[アップデート] AgentCore GatewayがBedrockのInvokeModel APIとモデルのフォールバックに対応したので試してみた

import boto3

client = boto3.client("bedrock-agentcore-control", region_name="us-east-1")
client.create_gateway_target(
    gatewayIdentifier="<GATEWAY_ID>",
    name="bedrock-runtime",
    credentialProviderConfigurations=[{"credentialProviderType": "GATEWAY_IAM_ROLE"}],
    targetConfiguration={"inference": {"connector": {"source": {"connectorId": "bedrock-runtime"}}}},
)

conditions=[{
    "matchModels": {
        "anyOf": [
            {"value": "primary-chat", "operator": "StringEquals"},  # 完全一致
            {"value": "team-*"},  # operator を省略すると StringLike
        ]
    }
}]

actions=[{
    "routeToTarget": {
        "staticRoute": {
            "targetName": "bedrock-mantle",
            "model": "openai.gpt-oss-120b",  # このモデルIDに差し替えて送る
        }
    }
}]

"staticRoute": {
    "targetName": "primary",
    "fallback": {
        "triggerOn": {
            "statusCodes": ["429", "5XX"],
            "errors": ["CONNECTION_ERROR", "FIRST_BYTE_TIMEOUT", "UNROUTABLE"],
        },
        "firstByteTimeoutMilliseconds": 3000,
        "circuitBreaker": {"mode": "ENABLED"},
        "targetFallback": [
            {"targetName": "bedrock-mantle", "model": "openai.gpt-oss-120b"},
        ],
    },
}

import json
import sys

import boto3

from call import GATEWAY_URL

# 接続先をGatewayの/inferenceに向けるだけ。認証はいつものSigV4
client = boto3.client(
    "bedrock-runtime",
    region_name="us-east-1",
    endpoint_url=f"{GATEWAY_URL}/inference",
)

CLAUDE = "us.anthropic.claude-haiku-4-5-20251001-v1:0"
claude_body = json.dumps({
    "anthropic_version": "bedrock-2023-05-31",
    "max_tokens": 128,
    "messages": [{"role": "user", "content": "こんにちは。一言で返して"}],
})

def invoke():
    response = client.invoke_model(modelId=CLAUDE, body=claude_body, contentType="application/json")
    data = json.loads(response["body"].read())
    print(data["model"], data["content"][0]["text"])

def stream():
    body = json.dumps({
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 256,
        "messages": [{"role": "user", "content": "AgentCore Gatewayについて3文で説明して"}],
    })
    response = client.invoke_model_with_response_stream(
        modelId=CLAUDE, body=body, contentType="application/json"
    )
    for event in response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if chunk["type"] == "content_block_delta":
            print(repr(chunk["delta"]["text"]))
        else:
            print(chunk["type"])

if __name__ == "__main__":
    {"invoke": invoke, "stream": stream}[sys.argv[1]]()

uv run invoke_model.py invoke
uv run invoke_model.py stream

anthropic.claude-haiku-4-5-20251001-v1:0 こんにちは！

'ータの'
'流'
'通'
'を効'
'率的'
'に制'
'御します。企'
'業が'
（中略）
'運用性を'
'実'
'現します。'
content_block_stop
message_delta
message_stop

bash set_mode.sh error
uv run call.py primary-chat 3

503  1.21s {"error": {"message": "primary is unavailable"}}
503  1.08s {"error": {"message": "primary is unavailable"}}
503  0.87s {"error": {"message": "primary is unavailable"}}

import time

import boto3

client = boto3.client("bedrock-agentcore-control", region_name="us-east-1")

rule = client.create_gateway_rule(
    gatewayIdentifier="<GATEWAY_ID>",
    priority=100,
    description="primary-chatが失敗したらBedrockのgpt-oss-120bへ切り替える",
    conditions=[
        {"matchModels": {"anyOf": [{"value": "primary-chat", "operator": "StringEquals"}]}}
    ],
    actions=[
        {
            "routeToTarget": {
                "staticRoute": {
                    "targetName": "primary",
                    "fallback": {
                        "targetFallback": [
                            {"targetName": "bedrock-mantle", "model": "openai.gpt-oss-120b"}
                        ],
                    },
                }
            }
        }
    ],
)
while client.get_gateway_rule(gatewayIdentifier="<GATEWAY_ID>", ruleId=rule["ruleId"])["status"] != "ACTIVE":
    time.sleep(5)
print(rule["ruleId"], "ACTIVE")

uv run create_rule.py

950fdf64-bfef-4309-9b76-9bbf9b04c263 ACTIVE

uv run call.py primary-chat 3

200  1.74s ('openai.gpt-oss-120b', 'こんにちは！ご用件や質問がありましたら、遠慮なくどうぞ。😊')
200  1.57s ('openai.gpt-oss-120b', 'こんにちは！ご用件や質問がありましたら、何でもお知らせくださ')
200  1.93s ('openai.gpt-oss-120b', 'こんにちは！今日はどのようなお手伝いができるでしょうか？🙂')

bash set_mode.sh ok
uv run call.py primary-chat 2

200  1.39s ('primary-chat', 'primaryからの応答です')
200  0.90s ('primary-chat', 'primaryからの応答です')

import sys
import time

import boto3

client = boto3.client("bedrock-agentcore-control", region_name="us-east-1")
GATEWAY_ID = "<GATEWAY_ID>"
RULE_ID = sys.argv[1]
breaker = sys.argv[2] if len(sys.argv) > 2 else "ENABLED"

client.update_gateway_rule(
    gatewayIdentifier=GATEWAY_ID,
    ruleId=RULE_ID,
    priority=100,
    description="primary-chatが失敗・3秒無応答ならBedrockのgpt-oss-120bへ切り替える",
    conditions=[
        {"matchModels": {"anyOf": [{"value": "primary-chat", "operator": "StringEquals"}]}}
    ],
    actions=[
        {
            "routeToTarget": {
                "staticRoute": {
                    "targetName": "primary",
                    "fallback": {
                        "firstByteTimeoutMilliseconds": 3000,  # 追加
                        "circuitBreaker": {"mode": breaker},  # 追加
                        "targetFallback": [
                            {"targetName": "bedrock-mantle", "model": "openai.gpt-oss-120b"}
                        ],
                    },
                }
            }
        }
    ],
)
time.sleep(5)
while client.get_gateway_rule(gatewayIdentifier=GATEWAY_ID, ruleId=RULE_ID)["status"] != "ACTIVE":
    time.sleep(5)
print("ACTIVE")

uv run update_rule.py <RULE_ID> DISABLED
bash set_mode.sh slow
uv run call.py primary-chat 3

200  4.57s ('openai.gpt-oss-120b', 'こんにちは！今日はどんなことをお手伝いできますか？😊')
200  4.73s ('openai.gpt-oss-120b', 'こんにちは！どのようなお手伝いが必要ですか？お気軽に教えてく')
200  4.73s ('openai.gpt-oss-120b', 'こんにちは！本日はいかがでしょうか？何かお手伝いできることが')

import sys
import time

import call

results = []
start = time.time()
for i in range(int(sys.argv[1])):
    t = time.time()
    call.call("primary-chat")
    results.append(time.time() - t)
print(f"合計 {time.time() - start:.1f}s / 1回あたり " + " ".join(f"{r:.1f}" for r in results))

# 無効のまま20回呼び出し、ログの取り込みを待ってからその区間の呼び出し回数を数える
START=$(date +%s); uv run breaker_test.py 20; END=$(date +%s)
sleep 60
bash count_primary.sh $START $END

# 有効にして同じことを行う
uv run update_rule.py <RULE_ID> ENABLED
START=$(date +%s); uv run breaker_test.py 20; END=$(date +%s)
sleep 60
bash count_primary.sh $START $END

合計 93.5s / 1回あたり 4.2 4.5 4.7 4.5 4.7 4.9 4.7 4.6 4.3 4.6 5.2 4.6 5.7 4.5 4.8 4.5 4.7 5.1 4.4 4.4
20

合計 70.1s / 1回あたり 4.8 4.9 5.1 4.4 4.5 4.7 4.5 4.4 4.5 4.6 5.0 1.5 1.3 3.1 1.4 1.2 2.7 1.3 1.3 4.7
12

bash set_mode.sh ok
uv run call.py primary-chat

200  1.25s ('primary-chat', 'primaryからの応答です')

import time

import boto3

client = boto3.client("bedrock-agentcore-control", region_name="us-east-1")

rule = client.create_gateway_rule(
    gatewayIdentifier="<GATEWAY_ID>",
    priority=50,
    description="team-で始まるモデル名をBedrockのgpt-oss-120bで処理する",
    conditions=[
        {"matchModels": {"anyOf": [{"value": "team-*", "operator": "StringLike"}]}}
    ],
    actions=[
        {
            "routeToTarget": {
                "staticRoute": {
                    "targetName": "bedrock-mantle",
                    "model": "openai.gpt-oss-120b",
                }
            }
        }
    ],
)
while client.get_gateway_rule(gatewayIdentifier="<GATEWAY_ID>", ruleId=rule["ruleId"])["status"] != "ACTIVE":
    time.sleep(5)
print(rule["ruleId"], "ACTIVE")

404  0.79s {"error":{"message":"Model 'team-standard' not found on any target.","type":"not_found_error","code":"404"}}

team-standard: 200  2.64s ('openai.gpt-oss-120b', 'こんにちは！今日はどのようなお手伝いが必要ですか？気になるこ')
team-fast:     200  1.31s ('openai.gpt-oss-120b', 'こんにちは！ご機嫌いかがですか？何かお手伝いできることがあれ')
primary-chat:  200  0.98s ('primary-chat', 'primaryからの応答です')

import time

import boto3

client = boto3.client("bedrock-agentcore-control", region_name="us-east-1")
GATEWAY_ID = "<GATEWAY_ID>"

for rule in client.list_gateway_rules(gatewayIdentifier=GATEWAY_ID)["gatewayRules"]:
    client.delete_gateway_rule(gatewayIdentifier=GATEWAY_ID, ruleId=rule["ruleId"])
for target in client.list_gateway_targets(gatewayIdentifier=GATEWAY_ID)["items"]:
    client.delete_gateway_target(gatewayIdentifier=GATEWAY_ID, targetId=target["targetId"])
while client.list_gateway_targets(gatewayIdentifier=GATEWAY_ID)["items"]:
    time.sleep(5)
client.delete_gateway(gatewayIdentifier=GATEWAY_ID)
client.delete_api_key_credential_provider(name="fallback-demo-primary-key")

aws lambda delete-function --function-name fallback-demo-primary --region us-east-1
aws logs delete-log-group --log-group-name /aws/lambda/fallback-demo-primary --region us-east-1

aws iam delete-role-policy --role-name fallback-demo-gateway-role --policy-name inference-permissions
aws iam delete-role --role-name fallback-demo-gateway-role
aws iam detach-role-policy --role-name fallback-demo-primary-role \
  --policy-arn arn:aws:iam::aws:policy/service-role/AWSLambdaBasicExecutionRole
aws iam delete-role --role-name fallback-demo-primary-role

uv run cleanup.py
bash cleanup.sh