Files
roboco/tests/unit/runtime/test_kimi_rate_limit.py
T
6374bbbed0 feat(kimi): Kimi K3 provider on the official kimi-code CLI (#713)
* feat(kimi): Kimi K3 provider on the official kimi-code CLI (Wave 1)

ModelProvider.KIMI routes through KimiCliProvider driving Moonshot's kimi
CLI on a Kimi subscription (OAuth device-code, no metered key). One-shot
delivery roles only (V1), interactive ban wired in both guard lists.

Auth: one shared RW auth mount; containers symlink credentials/ and
oauth/ (the CLI's cross-process refresh-lock dir) into a container-local
KIMI_CODE_HOME so every container and the host redeem the SAME rotating
refresh chain - live-verified that per-copy chains cross-invalidate after
the reuse-grace window. No orchestrator refresh daemon; an expires_at
preflight exits 78.

Config renderer mirrors the login-managed provider/model blocks
field-for-field (live-captured; the model value is the CLI-side name,
never the raw API id), plus per-role deny rules and the bash-guard as a
PreToolUse hook via a wrapper script (an env key on a hooks entry makes
the CLI silently drop ALL hooks - live-verified). Usage capture sums
wire.jsonl usage.record 4-bucket events; sniff classifies rate-limit/auth
from structured error text only, mapped to the shared 75/78 park
contract. Image installs the CLI latest-at-build (no version pin, by
policy) with the resolved version stamped as provenance, binary split to
/usr/local away from mutable state.

Migrations 090 (enum) + 091 (provider seed); catalog, pricing, routing
mode, and orchestrator park/usage wiring mirror the codex integration.

* feat(kimi): surface sweep + fleet-wide pin drop (Wave 2)

Compose x3 gain the agent-kimi-image service and the orchestrator's
read-write ~/.kimi-code mount + kimi-usage dir; .env.example documents
the Kimi block. Panel mirrors ModelProvider.KIMI and adds the kimi
routing mode (catalog filter, mode button, mix-picker group, badge) with
tests; provider routes gain the kimi remediation entry. CLAUDE.md and
docs/map document the runtime. Per the no-pins policy, agent-grok/
gemini/codex Dockerfiles drop their version pins for latest-at-build
with resolved-version provenance stamps (grok resolves 0.2.112 vs the
old 0.2.56 pin - verified by real builds of all four images).

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-29 01:48:55 +02:00

157 lines
5.3 KiB
Python

"""KIMI 429/auth parking: same exit-code convention as codex/grok, scoped to
ModelProvider.KIMI so a numeric-code collision with another provider's crash
can never mis-park (see ``_KIMI_RATE_LIMIT_EXIT_CODE`` / ``_KIMI_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 (
_KIMI_AUTH_EXIT_CODE,
_KIMI_RATE_LIMIT_EXIT_CODE,
AgentOrchestrator,
AgentState,
)
def _kimi_instance(provider_type: str = "kimi") -> AgentInstance:
cfg = type("C", (), {"provider_type": provider_type, "model": "kimi-code/k3"})()
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_kimi_rate_limit_exit() -> None:
inst = _kimi_instance()
assert AgentOrchestrator._is_kimi_rate_limit_exit(inst, _KIMI_RATE_LIMIT_EXIT_CODE)
assert not AgentOrchestrator._is_kimi_rate_limit_exit(inst, 0)
assert not AgentOrchestrator._is_kimi_rate_limit_exit(inst, 1)
# A codex exit at the SAME numeric code must NOT be classified as kimi.
assert not AgentOrchestrator._is_kimi_rate_limit_exit(
_kimi_instance(provider_type="openai"), _KIMI_RATE_LIMIT_EXIT_CODE
)
assert not AgentOrchestrator._is_kimi_rate_limit_exit(
_kimi_instance(provider_type="anthropic"), _KIMI_RATE_LIMIT_EXIT_CODE
)
def test_is_kimi_auth_exit() -> None:
inst = _kimi_instance()
assert AgentOrchestrator._is_kimi_auth_exit(inst, _KIMI_AUTH_EXIT_CODE)
assert not AgentOrchestrator._is_kimi_auth_exit(inst, 0)
assert not AgentOrchestrator._is_kimi_auth_exit(inst, 1)
assert not AgentOrchestrator._is_kimi_auth_exit(
_kimi_instance(provider_type="openai"), _KIMI_AUTH_EXIT_CODE
)
@pytest.mark.asyncio
async def test_park_kimi_rate_limited_activates_and_offlines(
monkeypatch: pytest.MonkeyPatch,
) -> None:
orch = AgentOrchestrator.__new__(AgentOrchestrator)
orch._waiting_records = {}
orch._rate_limit_ceo_notified = set()
inst = _kimi_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_kimi_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_kimi_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 = _kimi_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_kimi_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_kimi_429(
monkeypatch: pytest.MonkeyPatch,
) -> None:
orch = AgentOrchestrator.__new__(AgentOrchestrator)
inst = _kimi_instance()
park = AsyncMock()
finalize = AsyncMock()
monkeypatch.setattr(orch, "_park_kimi_rate_limited", park)
monkeypatch.setattr(orch, "_finalize_spawn_session", finalize)
await orch._handle_stopped_container("be-dev-1", inst, _KIMI_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_kimi_auth_exit(
monkeypatch: pytest.MonkeyPatch,
) -> None:
orch = AgentOrchestrator.__new__(AgentOrchestrator)
inst = _kimi_instance()
park = AsyncMock()
finalize = AsyncMock()
monkeypatch.setattr(orch, "_park_kimi_auth_unavailable", park)
monkeypatch.setattr(orch, "_finalize_spawn_session", finalize)
await orch._handle_stopped_container("be-dev-1", inst, _KIMI_AUTH_EXIT_CODE)
park.assert_awaited_once_with("be-dev-1", inst)
finalize.assert_not_awaited()