add fiddlecube to distros, update docs

adding fiddlecube as a remote safety provider to existing templates
updating docs to also show the fiddlecube remote provider

docs/source/distributions/remote_hosted_distro/nvidia.md

@@ -9,7 +9,7 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `remote::nvidia` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |

docs/source/distributions/self_hosted_distro/bedrock.md

@@ -16,7 +16,7 @@ The `llamastack/distribution-bedrock` distribution consists of the following pro
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `remote::bedrock` |
-| safety | `remote::bedrock` |
+| safety | `remote::bedrock`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |

docs/source/distributions/self_hosted_distro/cerebras.md

@@ -9,7 +9,7 @@ The `llamastack/distribution-cerebras` distribution consists of the following pr
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `remote::cerebras` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |

docs/source/distributions/self_hosted_distro/dell.md

@@ -20,7 +20,7 @@ The `llamastack/distribution-dell` distribution consists of the following provid
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `remote::tgi` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |

docs/source/distributions/self_hosted_distro/meta-reference-gpu.md

@@ -19,7 +19,7 @@ The `llamastack/distribution-meta-reference-gpu` distribution consists of the fo
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `inline::meta-reference` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |

docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md

@@ -19,7 +19,7 @@ The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `inline::meta-reference-quantized` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |

docs/source/distributions/self_hosted_distro/ollama.md

@@ -19,7 +19,7 @@ The `llamastack/distribution-ollama` distribution consists of the following prov
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `remote::ollama` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |

docs/source/distributions/self_hosted_distro/remote-vllm.md

@@ -18,7 +18,7 @@ The `llamastack/distribution-remote-vllm` distribution consists of the following
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `remote::vllm` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |

docs/source/distributions/self_hosted_distro/sambanova.md

@@ -17,7 +17,7 @@ The `llamastack/distribution-sambanova` distribution consists of the following p
 |-----|-------------|
 | agents | `inline::meta-reference` |
 | inference | `remote::sambanova` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |

docs/source/distributions/self_hosted_distro/tgi.md

@@ -20,7 +20,7 @@ The `llamastack/distribution-tgi` distribution consists of the following provide
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `remote::tgi` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |

docs/source/distributions/self_hosted_distro/together.md

@@ -19,7 +19,7 @@ The `llamastack/distribution-together` distribution consists of the following pr
 | datasetio | `remote::huggingface`, `inline::localfs` |
 | eval | `inline::meta-reference` |
 | inference | `remote::together` |
-| safety | `inline::llama-guard` |
+| safety | `inline::llama-guard`, `remote::fiddlecube` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
 | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |

docs/source/index.md

@@ -78,6 +78,7 @@ A number of "adapters" are available for some popular Inference and Vector Store
 |  Prompt Guard | Single Node |
 |  Code Scanner | Single Node |
 |  AWS Bedrock | Hosted |
+|  FiddleCube | Hosted |
 
 
 ```{toctree}

llama_stack/templates/bedrock/bedrock.py

@@ -19,7 +19,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::bedrock"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["remote::bedrock"],
+        "safety": ["remote::bedrock", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/bedrock/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - remote::bedrock
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/bedrock/run.yaml

@@ -27,6 +27,9 @@ providers:
   - provider_id: bedrock
     provider_type: remote::bedrock
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/cerebras/build.yaml

@@ -6,6 +6,7 @@ distribution_spec:
     - remote::cerebras
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     vector_io:
     - inline::faiss
     - remote::chromadb

llama_stack/templates/cerebras/cerebras.py

@@ -22,7 +22,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::cerebras"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "agents": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/cerebras/run.yaml

@@ -24,6 +24,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   vector_io:
   - provider_id: faiss
     provider_type: inline::faiss

llama_stack/templates/dell/build.yaml

@@ -11,6 +11,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/dell/dell.py

@@ -23,7 +23,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::tgi"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/dell/run-with-safety.yaml

@@ -32,6 +32,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/dell/run.yaml

@@ -28,6 +28,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/fireworks/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/fireworks/fireworks.py

@@ -28,7 +28,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::fireworks"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/fireworks/run.yaml

@@ -29,8 +29,8 @@ providers:
         namespace: null
         db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/faiss_store.db
   safety:
-  - provider_id: llama-guard
+  - provider_id: fiddlecube
-    provider_type: inline::llama-guard
+    provider_type: remote::fiddlecube
     config: {}
   agents:
   - provider_id: meta-reference

llama_stack/templates/hf-endpoint/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/hf-endpoint/hf_endpoint.py

@@ -23,7 +23,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::hf::endpoint"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/hf-endpoint/run-with-safety.yaml

@@ -37,6 +37,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/hf-endpoint/run.yaml

@@ -32,6 +32,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/hf-serverless/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/hf-serverless/hf_serverless.py

@@ -23,7 +23,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::hf::serverless"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/hf-serverless/run-with-safety.yaml

@@ -37,6 +37,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/hf-serverless/run.yaml

@@ -32,6 +32,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/meta-reference-gpu/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/meta-reference-gpu/meta_reference.py

@@ -27,7 +27,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["inline::meta-reference"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/meta-reference-gpu/run-with-safety.yaml

@@ -39,6 +39,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -33,6 +33,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/meta-reference-quantized-gpu/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py

@@ -22,7 +22,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["inline::meta-reference-quantized"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/meta-reference-quantized-gpu/run.yaml

@@ -35,6 +35,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/nvidia/build.yaml

@@ -8,6 +8,7 @@ distribution_spec:
     - inline::faiss
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/nvidia/nvidia.py

@@ -18,7 +18,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::nvidia"],
         "vector_io": ["inline::faiss"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/nvidia/run.yaml

@@ -29,6 +29,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/ollama/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/ollama/ollama.py

@@ -25,7 +25,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::ollama"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/ollama/run.yaml

@@ -31,6 +31,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/remote-vllm/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     eval:

llama_stack/templates/remote-vllm/run-with-safety.yaml

@@ -39,6 +39,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/remote-vllm/run.yaml

@@ -33,6 +33,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/remote-vllm/vllm.py

@@ -25,7 +25,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::vllm"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],
         "datasetio": ["remote::huggingface", "inline::localfs"],

llama_stack/templates/sambanova/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/sambanova/run.yaml

@@ -32,6 +32,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/sambanova/sambanova.py

@@ -24,7 +24,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::sambanova"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "tool_runtime": [

llama_stack/templates/tgi/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/tgi/run-with-safety.yaml

@@ -32,6 +32,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/tgi/run.yaml

@@ -31,6 +31,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/tgi/tgi.py

@@ -25,7 +25,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::tgi"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/together/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/together/run.yaml

@@ -32,6 +32,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/together/together.py

@@ -28,7 +28,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::together"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],

llama_stack/templates/vllm-gpu/build.yaml

@@ -10,6 +10,7 @@ distribution_spec:
     - remote::pgvector
     safety:
     - inline::llama-guard
+    - remote::fiddlecube
     agents:
     - inline::meta-reference
     telemetry:

llama_stack/templates/vllm-gpu/run.yaml

@@ -35,6 +35,9 @@ providers:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
+  - provider_id: fiddlecube
+    provider_type: remote::fiddlecube
+    config: {}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/templates/vllm-gpu/vllm.py

@@ -22,7 +22,7 @@ def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["inline::vllm"],
         "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["inline::llama-guard", "remote::fiddlecube"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],