---

date: 2026-06-05 title: 'Spice v2.0-stable (Jun 5, 2026)' type: blog authors: [phillipleblanc] tags: [release, distributed-query, cayenne, datafusion, cdc, cedar, postgres, mongodb, security, snowflake, udf, http, kafka, arrow, ducklake, data-connector]

---

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
• — SQL UDFs in spicepods, remote UDFs over HTTP, and optional geospatial UDFs

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.

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.

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 .

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/ 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, , ) and human-readable fields; the CLI shows an column.

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.

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

• @cluster2600
• @ewgenius
• @Jeadie
• @krinart
• @lukekim
• @peasee
• @penberg
• @phillipleblanc
• @sgrebnov

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:

• S3 metadata columns renamed: location, last_modified, size → _location, _last_modified, _size.

• Default query memory limit changed: Increased from 70% to 90%.

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:

Homebrew:

Docker:

Pull the spiceai/spiceai:2.0.0 image:

For available tags, see DockerHub.

Helm:

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

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