated).To(BeTrue())
+	})
+
+	It("ignores further writes after the cap was already hit", func() {
+		downstream := httptest.NewRecorder()
+		buf := &bytes.Buffer{}
+		bw := &bodyWriter{ResponseWriter: downstream, body: buf, maxBytes: 4}
+
+		_, _ = bw.Write([]byte("AAAA"))
+		_, _ = bw.Write([]byte("BBBB"))
+		_, _ = bw.Write([]byte("CCCC"))
+
+		Expect(buf.String()).To(Equal("AAAA"))
+		Expect(downstream.Body.String()).To(Equal("AAAABBBBCCCC"))
+		Expect(bw.truncated).To(BeTrue())
+	})
+})
+
+var _ = Describe("truncateForTrace", func() {
+	It("returns the input unchanged when below the cap", func() {
+		in := []byte("hello")
+		out, truncated := truncateForTrace(in, 1024)
+		Expect(truncated).To(BeFalse())
+		Expect(out).To(Equal(in))
+	})
+
+	It("truncates when the input exceeds the cap and signals truncation", func() {
+		in := []byte(strings.Repeat("z", 200))
+		out, truncated := truncateForTrace(in, 64)
+		Expect(truncated).To(BeTrue())
+		Expect(out).To(HaveLen(64))
+		Expect(string(out)).To(Equal(strings.Repeat("z", 64)))
+	})
+
+	It("treats maxBytes <= 0 as unlimited (back-compat with current default)", func() {
+		in := []byte(strings.Repeat("q", 10_000))
+		out, truncated := truncateForTrace(in, 0)
+		Expect(truncated).To(BeFalse())
+		Expect(out).To(HaveLen(len(in)))
+	})
+
+	It("does not retain the caller's backing array (defensive copy)", func() {
+		in := []byte("abcdefghij")
+		out, truncated := truncateForTrace(in, 4)
+		Expect(truncated).To(BeTrue())
+		Expect(string(out)).To(Equal("abcd"))
+
+		// Mutating the source must not corrupt the trace copy.
+		in[0] = 'Z'
+		Expect(string(out)).To(Equal("abcd"))
+	})
+})

core/http/react-ui/e2e/traces.spec.js

@@ -52,11 +52,22 @@ test.describe('Traces Settings', () => {
     await page.locator('button', { hasText: 'Tracing is' }).click()
     await expect(page.locator('text=Enable Tracing')).toBeVisible()
 
-    const maxItemsInput = page.locator('input[type="number"]')
+    // The Tracing panel has two numeric inputs (Max Items and Max Body Bytes).
+    // Disambiguate by placeholder so adding a third field later doesn't break this.
+    const maxItemsInput = page.getByPlaceholder('100')
     await maxItemsInput.fill('500')
     await expect(maxItemsInput).toHaveValue('500')
   })
 
+  test('set max body bytes value', async ({ page }) => {
+    await page.locator('button', { hasText: 'Tracing is' }).click()
+    await expect(page.locator('text=Enable Tracing')).toBeVisible()
+
+    const maxBodyBytesInput = page.getByPlaceholder('65536')
+    await maxBodyBytesInput.fill('16384')
+    await expect(maxBodyBytesInput).toHaveValue('16384')
+  })
+
   test('save shows toast', async ({ page }) => {
     // Expand settings
     await page.locator('button', { hasText: 'Tracing is' }).click()

core/http/react-ui/src/pages/Settings.jsx

@@ -435,6 +435,9 @@ export default function Settings() {
               <SettingRow label="Max Items" description="Maximum number of trace items to retain (0 = unlimited)">
                 <input className="input" type="number" style={{ width: 120 }} value={settings.tracing_max_items ?? ''} onChange={(e) => update('tracing_max_items', parseInt(e.target.value) || 0)} placeholder="100" disabled={!settings.enable_tracing} />
               </SettingRow>
+              <SettingRow label="Max Body Bytes" description="Per-field cap (bytes) for captured request/response bodies and backend trace Data fields. Prevents large LLM histories or TTS audio snippets from locking the Traces UI. 0 = uncapped.">
+                <input className="input" type="number" style={{ width: 120 }} value={settings.tracing_max_body_bytes ?? ''} onChange={(e) => update('tracing_max_body_bytes', parseInt(e.target.value) || 0)} placeholder="65536" disabled={!settings.enable_tracing} />
+              </SettingRow>
               <SettingRow label="Enable Backend Logging" description="Capture backend process output per model (without requiring debug mode)">
                 <Toggle checked={settings.enable_backend_logging} onChange={(v) => update('enable_backend_logging', v)} />
               </SettingRow>

core/http/react-ui/src/pages/Traces.jsx

@@ -406,7 +406,15 @@ export default function Traces() {
         <button className="btn btn-secondary btn-sm" onClick={fetchTraces}><i className="fas fa-rotate" /> Refresh</button>
         <button className="btn btn-secondary btn-sm" onClick={handleExport} disabled={traces.length === 0}><i className="fas fa-download" /> Export</button>
         <div style={{ flex: 1 }} />
-        <button className="btn btn-danger btn-sm" onClick={handleClear} disabled={traces.length === 0}><i className="fas fa-trash" /> Clear</button>
+        <button
+          className="btn btn-danger btn-sm"
+          onClick={handleClear}
+          /* Stay enabled while loading: a massive in-memory trace buffer is
+             precisely the case where the user can't see the table yet and
+             needs Clear to recover. Clearing an already-empty server-side
+             buffer is a harmless no-op. */
+          disabled={!loading && traces.length === 0}
+        ><i className="fas fa-trash" /> Clear</button>
       </div>
 
       {settings && (() => {
@@ -459,6 +467,17 @@ export default function Traces() {
                   disabled={!settings.enable_tracing}
                 />
               </SettingRow>
+              <SettingRow label="Max Body Bytes" description="Per-field cap for captured bodies and backend trace Data (0 = uncapped). Prevents oversized LLM histories or TTS snippets from locking this page in loading.">
+                <input
+                  className="input"
+                  type="number"
+                  style={{ width: 120 }}
+                  value={settings.tracing_max_body_bytes ?? ''}
+                  onChange={(e) => setSettings(prev => ({ ...prev, tracing_max_body_bytes: parseInt(e.target.value) || 0 }))}
+                  placeholder="65536"
+                  disabled={!settings.enable_tracing}
+                />
+              </SettingRow>
               <SettingRow label="Enable Backend Logging" description="Capture backend process output per model (without requiring debug mode)">
                 <Toggle
                   checked={settings.enable_backend_logging}

core/trace/audio_snippet.go

@@ -16,8 +16,12 @@ const MaxSnippetSeconds = 30
 
 // AudioSnippet captures the first MaxSnippetSeconds of a WAV file and computes
 // quality metrics. The result is a map suitable for merging into a BackendTrace
-// Data field.
-func AudioSnippet(wavPath string) map[string]any {
+// Data field. maxBytes caps the embedded base64 waveform so a single TTS or
+// transcription trace cannot blow past the backend-trace body cap (~1.3 MiB
+// of base64 per 30s of 16 kHz mono int16 PCM otherwise); when the encoded
+// waveform would exceed the cap the audio_wav_base64 field is dropped and
+// the rest of the metrics are returned. maxBytes <= 0 disables the cap.
+func AudioSnippet(wavPath string, maxBytes int) map[string]any {
 	raw, err := os.ReadFile(wavPath)
 	if err != nil {
 		xlog.Warn("audio snippet: read failed", "path", wavPath, "error", err)
@@ -34,12 +38,14 @@ func AudioSnippet(wavPath string) map[string]any {
 		sampleRate = 16000
 	}
 
-	return AudioSnippetFromPCM(pcm, sampleRate, len(pcm))
+	return AudioSnippetFromPCM(pcm, sampleRate, len(pcm), maxBytes)
 }
 
 // AudioSnippetFromPCM builds an audio snippet from raw PCM bytes (int16 LE mono).
-// totalPCMBytes is the full audio size before truncation (used to compute total duration).
-func AudioSnippetFromPCM(pcm []byte, sampleRate int, totalPCMBytes int) map[string]any {
+// totalPCMBytes is the full audio size before truncation (used to compute
+// total duration). maxBytes caps the embedded base64 waveform as described
+// on AudioSnippet.
+func AudioSnippetFromPCM(pcm []byte, sampleRate, totalPCMBytes, maxBytes int) map[string]any {
 	if len(pcm) == 0 || len(pcm)%2 != 0 {
 		return nil
 	}
@@ -89,8 +95,7 @@ func AudioSnippetFromPCM(pcm []byte, sampleRate int, totalPCMBytes int) map[stri
 	}
 	buf.Write(snippetPCM)
 
-	return map[string]any{
-		"audio_wav_base64":  base64.StdEncoding.EncodeToString(buf.Bytes()),
+	out := map[string]any{
 		"audio_duration_s":  math.Round(durationS*100) / 100,
 		"audio_snippet_s":   math.Round(snippetDuration*100) / 100,
 		"audio_sample_rate": sampleRate,
@@ -99,4 +104,15 @@ func AudioSnippetFromPCM(pcm []byte, sampleRate int, totalPCMBytes int) map[stri
 		"audio_peak_dbfs":   math.Round(peakDBFS*10) / 10,
 		"audio_dc_offset":   math.Round(dcOffset*10000) / 10000,
 	}
+	// Skip the embedded waveform when it would dominate the trace payload.
+	// Truncating mid-base64 produces an undecodable string, so the right
+	// move is to drop the field and let the UI render just the metrics.
+	encodedSize := base64.StdEncoding.EncodedLen(buf.Len())
+	if maxBytes <= 0 || encodedSize <= maxBytes {
+		out["audio_wav_base64"] = base64.StdEncoding.EncodeToString(buf.Bytes())
+	} else {
+		xlog.Debug("audio snippet: dropping audio_wav_base64", "encoded_bytes", encodedSize, "max_bytes", maxBytes)
+		out["audio_wav_base64_dropped_bytes"] = encodedSize
+	}
+	return out
 }

core/trace/audio_snippet_test.go

@@ -0,0 +1,49 @@
+package trace_test
+
+import (
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+
+	"github.com/mudler/LocalAI/core/trace"
+)
+
+// One second of mono 16-bit PCM at 16 kHz: 32 KiB raw. After the 44-byte
+// WAV header and base64 encoding the snippet runs ~42 KiB, which is well
+// over the small caps used here and matches the smallest realistic TTS
+// output size.
+const (
+	snippetSampleRate = 16000
+	snippetSeconds    = 1
+)
+
+func makePCM(seconds, sampleRate int) []byte {
+	return make([]byte, seconds*sampleRate*2) // int16 mono
+}
+
+var _ = Describe("AudioSnippetFromPCM byte cap", func() {
+	pcm := makePCM(snippetSeconds, snippetSampleRate)
+	totalPCM := len(pcm)
+
+	It("omits audio_wav_base64 when the encoded snippet would exceed the cap, keeping the metrics", func() {
+		out := trace.AudioSnippetFromPCM(pcm, snippetSampleRate, totalPCM, 1024)
+
+		Expect(out).ToNot(BeNil(), "metrics must still be returned even when the waveform is dropped")
+		Expect(out).ToNot(HaveKey("audio_wav_base64"), "oversized base64 must be dropped so the UI does not try to render invalid audio data")
+		Expect(out).To(HaveKey("audio_duration_s"))
+		Expect(out).To(HaveKey("audio_sample_rate"))
+		Expect(out).To(HaveKey("audio_rms_dbfs"))
+	})
+
+	It("includes audio_wav_base64 when the snippet fits under the cap", func() {
+		out := trace.AudioSnippetFromPCM(pcm, snippetSampleRate, totalPCM, 1024*1024)
+
+		Expect(out).To(HaveKey("audio_wav_base64"))
+		Expect(out["audio_wav_base64"]).ToNot(BeEmpty())
+	})
+
+	It("includes audio_wav_base64 when the cap is disabled (0)", func() {
+		out := trace.AudioSnippetFromPCM(pcm, snippetSampleRate, totalPCM, 0)
+
+		Expect(out).To(HaveKey("audio_wav_base64"))
+	})
+})

core/trace/backend_trace.go

@@ -2,6 +2,7 @@ package trace
 
 import (
 	"encoding/json"
+	"fmt"
 	"slices"
 	"sync"
 	"time"
@@ -49,13 +50,25 @@ var backendMu sync.Mutex
 var backendLogChan = make(chan *BackendTrace, 100)
 var backendInitOnce sync.Once
 
-func InitBackendTracingIfEnabled(maxItems int) {
+// backendMaxBodyBytes caps each captured string value in a BackendTrace.Data
+// field to keep the /api/backend-traces JSON small enough for the admin UI to
+// load on every 5s auto-refresh. Mirrors the API-trace body cap added in
+// commit 61bf34ea: without it a chatty LLM workload (full message history per
+// trace) or any TTS run (~1.3 MiB of audio_wav_base64 per trace) blows the
+// payload past tens of MiB and locks the Traces page in a loading state.
+//
+// 0 disables the cap. Set on the first InitBackendTracingIfEnabled call only,
+// matching the sync.Once-guarded maxItems semantics.
+var backendMaxBodyBytes int
+
+func InitBackendTracingIfEnabled(maxItems, maxBodyBytes int) {
 	backendInitOnce.Do(func() {
 		if maxItems <= 0 {
 			maxItems = 100
 		}
 		backendMu.Lock()
 		backendTraceBuffer = circularbuffer.New[*BackendTrace](maxItems)
+		backendMaxBodyBytes = maxBodyBytes
 		backendMu.Unlock()
 
 		go func() {
@@ -71,6 +84,9 @@ func InitBackendTracingIfEnabled(maxItems int) {
 }
 
 func RecordBackendTrace(t BackendTrace) {
+	if t.Data != nil && backendMaxBodyBytes > 0 {
+		t.Data = capDataStrings(t.Data, backendMaxBodyBytes)
+	}
 	select {
 	case backendLogChan <- &t:
 	default:
@@ -78,6 +94,35 @@ func RecordBackendTrace(t BackendTrace) {
 	}
 }
 
+// capDataStrings walks a trace Data map and replaces any string value (at any
+// depth) that exceeds maxBytes with a fixed-size marker that names the
+// original byte count. The replacement is intentionally short and not valid
+// base64/JSON: the goal is to flag "this was dropped" cheaply, not to keep a
+// partial value that the UI might try to render. Non-string scalars and
+// non-map containers pass through untouched so structural fields like
+// total_deltas or audio_sample_rate remain useful.
+func capDataStrings(data map[string]any, maxBytes int) map[string]any {
+	out := make(map[string]any, len(data))
+	for k, v := range data {
+		out[k] = capValue(v, maxBytes)
+	}
+	return out
+}
+
+func capValue(v any, maxBytes int) any {
+	switch val := v.(type) {
+	case string:
+		if len(val) > maxBytes {
+			return fmt.Sprintf("<truncated: %d bytes>", len(val))
+		}
+		return val
+	case map[string]any:
+		return capDataStrings(val, maxBytes)
+	default:
+		return v
+	}
+}
+
 func GetBackendTraces() []BackendTrace {
 	backendMu.Lock()
 	if backendTraceBuffer == nil {
@@ -136,3 +181,24 @@ func TruncateString(s string, maxLen int) string {
 	}
 	return s[:maxLen] + "..."
 }
+
+// TruncateToBytes caps a string at exactly maxBytes, preserving the leading
+// content and appending a marker so the UI knows the value was clipped.
+// Unlike TruncateString it guarantees output <= maxBytes, which matters for
+// fields that feed back into the trace pipeline: capDataStrings in
+// RecordBackendTrace re-checks size and would otherwise replace a producer's
+// head-preserving truncation with the bare marker, losing the prefix.
+//
+// maxBytes <= 0 disables the cap, matching backendMaxBodyBytes semantics.
+func TruncateToBytes(s string, maxBytes int) string {
+	if maxBytes <= 0 || len(s) <= maxBytes {
+		return s
+	}
+	suffix := fmt.Sprintf("...[truncated, %d bytes]", len(s))
+	if len(suffix) >= maxBytes {
+		// Pathologically small caps can't fit the marker; fall back to a
+		// hard cut so the contract (output <= maxBytes) still holds.
+		return s[:maxBytes]
+	}
+	return s[:maxBytes-len(suffix)] + suffix
+}

core/trace/backend_trace_cap_test.go

@@ -0,0 +1,160 @@
+package trace_test
+
+import (
+	"strings"
+	"time"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+
+	"github.com/mudler/LocalAI/core/trace"
+)
+
+// The /api/backend-traces endpoint ships up to TracingMaxItems entries to the
+// admin Traces UI on every 5s auto-refresh. Without a cap on the per-trace
+// Data field, a chatty agent-pool workload (LLM traces carry the full
+// `messages` array, TTS traces carry ~1.3 MiB of audio_wav_base64) makes the
+// response tens of MiB. The UI then stays in "loading" forever because the
+// download + parse runs longer than the refresh interval: the same symptom
+// the API-trace fix (commit 61bf34ea) addressed on the other side.
+//
+// These specs pin the generic safety net (Option A) so any future producer
+// that stuffs a large string into Data is automatically bounded.
+
+const (
+	smallCap     = 1024
+	smallCapStep = 16
+)
+
+var _ = Describe("RecordBackendTrace Data capping", func() {
+	BeforeEach(func() {
+		// Init is sync.Once so the first test wins; subsequent tests just
+		// clear the buffer. The cap value below has to match the first call.
+		trace.InitBackendTracingIfEnabled(64, smallCap)
+		trace.ClearBackendTraces()
+	})
+
+	It("replaces oversized top-level string values with a truncation marker", func() {
+		oversized := strings.Repeat("x", smallCap*4)
+
+		trace.RecordBackendTrace(trace.BackendTrace{
+			Timestamp: time.Now(),
+			Type:      trace.BackendTraceLLM,
+			ModelName: "m",
+			Data: map[string]any{
+				"messages": oversized,
+				"small":    "fits",
+			},
+		})
+
+		Eventually(trace.GetBackendTraces).Should(HaveLen(1))
+		got := trace.GetBackendTraces()[0]
+
+		Expect(got.Data["small"]).To(Equal("fits"), "fields under the cap must pass through untouched")
+
+		// The marker is the contract the UI reads to show truncation; the
+		// concrete shape can evolve but it must be a short fixed-size string
+		// that encodes the original byte count so users know what was dropped.
+		msg, ok := got.Data["messages"].(string)
+		Expect(ok).To(BeTrue(), "string fields stay strings after capping")
+		Expect(len(msg)).To(BeNumerically("<", smallCap), "capped value must fit under the configured cap")
+		Expect(msg).To(ContainSubstring("truncated"))
+		Expect(msg).To(ContainSubstring("4096"), "marker should reference the original byte count for diagnostics")
+	})
+
+	It("recurses into nested maps so deeply nested oversized strings are also bounded", func() {
+		oversized := strings.Repeat("y", smallCap*2)
+
+		trace.RecordBackendTrace(trace.BackendTrace{
+			Timestamp: time.Now(),
+			Type:      trace.BackendTraceLLM,
+			ModelName: "m",
+			Data: map[string]any{
+				"chat_deltas": map[string]any{
+					"content":         oversized,
+					"total_deltas":    5,
+					"tool_call_count": 0,
+				},
+			},
+		})
+
+		Eventually(trace.GetBackendTraces).Should(HaveLen(1))
+		got := trace.GetBackendTraces()[0]
+
+		deltas, ok := got.Data["chat_deltas"].(map[string]any)
+		Expect(ok).To(BeTrue(), "nested map structure must be preserved")
+		Expect(deltas["total_deltas"]).To(Equal(5), "non-string siblings must pass through untouched")
+
+		content, ok := deltas["content"].(string)
+		Expect(ok).To(BeTrue())
+		Expect(len(content)).To(BeNumerically("<", smallCap), "nested oversized string must still be capped")
+		Expect(content).To(ContainSubstring("truncated"))
+	})
+
+	It("leaves values within the cap untouched", func() {
+		smallVal := strings.Repeat("z", smallCap-smallCapStep)
+
+		trace.RecordBackendTrace(trace.BackendTrace{
+			Timestamp: time.Now(),
+			Type:      trace.BackendTraceEmbedding,
+			ModelName: "m",
+			Data: map[string]any{
+				"input_text": smallVal,
+			},
+		})
+
+		Eventually(trace.GetBackendTraces).Should(HaveLen(1))
+		got := trace.GetBackendTraces()[0]
+
+		Expect(got.Data["input_text"]).To(Equal(smallVal))
+	})
+
+	It("does not re-truncate values that producers already capped with TruncateToBytes", func() {
+		// Producers (LLM messages/response, etc.) prefer head-preserving
+		// truncation so users can still read the start of the conversation.
+		// TruncateToBytes guarantees output <= cap, so the generic safety
+		// net below must leave it alone, otherwise the kept prefix gets
+		// thrown away and replaced with the marker.
+		preTruncated := trace.TruncateToBytes(strings.Repeat("a", smallCap*4), smallCap)
+		Expect(len(preTruncated)).To(BeNumerically("<=", smallCap))
+
+		trace.RecordBackendTrace(trace.BackendTrace{
+			Timestamp: time.Now(),
+			Type:      trace.BackendTraceLLM,
+			ModelName: "m",
+			Data: map[string]any{
+				"messages": preTruncated,
+			},
+		})
+
+		Eventually(trace.GetBackendTraces).Should(HaveLen(1))
+		got := trace.GetBackendTraces()[0]
+		Expect(got.Data["messages"]).To(Equal(preTruncated))
+	})
+})
+
+var _ = Describe("TruncateToBytes", func() {
+	It("returns the input unchanged when it fits", func() {
+		Expect(trace.TruncateToBytes("hello", 1024)).To(Equal("hello"))
+	})
+
+	It("treats maxBytes <= 0 as unlimited", func() {
+		Expect(trace.TruncateToBytes("hello", 0)).To(Equal("hello"))
+		Expect(trace.TruncateToBytes("hello", -1)).To(Equal("hello"))
+	})
+
+	It("caps oversized input to at most maxBytes and preserves the head", func() {
+		in := strings.Repeat("a", 5000)
+		out := trace.TruncateToBytes(in, 100)
+		Expect(len(out)).To(BeNumerically("<=", 100), "output must never exceed the cap so the generic Record-time safety net doesn't fire")
+		Expect(out).To(HavePrefix("a"), "should keep the leading content readable")
+		Expect(out).To(ContainSubstring("truncated"), "should mark the value as truncated for the UI")
+	})
+
+	It("falls back to plain truncation when the cap is smaller than the suffix", func() {
+		in := strings.Repeat("a", 100)
+		out := trace.TruncateToBytes(in, 4)
+		Expect(len(out)).To(Equal(4))
+		Expect(out).To(Equal("aaaa"))
+	})
+})

core/trace/trace_suite_test.go

@@ -0,0 +1,13 @@
+package trace_test
+
+import (
+	"testing"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+func TestTrace(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "Trace test suite")
+}

go.mod

@@ -13,7 +13,7 @@ require (
 	github.com/aws/aws-sdk-go-v2/credentials v1.19.15
 	github.com/aws/aws-sdk-go-v2/service/s3 v1.99.1
 	github.com/charmbracelet/glamour v1.0.0
-	github.com/containerd/containerd v1.7.32
+	github.com/containerd/containerd v1.7.31
 	github.com/coreos/go-oidc/v3 v3.18.0
 	github.com/dhowden/tag v0.0.0-20240417053706-3d75831295e8
 	github.com/ebitengine/purego v0.10.0
@@ -104,28 +104,28 @@ require (
 	github.com/dunglas/httpsfv v1.1.0 // indirect
 	github.com/filecoin-project/go-clock v0.1.0 // indirect
 	github.com/go-jose/go-jose/v4 v4.1.4 // indirect
-	github.com/go-openapi/analysis v0.24.3 // indirect
-	github.com/go-openapi/errors v0.22.7 // indirect
-	github.com/go-openapi/loads v0.23.3 // indirect
-	github.com/go-openapi/runtime v0.29.3 // indirect
-	github.com/go-openapi/strfmt v0.26.1 // indirect
-	github.com/go-openapi/swag/cmdutils v0.25.5 // indirect
-	github.com/go-openapi/swag/conv v0.25.5 // indirect
-	github.com/go-openapi/swag/fileutils v0.25.5 // indirect
-	github.com/go-openapi/swag/jsonname v0.25.5 // indirect
-	github.com/go-openapi/swag/jsonutils v0.25.5 // indirect
-	github.com/go-openapi/swag/loading v0.25.5 // indirect
-	github.com/go-openapi/swag/mangling v0.25.5 // indirect
-	github.com/go-openapi/swag/netutils v0.25.5 // indirect
-	github.com/go-openapi/swag/stringutils v0.25.5 // indirect
-	github.com/go-openapi/swag/typeutils v0.25.5 // indirect
-	github.com/go-openapi/swag/yamlutils v0.25.5 // indirect
-	github.com/go-openapi/validate v0.25.2 // indirect
-	github.com/go-viper/mapstructure/v2 v2.5.0 // indirect
+	github.com/go-openapi/analysis v0.24.1 // indirect
+	github.com/go-openapi/errors v0.22.4 // indirect
+	github.com/go-openapi/loads v0.23.2 // indirect
+	github.com/go-openapi/runtime v0.29.2 // indirect
+	github.com/go-openapi/strfmt v0.25.0 // indirect
+	github.com/go-openapi/swag/cmdutils v0.25.4 // indirect
+	github.com/go-openapi/swag/conv v0.25.4 // indirect
+	github.com/go-openapi/swag/fileutils v0.25.4 // indirect
+	github.com/go-openapi/swag/jsonname v0.25.4 // indirect
+	github.com/go-openapi/swag/jsonutils v0.25.4 // indirect
+	github.com/go-openapi/swag/loading v0.25.4 // indirect
+	github.com/go-openapi/swag/mangling v0.25.4 // indirect
+	github.com/go-openapi/swag/netutils v0.25.4 // indirect
+	github.com/go-openapi/swag/stringutils v0.25.4 // indirect
+	github.com/go-openapi/swag/typeutils v0.25.4 // indirect
+	github.com/go-openapi/swag/yamlutils v0.25.4 // indirect
+	github.com/go-openapi/validate v0.25.1 // indirect
+	github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
 	github.com/google/certificate-transparency-go v1.3.2 // indirect
 	github.com/grpc-ecosystem/grpc-gateway/v2 v2.27.7 // indirect
 	github.com/in-toto/attestation v1.1.2 // indirect
-	github.com/in-toto/in-toto-golang v0.11.0 // indirect
+	github.com/in-toto/in-toto-golang v0.9.0 // indirect
 	github.com/invopop/jsonschema v0.13.0 // indirect
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
@@ -136,25 +136,26 @@ require (
 	github.com/moby/moby/client v0.4.0 // indirect
 	github.com/nats-io/nkeys v0.4.15 // indirect
 	github.com/nats-io/nuid v1.0.1 // indirect
-	github.com/oklog/ulid/v2 v2.1.1 // indirect
-	github.com/secure-systems-lab/go-securesystemslib v0.10.0 // indirect
+	github.com/oklog/ulid v1.3.1 // indirect
+	github.com/secure-systems-lab/go-securesystemslib v0.9.1 // indirect
 	github.com/shibumi/go-pathspec v1.3.0 // indirect
 	github.com/sigstore/protobuf-specs v0.5.1 // indirect
-	github.com/sigstore/rekor v1.5.0 // indirect
+	github.com/sigstore/rekor v1.4.3 // indirect
 	github.com/sigstore/rekor-tiles/v2 v2.0.1 // indirect
-	github.com/sigstore/sigstore v1.10.5 // indirect
-	github.com/sigstore/timestamp-authority/v2 v2.0.6 // indirect
+	github.com/sigstore/sigstore v1.10.0 // indirect
+	github.com/sigstore/timestamp-authority/v2 v2.0.3 // indirect
 	github.com/standard-webhooks/standard-webhooks/libraries v0.0.0-20260508151727-1282bb917829 // indirect
 	github.com/stretchr/testify v1.11.1 // indirect
 	github.com/sv-tools/openapi v0.2.1 // indirect
 	github.com/swaggo/swag/v2 v2.0.0-rc4 // indirect
 	github.com/tetratelabs/wazero v1.11.0 // indirect
-	github.com/theupdateframework/go-tuf/v2 v2.4.1 // indirect
+	github.com/theupdateframework/go-tuf/v2 v2.3.0 // indirect
 	github.com/tmc/langchaingo v0.1.14 // indirect
 	github.com/transparency-dev/formats v0.0.0-20251017110053-404c0d5b696c // indirect
 	github.com/transparency-dev/merkle v0.0.2 // indirect
 	github.com/wk8/go-ordered-map/v2 v2.1.8 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20260316180232-0b37fe3546d5 // indirect
+	go.mongodb.org/mongo-driver v1.17.6 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20260128011058-8636f8732409 // indirect
 	sigs.k8s.io/yaml v1.6.0 // indirect
 )
 
@@ -198,7 +199,7 @@ require (
 	github.com/eritikass/githubmarkdownconvertergo v0.1.10 // indirect
 	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
 	github.com/go-git/go-billy/v5 v5.9.0 // indirect
-	github.com/go-git/go-git/v5 v5.19.1 // indirect
+	github.com/go-git/go-git/v5 v5.19.0 // indirect
 	github.com/go-telegram/bot v1.17.0 // indirect
 	github.com/gobwas/glob v0.2.3 // indirect
 	github.com/gocolly/colly v1.2.0 // indirect
@@ -231,7 +232,7 @@ require (
 	github.com/segmentio/encoding v0.5.4 // indirect
 	github.com/sergi/go-diff v1.4.0 // indirect
 	github.com/skeema/knownhosts v1.3.1 // indirect
-	github.com/slack-go/slack v0.23.1 // indirect
+	github.com/slack-go/slack v0.17.3 // indirect
 	github.com/ssor/bom v0.0.0-20170718123548-6386211fdfcf // indirect
 	github.com/swaggo/files/v2 v2.0.2 // indirect
 	github.com/temoto/robotstxt v1.1.2 // indirect
@@ -332,7 +333,7 @@ require (
 	golang.org/x/net v0.53.0 // indirect; indirect (for websocket)
 	golang.org/x/oauth2 v0.36.0
 	golang.org/x/telemetry v0.0.0-20260409153401-be6f6cb8b1fa // indirect
-	golang.org/x/time v0.15.0 // indirect
+	golang.org/x/time v0.14.0 // indirect
 )
 
 require (
@@ -373,10 +374,10 @@ require (
 	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-ole/go-ole v1.3.0 // indirect
-	github.com/go-openapi/jsonpointer v0.22.5 // indirect
-	github.com/go-openapi/jsonreference v0.21.5 // indirect
-	github.com/go-openapi/spec v0.22.4 // indirect
-	github.com/go-openapi/swag v0.25.5 // indirect
+	github.com/go-openapi/jsonpointer v0.22.1 // indirect
+	github.com/go-openapi/jsonreference v0.21.3 // indirect
+	github.com/go-openapi/spec v0.22.1 // indirect
+	github.com/go-openapi/swag v0.25.4 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect
 	github.com/golang/snappy v0.0.5-0.20231225225746-43d5d4cd4e0e // indirect
@@ -504,7 +505,7 @@ require (
 	golang.zx2c4.com/wireguard v0.0.0-20250521234502-f333402bd9cb // indirect
 	golang.zx2c4.com/wireguard/windows v0.5.3 // indirect
 	gonum.org/v1/gonum v0.17.0 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20260316180232-0b37fe3546d5 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20260128011058-8636f8732409 // indirect
 	gopkg.in/fsnotify.v1 v1.4.7 // indirect
 	gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 // indirect
 	howett.net/plist v1.0.2-0.20250314012144-ee69052608d9 // indirect

go.sum

@@ -18,10 +18,10 @@ cloud.google.com/go v0.74.0/go.mod h1:VV1xSbzvo+9QJOxLDaJfTjx5e+MePCpCWwvftOeQmW
 cloud.google.com/go v0.78.0/go.mod h1:QjdrLG0uq+YwhjoVOLsS1t7TW8fs36kLs4XO5R5ECHg=
 cloud.google.com/go v0.79.0/go.mod h1:3bzgcEeQlzbuEAYu4mrWhKqWjmpprinYgKJLgKHnbb8=
 cloud.google.com/go v0.81.0/go.mod h1:mk/AM35KwGk/Nm2YSeZbxXdrNK3KZOYHmLkOqC2V6E0=
-cloud.google.com/go v0.123.0 h1:2NAUJwPR47q+E35uaJeYoNhuNEM9kM8SjgRgdeOJUSE=
-cloud.google.com/go v0.123.0/go.mod h1:xBoMV08QcqUGuPW65Qfm1o9Y4zKZBpGS+7bImXLTAZU=
-cloud.google.com/go/auth v0.18.2 h1:+Nbt5Ev0xEqxlNjd6c+yYUeosQ5TtEUaNcN/3FozlaM=
-cloud.google.com/go/auth v0.18.2/go.mod h1:xD+oY7gcahcu7G2SG2DsBerfFxgPAJz17zz2joOFF3M=
+cloud.google.com/go v0.121.6 h1:waZiuajrI28iAf40cWgycWNgaXPO06dupuS+sgibK6c=
+cloud.google.com/go v0.121.6/go.mod h1:coChdst4Ea5vUpiALcYKXEpR1S9ZgXbhEzzMcMR66vI=
+cloud.google.com/go/auth v0.17.0 h1:74yCm7hCj2rUyyAocqnFzsAYXgJhrG26XCFimrc/Kz4=
+cloud.google.com/go/auth v0.17.0/go.mod h1:6wv/t5/6rOPAX4fJiRjKkJCvswLwdet7G8+UGXt7nCQ=
 cloud.google.com/go/auth/oauth2adapt v0.2.8 h1:keo8NaayQZ6wimpNSmW5OPc283g65QNIiLpZnkHRbnc=
 cloud.google.com/go/auth/oauth2adapt v0.2.8/go.mod h1:XQ9y31RkqZCcwJWNSx2Xvric3RrU88hAYYbjDWYDL+c=
 cloud.google.com/go/bigquery v1.0.1/go.mod h1:i/xbL2UlR5RvWAURpBYZTtm/cXjCha9lbfbpx4poX+o=
@@ -37,10 +37,10 @@ cloud.google.com/go/datastore v1.1.0/go.mod h1:umbIZjpQpHh4hmRpGhH4tLFup+FVzqBi1
 cloud.google.com/go/firestore v1.1.0/go.mod h1:ulACoGHTpvq5r8rxGJ4ddJZBZqakUQqClKRT5SZwBmk=
 cloud.google.com/go/iam v1.5.3 h1:+vMINPiDF2ognBJ97ABAYYwRgsaqxPbQDlMnbHMjolc=
 cloud.google.com/go/iam v1.5.3/go.mod h1:MR3v9oLkZCTlaqljW6Eb2d3HGDGK5/bDv93jhfISFvU=
-cloud.google.com/go/kms v1.26.0 h1:cK9mN2cf+9V63D3H1f6koxTatWy39aTI/hCjz1I+adU=
-cloud.google.com/go/kms v1.26.0/go.mod h1:pHKOdFJm63hxBsiPkYtowZPltu9dW0MWvBa6IA4HM58=
-cloud.google.com/go/longrunning v0.8.0 h1:LiKK77J3bx5gDLi4SMViHixjD2ohlkwBi+mKA7EhfW8=
-cloud.google.com/go/longrunning v0.8.0/go.mod h1:UmErU2Onzi+fKDg2gR7dusz11Pe26aknR4kHmJJqIfk=
+cloud.google.com/go/kms v1.23.2 h1:4IYDQL5hG4L+HzJBhzejUySoUOheh3Lk5YT4PCyyW6k=
+cloud.google.com/go/kms v1.23.2/go.mod h1:rZ5kK0I7Kn9W4erhYVoIRPtpizjunlrfU4fUkumUp8g=
+cloud.google.com/go/longrunning v0.6.7 h1:IGtfDWHhQCgCjwQjV9iiLnUta9LBCo8R9QmAFsS/PrE=
+cloud.google.com/go/longrunning v0.6.7/go.mod h1:EAFV3IZAKmM56TyiE6VAP3VoTzhZzySwI/YI1s/nRsY=
 cloud.google.com/go/pubsub v1.0.1/go.mod h1:R0Gpsv3s54REJCy4fxDixWD93lHJMoZTyQ2kNxGRt3I=
 cloud.google.com/go/pubsub v1.1.0/go.mod h1:EwwdRX2sKPjnvnqCa270oGRyludottCI76h+R3AArQw=
 cloud.google.com/go/pubsub v1.2.0/go.mod h1:jhfEVHT8odbXTkndysNHCcx0awwzvfOlguIAii9o8iA=
@@ -55,8 +55,8 @@ dario.cat/mergo v1.0.2/go.mod h1:E/hbnu0NxMFBjpMIE34DRGLWqDy0g5FuKDhCb31ngxA=
 dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
 filippo.io/bigmod v0.1.1-0.20260103110540-f8a47775ebe5 h1:JA0fFr+kxpqTdxR9LOBiTWpGNchqmkcsgmdeJZRclZ0=
 filippo.io/bigmod v0.1.1-0.20260103110540-f8a47775ebe5/go.mod h1:OjOXDNlClLblvXdwgFFOQFJEocLhhtai8vGLy0JCZlI=
-filippo.io/edwards25519 v1.2.0 h1:crnVqOiS4jqYleHd9vaKZ+HKtHfllngJIiOpNpoJsjo=
-filippo.io/edwards25519 v1.2.0/go.mod h1:xzAOLCNug/yB62zG1bQ8uziwrIqIuxhctzJT18Q77mc=
+filippo.io/edwards25519 v1.1.0 h1:FNf4tywRC1HmFuKW5xopWpigGjJKiJSV0Cqo0cJWDaA=
+filippo.io/edwards25519 v1.1.0/go.mod h1:BxyFTGdWcka3PhytdK4V28tE5sGfRvvvRV7EaN4VDT4=
 filippo.io/keygen v0.0.0-20260114151900-8e2790ea4c5b h1:REI1FbdW71yO56Are4XAxD+OS/e+BQsB3gE4mZRQEXY=
 filippo.io/keygen v0.0.0-20260114151900-8e2790ea4c5b/go.mod h1:9nnw1SlYHYuPSo/3wjQzNjSbeHlq2NsKo5iEtfJPWP0=
 fyne.io/fyne/v2 v2.7.3 h1:xBT/iYbdnNHONWO38fZMBrVBiJG8rV/Jypmy4tVfRWE=
@@ -67,8 +67,8 @@ github.com/AdaLogics/go-fuzz-headers v0.0.0-20240806141605-e8a1dd7889d6 h1:He8af
 github.com/AdaLogics/go-fuzz-headers v0.0.0-20240806141605-e8a1dd7889d6/go.mod h1:8o94RPi1/7XTJvwPpRSzSUedZrtlirdB3r9Z20bi2f8=
 github.com/AdamKorcz/go-fuzz-headers-1 v0.0.0-20230919221257-8b5d3ce2d11d h1:zjqpY4C7H15HjRPEenkS4SAn3Jy2eRRjkjZbGR30TOg=
 github.com/AdamKorcz/go-fuzz-headers-1 v0.0.0-20230919221257-8b5d3ce2d11d/go.mod h1:XNqJ7hv2kY++g8XEHREpi+JqZo3+0l+CH2egBVN4yqM=
-github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0 h1:fou+2+WFTib47nS+nz/ozhEBnvU96bKHy6LjRsY4E28=
-github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0/go.mod h1:t76Ruy8AHvUAC8GfMWJMa0ElSbuIcO03NLpynfbgsPA=
+github.com/Azure/azure-sdk-for-go/sdk/azcore v1.20.0 h1:JXg2dwJUmPB9JmtVmdEB16APJ7jurfbY5jnfXpJoRMc=
+github.com/Azure/azure-sdk-for-go/sdk/azcore v1.20.0/go.mod h1:YD5h/ldMsG0XiIw7PdyNhLxaM317eFh5yNLccNfGdyw=
 github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.1 h1:Hk5QBxZQC1jb2Fwj6mpzme37xbCDdNTxU7O9eb5+LB4=
 github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.1/go.mod h1:IYus9qsFobWIc2YVwe/WPjcnyCkPKtnHAqUYeebc8z0=
 github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2 h1:9iefClla7iYpfYWdzPCRDozdmndjTm8DXdpCzPajMgA=
@@ -168,8 +168,8 @@ github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.22 h1:PUmZeJU6
 github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.22/go.mod h1:nO6egFBoAaoXze24a2C0NjQCvdpk8OueRoYimvEB9jo=
 github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.22 h1:SE+aQ4DEqG53RRCAIHlCf//B2ycxGH7jFkpnAh/kKPM=
 github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.22/go.mod h1:ES3ynECd7fYeJIL6+oax+uIEljmfps0S70BaQzbMd/o=
-github.com/aws/aws-sdk-go-v2/service/kms v1.50.3 h1:s/zDSG/a/Su9aX+v0Ld9cimUCdkr5FWPmBV8owaEbZY=
-github.com/aws/aws-sdk-go-v2/service/kms v1.50.3/go.mod h1:/iSgiUor15ZuxFGQSTf3lA2FmKxFsQoc2tADOarQBSw=
+github.com/aws/aws-sdk-go-v2/service/kms v1.48.2 h1:aL8Y/AbB6I+uw0MjLbdo68NQ8t5lNs3CY3S848HpETk=
+github.com/aws/aws-sdk-go-v2/service/kms v1.48.2/go.mod h1:VJcNH6BLr+3VJwinRKdotLOMglHO8mIKlD3ea5c7hbw=
 github.com/aws/aws-sdk-go-v2/service/s3 v1.99.1 h1:kU/eBN5+MWNo/LcbNa4hWDdN76hdcd7hocU5kvu7IsU=
 github.com/aws/aws-sdk-go-v2/service/s3 v1.99.1/go.mod h1:Fw9aqhJicIVee1VytBBjH+l+5ov6/PhbtIK/u3rt/ls=
 github.com/aws/aws-sdk-go-v2/service/signin v1.0.10 h1:a1Fq/KXn75wSzoJaPQTgZO0wHGqE9mjFnylnqEPTchA=
@@ -284,8 +284,8 @@ github.com/codahale/rfc6979 v0.0.0-20141003034818-6a90f24967eb h1:EDmT6Q9Zs+SbUo
 github.com/codahale/rfc6979 v0.0.0-20141003034818-6a90f24967eb/go.mod h1:ZjrT6AXHbDs86ZSdt/osfBi5qfexBrKUdONk989Wnk4=
 github.com/containerd/cgroups v1.1.0 h1:v8rEWFl6EoqHB+swVNjVoCJE8o3jX7e8nqBGPLaDFBM=
 github.com/containerd/cgroups v1.1.0/go.mod h1:6ppBcbh/NOOUU+dMKrykgaBnK9lCIBxHqJDGwsa1mIw=
-github.com/containerd/containerd v1.7.32 h1:S54xuVcPxeLaYgaRABtpJ2VyVUVsy0IGf7qHBs+sbY8=
-github.com/containerd/containerd v1.7.32/go.mod h1:jdwD6s/BhV4XVJGrvtziNPVA+83n66TwptVaPKprq4E=
+github.com/containerd/containerd v1.7.31 h1:jn3IMuTV4Bb1Uwb0MFPW2ASJAD3W1lh6QqqZHIZwDh4=
+github.com/containerd/containerd v1.7.31/go.mod h1:jdwD6s/BhV4XVJGrvtziNPVA+83n66TwptVaPKprq4E=
 github.com/containerd/continuity v0.4.4 h1:/fNVfTJ7wIl/YPMHjf+5H32uFhl63JucB34PlCpMKII=
 github.com/containerd/continuity v0.4.4/go.mod h1:/lNJvtJKUQStBzpVQ1+rasXO1LAWtUQssk28EZvJ3nE=
 github.com/containerd/errdefs v1.0.0 h1:tg5yIfIlQIrxYtu9ajqY42W3lpS19XqdxRQeEwYG8PI=
@@ -423,16 +423,17 @@ github.com/go-audio/riff v1.0.0 h1:d8iCGbDvox9BfLagY94fBynxSPHO80LmZCaOsmKxokA=
 github.com/go-audio/riff v1.0.0/go.mod h1:l3cQwc85y79NQFCRB7TiPoNiaijp6q8Z0Uv38rVG498=
 github.com/go-audio/wav v1.1.0 h1:jQgLtbqBzY7G+BM8fXF7AHUk1uHUviWS4X39d5rsL2g=
 github.com/go-audio/wav v1.1.0/go.mod h1:mpe9qfwbScEbkd8uybLuIpTgHyrISw/OTuvjUW2iGtE=
-github.com/go-chi/chi/v5 v5.2.5 h1:Eg4myHZBjyvJmAFjFvWgrqDTXFyOzjj7YIm3L3mu6Ug=
-github.com/go-chi/chi/v5 v5.2.5/go.mod h1:X7Gx4mteadT3eDOMTsXzmI4/rwUpOwBHLpAfupzFJP0=
+github.com/go-chi/chi v4.1.2+incompatible h1:fGFk2Gmi/YKXk0OmGfBh0WgmN3XB8lVnEyNz34tQRec=
+github.com/go-chi/chi/v5 v5.2.3 h1:WQIt9uxdsAbgIYgid+BpYc+liqQZGMHRaUwp0JUcvdE=
+github.com/go-chi/chi/v5 v5.2.3/go.mod h1:L2yAIGWB3H+phAw1NxKwWM+7eUH/lU8pOMm5hHcoops=
 github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 h1:+zs/tPmkDkHx3U66DAb0lQFJrpS6731Oaa12ikc+DiI=
 github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376/go.mod h1:an3vInlBmSxCcxctByoQdvwPiA7DTK7jaaFDBTtu0ic=
 github.com/go-git/go-billy/v5 v5.9.0 h1:jItGXszUDRtR/AlferWPTMN4j38BQ88XnXKbilmmBPA=
 github.com/go-git/go-billy/v5 v5.9.0/go.mod h1:jCnQMLj9eUgGU7+ludSTYoZL/GGmii14RxKFj7ROgHw=
 github.com/go-git/go-git-fixtures/v4 v4.3.2-0.20231010084843-55a94097c399 h1:eMje31YglSBqCdIqdhKBW8lokaMrL3uTkpGYlE2OOT4=
 github.com/go-git/go-git-fixtures/v4 v4.3.2-0.20231010084843-55a94097c399/go.mod h1:1OCfN199q1Jm3HZlxleg+Dw/mwps2Wbk9frAWm+4FII=
-github.com/go-git/go-git/v5 v5.19.1 h1:nX27AnaU43/K5bKktKwgBmR9lawoYVe1Ckg0rgzzN00=
-github.com/go-git/go-git/v5 v5.19.1/go.mod h1:Pb1v0c7/g8aGQJwx9Us09W85yGoyvSwuhEGMH7zjDKQ=
+github.com/go-git/go-git/v5 v5.19.0 h1:+WkVUQZSy/F1Gb13udrMKjIM2PrzsNfDKFSfo5tkMtc=
+github.com/go-git/go-git/v5 v5.19.0/go.mod h1:Pb1v0c7/g8aGQJwx9Us09W85yGoyvSwuhEGMH7zjDKQ=
 github.com/go-gl/gl v0.0.0-20231021071112-07e5d0ea2e71 h1:5BVwOaUSBTlVZowGO6VZGw2H/zl9nrd3eCZfYV+NfQA=
 github.com/go-gl/gl v0.0.0-20231021071112-07e5d0ea2e71/go.mod h1:9YTyiznxEY1fVinfM7RvRcjRHbw2xLBJ3AAGIT0I4Nw=
 github.com/go-gl/glfw v0.0.0-20190409004039-e6da0acd62b1/go.mod h1:vR7hzQXu2zJy9AVAgeJqvqgH9Q5CA+iKCZ2gyEVpxRU=
@@ -450,54 +451,54 @@ github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre
 github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0=
 github.com/go-ole/go-ole v1.3.0 h1:Dt6ye7+vXGIKZ7Xtk4s6/xVdGDQynvom7xCFEdWr6uE=
 github.com/go-ole/go-ole v1.3.0/go.mod h1:5LS6F96DhAwUc7C+1HLexzMXY1xGRSryjyPPKW6zv78=
-github.com/go-openapi/analysis v0.24.3 h1:a1hrvMr8X0Xt69KP5uVTu5jH62DscmDifrLzNglAayk=
-github.com/go-openapi/analysis v0.24.3/go.mod h1:Nc+dWJ/FxZbhSow5Yh3ozg5CLJioB+XXT6MdLvJUsUw=
-github.com/go-openapi/errors v0.22.7 h1:JLFBGC0Apwdzw3484MmBqspjPbwa2SHvpDm0u5aGhUA=
-github.com/go-openapi/errors v0.22.7/go.mod h1://QW6SD9OsWtH6gHllUCddOXDL0tk0ZGNYHwsw4sW3w=
-github.com/go-openapi/jsonpointer v0.22.5 h1:8on/0Yp4uTb9f4XvTrM2+1CPrV05QPZXu+rvu2o9jcA=
-github.com/go-openapi/jsonpointer v0.22.5/go.mod h1:gyUR3sCvGSWchA2sUBJGluYMbe1zazrYWIkWPjjMUY0=
-github.com/go-openapi/jsonreference v0.21.5 h1:6uCGVXU/aNF13AQNggxfysJ+5ZcU4nEAe+pJyVWRdiE=
-github.com/go-openapi/jsonreference v0.21.5/go.mod h1:u25Bw85sX4E2jzFodh1FOKMTZLcfifd1Q+iKKOUxExw=
-github.com/go-openapi/loads v0.23.3 h1:g5Xap1JfwKkUnZdn+S0L3SzBDpcTIYzZ5Qaag0YDkKQ=
-github.com/go-openapi/loads v0.23.3/go.mod h1:NOH07zLajXo8y55hom0omlHWDVVvCwBM/S+csCK8LqA=
-github.com/go-openapi/runtime v0.29.3 h1:h5twGaEqxtQg40ePiYm9vFFH1q06Czd7Ot6ufdK0w/Y=
-github.com/go-openapi/runtime v0.29.3/go.mod h1:8A1W0/L5eyNJvKciqZtvIVQvYO66NlB7INMSZ9bw/oI=
-github.com/go-openapi/spec v0.22.4 h1:4pxGjipMKu0FzFiu/DPwN3CTBRlVM2yLf/YTWorYfDQ=
-github.com/go-openapi/spec v0.22.4/go.mod h1:WQ6Ai0VPWMZgMT4XySjlRIE6GP1bGQOtEThn3gcWLtQ=
-github.com/go-openapi/strfmt v0.26.1 h1:7zGCHji7zSYDC2tCXIusoxYQz/48jAf2q+sF6wXTG+c=
-github.com/go-openapi/strfmt v0.26.1/go.mod h1:Zslk5VZPOISLwmWTMBIS7oiVFem1o1EI6zULY8Uer7Y=
-github.com/go-openapi/swag v0.25.5 h1:pNkwbUEeGwMtcgxDr+2GBPAk4kT+kJ+AaB+TMKAg+TU=
-github.com/go-openapi/swag v0.25.5/go.mod h1:B3RT6l8q7X803JRxa2e59tHOiZlX1t8viplOcs9CwTA=
-github.com/go-openapi/swag/cmdutils v0.25.5 h1:yh5hHrpgsw4NwM9KAEtaDTXILYzdXh/I8Whhx9hKj7c=
-github.com/go-openapi/swag/cmdutils v0.25.5/go.mod h1:pdae/AFo6WxLl5L0rq87eRzVPm/XRHM3MoYgRMvG4A0=
-github.com/go-openapi/swag/conv v0.25.5 h1:wAXBYEXJjoKwE5+vc9YHhpQOFj2JYBMF2DUi+tGu97g=
-github.com/go-openapi/swag/conv v0.25.5/go.mod h1:CuJ1eWvh1c4ORKx7unQnFGyvBbNlRKbnRyAvDvzWA4k=
-github.com/go-openapi/swag/fileutils v0.25.5 h1:B6JTdOcs2c0dBIs9HnkyTW+5gC+8NIhVBUwERkFhMWk=
-github.com/go-openapi/swag/fileutils v0.25.5/go.mod h1:V3cT9UdMQIaH4WiTrUc9EPtVA4txS0TOmRURmhGF4kc=
-github.com/go-openapi/swag/jsonname v0.25.5 h1:8p150i44rv/Drip4vWI3kGi9+4W9TdI3US3uUYSFhSo=
-github.com/go-openapi/swag/jsonname v0.25.5/go.mod h1:jNqqikyiAK56uS7n8sLkdaNY/uq6+D2m2LANat09pKU=
-github.com/go-openapi/swag/jsonutils v0.25.5 h1:XUZF8awQr75MXeC+/iaw5usY/iM7nXPDwdG3Jbl9vYo=
-github.com/go-openapi/swag/jsonutils v0.25.5/go.mod h1:48FXUaz8YsDAA9s5AnaUvAmry1UcLcNVWUjY42XkrN4=
-github.com/go-openapi/swag/jsonutils/fixtures_test v0.25.5 h1:SX6sE4FrGb4sEnnxbFL/25yZBb5Hcg1inLeErd86Y1U=
-github.com/go-openapi/swag/jsonutils/fixtures_test v0.25.5/go.mod h1:/2KvOTrKWjVA5Xli3DZWdMCZDzz3uV/T7bXwrKWPquo=
-github.com/go-openapi/swag/loading v0.25.5 h1:odQ/umlIZ1ZVRteI6ckSrvP6e2w9UTF5qgNdemJHjuU=
-github.com/go-openapi/swag/loading v0.25.5/go.mod h1:I8A8RaaQ4DApxhPSWLNYWh9NvmX2YKMoB9nwvv6oW6g=
-github.com/go-openapi/swag/mangling v0.25.5 h1:hyrnvbQRS7vKePQPHHDso+k6CGn5ZBs5232UqWZmJZw=
-github.com/go-openapi/swag/mangling v0.25.5/go.mod h1:6hadXM/o312N/h98RwByLg088U61TPGiltQn71Iw0NY=
-github.com/go-openapi/swag/netutils v0.25.5 h1:LZq2Xc2QI8+7838elRAaPCeqJnHODfSyOa7ZGfxDKlU=
-github.com/go-openapi/swag/netutils v0.25.5/go.mod h1:lHbtmj4m57APG/8H7ZcMMSWzNqIQcu0RFiXrPUara14=
-github.com/go-openapi/swag/stringutils v0.25.5 h1:NVkoDOA8YBgtAR/zvCx5rhJKtZF3IzXcDdwOsYzrB6M=
-github.com/go-openapi/swag/stringutils v0.25.5/go.mod h1:PKK8EZdu4QJq8iezt17HM8RXnLAzY7gW0O1KKarrZII=
-github.com/go-openapi/swag/typeutils v0.25.5 h1:EFJ+PCga2HfHGdo8s8VJXEVbeXRCYwzzr9u4rJk7L7E=
-github.com/go-openapi/swag/typeutils v0.25.5/go.mod h1:itmFmScAYE1bSD8C4rS0W+0InZUBrB2xSPbWt6DLGuc=
-github.com/go-openapi/swag/yamlutils v0.25.5 h1:kASCIS+oIeoc55j28T4o8KwlV2S4ZLPT6G0iq2SSbVQ=
-github.com/go-openapi/swag/yamlutils v0.25.5/go.mod h1:Gek1/SjjfbYvM+Iq4QGwa/2lEXde9n2j4a3wI3pNuOQ=
-github.com/go-openapi/testify/enable/yaml/v2 v2.4.1 h1:NZOrZmIb6PTv5LTFxr5/mKV/FjbUzGE7E6gLz7vFoOQ=
-github.com/go-openapi/testify/enable/yaml/v2 v2.4.1/go.mod h1:r7dwsujEHawapMsxA69i+XMGZrQ5tRauhLAjV/sxg3Q=
-github.com/go-openapi/testify/v2 v2.4.1 h1:zB34HDKj4tHwyUQHrUkpV0Q0iXQ6dUCOQtIqn8hE6Iw=
-github.com/go-openapi/testify/v2 v2.4.1/go.mod h1:HCPmvFFnheKK2BuwSA0TbbdxJ3I16pjwMkYkP4Ywn54=
-github.com/go-openapi/validate v0.25.2 h1:12NsfLAwGegqbGWr2CnvT65X/Q2USJipmJ9b7xDJZz0=
-github.com/go-openapi/validate v0.25.2/go.mod h1:Pgl1LpPPGFnZ+ys4/hTlDiRYQdI1ocKypgE+8Q8BLfY=
+github.com/go-openapi/analysis v0.24.1 h1:Xp+7Yn/KOnVWYG8d+hPksOYnCYImE3TieBa7rBOesYM=
+github.com/go-openapi/analysis v0.24.1/go.mod h1:dU+qxX7QGU1rl7IYhBC8bIfmWQdX4Buoea4TGtxXY84=
+github.com/go-openapi/errors v0.22.4 h1:oi2K9mHTOb5DPW2Zjdzs/NIvwi2N3fARKaTJLdNabaM=
+github.com/go-openapi/errors v0.22.4/go.mod h1:z9S8ASTUqx7+CP1Q8dD8ewGH/1JWFFLX/2PmAYNQLgk=
+github.com/go-openapi/jsonpointer v0.22.1 h1:sHYI1He3b9NqJ4wXLoJDKmUmHkWy/L7rtEo92JUxBNk=
+github.com/go-openapi/jsonpointer v0.22.1/go.mod h1:pQT9OsLkfz1yWoMgYFy4x3U5GY5nUlsOn1qSBH5MkCM=
+github.com/go-openapi/jsonreference v0.21.3 h1:96Dn+MRPa0nYAR8DR1E03SblB5FJvh7W6krPI0Z7qMc=
+github.com/go-openapi/jsonreference v0.21.3/go.mod h1:RqkUP0MrLf37HqxZxrIAtTWW4ZJIK1VzduhXYBEeGc4=
+github.com/go-openapi/loads v0.23.2 h1:rJXAcP7g1+lWyBHC7iTY+WAF0rprtM+pm8Jxv1uQJp4=
+github.com/go-openapi/loads v0.23.2/go.mod h1:IEVw1GfRt/P2Pplkelxzj9BYFajiWOtY2nHZNj4UnWY=
+github.com/go-openapi/runtime v0.29.2 h1:UmwSGWNmWQqKm1c2MGgXVpC2FTGwPDQeUsBMufc5Yj0=
+github.com/go-openapi/runtime v0.29.2/go.mod h1:biq5kJXRJKBJxTDJXAa00DOTa/anflQPhT0/wmjuy+0=
+github.com/go-openapi/spec v0.22.1 h1:beZMa5AVQzRspNjvhe5aG1/XyBSMeX1eEOs7dMoXh/k=
+github.com/go-openapi/spec v0.22.1/go.mod h1:c7aeIQT175dVowfp7FeCvXXnjN/MrpaONStibD2WtDA=
+github.com/go-openapi/strfmt v0.25.0 h1:7R0RX7mbKLa9EYCTHRcCuIPcaqlyQiWNPTXwClK0saQ=
+github.com/go-openapi/strfmt v0.25.0/go.mod h1:nNXct7OzbwrMY9+5tLX4I21pzcmE6ccMGXl3jFdPfn8=
+github.com/go-openapi/swag v0.25.4 h1:OyUPUFYDPDBMkqyxOTkqDYFnrhuhi9NR6QVUvIochMU=
+github.com/go-openapi/swag v0.25.4/go.mod h1:zNfJ9WZABGHCFg2RnY0S4IOkAcVTzJ6z2Bi+Q4i6qFQ=
+github.com/go-openapi/swag/cmdutils v0.25.4 h1:8rYhB5n6WawR192/BfUu2iVlxqVR9aRgGJP6WaBoW+4=
+github.com/go-openapi/swag/cmdutils v0.25.4/go.mod h1:pdae/AFo6WxLl5L0rq87eRzVPm/XRHM3MoYgRMvG4A0=
+github.com/go-openapi/swag/conv v0.25.4 h1:/Dd7p0LZXczgUcC/Ikm1+YqVzkEeCc9LnOWjfkpkfe4=
+github.com/go-openapi/swag/conv v0.25.4/go.mod h1:3LXfie/lwoAv0NHoEuY1hjoFAYkvlqI/Bn5EQDD3PPU=
+github.com/go-openapi/swag/fileutils v0.25.4 h1:2oI0XNW5y6UWZTC7vAxC8hmsK/tOkWXHJQH4lKjqw+Y=
+github.com/go-openapi/swag/fileutils v0.25.4/go.mod h1:cdOT/PKbwcysVQ9Tpr0q20lQKH7MGhOEb6EwmHOirUk=
+github.com/go-openapi/swag/jsonname v0.25.4 h1:bZH0+MsS03MbnwBXYhuTttMOqk+5KcQ9869Vye1bNHI=
+github.com/go-openapi/swag/jsonname v0.25.4/go.mod h1:GPVEk9CWVhNvWhZgrnvRA6utbAltopbKwDu8mXNUMag=
+github.com/go-openapi/swag/jsonutils v0.25.4 h1:VSchfbGhD4UTf4vCdR2F4TLBdLwHyUDTd1/q4i+jGZA=
+github.com/go-openapi/swag/jsonutils v0.25.4/go.mod h1:7OYGXpvVFPn4PpaSdPHJBtF0iGnbEaTk8AvBkoWnaAY=
+github.com/go-openapi/swag/jsonutils/fixtures_test v0.25.4 h1:IACsSvBhiNJwlDix7wq39SS2Fh7lUOCJRmx/4SN4sVo=
+github.com/go-openapi/swag/jsonutils/fixtures_test v0.25.4/go.mod h1:Mt0Ost9l3cUzVv4OEZG+WSeoHwjWLnarzMePNDAOBiM=
+github.com/go-openapi/swag/loading v0.25.4 h1:jN4MvLj0X6yhCDduRsxDDw1aHe+ZWoLjW+9ZQWIKn2s=
+github.com/go-openapi/swag/loading v0.25.4/go.mod h1:rpUM1ZiyEP9+mNLIQUdMiD7dCETXvkkC30z53i+ftTE=
+github.com/go-openapi/swag/mangling v0.25.4 h1:2b9kBJk9JvPgxr36V23FxJLdwBrpijI26Bx5JH4Hp48=
+github.com/go-openapi/swag/mangling v0.25.4/go.mod h1:6dxwu6QyORHpIIApsdZgb6wBk/DPU15MdyYj/ikn0Hg=
+github.com/go-openapi/swag/netutils v0.25.4 h1:Gqe6K71bGRb3ZQLusdI8p/y1KLgV4M/k+/HzVSqT8H0=
+github.com/go-openapi/swag/netutils v0.25.4/go.mod h1:m2W8dtdaoX7oj9rEttLyTeEFFEBvnAx9qHd5nJEBzYg=
+github.com/go-openapi/swag/stringutils v0.25.4 h1:O6dU1Rd8bej4HPA3/CLPciNBBDwZj9HiEpdVsb8B5A8=
+github.com/go-openapi/swag/stringutils v0.25.4/go.mod h1:GTsRvhJW5xM5gkgiFe0fV3PUlFm0dr8vki6/VSRaZK0=
+github.com/go-openapi/swag/typeutils v0.25.4 h1:1/fbZOUN472NTc39zpa+YGHn3jzHWhv42wAJSN91wRw=
+github.com/go-openapi/swag/typeutils v0.25.4/go.mod h1:Ou7g//Wx8tTLS9vG0UmzfCsjZjKhpjxayRKTHXf2pTE=
+github.com/go-openapi/swag/yamlutils v0.25.4 h1:6jdaeSItEUb7ioS9lFoCZ65Cne1/RZtPBZ9A56h92Sw=
+github.com/go-openapi/swag/yamlutils v0.25.4/go.mod h1:MNzq1ulQu+yd8Kl7wPOut/YHAAU/H6hL91fF+E2RFwc=
+github.com/go-openapi/testify/enable/yaml/v2 v2.0.2 h1:0+Y41Pz1NkbTHz8NngxTuAXxEodtNSI1WG1c/m5Akw4=
+github.com/go-openapi/testify/enable/yaml/v2 v2.0.2/go.mod h1:kme83333GCtJQHXQ8UKX3IBZu6z8T5Dvy5+CW3NLUUg=
+github.com/go-openapi/testify/v2 v2.0.2 h1:X999g3jeLcoY8qctY/c/Z8iBHTbwLz7R2WXd6Ub6wls=
+github.com/go-openapi/testify/v2 v2.0.2/go.mod h1:HCPmvFFnheKK2BuwSA0TbbdxJ3I16pjwMkYkP4Ywn54=
+github.com/go-openapi/validate v0.25.1 h1:sSACUI6Jcnbo5IWqbYHgjibrhhmt3vR6lCzKZnmAgBw=
+github.com/go-openapi/validate v0.25.1/go.mod h1:RMVyVFYte0gbSTaZ0N4KmTn6u/kClvAFp+mAVfS/DQc=
 github.com/go-skynet/go-llama.cpp v0.0.0-20240314183750-6a8041ef6b46 h1:lALhXzDkqtp12udlDLLg+ybXVMmL7Ox9tybqVLWxjPE=
 github.com/go-skynet/go-llama.cpp v0.0.0-20240314183750-6a8041ef6b46/go.mod h1:iub0ugfTnflE3rcIuqV2pQSo15nEw3GLW/utm5gyERo=
 github.com/go-sql-driver/mysql v1.9.3 h1:U/N249h2WzJ3Ukj8SowVFjdtZKfu9vlLZxjPXV1aweo=
@@ -514,8 +515,8 @@ github.com/go-text/typesetting v0.3.3 h1:ihGNJU9KzdK2QRDy1Bm7FT5RFQoYb+3n3EIhI/4
 github.com/go-text/typesetting v0.3.3/go.mod h1:vIRUT25mLQaSh4C8H/lIsKppQz/Gdb8Pu/tNwpi52ts=
 github.com/go-text/typesetting-utils v0.0.0-20250618110550-c820a94c77b8 h1:4KCscI9qYWMGTuz6BpJtbUSRzcBrUSSE0ENMJbNSrFs=
 github.com/go-text/typesetting-utils v0.0.0-20250618110550-c820a94c77b8/go.mod h1:3/62I4La/HBRX9TcTpBj4eipLiwzf+vhI+7whTc9V7o=
-github.com/go-viper/mapstructure/v2 v2.5.0 h1:vM5IJoUAy3d7zRSVtIwQgBj7BiWtMPfmPEgAXnvj1Ro=
-github.com/go-viper/mapstructure/v2 v2.5.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
+github.com/go-viper/mapstructure/v2 v2.4.0 h1:EBsztssimR/CONLSZZ04E8qAkxNYq4Qp9LvH92wZUgs=
+github.com/go-viper/mapstructure/v2 v2.4.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
 github.com/go-yaml/yaml v2.1.0+incompatible/go.mod h1:w2MrLa16VYP0jy6N7M5kHaCkaLENm+P+Tv+MfurjSw0=
 github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
 github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8=
@@ -629,12 +630,12 @@ github.com/google/trillian v1.7.2/go.mod h1:mfQJW4qRH6/ilABtPYNBerVJAJ/upxHLX81z
 github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
-github.com/googleapis/enterprise-certificate-proxy v0.3.14 h1:yh8ncqsbUY4shRD5dA6RlzjJaT4hi3kII+zYw8wmLb8=
-github.com/googleapis/enterprise-certificate-proxy v0.3.14/go.mod h1:vqVt9yG9480NtzREnTlmGSBmFrA+bzb0yl0TxoBQXOg=
+github.com/googleapis/enterprise-certificate-proxy v0.3.7 h1:zrn2Ee/nWmHulBx5sAVrGgAa0f2/R35S4DJwfFaUPFQ=
+github.com/googleapis/enterprise-certificate-proxy v0.3.7/go.mod h1:MkHOF77EYAE7qfSuSS9PU6g4Nt4e11cnsDUowfwewLA=
 github.com/googleapis/gax-go/v2 v2.0.4/go.mod h1:0Wqv26UfaUD9n4G6kQubkQ+KchISgw+vpHVxEJEs9eg=
 github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=
-github.com/googleapis/gax-go/v2 v2.19.0 h1:fYQaUOiGwll0cGj7jmHT/0nPlcrZDFPrZRhTsoCr8hE=
-github.com/googleapis/gax-go/v2 v2.19.0/go.mod h1:w2ROXVdfGEVFXzmlciUU4EdjHgWvB5h2n6x/8XSTTJA=
+github.com/googleapis/gax-go/v2 v2.15.0 h1:SyjDc1mGgZU5LncH8gimWo9lW1DtIfPibOG81vgd/bo=
+github.com/googleapis/gax-go/v2 v2.15.0/go.mod h1:zVVkkxAQHa1RQpg9z2AUCMnKhi0Qld9rcmyfL1OZhoc=
 github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
 github.com/gopherjs/gopherjs v1.17.2 h1:fQnZVsXk8uxXIStYb0N4bGk7jeyTalG/wsZjQ25dO0g=
 github.com/gopherjs/gopherjs v1.17.2/go.mod h1:pRRIvn/QzFLrKfvEz3qUuEhtE/zLCWfreZ6J5gM2i+k=
@@ -714,8 +715,8 @@ github.com/ianlancetaylor/demangle v0.0.0-20181102032728-5e5cf60278f6/go.mod h1:
 github.com/ianlancetaylor/demangle v0.0.0-20200824232613-28f6c0f3b639/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc=
 github.com/in-toto/attestation v1.1.2 h1:MBFn6lsMq6dptQZJBhalXTcWMb/aJy3V+GX3VYj/V1E=
 github.com/in-toto/attestation v1.1.2/go.mod h1:gYFddHMZj3DiQ0b62ltNi1Vj5rC879bTmBbrv9CRHpM=
-github.com/in-toto/in-toto-golang v0.11.0 h1:nfidMYBFx+E0lnmX5KUnN2Pdm8zdNKal1ayjJuzzRoA=
-github.com/in-toto/in-toto-golang v0.11.0/go.mod h1:u3PjTnwFKjp5a1YCcw8SJg0G+tMeKfVoWsWeFMDCMtw=
+github.com/in-toto/in-toto-golang v0.9.0 h1:tHny7ac4KgtsfrG6ybU8gVOZux2H8jN05AXJ9EBM1XU=
+github.com/in-toto/in-toto-golang v0.9.0/go.mod h1:xsBVrVsHNsB61++S6Dy2vWosKhuA3lUTQd+eF9HdeMo=
 github.com/inconshreveable/mousetrap v1.0.0/go.mod h1:PxqpIevigyE2G7u3NXJIT2ANytuPF1OarO4DADm73n8=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
@@ -824,8 +825,8 @@ github.com/labstack/echo/v4 v4.15.1 h1:S9keusg26gZpjMmPqB5hOEvNKnmd1lNmcHrbbH2ln
 github.com/labstack/echo/v4 v4.15.1/go.mod h1:xmw1clThob0BSVRX1CRQkGQ/vjwcpOMjQZSZa9fKA/c=
 github.com/labstack/gommon v0.4.2 h1:F8qTUNXgG1+6WQmqoUWnz8WiEU60mXVVw0P4ht1WRA0=
 github.com/labstack/gommon v0.4.2/go.mod h1:QlUFxVM+SNXhDL/Z7YhocGIBYOiwB0mXm1+1bAPHPyU=
-github.com/letsencrypt/boulder v0.20260223.0 h1:xdS2OnJNUasR6TgVIOpqqcvdkOu47+PQQMBk9ThuWBw=
-github.com/letsencrypt/boulder v0.20260223.0/go.mod h1:r3aTSA7UZ7dbDfiGK+HLHJz0bWNbHk6YSPiXgzl23sA=
+github.com/letsencrypt/boulder v0.20251110.0 h1:J8MnKICeilO91dyQ2n5eBbab24neHzUpYMUIOdOtbjc=
+github.com/letsencrypt/boulder v0.20251110.0/go.mod h1:ogKCJQwll82m7OVHWyTuf8eeFCjuzdRQlgnZcCl0V+8=
 github.com/lib/pq v1.10.9 h1:YXG7RB+JIjhP29X+OtkiDnYaXQwpS4JEWq7dtCCRUEw=
 github.com/lib/pq v1.10.9/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o=
 github.com/libp2p/go-buffer-pool v0.1.0 h1:oK4mSFcQz7cTQIfqbe4MIj9gLW+mnanjyFtc6cdF0Y8=
@@ -981,6 +982,10 @@ github.com/mudler/localrecall v0.6.1-0.20260507074622-a7724fef6f81 h1:8D9NJ/ikhs
 github.com/mudler/localrecall v0.6.1-0.20260507074622-a7724fef6f81/go.mod h1:28k5n19raUrkuwXkacdNsBlj8yuSnGhpT16tu+2+4dU=
 github.com/mudler/memory v0.0.0-20260406210934-424c1ecf2cf8 h1:Ry8RiWy8fZ6Ff4E7dPmjRsBrnHOnPeOOj2LhCgyjQu0=
 github.com/mudler/memory v0.0.0-20260406210934-424c1ecf2cf8/go.mod h1:EA8Ashhd56o32qN7ouPKFSRUs/Z+LrRCF4v6R2Oarm8=
+github.com/mudler/skillserver v0.0.6 h1:ixz6wUekLdTmbnpAavCkTydDF6UdXAG3ncYufSPK9G0=
+github.com/mudler/skillserver v0.0.6/go.mod h1:z3yFhcL9bSykmmh6xgGu0hyoItd4CnxgtWMEWw8uFJU=
+github.com/mudler/skillserver v0.0.7-0.20260520212528-3dae7f041b1e h1:ryXE1UEzGhLkDFYuaxJ0fZ6fg4l++TWfMCTJ1E7bYS8=
+github.com/mudler/skillserver v0.0.7-0.20260520212528-3dae7f041b1e/go.mod h1:z3yFhcL9bSykmmh6xgGu0hyoItd4CnxgtWMEWw8uFJU=
 github.com/mudler/skillserver v0.0.7-0.20260520220837-a7317cbf9145 h1:z59tA3IDYPt71nzH1jpxeaA1LuDw8aZfpTQFNU43Zb8=
 github.com/mudler/skillserver v0.0.7-0.20260520220837-a7317cbf9145/go.mod h1:z3yFhcL9bSykmmh6xgGu0hyoItd4CnxgtWMEWw8uFJU=
 github.com/mudler/water v0.0.0-20250808092830-dd90dcf09025 h1:WFLP5FHInarYGXi6B/Ze204x7Xy6q/I4nCZnWEyPHK0=
@@ -1031,10 +1036,10 @@ github.com/nicksnyder/go-i18n/v2 v2.5.1 h1:IxtPxYsR9Gp60cGXjfuR/llTqV8aYMsC472zD
 github.com/nicksnyder/go-i18n/v2 v2.5.1/go.mod h1:DrhgsSDZxoAfvVrBVLXoxZn/pN5TXqaDbq7ju94viiQ=
 github.com/nwaples/rardecode v1.1.0 h1:vSxaY8vQhOcVr4mm5e8XllHWTiM4JF507A0Katqw7MQ=
 github.com/nwaples/rardecode v1.1.0/go.mod h1:5DzqNKiOdpKKBH87u8VlvAnPZMXcGRhxWkRpHbbfGS0=
-github.com/nxadm/tail v1.4.11 h1:8feyoE3OzPrcshW5/MJ4sGESc5cqmGkGCWlco4l0bqY=
-github.com/nxadm/tail v1.4.11/go.mod h1:OTaG3NK980DZzxbRq6lEuzgU+mug70nY11sMd4JXXHc=
-github.com/oklog/ulid/v2 v2.1.1 h1:suPZ4ARWLOJLegGFiZZ1dFAkqzhMjL3J1TzI+5wHz8s=
-github.com/oklog/ulid/v2 v2.1.1/go.mod h1:rcEKHmBBKfef9DhnvX7y1HZBYxjXb0cP5ExxNsTT1QQ=
+github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
+github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
+github.com/oklog/ulid v1.3.1 h1:EGfNDEx6MqHz8B3uNV6QAib1UR2Lm97sHi3ocA6ESJ4=
+github.com/oklog/ulid v1.3.1/go.mod h1:CirwcVhetQ6Lv90oh/F+FBtV6XMibvdAFo93nm5qn4U=
 github.com/olekukonko/tablewriter v0.0.5 h1:P2Ga83D34wi1o9J6Wh1mRuqd4mF/x/lgBS7N7AbDhec=
 github.com/olekukonko/tablewriter v0.0.5/go.mod h1:hPp6KlRPjbx+hW8ykQs1w3UBbZlj6HuIJcUGPhkA7kY=
 github.com/ollama/ollama v0.20.4 h1:XXquZkzAptOoAzNHAyKQOhiShoDFMfn3Yp56C7Vfsjs=
@@ -1064,7 +1069,6 @@ github.com/oxffaa/gopher-parse-sitemap v0.0.0-20191021113419-005d2eb1def4/go.mod
 github.com/pascaldekloe/goe v0.0.0-20180627143212-57f6aae5913c/go.mod h1:lzWF7FIEvWOWxwDKqyGYQf6ZUaNfKdP144TG7ZOy1lc=
 github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58 h1:onHthvaw9LFnH4t2DcNVpwGmV9E1BkGknEliJkfwQj0=
 github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58/go.mod h1:DXv8WO4yhMYhSNPKjeNKa5WY9YCIEBRbNzFFPJbWO6Y=
-github.com/pborman/getopt v0.0.0-20170112200414-7148bc3a4c30/go.mod h1:85jBQOZwpVEaDAr341tbn15RS4fCAsIst0qp7i8ex1o=
 github.com/pelletier/go-toml v1.9.3/go.mod h1:u1nR/EPcESfeI/szUZKdtJ0xRNbUoANCkoOuaOx1Y+c=
 github.com/peterbourgon/diskv v2.0.1+incompatible h1:UBdAOUP5p4RWqPBg048CAvpKN+vxiaj6gdUUzhl4XmI=
 github.com/peterbourgon/diskv v2.0.1+incompatible/go.mod h1:uqqh8zWWbv1HBMNONnaR/tNboyR3/BZd58JJSHlUSCU=
@@ -1182,8 +1186,8 @@ github.com/schollz/progressbar/v3 v3.19.0/go.mod h1:IsO3lpbaGuzh8zIMzgY3+J8l4C8G
 github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529/go.mod h1:DxrIzT+xaE7yg65j358z/aeFdxmN0P9QXhEzd20vsDc=
 github.com/sebdah/goldie/v2 v2.7.1 h1:PkBHymaYdtvEkZV7TmyqKxdmn5/Vcj+8TpATWZjnG5E=
 github.com/sebdah/goldie/v2 v2.7.1/go.mod h1:oZ9fp0+se1eapSRjfYbsV/0Hqhbuu3bJVvKI/NNtssI=
-github.com/secure-systems-lab/go-securesystemslib v0.10.0 h1:l+H5ErcW0PAehBNrBxoGv1jjNpGYdZ9RcheFkB2WI14=
-github.com/secure-systems-lab/go-securesystemslib v0.10.0/go.mod h1:MRKONWmRoFzPNQ9USRF9i1mc7MvAVvF1LlW8X5VWDvk=
+github.com/secure-systems-lab/go-securesystemslib v0.9.1 h1:nZZaNz4DiERIQguNy0cL5qTdn9lR8XKHf4RUyG1Sx3g=
+github.com/secure-systems-lab/go-securesystemslib v0.9.1/go.mod h1:np53YzT0zXGMv6x4iEWc9Z59uR+x+ndLwCLqPYpLXVU=
 github.com/segmentio/asm v1.1.3 h1:WM03sfUOENvvKexOLp+pCqgb/WDjsi7EK8gIsICtzhc=
 github.com/segmentio/asm v1.1.3/go.mod h1:Ld3L4ZXGNcSLRg4JBsZ3//1+f/TjYl0Mzen/DQy1EJg=
 github.com/segmentio/encoding v0.5.4 h1:OW1VRern8Nw6ITAtwSZ7Idrl3MXCFwXHPgqESYfvNt0=
@@ -1208,32 +1212,32 @@ github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeV
 github.com/shurcooL/vfsgen v0.0.0-20200824052919-0d455de96546/go.mod h1:TrYk7fJVaAttu97ZZKrO9UbRa8izdowaMIZcxYMbVaw=
 github.com/sigstore/protobuf-specs v0.5.1 h1:/5OPaNuolRJmQfeZLayJGFXMpsRJEdgC6ah1/+7Px7U=
 github.com/sigstore/protobuf-specs v0.5.1/go.mod h1:DRBzpFuE+LnvQMN10/dU6nBeKwVLGEQ6o2FovN2Rats=
-github.com/sigstore/rekor v1.5.0 h1:rL7SghHd5HLCtsCrxw0yQg+NczGvM75EjSPPWuGjaiQ=
-github.com/sigstore/rekor v1.5.0/go.mod h1:D7JoVCUkxwQOpPDNYeu+CE8zeBC18Y5uDo6tF8s2rcQ=
+github.com/sigstore/rekor v1.4.3 h1:2+aw4Gbgumv8vYM/QVg6b+hvr4x4Cukur8stJrVPKU0=
+github.com/sigstore/rekor v1.4.3/go.mod h1:o0zgY087Q21YwohVvGwV9vK1/tliat5mfnPiVI3i75o=
 github.com/sigstore/rekor-tiles/v2 v2.0.1 h1:1Wfz15oSRNGF5Dzb0lWn5W8+lfO50ork4PGIfEKjZeo=
 github.com/sigstore/rekor-tiles/v2 v2.0.1/go.mod h1:Pjsbhzj5hc3MKY8FfVTYHBUHQEnP0ozC4huatu4x7OU=
-github.com/sigstore/sigstore v1.10.5 h1:KqrOjDhNOVY+uOzQFat2FrGLClPPCb3uz8pK3wuI+ow=
-github.com/sigstore/sigstore v1.10.5/go.mod h1:k/mcVVXw3I87dYG/iCVTSW2xTrW7vPzxxGic4KqsqXs=
+github.com/sigstore/sigstore v1.10.0 h1:lQrmdzqlR8p9SCfWIpFoGUqdXEzJSZT2X+lTXOMPaQI=
+github.com/sigstore/sigstore v1.10.0/go.mod h1:Ygq+L/y9Bm3YnjpJTlQrOk/gXyrjkpn3/AEJpmk1n9Y=
 github.com/sigstore/sigstore-go v1.1.4 h1:wTTsgCHOfqiEzVyBYA6mDczGtBkN7cM8mPpjJj5QvMg=
 github.com/sigstore/sigstore-go v1.1.4/go.mod h1:2U/mQOT9cjjxrtIUeKDVhL+sHBKsnWddn8URlswdBsg=
-github.com/sigstore/sigstore/pkg/signature/kms/aws v1.10.5 h1:aqHRubTITULckG9JAcq2FEhtKkT/RRE8oErfuV3smSI=
-github.com/sigstore/sigstore/pkg/signature/kms/aws v1.10.5/go.mod h1:h9eK9QyPqpFskF/ewFkRLtwh4/Q3FLc2/DXbym4IHN8=
-github.com/sigstore/sigstore/pkg/signature/kms/azure v1.10.5 h1:+9C6CUkv+J4iT67Lx+H1EGBfAdoAHqXumHadeIj9jA4=
-github.com/sigstore/sigstore/pkg/signature/kms/azure v1.10.5/go.mod h1:myZsg7wRiy/vf102g5uUAitYhtXCwepmAGxgHG1VHuE=
-github.com/sigstore/sigstore/pkg/signature/kms/gcp v1.10.5 h1:BpQx6AhjwIN9LmlO4ypkcMcHiWiepgZQGSw5U69frHU=
-github.com/sigstore/sigstore/pkg/signature/kms/gcp v1.10.5/go.mod h1:ejMD/17lMJ4HykQRPdj5NNr+OQYIEZto8HjDKghVMOA=
-github.com/sigstore/sigstore/pkg/signature/kms/hashivault v1.10.5 h1:OFwQZgWkB/6J6W5sy3SkXE4pJnhNRnE2cJd8ySXmHpo=
-github.com/sigstore/sigstore/pkg/signature/kms/hashivault v1.10.5/go.mod h1:Ee/enmyxi/RFLVlajbnjgH2wOWQwlJ0wY8qZrk43hEw=
-github.com/sigstore/timestamp-authority/v2 v2.0.6 h1:1Vh7/SdmLsVLG6Br6/bisd1SnlicfDm0MJYiA+D7Ppw=
-github.com/sigstore/timestamp-authority/v2 v2.0.6/go.mod h1:Nk5ucGBDyH0tXAIMZ0prf6xn8qfTnbJhSq+CDabYcfc=
+github.com/sigstore/sigstore/pkg/signature/kms/aws v1.10.0 h1:UOHpiyezCj5RuixgIvCV3QyuxIGQT+N6nGZEXA7OTTY=
+github.com/sigstore/sigstore/pkg/signature/kms/aws v1.10.0/go.mod h1:U0CZmA2psabDa8DdiV7yXab0AHODzfKqvD2isH7Hrvw=
+github.com/sigstore/sigstore/pkg/signature/kms/azure v1.10.0 h1:fq4+8Y4YadxeF8mzhoMRPZ1mVvDYXmI3BfS0vlkPT7M=
+github.com/sigstore/sigstore/pkg/signature/kms/azure v1.10.0/go.mod h1:u05nqPWY05lmcdHhv2lPaWTH3FGUhJzO7iW2hbboK3Q=
+github.com/sigstore/sigstore/pkg/signature/kms/gcp v1.10.0 h1:iUEf5MZYOuXGnXxdF/WrarJrk0DTVHqeIOjYdtpVXtc=
+github.com/sigstore/sigstore/pkg/signature/kms/gcp v1.10.0/go.mod h1:i6vg5JfEQix46R1rhQlrKmUtJoeH91drltyYOJEk1T4=
+github.com/sigstore/sigstore/pkg/signature/kms/hashivault v1.10.0 h1:dUvPv/MP23ZPIXZUW45kvCIgC0ZRfYxEof57AB6bAtU=
+github.com/sigstore/sigstore/pkg/signature/kms/hashivault v1.10.0/go.mod h1:fR/gDdPvJWGWL70/NgBBIL1O0/3Wma6JHs3tSSYg3s4=
+github.com/sigstore/timestamp-authority/v2 v2.0.3 h1:sRyYNtdED/ttLCMdaYnwpf0zre1A9chvjTnCmWWxN8Y=
+github.com/sigstore/timestamp-authority/v2 v2.0.3/go.mod h1:mDaHxkt3HmZYoIlwYj4QWo0RUr7VjYU52aVO5f5Qb3I=
 github.com/sirupsen/logrus v1.7.0/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
 github.com/sirupsen/logrus v1.8.1/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
 github.com/sirupsen/logrus v1.9.4 h1:TsZE7l11zFCLZnZ+teH4Umoq5BhEIfIzfRDZ1Uzql2w=
 github.com/sirupsen/logrus v1.9.4/go.mod h1:ftWc9WdOfJ0a92nsE2jF5u5ZwH8Bv2zdeOC42RjbV2g=
 github.com/skeema/knownhosts v1.3.1 h1:X2osQ+RAjK76shCbvhHHHVl3ZlgDm8apHEHFqRjnBY8=
 github.com/skeema/knownhosts v1.3.1/go.mod h1:r7KTdC8l4uxWRyK2TpQZ/1o5HaSzh06ePQNxPwTcfiY=
-github.com/slack-go/slack v0.23.1 h1:ZS5B96wxxYQRwvJ3/vJFtqtUZi3tXhsZCyT44Nv7M80=
-github.com/slack-go/slack v0.23.1/go.mod h1:H0yR/YBuRJ39RkE+JpV/d/oEsbanzTRowR82bCN0cEs=
+github.com/slack-go/slack v0.17.3 h1:zV5qO3Q+WJAQ/XwbGfNFrRMaJ5T/naqaonyPV/1TP4g=
+github.com/slack-go/slack v0.17.3/go.mod h1:X+UqOufi3LYQHDnMG1vxf0J8asC6+WllXrVrhl8/Prk=
 github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d h1:3VwvTjiRPA7cqtgOWddEL+JrcijMlXUmj99c/6YyZoY=
 github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d/go.mod h1:tAG61zBM1DYRaGIPloumExGvScf08oHuo0kFoOqdbT0=
 github.com/smarty/assertions v1.15.0 h1:cR//PqUBUiQRakZWqBiFFQ9wb8emQGDb0HeGdqGByCY=
@@ -1307,8 +1311,8 @@ github.com/tetratelabs/wazero v1.11.0 h1:+gKemEuKCTevU4d7ZTzlsvgd1uaToIDtlQlmNbw
 github.com/tetratelabs/wazero v1.11.0/go.mod h1:eV28rsN8Q+xwjogd7f4/Pp4xFxO7uOGbLcD/LzB1wiU=
 github.com/theupdateframework/go-tuf v0.7.0 h1:CqbQFrWo1ae3/I0UCblSbczevCCbS31Qvs5LdxRWqRI=
 github.com/theupdateframework/go-tuf v0.7.0/go.mod h1:uEB7WSY+7ZIugK6R1hiBMBjQftaFzn7ZCDJcp1tCUug=
-github.com/theupdateframework/go-tuf/v2 v2.4.1 h1:K6ewW064rKZCPkRo1W/CTbTtm/+IB4+coG1iNURAGCw=
-github.com/theupdateframework/go-tuf/v2 v2.4.1/go.mod h1:Nex2enPVYDFCklrnbTzl3OVwD7fgIAj0J5++z/rvCj8=
+github.com/theupdateframework/go-tuf/v2 v2.3.0 h1:gt3X8xT8qu/HT4w+n1jgv+p7koi5ad8XEkLXXZqG9AA=
+github.com/theupdateframework/go-tuf/v2 v2.3.0/go.mod h1:xW8yNvgXRncmovMLvBxKwrKpsOwJZu/8x+aB0KtFcdw=
 github.com/thoj/go-ircevent v0.0.0-20210723090443-73e444401d64 h1:l/T7dYuJEQZOwVOpjIXr1180aM9PZL/d1MnMVIxefX4=
 github.com/thoj/go-ircevent v0.0.0-20210723090443-73e444401d64/go.mod h1:Q1NAJOuRdQCqN/VIWdnaaEhV8LpeO2rtlBP7/iDJNII=
 github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
@@ -1328,10 +1332,10 @@ github.com/tink-crypto/tink-go-awskms/v2 v2.1.0 h1:N9UxlsOzu5mttdjhxkDLbzwtEecuX
 github.com/tink-crypto/tink-go-awskms/v2 v2.1.0/go.mod h1:PxSp9GlOkKL9rlybW804uspnHuO9nbD98V/fDX4uSis=
 github.com/tink-crypto/tink-go-gcpkms/v2 v2.2.0 h1:3B9i6XBXNTRspfkTC0asN5W0K6GhOSgcujNiECNRNb0=
 github.com/tink-crypto/tink-go-gcpkms/v2 v2.2.0/go.mod h1:jY5YN2BqD/KSCHM9SqZPIpJNG/u3zwfLXHgws4x2IRw=
-github.com/tink-crypto/tink-go-hcvault/v2 v2.4.0 h1:j+S+WKBQ5ya26A5EM/uXoVe+a2IaPQN8KgBJZ22cJ+4=
-github.com/tink-crypto/tink-go-hcvault/v2 v2.4.0/go.mod h1:OCKJIujnTzDq7f+73NhVs99oA2c1TR6nsOpuasYM6Yo=
-github.com/tink-crypto/tink-go/v2 v2.6.0 h1:+KHNBHhWH33Vn+igZWcsgdEPUxKwBMEe0QC60t388v4=
-github.com/tink-crypto/tink-go/v2 v2.6.0/go.mod h1:2WbBA6pfNsAfBwDCggboaHeB2X29wkU8XHtGwh2YIk8=
+github.com/tink-crypto/tink-go-hcvault/v2 v2.3.0 h1:6nAX1aRGnkg2SEUMwO5toB2tQkP0Jd6cbmZ/K5Le1V0=
+github.com/tink-crypto/tink-go-hcvault/v2 v2.3.0/go.mod h1:HOC5NWW1wBI2Vke1FGcRBvDATkEYE7AUDiYbXqi2sBw=
+github.com/tink-crypto/tink-go/v2 v2.5.0 h1:B8KLF6AofxdBIE4UJIaFbmoj5/1ehEtt7/MmzfI4Zpw=
+github.com/tink-crypto/tink-go/v2 v2.5.0/go.mod h1:2WbBA6pfNsAfBwDCggboaHeB2X29wkU8XHtGwh2YIk8=
 github.com/titanous/rocacheck v0.0.0-20171023193734-afe73141d399 h1:e/5i7d4oYZ+C1wj2THlRK+oAhjeS/TRQwMfkIuet3w0=
 github.com/titanous/rocacheck v0.0.0-20171023193734-afe73141d399/go.mod h1:LdwHTNJT99C5fTAzDz0ud328OgXz+gierycbcIx2fRs=
 github.com/tklauser/go-sysconf v0.3.16 h1:frioLaCQSsF5Cy1jgRBrzr6t502KIIwQ0MArYICU0nA=
@@ -1402,6 +1406,8 @@ go.etcd.io/etcd/client/pkg/v3 v3.5.0/go.mod h1:IJHfcCEKxYu1Os13ZdwCwIUTUVGYTSAM3
 go.etcd.io/etcd/client/v2 v2.305.0/go.mod h1:h9puh54ZTgAKtEbut2oe9P4L/oqKCVB6xsXlzd7alYQ=
 go.mau.fi/util v0.3.0 h1:Lt3lbRXP6ZBqTINK0EieRWor3zEwwwrDT14Z5N8RUCs=
 go.mau.fi/util v0.3.0/go.mod h1:9dGsBCCbZJstx16YgnVMVi3O2bOizELoKpugLD4FoGs=
+go.mongodb.org/mongo-driver v1.17.6 h1:87JUG1wZfWsr6rIz3ZmpH90rL5tea7O3IHuSwHUpsss=
+go.mongodb.org/mongo-driver v1.17.6/go.mod h1:Hy04i7O2kC4RS06ZrhPRqj/u4DTYkFDAAccj+rVKqgQ=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
 go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
 go.opencensus.io v0.22.2/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
@@ -1431,8 +1437,8 @@ go.opentelemetry.io/otel/trace v1.43.0 h1:BkNrHpup+4k4w+ZZ86CZoHHEkohws8AY+WTX09
 go.opentelemetry.io/otel/trace v1.43.0/go.mod h1:/QJhyVBUUswCphDVxq+8mld+AvhXZLhe+8WVFxiFff0=
 go.starlark.net v0.0.0-20250417143717-f57e51f710eb h1:zOg9DxxrorEmgGUr5UPdCEwKqiqG0MlZciuCuA3XiDE=
 go.starlark.net v0.0.0-20250417143717-f57e51f710eb/go.mod h1:YKMCv9b1WrfWmeqdV5MAuEHWsu5iC+fe6kYl2sQjdI8=
-go.step.sm/crypto v0.77.2 h1:qFjjei+RHc5kP5R7NW9OUWT7SqWIuAOvOkXqg4fNWj8=
-go.step.sm/crypto v0.77.2/go.mod h1:W0YJb9onM5l78qgkXIJ2Up6grnwW8EtpCKIza/NCg0o=
+go.step.sm/crypto v0.74.0 h1:/APBEv45yYR4qQFg47HA8w1nesIGcxh44pGyQNw6JRA=
+go.step.sm/crypto v0.74.0/go.mod h1:UoXqCAJjjRgzPte0Llaqen7O9P7XjPmgjgTHQGkKCDk=
 go.uber.org/atomic v1.6.0/go.mod h1:sABNBOSYdrvTF6hTgEIbc7YasKWGhgEQZyfxyTvoXHQ=
 go.uber.org/atomic v1.7.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
 go.uber.org/dig v1.19.0 h1:BACLhebsYdpQ7IROQ1AGPjrXcP5dF80U3gKoFzbaq/4=
@@ -1710,8 +1716,8 @@ golang.org/x/text v0.37.0/go.mod h1:a5sjxXGs9hsn/AJVwuElvCAo9v8QYLzvavO5z2PiM38=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
-golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
+golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
+golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
@@ -1809,8 +1815,8 @@ google.golang.org/api v0.40.0/go.mod h1:fYKFpnQN0DsDSKRVRcQSDQNtqWPfM9i+zNPxepjR
 google.golang.org/api v0.41.0/go.mod h1:RkxM5lITDfTzmyKFPt+wGrCJbVfniCr2ool8kTBzRTU=
 google.golang.org/api v0.43.0/go.mod h1:nQsDGjRXMo4lvh5hP0TKqF244gqhGcr/YSIykhUk/94=
 google.golang.org/api v0.44.0/go.mod h1:EBOGZqzyhtvMDoxwS97ctnh0zUmYY6CxqXsc1AvkYD8=
-google.golang.org/api v0.272.0 h1:eLUQZGnAS3OHn31URRf9sAmRk3w2JjMx37d2k8AjJmA=
-google.golang.org/api v0.272.0/go.mod h1:wKjowi5LNJc5qarNvDCvNQBn3rVK8nSy6jg2SwRwzIA=
+google.golang.org/api v0.256.0 h1:u6Khm8+F9sxbCTYNoBHg6/Hwv0N/i+V94MvkOSor6oI=
+google.golang.org/api v0.256.0/go.mod h1:KIgPhksXADEKJlnEoRa9qAII4rXcy40vfI8HRqcU964=
 google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
 google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
 google.golang.org/appengine v1.5.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
@@ -1861,12 +1867,12 @@ google.golang.org/genproto v0.0.0-20210310155132-4ce2db91004e/go.mod h1:FWY/as6D
 google.golang.org/genproto v0.0.0-20210319143718-93e7006c17a6/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
 google.golang.org/genproto v0.0.0-20210402141018-6c239bbf2bb1/go.mod h1:9lPAdzaEmUacj36I+k7YKbEc5CXzPIeORRgDAUOu28A=
 google.golang.org/genproto v0.0.0-20210602131652-f16073e35f0c/go.mod h1:UODoCrxHCcBojKKwX1terBiRUaqAsFqJiF615XL43r0=
-google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5 h1:JNfk58HZ8lfmXbYK2vx/UvsqIL59TzByCxPIX4TDmsE=
-google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5/go.mod h1:x5julN69+ED4PcFk/XWayw35O0lf/nGa4aNgODCmNmw=
-google.golang.org/genproto/googleapis/api v0.0.0-20260316180232-0b37fe3546d5 h1:CogIeEXn4qWYzzQU0QqvYBM8yDF9cFYzDq9ojSpv0Js=
-google.golang.org/genproto/googleapis/api v0.0.0-20260316180232-0b37fe3546d5/go.mod h1:EIQZ5bFCfRQDV4MhRle7+OgjNtZ6P1PiZBgAKuxXu/Y=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20260316180232-0b37fe3546d5 h1:aJmi6DVGGIStN9Mobk/tZOOQUBbj0BPjZjjnOdoZKts=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20260316180232-0b37fe3546d5/go.mod h1:4Hqkh8ycfw05ld/3BWL7rJOSfebL2Q+DVDeRgYgxUU8=
+google.golang.org/genproto v0.0.0-20250922171735-9219d122eba9 h1:LvZVVaPE0JSqL+ZWb6ErZfnEOKIqqFWUJE2D0fObSmc=
+google.golang.org/genproto v0.0.0-20250922171735-9219d122eba9/go.mod h1:QFOrLhdAe2PsTp3vQY4quuLKTi9j3XG3r6JPPaw7MSc=
+google.golang.org/genproto/googleapis/api v0.0.0-20260128011058-8636f8732409 h1:merA0rdPeUV3YIIfHHcH4qBkiQAc1nfCKSI7lB4cV2M=
+google.golang.org/genproto/googleapis/api v0.0.0-20260128011058-8636f8732409/go.mod h1:fl8J1IvUjCilwZzQowmw2b7HQB2eAuYBabMXzWurF+I=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20260128011058-8636f8732409 h1:H86B94AW+VfJWDqFeEbBPhEtHzJwJfTbgE2lZa54ZAQ=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20260128011058-8636f8732409/go.mod h1:j9x/tPzZkyxcgEFkiKEEGxfvyumM01BEtsW8xzOahRQ=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
 google.golang.org/grpc v1.20.1/go.mod h1:10oTOabMzJvdu6/UiuZezV6QK5dSlG84ov/aaiqXj38=
 google.golang.org/grpc v1.21.1/go.mod h1:oYelfM1adQP15Ek0mdvEgi9Df8B9CZIaU1084ijfRaM=