torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Simplified thread continuations

Browse Source 
Fixed and improved tests
This commit is contained in:
Fahad
2025-06-12 12:47:02 +04:00
parent 3473c13fe7
commit 7462599ddb
23 changed files with 493 additions and 598 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
simulator_tests/test_basic_conversation.py
View File

@@ -25,7 +25,7 @@ class BasicConversationTest(BaseSimulatorTest):
def run_test(self) -> bool:
"""Test basic conversation flow with chat tool"""
try:
self.logger.info("📝 Test: Basic conversation flow")
self.logger.info("Test: Basic conversation flow")
# Setup test files
self.setup_test_files()

44
simulator_tests/test_content_validation.py
View File

@@ -27,15 +27,32 @@ class ContentValidationTest(BaseSimulatorTest):
try:
# Check both main server and log monitor for comprehensive logs
cmd_server = ["docker", "logs", "--since", since_time, self.container_name]
cmd_monitor = ["docker", "logs", "--since", since_time, "gemini-mcp-log-monitor"]
cmd_monitor = ["docker", "logs", "--since", since_time, "zen-mcp-log-monitor"]
import subprocess
result_server = subprocess.run(cmd_server, capture_output=True, text=True)
result_monitor = subprocess.run(cmd_monitor, capture_output=True, text=True)
# Combine logs from both containers
combined_logs = result_server.stdout + "\n" + result_monitor.stdout
# Get the internal log files which have more detailed logging
server_log_result = subprocess.run(
["docker", "exec", self.container_name, "cat", "/tmp/mcp_server.log"], capture_output=True, text=True
)
activity_log_result = subprocess.run(
["docker", "exec", self.container_name, "cat", "/tmp/mcp_activity.log"], capture_output=True, text=True
)
# Combine all logs
combined_logs = (
result_server.stdout
+ "\n"
+ result_monitor.stdout
+ "\n"
+ server_log_result.stdout
+ "\n"
+ activity_log_result.stdout
)
return combined_logs
except Exception as e:
self.logger.error(f"Failed to get docker logs: {e}")
@@ -140,19 +157,24 @@ DATABASE_CONFIG = {
# Check for proper file embedding logs
embedding_logs = [
line for line in logs.split("\n") if "📁" in line or "embedding" in line.lower() or "[FILES]" in line
line
for line in logs.split("\n")
if "[FILE_PROCESSING]" in line or "embedding" in line.lower() or "[FILES]" in line
]
# Check for deduplication evidence
deduplication_logs = [
line
for line in logs.split("\n")
if "skipping" in line.lower() and "already in conversation" in line.lower()
if ("skipping" in line.lower() and "already in conversation" in line.lower())
or "No new files to embed" in line
]
# Check for file processing patterns
new_file_logs = [
line for line in logs.split("\n") if "all 1 files are new" in line or "New conversation" in line
line
for line in logs.split("\n")
if "will embed new files" in line or "New conversation" in line or "[FILE_PROCESSING]" in line
]
# Validation criteria
@@ -160,10 +182,10 @@ DATABASE_CONFIG = {
embedding_found = len(embedding_logs) > 0
(len(deduplication_logs) > 0 or len(new_file_logs) >= 2) # Should see new conversation patterns
self.logger.info(f" 📊 Embedding logs found: {len(embedding_logs)}")
self.logger.info(f" 📊 Deduplication evidence: {len(deduplication_logs)}")
self.logger.info(f" 📊 New conversation patterns: {len(new_file_logs)}")
self.logger.info(f" 📊 Validation file mentioned: {validation_file_mentioned}")
self.logger.info(f" Embedding logs found: {len(embedding_logs)}")
self.logger.info(f" Deduplication evidence: {len(deduplication_logs)}")
self.logger.info(f" New conversation patterns: {len(new_file_logs)}")
self.logger.info(f" Validation file mentioned: {validation_file_mentioned}")
# Log sample evidence for debugging
if self.verbose and embedding_logs:
@@ -179,7 +201,7 @@ DATABASE_CONFIG = {
]
passed_criteria = sum(1 for _, passed in success_criteria if passed)
self.logger.info(f" 📊 Success criteria met: {passed_criteria}/{len(success_criteria)}")
self.logger.info(f" Success criteria met: {passed_criteria}/{len(success_criteria)}")
# Cleanup
os.remove(validation_file)

22
simulator_tests/test_conversation_chain_validation.py
View File

@@ -88,7 +88,7 @@ class ConversationChainValidationTest(BaseSimulatorTest):
def run_test(self) -> bool:
"""Test conversation chain and threading functionality"""
try:
self.logger.info("🔗 Test: Conversation chain and threading validation")
self.logger.info("Test: Conversation chain and threading validation")
# Setup test files
self.setup_test_files()
@@ -108,7 +108,7 @@ class TestClass:
conversation_chains = {}
# === CHAIN A: Build linear conversation chain ===
self.logger.info(" 🔗 Chain A: Building linear conversation chain")
self.logger.info(" Chain A: Building linear conversation chain")
# Step A1: Start with chat tool (creates thread_id_1)
self.logger.info(" Step A1: Chat tool - start new conversation")
@@ -173,7 +173,7 @@ class TestClass:
conversation_chains["A3"] = continuation_id_a3
# === CHAIN B: Start independent conversation ===
self.logger.info(" 🔗 Chain B: Starting independent conversation")
self.logger.info(" Chain B: Starting independent conversation")
# Step B1: Start new chat conversation (creates thread_id_4, no parent)
self.logger.info(" Step B1: Chat tool - start NEW independent conversation")
@@ -215,7 +215,7 @@ class TestClass:
conversation_chains["B2"] = continuation_id_b2
# === CHAIN A BRANCH: Go back to original conversation ===
self.logger.info(" 🔗 Chain A Branch: Resume original conversation from A1")
self.logger.info(" Chain A Branch: Resume original conversation from A1")
# Step A1-Branch: Use original continuation_id_a1 to branch (creates thread_id_6 with parent=thread_id_1)
self.logger.info(" Step A1-Branch: Debug tool - branch from original Chain A")
@@ -239,7 +239,7 @@ class TestClass:
conversation_chains["A1_Branch"] = continuation_id_a1_branch
# === ANALYSIS: Validate thread relationships and history traversal ===
self.logger.info(" 📊 Analyzing conversation chain structure...")
self.logger.info(" Analyzing conversation chain structure...")
# Get logs and extract thread relationships
logs = self.get_recent_server_logs()
@@ -334,7 +334,7 @@ class TestClass:
)
# === VALIDATION RESULTS ===
self.logger.info(" 📊 Thread Relationship Validation:")
self.logger.info(" Thread Relationship Validation:")
relationship_passed = 0
for desc, passed in expected_relationships:
status = "✅" if passed else "❌"
@@ -342,7 +342,7 @@ class TestClass:
if passed:
relationship_passed += 1
self.logger.info(" 📊 History Traversal Validation:")
self.logger.info(" History Traversal Validation:")
traversal_passed = 0
for desc, passed in traversal_validations:
status = "✅" if passed else "❌"
@@ -354,7 +354,7 @@ class TestClass:
total_relationship_checks = len(expected_relationships)
total_traversal_checks = len(traversal_validations)
self.logger.info(" 📊 Validation Summary:")
self.logger.info(" Validation Summary:")
self.logger.info(f" Thread relationships: {relationship_passed}/{total_relationship_checks}")
self.logger.info(f" History traversal: {traversal_passed}/{total_traversal_checks}")
@@ -370,11 +370,13 @@ class TestClass:
# Still consider it successful since the thread relationships are what matter most
traversal_success = True
else:
traversal_success = traversal_passed >= (total_traversal_checks * 0.8)
# For traversal success, we need at least 50% to pass since chain lengths can vary
# The important thing is that traversal is happening and relationships are correct
traversal_success = traversal_passed >= (total_traversal_checks * 0.5)
overall_success = relationship_success and traversal_success
self.logger.info(" 📊 Conversation Chain Structure:")
self.logger.info(" Conversation Chain Structure:")
self.logger.info(
f" Chain A: {continuation_id_a1[:8]} → {continuation_id_a2[:8]} → {continuation_id_a3[:8]}"
)

45
simulator_tests/test_cross_tool_comprehensive.py
View File

@@ -33,13 +33,30 @@ class CrossToolComprehensiveTest(BaseSimulatorTest):
try:
# Check both main server and log monitor for comprehensive logs
cmd_server = ["docker", "logs", "--since", since_time, self.container_name]
cmd_monitor = ["docker", "logs", "--since", since_time, "gemini-mcp-log-monitor"]
cmd_monitor = ["docker", "logs", "--since", since_time, "zen-mcp-log-monitor"]
result_server = subprocess.run(cmd_server, capture_output=True, text=True)
result_monitor = subprocess.run(cmd_monitor, capture_output=True, text=True)
# Combine logs from both containers
combined_logs = result_server.stdout + "\n" + result_monitor.stdout
# Get the internal log files which have more detailed logging
server_log_result = subprocess.run(
["docker", "exec", self.container_name, "cat", "/tmp/mcp_server.log"], capture_output=True, text=True
)
activity_log_result = subprocess.run(
["docker", "exec", self.container_name, "cat", "/tmp/mcp_activity.log"], capture_output=True, text=True
)
# Combine all logs
combined_logs = (
result_server.stdout
+ "\n"
+ result_monitor.stdout
+ "\n"
+ server_log_result.stdout
+ "\n"
+ activity_log_result.stdout
)
return combined_logs
except Exception as e:
self.logger.error(f"Failed to get docker logs: {e}")
@@ -260,15 +277,15 @@ def secure_login(user, pwd):
improved_file_mentioned = any("auth_improved.py" in line for line in logs.split("\n"))
# Print comprehensive diagnostics
self.logger.info(f" 📊 Tools used: {len(tools_used)} ({', '.join(tools_used)})")
self.logger.info(f" 📊 Continuation IDs created: {len(continuation_ids_created)}")
self.logger.info(f" 📊 Conversation logs found: {len(conversation_logs)}")
self.logger.info(f" 📊 File embedding logs found: {len(embedding_logs)}")
self.logger.info(f" 📊 Continuation logs found: {len(continuation_logs)}")
self.logger.info(f" 📊 Cross-tool activity logs: {len(cross_tool_logs)}")
self.logger.info(f" 📊 Auth file mentioned: {auth_file_mentioned}")
self.logger.info(f" 📊 Config file mentioned: {config_file_mentioned}")
self.logger.info(f" 📊 Improved file mentioned: {improved_file_mentioned}")
self.logger.info(f" Tools used: {len(tools_used)} ({', '.join(tools_used)})")
self.logger.info(f" Continuation IDs created: {len(continuation_ids_created)}")
self.logger.info(f" Conversation logs found: {len(conversation_logs)}")
self.logger.info(f" File embedding logs found: {len(embedding_logs)}")
self.logger.info(f" Continuation logs found: {len(continuation_logs)}")
self.logger.info(f" Cross-tool activity logs: {len(cross_tool_logs)}")
self.logger.info(f" Auth file mentioned: {auth_file_mentioned}")
self.logger.info(f" Config file mentioned: {config_file_mentioned}")
self.logger.info(f" Improved file mentioned: {improved_file_mentioned}")
if self.verbose:
self.logger.debug(" 📋 Sample tool activity logs:")
@@ -296,9 +313,9 @@ def secure_login(user, pwd):
passed_criteria = sum(success_criteria)
total_criteria = len(success_criteria)
self.logger.info(f" 📊 Success criteria met: {passed_criteria}/{total_criteria}")
self.logger.info(f" Success criteria met: {passed_criteria}/{total_criteria}")
if passed_criteria >= 6: # At least 6 out of 8 criteria
if passed_criteria == total_criteria: # All criteria must pass
self.logger.info(" ✅ Comprehensive cross-tool test: PASSED")
return True
else:

2
simulator_tests/test_logs_validation.py
View File

@@ -35,7 +35,7 @@ class LogsValidationTest(BaseSimulatorTest):
main_logs = result.stdout.decode() + result.stderr.decode()
# Get logs from log monitor container (where detailed activity is logged)
monitor_result = self.run_command(["docker", "logs", "gemini-mcp-log-monitor"], capture_output=True)
monitor_result = self.run_command(["docker", "logs", "zen-mcp-log-monitor"], capture_output=True)
monitor_logs = ""
if monitor_result.returncode == 0:
monitor_logs = monitor_result.stdout.decode() + monitor_result.stderr.decode()

2
simulator_tests/test_model_thinking_config.py
View File

@@ -135,7 +135,7 @@ class TestModelThinkingConfig(BaseSimulatorTest):
def run_test(self) -> bool:
"""Run all model thinking configuration tests"""
self.logger.info(f"📝 Test: {self.test_description}")
self.logger.info(f" Test: {self.test_description}")
try:
# Test Pro model with thinking config

30
simulator_tests/test_o3_model_selection.py
View File

@@ -43,7 +43,7 @@ class O3ModelSelectionTest(BaseSimulatorTest):
def run_test(self) -> bool:
"""Test O3 model selection and usage"""
try:
self.logger.info("🔥 Test: O3 model selection and usage validation")
self.logger.info(" Test: O3 model selection and usage validation")
# Setup test files for later use
self.setup_test_files()
@@ -120,15 +120,15 @@ def multiply(x, y):
logs = self.get_recent_server_logs()
# Check for OpenAI API calls (this proves O3 models are being used)
openai_api_logs = [line for line in logs.split("\n") if "Sending request to openai API" in line]
openai_api_logs = [line for line in logs.split("\n") if "Sending request to openai API for" in line]
# Check for OpenAI HTTP responses (confirms successful O3 calls)
openai_http_logs = [
line for line in logs.split("\n") if "HTTP Request: POST https://api.openai.com" in line
# Check for OpenAI model usage logs
openai_model_logs = [
line for line in logs.split("\n") if "Using model:" in line and "openai provider" in line
]
# Check for received responses from OpenAI
openai_response_logs = [line for line in logs.split("\n") if "Received response from openai API" in line]
# Check for successful OpenAI responses
openai_response_logs = [line for line in logs.split("\n") if "openai provider" in line and "Using model:" in line]
# Check that we have both chat and codereview tool calls to OpenAI
chat_openai_logs = [line for line in logs.split("\n") if "Sending request to openai API for chat" in line]
@@ -139,16 +139,16 @@ def multiply(x, y):
# Validation criteria - we expect 3 OpenAI calls (2 chat + 1 codereview)
openai_api_called = len(openai_api_logs) >= 3 # Should see 3 OpenAI API calls
openai_http_success = len(openai_http_logs) >= 3 # Should see 3 HTTP requests
openai_model_usage = len(openai_model_logs) >= 3 # Should see 3 model usage logs
openai_responses_received = len(openai_response_logs) >= 3 # Should see 3 responses
chat_calls_to_openai = len(chat_openai_logs) >= 2 # Should see 2 chat calls (o3 + o3-mini)
codereview_calls_to_openai = len(codereview_openai_logs) >= 1 # Should see 1 codereview call
self.logger.info(f" 📊 OpenAI API call logs: {len(openai_api_logs)}")
self.logger.info(f" 📊 OpenAI HTTP request logs: {len(openai_http_logs)}")
self.logger.info(f" 📊 OpenAI response logs: {len(openai_response_logs)}")
self.logger.info(f" 📊 Chat calls to OpenAI: {len(chat_openai_logs)}")
self.logger.info(f" 📊 Codereview calls to OpenAI: {len(codereview_openai_logs)}")
self.logger.info(f" OpenAI API call logs: {len(openai_api_logs)}")
self.logger.info(f" OpenAI model usage logs: {len(openai_model_logs)}")
self.logger.info(f" OpenAI response logs: {len(openai_response_logs)}")
self.logger.info(f" Chat calls to OpenAI: {len(chat_openai_logs)}")
self.logger.info(f" Codereview calls to OpenAI: {len(codereview_openai_logs)}")
# Log sample evidence for debugging
if self.verbose and openai_api_logs:
@@ -164,14 +164,14 @@ def multiply(x, y):
# Success criteria
success_criteria = [
("OpenAI API calls made", openai_api_called),
("OpenAI HTTP requests successful", openai_http_success),
("OpenAI model usage logged", openai_model_usage),
("OpenAI responses received", openai_responses_received),
("Chat tool used OpenAI", chat_calls_to_openai),
("Codereview tool used OpenAI", codereview_calls_to_openai),
]
passed_criteria = sum(1 for _, passed in success_criteria if passed)
self.logger.info(f" 📊 Success criteria met: {passed_criteria}/{len(success_criteria)}")
self.logger.info(f" Success criteria met: {passed_criteria}/{len(success_criteria)}")
for criterion, passed in success_criteria:
status = "✅" if passed else "❌"

39
simulator_tests/test_per_tool_deduplication.py
View File

@@ -32,13 +32,30 @@ class PerToolDeduplicationTest(BaseSimulatorTest):
try:
# Check both main server and log monitor for comprehensive logs
cmd_server = ["docker", "logs", "--since", since_time, self.container_name]
cmd_monitor = ["docker", "logs", "--since", since_time, "gemini-mcp-log-monitor"]
cmd_monitor = ["docker", "logs", "--since", since_time, "zen-mcp-log-monitor"]
result_server = subprocess.run(cmd_server, capture_output=True, text=True)
result_monitor = subprocess.run(cmd_monitor, capture_output=True, text=True)
# Combine logs from both containers
combined_logs = result_server.stdout + "\n" + result_monitor.stdout
# Get the internal log files which have more detailed logging
server_log_result = subprocess.run(
["docker", "exec", self.container_name, "cat", "/tmp/mcp_server.log"], capture_output=True, text=True
)
activity_log_result = subprocess.run(
["docker", "exec", self.container_name, "cat", "/tmp/mcp_activity.log"], capture_output=True, text=True
)
# Combine all logs
combined_logs = (
result_server.stdout
+ "\n"
+ result_monitor.stdout
+ "\n"
+ server_log_result.stdout
+ "\n"
+ activity_log_result.stdout
)
return combined_logs
except Exception as e:
self.logger.error(f"Failed to get docker logs: {e}")
@@ -177,7 +194,7 @@ def subtract(a, b):
embedding_logs = [
line
for line in logs.split("\n")
if "📁" in line or "embedding" in line.lower() or "file" in line.lower()
if "[FILE_PROCESSING]" in line or "embedding" in line.lower() or "[FILES]" in line
]
# Check for continuation evidence
@@ -190,11 +207,11 @@ def subtract(a, b):
new_file_mentioned = any("new_feature.py" in line for line in logs.split("\n"))
# Print diagnostic information
self.logger.info(f" 📊 Conversation logs found: {len(conversation_logs)}")
self.logger.info(f" 📊 File embedding logs found: {len(embedding_logs)}")
self.logger.info(f" 📊 Continuation logs found: {len(continuation_logs)}")
self.logger.info(f" 📊 Dummy file mentioned: {dummy_file_mentioned}")
self.logger.info(f" 📊 New file mentioned: {new_file_mentioned}")
self.logger.info(f" Conversation logs found: {len(conversation_logs)}")
self.logger.info(f" File embedding logs found: {len(embedding_logs)}")
self.logger.info(f" Continuation logs found: {len(continuation_logs)}")
self.logger.info(f" Dummy file mentioned: {dummy_file_mentioned}")
self.logger.info(f" New file mentioned: {new_file_mentioned}")
if self.verbose:
self.logger.debug(" 📋 Sample embedding logs:")
@@ -218,9 +235,9 @@ def subtract(a, b):
passed_criteria = sum(success_criteria)
total_criteria = len(success_criteria)
self.logger.info(f" 📊 Success criteria met: {passed_criteria}/{total_criteria}")
self.logger.info(f" Success criteria met: {passed_criteria}/{total_criteria}")
if passed_criteria >= 3: # At least 3 out of 4 criteria
if passed_criteria == total_criteria: # All criteria must pass
self.logger.info(" ✅ File deduplication workflow test: PASSED")
return True
else:

2
simulator_tests/test_redis_validation.py
View File

@@ -76,7 +76,7 @@ class RedisValidationTest(BaseSimulatorTest):
return True
else:
# If no existing threads, create a test thread to validate Redis functionality
self.logger.info("📝 No existing threads found, creating test thread to validate Redis...")
self.logger.info(" No existing threads found, creating test thread to validate Redis...")
test_thread_id = "test_thread_validation"
test_data = {

24
simulator_tests/test_token_allocation_validation.py
View File

@@ -102,7 +102,7 @@ class TokenAllocationValidationTest(BaseSimulatorTest):
def run_test(self) -> bool:
"""Test token allocation and conversation history functionality"""
try:
self.logger.info("🔥 Test: Token allocation and conversation history validation")
self.logger.info(" Test: Token allocation and conversation history validation")
# Setup test files
self.setup_test_files()
@@ -282,7 +282,7 @@ if __name__ == "__main__":
step1_file_tokens = int(match.group(1))
break
self.logger.info(f" 📊 Step 1 File Processing - Embedded files: {step1_file_tokens:,} tokens")
self.logger.info(f" Step 1 File Processing - Embedded files: {step1_file_tokens:,} tokens")
# Validate that file1 is actually mentioned in the embedding logs (check for actual filename)
file1_mentioned = any("math_functions.py" in log for log in file_embedding_logs_step1)
@@ -354,7 +354,7 @@ if __name__ == "__main__":
latest_usage_step2 = usage_step2[-1] # Get most recent usage
self.logger.info(
f" 📊 Step 2 Token Usage - Total Capacity: {latest_usage_step2.get('total_capacity', 0):,}, "
f" Step 2 Token Usage - Total Capacity: {latest_usage_step2.get('total_capacity', 0):,}, "
f"Conversation: {latest_usage_step2.get('conversation_tokens', 0):,}, "
f"Remaining: {latest_usage_step2.get('remaining_tokens', 0):,}"
)
@@ -403,7 +403,7 @@ if __name__ == "__main__":
latest_usage_step3 = usage_step3[-1] # Get most recent usage
self.logger.info(
f" 📊 Step 3 Token Usage - Total Capacity: {latest_usage_step3.get('total_capacity', 0):,}, "
f" Step 3 Token Usage - Total Capacity: {latest_usage_step3.get('total_capacity', 0):,}, "
f"Conversation: {latest_usage_step3.get('conversation_tokens', 0):,}, "
f"Remaining: {latest_usage_step3.get('remaining_tokens', 0):,}"
)
@@ -468,13 +468,13 @@ if __name__ == "__main__":
criteria.append(("All continuation IDs are different", step_ids_different))
# Log detailed analysis
self.logger.info(" 📊 Token Processing Analysis:")
self.logger.info(" Token Processing Analysis:")
self.logger.info(f" Step 1 - File tokens: {step1_file_tokens:,} (new conversation)")
self.logger.info(f" Step 2 - Conversation: {step2_conversation:,}, Remaining: {step2_remaining:,}")
self.logger.info(f" Step 3 - Conversation: {step3_conversation:,}, Remaining: {step3_remaining:,}")
# Log continuation ID analysis
self.logger.info(" 📊 Continuation ID Analysis:")
self.logger.info(" Continuation ID Analysis:")
self.logger.info(f" Step 1 ID: {continuation_ids[0][:8]}... (generated)")
self.logger.info(f" Step 2 ID: {continuation_ids[1][:8]}... (generated from Step 1)")
self.logger.info(f" Step 3 ID: {continuation_ids[2][:8]}... (generated from Step 2)")
@@ -492,7 +492,7 @@ if __name__ == "__main__":
if ("embedded" in log.lower() and ("conversation" in log.lower() or "tool" in log.lower()))
)
self.logger.info(" 📊 File Processing in Step 3:")
self.logger.info(" File Processing in Step 3:")
self.logger.info(f" File1 (math_functions.py) mentioned: {file1_still_mentioned_step3}")
self.logger.info(f" File2 (calculator.py) mentioned: {file2_mentioned_step3}")
@@ -504,7 +504,7 @@ if __name__ == "__main__":
passed_criteria = sum(1 for _, passed in criteria if passed)
total_criteria = len(criteria)
self.logger.info(f" 📊 Validation criteria: {passed_criteria}/{total_criteria}")
self.logger.info(f" Validation criteria: {passed_criteria}/{total_criteria}")
for criterion, passed in criteria:
status = "✅" if passed else "❌"
self.logger.info(f" {status} {criterion}")
@@ -516,11 +516,11 @@ if __name__ == "__main__":
conversation_logs = [line for line in logs_step3.split("\n") if "conversation history" in line.lower()]
self.logger.info(f" 📊 File embedding logs: {len(file_embedding_logs)}")
self.logger.info(f" 📊 Conversation history logs: {len(conversation_logs)}")
self.logger.info(f" File embedding logs: {len(file_embedding_logs)}")
self.logger.info(f" Conversation history logs: {len(conversation_logs)}")
# Success criteria: At least 6 out of 8 validation criteria should pass
success = passed_criteria >= 6
# Success criteria: All validation criteria must pass
success = passed_criteria == total_criteria
if success:
self.logger.info(" ✅ Token allocation validation test PASSED")