v0.5.0

What's Changed

• docs: Added a new oci-llamastack notebook for how to build agents with OCI and llama stack by @omaryashraf5 in #4418
• docs: Add guide to migrating from Agents to Responses by @jwm4 in #4375
• feat: convert models API to use a FastAPI router by @nathan-weinberg in #4407
• chore: update mcp dependency constraint to >=1.23.0 by @derekhiggins in #4457
• feat(ci): added codeql scanning workflow by @gmatuz in #4462
• feat: migrate Conversations API to FastAPI router by @leseb in #4342
• fix(faiss): add backward compatibility for EmbeddedChunk deserialization by @leseb in #4463
• fix: Removed duplicate parameters from integration test by @gyliu513 in #4461
• fix: removed scan on push by @gmatuz in #4466
• chore: Document release process by @raghotham in #4470
• feat: build ARM64-based UBI starter image by @rhdedgar in #4474
• chore: add "Discussion" issue template by @nathan-weinberg in #4469
• chore: Updated test integration guide by @gyliu513 in #4460
• fix: update CONTRIBUTING.md to reflect pre-commit version used in CI by @eoinfennessy in #4468
• fix: skip resources with empty IDs from conditional env vars in config processing by @Elbehery in #4455
• fix: Fix Vector Store Integration Tests by @franciscojavierarceo in #4472
• chore: Delete CHANGELOG.md by @terrytangyuan in #4480
• ci: run ARM64 builds on nightly schedule only by @rhdedgar in #4479
• chore(github-deps): bump actions/checkout from 4.3.1 to 6.0.1 by @dependabot[bot] in #4491
• chore(github-deps): bump astral-sh/setup-uv from 7.1.6 to 7.2.0 by @dependabot[bot] in #4490
• chore(github-deps): bump docker/setup-qemu-action from 3.2.0 to 3.7.0 by @dependabot[bot] in #4489
• chore(github-deps): bump github/codeql-action from 3.31.9 to 4.31.9 by @dependabot[bot] in #4488
• chore(github-deps): bump stainless-api/upload-openapi-spec-action from 1.9.0 to 1.10.0 by @dependabot[bot] in #4487
• chore: Add backwards compatibility for Milvus Chunks by @franciscojavierarceo in #4484
• fix: aiohttp HTTP Parser auto_decompress feature susceptible to zip bomb by @leseb in #4494
• chore: Add backwards compatibility for qdrant chunks by @Ygnas in #4495
• chore: Updated CONTRIBUTING guidance for integration test by @gyliu513 in #4459
• fix: fonttools security advisory by @leseb in #4503
• chore: Add backwards compatibility for pgvector chunks by @Ygnas in #4506
• refactor!: change image_name to distro_name in StackConfig by @cdoern in #4396
• fix: Add backwards compatibility for sqlite-vec, chroma, and weaviate chunks by @ChristianZaccaria in #4502
• fix: urllib3 vulnerable to decompression-bomb safeguard bypass by @leseb in #4512
• fix: disable together banner by @cdoern in #4517
• chore: switch to monthly minor release by @leseb in #4518
• chore: change discussion template label by @nathan-weinberg in #4525
• chore: add maintenance policy to release doc by @leseb in #4514
• docs: fixed outdated links for api overview, routed to the updated links by @lalexandrh in #4524
• chore: upgrade virtualenv by @raghotham in #4585
• chore: resync client dep with main by @leseb in #4591
• fix: llama-stack-api packaging by @cdoern in #4593
• docs: add guidance for contributing new providers by @leseb in #4478
• feat: migrate post_training API to FastAPI router by @eoinfennessy in #4496
• fix(memory/rag): remove file:// uri prefix by @r-bit-rry in #4286
• fix: benchmark registration via registered_resources config by @leseb in #4600
• feat(api): migrate Eval API to FastAPI router (#4345) by @r-bit-rry in #4425
• feat: convert shields API to use a FastAPI router by @nathan-weinberg in #4412
• feat: convert datasetio API to use a FastAPI router by @nathan-weinberg in #4400
• feat: Elasticsearch integration for VectorIO by @ezimuel in #4007
• fix: enable vector store registration from config with OpenAI metadata by @are-ces in #4616
• docs: Update RAG Agent Documentation using vector_stores by @robinnarsinghranabhat in #4485
• chore(github-deps): bump github/codeql-action from 4.31.9 to 4.31.10 by @dependabot[bot] in #4640
• chore(github-deps): bump actions/cache from 5.0.1 to 5.0.2 by @dependabot[bot] in #4639
• chore(github-deps): bump docker/setup-buildx-action from 3.11.1 to 3.12.0 by @dependabot[bot] in #4638
• chore(github-deps): bump actions/setup-node from 6.1.0 to 6.2.0 by @dependabot[bot] in #4637
• fix: update responses limitations doc to track latest state by @iamemilio in #4392
• feat: Convert scoring API to use a FastAPI router by @gyliu513 in #4521
• fix: Removed unused para for test score by @gyliu513 in #4645
• fix: fix list-deps quoting in deps-only output by @gyliu513 in #4653
• feat(api): Implement connector support via static configuration by @jaideepr97 in #4263
• fix: default ollama URL in Quickstart was incorrect in 2 places by @damian0815 in #4646
• fix: unregister function first before register by @gyliu513 in #4473
• feat!: migrate safety API to FastAPI router by @r-bit-rry in #4643
• feat: convert prompts API to use a FastAPI router by @nathan-weinberg in #4649
• feat: add scheduled CI workflow for release branches by @cdoern in #4510
• fix: Fix redundant MCP tools/list calls by @jwm4 in #4634
• docs: Move demo script to step 3 for quick start by @gyliu513 in #4661
• feat: convert scoring_functions API to use FastAPI router. by @EleanorWho in #4599
• feat(ci): add Bedrock integration tests with record/replay by @skamenan7 in #4292
• feat: Core Changes for default embedding dims by @rriley99-oci in #4671
• fix: use SecretStr for AWS credentials by @eoinfennessy in #4681
• feat: Implemented reasoning.effort parameter in LLS Responses by @Nehanth in #4633
• fix: file_search_call results missing document attributes/metadata by @are-ces in #4680
• fix!: usage input_token_details and output_token_details are not optional by @mattf in #4690
• fix: completed_at is required output by @mattf in #4692
• fix: store is required output by @mattf in #4693
• docs: update contrib guidelines on PR reviews by @leseb in #4676
• docs: require test plan with script and output for API PRs by @leseb in #4659
• feat: Add OpenAI API conformance coverage analyzer by @leseb in #4668
• feat!: use global vertext API endpoint by @ktdreyer in #4674
• fix: Concurrent calls into SentenceTransformer() cause failures of client.vector_stores.file_batches.create() by @syedriko in #4636
• feat(PGVector): use HNSW index for embedding column in a vector store table in PGVector by @r3v5 in #4696
• feat(PGVector): implement removal of vector store metadata from PGVector metadata_store table when unregister vector store by @r3v5 in #4678
• feat: Add shutdown functionality to LlamaStackAsLibraryClient and AsyncLlamaStackAsLibraryClient by @syedriko in #4642
• docs: add Bedrock inference example notebook by @skamenan7 in #4586
• feat(ci): Add basic integration tests for reasoning using vllm by @s-akhtar-baig in #4682
• feat: add PyPI publishing workflow for llama-stack and llama-stack-api by @cdoern in #4667
• docs: Microsoft Agent Framework - llama stack by @omaryashraf5 in #4245
• feat(PGVector): implement automatic creation of vector extension during initialization of PGVectorVectorIOAdapter by @r3v5 in #4660
• chore(github-deps): bump pypa/gh-action-pypi-publish from 1.12.4 to 1.13.0 by @dependabot[bot] in #4725
• chore(github-deps): bump astral-sh/setup-uv from 6.0.1 to 7.2.0 by @dependabot[bot] in #4723
• chore(github-deps): bump actions/setup-node from 6.1.0 to 6.2.0 by @dependabot[bot] in #4721
• chore(github-deps): bump actions/upload-artifact from 4.6.2 to 6.0.0 by @dependabot[bot] in #4720
• chore(github-deps): bump actions/setup-python from 5.6.0 to 6.2.0 by @dependabot[bot] in #4719
• fix: Update reasoning content field to ensure compatibility with ollama and vllm by @s-akhtar-baig in #4715
• feat: Add endpoint authorization with YAML config by @derekhiggins in #4448
• feat: Refactor Agents API to use FastAPI Router by @skamenan7 in #4376
• test(ci): add ABAC testing with files API to auth tests by @derekhiggins in #4328
• docs: Updated quick start guide by @gyliu513 in #4435
• feat(PGVector): allow users to configure distance metric and HNSW index parameters for PGVector in Llama Stack YAML config by @r3v5 in #4714
• fix: formatting of pypi.yml by @cdoern in #4739
• feat(server): route vector-io via FastAPI router by @skamenan7 in #4595
• fix!: OpenAI API conformance for POST /embeddings endpoint by @eoinfennessy in #4644
• fix: CI after #4644 by @cdoern in #4741
• fix: Enabled blog for llamastack by @gyliu513 in #4467
• fix!: finish_reason now complies with OpenAI by @leseb in #4679
• fix: Remove unused scope-based endpoint authorization feature by @derekhiggins in #4734
• chore(ci): harden stainless-builds workflow for pull_request_target by @dgellow in #4597
• feat(ci): add API conformance check to pre-commit by @nathan-weinberg in #4664
• fix: make release-branch-scheduled-ci compatible with older branches by @cdoern in #4753
• fix: address security vulnerabilities in GitHub Actions workflows by @cdoern in #4752
• fix: Enable session polling during streaming responses by @rhuss in #4738
• fix: pass branch explicitly to install-llama-stack-client action by @cdoern in #4759
• feat: Complete support for parallel_tool_calls in LLS Responses by @s-akhtar-baig in #4608
• feat: implement fastapi router for connectors API by @jaideepr97 in #4402
• chore(benchmark): add vertical scaling benchmark by @mattf in #4477
• feat(storage): make responses table name configurable by @ChristianZaccaria in #4764
• feat: migrate Inference API to FastAPI router system by @r-bit-rry in #4755
• fix: trim whitespace from discovered branch names by @cdoern in #4773
• feat: Add max_output_tokens to Response API by @gyliu513 in #4592
• fix: prevent MDX build failure in OpenAI conformance report by @gyliu513 in #4737
• feat(PGVector): add support for IVFFlat vector index for ANN search in PGVector by @r3v5 in #4772
• feat(ci): unify PyPI/npm release workflow with dry-run support by @cdoern in #4774
• fix: install setuptools-scm in CI by @cdoern in #4782
• feat: Add comprehensive network configuration for remote inference providers by @leseb in #4748
• feat: ensure connector CRUD via config + readonly API methods by @jaideepr97 in #4760
• chore: Added ge for max_tool_calls and max_output_tokens by @gyliu513 in #4780
• fix: override version from release tag for all packages by @cdoern in #4788
• chore: bump fallback_version to 0.4.5.dev0 by @cdoern in #4790
• refactor: Part 1 - Introduce rerankers and fix tests for existing search modes by @varshaprasad96 in #4456
• chore(github-deps): bump sigstore/gh-action-sigstore-python from 3.0.1 to 3.2.0 by @dependabot[bot] in #4797
• chore(github-deps): bump actions/download-artifact from 4.3.0 to 7.0.0 by @dependabot[bot] in #4798
• chore(github-deps): bump github/codeql-action from 4.31.10 to 4.32.0 by @dependabot[bot] in #4799
• chore(github-deps): bump depends-on/depends-on-action from 61cb3f4a0e2c8ae4b90c9448dc57c7ba9ca24c35 to 826c144163ac67bf08347590a5f81afd45da63ca by @dependabot[bot] in #4800
• chore(github-deps): bump llamastack/llama-stack from 306e43f to 76bcb66 by @dependabot[bot] in #4803
• fix: suppress tar pipe error in npm dry-run verification by @cdoern in #4796
• feat(api): add backward compatibility for Eval API method signatures by @saichandrapandraju in #4683
• feat: Implement run_moderation for all safety providers with NotImplementedError by @m-misiura in #4662
• feat(new provider): Adding OCI 26ai Vector Support by @rriley99-oci in #4411
• fix: MCP CPU spike by using context manager for session cleanup by @jwm4 in #4758
• feat(PGVector): implement validation for embedding dimensions when creating a vector index for ANN search in pgvector by @r3v5 in #4732
• fix(provider-codegen): prevent env var secrets from leaking into generated docs by @eoinfennessy in #4658
• chore: remove inline reference inference implementation by @mattf in #4828
• chore: prune llama_stack.models package by @mattf in #4829
• fix: unify version computation for all packages in pypi workflow by @cdoern in #4810
• fix: bump fallback version by @cdoern in #4832
• fix(pypi): auto-detect release branch for client repo checkouts by @cdoern in #4831
• chore: prune unused inference utils by @mattf in #4836
• feat: Adds support for the safety_identifier parameter by @gyliu513 in #4793
• chore: reduce use of sku_types by @mattf in #4838
• fix: remove params={} from safety integration tests by @cdoern in #4842
• chore: pin llama-stack-client to 0.5.0 for release by @cdoern in #4841

New Contributors

• @gmatuz made their first contribution in #4462
• @eoinfennessy made their first contribution in #4468
• @lalexandrh made their first contribution in #4524
• @ezimuel made their first contribution in #4007
• @robinnarsinghranabhat made their first contribution in #4485
• @damian0815 made their first contribution in #4646
• @EleanorWho made their first contribution in #4599
• @saichandrapandraju made their first contribution in #4683
• @m-misiura made their first contribution in #4662

Full Changelog: v0.4.4...v0.5.0