debug(ci): remove tee pipe and limit to 2 eval sets for debugging

The tee pipe was truncating output — summary never appeared.
Temporarily limit to 2 eval sets to verify summary prints.

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

Author: christso

.github/workflows/evals.yml

@@ -6,7 +6,7 @@ on:
       suite_filter:
         description: "Comma-separated glob patterns for eval files to run"
         required: false
-        default: "evals/**/*.eval.yaml,examples/**/*.eval.yaml,examples/**/*.EVAL.yaml,examples/**/EVAL.yaml"
+        default: ""
       target:
         description: "Optional target override (leave empty to use each eval's own target)"
         required: false
@@ -60,7 +60,7 @@ jobs:
       - name: Resolve inputs
         id: filter
         env:
-          DEFAULT_PATTERNS: "evals/**/*.eval.yaml,examples/**/*.eval.yaml,examples/**/*.EVAL.yaml,examples/**/EVAL.yaml"
+          DEFAULT_PATTERNS: "examples/features/assert/evals/*.eval.yaml,examples/features/deterministic-evaluators/evals/*.eval.yaml,examples/features/agent-skills-evals/*.EVAL.yaml"
           # Exclude evals that need local scripts or multiple agent targets.
           # Negation patterns (!glob) are supported by the CLI.
           # multi-model-benchmark: needs multiple agents
@@ -98,10 +98,10 @@ jobs:
             --threshold ${{ steps.filter.outputs.threshold }} \
             --output .agentv/ci-results/junit.xml \
             --benchmark-json .agentv/ci-results/benchmark.json \
-            --artifacts .agentv/ci-results/artifacts \
-            2>&1 | tee .agentv/ci-results/eval-output.log
+            --artifacts .agentv/ci-results/artifacts
+          EXIT_CODE=$?
 
-          echo "exit_code=${PIPESTATUS[0]}" >> "$GITHUB_OUTPUT"
+          echo "exit_code=$EXIT_CODE" >> "$GITHUB_OUTPUT"
 
       - name: Post eval summary
         if: always()