From 26d0aa11eea7cbc9495a36a1154a169ecb32d9f6 Mon Sep 17 00:00:00 2001
From: Levi Neely <lneely@pascom.net>
Date: Fri, 20 Mar 2026 15:42:24 +0100
Subject: [PATCH] Remove obsolete test scripts

---
 test-code-execution.sh | 73 ------------------------------------------
 test_beads.sh          | 25 ---------------
 2 files changed, 98 deletions(-)
 delete mode 100755 test-code-execution.sh
 delete mode 100644 test_beads.sh

diff --git a/test-code-execution.sh b/test-code-execution.sh
deleted file mode 100755
index 51c50b1..0000000
--- a/test-code-execution.sh
+++ /dev/null
@@ -1,73 +0,0 @@
-#!/bin/bash
-# Test script to verify agents use execute_code pattern
-# Usage: ./test-code-execution.sh
-
-set -e
-
-NAMESPACE=$(namespace)
-if [ -z "$NAMESPACE" ]; then
-    echo "Error: No namespace found. Is anvillm running?"
-    exit 1
-fi
-
-AGENT_MOUNT="agent"
-
-echo "=== Testing Code Execution Pattern Adoption ==="
-echo ""
-
-# Create test agent with Taskmaster template
-echo "Creating test agent..."
-echo "new kiro-cli ." | 9p write $AGENT_MOUNT/ctl
-TEST_AGENT_ID=$(9p read $AGENT_MOUNT/list | head -1 | awk '{print $1}')
-echo "test-agent" | 9p write $AGENT_MOUNT/$TEST_AGENT_ID/alias
-
-# Load Taskmaster context
-cat ./bot-templates/Taskmaster | grep -A 1000 "^cat <<EOF" | grep -B 1000 "^EOF$" | grep -v "^cat <<EOF" | grep -v "^EOF$" | 9p write $AGENT_MOUNT/$TEST_AGENT_ID/context
-
-echo "Test agent created: $TEST_AGENT_ID"
-echo ""
-
-# Test query: Ask agent to find stale beads
-echo "Test 1: Query for stale beads (should use execute_code)"
-echo "Find all beads that haven't been updated in 30+ days and are still open. Show count by priority." | 9p write $AGENT_MOUNT/$TEST_AGENT_ID/prompt
-
-# Wait for response
-sleep 5
-
-# Read response
-echo ""
-echo "Agent response:"
-9p read $AGENT_MOUNT/$TEST_AGENT_ID/response
-echo ""
-
-# Check if execute_code was used
-echo "Checking tool usage..."
-TOOL_USAGE=$(9p read $AGENT_MOUNT/$TEST_AGENT_ID/stats 2>/dev/null || echo "")
-if echo "$TOOL_USAGE" | grep -q "execute_code"; then
-    echo "✓ Agent used execute_code"
-else
-    echo "✗ Agent did not use execute_code"
-fi
-
-echo ""
-echo "Test 2: Batch operation (should use execute_code for loop)"
-echo "Update all priority 1 beads to priority 2. Show progress." | 9p write $AGENT_MOUNT/$TEST_AGENT_ID/prompt
-
-sleep 5
-
-echo ""
-echo "Agent response:"
-9p read $AGENT_MOUNT/$TEST_AGENT_ID/response
-echo ""
-
-# Cleanup
-echo "Cleaning up test agent..."
-echo "stop $TEST_AGENT_ID" | 9p write $AGENT_MOUNT/ctl
-
-echo ""
-echo "=== Test Complete ==="
-echo ""
-echo "Manual verification steps:"
-echo "1. Check if agent used execute_code instead of multiple beads.list calls"
-echo "2. Verify filtering happened in sandbox (minimal context usage)"
-echo "3. Compare token usage to baseline (should be 80-99% reduction)"
diff --git a/test_beads.sh b/test_beads.sh
deleted file mode 100644
index 28befcd..0000000
--- a/test_beads.sh
+++ /dev/null
@@ -1,25 +0,0 @@
-#!/bin/bash
-set -e
-
-TESTDIR=$(mktemp -d)
-trap "rm -rf $TESTDIR" EXIT
-
-cd /home/lkn/src/anvillm/main
-
-# Build test binary
-go test -c ./internal/p9 -o /tmp/p9test
-
-# Test 1: Mount and create bead
-echo "=== Test 1: Mount project ==="
-mkdir -p "$TESTDIR/project1"
-
-# Test 2: Create bead in mount
-echo "=== Test 2: Create and label bead ==="
-
-# Test 3: Read from mount
-echo "=== Test 3: Read mount list ==="
-
-# Test 4: Unmount
-echo "=== Test 4: Unmount project ==="
-
-echo "✓ All tests passed"