d10bb2ab6f
`scripts/run_tests.sh tests/<dir>/` is how a change gets its regression
coverage run, so a test filed under the wrong directory is a test nobody
runs when that code changes. Two kinds of drift had accumulated.
Parallel directories for one source package, folded into the mirror:
tests/acp -> tests/acp_adapter (its __init__/conftest move with it)
tests/cli -> tests/hermes_cli (prompt_toolkit fixture merged into
hermes_cli/conftest.py)
tests/run_agent -> tests/agent (backoff fixture becomes
agent/conftest.py)
tests/relay -> tests/gateway/relay
tests/state -> tests/hermes_state
246 loose files at tests/ root, routed by the package they import/patch:
hermes_cli, hermes_state, agent, gateway, tools, plugins, tui_gateway, cron.
Installer and desktop-update script tests go to tests/scripts/{install,
desktop_update}/. 43 tests of root-level modules (batch_runner, utils,
hermes_constants, packaging) stay at the root.
Filenames drop their issue numbers (95 files: test_89315_x.py -> test_x.py);
the number stays in the module docstring where it has context.
Collisions: test_cli_skin_integration.py existed in both tests/ and tests/cli
with different subsets — merged into one (10 tests, all kept);
run_agent/test_pre_compress_memory_context.py -> agent/..._handoff.py;
tests/test_account_usage.py -> agent/test_account_usage_fetch.py;
tests/test_web_server.py -> hermes_cli/test_web_server_ws_ping.py.
Deleted: test_minisweagent_path.py (empty since PR #2804),
test_model_picker_scroll.py (tested a private copy of the logic, imported
nothing), test_process_loop_event_loop_warning.py (asserted asyncio behaviour,
imported nothing from Hermes).
Repo-root path arithmetic (Path(__file__).parents[N], dirname chains) is
bumped for the 202 files that changed depth and verified by evaluating every
such expression against the new location. classify_changes' desktop-updater
lane prefix, tests-os.yml's ignore glob and every in-tree path comment follow
the moves. tests/test_tests_tree_layout.py keeps the tree from drifting back.
127 lines
4.1 KiB
Python
127 lines
4.1 KiB
Python
"""Tests for Anthropic Sonnet long-context tier 429 handling.
|
|
|
|
When Claude Max users without "extra usage" hit the 1M context tier
|
|
on Sonnet, Anthropic returns HTTP 429 "Extra usage is required for long
|
|
context requests." This is NOT a transient rate limit — the agent should
|
|
reduce context_length to 200k and compress instead of retrying.
|
|
|
|
Only Sonnet is affected — Opus 1M is general access.
|
|
"""
|
|
|
|
from types import SimpleNamespace
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Detection logic
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestLongContextTierDetection:
|
|
"""Verify the detection heuristic matches the Anthropic error."""
|
|
|
|
@staticmethod
|
|
def _is_long_context_tier_error(status_code, error_msg, model="claude-sonnet-4.6"):
|
|
error_msg = error_msg.lower()
|
|
return (
|
|
status_code == 429
|
|
and "extra usage" in error_msg
|
|
and "long context" in error_msg
|
|
and "sonnet" in model.lower()
|
|
)
|
|
|
|
def test_matches_anthropic_error(self):
|
|
assert self._is_long_context_tier_error(
|
|
429,
|
|
"Extra usage is required for long context requests.",
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_rejects_partial_match(self):
|
|
"""Both 'extra usage' AND 'long context' must be present."""
|
|
assert not self._is_long_context_tier_error(
|
|
429, "extra usage required"
|
|
)
|
|
assert not self._is_long_context_tier_error(
|
|
429, "long context requests not supported"
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Context reduction
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestContextReduction:
|
|
"""When the long-context tier error fires, context_length should
|
|
drop to 200k and the reduced flag should be set correctly."""
|
|
|
|
def _make_compressor(self, context_length=1_000_000, threshold_percent=0.5):
|
|
c = SimpleNamespace(
|
|
context_length=context_length,
|
|
threshold_percent=threshold_percent,
|
|
threshold_tokens=int(context_length * threshold_percent),
|
|
_context_probed=False,
|
|
_context_probe_persistable=False,
|
|
)
|
|
return c
|
|
|
|
def test_reduces_1m_to_200k(self):
|
|
comp = self._make_compressor(1_000_000)
|
|
reduced_ctx = 200_000
|
|
|
|
if comp.context_length > reduced_ctx:
|
|
comp.context_length = reduced_ctx
|
|
comp.threshold_tokens = int(reduced_ctx * comp.threshold_percent)
|
|
comp._context_probed = True
|
|
comp._context_probe_persistable = False
|
|
|
|
assert comp.context_length == 200_000
|
|
assert comp.threshold_tokens == 100_000
|
|
assert comp._context_probed is True
|
|
# Must NOT persist — subscription tier, not model capability
|
|
assert comp._context_probe_persistable is False
|
|
|
|
def test_no_reduction_when_already_200k(self):
|
|
comp = self._make_compressor(200_000)
|
|
reduced_ctx = 200_000
|
|
|
|
original = comp.context_length
|
|
if comp.context_length > reduced_ctx:
|
|
comp.context_length = reduced_ctx
|
|
|
|
assert comp.context_length == original # unchanged
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Integration: agent error handler path
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestAgentErrorPath:
|
|
"""Verify the long-context 429 doesn't hit the generic rate-limit
|
|
or client-error handlers."""
|
|
|
|
def test_long_context_429_not_treated_as_rate_limit(self):
|
|
"""The error should be intercepted before the generic
|
|
is_rate_limited check fires a fallback switch."""
|
|
error_msg = "extra usage is required for long context requests."
|
|
status_code = 429
|
|
model = "claude-sonnet-4.6"
|
|
|
|
_is_long_context_tier_error = (
|
|
status_code == 429
|
|
and "extra usage" in error_msg
|
|
and "long context" in error_msg
|
|
and "sonnet" in model.lower()
|
|
)
|
|
assert _is_long_context_tier_error
|
|
|
|
|