v3.2.0
UseInterstellar/Interstellarv3.2.0Feb 9, 2026by kichanyurd
AI Summary
This release introduces a comprehensive set of features for agent guidance, session management, and data retrieval, including lifecycle hooks, streaming output, and labeling capabilities.
Key Highlights
- Added labeling system for Guidelines, Journeys, and Sessions with automatic propagation
- Introduced lifecycle hooks (`on_match`, `on_message`) and streaming message output mode
- Enhanced data retrieval capabilities with `attach_retriever()` and field dependencies
- Improved agent configuration with per-agent preambles and fluid mode greetings
- Fixed critical bugs in websocket handling and guideline matching logic
New Features
- Labels for categorization and filtering (Guidelines, Journeys, Sessions, JourneyNodes)
- Automatic session label propagation from matched entities
- Track parameter for guidelines to control 'previously applied' tracking
- Support for multiple targets in `prioritize_over()` and `depend_on()` methods
- Field dependencies for canned responses
- Conditional data retrieval via `attach_retriever()`
- Lifecycle callbacks (`on_match`, `on_message`) for journeys
- Per-agent preamble configuration
- Separate default greeting responses for first agent message in fluid mode
- Streaming message output mode
- Custom journey node ID support
Full Release Notes
## [3.2.0] - 2026-02-09 ### Added - Add labels to Guidelines, Journeys, JourneyNodes, and Sessions for categorization and filtering - Add automatic session label propagation from matched entities (guidelines, observations, journeys) - Add `track` parameter to guidelines to control "previously applied" tracking - Support multiple targets in `prioritize_over()` and `depend_on()` methods - Add `field_dependencies` to canned responses for explicit field availability requirements - Add `attach_retriever()` to Guideline, Journey, and JourneyState for conditional data retrieval - Add `on_match` and `on_message` hooks to journeys for lifecycle callbacks - Add per-agent preamble configuration (custom examples and instructions) - Add separate default greeting responses for first agent message in fluid mode - Add streaming message output mode - Allow specifying custom journey node ID - Add matched guidelines/journey states to completion ready event ### Changed - Make condition optional for SDK guidelines - Tweak default preamble examples - Soften log levels for relational guideline resolver - Add activated/skipped logs to custom guideline matcher batches ### Fixed - Fix websocket warning upon startup - Fix agent intention proposer (guidelines were getting rewritten incorrectly) - Fix multiple customer guideline matchers not working - Fix bug with context variable access in SDK