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 https://github.com/llamastack/llama-stack/pull/4418
* docs: Add guide to migrating from Agents to Responses by @jwm4 in https://github.com/llamastack/llama-stack/pull/4375
* feat: convert models API to use a FastAPI router by @nathan-weinberg in https://github.com/llamastack/llama-stack/pull/4407
* chore: update mcp dependency constraint to >=1.23.0 by @derekhiggins in https://github.com/llamastack/llama-stack/pull/4457
* feat(ci): added codeql scanning workflow by @gmatuz in https://github.com/llamastack/llama-stack/pull/4462
* feat: migrate Conversations API to FastAPI router by @leseb in https://github.com/llamastack/llama-stack/pull/4342
* fix(faiss): add backward compatibility for EmbeddedChunk deserialization by @leseb in https://github.com/llamastack/llama-stack/pull/4463
* fix: Removed duplicate parameters from integration test by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4461
* fix: removed scan on push by @gmatuz in https://github.com/llamastack/llama-stack/pull/4466
* chore: Document release process by @raghotham in https://github.com/llamastack/llama-stack/pull/4470
* feat: build ARM64-based UBI starter image by @rhdedgar in https://github.com/llamastack/llama-stack/pull/4474
* chore: add "Discussion" issue template by @nathan-weinberg in https://github.com/llamastack/llama-stack/pull/4469
* chore: Updated test integration guide by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4460
* fix: update `CONTRIBUTING.md` to reflect pre-commit version used in CI by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/4468
* fix: skip resources with empty IDs from conditional env vars in config processing by @Elbehery in https://github.com/llamastack/llama-stack/pull/4455
* fix: Fix Vector Store Integration Tests by @franciscojavierarceo in https://github.com/llamastack/llama-stack/pull/4472
* chore: Delete CHANGELOG.md by @terrytangyuan in https://github.com/llamastack/llama-stack/pull/4480
* ci: run ARM64 builds on nightly schedule only by @rhdedgar in https://github.com/llamastack/llama-stack/pull/4479
* chore(github-deps): bump actions/checkout from 4.3.1 to 6.0.1 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4491
* chore(github-deps): bump astral-sh/setup-uv from 7.1.6 to 7.2.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4490
* chore(github-deps): bump docker/setup-qemu-action from 3.2.0 to 3.7.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4489
* chore(github-deps): bump github/codeql-action from 3.31.9 to 4.31.9 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4488
* chore(github-deps): bump stainless-api/upload-openapi-spec-action from 1.9.0 to 1.10.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4487
* chore: Add backwards compatibility for Milvus Chunks by @franciscojavierarceo in https://github.com/llamastack/llama-stack/pull/4484
* fix: aiohttp HTTP Parser auto_decompress feature susceptible to zip bomb by @leseb in https://github.com/llamastack/llama-stack/pull/4494
* chore: Add backwards compatibility for qdrant chunks by @Ygnas in https://github.com/llamastack/llama-stack/pull/4495
* chore: Updated CONTRIBUTING guidance for integration test by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4459
* fix: fonttools security advisory by @leseb in https://github.com/llamastack/llama-stack/pull/4503
* chore: Add backwards compatibility for pgvector chunks by @Ygnas in https://github.com/llamastack/llama-stack/pull/4506
* refactor!: change image_name to distro_name in StackConfig by @cdoern in https://github.com/llamastack/llama-stack/pull/4396
* fix: Add backwards compatibility for sqlite-vec, chroma, and weaviate chunks by @ChristianZaccaria in https://github.com/llamastack/llama-stack/pull/4502
* fix: urllib3 vulnerable to decompression-bomb safeguard bypass by @leseb in https://github.com/llamastack/llama-stack/pull/4512
* fix: disable together banner by @cdoern in https://github.com/llamastack/llama-stack/pull/4517
* chore: switch to monthly minor release by @leseb in https://github.com/llamastack/llama-stack/pull/4518
* chore: change discussion template label by @nathan-weinberg in https://github.com/llamastack/llama-stack/pull/4525
* chore: add maintenance policy to release doc by @leseb in https://github.com/llamastack/llama-stack/pull/4514
* docs: fixed outdated links for api overview, routed to the updated links by @lalexandrh in https://github.com/llamastack/llama-stack/pull/4524
* chore: upgrade virtualenv by @raghotham in https://github.com/llamastack/llama-stack/pull/4585
* chore: resync client dep with main by @leseb in https://github.com/llamastack/llama-stack/pull/4591
* fix: llama-stack-api packaging by @cdoern in https://github.com/llamastack/llama-stack/pull/4593
* docs: add guidance for contributing new providers by @leseb in https://github.com/llamastack/llama-stack/pull/4478
* feat: migrate `post_training` API to FastAPI router by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/4496
* fix(memory/rag): remove file:// uri prefix by @r-bit-rry in https://github.com/llamastack/llama-stack/pull/4286
* fix: benchmark registration via registered_resources config by @leseb in https://github.com/llamastack/llama-stack/pull/4600
* feat(api): migrate Eval API to FastAPI router (#4345) by @r-bit-rry in https://github.com/llamastack/llama-stack/pull/4425
* feat: convert shields API to use a FastAPI router by @nathan-weinberg in https://github.com/llamastack/llama-stack/pull/4412
* feat: convert datasetio API to use a FastAPI router by @nathan-weinberg in https://github.com/llamastack/llama-stack/pull/4400
* feat: Elasticsearch integration for VectorIO by @ezimuel in https://github.com/llamastack/llama-stack/pull/4007
* fix: enable vector store registration from config with OpenAI metadata by @are-ces in https://github.com/llamastack/llama-stack/pull/4616
* docs: Update RAG Agent Documentation using vector_stores by @robinnarsinghranabhat in https://github.com/llamastack/llama-stack/pull/4485
* chore(github-deps): bump github/codeql-action from 4.31.9 to 4.31.10 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4640
* chore(github-deps): bump actions/cache from 5.0.1 to 5.0.2 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4639
* chore(github-deps): bump docker/setup-buildx-action from 3.11.1 to 3.12.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4638
* chore(github-deps): bump actions/setup-node from 6.1.0 to 6.2.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4637
* fix: update responses limitations doc to track latest state by @iamemilio in https://github.com/llamastack/llama-stack/pull/4392
* feat: Convert scoring API to use a FastAPI router by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4521
* fix: Removed unused para for test score by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4645
* fix: fix list-deps quoting in deps-only output by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4653
* feat(api): Implement connector support via static configuration  by @jaideepr97 in https://github.com/llamastack/llama-stack/pull/4263
* fix: default ollama URL in Quickstart was incorrect in 2 places by @damian0815 in https://github.com/llamastack/llama-stack/pull/4646
* fix: unregister function first before register by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4473
* feat!: migrate safety API to FastAPI router by @r-bit-rry in https://github.com/llamastack/llama-stack/pull/4643
* feat: convert prompts API to use a FastAPI router by @nathan-weinberg in https://github.com/llamastack/llama-stack/pull/4649
* feat: add scheduled CI workflow for release branches by @cdoern in https://github.com/llamastack/llama-stack/pull/4510
* fix: Fix redundant MCP tools/list calls by @jwm4 in https://github.com/llamastack/llama-stack/pull/4634
* docs: Move demo script to step 3 for quick start by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4661
* feat: convert scoring_functions API to use FastAPI router. by @EleanorWho in https://github.com/llamastack/llama-stack/pull/4599
* feat(ci): add Bedrock integration tests with record/replay by @skamenan7 in https://github.com/llamastack/llama-stack/pull/4292
* feat: Core Changes for default embedding dims by @rriley99-oci in https://github.com/llamastack/llama-stack/pull/4671
* fix: use `SecretStr` for AWS credentials by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/4681
* feat: Implemented reasoning.effort parameter in LLS Responses by @Nehanth in https://github.com/llamastack/llama-stack/pull/4633
* fix: file_search_call results missing document attributes/metadata by @are-ces in https://github.com/llamastack/llama-stack/pull/4680
* fix!: usage input_token_details and output_token_details are not optional by @mattf in https://github.com/llamastack/llama-stack/pull/4690
* fix: completed_at is required output by @mattf in https://github.com/llamastack/llama-stack/pull/4692
* fix: store is required output by @mattf in https://github.com/llamastack/llama-stack/pull/4693
* docs: update contrib guidelines on PR reviews by @leseb in https://github.com/llamastack/llama-stack/pull/4676
* docs: require test plan with script and output for API PRs by @leseb in https://github.com/llamastack/llama-stack/pull/4659
* feat: Add OpenAI API conformance coverage analyzer by @leseb in https://github.com/llamastack/llama-stack/pull/4668
* feat!: use global vertext API endpoint by @ktdreyer in https://github.com/llamastack/llama-stack/pull/4674
* fix: Concurrent calls into SentenceTransformer() cause failures of client.vector_stores.file_batches.create() by @syedriko in https://github.com/llamastack/llama-stack/pull/4636
* feat(PGVector): use HNSW index for embedding column in a vector store table in PGVector by @r3v5 in https://github.com/llamastack/llama-stack/pull/4696
* feat(PGVector): implement removal of vector store metadata from PGVector metadata_store table when unregister vector store by @r3v5 in https://github.com/llamastack/llama-stack/pull/4678
* feat: Add shutdown functionality to LlamaStackAsLibraryClient and AsyncLlamaStackAsLibraryClient by @syedriko in https://github.com/llamastack/llama-stack/pull/4642
* docs: add Bedrock inference example notebook by @skamenan7 in https://github.com/llamastack/llama-stack/pull/4586
* feat(ci): Add basic integration tests for reasoning using vllm by @s-akhtar-baig in https://github.com/llamastack/llama-stack/pull/4682
* feat: add PyPI publishing workflow for llama-stack and llama-stack-api by @cdoern in https://github.com/llamastack/llama-stack/pull/4667
* docs: Microsoft Agent Framework - llama stack by @omaryashraf5 in https://github.com/llamastack/llama-stack/pull/4245
* feat(PGVector): implement automatic creation of vector extension during initialization of PGVectorVectorIOAdapter by @r3v5 in https://github.com/llamastack/llama-stack/pull/4660
* chore(github-deps): bump pypa/gh-action-pypi-publish from 1.12.4 to 1.13.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4725
* chore(github-deps): bump astral-sh/setup-uv from 6.0.1 to 7.2.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4723
* chore(github-deps): bump actions/setup-node from 6.1.0 to 6.2.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4721
* chore(github-deps): bump actions/upload-artifact from 4.6.2 to 6.0.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4720
* chore(github-deps): bump actions/setup-python from 5.6.0 to 6.2.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4719
* fix: Update reasoning content field to ensure compatibility with ollama and vllm by @s-akhtar-baig in https://github.com/llamastack/llama-stack/pull/4715
* feat: Add endpoint authorization with YAML config by @derekhiggins in https://github.com/llamastack/llama-stack/pull/4448
* feat: Refactor Agents API to use FastAPI Router by @skamenan7 in https://github.com/llamastack/llama-stack/pull/4376
* test(ci): add ABAC testing with files API to auth tests by @derekhiggins in https://github.com/llamastack/llama-stack/pull/4328
* docs: Updated quick start guide by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4435
* feat(PGVector): allow users to configure distance metric and HNSW index parameters for PGVector in Llama Stack YAML config by @r3v5 in https://github.com/llamastack/llama-stack/pull/4714
* fix: formatting of pypi.yml by @cdoern in https://github.com/llamastack/llama-stack/pull/4739
* feat(server): route vector-io via FastAPI router by @skamenan7 in https://github.com/llamastack/llama-stack/pull/4595
* fix!: OpenAI API conformance for `POST /embeddings` endpoint by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/4644
* fix: CI after #4644 by @cdoern in https://github.com/llamastack/llama-stack/pull/4741
* fix: Enabled blog for llamastack by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4467
* fix!: finish_reason now complies with OpenAI  by @leseb in https://github.com/llamastack/llama-stack/pull/4679
* fix: Remove unused scope-based endpoint authorization feature by @derekhiggins in https://github.com/llamastack/llama-stack/pull/4734
* chore(ci): harden stainless-builds workflow for pull_request_target by @dgellow in https://github.com/llamastack/llama-stack/pull/4597
* feat(ci): add API conformance check to pre-commit by @nathan-weinberg in https://github.com/llamastack/llama-stack/pull/4664
* fix: make release-branch-scheduled-ci compatible with older branches by @cdoern in https://github.com/llamastack/llama-stack/pull/4753
* fix: address security vulnerabilities in GitHub Actions workflows by @cdoern in https://github.com/llamastack/llama-stack/pull/4752
* fix: Enable session polling during streaming responses by @rhuss in https://github.com/llamastack/llama-stack/pull/4738
* fix: pass branch explicitly to install-llama-stack-client action by @cdoern in https://github.com/llamastack/llama-stack/pull/4759
* feat: Complete support for parallel_tool_calls in LLS Responses by @s-akhtar-baig in https://github.com/llamastack/llama-stack/pull/4608
* feat: implement fastapi router for connectors API by @jaideepr97 in https://github.com/llamastack/llama-stack/pull/4402
* chore(benchmark): add vertical scaling benchmark by @mattf in https://github.com/llamastack/llama-stack/pull/4477
* feat(storage): make responses table name configurable by @ChristianZaccaria in https://github.com/llamastack/llama-stack/pull/4764
* feat: migrate Inference API to FastAPI router system by @r-bit-rry in https://github.com/llamastack/llama-stack/pull/4755
* fix: trim whitespace from discovered branch names by @cdoern in https://github.com/llamastack/llama-stack/pull/4773
* feat: Add max_output_tokens to Response API by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4592
* fix: prevent MDX build failure in OpenAI conformance report by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4737
* feat(PGVector): add support for IVFFlat vector index for ANN search in PGVector by @r3v5 in https://github.com/llamastack/llama-stack/pull/4772
* feat(ci): unify PyPI/npm release workflow with dry-run support by @cdoern in https://github.com/llamastack/llama-stack/pull/4774
* fix: install setuptools-scm in CI by @cdoern in https://github.com/llamastack/llama-stack/pull/4782
* feat: Add comprehensive network configuration for remote inference providers by @leseb in https://github.com/llamastack/llama-stack/pull/4748
* feat: ensure connector CRUD via config + readonly API methods  by @jaideepr97 in https://github.com/llamastack/llama-stack/pull/4760
* chore: Added ge for max_tool_calls and max_output_tokens by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4780
* fix: override version from release tag for all packages by @cdoern in https://github.com/llamastack/llama-stack/pull/4788
* chore: bump fallback_version to 0.4.5.dev0 by @cdoern in https://github.com/llamastack/llama-stack/pull/4790
* refactor: Part 1 - Introduce rerankers and fix tests for existing search modes  by @varshaprasad96 in https://github.com/llamastack/llama-stack/pull/4456
* chore(github-deps): bump sigstore/gh-action-sigstore-python from 3.0.1 to 3.2.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4797
* chore(github-deps): bump actions/download-artifact from 4.3.0 to 7.0.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4798
* chore(github-deps): bump github/codeql-action from 4.31.10 to 4.32.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4799
* chore(github-deps): bump depends-on/depends-on-action from 61cb3f4a0e2c8ae4b90c9448dc57c7ba9ca24c35 to 826c144163ac67bf08347590a5f81afd45da63ca by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4800
* chore(github-deps): bump llamastack/llama-stack from 306e43f882fdfbaf877f989f0c1ea900c6348055 to 76bcb6657de312160c726fbe069275cd5537b702 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/4803
* fix: suppress tar pipe error in npm dry-run verification by @cdoern in https://github.com/llamastack/llama-stack/pull/4796
* feat(api): add backward compatibility for Eval API method signatures by @saichandrapandraju in https://github.com/llamastack/llama-stack/pull/4683
* feat: Implement run_moderation for all safety providers with NotImplementedError  by @m-misiura in https://github.com/llamastack/llama-stack/pull/4662
* feat(new provider): Adding OCI 26ai Vector Support by @rriley99-oci in https://github.com/llamastack/llama-stack/pull/4411
* fix: MCP CPU spike by using context manager for session cleanup by @jwm4 in https://github.com/llamastack/llama-stack/pull/4758
* feat(PGVector): implement validation for embedding dimensions when creating a vector index for ANN search in pgvector by @r3v5 in https://github.com/llamastack/llama-stack/pull/4732
* fix(provider-codegen): prevent env var secrets from leaking into generated docs by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/4658
* chore: remove inline reference inference implementation by @mattf in https://github.com/llamastack/llama-stack/pull/4828
* chore: prune llama_stack.models package by @mattf in https://github.com/llamastack/llama-stack/pull/4829
* fix: unify version computation for all packages in pypi workflow by @cdoern in https://github.com/llamastack/llama-stack/pull/4810
* fix: bump fallback version by @cdoern in https://github.com/llamastack/llama-stack/pull/4832
* fix(pypi): auto-detect release branch for client repo checkouts by @cdoern in https://github.com/llamastack/llama-stack/pull/4831
* chore: prune unused inference utils by @mattf in https://github.com/llamastack/llama-stack/pull/4836
* feat: Adds support for the `safety_identifier` parameter by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4793
* chore: reduce use of sku_types by @mattf in https://github.com/llamastack/llama-stack/pull/4838
* fix: remove params={} from safety integration tests by @cdoern in https://github.com/llamastack/llama-stack/pull/4842
* chore: pin llama-stack-client to 0.5.0 for release by @cdoern in https://github.com/llamastack/llama-stack/pull/4841

## New Contributors
* @gmatuz made their first contribution in https://github.com/llamastack/llama-stack/pull/4462
* @eoinfennessy made their first contribution in https://github.com/llamastack/llama-stack/pull/4468
* @lalexandrh made their first contribution in https://github.com/llamastack/llama-stack/pull/4524
* @ezimuel made their first contribution in https://github.com/llamastack/llama-stack/pull/4007
* @robinnarsinghranabhat made their first contribution in https://github.com/llamastack/llama-stack/pull/4485
* @damian0815 made their first contribution in https://github.com/llamastack/llama-stack/pull/4646
* @EleanorWho made their first contribution in https://github.com/llamastack/llama-stack/pull/4599
* @saichandrapandraju made their first contribution in https://github.com/llamastack/llama-stack/pull/4683
* @m-misiura made their first contribution in https://github.com/llamastack/llama-stack/pull/4662

**Full Changelog**: https://github.com/llamastack/llama-stack/compare/v0.4.4...v0.5.0