ducoterra
396e4d47fb
Phase 03 (Story: Chat RAG Answer — happy path):
- app/rag/retriever.py: top-k cosine search + parent-doc selection with
per-doc dedupe and BOR_MAX_CONTEXT_CHARS cap ([…truncated…] marker)
- app/rag/prompts.py: locked persona + HIGH/DEFLECT prompt builders
- app/rag/llm.py: LLMError + chat_stream (turbo, temp 0.4, max 700, stream)
- app/api/chat.py: POST /api/chat SSE — delta* then done{deflected,
sources, suggestions}; query_log row + PLAN §9 per-turn log line;
structured error event on mid-stream failure, JSON 503 when DB down
- frontend: SSE reader, live bubble streaming, source chips -> /sources.html,
red role=alert banner, Send button state that always recovers
- fix(scaffold): [hidden] { display: none !important } — .kb-banner's
display:flex was overriding the hidden attribute (banner always visible)
- tests: unit (retriever/prompts/sse/llm) + integration (real Postgres RAG
turn, query_log, error + 503 paths, mid-turn failures) + Playwright story
suite (grounded answer, log row, raw SSE shape); smoke placeholder test
replaced with the real never-stale-button contract
49 lines
1.7 KiB
Python
49 lines
1.7 KiB
Python
"""Unit: SSE frame serialization for POST /api/chat (PLAN §4 contract)."""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
from app.api.chat import sse_event
|
|
|
|
|
|
def _payload(frame: str) -> dict:
|
|
assert frame.startswith("data: ")
|
|
assert frame.endswith("\n\n")
|
|
return json.loads(frame.removeprefix("data: ").strip())
|
|
|
|
|
|
def test_delta_frame_serializes_exactly() -> None:
|
|
frame = sse_event({"type": "delta", "text": "hi"})
|
|
assert frame == 'data: {"type": "delta", "text": "hi"}\n\n'
|
|
assert _payload(frame) == {"type": "delta", "text": "hi"}
|
|
|
|
|
|
def test_done_frame_carries_full_contract_shape() -> None:
|
|
payload = {
|
|
"type": "done",
|
|
"deflected": False,
|
|
"sources": [{"source": "Homelab", "path": "kubernetes.md", "title": "K8s"}],
|
|
"suggestions": [],
|
|
}
|
|
assert _payload(sse_event(payload)) == payload
|
|
|
|
|
|
def test_error_frame_serializes() -> None:
|
|
frame = sse_event({"type": "error", "detail": "boom"})
|
|
assert _payload(frame) == {"type": "error", "detail": "boom"}
|
|
|
|
|
|
def test_unicode_survives_roundtrip() -> None:
|
|
frame = sse_event({"type": "delta", "text": "🧠 café — \"quoted\""})
|
|
# ensure_ascii=False keeps the frame readable (no \uXXXX escapes).
|
|
assert "🧠 café" in frame
|
|
assert _payload(frame)["text"] == "🧠 café — \"quoted\""
|
|
|
|
|
|
def test_multi_line_text_stays_one_frame() -> None:
|
|
"""Newlines inside the JSON payload must be escaped so the frame
|
|
delimiter ``\\n\\n`` remains unambiguous."""
|
|
frame = sse_event({"type": "delta", "text": "line1\nline2\n\n"})
|
|
assert frame.count("\n\n") == 1 # only the frame terminator
|
|
assert _payload(frame)["text"] == "line1\nline2\n\n"
|