Changelog

Track the evolution of the Hikigai SDK. New features, improvements, and fixes.

v2.1.0

BREAKINGJanuary 2026

Multi-Agent Systems & Project Association

  • Multi-agent systems with sequential, parallel, and loop execution
  • Session-based conversation management
  • Project-scoped deployments (breaking change)
  • Tools now optional for simple LLM agents
Added
  • Multi-agent support: agent_type with sequential, parallel, and loop modes
  • Sub-agents deployment with sub_agents field for complex workflows
  • Session management with session_id parameter and with_session() method
  • Planning & reasoning modes (planning_mode: builtin or plan_react)
  • Code execution support (code_execution with gemini, vertex_sandbox, or local executor)
  • Advanced LLM control (temperature, top_p, top_k, max_output_tokens)
  • Project-scoped API keys and agent deployment with project_id
  • max_iterations parameter for loop agents
  • thinking_budget for planning mode token allocation
  • include_thoughts flag to expose reasoning in responses
Changed
  • BREAKING: project_id is now REQUIRED in AgentConfig
  • BREAKING: display_name is now REQUIRED (no longer optional)
  • BREAKING: version is now REQUIRED (no default value)
  • BREAKING: timeout is now REQUIRED (no default value)
  • Tools are now OPTIONAL - empty list allowed for simple LLM agents
  • SDK always sends tools, memory_mb, timeout fields regardless of values
  • Backend validates project_id matches API key scope
Improved
  • Better validation error messages with detailed field information
  • Frontend deployment wizard allows agents without tools
  • SDK payload construction optimized for required backend fields
  • Documentation updated with comprehensive multi-agent examples

v0.3.0

NEWDecember 2024

Schema Types & ADK Support

  • Typed input/output schemas for agents
  • Google ADK agent deployment support
  • Enhanced HIPAA compliance configuration
Added
  • InputSchema and OutputSchema classes for typed agent I/O
  • Field types: StringField, NumberField, IntegerField, BooleanField, ArrayField, ObjectField, EnumField
  • deploy_adk() and deploy_adk_project() methods for Google ADK agents
  • HIPAAConfig class for compliance settings
  • AgentVersion class for version metadata
  • Session-based conversations with with_session()
Improved
  • AgentConfig now supports schemas, versioning, and display names
  • Agent model includes tools, runtime config, and compliance flags
  • Performance optimization with __slots__ across all types
  • Lazy loading for constants (CATEGORIES, MODELS, TAGS)

v0.2.0

NEWNovember 2024

Async Client & Streaming

  • Full async/await API with HikigaiAsync
  • Auto-pagination for listing agents
  • Real-time streaming responses
Added
  • HikigaiAsync class for async operations
  • AsyncAgent wrapper for async invoke/stream
  • AgentPaginator with auto-pagination (iter_agents)
  • Streaming support via agent.stream()
  • deploy_from_file() for code-based deployment
Improved
  • Connection pooling for better performance
  • Agent caching to reduce API calls
  • InvokeResponse now includes latency_ms and tokens_used
Fixed
  • Rate limit retry handling with exponential backoff
  • Session ID persistence across invocations

v0.1.0

October 2024

Initial Release

  • Core SDK for deploying AI agents
  • HIPAA-compliant infrastructure
  • CLI tools for development
Added
  • Hikigai client class with deploy, agent, list_agents, delete_agent
  • AgentConfig for deployment configuration
  • Agent class with invoke() method
  • ToolConfig for agent tools
  • Exception hierarchy (HikigaiError, AuthenticationError, etc.)
  • CLI tool with deploy, list, get, invoke, delete commands
  • Logging utilities with set_log_level()
  • UsageResponse for API usage statistics

Start building with the SDK

Deploy your first healthcare AI agent in minutes.