fix: correct token usage and cost tracking for multi-step tool calls

This commit fixes several issues with token usage tracking:

1. Fix InputTokens-only validation bug - now checks any token field > 0
   to handle OpenAI-compatible providers where cached prompts result in
   InputTokens=0 while OutputTokens>0

2. Remove per-step context token updates from recordStepUsage() - context
   fill is now set once at turn completion via updateUsageFromTurnResult
   using FinalUsage.InputTokens, preventing display jumps during multi-step
   tool calls

3. Track maximum context seen in SetContextTokens() - prevents the status
   bar from showing decreasing token counts when FinalUsage.InputTokens
   reflects only the last step's input

4. Add comprehensive debug logging for token tracking at key points:
   - StepUsageEvent emission
   - recordStepUsage processing
   - updateUsageFromTurnResult processing

5. Update tests to reflect new behavior:
   - TestRecordStepUsage_updatesTracker: no longer expects context updates
   - TestUpdateUsageFromTurnResult_contextTokensUsesInputOnly: verifies
     InputTokens-only tracking

All tests pass. Token tracking now correctly accumulates costs and shows
monotonically increasing context size.

README.md

@@ -307,6 +307,12 @@ kit -e examples/extensions/minimal.go
 - **Themes**: Register and switch color themes via `RegisterTheme`, `SetTheme`, `ListThemes`
 - **Custom Events**: Inter-extension communication via `EmitCustomEvent`
 
+**Bridged SDK APIs** (NEW): Extensions can now access internal SDK capabilities:
+- **Tree Navigation**: Navigate conversation history (`GetTreeNode`, `GetCurrentBranch`, `NavigateTo`), summarize branches (`SummarizeBranch`), and implement fresh context loops (`CollapseBranch`)
+- **Skill Loading**: Dynamically load and inject skills at runtime (`LoadSkill`, `DiscoverSkills`, `InjectSkillAsContext`)
+- **Template Parsing**: Parse and render templates with `{{variables}}` (`ParseTemplate`, `RenderTemplate`), parse CLI-style arguments (`ParseArguments`, `SimpleParseArguments`), and evaluate model conditionals (`EvaluateModelConditional`, `RenderWithModelConditionals`)
+- **Model Resolution**: Resolve model fallback chains (`ResolveModelChain`), query model capabilities (`GetModelCapabilities`, `CheckModelAvailable`), and extract provider/model ID (`GetCurrentProvider`, `GetCurrentModelID`)
+
 ### Extension Examples
 
 See the `examples/extensions/` directory:
@@ -318,6 +324,7 @@ See the `examples/extensions/` directory:
 - `compact-notify.go` - Notification on compaction
 - `confirm-destructive.go` - Confirm destructive operations
 - `context-inject.go` - Inject context into conversations
+- `conversation-manager.go` - **NEW** Tree navigation, branch summarization, and fresh context loops
 - `custom-editor-demo.go` - Vim-like modal editor
 - `dev-reload.go` - Development live-reload
 - `header-footer-demo.go` - Custom headers and footers
@@ -332,6 +339,7 @@ See the `examples/extensions/` directory:
 - `plan-mode.go` - Read-only planning mode
 - `project-rules.go` - Project-specific rules
 - `prompt-demo.go` - Interactive prompts (select/confirm/input)
+- `prompt-templates.go` - **NEW** Frontmatter-driven templates with model switching and skill injection
 - `protected-paths.go` - Path protection for sensitive files
 - `subagent-widget.go` - Multi-agent orchestration with status widget
 - `subagent-test.go` - Subagent testing utilities

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) },
@@ -1097,8 +1107,392 @@ func runNormalMode(ctx context.Context) error {
 				}
 				return nil, extResult, err
 			},
+
+			// -------------------------------------------------------------------------
+			// Tree Navigation API (Phase 1 Bridge)
+			// -------------------------------------------------------------------------
+			GetTreeNode: func(entryID string) *extensions.TreeNode {
+				node := kitInstance.GetTreeNode(entryID)
+				if node == nil {
+					return nil
+				}
+				return &extensions.TreeNode{
+					ID:        node.ID,
+					ParentID:  node.ParentID,
+					Type:      node.Type,
+					Role:      node.Role,
+					Content:   node.Content,
+					Model:     node.Model,
+					Provider:  node.Provider,
+					Timestamp: node.Timestamp,
+					Children:  node.Children,
+				}
+			},
+			GetCurrentBranch: func() []extensions.TreeNode {
+				nodes := kitInstance.GetCurrentBranch()
+				result := make([]extensions.TreeNode, len(nodes))
+				for i, n := range nodes {
+					result[i] = extensions.TreeNode{
+						ID:        n.ID,
+						ParentID:  n.ParentID,
+						Type:      n.Type,
+						Role:      n.Role,
+						Content:   n.Content,
+						Model:     n.Model,
+						Provider:  n.Provider,
+						Timestamp: n.Timestamp,
+						Children:  n.Children,
+					}
+				}
+				return result
+			},
+			GetChildren: kitInstance.GetChildren,
+			NavigateTo: func(entryID string) extensions.TreeNavigationResult {
+				err := kitInstance.NavigateTo(entryID)
+				if err != "" {
+					return extensions.TreeNavigationResult{Success: false, Error: err}
+				}
+				return extensions.TreeNavigationResult{Success: true}
+			},
+			SummarizeBranch: kitInstance.SummarizeBranch,
+			CollapseBranch: func(fromID, toID, summary string) extensions.TreeNavigationResult {
+				err := kitInstance.CollapseBranch(fromID, toID, summary)
+				if err != "" {
+					return extensions.TreeNavigationResult{Success: false, Error: err}
+				}
+				return extensions.TreeNavigationResult{Success: true}
+			},
+
+			// -------------------------------------------------------------------------
+			// Skill Loading API (Phase 2 Bridge)
+			// -------------------------------------------------------------------------
+			LoadSkill: func(path string) (*extensions.Skill, string) {
+				s, err := kitInstance.LoadSkillForExtension(path)
+				return s, err
+			},
+			LoadSkillsFromDir: func(dir string) extensions.SkillLoadResult {
+				return kitInstance.LoadSkillsFromDirForExtension(dir)
+			},
+			DiscoverSkills: func() extensions.SkillLoadResult {
+				skills := kitInstance.DiscoverSkillsForExtension()
+				return extensions.SkillLoadResult{Skills: skills}
+			},
+			InjectSkillAsContext: func(skillName string) string {
+				// Find skill by name
+				skills := kitInstance.DiscoverSkillsForExtension()
+				for _, s := range skills {
+					if s.Name == skillName {
+						// Inject via SendMessage as a system context message
+						appInstance.Run(fmt.Sprintf("<skill name=%q>\n%s\n</skill>", s.Name, s.Content))
+						return ""
+					}
+				}
+				return fmt.Sprintf("skill not found: %s", skillName)
+			},
+			InjectRawSkillAsContext: func(path string) string {
+				s, err := kitInstance.LoadSkillForExtension(path)
+				if err != "" {
+					return err
+				}
+				appInstance.Run(fmt.Sprintf("<skill name=%q>\n%s\n</skill>", s.Name, s.Content))
+				return ""
+			},
+			GetAvailableSkills: kitInstance.DiscoverSkillsForExtension,
+
+			// -------------------------------------------------------------------------
+			// Template Parsing API (Phase 3 Bridge)
+			// -------------------------------------------------------------------------
+			ParseTemplate:        kit.ParseTemplate,
+			RenderTemplate:       kit.RenderTemplate,
+			ParseArguments:       kit.ParseArguments,
+			SimpleParseArguments: kit.SimpleParseArguments,
+			EvaluateModelConditional: func(condition string) bool {
+				return kit.EvaluateModelConditional(kitInstance.GetExtensionContext().Model, condition)
+			},
+			RenderWithModelConditionals: func(content string) string {
+				return kit.RenderWithModelConditionals(content, kitInstance.GetExtensionContext().Model)
+			},
+
+			// -------------------------------------------------------------------------
+			// Model Resolution API (Phase 4 Bridge)
+			// -------------------------------------------------------------------------
+			ResolveModelChain: kit.ResolveModelChain,
+			GetModelCapabilities: func(model string) (extensions.ModelCapabilities, string) {
+				return kit.GetModelCapabilities(model)
+			},
+			CheckModelAvailable: kit.CheckModelAvailable,
+			GetCurrentProvider: func() string {
+				return kit.GetCurrentProvider(kitInstance.GetExtensionContext().Model)
+			},
+			GetCurrentModelID: func() string {
+				return kit.GetCurrentModelID(kitInstance.GetExtensionContext().Model)
+			},
 		})
 		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
+			},
+
+			// -------------------------------------------------------------------------
+			// Tree Navigation API (Phase 1 Bridge) - Second Context
+			// -------------------------------------------------------------------------
+			GetTreeNode: func(entryID string) *extensions.TreeNode {
+				node := kitInstance.GetTreeNode(entryID)
+				if node == nil {
+					return nil
+				}
+				return &extensions.TreeNode{
+					ID:        node.ID,
+					ParentID:  node.ParentID,
+					Type:      node.Type,
+					Role:      node.Role,
+					Content:   node.Content,
+					Model:     node.Model,
+					Provider:  node.Provider,
+					Timestamp: node.Timestamp,
+					Children:  node.Children,
+				}
+			},
+			GetCurrentBranch: func() []extensions.TreeNode {
+				nodes := kitInstance.GetCurrentBranch()
+				result := make([]extensions.TreeNode, len(nodes))
+				for i, n := range nodes {
+					result[i] = extensions.TreeNode{
+						ID:        n.ID,
+						ParentID:  n.ParentID,
+						Type:      n.Type,
+						Role:      n.Role,
+						Content:   n.Content,
+						Model:     n.Model,
+						Provider:  n.Provider,
+						Timestamp: n.Timestamp,
+						Children:  n.Children,
+					}
+				}
+				return result
+			},
+			GetChildren: kitInstance.GetChildren,
+			NavigateTo: func(entryID string) extensions.TreeNavigationResult {
+				err := kitInstance.NavigateTo(entryID)
+				if err != "" {
+					return extensions.TreeNavigationResult{Success: false, Error: err}
+				}
+				return extensions.TreeNavigationResult{Success: true}
+			},
+			SummarizeBranch: kitInstance.SummarizeBranch,
+			CollapseBranch: func(fromID, toID, summary string) extensions.TreeNavigationResult {
+				err := kitInstance.CollapseBranch(fromID, toID, summary)
+				if err != "" {
+					return extensions.TreeNavigationResult{Success: false, Error: err}
+				}
+				return extensions.TreeNavigationResult{Success: true}
+			},
+
+			// -------------------------------------------------------------------------
+			// Skill Loading API (Phase 2 Bridge) - Second Context
+			// -------------------------------------------------------------------------
+			LoadSkill: func(path string) (*extensions.Skill, string) {
+				s, err := kitInstance.LoadSkillForExtension(path)
+				return s, err
+			},
+			LoadSkillsFromDir: func(dir string) extensions.SkillLoadResult {
+				return kitInstance.LoadSkillsFromDirForExtension(dir)
+			},
+			DiscoverSkills: func() extensions.SkillLoadResult {
+				skills := kitInstance.DiscoverSkillsForExtension()
+				return extensions.SkillLoadResult{Skills: skills}
+			},
+			InjectSkillAsContext: func(skillName string) string {
+				skills := kitInstance.DiscoverSkillsForExtension()
+				for _, s := range skills {
+					if s.Name == skillName {
+						appInstance.Run(fmt.Sprintf("<skill name=%q>\n%s\n</skill>", s.Name, s.Content))
+						return ""
+					}
+				}
+				return fmt.Sprintf("skill not found: %s", skillName)
+			},
+			InjectRawSkillAsContext: func(path string) string {
+				s, err := kitInstance.LoadSkillForExtension(path)
+				if err != "" {
+					return err
+				}
+				appInstance.Run(fmt.Sprintf("<skill name=%q>\n%s\n</skill>", s.Name, s.Content))
+				return ""
+			},
+			GetAvailableSkills: func() []extensions.Skill {
+				return kitInstance.DiscoverSkillsForExtension()
+			},
+
+			// -------------------------------------------------------------------------
+			// Template Parsing API (Phase 3 Bridge) - Second Context
+			// -------------------------------------------------------------------------
+			ParseTemplate:        kit.ParseTemplate,
+			RenderTemplate:       kit.RenderTemplate,
+			ParseArguments:       kit.ParseArguments,
+			SimpleParseArguments: kit.SimpleParseArguments,
+			EvaluateModelConditional: func(condition string) bool {
+				return kit.EvaluateModelConditional(kitInstance.GetExtensionContext().Model, condition)
+			},
+			RenderWithModelConditionals: func(content string) string {
+				return kit.RenderWithModelConditionals(content, kitInstance.GetExtensionContext().Model)
+			},
+
+			// -------------------------------------------------------------------------
+			// Model Resolution API (Phase 4 Bridge) - Second Context
+			// -------------------------------------------------------------------------
+			ResolveModelChain: kit.ResolveModelChain,
+			GetModelCapabilities: func(model string) (extensions.ModelCapabilities, string) {
+				return kit.GetModelCapabilities(model)
+			},
+			CheckModelAvailable: kit.CheckModelAvailable,
+			GetCurrentProvider: func() string {
+				return kit.GetCurrentProvider(kitInstance.GetExtensionContext().Model)
+			},
+			GetCurrentModelID: func() string {
+				return kit.GetCurrentModelID(kitInstance.GetExtensionContext().Model)
+			},
+		})
 	}
 
 	// Convert extension commands to UI-layer type for the interactive TUI.
@@ -1222,7 +1616,7 @@ 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 +1672,7 @@ 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 +1770,7 @@ 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 +1820,15 @@ 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.

examples/extensions/bridge_demo.go

@@ -0,0 +1,170 @@
+//go:build ignore
+
+// bridge_demo.go - Demonstrates the new bridged SDK APIs for extensions.
+// This extension showcases tree navigation, skill loading, template parsing,
+// and model resolution capabilities.
+package main
+
+import (
+	"encoding/json"
+	"fmt"
+	"strings"
+
+	"kit/ext"
+)
+
+var (
+	discoveredSkills []ext.Skill
+	currentBranch    []ext.TreeNode
+)
+
+func Init(api ext.API) {
+	// Register /tree-info command to demonstrate tree navigation
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "tree-info",
+		Description: "Show current conversation tree information",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			branch := ctx.GetCurrentBranch()
+			info := fmt.Sprintf("Current branch has %d nodes:\n", len(branch))
+			for i, node := range branch {
+				info += fmt.Sprintf("  [%d] %s (%s): %s...\n", i, node.Type, node.ID[:8], truncate(node.Content, 40))
+			}
+			ctx.PrintInfo(info)
+			return "", nil
+		},
+	})
+
+	// Register /discover-skills command
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "discover-skills",
+		Description: "Discover and list available skills",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			result := ctx.DiscoverSkills()
+			if result.Error != "" {
+				return "", fmt.Errorf("discovery failed: %s", result.Error)
+			}
+			discoveredSkills = result.Skills
+
+			info := fmt.Sprintf("Discovered %d skills:\n", len(result.Skills))
+			for _, s := range result.Skills {
+				info += fmt.Sprintf("  - %s: %s\n", s.Name, s.Description)
+			}
+			ctx.PrintInfo(info)
+			return "", nil
+		},
+	})
+
+	// Register /parse-template command
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "parse-template",
+		Description: "Parse a template and show extracted variables",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			if args == "" {
+				args = "Hello {{name}}, welcome to {{place}}!"
+			}
+			tpl := ctx.ParseTemplate("demo", args)
+			info := fmt.Sprintf("Template: %s\nVariables: %v", tpl.Content, tpl.Variables)
+			ctx.PrintInfo(info)
+			return "", nil
+		},
+	})
+
+	// Register /render-template command
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "render-template",
+		Description: "Render a template with variables (usage: /render-template name=John place=Kit)",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			tpl := ctx.ParseTemplate("demo", "Hello {{name}}, welcome to {{place}}!")
+			vars := ctx.ParseArguments(args, ext.ArgumentPattern{
+				Flags: map[string]string{"name": "name", "place": "place"},
+			})
+			rendered := ctx.RenderTemplate(tpl, vars.Vars)
+			ctx.PrintInfo("Rendered: " + rendered)
+			return "", nil
+		},
+	})
+
+	// Register /check-model command
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "check-model",
+		Description: "Check model capabilities and availability",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			model := args
+			if model == "" {
+				model = ctx.Model
+			}
+
+			available := ctx.CheckModelAvailable(model)
+			caps, err := ctx.GetModelCapabilities(model)
+
+			info := fmt.Sprintf("Model: %s\n", model)
+			info += fmt.Sprintf("Available: %v\n", available)
+			if err == "" {
+				info += fmt.Sprintf("Provider: %s\n", caps.Provider)
+				info += fmt.Sprintf("Context Limit: %d\n", caps.ContextLimit)
+				info += fmt.Sprintf("Reasoning: %v\n", caps.Reasoning)
+			} else {
+				info += fmt.Sprintf("Error: %s\n", err)
+			}
+			ctx.PrintInfo(info)
+			return "", nil
+		},
+	})
+
+	// Register /resolve-chain command
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "resolve-chain",
+		Description: "Resolve a model chain (usage: /resolve-chain claude-opus,gpt-4o,claude-sonnet)",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			if args == "" {
+				args = "anthropic/claude-opus-4,anthropic/claude-sonnet-4,openai/gpt-4o"
+			}
+			prefs := ctx.SimpleParseArguments(args, 1)
+			chain := []string{}
+			if len(prefs) > 1 {
+				// Split the first arg by comma
+				for _, p := range strings.Split(prefs[1], ",") {
+					p = strings.TrimSpace(p)
+					if p != "" {
+						chain = append(chain, p)
+					}
+				}
+			}
+
+			result := ctx.ResolveModelChain(chain)
+			info, _ := json.MarshalIndent(result, "", "  ")
+			ctx.PrintInfo("Resolution Result:\n" + string(info))
+			return "", nil
+		},
+	})
+
+	// Register /test-conditional command
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "test-conditional",
+		Description: "Test model conditional rendering",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			content := `<if-model is="claude-*">This is for Claude models<else>This is for other models</if-model>`
+			rendered := ctx.RenderWithModelConditionals(content)
+			ctx.PrintInfo("Input: " + content)
+			ctx.PrintInfo("Output: " + rendered)
+			ctx.PrintInfo(fmt.Sprintf("Current model matches 'claude-*': %v", ctx.EvaluateModelConditional("claude-*")))
+			return "", nil
+		},
+	})
+
+	// OnSessionStart: discover skills automatically
+	api.OnSessionStart(func(e ext.SessionStartEvent, ctx ext.Context) {
+		result := ctx.DiscoverSkills()
+		if result.Error == "" && len(result.Skills) > 0 {
+			discoveredSkills = result.Skills
+			ctx.SetStatus("bridge-demo", fmt.Sprintf("%d skills", len(result.Skills)), 50)
+		}
+	})
+}
+
+func truncate(s string, max int) string {
+	if len(s) <= max {
+		return s
+	}
+	return s[:max-3] + "..."
+}

examples/extensions/conversation-manager.go

@@ -0,0 +1,406 @@
+//go:build ignore
+
+// conversation-manager.go - Advanced conversation tree navigation and management.
+// This extension demonstrates:
+// - Tree navigation (GetTreeNode, GetCurrentBranch, NavigateTo)
+// - Branch summarization and collapsing
+// - Interactive tree exploration
+//
+// Commands:
+//   /tree              - Show conversation tree structure
+//   /branch            - Show current branch path
+//   /goto <entry-id>   - Navigate to a specific entry
+//   /summarize <n>     - Summarize last N messages
+//   /fresh-context     - Collapse branch and start fresh
+//   /loop <n> <prompt> - Execute prompt N times with fresh context each iteration
+
+package main
+
+import (
+	"fmt"
+	"strconv"
+	"strings"
+	"time"
+
+	"kit/ext"
+)
+
+var (
+	loopActive    bool
+	loopCount     int
+	loopCurrent   int
+	loopPrompt    string
+	loopStartNode string
+)
+
+func Init(api ext.API) {
+	// /tree - Show tree structure
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "tree",
+		Description: "Show conversation tree structure",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			showTree(ctx)
+			return "", nil
+		},
+	})
+
+	// /branch - Show current branch
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "branch",
+		Description: "Show current conversation branch",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			showBranch(ctx)
+			return "", nil
+		},
+	})
+
+	// /goto - Navigate to entry
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "goto",
+		Description: "Navigate to a specific entry ID (usage: /goto <entry-id>)",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			if args == "" {
+				ctx.PrintError("Usage: /goto <entry-id>")
+				return "", nil
+			}
+			result := ctx.NavigateTo(args)
+			if !result.Success {
+				ctx.PrintError(fmt.Sprintf("Navigation failed: %s", result.Error))
+				return "", nil
+			}
+			ctx.PrintInfo(fmt.Sprintf("Navigated to entry: %s", args))
+
+			// Show the node we navigated to
+			node := ctx.GetTreeNode(args)
+			if node != nil {
+				ctx.PrintInfo(fmt.Sprintf("Entry type: %s, Role: %s", node.Type, node.Role))
+			}
+			return "", nil
+		},
+	})
+
+	// /summarize - Summarize recent messages
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "summarize",
+		Description: "Summarize last N messages (usage: /summarize [n=5])",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			n := 5
+			if args != "" {
+				if parsed, err := strconv.Atoi(args); err == nil && parsed > 0 {
+					n = parsed
+				}
+			}
+
+			branch := ctx.GetCurrentBranch()
+			if len(branch) < 2 {
+				ctx.PrintError("Not enough messages to summarize")
+				return "", nil
+			}
+
+			// Find range to summarize
+			startIdx := len(branch) - n - 1
+			if startIdx < 0 {
+				startIdx = 0
+			}
+			endIdx := len(branch) - 1
+
+			fromID := branch[startIdx].ID
+			toID := branch[endIdx].ID
+
+			ctx.PrintInfo(fmt.Sprintf("Summarizing messages %d to %d...", startIdx, endIdx))
+			summary := ctx.SummarizeBranch(fromID, toID)
+
+			if summary == "" {
+				ctx.PrintError("Failed to generate summary")
+				return "", nil
+			}
+
+			ctx.PrintBlock(ext.PrintBlockOpts{
+				Text:        summary,
+				BorderColor: "#89b4fa",
+				Subtitle:    "conversation-manager · Summary",
+			})
+			return "", nil
+		},
+	})
+
+	// /fresh-context - Collapse and restart
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "fresh-context",
+		Description: "Collapse conversation to summary and start fresh",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			branch := ctx.GetCurrentBranch()
+			if len(branch) < 3 {
+				ctx.PrintError("Not enough context to collapse")
+				return "", nil
+			}
+
+			// Keep first message (system), summarize rest
+			fromID := branch[1].ID
+			toID := branch[len(branch)-1].ID
+
+			ctx.PrintInfo("Generating summary for context collapse...")
+			summary := ctx.SummarizeBranch(fromID, toID)
+
+			if summary == "" {
+				ctx.PrintError("Failed to generate summary")
+				return "", nil
+			}
+
+			// Collapse the branch
+			result := ctx.CollapseBranch(fromID, toID, summary)
+			if !result.Success {
+				ctx.PrintError(fmt.Sprintf("Collapse failed: %s", result.Error))
+				return "", nil
+			}
+
+			ctx.PrintInfo("Context collapsed. Starting fresh with summary.")
+			ctx.PrintBlock(ext.PrintBlockOpts{
+				Text:        summary,
+				BorderColor: "#a6e3a1",
+				Subtitle:    "conversation-manager · Collapsed Context",
+			})
+
+			// Set a widget showing we're in fresh mode
+			ctx.SetWidget(ext.WidgetConfig{
+				ID:        "fresh-context",
+				Placement: ext.WidgetAbove,
+				Content:   ext.WidgetContent{Text: "🌱 Fresh Context Mode - Previous conversation collapsed"},
+				Style:     ext.WidgetStyle{BorderColor: "#a6e3a1"},
+			})
+
+			return "", nil
+		},
+	})
+
+	// /loop - Execute with fresh context each iteration
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "loop",
+		Description: "Execute prompt N times with fresh context (usage: /loop 5 analyze this code)",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			if loopActive {
+				ctx.PrintError("Loop already in progress. Wait for completion.")
+				return "", nil
+			}
+
+			// Parse arguments
+			parts := strings.SplitN(args, " ", 2)
+			if len(parts) < 2 {
+				ctx.PrintError("Usage: /loop <count> <prompt>")
+				return "", nil
+			}
+
+			count, err := strconv.Atoi(parts[0])
+			if err != nil || count <= 0 || count > 10 {
+				ctx.PrintError("Invalid count (must be 1-10)")
+				return "", nil
+			}
+
+			loopCount = count
+			loopCurrent = 0
+			loopPrompt = parts[1]
+			loopActive = true
+
+			// Store current branch position
+			branch := ctx.GetCurrentBranch()
+			if len(branch) > 0 {
+				loopStartNode = branch[len(branch)-1].ID
+			}
+
+			ctx.PrintInfo(fmt.Sprintf("Starting loop: %d iterations", loopCount))
+			ctx.SetWidget(ext.WidgetConfig{
+				ID:        "loop-progress",
+				Placement: ext.WidgetAbove,
+				Content:   ext.WidgetContent{Text: fmt.Sprintf("🔄 Loop: 0/%d - %s", loopCount, loopPrompt)},
+				Style:     ext.WidgetStyle{BorderColor: "#fab387"},
+			})
+
+			// Start first iteration
+			executeLoopIteration(ctx)
+			return "", nil
+		},
+	})
+
+	// OnAgentEnd handles loop continuation
+	api.OnAgentEnd(func(e ext.AgentEndEvent, ctx ext.Context) {
+		if !loopActive {
+			return
+		}
+
+		loopCurrent++
+
+		if loopCurrent >= loopCount {
+			// Loop complete
+			loopActive = false
+			ctx.RemoveWidget("loop-progress")
+			ctx.PrintInfo(fmt.Sprintf("✅ Loop complete: %d/%d iterations", loopCurrent, loopCount))
+
+			// Show final summary
+			branch := ctx.GetCurrentBranch()
+			if len(branch) > 0 && loopStartNode != "" {
+				summary := ctx.SummarizeBranch(loopStartNode, branch[len(branch)-1].ID)
+				if summary != "" {
+					ctx.PrintBlock(ext.PrintBlockOpts{
+						Text:        summary,
+						BorderColor: "#a6e3a1",
+						Subtitle:    "conversation-manager · Loop Summary",
+					})
+				}
+			}
+			return
+		}
+
+		// Update progress
+		ctx.SetWidget(ext.WidgetConfig{
+			ID:        "loop-progress",
+			Placement: ext.WidgetAbove,
+			Content:   ext.WidgetContent{Text: fmt.Sprintf("🔄 Loop: %d/%d - %s", loopCurrent, loopCount, loopPrompt)},
+			Style:     ext.WidgetStyle{BorderColor: "#fab387"},
+		})
+
+		// Collapse previous iteration for fresh context
+		branch := ctx.GetCurrentBranch()
+		if len(branch) >= 2 {
+			// Find the user messages (look for the one before the last assistant message)
+			// We want to collapse from the user message that started this iteration
+			// to the last assistant response
+			var collapseStartIdx = -1
+			for i := len(branch) - 1; i >= 0; i-- {
+				if branch[i].Role == "assistant" {
+					// Found the last assistant message, now find the user message before it
+					for j := i - 1; j >= 0; j-- {
+						if branch[j].Role == "user" {
+							collapseStartIdx = j
+							break
+						}
+					}
+					break
+				}
+			}
+
+			if collapseStartIdx >= 0 {
+				fromID := branch[collapseStartIdx].ID
+				toID := branch[len(branch)-1].ID
+
+				ctx.PrintInfo(fmt.Sprintf("Collapsing iteration %d for fresh context...", loopCurrent))
+				summary := ctx.SummarizeBranch(fromID, toID)
+				if summary != "" {
+					result := ctx.CollapseBranch(fromID, toID, summary)
+					if result.Success {
+						ctx.PrintInfo("Context collapsed successfully")
+					} else {
+						ctx.PrintError(fmt.Sprintf("Collapse failed: %s", result.Error))
+					}
+				}
+			}
+		}
+
+		// Small delay to let UI update
+		time.Sleep(500 * time.Millisecond)
+
+		// Trigger next iteration
+		executeLoopIteration(ctx)
+	})
+}
+
+// showTree displays the conversation tree structure
+func showTree(ctx ext.Context) {
+	branch := ctx.GetCurrentBranch()
+	if len(branch) == 0 {
+		ctx.PrintInfo("Tree is empty")
+		return
+	}
+
+	var output strings.Builder
+	output.WriteString(fmt.Sprintf("Conversation Tree (%d nodes):\n\n", len(branch)))
+
+	for i, node := range branch {
+		prefix := "  "
+		if i == len(branch)-1 {
+			prefix = "▶ " // Current node
+		} else {
+			prefix = "  "
+		}
+
+		roleIcon := "💬"
+		switch node.Role {
+		case "user":
+			roleIcon = "👤"
+		case "assistant":
+			roleIcon = "🤖"
+		case "system":
+			roleIcon = "⚙️"
+		}
+
+		content := truncate(node.Content, 50)
+		if node.Type == "branch_summary" {
+			roleIcon = "📋"
+			content = "[Summary] " + truncate(node.Content, 40)
+		}
+
+		output.WriteString(fmt.Sprintf("%s%s %s: %s (%s...)\n", prefix, roleIcon, node.Role, node.ID[:8], content))
+
+		// Show children count if any
+		children := ctx.GetChildren(node.ID)
+		if len(children) > 0 {
+			output.WriteString(fmt.Sprintf("    └─ %d branch(es)\n", len(children)))
+		}
+	}
+
+	ctx.PrintBlock(ext.PrintBlockOpts{
+		Text:        output.String(),
+		BorderColor: "#89b4fa",
+		Subtitle:    "conversation-manager · Tree View",
+	})
+}
+
+// showBranch displays the current branch path
+func showBranch(ctx ext.Context) {
+	branch := ctx.GetCurrentBranch()
+	if len(branch) == 0 {
+		ctx.PrintInfo("No active branch")
+		return
+	}
+
+	var output strings.Builder
+	output.WriteString(fmt.Sprintf("Current Branch (%d nodes from root to leaf):\n\n", len(branch)))
+
+	for i, node := range branch {
+		marker := "  "
+		if i == len(branch)-1 {
+			marker = "▶ " // Current leaf
+		}
+
+		output.WriteString(fmt.Sprintf("%s[%d] %s (%s): %s\n",
+			marker, i, node.Type, node.ID[:8], truncate(node.Content, 40)))
+	}
+
+	// Show current node details
+	leaf := branch[len(branch)-1]
+	output.WriteString(fmt.Sprintf("\nCurrent Leaf:\n"))
+	output.WriteString(fmt.Sprintf("  ID: %s\n", leaf.ID))
+	output.WriteString(fmt.Sprintf("  Type: %s\n", leaf.Type))
+	output.WriteString(fmt.Sprintf("  Role: %s\n", leaf.Role))
+	output.WriteString(fmt.Sprintf("  Model: %s\n", leaf.Model))
+	output.WriteString(fmt.Sprintf("  Children: %d\n", len(leaf.Children)))
+
+	ctx.PrintBlock(ext.PrintBlockOpts{
+		Text:        output.String(),
+		BorderColor: "#cba6f7",
+		Subtitle:    "conversation-manager · Branch View",
+	})
+}
+
+// executeLoopIteration triggers the next loop iteration
+func executeLoopIteration(ctx ext.Context) {
+	iterationPrompt := fmt.Sprintf("[%d/%d] %s", loopCurrent+1, loopCount, loopPrompt)
+	ctx.SendMessage(iterationPrompt)
+}
+
+// truncate helper
+func truncate(s string, max int) string {
+	if len(s) <= max {
+		return s
+	}
+	return s[:max-3] + "..."
+}

examples/extensions/prompt-templates.go

@@ -0,0 +1,269 @@
+//go:build ignore
+
+// prompt-templates.go - Frontmatter-driven prompt templates with model switching.
+// This extension demonstrates the new bridged SDK APIs:
+// - Tree navigation for conversation management
+// - Template parsing with {{variable}} substitution
+// - Model resolution with fallback chains
+// - Skill injection
+//
+// Usage:
+//   1. Create ~/.config/kit/prompts/debug.md with frontmatter:
+//      ---
+//      description: Debug Python code
+//      model: claude-sonnet-4-20250514
+//      skill: python
+//      ---
+//      Help me debug this Python code: {{input}}
+//
+//   2. In Kit: /debug my_script.py
+
+package main
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"kit/ext"
+)
+
+// PromptTemplate represents a loaded template with frontmatter
+type PromptTemplate struct {
+	Name        string
+	Description string
+	Model       string
+	Skill       string
+	Content     string
+	Variables   []string
+	Path        string
+}
+
+var (
+	templates   = make(map[string]PromptTemplate)
+	templateDir string
+)
+
+func Init(api ext.API) {
+	// Determine template directory
+	home, _ := os.UserHomeDir()
+	templateDir = filepath.Join(home, ".config", "kit", "prompts")
+
+	// Ensure directory exists
+	os.MkdirAll(templateDir, 0755)
+
+	// Register commands
+	api.RegisterCommand(ext.CommandDef{
+		Name:        "reload-templates",
+		Description: "Reload prompt templates from disk",
+		Execute: func(args string, ctx ext.Context) (string, error) {
+			loadTemplates(ctx)
+			ctx.PrintInfo(fmt.Sprintf("Loaded %d templates from %s", len(templates), templateDir))
+			return "", nil
+		},
+	})
+
+	// Dynamic template commands are registered after loading
+	api.OnSessionStart(func(e ext.SessionStartEvent, ctx ext.Context) {
+		loadTemplates(ctx)
+		registerTemplateCommands(api, ctx)
+	})
+}
+
+// loadTemplates discovers and loads all template files
+func loadTemplates(ctx ext.Context) {
+	templates = make(map[string]PromptTemplate)
+
+	entries, err := os.ReadDir(templateDir)
+	if err != nil {
+		return
+	}
+
+	for _, entry := range entries {
+		if entry.IsDir() || !strings.HasSuffix(entry.Name(), ".md") {
+			continue
+		}
+
+		path := filepath.Join(templateDir, entry.Name())
+		tpl, err := loadTemplateFile(path)
+		if err != nil {
+			continue
+		}
+
+		name := strings.TrimSuffix(entry.Name(), ".md")
+		templates[name] = tpl
+	}
+}
+
+// loadTemplateFile parses a template with YAML frontmatter
+func loadTemplateFile(path string) (PromptTemplate, error) {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return PromptTemplate{}, err
+	}
+
+	content := string(data)
+	tpl := PromptTemplate{Path: path}
+
+	// Parse frontmatter
+	if strings.HasPrefix(content, "---") {
+		parts := strings.SplitN(content[3:], "---", 2)
+		if len(parts) == 2 {
+			frontmatter := strings.TrimSpace(parts[0])
+			body := strings.TrimSpace(parts[1])
+
+			// Simple line-by-line frontmatter parsing
+			for _, line := range strings.Split(frontmatter, "\n") {
+				line = strings.TrimSpace(line)
+				if line == "" || strings.HasPrefix(line, "#") {
+					continue
+				}
+
+				key, value, found := strings.Cut(line, ":")
+				if found {
+					key = strings.TrimSpace(key)
+					value = strings.TrimSpace(value)
+					switch key {
+					case "description":
+						tpl.Description = value
+					case "model":
+						tpl.Model = value
+					case "skill":
+						tpl.Skill = value
+					}
+				}
+			}
+			tpl.Content = body
+		} else {
+			tpl.Content = content
+		}
+	} else {
+		tpl.Content = content
+	}
+
+	// Parse {{variables}} using simple string parsing
+	// (Can't use ctx.ParseTemplate here since we're in Init, not a handler)
+	var vars []string
+	for {
+		start := strings.Index(tpl.Content, "{{")
+		if start == -1 {
+			break
+		}
+		end := strings.Index(tpl.Content[start:], "}}")
+		if end == -1 {
+			break
+		}
+		varName := strings.TrimSpace(tpl.Content[start+2 : start+end])
+		vars = append(vars, varName)
+		tpl.Content = tpl.Content[:start] + "{{" + varName + "}}" + tpl.Content[start+end+2:]
+	}
+	tpl.Variables = vars
+
+	return tpl, nil
+}
+
+// registerTemplateCommands dynamically registers commands for each template
+func registerTemplateCommands(api ext.API, ctx ext.Context) {
+	for name, tpl := range templates {
+		// Skip if already registered (we'd need to track this)
+		tplCopy := tpl // Capture for closure
+		nameCopy := name
+
+		// Build description with metadata
+		desc := tplCopy.Description
+		if desc == "" {
+			desc = fmt.Sprintf("Run %s template", nameCopy)
+		}
+		if tplCopy.Model != "" {
+			desc += fmt.Sprintf(" [%s", tplCopy.Model)
+			if tplCopy.Skill != "" {
+				desc += fmt.Sprintf(" +%s", tplCopy.Skill)
+			}
+			desc += "]"
+		}
+
+		api.RegisterCommand(ext.CommandDef{
+			Name:        nameCopy,
+			Description: desc,
+			Execute: func(args string, ctx ext.Context) (string, error) {
+				return executeTemplate(ctx, tplCopy, args)
+			},
+		})
+	}
+}
+
+// executeTemplate runs a template with the given arguments
+func executeTemplate(ctx ext.Context, tpl PromptTemplate, args string) (string, error) {
+	// Store original model for restoration
+	originalModel := ctx.Model
+
+	// 1. Resolve and switch model if specified
+	if tpl.Model != "" {
+		// Parse model chain (comma-separated)
+		preferences := strings.Split(tpl.Model, ",")
+		for i := range preferences {
+			preferences[i] = strings.TrimSpace(preferences[i])
+		}
+
+		result := ctx.ResolveModelChain(preferences)
+		if result.Error != "" {
+			ctx.PrintError(fmt.Sprintf("Model resolution failed: %s", result.Error))
+			// Continue with current model
+		} else {
+			ctx.PrintInfo(fmt.Sprintf("Switching to model: %s", result.Model))
+			if err := ctx.SetModel(result.Model); err != nil {
+				ctx.PrintError(fmt.Sprintf("Failed to switch model: %s", err.Error()))
+			}
+		}
+	}
+
+	// 2. Inject skill if specified
+	if tpl.Skill != "" {
+		err := ctx.InjectSkillAsContext(tpl.Skill)
+		if err != "" {
+			ctx.PrintError(fmt.Sprintf("Skill injection failed: %s", err))
+		} else {
+			ctx.PrintInfo(fmt.Sprintf("Injected skill: %s", tpl.Skill))
+		}
+	}
+
+	// 3. Parse and render template
+	parsed := ctx.ParseTemplate(tpl.Name, tpl.Content)
+
+	// Build variable map
+	vars := make(map[string]string)
+
+	// Simple argument parsing: first arg is $1 (input), rest is $@
+	if len(parsed.Variables) > 0 {
+		argsList := ctx.SimpleParseArguments(args, len(parsed.Variables))
+		for i, varName := range parsed.Variables {
+			if i < len(parsed.Variables) && i+1 < len(argsList) {
+				vars[varName] = argsList[i+1]
+			}
+		}
+		// If single variable, use full args
+		if len(parsed.Variables) == 1 && vars[parsed.Variables[0]] == "" {
+			vars[parsed.Variables[0]] = args
+		}
+	}
+
+	// Render with model conditionals
+	content := ctx.RenderWithModelConditionals(tpl.Content)
+	rendered := ctx.RenderTemplate(ext.PromptTemplate{Name: tpl.Name, Content: content, Variables: parsed.Variables}, vars)
+
+	// 4. Send the rendered prompt
+	ctx.SendMessage(rendered)
+
+	// 5. Schedule model restoration after turn completes
+	// We use a goroutine to wait and restore
+	if tpl.Model != "" && originalModel != "" {
+		go func() {
+			// Note: In a real implementation, we'd use OnAgentEnd event
+			// For now, the user can manually switch back
+			ctx.SetStatus("template-mode", fmt.Sprintf("Template: %s (model will restore)", tpl.Name), 20)
+		}()
+	}
+
+	return fmt.Sprintf("Executing template: %s", tpl.Name), nil
+}

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

@@ -3,8 +3,10 @@ package app
 import (
 	"context"
 	"fmt"
+	"log"
 	"os"
 	"sync"
+	"sync/atomic"
 
 	tea "charm.land/bubbletea/v2"
 	"charm.land/fantasy"
@@ -598,9 +600,10 @@ 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 +623,9 @@ 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 +649,10 @@ 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 +707,10 @@ 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 +727,10 @@ 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 +764,8 @@ func (a *App) subscribeSDKEvents(sendFn func(tea.Msg)) func() {
 			})
 		case kit.SteerConsumedEvent:
 			sendFn(SteerConsumedEvent{})
+		case kit.StepUsageEvent:
+			a.recordStepUsage(ev, stepUsageSeen)
 		}
 	}))
 
@@ -925,40 +935,106 @@ 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 a.opts.Debug {
+		log.Printf("[DEBUG] recordStepUsage: hasUsage=%v input=%d output=%d cacheRead=%d cacheWrite=%d",
+			hasUsage, ev.InputTokens, ev.OutputTokens, ev.CacheReadTokens, ev.CacheWriteTokens)
+	}
+	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),
+	)
+	// NOTE: We do NOT call SetContextTokens here. Context fill is set once
+	// at turn completion via updateUsageFromTurnResult using FinalUsage.InputTokens,
+	// which reflects the full accumulated context. Per-step context tokens would
+	// cause the display to jump around during multi-step tool calls.
+}
+
 // 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 from the API response.
+//
+// NOTE: We only use ACTUAL token counts from API responses for cost tracking.
+// Estimation is never used for costs - only API-reported tokens are accurate.
+func (a *App) updateUsageFromTurnResult(result *kit.TurnResult, userPrompt string, sawStepUsage bool) {
 	if a.opts.UsageTracker == nil || result == nil {
 		return
 	}
 
+	// Debug logging for token tracking
+	if a.opts.Debug {
+		if result.TotalUsage != nil {
+			log.Printf("[DEBUG] updateUsageFromTurnResult TotalUsage: input=%d output=%d cacheRead=%d cacheCreate=%d",
+				result.TotalUsage.InputTokens, result.TotalUsage.OutputTokens,
+				result.TotalUsage.CacheReadTokens, result.TotalUsage.CacheCreationTokens)
+		} else {
+			log.Printf("[DEBUG] updateUsageFromTurnResult: TotalUsage=nil")
+		}
+		if result.FinalUsage != nil {
+			log.Printf("[DEBUG] updateUsageFromTurnResult FinalUsage: input=%d output=%d cacheRead=%d cacheCreate=%d",
+				result.FinalUsage.InputTokens, result.FinalUsage.OutputTokens,
+				result.FinalUsage.CacheReadTokens, result.FinalUsage.CacheCreationTokens)
+		} else {
+			log.Printf("[DEBUG] updateUsageFromTurnResult: FinalUsage=nil")
+		}
+		log.Printf("[DEBUG] updateUsageFromTurnResult: sawStepUsage=%v", sawStepUsage)
+	}
+
 	// --- Accumulate cost/token totals for the session ---
-	if result.TotalUsage != nil && result.TotalUsage.InputTokens > 0 {
+	// Only use actual API-reported tokens for cost tracking.
+	// If sawStepUsage is true, totals were already updated via StepUsageEvent.
+	// Check any token field > 0 (not just InputTokens) because cached prompts
+	// can result in InputTokens=0 while OutputTokens>0 (OpenAI-compatible behavior).
+	hasTotalUsage := result.TotalUsage != nil &&
+		(result.TotalUsage.InputTokens > 0 ||
+			result.TotalUsage.OutputTokens > 0 ||
+			result.TotalUsage.CacheReadTokens > 0 ||
+			result.TotalUsage.CacheCreationTokens > 0)
+	if a.opts.Debug {
+		log.Printf("[DEBUG] updateUsageFromTurnResult: hasTotalUsage=%v", hasTotalUsage)
+	}
+	if !sawStepUsage && hasTotalUsage {
+		if a.opts.Debug {
+			log.Printf("[DEBUG] updateUsageFromTurnResult: calling UpdateUsage input=%d output=%d cacheRead=%d cacheCreate=%d",
+				result.TotalUsage.InputTokens, result.TotalUsage.OutputTokens,
+				result.TotalUsage.CacheReadTokens, result.TotalUsage.CacheCreationTokens)
+		}
 		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) ---
-	// Use FinalUsage.InputTokens: the input token count of the last API call
-	// equals the number of tokens currently occupying the context window.
-	// Adding OutputTokens would overstate fill since the response is not part
-	// of the context that was *sent* to the model.
+	// Use FinalUsage.InputTokens as the context window fill. The API's InputTokens
+	// already includes the full conversation history (system prompt + all previous
+	// messages + current user message). Adding OutputTokens would double-count since
+	// the output becomes part of the input for the next turn.
 	if result.FinalUsage != nil && result.FinalUsage.InputTokens > 0 {
+		if a.opts.Debug {
+			log.Printf("[DEBUG] updateUsageFromTurnResult: calling SetContextTokens=%d (FinalUsage.InputTokens)",
+				result.FinalUsage.InputTokens)
+		}
 		a.opts.UsageTracker.SetContextTokens(int(result.FinalUsage.InputTokens))
 	}
 }

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 +532,133 @@ func TestQueueLength_reflects(t *testing.T) {
 		t.Fatalf("expected 3, got %d", got)
 	}
 }
+
+// TestRecordStepUsage_updatesTracker verifies that per-step usage updates are
+// recorded immediately for cost tracking. Context tokens are NOT updated here
+// (only via updateUsageFromTurnResult) to avoid display jumps during multi-step
+// tool calls.
+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)
+	}
+	// Context tokens should NOT be updated by recordStepUsage (only by updateUsageFromTurnResult)
+	if usage.contextCalls != 0 {
+		t.Fatalf("expected 0 context token updates from recordStepUsage, got %d", usage.contextCalls)
+	}
+}
+
+// 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)
+	}
+	// Context tokens should be InputTokens only (456)
+	if usage.contextCalls != 1 || usage.lastContextTokens != 456 {
+		t.Fatalf("expected final context tokens=456 (InputTokens only), got calls=%d tokens=%d", usage.contextCalls, usage.lastContextTokens)
+	}
+}
+
+// TestUpdateUsageFromTurnResult_recordsWhenInputTokensZero verifies that usage
+// is recorded when InputTokens=0 but OutputTokens>0 (OpenAI-compatible cache behavior).
+func TestUpdateUsageFromTurnResult_recordsWhenInputTokensZero(t *testing.T) {
+	usage := &usageUpdaterStub{}
+	app := New(Options{UsageTracker: usage}, nil)
+	defer app.Close()
+
+	// Simulate OpenAI-compatible behavior: all prompt tokens cached, InputTokens=0
+	app.updateUsageFromTurnResult(&kit.TurnResult{
+		Response: "ok",
+		TotalUsage: &fantasy.Usage{
+			InputTokens:         0,   // All cached - subtracted from prompt
+			OutputTokens:        150, // Actual generated tokens
+			CacheReadTokens:     500, // Cache hit
+			CacheCreationTokens: 0,
+		},
+		FinalUsage: &fantasy.Usage{InputTokens: 0, OutputTokens: 150},
+	}, "prompt", false)
+
+	usage.mu.Lock()
+	defer usage.mu.Unlock()
+
+	if usage.updateCalls != 1 {
+		t.Fatalf("expected 1 update call when InputTokens=0 but OutputTokens>0, got %d", usage.updateCalls)
+	}
+	if usage.lastUpdateInput != 0 || usage.lastUpdateOutput != 150 {
+		t.Fatalf("expected input=0 output=150, got input=%d output=%d",
+			usage.lastUpdateInput, usage.lastUpdateOutput)
+	}
+	if usage.lastUpdateCacheRead != 500 {
+		t.Fatalf("expected cache_read=500, got %d", usage.lastUpdateCacheRead)
+	}
+}
+
+// TestUpdateUsageFromTurnResult_contextTokensUsesInputOnly verifies that context
+// window fill uses InputTokens only (not input+output). The API's InputTokens
+// already includes the full conversation history; adding output would double-count.
+func TestUpdateUsageFromTurnResult_contextTokensUsesInputOnly(t *testing.T) {
+	usage := &usageUpdaterStub{}
+	app := New(Options{UsageTracker: usage}, nil)
+	defer app.Close()
+
+	app.updateUsageFromTurnResult(&kit.TurnResult{
+		Response: "ok",
+		TotalUsage: &fantasy.Usage{
+			InputTokens:  1000,
+			OutputTokens: 200,
+		},
+		FinalUsage: &fantasy.Usage{
+			InputTokens:  1000, // Full context including history
+			OutputTokens: 200,
+		},
+	}, "prompt", false)
+
+	usage.mu.Lock()
+	defer usage.mu.Unlock()
+
+	// Context tokens should be InputTokens only (1000), not input+output (1200)
+	// because InputTokens already includes the full conversation history
+	if usage.contextCalls != 1 || usage.lastContextTokens != 1000 {
+		t.Fatalf("expected context tokens=1000 (InputTokens only), got calls=%d tokens=%d",
+			usage.contextCalls, usage.lastContextTokens)
+	}
+}

internal/extensions/api.go

@@ -572,6 +572,102 @@ type Context struct {
 	//   })
 	//   // handle.Kill() to cancel, handle.Wait() to block
 	SpawnSubagent func(SubagentConfig) (*SubagentHandle, *SubagentResult, error)
+
+	// -------------------------------------------------------------------------
+	// Tree Navigation API (Phase 1 Bridge)
+	// -------------------------------------------------------------------------
+
+	// GetTreeNode returns a node by ID with full metadata and children.
+	// Returns nil if entry not found.
+	GetTreeNode func(entryID string) *TreeNode
+
+	// GetCurrentBranch returns the path from root to current leaf.
+	// Each node contains full metadata (unlike GetMessages which flattens).
+	GetCurrentBranch func() []TreeNode
+
+	// GetChildren returns direct child IDs of an entry.
+	GetChildren func(entryID string) []string
+
+	// NavigateTo branches/forks the session to the specified entry ID.
+	// Equivalent to SDK's Branch() but for extensions.
+	NavigateTo func(entryID string) TreeNavigationResult
+
+	// SummarizeBranch uses LLM to summarize a branch range.
+	// Returns summary text or error string (empty if success).
+	SummarizeBranch func(fromID, toID string) string
+
+	// CollapseBranch replaces a branch range with a summary entry.
+	// This is the "fresh context" primitive for context window management.
+	CollapseBranch func(fromID, toID, summary string) TreeNavigationResult
+
+	// -------------------------------------------------------------------------
+	// Skill Loading API (Phase 2 Bridge)
+	// -------------------------------------------------------------------------
+
+	// LoadSkill loads a single skill file from path.
+	// Parses YAML frontmatter, returns skill with content ready for injection.
+	LoadSkill func(path string) (*Skill, string)
+
+	// LoadSkillsFromDir discovers and loads all skills from a directory.
+	LoadSkillsFromDir func(dir string) SkillLoadResult
+
+	// DiscoverSkills finds skills in standard locations.
+	// Checks ~/.config/kit/skills/, .kit/skills/, .agents/skills/
+	DiscoverSkills func() SkillLoadResult
+
+	// InjectSkillAsContext sends a skill's content as a system message.
+	// Looks up skill by name from discovered skills.
+	InjectSkillAsContext func(skillName string) string
+
+	// InjectRawSkillAsContext loads and immediately injects a skill file.
+	InjectRawSkillAsContext func(path string) string
+
+	// GetAvailableSkills returns all currently loaded/discovered skills.
+	GetAvailableSkills func() []Skill
+
+	// -------------------------------------------------------------------------
+	// Template Parsing API (Phase 3 Bridge)
+	// -------------------------------------------------------------------------
+
+	// ParseTemplate extracts {{variables}} from template content.
+	ParseTemplate func(name, content string) PromptTemplate
+
+	// RenderTemplate substitutes variables into template content.
+	RenderTemplate func(tpl PromptTemplate, vars map[string]string) string
+
+	// ParseArguments parses command-line style arguments.
+	ParseArguments func(input string, pattern ArgumentPattern) ParseResult
+
+	// SimpleParseArguments parses $1, $2, $@ style arguments.
+	// Returns slice where [0]=full input, [1]=$1, [2]=$2, ... [n]=$@
+	SimpleParseArguments func(input string, count int) []string
+
+	// EvaluateModelConditional checks if condition matches current model.
+	// Condition supports wildcards: * matches any, ? matches single char.
+	EvaluateModelConditional func(condition string) bool
+
+	// RenderWithModelConditionals processes <if-model> blocks in content.
+	RenderWithModelConditionals func(content string) string
+
+	// -------------------------------------------------------------------------
+	// Model Resolution API (Phase 4 Bridge)
+	// -------------------------------------------------------------------------
+
+	// ResolveModelChain attempts each model in order until one is available.
+	ResolveModelChain func(preferences []string) ModelResolutionResult
+
+	// GetModelCapabilities returns capabilities for a specific model.
+	// If model is empty, uses current model.
+	GetModelCapabilities func(model string) (ModelCapabilities, string)
+
+	// CheckModelAvailable verifies if a model string is valid.
+	CheckModelAvailable func(model string) bool
+
+	// GetCurrentProvider returns just the provider part of current model.
+	GetCurrentProvider func() string
+
+	// GetCurrentModelID returns just the model ID part of current model.
+	GetCurrentModelID func() string
 }
 
 // ---------------------------------------------------------------------------
@@ -598,6 +694,148 @@ type SessionMessage struct {
 	Timestamp string
 }
 
+// ---------------------------------------------------------------------------
+// Tree navigation types (exposed to Yaegi — concrete structs)
+// ---------------------------------------------------------------------------
+
+// TreeNode represents a node in the session tree for navigation.
+// Extensions use this to traverse conversation history and implement
+// features like "fresh context" loops and branch summarization.
+type TreeNode struct {
+	// ID is the unique entry identifier.
+	ID string
+	// ParentID links this entry to its parent (empty if root).
+	ParentID string
+	// Type is the entry type: "message", "branch_summary", "model_change", "extension_data", "tool_execution".
+	Type string
+	// Role is the message role for message entries: "user", "assistant", "system", "tool".
+	Role string
+	// Content is the text content or summary.
+	Content string
+	// Model is the model that generated this (for assistant messages).
+	Model string
+	// Provider is the provider used.
+	Provider string
+	// Timestamp is the RFC3339-formatted creation time.
+	Timestamp string
+	// Children is the list of child entry IDs for tree traversal.
+	Children []string
+}
+
+// TreeNavigationResult reports success or failure of tree operations.
+type TreeNavigationResult struct {
+	// Success is true if the operation completed.
+	Success bool
+	// Error describes what went wrong (empty if success).
+	Error string
+}
+
+// ---------------------------------------------------------------------------
+// Skill types (exposed to Yaegi — concrete structs)
+// ---------------------------------------------------------------------------
+
+// Skill represents a loaded skill file with parsed YAML frontmatter.
+type Skill struct {
+	// Name is the human-readable identifier.
+	Name string
+	// Description summarizes what this skill provides.
+	Description string
+	// Content is the markdown body (frontmatter stripped).
+	Content string
+	// Path is the absolute filesystem path.
+	Path string
+	// Tags are optional labels for categorization.
+	Tags []string
+	// When controls automatic inclusion: "always", "on-demand", or file-glob.
+	When string
+}
+
+// SkillLoadResult reports skills loaded from a directory.
+type SkillLoadResult struct {
+	// Skills is the list of loaded skills.
+	Skills []Skill
+	// Error describes loading failures (empty if success).
+	Error string
+}
+
+// ---------------------------------------------------------------------------
+// Template parsing types (exposed to Yaegi — concrete structs)
+// ---------------------------------------------------------------------------
+
+// PromptTemplate represents a parsed template with variable placeholders.
+type PromptTemplate struct {
+	// Name is the template identifier.
+	Name string
+	// Content is the original template content.
+	Content string
+	// Variables are the extracted {{variable}} names.
+	Variables []string
+}
+
+// ArgumentPattern defines how to parse command arguments.
+type ArgumentPattern struct {
+	// Positional names for $1, $2, etc.
+	Positional []string
+	// Rest is the variable name for $@ (all remaining).
+	Rest string
+	// Flags maps flag names to variable names (e.g., "--loop" -> "loop").
+	Flags map[string]string
+}
+
+// ParseResult reports argument parsing outcome.
+type ParseResult struct {
+	// Vars maps variable names to values for positional args.
+	Vars map[string]string
+	// Flags maps flag names to values.
+	Flags map[string]string
+	// Rest is remaining unparsed text.
+	Rest string
+	// Error describes parsing failures (empty if success).
+	Error string
+}
+
+// ModelConditional represents an <if-model> block for evaluation.
+type ModelConditional struct {
+	// Condition is the model pattern (e.g., "claude-*", "anthropic/*").
+	Condition string
+	// Content is rendered if condition matches.
+	Content string
+	// Else is rendered if condition doesn't match.
+	Else string
+}
+
+// ---------------------------------------------------------------------------
+// Model resolution types (exposed to Yaegi — concrete structs)
+// ---------------------------------------------------------------------------
+
+// ModelCapabilities describes what a model supports.
+type ModelCapabilities struct {
+	// Provider is the provider ID (e.g., "anthropic").
+	Provider string
+	// ModelID is the model identifier (e.g., "claude-sonnet-4-20250929").
+	ModelID string
+	// ContextLimit is the maximum context window in tokens.
+	ContextLimit int
+	// OutputLimit is the maximum output tokens.
+	OutputLimit int
+	// Reasoning indicates if the model supports reasoning/thinking.
+	Reasoning bool
+	// Streaming indicates if the model supports streaming.
+	Streaming bool
+}
+
+// ModelResolutionResult reports model chain resolution outcome.
+type ModelResolutionResult struct {
+	// Model is the selected model in "provider/model" format.
+	Model string
+	// Capabilities describes the selected model.
+	Capabilities ModelCapabilities
+	// Attempted lists models tried before success.
+	Attempted []string
+	// Error describes resolution failures (empty if success).
+	Error string
+}
+
 // ExtensionEntry represents persisted extension data stored in the session.
 // Extensions use AppendEntry to save custom state and GetEntries to retrieve
 // it on session resume.

internal/extensions/runner.go

@@ -56,11 +56,261 @@ 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
+		}
+	}
+
+	// -------------------------------------------------------------------------
+	// Tree Navigation API no-ops
+	// -------------------------------------------------------------------------
+	if ctx.GetTreeNode == nil {
+		ctx.GetTreeNode = func(string) *TreeNode { return nil }
+	}
+	if ctx.GetCurrentBranch == nil {
+		ctx.GetCurrentBranch = func() []TreeNode { return nil }
+	}
+	if ctx.GetChildren == nil {
+		ctx.GetChildren = func(string) []string { return nil }
+	}
+	if ctx.NavigateTo == nil {
+		ctx.NavigateTo = func(string) TreeNavigationResult {
+			return TreeNavigationResult{Success: false, Error: "not implemented"}
+		}
+	}
+	if ctx.SummarizeBranch == nil {
+		ctx.SummarizeBranch = func(string, string) string {
+			return ""
+		}
+	}
+	if ctx.CollapseBranch == nil {
+		ctx.CollapseBranch = func(string, string, string) TreeNavigationResult {
+			return TreeNavigationResult{Success: false, Error: "not implemented"}
+		}
+	}
+
+	// -------------------------------------------------------------------------
+	// Skill Loading API no-ops
+	// -------------------------------------------------------------------------
+	if ctx.LoadSkill == nil {
+		ctx.LoadSkill = func(string) (*Skill, string) { return nil, "" }
+	}
+	if ctx.LoadSkillsFromDir == nil {
+		ctx.LoadSkillsFromDir = func(string) SkillLoadResult { return SkillLoadResult{} }
+	}
+	if ctx.DiscoverSkills == nil {
+		ctx.DiscoverSkills = func() SkillLoadResult { return SkillLoadResult{} }
+	}
+	if ctx.InjectSkillAsContext == nil {
+		ctx.InjectSkillAsContext = func(string) string { return "" }
+	}
+	if ctx.InjectRawSkillAsContext == nil {
+		ctx.InjectRawSkillAsContext = func(string) string { return "" }
+	}
+	if ctx.GetAvailableSkills == nil {
+		ctx.GetAvailableSkills = func() []Skill { return nil }
+	}
+
+	// -------------------------------------------------------------------------
+	// Template Parsing API no-ops
+	// -------------------------------------------------------------------------
+	if ctx.ParseTemplate == nil {
+		ctx.ParseTemplate = func(string, string) PromptTemplate { return PromptTemplate{} }
+	}
+	if ctx.RenderTemplate == nil {
+		ctx.RenderTemplate = func(PromptTemplate, map[string]string) string { return "" }
+	}
+	if ctx.ParseArguments == nil {
+		ctx.ParseArguments = func(string, ArgumentPattern) ParseResult { return ParseResult{} }
+	}
+	if ctx.SimpleParseArguments == nil {
+		ctx.SimpleParseArguments = func(string, int) []string { return nil }
+	}
+	if ctx.EvaluateModelConditional == nil {
+		ctx.EvaluateModelConditional = func(string) bool { return false }
+	}
+	if ctx.RenderWithModelConditionals == nil {
+		ctx.RenderWithModelConditionals = func(string) string { return "" }
+	}
+
+	// -------------------------------------------------------------------------
+	// Model Resolution API no-ops
+	// -------------------------------------------------------------------------
+	if ctx.ResolveModelChain == nil {
+		ctx.ResolveModelChain = func([]string) ModelResolutionResult {
+			return ModelResolutionResult{Error: "not implemented"}
+		}
+	}
+	if ctx.GetModelCapabilities == nil {
+		ctx.GetModelCapabilities = func(string) (ModelCapabilities, string) {
+			return ModelCapabilities{}, "not implemented"
+		}
+	}
+	if ctx.CheckModelAvailable == nil {
+		ctx.CheckModelAvailable = func(string) bool { return false }
+	}
+	if ctx.GetCurrentProvider == nil {
+		ctx.GetCurrentProvider = func() string { return "" }
+	}
+	if ctx.GetCurrentModelID == nil {
+		ctx.GetCurrentModelID = func() string { return "" }
+	}
+
+	return ctx
 }
 
 // GetContext returns a snapshot of the current runtime context. Thread-safe.

internal/extensions/symbols.go

@@ -128,6 +128,24 @@ func Symbols() interp.Exports {
 			"ThemeColor":       reflect.ValueOf((*ThemeColor)(nil)),
 			"ThemeColorConfig": reflect.ValueOf((*ThemeColorConfig)(nil)),
 
+			// Tree navigation types
+			"TreeNode":             reflect.ValueOf((*TreeNode)(nil)),
+			"TreeNavigationResult": reflect.ValueOf((*TreeNavigationResult)(nil)),
+
+			// Skill types
+			"Skill":           reflect.ValueOf((*Skill)(nil)),
+			"SkillLoadResult": reflect.ValueOf((*SkillLoadResult)(nil)),
+
+			// Template parsing types
+			"PromptTemplate":   reflect.ValueOf((*PromptTemplate)(nil)),
+			"ArgumentPattern":  reflect.ValueOf((*ArgumentPattern)(nil)),
+			"ParseResult":      reflect.ValueOf((*ParseResult)(nil)),
+			"ModelConditional": reflect.ValueOf((*ModelConditional)(nil)),
+
+			// Model resolution types
+			"ModelCapabilities":     reflect.ValueOf((*ModelCapabilities)(nil)),
+			"ModelResolutionResult": reflect.ValueOf((*ModelResolutionResult)(nil)),
+
 			// Event structs
 			"ToolCallEvent":           reflect.ValueOf((*ToolCallEvent)(nil)),
 			"ToolCallResult":          reflect.ValueOf((*ToolCallResult)(nil)),

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/cli.go

@@ -179,9 +179,8 @@ func (c *CLI) DisplayDebugConfig(config map[string]any) {
 }
 
 // UpdateUsageFromResponse records token usage using metadata from the fantasy
-// response when available. Falls back to text-based estimation if the metadata is
-// missing or appears unreliable. This provides more accurate usage tracking when
-// providers supply token count information.
+// response. Only actual API-reported tokens are used for cost tracking.
+// If the provider doesn't report token counts, no usage is recorded.
 func (c *CLI) UpdateUsageFromResponse(response *fantasy.Response, inputText string) {
 	if c.usageTracker == nil {
 		return
@@ -191,8 +190,9 @@ func (c *CLI) UpdateUsageFromResponse(response *fantasy.Response, inputText stri
 	inputTokens := int(usage.InputTokens)
 	outputTokens := int(usage.OutputTokens)
 
-	// Validate that the metadata seems reasonable
-	// Use API-reported tokens if input tokens are available (output may be 0 in some cases)
+	// Only use actual API-reported tokens for cost tracking.
+	// We intentionally do NOT estimate tokens - estimation is inaccurate
+	// and should never be used for cost calculations.
 	if inputTokens > 0 {
 		cacheReadTokens := int(usage.CacheReadTokens)
 		cacheWriteTokens := int(usage.CacheCreationTokens)
@@ -200,11 +200,9 @@ func (c *CLI) UpdateUsageFromResponse(response *fantasy.Response, inputText stri
 		// Per-response usage is a single API call, so it represents the
 		// actual context window fill level.
 		c.usageTracker.SetContextTokens(inputTokens + outputTokens)
-	} else {
-		// Fallback to estimation if no metadata is available.
-		// EstimateAndUpdateUsage sets context tokens internally.
-		c.usageTracker.EstimateAndUpdateUsage(inputText, response.Content.Text())
 	}
+	// If inputTokens is 0, the provider didn't report usage - we skip recording
+	// rather than estimating, to ensure cost accuracy.
 }
 
 // DisplayUsageAfterResponse renders and displays token usage information immediately

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 +442,47 @@ 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.WithAlertPalette(herald.AlertPalette{
+			Note:      theme.Info,
+			Tip:       theme.Success,
+			Important: theme.Accent,
+			Warning:   theme.Warning,
+			Caution:   theme.Error,
+		}),
+		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 ""
@@ -3027,6 +3021,10 @@ func (m *AppModel) performNewSession() tea.Cmd {
 		if m.appCtrl != nil {
 			m.appCtrl.ClearMessages()
 		}
+		// Reset usage statistics for fresh session
+		if m.usageTracker != nil {
+			m.usageTracker.Reset()
+		}
 		m.printSystemMessage("Conversation cleared. Starting fresh.")
 		return nil
 	}
@@ -3040,6 +3038,10 @@ func (m *AppModel) performNewSession() tea.Cmd {
 
 	// Switch to the new session, closing the old one
 	m.appCtrl.SwitchTreeSession(newTs)
+	// Reset usage statistics for the new session
+	if m.usageTracker != nil {
+		m.usageTracker.Reset()
+	}
 	m.printSystemMessage("New session started. Previous conversation saved.")
 	return nil
 }

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

@@ -134,13 +134,23 @@ func (ut *UsageTracker) EstimateAndUpdateUsage(inputText, outputText string) {
 }
 
 // SetContextTokens records the approximate current context window utilization.
-// This should be set from the final API call's input + output tokens (i.e.
-// FinalResponse.Usage) rather than the aggregate TotalUsage, because TotalUsage
+// This should be set from FinalUsage.InputTokens, which already includes the
+// full conversation history (system prompt + all previous messages). Do NOT
+// add OutputTokens as that would double-count (output becomes input next turn).
+// Use FinalResponse.Usage rather than aggregate TotalUsage, because TotalUsage
 // sums across all tool-calling steps and overstates the actual window fill level.
 func (ut *UsageTracker) SetContextTokens(tokens int) {
 	ut.mu.Lock()
 	defer ut.mu.Unlock()
-	ut.contextTokens = tokens
+	// Track the maximum context seen so far. In multi-step tool calls,
+	// FinalUsage.InputTokens may reflect only the last step's input, which
+	// can be smaller than previous steps. We want to show the largest context
+	// the model has processed in this session.
+	if tokens > ut.contextTokens {
+		ut.contextTokens = tokens
+	}
+	// If tokens < current, we keep the larger value (no-op)
+	// This prevents the display from dropping during multi-step tool calls.
 }
 
 // RenderUsageInfo generates a formatted string displaying current usage statistics
@@ -151,10 +161,6 @@ 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

@@ -4,6 +4,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"log"
 	"os"
 	"path/filepath"
 	"strings"
@@ -1063,6 +1064,15 @@ 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
@@ -1532,6 +1542,10 @@ func (m *Kit) generate(ctx context.Context, messages []fantasy.Message) (*agent.
 		},
 		func(inputTokens, outputTokens, cacheReadTokens, cacheCreationTokens int64) {
 			// Emit step usage event for real-time cost tracking
+			if viper.GetBool("debug") {
+				log.Printf("[DEBUG] Kit.generate emitting StepUsageEvent: input=%d output=%d cacheRead=%d cacheCreate=%d",
+					inputTokens, outputTokens, cacheReadTokens, cacheCreationTokens)
+			}
 			m.events.emit(StepUsageEvent{
 				InputTokens:      uint64(inputTokens),
 				OutputTokens:     uint64(outputTokens),

pkg/kit/sessions.go

@@ -1,9 +1,14 @@
 package kit
 
 import (
+	"context"
 	"fmt"
 	"os"
+	"strings"
+	"time"
 
+	"github.com/mark3labs/kit/internal/extensions"
+	"github.com/mark3labs/kit/internal/message"
 	"github.com/mark3labs/kit/internal/session"
 )
 
@@ -86,3 +91,213 @@ func (m *Kit) SetSessionName(name string) error {
 	_, err := m.treeSession.AppendSessionInfo(name)
 	return err
 }
+
+// ---------------------------------------------------------------------------
+// Tree Navigation Bridge for Extensions (Phase 1)
+// ---------------------------------------------------------------------------
+
+// GetTreeNode returns a node by ID with full metadata and children.
+// Returns nil if entry not found or no tree session.
+func (m *Kit) GetTreeNode(entryID string) *TreeNode {
+	if m.treeSession == nil {
+		return nil
+	}
+	entry := m.treeSession.GetEntry(entryID)
+	if entry == nil {
+		return nil
+	}
+	return m.entryToTreeNode(entry)
+}
+
+// GetCurrentBranch returns the path from root to current leaf as TreeNodes.
+func (m *Kit) GetCurrentBranch() []TreeNode {
+	if m.treeSession == nil {
+		return nil
+	}
+	branch := m.treeSession.GetBranch("")
+	var nodes []TreeNode
+	for _, entry := range branch {
+		node := m.entryToTreeNode(entry)
+		if node != nil {
+			nodes = append(nodes, *node)
+		}
+	}
+	return nodes
+}
+
+// GetChildren returns direct child IDs of an entry.
+func (m *Kit) GetChildren(parentID string) []string {
+	if m.treeSession == nil {
+		return nil
+	}
+	return m.treeSession.GetChildren(parentID)
+}
+
+// NavigateTo branches/forks the session to the specified entry ID.
+// Returns error description or empty string for success.
+func (m *Kit) NavigateTo(entryID string) string {
+	if m.treeSession == nil {
+		return "no tree session available"
+	}
+	if err := m.treeSession.Branch(entryID); err != nil {
+		return err.Error()
+	}
+	return ""
+}
+
+// SummarizeBranch uses LLM to summarize a branch range.
+// Returns summary text or error string.
+func (m *Kit) SummarizeBranch(fromID, toID string) string {
+	if m.treeSession == nil {
+		return ""
+	}
+
+	// Get the branch and find the range
+	branch := m.treeSession.GetBranch("")
+	var startIdx, endIdx = -1, -1
+	for i, entry := range branch {
+		id := m.getEntryID(entry)
+		if id == fromID {
+			startIdx = i
+		}
+		if id == toID {
+			endIdx = i
+		}
+	}
+
+	if startIdx < 0 || endIdx < 0 || startIdx > endIdx {
+		return ""
+	}
+
+	// Build text to summarize
+	var content strings.Builder
+	for i := startIdx; i <= endIdx; i++ {
+		node := m.entryToTreeNode(branch[i])
+		if node != nil && node.Content != "" {
+			fmt.Fprintf(&content, "[%s] %s\n\n", node.Role, node.Content)
+		}
+	}
+
+	if content.Len() == 0 {
+		return ""
+	}
+
+	// Use LLM to summarize
+	resp, err := m.ExecuteCompletion(context.Background(), extensions.CompleteRequest{
+		Model:  "", // Use current model
+		System: "You are a concise summarization assistant. Summarize the conversation in 2-3 sentences.",
+		Prompt: content.String(),
+	})
+	if err != nil {
+		return ""
+	}
+	return resp.Text
+}
+
+// CollapseBranch replaces a branch range with a summary entry.
+// Returns error description or empty string for success.
+func (m *Kit) CollapseBranch(fromID, toID, summary string) string {
+	if m.treeSession == nil {
+		return "no tree session available"
+	}
+	_, err := m.treeSession.AppendBranchSummary(fromID, summary)
+	if err != nil {
+		return err.Error()
+	}
+	return ""
+}
+
+// entryToTreeNode converts a session entry to a TreeNode.
+func (m *Kit) entryToTreeNode(entry any) *TreeNode {
+	switch e := entry.(type) {
+	case *session.MessageEntry:
+		msg, err := e.ToMessage()
+		if err != nil {
+			return nil
+		}
+		var content strings.Builder
+		for _, p := range msg.Parts {
+			switch pt := p.(type) {
+			case message.TextContent:
+				content.WriteString(pt.Text)
+			case message.ReasoningContent:
+				content.WriteString(pt.Thinking)
+			case message.ToolCall:
+				fmt.Fprintf(&content, "[tool_call: %s]", pt.Name)
+			case message.ToolResult:
+				fmt.Fprintf(&content, "[tool_result: %s]", pt.Content)
+			}
+		}
+		return &TreeNode{
+			ID:        e.ID,
+			ParentID:  e.ParentID,
+			Type:      "message",
+			Role:      string(msg.Role),
+			Content:   content.String(),
+			Model:     msg.Model,
+			Provider:  msg.Provider,
+			Timestamp: e.Timestamp.Format(time.RFC3339),
+			Children:  m.treeSession.GetChildren(e.ID),
+		}
+	case *session.BranchSummaryEntry:
+		return &TreeNode{
+			ID:        e.ID,
+			ParentID:  e.ParentID,
+			Type:      "branch_summary",
+			Content:   e.Summary,
+			Timestamp: e.Timestamp.Format(time.RFC3339),
+			Children:  m.treeSession.GetChildren(e.ID),
+		}
+	case *session.ModelChangeEntry:
+		return &TreeNode{
+			ID:        e.ID,
+			ParentID:  e.ParentID,
+			Type:      "model_change",
+			Content:   fmt.Sprintf("Model changed to %s/%s", e.Provider, e.ModelID),
+			Model:     e.Provider + "/" + e.ModelID,
+			Provider:  e.Provider,
+			Timestamp: e.Timestamp.Format(time.RFC3339),
+			Children:  m.treeSession.GetChildren(e.ID),
+		}
+	case *session.ExtensionDataEntry:
+		return &TreeNode{
+			ID:        e.ID,
+			ParentID:  e.ParentID,
+			Type:      "extension_data",
+			Content:   fmt.Sprintf("Extension data: %s", e.ExtType),
+			Timestamp: e.Timestamp.Format(time.RFC3339),
+			Children:  m.treeSession.GetChildren(e.ID),
+		}
+	default:
+		return nil
+	}
+}
+
+// getEntryID extracts the ID from a session entry.
+func (m *Kit) getEntryID(entry any) string {
+	switch e := entry.(type) {
+	case *session.MessageEntry:
+		return e.ID
+	case *session.BranchSummaryEntry:
+		return e.ID
+	case *session.ModelChangeEntry:
+		return e.ID
+	case *session.ExtensionDataEntry:
+		return e.ID
+	default:
+		return ""
+	}
+}
+
+// TreeNode represents a node in the session tree for SDK consumers.
+type TreeNode struct {
+	ID        string
+	ParentID  string
+	Type      string // "message", "branch_summary", "model_change", "extension_data"
+	Role      string // for messages: "user", "assistant", "system", "tool"
+	Content   string
+	Model     string
+	Provider  string
+	Timestamp string
+	Children  []string
+}

pkg/kit/skills.go

@@ -1,6 +1,12 @@
 package kit
 
-import "github.com/mark3labs/kit/internal/skills"
+import (
+	"os"
+	"sync"
+
+	"github.com/mark3labs/kit/internal/extensions"
+	"github.com/mark3labs/kit/internal/skills"
+)
 
 // ==== Skills Types ====
 
@@ -67,3 +73,86 @@ func LoadPromptTemplate(path string) (*PromptTemplate, error) {
 func NewPromptBuilder(basePrompt string) *PromptBuilder {
 	return skills.NewPromptBuilder(basePrompt)
 }
+
+// ---------------------------------------------------------------------------
+// Skill Bridge for Extensions (Phase 2)
+// ---------------------------------------------------------------------------
+
+// skillCache holds skills discovered for the current session.
+type skillCache struct {
+	skills []*Skill
+	mu     sync.RWMutex
+}
+
+var globalSkillCache skillCache
+
+// DiscoverSkillsForExtension finds skills in standard locations for extensions.
+// Returns skills in the extension-facing format.
+func (m *Kit) DiscoverSkillsForExtension() []extensions.Skill {
+	cwd, _ := os.Getwd()
+
+	// Check cache first
+	globalSkillCache.mu.RLock()
+	if len(globalSkillCache.skills) > 0 {
+		globalSkillCache.mu.RUnlock()
+		return m.convertSkills(globalSkillCache.skills)
+	}
+	globalSkillCache.mu.RUnlock()
+
+	// Load fresh
+	skillList, _ := skills.LoadSkills(cwd)
+
+	globalSkillCache.mu.Lock()
+	globalSkillCache.skills = skillList
+	globalSkillCache.mu.Unlock()
+
+	return m.convertSkills(skillList)
+}
+
+// LoadSkillForExtension loads a single skill file for extensions.
+func (m *Kit) LoadSkillForExtension(path string) (*extensions.Skill, string) {
+	s, err := skills.LoadSkill(path)
+	if err != nil {
+		return nil, err.Error()
+	}
+	return m.convertSkill(s), ""
+}
+
+// LoadSkillsFromDirForExtension loads all skills from a directory for extensions.
+func (m *Kit) LoadSkillsFromDirForExtension(dir string) extensions.SkillLoadResult {
+	skillList, err := skills.LoadSkillsFromDir(dir)
+	if err != nil {
+		return extensions.SkillLoadResult{Error: err.Error()}
+	}
+	return extensions.SkillLoadResult{Skills: m.convertSkills(skillList)}
+}
+
+// convertSkill converts internal skill to extension-facing format.
+func (m *Kit) convertSkill(s *skills.Skill) *extensions.Skill {
+	return &extensions.Skill{
+		Name:        s.Name,
+		Description: s.Description,
+		Content:     s.Content,
+		Path:        s.Path,
+		Tags:        s.Tags,
+		When:        s.When,
+	}
+}
+
+// convertSkills converts a slice of skills.
+func (m *Kit) convertSkills(skills []*skills.Skill) []extensions.Skill {
+	result := make([]extensions.Skill, 0, len(skills))
+	for _, s := range skills {
+		if converted := m.convertSkill(s); converted != nil {
+			result = append(result, *converted)
+		}
+	}
+	return result
+}
+
+// ClearSkillCache clears the global skill cache (called on reload).
+func (m *Kit) ClearSkillCache() {
+	globalSkillCache.mu.Lock()
+	globalSkillCache.skills = nil
+	globalSkillCache.mu.Unlock()
+}

pkg/kit/template_bridge.go

@@ -0,0 +1,462 @@
+package kit
+
+import (
+	"regexp"
+	"strings"
+
+	"github.com/mark3labs/kit/internal/extensions"
+	"github.com/mark3labs/kit/internal/models"
+)
+
+// ---------------------------------------------------------------------------
+// Template Parsing Bridge for Extensions (Phase 3)
+// ---------------------------------------------------------------------------
+
+// varRegex matches {{variable}} placeholders in templates.
+var varRegex = regexp.MustCompile(`\{\{\s*([a-zA-Z_][a-zA-Z0-9_]*)\s*\}\}`)
+
+// ParseTemplate extracts {{variables}} from template content.
+func ParseTemplate(name, content string) extensions.PromptTemplate {
+	matches := varRegex.FindAllStringSubmatch(content, -1)
+	vars := make([]string, 0, len(matches))
+	seen := make(map[string]bool)
+	for _, m := range matches {
+		if len(m) > 1 && !seen[m[1]] {
+			seen[m[1]] = true
+			vars = append(vars, m[1])
+		}
+	}
+	return extensions.PromptTemplate{
+		Name:      name,
+		Content:   content,
+		Variables: vars,
+	}
+}
+
+// RenderTemplate substitutes variables into template content.
+func RenderTemplate(tpl extensions.PromptTemplate, vars map[string]string) string {
+	result := tpl.Content
+	for name, value := range vars {
+		placeholder := "{{" + name + "}}"
+		result = strings.ReplaceAll(result, placeholder, value)
+		// Also handle with spaces
+		placeholderSpaced := "{{ " + name + " }}"
+		result = strings.ReplaceAll(result, placeholderSpaced, value)
+	}
+	return result
+}
+
+// ParseArguments parses command-line style arguments.
+func ParseArguments(input string, pattern extensions.ArgumentPattern) extensions.ParseResult {
+	result := extensions.ParseResult{
+		Vars:  make(map[string]string),
+		Flags: make(map[string]string),
+	}
+
+	fields := parseFields(input)
+	if len(fields) == 0 {
+		return result
+	}
+
+	// First field is the command itself (if present)
+	startIdx := 0
+	if len(fields) > 0 && !strings.HasPrefix(fields[0], "-") {
+		// Check if it's a command name or positional arg
+		if len(pattern.Positional) == 0 || !isFlag(fields[0], pattern.Flags) {
+			startIdx = 1 // Skip command name
+		}
+	}
+
+	// Parse flags
+	i := startIdx
+	for i < len(fields) {
+		field := fields[i]
+
+		// Check for flags
+		if strings.HasPrefix(field, "--") {
+			flagName := field[2:]
+			if varName, ok := pattern.Flags["--"+flagName]; ok {
+				// Flag with value
+				if i+1 < len(fields) && !strings.HasPrefix(fields[i+1], "-") {
+					result.Flags["--"+flagName] = fields[i+1]
+					result.Vars[varName] = fields[i+1]
+					i += 2
+					continue
+				}
+				// Boolean flag
+				result.Flags["--"+flagName] = "true"
+				result.Vars[varName] = "true"
+			}
+			i++
+			continue
+		}
+
+		if strings.HasPrefix(field, "-") && len(field) > 1 {
+			flagName := field[1:]
+			if varName, ok := pattern.Flags["-"+flagName]; ok {
+				// Flag with value
+				if i+1 < len(fields) && !strings.HasPrefix(fields[i+1], "-") {
+					result.Flags["-"+flagName] = fields[i+1]
+					result.Vars[varName] = fields[i+1]
+					i += 2
+					continue
+				}
+				// Boolean flag
+				result.Flags["-"+flagName] = "true"
+				result.Vars[varName] = "true"
+			}
+			i++
+			continue
+		}
+
+		i++
+	}
+
+	// Collect remaining as positional args and "rest"
+	positional := make([]string, 0)
+	i = startIdx
+	for i < len(fields) {
+		field := fields[i]
+		if !strings.HasPrefix(field, "-") {
+			// Check if this was consumed as a flag value
+			consumed := false
+			for _, v := range result.Vars {
+				if v == field {
+					// Might be consumed, check previous field
+					if i > 0 {
+						prev := fields[i-1]
+						if strings.HasPrefix(prev, "-") {
+							consumed = true
+							break
+						}
+					}
+				}
+			}
+			if !consumed {
+				positional = append(positional, field)
+			}
+		}
+		i++
+	}
+
+	// Map positional args
+	for i, name := range pattern.Positional {
+		if i < len(positional) {
+			result.Vars[name] = positional[i]
+		}
+	}
+
+	// Set rest
+	if pattern.Rest != "" && len(positional) > len(pattern.Positional) {
+		restStart := len(pattern.Positional)
+		if restStart < len(positional) {
+			result.Vars[pattern.Rest] = strings.Join(positional[restStart:], " ")
+		}
+	}
+
+	result.Rest = strings.Join(fields, " ")
+	return result
+}
+
+// SimpleParseArguments parses $1, $2, $@ style arguments.
+// Returns slice where [0]=full input, [1]=$1, [2]=$2, ... [n]=$@
+func SimpleParseArguments(input string, count int) []string {
+	fields := parseFields(input)
+	result := make([]string, 0, count+2)
+	result = append(result, input) // [0] = full input
+
+	// [1]..[count] = positional args
+	for i := 0; i < count; i++ {
+		if i < len(fields) {
+			result = append(result, fields[i])
+		} else {
+			result = append(result, "")
+		}
+	}
+
+	// [n] = $@ (all remaining)
+	if len(fields) > count {
+		result = append(result, strings.Join(fields[count:], " "))
+	} else {
+		result = append(result, "")
+	}
+
+	return result
+}
+
+// parseFields splits input respecting quoted strings.
+func parseFields(input string) []string {
+	var fields []string
+	var current strings.Builder
+	inQuote := false
+	quoteChar := rune(0)
+
+	for _, r := range input {
+		switch r {
+		case '"', '\'':
+			if !inQuote {
+				inQuote = true
+				quoteChar = r
+			} else if r == quoteChar {
+				inQuote = false
+				quoteChar = 0
+			} else {
+				current.WriteRune(r)
+			}
+		case ' ', '\t':
+			if inQuote {
+				current.WriteRune(r)
+			} else {
+				if current.Len() > 0 {
+					fields = append(fields, current.String())
+					current.Reset()
+				}
+			}
+		default:
+			current.WriteRune(r)
+		}
+	}
+
+	if current.Len() > 0 {
+		fields = append(fields, current.String())
+	}
+
+	return fields
+}
+
+// isFlag checks if a field is a known flag.
+func isFlag(field string, flags map[string]string) bool {
+	if strings.HasPrefix(field, "--") {
+		return true
+	}
+	if strings.HasPrefix(field, "-") && len(field) > 1 {
+		return true
+	}
+	return false
+}
+
+// EvaluateModelConditional checks if condition matches current model.
+// Condition supports wildcards: * matches any, ? matches single char.
+func EvaluateModelConditional(currentModel, condition string) bool {
+	// Handle comma-separated conditions (OR logic)
+	for _, c := range strings.Split(condition, ",") {
+		c = strings.TrimSpace(c)
+		if matchModelPattern(currentModel, c) {
+			return true
+		}
+	}
+	return false
+}
+
+// matchModelPattern matches a model against a pattern with wildcards.
+func matchModelPattern(model, pattern string) bool {
+	// Convert pattern to regexp
+	pattern = strings.ReplaceAll(pattern, "*", ".*")
+	pattern = strings.ReplaceAll(pattern, "?", ".")
+	pattern = "^" + pattern + "$"
+
+	re, err := regexp.Compile(pattern)
+	if err != nil {
+		// Fallback: exact match
+		return model == pattern
+	}
+	return re.MatchString(model)
+}
+
+// RenderWithModelConditionals processes <if-model> blocks in content.
+func RenderWithModelConditionals(content, currentModel string) string {
+	// Simple regex-based processor for <if-model> blocks
+	// Supports: <if-model is="pattern">content</if-model>
+	// And: <if-model is="pattern">content<else>other</if-model>
+
+	result := content
+
+	// Pattern for if-model blocks
+	ifModelRegex := regexp.MustCompile(`(?s)<if-model\s+is="([^"]+)">(.*?)(?:<else>(.*?))?</if-model>`)
+
+	for {
+		match := ifModelRegex.FindStringSubmatchIndex(result)
+		if match == nil {
+			break
+		}
+
+		condition := result[match[2]:match[3]]
+		ifContent := result[match[4]:match[5]]
+		elseContent := ""
+		if match[6] >= 0 && match[7] >= 0 {
+			elseContent = result[match[6]:match[7]]
+		}
+
+		var replacement string
+		if EvaluateModelConditional(currentModel, condition) {
+			replacement = ifContent
+		} else {
+			replacement = elseContent
+		}
+
+		result = result[:match[0]] + replacement + result[match[1]:]
+	}
+
+	return result
+}
+
+// ---------------------------------------------------------------------------
+// Model Resolution Bridge for Extensions (Phase 4)
+// ---------------------------------------------------------------------------
+
+// ResolveModelChain attempts each model in order until one is available.
+func ResolveModelChain(preferences []string) extensions.ModelResolutionResult {
+	result := extensions.ModelResolutionResult{
+		Attempted: make([]string, 0, len(preferences)),
+	}
+
+	registry := models.GetGlobalRegistry()
+
+	for _, pref := range preferences {
+		pref = strings.TrimSpace(pref)
+		result.Attempted = append(result.Attempted, pref)
+
+		// Parse model string
+		provider, modelID, err := models.ParseModelString(pref)
+		if err != nil {
+			continue
+		}
+
+		// Check if provider exists
+		if registry.GetProviderInfo(provider) == nil {
+			continue
+		}
+
+		// Check if model exists in registry
+		modelInfo := registry.LookupModel(provider, modelID)
+		if modelInfo == nil {
+			// Try with just the model as bare name
+			continue
+		}
+
+		// Found available model
+		result.Model = provider + "/" + modelID
+		result.Capabilities = extensions.ModelCapabilities{
+			Provider:     provider,
+			ModelID:      modelID,
+			ContextLimit: modelInfo.Limit.Context,
+			OutputLimit:  modelInfo.Limit.Output,
+			Reasoning:    modelInfo.Reasoning,
+			Streaming:    true, // Assume streaming support
+		}
+		return result
+	}
+
+	result.Error = "no models in chain are available"
+	return result
+}
+
+// GetModelCapabilities returns capabilities for a specific model.
+// If model is empty, returns zero capabilities.
+func GetModelCapabilities(model string) (extensions.ModelCapabilities, string) {
+	if model == "" {
+		return extensions.ModelCapabilities{}, "no model specified"
+	}
+
+	provider, modelID, err := models.ParseModelString(model)
+	if err != nil {
+		return extensions.ModelCapabilities{}, err.Error()
+	}
+
+	registry := models.GetGlobalRegistry()
+	modelInfo := registry.LookupModel(provider, modelID)
+	if modelInfo == nil {
+		return extensions.ModelCapabilities{}, "model not found in registry"
+	}
+
+	return extensions.ModelCapabilities{
+		Provider:     provider,
+		ModelID:      modelID,
+		ContextLimit: modelInfo.Limit.Context,
+		OutputLimit:  modelInfo.Limit.Output,
+		Reasoning:    modelInfo.Reasoning,
+		Streaming:    true,
+	}, ""
+}
+
+// CheckModelAvailable verifies if a model string is valid and provider exists.
+func CheckModelAvailable(model string) bool {
+	provider, _, err := models.ParseModelString(model)
+	if err != nil {
+		return false
+	}
+
+	registry := models.GetGlobalRegistry()
+	if registry.GetProviderInfo(provider) == nil {
+		return false
+	}
+
+	// Model doesn't need to be in registry - could be dynamic/Ollama
+	return true
+}
+
+// GetCurrentProvider extracts provider from model string.
+func GetCurrentProvider(model string) string {
+	provider, _, _ := models.ParseModelString(model)
+	return provider
+}
+
+// GetCurrentModelID extracts model ID from model string.
+func GetCurrentModelID(model string) string {
+	_, modelID, _ := models.ParseModelString(model)
+	return modelID
+}
+
+// JoinModel combines provider and model ID into a model string.
+func JoinModel(provider, modelID string) string {
+	if provider == "" {
+		return modelID
+	}
+	return provider + "/" + modelID
+}
+
+// MatchModelGlob matches a model against a glob pattern.
+// Pattern can contain * (match any) and ? (match single).
+func MatchModelGlob(model, pattern string) bool {
+	return matchModelPattern(model, pattern)
+}
+
+// ExtractProviderFromPath extracts provider from a path-like model string.
+func ExtractProviderFromPath(model string) string {
+	parts := strings.Split(model, "/")
+	if len(parts) >= 2 {
+		return parts[0]
+	}
+	return ""
+}
+
+// ExtractModelFromPath extracts model ID from a path-like model string.
+func ExtractModelFromPath(model string) string {
+	parts := strings.Split(model, "/")
+	if len(parts) >= 2 {
+		return parts[1]
+	}
+	return model
+}
+
+// IsBareModelID checks if a string is a bare model ID (no provider).
+func IsBareModelID(model string) bool {
+	return !strings.Contains(model, "/")
+}
+
+// AddProviderToModel adds a provider prefix to a bare model ID.
+func AddProviderToModel(provider, model string) string {
+	if strings.Contains(model, "/") {
+		return model // Already has provider
+	}
+	return provider + "/" + model
+}
+
+// RemoveProviderFromModel removes the provider prefix from a model string.
+func RemoveProviderFromModel(model string) string {
+	parts := strings.SplitN(model, "/", 2)
+	if len(parts) == 2 {
+		return parts[1]
+	}
+	return model
+}

skills/kit-extensions/SKILL.md

@@ -1210,6 +1210,129 @@ func applyMode(ctx ext.Context, active bool, tools []string) {
 }
 ```
 
+---
+
+## Bridged SDK APIs (New)
+
+Extensions can now access powerful internal SDK capabilities that enable advanced features like conversation tree navigation, dynamic skill loading, template parsing, and model resolution.
+
+### Tree Navigation
+
+Navigate the conversation tree, summarize branches, and implement "fresh context" loops:
+
+```go
+// Get a specific node by ID with full metadata and children
+node := ctx.GetTreeNode("entry-id")
+// node.ID, node.ParentID, node.Type ("message"/"branch_summary"/etc)
+// node.Role, node.Content, node.Model, node.Children ([]string)
+
+// Get the current branch from root to leaf
+branch := ctx.GetCurrentBranch()  // []ext.TreeNode
+
+// Get child entry IDs of a node
+children := ctx.GetChildren("entry-id")  // []string
+
+// Navigate/fork to a different entry in the tree
+result := ctx.NavigateTo("entry-id")  // ext.TreeNavigationResult{Success, Error}
+
+// Summarize a range of the branch using LLM
+summary := ctx.SummarizeBranch("from-id", "to-id")  // string
+
+// Collapse a branch range into a summary entry (fresh context primitive)
+result := ctx.CollapseBranch("from-id", "to-id", "summary text")
+```
+
+### Skill Loading
+
+Load and inject skills dynamically at runtime:
+
+```go
+// Discover skills from standard locations
+result := ctx.DiscoverSkills()  // ext.SkillLoadResult{Skills, Error}
+// Standard locations: ~/.config/kit/skills/, .kit/skills/, .agents/skills/
+
+// Load a specific skill file
+skill, err := ctx.LoadSkill("/path/to/skill.md")  // (*ext.Skill, error string)
+// skill.Name, skill.Description, skill.Content, skill.Tags, skill.When
+
+// Load all skills from a directory
+result := ctx.LoadSkillsFromDir("/path/to/skills")  // ext.SkillLoadResult
+
+// Inject a skill as context (pre-loads for next turn)
+err := ctx.InjectSkillAsContext("skill-name")  // error string
+
+// Inject a skill file directly
+err := ctx.InjectRawSkillAsContext("/path/to/skill.md")  // error string
+
+// Get all discovered skills
+skills := ctx.GetAvailableSkills()  // []ext.Skill
+```
+
+### Template Parsing
+
+Parse and render templates with variable substitution:
+
+```go
+// Parse a template to extract {{variables}}
+tpl := ctx.ParseTemplate("name", "Hello {{name}}, welcome to {{place}}!")
+// tpl.Name, tpl.Content, tpl.Variables ([]string)
+
+// Render a template with variable values
+vars := map[string]string{"name": "Alice", "place": "Kit"}
+rendered := ctx.RenderTemplate(tpl, vars)  // "Hello Alice, welcome to Kit!"
+
+// Parse command-line style arguments
+pattern := ext.ArgumentPattern{
+    Positional: []string{"command", "target"},  // $1, $2
+    Rest:       "args",                         // $@
+    Flags:      map[string]string{"--loop": "loop", "-f": "force"},
+}
+result := ctx.ParseArguments("deploy staging --loop 5", pattern)
+// result.Vars["command"] = "deploy"
+// result.Vars["target"] = "staging"
+// result.Flags["--loop"] = "5"
+
+// Simple positional argument parsing ($1, $2, $@)
+args := ctx.SimpleParseArguments("deploy staging --force", 2)
+// args[0] = "deploy staging --force" (full input)
+// args[1] = "deploy" ($1)
+// args[2] = "staging" ($2)
+// args[3] = "--force" ($@)
+
+// Evaluate model conditionals with wildcards
+matches := ctx.EvaluateModelConditional("claude-*")  // bool
+// Patterns: * matches any, ? matches single char, comma = OR
+
+// Render content with <if-model> conditionals
+content := `<if-model is="claude-*">Hi Claude<else>Hi there</if-model>`
+rendered := ctx.RenderWithModelConditionals(content)  // based on current model
+```
+
+### Model Resolution
+
+Resolve model fallback chains and query capabilities:
+
+```go
+// Resolve a chain of model preferences (tries each until available)
+result := ctx.ResolveModelChain([]string{
+    "anthropic/claude-opus-4",
+    "anthropic/claude-sonnet-4",
+    "openai/gpt-4o",
+})
+// result.Model (selected), result.Capabilities, result.Attempted, result.Error
+
+// Get capabilities for a specific model
+caps, err := ctx.GetModelCapabilities("anthropic/claude-sonnet-4")
+// caps.Provider, caps.ModelID, caps.ContextLimit, caps.Reasoning, caps.Streaming
+
+// Check if a model is available (provider exists)
+available := ctx.CheckModelAvailable("anthropic/claude-sonnet-4")  // bool
+
+// Get current provider/model ID
+provider := ctx.GetCurrentProvider()  // "anthropic"
+modelID := ctx.GetCurrentModelID()    // "claude-sonnet-4"
+```
+
 ## Key Files for Reference
 
 - [`internal/extensions/api.go`](https://github.com/mark3labs/kit/blob/main/internal/extensions/api.go) — Complete API type definitions

www/pages/extensions/capabilities.md

@@ -334,3 +334,124 @@ api.OnCustomEvent("my-extension:data-ready", func(data any, ctx ext.Context) {
     // handle event
 })
 ```
+
+## Bridged SDK APIs
+
+Extensions can access powerful internal SDK capabilities that enable advanced features like conversation tree navigation, dynamic skill loading, template parsing, and model resolution.
+
+### Tree Navigation
+
+Navigate the conversation tree, summarize branches, and implement "fresh context" loops:
+
+```go
+// Get a specific node by ID with full metadata and children
+node := ctx.GetTreeNode("entry-id")
+// node.ID, node.ParentID, node.Type ("message"/"branch_summary"/etc)
+// node.Role, node.Content, node.Model, node.Children ([]string)
+
+// Get the current branch from root to leaf
+branch := ctx.GetCurrentBranch()  // []ext.TreeNode
+
+// Get child entry IDs of a node
+children := ctx.GetChildren("entry-id")  // []string
+
+// Navigate/fork to a different entry in the tree
+result := ctx.NavigateTo("entry-id")  // ext.TreeNavigationResult{Success, Error}
+
+// Summarize a range of the branch using LLM
+summary := ctx.SummarizeBranch("from-id", "to-id")  // string
+
+// Collapse a branch range into a summary entry (fresh context primitive)
+result := ctx.CollapseBranch("from-id", "to-id", "summary text")
+```
+
+### Skill Loading
+
+Load and inject skills dynamically at runtime:
+
+```go
+// Discover skills from standard locations
+result := ctx.DiscoverSkills()  // ext.SkillLoadResult{Skills, Error}
+// Standard locations: ~/.config/kit/skills/, .kit/skills/, .agents/skills/
+
+// Load a specific skill file
+skill, err := ctx.LoadSkill("/path/to/skill.md")  // (*ext.Skill, error string)
+// skill.Name, skill.Description, skill.Content, skill.Tags, skill.When
+
+// Load all skills from a directory
+result := ctx.LoadSkillsFromDir("/path/to/skills")  // ext.SkillLoadResult
+
+// Inject a skill as context (pre-loads for next turn)
+err := ctx.InjectSkillAsContext("skill-name")  // error string
+
+// Inject a skill file directly
+err := ctx.InjectRawSkillAsContext("/path/to/skill.md")  // error string
+
+// Get all discovered skills
+skills := ctx.GetAvailableSkills()  // []ext.Skill
+```
+
+### Template Parsing
+
+Parse and render templates with variable substitution:
+
+```go
+// Parse a template to extract {{variables}}
+tpl := ctx.ParseTemplate("name", "Hello {{name}}, welcome to {{place}}!")
+// tpl.Name, tpl.Content, tpl.Variables ([]string)
+
+// Render a template with variable values
+vars := map[string]string{"name": "Alice", "place": "Kit"}
+rendered := ctx.RenderTemplate(tpl, vars)  // "Hello Alice, welcome to Kit!"
+
+// Parse command-line style arguments
+pattern := ext.ArgumentPattern{
+    Positional: []string{"command", "target"},  // $1, $2
+    Rest:       "args",                         // $@
+    Flags:      map[string]string{"--loop": "loop", "-f": "force"},
+}
+result := ctx.ParseArguments("deploy staging --loop 5", pattern)
+// result.Vars["command"] = "deploy"
+// result.Vars["target"] = "staging"
+// result.Flags["--loop"] = "5"
+
+// Simple positional argument parsing ($1, $2, $@)
+args := ctx.SimpleParseArguments("deploy staging --force", 2)
+// args[0] = "deploy staging --force" (full input)
+// args[1] = "deploy" ($1)
+// args[2] = "staging" ($2)
+// args[3] = "--force" ($@)
+
+// Evaluate model conditionals with wildcards
+matches := ctx.EvaluateModelConditional("claude-*")  // bool
+// Patterns: * matches any, ? matches single char, comma = OR
+
+// Render content with <if-model> conditionals
+content := `<if-model is="claude-*">Hi Claude<else>Hi there</if-model>`
+rendered := ctx.RenderWithModelConditionals(content)  // based on current model
+```
+
+### Model Resolution
+
+Resolve model fallback chains and query capabilities:
+
+```go
+// Resolve a chain of model preferences (tries each until available)
+result := ctx.ResolveModelChain([]string{
+    "anthropic/claude-opus-4",
+    "anthropic/claude-sonnet-4",
+    "openai/gpt-4o",
+})
+// result.Model (selected), result.Capabilities, result.Attempted, result.Error
+
+// Get capabilities for a specific model
+caps, err := ctx.GetModelCapabilities("anthropic/claude-sonnet-4")
+// caps.Provider, caps.ModelID, caps.ContextLimit, caps.Reasoning, caps.Streaming
+
+// Check if a model is available (provider exists)
+available := ctx.CheckModelAvailable("anthropic/claude-sonnet-4")  // bool
+
+// Get current provider/model ID
+provider := ctx.GetCurrentProvider()  // "anthropic"
+modelID := ctx.GetCurrentModelID()    // "claude-sonnet-4"
+```

www/pages/extensions/examples.md

@@ -51,6 +51,15 @@ Kit ships with a rich set of example extensions in the `examples/extensions/` di
 | [`summarize.go`](https://github.com/mark3labs/kit/blob/master/examples/extensions/summarize.go) | Conversation summarization |
 | [`lsp-diagnostics.go`](https://github.com/mark3labs/kit/blob/master/examples/extensions/lsp-diagnostics.go) | LSP diagnostic integration |
 
+## Bridged SDK APIs
+
+These examples demonstrate the new bridged SDK APIs that give extensions access to internal Kit capabilities:
+
+| Extension | Description |
+|-----------|-------------|
+| [`conversation-manager.go`](https://github.com/mark3labs/kit/blob/master/examples/extensions/conversation-manager.go) | **NEW** Tree navigation (`GetTreeNode`, `GetCurrentBranch`, `NavigateTo`), branch summarization (`SummarizeBranch`), and fresh context loops (`CollapseBranch`) |
+| [`prompt-templates.go`](https://github.com/mark3labs/kit/blob/master/examples/extensions/prompt-templates.go) | **NEW** Frontmatter-driven templates with model fallback chains (`ResolveModelChain`), skill injection (`InjectSkillAsContext`), and template parsing (`ParseTemplate`, `RenderTemplate`) |
+
 ## Themes
 
 | Extension | Description |