Files
brain-of-reese/tests/integration/test_api.py
T
ducoterra 15c1272828 feat(rag): agent document tools — list/read tools with env-tuned budgets, SSE tool events + "calling tool" UI
Grounded chat turns now run the agent loop (app/rag/agent.py) instead
of a bare chat_stream: while the per-turn budgets last
(BOR_AGENT_LIST_CALLS / BOR_AGENT_READ_CALLS, default 1 each) the model
gets list_documents (the indexed catalog, /api/docs order) and
read_document (full text, never truncated — A7-revised contract); once
both budgets are spent the tools key is dropped from the request and
the model must answer. Rejected calls (unknown tool, unknown/missing
path, document already in context, spent budget) consume no budget.
Budgets 0/0 make exactly one tools=None request — byte-identical to
the pre-phase path (budgets-as-kill-switch). Deflected turns keep the
direct chat_stream (A8 unchanged; the LOW prompt never carries the
<tools> section).

SSE contract gains {"type":"tool","name":...,"argument":
"source/path"|null} frames ahead of the answer deltas (PLAN §4
extension, owner permission 2026-08-26); done.sources, query_log.sources
and the per-turn log line (gains tool_calls=N) report the retrieval
docs + read docs, deduped. The UI shows a "calling tool"
button/label state and one visible .tool-call line per call above the
answer; the lines persist with the chat record and re-render on
reload. chat_stream passes tools through and accumulates streaming
tool_calls deltas into ToolCallPiece (tools=None stays byte-identical).

E2E: deterministic mock tool flow ("use your tools" + <tools> marker:
list -> read first catalog line -> quoted answer) plus the story suite
(marker flow, reload re-render, plain/deflected no-tool regressions).
Docs: .env.example + README (the two tools, the budgets, the SSE tool
frame, the "calling tool" UI state).

probe: turbo tool_calls=supported 2026-08-26 (uv run python -m
scripts.llm_probe --tools — non-streaming + streaming
finish_reason=tool_calls, indexed delta.tool_calls partials)
2026-08-26 22:39:14 -04:00

215 lines
7.6 KiB
Python

"""Integration tests: HTTP API surface (no database required)."""
from __future__ import annotations
import json
import pytest
from app.config import get_settings
def test_health_reports_ok(client) -> None:
r = client.get("/api/health")
assert r.status_code == 200
body = r.json()
assert body["status"] == "ok"
assert body["db"] in {"up", "down"}
assert body["version"]
def test_suggestions_returns_list(client) -> None:
r = client.get("/api/suggestions")
assert r.status_code == 200
suggestions = r.json()["suggestions"]
assert isinstance(suggestions, list)
assert len(suggestions) >= 3
assert all(isinstance(s, str) and s.strip() for s in suggestions)
def test_suggestions_honors_bor_suggestions_env_override(monkeypatch) -> None:
"""GET /api/suggestions reflects the BOR_SUGGESTIONS JSON env override."""
from fastapi.testclient import TestClient
from app.main import create_app
override = [
"How do I back up with Borg?",
"How is my K3S cluster set up?",
"How do I deploy a service?",
"What proxy fronts reeseapps.com?",
]
get_settings.cache_clear()
try:
monkeypatch.setenv("BOR_SUGGESTIONS", json.dumps(override))
fresh_client = TestClient(create_app())
finally:
get_settings.cache_clear()
r = fresh_client.get("/api/suggestions")
assert r.status_code == 200
assert r.json() == {"suggestions": override}
@pytest.mark.parametrize(
("path", "marker"),
[
("/", "Brain of Reese"),
("/sources.html", "Knowledge base"),
("/document.html", "Brain of Reese"), # phase 10: viewer page
("/login.html", "Sign in"), # phase 16: admin sign-in page
("/tuning.html", "Global Tuning"), # phase 27: global tuning page
("/git-sources.html", "Git sources"), # phase 35: admin git sources page
],
)
def test_html_pages_served_locally_no_cdn(client, path: str, marker: str) -> None:
"""No-CDN check (PLAN §7.3, re-verified on BOTH pages in phase 07 and
on the viewer page in phase 10): each page is served by FastAPI and
references only same-origin assets (no https:// script/link tags)."""
r = client.get(path)
assert r.status_code == 200
assert marker in r.text
assert 'src="https://' not in r.text
assert 'href="https://' not in r.text
# Phase 33 (cache busting): the five HTML pages revalidate (no-cache) with
# ?v=<token> asset refs; /assets/* is immutable for a year; /api/* is
# untouched. The token itself is unit-tested in tests/unit/test_caching.py.
def test_index_page_no_cache_with_versioned_asset_refs(client) -> None:
"""GET / — always revalidated, and the stylesheet reference carries
the process version token (non-empty, matching asset_version())."""
from app.core.caching import asset_version
token = asset_version()
assert token # non-empty in every supported environment
r = client.get("/")
assert r.status_code == 200
assert r.headers["cache-control"] == "no-cache"
assert f'href="/assets/styles.css?v={token}"' in r.text
# The unversioned reference is gone from the served body.
assert 'href="/assets/styles.css">' not in r.text
@pytest.mark.parametrize(
"path",
["/sources.html", "/document.html", "/login.html", "/tuning.html", "/git-sources.html"],
)
def test_html_pages_no_cache_with_versioned_refs(client, path: str) -> None:
"""Each of the other four pages revalidates and carries at least one
versioned asset reference."""
from app.core.caching import asset_version
r = client.get(path)
assert r.status_code == 200
assert r.headers["cache-control"] == "no-cache"
assert f"?v={asset_version()}" in r.text
def test_index_html_variant_no_cache_versioned(client) -> None:
"""/index.html is the same page as / — same caching treatment."""
from app.core.caching import asset_version
r = client.get("/index.html")
assert r.status_code == 200
assert r.headers["cache-control"] == "no-cache"
assert f"?v={asset_version()}" in r.text
def test_assets_served_immutable_for_a_year(client) -> None:
r = client.get("/assets/styles.css")
assert r.status_code == 200
cc = r.headers["cache-control"]
assert "public" in cc
assert "max-age=31536000" in cc
assert "immutable" in cc
# The asset body is untouched (header-only middleware).
assert client.get("/assets/app.js?v=whichever").status_code == 200
def test_api_health_gets_no_cache_control_injected(client) -> None:
"""Baseline (pre-middleware) behavior for /api/*: FastAPI's JSON
responses ship no Cache-Control header — the middleware must not
inject one."""
r = client.get("/api/health")
assert r.status_code == 200
assert "cache-control" not in r.headers
def test_styles_and_js_served(client) -> None:
assert client.get("/assets/styles.css").status_code == 200
assert client.get("/assets/app.js").status_code == 200
assert client.get("/assets/sources.js").status_code == 200
assert client.get("/assets/markdown.js").status_code == 200 # phase 10: shared renderer
assert client.get("/assets/document.js").status_code == 200 # phase 10: viewer page
assert client.get("/assets/login.js").status_code == 200 # phase 16: login page
assert client.get("/assets/document-modal.js").status_code == 200 # phase 26: modal module
assert client.get("/assets/tuning.js").status_code == 200 # phase 27: tuning page
assert client.get("/assets/git-sources.js").status_code == 200 # phase 35: git sources page
# Emoji code points banned from UI chrome (phase 08): the pictograph
# blocks, VS-16/ZWJ, plus the exact glyphs the old light theme used
# (🧠 🧑 👋 📂 ⚠).
_EMOJI_GLYPHS = "\U0001F9E0\U0001F9D1\U0001F44B\U0001F4C2\u26A0"
def _find_emoji(text: str) -> list[str]:
hits: list[str] = []
for ch in text:
cp = ord(ch)
if (
0x1F300 <= cp <= 0x1FAFF
or 0x2600 <= cp <= 0x27BF
or 0x2B00 <= cp <= 0x2BFF
or cp in (0xFE0F, 0x200D)
or ch in _EMOJI_GLYPHS
):
hits.append(ch)
return hits
@pytest.mark.parametrize(
"path",
[
"/",
"/sources.html",
"/document.html",
"/login.html", # phase 16
"/tuning.html", # phase 27
"/git-sources.html", # phase 35
"/assets/app.js",
"/assets/sources.js",
"/assets/markdown.js",
"/assets/document.js",
"/assets/login.js", # phase 16
"/assets/document-modal.js", # phase 26: the document modal module
"/assets/git-sources.js", # phase 35: the git sources page module
"/assets/styles.css",
],
)
def test_ui_chrome_has_no_emoji(client, path: str) -> None:
"""Permanent regression guard (phase 08): the UI chrome — all pages,
the JS that renders it, and the stylesheet — is emoji-free.
Phase 37 revision (owner permission 2026-08-26, PLAN §4): the agent's
``.tool-call`` line carries two CONTENT marks — 🔎 (list) and 📄
(read) — the only emoji in the whole frontend, and only as the exact
tool-line template strings in app.js. The guard strips precisely
those two literals; any other emoji, or those marks anywhere else,
still fails."""
r = client.get(path)
assert r.status_code == 200
text = r.text
if path == "/assets/app.js":
text = text.replace('"🔎 Listing documents"', "")
text = text.replace('"📄 Reading "', "")
assert _find_emoji(text) == [], f"emoji found in {path}: {_find_emoji(text)!r}"
def test_chat_requires_message(client) -> None:
r = client.post("/api/chat", json={"message": ""})
assert r.status_code == 422