refactor(core-ai): comprehensive cleanup - PydanticAI only architecture
Remove all obsolete agent implementations and framework references. Keep only PydanticAI (primary) and SimpleLiteLLM (fallback). This cleanup eliminates confusion between multiple frameworks that were tried during development (LangChain, LangGraph, ADK, OllamaNative) and establishes PydanticAI as the single agent framework going forward. BREAKING CHANGES: - Removed OllamaNativeAgent - use PydanticAgent instead - Removed /test/ollama-tools diagnostic endpoint - Default /v1/chat/completions now uses PydanticAgent Files Deleted (32 total): - Obsolete agents: ollama_native_agent.py - Diagnostic files: ARCHITECTURE.md, DIAGNOSTIC_RESULTS.md, PHASE*.md - Legacy tools: src/tools.py - Test files: test_ai_flow_quality.py, test_02/03 (diagnostic layers) - Documentation: ADK_Ollama_Research.md, agent-flow-diagrams.md - Session docs: 3 files with LangChain/LangGraph implementations - Plans: 5 completed plans about obsolete frameworks - Migration docs: MIGRATION_PLAN_LANGCHAIN_TO_ADK.md Files Modified (8 total): - main.py: Refactored to PydanticAI only (305 lines vs 457 before) - agents/__init__.py: Removed OllamaNativeAgent exports - README.md: Complete rewrite for PydanticAI architecture - prompts.py: Updated for PydanticAI (infrastructure tool guidance) - STATUS.md: Updated to v0.11.0-pydantic-ai - CHANGELOG.md: Added v0.11.0 entry documenting cleanup - plans/active/*.md: Updated to reference PydanticAI Current Architecture: - Framework: PydanticAI with native Ollama SDK - Agents: PydanticAgent (primary) + SimpleLiteLLMAgent (fallback) - Model: mistral-nemo:latest - Tools: 6 core + 28+ OpenAPI-discovered - Memory: 3-tier system with Qdrant - VRAM: ~4-6GB Lines Removed: ~3000+ lines of obsolete code 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Claude
@@ -1,144 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Diagnostic tool to test direct LiteLLM → Ollama communication.
|
||||
This bypasses all abstractions and tests the raw integration.
|
||||
|
||||
Usage:
|
||||
python diagnostics/test_litellm_direct.py
|
||||
"""
|
||||
import asyncio
|
||||
import sys
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
# Add parent directory to path to import from src
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent))
|
||||
|
||||
from src.config import get_settings
|
||||
|
||||
# Import LiteLLM
|
||||
try:
|
||||
import litellm
|
||||
litellm.set_verbose = True
|
||||
except ImportError:
|
||||
print("✗ LiteLLM not installed. Run: pip install litellm")
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
async def test_litellm_direct():
|
||||
"""Test direct LiteLLM completion with Ollama"""
|
||||
settings = get_settings()
|
||||
|
||||
print("=" * 70)
|
||||
print("LITELLM DIRECT TEST")
|
||||
print("=" * 70)
|
||||
|
||||
# Test configuration
|
||||
model_name = settings.agent_model
|
||||
litellm_model = f"ollama/{model_name}"
|
||||
api_base = settings.ollama_base_url
|
||||
|
||||
print(f"\n1. Configuration")
|
||||
print(f" LiteLLM Model: {litellm_model}")
|
||||
print(f" API Base: {api_base}")
|
||||
print(f" Temperature: 0.1")
|
||||
|
||||
# Test messages
|
||||
test_cases = [
|
||||
{
|
||||
"name": "Simple question (no system prompt)",
|
||||
"messages": [
|
||||
{"role": "user", "content": "What is the capital of France? Answer in one word."}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "Simple question (with system prompt)",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are a helpful assistant. Answer questions concisely."},
|
||||
{"role": "user", "content": "What is the capital of France? Answer in one word."}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "Math problem",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "What is 2 + 2? Answer with just the number."}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
# Run tests
|
||||
for i, test_case in enumerate(test_cases, 1):
|
||||
print(f"\n{'-' * 70}")
|
||||
print(f"Test {i}/{len(test_cases)}: {test_case['name']}")
|
||||
print(f"{'-' * 70}")
|
||||
|
||||
# Log messages being sent
|
||||
print("\nMessages being sent:")
|
||||
for j, msg in enumerate(test_case['messages']):
|
||||
content_preview = msg['content'][:60] + "..." if len(msg['content']) > 60 else msg['content']
|
||||
print(f" [{j}] {msg['role']}: {content_preview}")
|
||||
|
||||
try:
|
||||
# Test non-streaming first
|
||||
print("\n→ Testing non-streaming mode...")
|
||||
response = await litellm.acompletion(
|
||||
model=litellm_model,
|
||||
messages=test_case['messages'],
|
||||
api_base=api_base,
|
||||
temperature=0.1,
|
||||
stream=False
|
||||
)
|
||||
|
||||
content = response.choices[0].message.content
|
||||
finish_reason = response.choices[0].finish_reason
|
||||
|
||||
print(f"\n✓ Non-streaming response received:")
|
||||
print(f" Content: {content}")
|
||||
print(f" Finish reason: {finish_reason}")
|
||||
print(f" Model: {response.model}")
|
||||
|
||||
# Test streaming
|
||||
print("\n→ Testing streaming mode...")
|
||||
stream_response = await litellm.acompletion(
|
||||
model=litellm_model,
|
||||
messages=test_case['messages'],
|
||||
api_base=api_base,
|
||||
temperature=0.1,
|
||||
stream=True
|
||||
)
|
||||
|
||||
chunks = []
|
||||
chunk_count = 0
|
||||
async for chunk in stream_response:
|
||||
chunk_count += 1
|
||||
if chunk.choices[0].delta.content:
|
||||
chunks.append(chunk.choices[0].delta.content)
|
||||
|
||||
full_content = "".join(chunks)
|
||||
print(f"\n✓ Streaming response received:")
|
||||
print(f" Content: {full_content}")
|
||||
print(f" Chunks: {chunk_count}")
|
||||
|
||||
print(f"\n✓ Test {i} PASSED")
|
||||
|
||||
except Exception as e:
|
||||
print(f"\n✗ Test {i} FAILED")
|
||||
print(f" Error: {type(e).__name__}: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return False
|
||||
|
||||
print("\n" + "=" * 70)
|
||||
print("✓ ALL LITELLM TESTS PASSED!")
|
||||
print("=" * 70)
|
||||
print("\nNext steps:")
|
||||
print(" 1. If this works, the LiteLLM → Ollama connection is solid")
|
||||
print(" 2. Any issues are likely in the agent wrapper or API layer")
|
||||
print(" 3. Run the full test suite: bash diagnostics/run_all_tests.sh")
|
||||
return True
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
result = asyncio.run(test_litellm_direct())
|
||||
sys.exit(0 if result else 1)
|
||||
Reference in New Issue
Block a user