Files
roboco/tests/unit/runtime/test_codex_rate_limit.py
c70ff3cf9a feat(providers): Codex CLI provider — OpenAI via ModelProvider.OPENAI (#659)
* feat(providers): Codex CLI provider — OpenAI via ModelProvider.OPENAI

Mirrors the grok blueprint end to end: CodexCliProvider (RO ~/.codex
mount, ANTHROPIC_* blanked), an orchestrator-side codex_auth.py
refresher (JWT-exp staleness, atomic rewrite, lock-serialized single-use
rotation, --check backstop; the CLI's own in-process refresh write
no-ops on the RO mount by design — margins keep the orchestrator ahead
of the CLI's 5-minute window), config.toml rendering with required=true
gateway MCP servers, execpolicy deny rules (forbidden-only), per-role
--sandbox (developer=workspace-write, review/doc roles read-only),
codex exec --json with pinned ROBOCO_CODEX_CLI_MODEL (gpt-5.3-codex),
usage summed from typed turn.completed events priced via the real
4-bucket split, dedicated image + entrypoint, registry/park/finalize/
compose/release wiring. V1 excludes interactive intake/secretary.

Per adversarial review: migration 083 seeds the openai provider row
enabled=True (without it every routing path 404'd — the whole feature
was operationally dead code; grok needed the same seed in 039), the
panel picker gained the OpenAI catalog group it silently lacked, and
exit classification is structural — only stderr and error.message
fields from error events are sniffed (word-boundaried patterns, exact
auth phrases, bare 'login' dropped), so the model echoing on-topic
words can never false-park the provider fleet-wide, proven by a
benign-transcript test. Known open risk flagged, not claimed: whether
codex's workspace-write OS sandbox excludes /app is unverified, and no
hook mechanism exists to port the bash-guard defense-in-depth.

* fix(providers): containment barrier on usage.json reads (code scanning)

CodeQL flagged the codex usage read as path injection — correctly:
os.path.basename does not neutralize '..', and the upstream segment
validator isn't in CodeQL's taint model. The grok/codex reads collapse
into one _read_usage_json_contained helper that resolves the built path
and refuses anything outside the resolved usage root — a hostile id can
never escape regardless of upstream drift. Traversal + containment
regression tests added; a stray noqa in the test file replaced with a
named constant per repo rule.

* fix(providers): use realpath+startswith containment CodeQL recognizes

The is_relative_to() guard was a real barrier but not in CodeQL's
py/path-injection sanitizer model, so the alert persisted. Switch to
the canonical os.path.realpath + startswith(root + os.sep) form, which
CodeQL recognizes as a path-traversal barrier; behavior is identical
(refuse any candidate resolving outside the usage root).

* fix(providers): regexp-allowlist the usage-id segment (CodeQL barrier)

Neither is_relative_to nor realpath+startswith was recognized by
CodeQL's py/path-injection sanitizer model across the str->Path->open
flow. Sanitize the tainted component at the source instead: the id must
fullmatch a strict slug token ([A-Za-z0-9][A-Za-z0-9._-]*, no
separators, no '..'), which CodeQL recognizes as a path-injection
barrier; the realpath+startswith containment stays as defense-in-depth.

* fix(providers): standalone regexp guard so CodeQL recognizes the barrier

The sanitizer was one disjunct of a compound 'or' condition, which
CodeQL's guard analysis does not trace as a barrier. Split the regexp
fullmatch into its own single-condition guard (the redundant '..' check
is dropped — the required alphanumeric first char already excludes it).

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-23 03:20:29 +02:00

159 lines
5.3 KiB
Python

"""CODEX 429/auth parking: same exit-code convention as grok, scoped to
ModelProvider.OPENAI so a numeric-code collision with another provider's crash
can never mis-park (see ``_CODEX_RATE_LIMIT_EXIT_CODE`` / ``_CODEX_AUTH_EXIT_CODE``
in ``roboco.runtime.orchestrator``).
"""
from __future__ import annotations
from unittest.mock import AsyncMock
import pytest
from roboco.models.runtime import AgentInstance
from roboco.runtime.orchestrator import (
_CODEX_AUTH_EXIT_CODE,
_CODEX_RATE_LIMIT_EXIT_CODE,
AgentOrchestrator,
AgentState,
)
def _codex_instance(provider_type: str = "openai") -> AgentInstance:
cfg = type("C", (), {"provider_type": provider_type, "model": "gpt-5.3-codex"})()
inst = AgentInstance(agent_id="be-dev-1", state=AgentState.ACTIVE, config=cfg)
inst.current_task_id = "task-1"
inst.container_id = "cid"
return inst
class _FakeTracker:
def __init__(self) -> None:
self.activated_with: dict[str, object] | None = None
async def activate(
self,
*,
retry_after: float,
affected_agents: list[str],
kind: str = "rate_limited",
) -> None:
self.activated_with = {
"retry_after": retry_after,
"affected_agents": affected_agents,
"kind": kind,
}
def test_is_codex_rate_limit_exit() -> None:
inst = _codex_instance()
assert AgentOrchestrator._is_codex_rate_limit_exit(
inst, _CODEX_RATE_LIMIT_EXIT_CODE
)
assert not AgentOrchestrator._is_codex_rate_limit_exit(inst, 0)
assert not AgentOrchestrator._is_codex_rate_limit_exit(inst, 1)
# A grok exit at the SAME numeric code must NOT be classified as codex.
assert not AgentOrchestrator._is_codex_rate_limit_exit(
_codex_instance(provider_type="grok"), _CODEX_RATE_LIMIT_EXIT_CODE
)
assert not AgentOrchestrator._is_codex_rate_limit_exit(
_codex_instance(provider_type="anthropic"), _CODEX_RATE_LIMIT_EXIT_CODE
)
def test_is_codex_auth_exit() -> None:
inst = _codex_instance()
assert AgentOrchestrator._is_codex_auth_exit(inst, _CODEX_AUTH_EXIT_CODE)
assert not AgentOrchestrator._is_codex_auth_exit(inst, 0)
assert not AgentOrchestrator._is_codex_auth_exit(inst, 1)
assert not AgentOrchestrator._is_codex_auth_exit(
_codex_instance(provider_type="grok"), _CODEX_AUTH_EXIT_CODE
)
@pytest.mark.asyncio
async def test_park_codex_rate_limited_activates_and_offlines(
monkeypatch: pytest.MonkeyPatch,
) -> None:
orch = AgentOrchestrator.__new__(AgentOrchestrator)
orch._waiting_records = {}
orch._rate_limit_ceo_notified = set()
inst = _codex_instance()
inst.error_count = 2 # pretend prior crashes — parking must NOT count one
tracker = _FakeTracker()
monkeypatch.setattr(orch, "_make_tracker", lambda _p: tracker)
finalize = AsyncMock()
monkeypatch.setattr(orch, "_finalize_spawn_session", finalize)
monkeypatch.setattr(orch, "_persist_waiting_record", AsyncMock())
await orch._park_codex_rate_limited("be-dev-1", inst)
finalize.assert_awaited_once()
assert inst.state == AgentState.OFFLINE
assert inst.container_id is None
assert inst.error_count == 0 # a 429 is not a crash
assert tracker.activated_with == {
"retry_after": pytest.approx(60.0),
"affected_agents": ["be-dev-1"],
"kind": "rate_limited",
}
@pytest.mark.asyncio
async def test_park_codex_auth_unavailable_activates_with_auth_missing_kind(
monkeypatch: pytest.MonkeyPatch,
) -> None:
orch = AgentOrchestrator.__new__(AgentOrchestrator)
orch._waiting_records = {}
orch._rate_limit_ceo_notified = set()
inst = _codex_instance()
inst.error_count = 2
tracker = _FakeTracker()
monkeypatch.setattr(orch, "_make_tracker", lambda _p: tracker)
monkeypatch.setattr(orch, "_finalize_spawn_session", AsyncMock())
monkeypatch.setattr(orch, "_persist_waiting_record", AsyncMock())
await orch._park_codex_auth_unavailable("be-dev-1", inst)
assert inst.state == AgentState.OFFLINE
assert inst.container_id is None
assert inst.error_count == 0
assert tracker.activated_with == {
"retry_after": pytest.approx(60.0),
"affected_agents": ["be-dev-1"],
"kind": "auth_missing",
}
@pytest.mark.asyncio
async def test_handle_stopped_container_parks_on_codex_429(
monkeypatch: pytest.MonkeyPatch,
) -> None:
orch = AgentOrchestrator.__new__(AgentOrchestrator)
inst = _codex_instance()
park = AsyncMock()
finalize = AsyncMock()
monkeypatch.setattr(orch, "_park_codex_rate_limited", park)
monkeypatch.setattr(orch, "_finalize_spawn_session", finalize)
await orch._handle_stopped_container("be-dev-1", inst, _CODEX_RATE_LIMIT_EXIT_CODE)
park.assert_awaited_once_with("be-dev-1", inst)
finalize.assert_not_awaited()
@pytest.mark.asyncio
async def test_handle_stopped_container_parks_on_codex_auth_exit(
monkeypatch: pytest.MonkeyPatch,
) -> None:
orch = AgentOrchestrator.__new__(AgentOrchestrator)
inst = _codex_instance()
park = AsyncMock()
finalize = AsyncMock()
monkeypatch.setattr(orch, "_park_codex_auth_unavailable", park)
monkeypatch.setattr(orch, "_finalize_spawn_session", finalize)
await orch._handle_stopped_container("be-dev-1", inst, _CODEX_AUTH_EXIT_CODE)
park.assert_awaited_once_with("be-dev-1", inst)
finalize.assert_not_awaited()