* Remove dead code: 5 unused symbols across internal packages
- internal/models: LoadModelSettingsFromConfig (zero refs)
- internal/prompts: PromptTemplate.ExpandWithArgs (zero refs)
- internal/app: NewMessageStore (tests migrated to NewMessageStoreWithMessages)
- internal/config: HasEnvVars (+ its test)
- internal/core: ContextWithSudoPassword (test migrated to context.WithValue)
* pkg/kit: use TreeManager alias in exported signatures
NewTreeManagerAdapter and InitTreeSession now spell their signatures with
the public kit.TreeManager alias instead of internal/session.TreeManager,
so go doc renders domain types rather than internal paths.
* Consolidate tool-kind classification into internal/extensions
coreToolKinds + toolKindFor were duplicated verbatim in
internal/extensions/wrapper.go and pkg/kit/events.go, risking silent
divergence between extension events and SDK events. Single source of
truth now lives in internal/extensions/toolkinds.go; pkg/kit re-exports
the constants.
* Consolidate Anthropic OAuth detection and usage-tracker refresh
The 'is the active Anthropic credential a stored OAuth token' check was
copy-pasted at 5 sites, all prefix-matching the magic string
'stored OAuth' produced in internal/auth. Now:
- internal/auth: new CredentialSourceOAuth constant + IsAnthropicOAuth()
- internal/ui: new UpdateUsageTrackerForModel(); CreateUsageTracker and
SetupCLI share lookupTrackableModel (SetupCLI no longer re-inlines the
tracker construction)
- cmd/root.go + cmd/extension_context.go: verbatim-duplicated tracker
refresh blocks replaced with ui.UpdateUsageTrackerForModel
- pkg/kit isAnthropicOAuth delegates to auth.IsAnthropicOAuth
- internal/models compares source against the constant
* pkg/kit: consolidate model-path helpers and argument tokenizer
- ExtractModelFromPath mis-parsed model IDs containing '/' (e.g.
'openrouter/meta/llama' -> 'meta'); it now delegates to
RemoveProviderFromModel and is deprecated alongside
ExtractProviderFromPath (-> GetCurrentProvider)
- parseFields delegated to prompts.ParseCommandArgs so extension argument
parsing and builtin prompt-template parsing share one quote/escape
grammar; ParseCommandArgs now also splits on tabs (superset of both
previous tokenizers)
* Unify the two {{variable}} template engines
internal/skills and pkg/kit/template_bridge each had their own grammar:
skills rejected '{{ name }}' (whitespace) but allowed digit-first names;
the bridge was the opposite. A template behaved differently depending on
whether it was loaded as a skill prompt or via the extension API.
internal/skills is now the single engine using the superset grammar
(\{\{\s*(\w+)\s*\}\}); pkg/kit ParseTemplate/RenderTemplate are thin
adapters over it. Expand is now regex-based so whitespace placeholders
expand consistently; missing variables are still left as-is.
* internal/ui: extract switchModel helper for model-switch flow
The model-selector handler (ModelSelectedMsg) and /model slash command
duplicated the full switch sequence (thinking-level fallback, setModel,
display-state update, preference persistence, ModelChange emit) and had
already drifted in ordering. Both now call a single switchModel method.
Display state is still updated directly (no prog.Send from Update).
* extbridge: extract shared BaseContext for extension wiring
cmd/extension_context.go and internal/acpserver/session.go each built a
giant extensions.Context literal, duplicating ~15 delegation closures
(GetContextStats, GetMessages, AppendEntry, options, SetModel core,
Complete, SpawnSubagent, ...) that had to be kept in sync by hand. New
data-access fields had to be wired in both places or ACP-mode extensions
silently got nil function fields.
extbridge.BaseContext now provides the headless half; both call sites
overlay only their UI-specific closures. As a side effect ACP mode gains
previously-missing APIs (state, tree navigation, skills, template
parsing, model resolution) that were nil before. The interactive TUI
keeps its exact SetModel/ReloadExtensions ordering via overrides.
* internal/tools: extract withOAuthRetry and marshalToolResult helpers
ExecuteTool repeated the OAuth-error/re-auth/retry stanza verbatim twice
(sync and task-augmented paths) and the marshal-and-wrap stanza four
times. Both are now single helpers with identical error strings, so a
fix to OAuth retry or error categorization applies everywhere at once.
* internal/ui: extract buildShareFile with defer-based cleanup
handleShareCommand repeated the close/remove/print/return cleanup chain
four times across its temp-file write error paths. File assembly now
lives in buildShareFile with a single deferred cleanup on error.
* cmd: extract flag validation, preference restore, and provider-URL routing from runNormalMode
runNormalMode opened with ~150 lines of policy logic (flag-combination
validation, persisted model/thinking-level preference restoration, and
two subtle --provider-url model-rewrite rules). These are now standalone
functions (validateModeFlags, restorePersistedPreferences,
applyProviderURLRouting) so the routing policy is independently readable
and testable. Behaviour unchanged; ordering preserved.
* fix: address review findings on SDK godoc and nil guard
- pkg/kit: remove internal package paths from exported godoc on
ParseTemplate and the ToolKind* constants (SDK doc surface must not
reference internal packages)
- internal/tools: guard marshalToolResult against a nil CallToolResult
(json.Marshal(nil) succeeds as 'null', then result.IsError panics if
a client returns nil result with nil error)
Skipped the TreeNode Children deep-copy suggestion: the slice already
comes from TreeManager.GetChildren which returns a fresh copy per call
into a throwaway intermediate, so no internal state is exposed.
- Remove unused SetOpenAICredentials/validateOpenAIAPIKey (internal/auth)
- Remove unused SudoPasswordRequiredMetadata/IsSudoPasswordRequiredResult
(internal/core)
- Add Extension* type aliases in pkg/kit/extension_api.go so the public
ExtensionAPI interface no longer exposes internal/extensions types
- Extract bridgeObserve generic helper and llmToContextMessages /
contextMessagesToLLM in pkg/kit/extensions_bridge.go (~150 lines saved)
- Extract parseHeaders and buildOAuthConfig in connection_pool.go to
deduplicate SSE/Streamable client construction (~60 lines saved)
- Eliminate redundant second buildInteractiveExtensionContext call in
cmd/root.go; swap print closures on the same context instead
- Replace 'Fantasy' with 'agent' in internal comment (pkg/kit/kit.go)
Implement Phase 1 of the MCP Tasks spec so long-running tools/call
requests can run asynchronously, survive proxy timeouts, and be
cancelled mid-flight.
- connection pool now advertises mcp.NewTasksCapability() during
initialize and captures the InitializeResult so callers can detect
per-server task support
- new MCPServerConfig.TasksMode (auto|never|always, default auto)
parsed from both new and legacy mcp.json shapes
- ExecuteTool augments tools/call with TaskParams when policy and
capability allow, polls tasks/get / tasks/result until terminal,
and best-effort tasks/cancel on context cancellation
- new MCPToolManager methods: SetTaskConfig, ListServerTasks,
GetServerTask, CancelServerTask
- public SDK surface in pkg/kit: MCPTask, MCPTaskStatus, MCPTaskMode,
MCPTaskProgress, MCPTaskProgressHandler, plus Options fields
(MCPTaskMode, MCPTaskTimeout, MCPTaskTTL, MCPTaskPollInterval,
MCPTaskMaxPollInterval, MCPTaskProgress) and Kit.{List,Get,Cancel}
MCPTask methods
- works around two upstream mcp-go v0.51.0 parser bugs
(ParseCallToolResult rejects task responses; ParseTaskResultResult
looks for content under a non-existent nested key) by decoding the
wire shape directly via the transport
- defaults to MCPTaskModeAuto so servers that don't advertise task
support behave exactly as before
Fixes#21
- Add NoOAuth field to MCPServerConfig with JSON/YAML support
- Guard OAuth error handling and transport setup with the new flag
- Prevents failed dynamic client registration on servers like PubMed
that do not support OAuth
- Add InProcessServer field to MCPServerConfig (json:"-", never serialized)
- Add "inprocess" transport type to config, validation, and connection pool
- Add createInProcessClient() using mcp-go client.NewInProcessClient()
- Add Kit.AddInProcessMCPServer() convenience method
- Add Options.InProcessMCPServers for init-time registration
- Export MCPServer type alias (= server.MCPServer) in pkg/kit/types.go
- Add 8 tests covering config, pool, tool manager, and edge cases
- Update SDK README, kit-sdk skill, and www docs
- Extract all MCP content types in prompt expansion: ImageContent,
AudioContent, EmbeddedResource (text and blob), and ResourceLink
- Add MCPFilePart type to carry decoded binary attachments through
the tools → SDK → bridge → UI layers
- Inline text resources as fenced code blocks with URI annotation
- Decode image/audio/blob content from base64 into LLMFilePart
attachments submitted via RunWithFiles
- Render ResourceLink as text annotation for the LLM
- Show attachment badges on user messages (e.g. '1 image(s) attached')
matching the existing clipboard paste UI pattern
- Log warnings on base64 decode failures instead of silently dropping
Phase 1: Smart @ for local files
- ProcessFileAttachments now returns FileAttachmentResult with separate
ProcessedText and FileParts fields instead of a plain string
- Binary files (images, audio, video, PDFs, etc.) detected via MIME type
are extracted as multimodal FileParts instead of XML-wrapped text garbage
- detectMediaType() uses extension-based lookup then content sniffing
- isBinaryMediaType() classifies image/*, audio/*, video/*, and specific
application types as binary
- @mcp:server:uri token format for referencing MCP resources in text
- All 4 submission paths (TUI submit, TUI steer, MCP prompt, CLI) updated
- App.RunOnceWithFiles/RunOnceResultWithFiles/RunOnceWithDisplayAndFiles
added for non-interactive multimodal submission
Phase 2: MCP resources in @ autocomplete
- MCPToolManager gains loadServerResources(), GetResources(), ReadResource(),
SubscribeResource(), UnsubscribeResource(), RefreshServerResources()
- MCPResource and MCPResourceContent types for resource metadata/content
- FileSuggestion extended with IsMCPResource, MCPServerName, MCPResourceURI
- InputComponent.SetMCPResourceProvider() wires resource suggestions into
the @ popup alongside local files
- @ popup merges local file suggestions with MCP resource suggestions,
sorted by fuzzy match score
- MCP resources display 'mcp:servername' in the popup description
- Selecting an MCP resource inserts @mcp:server:uri format
- ProcessFileAttachments resolves @mcp: tokens via MCPResourceReader callback
- Text resources are XML-wrapped as <resource>; binary resources become
FileParts for multimodal submission
- Agent, Kit SDK, and cmd/root.go wired end-to-end
Phase 3: Resource subscriptions (foundation)
- SubscribeResource/UnsubscribeResource on MCPToolManager
- onResourcesChanged callback for live refresh (wired but not yet
triggering UI refresh automatically)
- RefreshServerResources for manual resource list refresh
- Replace fantasy.AgentTool with plain MCPTool struct in MCPToolManager
- Move fantasy adapter from internal/tools to internal/agent as mcpAgentTool
- Add MCPToolManager.ExecuteTool() for framework-agnostic tool execution
- Remove dead fantasy.LanguageModel field from MCPConnectionPool
- Remove MCPToolManager.SetModel() (was only feeding the dead field)
internal/tools is now a pure MCP client library with no LLM framework
dependency. The fantasy-to-MCP bridging is confined to the agent layer
where it belongs.
- Store authHandler and tokenStoreFactory on Agent struct so
AddMCPServer() can propagate them to new MCPToolManagers (#3)
- Add OAuthClientID, OAuthClientSecret, OAuthScopes fields to
MCPServerConfig for servers without dynamic registration (#4)
- Pass OAuth fields from server config to transport OAuthConfig
in both SSE and Streamable HTTP client creation paths
- Add GetAuthHandler() accessor to MCPToolManager
- Add tests for auth handler propagation and OAuth config parsing
Closes#3, closes#4
- Add AddServer/RemoveServer to MCPToolManager for runtime server management
- Add RemoveConnection to MCPConnectionPool for per-server teardown
- Add AddMCPServer/RemoveMCPServer/ListMCPServers to Agent and SDK Kit
- Lazily create connection pool so AddServer works without prior LoadTools
- Wire onToolsChanged callback to trigger agent tool list rebuild
- Make MCPToolManager.Close nil-safe when pool was never initialized
Tests:
- Integration tests with real stdio MCP server (Python echo server)
- Agent-level tests using mock LLM model (no API key needed)
- Unit tests for error paths, callbacks, idempotency, nil safety
- SDK type surface tests
- Add MCPTokenStoreFactory option to kit.Options allowing SDK consumers
to provide custom token storage backends for remote MCP servers
- Thread TokenStoreFactory through the full chain: kit.Options →
kitsetup → agent → MCPToolManager → MCPConnectionPool
- Add createTokenStore() helper on connection pool that delegates to the
factory or falls back to the default FileTokenStore
- Export MCPTokenStore, MCPToken, MCPTokenStoreFactory, and ErrMCPNoToken
in pkg/kit/types.go following SDK naming conventions
- Default behavior (file-based storage) is preserved when factory is nil
Background MCP tool loading (added in 7e54710) caused tools to not appear
in the UI because tool names and counts were captured at startup before
loading completed. This adds:
- MCPToolsReadyEvent and MCPServerLoadedEvent for progress notifications
- Dynamic GetToolNames/GetMCPToolCount callbacks for live updates
- Per-server status messages as each MCP server finishes loading
- Refresh handlers to update /tools output and status bar when ready
Load MCP server tools in the background so the UI appears immediately
instead of blocking until all servers connect. The first LLM call
automatically waits for tools to be ready before proceeding.
Key changes:
- NewAgent() starts MCP loading in a background goroutine and returns
immediately with core/extension tools only
- GenerateWithLoop() calls ensureMCPTools() to lazily wait and rebuild
the fantasy agent with full tool set before first LLM call
- Parallelize LoadTools() across all configured MCP servers
- Add WaitForMCPTools() and MCPToolsReady() for status checking
- Refactor SetModel/SetExtraTools to use shared rebuildFantasyAgent()
- Expose async MCP status methods in public SDK
- Add MCPAuthHandler interface at SDK level (pkg/kit/) so all consumers
(CLI, TUI, SDK embedders) control the OAuth UX through one interface
- Default handler opens system browser + local callback server with PKCE
- CLIMCPAuthHandler wraps default with status messages (stderr pre-TUI,
system messages via TUI event system once running)
- Always enable OAuth on remote transports (streamable HTTP, SSE) when
handler is configured; harmless for servers that don't need it
- Dynamic client registration when no client ID is pre-configured
- File-based TokenStore persists tokens to ~/.config/.kit/mcp_tokens.json
keyed by server URL so users don't re-auth on restart
- Catch OAuthAuthorizationRequiredError at connection init (startup) and
tool execution (mid-session token expiry), run auth flow, retry once
- Fix error wrapping (%v -> %w) in connection pool so errors.As can
unwrap through the chain to find OAuth errors
- Thread AuthHandler through MCPToolManager -> AgentConfig ->
AgentCreationOptions -> AgentSetupOptions -> kit.Options
- 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
- agent: remove unused currentToolName variable and its compiler-suppressor
'_ = currentToolName'; currentToolArgs is the field actually used by
OnToolResult callbacks
- tools/connection_pool: collapse double-nested identical if guard into a
single check (copy-paste artifact)
- tools/mcp_test: replace hand-rolled contains() helper with strings.Contains;
add 'strings' import and delete the redundant function
Remove the entire internal/builtin package (bash, fetch, todo, http, fs
servers) and all inprocess/builtin transport support from config and
connection pool.
Add internal/core package with 7 direct fantasy.AgentTool implementations
matching pi's coding agent: bash, read, write, edit, grep, find, ls.
These execute in-process with zero MCP/JSON serialization overhead.
Add internal/message package with crush-inspired custom content blocks:
ContentPart interface with TextContent, ReasoningContent, ToolCall,
ToolResult, and Finish types. Messages carry heterogeneous Parts slices
with type-tagged JSON serialization for persistence and a ToFantasyMessages
bridge for LLM provider integration.
Core tools are always registered on the agent. External MCP servers remain
supported for additional tools, but MCP loading failures are now non-fatal
since core tools guarantee a working baseline.
OpenAI strictly validates JSON Schema and rejects 'required': null (expects
an array). When MCP tools had no required fields, the nil []string serialized
as null. Initialize required as []string{} and sanitize nested schemas
recursively to remove null/invalid required fields from MCP server responses.
Replace catwalk dependency with direct models.dev integration (97 providers,
3039 models vs catwalk's 22/679). Auto-route @ai-sdk/openai-compatible
providers through fantasy's openaicompat using the api URL from models.dev,
eliminating the need for --provider-url. Add --all flag to 'mcphost models'
to show all providers vs just fantasy-compatible ones.
Fix all 74 golangci-lint issues: errcheck (53), staticcheck SA4006 (24),
SA9003 (2), ST1005 (5), ineffassign (3). Restructure styles.go color
handling into a colorScheme struct to eliminate SA4006 false positives
from new(x) syntax.
Each spinner created a new tea.NewProgram which sent DECRQM queries for
synchronized output mode 2026. When the program exited and restored
cooked terminal mode, the terminal's DECRPM response leaked as visible
^[[?2026;2$y characters. Replace Bubble Tea spinner with a simple
goroutine animation loop writing directly to stderr via lipgloss.
Add support for using Claude models via Google Cloud Vertex AI through
the `google-vertex-anthropic` provider. This enables users who have
Claude access through their Google Cloud account to use mcphost with
Vertex AI authentication.
Changes:
- Add `google-vertex-anthropic` provider case and createVertexAnthropicProvider()
- Support multiple env var names for project/region to match eino-claude:
- Project: ANTHROPIC_VERTEX_PROJECT_ID, GOOGLE_CLOUD_PROJECT, GCLOUD_PROJECT
- Region: CLOUD_ML_REGION (defaults to "global" if not set)
- Upgrade eino from v0.5.11 to v0.7.11 (required by eino-claude v0.1.12)
- Migrate schema API from OpenAPI v3 to JSON Schema (eino v0.7.11 change)
Usage:
# Authenticate with Google Cloud
gcloud auth application-default login
# Set required environment variables
export ANTHROPIC_VERTEX_PROJECT_ID="your-project-id"
export CLOUD_ML_REGION="us-east5" # or use default "global"
# Run mcphost
mcphost --model google-vertex-anthropic:claude-sonnet-4@20250514
Reference: https://docs.anthropic.com/en/docs/claude-code/google-vertex-ai🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: convert JSON Schema draft-07 exclusive bounds to draft-04 format
Chrome DevTools MCP and other MCP servers use JSON Schema draft-07 where
exclusiveMinimum/exclusiveMaximum are numeric values representing the
actual bounds. However, kin-openapi (OpenAPI 3.0) expects these fields
as booleans that modify the minimum/maximum values (draft-04 format).
This fix recursively processes input schemas to convert:
- exclusiveMinimum: N → minimum: N, exclusiveMinimum: true
- exclusiveMaximum: N → maximum: N, exclusiveMaximum: true
Handles nested schemas in properties, items, additionalProperties,
and schema composition keywords (allOf, anyOf, oneOf, not).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: add table-driven tests for JSON Schema draft conversion
Adds comprehensive tests for convertExclusiveBoundsToBoolean():
- Simple exclusiveMinimum/exclusiveMaximum conversion
- Both bounds together
- Already boolean values (draft-04 style, unchanged)
- No exclusive bounds (unchanged)
- Nested properties
- Array items
- allOf composition
- additionalProperties
- Real-world Chrome DevTools MCP schema example
- Invalid JSON handling (returns unchanged)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Replace fmt.Printf calls in connection pool health check routines with debug logger calls. Health check messages are now only displayed when the --debug flag is enabled, providing a cleaner terminal output during normal operation while maintaining diagnostic information for troubleshooting.
* feat: add MCP connection pool with health check and retry mechanism
* feat: add proactive connection health check before tool calls
- Add GetConnectionWithHealthCheck method to perform health check before reusing connections
- Add performHealthCheck method to test connection health with ListTools call
- Modify InvokableRun to use health-checked connections
- This prevents first tool call failure when connection is broken
- Improves user experience by ensuring connections are healthy before tool execution
---------
Co-authored-by: 茂勋 <shancangchen.csc@alibaba-inc.com>
Fixes#89: Tools created without input properties were causing OpenAI function
calling validation errors with "object schema missing properties" message.
The issue occurred when MCP tools had no input parameters, resulting in OpenAPI
schemas with Type="object" but Properties=nil, which violates OpenAI's function
calling schema requirements.
Changes:
- Add schema validation fix in loadServerTools to ensure object schemas have
empty properties map when Properties is nil
- Add comprehensive regression test TestIssue89_ObjectSchemaMissingProperties
- Add additional test coverage for tools without properties
The fix ensures backward compatibility while resolving the validation error.
Users no longer need the workaround of adding dummy parameters to their tools.
🤖 Generated with [opencode](https://opencode.ai)
Co-authored-by: opencode <noreply@opencode.ai>
Ed Zynda