mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
99 lines
4 KiB
Python
99 lines
4 KiB
Python
"""Regression guard for #14782: json.JSONDecodeError must not be classified
|
|
as a local validation error by the main agent loop.
|
|
|
|
`json.JSONDecodeError` inherits from `ValueError`. The agent loop's
|
|
non-retryable classifier at run_agent.py treats `ValueError` / `TypeError`
|
|
as local programming bugs and skips retry. Without an explicit carve-out,
|
|
a transient provider hiccup (malformed response body, truncated stream,
|
|
routing-layer corruption) that surfaces as a JSONDecodeError would bypass
|
|
the retry path and fail the turn immediately.
|
|
|
|
This test mirrors the exact predicate shape used in run_agent.py so that
|
|
any future refactor of that predicate must preserve the invariant:
|
|
|
|
JSONDecodeError → NOT local validation error (retryable)
|
|
UnicodeEncodeError → NOT local validation error (surrogate path)
|
|
bare ValueError → IS local validation error (programming bug)
|
|
bare TypeError → IS local validation error (programming bug)
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
|
|
def _mirror_agent_predicate(err: BaseException) -> bool:
|
|
"""Exact shape of run_agent.py's is_local_validation_error check.
|
|
|
|
Kept in lock-step with the source. If you change one, change both —
|
|
or, better, refactor the check into a shared helper and have both
|
|
sites import it.
|
|
"""
|
|
import ssl
|
|
|
|
return (
|
|
isinstance(err, (ValueError, TypeError))
|
|
and not isinstance(err, (UnicodeEncodeError, json.JSONDecodeError))
|
|
and not isinstance(err, ssl.SSLError)
|
|
# NoneType-is-not-iterable shape errors come from upstream SDK /
|
|
# provider response mismatches, not local programming bugs. See
|
|
# the agent/conversation_loop.py inline comment for #33136.
|
|
and not (
|
|
isinstance(err, TypeError)
|
|
and "nonetype" in str(err).lower()
|
|
and "not iterable" in str(err).lower()
|
|
)
|
|
)
|
|
|
|
|
|
class TestJSONDecodeErrorIsRetryable:
|
|
|
|
def test_json_decode_error_is_not_local_validation(self):
|
|
"""Provider returning malformed JSON surfaces as JSONDecodeError —
|
|
must be treated as transient so the retry path runs."""
|
|
try:
|
|
json.loads("{not valid json")
|
|
except json.JSONDecodeError as exc:
|
|
assert not _mirror_agent_predicate(exc), (
|
|
"json.JSONDecodeError must be excluded from the "
|
|
"ValueError/TypeError local-validation classification."
|
|
)
|
|
else:
|
|
raise AssertionError("json.loads should have raised")
|
|
|
|
|
|
def test_bare_value_error_is_local_validation(self):
|
|
"""Programming bugs that raise bare ValueError must still be
|
|
classified as local validation errors (non-retryable)."""
|
|
assert _mirror_agent_predicate(ValueError("bad arg"))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestNoneTypeNotIterableIsRetryable:
|
|
"""Regression for #33136 / closes lingering Telegram \"Non-retryable error (HTTP None)\".
|
|
|
|
The chatgpt.com Codex backend (and any other upstream SDK / provider shim)
|
|
can surface ``TypeError: 'NoneType' object is not iterable`` as a wire-shape
|
|
mismatch, not a local programming bug. Even after #33042 made our own
|
|
consumer immune, third-party paths and mocked clients can still produce
|
|
this shape. The classifier should treat it as retryable so the normal
|
|
retry/fallback chain runs.
|
|
"""
|
|
|
|
def test_nonetype_not_iterable_is_retryable(self):
|
|
err = TypeError("'NoneType' object is not iterable")
|
|
assert not _mirror_agent_predicate(err), (
|
|
"TypeError('NoneType ... not iterable') must be excluded from "
|
|
"is_local_validation_error — it is a provider/SDK shape mismatch, "
|
|
"not a local bug. See #33136."
|
|
)
|
|
|
|
|
|
def test_unrelated_type_error_remains_local_validation(self):
|
|
"""TypeError without the NoneType-not-iterable pattern still aborts (programming bug)."""
|
|
assert _mirror_agent_predicate(TypeError("tools must be a list"))
|
|
assert _mirror_agent_predicate(TypeError("expected str, got int"))
|
|
|
|
|