Spice v2.0-stable (Jun 5, 2026)

June 5, 2026 · 94 min read

Co-Founder and CTO of Spice AI

53 releases since Spice 1.0-stable, Spice.ai OSS has reached the 2.0-stable milestone! 🎉

Spice v2.0.0 is the next major release of Spice and a major milestone in the project's development, advancing Spice from a single-node engine into a distributed data and query platform built for enterprise AI agents. These agents need low-latency, governed access to data spread across many production systems, and because they generate their own queries autonomously, that access has to be sandboxed, observable, and able to absorb occasional heavy analytical queries without overwhelming the underlying systems. The release is headlined by multi-node distributed query, now generally available — multi-active, highly-available, and object-store-native, built on Apache Ballista — distributing both query execution and ingestion across executors with data-local routing and per-executor statistics for distributed join planning. Alongside it, the Spice Cayenne data accelerator is generally available, built on the Vortex compressed columnar format, with a high-throughput CDC write path, MERGE INTO, SQL-defined partitioning, inline writes, a dedicated compaction runtime, and write-path statistics for distributed join sizing. The engine also moves to DataFusion v52 with sort pushdown, a rewritten merge join, and dynamic filters, and the Spice CLI is rewritten in Rust as a single self-contained binary.

v2.0 also expands real-time and write-path capabilities across the platform: native CDC from MongoDB Change Streams and PostgreSQL WAL logical replication, durable Kafka CDC offsets, DML write-back for PostgreSQL, Snowflake, DynamoDB, Arrow, and DuckLake, DDL and MERGE INTO for Iceberg catalogs, mutual TLS across server endpoints and outbound connectors, HashiCorp Vault and Azure Key Vault secret stores, user-defined functions, hybrid search with Elasticsearch and DuckDB HNSW vector indexes, provider-aware LLM prompt caching, and the Responses API across all model providers.

Highlights in v2.0.0 include:

Spice Cayenne (GA) — generally available on the Vortex compressed columnar format, with WAL-staged writes, inline low-latency writes, fast-path CDC deletes, merge-on-read position deletes, composite & SQL-defined partitioning, MERGE INTO, dedicated compaction runtime, and join-sizing statistics maintained on the write path
Multi-Active HA Distributed Query (GA) — multi-node distributed query built on Apache Ballista, with object-store-native clustering, dynamic cluster sizing, distributed ingestion, data-local query routing, per-executor table statistics for distributed join planning, and async queries via /v1/queries
Mutual TLS (mTLS) — public mTLS for HTTP and Flight, TLS cert hot-reload, and mTLS client certificates for FlightSQL and Spice.ai connectors
Enterprise Authentication & Authorization — OIDC bearer-token verification and Cedar-based authorization policy with per-principal row- and column-level filtering
New Secret Stores — HashiCorp Vault and Azure Key Vault
CDC Sources — native MongoDB Change Streams, PostgreSQL WAL logical replication, and durable Kafka CDC offsets — no Debezium or Kafka middleware required
DML & DDL — INSERT/UPDATE/DELETE write-back for PostgreSQL, Snowflake, DynamoDB, and Arrow; CREATE TABLE/DROP TABLE and MERGE INTO for Iceberg catalogs
User-Defined Functions — SQL UDFs in spicepods, remote UDFs over HTTP, and optional geospatial ST_* UDFs
On-Demand Dataset Loading & Unified Query Cancellation — faster startup and end-to-end cancellation across HTTP, Flight, FlightSQL, and MCP
Dynamic HTTP Connector — OAuth2 refresh tokens, pagination, dynamic headers, subquery-driven parameters, and rate-control state persisted across restarts
Storage-Profile Accelerator Tuning & refresh_mode: snapshot — storage-aware acceleration defaults and point-in-time snapshot acceleration
Search & Vectors — Elasticsearch data connector with native hybrid search, DuckDB HNSW vector engine with a statically linked VSS extension, multi-vector MaxSim embeddings, and a rerank() UDTF
AI & LLM — provider-aware prompt caching, Responses API across all providers, MCP Streamable HTTP transport, and a searchable LLM tool registry
New Data Connectors — Elasticsearch (Alpha), GCS (Alpha), Azure Cosmos DB (Alpha), Git (RC), ADBC, DuckLake (Beta), and catalog connectors for PostgreSQL, MySQL, MSSQL, and Snowflake
Rust CLI — single-binary spice CLI with spice query async REPL, shell completions, and --output=json
Dependency upgrades including DataFusion v52.5, DuckDB v1.5.3, Arrow v57.2, iceberg-rust v0.9.1, Turso v0.6.1, and Vortex v0.69

Spice v2.0 includes several breaking changes. Review the breaking changes section before upgrading.

Distribution Changes

AI/ML support including local LLM/ML model and hosted LLM inference is now included in the default Spice build and image. The separate models build variant has been removed.

With models now included by default, the data-only distribution (without AI/ML support) is only published in nightly builds. Official production-ready data-only distributions are available exclusively through Spice Cloud and the Enterprise release.

A new Network Attached Storage (NAS) distribution with built-in SMB and NFS data connector support is also available in nightly builds and with Spice.ai Enterprise.

Distribution / Variant	Open Source	Spice Cloud	Enterprise
Default	✅	✅	✅
Data	Nightly only	✅	✅
NAS (SMB + NFS)	Nightly only	❌	✅
Metal (macOS)	✅	✅	✅
CUDA (Linux)	Nightly only	✅	✅
Allocator variants	Nightly only	✅	✅
ODBC connector	Local build only	✅	✅

Native Windows builds are no longer provided; use WSL for local development. For more details, see the Distributions documentation.

What's New in v2.0.0

Spice Cayenne Reaches General Availability

The Spice Cayenne data accelerator is generally available in v2.0, with a major focus across the release candidates on write-path throughput, correctness, and distributed operation.

Write path & ingest:

Staged Append Writes: WAL-based staged append writes prevent partial writes and data loss on stream errors — batches commit atomically.
Inline Writes: Small writes are serialized as Arrow IPC and committed directly into the Cayenne metastore, bypassing the staged Vortex write path for low-latency ingest. Inline upserts atomically rewrite existing inline rows, inline data stays query-visible via an in-memory union scan, and rows are checkpointed to Vortex when thresholds are reached. Inline writes now also proceed with pending deletions in flight, and inline flush caps scale with available memory and storage class.
Fast-Path CDC Deletes: DELETE statements whose filters identify primary keys directly — including composite keys expressed as (k1, k2) IN ((...), (...)) — skip the table scan entirely.
Merge-On-Read Position Deletes: Primary-key upsert tables use position deletes with memory-pool accounting, avoiding full-table rewrites on update-heavy workloads.
Resident Upsert Keysets: CDC upsert primary-key keysets stay resident between batches, avoiding per-batch full-table rebuilds.
CDC Sub-Batch Efficiency: Interleaved upsert/delete workloads produce fewer sub-batch splits, with last-write-wins deduplication applied within batches.
Dedicated Compaction Runtime: Background compaction runs on a dedicated thread pool with CDC pipelining and protected snapshots, isolating compaction work from query and ingest paths.

Query & planning:

Join Filter Propagation: Filters propagate across equi-join keys, with range fallback for large join filters and IN-list rewrites.
Write-Path Join-Sizing Statistics: Cayenne maintains live row counts and HyperLogLog-based distinct-value estimates on the write path, so distributed JoinSelection can correctly size joins without rescans.
Scan-Result Cache: A new scan-result cache accelerates hot reads, with parallel Vortex partition writes and lock-free deletion caches with bloom-prefiltered probes.

SQL & catalog:

MERGE INTO: Upsert-style MERGE INTO for Cayenne catalog tables, distributed across executors in cluster mode.
PARTITION BY in SQL: Define partitioning directly in CREATE TABLE ... PARTITION BY (...); metadata is persisted in the catalog and survives restarts.
Composite Partitioning: partition_by: [col1, col2] with hierarchical path-like keys.
File-Based Retention Deletes: Time-based retention uses file-level deletes for both position-based and primary-key tables.

Correctness: Synchronized partition commits, correct NULL-sentinel handling for nullable partition expressions, tombstoned inline-checkpointed rows on upsert (preventing duplicate primary keys), and live reads through expired protected snapshots.

Multi-Active HA Distributed Query (GA)

Spice.ai Enterprise feature. See High Availability.

Distributed Query is generally available. Built on Apache Ballista, it distributes query execution across multiple active executor nodes with no single point of failure, reading directly from object storage rather than relying on a central cluster.

Distributed query supports two execution modes:

Synchronous: Queries for accelerated datasets are distributed across executors and results stream back in real-time — best for interactive, latency-sensitive queries.
Asynchronous: Queries submitted via the HTTP /v1/queries API materialize results to object storage for later retrieval — best for long-running analytical and batch workloads.

Key capabilities:

Dynamic Cluster Sizing: The planner adjusts parallelism to the number of active executors as nodes join or leave.
Distributed Ingestion: Ingestion for partitioned accelerated tables is distributed across executors, with partition-aware write-through splitting scheduler-side Flight DoPut writes to the responsible executors.
Data-Local Query Routing: Cayenne catalog queries route to the executors holding the relevant partitions.
Per-Executor Table Statistics: Executors report table statistics — including NDV-aware estimates — so distributed JoinSelection can size joins correctly, fixing out-of-memory conditions on large semi-joins.
Readiness & Failure Detection: /v1/ready gates on a configurable executor quorum for safe rolling deployments; scheduler readiness additionally waits for executor partition loads; executor heartbeat timeout reduced from 180s to 30s.
Distributed DML & DDL: UPDATE/DELETE forwarding to all executors, executor DDL sync for late joiners, and distributed MERGE INTO.
Cluster Observability: New cluster metrics (including scheduler_active_executors_count), distributed runtime.task_history replication, and a Grafana dashboard.
Ballista S3 Shuffle: Async queries with runtime.params.shuffle_location: s3://... complete reliably with executor-environment-derived S3 clients.

Security: Mutual TLS, Secret Stores, and Hardening

Several capabilities in this section are Spice.ai Enterprise features. See Enterprise Security.

Mutual TLS across the platform:

Public mTLS for HTTP and Flight: client_auth_mode: request (optional, for migration windows) or required (strict) client-certificate verification.
TLS Cert Hot-Reload: The runtime reloads TLS certificates on SIGHUP for zero-downtime rotation.
Outbound mTLS Client Certificates: FlightSQL and Spice.ai data connectors present client certificates to upstream services; the spice sql REPL supports mTLS client auth.

runtime:
  tls:
    enabled: true
    certificate_file: /etc/spice/tls/server.crt
    key_file: /etc/spice/tls/server.key
    client_auth_mode: required
    client_auth_ca_file: /etc/spice/tls/client-ca.crt

Authentication & Authorization (Spice.ai Enterprise):

OIDC Authentication: Validate OIDC bearer tokens (JWTs) issued by enterprise identity providers — Microsoft Entra ID, Okta, Auth0, AWS Cognito, and Google — for secure access to runtime endpoints, standalone or combined with API keys.
Principal-Based Policy Enforcement: Fine-grained, Cedar-based authorization policy configured under runtime.authorization governs allow/deny access across datasets, models, tools, and endpoints. Combined with identity SQL functions (current_principal(), current_principal_email(), current_principal_groups()), policies enforce per-principal row-level filtering and column masking.

New Secret Stores: HashiCorp Vault (KV v1/v2; token, approle, kubernetes, and jwt auth with automatic lease renewal) and Azure Key Vault (service principal, managed identity, workload identity, Azure CLI, or auto-detect; sovereign cloud support).

Hardening:

Read-only API Key Enforcement on the Flight DoGet path and async query endpoints.
Per-Principal Cache Namespacing: SQL, search, and caching-accelerator caches are namespaced per authenticated principal so cached results never cross identity boundaries.
API Key Timing Leak & Remote-UDF SSRF: Closed a timing-based position-disclosure leak in API key comparison and blocked SSRF via remote UDF endpoints.
Snowflake Function Deny-List: A function deny-list is enforced in Snowflake federation pushdown, and Snowflake account identifiers and auth configuration are validated at startup.
MCP allowed_hosts: MCP servers can be restricted to an explicit allowlist of upstream hosts.

Change Data Capture (CDC) Sources

See Change Data Capture (CDC) for an overview of CDC in Spice.

MongoDB Change Streams: MongoDB datasets with refresh_mode: changes stream changes natively into any local accelerator — no Debezium or Kafka required.
PostgreSQL Native Replication (WAL): PostgreSQL datasets stream INSERT/UPDATE/DELETE directly from logical replication using pgoutput decoding, with automatic per-replica slot management, an initial REPEATABLE READ bootstrap snapshot, and durable LSN acknowledgement.
Kafka CDC Offset Persistence: Kafka CDC offsets persist in sidecar tables for durable, resumable streams across restarts and failovers.
Pipelined CDC Ingestion: Source reads overlap with batch apply, with envelope coalescing and improved nullability propagation.
Debezium Schema Evolution: Schema changes in Debezium-sourced datasets no longer break dataset initialization on reload.

datasets:
  - from: postgres:my_table
    name: my_table
    params:
      pg_host: localhost
      pg_db: mydb
    acceleration:
      enabled: true
      engine: duckdb
      refresh_mode: changes

DML, DDL, and Write-Back

Spice v2.0 turns more connectors and catalogs into full read/write tables:

PostgreSQL DML: INSERT, UPDATE, and DELETE write-back on PostgreSQL datasets, with foreign-key metadata exposed via the PostgreSQL catalog connector.
Snowflake DML: INSERT, UPDATE, and DELETE write-back on Snowflake datasets.
DynamoDB DML: INSERT, UPDATE, and DELETE for DynamoDB, complementing read and CDC streaming.
Arrow Primary Key Upserts: Native update-or-insert semantics for in-memory Arrow-accelerated tables.
DDL for Iceberg: CREATE TABLE and DROP TABLE via FlightSQL and /v1/sql for Iceberg, with catalog.access: read_write_create.
DuckLake INSERT: DuckLake catalog tables with read_write access support INSERT.

SQL & User-Defined Functions

See the SQL Reference for the full SQL surface area.

User-Defined Functions: Define reusable SQL UDFs as first-class spicepod components, or invoke remote functions over HTTP (Spice.ai Enterprise), plus table user functions.
Spatial SQL UDFs: Optional geospatial ST_* UDFs for geometry workloads.
JSON UDTFs: flatten_json, json_tree, and flatten_json_properties table-valued functions for JSON transformation and schema decomposition (with options such as expand_maps). See JSON Functions and Operators.
PostgreSQL Metadata UDFs: Dataset and column descriptions are exposed via PostgreSQL-compatible UDFs (obj_description, col_description), so BI tools and psql surface Spice metadata.
FlightSQL Substrait Plans: CommandStatementSubstraitPlan support for clients submitting Substrait-encoded plans.
SQL REPL Expanded View: Toggle \x for a vertical key-value layout on wide result sets.
Prepared statement, federation, and unparsing fixes across the engine, including keeping correlated subqueries out of JOIN ON conditions for Spice Cloud federation and correct EXISTS/NOT EXISTS subquery handling in the federation analyzer.

Runtime Features

On-Demand Dataset Loading: Datasets can be deferred — registered with a declared schema at startup (columns[].type, columns[].nullable) and fully resolved on first reference, reducing startup time and memory for large spicepods.
Unified Query Cancellation: HTTP, Flight, FlightSQL, MCP, and internal execution paths honour a unified cancellation signal — disconnects, REPL Ctrl-C, and cancelled HTTP requests cancel the query end-to-end.
Storage-Profile Accelerator Tuning: acceleration.storage_profile (auto, local_ssd, ebs, tmpfs) applies storage-aware defaults across DuckDB, SQLite, Turso, and Cayenne file-mode accelerators; auto detects the backing storage.
refresh_mode: snapshot (Spice.ai Enterprise): Point-in-time snapshot acceleration with SQLite/Turso WAL flushing and Cayenne metastore slice integration, now reporting accurate readiness when no snapshot exists yet.
Structured Component Errors: /v1/datasets?status=true and /v1/models?status=true return structured error objects (category, type, code) and human-readable error_message fields; the CLI shows an ERROR column.
Actionable Config Errors: Parameter typos, missing secret references, and unknown engine names produce specific, actionable errors with suggestions.

Spicepod v2

Spicepods now support version: v2, the default for spice init, while v1 spicepods continue to work with automatic migration of deprecated fields.

Version	Status
`v2`	Default. Used by `spice init`.
`v1`	Supported. Deprecated fields auto-migrate.
`v1beta1`	Removed. No longer accepted.

v1 (deprecated)	v2 (preferred)	Notes
`runtime.results_cache`	`runtime.caching.sql_results`	All fields migrate automatically. `cache_max_size` → `max_size`.
`runtime.memory_limit`	`runtime.query.memory_limit`	Auto-migrated. `query.memory_limit` takes priority if both set.
`runtime.temp_directory`	`runtime.query.temp_directory`	Auto-migrated. `query.temp_directory` takes priority if both set.
`dataset.invalid_type_action`	`dataset.unsupported_type_action`	Auto-migrated. v2 adds a new `string` variant.

New v2 fields include runtime.ready_state, runtime.query.spill_compression, runtime.caching.sql_results.stale_while_revalidate_ttl, runtime.caching.sql_results.encoding, scheduler partition-assignment configuration, and catalog.access: read_write_create.

Data Connectors & Catalogs

New connectors:

Elasticsearch (Alpha, Spice.ai Enterprise): Query Elasticsearch indexes as SQL tables with native hybrid search — vector_search() kNN, text_search() BM25, and rrf() fusion — plus Elasticsearch as a backing vector engine, direct FTS engine configuration, and index lifecycle controls.
GCS (Alpha): Federated queries against Google Cloud Storage, with Iceberg table support.
Azure Cosmos DB (Alpha): Read-only NoSQL / Core SQL API connector with cross-partition scans and schema inference.
Git (RC): HTTPS/SSH auth, Git LFS support, and per-repo connection resilience.
ADBC: Data connector and catalog with full query federation, BigQuery support, and schema/table discovery.
DuckLake (Beta): Lakehouse-style data management with DuckDB as the metadata catalog and object storage for data — ACID transactions, time travel, and schema evolution on Parquet.
Self-Hosted Spice Connector: Connect Spice to another self-hosted Spice runtime as a federated source.

New catalog connectors for PostgreSQL, MySQL, MSSQL, and Snowflake, using native metadata catalogs for schema and table discovery. Unity Catalog compatibility extends to OSS Unity Catalog deployments, and DDL-defined catalogs can expose and query views.

HTTP connector: OAuth2 refresh-token authentication, query-parameter and no-limit pagination, dynamic request headers parameterised from query predicates, subquery-driven request parameters for fan-out queries, response metadata as queryable columns, map-to-array conversion, shared and persistent rate-control state across restarts and replicas, no caching of transient 429/5xx errors, and a correctly populated fetched_at column.

JSON ingestion: Single-object documents, JSONL, BOM-prefixed input, Socrata SODA responses, format auto-detection, and RFC 6901 json_pointer extraction of nested payloads.

Databricks: Resilience controls, Unity Catalog-aware permission prechecks with structured advisory errors, Classic SQL Warehouse foreign-table compatibility, connect_timeout/client_timeout parameters, a Databricks SQL dialect for federation, and Delta Lake column mapping (Name and Id modes).

Other connector improvements: MongoDB SRV support; MySQL mysql_zero_date_behavior; Snowflake OBJECT, MAP, GEOGRAPHY, GEOMETRY, VECTOR, and TIMESTAMP_LTZ types plus key-pair auth; ClickHouse Date32; S3 s3_url_style for path-style addressing and faster Parquet reads; GraphQL custom auth headers; Oracle and MSSQL sort/limit pushdown; GitHub GraphQL resilience; and improved Kafka reliability.

AI & LLM

Provider-Aware Prompt Caching: LLM calls automatically use provider-side prompt caching (e.g., Anthropic, OpenAI) for system prompts and tool descriptions, reducing latency and cost.
Responses API Across All Providers: The Responses API works with every configured model provider, including streaming response.output_text.delta events and Authorization: Bearer header support.
Multi-Vector Embeddings with MaxSim: List-of-string columns produce one embedding per element with MaxSim/mean/sum scoring for ColBERT-style late-interaction retrieval, plus a _match column identifying the best-matching element.
rerank() UDTF: Reorder results from vector_search, text_search, or rrf using any registered chat model as a reranker, with automatic query propagation and pushdown support.
Searchable LLM Tool Registry: Agents discover tools via semantic search instead of enumerating every tool in the system prompt.
MCP Improvements: Streamable HTTP transport (/v1/mcp) on rmcp v1.5.0, native auth for streamable HTTP tools (mcp_auth_token, mcp_headers), external MCP server tool calls traced in task history, and configurable allowed_hosts.
Per-Model Rate-Limited AI UDF Execution for controlling concurrent AI function invocations.

Search & Vectors

DuckDB Vector Engine: vector_engine: duckdb uses DuckDB's HNSW index for fast approximate nearest-neighbor search without an external vector store. In v2.0.0, the DuckDB VSS extension is statically linked into the bundled DuckDB, so HNSW vector search works out-of-the-box on clean machines with no extension download. HNSW indexes are preserved across data refresh, and cosine_distance pushes down via array_cosine_distance.
Hybrid Search: Combine kNN vector search and BM25 full-text search with reciprocal rank fusion (rrf()), backed by Tantivy, Elasticsearch, or DuckDB.
Full-Text Search Performance: Significantly faster Tantivy ingestion with rollback-on-error, and search metadata is correctly preserved on indexing and in Vortex physical schema calculation.
Embedding Validation: row_id columns are validated during dataset initialization.

Caching

Improvements across Caching:

Stale-While-Revalidate: runtime.caching.sql_results.stale_while_revalidate_ttl serves stale results while revalidating in the background.
Cache Encoding: Optional compression (e.g., zstd) for SQL results cache entries.
Retention Policies for cached query results, and improved CDC-driven cache invalidation (including view plan invalidation on updates).
Idle Cache Maintenance: Periodic maintenance drains invalidation predicates on idle caches, fixing unbounded memory growth in rarely-read caches.

Performance & Query Engine

Apache DataFusion is upgraded to v52.5 over the course of the release cycle, bringing:

Sort Pushdown to Scans: ~30x faster top-K queries on pre-sorted data; Parquet scans reverse row-group order for DESC on ASC-sorted files.
Rewritten Sort-Merge Join: Up to three orders of magnitude faster in pathological cases (e.g., TPC-H Q21: minutes → milliseconds).
Dynamic Filters: MIN/MAX aggregates and hash-join build sides prune files, row groups, and rows during execution.
Faster CASE Expressions, statistics caching, and prefix-aware list-files caching for faster planning.
TableProvider DELETE/UPDATE hooks and the RelationPlanner API for extensible SQL planning.
Strict Overflow Handling: try_cast_to errors on overflow instead of silently producing NULLs.

Additional engine work: default query memory limit raised from 70% to 90% with GreedyMemoryPool, partial aggregation optimization for FlightSQLExec, improved partitioned query planning, and metastore transaction support to prevent concurrent conflicts.

Rust CLI

The Spice CLI is completely rewritten from Go to Rust — a single spice binary built from the same codebase as spiced, with full feature parity across 27+ commands.

spice query: Interactive REPL for async queries with multi-line SQL, progress indication, and cancellation.
spice dataset configure: Non-interactive flag-based configuration (--from, --description, --param KEY=VALUE, --set) alongside interactive prompts.
spice completions: Shell completion script generation.
--output=json: Machine-readable output for scripting; spice login --output adds env, json, and keychain modes.
spice init writes a yaml-language-server schema directive for IDE completions.

Observability

OpenTelemetry: Exporter fixes, authenticated metrics export, configurable metric name prefix (runtime.telemetry.metric_prefix), delta temporality by default, and OTLP resource attributes via runtime.telemetry.properties.
Query Metrics: The query_executions metric gains a datasets dimension for per-dataset query attribution.
Ingestion Metrics: rows_written, bytes_written, and dataset_acceleration_size_bytes for acceleration refresh and Flight DoPut/ADBC ingestion, and EXPLAIN ANALYZE metrics in FlightSQLExec.
Task History: Distributed task history in cluster mode and tracing for external MCP server tool calls.

Notable Bug Fixes

localpod synchronization: localpod child datasets correctly track parent refreshes when the parent uses the in-memory Arrow accelerator.
Spice Cloud federation: Correlated subqueries are kept out of JOIN ON conditions, fixing rejected federated queries.
refresh_mode: snapshot: No longer reports Ready with empty data when no snapshot exists.
Search metadata: Field and schema metadata preserved on search indexing and in Vortex physical schema calculation.
HTTP connector: fetched_at column is correctly populated.
Connector correctness: DynamoDB Streams transient-error retries and typed-NULL DML handling; ScyllaDB physical filter pushdown disabled to fix incorrect results; MSSQL TOP N pushdown; DuckDB DELETE/UPDATE on full and caching refresh modes; Turso checked arithmetic for timestamp conversions; ODBC queries no longer silently return 0 rows on failure; Flight GetFlightInfo/DoGet schema parity.

Dependency Updates

Dependency / Component	Version
DataFusion	v52.5
Ballista	v52
Arrow (arrow-rs)	v57.2
DuckDB	v1.5.3 (with statically linked VSS)
iceberg-rust	v0.9.1
Turso (libsql)	v0.6.1
Vortex	v0.69.0
delta_kernel	v0.18.2
rmcp (MCP)	v1.5.0
mistral.rs	v0.8.x (candle v0.10.1)
ADBC Core	v0.23
Rust toolchain	v1.94.1

Contributors

Breaking Changes

Models included by default: The separate models build variant has been removed. Local LLM inference is always included in the default build and image.
Windows native builds removed: Use WSL for local development.
Spicepod version defaults to v2: spice init creates version: v2 spicepods. v1 remains supported with auto-migration; v1beta1 is no longer accepted.

Flattened runtime.scheduler configuration: The nested runtime.scheduler.partition_management block is flattened and renamed:

# Before
runtime:
  scheduler:
    partition_management:
      interval: 30s
      max_assignments_per_cycle: 16
      discovery_timeout: 10s

# After
runtime:
  scheduler:
    partition_assignment_interval: 30s
    max_assignments_per_interval: 16
    partition_discovery_timeout: 10s

S3 metadata columns renamed: location, last_modified, size → _location, _last_modified, _size.
Default query memory limit changed: Increased from 70% to 90%.
Metric renames: accelerated_refresh metrics renamed to acceleration_refresh; last_refresh_time gauge renamed to include the milliseconds unit.
DuckDB parameter rename: partitioned_write_flush_threshold → partitioned_write_flush_threshold_rows.
/v1/search API: Always returns an array in matches, even for single results.
/v1/evals API removed.
Perplexity model provider removed.
x.ai model endpoint: x.ai models exclusively use the /v1/responses endpoint.

Upgrade Guide from v1.x

Most v1 spicepods continue to work on v2.0 — v1 remains supported and deprecated fields auto-migrate at load time — so many deployments can upgrade by updating the binary or image alone. The steps below cover the breaking changes that may require manual action. Review each before upgrading a production deployment.

1. Build, image, and platform changes

Models are now included by default. The separate models build variant (and the corresponding -models image tags) has been removed; local LLM inference is always included in the default build and image. If your deployment pinned a models build or -models-tagged image, switch to the default build/image.
Native Windows builds are removed. Use WSL for local Windows development.

2. Adopt Spicepod `v2` (recommended)

spice init now creates version: v2 spicepods. v1 spicepods remain supported with automatic migration, but v1beta1 is no longer accepted. To move to v2, set version: v2 and update the following fields — each auto-migrates from v1, but updating now clears the deprecation:

v1 (deprecated)	v2 (preferred)
`runtime.results_cache`	`runtime.caching.sql_results` (`cache_max_size` → `max_size`)
`runtime.memory_limit`	`runtime.query.memory_limit`
`runtime.temp_directory`	`runtime.query.temp_directory`
`dataset.invalid_type_action`	`dataset.unsupported_type_action`

3. Update changed configuration

DuckDB parameter rename: partitioned_write_flush_threshold → partitioned_write_flush_threshold_rows.
Default query memory limit raised from 70% to 90%. If you relied on the previous default to leave headroom for other processes on the host, set it explicitly via runtime.query.memory_limit.

4. Update queries and API clients

S3 metadata columns renamed: location, last_modified, size → _location, _last_modified, _size. Update any queries that reference these columns.
/v1/search always returns an array in matches, even for a single result. Update clients that assumed a scalar value.
/v1/evals API removed. Remove integrations that depend on it.

5. Update model providers

Perplexity model provider removed. Re-point affected models to another provider.
x.ai models use the /v1/responses endpoint exclusively. Ensure x.ai integrations target the Responses API.

6. Update observability

Metric renames: accelerated_refresh → acceleration_refresh, and the last_refresh_time gauge is renamed to include the milliseconds unit. Update dashboards and alerts that reference these metric names.

After updating, restart the runtime and verify datasets and models report ready via /v1/datasets?status=true and /v1/models?status=true (the CLI shows a Ready/ERROR column).

Cookbook Updates

New Spice Cookbook recipes added during the v2.0 release cycle:

Async Queries: Submit long-running queries asynchronously and retrieve results later.
DuckLake Catalog: Lakehouse-style data management with ACID transactions and time travel.
Distributed Query: Run Spice in multi-active distributed cluster mode.
mTLS: Mutual TLS for HTTP and Flight endpoints.
Elasticsearch Connector: Query Elasticsearch indexes as SQL tables.
MCP Server: Use Spice as an MCP server over Streamable HTTP.
Snowflake DML: Write-back to Snowflake with INSERT/UPDATE/DELETE.
PostgreSQL, MySQL, and MSSQL Catalogs: Schema and table discovery for external databases.
Full-Text Search: BM25 full-text search over accelerated datasets.

The Spice Cookbook includes more than 100 recipes to help you get started with Spice quickly and easily.

Upgrading

To upgrade to v2.0.0, use one of the following methods:

CLI:

spice upgrade

Homebrew:

brew upgrade spiceai/spiceai/spice

Docker:

Pull the spiceai/spiceai:2.0.0 image:

docker pull spiceai/spiceai:2.0.0

For available tags, see DockerHub.

Helm:

helm repo update
helm upgrade spiceai spiceai/spiceai --version 2.0.0

AWS Marketplace:

Spice is available in the AWS Marketplace.

What's Changed

Changelog

Add TPC-DS integration tests with S3 source and PostgreSQL acceleration by @phillipleblanc in #9006
fix(tests): fix flaky/slow/failing unit tests by @phillipleblanc in #9009
fix: Update benchmark snapshots for DF51 upgrade by @app/github-actions in #9008
fix: add feature gate to rrf TEST_EMBEDDING_MODEL by @phillipleblanc in #9017
fix: features check by @phillipleblanc in #9014
fix: Enable Cayenne acceleration snapshots by @lukekim in #9020
URL table support by @lukekim in #9018
ScyllaDB key filter by @lukekim in #8997
fix: Schema mismatch when using column projection with HTTP caching by @phillipleblanc in #9021
Add more tests for HTTP caching with columns selection by @sgrebnov in #9025
HTTP cache snapshots: default to time_interval and fix snapshots_creation_policy: on_change by @sgrebnov in #9026
Fix duplicate snapshot creation on startup by @sgrebnov in #9029
Add ScyllaDB and SMB to the README table by @krinart in #9034
Remove waiting for runtime to be ready before creating snapshot by @krinart in #9033
Fix snapshot on_change policy to skip when no writes occurred by @sgrebnov in #9028
Release notes for release release/1.11.0-rc.2 by @krinart in #9016
ci: use arduino/setup-protoc for official protobuf compiler by @phillipleblanc in #9036
ci: install unzip on aarch64 runner for arduino/setup-protoc by @phillipleblanc in #9038
fix: don't fail release if upload to minio fails by @phillipleblanc in #9039
Add missing protoc step to setup-cc action by @krinart in #9041
fix: Update Search integration test snapshots by @app/github-actions in #9013
Fix formula_1 and codebase_community in bird-bench by @Jeadie in #9000
Cayenne S3 Express One Zone improvements by @lukekim in #9015
Add zlib1g-dev to CI by @lukekim in #9052
Improve validation and logging for hash indexes by @lukekim in #9047
Upgrade Vortex with CASE-WHEN by @lukekim in #9051
x.ai models now exclusively use /v1/responses endpoint by @lukekim in #9400
Improvements for snapshot schema comparison by @krinart in #9401
v2.0 breaking changes by @lukekim in #9233
Create PartitionManagementTask for scheduler to update accelerated table partition assignments by @Jeadie in #9378
refactor(Cayenne): route all write orchestration through CayenneDataSink by @sgrebnov in #9402
Refactor benchmark to use QueryExecutor trait by @Jeadie in #9418
feat: Add spidapter build and release workflow by @peasee in #9427
Testoperator: add support for api-key when connecting to external spice instance by @sgrebnov in #9421
Initial implementation of Ducklake catalog & data connectors by @lukekim in #9083
Require aws_lc_rs since jsonwebtoken upgrade by @Jeadie in #9426
feat: Add spidapter tool by @peasee in #9425
Add release notes for 1.11.2 patch release by @sgrebnov in #9430
feat(spidapter): integrate system-adapter-protocol with SCP provisioning by @phillipleblanc in #9434
Add DuckLake TPCH E2E workflow and federated Spicepod configuration by @lukekim in #9431
fix(spidapter): use Flight handshake auth instead of x-api-key header by @phillipleblanc in #9435
[spidapter] Keep only what sparks joy by @Jeadie in #9439
Refactor binary operator balancing by @Jeadie in #9424
feat: Add Iceberg DDL support (CREATE TABLE / DROP TABLE) for default catalog override by @phillipleblanc in #9440
Fix Flight SQL schema consistency: expand view types and verify field names by @sgrebnov in #9438
Update spidapter for new system-adapter-protocol by @sgrebnov in #9442
docs: fix typos and syntax errors in style guide and error handling docs by @cluster2600 in #9445
Add acceleration refresh ingestion metrics (rows_written, bytes_written) by @phillipleblanc in #9461
Refactor(Cayenne): Replace CatalogError and string based errors with Snafu errors by @sgrebnov in #9403
Replace deprecated claude-3-5-haiku-latest with claude-haiku-4-5 by @Jeadie in #9492
Fix #9481: Preserve schema in results cache for empty query results by @phillipleblanc in #9485
Fix partition by serializing by @Jeadie in #9474
query: reconcile execution stream nullability with logical plan schema by @phillipleblanc in #9486
initial spice-cloud-client crate and spice cloud metrics --app <app-name>. by @Jeadie in #9480
feat: Return dataset error message in datasets API by @peasee in #9487
Spicebench by @lukekim in #9447
build(deps): consolidate dependabot dependency updates by @phillipleblanc in #9504
fix(cluster): route non-partitioned accelerated tables in distributed mode by @phillipleblanc in #9508
Enable core scalar UDFs in refresh SQL by @sgrebnov in #9502
Fix metrics in Spidapter again by @Jeadie in #9497
fix(cluster): tolerate Completed->status propagation race in distributed query handle by @phillipleblanc in #9510
feat: Support distributed ingestion in cayenne catalog by @peasee in #9506
Fix Cayenne duplicate primary keys after DELETE + UPSERT CDC sequences by @krinart in #9494
fix(cluster): rewrite table scans inside subqueries for distributed execution by @phillipleblanc in #9518
fix: Set catalog mode to readwritecreate in spidapter by @peasee in #9519
Upgrade AWS SDK crates & set APN user-agent in AWS SDK credential bridge by @lukekim in #8328
feat(runtime): add runtime ready_state on_registration semantics by @lukekim in #9522
fix: Add spidapter post-setup retries by @peasee in #9526
Make partition discovery more robust and make initialization non-blocking by @sgrebnov in #9499
Make lint-rust-fix support targeted packages and features by @Jeadie in #9511
Handle new Cloud SCP API by @Jeadie in #9532
Refactor and simplify streaming benchmarks by @krinart in #9405
fix: ensure spidapter only increments attempts on failures by @peasee in #9534
feat: Support specifying app resources in spidapter by @peasee in #9536
test(runtime): Spice Cayenne DDL integration test by @lukekim in #9535
fix: Handle schema evolution mismatch errors during data refresh by @lukekim in #9527
fix: resolve clippy lint warnings by @phillipleblanc in #9547
pr-builds --tag <TAG> for build_and_release.yml by @Jeadie in #9507
Add --output flag to spice login with env/json/keychain modes by @Jeadie in #9541
Don't use 'PartitionedTableScanRewrite' in async distributed query by @Jeadie in #9548
feat(spidapter): add local backend mode with single executor by @phillipleblanc in #9531
support chat template in HF by @Jeadie in #9543
fix(cayenne): stream PK retention deletes and run OOM regression in CI by @phillipleblanc in #9533
cayenne: Staged append writes to prevent partial writes and data loss on stream error by @sgrebnov in #9491
AcceleratedTable::scan use FederatedTable::scan when ClusterRole::Scheduler by @Jeadie in #9550
Upgrade to delta-kernel-rs v0.18.2 by @lukekim in #9528
Run cayenne tests as part of PR CI by @sgrebnov in #9554
Upgrade to DataFusion v52.2.0 by @lukekim in #9419
Remove Snapshot Compaction + Add snapshot existence check by @krinart in #9523
Update dependencies by @lukekim in #9566
fix: Update benchmark snapshots by @app/github-actions in #9565
fix: Compare Cayenne table configuration on startup by @peasee in #9529
Make Refresh::refresh_sql more robust to alterations over time. by @Jeadie in #9549
fix: Update datafusion-table-providers dependency to latest revision by @lukekim in #9574
Unset AWS_ENDPOINT_URL when empty by @krinart in #9575
fix: allow BytesProcessedExec repartitioning for unordered input by @lukekim in #9540
Sanitize DataFusion errors by @lukekim in #9530
Add conditional logging for partition assignments by @Jeadie in #9577
use 'properly early exit on SIGTERM' by @Jeadie in #9573
Update datafusion to 52.2.0 by @phillipleblanc in #9582
Ensure we query one and only one partition per request by @Jeadie in #9416
feat: Add support for Spicepod version v2 by @lukekim in #9583
[SpiceDQ] Improve error messages; Avoid race condition on allocate_initial_partitions. by @Jeadie in #9579
Update ballista dependencies to latest 52.0.0 revision by @lukekim in #9581
Fix Databricks spark_connect mode always disabled by @phillipleblanc in #9586
Support partitioning in Arrow accelerator by @Jeadie in #9571
Fix spice query CLI response deserialization by @phillipleblanc in #9588
fix: Update benchmark snapshots by @app/github-actions in #9584
fix: Share RuntimeEnv across Cayenne read/write/delete paths for targeted list_files_cache invalidation by @sgrebnov in #9589
feat: Add file:// state_location support for async queries scheduler by @phillipleblanc in #9590
Update endgame links by @krinart in #9598
ci: fix E2E CLI upgrade test to use latest release for spiced download by @phillipleblanc in #9613
fix(DF): Lazily initialize BatchCoalescer in RepartitionExec to avoid schema type mismatch by @sgrebnov in #9623
feat: Implement catalog connectors for various databases by @lukekim in #9509
Refactor and clean up code across multiple crates by @lukekim in #9620
fix: Improve error handling for distributed mode and state_location configuration by @lukekim in #9611
Properly install postgres in install-postgres action by @krinart in #9629
fix: Use Python venv for schema validation in CI by @phillipleblanc in #9637
Update spicepod.schema.json by @app/github-actions in #9640
Update testoperator dispatch to use release/2.0 branch by @phillipleblanc in #9641
fix: Align CUDA asset names in Dockerfile and install tests with build output by @phillipleblanc in #9639
Fix expect test scripts in E2E Installation AI test by @sgrebnov in #9643
testoperator for partitioned arrow accelerator by @Jeadie in #9635
Remove default 1s refresh_check_interval from spidapter for hive datasets by @phillipleblanc in #9645
Fix scheduler panic and cancel race condition by @phillipleblanc in #9644
Align Spice.ai connector parameter names across catalog/data connectors by @lukekim in #9632
docs: update distribution details and add NAS support in release notes by @lukekim in #9650
Enable postgres-accel in CI builds for benchmarks by @sgrebnov in #9649
perf: Cache Turso metastore connection across operations by @penberg in #9646
Add 'scheduler_state_location' to spidapter by @Jeadie in #9655
Implement Cayenne S3 Express multi-zone live test with data validation by @lukekim in #9631
chore(spidapter): bump default memory limit from 8Gi to 32Gi by @phillipleblanc in #9661
perf: Use prepare_cached() in Turso and SQLite metastore backends by @penberg in #9662
Improve CDC cache invalidation by @krinart in #9651
Refactor Cayenne IDs to use UUIDv7 strings by @lukekim in #9667
fix: add liveness check for dead executors in partition routing by @Jeadie in #9657
fix(s3): Fix metadata column schema mismatches in projected queries by @sgrebnov in #9664
s3_metadata_columns tests: include test for location outside table prefix by @sgrebnov in #9676
docs: Update DuckDB, GCS, Git connector and Cayenne documentation by @lukekim in #9671
Add s3_url_style support for S3 connector URL addressing by @phillipleblanc in #9642
Consolidate E2E workflows and require WSL for Windows runtime by @lukekim in #9660
Upgrade to Rust v1.93.1 by @lukekim in #9669
Security fixes and improvements by @lukekim in #9666
feat(flight): add DoPut rows/bytes written metrics for DoPut ETL ingestion tracking by @phillipleblanc in #9663
Skip caching http error response + add response_headers by @krinart in #9670
refactor: Remove v1/evals functionality by @Jeadie in #9420
Make a test harness for Distributed Spice integration tests by @Jeadie in #9615
Enable on_zero_results: use_source for views by @krinart in #9699
fix(spidapter): Lower memory limit, passthrough AWS secrets, override flight URL by @peasee in #9704
Show an error on a shared acceleration file with snapshots enabled by @krinart in #9698
Fixes for anthropic by @Jeadie in #9707
Use max_partitions_per_executor in allocate_initial_partitions by @Jeadie in #9659
[SpiceDQ] Accelerations must have partition key by @Jeadie in #9711
Upgrade to Turso v0.5 by @lukekim in #9628
feat: Rename metadata columns to _location, _last_modified, _size by @phillipleblanc in #9712
fix: bump datafusion-ballista to fix BatchCoalescer schema mismatch panic by @phillipleblanc in #9716
fix: Ensure Cayenne respects target file size by @peasee in #9730
refactor: Make DDL preprocessing generic from Iceberg DDL processing by @peasee in #9731
[SpiceDQ] Distribute query of Cayenne Catalog to executors with data by @Jeadie in #9727
Properly set primary_keys/on_conflict for Cayenne tables by @krinart in #9739
Add executor resource and replica support to cloud app config by @ewgenius in #9734
feat: Support PARTITION BY in Cayenne Catalog table creation by @peasee in #9741
Update datafusion and related packages to version 52.3.0 by @lukekim in #9708
Route FlightSQL statement updates through QueryBuilder by @phillipleblanc in #9754
JSON file format improvements by @lukekim in #9743
[SpiceDQ] Partition Cayenne catalogs writes through to executors by @Jeadie in #9737
Update to DF v52.3.0 versions of datafusion & datafusion-tableproviders by @lukekim in #9756
Make S3 metadata column handling more robust by @sgrebnov in #9762
Fetch API keys from dedicated endpoint instead of apps response by @phillipleblanc in #9767
Update arrow-rs, datafusion-federation, and datafusion-table-providers dependencies by @phillipleblanc in #9769
Chunk metastore batch inserts to respect SQLite parameter limits by @phillipleblanc in #9770
Improve JSON SODA support by @lukekim in #9795
Add ADBC Data Connector by @lukekim in #9723
docs: Release Cayenne as RC by @peasee in #9766
cli[feat]: cloud mode to use region-specific endpoints by @lukekim in #9803
Include updated JSON formats in HTTPS connector by @lukekim in #9800
Flight DoPut: Partition-aware write-through forwarding by @Jeadie in #9759
Pass through authentication to ADBC connector by @lukekim in #9801
Move scheduler_state_location from adapter metadata to env var by @phillipleblanc in #9802
Fix Cayenne DoPut upsert returning stale data after 3+ writes by @phillipleblanc in #9806
Fix JSON column projection producing schema mismatch by @sgrebnov in #9811
Fix http connector by @krinart in #9818
Fix ADBC Connector build and test by @lukekim in #9813
Support update & delete DML for distributed cayenne catalog by @Jeadie in #9805
Set allow_http param when S3 endpoint uses http scheme by @phillipleblanc in #9834
fix: Cayenne Catalog DDL requires a connected executor in distributed mode by @Jeadie in #9838
fix: Add conditional put support for file:// scheduler state location by @Jeadie in #9842
fix: Require the DDL primary key contain the partition key by @Jeadie in #9844
fix: Databricks SQL Warehouse schema retrieval with INLINE disposition and async retry by @lukekim in #9846
Filter pushdown improvements for SqlTable by @lukekim in #9852
feat: add iam_role_source parameter for AWS credential configuration by @lukekim in #9854
Fix ODBC queries silently returning 0 rows on query failure by @lukekim in #9864
feat(adbc): Add ADBC catalog connector with schema/table discovery by @lukekim in #9865
Make Turso SQL unparsing more robust and fix date comparisons by @lukekim in #9871
Fix Flight/FlightSQL filter precedence and mutable query consistency by @lukekim in #9876
Partial Aggregation optimisation for FlightSQLExec by @lukekim in #9882
fix: v1/responses API preserves client instructions when system_prompt is set by @Jeadie in #9884
feat: emit scheduler_active_executors_count and use it in spidapter by @Jeadie in #9885
feat: Add custom auth header support for GraphQL connector by @krinart in #9899
Add --endpoint flag to spice run with scheme-based routing by @lukekim in #9903
When executor connects, send DDL for existing tables by @Jeadie in #9904
fix: Improve ADBC driver shutdown handling and error classification by @lukekim in #9905
fix: require all executors to succeed for distributed DML (DELETE/UPDATE) forwarding by @Jeadie in #9908
fix(cayenne catalog): fix catalog refresh race condition causing duplicate primary keys by @Jeadie in #9909
Remove Perplexity support by @Jeadie in #9910
Fix refresh_sql support for debezium constraints by @krinart in #9912
Implement DML for DynamoDBTableProvider by @lukekim in #9915
chore: Update iceberg-rust fork to v0.9 by @lukekim in #9917
Run physical optimizer on FallbackOnZeroResultsScanExec fallback plan by @sgrebnov in #9927
Improve Databricks error message when dataset has no columns by @sgrebnov in #9928
Delta Lake: fix data skipping for >= timestamp predicates by @sgrebnov in #9932
fix: Ensure distributed Cayenne DML inserts are forwarded to executors by @Jeadie in #9948
Add full query federation support for ADBC data connector by @lukekim in #9953
Make time_format deserialization case-insensitive by @claudespice in #9955
Hash ADBC join-pushdown context to prevent credential leaks in EXPLAIN plans by @lukekim in #9956
fix: Normalize Arrow Dictionary types for DuckDB and SQLite acceleration by @sgrebnov in #9959
ADBC BigQuery: Improve BigQuery dialect date/time and interval SQL generation by @lukekim in #9967
Make BigQueryDialect more robust and add BigQuery TPC-H benchmark support by @lukekim in #9969
fix: Show proper unauthorized error instead of misleading runtime unavailable by @lukekim in #9972
fix: Enforce target_chunk_size as hard maximum in chunking by @lukekim in #9973
Add caching retention by @krinart in #9984
fix: improve Databricks schema error detection and messages by @lukekim in #9987
fix: Set default S3 region for opendal operator and fix cayenne nextest by @phillipleblanc in #9995
fix(PostgreSQL): fix schema discovery for PostgreSQL partitioned tables by @sgrebnov in #9997
fix: Defer cache size check until after encoding for compressed results by @krinart in #10001
fix: Rewrite numeric BETWEEN to CAST(AS REAL) for Turso by @lukekim in #10003
fix: Handle integer time columns in append refresh for all accelerators by @sgrebnov in #10004
fix: preserve s3a:// scheme when building OpenDalStorageFactory with custom endpoint by @phillipleblanc in #10006
Fix ISO8601 time_format with Vortex/Cayenne append refresh by @sgrebnov in #10009
fix: Address data correctness bugs found in audit by @sgrebnov in #10015
fix(federation): fix SQL unparsing for Inexact filter pushdown with alias by @lukekim in #10017
Improve GitHub connector ref handling and resilience by @lukekim in #10023
feat: Add spice completions command for shell completion generation by @lukekim in #10024
fix: Fix data correctness bugs in DynamoDB decimal conversion and GraphQL pagination by @sgrebnov in #10054
Implement RefreshDataset for distributed control stream by @Jeadie in #10055
perf: Improve S3 parquet read performance by @sgrebnov in #10064
fix: Prevent write-through stalls and preserve PartitionTableProvider during catalog refresh by @Jeadie in #10066
feat: spice completions auto-detects shell directory and writes file by @lukekim in #10068
fix: Bug in DynamoDB, GraphQL, and ISO8601 refresh data handling by @sgrebnov in #10063
fix partial aggregation deduplication on string checking by @lukekim in #10078
fix: add MetastoreTransaction support to prevent concurrent transaction conflicts by @phillipleblanc in #10080
fix: Use GreedyMemoryPool, add spidapter query memory limit arg by @phillipleblanc in #10082
feat: Add metrics for EXPLAIN ANALYZE in FlightSQLExec by @lukekim in #10084
Use strict cast in try_cast_to to error on overflow instead of silent NULL by @sgrebnov in #10104
feat: Implement MERGE INTO for Cayenne catalog tables by @peasee in #10105
feat: Add distributed MERGE INTO support for Cayenne catalog tables by @peasee in #10106
Improve JSON format auto-detection for single multi-line objects by @lukekim in #10107
Add mode: file_update acceleration mode by @krinart in #10108
Coerce unsupported Arrow types to Iceberg v2 equivalents in REST catalog API by @peasee in #10109
fix: Update default query memory limit to 90% from 70% by @phillipleblanc in #10112
feat: Add mTLS client auth support to spice sql REPL by @lukekim in #10113
fix(datafusion-federation): report error on overflow instead of silent NULL by @sgrebnov in #10124
fix: Prevent data loss in MERGE when source has duplicate keys by @peasee in #10126
feat: Add ClickHouse Date32 type support by @sgrebnov in #10132
Add Delta Lake column mapping support (Name/Id modes) by @sgrebnov in #10134
fix: Restore Turso numeric BETWEEN rewrite lost in DML revert by @lukekim in #10139
fix: Enable arm64 Linux builds with fp16 and lld workarounds by @lukekim in #10142
fix: remove double trailing slash in Unity Catalog storage locations by @sgrebnov in #10147
fix: Improve GitHub GraphQL client resilience and performance by @lukekim in #10151
Enable reqwest compression and optimize HTTP client settings by @lukekim in #10154
fix: executor startup failures by @Jeadie in #10155
feat: Distributed runtime.task_history support by @Jeadie in #10156
fix: Preserve timestamp timezone in DDL forwarding to executors by @peasee in #10159
feat: Per-model rate-limited concurrent AI UDF execution by @Jeadie in #10160
fix(Turso): Reject subquery/outer-ref filter pushdown in Turso provider by @lukekim in #10174
Fix linux/macos spice upgrade by @phillipleblanc in #10194
Improve CREATE TABLE LIKE error messages, success output, EXPLAIN, and validation by @peasee in #10203
fix: chunk MERGE delete filters and update Vortex for stack-safe IN-lists by @peasee in #10207
Propagate runtime.params.parquet_page_index to Delta Lake connector by @sgrebnov in #10209
Properly mark dataset as Ready on Scheduler by @Jeadie in #10215
fix: handle Utf8View/LargeUtf8 in GitHub connector ref filters by @lukekim in #10217
fix(databricks): Fix schema introspection and timestamp overflow by @lukekim in #10226
fix(databricks): Fix schema introspection failures for non-Unity-Catalog environments by @lukekim in #10227
feat: Add pagination support to HTTP data connector by @lukekim in #10228
feat(databricks): DESCRIBE TABLE fallback and source-native type parsing for Lakehouse Federation by @lukekim in #10229
fix(databricks): harden HTTP retries, compression, and token refresh by @lukekim in #10232
feat[helm chart]: Add support for ServiceAccount annotations and AWS IRSA example by @peasee in #9833
fix: Log warning and fall back gracefully on Cayenne config change by @krinart in #9092
fix: Handle engine mismatch gracefully in snapshot fallback loop by @krinart in #9187
fix: Full Text Search schema mismatch with ADBC connector by @lukekim in #10235
docs: Update v2.0.0-rc.2 release notes with latest changes by @lukekim in #10238
Fix append refresh dedup failure when refresh_sql selects column subset by @sgrebnov in #10225
Revert "Properly mark dataset as Ready on Scheduler (#10215)" by @sgrebnov in #10242
Fix failing merge conflicts for benchmarks by @krinart in #10247
fix(github): fetch commits for dynamic and slash refs by @lukekim in #10233
Upgrade DataFusion to v52.5.0-rc1 by @lukekim in #10249
Merge develop to trunk (2026-04-09) by @claudespice in #10248
fix: Validate embedding row_id columns during dataset init (fixes #8226) by @claudespice in #10208
fix: Update tpch benchmark snapshots for federated/glue[csv].yaml by @app/github-actions in #10244
feat(databricks): add resilience controls, UC awareness, and task history instrumentation by @lukekim in #10246
fix: Make PartitionManager resilient to bare vs fully qualified table references by @sgrebnov in #10257
fix: Update tpch benchmark snapshots for accelerated/s3[parquet]-cayenne[file].yaml by @app/github-actions in #10256
Merge develop to trunk (2026-04-10) by @claudespice in #10251
Improve Snowflake/ADBC dataset registration performance and observability by @lukekim in #10266
Fixes for kafka connector by @krinart in #10263
fix(runtime): gate otel code tags, suppress aws sdk noise, and unblock connector init by @lukekim in #10260
fix(runtime): avoid regionless AWS SDK loads by @lukekim in #10271
Add versioned release install workflow coverage by @lukekim in #10276
fix(runtime): handle HTTP JSON unions and spicepod reloads by @lukekim in #10277
Databricks UC permission prechecks: explicit denial as permanent error, ambiguous cases advisory by @lukekim in #10274
Revert component status changes re-introduced by develop merge (#10248) by @sgrebnov in #10293
Fix broken CI workflows by @ewgenius in #10294
Group dependabot updates by ecosystem by @lukekim in #10296
fix(tests): Replace flaky S3 Vectors snapshot tests with structural validation by @lukekim in #10301
Update test_github_workflows snapshot by @lukekim in #10304
fix(ci): fix Bedrock runner mismatch and snapshot auto-merge failure by @ewgenius in #10306
feat(http): Add map-to-array conversion and query-parameter pagination by @lukekim in #10295
New crate: datafusion-ddl by @Jeadie in #10205
Make Databricks UC permission checks advisory with structured error reporting by @lukekim in #10283
build(deps): bump the github-actions-dependencies group with 4 updates by @app/dependabot in #10298
fix: Clear cached plans on view updates by @peasee in #10312
build(deps): bump the aws-sdk group with 7 updates by @app/dependabot in #10299
Code out of runtime. by @Jeadie in #10178
fix: Respect function registry denies for accelerated table filter pushdown by @peasee in #10311
fix: Don't block heartbeat when all slots acquired by @peasee in #10322
fix: strip only outer parens in get_table_partition_expr_from_ctx by @Jeadie in #10323
Upgrade datafusion-table-providers with MongoDB SRV support by @lukekim in #10317
fix: Avoid pushing down bucketing partition expressions into executors by @peasee in #10324
Upgrade datafusion-table-providers to d1b911a5 and bump adbc to 0.23 by @lukekim in #10329
fix: Update Search integration test snapshots by @app/github-actions in #10308
Handle foreign table + Classic sql warehouse combination gracefully by @krinart in #10318
New crate datafusion-flightsql by @Jeadie in #10201
Set tantivy=warn unless very verbose logging by @Jeadie in #10338
Remove image registry and image name options from spidapter by @ewgenius in #10241
build(deps): bump sysinfo from 0.37.2 to 0.38.4 by @app/dependabot in #10291
build(deps): bump futures from 0.3.31 to 0.3.32 by @app/dependabot in #10289
New crate 'datafusion-dml' by @Jeadie in #10334
Jeadie/26 04 16/spice sql by @Jeadie in #10343
Add Teraswitch/Pittsburgh apt mirrors + retry config for CI runners by @lukekim in #10349
Implement sort pushdown and fix pushdown gaps across providers by @lukekim in #10337
Merge develop to trunk (2026-04-16) by @claudespice in #10345
Update candle and mistral.rs lock-step pins by @lukekim in #10278
docs: fix status badges in README by @lukekim in #10350
Migrate secrets to vars by @krinart in #10354
Add limit pushdown and improve sort pushdown for Oracle and MSSQL by @sgrebnov in #10351
Fix ubuntu mirror configuration by @ewgenius in #10359
fix: Increase throughput test default ready_wait from 30s to 300s (fixes #8207) by @claudespice in #10344
Add auth headers support to OTEL metrics exporter by @lukekim in #10347
fix(github): shrink GraphQL page size on gateway errors; lower comment defaults by @lukekim in #10355
Relax apt mirror substitution failure to warning in CI action by @ewgenius in #10361
feat(http): Add OAuth2 refresh-token auth to HTTP connector by @lukekim in #10348
Upgrade Rust toolchain to 1.94.1 by @lukekim in #10353
Handle order by and sort in PartitionedTableScanRewrite by @Jeadie in #9656
Fix OTEL Exporter by @krinart in #10363
Pin spiceai candle / TEI forks to merged revs; drop local [patch] overrides by @lukekim in #10362
Integrate spiceio and makefile_targets into pr.yml by @lukekim in #10357
ci: skip artifact compression for test binaries/archives by @lukekim in #10381
chore(deps): bump spiceai/candle, spiceai/mistral.rs, aws-lc-rs, tantivy, rand by @lukekim in #10379
Bump datafusion-table-providers (#10375) by @lukekim in #10384
fix: Update Search integration test snapshots by @app/github-actions in #10376
v2.0.0-rc.3 preparation by @ewgenius in #10382
fix(spicepod): JSON schema accepts string or {name: expr} for partition_by by @lukekim in #10352
fix: Use ROUND for Turso decimal BETWEEN comparisons (fixes #9872) by @claudespice in #10360
Revert "v2.0.0-rc.3 preparation" from trunk by @ewgenius in #10386
Add on_schema_resolved dataset ready state by @lukekim in #10368
feat: Add Elasticsearch data connector with hybrid search support by @lukekim in #10258
ci: bump test archive upload compression-level to 1 by @lukekim in #10388
feat(git-connector): promote Git connector to RC status by @lukekim in #10385
feat(postgres): stream WAL directly to Spice accelerators by @lukekim in #10364
Add schema decomposition to the HTTP connector by @lukekim in #10393
fix(cayenne): Skip catalog refresh state reload for existing providers by @sgrebnov in #10396
Make cayenne-flightsql tool by @Jeadie in #10356
build(deps): bump the github-actions-dependencies group with 2 updates by @app/dependabot in #10398
Update openapi.json by @app/github-actions in #10272
Merge develop to trunk — 2026-04-19 by @claudespice in #10407
feat(otel): default OTLP push exporter to delta temporality by @phillipleblanc in #10412
fix: Restore analyzer rule ordering to run federation before type coercion by @sgrebnov in #10415
fix: Map Utf8/LargeUtf8 to STRING in Databricks/Spark SQL dialects by @sgrebnov in #10420
feat(otel): add metric name prefix at runtime.telemetry.metric_prefix by @phillipleblanc in #10418
fix: Map LargeUtf8 to VARCHAR in Athena ODBC dialect by @sgrebnov in #10419
feat(cluster): connector-driven object store registration on executors by @phillipleblanc in #10414
build(deps): bump ubuntu from 22.04 to 24.04 in the docker-dependencies group by @app/dependabot in #10397
fix: Update benchmark snapshots Apr 20 by @app/github-actions in #10417
feat(otel): apply runtime.telemetry.properties as resource attributes on exported metrics by @phillipleblanc in #10416
Publish RC releases to DockerHub; upgrade runners to ubuntu-24.04 by @lukekim in #10428
feat: Add Azure Cosmos DB (NoSQL) data connector (RC) by @lukekim in #10392
feat(datafusion): flatten_json_properties + json_tree UDTFs by @lukekim in #10406
Harden /v1/tools and /v1/nsql against unauthenticated / LLM-driven SQL by @lukekim in #10365
feat(embeddings): multi-vector embeddings with MaxSim + late-interaction by @lukekim in #10408
Update GH runners for CUDA builds by @ewgenius in #10432
fix(delta_lake): register object stores on cluster executors by @phillipleblanc in #10436
DF-native DML by @krinart in #10327
ci: run Build and Test on spiceai-macos; split install jobs by profile by @lukekim in #10434
Improve search UDTFs: text_search, vector_search, rrf by @lukekim in #10387
fix(model2vec): Improve robustness of model loading for sentence-transformers layouts by @sgrebnov in #10444
Merge develop to trunk — 2026-04-21 by @claudespice in #10448
Enable filter pushdown for vector_search UDTF by @sgrebnov in #10447
Support Snowflake OBJECT, MAP, GEOGRAPHY, GEOMETRY, VECTOR, TIMESTAMP_LTZ types by @lukekim in #10451
Fix Databricks tests by @krinart in #10449
fix(cluster): forward register_object_stores through connector wrappers by @phillipleblanc in #10460
Fixes for vector-search by @krinart in #10455
Add expand_maps option and flatten_json UDTF by @lukekim in #10452
fix: Update Search integration test snapshots by @app/github-actions in #10458
Fix physical codec decode ambiguity for empty protobuf messages by @sgrebnov in #10466
chore(logging): demote s3_single_file_cached skip refresh log to debug by @phillipleblanc in #10467
Enable filter pushdown for rrf UDTF by @sgrebnov in #10465
feat(cluster): consolidate distributed state into cluster.json by @phillipleblanc in #10463
feat(cayenne): Add column statistics and data inlining by @lukekim in #10314
docs(copilot): flag missing wrapper delegation when adding default trait methods by @phillipleblanc in #10461
Wire Elasticsearch vector engine write path through acceleration by @lukekim in #10453
Add helm lint CI by @ewgenius in #10468
Fix Azure and GCS acceleration snapshot object store credential handling by @phillipleblanc in #10486
Update spicepod.schema.json by @app/github-actions in #10485
fix(secrets): harden AWS Secrets Manager secret store by @lukekim in #10478
Update datafusion-ballista crate by @sgrebnov in #10488
feat(secrets): add ParameterSpec and more params for AWS secrets manager by @phillipleblanc in #10487
Add rerank UDTF for hybrid search with query auto-propagation by @lukekim in #10469
Fix flatten_json_properties by @krinart in #10475
fix: preserve field and schema metadata in expand_views_schema by @claudespice in #10494
Upgrade rmcp to upstream 1.5.0; switch MCP server to Streamable HTTP by @lukekim in #10491
fix: handle Snowflake TIMESTAMP_LTZ wire format and prevent nanosecond overflow by @claudespice in #10493
Lint parity in Makefile by @krinart in #10492
Add connect_timeout/client_timeout params to Databricks sql_warehouse mode by @lukekim in #10495
fix(tracing): suppress opentelemetry INFO logs at all verbosity levels by @lukekim in #10497
DynamoDB DML by @krinart in #10470
feat(cayenne): native vector search via SIMD similarity UDFs by @lukekim in #10456
fix(cli): suppress banner for all JSON-producing cloud subcommands (fixes #10498) by @claudespice in #10510
fix(deps): bump openssl to 0.10.78 by @phillipleblanc in #10509
fix(s3): quiet AWS SDK credential probe when no region is configured by @phillipleblanc in #10506
fix(cdc): emit ready signal on caught-up Kafka/Debezium streams (#5201) by @phillipleblanc in #10504
runtime-cluster crate + Run partition discovery before forwarding refresh to executors by @krinart in #10490
Update lint-rust target to use --keep-going by @Jeadie in #10508
Add TPC-H SF100 s3[parquet]-duckdb[file] benchmark spicepod by @lukekim in #10524
Remove dev-profile install steps from pr.yml by @Jeadie in #10507
fix: add missing NULL check on Timestamp path in append refresh by @claudespice in #10518
fix: return error on Decimal128/256 overflow instead of silently dropping scale by @claudespice in #10519
fix: delegate update and delete_from in IndexedTableProvider and EmbeddingTable by @claudespice in #10520
feat(devx): make config errors, CLI, and REPL lead users to success by @lukekim in #10489
fix(rerank): defer execution to RerankExec, enable filters and projection pushdown by @sgrebnov in #10514
fix(llms): support Gemma models with missing attention_bias config field by @lukekim in #10523
Fix vector_search silently ignoring named limit/column/include_score args by @sgrebnov in #10527
fix: split unsupported filters locally in scan() for UseSource mode by @ewgenius in #10528
feat(secrets): add Azure Key Vault secret store by @lukekim in #10496
Bump mistralrs by @krinart in #10532
Fix benchmark configurations and CI build issues by @sgrebnov in #10535
Fix catalog query overrides for MySQL and MSSQL benchmarks by @sgrebnov in #10543
For Cayenne, preserve matched columns for MERGE ... ON <cols> by @Jeadie in #10340
build(deps): bump the aws-sdk group across 1 directory with 5 updates by @app/dependabot in #10538
docs: update AI agent instructions (git workflow + Rust 1.94) by @lukekim in #10544
fix: Update tpch benchmark snapshots by @app/github-actions in #10529
fix: Update tpch benchmark snapshots for accelerated/s3[parquet]-duckdb[file].yaml by @app/github-actions in #10525
Extract runtime-datafusion from runtime by @krinart in #10545
Use generic DML extension planner for Cayenne by @Jeadie in #10437
fix: Update Search integration test snapshots by @app/github-actions in #10552
Fix security and correctness audit issues by @lukekim in #10526
fix(MySQL): revert MySQL result column reorder to fix federated query failures by @sgrebnov in #10557
Fix protoc installation by @krinart in #10566
fix: Disable Ballista dynamic filters on HashJoinExec by @peasee in #10548
Support views on DDL catalogs by @Jeadie in #10554
Update datafusion by @Jeadie in #10422
Improve full-text search indexing performance by @sgrebnov in #10464
feat(mysql): add mysql_zero_date_behavior parameter (null|error) by @phillipleblanc in #10573
fix(snowflake): declare private_key in connector PARAMETERS (fixes #10517) by @claudespice in #10559
Honour CARGO_TARGET_DIR in Makefiles by @Jeadie in #10569
Enable cosine_distance pushdown to DuckDB accelerator via array_cosine_distance by @sgrebnov in #10564
fix: Update test snapshots by @app/github-actions in #10570
fix: Update tpch benchmark snapshots by @app/github-actions in #10560
feat(snapshots): make snapshots an optional feature by @phillipleblanc in #10574
Enforce read-only API key restrictions on Flight DoGet and async query paths by @Jeadie in #10551
Improved security posture on Github workflows by @Jeadie in #10556
fix: Update datafusion-table-providers to improve SqlTable filter pushdown by @sgrebnov in #10595
feat(secrets): add HashiCorp Vault secret store by @phillipleblanc in #10561
fix: delegate update() in UpsertDedupTableProvider to inner provider by @claudespice in #10593
Add DuckDB vector engine support by @lukekim in #10562
Sharepoint - add object-store listing connector with expanded auth and write support by @lukekim in #10473
fix: Install protoc from source by @peasee in #10597
Enable DML support for PostgreSQL data connector by @phillipleblanc in #10446
feat(postgres): support inline PEM sslrootcert by @claudespice in #10578
Add foreign key metadata discovery to PostgreSQL Catalog by @sgrebnov in #10849
Add Snowflake DML support by @lukekim in #10747
Add MongoDB Change Streams support by @lukekim in #10813
Add user-defined functions by @lukekim in #10571
Add table user functions and gate HTTP servers by @lukekim in #10675
feat: add on-demand dataset loading by @phillipleblanc in #10629
feat(runtime): declared-schema deferred datasets by @phillipleblanc in #10669
feat(spicepod, runtime): add columns[].type / nullable + lenient type parser by @phillipleblanc in #10661
Replace external smb crate with internal SMB 3.1.1 client by @phillipleblanc in #10516
Add unified query cancellation across all paths by @lukekim in #10390
Add dynamic HTTP request headers by @lukekim in #10604
feat(http): Support dynamic HTTP connector request params from subqueries by @lukekim in #10636
feat(http): pass through HTTP metadata columns with JSON schema decomposition by @lukekim in #10679
Add nolimit HTTP pagination max pages by @lukekim in #10673
Add shared HTTP rate control for connectors by @lukekim in #10648
Use origin label instead of name for HTTP rate control metrics by @lukekim in #10689
fix(http): reject OR across different HTTP filter columns by @lukekim in #10625
Add provider-aware LLM prompt caching by @lukekim in #10645
Add searchable registry mode for LLM tools by @lukekim in #10647
feat: refresh_mode: snapshot + SQLite/Turso WAL flush + Cayenne metastore slice by @phillipleblanc in #10651
feat: per-principal cache namespacing for SQL/search/caching-accelerator by @lukekim in #10702
Add self-hosted Spice connector support by @phillipleblanc in #10546
Add Delta Lake Azure tenant parameter by @phillipleblanc in #10671
Support OAuth2 client credentials in 'spice cloud login' by @ewgenius in #10586
Add configurable allowed_hosts for MCP by @lukekim in #10638
fix: make Helm chart probes configurable by @peasee in #10696
Strip high-cardinality datasets dim from anonymous telemetry by @lukekim in #10711
feat(elasticsearch): direct FTS engine config + index lifecycle and ingestion controls by @lukekim in #10672
Add DuckDB HNSW vector index support for accelerated views by @sgrebnov in #10695
Rewrite DuckDB vector search SQL to activate HNSW_INDEX_SCAN by @sgrebnov in #10674
Fix DuckDB HNSW vector indexes lost after data refresh by @sgrebnov in #10668
Fix DuckDB DELETE/UPDATE on full and caching refresh mode datasets by @phillipleblanc in #10632
Fix DuckLake connector: downcast, module registration, schema discovery, and S3 credentials by @sgrebnov in #10650
Fix federation pushing denied functions inside subqueries to remote engines by @phillipleblanc in #10692
fix(caching): honour refresh_on_startup: always in caching mode by @phillipleblanc in #10594
fix(iceberg): rebuild storage factory when Hadoop catalog scheme is inferred by @sgrebnov in #10601
Pipeline CDC ingestion: overlap source reads with batch apply by @lukekim in #10676
fix: add NULL check to CDC primary key extraction by @lukekim in #10684
Properly handle nullability during CDC processing by @krinart in #10803
Flatten scheduler config and rename partition management → partition assignment by @lukekim in #10450
Improve NSQL UX and harden internal LLM tools by @lukekim in #10715
Support Responses API across model providers by @lukekim in #10724
Update xAI default model and handle Grok model retirements by @Jeadie in #10723
Improve cli table layout by @krinart in #10725
TLS cert hot-reload (mTLS plan M1) by @phillipleblanc in #10727
Fix DuckLake catalog include filter being ignored by @phillipleblanc in #10738
Promote DuckLake Catalog and Data Connector to Beta quality by @sgrebnov in #10743
feat(ducklake): Support INSERT on catalog tables with read_write access by @sgrebnov in #10744
perf(cdc): coalesce envelopes and overlap commits in apply pipeline by @lukekim in #10745
feat: Allow full version tags in spicepod version by @peasee in #10748
Add Arrow primary key upserts by @lukekim in #10749
fix(snapshot): keep refresh_mode snapshot read-only by @phillipleblanc in #10752
feat(tls): public mTLS for HTTP and Flight (channel + identity modes) by @phillipleblanc in #10753
perf(cayenne): lock-free deletion caches with bloom-prefiltered probe by @lukekim in #10756
fix(security): close API key timing-position leak and remote-UDF SSRF by @lukekim in #10757
Fix 'wait_until_dependent_tables_are_ready' for catalogs by @phillipleblanc in #10758
Fixes for views and resolved tables on 'spice refresh' CLI by @phillipleblanc in #10759
Implement FlightSQL CommandStatementSubstraitPlan support by @lukekim in #10761
feat(connectors): mTLS client cert support for flightsql and spiceai connectors by @phillipleblanc in #10764
Allow arbitrary filenames when specifying spicepod path + kind validation by @krinart in #10777
fix: ignore field metadata in schema compatibility check in index_table_scan by @Jeadie in #10778
Display pushed-down limits in EXPLAIN TREE output by @lukekim in #10779
fix: enable streaming append for Kafka with Cayenne accelerator by @lukekim in #10780
fix: bound chunked-index intermediate batch size to prevent OOM by @phillipleblanc in #10783
fix: label all columns in spice cloud metrics table output by @claudespice in #10784
fix: use checked arithmetic for Turso integer-millis timestamp read path by @claudespice in #10786
fix: use checked arithmetic in timestamp-to-nanosecond conversions by @claudespice in #10666
Upgrade to DuckDB v1.5.2 by @sgrebnov in #10788
Improve CDC ingestion performance by @lukekim in #10789
Fix tool_search/tool_invoke spans by @lukekim in #10791
Add Cayenne inline mutations and benchmark coverage by @lukekim in #10792
Ensure we always resolve table names in distributed mode/metadata by @Jeadie in #10793
Remove permanent errors from DynamoDB Streams by @krinart in #10794
Add expanded view mode for wide table display in SQL REPL by @lukekim in #10797
Fix Cayenne CDC schema mismatch error by @sgrebnov in #10800
Executors should create catalog tables on join by @Jeadie in #10807
Add compressed file support for listing connectors by @lukekim in #10809
Improve Cayenne mutation, scan, and inline memtable scaling by @lukekim in #10811
Add range fallback for large join filters by @lukekim in #10816
Improve Cayenne join filter pushdown by @lukekim in #10818
Synchronize Cayenne partition commits across partitions by @phillipleblanc in #10819
fix: Deny nondistributed cayenne catalog by @peasee in #10821
Enable parallel Cayenne Vortex writes by @lukekim in #10822
Expand Arrow type handling in formatting and Elasticsearch by @lukekim in #10825
Add response.output_text.delta to responses API by @krinart in #10828
feat(cayenne): add join filter propagation and no-spill Q21 planning by @lukekim in #10840
Upgrade Turso to v0.6.0 by @sgrebnov in #10843
feat(cli): add spice feedback command to open community Slack by @lukekim in #10856
Upgrade iceberg to v0.9.1 by @sgrebnov in #10859
feat(cluster): per-request executor readiness gate on /v1/ready by @phillipleblanc in #10860
fix: Require dim-side statistics for CayennePropagateFilterAcrossEquiJoinKeys by @sgrebnov in #10863
fix: Debezium schema evolution breaks dataset init on reload by @claudespice in #10144
fix(mssql): Push topK limit to SQL Server for non-nullable sort columns by @Jeadie in #10621
fix(ScyllaDB): disable physical filter pushdown by @sgrebnov in #10772
fix: handle typed NULLs and prevent overflow in DynamoDB DML type conversions by @krinart in #10511
fix: use InsertOp::Overwrite in DynamoDB bootstrap scan_and_overwrite_accelerator by @krinart in #10639
Improve DynamoDB Bootstrap performance by @krinart in #10616
fix: preserve field and schema metadata in Vortex type transformation by @lukekim in #10628
fix: GH connector - explicitly use AWS LC RS crypto provider for jwt by @phillipleblanc in #10619
fix: add snapshot mode guards to delete_from/update and delegate DML in SwappableTableProvider by @phillipleblanc in #10685
Persist HTTP rate-control state in object storage by @lukekim in #10697
Rate limit metrics HTTP endpoint by @lukekim in #10162
feat(geo): add optional spatial SQL UDF support by @lukekim in #10833
feat(cayenne): CDC throughput, compaction, scan caching, and benchmarks by @lukekim in #10852
fix(cayenne): fix Vortex panic on highly compressible data by @sgrebnov in #10855
fix(cayenne): Read live protected snapshots after cleanup grace period by @sgrebnov in #10901
fix: Disable Cayenne HashJoin rewriter optimizer by @sgrebnov in #10882
Fix GetFlightInfo vs DoGet Flight Schema by @krinart in #10864
fix(search): preserve column casing in /v1/search primary key plumbing by @claudespice in #10909
fix(object-store): dedupe s3 url style auto-detection log by @phillipleblanc in #10898
Improve Spice CLI manifest editing and direct command modes by @lukekim in #10815
Persist Kafka CDC offsets in sidecar tables by @lukekim in #10823
feat(task-history): record Ballista stages for distributed queries by @phillipleblanc in #10831
Add '#[deny(clippy::missing_trait_methods)]' to wrapper/delegation trait impls by @Jeadie in #10795
Optimize Cayenne catalog maintenance paths by @lukekim in #10904
Centralize DuckDB settings for accelerator by @ewgenius in #10895
deps(ballista): bump to 47e2b494 to fix S3 shuffle reads under cluster mode by @phillipleblanc in #10910
Authorization header + Bump async-openai + responses_adapter fix by @krinart in #10911
Tune accelerators by storage profile by @lukekim in #10913
feat: add dataset-level on_schema_change config by @lukekim in #10908
Handle NULL sentinel for nullable partition expressions by @Jeadie in #10880
fix: Remove Cayenne Catalog from catalog registration by @peasee in #10914
Add catalog name to foreign key metadata in postgres catalog by @Jeadie in #10917
Cayenne perf: eliminate redundant clones, PK point-lookup fanout fix, IN-list rewrite + microbench coverage by @lukekim in #10916
fix(turso-shared): retry on Turso BEGIN CONCURRENT "Write-write conflict" by @lukekim in #10946
Vendor Vortex DataFusion for Cayenne by @lukekim in #10933
perf(cayenne): background retention + enable CDC pipelining for retention-configured tables by @lukekim in #10936
feat(cayenne): scale metastore pool to 32 + vs_duckdb_scaling benches (1→128 concurrency, sqlite + turso lanes) by @lukekim in #10943
feat(mcp): support auth for streamable HTTP tools by @phillipleblanc in #10927
Explicit error if v1/search requests a table without search index by @Jeadie in #10968
Fix spicepod loading failure when directory name contains dots by @sgrebnov in #10958
Extend append tests with arrow engine configurations by @sgrebnov in #10959
Remove dataset on_schema_change Policy from rc.5 release notes by @sgrebnov in #10964
Skip tpcds_q78 for Cayenne engine at SF100 by @sgrebnov in #10966
fix: Update benchmark snapshots May-20 by @app/github-actions in #10952
Fix #10951: UdtfExec invariant Vec lengths must match children count by @phillipleblanc in #10953
docs(release): update v2.0.0-rc.5 notes with latest trunk PRs by @lukekim in #10949
Remove eval related things for v2.0.0 by @Jeadie in #10945
build(deps): bump ubuntu from 24.04 to 26.04 in the docker-dependencies group by @app/dependabot in #10883
fix: Add publish = false to chbench-driver by @sgrebnov in #10939
[Bug] Timing between reconnect and AllocateInitialPartitions leaves connection without flight_sql_client by @Jeadie in #10805
Fix: refresh_mode: snapshot reports Ready with empty data when no snapshot exists by @sgrebnov in #10979
fix(cluster): gate scheduler readiness on executor partition loads by @phillipleblanc in #10992
fix: handle EXISTS/NOT EXISTS subqueries in federation analyzer by @sgrebnov in #10996
Refactor spice dataset configuration command by @Jeadie in #10999
fix: preserve field and schema metadata in Vortex physical schema calculation by @claudespice in #11013
fix: validate Snowflake account identifiers and auth config by @Jeadie in #11024
Fix Unity Catalog connector deserialization failure with OSS Unity Catalog by @ewgenius in #11026
feat(cayenne): allow inline writes with pending deletions (deletes/upserts) by @sgrebnov in #11031
Expose metadata descriptions via PostgreSQL UDFs by @lukekim in #11032
Remove default runtime features - enable explicitly in spiced by @phillipleblanc in #11037
feat(cayenne): fast-path CDC deletes by extracting PK values from filters by @sgrebnov in #11049
Cayenne optimizer rules: auto relevance test for q21-shape (all-Cayenne CH-Bench) and runtime rule selection by @lukekim in #11050
refactor(cdc): reduce CDC sub-batch splits for interleaved upsert/delete workloads by @sgrebnov in #11051
fix(snowflake): enforce function deny-list in federation pushdown by @claudespice in #11057
fix(mcp): trace external server tool calls in task history by @ewgenius in #11058
perf(cdc): Last-write-wins dedup in group_into_sub_batches to reduce sub-batch splits by @sgrebnov in #11059
PM edits to v2.0.0-rc5 by @lukekim in #11067
fix(snowflake): wire deny-list in extracted connector crate (#10703) by @claudespice in #11071
perf(cayenne): keep CDC upsert PK keysets resident to avoid per-batch full-table rebuilds by @lukekim in #11074
Fix metadata on search indexing by @Jeadie in #11080
feat(cayenne): merge-on-read position deletes for PK upsert tables + memory-pool accounting by @lukekim in #11085
perf(cayenne): scale CDC inline flush caps with memory + storage class by @lukekim in #11087
feat(cluster): report per-executor table statistics so distributed JoinSelection can size joins by @phillipleblanc in #11089
Improve Cayenne CDC write and compaction path tracing by @sgrebnov in #11091
Support tuple-IN composite PK extraction in Cayenne delete fast-path by @sgrebnov in #11093
feat(cluster): NDV-aware executor stats so CDC q18 join swap fires by @phillipleblanc in #11098
feat(cayenne): maintain join-sizing stats on the write path by @phillipleblanc in #11104
fix(cache): run periodic moka maintenance for idle caches by @phillipleblanc in #11106
Upgrade to DuckDB 1.5.3 + statically link the VSS (HNSW) extension by @sgrebnov in #11107
Fix fetched_at for HTTP connector by @Jeadie in #11116
fix(cayenne): tombstone inline-checkpointed rows on upsert to prevent duplicate PKs by @sgrebnov in #11129
feat: dedicated compaction runtime for Cayenne + CDC pipelining, protected snapshots, and test coverage by @lukekim in #11130
Add datasets dimension to the query_executions metric by @phillipleblanc in #11138
Fix #11137: localpod child not tracking parent refreshes with in-memory (arrow) parent accelerator by @phillipleblanc in #11139
Fix Windows build: vendor the VSS extension (drop nested submodule) by @phillipleblanc in #11140
fix(spiceai): keep correlated subqueries out of JOIN ON for Spice Cloud federation by @phillipleblanc in #11143
Refactor spice dataset configuration command by @Jeadie in #10999
feat(cayenne): sharded parallel Vortex encode with key/time clustering by @lukekim in #11144
fix(cluster): prevent DoPut write pipeline self-deadlock under ingest backpressure by @phillipleblanc in #11160
fix(cayenne): only warn on genuine protected-snapshot amplification by @lukekim in #11158

Full Changelog: https://github.com/spiceai/spiceai/compare/v1.11.6...v2.0.0

Highlights in v2.0.0 include:​

Distribution Changes​

What's New in v2.0.0​

Spice Cayenne Reaches General Availability​

Multi-Active HA Distributed Query (GA)​

Security: Mutual TLS, Secret Stores, and Hardening​

Change Data Capture (CDC) Sources​

DML, DDL, and Write-Back​

SQL & User-Defined Functions​

Runtime Features​

Spicepod v2​

Data Connectors & Catalogs​

AI & LLM​

Search & Vectors​

Caching​

Performance & Query Engine​

Rust CLI​

Observability​

Notable Bug Fixes​

Dependency Updates​

Contributors​

Breaking Changes​

Upgrade Guide from v1.x​

1. Build, image, and platform changes​

2. Adopt Spicepod v2 (recommended)​

3. Update changed configuration​

4. Update queries and API clients​

5. Update model providers​

6. Update observability​

Cookbook Updates​

Upgrading​

What's Changed​

Changelog​