fix(evals): restore workspace.template for mock agent evals

- file-changes, file-changes-graders, functional-grading: added
  workspace.template to eval files (was previously in target config
  via the now-removed workspace_template field)
- agent-skills-evals: removed broken echo provider — these evals
  need a real agent (skill-trigger), so they use root default target

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: christso

examples/features/agent-skills-evals/.agentv/providers/echo.ts

@@ -10,6 +10,9 @@
 
 description: Verify file_changes diffs are accessible to LLM grader (rubrics, built-in, and copilot-cli)
 
+workspace:
+  template: ../workspace-template
+
 execution:
   target: mock_agent
 

examples/features/agent-skills-evals/.agentv/targets.yaml

@@ -12,6 +12,9 @@
 name: file-changes
 description: Verify file_changes captures edits, creates, and deletes across multiple tests
 
+workspace:
+  template: ../workspace-template
+
 execution:
   target: mock_agent
 

examples/features/file-changes-graders/evals/dataset.eval.yaml

@@ -13,6 +13,9 @@
 name: functional-grading
 description: Functional grading with workspace_path — deploy-and-test pattern
 
+workspace:
+  template: ../workspace-template
+
 execution:
   target: mock_agent