1. Adds v2 model configuration with label-based model selection, enabling optimization and subgraph model usage in the future. (#50367)
2. Adds session_ids JWT claim enforcement across all AIAv2 REST API endpoints. (#50699)
3. Updates the @langchain/anthropic dependency to improve token limit handling. (#50692)
4. Fixes an issue where tasks running for more than 60 seconds could end up in an inconsistent state. (#50895)

1. Fixes an issue where the PGSSL environment variable was ignored, causing connection failures to SSL-required PostgreSQL databases. (#50374)

1. Fixes CVE-2025-66414 and CVE-2026-0621 vulnerabilities. (#50315)
2. Fixes an OpenAI model issue when multiple tool calls are made in parallel. (#50316)

1. Introduces AI Assistant v2, supporting agents with tool use and reasoning traces.
2. Improves system prompt guards to prevent malicious attacks and prompt injections. (#49600)
3. Updates langgraph, langchain, and zod dependencies. (#49509)
4. Fixes a batch size issue when embedding large documents using OpenAI models. (#50159)
5. Fixes a bug in which the AI assistant was unable to provide summaries. (J#AI-283)
6. Fixes duplicate human messages being appended to requests. (#49622)
7. Fixes feature enablement in evaluation mode for all features. (#49408)

- Adds support for password-protected PDFs to AI Assistant. (J#AI-28)

- Improves database configuration by only requiring the DATABASE_URL environment variable. (#48886)

- Changes handling of the empty document_ids array in JWT claims so that it restricts access to no documents instead of all documents. (#49082)

- Improves ordinal page references in redaction queries. (#48367)

- Fixes an issue ingesting documents when they contain no changing or permanent IDs. (#48503)

- Fixes an issue where models without temperature support fail to initialize. (#48496)

1. Adds support for generating answers using information from multiple documents. (J#AI-173)
2. Improves Document Comparison category hits, avoiding some uncategorized changes. (#47978)
3. Improves document retrieval through chunking documents by paragraphs, tables, and key-value pairs. (J#AI-184)
4. Fixes an issue where rate limiting may not work correctly in some scenarios. (J#AI-209)
5. Fixes an issue where the rate limiting error message may incorrectly refer to 'messages per day', even when you configure a different time period. (J#AI-200)

1. Improves case insensitivity when identifying redaction terms. (#47440)
2. Improves ingestion performance for all documents. (#47650)
3. Improves the size of the Docker image by optimizing its internal structure. (J#AI-181)
4. Improves document retrieval across single- and multi-document queries. (#47583)
5. Fixes bundle ID checking for origin checks from iOS. (#47784)
6. Fixes an error message about an invalid document index if multiple documents are ingested simultaneously. (J#AI-191)
7. Fixes an issue that may happen when ingesting a document with multiple layers from Document Engine. (J#AIA-178)

1. Adds AI-powered text comparison. (J#AI-171)
2. Improves term detection in redaction when content is short. (#47404)
3. Improves term detection in the redaction agent. (J#AI-149)
4. Optimizes the loading of documents from Document Engine by avoiding unnecessary ingestions. (J#AI-163)

1. AI Assistant no longer requires Document Engine to function and can now be used by other Nutrient SDKs, including the Web SDK. (J#AI-75)
2. Adds a new CONFIG_DIR environment variable which states where the service-config.yml is located in the container. (J#AI-119)
3. Adds new Server API to ingest documents from Document Engine. (J#AI-110)
4. Improves REST API error messages by including detailed information about failing paths. (#46262)
5. Improves the redaction workflow by interpreting natural language page range instructions and prompting follow-up actions for clarification when page ranges are unspecified. (J#AI-81)
6. Fixes CVE-2024-21538 by removing external dependency on express-requests-logger. (J#AI-108)
7. Fixes an issue where the document IDs of some documents may be incorrectly truncated. (J#AI-123)
8. Fixes an issue where uploading documents with lots of pages may fail unexpectedly. (J#AI-128)

1. Fixes OpenAI-compatible model-provider usage when no API key was set. (#45928)

1. Adds a check at startup to ensure requested models are accessible. (J#AI-80)
2. Adds support for AWS Bedrock as a model provider. (J#AI-80)
3. Adds support for OpenAI API-compatible model providers. (J#AI-80)
4. Adds support for embedding models of any dimension size. (J#AI-80)
5. Improves the routing mechanism to better identify user intent. (#45716)
6. Fixes an issue with suggested questions by relaxing the required question count. (#45715)

1. Release of 1.0.0.