co-mono/packages/agent/CHANGELOG.md

Changelog

[Unreleased]

[0.42.5] - 2026-01-11

[0.42.4] - 2026-01-10

[0.42.3] - 2026-01-10

[0.42.2] - 2026-01-10

[0.42.1] - 2026-01-09

[0.42.0] - 2026-01-09

[0.41.0] - 2026-01-09

[0.40.1] - 2026-01-09

[0.40.0] - 2026-01-08

[0.39.1] - 2026-01-08

[0.39.0] - 2026-01-08

[0.38.0] - 2026-01-08

Added

• thinkingBudgets option on Agent and AgentOptions to customize token budgets per thinking level (#529 by @melihmucuk)

[0.37.8] - 2026-01-07

[0.37.7] - 2026-01-07

[0.37.6] - 2026-01-06

[0.37.5] - 2026-01-06

[0.37.4] - 2026-01-06

[0.37.3] - 2026-01-06

Added

• sessionId option on Agent to forward session identifiers to LLM providers for session-based caching.

[0.37.2] - 2026-01-05

[0.37.1] - 2026-01-05

[0.37.0] - 2026-01-05

Fixed

• minimal thinking level now maps to minimal reasoning effort instead of being treated as low.

[0.36.0] - 2026-01-05

[0.35.0] - 2026-01-05

[0.34.2] - 2026-01-04

[0.34.1] - 2026-01-04

[0.34.0] - 2026-01-04

[0.33.0] - 2026-01-04

[0.32.3] - 2026-01-03

[0.32.2] - 2026-01-03

[0.32.1] - 2026-01-03

[0.32.0] - 2026-01-03

Breaking Changes

• Queue API replaced with steer/followUp: The queueMessage() method has been split into two methods with different delivery semantics (#403):
  • steer(msg): Interrupts the agent mid-run. Delivered after current tool execution, skips remaining tools.
  • followUp(msg): Waits until the agent finishes. Delivered only when there are no more tool calls or steering messages.
• Queue mode renamed: queueMode option renamed to steeringMode. Added new followUpMode option. Both control whether messages are delivered one-at-a-time or all at once.
• AgentLoopConfig callbacks renamed: getQueuedMessages split into getSteeringMessages and getFollowUpMessages.
• Agent methods renamed:
  • queueMessage() → steer() and followUp()
  • clearMessageQueue() → clearSteeringQueue(), clearFollowUpQueue(), clearAllQueues()
  • setQueueMode()/getQueueMode() → setSteeringMode()/getSteeringMode() and setFollowUpMode()/getFollowUpMode()

Fixed

• prompt() and continue() now throw if called while the agent is already streaming, preventing race conditions and corrupted state. Use steer() or followUp() to queue messages during streaming, or await the previous call.

[0.31.1] - 2026-01-02

[0.31.0] - 2026-01-02

Breaking Changes

• Transport abstraction removed: ProviderTransport, AppTransport, and AgentTransport interface have been removed. Use the streamFn option directly for custom streaming implementations.

• Agent options renamed:

  • transport → removed (use streamFn instead)
  • messageTransformer → convertToLlm
  • preprocessor → transformContext

• AppMessage renamed to AgentMessage: All references to AppMessage have been renamed to AgentMessage for consistency.

• CustomMessages renamed to CustomAgentMessages: The declaration merging interface has been renamed.

• UserMessageWithAttachments and Attachment types removed: Attachment handling is now the responsibility of the convertToLlm function.

• Agent loop moved from @mariozechner/pi-ai: The agentLoop, agentLoopContinue, and related types have moved to this package. Import from @mariozechner/pi-agent instead.

Added

• streamFn option on Agent for custom stream implementations. Default uses streamSimple from pi-ai.

• streamProxy() utility function for browser apps that need to proxy LLM calls through a backend server. Replaces the removed AppTransport.

• getApiKey option for dynamic API key resolution (useful for expiring OAuth tokens like GitHub Copilot).

• agentLoop() and agentLoopContinue() low-level functions for running the agent loop without the Agent class wrapper.

• New exported types: AgentLoopConfig, AgentContext, AgentTool, AgentToolResult, AgentToolUpdateCallback, StreamFn.

Changed

• Agent constructor now has all options optional (empty options use defaults).

• queueMessage() is now synchronous (no longer returns a Promise).