feat(eval): update promptfoo config and memory_ops case

- Updated promptfoo configuration to specify individual test cases, excluding progressive_disclosure.yaml.
- Modified memory_ops.yaml to change the description of a test case to reflect the agent's response behavior with memory active.

eval/cases/memory_ops.yaml

@@ -48,8 +48,7 @@
                          out.includes('no matching') || out.length > 10;
         return { pass: graceful, score: graceful ? 1.0 : 0.0, reason: graceful ? 'handled empty search gracefully' : 'no meaningful response' };
 
-- description: "reduced iterations provider: agent respects max_tool_iterations limit"
-  providers: ["picoclaw-no-memory"]
+- description: "agent responds to greeting with memory system active"
   vars:
     prompt: "Hello, what can you help me with today?"
   assert:

eval/promptfooconfig-default.yaml

@@ -27,6 +27,17 @@ defaultTest:
         const ok = dur < 60000;
         return { pass: ok, score: ok ? 1.0 : 0.0, reason: `duration: ${dur}ms (limit: 60000ms)` };
 
-tests: "cases/*.yaml"
+# Excludes progressive_disclosure.yaml (requires picoclaw-progressive provider)
+# Run `make eval-matrix` to test all providers including progressive disclosure.
+tests:
+  - "cases/tool_calling.yaml"
+  - "cases/multi_step.yaml"
+  - "cases/edge_cases.yaml"
+  - "cases/token_efficiency.yaml"
+  - "cases/memory_ops.yaml"
+  - "cases/subagent.yaml"
+  - "cases/skills.yaml"
+  - "cases/reasoning.yaml"
+  - "cases/error_recovery.yaml"
 
 outputPath: "results/latest.json"