v1.0.2

What's Changed

• chore: update ogx-client to ^1.0.1 in UI lockfile by @cdoern in #5840
• fix(storage): reset SQL engines after temp event loop init (backport #5837) by @mergify[bot] in #5841

Full Changelog: v1.0.1...v1.0.2

v1.0.1

What's Changed

• chore: update ogx-client to ^1.0.0 in UI lockfile by @cdoern in #5812
• perf(routers): parallelize health and vector store fan-out (backport #5802) by @mergify[bot] in #5818
• fix(storage): asyncio.Lock for SQLStore and MongoDB expiration enforcement (backport #5803) by @mergify[bot] in #5824
• fix: Harden secret handling and passthrough fallbacks (backport #5799) by @mergify[bot] in #5825
• fix: improve async safety in routers and Redis KV reads (backport #5800) by @mergify[bot] in #5823
• fix(providers): async safety fixes for Databricks, WatsonX, Bing, Tavily, OCI, OpenAI Files (backport #5828) by @mergify[bot] in #5829
• fix(milvus): Handle missing collections in query/delete paths (backport #5836) by @mergify[bot] in #5838

Full Changelog: v1.0.0...v1.0.1

v1.0.0

What's Changed

• feat(file_processors): add inline::auto composite file processor by @leseb in #5673
• chore(github-deps): bump github/codeql-action from 4.35.2 to 4.35.3 by @dependabot[bot] in #5679
• fix(ollama): tolerate dict-backed reasoning messages in OpenAI preprocessing by @skamenan7 in #5638
• chore: bump fallback_version to 0.8.1.dev0 by @cdoern in #5685
• fix(vector_io): improve error reporting for file processor rejections by @leseb in #5690
• feat(docs): redesign provider cards, DocCardList, and tables site-wide by @leseb in #5694
• feat(cli): add top-level 'ogx run' and 'ogx letsgo' shortcuts by @leseb in #5689
• feat(file_processors): add inline::markitdown provider and wire into auto dispatcher by @leseb in #5688
• fix(deps): add missing dependencies to starter extra by @zy1o in #5674
• perf(responses): batch guardrail checks during streaming by @leseb in #5664
• fix(openai): clamp max_tokens to per-model limits to prevent overflow errors by @leseb in #5696
• feat(letsgo): use inline::auto file processor by @mattf in #5704
• ci(integration-tests): run only server client on PRs by @leseb in #5697
• feat(letsgo): add Claude Code compatibility by @mattf in #5709
• docs(claude-code): fix incorrect --model examples and clarify routing by @leseb in #5692
• feat(inference): add chat completion message listing endpoint. by @skamenan7 in #5459
• fix(auth): fetch GitHub org memberships for RBAC attribute mapping by @leseb in #5711
• feat(landing): add CLI showcase section for Claude Code, Codex, and OpenCode by @leseb in #5716
• fix: stale llama_stack log ref by @cdoern in #5717
• fix(python-deps): added missing dev group dependencies by @zy1o in #5708
• fix(ci): allow conventional commit scope in breaking-change ack regex by @cdoern in #5718
• fix(chore): cleanup integration-tests action ref after rename by @zy1o in #5721
• fix(test): fix hardcoded relative path in persistance test by @zy1o in #5722
• fix(auth): respect verify_tls in OAuth2 introspection by @leseb in #5710
• fix(storage): propagate real add-column errors in sqlstore by @leseb in #5713
• fix(responses): honor include on input item retrieval. by @skamenan7 in #5605
• fix(deps): move CVE-pinned transitive deps to constraint-dependencies by @leseb in #5707
• fix(storage): filter expired rows in PostgreSQL keys_in_range() by @leseb in #5712
• fix(auth): Return 503 only for auth service outages by @leseb in #5715
• fix(nvidia-safety): use provider_resource_id instead of shield_id for NeMoGuardrails model by @VANDRANKI in #5726
• fix(vertexai): preserve reasoning_content as thought parts in multi-turn conversations by @major in #5677
• fix(cli): remove ogx stack rm command due to lack of CLI discovery by @leseb in #5735
• test(storage): add unit tests for PostgresKVStoreImpl by @leseb in #5730
• fix(storage): add namespace support and expiration filtering to all kvstore backends by @leseb in #5731
• feat(ogx-api): introduce ogx_api.provider and ogx_api.types namespaces by @cdoern in #5740
• fix(deps): address critical and high severity security vulnerabilities by @leseb in #5742
• refactor(storage): replace psycopg2 with asyncpg in PostgreSQL KV store by @leseb in #5739
• ci: reduce GitHub Actions runner usage for free-plan constraints by @leseb in #5751
• fix(conversations): compute has_more and support cursor pagination in list_items by @vamsi-01 in #5612
• refactor(api)!: deprecate Safety run-shield and Shields list/get endpoints#22 by @rhdedgar in #5744
• fix: strip per-chunk usage from Gemini streaming responses to prevent token overcounting by @mattf in #5171
• fix(ci): add all ollama variants to the re-record workflow by @leseb in #5746
• feat(conversations): enhance OpenAI API coverage for conversations by @leseb in #5748
• feat!: multi-tenancy core for MaaS deployments by @franciscojavierarceo in #5756
• ci(security): add Python SAST via Ruff bandit rules and CodeQL scanning by @leseb in #5738
• fix(http): configure explicit timeouts and improve connection pooling by @leseb in #5737
• fix(ci): pin record-integration-tests action refs to merge commit SHA by @leseb in #5762
• docs(website): update landing page to promote library mode by @leseb in #5761
• feat(connectors,batches)!: migrate KVStore to AuthorizedSqlStore by @franciscojavierarceo in #5757
• chore(github-deps): bump github/codeql-action from 4.35.3 to 4.35.4 by @dependabot[bot] in #5766
• feat(files): enhance OpenAI API coverage for Files API by @leseb in #5747
• fix(deps): bump constraint-dependencies in ogx_api to resolve Dependabot alerts by @leseb in #5778
• fix(nvidia): use proper URL parsing instead of substring check for hostname validation by @leseb in #5777
• fix(deps): patch high-severity CVEs in python-multipart, protobuf, lxml, and npm packages by @leseb in #5775
• refactor: remove dead code across the codebase by @leseb in #5779
• docs(api): document datatype stability and ogx-api package surfaces by @cdoern in #5719
• docs(blog): add consistent agentic API layer blog post by @leseb in #5687
• fix(ci): break record-integration-tests feedback loop by @cdoern in #5781
• fix(core): make OGXAsLibraryClient thread-safe by @zy1o in #5773
• feat(storage)!: enforce AuthorizedSqlStore usage for APIs requiring access control by @leseb in #5776
• refactor(connectors)!: move connector routes to /v1alpha/admin/connectors by @mattf in #5659
• refactor(server): adopt gateway-first architecture for edge concerns by @leseb in #5750
• ci(auth): add GitHub Actions workflow for prompts tenant isolation tests by @franciscojavierarceo in #5758
• refactor(tools)!: move /v1/tools route to /v1/admin/tools by @leseb in #5787
• feat(interactions): add previous_interaction_id for multi-turn conversations by @leseb in #5669
• refactor!: remove Safety API and replace with moderation_endpoint by @leseb in #5291
• fix(tests): Use provider_type instead of provider_id for vector-io test parametrization by @franciscojavierarceo in #5263
• fix(vector_io): set WAL mode and busy_timeout on sqlite-vec connections by @extrasmall0 in #5428
• fix: change logprobs type from bool to int in Completions endpoint by @extrasmall0 in #5343
• feat(vector_io): add tenant isolation for vector store metadata by @franciscojavierarceo in #5782
• feat(letsgo): add Gemini and Azure support by @mattf in #5706
• perf(storage): use asyncpg connection pool in PostgreSQL kvstore by @derekhiggins in #5734
• feat!: multi-SDK response shapes for /v1/models by @leseb in #5522

New Contributors

• @zy1o made their first contribution in #5674
• @VANDRANKI made their first contribution in #5726
• @vamsi-01 made their first contribution in #5612
• @extrasmall0 made their first contribution in #5428

Full Changelog: v0.8.0...v1.0.0

v0.8.0

What's Changed

• chore: bump fallback_version to 0.7.1.dev0 by @cdoern in #5414
• ci: remove starter-gpu and dell from Docker image build matrix by @cdoern in #5413
• docs: add release notes for version 0.7.0 by @Artemon-line in #5408
• docs: fix documentation inconsistencies, stale references, and broken links by @leseb in #5411
• fix(security): Pin tornado>=6.5.5 (GHSA-qjxf-f2mg-c6mc) by @nathan-weinberg in #5425
• docs: comprehensive documentation overhaul and starter extra by @leseb in #5423
• fix(vector_io): wire file_processors provider into vector store file insertion by @alinaryan in #5339
• fix(vector_io): honor default_search_mode config and fix sqlite-vec BM25 score inversion by @franciscojavierarceo in #5445
• docs: blog post for mlflow observability by @gyliu513 in #5444
• feat(messages): add native Anthropic Messages API (/v1/messages) by @cdoern in #5386
• docs: enhance landing page and docs theme by @leseb in #5461
• ci: auto-bump client versions if they already exist on PyPI/npm by @cdoern in #5463
• refactor!: remove deprecated Eval API and related APIs by @leseb in #5290
• chore(github-deps): bump actions/github-script from 7.1.0 to 8.0.0 by @dependabot[bot] in #5433
• chore(github-deps): bump github/codeql-action from 4.32.6 to 4.35.1 by @dependabot[bot] in #5434
• chore(github-deps): bump actions/upload-artifact from 6.0.0 to 7.0.0 by @dependabot[bot] in #5439
• chore(github-deps): bump actions/download-artifact from 8.0.0 to 8.0.1 by @dependabot[bot] in #5440
• docs: split landing page endpoints into OpenAI, Anthropic, and native sections by @leseb in #5465
• chore(github-deps): bump llamastack/llama-stack from 2b0ece2 to 725a0c3 by @dependabot[bot] in #5437
• fix: remove orphan OpenAPI tags for deleted eval/scoring/dataset APIs by @leseb in #5467
• fix: remove empty sidebar categories breaking docs build by @leseb in #5470
• test: add langchain/langgraph responses integration tests by @msager27 in #4887
• fix: initialize tool call arguments to "" instead of "{}" in streaming by @NickGagan in #5462
• docs: update architecture diagram to reflect full API surface by @leseb in #5468
• docs: add Anthropic SDK example with two-level SDK toggle on landing page by @leseb in #5473
• fix(ci): map workflow package names to actual PyPI/npm package names by @cdoern in #5482
• feat(ui): add missing dashboard pages and migrate chat to Responses API by @leseb in #5481
• docs: comprehensive docs UX improvements by @leseb in #5475
• fix: filter schemas by references in deprecated spec by @leseb in #5485
• fix: improve Vector Stores OpenAI API conformance by @leseb in #5398
• feat: add conversation compaction support to Responses API by @franciscojavierarceo in #5327
• chore: bump fallback_version to 0.7.2.dev0 by @cdoern in #5486
• fix(conformance): improve OpenAI API conformance score from 89.1% to 91.2% by @franciscojavierarceo in #5490
• fix!: remove nullable annotations from Responses fields to match OpenAI spec by @franciscojavierarceo in #5494
• fix: improve OpenAI API conformance by keeping type object on schemas by @leseb in #5498
• fix: address unresolved review comments from PyPDF File Processor PR#4743 by @RobuRishabh in #5173
• fix: improve OpenAI API conformance for Models and Files by @leseb in #5499
• docs: redesign landing page and align docs with project moat by @leseb in #5500
• chore: remove broken GitHub Discussions link by @nathan-weinberg in #5502
• docs: add issue reporting section to docs landing page by @nathan-weinberg in #5503
• docs: add Docker Hub link to documentation footer Resources section by @nathan-weinberg in #5505
• docs: improve landing page mobile UX and add animations by @leseb in #5506
• fix(docs): align dropdown menu background with teal color scheme by @leseb in #5508
• build(vertexai): add google-genai>=1.69.0 version floor by @major in #5455
• docs: Updated starter configuration by @rigazilla in #5495
• feat(vertexai): wire up service_tier parameter to Gemini API by @major in #5453
• fix(responses): store compacted responses for previous_response_id chaining by @franciscojavierarceo in #5507
• feat: enable native messages for vllm by @cdoern in #5510
• feat: add Google Interactions API front-end (v1alpha) by @leseb in #5488
• fix(docs): fix architecture SVG tagline overlap and update API branding by @leseb in #5516
• feat(messages): add native count_tokens support for passthrough providers by @cdoern in #5511
• feat: add Google Interactions API front-end with Gemini passthrough by @leseb in #5513
• feat(evals): add multitenant security and retrieval quality benchmarks by @varshaprasad96 in #5515
• feat(docs): add Google Interactions API coverage analyzer by @leseb in #5519
• test(interactions): add integration tests using Google GenAI SDK by @leseb in #5517
• feat(docs): add Anthropic Messages API conformance tracking by @leseb in #5520
• docs(messages): clarify provider description with passthrough and translation modes by @leseb in #5518
• feat: add mlflow support for llamastack by @gyliu513 in #5409
• ci: auto-trigger docs site deploy when docs change on main by @leseb in #5526
• chore(mypy): add type hints to remaining CLI module files by @Elbehery in #5399
• chore(github-deps): bump llamastack/llama-stack from 725a0c3 to e92196d by @dependabot[bot] in #5530
• chore(github-deps): bump actions/upload-artifact from 7.0.0 to 7.0.1 by @dependabot[bot] in #5532
• chore(github-deps): bump docker/login-action from 4.0.0 to 4.1.0 by @dependabot[bot] in #5533
• chore(github-deps): bump docker/build-push-action from 7.0.0 to 7.1.0 by @dependabot[bot] in #5534
• docs: remove leftover TODO comments from getting started notebooks by @aymenhmaidiwastaken in #5514
• build: bump pypdf to ≥6.10.0 in vector_io provider deps by @Ygnas in #5523
• chore(deps): bump next from 15.5.7 to 15.5.15 in /src/llama_stack_ui by @dependabot[bot] in #5528
• chore(github-deps): bump pypa/gh-action-pypi-publish from 1.13.0 to 1.14.0 by @dependabot[bot] in #5529
• docs: clean up footer links and rename OpenAI label by @leseb in #5524
• docs: add interactive Responses API flow simulator by @leseb in #5540
• fix(ci): add --group test to unused recordings check by @leseb in #5541
• docs(telemetry): expand observability docs with metrics reference and setup guide by @leseb in #5525
• fix(docs): add missing sidebar icons and fix 404s for API tags by @leseb in #5539
• fix(docs): remove dead API links and add missing OpenAPI tags by @leseb in #5543
• fix(docs): updated "Get started" commands in README by @nathan-weinberg in #5547
• docs: expand integration test instructions in AGENTS.md by @franciscojavierarceo in #5509
• fix(logging): log registry refresh cancel as warning by @nathan-weinberg in #5548
• fix(ci): pin semgrep for UBI9 glibc 2.34 compatibility by @leseb in #5552
• fix(docs): consolidate sidebar and polish navbar icons by @leseb in #5553
• feat(config): allow model registry refresh interval to be configurable by @nathan-weinberg in #5558
• feat(messages): implement prompt caching metrics tracking by @cdoern in #5469
• docs: add Codex CLI integrati...

v0.7.1

What's Changed

• chore: update llama-stack-client to ^0.7.0 in UI lockfile by @cdoern in #5415
• fix: add [starter] pip extra for zero-install experience (backport) by @leseb in #5424
• fix: initialize tool call arguments to "" instead of "{}" in streaming (backport #5462) by @mergify[bot] in #5474
• ci: auto-bump client versions if they already exist on PyPI/npm (backport #5463) by @mergify[bot] in #5476

Full Changelog: v0.7.0...v0.7.1

v0.7.0

What's Changed

• fix: exclude informational checks from ci-status aggregation by @leseb in #5105
• feat: add Responses API test coverage analyzer and conformance annotations by @leseb in #5101
• refactor!: remove fine_tuning API by @leseb in #5104
• fix!: remove duplicate dataset_id parameter in append-rows endpoint by @eoinfennessy in #4849
• fix: Multi-worker cache synchronization for vector stores by @elinacse in #5076
• feat: Add integration test for service_tier with openai client by @gyliu513 in #5103
• feat: test responses API integration tests against Azure AI Foundry by @iamemilio in #5107
• fix(security): add path traversal and header injection defenses by @rhdedgar in #5086
• feat!: Part 2 - implement inline neural rerank for RAG by @r3v5 in #4877
• feat: add provider compatibility matrix for Responses API by @leseb in #5113
• perf: lazy-load braintrust autoevals to reduce idle memory (~63MB) by @leseb in #5078
• feat: add provider version tracking to compatibility matrix by @leseb in #5115
• perf: lazy-load torch in embedding_mixin to reduce startup memory by @leseb in #5116
• perf: lazy-load torch and transformers in prompt_guard by @leseb in #5117
• perf: lazy-load numpy, faiss, and sqlite_vec in vector_io providers by @leseb in #5118
• fix(CI): reduce Mergify PR update frequency by @gyliu513 in #5106
• feat: Add support for filters in PGVector and replace f-string usage in table name by @franciscojavierarceo in #5111
• fix: bump pyjwt to 2.12.0 (CVE-2026-32597) by @eoinfennessy in #5127
• fix(inference): improve chat completions OpenAI conformance by @cdoern in #5108
• fix(storage): resolve asyncio event loop mismatch via operation deferral by @derekhiggins in #5130
• fix(ci): use RELEASE_PAT and PRs in post-release workflow by @cdoern in #5132
• chore: bump fallback_version to 0.6.1.dev0 by @cdoern in #5136
• fix: remove UV_EXTRA_INDEX_URL from Release branch ci by @cdoern in #5138
• fix(ci): add uv lock to post-release workflow to update stale lockfile by @cdoern in #5139
• chore(github-deps): bump stainless-api/upload-openapi-spec-action from 1.11.6 to 1.13.0 by @dependabot[bot] in #5148
• chore(github-deps): bump docker/setup-buildx-action from 3.12.0 to 4.0.0 by @dependabot[bot] in #5142
• chore(github-deps): bump astral-sh/setup-uv from 7.3.1 to 7.5.0 by @dependabot[bot] in #5143
• feat(blog): Agentic flows tutorial by @raghotham in #5035
• chore(github-deps): bump docker/login-action from 3.7.0 to 4.0.0 by @dependabot[bot] in #5146
• chore(github-deps): bump llamastack/llama-stack from ce063ac to 2157c09 by @dependabot[bot] in #5145
• feat: Add OpenAI client integration test for top_logprobs by @gyliu513 in #5124
• ci(mergify): skip conflict comments on stale PRs by @leseb in #5156
• feat: Add stream_options parameter support by @gyliu513 in #4815
• feat: promote connector API from v1alpha to v1beta by @leseb in #5129
• refactor: replace LiteLLM with OpenAI mixin for WatsonX provider by @leseb in #5133
• fix: optimize connector listing by @gyliu513 in #5164
• feat: Add OpenAI client integration test for incomplete_details by @gyliu513 in #5157
• refactor!: rename meta-reference providers to builtin by @leseb in #5131
• feat!: eliminate /files/{file_id} GET differences by @r3v5 in #5154
• feat: Add OpenAI client integration test for reasoning effort by @gyliu513 in #5170
• fix: replace blocking requests calls with async httpx in remote providers by @gyliu513 in #5162
• fix: remove references to defunct inline::builtin inference provider by @leseb in #5174
• fix(vertexai): use SDK-native model names instead of stripping prefixes by @major in #5169
• docs: add multi-tenant isolation example for conversations and responses by @jaideepr97 in #5176
• fix: Remove duplicate decode by @gyliu513 in #5177
• refactor: decouple file_search from legacy knowledge_search tool_groups by @leseb in #5175
• feat: add configurable asyncpg connection pool settings by @iamemilio in #5160
• chore: remove unused LiteLLMOpenAIMixin by @mattf in #5159
• fix: Disable asyncpg OTel auto-instrumentation to prevent duplicate DB spans by @iamemilio in #5158
• refactor!: rename knowledge_search to file_search across codebase by @leseb in #5186
• fix: re-enable external provider module test by @cdoern in #5182
• feat: add WatsonX Responses API integration test recordings by @leseb in #5120
• feat: Add metrics for vector io by @gyliu513 in #5096
• refactor: rename rag-runtime provider and builtin::rag toolgroup to file-search by @leseb in #5187
• feat: auto-record integration tests on PRs with multi-provider support by @cdoern in #5123
• fix: update recording workflow action SHAs to include skip-commit support by @cdoern in #5199
• fix: support workflow_dispatch in commit-recordings via PR metadata artifact by @cdoern in #5202
• fix: bump pyasn1 to 0.6.3 (CVE-2026-30922) by @eoinfennessy in #5207
• docs: Add post about Responses API in Llama Stack by @jwm4 in #5196
• fix: support fork PRs in commit-recordings workflow by @cdoern in #5204
• fix: clean up artifacts before cloning fork PR branch by @cdoern in #5212
• fix: handle both artifact structures for recordings copy by @cdoern in #5214
• chore: rename bug template by @leseb in #5210
• fix: only comment on PR when recordings are actually pushed by @cdoern in #5218
• fix: prevent OTel context leak in fire-and-forget background tasks by @iamemilio in #5168
• fix: provider_data_var context leak by @jaideepr97 in #5227
• chore: Update formatting in CONTRIBUTING.md by @raghotham in #5231
• chore(github-deps): bump actions/cache from 5.0.3 to 5.0.4 by @dependabot[bot] in #5241
• chore(github-deps): bump actions/upload-artifact from 4.6.2 to 7.0.0 by @dependabot[bot] in #5235
• chore(github-deps): bump docker/build-push-action from 6.19.2 to 7.0.0 by @dependabot[bot] in #5236
• chore(github-deps): update llamastack/llama-stack requirement to 700b202 by @dependabot[bot] in #5239
• chore(github-deps): bump docker/setup-qemu-action from 3.7.0 to 4.0.0 by @dependabot[bot] in #5234
• feat!: BREAKING CHANGE: make sentence_transformers trust_remote_code configurable, default to False by @derekhiggins in #4602
• docs: add architecture documentation and module-level READMEs by @leseb in #5213
• refactor!: remove tool_groups from public API and auto-register from provider specs by @leseb in #4997
• docs: add AGENTS.md with gui...

v0.6.1

What's Changed

• fix: remove UV_EXTRA_INDEX_URL from Release branch ci (backport #5138) by @mergify[bot] in #5140
• chore: update llama-stack-client to ^0.6.0 in UI lockfile by @cdoern in #5137
• fix(storage): resolve asyncio event loop mismatch via operation deferral (#5130) by @derekhiggins in #5135
• feat(blog): Agentic flows tutorial (backport #5035) by @mergify[bot] in #5167
• fix: milvus hybrid ranker usage (backport #5312) by @mergify[bot] in #5368

Full Changelog: v0.6.0...v0.6.1

v0.6.0

What's Changed

• chore: update convert_tooldef_to_openai_tool to match its usage by @mattf in #4837
• feat!: improve consistency of post-training API endpoints by @eoinfennessy in #4606
• fix: Arbitrary file write via a non-default configuration by @VaishnaviHire in #4844
• chore: reduce uses of models.llama.datatypes by @mattf in #4847
• docs: add technical release steps and improvements to RELEASE_PROCESS.md by @cdoern in #4792
• chore: bump fallback version to 0.5.1 by @cdoern in #4846
• fix: Exclude null 'strict' field in function tools to prevent OpenAI … by @gyliu513 in #4795
• chore(test): add test to verify responses params make it to backend service by @mattf in #4850
• chore: revert "fix: disable together banner (#4517)" by @mattf in #4856
• fix: update together to work with latest api.together.xyz service (circa feb 2026) by @mattf in #4857
• chore(github-deps): bump astral-sh/setup-uv from 7.2.0 to 7.3.0 by @dependabot[bot] in #4867
• chore(github-deps): bump github/codeql-action from 4.32.0 to 4.32.2 by @dependabot[bot] in #4861
• chore(github-deps): bump actions/cache from 5.0.2 to 5.0.3 by @dependabot[bot] in #4859
• chore(github-deps): bump llamastack/llama-stack from 76bcb66 to c518b35 by @dependabot[bot] in #4858
• fix(ci): ensure oasdiff is available for openai-coverage hook by @EleanorWho in #4835
• fix: Deprecate items when create conversation by @gyliu513 in #4765
• chore: refactor chunking to use configurable tiktoken encoding and document tokenizer limits by @mattf in #4870
• chore: prune unused parts of models packages (checkpoint, tokenizer, prompt templates, datatypes) by @mattf in #4871
• chore: prune unused utils from utils.memory.vector_store by @mattf in #4873
• fix: Escape special characters in auto-generated provider documentati… by @gyliu513 in #4822
• chore(docs): Use starter for opentelemetry integration test by @gyliu513 in #4875
• fix: kvstore should call shutdown but not close by @gyliu513 in #4872
• fix: uvicorn log ambiguity by @cdoern in #4522
• chore(github-deps): bump actions/checkout from 4.2.2 to 6.0.2 by @dependabot[bot] in #4865
• chore: cleanup mypy excludes by @mattf in #4876
• feat: add integration test for max_output_tokens by @gyliu513 in #4825
• chore(test): add test to verify responses params make it to backend s… by @gyliu513 in #4852
• ci: add Docker image publishing to release workflow by @cdoern in #4882
• feat: add ProcessFileRequest model to file_processors API by @alinaryan in #4885
• docs: update responses api known limitations doc by @jaideepr97 in #4845
• fix(vector_io): align Protocol signatures with request models by @skamenan7 in #4747
• fix: add _ExceptionTranslatingRoute to prevent keep-alive breakage on Linux by @iamemilio in #4886
• docs: add release notes for version 0.5 by @rhuss in #4855
• fix(ci): disable uv cache cleanup when UV_NO_CACHE is set by @cdoern in #4889
• feat: Add truncation parameter support by @gyliu513 in #4813
• chore(ci): bump pinned action commit hashes in integration-tests.yml by @cdoern in #4895
• docs: Add README for running observability test by @gyliu513 in #4884
• fix: update rerank routing to match params by @mattf in #4900
• feat: Add prompt_cache_key parameter support by @gyliu513 in #4775
• chore: add rerank support to recorder by @mattf in #4903
• feat: add rerank support to vllm inference provider by @mattf in #4902
• fix(inference): use flat response message model for chat/completions by @cdoern in #4891
• feat: add llama cpp server remote inference provider by @Bobbins228 in #4382
• fix: Remove pillow as direct dependency by @VaishnaviHire in #4901
• fix: pre-commit run -a by @mattf in #4907
• fix(ci): Removed kotlin from preview builds by @gyliu513 in #4910
• feat: Add service_tier parameter support by @gyliu513 in #4816
• chore(github-deps): bump github/codeql-action from 4.32.2 to 4.32.3 by @dependabot[bot] in #4918
• chore(github-deps): bump docker/login-action from 3.4.0 to 3.7.0 by @dependabot[bot] in #4916
• chore(github-deps): bump llamastack/llama-stack from c7cdb40 to 4c1b03b by @dependabot[bot] in #4915
• chore(github-deps): bump stainless-api/upload-openapi-spec-action from 1.10.0 to 1.11.6 by @dependabot[bot] in #4913
• chore(github-deps): bump docker/build-push-action from 6.15.0 to 6.19.2 by @dependabot[bot] in #4912
• fix(vertexai): raise descriptive error on auth failure instead of silent empty string by @major in #4909
• fix: resolve StorageConfig default env vars at construction time by @major in #4897
• feat: Add incomplete_details response property by @gyliu513 in #4812
• feat(client-sdks): add OpenAPI Generator tooling by @aegeiger in #4874
• fix(vector_io): eliminate duplicate call for vector store registration by @r3v5 in #4925
• test(vertexai): add unit tests for VertexAI inference adapter by @major in #4927
• feat: introduce new how-to blog by @cdoern in #4794
• chore: remove reference to non-existent WeaviateRequestProviderData by @mattf in #4937
• feat: standardized error types with HTTP status codes by @iamemilio in #4878
• feat: add opentelemetry-distro to core dependencies by @Artemon-line in #4935
• feat(ci): Add nightly job for doc build by @gyliu513 in #4911
• fix: Ensure user isolation for stored conversations and responses by @jaideepr97 in #4834
• fix: align chat completion usage schema with OpenAI spec by @cdoern in #4930
• fix: allow conversation item type to be omitted by @mattf in #4948
• feat: Enable inline PyPDF file_processors provider by @alinaryan in #4743
• feat: add support for /responses background parameter by @cdoern in #4824
• feat(vector_io): Implement Contextual Retrieval for improved RAG search quality by @r-bit-rry in #4750
• chore: use SecretStr for x-llamastack-provider-data keys by @mattf in #4939
• chore: remove unused vector store utils by @mattf in #4961
• feat: auto-identify embedding models for vllm by @mattf in #4975
• chore(github-deps): bump llamastack/llama-stack from 4c1b03b to 7d9786b by @dependabot[bot] in #4971
• chore(github-deps): bump actions/checkout from 6.0.1 to 6.0.2 by @dependabot[bot] in #4969
• chore(github-deps): bump actions/cache from 4.2.0 to 5.0.3 by @dependabot[bot] in #4963
• chore(github-deps): bump github/codeql-action from 4.32.3 to 4.32.4 by @dependabot...

v0.5.2

What's Changed

• chore: bump llama-stack-client to 0.5.1 by @cdoern in #4957
• ci: add arm64 image manifest publishing to release workflow by @rhdedgar in #5006
• feat(ci): automate post-release and pre-release version management (backport #4938) by @mergify[bot] in #5032
• fix(llama-guard): less strict parsing of safety categories (backport #5045) by @mergify[bot] in #5053
• fix: OCI26ai sql query patches (backport #5046) by @mergify[bot] in #5054

Full Changelog: v0.5.1...v0.5.2

v0.5.1

What's Changed

• fix: [release-0.5.x] Arbitrary file write via a non-default configuration (#4844) by @VaishnaviHire in #4869
• fix(vertexai): raise descriptive error on auth failure instead of silent empty string (backport #4909) by @mergify[bot] in #4923
• fix: resolve StorageConfig default env vars at construction time (backport #4897) by @mergify[bot] in #4924
• feat: add opentelemetry-distro to core dependencies (backport #4935) by @mergify[bot] in #4943
• fix(vector_io): eliminate duplicate call for vector store registration (backport #4925) by @mergify[bot] in #4941
• chore: bump version to 0.5.1 for release by @cdoern in #4955

Full Changelog: v0.5.0...v0.5.1