chore!: remove telemetry API usage (#3815)

# What does this PR do? remove telemetry as a providable API from the codebase. This includes removing it from generated distributions but also the provider registry, the router, etc since `setup_logger` is tied pretty strictly to `Api.telemetry` being in impls we still need an "instantiated provider" in our implementations. However it should not be auto-routed or provided. So in validate_and_prepare_providers (called from resolve_impls) I made it so that if run_config.telemetry.enabled, we set up the meta-reference "provider" internally to be used so that log_event will work when called. This is the neatest way I think we can remove telemetry from the provider configs but also not need to rip apart the whole "telemetry is a provider" logic just yet, but we can do it internally later without disrupting users. so telemetry is removed from the registry such that if a user puts `telemetry:` as an API in their build/run config it will err out, but can still be used by us internally as we go through this transition. relates to #3806 Signed-off-by: Charlie Doern <cdoern@redhat.com>
2025-10-18 23:28:53 +00:00 · 2025-10-16 13:39:32 -04:00 · 2025-10-16 13:39:32 -04:00 · f22aaef42f
commit f22aaef42f
parent 8c5705d39e
41 changed files with 48 additions and 188 deletions
--- a/llama_stack/distributions/ci-tests/build.yaml
+++ b/llama_stack/distributions/ci-tests/build.yaml
@ -32,8 +32,6 @@ distribution_spec:
    - provider_type: inline::code-scanner
    agents:
    - provider_type: inline::meta-reference
-    telemetry:
-    - provider_type: inline::meta-reference
    post_training:
    - provider_type: inline::torchtune-cpu
    eval:
--- a/llama_stack/distributions/ci-tests/run.yaml
+++ b/llama_stack/distributions/ci-tests/run.yaml
@ -10,7 +10,6 @@ apis:
 - post_training
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -154,13 +153,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  post_training:
  - provider_id: torchtune-cpu
    provider_type: inline::torchtune-cpu
--- a/llama_stack/distributions/dell/build.yaml
+++ b/llama_stack/distributions/dell/build.yaml
@ -14,8 +14,6 @@ distribution_spec:
    - provider_type: inline::llama-guard
    agents:
    - provider_type: inline::meta-reference
-    telemetry:
-    - provider_type: inline::meta-reference
    eval:
    - provider_type: inline::meta-reference
    datasetio:
--- a/llama_stack/distributions/dell/dell.py
+++ b/llama_stack/distributions/dell/dell.py
@ -32,7 +32,6 @@ def get_distribution_template() -> DistributionTemplate:
        ],
        "safety": [BuildProvider(provider_type="inline::llama-guard")],
        "agents": [BuildProvider(provider_type="inline::meta-reference")],
-        "telemetry": [BuildProvider(provider_type="inline::meta-reference")],
        "eval": [BuildProvider(provider_type="inline::meta-reference")],
        "datasetio": [
            BuildProvider(provider_type="remote::huggingface"),
--- a/llama_stack/distributions/dell/run-with-safety.yaml
+++ b/llama_stack/distributions/dell/run-with-safety.yaml
@ -7,7 +7,6 @@ apis:
 - inference
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -45,13 +44,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
--- a/llama_stack/distributions/dell/run.yaml
+++ b/llama_stack/distributions/dell/run.yaml
@ -7,7 +7,6 @@ apis:
 - inference
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -41,13 +40,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
--- a/llama_stack/distributions/meta-reference-gpu/build.yaml
+++ b/llama_stack/distributions/meta-reference-gpu/build.yaml
@ -12,8 +12,6 @@ distribution_spec:
    - provider_type: inline::llama-guard
    agents:
    - provider_type: inline::meta-reference
-    telemetry:
-    - provider_type: inline::meta-reference
    eval:
    - provider_type: inline::meta-reference
    datasetio:
--- a/llama_stack/distributions/meta-reference-gpu/meta_reference.py
+++ b/llama_stack/distributions/meta-reference-gpu/meta_reference.py
@ -34,7 +34,6 @@ def get_distribution_template() -> DistributionTemplate:
        ],
        "safety": [BuildProvider(provider_type="inline::llama-guard")],
        "agents": [BuildProvider(provider_type="inline::meta-reference")],
-        "telemetry": [BuildProvider(provider_type="inline::meta-reference")],
        "eval": [BuildProvider(provider_type="inline::meta-reference")],
        "datasetio": [
            BuildProvider(provider_type="remote::huggingface"),
--- a/llama_stack/distributions/meta-reference-gpu/run-with-safety.yaml
+++ b/llama_stack/distributions/meta-reference-gpu/run-with-safety.yaml
@ -7,7 +7,6 @@ apis:
 - inference
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -56,13 +55,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
--- a/llama_stack/distributions/meta-reference-gpu/run.yaml
+++ b/llama_stack/distributions/meta-reference-gpu/run.yaml
@ -7,7 +7,6 @@ apis:
 - inference
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -46,13 +45,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
--- a/llama_stack/distributions/nvidia/build.yaml
+++ b/llama_stack/distributions/nvidia/build.yaml
@ -10,8 +10,6 @@ distribution_spec:
    - provider_type: remote::nvidia
    agents:
    - provider_type: inline::meta-reference
-    telemetry:
-    - provider_type: inline::meta-reference
    eval:
    - provider_type: remote::nvidia
    post_training:
--- a/llama_stack/distributions/nvidia/nvidia.py
+++ b/llama_stack/distributions/nvidia/nvidia.py
@ -21,7 +21,6 @@ def get_distribution_template(name: str = "nvidia") -> DistributionTemplate:
        "vector_io": [BuildProvider(provider_type="inline::faiss")],
        "safety": [BuildProvider(provider_type="remote::nvidia")],
        "agents": [BuildProvider(provider_type="inline::meta-reference")],
-        "telemetry": [BuildProvider(provider_type="inline::meta-reference")],
        "eval": [BuildProvider(provider_type="remote::nvidia")],
        "post_training": [BuildProvider(provider_type="remote::nvidia")],
        "datasetio": [
--- a/llama_stack/distributions/nvidia/run-with-safety.yaml
+++ b/llama_stack/distributions/nvidia/run-with-safety.yaml
@ -9,7 +9,6 @@ apis:
 - post_training
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -48,13 +47,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  eval:
  - provider_id: nvidia
    provider_type: remote::nvidia
--- a/llama_stack/distributions/nvidia/run.yaml
+++ b/llama_stack/distributions/nvidia/run.yaml
@ -9,7 +9,6 @@ apis:
 - post_training
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -43,13 +42,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  eval:
  - provider_id: nvidia
    provider_type: remote::nvidia
--- a/llama_stack/distributions/open-benchmark/build.yaml
+++ b/llama_stack/distributions/open-benchmark/build.yaml
@ -16,8 +16,6 @@ distribution_spec:
    - provider_type: inline::llama-guard
    agents:
    - provider_type: inline::meta-reference
-    telemetry:
-    - provider_type: inline::meta-reference
    eval:
    - provider_type: inline::meta-reference
    datasetio:
--- a/llama_stack/distributions/open-benchmark/open_benchmark.py
+++ b/llama_stack/distributions/open-benchmark/open_benchmark.py
@ -105,7 +105,6 @@ def get_distribution_template() -> DistributionTemplate:
        ],
        "safety": [BuildProvider(provider_type="inline::llama-guard")],
        "agents": [BuildProvider(provider_type="inline::meta-reference")],
-        "telemetry": [BuildProvider(provider_type="inline::meta-reference")],
        "eval": [BuildProvider(provider_type="inline::meta-reference")],
        "datasetio": [
            BuildProvider(provider_type="remote::huggingface"),
--- a/llama_stack/distributions/open-benchmark/run.yaml
+++ b/llama_stack/distributions/open-benchmark/run.yaml
@ -7,7 +7,6 @@ apis:
 - inference
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -76,13 +75,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
--- a/llama_stack/distributions/postgres-demo/build.yaml
+++ b/llama_stack/distributions/postgres-demo/build.yaml
@ -11,8 +11,6 @@ distribution_spec:
    - provider_type: inline::llama-guard
    agents:
    - provider_type: inline::meta-reference
-    telemetry:
-    - provider_type: inline::meta-reference
    tool_runtime:
    - provider_type: remote::brave-search
    - provider_type: remote::tavily-search
--- a/llama_stack/distributions/postgres-demo/postgres_demo.py
+++ b/llama_stack/distributions/postgres-demo/postgres_demo.py
@ -42,7 +42,6 @@ def get_distribution_template() -> DistributionTemplate:
        "vector_io": [BuildProvider(provider_type="remote::chromadb")],
        "safety": [BuildProvider(provider_type="inline::llama-guard")],
        "agents": [BuildProvider(provider_type="inline::meta-reference")],
-        "telemetry": [BuildProvider(provider_type="inline::meta-reference")],
        "tool_runtime": [
            BuildProvider(provider_type="remote::brave-search"),
            BuildProvider(provider_type="remote::tavily-search"),
@ -116,17 +115,6 @@ def get_distribution_template() -> DistributionTemplate:
                            ),
                        )
                    ],
-                    "telemetry": [
-                        Provider(
-                            provider_id="meta-reference",
-                            provider_type="inline::meta-reference",
-                            config=dict(
-                                service_name="${env.OTEL_SERVICE_NAME:=\u200b}",
-                                sinks="${env.TELEMETRY_SINKS:=console,otel_trace}",
-                                otel_exporter_otlp_endpoint="${env.OTEL_EXPORTER_OTLP_ENDPOINT:=http://localhost:4318/v1/traces}",
-                            ),
-                        )
-                    ],
                },
                default_models=default_models + [embedding_model],
                default_tool_groups=default_tool_groups,
--- a/llama_stack/distributions/postgres-demo/run.yaml
+++ b/llama_stack/distributions/postgres-demo/run.yaml
@ -4,7 +4,6 @@ apis:
 - agents
 - inference
 - safety
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -49,13 +48,6 @@ providers:
        db: ${env.POSTGRES_DB:=llamastack}
        user: ${env.POSTGRES_USER:=llamastack}
        password: ${env.POSTGRES_PASSWORD:=llamastack}
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=console,otel_trace}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=http://localhost:4318/v1/traces}
  tool_runtime:
  - provider_id: brave-search
    provider_type: remote::brave-search
--- a/llama_stack/distributions/starter-gpu/build.yaml
+++ b/llama_stack/distributions/starter-gpu/build.yaml
@ -33,8 +33,6 @@ distribution_spec:
    - provider_type: inline::code-scanner
    agents:
    - provider_type: inline::meta-reference
-    telemetry:
-    - provider_type: inline::meta-reference
    post_training:
    - provider_type: inline::huggingface-gpu
    eval:
--- a/llama_stack/distributions/starter-gpu/run.yaml
+++ b/llama_stack/distributions/starter-gpu/run.yaml
@ -10,7 +10,6 @@ apis:
 - post_training
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -154,13 +153,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  post_training:
  - provider_id: huggingface-gpu
    provider_type: inline::huggingface-gpu
--- a/llama_stack/distributions/starter/build.yaml
+++ b/llama_stack/distributions/starter/build.yaml
@ -33,8 +33,6 @@ distribution_spec:
    - provider_type: inline::code-scanner
    agents:
    - provider_type: inline::meta-reference
-    telemetry:
-    - provider_type: inline::meta-reference
    post_training:
    - provider_type: inline::torchtune-cpu
    eval:
--- a/llama_stack/distributions/starter/run.yaml
+++ b/llama_stack/distributions/starter/run.yaml
@ -10,7 +10,6 @@ apis:
 - post_training
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -154,13 +153,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  post_training:
  - provider_id: torchtune-cpu
    provider_type: inline::torchtune-cpu
--- a/llama_stack/distributions/starter/starter.py
+++ b/llama_stack/distributions/starter/starter.py
@ -120,7 +120,6 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
            BuildProvider(provider_type="inline::code-scanner"),
        ],
        "agents": [BuildProvider(provider_type="inline::meta-reference")],
-        "telemetry": [BuildProvider(provider_type="inline::meta-reference")],
        "post_training": [BuildProvider(provider_type="inline::torchtune-cpu")],
        "eval": [BuildProvider(provider_type="inline::meta-reference")],
        "datasetio": [
--- a/llama_stack/distributions/watsonx/build.yaml
+++ b/llama_stack/distributions/watsonx/build.yaml
@ -11,8 +11,6 @@ distribution_spec:
    - provider_type: inline::llama-guard
    agents:
    - provider_type: inline::meta-reference
-    telemetry:
-    - provider_type: inline::meta-reference
    eval:
    - provider_type: inline::meta-reference
    datasetio:
--- a/llama_stack/distributions/watsonx/run.yaml
+++ b/llama_stack/distributions/watsonx/run.yaml
@ -8,7 +8,6 @@ apis:
 - inference
 - safety
 - scoring
- telemetry
 - tool_runtime
 - vector_io
 providers:
@ -41,13 +40,6 @@ providers:
      responses_store:
        type: sqlite
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=}
-      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
--- a/llama_stack/distributions/watsonx/watsonx.py
+++ b/llama_stack/distributions/watsonx/watsonx.py
@ -20,7 +20,6 @@ def get_distribution_template(name: str = "watsonx") -> DistributionTemplate:
        "vector_io": [BuildProvider(provider_type="inline::faiss")],
        "safety": [BuildProvider(provider_type="inline::llama-guard")],
        "agents": [BuildProvider(provider_type="inline::meta-reference")],
-        "telemetry": [BuildProvider(provider_type="inline::meta-reference")],
        "eval": [BuildProvider(provider_type="inline::meta-reference")],
        "datasetio": [
            BuildProvider(provider_type="remote::huggingface"),