retoorandClaude Sonnet 5
a693a6f4d8
Admin-unlimited Dev Workspaces: an admin-owned workspace is now exempt from the max-workspace-count limit, the max-tunnel-count limit, and the whole idle-stop/idle-warn/retention-delete lifecycle. Resolved once in quota.resolve() as Limits.unlimited (owner uid checked against get_admin_uids()), consumed at the three enforcement points (provision.ensure, provision.publish_tunnel, WorkspaceService._advance_lifecycle). Also hardens get_admin_uids()/get_primary_admin_uid() against a partially-schemaed users table (uid/role column guard), which a fresh test/init_db() path could hit. AI gateway per-model automatic fallback: any gateway_models route (chat/embed/image) can now name a fallback_model, picked on /admin/gateway from a select box of other configured public model names of the same kind only (never an internal upstream model id). When a route fails after its own retries are exhausted, the gateway retries once, automatically, against the fallback's own provider/pricing/key, before any bytes reach the client (including for a streaming response). One hop only, no chains or cycles; self-reference and cross-kind fallbacks are rejected at write time. AI gateway real upstream streaming and thinking-default control: stream:true is now forwarded to the upstream and relayed to the client as real SSE chunks (measured TTFT/inter-token latency) instead of a simulated split response, and every chat/vision call explicitly disables model "thinking" by default (admin-overridable via gateway_thinking), with per-dialect handling for DeepSeek, OpenRouter, and Ollama. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TjdKTWgWpW2SMNW8SFqxz5
245 lines
7.6 KiB
Python
245 lines
7.6 KiB
Python
# retoor <retoor@molodetz.nl>
|
|
|
|
import requests
|
|
|
|
from tests.conftest import BASE_URL
|
|
from tests.api.admin.gateway.index import (
|
|
JSON_gateway,
|
|
admin_session,
|
|
member_key,
|
|
_unique_gateway,
|
|
)
|
|
|
|
|
|
def test_models_require_admin(seeded_db):
|
|
assert (
|
|
requests.get(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
headers=JSON_gateway,
|
|
allow_redirects=False,
|
|
).status_code
|
|
== 401
|
|
)
|
|
key = member_key()
|
|
assert (
|
|
requests.get(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
headers={**JSON_gateway, "X-API-KEY": key},
|
|
allow_redirects=False,
|
|
).status_code
|
|
== 403
|
|
)
|
|
assert (
|
|
admin_session(seeded_db).get(f"{BASE_URL}/admin/gateway/models").status_code
|
|
== 200
|
|
)
|
|
|
|
|
|
def test_model_route_create_and_economy(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
source = _unique_gateway("src")
|
|
|
|
created = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={
|
|
"source_model": source,
|
|
"provider": "",
|
|
"target_model": "vendor/y",
|
|
"kind": "chat",
|
|
"price_output_per_m": 5.0,
|
|
"price_cache_miss_per_m": 2.0,
|
|
"context_window": 32000,
|
|
},
|
|
)
|
|
assert created.status_code == 200, created.text[:300]
|
|
assert created.json()["model"]["target_model"] == "vendor/y"
|
|
|
|
listed = admin.get(f"{BASE_URL}/admin/gateway/models").json()
|
|
row = next(m for m in listed["models"] if m["source_model"] == source)
|
|
assert row["kind"] == "chat"
|
|
assert row["price_output_per_m"] == 5.0
|
|
assert row["context_window"] == 32000
|
|
|
|
deleted = admin.delete(f"{BASE_URL}/admin/gateway/models/{source}")
|
|
assert deleted.status_code == 200
|
|
assert admin.delete(f"{BASE_URL}/admin/gateway/models/{source}").status_code == 404
|
|
|
|
|
|
def test_model_route_tiered_and_off_peak_pricing_round_trip(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
source = _unique_gateway("tiered")
|
|
|
|
created = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={
|
|
"source_model": source,
|
|
"target_model": "vendor/tiered",
|
|
"kind": "chat",
|
|
"price_cache_hit_per_m": 0.0028,
|
|
"price_cache_miss_per_m": 0.14,
|
|
"price_output_per_m": 0.28,
|
|
"context_tier_threshold_tokens": 128000,
|
|
"price_output_per_m_tier2": 0.56,
|
|
"off_peak_start_minute": 990,
|
|
"off_peak_end_minute": 30,
|
|
"off_peak_discount_pct": 25.0,
|
|
},
|
|
)
|
|
assert created.status_code == 200, created.text[:300]
|
|
model = created.json()["model"]
|
|
assert model["context_tier_threshold_tokens"] == 128000
|
|
assert model["price_output_per_m_tier2"] == 0.56
|
|
assert model["price_cache_hit_per_m_tier2"] is None
|
|
assert model["off_peak_start_minute"] == 990
|
|
assert model["off_peak_end_minute"] == 30
|
|
assert model["off_peak_discount_pct"] == 25.0
|
|
|
|
listed = admin.get(f"{BASE_URL}/admin/gateway/models").json()
|
|
row = next(m for m in listed["models"] if m["source_model"] == source)
|
|
assert row["context_tier_threshold_tokens"] == 128000
|
|
assert row["price_output_per_m_tier2"] == 0.56
|
|
assert row["off_peak_start_minute"] == 990
|
|
assert row["off_peak_end_minute"] == 30
|
|
assert row["off_peak_discount_pct"] == 25.0
|
|
|
|
deleted = admin.delete(f"{BASE_URL}/admin/gateway/models/{source}")
|
|
assert deleted.status_code == 200
|
|
|
|
|
|
def test_model_route_off_peak_requires_both_start_and_end(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
source = _unique_gateway("badwindow")
|
|
|
|
only_start = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={
|
|
"source_model": source,
|
|
"target_model": "vendor/w",
|
|
"kind": "chat",
|
|
"off_peak_start_minute": 60,
|
|
},
|
|
)
|
|
assert only_start.status_code == 400
|
|
assert only_start.json()["ok"] is False
|
|
|
|
only_end = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={
|
|
"source_model": source,
|
|
"target_model": "vendor/w",
|
|
"kind": "chat",
|
|
"off_peak_end_minute": 120,
|
|
},
|
|
)
|
|
assert only_end.status_code == 400
|
|
assert only_end.json()["ok"] is False
|
|
|
|
|
|
def test_model_route_fallback_round_trip(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
backup = _unique_gateway("fb-backup")
|
|
primary = _unique_gateway("fb-primary")
|
|
|
|
created_backup = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={"source_model": backup, "target_model": "vendor/backup", "kind": "chat"},
|
|
)
|
|
assert created_backup.status_code == 200, created_backup.text[:300]
|
|
|
|
created_primary = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={
|
|
"source_model": primary,
|
|
"target_model": "vendor/primary",
|
|
"kind": "chat",
|
|
"fallback_model": backup,
|
|
},
|
|
)
|
|
assert created_primary.status_code == 200, created_primary.text[:300]
|
|
assert created_primary.json()["model"]["fallback_model"] == backup
|
|
|
|
listed = admin.get(f"{BASE_URL}/admin/gateway/models").json()
|
|
row = next(m for m in listed["models"] if m["source_model"] == primary)
|
|
assert row["fallback_model"] == backup
|
|
|
|
admin.delete(f"{BASE_URL}/admin/gateway/models/{primary}")
|
|
admin.delete(f"{BASE_URL}/admin/gateway/models/{backup}")
|
|
|
|
|
|
def test_model_route_fallback_must_reference_an_existing_route(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
source = _unique_gateway("fb-ghost")
|
|
|
|
response = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={
|
|
"source_model": source,
|
|
"target_model": "vendor/z",
|
|
"kind": "chat",
|
|
"fallback_model": _unique_gateway("does-not-exist"),
|
|
},
|
|
)
|
|
assert response.status_code == 400
|
|
assert response.json()["ok"] is False
|
|
|
|
|
|
def test_model_route_fallback_must_be_the_same_kind(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
embed_route = _unique_gateway("fb-embed")
|
|
chat_route = _unique_gateway("fb-chat")
|
|
|
|
admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={"source_model": embed_route, "target_model": "vendor/e", "kind": "embed"},
|
|
)
|
|
response = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={
|
|
"source_model": chat_route,
|
|
"target_model": "vendor/c",
|
|
"kind": "chat",
|
|
"fallback_model": embed_route,
|
|
},
|
|
)
|
|
assert response.status_code == 400
|
|
assert response.json()["ok"] is False
|
|
|
|
admin.delete(f"{BASE_URL}/admin/gateway/models/{embed_route}")
|
|
|
|
|
|
def test_model_route_fallback_rejects_self_reference(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
source = _unique_gateway("fb-self")
|
|
|
|
response = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={
|
|
"source_model": source,
|
|
"target_model": "vendor/z",
|
|
"kind": "chat",
|
|
"fallback_model": source,
|
|
},
|
|
)
|
|
assert response.status_code == 400
|
|
assert response.json()["ok"] is False
|
|
|
|
|
|
def test_model_route_validation(seeded_db):
|
|
admin = admin_session(seeded_db)
|
|
missing_target = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={"source_model": _unique_gateway("src")},
|
|
)
|
|
assert missing_target.status_code == 400
|
|
assert missing_target.json()["ok"] is False
|
|
|
|
bad_kind = admin.post(
|
|
f"{BASE_URL}/admin/gateway/models",
|
|
json={
|
|
"source_model": _unique_gateway("src"),
|
|
"target_model": "vendor/z",
|
|
"kind": "bogus",
|
|
},
|
|
)
|
|
assert bad_kind.status_code == 400
|