refactor(ui): trim leading whitespace from thinking content

Use strings.TrimLeft to remove leading spaces, tabs, and newlines
from thinking/reasoning content for cleaner left alignment.

btca.config.jsonc

@@ -76,6 +76,12 @@
       "name": "opencode",
       "url": "https://github.com/anomalyco/opencode",
       "branch": "dev"
+    },
+    {
+      "type": "git",
+      "name": "herald",
+      "url": "https://github.com/indaco/herald",
+      "branch": "main"
     }
   ],
   "model": "claude-haiku-4-5",

cmd/root.go

@@ -799,16 +799,26 @@ func runNormalMode(ctx context.Context) error {
 	appInstance := app.New(appOpts, messages)
 	defer appInstance.Close()
 
+	// Buffer for extension messages during startup (printed after startup banner).
+	var startupExtensionMessages []string
+
 	// Set up extension context and emit SessionStart.
 	if kitInstance.HasExtensions() {
 		cwd, _ := os.Getwd()
 		kitInstance.SetExtensionContext(extensions.Context{
-			CWD:           cwd,
-			Model:         modelName,
-			Interactive:   positionalPrompt == "",
-			Print:         func(text string) { appInstance.PrintFromExtension("", text) },
-			PrintInfo:     func(text string) { appInstance.PrintFromExtension("info", text) },
-			PrintError:    func(text string) { appInstance.PrintFromExtension("error", text) },
+			CWD:         cwd,
+			Model:       modelName,
+			Interactive: positionalPrompt == "",
+			Print: func(text string) {
+				// Capture messages during startup, print after startup banner.
+				startupExtensionMessages = append(startupExtensionMessages, text)
+			},
+			PrintInfo: func(text string) {
+				startupExtensionMessages = append(startupExtensionMessages, text)
+			},
+			PrintError: func(text string) {
+				startupExtensionMessages = append(startupExtensionMessages, text)
+			},
 			PrintBlock:    appInstance.PrintBlockFromExtension,
 			SendMessage:   func(text string) { appInstance.Run(text) },
 			CancelAndSend: func(text string) { appInstance.InterruptAndSend(text) },
@@ -1099,6 +1109,150 @@ func runNormalMode(ctx context.Context) error {
 			},
 		})
 		kitInstance.EmitSessionStart()
+
+		// Restore normal print functions for runtime use.
+		kitInstance.SetExtensionContext(extensions.Context{
+			CWD:           cwd,
+			Model:         modelName,
+			Interactive:   positionalPrompt == "",
+			Print:         func(text string) { appInstance.PrintFromExtension("", text) },
+			PrintInfo:     func(text string) { appInstance.PrintFromExtension("info", text) },
+			PrintError:    func(text string) { appInstance.PrintFromExtension("error", text) },
+			PrintBlock:    appInstance.PrintBlockFromExtension,
+			SendMessage:   func(text string) { appInstance.Run(text) },
+			CancelAndSend: func(text string) { appInstance.InterruptAndSend(text) },
+			Exit:          func() { appInstance.QuitFromExtension() },
+			SetWidget: func(config extensions.WidgetConfig) {
+				kitInstance.SetExtensionWidget(config)
+				appInstance.NotifyWidgetUpdate()
+			},
+			RemoveWidget: func(id string) {
+				kitInstance.RemoveExtensionWidget(id)
+				appInstance.NotifyWidgetUpdate()
+			},
+			SetHeader: func(config extensions.HeaderFooterConfig) {
+				kitInstance.SetExtensionHeader(config)
+				appInstance.NotifyWidgetUpdate()
+			},
+			RemoveHeader: func() {
+				kitInstance.RemoveExtensionHeader()
+				appInstance.NotifyWidgetUpdate()
+			},
+			SetFooter: func(config extensions.HeaderFooterConfig) {
+				kitInstance.SetExtensionFooter(config)
+				appInstance.NotifyWidgetUpdate()
+			},
+			RemoveFooter: func() {
+				kitInstance.RemoveExtensionFooter()
+				appInstance.NotifyWidgetUpdate()
+			},
+			PromptSelect: func(config extensions.PromptSelectConfig) extensions.PromptSelectResult {
+				ch := make(chan app.PromptResponse, 1)
+				appInstance.SendPromptRequest(app.PromptRequestEvent{
+					PromptType: "select",
+					Message:    config.Message,
+					Options:    config.Options,
+					ResponseCh: ch,
+				})
+				resp := <-ch
+				if resp.Cancelled {
+					return extensions.PromptSelectResult{Cancelled: true}
+				}
+				return extensions.PromptSelectResult{Value: resp.Value, Index: resp.Index}
+			},
+			PromptConfirm: func(config extensions.PromptConfirmConfig) extensions.PromptConfirmResult {
+				ch := make(chan app.PromptResponse, 1)
+				def := "false"
+				if config.DefaultValue {
+					def = "true"
+				}
+				appInstance.SendPromptRequest(app.PromptRequestEvent{
+					PromptType: "confirm",
+					Message:    config.Message,
+					Default:    def,
+					ResponseCh: ch,
+				})
+				resp := <-ch
+				if resp.Cancelled {
+					return extensions.PromptConfirmResult{Cancelled: true}
+				}
+				return extensions.PromptConfirmResult{Value: resp.Confirmed}
+			},
+			PromptInput: func(config extensions.PromptInputConfig) extensions.PromptInputResult {
+				ch := make(chan app.PromptResponse, 1)
+				appInstance.SendPromptRequest(app.PromptRequestEvent{
+					PromptType:  "input",
+					Message:     config.Message,
+					Placeholder: config.Placeholder,
+					Default:     config.Default,
+					ResponseCh:  ch,
+				})
+				resp := <-ch
+				if resp.Cancelled {
+					return extensions.PromptInputResult{Cancelled: true}
+				}
+				return extensions.PromptInputResult{Value: resp.Value}
+			},
+			ShowOverlay: func(config extensions.OverlayConfig) extensions.OverlayResult {
+				ch := make(chan app.OverlayResponse, 1)
+				appInstance.SendOverlayRequest(app.OverlayRequestEvent{
+					Title:       config.Title,
+					Content:     config.Content.Text,
+					Markdown:    config.Content.Markdown,
+					BorderColor: config.Style.BorderColor,
+					Background:  config.Style.Background,
+					Width:       config.Width,
+					MaxHeight:   config.MaxHeight,
+					Anchor:      string(config.Anchor),
+					Actions:     config.Actions,
+					ResponseCh:  ch,
+				})
+				resp := <-ch
+				if resp.Cancelled {
+					return extensions.OverlayResult{Cancelled: true, Index: -1}
+				}
+				return extensions.OverlayResult{
+					Action: resp.Action,
+					Index:  resp.Index,
+				}
+			},
+			SpawnSubagent: func(config extensions.SubagentConfig) (*extensions.SubagentHandle, *extensions.SubagentResult, error) {
+				// In-process subagent via SDK.
+				sdkCfg := kit.SubagentConfig{
+					Prompt:       config.Prompt,
+					Model:        config.Model,
+					SystemPrompt: config.SystemPrompt,
+					Timeout:      config.Timeout,
+					NoSession:    config.NoSession,
+				}
+				// Bridge SDK events to extension SubagentEvents.
+				if config.OnEvent != nil {
+					sdkCfg.OnEvent = func(e kit.Event) {
+						se := sdkEventToSubagentEvent(e)
+						if se.Type != "" {
+							config.OnEvent(se)
+						}
+					}
+				}
+				result, err := kitInstance.Subagent(ctx, sdkCfg)
+				if result == nil {
+					return nil, &extensions.SubagentResult{Error: err}, err
+				}
+				extResult := &extensions.SubagentResult{
+					Response:  result.Response,
+					Error:     result.Error,
+					SessionID: result.SessionID,
+					Elapsed:   result.Elapsed,
+				}
+				if result.Usage != nil {
+					extResult.Usage = &extensions.SubagentUsage{
+						InputTokens:  result.Usage.InputTokens,
+						OutputTokens: result.Usage.OutputTokens,
+					}
+				}
+				return nil, extResult, err
+			},
+		})
 	}
 
 	// Convert extension commands to UI-layer type for the interactive TUI.
@@ -1222,7 +1376,7 @@ func runNormalMode(ctx context.Context) error {
 		return fmt.Errorf("--quiet requires a prompt")
 	}
 
-	return runInteractiveModeBubbleTea(ctx, appInstance, modelName, parsedProvider, kitInstance.GetLoadingMessage(), serverNames, toolNames, mcpToolCount, extensionToolCount, usageTracker, extCommands, promptTemplates, contextPaths, skillItems, getWidgets, getHeader, getFooter, getToolRenderer, getEditorInterceptor, getUIVisibility, getStatusBarEntries, emitBeforeFork, emitBeforeSessionSwitch, getGlobalShortcuts, getExtensionCommands, setModelForUI, emitModelChangeForUI, kitInstance.IsReasoningModel(), kitInstance.GetThinkingLevel(), setThinkingLevelForUI, switchSessionForUI)
+	return runInteractiveModeBubbleTea(ctx, appInstance, modelName, parsedProvider, kitInstance.GetLoadingMessage(), serverNames, toolNames, mcpToolCount, extensionToolCount, usageTracker, extCommands, promptTemplates, contextPaths, skillItems, getWidgets, getHeader, getFooter, getToolRenderer, getEditorInterceptor, getUIVisibility, getStatusBarEntries, emitBeforeFork, emitBeforeSessionSwitch, getGlobalShortcuts, getExtensionCommands, setModelForUI, emitModelChangeForUI, kitInstance.IsReasoningModel(), kitInstance.GetThinkingLevel(), setThinkingLevelForUI, switchSessionForUI, startupExtensionMessages)
 }
 
 // runNonInteractiveModeApp executes a single prompt via the app layer and exits,
@@ -1278,7 +1432,7 @@ func runNonInteractiveModeApp(ctx context.Context, appInstance *app.App, cli *ui
 
 	// If --no-exit was requested, hand off to the interactive TUI.
 	if noExit {
-		return runInteractiveModeBubbleTea(ctx, appInstance, modelName, providerName, loadingMessage, serverNames, toolNames, mcpToolCount, extensionToolCount, usageTracker, extCommands, promptTemplates, contextPaths, skillItems, getWidgets, getHeader, getFooter, getToolRenderer, getEditorInterceptor, getUIVisibility, getStatusBarEntries, emitBeforeFork, emitBeforeSessionSwitch, getGlobalShortcuts, getExtensionCommands, setModel, emitModelChange, isReasoningModel, thinkingLevel, setThinkingLevel, switchSession)
+		return runInteractiveModeBubbleTea(ctx, appInstance, modelName, providerName, loadingMessage, serverNames, toolNames, mcpToolCount, extensionToolCount, usageTracker, extCommands, promptTemplates, contextPaths, skillItems, getWidgets, getHeader, getFooter, getToolRenderer, getEditorInterceptor, getUIVisibility, getStatusBarEntries, emitBeforeFork, emitBeforeSessionSwitch, getGlobalShortcuts, getExtensionCommands, setModel, emitModelChange, isReasoningModel, thinkingLevel, setThinkingLevel, switchSession, nil)
 	}
 
 	return nil
@@ -1376,7 +1530,7 @@ func writeJSONError(err error) {
 //  4. Calls program.Run() which blocks until the user quits (Ctrl+C or /quit).
 //
 // SetupCLI is not used for interactive mode; the TUI (AppModel) handles its own rendering.
-func runInteractiveModeBubbleTea(_ context.Context, appInstance *app.App, modelName, providerName, loadingMessage string, serverNames, toolNames []string, mcpToolCount, extensionToolCount int, usageTracker *ui.UsageTracker, extCommands []ui.ExtensionCommand, promptTemplates []*prompts.PromptTemplate, contextPaths []string, skillItems []ui.SkillItem, getWidgets func(string) []ui.WidgetData, getHeader, getFooter func() *ui.WidgetData, getToolRenderer func(string) *ui.ToolRendererData, getEditorInterceptor func() *ui.EditorInterceptor, getUIVisibility func() *ui.UIVisibility, getStatusBarEntries func() []ui.StatusBarEntryData, emitBeforeFork func(string, bool, string) (bool, string), emitBeforeSessionSwitch func(string) (bool, string), getGlobalShortcuts func() map[string]func(), getExtensionCommands func() []ui.ExtensionCommand, setModel func(string) error, emitModelChange func(string, string, string), isReasoningModel bool, thinkingLevel string, setThinkingLevel func(string) error, switchSession func(string) error) error {
+func runInteractiveModeBubbleTea(_ context.Context, appInstance *app.App, modelName, providerName, loadingMessage string, serverNames, toolNames []string, mcpToolCount, extensionToolCount int, usageTracker *ui.UsageTracker, extCommands []ui.ExtensionCommand, promptTemplates []*prompts.PromptTemplate, contextPaths []string, skillItems []ui.SkillItem, getWidgets func(string) []ui.WidgetData, getHeader, getFooter func() *ui.WidgetData, getToolRenderer func(string) *ui.ToolRendererData, getEditorInterceptor func() *ui.EditorInterceptor, getUIVisibility func() *ui.UIVisibility, getStatusBarEntries func() []ui.StatusBarEntryData, emitBeforeFork func(string, bool, string) (bool, string), emitBeforeSessionSwitch func(string) (bool, string), getGlobalShortcuts func() map[string]func(), getExtensionCommands func() []ui.ExtensionCommand, setModel func(string) error, emitModelChange func(string, string, string), isReasoningModel bool, thinkingLevel string, setThinkingLevel func(string) error, switchSession func(string) error, startupExtensionMessages []string) error {
 	// Determine terminal size; fall back gracefully.
 	termWidth, termHeight, err := term.GetSize(int(os.Stdout.Fd()))
 	if err != nil || termWidth == 0 {
@@ -1426,6 +1580,15 @@ func runInteractiveModeBubbleTea(_ context.Context, appInstance *app.App, modelN
 	// Print startup info to stdout before Bubble Tea takes over the screen.
 	appModel.PrintStartupInfo()
 
+	// Print any extension messages that were captured during startup.
+	if len(startupExtensionMessages) > 0 {
+		fmt.Println()
+		for _, msg := range startupExtensionMessages {
+			fmt.Println(msg)
+		}
+		fmt.Println()
+	}
+
 	program := tea.NewProgram(appModel)
 
 	// Register the program with the app layer so agent events are sent to the TUI.

go.mod

@@ -82,6 +82,7 @@ require (
 	github.com/googleapis/gax-go/v2 v2.20.0 // indirect
 	github.com/gorilla/css v1.0.1 // indirect
 	github.com/gorilla/websocket v1.5.3 // indirect
+	github.com/indaco/herald v0.9.0 // indirect
 	github.com/kaptinlin/go-i18n v0.2.12 // indirect
 	github.com/kaptinlin/jsonpointer v0.4.17 // indirect
 	github.com/kaptinlin/jsonschema v0.7.6 // indirect

go.sum

@@ -187,6 +187,8 @@ github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUq
 github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
+github.com/indaco/herald v0.9.0 h1:LrAfXEHkKz8WmctUKdndppIU/qFpylSbZ8galS0DVAc=
+github.com/indaco/herald v0.9.0/go.mod h1:T5g1+XLYvpjouhzAGHnAHDCKizhESkoV6+QPZ3DhgWA=
 github.com/kaptinlin/go-i18n v0.2.12 h1:ywDsvb4KDFddMC2dpI/rrIzGU2mWUSvHmWUm9BMsdl4=
 github.com/kaptinlin/go-i18n v0.2.12/go.mod h1:pVcu9qsW5pOIOoZFJXesRYmLos1vMQrby70JPAoWmJU=
 github.com/kaptinlin/jsonpointer v0.4.17 h1:mY9k8ciWncxbsECyaxKnR0MdmxamNdp2tLQkAKVrtSk=

internal/app/app.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"os"
 	"sync"
+	"sync/atomic"
 
 	tea "charm.land/bubbletea/v2"
 	"charm.land/fantasy"
@@ -598,9 +599,10 @@ func (a *App) executeStep(ctx context.Context, prompt string, eventFn func(tea.M
 		}
 	}
 
-	// Subscribe to SDK events for TUI rendering. The subscription is
-	// temporary — it lives only for the duration of this step.
-	unsub := a.subscribeSDKEvents(sendFn)
+	// Subscribe to SDK events for TUI rendering and per-step usage updates.
+	// The subscription is temporary — it lives only for the duration of this step.
+	var sawStepUsage atomic.Bool
+	unsub := a.subscribeSDKEvents(sendFn, &sawStepUsage)
 	defer unsub()
 
 	// Show spinner while the agent works.
@@ -620,8 +622,9 @@ func (a *App) executeStep(ctx context.Context, prompt string, eventFn func(tea.M
 	// Sync in-memory store with the SDK's authoritative conversation.
 	a.store.Replace(result.Messages)
 
-	// Update usage tracker.
-	a.updateUsageFromTurnResult(result, prompt)
+	// Update usage tracker. If per-step usage was already recorded from
+	// StepUsageEvent callbacks, avoid double-counting totals.
+	a.updateUsageFromTurnResult(result, prompt, sawStepUsage.Load())
 
 	return result, nil
 }
@@ -645,9 +648,10 @@ func (a *App) executeBatch(ctx context.Context, items []queueItem, eventFn func(
 		}
 	}
 
-	// Subscribe to SDK events for TUI rendering. The subscription is
-	// temporary — it lives only for the duration of this step.
-	unsub := a.subscribeSDKEvents(sendFn)
+	// Subscribe to SDK events for TUI rendering and per-step usage updates.
+	// The subscription is temporary — it lives only for the duration of this step.
+	var sawStepUsage atomic.Bool
+	unsub := a.subscribeSDKEvents(sendFn, &sawStepUsage)
 	defer unsub()
 
 	// Show spinner while the agent works.
@@ -702,8 +706,10 @@ func (a *App) executeBatch(ctx context.Context, items []queueItem, eventFn func(
 	// Sync in-memory store with the SDK's authoritative conversation.
 	a.store.Replace(result.Messages)
 
-	// Update usage tracker (using last item's prompt for tracking).
-	a.updateUsageFromTurnResult(result, items[len(items)-1].Prompt)
+	// Update usage tracker (using last item's prompt for fallback estimation).
+	// If per-step usage was already recorded from StepUsageEvent callbacks,
+	// avoid double-counting totals.
+	a.updateUsageFromTurnResult(result, items[len(items)-1].Prompt, sawStepUsage.Load())
 
 	return result, nil
 }
@@ -720,9 +726,10 @@ func (a *App) sendEvent(msg tea.Msg) {
 }
 
 // subscribeSDKEvents registers temporary SDK event subscribers that convert
-// SDK events to tea.Msg events and dispatch them via sendFn. Returns an
-// unsubscribe function that removes all listeners.
-func (a *App) subscribeSDKEvents(sendFn func(tea.Msg)) func() {
+// SDK events to tea.Msg events and dispatch them via sendFn. When stepUsageSeen
+// is provided, it is set to true after any non-zero StepUsageEvent is observed.
+// Returns an unsubscribe function that removes all listeners.
+func (a *App) subscribeSDKEvents(sendFn func(tea.Msg), stepUsageSeen *atomic.Bool) func() {
 	k := a.opts.Kit
 	var unsubs []func()
 
@@ -756,6 +763,8 @@ func (a *App) subscribeSDKEvents(sendFn func(tea.Msg)) func() {
 			})
 		case kit.SteerConsumedEvent:
 			sendFn(SteerConsumedEvent{})
+		case kit.StepUsageEvent:
+			a.recordStepUsage(ev, stepUsageSeen)
 		}
 	}))
 
@@ -925,32 +934,56 @@ func (a *App) PrintBlockFromExtension(opts extensions.PrintBlockOpts) {
 	}
 }
 
+// recordStepUsage applies token/cost usage reported for a completed step.
+// Step usage events arrive even when a turn is later cancelled, so this keeps
+// the usage widget accurate on all stop paths.
+func (a *App) recordStepUsage(ev kit.StepUsageEvent, stepUsageSeen *atomic.Bool) {
+	hasUsage := ev.InputTokens > 0 || ev.OutputTokens > 0 || ev.CacheReadTokens > 0 || ev.CacheWriteTokens > 0
+	if !hasUsage {
+		return
+	}
+	if stepUsageSeen != nil {
+		stepUsageSeen.Store(true)
+	}
+	if a.opts.UsageTracker == nil {
+		return
+	}
+	a.opts.UsageTracker.UpdateUsage(
+		int(ev.InputTokens),
+		int(ev.OutputTokens),
+		int(ev.CacheReadTokens),
+		int(ev.CacheWriteTokens),
+	)
+	// Keep context fill reasonably fresh during long/partial turns.
+	a.opts.UsageTracker.SetContextTokens(int(ev.InputTokens + ev.OutputTokens))
+}
+
 // updateUsageFromTurnResult records token usage from an SDK TurnResult into the
 // configured UsageTracker. Called once per turn after the turn completes.
 //
-// Cost/token accumulation uses TotalUsage (sum across all tool-calling steps in
-// the turn). Context-window fill uses FinalUsage.InputTokens only — that is the
-// number of tokens sent to the model on the last API call, which equals the
-// actual context window occupation (all accumulated messages + tool results).
-// OutputTokens are not added here because they are the response length, not
-// context fill.
-func (a *App) updateUsageFromTurnResult(result *kit.TurnResult, userPrompt string) {
+// When sawStepUsage is true, totals were already accumulated incrementally via
+// StepUsageEvent callbacks; in that case this method only updates context fill.
+// Otherwise it falls back to TotalUsage (or estimation) to keep costs/tokens
+// visible for providers/modes that don't emit per-step usage.
+func (a *App) updateUsageFromTurnResult(result *kit.TurnResult, userPrompt string, sawStepUsage bool) {
 	if a.opts.UsageTracker == nil || result == nil {
 		return
 	}
 
 	// --- Accumulate cost/token totals for the session ---
-	if result.TotalUsage != nil && result.TotalUsage.InputTokens > 0 {
-		a.opts.UsageTracker.UpdateUsage(
-			int(result.TotalUsage.InputTokens),
-			int(result.TotalUsage.OutputTokens),
-			int(result.TotalUsage.CacheReadTokens),
-			int(result.TotalUsage.CacheCreationTokens),
-		)
-	} else {
-		// Provider didn't report token counts — fall back to character-based
-		// estimates so the footer shows something rather than nothing.
-		a.opts.UsageTracker.EstimateAndUpdateUsage(userPrompt, result.Response)
+	if !sawStepUsage {
+		if result.TotalUsage != nil && result.TotalUsage.InputTokens > 0 {
+			a.opts.UsageTracker.UpdateUsage(
+				int(result.TotalUsage.InputTokens),
+				int(result.TotalUsage.OutputTokens),
+				int(result.TotalUsage.CacheReadTokens),
+				int(result.TotalUsage.CacheCreationTokens),
+			)
+		} else {
+			// Provider didn't report token counts — fall back to character-based
+			// estimates so the footer shows something rather than nothing.
+			a.opts.UsageTracker.EstimateAndUpdateUsage(userPrompt, result.Response)
+		}
 	}
 
 	// --- Context window fill (drives the % bar) ---

internal/app/app_test.go

@@ -7,6 +7,8 @@ import (
 	"testing"
 	"time"
 
+	"charm.land/fantasy"
+
 	kit "github.com/mark3labs/kit/pkg/kit"
 )
 
@@ -14,6 +16,47 @@ import (
 // Helpers
 // --------------------------------------------------------------------------
 
+type usageUpdaterStub struct {
+	mu sync.Mutex
+
+	updateCalls   int
+	estimateCalls int
+	contextCalls  int
+
+	lastUpdateInput      int
+	lastUpdateOutput     int
+	lastUpdateCacheRead  int
+	lastUpdateCacheWrite int
+	lastContextTokens    int
+	lastEstimateInput    string
+	lastEstimateOutput   string
+}
+
+func (s *usageUpdaterStub) UpdateUsage(inputTokens, outputTokens, cacheReadTokens, cacheWriteTokens int) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.updateCalls++
+	s.lastUpdateInput = inputTokens
+	s.lastUpdateOutput = outputTokens
+	s.lastUpdateCacheRead = cacheReadTokens
+	s.lastUpdateCacheWrite = cacheWriteTokens
+}
+
+func (s *usageUpdaterStub) EstimateAndUpdateUsage(inputText, outputText string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.estimateCalls++
+	s.lastEstimateInput = inputText
+	s.lastEstimateOutput = outputText
+}
+
+func (s *usageUpdaterStub) SetContextTokens(tokens int) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.contextCalls++
+	s.lastContextTokens = tokens
+}
+
 // turnResult builds a minimal TurnResult with response text t.
 func turnResult(t string) *kit.TurnResult {
 	return &kit.TurnResult{Response: t}
@@ -489,3 +532,67 @@ func TestQueueLength_reflects(t *testing.T) {
 		t.Fatalf("expected 3, got %d", got)
 	}
 }
+
+// TestRecordStepUsage_updatesTracker verifies that per-step usage updates are
+// recorded immediately (including context tokens) for stop-path correctness.
+func TestRecordStepUsage_updatesTracker(t *testing.T) {
+	usage := &usageUpdaterStub{}
+	app := New(Options{UsageTracker: usage}, nil)
+	defer app.Close()
+
+	app.recordStepUsage(kit.StepUsageEvent{
+		InputTokens:      120,
+		OutputTokens:     45,
+		CacheReadTokens:  5,
+		CacheWriteTokens: 2,
+	}, nil)
+
+	usage.mu.Lock()
+	defer usage.mu.Unlock()
+
+	if usage.updateCalls != 1 {
+		t.Fatalf("expected 1 update call, got %d", usage.updateCalls)
+	}
+	if usage.lastUpdateInput != 120 || usage.lastUpdateOutput != 45 || usage.lastUpdateCacheRead != 5 || usage.lastUpdateCacheWrite != 2 {
+		t.Fatalf("unexpected usage update payload: in=%d out=%d cache_read=%d cache_write=%d",
+			usage.lastUpdateInput, usage.lastUpdateOutput, usage.lastUpdateCacheRead, usage.lastUpdateCacheWrite)
+	}
+	if usage.contextCalls != 1 {
+		t.Fatalf("expected 1 context token update, got %d", usage.contextCalls)
+	}
+	if usage.lastContextTokens != 165 {
+		t.Fatalf("expected context tokens 165, got %d", usage.lastContextTokens)
+	}
+}
+
+// TestUpdateUsageFromTurnResult_skipsTotalsWhenStepUsageSeen ensures we avoid
+// double-counting totals once StepUsageEvent-based updates were already applied.
+func TestUpdateUsageFromTurnResult_skipsTotalsWhenStepUsageSeen(t *testing.T) {
+	usage := &usageUpdaterStub{}
+	app := New(Options{UsageTracker: usage}, nil)
+	defer app.Close()
+
+	app.updateUsageFromTurnResult(&kit.TurnResult{
+		Response: "ok",
+		TotalUsage: &fantasy.Usage{
+			InputTokens:         999,
+			OutputTokens:        111,
+			CacheReadTokens:     7,
+			CacheCreationTokens: 3,
+		},
+		FinalUsage: &fantasy.Usage{InputTokens: 456},
+	}, "prompt", true)
+
+	usage.mu.Lock()
+	defer usage.mu.Unlock()
+
+	if usage.updateCalls != 0 {
+		t.Fatalf("expected no total usage update when sawStepUsage=true, got %d", usage.updateCalls)
+	}
+	if usage.estimateCalls != 0 {
+		t.Fatalf("expected no estimate update when sawStepUsage=true, got %d", usage.estimateCalls)
+	}
+	if usage.contextCalls != 1 || usage.lastContextTokens != 456 {
+		t.Fatalf("expected final context tokens=456, got calls=%d tokens=%d", usage.contextCalls, usage.lastContextTokens)
+	}
+}

internal/extensions/runner.go

@@ -56,11 +56,165 @@ func NewRunner(exts []LoadedExtension) *Runner {
 }
 
 // SetContext updates the runtime context (session ID, model, etc.) that is
-// passed to every handler invocation. Thread-safe.
+// passed to every handler invocation. Nil function fields are replaced with
+// safe no-ops so extension handlers never panic on a missing callback.
+// Thread-safe.
 func (r *Runner) SetContext(ctx Context) {
 	r.mu.Lock()
 	defer r.mu.Unlock()
-	r.ctx = ctx
+	r.ctx = normalizeContext(ctx)
+}
+
+// normalizeContext replaces nil function fields in ctx with no-op stubs so
+// that extension handlers can call any ctx method without a nil-function panic.
+func normalizeContext(ctx Context) Context {
+	if ctx.Print == nil {
+		ctx.Print = func(string) {}
+	}
+	if ctx.PrintInfo == nil {
+		ctx.PrintInfo = func(string) {}
+	}
+	if ctx.PrintError == nil {
+		ctx.PrintError = func(string) {}
+	}
+	if ctx.PrintBlock == nil {
+		ctx.PrintBlock = func(PrintBlockOpts) {}
+	}
+	if ctx.SendMessage == nil {
+		ctx.SendMessage = func(string) {}
+	}
+	if ctx.CancelAndSend == nil {
+		ctx.CancelAndSend = func(string) {}
+	}
+	if ctx.SetWidget == nil {
+		ctx.SetWidget = func(WidgetConfig) {}
+	}
+	if ctx.RemoveWidget == nil {
+		ctx.RemoveWidget = func(string) {}
+	}
+	if ctx.SetHeader == nil {
+		ctx.SetHeader = func(HeaderFooterConfig) {}
+	}
+	if ctx.RemoveHeader == nil {
+		ctx.RemoveHeader = func() {}
+	}
+	if ctx.SetFooter == nil {
+		ctx.SetFooter = func(HeaderFooterConfig) {}
+	}
+	if ctx.RemoveFooter == nil {
+		ctx.RemoveFooter = func() {}
+	}
+	if ctx.PromptSelect == nil {
+		ctx.PromptSelect = func(PromptSelectConfig) PromptSelectResult {
+			return PromptSelectResult{Cancelled: true}
+		}
+	}
+	if ctx.PromptConfirm == nil {
+		ctx.PromptConfirm = func(PromptConfirmConfig) PromptConfirmResult {
+			return PromptConfirmResult{Cancelled: true}
+		}
+	}
+	if ctx.PromptInput == nil {
+		ctx.PromptInput = func(PromptInputConfig) PromptInputResult {
+			return PromptInputResult{Cancelled: true}
+		}
+	}
+	if ctx.PromptMultiSelect == nil {
+		ctx.PromptMultiSelect = func(PromptMultiSelectConfig) PromptMultiSelectResult {
+			return PromptMultiSelectResult{Cancelled: true}
+		}
+	}
+	if ctx.ShowOverlay == nil {
+		ctx.ShowOverlay = func(OverlayConfig) OverlayResult {
+			return OverlayResult{Cancelled: true, Index: -1}
+		}
+	}
+	if ctx.SetEditor == nil {
+		ctx.SetEditor = func(EditorConfig) {}
+	}
+	if ctx.ResetEditor == nil {
+		ctx.ResetEditor = func() {}
+	}
+	if ctx.SetEditorText == nil {
+		ctx.SetEditorText = func(string) {}
+	}
+	if ctx.SetUIVisibility == nil {
+		ctx.SetUIVisibility = func(UIVisibility) {}
+	}
+	if ctx.SetStatus == nil {
+		ctx.SetStatus = func(string, string, int) {}
+	}
+	if ctx.RemoveStatus == nil {
+		ctx.RemoveStatus = func(string) {}
+	}
+	if ctx.GetContextStats == nil {
+		ctx.GetContextStats = func() ContextStats { return ContextStats{} }
+	}
+	if ctx.GetMessages == nil {
+		ctx.GetMessages = func() []SessionMessage { return nil }
+	}
+	if ctx.GetSessionPath == nil {
+		ctx.GetSessionPath = func() string { return "" }
+	}
+	if ctx.AppendEntry == nil {
+		ctx.AppendEntry = func(string, string) (string, error) { return "", nil }
+	}
+	if ctx.GetEntries == nil {
+		ctx.GetEntries = func(string) []ExtensionEntry { return nil }
+	}
+	if ctx.GetOption == nil {
+		ctx.GetOption = func(string) string { return "" }
+	}
+	if ctx.SetOption == nil {
+		ctx.SetOption = func(string, string) {}
+	}
+	if ctx.SetModel == nil {
+		ctx.SetModel = func(string) error { return nil }
+	}
+	if ctx.GetAvailableModels == nil {
+		ctx.GetAvailableModels = func() []ModelInfoEntry { return nil }
+	}
+	if ctx.EmitCustomEvent == nil {
+		ctx.EmitCustomEvent = func(string, string) {}
+	}
+	if ctx.GetAllTools == nil {
+		ctx.GetAllTools = func() []ToolInfo { return nil }
+	}
+	if ctx.SetActiveTools == nil {
+		ctx.SetActiveTools = func([]string) {}
+	}
+	if ctx.Exit == nil {
+		ctx.Exit = func() {}
+	}
+	if ctx.Complete == nil {
+		ctx.Complete = func(CompleteRequest) (CompleteResponse, error) {
+			return CompleteResponse{}, nil
+		}
+	}
+	if ctx.SuspendTUI == nil {
+		ctx.SuspendTUI = func(callback func()) error { callback(); return nil }
+	}
+	if ctx.RenderMessage == nil {
+		ctx.RenderMessage = func(string, string) {}
+	}
+	if ctx.RegisterTheme == nil {
+		ctx.RegisterTheme = func(string, ThemeColorConfig) {}
+	}
+	if ctx.SetTheme == nil {
+		ctx.SetTheme = func(string) error { return nil }
+	}
+	if ctx.ListThemes == nil {
+		ctx.ListThemes = func() []string { return nil }
+	}
+	if ctx.ReloadExtensions == nil {
+		ctx.ReloadExtensions = func() error { return nil }
+	}
+	if ctx.SpawnSubagent == nil {
+		ctx.SpawnSubagent = func(SubagentConfig) (*SubagentHandle, *SubagentResult, error) {
+			return nil, nil, nil
+		}
+	}
+	return ctx
 }
 
 // GetContext returns a snapshot of the current runtime context. Thread-safe.

internal/ui/children_test.go

@@ -349,7 +349,7 @@ func TestStreamComponent_SpinnerKeepsRunningDuringStreaming(t *testing.T) {
 	c = sendStreamMsg(c, app.StreamChunkEvent{Content: "hello"})
 
 	// Flush pending chunks (simulates the 16ms tick firing).
-	c = sendStreamMsg(c, streamFlushTickMsg{})
+	c = sendStreamMsg(c, streamFlushTickMsg{generation: c.flushGeneration})
 
 	if !c.spinning {
 		t.Fatal("expected spinning=true after first chunk")
@@ -376,7 +376,7 @@ func TestStreamComponent_ChunkAccumulation(t *testing.T) {
 	}
 
 	// Flush pending chunks (simulates the 16ms tick firing).
-	c = sendStreamMsg(c, streamFlushTickMsg{})
+	c = sendStreamMsg(c, streamFlushTickMsg{generation: c.flushGeneration})
 
 	got := c.streamContent.String()
 	want := "Hello, world!"
@@ -396,6 +396,7 @@ func TestStreamComponent_ToolExecution_IsStarting_ShowsSpinner(t *testing.T) {
 	c := newTestStream()
 
 	_, cmd := c.Update(app.ToolExecutionEvent{
+		ToolCallID: "call-exec-1",
 		ToolName:   "exec_tool",
 		IsStarting: true,
 	})
@@ -403,8 +404,9 @@ func TestStreamComponent_ToolExecution_IsStarting_ShowsSpinner(t *testing.T) {
 	if !c.spinning {
 		t.Fatal("expected spinning=true during tool execution")
 	}
-	if len(c.activeTools) != 1 || !strings.Contains(c.activeTools[0], "exec_tool") {
-		t.Fatalf("expected activeTools to contain tool name, got %v", c.activeTools)
+	tools := c.activeToolDisplays()
+	if len(tools) != 1 || !strings.Contains(tools[0], "exec_tool") {
+		t.Fatalf("expected activeTools to contain tool name, got %v", tools)
 	}
 	if cmd == nil {
 		t.Fatal("expected tick cmd from ToolExecutionEvent{IsStarting:true}")
@@ -418,11 +420,13 @@ func TestStreamComponent_ToolExecution_NotStarting_KeepsSpinning(t *testing.T) {
 	c = sendStreamMsg(c, app.SpinnerEvent{Show: true})
 	// Simulate a tool starting
 	c = sendStreamMsg(c, app.ToolExecutionEvent{
+		ToolCallID: "call-some-1",
 		ToolName:   "some_tool",
 		IsStarting: true,
 	})
 
 	c = sendStreamMsg(c, app.ToolExecutionEvent{
+		ToolCallID: "call-some-1",
 		ToolName:   "some_tool",
 		IsStarting: false,
 	})
@@ -440,9 +444,9 @@ func TestStreamComponent_ParallelToolExecution(t *testing.T) {
 	c := newTestStream()
 
 	// Start three tools in parallel
-	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolName: "read", IsStarting: true})
-	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolName: "grep", IsStarting: true})
-	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolName: "find", IsStarting: true})
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-read", ToolName: "read", IsStarting: true})
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-grep", ToolName: "grep", IsStarting: true})
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-find", ToolName: "find", IsStarting: true})
 
 	if len(c.activeTools) != 3 {
 		t.Fatalf("expected 3 active tools, got %d: %v", len(c.activeTools), c.activeTools)
@@ -455,19 +459,44 @@ func TestStreamComponent_ParallelToolExecution(t *testing.T) {
 	}
 
 	// Finish one tool
-	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolName: "grep", IsStarting: false})
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-grep", ToolName: "grep", IsStarting: false})
 	if len(c.activeTools) != 2 {
 		t.Fatalf("expected 2 active tools after one finished, got %d: %v", len(c.activeTools), c.activeTools)
 	}
 
 	// Finish remaining tools
-	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolName: "read", IsStarting: false})
-	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolName: "find", IsStarting: false})
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-read", ToolName: "read", IsStarting: false})
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-find", ToolName: "find", IsStarting: false})
 	if len(c.activeTools) != 0 {
 		t.Fatalf("expected 0 active tools after all finished, got %d: %v", len(c.activeTools), c.activeTools)
 	}
 }
 
+// TestStreamComponent_ParallelSameToolName_UsesToolCallID verifies finishing one
+// tool call does not remove another concurrent call with the same tool name.
+func TestStreamComponent_ParallelSameToolName_UsesToolCallID(t *testing.T) {
+	c := newTestStream()
+
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-read-1", ToolName: "read", IsStarting: true})
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-read-2", ToolName: "read", IsStarting: true})
+
+	tools := c.activeToolDisplays()
+	if len(tools) != 2 {
+		t.Fatalf("expected 2 active read calls, got %d (%v)", len(tools), tools)
+	}
+
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-read-1", ToolName: "read", IsStarting: false})
+	tools = c.activeToolDisplays()
+	if len(tools) != 1 {
+		t.Fatalf("expected 1 active read call after finishing one ID, got %d (%v)", len(tools), tools)
+	}
+
+	c = sendStreamMsg(c, app.ToolExecutionEvent{ToolCallID: "call-read-2", ToolName: "read", IsStarting: false})
+	if len(c.activeToolDisplays()) != 0 {
+		t.Fatalf("expected no active tools after finishing both IDs, got %v", c.activeToolDisplays())
+	}
+}
+
 // --------------------------------------------------------------------------
 // TestStreamComponent_GetRenderedContent verifies the method returns rendered
 // text when content is accumulated, and empty string when not.
@@ -621,3 +650,43 @@ func TestStreamComponent_StaleTick_Discarded(t *testing.T) {
 		t.Fatal("current-gen tick should reschedule")
 	}
 }
+
+// TestStreamComponent_StaleFlushTick_Discarded verifies that flush ticks from a
+// previous generation (e.g. pre-Reset) are ignored.
+func TestStreamComponent_StaleFlushTick_Discarded(t *testing.T) {
+	c := newTestStream()
+
+	// Start a pending flush and capture its generation.
+	c = sendStreamMsg(c, app.StreamChunkEvent{Content: "old"})
+	staleGen := c.flushGeneration
+	if !c.flushPending {
+		t.Fatal("precondition: expected flushPending=true after first chunk")
+	}
+
+	// Reset should invalidate in-flight flush ticks.
+	c.Reset()
+	if c.flushGeneration == staleGen {
+		t.Fatal("expected flushGeneration to change after Reset")
+	}
+
+	// New content in a new generation.
+	c = sendStreamMsg(c, app.StreamChunkEvent{Content: "new"})
+	if got := c.pendingStream.String(); got != "new" {
+		t.Fatalf("expected pendingStream='new', got %q", got)
+	}
+
+	// Stale flush tick should be ignored.
+	c = sendStreamMsg(c, streamFlushTickMsg{generation: staleGen})
+	if got := c.pendingStream.String(); got != "new" {
+		t.Fatalf("stale flush tick should not commit pending stream, got %q", got)
+	}
+
+	// Current generation flush should commit.
+	c = sendStreamMsg(c, streamFlushTickMsg{generation: c.flushGeneration})
+	if got := c.pendingStream.String(); got != "" {
+		t.Fatalf("expected pendingStream empty after current flush, got %q", got)
+	}
+	if got := c.streamContent.String(); got != "new" {
+		t.Fatalf("expected streamContent='new' after current flush, got %q", got)
+	}
+}

internal/ui/messages.go

@@ -9,6 +9,7 @@ import (
 	"time"
 
 	"charm.land/lipgloss/v2"
+	"github.com/indaco/herald"
 )
 
 // ansiEscapeRe matches ANSI escape sequences used for terminal styling.
@@ -22,9 +23,9 @@ const (
 	UserMessage MessageType = iota
 	AssistantMessage
 	ToolMessage
-	ToolCallMessage // New type for showing tool calls in progress
-	SystemMessage   // New type for KIT system messages (help, tools, etc.)
-	ErrorMessage    // New type for error messages
+	ToolCallMessage
+	SystemMessage
+	ErrorMessage
 )
 
 // UIMessage encapsulates a fully rendered message ready for display in the UI,
@@ -40,25 +41,23 @@ type UIMessage struct {
 	Streaming bool
 }
 
-// Helper functions to get theme colors
+// toolDisplayNames maps raw tool names to human-friendly display names.
+var toolDisplayNames = map[string]string{
+	"bash":  "Bash",
+	"read":  "Read",
+	"write": "Write",
+	"edit":  "Edit",
+	"grep":  "Grep",
+	"find":  "Find",
+	"ls":    "Ls",
+}
+
+// getTheme returns the current theme (helper for compact_renderer.go)
 func getTheme() Theme {
 	return GetTheme()
 }
 
-// toolDisplayNames maps raw tool names to human-friendly display names.
-var toolDisplayNames = map[string]string{
-	"bash":          "Bash",
-	"read":          "Read",
-	"write":         "Write",
-	"edit":          "Edit",
-	"grep":          "Grep",
-	"find":          "Find",
-	"ls":            "Ls",
-	"run_shell_cmd": "Bash",
-}
-
 // toolDisplayName returns a human-friendly display name for a tool.
-// Falls back to capitalizing the first letter of the raw name.
 func toolDisplayName(rawName string) string {
 	if display, ok := toolDisplayNames[rawName]; ok {
 		return display
@@ -70,8 +69,6 @@ func toolDisplayName(rawName string) string {
 }
 
 // formatToolParams formats tool input parameters for inline header display.
-// Extracts the primary parameter (command/filePath) first, then shows
-// remaining params as (key=val, ...). Truncates to maxWidth.
 func formatToolParams(toolArgs string, maxWidth int) string {
 	args := strings.TrimSpace(toolArgs)
 	if args == "" || args == "{}" {
@@ -80,7 +77,6 @@ func formatToolParams(toolArgs string, maxWidth int) string {
 
 	var params map[string]any
 	if err := json.Unmarshal([]byte(args), &params); err != nil {
-		// Fallback: strip braces and return raw content
 		args = strings.TrimPrefix(args, "{")
 		args = strings.TrimSuffix(args, "}")
 		args = strings.TrimSpace(args)
@@ -94,7 +90,6 @@ func formatToolParams(toolArgs string, maxWidth int) string {
 		return ""
 	}
 
-	// Identify primary parameter by checking known keys in priority order
 	primaryKeys := []string{"command", "filePath", "path", "pattern", "query", "url"}
 	var primaryKey string
 	var primaryVal string
@@ -111,8 +106,6 @@ func formatToolParams(toolArgs string, maxWidth int) string {
 		result.WriteString(primaryVal)
 	}
 
-	// Collect remaining parameters, skipping body-content keys (already
-	// rendered in the tool body) and any values that are too large.
 	bodyKeys := map[string]bool{
 		"content":  true,
 		"old_text": true,
@@ -155,65 +148,35 @@ func formatToolParams(toolArgs string, maxWidth int) string {
 }
 
 // MessageRenderer handles the formatting and rendering of different message types
-// with consistent styling, markdown support, and appropriate visual hierarchies
-// for the standard (non-compact) display mode.
 type MessageRenderer struct {
-	width int
-	debug bool
-
-	// getToolRenderer returns extension-provided rendering overrides for a
-	// specific tool. May be nil if no extensions are loaded. Used in
-	// RenderToolMessage to check for custom header/body formatting before
-	// falling back to builtin renderers.
+	width           int
+	debug           bool
+	ty              *herald.Typography
 	getToolRenderer func(toolName string) *ToolRendererData
 }
 
-// newMessageRenderer creates and initializes a new MessageRenderer with the specified
-// terminal width and debug mode setting. The width parameter determines line wrapping
-// and layout calculations.
+// newMessageRenderer creates and initializes a new MessageRenderer
 func newMessageRenderer(width int, debug bool) *MessageRenderer {
 	return &MessageRenderer{
 		width: width,
 		debug: debug,
+		ty:    createTypography(GetTheme()),
 	}
 }
 
-// SetWidth updates the terminal width for the renderer, affecting how content
-// is wrapped and formatted in subsequent render operations.
+// SetWidth updates the terminal width for the renderer
 func (r *MessageRenderer) SetWidth(width int) {
 	r.width = width
 }
 
-// RenderUserMessage renders a user's input message with distinctive right-aligned
-// formatting, including the system username, timestamp, and markdown-rendered content.
-// The message is displayed with a colored right border for visual distinction.
+// RenderUserMessage renders a user's input message using herald Tip alert
 func (r *MessageRenderer) RenderUserMessage(content string, timestamp time.Time) UIMessage {
-	theme := getTheme()
-
-	// Only run markdown rendering when the message contains code spans or
-	// fenced code blocks. Plain text is rendered directly so that newlines
-	// are preserved without the extra paragraph spacing glamour adds.
-	var messageContent string
-	if strings.Contains(content, "`") {
-		// Glamour treats single \n as a soft break, so convert to paragraph
-		// breaks and collapse the resulting blank lines after rendering.
-		mdContent := strings.ReplaceAll(content, "\n", "\n\n")
-		messageContent = r.renderMarkdown(mdContent, r.width-8)
-		messageContent = removeBlankLines(messageContent)
-	} else {
-		messageContent = content
+	if strings.TrimSpace(content) == "" {
+		content = "(empty message)"
 	}
 
-	fullContent := strings.TrimSuffix(messageContent, "\n")
-
-	// Left border with Blue color for user messages.
-	rendered := renderContentBlock(
-		fullContent,
-		r.width,
-		WithAlign(lipgloss.Left),
-		WithBorderColor(theme.Info),
-		WithMarginBottom(1),
-	)
+	rendered := r.ty.Tip(content)
+	rendered = lipgloss.NewStyle().MarginBottom(1).Render(rendered)
 
 	return UIMessage{
 		Type:      UserMessage,
@@ -223,12 +186,8 @@ func (r *MessageRenderer) RenderUserMessage(content string, timestamp time.Time)
 	}
 }
 
-// RenderAssistantMessage renders an AI assistant's response with left-aligned formatting,
-// including the model name, timestamp, and markdown-rendered content. Empty responses
-// are ignored and return an empty message. The message features a colored left border
-// for visual distinction.
+// RenderAssistantMessage renders an AI assistant's response
 func (r *MessageRenderer) RenderAssistantMessage(content string, timestamp time.Time, modelName string) UIMessage {
-	// Ignore empty responses - don't render anything
 	if strings.TrimSpace(content) == "" {
 		return UIMessage{
 			Type:      AssistantMessage,
@@ -238,17 +197,9 @@ func (r *MessageRenderer) RenderAssistantMessage(content string, timestamp time.
 		}
 	}
 
-	theme := getTheme()
-	messageContent := r.renderMarkdown(content, r.width-8)
-	fullContent := strings.TrimSuffix(messageContent, "\n")
-
-	// Left border with Primary (Mauve) color for assistant messages.
-	rendered := renderContentBlock(
-		fullContent,
-		r.width,
-		WithBorderColor(theme.Primary),
-		WithMarginBottom(1),
-	)
+	// Use markdown rendering with Chroma syntax highlighting
+	rendered := toMarkdown(content, r.width-4)
+	rendered = lipgloss.NewStyle().MarginBottom(1).Render(rendered)
 
 	return UIMessage{
 		Type:      AssistantMessage,
@@ -258,30 +209,14 @@ func (r *MessageRenderer) RenderAssistantMessage(content string, timestamp time.
 	}
 }
 
-// RenderSystemMessage renders KIT system messages such as help text, command outputs,
-// and informational notifications. These messages are displayed with a distinctive system
-// color border and "KIT System" label to differentiate them from user and AI content.
+// RenderSystemMessage renders KIT system messages using herald Note alert
 func (r *MessageRenderer) RenderSystemMessage(content string, timestamp time.Time) UIMessage {
-	theme := getTheme()
-
-	var messageContent string
 	if strings.TrimSpace(content) == "" {
-		messageContent = "No content available"
-	} else if strings.Contains(content, "`") {
-		messageContent = r.renderMarkdown(content, r.width-8)
-	} else {
-		messageContent = content
+		content = "No content available"
 	}
 
-	fullContent := "◇ " + strings.TrimSuffix(messageContent, "\n")
-
-	rendered := renderContentBlock(
-		fullContent,
-		r.width,
-		WithNoBorder(),
-		WithForeground(theme.Muted),
-		WithMarginBottom(1),
-	)
+	rendered := r.ty.Note(content)
+	rendered = lipgloss.NewStyle().MarginBottom(1).Render(rendered)
 
 	return UIMessage{
 		Type:      SystemMessage,
@@ -291,27 +226,9 @@ func (r *MessageRenderer) RenderSystemMessage(content string, timestamp time.Tim
 	}
 }
 
-// RenderDebugMessage renders diagnostic and debugging information with special formatting
-// including a debug icon, colored border, and structured layout. Debug messages are only
-// displayed when debug mode is enabled and help developers troubleshoot issues.
+// RenderDebugMessage renders diagnostic and debugging information
 func (r *MessageRenderer) RenderDebugMessage(message string, timestamp time.Time) UIMessage {
-	baseStyle := lipgloss.NewStyle()
-
-	theme := getTheme()
-	style := baseStyle.
-		Width(r.width - 3).
-		BorderLeft(true).
-		Foreground(theme.Muted).
-		BorderForeground(theme.Tool).
-		BorderStyle(lipgloss.ThickBorder()).
-		PaddingLeft(1).
-		MarginLeft(2).
-		MarginBottom(1)
-
-	header := baseStyle.
-		Foreground(theme.Tool).
-		Bold(true).
-		Render("🔍 Debug Output")
+	header := r.ty.H6("🔍 Debug Output")
 
 	lines := strings.Split(message, "\n")
 	var formattedLines []string
@@ -321,87 +238,52 @@ func (r *MessageRenderer) RenderDebugMessage(message string, timestamp time.Time
 		}
 	}
 
-	content := baseStyle.
-		Foreground(theme.Muted).
-		Render(strings.Join(formattedLines, "\n"))
-
-	fullContent := lipgloss.JoinVertical(lipgloss.Left,
+	content := r.ty.Compose(
 		header,
-		content,
+		r.ty.P(strings.Join(formattedLines, "\n")),
 	)
+	content = lipgloss.NewStyle().MarginBottom(1).Render(content)
 
 	return UIMessage{
-		Content: style.Render(fullContent),
-		Height:  lipgloss.Height(style.Render(fullContent)),
+		Content: content,
+		Height:  lipgloss.Height(content),
 	}
 }
 
-// RenderDebugConfigMessage renders configuration settings in a formatted debug display
-// with key-value pairs shown in a structured layout. Used to display runtime configuration
-// for debugging purposes with a distinctive icon and border styling.
+// RenderDebugConfigMessage renders configuration settings
 func (r *MessageRenderer) RenderDebugConfigMessage(config map[string]any, timestamp time.Time) UIMessage {
-	baseStyle := lipgloss.NewStyle()
-
-	theme := getTheme()
-	style := baseStyle.
-		Width(r.width - 1).
-		BorderLeft(true).
-		Foreground(theme.Muted).
-		BorderForeground(theme.Tool).
-		BorderStyle(lipgloss.ThickBorder()).
-		PaddingLeft(1)
-
-	header := baseStyle.
-		Foreground(theme.Tool).
-		Bold(true).
-		Render("🔧 Debug Configuration")
+	header := r.ty.H6("🔧 Debug Configuration")
 
 	var configLines []string
 	for key, value := range config {
 		if value != nil {
-			configLines = append(configLines, fmt.Sprintf("  %s: %v", key, value))
+			configLines = append(configLines, fmt.Sprintf("%s: %v", key, value))
 		}
 	}
 
-	configContent := baseStyle.
-		Foreground(theme.Muted).
-		Render(strings.Join(configLines, "\n"))
-
-	parts := []string{header}
+	var content string
 	if len(configLines) > 0 {
-		parts = append(parts, configContent)
+		content = r.ty.Compose(
+			header,
+			r.ty.P(strings.Join(configLines, "\n")),
+		)
+	} else {
+		content = header
 	}
-
-	rendered := style.Render(
-		lipgloss.JoinVertical(lipgloss.Left, parts...),
-	)
+	content = lipgloss.NewStyle().MarginBottom(1).Render(content)
 
 	return UIMessage{
 		Type:      SystemMessage,
-		Content:   rendered,
-		Height:    lipgloss.Height(rendered),
+		Content:   content,
+		Height:    lipgloss.Height(content),
 		Timestamp: timestamp,
 	}
 }
 
-// RenderErrorMessage renders error notifications with distinctive red coloring and
-// bold text to ensure visibility. Error messages include timestamp information and
-// are displayed with an error-colored border for immediate recognition.
+// RenderErrorMessage renders error notifications
 func (r *MessageRenderer) RenderErrorMessage(errorMsg string, timestamp time.Time) UIMessage {
-	theme := getTheme()
-
-	errorContent := lipgloss.NewStyle().
-		Foreground(theme.Error).
-		Bold(true).
-		Render(errorMsg)
-
-	rendered := renderContentBlock(
-		errorContent,
-		r.width,
-		WithAlign(lipgloss.Left),
-		WithBorderColor(theme.Error),
-		WithMarginBottom(1),
-	)
+	rendered := r.ty.Caution(errorMsg)
+	rendered = lipgloss.NewStyle().MarginBottom(1).Render(rendered)
 
 	return UIMessage{
 		Type:      ErrorMessage,
@@ -411,43 +293,30 @@ func (r *MessageRenderer) RenderErrorMessage(errorMsg string, timestamp time.Tim
 	}
 }
 
-// RenderToolCallMessage renders a notification that a tool is being executed, showing
-// the tool name, formatted arguments (if any), and execution timestamp. The message
-// uses tool-specific coloring to distinguish it from regular conversation messages.
+// RenderToolCallMessage renders a notification that a tool is being executed
 func (r *MessageRenderer) RenderToolCallMessage(toolName, toolArgs string, timestamp time.Time) UIMessage {
-	// Format timestamp
 	timeStr := timestamp.Local().Format("15:04")
 
-	// Format arguments with better presentation
-	theme := getTheme()
 	var argsContent string
 	if toolArgs != "" && toolArgs != "{}" {
-		argsContent = lipgloss.NewStyle().
-			Foreground(theme.Muted).
-			Italic(true).
-			Render(fmt.Sprintf("Arguments: %s", r.formatToolArgs(toolArgs)))
+		argsContent = r.ty.Italic(fmt.Sprintf("Arguments: %s", r.formatToolArgs(toolArgs)))
 	}
 
-	// Create info line
 	info := fmt.Sprintf(" Executing %s (%s)", toolName, timeStr)
+	infoStyled := r.ty.Small(info)
 
-	// Combine parts
 	var fullContent string
 	if argsContent != "" {
-		fullContent = argsContent + "\n" +
-			lipgloss.NewStyle().Foreground(theme.VeryMuted).Render(info)
+		fullContent = r.ty.Compose(
+			argsContent,
+			infoStyled,
+		)
 	} else {
-		fullContent = lipgloss.NewStyle().Foreground(theme.VeryMuted).Render(info)
+		fullContent = infoStyled
 	}
 
-	// Use the new block renderer
-	rendered := renderContentBlock(
-		fullContent,
-		r.width,
-		WithAlign(lipgloss.Left),
-		WithBorderColor(theme.Tool),
-		WithMarginBottom(1),
-	)
+	rendered := r.ty.Warning(fullContent)
+	rendered = lipgloss.NewStyle().MarginBottom(1).Render(rendered)
 
 	return UIMessage{
 		Type:      ToolCallMessage,
@@ -457,47 +326,18 @@ func (r *MessageRenderer) RenderToolCallMessage(toolName, toolArgs string, times
 	}
 }
 
-// RenderToolMessage renders a unified tool block combining the tool invocation
-// header (icon + display name + params) with the execution result body. The
-// border color indicates status: green for success, red for error. This replaces
-// the previous two-block approach (separate call + result blocks).
+// RenderToolMessage renders a unified tool block
 func (r *MessageRenderer) RenderToolMessage(toolName, toolArgs, toolResult string, isError bool) UIMessage {
-	theme := getTheme()
-
-	// Resolve extension renderer once for all overrides.
 	var extRd *ToolRendererData
 	if r.getToolRenderer != nil {
 		extRd = r.getToolRenderer(toolName)
 	}
 
-	// --- Header: [icon] [name] [params] ---
-	var icon string
-	borderColor := theme.Success
-	iconColor := theme.Success
-	if isError {
-		icon = "×"
-		borderColor = theme.Error
-		iconColor = theme.Error
-	} else {
-		icon = "✓"
-	}
-
-	// Extension can override border color (applies to both success and error).
-	if extRd != nil && extRd.BorderColor != "" {
-		borderColor = lipgloss.Color(extRd.BorderColor)
-	}
-
-	iconStr := lipgloss.NewStyle().Foreground(iconColor).Bold(true).Render(icon)
-
-	// Extension can override display name.
 	displayName := toolDisplayName(toolName)
 	if extRd != nil && extRd.DisplayName != "" {
 		displayName = extRd.DisplayName
 	}
-	nameStr := lipgloss.NewStyle().Foreground(theme.Info).Bold(true).Render(displayName)
 
-	// Format params with width budget for the header line.
-	// Check extension renderer for custom header params first.
 	paramBudget := max(r.width-10-len(displayName), 20)
 	var params string
 	if extRd != nil && extRd.RenderHeader != nil {
@@ -507,69 +347,70 @@ func (r *MessageRenderer) RenderToolMessage(toolName, toolArgs, toolResult strin
 		params = formatToolParams(toolArgs, paramBudget)
 	}
 
-	header := iconStr + " " + nameStr
-	if params != "" {
-		header += " " + lipgloss.NewStyle().Foreground(theme.Muted).Render(params)
+	var icon string
+	iconColor := GetTheme().Success
+	if isError {
+		icon = "×"
+		iconColor = GetTheme().Error
+	} else {
+		icon = "✓"
 	}
 
-	// --- Body: check extension renderer first, then builtin, then default ---
+	// Style the tool name with color
+	theme := GetTheme()
+	nameColor := theme.Info
+	if isError {
+		nameColor = theme.Error
+	}
+	styledName := lipgloss.NewStyle().Foreground(nameColor).Bold(true).Render(displayName)
+	styledIcon := lipgloss.NewStyle().Foreground(iconColor).Render(icon)
+
+	// Build the content: icon + name + params on first line, then body
+	headerLine := styledIcon + " " + styledName
+	if params != "" {
+		headerLine += " " + lipgloss.NewStyle().Foreground(theme.Muted).Render(params)
+	}
+
+	// Get body content
 	var body string
 	if extRd != nil && extRd.RenderBody != nil {
 		body = extRd.RenderBody(toolResult, isError, r.width-8)
-		// Apply markdown rendering if requested and body is non-empty.
 		if body != "" && extRd.BodyMarkdown {
 			body = strings.TrimSuffix(toMarkdown(body, r.width-8), "\n")
 		}
 	}
 	if body == "" {
 		if isError {
-			body = lipgloss.NewStyle().
-				Foreground(theme.Error).
-				Render(toolResult)
+			body = r.formatToolResult(toolName, toolResult)
 		} else {
 			body = renderToolBody(toolName, toolArgs, toolResult, r.width-8)
 			if body == "" {
-				body = r.formatToolResult(toolName, toolResult, r.width-8)
+				body = r.formatToolResult(toolName, toolResult)
 			}
 		}
 	}
 
 	if strings.TrimSpace(body) == "" {
-		body = lipgloss.NewStyle().
-			Italic(true).
-			Foreground(theme.Muted).
-			Render("(no output)")
+		body = r.ty.Italic("(no output)")
 	}
 
-	// Combine header + body into a single block.
-	fullContent := header + "\n\n" + strings.TrimSuffix(body, "\n")
-
-	// Build rendering options; extension can override background.
-	blockOpts := []renderingOption{
-		WithAlign(lipgloss.Left),
-		WithBorderColor(borderColor),
-		WithMarginBottom(1),
-	}
-	if extRd != nil && extRd.Background != "" {
-		blockOpts = append(blockOpts, WithBackground(lipgloss.Color(extRd.Background)))
-	}
-
-	rendered := renderContentBlock(
-		fullContent,
-		r.width,
-		blockOpts...,
+	// Compose: icon + name + params, then body
+	fullContent := r.ty.Compose(
+		headerLine,
+		"",
+		body,
 	)
+	fullContent = lipgloss.NewStyle().MarginBottom(1).Render(fullContent)
 
 	return UIMessage{
 		Type:    ToolMessage,
-		Content: rendered,
-		Height:  lipgloss.Height(rendered),
+		Content: fullContent,
+		Height:  lipgloss.Height(fullContent),
 	}
 }
 
 // formatToolArgs formats tool arguments for display
 func (r *MessageRenderer) formatToolArgs(args string) string {
-	// Remove outer braces and clean up JSON formatting
 	args = strings.TrimSpace(args)
 	if strings.HasPrefix(args, "{") && strings.HasSuffix(args, "}") {
 		args = strings.TrimPrefix(args, "{")
@@ -577,12 +418,10 @@ func (r *MessageRenderer) formatToolArgs(args string) string {
 		args = strings.TrimSpace(args)
 	}
 
-	// If it's empty after cleanup, return a placeholder
 	if args == "" {
 		return "(no arguments)"
 	}
 
-	// Truncate if too long, but skip truncation in debug mode
 	if !r.debug {
 		maxLen := 100
 		if len(args) > maxLen {
@@ -594,10 +433,7 @@ func (r *MessageRenderer) formatToolArgs(args string) string {
 }
 
 // formatToolResult formats tool results based on tool type
-func (r *MessageRenderer) formatToolResult(toolName, result string, width int) string {
-	baseStyle := lipgloss.NewStyle()
-
-	// Truncate very long results only if not in debug mode
+func (r *MessageRenderer) formatToolResult(toolName, result string) string {
 	if !r.debug {
 		maxLines := 10
 		lines := strings.Split(result, "\n")
@@ -606,51 +442,40 @@ func (r *MessageRenderer) formatToolResult(toolName, result string, width int) s
 		}
 	}
 
-	// Format bash/command output with better formatting
-	if strings.Contains(toolName, "bash") || strings.Contains(toolName, "command") || strings.Contains(toolName, "shell") || toolName == "run_shell_cmd" {
-		theme := getTheme()
-
-		// Split result into sections if it contains both stdout and stderr
+	if strings.Contains(toolName, "bash") || strings.Contains(toolName, "command") ||
+		strings.Contains(toolName, "shell") {
 		if strings.Contains(result, "<stdout>") || strings.Contains(result, "<stderr>") {
-			return r.formatBashOutput(result, width, theme)
+			return parseBashOutput(result, GetTheme())
 		}
-
-		// For simple output, just render as monospace text with proper line breaks
-		return baseStyle.
-			Width(width).
-			Foreground(theme.Muted).
-			Render(result)
 	}
 
-	// For other tools, render as muted text
-	theme := getTheme()
-	return baseStyle.
-		Width(width).
-		Foreground(theme.Muted).
-		Render(result)
+	return result
 }
 
-// formatBashOutput formats bash command output with proper section handling.
-// Delegates tag parsing to the shared parseBashOutput helper.
-func (r *MessageRenderer) formatBashOutput(result string, width int, theme Theme) string {
-	parsed := parseBashOutput(result, theme)
-	return lipgloss.NewStyle().
-		Width(width).
-		Foreground(theme.Muted).
-		Render(parsed)
-}
-
-// renderMarkdown renders markdown content using glamour
-func (r *MessageRenderer) renderMarkdown(content string, width int) string {
-	rendered := toMarkdown(content, width)
-	return strings.TrimSuffix(rendered, "\n")
+// createTypography creates a typography instance from theme
+func createTypography(theme Theme) *herald.Typography {
+	return herald.New(
+		herald.WithPalette(herald.ColorPalette{
+			Primary:   theme.Primary,
+			Secondary: theme.Secondary,
+			Tertiary:  theme.Info,
+			Accent:    theme.Accent,
+			Highlight: theme.Highlight,
+			Muted:     theme.Muted,
+			Text:      theme.Text,
+			Surface:   theme.Background,
+			Base:      theme.CodeBg,
+		}),
+		herald.WithCodeLineNumbers(true),
+		// Customize alert labels
+		herald.WithAlertLabel(herald.AlertNote, "Info"),
+		herald.WithAlertLabel(herald.AlertTip, "You"),
+		herald.WithAlertLabel(herald.AlertWarning, "Working"),
+		herald.WithAlertLabel(herald.AlertCaution, "Error"),
+	)
 }
 
 // removeBlankLines removes lines that are visually blank from rendered output.
-// Glamour wraps every character (including padding spaces) with ANSI color
-// codes, so we must strip escape sequences before checking whether a line is
-// empty. This collapses paragraph spacing so user messages render without
-// extra vertical gaps.
 func removeBlankLines(s string) string {
 	lines := strings.Split(s, "\n")
 	filtered := lines[:0]

internal/ui/model.go

@@ -8,7 +8,6 @@ import (
 	"os"
 	"os/exec"
 	"strings"
-	"sync"
 	"time"
 
 	tea "charm.land/bubbletea/v2"
@@ -584,8 +583,8 @@ type AppModel struct {
 	streamingBashStderr []string
 	// streamingBashMaxLines caps how many lines to accumulate to prevent memory issues.
 	streamingBashMaxLines int
-	// streamingMu protects the streaming bash output fields from concurrent access.
-	streamingMu sync.RWMutex
+	// streaming bash fields are only mutated/read from the Bubble Tea event loop
+	// (Update/View), so no mutex is required here.
 	// streamingBashCommand holds the command being executed for display as a header.
 	streamingBashCommand string
 }
@@ -787,28 +786,29 @@ func (m *AppModel) PrintStartupInfo() {
 		return
 	}
 
-	render := func(text string) string {
-		return m.renderer.RenderSystemMessage(text, time.Now()).Content
-	}
+	// Create typography instance for startup rendering
+	ty := createTypography(GetTheme())
 
 	fmt.Println()
 
-	// Build the combined startup content.
-	var lines []string
+	// Build key-value pairs for startup info
+	var pairs [][2]string
 
 	if m.providerName != "" && m.modelName != "" {
-		lines = append(lines, fmt.Sprintf("Model loaded: %s (%s)", m.providerName, m.modelName))
+		pairs = append(pairs, [2]string{"Model", fmt.Sprintf("%s (%s)", m.providerName, m.modelName)})
 	}
 
 	if m.loadingMessage != "" {
-		lines = append(lines, m.loadingMessage)
+		pairs = append(pairs, [2]string{"Status", m.loadingMessage})
 	}
 
 	// Context — loaded AGENTS.md files.
 	if len(m.contextPaths) > 0 {
-		for _, p := range m.contextPaths {
-			lines = append(lines, fmt.Sprintf("Context: %s", tildeHome(p)))
+		contextStr := tildeHome(m.contextPaths[0])
+		if len(m.contextPaths) > 1 {
+			contextStr += fmt.Sprintf(" +%d more", len(m.contextPaths)-1)
 		}
+		pairs = append(pairs, [2]string{"Context", contextStr})
 	}
 
 	// Skills — listed by name.
@@ -817,21 +817,23 @@ func (m *AppModel) PrintStartupInfo() {
 		for i, si := range m.skillItems {
 			names[i] = si.Name
 		}
-		lines = append(lines, fmt.Sprintf("Skills: %s", strings.Join(names, ", ")))
+		pairs = append(pairs, [2]string{"Skills", strings.Join(names, ", ")})
 	}
 
 	// Extension tool count (only shown when > 0).
 	if m.extensionToolCount > 0 {
-		lines = append(lines, fmt.Sprintf("Loaded %d extension tools", m.extensionToolCount))
+		pairs = append(pairs, [2]string{"Extensions", fmt.Sprintf("%d tools", m.extensionToolCount)})
 	}
 
 	// MCP tool count (only shown when > 0).
 	if m.mcpToolCount > 0 {
-		lines = append(lines, fmt.Sprintf("Loaded %d tools from MCP servers", m.mcpToolCount))
+		pairs = append(pairs, [2]string{"MCP", fmt.Sprintf("%d tools", m.mcpToolCount)})
 	}
 
-	if len(lines) > 0 {
-		fmt.Println(render(strings.Join(lines, "\n\n")))
+	if len(pairs) > 0 {
+		rendered := ty.KVGroup(pairs)
+		rendered = lipgloss.NewStyle().MarginBottom(1).Render(rendered)
+		fmt.Println(rendered)
 	}
 }
 
@@ -1378,9 +1380,7 @@ func (m *AppModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 				Command string `json:"command"`
 			}
 			if err := json.Unmarshal([]byte(msg.ToolArgs), &args); err == nil && args.Command != "" {
-				m.streamingMu.Lock()
 				m.streamingBashCommand = args.Command
-				m.streamingMu.Unlock()
 			}
 		}
 
@@ -1395,11 +1395,9 @@ func (m *AppModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 		// Buffer tool result for scrollback.
 		m.printToolResult(msg)
 		// Clear streaming bash output since tool completed.
-		m.streamingMu.Lock()
 		m.streamingBashOutput = nil
 		m.streamingBashStderr = nil
 		m.streamingBashCommand = ""
-		m.streamingMu.Unlock()
 		// Start spinner again while waiting for the next LLM response.
 		if m.stream != nil {
 			_, cmd := m.stream.Update(app.SpinnerEvent{Show: true})
@@ -1408,7 +1406,6 @@ func (m *AppModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 
 	case app.ToolOutputEvent:
 		// Accumulate streaming bash output for display.
-		m.streamingMu.Lock()
 		if msg.IsStderr {
 			m.streamingBashStderr = append(m.streamingBashStderr, msg.Chunk)
 			// Cap stderr lines to prevent memory issues.
@@ -1422,7 +1419,6 @@ func (m *AppModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 				m.streamingBashOutput = m.streamingBashOutput[len(m.streamingBashOutput)-m.streamingBashMaxLines:]
 			}
 		}
-		m.streamingMu.Unlock()
 
 	case app.ToolCallContentEvent:
 		// In streaming mode this text was already delivered via StreamChunkEvents
@@ -1847,13 +1843,11 @@ func (m *AppModel) renderStream() string {
 // Lines are truncated to the terminal width and capped to maxBashLines to prevent
 // long-running commands from blowing up the TUI layout.
 func (m *AppModel) renderStreamingBashOutput(theme Theme) string {
-	m.streamingMu.RLock()
 	stdoutLines := make([]string, len(m.streamingBashOutput))
 	copy(stdoutLines, m.streamingBashOutput)
 	stderrLines := make([]string, len(m.streamingBashStderr))
 	copy(stderrLines, m.streamingBashStderr)
 	command := m.streamingBashCommand
-	m.streamingMu.RUnlock()
 
 	if len(stdoutLines) == 0 && len(stderrLines) == 0 {
 		return ""

internal/ui/stream.go

@@ -7,6 +7,7 @@ import (
 
 	tea "charm.land/bubbletea/v2"
 	"charm.land/lipgloss/v2"
+	"github.com/indaco/herald"
 	"github.com/mark3labs/kit/internal/app"
 )
 
@@ -79,7 +80,12 @@ func streamSpinnerTickCmd(generation uint64) tea.Cmd {
 // streamFlushTickMsg fires when it's time to commit pending chunks to the
 // main content builders and trigger a re-render. This coalesces rapid
 // streaming chunks into fewer expensive markdown re-renders.
-type streamFlushTickMsg struct{}
+//
+// generation ties the tick to the pending flush session that created it so
+// stale ticks from a prior Reset() are discarded.
+type streamFlushTickMsg struct {
+	generation uint64
+}
 
 // streamFlushInterval is the coalescing window for stream chunks. Chunks
 // arriving within this window are batched into a single render pass.
@@ -89,9 +95,9 @@ const streamFlushInterval = 16 * time.Millisecond
 
 // streamFlushTickCmd returns a tea.Cmd that fires streamFlushTickMsg after
 // the coalescing interval.
-func streamFlushTickCmd() tea.Cmd {
+func streamFlushTickCmd(generation uint64) tea.Cmd {
 	return tea.Tick(streamFlushInterval, func(_ time.Time) tea.Msg {
-		return streamFlushTickMsg{}
+		return streamFlushTickMsg{generation: generation}
 	})
 }
 
@@ -149,9 +155,11 @@ type StreamComponent struct {
 	// spinnerFrame is the current frame index.
 	spinnerFrame int
 
-	// activeTools tracks the names of tools currently executing in parallel.
-	// When multiple tools run concurrently, all are displayed in the spinner.
-	activeTools []string
+	// activeTools maps ToolCallID -> display label for currently running tools.
+	activeTools map[string]string
+
+	// activeToolOrder preserves deterministic display order for active tools.
+	activeToolOrder []string
 
 	// streamContent holds committed streaming text (flushed from pending).
 	streamContent strings.Builder
@@ -172,6 +180,10 @@ type StreamComponent struct {
 	// the same coalescing window.
 	flushPending bool
 
+	// flushGeneration is incremented when stream state resets so stale flush
+	// ticks from a previous step can be discarded.
+	flushGeneration uint64
+
 	// renderCache holds the last rendered output string. Reused by View()
 	// between flush ticks to avoid redundant markdown re-parsing.
 	renderCache string
@@ -190,14 +202,8 @@ type StreamComponent struct {
 	// reasoningDuration holds the total reasoning time, frozen when streaming text begins.
 	reasoningDuration time.Duration
 
-	// messageRenderer renders assistant messages in standard mode.
-	messageRenderer *MessageRenderer
-
-	// compactRenderer renders assistant messages in compact mode.
-	compactRenderer *CompactRenderer
-
-	// compactMode selects which renderer to use.
-	compactMode bool
+	// renderer renders streaming assistant text in either compact or standard mode.
+	renderer Renderer
 
 	// modelName is displayed in the streaming text header.
 	modelName string
@@ -211,6 +217,9 @@ type StreamComponent struct {
 	// height constrains the render output to at most this many lines.
 	// 0 means unconstrained.
 	height int
+
+	// ty provides typography functions for rendering text.
+	ty *herald.Typography
 }
 
 // NewStreamComponent creates a new StreamComponent ready to be embedded in AppModel.
@@ -218,13 +227,20 @@ func NewStreamComponent(compactMode bool, width int, modelName string) *StreamCo
 	if width == 0 {
 		width = 80
 	}
+
+	var renderer Renderer
+	if compactMode {
+		renderer = NewCompactRenderer(width, false)
+	} else {
+		renderer = newMessageRenderer(width, false)
+	}
+
 	return &StreamComponent{
-		spinnerFrames:   knightRiderFrames(),
-		compactMode:     compactMode,
-		modelName:       modelName,
-		messageRenderer: newMessageRenderer(width, false),
-		compactRenderer: NewCompactRenderer(width, false),
-		width:           width,
+		spinnerFrames: knightRiderFrames(),
+		modelName:     modelName,
+		renderer:      renderer,
+		width:         width,
+		ty:            createTypography(GetTheme()),
 	}
 }
 
@@ -251,11 +267,13 @@ func (s *StreamComponent) Reset() {
 	s.spinnerGeneration++ // invalidate any in-flight tick commands
 	s.spinnerFrame = 0
 	s.activeTools = nil
+	s.activeToolOrder = nil
 	s.streamContent.Reset()
 	s.reasoningContent.Reset()
 	s.pendingStream.Reset()
 	s.pendingReasoning.Reset()
 	s.flushPending = false
+	s.flushGeneration++
 	s.renderCache = ""
 	s.renderDirty = false
 	s.timestamp = time.Time{}
@@ -323,8 +341,9 @@ func (s *StreamComponent) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 
 	case tea.WindowSizeMsg:
 		s.width = msg.Width
-		s.messageRenderer.SetWidth(s.width)
-		s.compactRenderer.SetWidth(s.width)
+		if s.renderer != nil {
+			s.renderer.SetWidth(s.width)
+		}
 		// Invalidate render cache — width change affects wrapping/styling.
 		s.renderCache = ""
 		s.renderDirty = true
@@ -360,6 +379,9 @@ func (s *StreamComponent) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 		}
 
 	case streamFlushTickMsg:
+		if msg.generation != s.flushGeneration {
+			break
+		}
 		s.flushPending = false
 		s.commitPending()
 
@@ -374,7 +396,7 @@ func (s *StreamComponent) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 		s.pendingReasoning.WriteString(msg.Delta)
 		if !s.flushPending {
 			s.flushPending = true
-			return s, streamFlushTickCmd()
+			return s, streamFlushTickCmd(s.flushGeneration)
 		}
 
 	case app.StreamChunkEvent:
@@ -389,14 +411,25 @@ func (s *StreamComponent) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 		s.pendingStream.WriteString(msg.Content)
 		if !s.flushPending {
 			s.flushPending = true
-			return s, streamFlushTickCmd()
+			return s, streamFlushTickCmd(s.flushGeneration)
 		}
 
 	case app.ToolExecutionEvent:
+		toolID := msg.ToolCallID
+		if toolID == "" {
+			// Defensive fallback for older/third-party emitters that may omit
+			// ToolCallID. Best-effort only: same-name+args concurrent calls can
+			// still collide without a stable ID.
+			toolID = fmt.Sprintf("%s|%s", msg.ToolName, msg.ToolArgs)
+		}
 		if msg.IsStarting {
-			// Add tool to active list for parallel execution display.
-			toolDisplay := formatToolExecutionMessage(msg.ToolName, msg.ToolArgs)
-			s.activeTools = append(s.activeTools, toolDisplay)
+			if s.activeTools == nil {
+				s.activeTools = make(map[string]string)
+			}
+			if _, exists := s.activeTools[toolID]; !exists {
+				s.activeToolOrder = append(s.activeToolOrder, toolID)
+			}
+			s.activeTools[toolID] = formatToolExecutionMessage(msg.ToolName)
 			s.spinnerFrame = 0
 			if !s.spinning {
 				s.phase = streamPhaseActive
@@ -405,9 +438,10 @@ func (s *StreamComponent) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 				return s, streamSpinnerTickCmd(s.spinnerGeneration)
 			}
 		} else {
-			// Tool finished — remove from active list but keep spinning if others remain.
-			toolDisplay := formatToolExecutionMessage(msg.ToolName, msg.ToolArgs)
-			s.activeTools = removeFromSlice(s.activeTools, toolDisplay)
+			if s.activeTools != nil {
+				delete(s.activeTools, toolID)
+			}
+			s.activeToolOrder = removeToolID(s.activeToolOrder, toolID)
 		}
 	}
 
@@ -482,39 +516,30 @@ func (s *StreamComponent) viewContent(fullContent string) string {
 	return fullContent
 }
 
-// renderReasoningBlock renders the reasoning/thinking content in a surface-tinted
-// box. When collapsed, shows the last 10 lines with a truncation hint. When
+// renderReasoningBlock renders the reasoning/thinking content using blockquote.
+// When collapsed, shows the last 10 lines with a truncation hint. When
 // expanded, shows all lines. Includes a "Thought for Xs" duration footer.
 func (s *StreamComponent) renderReasoningBlock(reasoning string) string {
-	theme := GetTheme()
-	maxWidth := max(s.width-4, 20)
-
 	lines := strings.Split(strings.TrimRight(reasoning, "\n"), "\n")
 
-	contentStyle := lipgloss.NewStyle().
-		Foreground(theme.Muted).
-		Background(theme.MutedBorder).
-		Italic(true)
-
 	var parts []string
 
 	// When collapsed and content exceeds 10 lines, show only the last 10
-	// with a truncation hint (matching iteratr's thinking block pattern).
+	// with a truncation hint.
 	const maxCollapsedLines = 10
 	if !s.thinkingVisible && len(lines) > maxCollapsedLines {
 		hidden := len(lines) - maxCollapsedLines
-		hintStyle := lipgloss.NewStyle().
-			Foreground(theme.VeryMuted).
-			Background(theme.MutedBorder).
-			Italic(true)
-		parts = append(parts, hintStyle.Render(fmt.Sprintf("... (%d lines hidden)", hidden)))
+		parts = append(parts, s.ty.Italic(fmt.Sprintf("... (%d lines hidden)", hidden)))
 		lines = lines[len(lines)-maxCollapsedLines:]
 	}
 
-	// Render reasoning text.
-	parts = append(parts, contentStyle.Width(maxWidth).Render(strings.Join(lines, "\n")))
+	// Main content using Italic with Muted color for visual distinction.
+	content := strings.TrimLeft(strings.Join(lines, "\n"), " \t\n")
+	theme := GetTheme()
+	mutedStyle := lipgloss.NewStyle().Foreground(theme.Muted)
+	parts = append(parts, mutedStyle.Render(s.ty.Italic(content)))
 
-	// Duration footer.
+	// Duration footer with VeryMuted label and Accent duration.
 	var duration time.Duration
 	if s.reasoningDuration > 0 {
 		duration = s.reasoningDuration
@@ -528,21 +553,21 @@ func (s *StreamComponent) renderReasoningBlock(reasoning string) string {
 		} else {
 			durationStr = fmt.Sprintf("%.1fs", duration.Seconds())
 		}
-		footer := lipgloss.NewStyle().Foreground(theme.VeryMuted).Background(theme.MutedBorder).Render("Thought for ") +
-			lipgloss.NewStyle().Foreground(theme.Info).Background(theme.MutedBorder).Render(durationStr)
-		parts = append(parts, footer)
+		label := lipgloss.NewStyle().Foreground(theme.VeryMuted).Render("Thought for ")
+		durationStyled := lipgloss.NewStyle().Foreground(theme.Accent).Render(durationStr)
+		parts = append(parts, label+durationStyled)
 	}
 
-	innerContent := strings.Join(parts, "\n")
-
-	// Wrap in box with surface background for visual distinction.
-	boxStyle := lipgloss.NewStyle().
-		Background(theme.MutedBorder). // Surface0 (#313244)
-		PaddingLeft(1).
-		Width(maxWidth + 2).
-		MarginBottom(1)
-
-	return boxStyle.Render(innerContent)
+	// Concatenate parts with newline between blockquote and footer
+	var result string
+	if len(parts) == 1 {
+		result = parts[0]
+	} else if len(parts) == 2 {
+		result = parts[0] + "\n" + parts[1]
+	} else {
+		result = strings.Join(parts, "\n")
+	}
+	return lipgloss.NewStyle().MarginBottom(1).Render(result)
 }
 
 // SetThinkingVisible sets whether reasoning blocks are shown or collapsed.
@@ -568,7 +593,8 @@ func (s *StreamComponent) SpinnerView() string {
 		return ""
 	}
 	frame := s.spinnerFrames[s.spinnerFrame%len(s.spinnerFrames)]
-	if len(s.activeTools) == 0 {
+	tools := s.activeToolDisplays()
+	if len(tools) == 0 {
 		return "  " + frame
 	}
 	theme := GetTheme()
@@ -578,10 +604,10 @@ func (s *StreamComponent) SpinnerView() string {
 
 	// Format active tools list
 	var toolsMsg string
-	if len(s.activeTools) == 1 {
-		toolsMsg = s.activeTools[0]
+	if len(tools) == 1 {
+		toolsMsg = tools[0]
 	} else {
-		toolsMsg = "Running: " + strings.Join(s.activeTools, ", ")
+		toolsMsg = "Running: " + strings.Join(tools, ", ")
 	}
 	return "  " + frame + " " + msgStyle.Render(toolsMsg)
 }
@@ -593,28 +619,39 @@ func (s *StreamComponent) renderStreamingText(text string) string {
 	if ts.IsZero() {
 		ts = time.Now()
 	}
-
-	if s.compactMode {
-		msg := s.compactRenderer.RenderAssistantMessage(text, ts, s.modelName)
-		return msg.Content
+	if s.renderer == nil {
+		return text
 	}
-	msg := s.messageRenderer.RenderAssistantMessage(text, ts, s.modelName)
+	msg := s.renderer.RenderAssistantMessage(text, ts, s.modelName)
 	return msg.Content
 }
 
-// removeFromSlice removes the first occurrence of a string from a slice.
-func removeFromSlice(slice []string, s string) []string {
-	for i, v := range slice {
-		if v == s {
-			return append(slice[:i], slice[i+1:]...)
+func (s *StreamComponent) activeToolDisplays() []string {
+	if len(s.activeTools) == 0 {
+		return nil
+	}
+	out := make([]string, 0, len(s.activeToolOrder))
+	for _, id := range s.activeToolOrder {
+		if display, ok := s.activeTools[id]; ok {
+			out = append(out, display)
 		}
 	}
-	return slice
+	return out
+}
+
+// removeToolID removes the first occurrence of a tool ID from a slice.
+func removeToolID(ids []string, id string) []string {
+	for i, v := range ids {
+		if v == id {
+			return append(ids[:i], ids[i+1:]...)
+		}
+	}
+	return ids
 }
 
 // formatToolExecutionMessage creates a descriptive spinner message for tool execution.
-// For spawn_subagent, it shows simply as "Subagent" with optional task preview.
-func formatToolExecutionMessage(toolName, toolArgs string) string {
+// For spawn_subagent, it shows simply as "Subagent".
+func formatToolExecutionMessage(toolName string) string {
 	if toolName == "spawn_subagent" {
 		return "Subagent"
 	}

internal/ui/tool_renderers.go

@@ -46,7 +46,7 @@ func renderToolBody(toolName, toolArgs, toolResult string, width int) string {
 		if body := renderWriteBody(toolArgs, toolResult, width); body != "" {
 			return body
 		}
-	case toolName == "bash" || toolName == "run_shell_cmd" ||
+	case toolName == "bash" || toolName == "grep" || toolName == "find" ||
 		strings.Contains(toolName, "shell") || strings.Contains(toolName, "command"):
 		if body := renderBashBody(toolResult, width); body != "" {
 			return body
@@ -777,7 +777,7 @@ func renderToolBodyCompact(toolName, toolArgs, toolResult string, width int) str
 		return renderReadCompact(toolResult)
 	case toolName == "write":
 		return renderWriteCompact(toolArgs)
-	case toolName == "bash" || toolName == "run_shell_cmd" ||
+	case toolName == "bash" || toolName == "grep" || toolName == "find" ||
 		strings.Contains(toolName, "shell") || strings.Contains(toolName, "command"):
 		return renderBashCompact(toolResult, width)
 	case toolName == "spawn_subagent":
@@ -939,8 +939,8 @@ func renderBashCompact(toolResult string, width int) string {
 // Subagent tool renderers — show only summary, not full output
 // ---------------------------------------------------------------------------
 
-// renderSubagentBody renders a clean summary of subagent results.
-// Extracts timing/token info and shows only a brief summary instead of raw output.
+// renderSubagentBody renders a clean summary of subagent results with bash-style
+// background styling for consistency with other tools.
 func renderSubagentBody(toolResult string, width int) string {
 	theme := getTheme()
 	result := strings.TrimSpace(toolResult)
@@ -960,9 +960,19 @@ func renderSubagentBody(toolResult string, width int) string {
 	// First line is always the status summary
 	statusLine := lines[0]
 
-	// Build a clean summary
-	var summary strings.Builder
-	summary.WriteString(lipgloss.NewStyle().Foreground(theme.Muted).Render(statusLine))
+	// Build content lines for display with bash-style background
+	outputStyle := lipgloss.NewStyle().Background(theme.CodeBg).PaddingLeft(1)
+	errorStyle := lipgloss.NewStyle().Foreground(theme.Error).Background(theme.CodeBg).PaddingLeft(1)
+
+	const lineIndent = "  "
+	lineWidth := max(width-len(lineIndent), 20)
+	maxLineChars := lineWidth - 1 // account for PaddingLeft(1)
+
+	var contentLines []string
+
+	// Add status line
+	styledStatus := outputStyle.Width(lineWidth).Render(truncateLine(statusLine, maxLineChars))
+	contentLines = append(contentLines, lineIndent+styledStatus)
 
 	// For successful results, extract a brief preview of the actual result
 	if strings.Contains(statusLine, "successfully") {
@@ -970,25 +980,45 @@ func renderSubagentBody(toolResult string, width int) string {
 		if _, resultContent, found := strings.Cut(result, "Result:\n"); found {
 			resultContent = strings.TrimSpace(resultContent)
 			if resultContent != "" {
-				// Show first 3 meaningful lines as preview
-				preview := extractSubagentPreview(resultContent, 3, width-4)
-				if preview != "" {
-					summary.WriteString("\n\n")
-					summary.WriteString(lipgloss.NewStyle().
-						Foreground(theme.Muted).
-						Italic(true).
-						Render(preview))
+				// Show first few meaningful lines as preview
+				previewLines := extractSubagentPreviewLines(resultContent, 5, maxLineChars)
+				if len(previewLines) > 0 {
+					// Add blank separator line
+					blankLine := outputStyle.Width(lineWidth).Render("")
+					contentLines = append(contentLines, lineIndent+blankLine)
+
+					for _, line := range previewLines {
+						styled := outputStyle.Width(lineWidth).Render(line)
+						contentLines = append(contentLines, lineIndent+styled)
+					}
+				}
+			}
+		}
+	} else {
+		// For failed results, show error info
+		if _, errorContent, found := strings.Cut(result, "Error:\n"); found {
+			errorContent = strings.TrimSpace(errorContent)
+			if errorContent != "" {
+				previewLines := extractSubagentPreviewLines(errorContent, 3, maxLineChars)
+				if len(previewLines) > 0 {
+					blankLine := outputStyle.Width(lineWidth).Render("")
+					contentLines = append(contentLines, lineIndent+blankLine)
+
+					for _, line := range previewLines {
+						styled := errorStyle.Width(lineWidth).Render(line)
+						contentLines = append(contentLines, lineIndent+styled)
+					}
 				}
 			}
 		}
 	}
 
-	return summary.String()
+	return strings.Join(contentLines, "\n")
 }
 
-// extractSubagentPreview extracts the first N non-empty lines from content,
-// truncating each line to maxWidth.
-func extractSubagentPreview(content string, maxLines, maxWidth int) string {
+// extractSubagentPreviewLines extracts the first N non-empty lines from content,
+// truncating each line to maxWidth. Returns as a slice of strings.
+func extractSubagentPreviewLines(content string, maxLines, maxWidth int) []string {
 	lines := strings.Split(content, "\n")
 	var preview []string
 
@@ -1007,12 +1037,6 @@ func extractSubagentPreview(content string, maxLines, maxWidth int) string {
 		}
 	}
 
-	if len(preview) == 0 {
-		return ""
-	}
-
-	result := strings.Join(preview, "\n")
-
 	// Count remaining lines for "more" indicator
 	totalLines := 0
 	for _, line := range lines {
@@ -1021,10 +1045,10 @@ func extractSubagentPreview(content string, maxLines, maxWidth int) string {
 		}
 	}
 	if totalLines > maxLines {
-		result += fmt.Sprintf("\n...(%d more lines)", totalLines-maxLines)
+		preview = append(preview, fmt.Sprintf("...(%d more lines)", totalLines-maxLines))
 	}
 
-	return result
+	return preview
 }
 
 // renderSubagentCompact returns a brief one-line summary for subagent results.

internal/ui/usage_tracker.go

@@ -151,10 +151,6 @@ func (ut *UsageTracker) RenderUsageInfo() string {
 	ut.mu.RLock()
 	defer ut.mu.RUnlock()
 
-	if ut.sessionStats.RequestCount == 0 {
-		return ""
-	}
-
 	baseStyle := lipgloss.NewStyle()
 
 	// Display the current context window token count (from the last API call),

internal/ui/usage_tracker_render_test.go

@@ -67,3 +67,62 @@ func TestUsageTracker_RenderUsageInfo_OAuth(t *testing.T) {
 		t.Errorf("Expected regular rendered output to show actual cost, got: %s", regularRendered)
 	}
 }
+
+func TestUsageTracker_RenderUsageInfo_StartupState(t *testing.T) {
+	// Create a mock model info with costs and context limit
+	modelInfo := &models.ModelInfo{
+		ID:   "claude-3-5-sonnet-20241022",
+		Name: "Claude 3.5 Sonnet v2",
+		Cost: models.Cost{
+			Input:  3.0,
+			Output: 15.0,
+		},
+		Limit: models.Limit{
+			Context: 200000,
+			Output:  8192,
+		},
+	}
+
+	// Test startup state (no requests made yet) - Regular API key
+	regularTracker := NewUsageTracker(modelInfo, "anthropic", 80, false)
+	rendered := stripAnsi(regularTracker.RenderUsageInfo())
+
+	// Should NOT return empty string on startup
+	if rendered == "" {
+		t.Errorf("Expected non-empty output on startup, got empty string")
+	}
+
+	// Should show 0 tokens
+	if !strings.Contains(rendered, "Tokens: 0") {
+		t.Errorf("Expected 'Tokens: 0' on startup, got: %s", rendered)
+	}
+
+	// Should NOT show percentage when tokens are 0
+	if strings.Contains(rendered, "(%") {
+		t.Errorf("Expected no percentage on startup with 0 tokens, got: %s", rendered)
+	}
+
+	// Should show $0.0000 cost for regular API key
+	if !strings.Contains(rendered, "Cost: $0.0000") {
+		t.Errorf("Expected 'Cost: $0.0000' on startup, got: %s", rendered)
+	}
+
+	// Test startup state (no requests made yet) - OAuth
+	oauthTracker := NewUsageTracker(modelInfo, "anthropic", 80, true)
+	oauthRendered := stripAnsi(oauthTracker.RenderUsageInfo())
+
+	// Should NOT return empty string on startup
+	if oauthRendered == "" {
+		t.Errorf("Expected non-empty output on startup for OAuth, got empty string")
+	}
+
+	// Should show 0 tokens for OAuth
+	if !strings.Contains(oauthRendered, "Tokens: 0") {
+		t.Errorf("Expected 'Tokens: 0' on startup for OAuth, got: %s", oauthRendered)
+	}
+
+	// Should show $0.00 cost for OAuth
+	if !strings.Contains(oauthRendered, "Cost: $0.00") {
+		t.Errorf("Expected 'Cost: $0.00' on startup for OAuth, got: %s", oauthRendered)
+	}
+}

pkg/kit/kit.go

@@ -1063,6 +1063,15 @@ func New(ctx context.Context, opts *Options) (*Kit, error) {
 	// Bridge extension events to SDK hooks.
 	if agentResult.ExtRunner != nil {
 		k.bridgeExtensions(agentResult.ExtRunner)
+
+		// Initialize extension context with minimal defaults. SDK users can call
+		// SetExtensionContext to override with richer implementations (TUI callbacks,
+		// prompts, etc.). This ensures extensions never crash on nil function fields.
+		k.SetExtensionContext(extensions.Context{
+			CWD:         cwd,
+			Model:       k.modelString,
+			Interactive: false, // SDK mode defaults to non-interactive
+		})
 	}
 
 	return k, nil