feat: add /jobs API

This API will be later tied to jobs as defined for specific flows
(post-training, eval, etc.) through the common scheduler mechanism.

Note: At the moment, API does nothing useful. (Except returning Not
Implemented errors when called.)

This is an alternative to developing per-flow jobs APIs. Eventually,
once /jobs API is implemented, we should be able to deprecate existing
APIs under /v1/post-training/, /v1/eval/ etc.

See #1587 (tracker)
See #1238 (design details)

Note: This is an alternative path to #1582 and #1583.

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>

docs/_static/llama-stack-spec.yaml

@@ -142,6 +142,30 @@ paths:
             schema:
               $ref: '#/components/schemas/BatchCompletionRequest'
         required: true
+  /v1/jobs/{job_id}/cancel:
+    post:
+      responses:
+        '200':
+          description: OK
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - Jobs
+      description: ''
+      parameters:
+        - name: job_id
+          in: path
+          required: true
+          schema:
+            type: string
   /v1/post-training/job/cancel:
     post:
       responses:
@@ -633,6 +657,57 @@ paths:
           required: true
           schema:
             type: string
+  /v1/jobs/{job_id}:
+    get:
+      responses:
+        '200':
+          description: OK
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/JobInfo'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - Jobs
+      description: ''
+      parameters:
+        - name: job_id
+          in: path
+          required: true
+          schema:
+            type: string
+    delete:
+      responses:
+        '200':
+          description: OK
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - Jobs
+      description: ''
+      parameters:
+        - name: job_id
+          in: path
+          required: true
+          schema:
+            type: string
   /v1/inference/embeddings:
     post:
       responses:
@@ -1731,6 +1806,29 @@ paths:
           required: true
           schema:
             type: string
+  /v1/jobs:
+    get:
+      responses:
+        '200':
+          description: OK
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ListJobsResponse'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - Jobs
+      description: ''
+      parameters: []
   /v1/models:
     get:
       responses:
@@ -3213,6 +3311,10 @@ components:
     CompletionResponse:
       type: object
       properties:
+        metrics:
+          type: array
+          items:
+            $ref: '#/components/schemas/MetricEvent'
         content:
           type: string
           description: The generated completion text
@@ -3531,6 +3633,10 @@ components:
     CompletionResponseStreamChunk:
       type: object
       properties:
+        metrics:
+          type: array
+          items:
+            $ref: '#/components/schemas/MetricEvent'
         delta:
           type: string
           description: >-
@@ -4901,6 +5007,60 @@ components:
       required:
         - type
       title: UnionType
+    JobArtifact:
+      type: object
+      properties:
+        name:
+          type: string
+        type:
+          type: string
+        uri:
+          type: string
+        metadata:
+          type: object
+          title: dict
+          description: >-
+            dict() -> new empty dictionary dict(mapping) -> new dictionary initialized
+            from a mapping object's     (key, value) pairs dict(iterable) -> new dictionary
+            initialized as if via:     d = {}     for k, v in iterable:         d[k]
+            = v dict(**kwargs) -> new dictionary initialized with the name=value pairs     in
+            the keyword argument list.  For example:  dict(one=1, two=2)
+      additionalProperties: false
+      required:
+        - name
+        - type
+        - uri
+        - metadata
+      title: JobArtifact
+    JobInfo:
+      type: object
+      properties:
+        uuid:
+          type: string
+        type:
+          type: string
+        status:
+          type: string
+        scheduled_at:
+          type: string
+          format: date-time
+        started_at:
+          type: string
+          format: date-time
+        completed_at:
+          type: string
+          format: date-time
+        artifacts:
+          type: array
+          items:
+            $ref: '#/components/schemas/JobArtifact'
+      additionalProperties: false
+      required:
+        - uuid
+        - type
+        - status
+        - artifacts
+      title: JobInfo
     Model:
       type: object
       properties:
@@ -5562,6 +5722,17 @@ components:
       title: ListFileResponse
       description: >-
         Response representing a list of file entries.
+    ListJobsResponse:
+      type: object
+      properties:
+        data:
+          type: array
+          items:
+            $ref: '#/components/schemas/JobInfo'
+      additionalProperties: false
+      required:
+        - data
+      title: ListJobsResponse
     ListModelsResponse:
       type: object
       properties:
@@ -6818,6 +6989,7 @@ tags:
       Llama Stack Inference API for generating completions, chat completions, and
       embeddings.
   - name: Inspect
+  - name: Jobs
   - name: Models
   - name: PostTraining (Coming Soon)
   - name: Safety
@@ -6842,6 +7014,7 @@ x-tagGroups:
       - Files (Coming Soon)
       - Inference
       - Inspect
+      - Jobs
       - Models
       - PostTraining (Coming Soon)
       - Safety