Merge branch 'main' into nvidia-e2e-notebook

2025-07-21 12:09:40 +00:00 · 2025-05-06 11:12:34 -04:00 · 2025-05-06 11:12:34 -04:00 · b1d941e1f0
commit b1d941e1f0
parent 012dd6891f 2413447467
447 changed files with 6462 additions and 64778 deletions
--- a/llama_stack/templates/bedrock/bedrock.py
+++ b/llama_stack/templates/bedrock/bedrock.py
@ -29,7 +29,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -55,10 +54,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/bedrock/build.yaml
+++ b/llama_stack/templates/bedrock/build.yaml
@ -26,7 +26,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/bedrock/run.yaml
+++ b/llama_stack/templates/bedrock/run.yaml
@ -87,9 +87,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -140,7 +137,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/cerebras/build.yaml
+++ b/llama_stack/templates/cerebras/build.yaml
@ -27,6 +27,5 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
 image_type: conda
--- a/llama_stack/templates/cerebras/cerebras.py
+++ b/llama_stack/templates/cerebras/cerebras.py
@ -34,7 +34,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
        ],
    }
@ -77,10 +76,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/cerebras/report.md
+++ b/llama_stack/templates/cerebras/report.md
@ -41,4 +41,3 @@
 |:-----|:-----|:-----|:-----|
 | /create_agent_turn | rag | test_rag_agent | ✅ |
 | /create_agent_turn | custom_tool | test_custom_tool | ❌ |
-| /create_agent_turn | code_execution | test_code_interpreter_for_attachments | ✅ |
--- a/llama_stack/templates/cerebras/run.yaml
+++ b/llama_stack/templates/cerebras/run.yaml
@ -93,9 +93,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -138,7 +135,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/ci-tests/build.yaml
+++ b/llama_stack/templates/ci-tests/build.yaml
@ -27,7 +27,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/ci-tests/ci_tests.py
+++ b/llama_stack/templates/ci-tests/ci_tests.py
@ -40,7 +40,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -71,10 +70,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]
    available_models = {
        "fireworks": MODEL_ENTRIES,
--- a/llama_stack/templates/ci-tests/run.yaml
+++ b/llama_stack/templates/ci-tests/run.yaml
@ -90,9 +90,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -236,7 +233,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/dell/build.yaml
+++ b/llama_stack/templates/dell/build.yaml
@ -28,6 +28,5 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
 image_type: conda
--- a/llama_stack/templates/dell/dell.py
+++ b/llama_stack/templates/dell/dell.py
@ -30,7 +30,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
        ],
    }
@ -87,10 +86,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/dell/run-with-safety.yaml
+++ b/llama_stack/templates/dell/run-with-safety.yaml
@ -93,9 +93,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -127,7 +124,5 @@ tool_groups:
  provider_id: brave-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/dell/run.yaml
+++ b/llama_stack/templates/dell/run.yaml
@ -89,9 +89,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -118,7 +115,5 @@ tool_groups:
  provider_id: brave-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/dev/build.yaml
+++ b/llama_stack/templates/dev/build.yaml
@ -31,7 +31,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/dev/dev.py
+++ b/llama_stack/templates/dev/dev.py
@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.

-from typing import List, Tuple

 from llama_stack.apis.models.models import ModelType
 from llama_stack.distribution.datatypes import (
@ -50,7 +49,7 @@ from llama_stack.templates.template import (
 )


-def get_inference_providers() -> Tuple[List[Provider], List[ModelInput]]:
+def get_inference_providers() -> tuple[list[Provider], list[ModelInput]]:
    # in this template, we allow each API key to be optional
    providers = [
        (
@ -107,7 +106,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -150,10 +148,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]
    embedding_model = ModelInput(
        model_id="all-MiniLM-L6-v2",
--- a/llama_stack/templates/dev/run.yaml
+++ b/llama_stack/templates/dev/run.yaml
@ -119,9 +119,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -432,7 +429,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/fireworks/build.yaml
+++ b/llama_stack/templates/fireworks/build.yaml
@ -28,7 +28,6 @@ distribution_spec:
    - remote::brave-search
    - remote::tavily-search
    - remote::wolfram-alpha
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/fireworks/fireworks.py
+++ b/llama_stack/templates/fireworks/fireworks.py
@ -40,7 +40,6 @@ def get_distribution_template() -> DistributionTemplate:
            "remote::brave-search",
            "remote::tavily-search",
            "remote::wolfram-alpha",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -90,10 +89,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/fireworks/report.md
+++ b/llama_stack/templates/fireworks/report.md
@ -43,4 +43,3 @@
 |:-----|:-----|:-----|:-----|:-----|
 | inline::meta-reference | /create_agent_turn | rag | test_rag_agent | ✅ |
 | inline::meta-reference | /create_agent_turn | custom_tool | test_custom_tool | ✅ |
-| inline::meta-reference | /create_agent_turn | code_execution | test_code_interpreter_for_attachments | ✅ |
--- a/llama_stack/templates/fireworks/run-with-safety.yaml
+++ b/llama_stack/templates/fireworks/run-with-safety.yaml
@ -102,9 +102,6 @@ providers:
    provider_type: remote::wolfram-alpha
    config:
      api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -255,7 +252,5 @@ tool_groups:
  provider_id: wolfram-alpha
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/fireworks/run.yaml
+++ b/llama_stack/templates/fireworks/run.yaml
@ -97,9 +97,6 @@ providers:
    provider_type: remote::wolfram-alpha
    config:
      api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -245,7 +242,5 @@ tool_groups:
  provider_id: wolfram-alpha
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/groq/build.yaml
+++ b/llama_stack/templates/groq/build.yaml
@ -24,6 +24,5 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
 image_type: conda
--- a/llama_stack/templates/groq/groq.py
+++ b/llama_stack/templates/groq/groq.py
@ -33,7 +33,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
        ],
    }
@ -72,10 +71,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/groq/run.yaml
+++ b/llama_stack/templates/groq/run.yaml
@ -93,9 +93,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -203,7 +200,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/hf-endpoint/build.yaml
+++ b/llama_stack/templates/hf-endpoint/build.yaml
@ -26,7 +26,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/hf-endpoint/hf_endpoint.py
+++ b/llama_stack/templates/hf-endpoint/hf_endpoint.py
@ -32,7 +32,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -79,10 +78,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/hf-endpoint/run-with-safety.yaml
+++ b/llama_stack/templates/hf-endpoint/run-with-safety.yaml
@ -98,9 +98,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -135,7 +132,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/hf-endpoint/run.yaml
+++ b/llama_stack/templates/hf-endpoint/run.yaml
@ -93,9 +93,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -125,7 +122,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/hf-serverless/build.yaml
+++ b/llama_stack/templates/hf-serverless/build.yaml
@ -27,7 +27,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/hf-serverless/hf_serverless.py
+++ b/llama_stack/templates/hf-serverless/hf_serverless.py
@ -32,7 +32,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -80,10 +79,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/hf-serverless/run-with-safety.yaml
+++ b/llama_stack/templates/hf-serverless/run-with-safety.yaml
@ -98,9 +98,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -135,7 +132,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/hf-serverless/run.yaml
+++ b/llama_stack/templates/hf-serverless/run.yaml
@ -93,9 +93,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -125,7 +122,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/llama_api/build.yaml
+++ b/llama_stack/templates/llama_api/build.yaml
@ -27,7 +27,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/llama_api/llama_api.py
+++ b/llama_stack/templates/llama_api/llama_api.py
@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.

-from typing import List, Tuple

 from llama_stack.apis.models.models import ModelType
 from llama_stack.distribution.datatypes import (
@ -36,7 +35,7 @@ from llama_stack.templates.template import (
 )


-def get_inference_providers() -> Tuple[List[Provider], List[ModelInput]]:
+def get_inference_providers() -> tuple[list[Provider], list[ModelInput]]:
    # in this template, we allow each API key to be optional
    providers = [
        (
@ -73,7 +72,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -116,10 +114,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]
    embedding_model = ModelInput(
        model_id="all-MiniLM-L6-v2",
--- a/llama_stack/templates/llama_api/run.yaml
+++ b/llama_stack/templates/llama_api/run.yaml
@ -102,9 +102,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -161,7 +158,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/meta-reference-gpu/build.yaml
+++ b/llama_stack/templates/meta-reference-gpu/build.yaml
@ -26,7 +26,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/meta-reference-gpu/meta_reference.py
+++ b/llama_stack/templates/meta-reference-gpu/meta_reference.py
@ -36,7 +36,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -86,10 +85,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
@ -108,9 +108,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -145,7 +142,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/meta-reference-gpu/run.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run.yaml
@ -98,9 +98,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -130,7 +127,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/ollama/build.yaml
+++ b/llama_stack/templates/ollama/build.yaml
@ -26,7 +26,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
    - remote::wolfram-alpha
--- a/llama_stack/templates/ollama/ollama.py
+++ b/llama_stack/templates/ollama/ollama.py
@ -31,7 +31,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
            "remote::wolfram-alpha",
@ -75,10 +74,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
        ToolGroupInput(
            toolgroup_id="builtin::wolfram_alpha",
            provider_id="wolfram-alpha",
--- a/llama_stack/templates/ollama/report.md
+++ b/llama_stack/templates/ollama/report.md
@ -41,4 +41,3 @@
 |:-----|:-----|:-----|:-----|
 | /create_agent_turn | rag | test_rag_agent | ✅ |
 | /create_agent_turn | custom_tool | test_custom_tool | ✅ |
-| /create_agent_turn | code_execution | test_code_interpreter_for_attachments | ✅ |
--- a/llama_stack/templates/ollama/run-with-safety.yaml
+++ b/llama_stack/templates/ollama/run-with-safety.yaml
@ -91,9 +91,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -136,8 +133,6 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 - toolgroup_id: builtin::wolfram_alpha
  provider_id: wolfram-alpha
 server:
--- a/llama_stack/templates/ollama/run.yaml
+++ b/llama_stack/templates/ollama/run.yaml
@ -89,9 +89,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -126,8 +123,6 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 - toolgroup_id: builtin::wolfram_alpha
  provider_id: wolfram-alpha
 server:
--- a/llama_stack/templates/open-benchmark/build.yaml
+++ b/llama_stack/templates/open-benchmark/build.yaml
@ -30,7 +30,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/open-benchmark/open_benchmark.py
+++ b/llama_stack/templates/open-benchmark/open_benchmark.py
@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.

-from typing import Dict, List, Tuple

 from llama_stack.apis.datasets import DatasetPurpose, URIDataSource
 from llama_stack.apis.models.models import ModelType
@ -36,7 +35,7 @@ from llama_stack.templates.template import (
 )


-def get_inference_providers() -> Tuple[List[Provider], Dict[str, List[ProviderModelEntry]]]:
+def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderModelEntry]]]:
    # in this template, we allow each API key to be optional
    providers = [
        (
@ -108,7 +107,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -146,10 +144,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    default_models = get_model_registry(available_models) + [
--- a/llama_stack/templates/open-benchmark/run.yaml
+++ b/llama_stack/templates/open-benchmark/run.yaml
@ -116,9 +116,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -242,7 +239,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/passthrough/build.yaml
+++ b/llama_stack/templates/passthrough/build.yaml
@ -28,7 +28,6 @@ distribution_spec:
    - remote::brave-search
    - remote::tavily-search
    - remote::wolfram-alpha
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/passthrough/passthrough.py
+++ b/llama_stack/templates/passthrough/passthrough.py
@ -38,7 +38,6 @@ def get_distribution_template() -> DistributionTemplate:
            "remote::brave-search",
            "remote::tavily-search",
            "remote::wolfram-alpha",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -100,10 +99,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/passthrough/run-with-safety.yaml
+++ b/llama_stack/templates/passthrough/run-with-safety.yaml
@ -102,9 +102,6 @@ providers:
    provider_type: remote::wolfram-alpha
    config:
      api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -148,7 +145,5 @@ tool_groups:
  provider_id: wolfram-alpha
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/passthrough/run.yaml
+++ b/llama_stack/templates/passthrough/run.yaml
@ -97,9 +97,6 @@ providers:
    provider_type: remote::wolfram-alpha
    config:
      api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -138,7 +135,5 @@ tool_groups:
  provider_id: wolfram-alpha
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/remote-vllm/build.yaml
+++ b/llama_stack/templates/remote-vllm/build.yaml
@ -27,7 +27,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
    - remote::wolfram-alpha
--- a/llama_stack/templates/remote-vllm/run-with-safety.yaml
+++ b/llama_stack/templates/remote-vllm/run-with-safety.yaml
@ -102,9 +102,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -143,8 +140,6 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 - toolgroup_id: builtin::wolfram_alpha
  provider_id: wolfram-alpha
 server:
--- a/llama_stack/templates/remote-vllm/run.yaml
+++ b/llama_stack/templates/remote-vllm/run.yaml
@ -95,9 +95,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -131,8 +128,6 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 - toolgroup_id: builtin::wolfram_alpha
  provider_id: wolfram-alpha
 server:
--- a/llama_stack/templates/remote-vllm/vllm.py
+++ b/llama_stack/templates/remote-vllm/vllm.py
@ -34,7 +34,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
            "remote::wolfram-alpha",
@ -84,10 +83,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
        ToolGroupInput(
            toolgroup_id="builtin::wolfram_alpha",
            provider_id="wolfram-alpha",
--- a/llama_stack/templates/sambanova/build.yaml
+++ b/llama_stack/templates/sambanova/build.yaml
@ -17,6 +17,5 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
 image_type: conda
--- a/llama_stack/templates/sambanova/run.yaml
+++ b/llama_stack/templates/sambanova/run.yaml
@ -65,9 +65,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -186,7 +183,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/sambanova/sambanova.py
+++ b/llama_stack/templates/sambanova/sambanova.py
@ -31,7 +31,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
        ],
    }
@ -80,10 +79,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/template.py
+++ b/llama_stack/templates/template.py
@ -5,7 +5,7 @@
 # the root directory of this source tree.

 from pathlib import Path
-from typing import Dict, List, Literal, Optional, Tuple
+from typing import Literal

 import jinja2
 import yaml
@ -32,8 +32,8 @@ from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig


 def get_model_registry(
-    available_models: Dict[str, List[ProviderModelEntry]],
-) -> List[ModelInput]:
+    available_models: dict[str, list[ProviderModelEntry]],
+) -> list[ModelInput]:
    models = []
    for provider_id, entries in available_models.items():
        for entry in entries:
@ -57,18 +57,18 @@ class DefaultModel(BaseModel):


 class RunConfigSettings(BaseModel):
-    provider_overrides: Dict[str, List[Provider]] = Field(default_factory=dict)
-    default_models: Optional[List[ModelInput]] = None
-    default_shields: Optional[List[ShieldInput]] = None
-    default_tool_groups: Optional[List[ToolGroupInput]] = None
-    default_datasets: Optional[List[DatasetInput]] = None
-    default_benchmarks: Optional[List[BenchmarkInput]] = None
+    provider_overrides: dict[str, list[Provider]] = Field(default_factory=dict)
+    default_models: list[ModelInput] | None = None
+    default_shields: list[ShieldInput] | None = None
+    default_tool_groups: list[ToolGroupInput] | None = None
+    default_datasets: list[DatasetInput] | None = None
+    default_benchmarks: list[BenchmarkInput] | None = None

    def run_config(
        self,
        name: str,
-        providers: Dict[str, List[str]],
-        container_image: Optional[str] = None,
+        providers: dict[str, list[str]],
+        container_image: str | None = None,
    ) -> StackRunConfig:
        provider_registry = get_provider_registry()

@ -135,15 +135,15 @@ class DistributionTemplate(BaseModel):
    description: str
    distro_type: Literal["self_hosted", "remote_hosted", "ondevice"]

-    providers: Dict[str, List[str]]
-    run_configs: Dict[str, RunConfigSettings]
-    template_path: Optional[Path] = None
+    providers: dict[str, list[str]]
+    run_configs: dict[str, RunConfigSettings]
+    template_path: Path | None = None

    # Optional configuration
-    run_config_env_vars: Optional[Dict[str, Tuple[str, str]]] = None
-    container_image: Optional[str] = None
+    run_config_env_vars: dict[str, tuple[str, str]] | None = None
+    container_image: str | None = None

-    available_models_by_provider: Optional[Dict[str, List[ProviderModelEntry]]] = None
+    available_models_by_provider: dict[str, list[ProviderModelEntry]] | None = None

    def build_config(self) -> BuildConfig:
        return BuildConfig(
--- a/llama_stack/templates/tgi/build.yaml
+++ b/llama_stack/templates/tgi/build.yaml
@ -27,7 +27,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/tgi/run-with-safety.yaml
+++ b/llama_stack/templates/tgi/run-with-safety.yaml
@ -93,9 +93,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -125,7 +122,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/tgi/run.yaml
+++ b/llama_stack/templates/tgi/run.yaml
@ -92,9 +92,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -124,7 +121,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/tgi/tgi.py
+++ b/llama_stack/templates/tgi/tgi.py
@ -34,7 +34,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -83,10 +82,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/together/build.yaml
+++ b/llama_stack/templates/together/build.yaml
@ -27,7 +27,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
    - remote::wolfram-alpha
--- a/llama_stack/templates/together/report.md
+++ b/llama_stack/templates/together/report.md
@ -43,4 +43,3 @@
 |:-----|:-----|:-----|:-----|:-----|
 | inline::meta-reference | /create_agent_turn | rag | test_rag_agent | ✅ |
 | inline::meta-reference | /create_agent_turn | custom_tool | test_custom_tool | ✅ |
-| inline::meta-reference | /create_agent_turn | code_execution | test_code_interpreter_for_attachments | ✅ |
--- a/llama_stack/templates/together/run-with-safety.yaml
+++ b/llama_stack/templates/together/run-with-safety.yaml
@ -98,9 +98,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -270,8 +267,6 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 - toolgroup_id: builtin::wolfram_alpha
  provider_id: wolfram-alpha
 server:
--- a/llama_stack/templates/together/run.yaml
+++ b/llama_stack/templates/together/run.yaml
@ -93,9 +93,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -260,8 +257,6 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 - toolgroup_id: builtin::wolfram_alpha
  provider_id: wolfram-alpha
 server:
--- a/llama_stack/templates/together/together.py
+++ b/llama_stack/templates/together/together.py
@ -39,7 +39,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
            "remote::wolfram-alpha",
@ -74,10 +73,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
        ToolGroupInput(
            toolgroup_id="builtin::wolfram_alpha",
            provider_id="wolfram-alpha",
--- a/llama_stack/templates/verification/build.yaml
+++ b/llama_stack/templates/verification/build.yaml
@ -32,7 +32,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/verification/run.yaml
+++ b/llama_stack/templates/verification/run.yaml
@ -126,9 +126,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -640,7 +637,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/verification/verification.py
+++ b/llama_stack/templates/verification/verification.py
@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.

-from typing import Dict, List, Tuple

 from llama_stack.apis.models.models import ModelType
 from llama_stack.distribution.datatypes import (
@ -51,7 +50,7 @@ from llama_stack.templates.template import (
 )


-def get_inference_providers() -> Tuple[List[Provider], Dict[str, List[ProviderModelEntry]]]:
+def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderModelEntry]]]:
    # in this template, we allow each API key to be optional
    providers = [
        (
@ -113,7 +112,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -156,10 +154,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]
    embedding_model = ModelInput(
        model_id="all-MiniLM-L6-v2",
--- a/llama_stack/templates/vllm-gpu/build.yaml
+++ b/llama_stack/templates/vllm-gpu/build.yaml
@ -27,7 +27,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/vllm-gpu/run.yaml
+++ b/llama_stack/templates/vllm-gpu/run.yaml
@ -97,9 +97,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -129,7 +126,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/vllm-gpu/vllm.py
+++ b/llama_stack/templates/vllm-gpu/vllm.py
@ -31,7 +31,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -75,10 +74,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    return DistributionTemplate(
--- a/llama_stack/templates/watsonx/build.yaml
+++ b/llama_stack/templates/watsonx/build.yaml
@ -24,7 +24,6 @@ distribution_spec:
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
-    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
 image_type: conda
--- a/llama_stack/templates/watsonx/run.yaml
+++ b/llama_stack/templates/watsonx/run.yaml
@ -91,9 +91,6 @@ providers:
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:}
      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
@ -204,7 +201,5 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
  port: 8321
--- a/llama_stack/templates/watsonx/watsonx.py
+++ b/llama_stack/templates/watsonx/watsonx.py
@ -25,7 +25,6 @@ def get_distribution_template() -> DistributionTemplate:
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
-            "inline::code-interpreter",
            "inline::rag-runtime",
            "remote::model-context-protocol",
        ],
@ -49,10 +48,6 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
    ]

    default_models = get_model_registry(available_models)