模型和指示

上的預設值create-harness：

aws bedrock-agentcore-control create-harness \
  --harness-name "research-agent" \
  --execution-role-arn "arn:aws:iam::123456789012:role/MyHarnessRole" \
  --system-prompt '[{"text": "You are a research assistant."}]' \
  --tools '[{"type": "agentcore_browser", "name": "browser"}]'

每次調用的覆寫數：

response = client.invoke_harness(
    harnessArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    # These apply only to this call; the harness defaults stay intact
    model={"bedrockModelConfig": {"modelId": "us.anthropic.claude-opus-4-5-20251101-v1:0"}},
    systemPrompt=[{"text": "You are a terse research assistant. One paragraph answers only."}],
    tools=[
        {"type": "agentcore_browser", "name": "browser"},
        {"type": "agentcore_code_interpreter", "name": "code_interpreter"},
    ],
    messages=[{"role": "user", "content": [{"text": "Summarize this paper as a bullet list."}]}],
)

若要永久變更預設值，請使用 update-harness。

建立或更新繫帶時設定預設值：

# Create a project if one does not already exist.
agentcore create

# Add a harness to the project
agentcore add harness \
  --name research-agent \
  --model-id us.anthropic.claude-sonnet-4-6-20250514-v1:0 \
  --system-prompt "You are a research assistant." \
  --tools agentcore-browser

agentcore deploy

在調用時覆寫：

# Switch the model for one call
agentcore invoke --harness research-agent \
  --model-id us.anthropic.claude-opus-4-5-20251101-v1:0 \
  "Summarize this research paper"

# Swap tools for one call
agentcore invoke --harness research-agent \
  --tools agentcore-browser,code-interpreter \
  "Plot the citation counts as a bar chart"

可在調用時覆寫：--model-id、--tools、--system-prompt、--max-iterations--max-tokens、--harness-timeout、--skills、--allowed-tools、、--actor-id。新增 --verbose以列印用於偵錯的原始串流 JSON 事件。

若要永久變更預設值，請編輯app/<name>/harness.json並執行 agentcore deploy。

agentcore 在專案目錄中執行 以開啟 TUI，選取新增，然後選擇繫結 。精靈會逐步引導您完成模型和指令組態。

繼續完成其餘步驟 （環境、記憶體、進階設定） 並確認。然後執行 agentcore deploy 以套用。

使用 AgentCore Identity 註冊 API 金鑰：

aws bedrock-agentcore-control create-api-key-credential-provider \
  --name my-openai-key \
  --api-key "$OPENAI_API_KEY"

切換相同工作階段的提供者：

# Turn 1: Bedrock (native Converse API)
response = client.invoke_harness(
    harnessArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    model={"bedrockModelConfig": {"modelId": "us.anthropic.claude-sonnet-4-5-20250514-v1:0"}},
    messages=[{"role": "user", "content": [{"text": "Analyze this codebase."}]}],
)

# Turn 2: Bedrock Mantle (OpenAI Responses format, no API key needed)
response = client.invoke_harness(
    harnessArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    model={
        "bedrockModelConfig": {
            "modelId": "openai.gpt-4o",
            "apiFormat": "responses",
            "additionalParams": {"reasoning": {"effort": "high"}},
        }
    },
    messages=[{"role": "user", "content": [{"text": "Now suggest fixes for the top three issues."}]}],
)

# Turn 3: OpenAI model via Bedrock Mantle (no API key needed)
response = client.invoke_harness(
    harnessArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    model={
        "openAiModelConfig": {
            "modelId": "gpt-5.4",
            "apiFormat": "responses",
            "endpoint": {"bedrockMantle": {}},
        }
    },
    messages=[{"role": "user", "content": [{"text": "Summarize the fixes as a bullet list."}]}],
)

將 API 金鑰新增至 AgentCore Identity：

agentcore add credential --type api-key --name my-openai-key --api-key $OPENAI_API_KEY
agentcore deploy

使用 Bedrock Mantle 叫用 （回應格式，不需要 API 金鑰）：

SESSION_ID="$(uuidgen)"

# Turn 1: Bedrock Mantle (Responses format)
agentcore invoke --harness my-agent \
  --model-id us.anthropic.claude-sonnet-4-5-20250514-v1:0 \
  --api-format responses \
  --session-id "$SESSION_ID" \
  "Analyze this codebase and identify performance bottlenecks."

直接切換到相同工作階段上的 OpenAI：

# Turn 2: OpenAI direct on the same session
agentcore invoke --harness my-agent \
  --model-provider open_ai \
  --model-id gpt-5.4 \
  --api-key-arn arn:aws:bedrock-agentcore:us-west-2:123456789012:token-vault/default/apikeycredentialprovider/my-openai-key \
  --session-id "$SESSION_ID" \
  "Now suggest fixes for the top three issues."

當您使用 --api-format旗標建立或更新繫帶時，請設定 API 格式：

# Bedrock model through the OpenAI-compatible Responses API (bedrock-mantle endpoint)
agentcore add harness --name research-agent \
  --model-provider bedrock \
  --model-id us.anthropic.claude-sonnet-4-5-20250514-v1:0 \
  --api-format responses
agentcore deploy

# OpenAI model using the Chat Completions API
agentcore add harness --name openai-agent \
  --model-provider open_ai \
  --model-id gpt-5.4 \
  --api-key-arn arn:aws:bedrock-agentcore:us-west-2:123456789012:token-vault/default/apikeycredentialprovider/my-openai-key \
  --api-format chat_completions
agentcore deploy

設定 LiteLLM 模型：

response = client.invoke_harness(
    harnessArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    model={
        "liteLlmModelConfig": {
            "modelId": "gemini/gemini-2.5-pro",
            "apiKeyArn": "arn:aws:bedrock-agentcore:us-west-2:123456789012:token-vault/default/apikeycredentialprovider/my-gemini-key",
        }
    },
    messages=[{"role": "user", "content": [{"text": "Summarize this paper."}]}],
)

使用 設定 LiteLLM 模型--model-provider lite_llm：

agentcore add harness --name research-agent \
  --model-provider lite_llm \
  --model-id gemini/gemini-2.5-pro \
  --api-key-arn arn:aws:bedrock-agentcore:us-west-2:123456789012:token-vault/default/apikeycredentialprovider/my-gemini-key
agentcore deploy

使用 到達與 OpenAI 相容的閘道--api-base，並使用 傳遞提供者特定的參數--additional-params：

agentcore add harness --name proxy-agent \
  --model-provider lite_llm \
  --model-id openai/gpt-5.4 \
  --api-base https://my-llm-gateway.example.com/v1 \
  --api-key-arn arn:aws:bedrock-agentcore:us-west-2:123456789012:token-vault/default/apikeycredentialprovider/my-gateway-key \
  --additional-params '{"timeout": 30}'
agentcore deploy