Replace concrete LLMMessage/LLMUsage/LLMResponse/LLMFilePart structs with
type aliases to charm.land/fantasy types, exposing them under clean
LLM-prefixed names. This gives SDK consumers full access to rich message
parts (tool calls, reasoning, tool results) without importing fantasy
directly.
Key changes:
- LLM types are now aliases: LLMMessage=fantasy.Message, etc.
- Added aliases for all part types: LLMTextPart, LLMToolCallPart, etc.
- Re-exported constructors: NewLLMUserMessage, NewLLMSystemMessage
- Removed lossy conversion helpers (llm_convert.go, fantasyMsgsToKit)
- Updated all internal packages to use aliases consistently
- Added ACP smoke test script and prompt template
- Fixed lint issues: unused vars, modernize min() usage
The compact display mode was purely a UI concern that added complexity
without providing unique value. Anyone wanting compact-style formatting
can implement it as an extension using the Renderer interface.
- Delete internal/ui/compact_renderer.go
- Remove renderToolBodyCompact and all compact tool body renderers from
tool_renderers.go
- Simplify NewCLI(debug bool) — drop compact parameter
- Simplify NewStreamComponent(width, modelName) — drop compactMode parameter
- Remove CompactMode from AppModelOptions, app.Options, CLISetupOptions
- Remove Compact from internal/config/config.go
- Remove --compact flag, var, and viper binding from cmd/root.go
- Update format.go: remove CompactRenderer interface compile-time check
and clean up comments
- Implement proper handling for all ACP content block types:
- ContentBlockText: extracts text content
- ContentBlockImage: decodes base64 to LLMFilePart
- ContentBlockAudio: decodes base64 to LLMFilePart
- ContentBlockResource: handles text and binary embedded resources
- ContentBlockResourceLink: reads files from disk
- Text files are now included inline in the message (not as FilePart)
to avoid OpenAI API errors. Only binary files (images, audio, PDFs)
are sent as FilePart attachments.
- Add fallback MIME types when not provided by client
- Add default prompt text when user attaches files without text
- Add comprehensive debug logging for content extraction
- Enable debug logging in ACP command when --debug flag is used
- Display kitBanner() before PrintStartupInfo() when running Kit normally
- The ASCII art banner with KITT scanner lights now appears at the top
of the screen, before Model, Context, Skills information
- Maintains consistent styling with the existing usage/help screen
Two related fixes for --provider-url handling:
1. Don't restore custom/* models from preferences without --provider-url
- When user runs with --provider-url, model defaults to custom/custom
- If they switch models, custom/custom gets persisted to preferences
- On next run without --provider-url, restoring custom/custom fails
- Now we skip restoring custom/* models when no --provider-url is provided
2. Auto-prefix bare model names with custom/ when --provider-url is set
- Users often provide just the model name (e.g., qwen3.5-35b-a3b)
- This failed with 'invalid model format' error
- Now auto-prefixed with custom/ for OpenAI-compatible endpoints
- Fix gofmt formatting issues in 7 files
- Replace atomic.AddUint64 with atomic.Uint64 type (modernize)
- Replace for i := 0; i < count; i++ with for i := range count (modernize)
- Replace strings.Split with strings.SplitSeq (modernize)
- Replace deprecated GetFantasyProviders with GetLLMProviders
- Replace deprecated GetFantasyMessages with GetLLMMessages
- Replace deprecated ConvertFromFantasyMessage with ConvertFromLLMMessage
- Replace deprecated FromFantasyMessage with FromLLMMessage
- Replace deprecated ToFantasyMessages with ToLLMMessages
- Remove 2 unused formatToolArgs functions
- Create ExtensionAPI interface with all extension-related methods
- Add extensionAPI type that wraps *Kit and implements the interface
- Add Kit.Extensions() method to access the ExtensionAPI
- Remove ~30 Extension* methods from Kit (breaking SDK change)
- Update all internal callers (cmd/, internal/acpserver/) to use Extensions().Method()
- Extensions themselves unaffected (use kit/ext API via Yaegi)
This cleans up the Kit API surface while maintaining full extension functionality.
Replace var function aliases with proper func wrappers (types.go)
- ParseModelString, CreateProvider, GetGlobalRegistry, LoadSystemPrompt
were package-level vars, making them reassignable and rendering oddly
in go doc. Now plain func wrappers with matching signatures.
Fix Subagent() double-error return convention
- Was returning both (*SubagentResult{Error: err}, err) simultaneously.
Now returns (nil, err) on failure, consistent with Go conventions.
- Removed SubagentResult.Error field; errors come from the error return.
- Updated all call sites in cmd/root.go, internal/acpserver, and kit.go.
Fix NavigateTo/SummarizeBranch/CollapseBranch string-encoded errors
- All three returned "" or an error string instead of error values,
making it impossible to distinguish success from failure in SummarizeBranch
(empty string meant both "no content" and "LLM failed").
- NavigateTo: string -> error
- SummarizeBranch: string -> (string, error)
- CollapseBranch: string -> error
- Updated cmd/root.go bridge closures to use err != nil and err.Error().
Remove duplicate GetSessionFilePath (use GetSessionPath)
- GetSessionPath (sessions.go) and GetSessionFilePath (kit.go) were
identical. Removed GetSessionFilePath; updated cmd/root.go and
internal/acpserver to call GetSessionPath directly.
## Dead code removal
- Delete slash_command_input.go (352 lines, never instantiated)
- Remove FormatCompactLine, StyleCompactSymbol/Label/Content from
enhanced_styles.go (zero call sites)
- Remove getTheme() alias in messages.go; standardize on GetTheme()
across compact_renderer.go (8 sites) and tool_renderers.go (14 sites)
## BubbleTea correctness
- Fix child model discards: all m.stream.Update() and m.input.Update()
calls now store the returned model via type-assertion (13 sites)
- Fix Init(): remove vestigial nil guards; StreamComponent.Init() always
returns nil so only m.input.Init() is needed
- Fix /clear divergence: remove silent InputComponent /clear handler so
parent AppModel handles it with the proper system message (one path)
## Architecture / maintainability
- Unify slash-command dispatch from two-pass (exact + prefix) to single
parse: strings.Cut once, GetCommandByName on name, pass args to
handleSlashCommand(sc, args); eliminates 3 separate dispatch sites
- Add noopCmd package-level var replacing three inline func()tea.Msg{nil}
sentinel returns
- Remove stale TAS-15/16/17 comments from interface declarations
- Deduplicate headerProviderForUI / footerProviderForUI in cmd/root.go
into a shared headerFooterProviderForUI helper (removes ~28 duplicated lines)
## Performance
- Cache glamour.TermRenderer keyed by width in styles.go; invalidate on
theme change — eliminates full goldmark parser re-init every flush tick
- Add styleMarginBottom1 package-level var replacing 9 per-frame
lipgloss.NewStyle().MarginBottom(1) allocations
- Add layoutDirty flag: replace 9 distributeHeight() calls in Update()
with m.layoutDirty=true; flush once in View() — guarantees exactly one
layout measurement per frame instead of N (reduces double-render)
- Add WidgetUpdateEvent coalescing in app.NotifyWidgetUpdate() via
atomic.Bool + 16ms debounce; prevents fast extension tickers from
flooding BubbleTea's message queue with redundant re-render triggers
## Concurrency safety
- Convert all NotifyWidgetUpdate() call sites in cmd/root.go to
go appInstance.NotifyWidgetUpdate() (16 sites) — eliminates deadlock
risk when called synchronously from inside BubbleTea's Update() handler
- Add bottom margin to startup header (KVGroup)
- Add bottom margin to thinking/reasoning blocks
- Fix thinking block footer to appear on new line without extra spacing
- Update spawn_subagent tool output to use bash-style formatting
- Add blank line after extension startup messages for visual separation
- Replace MessageRenderer with herald-based implementation
- Use herald alerts (Note, Tip, Warning, Caution) for message types
- Use blockquote for thinking/reasoning content
- Use KVGroup for startup info display
- Add margin-bottom to all message types for visual separation
- Simplify Read tool with herald CodeBlock and line numbers
- Add detectLanguage helper for syntax highlighting
- Capture extension startup messages and print after startup banner
- Remove ~200 lines of custom rendering code
Implements OAuth authentication for OpenAI ChatGPT Plus/Pro (Codex) similar to pi:
- Add OpenAICredentials type with OAuth and API key support
- Add OpenAI OAuth client with correct endpoints (auth.openai.com)
- Implement PKCE-based OAuth flow with local callback server on :1455
- Add login/logout/status commands for openai provider
- Support both ChatGPT/Codex OAuth tokens (chatgpt.com/backend-api) and
regular OpenAI API keys (api.openai.com)
- Extract and store ChatGPT account ID from JWT token
- Add custom HTTP transport with required Codex headers:
- chatgpt-account-id, originator, OpenAI-Beta: responses=experimental
- Update provider selection to use correct endpoint based on auth type
Usage:
kit auth login openai # OAuth with ChatGPT account
kit auth logout openai
kit auth status
The implementation follows the same patterns as the existing Anthropic OAuth
support, with automatic token refresh and secure credential storage in
~/.config/.kit/credentials.json
When switching models (e.g., via /model command or ctx.SetModel), the usage
tracker now updates its model info to reflect the new model's:
- Pricing for cost calculations
- Context limits for percentage display
- OAuth status (to show bash costs when using OAuth creds)
Previously, token costs and context percentages continued using the old
model's settings after a switch, causing incorrect display for:
- Users switching from paid to free/OAuth models
- Users switching between models with different pricing
Changes:
- Add UpdateModelInfo() method to UsageTracker
- Call UpdateModelInfo() in both SetModel callbacks (extension and UI)
- Add auth import for OAuth detection in root.go
Allow users to define custom models in ~/.kit.yml under the customModels
section. These models are automatically merged into the custom provider.
Example config:
customModels:
my-model:
name: "My Custom Model"
reasoning: true
temperature: true
cost:
input: 0.002
output: 0.004
limit:
context: 128000
output: 32000
Usage:
kit --model custom/my-model "Hello"
kit --provider-url "http://localhost:8080" --model custom/my-model "Hello"
Note: When --provider-url is specified without --model, kit defaults to
custom/custom. When --provider-url is specified WITH a custom model from
config, that model is used.
Bug fixes:
- Fixed kit.New() re-loading config file and overriding CLI-specified config
- Fixed models command to reload registry for custom models
When users pass --provider-url without --model, automatically default
to custom/custom instead of the saved model preference. This lets users
point kit at any OpenAI-compatible endpoint without needing a provider/model
pair from the database.
The custom/custom model has:
- Zero cost (input/output = 0)
- 262K context window, 65K output limit
- Reasoning and temperature support
- Routes through openaicompat fantasy provider
The skill command now runs 'npx skills add mark3labs/kit' without
filtering to a single skill, installing both available skills:
1. Extensions - creating Kit extensions
2. SDK - building with the Kit Go SDK
Add user-defined prompt templates that expand into full prompts with
shell-style argument substitution.
Features:
- Templates loaded from ~/.kit/prompts/*.md and .kit/prompts/*.md
- YAML frontmatter support for description
- Argument placeholders: $1, $2, $@, $ARGUMENTS, ${@:N}, ${@:N:L}
- Autocomplete integration (templates appear as /name commands)
- CLI flags: --prompt-template and --no-prompt-templates
- First-match-wins collision handling with logged diagnostics
Example template:
---
description: Review code for issues
---
Review the following code for bugs and security issues.
Focus on $1 specifically.
Usage: /review error handling
Model and thinking level choices now survive restarts, matching the
existing theme persistence pattern. Selections are saved to
~/.config/kit/preferences.yml and restored on next launch.
Precedence: CLI flag > config file > saved preference > default
Changes:
- Extended preferences struct with model and thinking_level fields
- Refactored preferences.go to shared load/save helpers (DRY)
- Added SaveModelPreference/LoadModelPreference
- Added SaveThinkingLevelPreference/LoadThinkingLevelPreference
- Persist on /model, model selector, /thinking, and Shift+Tab cycle
- Restore at startup in runNormalMode when no explicit flag/config
- Added modelFlagChanged/thinkingFlagChanged to detect explicit flags
- Comprehensive tests for all preference operations
Theme choices via /theme or ctx.SetTheme() were previously lost on
restart. Now the selected theme name is saved to
~/.config/kit/preferences.yml and restored on next launch.
Precedence: .kit.yml theme > preferences.yml > default (kitt).
- Add internal/ui/preferences.go with atomic save/load
- ApplyTheme() now persists; ApplyThemeWithoutSave() for startup
- Fallback to saved preference in cmd/root.go init()
Add RegisterTheme, SetTheme, and ListThemes to the extension Context,
allowing extensions to create custom themes at runtime and switch
between them. Uses ThemeColor/ThemeColorConfig concrete structs (no
interfaces) for Yaegi safety.
Include neon-theme.go example extension demonstrating the API.
Replace the Catppuccin color palette with a Knight Rider KITT-inspired
theme — scanner reds, amber dashboard glows, and dark cockpit tones.
No blues or bright greens; the entire palette stays in the warm
red/amber/gray family.
Unify the theme system by folding the standalone MarkdownTheme config
into the main Theme struct, eliminating the separate config path.
Replace all hardcoded lipgloss.Color() calls across input, overlay,
and CLI components with semantic theme references so every color
responds to theme customization.
- Replace custom multi-select with huh.NewMultiSelect for kit install --select
- Replace raw bufio prompts in cmd/auth.go with huh.NewConfirm and huh.NewInput
- Fix extension discovery to use opinionated conventions (only scan root,
extensions/, ext/, examples/extensions/ directories, skip cmd/internal/pkg/)
- Fix loader to use same convention-based scanning for installed git repos
- Fix errcheck lint warning in loader.go
Add SubagentEvent type to extension API and OnEvent field to
SubagentConfig so extensions can watch subagent tool calls, text
chunks, reasoning deltas, and turn lifecycle events in real time.
The SDK's Kit.Subagent() already had OnEvent via kit.SubagentConfig.
This wires it through to the extension layer with a concrete
SubagentEvent struct (Yaegi-safe) and bridges SDK events to it
in both cmd/root.go and the ACP server.
Subagents now run as child Kit instances in the same process instead of
spawning a kit binary subprocess. This removes the binary dependency,
eliminates JSON serialization overhead, and enables SDK-only consumers
to use subagents without installing the kit CLI.
- Add Kit.Subagent() method for in-process subagent execution
- Add SubagentConfig/SubagentResult types to the SDK
- Add context-based SubagentSpawnFunc injection so core spawn_subagent
tool calls back to Kit.Subagent() without an import cycle
- Add SubagentTools() bundle (all core tools minus spawn_subagent)
- Add viperInitMu for thread-safe concurrent kit.New() calls
- Wire extension ctx.SpawnSubagent and ACP server to use in-process
- Child Kit gets parent's model as fallback, in-memory or persisted
session, and no extensions (preventing recursive loading)
Thread ToolCallID, ToolKind, ParsedArgs, FileDiff metadata, StopReason,
SessionID, and StructuredMessages across the SDK event bus, extension
wrapper, app bridge, hooks, and ACP server layers.
- Gap 1: ToolCallID from Fantasy's ToolCallContent threaded end-to-end
- Gap 2: ToolKind via static lookup (execute/edit/read/search/agent)
- Gap 3+4: FileDiffInfo with DiffBlocks via fantasy.ToolResponse.Metadata
- Gap 5: StopReason from Fantasy FinishReason on TurnEndEvent/TurnResult
- Gap 6: Subagent sessions now opt-out (NoSession); SessionID in JSON output
- Gap 7: GetStructuredMessages() returns typed ContentParts
- Gap 8: ParsedArgs map[string]any on tool events for convenience
Edit/write tools attach structured diff metadata. ACP server uses real
ToolCallIDs. Extension and SDK events kept in sync with matching fields.
Implement 4-phase subagent system enabling LLM and extensions to spawn,
manage, and orchestrate child Kit instances for parallel task execution.
- Phase 1: SDK API with SpawnSubagent() for extensions
- Phase 2: spawn_subagent core tool for LLM usage
- Phase 3: Session hierarchy with ParentSessionID tracking
- Phase 4: Provider pooling for concurrent model access
New files:
- internal/extensions/subagent.go: SpawnSubagent implementation
- internal/core/subagent.go: Core tool definition
- internal/models/pool.go: Provider pool for concurrency
- examples/extensions/subagent-test.go: Test extension
- openspec/subagent-support.md: Design specification
Add extended thinking/reasoning support for Anthropic and OpenAI models:
- ThinkingLevel type (off/minimal/low/medium/high) with token budgets
- Stream reasoning deltas via OnReasoningDelta through SDK→TUI event pipeline
- Render thinking blocks in StreamComponent (muted italic, collapsible)
- ctrl+t toggles thinking visibility, shift+tab cycles thinking level
- /thinking slash command with tab-completion for level names
- --thinking-level CLI flag and config file support
- Map ThinkingLevel to OpenAI ReasoningEffort for Responses API
- Auto-bump Anthropic max_tokens when thinking budget exceeds it
- Fix ResponseCompleteEvent prematurely resetting stream in streaming mode
- Status bar displays current thinking level
Add /model command that allows switching LLM models mid-session.
When invoked without arguments, opens a full-screen selector overlay
showing only models with configured API keys, with inline fuzzy search,
cursor navigation, and current model indicator. When invoked with an
argument (e.g. /model anthropic/claude-haiku-4-5), switches directly.
Also upgrades all Go dependencies to latest versions.
Drop the --prompt/-p flag entirely. Non-interactive mode is now
triggered by passing positional arguments:
kit "Explain this"
kit @file.go "Review this" --json
kit @a.go @b.go --quiet
Updated extension examples (kit-kit.go, subagent-widget.go) to pass
the prompt as a positional arg. Updated AGENTS.md and README.md.
Positional args are now the main way to run non-interactive mode:
kit "Explain this codebase"
kit @code.ts @test.ts "Review these files"
kit @go.mod "What module?" --quiet
--prompt is hidden but still works for subprocess compat (extensions
spawn kit with --prompt internally). Updated --quiet/--json/--no-exit
error messages to reference the new positional arg pattern.
Enables: kit @code.ts @test.ts "Review these files"
Positional args starting with @ are treated as file attachments —
their content is read and prepended to the prompt. Remaining
positional args are joined as the prompt text. Works alongside
--prompt flag (files prepended, extra text appended).
Type @ in the input to trigger a fuzzy file picker popup. Files are
discovered via git ls-files (with os.ReadDir fallback), scored by
fuzzy match, and displayed in the existing autocomplete popup.
Tab/Enter inserts the selected path; directories keep the popup open
for drilling. On submit, @file tokens are expanded into XML-wrapped
file content before being sent to the agent. No CWD restriction —
supports ~/, ../, and absolute paths.
- ctx.SuspendTUI(callback): releases terminal for interactive subprocesses
(vim, shell, htop), automatically restores TUI when callback returns.
Uses BubbleTea v2 ReleaseTerminal/RestoreTerminal.
- api.RegisterMessageRenderer(config) + ctx.RenderMessage(name, content):
named render functions for branded/styled extension output. Renderers
receive content and terminal width, return ANSI-styled strings.
- ctx.ReloadExtensions(): hot-reloads all extensions from disk. Emits
SessionShutdown to old extensions, reloads source, emits SessionStart
to new. Event handlers, commands, renderers, shortcuts update immediately.
TUI command list refreshes via WidgetUpdateEvent. Extension tools are
NOT updated (baked into agent at creation, documented limitation).
New example extensions: interactive-shell.go, branded-output.go, dev-reload.go
- RegisterShortcut(ShortcutDef, handler) for global keyboard shortcuts
that fire across all non-modal app states (after ctrl+c, before
component dispatch). Handlers run in goroutines for safe blocking calls.
- ToolContext with IsCancelled/OnProgress for rich tool execution;
ExecuteWithContext on ToolDef takes priority over simple Execute.
- Source field on ToolCallEvent (currently "llm", forward-compatible
with future user-initiated tool calls).
- Fix missing //go:build ignore on context-inject.go.
- Update plan-mode.go to register ctrl+alt+p shortcut.
Add three new extension events that allow extensions to gate destructive
session operations and compaction:
- OnBeforeFork: fires before branching in the tree selector; handler can
cancel with reason (e.g. dirty-repo guard)
- OnBeforeSessionSwitch: fires before /new resets the session branch;
handler can cancel with reason
- OnBeforeCompact: fires before context compaction (auto or manual);
handler receives token stats and IsAutomatic flag, can cancel
Includes SDK hook registry (beforeCompact), extension bridge, UI
callbacks threaded through AppModelOptions, and two example extensions:
- confirm-destructive.go: git dirty check + fork confirmation
- compact-notify.go: compaction notification + auto-compact gating
Extensions can now provide a Complete function on CommandDef that supplies
argument suggestions. When the user types a command name followed by a space,
the input popup switches to argument-completion mode, calling Complete with
the partial text and displaying matching suggestions.
Implement Phase 1 extension API gaps identified in the pi-mono gap analysis:
- Gap 1: Session Management API (GetMessages, GetSessionPath) — read-only
access to conversation history from extensions
- Gap 2: Session Persistence (AppendEntry, GetEntries) — custom extension
data survives across session restarts via new ExtensionDataEntry type
- Gap 10: SetEditorText — extensions can pre-fill the input editor
- Gap M3: Keyed Status Bar (SetStatus, RemoveStatus) — multiple extensions
can place independent entries in the TUI status bar, ordered by priority
Add a --json flag that outputs structured JSON (response, model, usage,
messages with typed parts) when used with --prompt. Update kit-kit and
subagent-widget extensions to use --json for cleaner subprocess output
parsing instead of raw text heuristics.
Ed Zynda