Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
422 commits
Select commit Hold shift + click to select a range
36fd97e
chore(ui-deps): bump next from 15.3.3 to 15.5.3 in /llama_stack/ui (#…
dependabot[bot] Sep 15, 2025
b6cb817
chore(ui-deps): bump @radix-ui/react-select from 2.2.5 to 2.2.6 in /l…
dependabot[bot] Sep 15, 2025
01bdcce
chore(recorder): update mocks to be closer to non-mock environment (#…
mattf Sep 15, 2025
ab32173
feat: create HTTP DELETE API endpoints to unregister ScoringFn and Be…
r3v5 Sep 15, 2025
f4ab154
feat: add dynamic model registration support to TGI inference (#3417)
mattf Sep 15, 2025
65d45c7
chore: various watsonx fixes (#3428)
leseb Sep 16, 2025
6b855af
feat: introduce api leveling proposal (#3317)
cdoern Sep 16, 2025
3defdf7
fix: docker failing to start container[pydantic] (#3460)
slekkala1 Sep 16, 2025
49d4a5c
feat: add embedding and dynamic model support to Together inference a…
mattf Sep 16, 2025
ececc32
build: Bump version to 0.2.22
github-actions[bot] Sep 16, 2025
e0e2b1b
fix: Added a bug fix when registering new models (#3453)
omaryashraf5 Sep 17, 2025
fad4843
fix: unbound variable PR_HEAD_REPO (#3469)
derekhiggins Sep 17, 2025
9acf497
fix: Fixing prompts import warning (#3455)
franciscojavierarceo Sep 17, 2025
9fe8097
docs: update documentation links (#3459)
reluctantfuturist Sep 17, 2025
ac1414b
fix: Set provider_id in NVIDIA notebook when registering dataset (#3472)
JashG Sep 17, 2025
42c23b4
feat: update qdrant hash function from SHA-1 to SHA-256 (#3477)
rhdedgar Sep 17, 2025
4842145
feat: Add dynamic authentication token forwarding support for vLLM (#…
akram Sep 18, 2025
521865c
feat: include all models from provider's /v1/models (#3471)
mattf Sep 18, 2025
ea396a5
chore: update the ollama inference impl to use OpenAIMixin for openai…
mattf Sep 18, 2025
e66103c
fix: add missing files provider to NVIDIA distribution (#3479)
jiayin-nvidia Sep 18, 2025
8422bd1
feat: combine ProviderSpec datatypes (#3378)
cdoern Sep 18, 2025
4c2fcb6
chore: refactor server.main (#3462)
ehhuang Sep 19, 2025
9378bdc
docs: Fix incorrect vector_db_id usage in RAG tutorial (#3444)
adam-d-young Sep 19, 2025
d3600b9
fix: force milvus-lite installation for inline::milvus (#3488)
leseb Sep 19, 2025
f44eb93
chore: simplify authorized sqlstore (#3496)
ehhuang Sep 19, 2025
142a38d
chore: remove duplicate AnthropicProviderDataValidator (#3512)
mattf Sep 20, 2025
e3f77c1
fix: Update inference recorder to handle both Ollama and OpenAI model…
derekhiggins Sep 21, 2025
0e43be3
fix: handle missing API keys gracefully in model refresh (#3493)
derekhiggins Sep 22, 2025
e2e42c8
chore: remove duplicate OpenAI and Gemini data validators (#3513)
mattf Sep 22, 2025
6ce2cf3
chore(github-deps): bump astral-sh/setup-uv from 6.6.1 to 6.7.0 (#3502)
dependabot[bot] Sep 22, 2025
21f7667
chore(ui-deps): bump remeda from 2.30.0 to 2.32.0 in /llama_stack/ui …
dependabot[bot] Sep 22, 2025
7c4a740
chore(ui-deps): bump @radix-ui/react-dialog from 1.1.13 to 1.1.15 in …
dependabot[bot] Sep 22, 2025
a130191
chore(ui-deps): bump jest-environment-jsdom from 29.7.0 to 30.1.2 in …
dependabot[bot] Sep 22, 2025
e3fd70c
fix: change ModelRegistryHelper to use ProviderModelEntry instead of…
wukaixingxp Sep 22, 2025
8d82619
chore: Refactor fireworks to use OpenAIMixin (#3480)
slekkala1 Sep 22, 2025
a7f9ce9
chore: fix build (#3522)
ehhuang Sep 23, 2025
62e0aef
fix: return llama stack model id from embeddings (#3525)
mattf Sep 23, 2025
2be869b
fix(dev): fix vllm inference recording (await models.list) (#3524)
mattf Sep 23, 2025
9406a99
chore: refactor tracingmiddelware (#3520)
ehhuang Sep 23, 2025
d07ebce
feat: (re-)enable Databricks inference adapter (#3500)
mattf Sep 23, 2025
ce7a3b4
feat: update Cerebras inference provider to support dynamic model lis…
mattf Sep 23, 2025
2f58d87
docs: fix typos in RAG docs (#3530)
nathan-weinberg Sep 23, 2025
48a551e
chore(perf): run guidellm benchmarks (#3421)
ehhuang Sep 24, 2025
914c8cb
fix: fix API docstrings for proper MDX parsing (#3526)
reluctantfuturist Sep 24, 2025
0a7d1ad
fix: update OpenAPI generator (#3527)
reluctantfuturist Sep 24, 2025
45da318
fix: update API conformance test to point to new schema location (#3528)
reluctantfuturist Sep 24, 2025
d238657
docs: provider and distro codegen migration (#3531)
reluctantfuturist Sep 24, 2025
05ff4c4
docs: advanced_apis migration (#3532)
reluctantfuturist Sep 24, 2025
c71ce8d
docs: concepts and building_applications migration (#3534)
reluctantfuturist Sep 24, 2025
610526d
docs: static content migration (#3535)
reluctantfuturist Sep 24, 2025
aebd728
docs: docusaurus setup (#3541)
reluctantfuturist Sep 24, 2025
8537ada
docs: MDX leftover fixes (#3536)
reluctantfuturist Sep 24, 2025
6101c8e
docs: fix broken links (#3540)
reluctantfuturist Sep 24, 2025
a50b639
chore: use ollama/all-minilm:l6-v2 for ollama tests (#3537)
mattf Sep 24, 2025
b67aef2
feat: add static embedding metadata to dynamic model listings for pro…
mattf Sep 25, 2025
28d83fa
fix: docs deployment URL (#3556)
reluctantfuturist Sep 25, 2025
9c751b6
feat: use FIPS validated CSPRNG for telemetry (#3554)
rhdedgar Sep 26, 2025
65e01b5
feat: together now supports base64 embedding encoding (#3559)
mattf Sep 26, 2025
c88c4ff
feat: introduce API leveling, post_training, eval to v1alpha (#3449)
cdoern Sep 26, 2025
926c3ad
chore: prune mypy exclude list (#3561)
mattf Sep 26, 2025
b6e2934
fix: Gracefully handle errors when listing MCP tools (#2544)
bbrowning Sep 26, 2025
da5ea10
fix: ensure ModelRegistryHelper init for together and fireworks (#3572)
mattf Sep 26, 2025
7a25be6
fix: Revert "fix: Added a bug fix when registering new models" (#3473)
mattf Sep 26, 2025
4487b88
build: Bump version to 0.2.23
github-actions[bot] Sep 26, 2025
b48d5cf
feat(internal): add image_url download feature to OpenAIMixin (#3516)
mattf Sep 26, 2025
60484c5
chore(api): remove batch inference (#3261)
mattf Sep 26, 2025
53b1572
chore(apis): unpublish deprecated /v1/inference apis (#3297)
mattf Sep 27, 2025
0d94f3e
chore: recordings for fireworks (inference + openai) (#3573)
mattf Sep 27, 2025
c392f3a
chore: remove extra logging (#3574)
ehhuang Sep 27, 2025
1a8d3ed
chore: MANIFEST maintenance (#3454)
leseb Sep 27, 2025
65f7b81
feat: Add items and title to ToolParameter/ToolParamDefinition (#3003)
TamiTakamiya Sep 27, 2025
8dc9fd6
feat(ci): use @next branch from llama-stack-client (#3576)
ashwinb Sep 27, 2025
d95853d
chore(ui-deps): bump shiki from 1.29.2 to 3.13.0 in /llama_stack/ui (…
dependabot[bot] Sep 29, 2025
9fdfd3a
chore(ui-deps): bump tw-animate-css from 1.2.9 to 1.4.0 in /llama_sta…
dependabot[bot] Sep 29, 2025
90bb9cf
chore(github-deps): bump actions/cache from 4.2.4 to 4.3.0 (#3577)
dependabot[bot] Sep 29, 2025
7c466a7
chore: skip nvidia datastore tests when nvidia datastore is not enabl…
mattf Sep 29, 2025
8ab6684
chore: introduce write queue for response_store (#3497)
ehhuang Sep 29, 2025
fdb144f
revert: feat(ci): use @next branch from llama-stack-client (#3593)
ashwinb Sep 29, 2025
aab22dc
fix: adding mime type of application/json support (#3452)
wukaixingxp Sep 29, 2025
975ead1
chore(api): remove deprecated embeddings impls (#3301)
mattf Sep 29, 2025
aac42dd
feat(api): level inference/rerank and remove experimental (#3565)
cdoern Sep 29, 2025
45f438c
chore: skip safety tests when shield not available (#3592)
mattf Sep 29, 2025
7c888fc
feat: update eval runner to use openai endpoints (#3588)
mattf Sep 29, 2025
498be13
docs: update image paths (#3599)
reluctantfuturist Sep 29, 2025
e9eb004
fix: remove inference.completion from docs (#3589)
mattf Sep 29, 2025
455579a
fix: Remove deprecated user param in OpenAIResponseObject (#3596)
slekkala1 Sep 29, 2025
ddf3f17
fix: ensure usage is requested if telemetry is enabled (#3571)
mhdawson Sep 29, 2025
5e7fed8
feat(openai_movement): Change URL structures to kill /openai/v1 (par…
ashwinb Sep 29, 2025
3a09f00
feat(files): fix expires_after API shape (#3604)
ashwinb Sep 30, 2025
56b625d
feat(openai_movement)!: Change URL structures to kill /openai/v1 (pa…
ashwinb Sep 30, 2025
6cce553
fix: mcp tool with array type should include items (#3602)
ehhuang Sep 30, 2025
62e3026
feat: add llamastack + CrewAI integration example notebook (#3275)
wukaixingxp Sep 30, 2025
cb33f45
chore: unpublish /inference/chat-completion (#3609)
mattf Sep 30, 2025
2de4e6c
feat: use /v1/chat/completions for safety model inference (#3591)
mattf Sep 30, 2025
1e25a72
feat(api): level /agents as `v1alpha` (#3610)
cdoern Sep 30, 2025
cc64093
feat(api): Add Vector Store File batches api stub (#3615)
slekkala1 Sep 30, 2025
73de235
fix(eval): use client.alpha for eval tests
ashwinb Sep 30, 2025
606f4cf
fix(expires_after): make sure multipart/form-data is properly parsed …
ashwinb Sep 30, 2025
c4c980b
docs: frontpage update (#3620)
reluctantfuturist Sep 30, 2025
0837fa7
docs: update safety notebook (#3617)
reluctantfuturist Sep 30, 2025
d350e36
feat: add support for require_approval argument when creating respons…
grs Sep 30, 2025
ac7c35f
fix: don't pass default response format in Responses (#3614)
ehhuang Sep 30, 2025
42414a1
fix(logging): disable console telemetry sink by default (#3623)
ashwinb Sep 30, 2025
ca47d90
fix: Ensure that tool calls with no arguments get handled correctly …
jaideepr97 Oct 1, 2025
ea15f2a
chore: use openai_chat_completion for llm as a judge scoring (#3635)
mattf Oct 1, 2025
f7c5ef4
chore: remove /v1/inference/completion and implementations (#3622)
mattf Oct 1, 2025
d167101
feat(api): implement v1beta leveling, and additional alpha (#3594)
cdoern Oct 1, 2025
4819a2e
feat(conformance): skip test if breaking change is ack (#3619)
cdoern Oct 1, 2025
853e9b3
fix: log level (#3637)
ehhuang Oct 1, 2025
7f1a33f
docs: update API conformance test (#3631)
reluctantfuturist Oct 1, 2025
b6a5bcc
docs: api separation (#3630)
reluctantfuturist Oct 1, 2025
28bbbcf
docs: adding supplementary markdown content to API specs (#3632)
reluctantfuturist Oct 1, 2025
4dbe059
chore: add provider-data-api-key support to openaimixin (#3639)
mattf Oct 1, 2025
5adcf0e
chore: Remove debug logging from telemetry adapter (#3643)
ehhuang Oct 1, 2025
267f658
docs: fix broken links (#3647)
reluctantfuturist Oct 1, 2025
cb36b3b
docs: add favicon and mobile styling (#3650)
reluctantfuturist Oct 2, 2025
382eb25
docs: fix more broken links (#3649)
reluctantfuturist Oct 2, 2025
426dc54
docs: Fix Dell distro documentation code snippets (#3640)
ConnorHack Oct 2, 2025
7e48cc4
refactor(agents): migrate to OpenAI chat completions API (#3323)
aakankshaduggal Oct 2, 2025
f1748e2
fix: re-enable conformance skipping ability (#3651)
cdoern Oct 2, 2025
4161102
chore!: add double routes for v1/openai/v1 (#3636)
leseb Oct 2, 2025
1d02385
docs: Update docs navbar config (#3653)
kelbrown20 Oct 2, 2025
24ee577
docs: API spec generation for Stainless (#3655)
reluctantfuturist Oct 2, 2025
0e13512
chore: fix agents tests for non-ollama providers, provide max_tokens …
mattf Oct 2, 2025
6afa96b
fix(api): fix a mistake from #3636 which overwrote POST /responses
ashwinb Oct 2, 2025
ceca3c0
chore: fix/add logging categories (#3658)
ehhuang Oct 2, 2025
1f5003d
chore: fix precommit (#3663)
ehhuang Oct 2, 2025
ef07365
feat(tools)!: substantial clean up of "Tool" related datatypes (#3627)
ashwinb Oct 2, 2025
14a94e9
fix: responses <> chat completion input conversion (#3645)
ehhuang Oct 2, 2025
0a41c4e
chore: OpenAIMixin implements ModelsProtocolPrivate (#3662)
mattf Oct 3, 2025
52c8df2
feat: auto-detect Console width (#3327)
rhdedgar Oct 3, 2025
bcdbb53
feat: implement keyword and hybrid search for Weaviate provider (#3264)
ChristianZaccaria Oct 3, 2025
4dfbe46
fix(docs): Correct indentation in documented example for access_polic…
anastasds Oct 3, 2025
d266c59
chore: remove deprecated inference.chat_completion implementations (#…
mattf Oct 3, 2025
a09e30b
docs!: adjust external provider docs (#3484)
cdoern Oct 3, 2025
a20e8ea
feat: Add OpenAI Conversations API (#3429)
franciscojavierarceo Oct 3, 2025
ce77c27
chore: use remoteinferenceproviderconfig for remote inference provide…
mattf Oct 3, 2025
9f6c658
docs: update OG image (#3669)
reluctantfuturist Oct 3, 2025
5a44b9f
feat: add comment-triggered pre-commit bot for PRs (#3672)
ashwinb Oct 3, 2025
f232b78
fix(ci): update hashes
ashwinb Oct 3, 2025
188a56a
fix: merge workflows to avoid GITHUB_TOKEN limitation
ashwinb Oct 3, 2025
61b4238
feat(api): add extra_body parameter support with shields example (#3670)
ashwinb Oct 3, 2025
7ec7e0c
chore: Add weaviate client to unit group in pyproject.toml and uv.loc…
franciscojavierarceo Oct 3, 2025
6bcd3e2
chore: update CODEOWNERS (#3613)
reluctantfuturist Oct 4, 2025
3f36bfa
chore(tests): normalize recording IDs and timestamps to reduce git di…
ashwinb Oct 4, 2025
c21bb0e
chore: fix setup_telemetry script (#3680)
ehhuang Oct 4, 2025
f176196
docs: Update links in README for quick start and documentation (#3678)
seyeong-han Oct 4, 2025
045a0c1
feat(tests): implement test isolation for inference recordings (#3681)
ashwinb Oct 4, 2025
351c4b9
chore: inference=remote::llama-openai-compat does not support /v1/com…
mattf Oct 4, 2025
91c6a8a
chore(ui-deps): bump next from 15.5.3 to 15.5.4 in /llama_stack/ui (#…
dependabot[bot] Oct 6, 2025
c0f0a03
chore(ui-deps): bump react-dom and @types/react-dom in /llama_stack/u…
dependabot[bot] Oct 6, 2025
45cf74d
chore(python-deps): bump requests from 2.32.4 to 2.32.5 (#3691)
dependabot[bot] Oct 6, 2025
59e5bde
chore(github-deps): bump astral-sh/setup-uv from 6.7.0 to 6.8.0 (#3686)
dependabot[bot] Oct 6, 2025
198536f
chore(github-deps): bump actions/github-script from 7.0.1 to 8.0.0 (#…
dependabot[bot] Oct 6, 2025
92219fd
chore(python-deps): bump pandas from 2.3.1 to 2.3.3 (#3689)
dependabot[bot] Oct 6, 2025
426cac0
chore: use uvicorn to start llama stack server everywhere (#3625)
ehhuang Oct 6, 2025
f00bcd9
feat: allow for multiple external provider specs (#3341)
cdoern Oct 6, 2025
724dac4
chore: give OpenAIMixin subcalsses a change to list models without le…
mattf Oct 6, 2025
d23ed26
chore: turn OpenAIMixin into a pydantic.BaseModel (#3671)
mattf Oct 6, 2025
ae74b31
chore: remove vLLM inference adapter's custom list_models (#3703)
mattf Oct 6, 2025
de9940c
chore: disable openai_embeddings on inference=remote::llama-openai-co…
mattf Oct 6, 2025
892ea75
chore: remove together inference adapter's custom check_model_availab…
mattf Oct 6, 2025
a8da6ba
docs: API docstrings cleanup for better documentation rendering (#3661)
reluctantfuturist Oct 6, 2025
696fefb
chore: logger category fix (#3706)
ehhuang Oct 6, 2025
597d405
chore: fix closing error (#3709)
ehhuang Oct 6, 2025
bba9957
feat(api): Add vector store file batches api (#3642)
slekkala1 Oct 6, 2025
50f9ca3
chore: remove dead code (#3713)
ehhuang Oct 7, 2025
509ac4a
feat: enable Runpod inference adapter (#3707)
justinwlin Oct 7, 2025
1fcde5f
fix: update pyproject.toml dependencies for vector processing (#3555)
skamenan7 Oct 7, 2025
8b9af03
fix: refresh log should be debug (#3720)
cdoern Oct 7, 2025
e892a3f
feat: add refresh_models support to inference adapters (default: fals…
mattf Oct 7, 2025
6389bf5
fix: make telemetry optional for agents (#3705)
cdoern Oct 7, 2025
d5b136a
feat: Enabling Annotations in Responses (#3698)
franciscojavierarceo Oct 7, 2025
1970b4a
fix: improve model availability checks: Allows use of unavailable mod…
akram Oct 7, 2025
c2d97a9
chore: fix flaky unit test and add proper shutdown for file batches (…
slekkala1 Oct 7, 2025
bc7d4b4
fix(scripts): select container runtime for telemetry (#3727)
iamemilio Oct 7, 2025
c940fe7
fix: fix nvidia provider (#3716)
wukaixingxp Oct 8, 2025
b6e9f41
chore: Revert "fix: fix nvidia provider (#3716)" (#3730)
ehhuang Oct 8, 2025
1ac320b
chore: remove dead code (#3729)
slekkala1 Oct 8, 2025
a3f5072
chore!: remove --env from `llama stack run` (#3711)
ehhuang Oct 8, 2025
0cde3d9
chore: require valid logging category (#3712)
ehhuang Oct 8, 2025
702fcd1
fix: Raising an error message to the user when registering an existin…
omaryashraf5 Oct 8, 2025
62bac0a
chore(github-deps): bump actions/stale from 10.0.0 to 10.1.0 (#3684)
dependabot[bot] Oct 8, 2025
5d711d4
fix: Update watsonx.ai provider to use LiteLLM mixin and list all mod…
jwm4 Oct 8, 2025
96886af
fix(responses): fix regression in support for mcp tool require_approv…
grs Oct 8, 2025
79bed44
fix(tests): ensure test isolation in server mode (#3737)
ashwinb Oct 8, 2025
b96640e
chore: Removing Weaviate, PGVector, and Milvus from unit tests (#3742)
franciscojavierarceo Oct 8, 2025
16db42e
feat(tests): add --collect-only option to integration test script (#3…
ashwinb Oct 8, 2025
05a62a6
chore: print integration tests command (#3747)
ehhuang Oct 8, 2025
4b9ebbf
chore: revert "fix: Raising an error message to the user when registe…
leseb Oct 9, 2025
26fd5db
fix: add traces for tool calls and mcp tool listing (#3722)
grs Oct 9, 2025
f50ce11
feat(tests): make inference_recorder into api_recorder (include tool_…
ashwinb Oct 9, 2025
a055a32
fix(tests): remove chroma and qdrant from vector io unit tests (#3759)
ashwinb Oct 9, 2025
841d0c3
fix(testing): improve api_recorder error messages for missing recordi…
ashwinb Oct 9, 2025
7ee0ee7
chore!: remove model mgmt from CLI for Hugging Face CLI (#3700)
leseb Oct 9, 2025
145b2bc
feat: make object registration idempotent (#3752)
mattf Oct 10, 2025
8fe4a21
fix(inference): propagate 401/403 errors from remote providers (#3762)
ashwinb Oct 10, 2025
ebae038
fix: update dangling references to llama download command (#3763)
ashwinb Oct 10, 2025
aaf5036
feat(responses): add usage types to inference and responses APIs (#3764)
ashwinb Oct 10, 2025
a548169
fix: allow skipping model availability check for vLLM (#3739)
akram Oct 10, 2025
e039b61
feat(responses)!: add in_progress, failed, content part events (#3765)
ashwinb Oct 10, 2025
6d8f612
fix: update normalize to search all recordings dirs (#3767)
derekhiggins Oct 10, 2025
0066d98
feat: use SecretStr for inference provider auth credentials (#3724)
mattf Oct 10, 2025
8bf07f9
feat: reuse previous mcp tool listings where possible (#3710)
grs Oct 10, 2025
548ccff
fix(mypy): fix wrong attribute access (#3770)
ashwinb Oct 10, 2025
932fea8
fix(ci): remove responses from CI for now (#3773)
ashwinb Oct 10, 2025
e7d21e1
feat: Add support for Conversations in Responses API (#3743)
franciscojavierarceo Oct 10, 2025
1394403
feat(responses): implement usage tracking in streaming responses (#3771)
ashwinb Oct 10, 2025
32fde8d
feat: Add /v1/embeddings endpoint to batches API (#3384)
varshaprasad96 Oct 10, 2025
6954fe2
fix(auth): allow unauthenticated access to health and version endpoin…
derekhiggins Oct 10, 2025
80d58ab
chore: refactor (chat)completions endpoints to use shared params stru…
ehhuang Oct 10, 2025
06e4cd8
feat(api)!: BREAKING CHANGE: support passing `extra_body` through to …
ehhuang Oct 10, 2025
a165b8b
chore!: BREAKING CHANGE removing VectorDB APIs (#3774)
franciscojavierarceo Oct 11, 2025
f15d865
chore(github-deps): bump astral-sh/setup-uv from 6.8.0 to 7.0.0 (#3782)
dependabot[bot] Oct 11, 2025
2cb1b19
chore(python-deps): bump psycopg2-binary from 2.9.10 to 2.9.11 (#3785)
dependabot[bot] Oct 11, 2025
dac1d7b
chore(python-deps): bump fire from 0.7.0 to 0.7.1 (#3787)
dependabot[bot] Oct 11, 2025
f365961
fix(tests): handle TEST_CONTEXT not being set
ashwinb Oct 11, 2025
7c63aeb
feat(responses)!: add reasoning and annotation added events (#3793)
ashwinb Oct 11, 2025
e637887
fix(misc): pre-commit fix for server.py
ashwinb Oct 11, 2025
13518e7
chore(python-deps): bump ollama from 0.5.1 to 0.6.0 (#3786)
dependabot[bot] Oct 11, 2025
055a766
chore(python-deps): bump blobfile from 3.0.0 to 3.1.0 (#3784)
dependabot[bot] Oct 11, 2025
cfd2e30
chore(python-deps): bump black from 25.1.0 to 25.9.0 (#3783)
dependabot[bot] Oct 11, 2025
4fb39f0
chore(ui-deps): bump @types/react from 19.2.0 to 19.2.2 in /llama_sta…
dependabot[bot] Oct 12, 2025
190b96e
chore(ui-deps): bump @types/react-dom from 19.2.0 to 19.2.1 in /llama…
dependabot[bot] Oct 12, 2025
25ea94f
chore(ui-deps): bump eslint from 9.26.0 to 9.37.0 in /llama_stack/ui …
dependabot[bot] Oct 12, 2025
e94840d
chore(ui-deps): bump framer-motion from 12.23.12 to 12.23.24 in /llam…
dependabot[bot] Oct 12, 2025
82cbcad
chore(ui-deps): bump lucide-react from 0.542.0 to 0.545.0 in /llama_s…
dependabot[bot] Oct 12, 2025
3bb6ef3
chore!: Safety api refactoring to use OpenAIMessageParam (#3796)
slekkala1 Oct 12, 2025
ecc8a55
feat(api)!: support extra_body to embeddings and vector_stores APIs (…
ashwinb Oct 13, 2025
b95f095
feat: Allow :memory: for kvstore (#3696)
raghotham Oct 13, 2025
642126e
fix: record job checking wrong directory (#3799)
derekhiggins Oct 13, 2025
968c364
chore: Auto-detect Provider ID when only 1 Vector Store Provider avai…
franciscojavierarceo Oct 13, 2025
1136daf
fix: replace python-jose with PyJWT for JWT handling (#3756)
leseb Oct 14, 2025
0dbf79c
fix: Fixed WatsonX remote inference provider (#3801)
are-ces Oct 14, 2025
007efa6
refactor: replace default all-MiniLM-L6-v2 embedding model by nomic-e…
r3v5 Oct 14, 2025
1590047
docs: Update CONTRIBUTING: py 3.12 and pre-commit==4.3.0 (#3807)
jwm4 Oct 14, 2025
866c13c
chore(api)!: BREAKING CHANGE: remove ALL telemetry APIs (#3740)
ehhuang Oct 14, 2025
d875e42
refactor: use `extra_body` to pass in `input_type` params for asymmet…
jiayin-nvidia Oct 14, 2025
ef4bc70
feat: Enable setting a default embedding model in the stack (#3803)
franciscojavierarceo Oct 15, 2025
ce8ea2f
chore: Support embedding params from metadata for Vector Store (#3811)
slekkala1 Oct 15, 2025
add8cd8
feat(gemini): Support gemini-embedding-001 and fix models/ prefix in …
jperezdealgaba Oct 15, 2025
e9b4278
feat(responses)!: improve responses + conversations implementations (…
ashwinb Oct 15, 2025
bc8b377
fix(vector-io): handle missing document_id in insert_chunks (#3521)
skamenan7 Oct 15, 2025
d709eeb
chore: mark recordings as generated files (#3816)
ehhuang Oct 15, 2025
0a96a7f
fix(responses): fix subtle bugs in non-function tool calling (#3817)
ashwinb Oct 15, 2025
6ba9db3
chore!: BREAKING CHANGE: remove sqlite from telemetry config (#3808)
ehhuang Oct 15, 2025
8e7e0dd
fix(responses): use conversation items when no stored messages exist …
ashwinb Oct 15, 2025
99141c2
feat: Add responses and safety impl extra_body (#3781)
slekkala1 Oct 15, 2025
f205ab6
fix(responses): fixes, re-record tests (#3820)
ashwinb Oct 15, 2025
9006b93
chore: remove test_cases/openai/responses.json
derekhiggins Oct 16, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
1 change: 1 addition & 0 deletions .gitattributes
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
tests/**/recordings/** linguist-generated=true
2 changes: 1 addition & 1 deletion .github/CODEOWNERS
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,4 @@

# These owners will be the default owners for everything in
# the repo. Unless a later match takes precedence,
* @ashwinb @yanxi0830 @hardikjshah @raghotham @ehhuang @terrytangyuan @leseb @bbrowning @reluctantfuturist @mattf @slekkala1
* @ashwinb @yanxi0830 @hardikjshah @raghotham @ehhuang @terrytangyuan @leseb @bbrowning @reluctantfuturist @mattf @slekkala1 @franciscojavierarceo
4 changes: 2 additions & 2 deletions .github/ISSUE_TEMPLATE/config.yml
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,10 @@ blank_issues_enabled: false

contact_links:
- name: Have you read the docs?
url: https://llama-stack.readthedocs.io/en/latest/index.html
url: https://llamastack.github.io/providers/external/index.html
about: Much help can be found in the docs
- name: Start a discussion
url: https://github.com/meta-llama/llama-stack/discussions/new
url: https://github.com/llamastack/llama-stack/discussions/new/
about: Start a discussion on a topic
- name: Chat on Discord
url: https://discord.gg/llama-stack
Expand Down
1 change: 0 additions & 1 deletion .github/TRIAGERS.md
Original file line number Diff line number Diff line change
@@ -1,2 +1 @@
# This file documents Triage members in the Llama Stack community
@bbrowning @franciscojavierarceo @leseb
70 changes: 40 additions & 30 deletions .github/actions/run-and-record-tests/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -2,26 +2,28 @@ name: 'Run and Record Tests'
description: 'Run integration tests and handle recording/artifact upload'

inputs:
test-subdirs:
description: 'Comma-separated list of test subdirectories to run'
required: true
test-pattern:
description: 'Regex pattern to pass to pytest -k'
required: false
default: ''
stack-config:
description: 'Stack configuration to use'
required: true
provider:
description: 'Provider to use for tests'
required: true
setup:
description: 'Setup to use for tests (e.g., ollama, gpt, vllm)'
required: false
default: ''
inference-mode:
description: 'Inference mode (record or replay)'
required: true
run-vision-tests:
description: 'Whether to run vision tests'
suite:
description: 'Test suite to use: base, responses, vision, etc.'
required: false
default: ''
subdirs:
description: 'Comma-separated list of test subdirectories to run; overrides suite'
required: false
default: 'false'
default: ''
pattern:
description: 'Regex pattern to pass to pytest -k'
required: false
default: ''

runs:
using: 'composite'
Expand All @@ -36,33 +38,41 @@ runs:
- name: Run Integration Tests
shell: bash
run: |
./scripts/integration-tests.sh \
--stack-config '${{ inputs.stack-config }}' \
--provider '${{ inputs.provider }}' \
--test-subdirs '${{ inputs.test-subdirs }}' \
--test-pattern '${{ inputs.test-pattern }}' \
--inference-mode '${{ inputs.inference-mode }}' \
${{ inputs.run-vision-tests == 'true' && '--run-vision-tests' || '' }} \
| tee pytest-${{ inputs.inference-mode }}.log
SCRIPT_ARGS="--stack-config ${{ inputs.stack-config }} --inference-mode ${{ inputs.inference-mode }}"

# Add optional arguments only if they are provided
if [ -n '${{ inputs.setup }}' ]; then
SCRIPT_ARGS="$SCRIPT_ARGS --setup ${{ inputs.setup }}"
fi
if [ -n '${{ inputs.suite }}' ]; then
SCRIPT_ARGS="$SCRIPT_ARGS --suite ${{ inputs.suite }}"
fi
if [ -n '${{ inputs.subdirs }}' ]; then
SCRIPT_ARGS="$SCRIPT_ARGS --subdirs ${{ inputs.subdirs }}"
fi
if [ -n '${{ inputs.pattern }}' ]; then
SCRIPT_ARGS="$SCRIPT_ARGS --pattern ${{ inputs.pattern }}"
fi

echo "=== Running command ==="
echo "uv run --no-sync ./scripts/integration-tests.sh $SCRIPT_ARGS"
echo ""

uv run --no-sync ./scripts/integration-tests.sh $SCRIPT_ARGS | tee pytest-${{ inputs.inference-mode }}.log


- name: Commit and push recordings
if: ${{ inputs.inference-mode == 'record' }}
shell: bash
run: |
echo "Checking for recording changes"
git status --porcelain tests/integration/recordings/
git status --porcelain tests/integration/

if [[ -n $(git status --porcelain tests/integration/recordings/) ]]; then
if [[ -n $(git status --porcelain tests/integration/) ]]; then
echo "New recordings detected, committing and pushing"
git add tests/integration/recordings/

if [ "${{ inputs.run-vision-tests }}" == "true" ]; then
git commit -m "Recordings update from CI (vision)"
else
git commit -m "Recordings update from CI"
fi
git add tests/integration/

git commit -m "Recordings update from CI (suite: ${{ inputs.suite }})"
git fetch origin ${{ github.ref_name }}
git rebase origin/${{ github.ref_name }}
echo "Rebased successfully"
Expand Down
8 changes: 4 additions & 4 deletions .github/actions/setup-ollama/action.yml
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
name: Setup Ollama
description: Start Ollama
inputs:
run-vision-tests:
description: 'Run vision tests: "true" or "false"'
suite:
description: 'Test suite to use: base, responses, vision, etc.'
required: false
default: 'false'
default: ''
runs:
using: "composite"
steps:
- name: Start Ollama
shell: bash
run: |
if [ "${{ inputs.run-vision-tests }}" == "true" ]; then
if [ "${{ inputs.suite }}" == "vision" ]; then
image="ollama-with-vision-model"
else
image="ollama-with-models"
Expand Down
9 changes: 6 additions & 3 deletions .github/actions/setup-runner/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -16,14 +16,16 @@ runs:
uses: astral-sh/setup-uv@6b9c6063abd6010835644d4c2e1bef4cf5cd0fca # v6.0.1
with:
python-version: ${{ inputs.python-version }}
activate-environment: true
version: 0.7.6

- name: Install dependencies
shell: bash
run: |
echo "Updating project dependencies via uv sync"
uv sync --all-groups
uv pip install ollama faiss-cpu

echo "Installing ad-hoc dependencies"
uv pip install faiss-cpu

# Install llama-stack-client-python based on the client-version input
if [ "${{ inputs.client-version }}" = "latest" ]; then
Expand All @@ -37,4 +39,5 @@ runs:
exit 1
fi

uv pip install -e .
echo "Installed llama packages"
uv pip list | grep llama
35 changes: 25 additions & 10 deletions .github/actions/setup-test-environment/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,14 +8,14 @@ inputs:
client-version:
description: 'Client version (latest or published)'
required: true
provider:
description: 'Provider to setup (ollama or vllm)'
required: true
setup:
description: 'Setup to configure (ollama, vllm, gpt, etc.)'
required: false
default: 'ollama'
run-vision-tests:
description: 'Whether to setup provider for vision tests'
suite:
description: 'Test suite to use: base, responses, vision, etc.'
required: false
default: 'false'
default: ''
inference-mode:
description: 'Inference mode (record or replay)'
required: true
Expand All @@ -30,19 +30,34 @@ runs:
client-version: ${{ inputs.client-version }}

- name: Setup ollama
if: ${{ inputs.provider == 'ollama' && inputs.inference-mode == 'record' }}
if: ${{ (inputs.setup == 'ollama' || inputs.setup == 'ollama-vision') && inputs.inference-mode == 'record' }}
uses: ./.github/actions/setup-ollama
with:
run-vision-tests: ${{ inputs.run-vision-tests }}
suite: ${{ inputs.suite }}

- name: Setup vllm
if: ${{ inputs.provider == 'vllm' && inputs.inference-mode == 'record' }}
if: ${{ inputs.setup == 'vllm' && inputs.inference-mode == 'record' }}
uses: ./.github/actions/setup-vllm

- name: Build Llama Stack
shell: bash
run: |
uv run llama stack build --template ci-tests --image-type venv
# Install llama-stack-client-python based on the client-version input
if [ "${{ inputs.client-version }}" = "latest" ]; then
echo "Installing latest llama-stack-client-python from main branch"
export LLAMA_STACK_CLIENT_DIR=git+https://github.com/llamastack/llama-stack-client-python.git@main
elif [ "${{ inputs.client-version }}" = "published" ]; then
echo "Installing published llama-stack-client-python from PyPI"
unset LLAMA_STACK_CLIENT_DIR
else
echo "Invalid client-version: ${{ inputs.client-version }}"
exit 1
fi

echo "Building Llama Stack"

LLAMA_STACK_DIR=. \
uv run --no-sync llama stack build --template ci-tests --image-type venv

- name: Configure git for commits
shell: bash
Expand Down
12 changes: 12 additions & 0 deletions .github/dependabot.yml
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ updates:
day: "saturday"
commit-message:
prefix: chore(github-deps)

- package-ecosystem: "uv"
directory: "/"
schedule:
Expand All @@ -19,3 +20,14 @@ updates:
- python
commit-message:
prefix: chore(python-deps)

- package-ecosystem: npm
directory: "/llama_stack/ui"
schedule:
interval: "weekly"
day: "saturday"
labels:
- type/dependencies
- javascript
commit-message:
prefix: chore(ui-deps)
6 changes: 4 additions & 2 deletions .github/workflows/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,18 +5,20 @@ Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a tabl
| Name | File | Purpose |
| ---- | ---- | ------- |
| Update Changelog | [changelog.yml](changelog.yml) | Creates PR for updating the CHANGELOG.md |
| API Conformance Tests | [conformance.yml](conformance.yml) | Run the API Conformance test suite on the changes. |
| Installer CI | [install-script-ci.yml](install-script-ci.yml) | Test the installation script |
| Integration Auth Tests | [integration-auth-tests.yml](integration-auth-tests.yml) | Run the integration test suite with Kubernetes authentication |
| SqlStore Integration Tests | [integration-sql-store-tests.yml](integration-sql-store-tests.yml) | Run the integration test suite with SqlStore |
| Integration Tests (Replay) | [integration-tests.yml](integration-tests.yml) | Run the integration test suite from tests/integration in replay mode |
| Integration Tests (Replay) | [integration-tests.yml](integration-tests.yml) | Run the integration test suites from tests/integration in replay mode |
| Vector IO Integration Tests | [integration-vector-io-tests.yml](integration-vector-io-tests.yml) | Run the integration test suite with various VectorIO providers |
| Pre-commit | [pre-commit.yml](pre-commit.yml) | Run pre-commit checks |
| Pre-commit Bot | [precommit-trigger.yml](precommit-trigger.yml) | Pre-commit bot for PR |
| Test Llama Stack Build | [providers-build.yml](providers-build.yml) | Test llama stack build |
| Python Package Build Test | [python-build-test.yml](python-build-test.yml) | Test building the llama-stack PyPI project |
| Integration Tests (Record) | [record-integration-tests.yml](record-integration-tests.yml) | Run the integration test suite from tests/integration |
| Check semantic PR titles | [semantic-pr.yml](semantic-pr.yml) | Ensure that PR titles follow the conventional commit spec |
| Close stale issues and PRs | [stale_bot.yml](stale_bot.yml) | Run the Stale Bot action |
| Test External Providers Installed via Module | [test-external-provider-module.yml](test-external-provider-module.yml) | Test External Provider installation via Python module |
| Test External API and Providers | [test-external.yml](test-external.yml) | Test the External API and Provider mechanisms |
| UI Tests | [ui-unit-tests.yml](ui-unit-tests.yml) | Run the UI test suite |
| Unit Tests | [unit-tests.yml](unit-tests.yml) | Run the unit test suite |
| Update ReadTheDocs | [update-readthedocs.yml](update-readthedocs.yml) | Update the Llama Stack ReadTheDocs site |
2 changes: 1 addition & 1 deletion .github/workflows/changelog.yml
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ jobs:
pull-requests: write # for peter-evans/create-pull-request to create a PR
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
with:
ref: main
fetch-depth: 0
Expand Down
Loading