v0.7.0

## What's Changed
* fix: exclude informational checks from ci-status aggregation by @leseb in https://github.com/llamastack/llama-stack/pull/5105
* feat: add Responses API test coverage analyzer and conformance annotations by @leseb in https://github.com/llamastack/llama-stack/pull/5101
* refactor!: remove fine_tuning API by @leseb in https://github.com/llamastack/llama-stack/pull/5104
* fix!: remove duplicate dataset_id parameter in append-rows endpoint by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/4849
* fix: Multi-worker cache synchronization for vector stores by @elinacse in https://github.com/llamastack/llama-stack/pull/5076
* feat: Add integration test for service_tier with openai client by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5103
* feat: test responses API integration tests against Azure AI Foundry by @iamemilio in https://github.com/llamastack/llama-stack/pull/5107
* fix(security): add path traversal and header injection defenses by @rhdedgar in https://github.com/llamastack/llama-stack/pull/5086
* feat!: Part 2 - implement inline neural rerank for RAG by @r3v5 in https://github.com/llamastack/llama-stack/pull/4877
* feat: add provider compatibility matrix for Responses API by @leseb in https://github.com/llamastack/llama-stack/pull/5113
* perf: lazy-load braintrust autoevals to reduce idle memory (~63MB) by @leseb in https://github.com/llamastack/llama-stack/pull/5078
* feat: add provider version tracking to compatibility matrix by @leseb in https://github.com/llamastack/llama-stack/pull/5115
* perf: lazy-load torch in embedding_mixin to reduce startup memory by @leseb in https://github.com/llamastack/llama-stack/pull/5116
* perf: lazy-load torch and transformers in prompt_guard by @leseb in https://github.com/llamastack/llama-stack/pull/5117
* perf: lazy-load numpy, faiss, and sqlite_vec in vector_io providers by @leseb in https://github.com/llamastack/llama-stack/pull/5118
* fix(CI): reduce Mergify PR update frequency by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5106
* feat: Add support for filters in PGVector and replace f-string usage in table name by @franciscojavierarceo in https://github.com/llamastack/llama-stack/pull/5111
* fix: bump pyjwt to 2.12.0 (CVE-2026-32597) by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/5127
* fix(inference): improve chat completions OpenAI conformance by @cdoern in https://github.com/llamastack/llama-stack/pull/5108
* fix(storage): resolve asyncio event loop mismatch via operation deferral by @derekhiggins in https://github.com/llamastack/llama-stack/pull/5130
* fix(ci): use RELEASE_PAT and PRs in post-release workflow by @cdoern in https://github.com/llamastack/llama-stack/pull/5132
* chore: bump fallback_version to 0.6.1.dev0 by @cdoern in https://github.com/llamastack/llama-stack/pull/5136
* fix: remove UV_EXTRA_INDEX_URL from Release branch ci by @cdoern in https://github.com/llamastack/llama-stack/pull/5138
* fix(ci): add uv lock to post-release workflow to update stale lockfile by @cdoern in https://github.com/llamastack/llama-stack/pull/5139
* chore(github-deps): bump stainless-api/upload-openapi-spec-action from 1.11.6 to 1.13.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5148
* chore(github-deps): bump docker/setup-buildx-action from 3.12.0 to 4.0.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5142
* chore(github-deps): bump astral-sh/setup-uv from 7.3.1 to 7.5.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5143
* feat(blog): Agentic flows tutorial by @raghotham in https://github.com/llamastack/llama-stack/pull/5035
* chore(github-deps): bump docker/login-action from 3.7.0 to 4.0.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5146
* chore(github-deps): bump llamastack/llama-stack from ce063acfe127393537cb0a5deb29cd20063c76af to 2157c0903ed748e95f41a2fc3b3a75cb4c469a40 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5145
* feat: Add OpenAI client integration test for top_logprobs by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5124
* ci(mergify): skip conflict comments on stale PRs by @leseb in https://github.com/llamastack/llama-stack/pull/5156
* feat: Add stream_options parameter support by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4815
* feat: promote connector API from v1alpha to v1beta by @leseb in https://github.com/llamastack/llama-stack/pull/5129
* refactor: replace LiteLLM with OpenAI mixin for WatsonX provider by @leseb in https://github.com/llamastack/llama-stack/pull/5133
* fix: optimize connector listing by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5164
* feat: Add OpenAI client integration test for incomplete_details by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5157
* refactor!: rename meta-reference providers to builtin by @leseb in https://github.com/llamastack/llama-stack/pull/5131
* feat!: eliminate /files/{file_id} GET differences by @r3v5 in https://github.com/llamastack/llama-stack/pull/5154
* feat: Add OpenAI client integration test for reasoning effort by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5170
* fix: replace blocking requests calls with async httpx in remote providers by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5162
* fix: remove references to defunct inline::builtin inference provider by @leseb in https://github.com/llamastack/llama-stack/pull/5174
* fix(vertexai): use SDK-native model names instead of stripping prefixes by @major in https://github.com/llamastack/llama-stack/pull/5169
* docs: add multi-tenant isolation example for conversations and responses by @jaideepr97 in https://github.com/llamastack/llama-stack/pull/5176
* fix: Remove duplicate decode by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5177
* refactor: decouple file_search from legacy knowledge_search tool_groups by @leseb in https://github.com/llamastack/llama-stack/pull/5175
* feat: add configurable asyncpg connection pool settings by @iamemilio in https://github.com/llamastack/llama-stack/pull/5160
* chore: remove unused LiteLLMOpenAIMixin by @mattf in https://github.com/llamastack/llama-stack/pull/5159
* fix: Disable asyncpg OTel auto-instrumentation to prevent duplicate DB spans by @iamemilio in https://github.com/llamastack/llama-stack/pull/5158
* refactor!: rename knowledge_search to file_search across codebase by @leseb in https://github.com/llamastack/llama-stack/pull/5186
* fix: re-enable external provider module test by @cdoern in https://github.com/llamastack/llama-stack/pull/5182
* feat: add WatsonX Responses API integration test recordings by @leseb in https://github.com/llamastack/llama-stack/pull/5120
* feat: Add metrics for vector io by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5096
* refactor: rename rag-runtime provider and builtin::rag toolgroup to file-search by @leseb in https://github.com/llamastack/llama-stack/pull/5187
* feat: auto-record integration tests on PRs with multi-provider support by @cdoern in https://github.com/llamastack/llama-stack/pull/5123
* fix: update recording workflow action SHAs to include skip-commit support by @cdoern in https://github.com/llamastack/llama-stack/pull/5199
* fix: support workflow_dispatch in commit-recordings via PR metadata artifact by @cdoern in https://github.com/llamastack/llama-stack/pull/5202
* fix: bump pyasn1 to 0.6.3 (CVE-2026-30922) by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/5207
* docs: Add post about Responses API in Llama Stack by @jwm4 in https://github.com/llamastack/llama-stack/pull/5196
* fix: support fork PRs in commit-recordings workflow by @cdoern in https://github.com/llamastack/llama-stack/pull/5204
* fix: clean up artifacts before cloning fork PR branch by @cdoern in https://github.com/llamastack/llama-stack/pull/5212
* fix: handle both artifact structures for recordings copy by @cdoern in https://github.com/llamastack/llama-stack/pull/5214
* chore: rename bug template by @leseb in https://github.com/llamastack/llama-stack/pull/5210
* fix: only comment on PR when recordings are actually pushed by @cdoern in https://github.com/llamastack/llama-stack/pull/5218
* fix: prevent OTel context leak in fire-and-forget background tasks by @iamemilio in https://github.com/llamastack/llama-stack/pull/5168
* fix: provider_data_var context leak by @jaideepr97 in https://github.com/llamastack/llama-stack/pull/5227
* chore: Update formatting in CONTRIBUTING.md by @raghotham in https://github.com/llamastack/llama-stack/pull/5231
* chore(github-deps): bump actions/cache from 5.0.3 to 5.0.4 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5241
* chore(github-deps): bump actions/upload-artifact from 4.6.2 to 7.0.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5235
* chore(github-deps): bump docker/build-push-action from 6.19.2 to 7.0.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5236
* chore(github-deps): update llamastack/llama-stack requirement to 700b202df7e520c1b19977e97657b3aebc055e56 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5239
* chore(github-deps): bump docker/setup-qemu-action from 3.7.0 to 4.0.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5234
* feat!: BREAKING CHANGE: make sentence_transformers trust_remote_code configurable, default to False by @derekhiggins in https://github.com/llamastack/llama-stack/pull/4602
* docs: add architecture documentation and module-level READMEs by @leseb in https://github.com/llamastack/llama-stack/pull/5213
* refactor!: remove tool_groups from public API and auto-register from provider specs by @leseb in https://github.com/llamastack/llama-stack/pull/4997
* docs: add AGENTS.md with guidelines for AI coding agents by @leseb in https://github.com/llamastack/llama-stack/pull/5211
* refactor: convert tools API to use FastAPI router mechanism by @leseb in https://github.com/llamastack/llama-stack/pull/5246
* feat: add api level request metrics by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5201
* feat: Infinispan vector-io provider by @rigazilla in https://github.com/llamastack/llama-stack/pull/4839
* fix: use vision_model_id for image tests and fix Bedrock logprobs edge cases by @iamemilio in https://github.com/llamastack/llama-stack/pull/5229
* feat: add forward_headers support to inference passthrough provider by @skamenan7 in https://github.com/llamastack/llama-stack/pull/5134
* fix: bump nltk to 3.9.4 (CVE-2026-33236) by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/5259
* feat: add Bedrock to responses CI suite with recordings by @iamemilio in https://github.com/llamastack/llama-stack/pull/5254
* chore: add missing gitignore patterns for Python and TypeScript tooling by @EleanorWho in https://github.com/llamastack/llama-stack/pull/5265
* chore: add conventional-pre-commit for commit validation by @derekhiggins in https://github.com/llamastack/llama-stack/pull/5251
* fix: increase time threshold for flaky vllm async test by @cdoern in https://github.com/llamastack/llama-stack/pull/5270
* chore: trim README for clarity and structure by @EleanorWho in https://github.com/llamastack/llama-stack/pull/5258
* feat: add parameter usage metrics for Responses API by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5255
* ci: add markdownlint pre-commit hook and fix all violations by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/5271
* refactor: remove starter-gpu distribution by @leseb in https://github.com/llamastack/llama-stack/pull/5279
* refactor!: rename agents API to responses API by @leseb in https://github.com/llamastack/llama-stack/pull/5195
* fix: improve MCP server readiness check in tests by @derekhiggins in https://github.com/llamastack/llama-stack/pull/5306
* fix: make InmemoryKVStore.delete consistent with other backends on missing keys by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5289
* refactor: split large files into focused modules by @skamenan7 in https://github.com/llamastack/llama-stack/pull/5281
* fix: allow multi-worker server with dual-stack IPv6 support by @derekhiggins in https://github.com/llamastack/llama-stack/pull/5284
* ci: add actionlint pre-commit hook and fix violations by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/5285
* ci: test last 3 release branches in scheduled CI by @cdoern in https://github.com/llamastack/llama-stack/pull/5277
* fix: Auto-expand provider dependencies for --providers in stack CLI by @gyliu513 in https://github.com/llamastack/llama-stack/pull/4654
* ci: replace noisy auto-update with merge queue in Mergify by @leseb in https://github.com/llamastack/llama-stack/pull/5310
* fix: make Mergify queue compatible with branch protection by @leseb in https://github.com/llamastack/llama-stack/pull/5315
* fix: make Mergify merge_conditions identical to queue_conditions by @leseb in https://github.com/llamastack/llama-stack/pull/5317
* docs: blog post on Open Responses compliance and OpenAI compatibility by @franciscojavierarceo in https://github.com/llamastack/llama-stack/pull/5232
* ci: add retry logic for oasdiff install in pre-commit workflow by @leseb in https://github.com/llamastack/llama-stack/pull/5314
* fix: milvus hybrid ranker usage by @jakub-walaszczyk in https://github.com/llamastack/llama-stack/pull/5312
* feat!: add schema transforms and types for OpenAI API conformance by @nathan-weinberg in https://github.com/llamastack/llama-stack/pull/5166
* fix(watsonx): replace blocking requests calls with async httpx in WatsonX provider by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5280
* ci: remove docker mode from integration test matrix by @leseb in https://github.com/llamastack/llama-stack/pull/5311
* feat(file_processors): add inline docling provider for structure-aware PDF parsing by @alinaryan in https://github.com/llamastack/llama-stack/pull/5049
* fix(docs): use inline author definition in responses-api blog post by @raghotham in https://github.com/llamastack/llama-stack/pull/5324
* docs: add docstrings to public classes and functions by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5267
* chore(conformance): update OpenAI spec to include compact API by @cdoern in https://github.com/llamastack/llama-stack/pull/5325
* fix(docs): add blog authors.yml and use author keys in all blog posts by @raghotham in https://github.com/llamastack/llama-stack/pull/5326
* docs: rewrite README and docs to lead with OpenAI API compatibility by @leseb in https://github.com/llamastack/llama-stack/pull/5323
* feat(responses): add cancel endpoint for background responses by @cdoern in https://github.com/llamastack/llama-stack/pull/5268
* refactor: remove TGI and HuggingFace inference providers by @leseb in https://github.com/llamastack/llama-stack/pull/5333
* fix: remove stale litellm reference from watsonx test comment by @leseb in https://github.com/llamastack/llama-stack/pull/5286
* build: bump pymilvus minimum version from 2.6.1 to 2.6.2 by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/5334
* chore: update mypy exclude list and add pre-commit hook that enforces strict type checking by @Elbehery in https://github.com/llamastack/llama-stack/pull/5269
* docs: add setup and usage documentation for inline::docling provider by @alinaryan in https://github.com/llamastack/llama-stack/pull/5329
* feat(responses): Add application/x-www-form-urlencoded content type support by @r3v5 in https://github.com/llamastack/llama-stack/pull/5193
* chore(github-deps): bump dorny/paths-filter from 3.0.2 to 4.0.1 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5346
* chore(github-deps): bump oven-sh/setup-bun from 2.1.3 to 2.2.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5347
* chore(github-deps): bump sigstore/gh-action-sigstore-python from 3.2.0 to 3.3.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5353
* chore(github-deps): bump llamastack/llama-stack from 700b202df7e520c1b19977e97657b3aebc055e56 to deaca2d9c71df35c5a4cab2e8fcfd11b07c63e41 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5349
* chore(github-deps): bump astral-sh/setup-uv from 7.5.0 to 7.6.0 by @dependabot[bot] in https://github.com/llamastack/llama-stack/pull/5351
* build: exclude milvus-lite on unsupported architectures by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/5335
* chore: add type hints to DynamicApiMeta class methods by @Elbehery in https://github.com/llamastack/llama-stack/pull/5262
* ci: add GCP Workload Identity Federation for Vertex AI recording workflow by @Artemon-line in https://github.com/llamastack/llama-stack/pull/5276
* chore: add type hints to schema registration functions by @Elbehery in https://github.com/llamastack/llama-stack/pull/5264
* fix: gate conversation sync on store flag to prevent data leak when store=false by @jaideepr97 in https://github.com/llamastack/llama-stack/pull/5305
* chore: add type hints to FastAPI SSE generator functions by @Elbehery in https://github.com/llamastack/llama-stack/pull/5266
* chore: add type hints to inference FastAPI SSE generator function by @Elbehery in https://github.com/llamastack/llama-stack/pull/5361
* fix: handle asyncio.CancelledError in metrics try/except blocks by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5336
* chore: add type hints to CLI files by @Elbehery in https://github.com/llamastack/llama-stack/pull/5364
* chore: fix strict typing issues in llama_stack_api utility modules by @Elbehery in https://github.com/llamastack/llama-stack/pull/5367
* fix: check require_approval field instead of mcp_server in ApprovalFilter isinstance check by @jaideepr97 in https://github.com/llamastack/llama-stack/pull/5288
* refactor: split large test and source files into focused modules by @skamenan7 in https://github.com/llamastack/llama-stack/pull/5299
* fix: vLLM health() and rerank() now honour TLS and auth credentials by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5340
* fix(logging): ensure consistent logging when server started via `llama stack run` or `uvicorn create_app` by @eoinfennessy in https://github.com/llamastack/llama-stack/pull/5275
* fix: race condition in background response cancel causing CI flake by @leseb in https://github.com/llamastack/llama-stack/pull/5363
* test: Update responses tests based on vllm testing by @msager27 in https://github.com/llamastack/llama-stack/pull/5328
* chore: bump fallback_version to 0.6.2.dev0 by @cdoern in https://github.com/llamastack/llama-stack/pull/5375
* feat: migrate logging to structlog with structured key-value output by @leseb in https://github.com/llamastack/llama-stack/pull/5215
* chore: add type hints to core access control modules by @Elbehery in https://github.com/llamastack/llama-stack/pull/5370
* fix: replace blunt pop with assistant message rewriting in _separate_tool_calls by @jaideepr97 in https://github.com/llamastack/llama-stack/pull/5303
* refactor: remove deprecated register/unregister model endpoints by @leseb in https://github.com/llamastack/llama-stack/pull/5341
* chore: add type hints to remaining core server modules by @Elbehery in https://github.com/llamastack/llama-stack/pull/5377
* chore: add type hints to core configuration and build modules by @Elbehery in https://github.com/llamastack/llama-stack/pull/5371
* chore: add type hints to core storage modules by @Elbehery in https://github.com/llamastack/llama-stack/pull/5373
* fix: vLLM rerank() uses provider-data-aware API key lookup by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5374
* feat: add reasoning output types to OpenAI Responses API spec by @robinnarsinghranabhat in https://github.com/llamastack/llama-stack/pull/5357
* docs: blog post for llamastack observability by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5387
* ci: remove Mergify queue config in favor of GitHub merge queue by @leseb in https://github.com/llamastack/llama-stack/pull/5383
* refactor: complete FastAPI router migration and remove @webmethod by @leseb in https://github.com/llamastack/llama-stack/pull/5248
* docs: update README badges with logos, conformance score, and DeepWiki by @leseb in https://github.com/llamastack/llama-stack/pull/5389
* fix: convert Path to str in _build_ssl_context() for httpx compatibility by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5380
* fix: pre-cache tiktoken cl100k_base encoding at image build time by @Bobbins228 in https://github.com/llamastack/llama-stack/pull/5391
* feat: add reasoning as valid conversation item by @mattf in https://github.com/llamastack/llama-stack/pull/5392
* chore(mypy): reduce mypy errors in agents=builtin::responses by @mattf in https://github.com/llamastack/llama-stack/pull/5342
* docs: fix all build warnings for clean Docusaurus build by @raghotham in https://github.com/llamastack/llama-stack/pull/5358
* fix: escape < and > in conformance.mdx table cells for MDX compatibility by @raghotham in https://github.com/llamastack/llama-stack/pull/5396
* feat: Add inference metrics by @gyliu513 in https://github.com/llamastack/llama-stack/pull/5320
* chore: add type hints to Core module files by @Elbehery in https://github.com/llamastack/llama-stack/pull/5365
* chore: add type hints to telemetry module by @Elbehery in https://github.com/llamastack/llama-stack/pull/5366
* ci!: cache HuggingFace models and datasets for offline replay tests by @leseb in https://github.com/llamastack/llama-stack/pull/5382
* docs: modernize documentation theme and landing page by @leseb in https://github.com/llamastack/llama-stack/pull/5402
* docs: update stale documentation to reflect current architecture by @leseb in https://github.com/llamastack/llama-stack/pull/5393
* feat: reasoning output responses api by @robinnarsinghranabhat in https://github.com/llamastack/llama-stack/pull/5206
* fix: surface tiktoken encoding check at provider startup by @Bobbins228 in https://github.com/llamastack/llama-stack/pull/5401
* fix: correct llama-stack-api package metadata and README examples by @leseb in https://github.com/llamastack/llama-stack/pull/5395
* chore: add type hints to core server component modules by @Elbehery in https://github.com/llamastack/llama-stack/pull/5372
* docs: Mintlify-inspired documentation UI improvements by @leseb in https://github.com/llamastack/llama-stack/pull/5405
* fix(tests): validate provider types exist in backward compat test by @derekhiggins in https://github.com/llamastack/llama-stack/pull/5226
* fix: move reasoning wrapper types to llama-stack-api and fix mypy errors by @cdoern in https://github.com/llamastack/llama-stack/pull/5407
* docs: modernize theme, landing page, and API code samples by @leseb in https://github.com/llamastack/llama-stack/pull/5410

## New Contributors
* @elinacse made their first contribution in https://github.com/llamastack/llama-stack/pull/5076
* @rigazilla made their first contribution in https://github.com/llamastack/llama-stack/pull/4839
* @jakub-walaszczyk made their first contribution in https://github.com/llamastack/llama-stack/pull/5312

**Full Changelog**: https://github.com/llamastack/llama-stack/compare/v0.6.1...v0.7.0