mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-10-07 16:19:09 +00:00
Adam Moussa
1c93e5c62b
Migrate off direct provider APIs: AWS Bedrock for Anthropic/Claude via the cross-region inference profile us.anthropic.claude-opus-4-8, Fireworks AI for all non-Claude models. Drop OpenAI (gpt-5.5) and Google (gemini-3.5-flash) entirely. DEFAULT_MODEL_ID is now Bedrock Claude; all Fireworks models stay freely selectable for the agent and reviewer graphs and via team/profile defaults. - pyproject: add langchain-aws (ChatBedrockConverse + boto3) - options.py: Bedrock Claude entry + default; remove openai/google entries - model.py: bedrock_converse provider_model_kwargs (effort -> thinking budget), region pin in make_model, bedrock<->fireworks fallback pairing, AWS_REGION/ FIREWORKS_API_KEY local-dev validation - server.py: provider-aware fallback kwargs build - sanitize_thinking_blocks: also sanitize ChatBedrockConverse thinking blocks - model_fallback: treat transient botocore ClientError codes as fallback-worthy - eval_jobs: repoint hardcoded eval model id to Bedrock Claude - tests: repoint dropped model ids; drop obsolete google test module
83 lines
2.7 KiB
Python
83 lines
2.7 KiB
Python
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock, patch
|
|
|
|
import pytest
|
|
from pydantic import ValidationError
|
|
|
|
from agent.dashboard.team_settings import (
|
|
TeamSettingsUpdate,
|
|
get_team_default_grouping_model,
|
|
)
|
|
|
|
_REVIEWER_SUBAGENT_PAIR = ("fireworks:accounts/fireworks/models/deepseek-v4-pro", "low")
|
|
_GROUPING_PAIR = ("fireworks:accounts/fireworks/models/kimi-k2p7-code", "low")
|
|
|
|
|
|
def _settings(**overrides: object) -> dict[str, object]:
|
|
base: dict[str, object] = {
|
|
"default_reviewer_subagent_model": _REVIEWER_SUBAGENT_PAIR[0],
|
|
"default_reviewer_subagent_reasoning_effort": _REVIEWER_SUBAGENT_PAIR[1],
|
|
"default_grouping_model": None,
|
|
"default_grouping_reasoning_effort": None,
|
|
}
|
|
base.update(overrides)
|
|
return base
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_grouping_inherits_reviewer_subagent_when_unset() -> None:
|
|
with patch(
|
|
"agent.dashboard.team_settings.get_team_settings",
|
|
new_callable=AsyncMock,
|
|
return_value=_settings(),
|
|
):
|
|
assert await get_team_default_grouping_model() == _REVIEWER_SUBAGENT_PAIR
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_grouping_uses_configured_model_when_set() -> None:
|
|
with patch(
|
|
"agent.dashboard.team_settings.get_team_settings",
|
|
new_callable=AsyncMock,
|
|
return_value=_settings(
|
|
default_grouping_model=_GROUPING_PAIR[0],
|
|
default_grouping_reasoning_effort=_GROUPING_PAIR[1],
|
|
),
|
|
):
|
|
assert await get_team_default_grouping_model() == _GROUPING_PAIR
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_grouping_inherits_when_configured_model_invalid() -> None:
|
|
with patch(
|
|
"agent.dashboard.team_settings.get_team_settings",
|
|
new_callable=AsyncMock,
|
|
return_value=_settings(
|
|
default_grouping_model="bogus:model",
|
|
default_grouping_reasoning_effort="high",
|
|
),
|
|
):
|
|
assert await get_team_default_grouping_model() == _REVIEWER_SUBAGENT_PAIR
|
|
|
|
|
|
def test_team_settings_update_accepts_grouping_pair() -> None:
|
|
update = TeamSettingsUpdate(
|
|
default_grouping_model=_GROUPING_PAIR[0],
|
|
default_grouping_reasoning_effort=_GROUPING_PAIR[1],
|
|
)
|
|
assert update.default_grouping_model == _GROUPING_PAIR[0]
|
|
assert update.default_grouping_reasoning_effort == _GROUPING_PAIR[1]
|
|
|
|
|
|
def test_team_settings_update_rejects_grouping_effort_without_model() -> None:
|
|
with pytest.raises(ValidationError):
|
|
TeamSettingsUpdate(default_grouping_reasoning_effort="high")
|
|
|
|
|
|
def test_team_settings_update_rejects_unsupported_grouping_effort() -> None:
|
|
with pytest.raises(ValidationError):
|
|
TeamSettingsUpdate(
|
|
default_grouping_model=_GROUPING_PAIR[0],
|
|
default_grouping_reasoning_effort="max",
|
|
)
|