Teknium
39975613b1
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
53 lines
1.9 KiB
Python
53 lines
1.9 KiB
Python
"""Regression tests for #28156 — Bedrock picker must be region-scoped.
|
|
|
|
Geo-prefixed cross-region inference profiles (us.*, eu.*, apac.*, ...) only
|
|
route from endpoints in their own geography. Offering us.* profiles to an
|
|
eu-central-2 picker produces configs AWS rejects regardless of credentials.
|
|
"""
|
|
|
|
from hermes_cli.model_setup_flows import (
|
|
BEDROCK_GEO_PREFIXES,
|
|
bedrock_model_routable_from_region,
|
|
bedrock_region_geo_prefix,
|
|
)
|
|
|
|
|
|
class TestRegionGeoPrefix:
|
|
def test_known_geographies(self):
|
|
assert bedrock_region_geo_prefix("us-east-1") == "us."
|
|
assert bedrock_region_geo_prefix("eu-central-2") == "eu."
|
|
assert bedrock_region_geo_prefix("ap-southeast-1") == "ap."
|
|
assert bedrock_region_geo_prefix("ca-central-1") == "ca."
|
|
assert bedrock_region_geo_prefix("sa-east-1") == "sa."
|
|
assert bedrock_region_geo_prefix("me-south-1") == "me."
|
|
assert bedrock_region_geo_prefix("af-south-1") == "af."
|
|
|
|
def test_unknown_region_is_empty(self):
|
|
assert bedrock_region_geo_prefix("") == ""
|
|
assert bedrock_region_geo_prefix("moon-base-1") == ""
|
|
|
|
|
|
class TestRoutableFromRegion:
|
|
def test_us_profile_not_offered_in_eu(self):
|
|
assert not bedrock_model_routable_from_region(
|
|
"us.anthropic.claude-sonnet-4-6", "eu-central-2"
|
|
)
|
|
|
|
|
|
|
|
|
|
class TestGeoPrefixContract:
|
|
def test_every_geo_prefix_maps_to_a_routable_region_or_is_alias(self):
|
|
"""Invariant: each geo prefix is either reachable from some region's
|
|
geo mapping or an ap-family alias — no dead entries."""
|
|
mapped = {
|
|
bedrock_region_geo_prefix(r)
|
|
for r in (
|
|
"us-east-1", "eu-central-2", "ap-southeast-1",
|
|
"ca-central-1", "sa-east-1", "me-south-1", "af-south-1",
|
|
)
|
|
}
|
|
ap_aliases = {"apac.", "jp."}
|
|
for prefix in BEDROCK_GEO_PREFIXES:
|
|
assert prefix in mapped or prefix in ap_aliases
|