fix(openai): stream usage non-zero when tools are enabled (#9941 )

* chore: ignore local .worktrees directory Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(openai): stream usage non-zero when tools are enabled The streaming chat-completions worker for tool-bearing requests (processTools in core/http/endpoints/openai/chat.go) never forwarded the cumulative TokenUsage from ComputeChoices to the chunks it placed on the responses channel. The outer streaming loop's running usage tracker therefore stayed at the zero value, and the include_usage trailer reported {prompt_tokens:0, completion_tokens:0, total_tokens:0} whenever the request carried a `tools` array. Without tools, the alternative `process` path stamps Usage on every chunk, so that path was unaffected. Forward the final TokenUsage via a usage-only sentinel chunk (empty Choices, populated Usage) emitted right before close(responses). The outer loop's per-chunk Usage capture moves above the empty-Choices skip so the sentinel updates the tracker without ever reaching the wire, keeping the existing OpenAI spec contract (intermediate chunks carry no `usage` field, and the deferred-final-chunk helpers remain Usage-free per the regression test for issue #8546). Adds streamUsageFromTokenUsage, usageSentinelChunk, and applyChunkToUsage helpers with focused Ginkgo coverage plus a flow-level test that mirrors the outer-loop sequence. Fixes #9927 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:opus-4-7 [Claude Code] * refactor(openai): return final TokenUsage from stream workers Replace the usage-only sentinel SSE chunk introduced in the previous commit with a plain return value. The streaming workers process and processTools (now extracted as package-level processStream and processStreamWithTools) return (backend.TokenUsage, error); the outer ChatEndpoint loop reads the cumulative counts off the existing `ended` channel (now carrying streamWorkerResult{usage, err}) and builds the include_usage trailer from a normal Go value after the LOOP exits. This drops the empty-Choices "skip but capture Usage" rule from the outer loop and removes the usageSentinelChunk / applyChunkToUsage helpers entirely. The SSE responses channel is back to a single purpose: wire chunks only. processStream and processStreamWithTools move into chat_stream_workers.go so they can be exercised directly from tests. The chat_stream_usage_test.go suite now drives the workers with a mocked backend.ModelInferenceFunc and asserts on the returned TokenUsage. The regression coverage for issue #9927 is therefore behavioral: reverting the fix (discarding ComputeChoices' usage return) makes the assertions fail with concrete count mismatches. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:opus-4-7 [Claude Code] --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
chore: ⬆️ Update ggml-org/llama.cpp to bb28c1fe246b72276ee1d00ce89306be7b865766 (#9934 )
2026-05-22 07:38:26 -04:00 · 2026-05-22 10:13:41 +02:00 · 2026-05-22 09:49:33 +02:00 · 2026-05-22 08:31:49 +02:00 · 2026-05-22 00:31:19 +02:00
10 changed files with 795 additions and 538 deletions
--- a/.gitignore
+++ b/.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/
--- a/backend/cpp/ds4/Makefile
+++ b/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))))
--- a/backend/cpp/llama-cpp/Makefile
+++ b/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?=
--- a/backend/go/stablediffusion-ggml/Makefile
+++ b/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

--- a/core/http/endpoints/openai/chat.go
+++ b/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)
 				}

--- a/core/http/endpoints/openai/chat_emit.go
+++ b/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:
--- a/core/http/endpoints/openai/chat_stream_usage_test.go
+++ b/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))
+		})
+	})
+})
--- a/core/http/endpoints/openai/chat_stream_workers.go
+++ b/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
+}
--- a/go.mod
+++ b/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
--- a/go.sum
+++ b/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=
Author	SHA1	Message	Date
LocalAI [bot]	0b2ae3c6ca	fix(openai): stream usage non-zero when tools are enabled (#9941 ) * chore: ignore local .worktrees directory Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(openai): stream usage non-zero when tools are enabled The streaming chat-completions worker for tool-bearing requests (processTools in core/http/endpoints/openai/chat.go) never forwarded the cumulative TokenUsage from ComputeChoices to the chunks it placed on the responses channel. The outer streaming loop's running usage tracker therefore stayed at the zero value, and the include_usage trailer reported {prompt_tokens:0, completion_tokens:0, total_tokens:0} whenever the request carried a `tools` array. Without tools, the alternative `process` path stamps Usage on every chunk, so that path was unaffected. Forward the final TokenUsage via a usage-only sentinel chunk (empty Choices, populated Usage) emitted right before close(responses). The outer loop's per-chunk Usage capture moves above the empty-Choices skip so the sentinel updates the tracker without ever reaching the wire, keeping the existing OpenAI spec contract (intermediate chunks carry no `usage` field, and the deferred-final-chunk helpers remain Usage-free per the regression test for issue #8546). Adds streamUsageFromTokenUsage, usageSentinelChunk, and applyChunkToUsage helpers with focused Ginkgo coverage plus a flow-level test that mirrors the outer-loop sequence. Fixes #9927 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:opus-4-7 [Claude Code] * refactor(openai): return final TokenUsage from stream workers Replace the usage-only sentinel SSE chunk introduced in the previous commit with a plain return value. The streaming workers process and processTools (now extracted as package-level processStream and processStreamWithTools) return (backend.TokenUsage, error); the outer ChatEndpoint loop reads the cumulative counts off the existing `ended` channel (now carrying streamWorkerResult{usage, err}) and builds the include_usage trailer from a normal Go value after the LOOP exits. This drops the empty-Choices "skip but capture Usage" rule from the outer loop and removes the usageSentinelChunk / applyChunkToUsage helpers entirely. The SSE responses channel is back to a single purpose: wire chunks only. processStream and processStreamWithTools move into chat_stream_workers.go so they can be exercised directly from tests. The chat_stream_usage_test.go suite now drives the workers with a mocked backend.ModelInferenceFunc and asserts on the returned TokenUsage. The regression coverage for issue #9927 is therefore behavioral: reverting the fix (discarding ComputeChoices' usage return) makes the assertions fail with concrete count mismatches. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:opus-4-7 [Claude Code] --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>	2026-05-22 10:13:41 +02:00
LocalAI [bot]	4735345105	chore: ⬆️ Update ggml-org/llama.cpp to `bb28c1fe246b72276ee1d00ce89306be7b865766` (#9934 ) ⬆️ Update ggml-org/llama.cpp Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>	2026-05-22 09:49:33 +02:00
LocalAI [bot]	7384fd800b	chore: ⬆️ Update antirez/ds4 to `8d576642c39b9a2d782a80159ba84ef5a81c0b81` (#9932 ) ⬆️ Update antirez/ds4 Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>	2026-05-22 08:31:49 +02:00
LocalAI [bot]	6942713d85	chore: ⬆️ Update leejet/stable-diffusion.cpp to `3a8788cb7d74f185d6b18688e9563015524ecaf5` (#9933 ) ⬆️ Update leejet/stable-diffusion.cpp Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>	2026-05-22 00:31:19 +02:00