From 9ce00ede9bb2f1db7a91d6d4379886294cad287a Mon Sep 17 00:00:00 2001
From: Xi Yan <xiyan@meta.com>
Date: Thu, 13 Feb 2025 09:48:52 -0800
Subject: [PATCH] update

---
 docs/_static/llama-stack-spec.html            | 55 +++----------------
 docs/_static/llama-stack-spec.yaml            | 13 +----
 .../Llama_Stack_Benchmark_Evals.ipynb         |  2 +-
 .../distribution/routers/routing_tables.py    |  6 ++
 4 files changed, 18 insertions(+), 58 deletions(-)

diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html
index 2c5827d37..6cd8b4758 100644
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@@ -2665,15 +2665,6 @@
             "EvalTask": {
                 "type": "object",
                 "properties": {
-                    "identifier": {
-                        "type": "string"
-                    },
-                    "provider_resource_id": {
-                        "type": "string"
-                    },
-                    "provider_id": {
-                        "type": "string"
-                    },
                     "type": {
                         "type": "string",
                         "const": "eval_task",
@@ -2682,53 +2673,23 @@
                     "dataset_id": {
                         "type": "string"
                     },
-                    "scoring_functions": {
-                        "type": "array",
-                        "items": {
-                            "type": "string"
-                        }
-                    },
-                    "metadata": {
-                        "type": "object",
-                        "additionalProperties": {
-                            "oneOf": [
-                                {
-                                    "type": "null"
-                                },
-                                {
-                                    "type": "boolean"
-                                },
-                                {
-                                    "type": "number"
-                                },
-                                {
-                                    "type": "string"
-                                },
-                                {
-                                    "type": "array"
-                                },
-                                {
-                                    "type": "object"
-                                }
-                            ]
-                        }
+                    "config": {
+                        "$ref": "#/components/schemas/AgentConfig"
                     }
                 },
                 "additionalProperties": false,
                 "required": [
-                    "identifier",
-                    "provider_resource_id",
-                    "provider_id",
                     "type",
-                    "dataset_id",
-                    "scoring_functions",
-                    "metadata"
+                    "config"
                 ]
             },
             "ListEvalTasksResponse": {
                 "type": "object",
                 "properties": {
-                    "data": {
+                    "sampling_params": {
+                        "$ref": "#/components/schemas/SamplingParams"
+                    },
+                    "input_shields": {
                         "type": "array",
                         "items": {
                             "$ref": "#/components/schemas/EvalTask"
@@ -2768,7 +2729,7 @@
                     "input_shields": {
                         "type": "array",
                         "items": {
-                            "type": "string"
+                            "$ref": "#/components/schemas/ToolDef"
                         }
                     },
                     "output_shields": {
diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml
index c743ce47a..19980de99 100644
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@@ -1616,12 +1616,6 @@ components:
     EvalTask:
       type: object
       properties:
-        identifier:
-          type: string
-        provider_resource_id:
-          type: string
-        provider_id:
-          type: string
         type:
           type: string
           const: eval_task
@@ -1644,9 +1638,6 @@ components:
               - type: object
       additionalProperties: false
       required:
-        - identifier
-        - provider_resource_id
-        - provider_id
         - type
         - dataset_id
         - scoring_functions
@@ -1654,7 +1645,9 @@ components:
     ListEvalTasksResponse:
       type: object
       properties:
-        data:
+        sampling_params:
+          $ref: '#/components/schemas/SamplingParams'
+        input_shields:
           type: array
           items:
             $ref: '#/components/schemas/EvalTask'
diff --git a/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb b/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
index 8eecf84ab..2861c8499 100644
--- a/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
+++ b/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
@@ -1214,7 +1214,7 @@
         "            \"sampling_params\": {\n",
         "                \"strategy\": {\n",
         "                    \"type\": \"greedy\",\n",
-        "                },\n",
+        "                },b\n",
         "                \"max_tokens\": 4096,\n",
         "                \"repeat_penalty\": 1.0,\n",
         "            },\n",
diff --git a/llama_stack/distribution/routers/routing_tables.py b/llama_stack/distribution/routers/routing_tables.py
index ec258af49..563c5c5ab 100644
--- a/llama_stack/distribution/routers/routing_tables.py
+++ b/llama_stack/distribution/routers/routing_tables.py
@@ -472,16 +472,20 @@ class BenchmarksRoutingTable(CommonRoutingTableImpl, Benchmarks):
     async def DEPRECATED_list_eval_tasks(self) -> ListBenchmarksResponse:
         logger.warning("DEPRECATED: Use /eval/benchmarks instead")
         return await self.list_benchmarks()
+        return await self.list_benchmarks()
 
     async def DEPRECATED_get_eval_task(
         self,
+        task_id: str,
         eval_task_id: str,
     ) -> Optional[Benchmark]:
         logger.warning("DEPRECATED: Use /eval/benchmarks instead")
+        return await self.get_benchmark(task_id)
         return await self.get_benchmark(eval_task_id)
 
     async def DEPRECATED_register_eval_task(
         self,
+        task_id: str,
         eval_task_id: str,
         dataset_id: str,
         scoring_functions: List[str],
@@ -490,6 +494,8 @@ class BenchmarksRoutingTable(CommonRoutingTableImpl, Benchmarks):
         metadata: Optional[Dict[str, Any]] = None,
     ) -> None:
         logger.warning("DEPRECATED: Use /eval/benchmarks instead")
+        return await self.register_benchmark(
+            benchmark_id=task_id,
         return await self.register_benchmark(
             benchmark_id=eval_task_id,
             dataset_id=dataset_id,