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
68 lines
2.2 KiB
Python
68 lines
2.2 KiB
Python
"""Middleware that removes malformed Anthropic thinking blocks before model calls."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from collections.abc import Awaitable, Callable
|
|
from typing import Any
|
|
|
|
from langchain.agents.middleware import AgentMiddleware
|
|
from langchain.agents.middleware.types import ModelCallResult, ModelRequest, ModelResponse
|
|
from langchain_anthropic import ChatAnthropic
|
|
from langchain_aws import ChatBedrockConverse
|
|
from langchain_core.messages import AIMessage
|
|
|
|
|
|
def _is_chat_anthropic(model: object) -> bool:
|
|
seen: set[int] = set()
|
|
current = model
|
|
for _ in range(10):
|
|
if isinstance(current, (ChatAnthropic, ChatBedrockConverse)):
|
|
return True
|
|
current_id = id(current)
|
|
if current_id in seen:
|
|
return False
|
|
seen.add(current_id)
|
|
bound = getattr(current, "bound", None)
|
|
if bound is None or bound is current:
|
|
return False
|
|
current = bound
|
|
return False
|
|
|
|
|
|
def _sanitize_messages(messages: list[Any]) -> None:
|
|
for message in messages:
|
|
if not isinstance(message, AIMessage) or not isinstance(message.content, list):
|
|
continue
|
|
content = [
|
|
block
|
|
for block in message.content
|
|
if not (
|
|
isinstance(block, dict)
|
|
and block.get("type") == "thinking"
|
|
and not block.get("thinking")
|
|
)
|
|
]
|
|
if len(content) != len(message.content):
|
|
message.content = content
|
|
|
|
|
|
class SanitizeThinkingBlocksMiddleware(AgentMiddleware):
|
|
"""Drop empty Anthropic thinking blocks before provider validation."""
|
|
|
|
def wrap_model_call(
|
|
self,
|
|
request: ModelRequest,
|
|
handler: Callable[[ModelRequest], ModelResponse],
|
|
) -> ModelCallResult:
|
|
if _is_chat_anthropic(request.model):
|
|
_sanitize_messages(request.messages)
|
|
return handler(request)
|
|
|
|
async def awrap_model_call(
|
|
self,
|
|
request: ModelRequest,
|
|
handler: Callable[[ModelRequest], Awaitable[ModelResponse]],
|
|
) -> Any:
|
|
if _is_chat_anthropic(request.model):
|
|
_sanitize_messages(request.messages)
|
|
return await handler(request)
|