From e05127b38063be741ccbc89de3ce3f1183f9b9da Mon Sep 17 00:00:00 2001 From: Logan Kleier Date: Mon, 20 Jul 2026 12:14:07 -0700 Subject: [PATCH] fix(gcp-to-aws): stop recommending classic Bedrock Agents (maintenance mode, closed to new customers 2026-07-30) --- .../references/design-refs/ai-gemini-to-bedrock.md | 2 +- .../references/design-refs/ai-openai-to-bedrock.md | 4 ++-- .../references/phases/clarify/clarify-ai.md | 12 +++++++----- .../gcp-to-aws/references/phases/clarify/clarify.md | 4 ++-- .../gcp-to-aws/references/phases/design/design-ai.md | 2 +- 5 files changed, 13 insertions(+), 11 deletions(-) diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-gemini-to-bedrock.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-gemini-to-bedrock.md index 1b2458c7..fbc545fd 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-gemini-to-bedrock.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-gemini-to-bedrock.md @@ -24,7 +24,7 @@ Gemini 3.5 Flash is now GA (May 2026) — the current flagship Flash model. Gemi - Claude Sonnet 4.6 / Opus 4.x lead on real-world agentic tasks (GDPval evaluation) — the gap between benchmarks and production agent reliability is real - Claude prompt caching (90% savings on repeated content) has no Gemini equivalent - Claude function calling remains best-in-class for complex multi-turn tool use -- AWS ecosystem integration (Bedrock Agents, Knowledge Bases, Guardrails) has no Gemini equivalent +- AWS ecosystem integration (AgentCore, Knowledge Bases, Guardrails) has no Gemini equivalent **Migration case by tier:** diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-openai-to-bedrock.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-openai-to-bedrock.md index aa20989c..700f38a8 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-openai-to-bedrock.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-openai-to-bedrock.md @@ -201,9 +201,9 @@ Assistants API and Responses API are different surfaces. Do not treat all Assist → Mantle Responses API with tool use is viable. Moderate code migration (1-2 weeks) to adapt tool definitions and run lifecycle. **4. App uses Assistants API with file search, vector stores, code interpreter, persistent Assistant objects, or complex run lifecycle management** -→ Do not recommend Mantle. Evaluate: Bedrock Agents (sessions, action groups, knowledge bases) for full agentic replacement (2-4 week migration), or app-managed orchestration if the team prefers to own state. +→ Do not recommend Mantle. Evaluate: Bedrock AgentCore (Harness sessions/memory, action groups as MCP tools via Gateway, gateway-fronted knowledge bases) for full agentic replacement (2-4 week migration), or app-managed orchestration if the team prefers to own state. Never target classic Bedrock Agents (`bedrock-agent`): it is in maintenance mode and closed to new customers as of July 30, 2026. -**When to prefer Converse API over Mantle:** If you need Bedrock-specific features (Guardrails, Knowledge Bases, prompt caching, Bedrock Agents integration) or your target region doesn't have Mantle. Mantle is the fastest path; Converse API is the most feature-complete path. +**When to prefer Converse API over Mantle:** If you need Bedrock-specific features (Guardrails, Knowledge Bases, prompt caching, AgentCore integration) or your target region doesn't have Mantle. Mantle is the fastest path; Converse API is the most feature-complete path. ### GPT-5.4 → Claude Sonnet 4.6 diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify-ai.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify-ai.md index 1a4a0d22..69b7aaac 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify-ai.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify-ai.md @@ -136,14 +136,16 @@ _Skip when:_ Auto-detection fully resolves the framework(s). Use detected value( | Answer | Recommendation Impact | Migration Effort | Timeline | | ---------------------------------- | --------------------------------------------------------------------------------------------------------- | ----------------- | ---------------------------------------------------- | -| A) No framework — direct API calls | Swap SDK calls to Bedrock SDK; evaluate Bedrock Agents if planning agentic | Low | 1–3 weeks depending on call sites | +| A) No framework — direct API calls | Swap SDK calls to Bedrock SDK; evaluate AgentCore (Harness) if planning agentic | Low | 1–3 weeks depending on call sites | | B) LLM router/gateway | Add Bedrock as provider in gateway config; no app code changes; verify SigV4 auth | Minimal | Hours to 1–3 days | | C) LangChain / LangGraph | Provider swap via `ChatBedrock`; chains/graphs/tools preserved; validate tool schemas | Low | 1–3 days; 1 week if complex graphs | | D) Multi-agent framework | Path 1: Keep framework, swap LLM provider (lower effort). Path 2: Migrate to Bedrock multi-agent (deeper) | Medium | Path 1: 3–5 days; Path 2: 2–4 weeks | -| E) OpenAI Agents SDK | Highest effort; tightly coupled to OpenAI API; recommend Bedrock Agents or LangGraph as portable step | High | 2–4 weeks | -| F) MCP / A2A | Bedrock Agents supports MCP natively; A2A interop available; recommend Bedrock Agents as orchestration | Low–Medium | 3–5 days MCP; 1–2 weeks A2A | +| E) OpenAI Agents SDK | Highest effort; tightly coupled to OpenAI API; recommend AgentCore (Harness, or Runtime for code loops) | High | 2–4 weeks | +| F) MCP / A2A | AgentCore supports MCP natively (Gateway exposes tools as MCP); A2A interop; recommend AgentCore | Low–Medium | 3–5 days MCP; 1–2 weeks A2A | | G) Voice platform | If platform supports Bedrock natively → config change; otherwise evaluate Nova 2 Sonic | Minimal to Medium | Hours if native; 2–3 weeks if Nova 2 Sonic migration | +> **Never recommend classic Bedrock Agents (`bedrock-agent`) as a migration target.** It is in maintenance mode and closed to new customers as of July 30, 2026 ([AWS announcement](https://aws.amazon.com/about-aws/whats-new/2026/06/aws-service-availability/)). Agentic targets are AgentCore Harness (config-based, default) or AgentCore Runtime (code-defined loops) — consistent with Q23–Q26. + ### Combination Logic | Combination | Approach | @@ -152,7 +154,7 @@ _Skip when:_ Auto-detection fully resolves the framework(s). Use detected value( | B only | Quick win — gateway config change, skip SDK migration steps | | B + any other | Gateway swap is the quick win; assess framework migration as separate workstream | | C + A | Two workstreams: LangChain provider swap (fast) + direct call migration (slower) | -| D + F | Complex — multi-agent with MCP tooling; recommend Bedrock Agents to unify orchestration and tools | +| D + F | Complex — multi-agent with MCP tooling; recommend AgentCore to unify orchestration and tools | | E + anything | E is the long pole; plan timeline around Agents SDK migration; other layers may be quick wins | | Multiple frameworks (C+D, C+E, etc.) | Assess independently; prioritize by traffic volume or business criticality; consolidate post-migration | @@ -227,7 +229,7 @@ Interpret → `ai_priority`. Default: E → `"balanced"`. | Extended thinking / Chain-of-thought | Claude Sonnet 4.6 with extended thinking mode; Claude Opus 4.6 for most complex reasoning | | Prompt caching | Claude Sonnet 4.6 with prompt caching enabled; cost savings analysis included. **Caveat:** caching only helps for long, repeated context (system prompts, documents). Per-model minimum token thresholds (~1K–4K tokens) and TTL apply — short prompts won't cache. Verify current minimums at docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html before recommending. | | RAG optimization | Amazon Bedrock Knowledge Bases recommended alongside model; Titan Embeddings for vector store | -| Agentic workflows | Claude Sonnet 4.6 with Bedrock Agents; multi-agent orchestration guidance included | +| Agentic workflows | Claude Sonnet 4.6 with AgentCore (Harness); multi-agent orchestration guidance included | | Real-time speed (< 500ms) | Claude Haiku 4.5 or Nova Micro; streaming response guidance included | | Multimodal with image generation | Claude Sonnet 4.6 (vision) + Amazon Nova Canvas for generation | | Real-time conversational speech | Amazon Nova 2 Sonic recommended for speech-to-speech; latency guidance included | diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify.md index c5eb3227..bfeb7b45 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify.md @@ -507,8 +507,8 @@ If user opts in, present Q-E1–Q-E2 (defined in **Category E — Migration Post | CCPA / CPRA | Q2 = G (CCPA / CPRA) | Consumer privacy, logging/retention, data-inventory posture; confirm regions with legal review | | Gateway-only AI | Q14 = B only (LLM router/gateway) | Config change only; skip SDK migration | | LangChain/LangGraph AI | Q14 includes C | Provider swap via ChatBedrock; 1–3 days | -| OpenAI Agents SDK | Q14 includes E | Highest AI effort; Bedrock Agents; 2–4 weeks | -| Multi-agent + MCP | Q14 = D + F | Bedrock Agents to unify orchestration + MCP | +| OpenAI Agents SDK | Q14 includes E | Highest AI effort; AgentCore (Harness/Runtime); 2–4 weeks | +| Multi-agent + MCP | Q14 = D + F | AgentCore to unify orchestration + MCP (Gateway) | | Voice platform AI | Q14 includes G | Check native Bedrock support; Nova 2 Sonic if needed | | GPT-5.5 migration | Q19 = GPT-5.5 | Claude Opus 4.6 — Bedrock 17% cheaper on output; or Sonnet 4.6 for 53% savings | | GPT-5.5 Pro migration | Q19 = GPT-5.5 Pro | Nova 2 Pro — 95% cheaper on Bedrock | diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/design/design-ai.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/design/design-ai.md index a2bc8240..207ec341 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/design/design-ai.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/design/design-ai.md @@ -230,7 +230,7 @@ For each capability in `integration.capabilities_summary` that is `true`, check | Batch Processing | BatchPredictionJob | Batch Inference (async) | Partial | | Fine-tuning | Vertex AI tuning | Bedrock Custom Model | Partial | | Grounding / RAG | Vertex AI Search & RAG | Bedrock Knowledge Bases | Full | -| Agents | Vertex AI Agent Builder | Bedrock Agents | Full | +| Agents | Vertex AI Agent Builder | Bedrock AgentCore (Harness) | Full | Record `capability_gaps[]` for any Partial or None parity.