Fix usage widget startup visibility and stop-path updates

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/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/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
 }
@@ -1378,9 +1377,7 @@ 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 +1392,9 @@ 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 +1403,6 @@ 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 +1416,6 @@ 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 +1840,11 @@ 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

@@ -79,7 +79,12 @@ 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 +94,9 @@ 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 +154,11 @@ 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 +179,10 @@ 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 +201,8 @@ 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
@@ -218,13 +223,19 @@ 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,
 	}
 }
 
@@ -251,11 +262,13 @@ 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 +336,9 @@ 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 +374,9 @@ 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 +391,7 @@ 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 +406,25 @@ 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 +433,10 @@ 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)
 		}
 	}
 
@@ -568,7 +597,8 @@ 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 +608,10 @@ 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 +623,39 @@ 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/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)
+	}
+}