Skip to content

Hotfix | Rogue-Server | Bedrock support #132

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yuval-qf merged 1 commit into from
Nov 10, 2025
Merged

Hotfix | Rogue-Server | Bedrock support #132

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion .vscode/launch.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
"python": "./.venv/bin/python",
"module": "rogue",
"args": [
"--debug",
"server",
"--host",
"0.0.0.0",
Expand Down Expand Up @@ -57,7 +58,7 @@
"--protocol",
"mcp",
"--judge-llm",
"openai/o4-mini",
"bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0",
"--workdir",
"./examples/tshirt_store_agent/.rogue"
],
Expand Down
2 changes: 1 addition & 1 deletion VERSION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
0.2.2
0.2.3
1 change: 1 addition & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ requires-python = ">=3.10"
dependencies = [
"a2a-sdk==0.2.10",
"backoff>=2.2.1",
"boto3>=1.40.69",
"click>=8.0.0",
"datasets==3.6.0",
"fastapi>=0.121.0",
Expand Down
21 changes: 18 additions & 3 deletions rogue/evaluator_agent/base_evaluator_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import json
from abc import ABC, abstractmethod
from types import TracebackType
from typing import TYPE_CHECKING, Any, Callable, Optional, Self, Type
Expand Down Expand Up @@ -365,7 +366,6 @@ def _log_evaluation(
context_id: str,
evaluation_passed: bool,
reason: str,
scenario_type: Optional[str],
**kwargs,
) -> None:
"""
Expand Down Expand Up @@ -395,7 +395,19 @@ def _log_evaluation(
"context_id": context_id,
},
)
scenario_dict = {"scenario": scenario}

try:
scenario_dict = json.loads(scenario)
except json.JSONDecodeError:
logger.warning(
"⚠️ Failed to parse scenario dict as JSON - recovering",
extra={
"scenario": scenario,
"context_id": context_id,
},
)
scenario_dict = {"scenario": scenario}
return
elif isinstance(scenario, dict):
scenario_dict = scenario
else:
Expand Down Expand Up @@ -423,7 +435,10 @@ def _log_evaluation(
),
"evaluation_passed (from agent)": evaluation_passed,
"reason (from agent)": reason,
"scenario_type": scenario_type,
"scenario_type": scenario_dict.get(
"scenario_type",
ScenarioType.POLICY.value,
),
"expected_outcome": scenario_dict.get(
"expected_outcome",
"None",
Expand Down
10 changes: 10 additions & 0 deletions rogue/evaluator_agent/mcp/mcp_evaluator_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,6 +102,16 @@ async def _send_message_to_evaluated_agent(
context_id: str,
message: str,
) -> dict[str, str]:
"""
Sends a message to the evaluated agent and returns the agent's response.
:param message: the text to send to the other agent.
:param context_id: The context ID of the conversation.
Each conversation has a unique context_id. All messages in the conversation
have the same context_id.
:return: A dictionary containing the response from the evaluated agent.
- "response": the response string. If there is no response
from the other agent, the string is empty.
"""
logger.info(
"🔗 Making MCP call to evaluated agent",
extra={
Expand Down
Loading
Loading