Releases

Stay up to date with the latest Pika Framework releases, new features, and important changes.

Current Version

What's New in 0.15.4

Opensearch Type Issue - Fixed minor opensearch type issue
- Fixed issue where metrics were not corectly being transformed on way in/out of opensearch

Latest Stable: 0.15.4 (November 4, 2025)

What's New in 0.15.3

Cost Distribution Charts - Added cost distribution charts to session analytics
- Added cost distribution charts to session analytics
Auto Insights Runaway Issue - Fixed auto insights runaway issue
- Fixed data corruption issue allowing auto insights to run indefinitely (made self healing)

What's New in 0.15.2

Analtyics Backfill Tool - Fixed analtyics tool flushing issuenot flushing messages to OpenSearch
- Fixed issue where analytics tool was not flushing messages to OpenSearch

Check your project version:

cat .pika-sync.json | grep pikaVersion

What's New in 0.15.0

Message-Level Analytics - Enhanced session analytics with comprehensive message insights
- Message counts: user messages, assistant responses, averages per session
- Per-response metrics: cost, tokens, execution duration
- Timing analytics: response time, user think time, session duration, long gap detection
- New time series chart showing user vs assistant message counts
- Pre-computed statistics for 10-100x faster queries
Message Content Search - Session Insights search now includes full-text message search
- Search across message text, extracted LLM instructions, and model names
- Seamless integration with existing session field search
Message Index - New dedicated OpenSearch index for message documents
- Full-text search on message content and LLM instructions
- Automatic replication from DynamoDB via Lambda stream handler
Migration Tools - Three migration scripts for safe deployment
- update-session-mapping-for-messages.ts - Update session index (run BEFORE deployment)
- backfill-invocation-mode-to-messages/ - Backfill message metadata
- backfill-messages-to-opensearch/ - Populate message index and analytics

Find All Type Changes for This Release:

Search the repository for @since 0.15.0 to find all type definitions that were added, updated, or removed in this release.

What's New in 0.14.2

Admin Site Session Insights - Improved admin site session insights feature
- Enhanced client-side filtering with hybrid search capabilities
- Added batch user lookup API for displaying user names
- Improved entity column handling with automatic name enrichment
- Better UX with hover-to-copy functionality and reactive updates

What's New in 0.14.1

Bug Fix - Fixed stack tags to ensure they are converted to required string type before being applied to Bedrock inference profiles

What's New in 0.14.0

Component Tags for Granular Cost Tracking - Enhanced stack tagging with component-level identification
- New componentTagNames array in stackTags configuration tags each infrastructure resource with its component name
- Component tags applied to all AWS resources: Lambda, DynamoDB, S3, ECS, Fargate, KMS, OpenSearch, Bedrock inference profiles
- Enables granular cost analysis in AWS Cost Explorer - see costs for specific Lambda functions, DynamoDB tables, or AI models
- Example: Filter by AWS Lambda, then group by component tag to see costs for each function separately
- Particularly valuable for Bedrock costs - track which AI models consume the most
- Helper method applyComponentTags() in custom-stack-defs.ts for easy tagging of custom infrastructure
- See AWS CDK deployment guide Component Tags section
Tag Environment Variable Support - CloudFormation custom resources can now access and apply tags
- Tags passed to custom resource Lambdas via STACK_TAGS and COMPONENT_TAG_NAMES environment variables
- New utility functions: getStackTagsFromEnv(), getComponentTagNamesFromEnv(), createComponentTags(), etc.
- Bedrock inference profiles and KMS keys now properly tagged with component identifiers
Tag Size Validation - Prevents deployment failures due to AWS Lambda limits
- 500-byte limit enforced on combined tag environment variables
- CDK synthesis fails early with clear error if limit exceeded
Bug Fixes - Fixed inference profile tag deduplication and custom resource re-invocation
Type Additions - New property with @since 0.14.0 annotation:
- PikaConfig.stackTags.componentTagNames - Component tag names array

Find All Type Changes for This Release:

Search the repository for @since 0.14.0 to find all type definitions that were added, updated, or removed in this release.

What's New in 0.13.0

Inference Profile Cost Tracking - Automatic creation of named inference profiles for granular AI model cost analysis
- Pika automatically creates named inference profiles for Claude 4 Sonnet, Claude 4.5 Haiku, and Claude 4.5 Sonnet
- Enables per-model cost tracking in AWS Cost Explorer
- Inference profiles follow naming pattern: {stackName}-{profileName} (e.g., pika-test-claude-sonnet-4-5)
- All profiles tagged with your configured stackTags for flexible cost allocation
- See Track AI Model Costs guide
AWS Resource Tagging System - Comprehensive tagging for cost tracking, organization, and compliance
- New stackTags configuration in pika-config.ts with common, pikaServiceTags, and pikaChatTags categories
- Dynamic placeholder support: {stage}, {timestamp}, {accountId}, {region}, {pika.projNameKebabCase}, etc.
- Tags applied to all AWS resources including Lambda, DynamoDB, S3, CloudFront, and inference profiles
- See Configure AWS Resource Tags guide
Type Additions - New interfaces with @since 0.13.0 annotations:
- PikaConfig.stackTags - AWS resource tagging configuration
- MarkdownRendererConfig - Markdown renderer options
- IAppState.convertMarkdownToHtml() - Markdown conversion method

Find All Type Changes for This Release:

Search the repository for @since 0.13.0 to find all type definitions that were added, updated, or removed in this release.

What's New in 0.12.0

Entity List Value Retrieval - New required method for entity implementations
- Added getValuesForEntityList() method to fetch entity display names by ID
- Required for displaying entity names in session analytics and admin UI
- Important: When syncing, this method must be manually added to custom-data.ts
- Can return empty array if entity feature is not being used
Session Analytics UI Improvements - Enhanced admin site analytics interface
- Improved visual design and layout of session analytics dashboard
- Better organization of filters and controls with refined toggle groups
- Enhanced date range selection with popup calendar
- More intuitive entity filtering interface
Type Additions - New GetValuesForEntityListRequest and GetValuesForEntityListResponse interfaces with @since 0.12.0 annotations

What's New in 0.11.3

pika-cli Sync Command Improvements - Better temp file handling and visual diff functionality
- Changed temp directory location from project directory to OS temp directory for cleaner workspace
- Added automatic cleanup of old pika-sync-* temp directories
- Fixed --visualdiff mode to keep temp files available for editor review
- Fixed visual diff command execution for better cross-platform compatibility
- Added informative logging about temp file location when using --visualdiff
Site Admin General Settings Fix - Fixed page header right snippet not being assigned
OpenSearch Error Logging - Improved error message logging for source filtering failures

What's New in 0.11.2

CI/CD Pipeline Fix - Fixed pnpm lockfile synchronization issue
- Resolved ERR_PNPM_OUTDATED_LOCKFILE error in GitHub Actions workflows
- Regenerated lockfile to sync dependency ordering with package.json files
- Ensures successful frozen-lockfile installation in CI environments

What's New in 0.11.1

Site Admin Type Safety Improvements - Fixed TypeScript type handling in site admin pages
- Removed unnecessary as any type casts for page header snippets
- Improved type safety in 6 site admin components: chat apps, general settings, instruction augmentation, memory, session analytics, and session insights

What's New in 0.11.0

Enhanced Session Analytics Dashboard - Comprehensive analytics with advanced filtering and aggregations
- Filter sessions by invocation mode, user type, and source
- Cost aggregations by invocation mode with visual charts
- Session count trends and distribution visualizations
Widget Metadata System - Dynamic UI chrome for widgets across all rendering contexts
- Set title, icon, loading status, and custom actions for widgets
- Metadata can be set initially or dynamically updated
- Support for spotlight, canvas, and dialog widgets
Dynamic Widget Registration for Canvas/Dialog - No tag definitions required
- Auto-generation of tag definitions when needed
- Auto-enables requested rendering context
Widget Context API - Access full context from widget action callbacks
- New getWidgetContext(instanceId) method
- Widget actions receive element reference and full context
Automatic User Profile Sync - Framework syncs firstName/lastName from auth provider
Type Organization Improvements - Better organized TypeScript types with @since annotations

Breaking Changes:

OpenSearch keyword field migration required for session analytics aggregations
User type migration required for chat sessions
WidgetAction callback signature changed to receive context object

See the Migration Guide for complete upgrade instructions.

Find All Type Changes for This Release:

Search the repository for @since 0.11.0 to find all type definitions that were added, updated, or removed in this release.

What's New in 0.9.0

Complete Documentation Site Overhaul - Brand new Astro-based documentation experience
Comprehensive documentation following Diátaxis framework (Tutorials, How-To Guides, Explanations, Reference)
Reorganized content structure: Why Pika, Getting Started, Concepts, Capabilities, Guides, Reference, Platform
Enhanced content with detailed diagrams, code examples, and step-by-step instructions
Improved navigation, search functionality, and custom Markdoc components
Documentation generation prompt template for AI-assisted content creation
Updated release tooling for better version management

What's New in 0.8.0

Widget Instance Registry - Comprehensive tracking system for all rendered web components
Centralized registry accessible via chatAppState.widgetInstances with DOM element references
Automatic lifecycle tracking across all rendering contexts (spotlight, canvas, dialog, inline, static)
Cross-widget communication, debugging, and programmatic manipulation capabilities
Memory leak prevention with automatic cleanup when widgets are removed
Enhanced API returning both instanceId and element reference

What's New in 0.7.0

Web Component Initialization Enhancement - Direct property and attribute setting when rendering components
New DataForWidget interface with attributes, properties, and onReady callback
Pass complex objects, arrays, or functions directly to web component properties
Get notified when component is ready with lifecycle callback
Comprehensive documentation with detailed examples

What's New in 0.6.2

Chat Input Height Fix - Textarea now properly resets to original size after submitting questions
Improved user experience with predictable input field sizing
Fixed height reset behavior in chat input component

What's New in 0.6.1

S3 File Content Route Fix - Improved reliability and safety for S3 text file retrieval
Added 50MB file size limit to prevent memory issues
Fixed route path structure for proper parameter handling
Better error handling for oversized files

What's New in 0.6.0

S3 File Access for Web Components - New getS3TextFileContent() method enables secure retrieval of text files from the Pika S3 bucket
No AWS credential management required for web components
Perfect for loading configuration files, data files, or dynamic content
Comprehensive documentation with examples

How Releases Work

Version Numbering (0.x.x)

While Pika is pre-1.0, we use:

0.x.0 - Breaking changes or significant new features
0.x.y - Bug fixes and minor improvements

Once we reach 1.0, we'll follow strict semantic versioning.

Release Frequency

Breaking changes: Released promptly with migration guides
New features: Batched when ready (typically every 2-4 weeks)
Bug fixes: Released as needed

What You Get

Each release includes:

Changelog - Detailed list of changes
Migration guides - Step-by-step instructions for breaking changes
Version metadata - Tracked in your .pika-sync.json
Automatic sync support - pika sync handles updates intelligently

Sync Your Project

Update to the latest version:

# See what will change
pika sync --dry-run

# View detailed diffs
pika sync --diff

# Apply updates
pika sync

The sync command will:

Check your current version
Download the latest framework
Show you what's changed
Warn about breaking changes
Preserve your customizations
Apply updates safely

Breaking Changes

When breaking changes are introduced:

Automatic detection - pika sync will detect breaking changes
Block sync - Won't proceed without acknowledgment
Clear guidance - Links to migration guides
Manual steps - Detailed instructions for required changes

Version History

Version	Date	Type	Summary
0.15.4	Nov 4 2025	Patch	Opensearch type issue fix
0.15.3	Nov 4 2025	Patch	Cost distribution charts and auto insights fix
0.15.2	Nov 3 2025	Patch	Analytics tool flushing issue fix
0.15.1	Nov 3 2025	Patch	Backfill tool robustness and performance fixes
0.15.0	Nov 3 2025	Breaking	Message-level analytics and content search
0.14.2	Nov 2 2025	Patch	Admin site session insights improvements
0.14.1	Nov 1 2025	Patch	Bedrock inference profile stack tag type fix
0.14.0	Nov 1 2025	Feature	Component-level tagging for granular cost tracking
0.13.0	Oct 31 2025	Feature	Inference profile cost tracking and AWS resource tagging
0.12.0	Oct 31 2025	Feature	Entity method addition and analytics UI improvements
0.11.3	Oct 30 2025	Patch	pika-cli sync improvements and minor fixes
0.11.2	Oct 30 2025	Patch	CI/CD pipeline lockfile sync fix
0.11.1	Oct 30 2025	Patch	Type safety improvements in site admin pages
0.11.0	Oct 30 2025	Breaking	Session analytics and widget metadata system
0.10.0	Oct 28 2025	Feature	Context-aware widgets and dynamic spotlight
0.9.0	Oct 27 2025	Feature	Complete documentation site overhaul
0.8.0	Oct 24 2025	Feature	Widget instance registry with DOM tracking
0.7.0	Oct 24 2025	Feature	Web component initialization enhancement
0.6.2	Oct 22 2025	Patch	Chat input height fix
0.6.1	Oct 21 2025	Patch	S3 file content route fixes
0.6.0	Oct 21 2025	Feature	S3 file access for web components
0.5.2	Oct 21 2025	Patch	Instruction augmentation fixes
0.5.1	Oct 21 2025	Patch	Session source field fix
0.5.0	Oct 21 2025	Breaking	Tag system refactor + Chat session GSI update
0.4.0	Oct 20 2025	Stable	Initial tracked release

Learn More

Full Changelog - Complete version history
Migration Guides - Step-by-step upgrade instructions
Sync System - How syncing works

Stay Informed

Keep your project updated:

# Check for updates regularly
pika sync --dry-run

Questions?

Not sure if you should upgrade? Check the changelog for your version
Breaking change coming? Migration guides provide complete instructions
Sync issues? See Troubleshooting