retoorandClaude Sonnet 5
569f1dcc64
AI gateway: - Add a generic, admin-selectable `client_profile` field on gateway_providers (e.g. "opencode") so a provider needing special request headers (OpenCode Zen's client-identity spoofing) is configured like any other provider, not hardcoded by name. - Track per-(provider, model) reliability/speed/latency health in memory, seeded from the existing gateway_usage_ledger at startup - purely observational, never influences routing. - New Stats tab on /admin/gateway: request volume, latency, per-model breakdowns, and reliability weight, charted with a vendored Chart.js and devplace's own theme tokens. - Record which model a failed request actually fell back to (fallback_used_route), surfaced in the Recent Failures table. - Stop excluding context_length errors from fallback, and skip a primary attempt outright when its known context window is already too small for the estimated request size, going straight to the fallback. - gateway_usage_ledger's provider/fallback_used_route columns and indexes are ensured centrally in database/schema.py's init_db(), the single point of truth for this table's schema. - Non-OpenAI upstream routing and client-model passthrough; trust only the upstream's own X-Gateway-Model header for served-model attribution. Devii agent: - Fix a real lockup: plan/verify tools could be individually disabled via the admin tool toggles while still being required by the protocol gate, permanently bricking any task that needed tools. They can no longer be disabled, and the gate now also checks the tool is actually offered. - Fix compaction being silently calibrated for a 1M-token model while running a much smaller one: context budget is now percentage-based and the summarizer's own request is sized to fit the real model. - Give a specific, actionable retry message when plan()'s own arguments get cut off by the output limit, and tighten its schema to discourage overlong plans. Other: - Backup service: offload completed backups to a remote Hetzner Storage Box. - Container manager: fix orphan blob leaks from sync races, add a two-phase plan/execute `system prune` CLI command. - Admin gateway UI: replace the JS-rendered model/provider tables with server-rendered forms and pages. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01DhmEkvutuwtzFVcLbTrhdo
98 lines
2.9 KiB
Python
98 lines
2.9 KiB
Python
# retoor <retoor@molodetz.nl>
|
|
|
|
import time
|
|
|
|
import requests
|
|
|
|
from devplacepy.database import get_table, refresh_snapshot
|
|
from tests.conftest import BASE_URL
|
|
|
|
JSON_gateway = {"Accept": "application/json"}
|
|
_counter_gateway = [0]
|
|
|
|
|
|
def _db_user_gateway(name):
|
|
refresh_snapshot()
|
|
return get_table("users").find_one(username=name)
|
|
|
|
|
|
def _unique_gateway(prefix="gw"):
|
|
_counter_gateway[0] += 1
|
|
return f"{prefix}{int(time.time() * 1000)}{_counter_gateway[0]}"
|
|
|
|
|
|
def admin_session(seeded_db):
|
|
session = requests.Session()
|
|
session.headers.update(
|
|
{"X-API-KEY": _db_user_gateway("alice_test")["api_key"], **JSON_gateway}
|
|
)
|
|
return session
|
|
|
|
|
|
def member_key():
|
|
name = _unique_gateway("gwmem")
|
|
requests.post(
|
|
f"{BASE_URL}/auth/signup",
|
|
data={
|
|
"username": name,
|
|
"email": f"{name}@t.dev",
|
|
"password": "secret123",
|
|
"confirm_password": "secret123",
|
|
"birth_date": "1990-01-01",
|
|
"accept_terms": "1",
|
|
},
|
|
allow_redirects=True,
|
|
)
|
|
return _db_user_gateway(name)["api_key"]
|
|
|
|
|
|
def test_gateway_page_requires_admin(seeded_db):
|
|
assert (
|
|
requests.get(
|
|
f"{BASE_URL}/admin/gateway", headers=JSON_gateway, allow_redirects=False
|
|
).status_code
|
|
== 401
|
|
)
|
|
key = member_key()
|
|
assert (
|
|
requests.get(
|
|
f"{BASE_URL}/admin/gateway",
|
|
headers={**JSON_gateway, "X-API-KEY": key},
|
|
allow_redirects=False,
|
|
).status_code
|
|
== 403
|
|
)
|
|
|
|
|
|
def test_gateway_page_renders_for_admin(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
response = admin.get(f"{BASE_URL}/admin/gateway", headers={"Accept": "text/html"})
|
|
assert response.status_code == 200
|
|
assert "Gateway routing" in response.text
|
|
|
|
|
|
def test_gateway_page_tabs_default_and_select_content(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
|
|
default_page = admin.get(f"{BASE_URL}/admin/gateway", headers={"Accept": "text/html"})
|
|
assert "Model routes" in default_page.text
|
|
assert "GatewayAdmin" not in default_page.text
|
|
|
|
providers_page = admin.get(f"{BASE_URL}/admin/gateway?tab=providers", headers={"Accept": "text/html"})
|
|
assert "Providers" in providers_page.text
|
|
assert "Model routes" not in providers_page.text
|
|
|
|
quota_page = admin.get(f"{BASE_URL}/admin/gateway?tab=quota", headers={"Accept": "text/html"})
|
|
assert "Quota rules" in quota_page.text
|
|
assert "Model routes" not in quota_page.text
|
|
|
|
unknown_tab_page = admin.get(f"{BASE_URL}/admin/gateway?tab=bogus", headers={"Accept": "text/html"})
|
|
assert "Model routes" in unknown_tab_page.text
|
|
|
|
|
|
def test_gateway_page_json_reports_active_tab(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
response = admin.get(f"{BASE_URL}/admin/gateway?tab=providers")
|
|
assert response.status_code == 200
|
|
assert response.json()["tab"] == "providers"
|