Setting the file. One moment.
Subchapter 25.72
references/vendored/ai/design-ref-harness.mdMarkdown9 KBView on GitHub
Canonical AgentCore Harness design reference. Source-cloud agnostic: Harness is the target, and the incremental-migration shape does not vary by source cloud. Vendored into each consuming skill as and kept byte-identical by ; edit HERE, then run .
references/vendored/ai/design-ref-harness.mdshared:checkshared:syncLoaded by design-ai.md Step 0.6 when agentic_profile.is_agentic == true AND ai_constraints.agentic.migration_approach == "harness".
Prerequisites: references/vendored/ai/ai-migration-guardrails.md must already be loaded (Step 0.6 loads it before this file). Do NOT duplicate regional caveats, pricing rules, or effort estimation rules here.
Recommend Harness when:
Do NOT recommend Harness as primary path when:
For these cases: fall back to retarget path (standard model-swap design in Parts 1–6 of design-ai.md).
Map discovered elements to Harness configuration:
| Discovered element | Harness config | Notes |
|---|---|---|
bedrock_models[0].aws_model_id | model (default) | Primary Bedrock model from Part 1 model selection |
agents[0].role or system prompt from code | systemPrompt | Extract from code if possible; placeholder if not |
Tools with transport: "mcp" | tools[]: {"type": "remote_mcp", "config": {"remoteMcp": {"url": "..."}}} | Direct MCP server connection |
Tools with transport: "api" | tools[]: {"type": "remote_mcp"} or {"type": "agentcore_gateway"} | Wrap API as MCP server, or use Gateway for centralized auth |
Tools with transport: "function" (browser/web) | tools[]: {"type": "agentcore_browser"} | Built-in browser tool |
Tools with transport: "function" (code execution) | tools[]: {"type": "agentcore_code_interpreter"} | Built-in code interpreter |
Tools with transport: "function" (other) | tools[]: {"type": "inline_function", "config": {...}} | Client-side execution; Harness pauses and returns call to your code |
memory_requirement: "session" | Default behavior | Harness sessions are stateful by default (microVM per session) |
memory_requirement: "cross_session" | AgentCore Memory service | Configure memory persistence across sessions |
memory_requirement: "none" | No memory config needed | Stateless invocations |
Tool mapping decision:
For each tool in tool_manifest[]:
├── transport == "mcp" → remote_mcp (direct connection)
├── transport == "api"
│ ├── auth_hint == "oauth" or multiple tools share auth → agentcore_gateway (centralized auth)
│ └── auth_hint == "api_key" or "none" → remote_mcp (simpler, wrap as MCP)
├── transport == "function"
│ ├── tool does web browsing/scraping → agentcore_browser
│ ├── tool executes code/scripts → agentcore_code_interpreter
│ └── other local function → inline_function (client-side)
└── transport == "unknown" → inline_function (safest default; client controls execution)If ai_constraints.agentic.incremental_migration == true:
--model-provider open_ai --model-id gpt-4o)--model-id per invocation with Bedrock model from designtest_comparison.py against both models on same sessionWhen Harness path is selected, write this to aws-design-ai.json:
{
"agentic_design": {
"migration_approach": "harness",
"harness_config": {
"name": "from agentic_profile.agents[0].agent_id",
"model_id": "from bedrock_models[0].aws_model_id",
"system_prompt": "extracted from code or placeholder",
"tools": [
{
"type": "remote_mcp|agentcore_browser|agentcore_code_interpreter|agentcore_gateway|inline_function",
"name": "tool name from tool_manifest",
"config": {}
}
],
"memory_enabled": true,
"memory_type": "session|cross_session",
"incremental_migration": true,
"source_model_provider": "open_ai|google",
"source_model_id": "from models[0].model_id",
"policy_recommended": true
},
"regional_fit": "available|unavailable",
"deployment_regions": ["from preferences.json target_region"],
"warnings": []
}
}Field rules:
harness_config.name — Derived from first agent’s agent_id. Use kebab-case.harness_config.model_id — The Bedrock model ID selected in Part 1 (e.g., us.anthropic.claude-sonnet-5)harness_config.system_prompt — Extracted from agent code if available; otherwise "[TODO: Add system prompt from your agent definition]"harness_config.tools — Mapped from tool_manifest[] using the tool mapping decision tree aboveharness_config.source_model_provider — "open_ai" or "google" based on summary.ai_sourceharness_config.source_model_id — Original model ID from models[0].model_idharness_config.policy_recommended — Set to true when tool_manifest[] contains tools with write operations (database mutations, API calls, file writes). Recommend AgentCore Policy for tool-call guardrails.regional_fit — Result of Step 0.5 regional check for AgentCore Harness in target region. Harness is GA in all commercial regions — this should almost always be "available".After the standard model comparison summary from design-ai.md, add:
Agentic Migration: AgentCore Harness
- Approach: Config-based agent deployment on AgentCore
- Tools mapped: [count] tools → [types breakdown]
- Memory: [session/cross-session/none]
- Incremental migration: [yes/no]
- Regional availability: [available/preview in target region]
- Estimated effort: [range] depending on [drivers from guardrails]