c3218f70c4
Domain layer (zero framework imports): - domain/models.py: pure dataclasses (RuleDocument, RuleSearchResult, Conversation, ChatMessage, LLMResponse, ChatResult) - domain/ports.py: ABC interfaces (RuleRepository, LLMPort, ConversationStore, IssueTracker) - domain/services.py: ChatService orchestrates Q&A flow using only ports Outbound adapters (implement domain ports): - adapters/outbound/openrouter.py: OpenRouterLLM with persistent httpx client, robust JSON parsing, regex citation fallback - adapters/outbound/sqlite_convos.py: SQLiteConversationStore with async_sessionmaker, timezone-aware datetimes, cleanup support - adapters/outbound/gitea_issues.py: GiteaIssueTracker with markdown injection protection (fenced code blocks) - adapters/outbound/chroma_rules.py: ChromaRuleRepository with clamped similarity scores Inbound adapter: - adapters/inbound/api.py: thin FastAPI router with input validation (max_length constraints), proper HTTP status codes (503 for missing LLM) Configuration & wiring: - config/settings.py: Pydantic v2 SettingsConfigDict (no module-level singleton) - config/container.py: create_app() factory with lifespan-managed DI - main.py: minimal entry point Test infrastructure (90 tests, all passing): - tests/fakes/: in-memory implementations of all 4 ports - tests/domain/: 26 tests for models and ChatService - tests/adapters/: 64 tests for all adapters using fakes/mocks - No real API calls, no model downloads, no disk I/O in fast tests Also fixes: aiosqlite version constraint (>=0.19.0), adds hatch build targets for new package layout. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
61 lines
1.9 KiB
Python
61 lines
1.9 KiB
Python
"""In-memory LLM for testing — returns canned responses, no API calls."""
|
|
|
|
from typing import Optional
|
|
|
|
from domain.models import RuleSearchResult, LLMResponse
|
|
from domain.ports import LLMPort
|
|
|
|
|
|
class FakeLLM(LLMPort):
|
|
"""Returns predictable responses based on whether rules were provided.
|
|
|
|
Configurable for testing specific scenarios (low confidence, errors, etc.).
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
default_answer: str = "Based on the rules, here is the answer.",
|
|
default_confidence: float = 0.9,
|
|
no_rules_answer: str = "I don't have a rule that addresses this question.",
|
|
no_rules_confidence: float = 0.1,
|
|
force_error: Optional[Exception] = None,
|
|
):
|
|
self.default_answer = default_answer
|
|
self.default_confidence = default_confidence
|
|
self.no_rules_answer = no_rules_answer
|
|
self.no_rules_confidence = no_rules_confidence
|
|
self.force_error = force_error
|
|
self.calls: list[dict] = []
|
|
|
|
async def generate_response(
|
|
self,
|
|
question: str,
|
|
rules: list[RuleSearchResult],
|
|
conversation_history: Optional[list[dict[str, str]]] = None,
|
|
) -> LLMResponse:
|
|
self.calls.append(
|
|
{
|
|
"question": question,
|
|
"rules": rules,
|
|
"history": conversation_history,
|
|
}
|
|
)
|
|
|
|
if self.force_error:
|
|
raise self.force_error
|
|
|
|
if rules:
|
|
return LLMResponse(
|
|
answer=self.default_answer,
|
|
cited_rules=[r.rule_id for r in rules],
|
|
confidence=self.default_confidence,
|
|
needs_human=False,
|
|
)
|
|
else:
|
|
return LLMResponse(
|
|
answer=self.no_rules_answer,
|
|
cited_rules=[],
|
|
confidence=self.no_rules_confidence,
|
|
needs_human=True,
|
|
)
|