feat: integrate Tatlock agent with PydanticAI and Ollama

Convert Tatlock from mock to real PydanticAI agent:
- Connect to Ollama backend (mistral-nemo:latest)
- British butler personality with research-oriented mindset
- Lazy initialization pattern for better testability
- Register permanent tools (calculator, date/time, search)
- Streaming response support with reasoning output
- Error handling for PydanticAI exceptions
- Update registry tests for tools capability
- Add integration test for streaming functionality
This commit is contained in:
2025-12-07 00:12:39 +01:00
parent f3e2681a6c
commit 67481515cc
3 changed files with 711 additions and 43 deletions
+9 -9
View File
@@ -22,7 +22,7 @@ async def test_list_models():
# Check model IDs
model_ids = [m["id"] for m in models]
assert "lorem-tester" in model_ids
assert "tatlock" in model_ids
assert "Tatlock" in model_ids
# Check structure
for model in models:
@@ -57,16 +57,16 @@ async def test_lorem_tester_capabilities():
async def test_tatlock_capabilities():
"""Test tatlock model capabilities."""
models = await ModelRegistry.list_models()
tatlock_model = next(m for m in models if m["id"] == "tatlock")
tatlock_model = next(m for m in models if m["id"] == "Tatlock")
capabilities = tatlock_model["capabilities"]
# Tatlock is placeholder - minimal capabilities
# Tatlock Phase 1 - basic streaming, reasoning, and permanent tools
assert capabilities["streaming"] is True
assert capabilities["reasoning"] is False # Not yet
assert capabilities["tools"] is False # Not yet
assert capabilities["vision"] is False
assert capabilities["audio"] is False
assert capabilities["reasoning"] is True # Basic reasoning summaries
assert capabilities["tools"] is True # Permanent tools: calculator, date/time, search
assert capabilities["vision"] is False # Future
assert capabilities["audio"] is False # Future
@pytest.mark.unit
@@ -80,7 +80,7 @@ def test_get_agent_lorem_tester():
@pytest.mark.unit
def test_get_agent_tatlock():
"""Test getting tatlock agent instance."""
agent = ModelRegistry.get_agent("tatlock")
agent = ModelRegistry.get_agent("Tatlock")
assert isinstance(agent, TatlockAgent)
@@ -98,7 +98,7 @@ def test_get_agent_not_found():
def test_model_exists():
"""Test checking if model exists."""
assert ModelRegistry.model_exists("lorem-tester") is True
assert ModelRegistry.model_exists("tatlock") is True
assert ModelRegistry.model_exists("Tatlock") is True
assert ModelRegistry.model_exists("nonexistent") is False
+410
View File
@@ -0,0 +1,410 @@
"""
Integration tests for Tatlock agent streaming through full API stack.
These tests verify the complete streaming flow from API endpoint through
StreamingCoordinator to TatlockAgent, ensuring no text duplication and
proper delta calculation.
"""
import json
import pytest
from httpx import AsyncClient
from fastapi.testclient import TestClient
@pytest.mark.integration
@pytest.mark.asyncio
async def test_tatlock_streaming_no_duplication(async_client: AsyncClient):
"""
Integration test: Verify Tatlock streaming produces no text duplication.
This test catches the bug where accumulated text from PydanticAI was
being re-streamed multiple times by the StreamingCoordinator.
"""
request_data = {
"model": "Tatlock",
"input": [{"role": "user", "content": "Say hello"}],
"stream": True
}
collected_deltas = []
async with async_client.stream(
"POST",
"/v1/responses",
json=request_data,
timeout=30.0, # Give enough time for Ollama response
) as response:
assert response.status_code == 200
assert response.headers["content-type"] == "text/event-stream; charset=utf-8"
async for line in response.aiter_lines():
if not line.strip():
continue
if line.startswith("event: "):
event_type = line[7:].strip()
elif line.startswith("data: "):
data_str = line[6:].strip()
if data_str != "[DONE]":
try:
chunk = json.loads(data_str)
# Collect output text deltas
if chunk.get("event") == "response.output_text.delta":
collected_deltas.append(chunk["delta"])
except json.JSONDecodeError:
pass
# Reconstruct full text from deltas
full_text = "".join(collected_deltas)
# Verify we got some response
assert len(full_text) > 0, "Should have received some text"
# Verify no obvious duplication patterns
# Check that common words don't appear excessively repeated
words = full_text.lower().split()
if len(words) > 0:
# Check for consecutive duplicate words (sign of duplication bug)
consecutive_dupes = sum(
1 for i in range(len(words) - 1)
if words[i] == words[i + 1] and len(words[i]) > 3
)
# Allow a few duplicates (natural language), but not excessive
assert consecutive_dupes < len(words) * 0.1, \
f"Too many consecutive duplicate words: {consecutive_dupes}/{len(words)}"
@pytest.mark.integration
@pytest.mark.asyncio
async def test_tatlock_chat_streaming_no_duplication(async_client: AsyncClient):
"""
Integration test: Verify Tatlock streaming through Chat Completions API.
Tests the full stack through the chat completions wrapper to ensure
streaming works correctly without duplication.
"""
request_data = {
"model": "Tatlock",
"messages": [{"role": "user", "content": "Hello"}],
"stream": True
}
collected_content = []
async with async_client.stream(
"POST",
"/v1/chat/completions",
json=request_data,
timeout=30.0,
) as response:
assert response.status_code == 200
async for line in response.aiter_lines():
if not line.strip():
continue
if line.startswith("data: "):
data_str = line[6:].strip()
if data_str == "[DONE]":
break
try:
chunk = json.loads(data_str)
# Collect content deltas from choices
if "choices" in chunk and len(chunk["choices"]) > 0:
delta = chunk["choices"][0].get("delta", {})
if "content" in delta and delta["content"]:
collected_content.append(delta["content"])
except json.JSONDecodeError:
pass
# Reconstruct full response
full_response = "".join(collected_content)
# Verify we got a response
assert len(full_response) > 0, "Should have received response content"
# Check for duplication patterns
words = full_response.lower().split()
if len(words) > 0:
consecutive_dupes = sum(
1 for i in range(len(words) - 1)
if words[i] == words[i + 1] and len(words[i]) > 3
)
assert consecutive_dupes < len(words) * 0.1, \
f"Too many consecutive duplicate words in chat response: {consecutive_dupes}/{len(words)}"
@pytest.mark.integration
def test_tatlock_non_streaming_responses_api(client: TestClient):
"""
Integration test: Verify Tatlock non-streaming through Responses API.
"""
request_data = {
"model": "Tatlock",
"input": [{"role": "user", "content": "Say hello"}],
"stream": False
}
response = client.post("/v1/responses", json=request_data, timeout=30.0)
assert response.status_code == 200
data = response.json()
# Verify response structure
assert data["status"] == "completed"
assert "output" in data
assert len(data["output"]) > 0
# Get the message content
message_item = next((item for item in data["output"] if item["type"] == "message"), None)
assert message_item is not None, "Should have a message output item"
assert len(message_item["content"]) > 0
text = message_item["content"][0]["text"]
assert len(text) > 0, "Should have response text"
@pytest.mark.integration
def test_tatlock_non_streaming_chat_api(client: TestClient):
"""
Integration test: Verify Tatlock non-streaming through Chat Completions API.
"""
request_data = {
"model": "Tatlock",
"messages": [{"role": "user", "content": "Hello"}],
"stream": False
}
response = client.post("/v1/chat/completions", json=request_data, timeout=30.0)
assert response.status_code == 200
data = response.json()
# Verify OpenAI-compatible structure
assert "id" in data
assert data["object"] == "chat.completion"
assert "choices" in data
assert len(data["choices"]) > 0
# Verify content
choice = data["choices"][0]
assert choice["message"]["role"] == "assistant"
assert len(choice["message"]["content"]) > 0
@pytest.mark.integration
@pytest.mark.asyncio
async def test_tatlock_streaming_delta_accumulation(async_client: AsyncClient):
"""
Integration test: Verify deltas accumulate correctly without duplication.
This test explicitly checks that when we accumulate all deltas,
we get a coherent response without repeated text.
"""
request_data = {
"model": "Tatlock",
"input": [{"role": "user", "content": "Count to three"}],
"stream": True
}
collected_deltas = []
previous_full_text = ""
async with async_client.stream(
"POST",
"/v1/responses",
json=request_data,
timeout=30.0,
) as response:
assert response.status_code == 200
async for line in response.aiter_lines():
if not line.strip():
continue
if line.startswith("data: "):
data_str = line[6:].strip()
if data_str != "[DONE]":
try:
chunk = json.loads(data_str)
if chunk.get("event") == "response.output_text.delta":
delta = chunk["delta"]
collected_deltas.append(delta)
# Verify each delta is new content
current_full = "".join(collected_deltas)
assert current_full.startswith(previous_full_text), \
"Deltas should accumulate progressively"
previous_full_text = current_full
except json.JSONDecodeError:
pass
full_text = "".join(collected_deltas)
assert len(full_text) > 0
@pytest.mark.integration
@pytest.mark.asyncio
async def test_tatlock_with_reasoning(async_client: AsyncClient):
"""
Integration test: Verify Tatlock with reasoning enabled.
"""
request_data = {
"model": "Tatlock",
"input": [{"role": "user", "content": "Hello"}],
"reasoning": {"effort": "medium", "summary": "auto"},
"stream": True
}
has_reasoning = False
has_output = False
async with async_client.stream(
"POST",
"/v1/responses",
json=request_data,
timeout=30.0,
) as response:
assert response.status_code == 200
async for line in response.aiter_lines():
if not line.strip():
continue
if line.startswith("data: "):
data_str = line[6:].strip()
if data_str != "[DONE]":
try:
chunk = json.loads(data_str)
if chunk.get("event") == "response.reasoning_summary_text.delta":
has_reasoning = True
elif chunk.get("event") == "response.output_text.delta":
has_output = True
except json.JSONDecodeError:
pass
assert has_reasoning, "Should have reasoning summary"
assert has_output, "Should have output text"
@pytest.mark.integration
@pytest.mark.asyncio
async def test_tatlock_markdown_formatting_preserved(async_client: AsyncClient):
"""
Integration test: Verify markdown formatting is preserved in responses.
Tests that code blocks, newlines, and other markdown formatting
are properly preserved through the streaming pipeline.
"""
request_data = {
"model": "Tatlock",
"input": [{"role": "user", "content": "Can you give me an HTML5 boilerplate template?"}],
"stream": True
}
collected_deltas = []
async with async_client.stream(
"POST",
"/v1/responses",
json=request_data,
timeout=45.0, # Give extra time for code generation
) as response:
assert response.status_code == 200
async for line in response.aiter_lines():
if not line.strip():
continue
if line.startswith("data: "):
data_str = line[6:].strip()
if data_str != "[DONE]":
try:
chunk = json.loads(data_str)
if chunk.get("event") == "response.output_text.delta":
collected_deltas.append(chunk["delta"])
except json.JSONDecodeError:
pass
# Reconstruct full response
full_response = "".join(collected_deltas)
# Always print the response for debugging
print("\n" + "="*80)
print("FULL RESPONSE (repr):")
print("="*80)
print(repr(full_response))
print("\n" + "="*80)
print("FULL RESPONSE (formatted):")
print("="*80)
print(full_response)
print("="*80 + "\n")
# Verify we got a response
assert len(full_response) > 100, "Should have a substantial response"
# Verify markdown code block is present
assert "```" in full_response, "Response should contain markdown code blocks"
# Verify newlines are preserved (not all collapsed to spaces)
newline_count = full_response.count('\n')
assert newline_count > 5, f"Should have multiple newlines preserved, got {newline_count}"
# Verify code block markers are complete
code_block_starts = full_response.count("```")
# Should have at least opening and closing markers (even count)
assert code_block_starts % 2 == 0, "Code blocks should have matching opening/closing markers"
assert code_block_starts >= 2, "Should have at least one complete code block"
# Verify HTML tags are present (indicates code block content is preserved)
assert "<!DOCTYPE html>" in full_response or "<html" in full_response, \
"Should contain HTML5 boilerplate elements"
# Verify indentation is preserved (check for multiple spaces in a row)
# This indicates that code formatting with indentation is maintained
assert " " in full_response, "Should preserve indentation (multiple spaces)"
# Log the response for debugging if test fails
if "```" not in full_response or newline_count < 5:
print("\n=== Full Response ===")
print(repr(full_response)) # Use repr to see escaped characters
print("\n=== Newline count ===")
print(f"Found {newline_count} newlines")
@pytest.mark.integration
def test_tatlock_markdown_non_streaming(client: TestClient):
"""
Integration test: Verify markdown in non-streaming mode.
"""
request_data = {
"model": "Tatlock",
"input": [{"role": "user", "content": "Give me a simple Python hello world code"}],
"stream": False
}
response = client.post("/v1/responses", json=request_data, timeout=30.0)
assert response.status_code == 200
data = response.json()
# Get the message content
message_item = next((item for item in data["output"] if item["type"] == "message"), None)
assert message_item is not None
text = message_item["content"][0]["text"]
# Verify markdown code block
assert "```" in text, "Should contain code block markers"
assert "\n" in text, "Should contain newlines"