Claude requires max_tokens > thinking.budget_tokens. When caller specifies
a small maxTokens (e.g. compaction with ~13k tokens) and reasoning is enabled
with high budget (16k tokens), the constraint was violated.
Fix: In mapOptionsForApi, add thinkingBudget on top of caller's maxTokens
(capped at model.maxTokens). If still not enough room, reduce thinkingBudget
to leave space for output.
Applied to both anthropic-messages and google-gemini-cli APIs.
Also adds test utilities for OAuth credential resolution and tests for
compaction with thinking models.
fixes#413
Builds on #406 to support simpler proxy use case:
- Override just baseUrl to route built-in provider through proxy
- All built-in models preserved, no need to redefine them
- Full replacement still works when models array is provided
* Allow models.json to override built-in providers
When a provider is defined in models.json with the same name as a
built-in provider (e.g., 'anthropic', 'google'), the built-in models
for that provider are completely replaced by the custom definition.
This enables users to:
- Use custom base URLs (proxies, self-hosted endpoints)
- Define a subset of models they want available
- Customize model configurations for built-in providers
Example usage in ~/.pi/agent/models.json:
{
"providers": {
"anthropic": {
"baseUrl": "https://my-proxy.example.com/v1",
"apiKey": "ANTHROPIC_API_KEY",
"api": "anthropic-messages",
"models": [...]
}
}
}
* Refactor model-registry for readability
- Extract CustomModelsResult type and emptyCustomModelsResult helper
- Extract loadBuiltInModels method with clear skip logic
- Simplify loadModels with destructuring and ternary
- Reduce repetition in error handling paths
* Refactor model-registry tests for readability
- Extract providerConfig() helper to hide irrelevant model fields
- Extract writeModelsJson() helper for file writing
- Extract getModelsForProvider() helper for filtering
- Move modelsJsonPath to beforeEach
Reduces test file from 262 to 130 lines while maintaining same coverage.
- Update settings-manager with steeringMode/followUpMode (migrates old queueMode)
- Update sdk.ts to use new mode options
- Update settings-selector UI to show both modes
- Add Alt+Enter keybind for follow-up messages
- Update RPC API: steer/follow_up commands, set_steering_mode/set_follow_up_mode
- Update rpc-client with new methods
- Delete dead code: queue-mode-selector.ts
- Update tests for new API
- Update mom/context.ts stubs
- Update web-ui example
- Rename queueMessage to steer(), add followUp()
- Split _pendingMessages into _steeringMessages and _followUpMessages
- Update sendHookMessage to accept deliverAs option
- Rename hasQueuedMessages to hasPendingMessages
- Rename queuedMessageCount to pendingMessageCount
- Update clearQueue() return type to { steering, followUp }
- Update UI to show steering vs follow-up messages differently
WIP: settings-manager, sdk, interactive-mode, rpc-mode still need updates
Agent.prompt() and Agent.continue() now throw if called while already
streaming, preventing race conditions and corrupted state. Use
queueMessage() to queue messages during streaming, or await the
previous call.
AgentSession.prompt() has the same guard with a message directing
users to queueMessage().
Ref #403
Move line count from header to footer to avoid changing the first line
during streaming, which was triggering full screen re-renders in the
TUI's differential rendering logic.
HookContext (all events):
- isIdle() - read-only state check
- hasQueuedMessages() - read-only state check
- abort() - fire-and-forget, does not wait
HookCommandContext (slash commands only):
- waitForIdle() - waits for agent to finish
- newSession(options?) - create new session
- branch(entryId) - branch from entry
- navigateTree(targetId, options?) - navigate session tree
Session control methods moved from HookAPI (pi.*) to HookCommandContext (ctx.*)
because they can deadlock when called from event handlers that run inside
the agent loop (tool_call, tool_result, context events).
HookAPI additions:
- pi.newSession(options?) - create new session with optional setup callback
- pi.branch(entryId) - branch from a specific entry
- pi.navigateTree(targetId, options?) - navigate the session tree
HookContext additions:
- ctx.isIdle() - check if agent is streaming
- ctx.waitForIdle() - wait for agent to finish
- ctx.abort() - abort current operation
- ctx.hasQueuedMessages() - check for queued user messages
These enable hooks to programmatically manage sessions (handoff, templates)
and check agent state before showing interactive UI.
Fixes#388
- Remove session_before_new and session_new hook events
- Add reason: 'new' | 'resume' to session_before_switch and session_switch events
- Remove 'new' reason from custom tool onSession (use 'switch' for both /new and /resume)
- Rename reset() to newSession(options?) in AgentSession
- Add NewSessionOptions with optional parentSession for lineage tracking
- Rename branchedFrom to parentSession in SessionHeader
- Rename RPC reset command to new_session with optional parentSession
- Update example hooks to use new event structure
- Update documentation and changelog
Based on discussion in #293
- Add theme property to HookUIContext interface
- Implement in interactive, RPC, and no-op contexts
- Add status-line.ts example hook
- Document styling with theme colors in hooks.md
* Add ctx.ui.setStatus(key, text) API for hooks to display status in footer
- Add setStatus to HookUIContext interface
- Implement in interactive mode (FooterComponent)
- Implement in RPC mode (fire-and-forget)
- Add no-op implementations for headless contexts
- Multiple statuses displayed on single line, sorted by key
- Supports ANSI styling (hooks handle their own colors)
* Remove setStatus from changelog for now
* Fix hook status API to follow TUI rules
- Sanitize status text: replace newlines, tabs, carriage returns with spaces
- Truncate combined status line to terminal width using truncateToWidth
- Update JSDoc to document sanitization and truncation behavior
- Remove unused createHookUIContext method
- Add missing setStatus to test mock
* Add setStatus to changelog
* Use dim ellipsis for hook status truncation for consistency with footer style
---------
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
- Add setEditorText() and getEditorText() to HookUIContext for prompt generator pattern
- custom() now accepts async factories for fire-and-forget work
- Add CancellableLoader component to tui package
- Add BorderedLoader component for hooks with cancel UI
- Export HookAPI, HookContext, HookFactory from main package
- Update all examples to import from packages instead of relative paths
- Update hooks.md and custom-tools.md documentation
fixes#350
- CustomAgentTool renamed to CustomTool
- ToolAPI renamed to CustomToolAPI
- ToolContext renamed to CustomToolContext
- ToolSessionEvent renamed to CustomToolSessionEvent
- Added CustomToolContext parameter to execute() and onSession()
- CustomToolFactory now returns CustomTool<any, any> for type compatibility
- dispose() replaced with onSession({ reason: 'shutdown' })
- Added wrapCustomTool() to convert CustomTool to AgentTool
- Session exposes setToolUIContext() instead of leaking internals
- Fix ToolExecutionComponent to sync with toolOutputExpanded state
- Update all custom tool examples for new API
Compaction API:
- prepareCompaction() now takes (pathEntries, settings) only
- CompactionPreparation restructured: removed cutPoint/messagesToKeep/boundaryStart, added turnPrefixMessages/isSplitTurn/previousSummary/fileOps/settings
- compact() now takes (preparation, model, apiKey, customInstructions?, signal?)
- Fixed token overflow by using getPath() instead of getEntries()
Hook types:
- HookEventContext renamed to HookContext
- HookCommandContext removed, RegisteredCommand.handler takes (args, ctx)
- HookContext now includes model field
- SessionBeforeCompactEvent: removed previousCompactions/model, added branchEntries
- SessionBeforeTreeEvent: removed model (use ctx.model)
- HookRunner.initialize() added for modes to set up callbacks
- Move compaction.ts to src/core/compaction/compaction.ts
- Extract branch summarization to src/core/compaction/branch-summarization.ts
- Add index.ts to re-export all compaction utilities
- Update all imports across the codebase
- Add test/utilities.ts with shared helpers (API_KEY, userMsg, assistantMsg, createTestSession)
- Add agent-session-tree-navigation.test.ts with e2e tests for tree navigation
- Add getChildren() method to SessionManager
- Add summaryEntry to navigateTree return type
- Update existing tests to use shared utilities
- Check response.stopReason instead of catching errors for abort detection
- Return result object from _generateBranchSummary instead of throwing
- Fix summary attachment: attach to navigation target position, not old branch
- Support root-level summaries (parentId=null) in branchWithSummary
- Remove setTimeout hack for re-showing tree selector on abort
Major changes:
- Replace monolithic SessionEvent with reason discriminator with individual
event types: session_start, session_before_switch, session_switch,
session_before_new, session_new, session_before_branch, session_branch,
session_before_compact, session_compact, session_shutdown
- Each event has dedicated result type (SessionBeforeSwitchResult, etc.)
- HookHandler type now allows bare return statements (void in return type)
- HookAPI.on() has proper overloads for each event with correct typing
Additional fixes:
- AgentSession now always subscribes to agent in constructor (was only
subscribing when external subscribe() called, breaking internal handlers)
- Standardize on undefined over null throughout codebase
- HookUIContext methods return undefined instead of null
- SessionManager methods return undefined instead of null
- Simplify hook exports to 'export type * from types.js'
- Add detailed JSDoc for skipConversationRestore vs cancel
- Fix createBranchedSession to rebuild index in persist mode
- newSession() now returns the session file path
Updated all example hooks, tests, and emission sites to use new event types.
- addMessageToChat: exhaustive switch for all AgentMessage roles
- renderSessionContext: delegates to addMessageToChat, special handling for assistant tool calls and tool results
- export-html formatMessage: exhaustive switch for all AgentMessage roles
- Removed isHookMessage, isBashExecutionMessage type guards in favor of role checks
- Fixed imports and removed unused getLatestCompactionEntry
- Removed Attachment from agent package (now in web-ui/coding-agent)
- Agent.prompt now takes (text, images?: ImageContent[])
- Removed transports from web-ui (duplicate of agent package)
- Updated coding-agent to use local message types
- Updated mom package for new agent API
Remaining: Fix AgentInterface.ts to compose UserMessageWithAttachments
- Renamed AppMessage to AgentMessage throughout
- New agent-loop.ts with AgentLoopContext, AgentLoopConfig
- Removed transport abstraction, Agent now takes streamFn directly
- Extracted streamProxy to proxy.ts utility
- Removed agent-loop from pi-ai (now in agent package)
- Updated consumers (coding-agent, mom) for AgentMessage rename
- Tests updated but some consumers still need migration
Known issues:
- AgentTool, AgentToolResult not exported from pi-ai
- Attachment not exported from pi-agent-core
- ProviderTransport removed but still referenced
- messageTransformer -> convertToLlm migration incomplete
- CustomMessages declaration merging not working properly
- Extract execCommand to src/core/exec.ts, shared by hooks and custom-tools
- Rename CustomMessageRenderer -> HookMessageRenderer
- Rename registerCustomMessageRenderer -> registerMessageRenderer
- Renderer now receives HookMessage instead of CustomMessageEntry
- CustomMessageComponent now has setExpanded() and responds to Ctrl+E toggle
- Re-export ExecOptions/ExecResult from exec.ts for backward compatibility
- compaction-hooks-example.test.ts: get sessionManager/modelRegistry from ctx
- compaction-hooks.test.ts:
- Pass sessionManager/modelRegistry to HookRunner constructor
- Remove setSessionFile call
- Update tests to use session.sessionManager instead of event.sessionManager
Breaking changes to Hook API:
- pi.send(text, attachments?) replaced with pi.sendMessage(message, triggerTurn?)
- Creates CustomMessageEntry instead of user messages
- Properly handles queuing during streaming via agent loop
- Supports optional turn triggering when idle
- New pi.appendEntry(customType, data?) for hook state persistence
- New pi.registerCommand(name, options) for custom slash commands
- Handler types renamed: SendHandler -> SendMessageHandler, new AppendEntryHandler
Implementation:
- AgentSession.sendHookMessage() handles all three cases:
- Streaming: queues message with _hookData marker, agent loop processes it
- Not streaming + triggerTurn: appends to state/session, calls agent.continue()
- Not streaming + no trigger: appends to state/session only
- message_end handler routes based on _hookData presence to correct persistence
- HookRunner gains getRegisteredCommands() and getCommand() methods
New types: HookMessage<T>, RegisteredCommand, CommandContext
- Add renderCustomMessage to HookAPI for registering custom renderers
- Add CustomMessageRenderer type and CustomMessageRenderOptions
- Store customMessageRenderers in LoadedHook
- Add getCustomMessageRenderer(customType) to HookRunner
- SessionContext.entries now aligned with messages (same length, corresponding indices)
TUI can now correlate messages with their source entries to identify
custom_message entries and use hook-provided renderers.
- Add LabelEntry type with targetId and label (string | undefined)
- Add labelsById map built on load via linear scan
- Add getLabel(id) and appendLabelChange(targetId, label) methods
- Add label field to SessionTreeNode, populated by getTree()
- Update createBranchedSession to preserve labels for entries on path
- Labels are ignored by buildSessionContext (not sent to LLM)
- Add comprehensive tests for label functionality
- SessionEntry now only contains conversation entries (messages, compaction, etc.)
- SessionHeader is separate, not part of SessionEntry
- FileEntry = SessionHeader | SessionEntry (for file storage)
- getEntries() filters out header, returns SessionEntry[]
- Added getHeader() for accessing session metadata
- Updated compaction and tests to not expect header in entries
- Updated mom package to use FileEntry for internal storage
- getEnvApiKey: ANTHROPIC_OAUTH_TOKEN now takes precedence over ANTHROPIC_API_KEY
- findCutPoint: Stop scan-backwards loop at session header (was decrementing past it causing null preparation)
- generateSummary/generateTurnPrefixSummary: Throw on stopReason=error instead of returning empty string
- Test files: Fix API key priority order, use keepRecentTokens=1 for small test conversations
- Add AuthStorage class for credential storage (auth.json)
- Add ModelRegistry class for model management with API key resolution
- Add discoverAuthStorage() and discoverModels() discovery functions
- Add migration from legacy oauth.json and settings.json apiKeys to auth.json
- Remove configureOAuthStorage, defaultGetApiKey, findModel, discoverAvailableModels
- Remove apiKeys from Settings type and SettingsManager methods
- Rename getOAuthPath to getAuthPath
- Update SDK, examples, docs, tests, and mom package
Fixes#296
- Merge branch event into session with before_branch/branch reasons
- Add before_switch, before_clear, shutdown reasons
- before_* events can be cancelled with { cancel: true }
- Update RPC commands to return cancelled status
- Add shutdown event on process exit
- New example hooks: confirm-destructive, dirty-repo-guard, auto-commit-on-exit
fixes#278
- SettingsManager now loads .pi/settings.json from cwd (project settings)
- Project settings merge with global settings (deep merge for objects)
- Setters only modify global settings, project settings are read-only
- Add static factories: SettingsManager.create(cwd?, agentDir?), SettingsManager.inMemory(settings?)
- Add applyOverrides() for programmatic overrides
- Replace 'settings' option with 'settingsManager' in CreateAgentSessionOptions
- Update examples to use new pattern
Incorporates PR #276 approach
