diff --git a/migrate/plugins/migration-to-aws/agents/llm2bedrock-prompt-evaluator.md b/migrate/plugins/migration-to-aws/agents/llm2bedrock-prompt-evaluator.md index 30da391e..8d67b679 100644 --- a/migrate/plugins/migration-to-aws/agents/llm2bedrock-prompt-evaluator.md +++ b/migrate/plugins/migration-to-aws/agents/llm2bedrock-prompt-evaluator.md @@ -685,7 +685,7 @@ The eval schema fields (validated, extras rejected): - `no_golden_cases: true` — when `total_cases == 0` (T2-2 abort / paste / vision-no-images / embeddings paths). Tells T2-6 to render "no quality data" instead of "0% pass rate". - Free-form addenda — manual-review notes, per-layer status hints. Keep total `notes` under ~500 chars to fit dashboards. - **`live_source_baseline`** — MANDATORY. `true` ONLY when §9 produced live side-by-side responses for at least one prompt. `false` when §9 was skipped (no source key) or every live call failed. The report banner depends on this flag. -- **`judge_model`** — MANDATORY. Identifier of the LLM running THIS agent (e.g. `claude-opus-4-7`, `claude-haiku-4-5-20251001-v1:0`). The report discloses it so readers can assess same-family bias risk against the target Bedrock model. If you cannot identify the exact ID, pass `"unknown"` — never drop the field. +- **`judge_model`** — MANDATORY. Identifier of the LLM running THIS agent (e.g. `claude-opus-4-8`, `claude-haiku-4-5-20251001-v1:0`). The report discloses it so readers can assess same-family bias risk against the target Bedrock model. If you cannot identify the exact ID, pass `"unknown"` — never drop the field. - **`source_baseline_quality`** — `'good'` (live baseline ran and looked fine), `'poor'` (live baseline ran but the source model's own output looked degraded — empty responses, error bodies, or obvious wrong-version behavior; per §9 step 3), or `'unknown'` (no live baseline ran). The orchestrator surfaces `'poor'` at the quality gate. `live_source_baseline` and `judge_model` are MANDATORY — always include both, every time, even if uncertain. Never omit them. @@ -704,7 +704,7 @@ When §7 routed past §10–§13 with `total_cases == 0` (no golden dataset to e "failures": 1, "notes": "live_source_baseline_used_model: \n1 prompt needs manual review — see notes for details.", "live_source_baseline": true, - "judge_model": "claude-opus-4-7", + "judge_model": "claude-opus-4-8", "source_baseline_quality": "good" } ``` @@ -723,7 +723,7 @@ When `total_cases == 0` (T2-2 abort / paste / vision-no-images / embeddings path "failures": 0, "notes": "no_golden_cases: true\nreason: T2-2 reported total_golden_cases=0; layers 1/2 passed but no quality data to score.", "live_source_baseline": false, - "judge_model": "claude-opus-4-7", + "judge_model": "claude-opus-4-8", "source_baseline_quality": "unknown" } ``` diff --git a/migrate/plugins/migration-to-aws/fixtures/migration-report-reference.html b/migrate/plugins/migration-to-aws/fixtures/migration-report-reference.html index 6d3f1508..31bafcff 100644 --- a/migrate/plugins/migration-to-aws/fixtures/migration-report-reference.html +++ b/migrate/plugins/migration-to-aws/fixtures/migration-report-reference.html @@ -334,7 +334,7 @@

High-level service mapping

Cloud SQL PostgreSQLRDS PostgreSQL db.t4g.microTailored to your setup (single-AZ) Cloud StorageS3Standard pairing BigQueryDeferred — specialist engagementSpecialist required - Vertex AI / GeminiBedrock Claude Sonnet 4.6Tailored to your setup (quality priority) + Vertex AI / GeminiBedrock Claude Sonnet 5Tailored to your setup (quality priority) Vertex AI ImagenBedrock Nova CanvasTailored to your setup @@ -749,7 +749,7 @@

Model mappings

GCP AI models mapped to Amazon Bedrock targets. GCP modelBedrock targetWorkloadComplexity - gemini-2.5-flashanthropic.claude-sonnet-4-6Text generation, structured outputMedium + gemini-2.5-flashanthropic.claude-sonnet-5Text generation, structured outputMedium imagen-3.0-generate-001amazon.nova-canvas-v1:0Image generation (~500/mo)Medium @@ -759,13 +759,13 @@

Model cost comparison

Bedrock model options vs current GCP AI spend ($1,250/mo). Bedrock modelMonthly est.vs GCP ($1,250/mo)QualityNotes - Claude Sonnet 4.6 (recommended)$780-38%HighQuality priority (Q16); selected target + Claude Sonnet 5 (recommended)$780-38%HighQuality priority (Q16); selected target Claude Haiku 4.5$260-79%Medium-HighBalance of cost and quality Nova Lite v1$14-99%MediumBackup if A/B test passes quality bar -

Recommended model token breakdown (Claude Sonnet 4.6)

+

Recommended model token breakdown (Claude Sonnet 5)

@@ -791,7 +791,7 @@

Code changes

Production readiness checklist

- + diff --git a/migrate/plugins/migration-to-aws/skills/agent-advisor/references/diagram/build-diagram.md b/migrate/plugins/migration-to-aws/skills/agent-advisor/references/diagram/build-diagram.md index b0015e84..a345b7e3 100644 --- a/migrate/plugins/migration-to-aws/skills/agent-advisor/references/diagram/build-diagram.md +++ b/migrate/plugins/migration-to-aws/skills/agent-advisor/references/diagram/build-diagram.md @@ -61,7 +61,7 @@ the same topology discipline as Path 1: - **Primary request flow (solid edges):** User → the app's entry surface (the runtime hosting the migrated app + its `/invocations` entrypoint) → the app's orchestration layer (e.g. LangChain) → the Bedrock target model. Show the provider swap explicitly — label the model - node with the migrated target (e.g. "Bedrock: Claude Sonnet 4.6") and note the source it + node with the migrated target (e.g. "Bedrock: Claude Sonnet 5") and note the source it replaced where useful (e.g. "was: OpenAI gpt-3.5-turbo"). - **State / memory (solid edge to a store):** if the app has conversation memory, show it as its own node mapped to its AWS target (e.g. in-process `ConversationBufferWindowMemory` → diff --git a/migrate/plugins/migration-to-aws/skills/agent-advisor/references/phases/generate/generate.md b/migrate/plugins/migration-to-aws/skills/agent-advisor/references/phases/generate/generate.md index 67953329..c01f58ef 100644 --- a/migrate/plugins/migration-to-aws/skills/agent-advisor/references/phases/generate/generate.md +++ b/migrate/plugins/migration-to-aws/skills/agent-advisor/references/phases/generate/generate.md @@ -66,7 +66,7 @@ summary first, technical detail after (single layered doc — do not fork by aud `$RUN_DIR/recommendation.md`. Append the freshness footer. For `migrate`: also fill Section 9 (Bedrock model) with the **coarse family mapping** -(e.g. "GPT-4o → Claude Sonnet 4.6 family") and a note that detailed pricing/TCO come from the +(e.g. "GPT-4o → Claude Sonnet 5 family") and a note that detailed pricing/TCO come from the migration plugins — no dollar figures. Section 10 (cost magnitude) presents the per-unit target-state bands from estimate.json and notes that the migration TCO comparison and current-spend delta are produced by the migration plugins. diff --git a/migrate/plugins/migration-to-aws/skills/agent-advisor/references/phases/poc/poc.md b/migrate/plugins/migration-to-aws/skills/agent-advisor/references/phases/poc/poc.md index d0348196..fa6b969b 100644 --- a/migrate/plugins/migration-to-aws/skills/agent-advisor/references/phases/poc/poc.md +++ b/migrate/plugins/migration-to-aws/skills/agent-advisor/references/phases/poc/poc.md @@ -126,7 +126,7 @@ contract but never replaces it. Resolve each unit's model and `api_path` from IT never take one unit's decision from another or from a run-wide plan scalar. For each unit, `design.json.units[].model_recommendation.model` carries the selected -path-specific model ID (for example, `anthropic.claude-sonnet-4-6`). +path-specific model ID (for example, `anthropic.claude-sonnet-5`). `model_recommendation.invocation_model_id` is the exact account-callable ID only after CRIS resolution. These identities must remain separate. @@ -155,11 +155,11 @@ The block's `target_bedrock_model` and path should equal `model_recommendation` validated them. If they differ, stop and return to Model Recommend; do not choose one silently. **Strip environment annotations from the model id.** The running assistant's model name may -carry a context-window annotation like `[1m]` (e.g. `us.anthropic.claude-sonnet-4-6[1m]`). +carry a context-window annotation like `[1m]` (e.g. `us.anthropic.claude-sonnet-5[1m]`). That suffix is a harness label, NOT a valid Bedrock model/inference-profile id — a Bedrock call with it 404s. Before writing the id into any generated file, strip any trailing `[...]` bracket annotation. The id you emit must be exactly what Bedrock accepts (e.g. -`us.anthropic.claude-sonnet-4-6`). If unsure of the exact id, use the `TODO: verify model id` +`us.anthropic.claude-sonnet-5`). If unsure of the exact id, use the `TODO: verify model id` placeholder rather than a bracket-tagged string. **Single-unit path:** when `units[]` length is 1, the above logic applies to the one unit — diff --git a/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_build_diagram.py b/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_build_diagram.py index 08b86390..bf5245c1 100644 --- a/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_build_diagram.py +++ b/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_build_diagram.py @@ -34,7 +34,7 @@ def test_service_labels_include_payments_and_registry(): def test_payments_registry_render_in_diagram(): out = build_diagram.render_mermaid( - "agentcore", ["identity", "payments", "registry"], "claude_sonnet_4_6", "harness") + "agentcore", ["identity", "payments", "registry"], "claude_sonnet_5", "harness") assert "Payments" in out and "Registry" in out @@ -58,11 +58,11 @@ def test_resolve_services_filters_unknown_and_dedupes(): def test_mermaid_has_runtime_model_and_services(): out = build_diagram.render_mermaid( - "agentcore", ["identity", "memory"], "claude_sonnet_4_6", "harness") + "agentcore", ["identity", "memory"], "claude_sonnet_5", "harness") assert out.startswith("flowchart TD") assert "AgentCore Runtime" in out assert "harness" in out.lower() - assert "claude_sonnet_4_6" in out + assert "claude_sonnet_5" in out assert "Identity" in out and "Memory" in out assert "migration-to-aws" not in out # no handoff for agentcore @@ -71,7 +71,7 @@ def test_mermaid_model_is_solid_edge_services_are_dotted(): # Topology: the model is a downstream call (solid invoke edge); services are # cross-cutting capabilities attached with a dotted edge into a subgraph. out = build_diagram.render_mermaid( - "agentcore", ["identity", "memory"], "claude_sonnet_4_6", "harness") + "agentcore", ["identity", "memory"], "claude_sonnet_5", "harness") assert "rt -->|invoke| model" in out # model = solid data-flow edge assert 'subgraph svcs["AgentCore services"]' in out assert "rt -.-> svcs" in out # services = dotted attachment @@ -81,31 +81,31 @@ def test_mermaid_model_is_solid_edge_services_are_dotted(): def test_mermaid_no_services_no_subgraph(): out = build_diagram.render_mermaid( - "agentcore", [], "claude_sonnet_4_6", "harness") + "agentcore", [], "claude_sonnet_5", "harness") assert "subgraph" not in out assert "rt -->|invoke| model" in out def test_mermaid_adds_handoff_note_for_ecs(): - out = build_diagram.render_mermaid("ecs", [], "claude_sonnet_4_6", None) + out = build_diagram.render_mermaid("ecs", [], "claude_sonnet_5", None) assert "Amazon ECS (Fargate)" in out assert "migration-to-aws" in out def test_mermaid_deterministic(): a = build_diagram.render_mermaid("agentcore", ["identity", "memory"], - "claude_sonnet_4_6", "harness") + "claude_sonnet_5", "harness") b = build_diagram.render_mermaid("agentcore", ["identity", "memory"], - "claude_sonnet_4_6", "harness") + "claude_sonnet_5", "harness") assert a == b def test_ascii_contains_runtime_model_services(): out = build_diagram.render_ascii( - "agentcore", ["identity", "memory"], "claude_sonnet_4_6", "harness") + "agentcore", ["identity", "memory"], "claude_sonnet_5", "harness") assert "AgentCore Runtime" in out assert "harness" in out.lower() - assert "claude_sonnet_4_6" in out + assert "claude_sonnet_5" in out assert "- Identity" in out and "- Memory" in out assert "migration-to-aws" not in out # Model is on the primary flow; services are attached, not call targets. @@ -114,7 +114,7 @@ def test_ascii_contains_runtime_model_services(): def test_ascii_handoff_for_ecs(): - out = build_diagram.render_ascii("ecs", [], "claude_sonnet_4_6", None) + out = build_diagram.render_ascii("ecs", [], "claude_sonnet_5", None) assert "Amazon ECS" in out assert "migration-to-aws" in out @@ -122,21 +122,21 @@ def test_ascii_handoff_for_ecs(): def test_ascii_no_handoff_for_standard_lambda(): # Standard Lambda is a self-contained Build target (function skeleton), not a # heavy-infrastructure handoff — no migration-to-aws note. - out = build_diagram.render_ascii("lambda", [], "claude_sonnet_4_6", None) + out = build_diagram.render_ascii("lambda", [], "claude_sonnet_5", None) assert "AWS Lambda" in out assert "migration-to-aws" not in out def test_ascii_deterministic(): - a = build_diagram.render_ascii("eks", ["identity"], "claude_sonnet_4_6", None) - b = build_diagram.render_ascii("eks", ["identity"], "claude_sonnet_4_6", None) + a = build_diagram.render_ascii("eks", ["identity"], "claude_sonnet_5", None) + b = build_diagram.render_ascii("eks", ["identity"], "claude_sonnet_5", None) assert a == b def test_build_diagram_end_to_end(): result = {"verdict": "agentcore", "deployment_model": "harness", "agentcore_services": ["identity"], - "model_recommendation": {"model": "claude_sonnet_4_6"}} + "model_recommendation": {"model": "claude_sonnet_5"}} out = build_diagram.build_diagram(result, {}) assert "flowchart TD" in out["mermaid"] assert "AgentCore Runtime" in out["ascii"] @@ -151,7 +151,7 @@ def test_build_diagram_no_viable(): def test_golden_agentcore_full(): result = {"verdict": "agentcore", "deployment_model": "framework_on_runtime", "agentcore_services": ["identity", "observability", "memory", "gateway"], - "model_recommendation": {"model": "claude_sonnet_4_6"}} + "model_recommendation": {"model": "claude_sonnet_5"}} out = build_diagram.build_diagram(result, {}) # runtime + deployment model + all four services + model, no handoff assert "framework_on_runtime" in out["mermaid"] @@ -163,7 +163,7 @@ def test_golden_agentcore_full(): def test_golden_lambda_microvms_no_services_no_handoff(): result = {"verdict": "lambda_microvms", "deployment_model": None, "agentcore_services": [], - "model_recommendation": {"model": "claude_sonnet_4_6"}} + "model_recommendation": {"model": "claude_sonnet_5"}} out = build_diagram.build_diagram(result, {}) assert "Lambda MicroVMs" in out["mermaid"] assert "migration-to-aws" not in out["mermaid"] # MicroVMs is not a handoff runtime @@ -172,7 +172,7 @@ def test_golden_lambda_microvms_no_services_no_handoff(): def test_golden_ecs_has_handoff(): result = {"verdict": "ecs", "deployment_model": None, "agentcore_services": ["identity"], - "model_recommendation": {"model": "claude_sonnet_4_6"}} + "model_recommendation": {"model": "claude_sonnet_5"}} out = build_diagram.build_diagram(result, {}) assert "migration-to-aws" in out["mermaid"] assert "migration-to-aws" in out["ascii"] @@ -181,7 +181,7 @@ def test_golden_ecs_has_handoff(): def test_golden_co_recommend_renders_chosen(): result = {"verdict": "co_recommend", "co_recommend": ["ecs", "eks"], "deployment_model": None, "agentcore_services": [], - "model_recommendation": {"model": "claude_sonnet_4_6"}} + "model_recommendation": {"model": "claude_sonnet_5"}} out = build_diagram.build_diagram(result, {"chosen_runtime": "eks"}) assert "Amazon EKS" in out["mermaid"] assert "migration-to-aws" in out["mermaid"] # eks is a handoff runtime @@ -192,7 +192,7 @@ def _two_unit_design(): "units": [ {"id": "chat-agent", "workload_class": "agent_session", "verdict": "agentcore", - "model_recommendation": {"model": "claude_sonnet_4_6"}}, + "model_recommendation": {"model": "claude_sonnet_5"}}, {"id": "summarizer", "workload_class": "batch", "verdict": "batch", "model_recommendation": None}, ], @@ -219,7 +219,7 @@ def _consolidated_design(): "units": [ {"id": "chat-agent", "workload_class": "agent_session", "verdict": "agentcore", "effective_runtime": "ecs", - "model_recommendation": {"model": "claude_sonnet_4_6"}}, + "model_recommendation": {"model": "claude_sonnet_5"}}, {"id": "summarizer", "workload_class": "batch", "verdict": "batch", "effective_runtime": "ecs", "model_recommendation": None}, @@ -279,10 +279,10 @@ def _mixed_gateway_design(): "units": [ {"id": "orchestrator", "workload_class": "agent_session", "verdict": "agentcore", "coupling": {"mode": "a2a", "interacts_with": ["tool-agent"]}, - "model_recommendation": {"model": "claude_sonnet_4_6"}}, + "model_recommendation": {"model": "claude_sonnet_5"}}, {"id": "tool-agent", "workload_class": "agent_session", "verdict": "agentcore", "coupling": {"mode": "none", "interacts_with": []}, - "model_recommendation": {"model": "claude_sonnet_4_6"}}, + "model_recommendation": {"model": "claude_sonnet_5"}}, {"id": "loner", "workload_class": "batch", "verdict": "batch", "coupling": {"mode": "none", "interacts_with": []}, "model_recommendation": None}, @@ -312,7 +312,7 @@ def _mixed_queue_and_gateway_design(): "units": [ {"id": "api-a", "workload_class": "agent_session", "verdict": "agentcore", "coupling": {"mode": "api", "interacts_with": ["api-b"]}, - "model_recommendation": {"model": "claude_sonnet_4_6"}}, + "model_recommendation": {"model": "claude_sonnet_5"}}, {"id": "api-b", "workload_class": "service", "verdict": "fargate", "coupling": {"mode": "none", "interacts_with": []}, "model_recommendation": None}, @@ -349,11 +349,11 @@ def test_single_unit_design_falls_back_to_legacy_render(): legacy = build_diagram.build_diagram( {"verdict": "agentcore", "agentcore_services": [], - "model_recommendation": {"model": "claude_sonnet_4_6"}}, {}) + "model_recommendation": {"model": "claude_sonnet_5"}}, {}) unitized = build_diagram.build_diagram( {"verdict": "agentcore", "agentcore_services": [], - "model_recommendation": {"model": "claude_sonnet_4_6"}}, {}, design=d) + "model_recommendation": {"model": "claude_sonnet_5"}}, {}, design=d) assert unitized["mermaid"] == legacy["mermaid"], \ "collapse invariant: one unit renders exactly the legacy diagram" @@ -366,7 +366,7 @@ def _temporal_design(): "model_recommendation": None}, {"id": "doc-chat", "workload_class": "agent_session", "verdict": "agentcore", - "model_recommendation": {"model": "claude_sonnet_4_6"}, + "model_recommendation": {"model": "claude_sonnet_5"}, "task_queue": "agent-tasks"}, {"id": "ocr", "workload_class": "batch", "verdict": "batch", "model_recommendation": None, @@ -389,7 +389,7 @@ def _temporal_design_multi_fleet(): {"id": "fleet-b", "workload_class": "temporal_worker_poll", "verdict": "ecs", "queues": ["batch-tasks"], "model_recommendation": None}, {"id": "chat", "workload_class": "agent_session", "verdict": "agentcore", - "model_recommendation": {"model": "claude_sonnet_4_6"}, + "model_recommendation": {"model": "claude_sonnet_5"}, "task_queue": "agent-tasks"}, {"id": "ocr", "workload_class": "batch", "verdict": "batch", "model_recommendation": None, "task_queue": "batch-tasks"}, diff --git a/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_collapse_invariant.py b/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_collapse_invariant.py index 102db80c..170f56a3 100644 --- a/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_collapse_invariant.py +++ b/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_collapse_invariant.py @@ -31,10 +31,10 @@ def test_scoring_identical_via_unit_loop(): def test_diagram_identical_for_single_unit_design(): result = {"verdict": "agentcore", "agentcore_services": ["memory"], - "model_recommendation": {"model": "claude_sonnet_4_6"}} + "model_recommendation": {"model": "claude_sonnet_5"}} design = {"units": [{"id": "only", "workload_class": "agent_session", "verdict": "agentcore", - "model_recommendation": {"model": "claude_sonnet_4_6"}}], + "model_recommendation": {"model": "claude_sonnet_5"}}], "platform": {"mode": "split", "runtime": None, "interconnect": "in_process", "shared_services": []}} assert build_diagram.build_diagram(result, {}, design=design) == \ diff --git a/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_unit_grouping.py b/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_unit_grouping.py index 16f29c14..06877f06 100644 --- a/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_unit_grouping.py +++ b/migrate/plugins/migration-to-aws/skills/agent-advisor/scripts/test_unit_grouping.py @@ -651,7 +651,7 @@ def test_build_diagram_single_unit_design_renders_from_unit(): "id": "solo", "workload_class": "agent_session", "verdict": "agentcore", "effective_runtime": "agentcore", "deployment_model": "harness", - "model_recommendation": {"model": "claude_sonnet_4_6"}, + "model_recommendation": {"model": "claude_sonnet_5"}, "agentcore_services": ["memory"], }], "platform": {"mode": "split", "runtime": None, "interconnect": "in_process"}, @@ -660,7 +660,7 @@ def test_build_diagram_single_unit_design_renders_from_unit(): out = build_diagram.build_diagram({"units": {"solo": {}}}, {}, design=design) assert "AgentCore Runtime" in out["mermaid"], \ "single-unit design must render the unit's effective_runtime, not None" - assert "claude_sonnet_4_6" in out["mermaid"], \ + assert "claude_sonnet_5" in out["mermaid"], \ "single-unit design must render the unit's model, not 'unknown'" @@ -904,14 +904,14 @@ def test_build_diagram_preserves_authoritative_empty_services(): "units": [{ "id": "solo", "workload_class": "agent_session", "verdict": "ecs", "effective_runtime": "ecs", - "model_recommendation": {"model": "claude_sonnet_4_6"}, + "model_recommendation": {"model": "claude_sonnet_5"}, "agentcore_services": [], # authoritative: user declined all }], "platform": {"mode": "split", "runtime": None, "interconnect": "in_process"}, } # result carries scoring defaults that must NOT leak in when the unit says []. result = {"verdict": "ecs", "agentcore_services": ["identity", "observability"], - "model_recommendation": {"model": "claude_sonnet_4_6"}} + "model_recommendation": {"model": "claude_sonnet_5"}} out = build_diagram.build_diagram(result, {}, design=design) assert "Identity" not in out["mermaid"] and "Observability" not in out["mermaid"], \ "an authoritative empty agentcore_services must not fall back to scoring defaults" diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-anthropic-to-bedrock.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-anthropic-to-bedrock.md index 626d1148..21aea6a9 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-anthropic-to-bedrock.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/ai-anthropic-to-bedrock.md @@ -10,13 +10,16 @@ | Anthropic SDK model | Bedrock model ID | Tier | Input/Output per 1M | | ------------------- | ------------------------------------------ | -------- | ------------------- | -| `claude-opus-4-*` | `anthropic.claude-opus-4-6-v1` | Premium | $5 / $25 | -| `claude-sonnet-4-*` | `anthropic.claude-sonnet-4-6` | Flagship | $3 / $15 | +| `claude-opus-4-*` | `anthropic.claude-opus-4-8` | Premium | $5 / $25 | +| `claude-sonnet-5-*` | `anthropic.claude-sonnet-5` | Flagship | $2 / $10 intro† | +| `claude-sonnet-4-*` | `anthropic.claude-sonnet-5` | Flagship | $2 / $10 intro† | | `claude-haiku-4-*` | `anthropic.claude-haiku-4-5-20251001-v1:0` | Fast | $1 / $5 | +† Claude Sonnet 5 intro pricing through Aug 31, 2026; then $3 / $15 (same as Sonnet 4.6). Prefer the `us.` inference-profile prefix for on-demand invoke. Sonnet 4.6 (`anthropic.claude-sonnet-4-6`) remains Active if the customer must stay on the 4.6 SKU. + Older Claude models — Claude 3.5 Haiku, Claude 3 Sonnet, Claude 3.5 Sonnet (v1/v2), Claude 3 Haiku, and Claude 3.7 Sonnet — are past EOL or within the 90-day exclusion window. Do **not** recommend them as migration targets. See `shared/ai-model-lifecycle.md` for authoritative status (recomputed each run). -**Recommendation:** Migrate to Claude 4.x directly. Converse API call shape is identical across generations. +**Recommendation:** Default new Bedrock targets to **Claude Sonnet 5** (flagship) / **Claude Opus 4.8** (hardest reasoning) / **Claude Haiku 4.5** (cost/speed). Converse API call shape is identical across generations. Do **not** default to Claude Fable 5 (frontier / Mythos-class pricing — opt-in only). --- @@ -33,7 +36,7 @@ Remove ANTHROPIC_API_KEY. Use IAM role with bedrock:InvokeModel. Before: `client.messages.create(model=..., max_tokens=1024, messages=[{"role": "user", "content": "Hello"}])` -After: `client.converse(modelId="anthropic.claude-sonnet-4-6", messages=[{"role": "user", "content": [{"text": "Hello"}]}], inferenceConfig={"maxTokens": 1024})` +After: `client.converse(modelId="anthropic.claude-sonnet-5", messages=[{"role": "user", "content": [{"text": "Hello"}]}], inferenceConfig={"maxTokens": 1024})` Key differences: 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 fbc545fd..80a68866 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 @@ -8,6 +8,8 @@ Verify all pricing via AWS Pricing MCP or `references/shared/pricing-cache.md`. **Model lifecycle:** Before recommending any Bedrock model, check `references/shared/ai-model-lifecycle.md`. Do not recommend Legacy models as primary selections for new migrations. Legacy models are annotated below where they appear. +**Recommend defaults (Jul 2026):** Claude Sonnet 5 (`anthropic.claude-sonnet-5`) for balanced/flagship; Claude Opus 4.8 for hardest reasoning; Claude Haiku 4.5 for cost/speed. Sonnet 5 intro pricing is **$2/$10 through Aug 31, 2026**, then $3/$15 — comparison tables below use the steady-state $3/$15 rate unless noted. Do not default to Claude Fable 5. + --- ## Competitive Reality (May 2026) @@ -16,19 +18,19 @@ Gemini 3.5 Flash is now GA (May 2026) — the current flagship Flash model. Gemi - Gemini 3.1 Pro leads 13/16 Google-reported benchmarks and 6/10 on the Artificial Analysis Intelligence Index - ARC-AGI-2: 77.1%, SWE-Bench: 80.6% (tied with Opus 4.6 at 80.8%) -- Gemini 3.1 Pro costs $2/$12 per 1M tokens — less than half of Opus 4.6 ($5/$25), cheaper than Sonnet 4.6 ($3/$15) +- Gemini 3.1 Pro costs $2/$12 per 1M tokens — less than half of Opus 4.6 ($5/$25), cheaper than Sonnet 5 ($3/$15) - Gemini 3.5 Flash at $1.50/$9.00 is 5x more expensive than the old Gemini 2.5 Flash ($0.30/$2.50) — the Bedrock cost savings case is now much stronger for Flash-tier users **Where Bedrock still wins:** -- 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 Sonnet 5 / 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 (AgentCore, Knowledge Bases, Guardrails) has no Gemini equivalent **Migration case by tier:** -- Gemini 3.5 Flash → Bedrock: **strong cost case** — Nova Lite is 94% cheaper; even Claude Sonnet 4.6 is comparable at $3/$15 vs $1.50/$9.00 +- Gemini 3.5 Flash → Bedrock: **strong cost case** — Nova Lite is 94% cheaper; even Claude Sonnet 5 is comparable at $3/$15 vs $1.50/$9.00 - Gemini 3.1 Pro → Bedrock: driven by AWS consolidation, agentic reliability, or ecosystem — NOT cost or general benchmarks - Gemini 3.1 Flash-Lite → Nova Lite/Micro: still 76-88% cheaper, strong cost case - Gemini 2.5 Pro → Bedrock: moderate case (older model) @@ -39,7 +41,7 @@ Gemini 3.5 Flash is now GA (May 2026) — the current flagship Flash model. Gemi | Model | Best For | Complexity | Speed | Context | | ----------------- | ------------------------------------------------------------------- | ---------- | ------ | ------- | -| Claude Sonnet 4.6 | Agentic tasks, tool use | High | High | 200K | +| Claude Sonnet 5 | Agentic tasks, tool use | High | High | 1M | | Claude Opus 4.6 | Maximum reasoning | High | Medium | 200K | | Claude Haiku 4.5 | Simple + fast | Medium | High | 200K | | Llama 4 Maverick | Cost-effective + multimodal | Medium | High | 1M | @@ -61,13 +63,13 @@ Gemini 3.5 Flash is now GA (May 2026) — the current flagship Flash model. Gemi | Gemini Model | Price (in/out per 1M) | Best Bedrock Match | Bedrock Price | Winner | | -------------- | --------------------- | --------------------- | -------------- | ------------------- | -| Gemini 3.1 Pro | $2.00 / $12.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | Gemini 24% cheaper | -| Gemini 3.1 Pro | $2.00 / $12.00 | Claude Opus 4.7 / 4.6 | $5.00 / $25.00 | Gemini 54% cheaper | +| Gemini 3.1 Pro | $2.00 / $12.00 | Claude Sonnet 5 | $3.00 / $15.00 | Gemini 24% cheaper | +| Gemini 3.1 Pro | $2.00 / $12.00 | Claude Opus 4.8 | $5.00 / $25.00 | Gemini 54% cheaper | | Gemini 3.1 Pro | $2.00 / $12.00 | Nova 2 Pro | $1.38 / $11.00 | Bedrock 14% cheaper | | Gemini 3 Pro | $0.50 / $3.00 | Llama 4 Maverick | $0.24 / $0.97 | Bedrock 64% cheaper | | Gemini 3 Pro | $0.50 / $3.00 | Llama 4 Scout | $0.17 / $0.66 | Bedrock 75% cheaper | | Gemini 3 Pro | $0.50 / $3.00 | Nova Pro | $0.80 / $3.20 | Gemini 17% cheaper | -| Gemini 2.5 Pro | $1.25 / $10.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | Gemini 40% cheaper | +| Gemini 2.5 Pro | $1.25 / $10.00 | Claude Sonnet 5 | $3.00 / $15.00 | Gemini 40% cheaper | | Gemini 2.5 Pro | $1.25 / $10.00 | Nova Pro | $0.80 / $3.20 | Bedrock 62% cheaper | | Gemini 2.5 Pro | $1.25 / $10.00 | Nova 2 Pro | $1.38 / $11.00 | Gemini 9% cheaper | @@ -78,11 +80,11 @@ Gemini 3.5 Flash is now GA (May 2026) — the current flagship Flash model. Gemi | Gemini Model | Price (in/out per 1M) | Best Bedrock Match | Bedrock Price | Winner | | ------------------------- | ----------------------------------------------------------- | ---------------------------------------- | -------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Gemini 3.5 Flash (GA) | $1.50 / $9.00 | Nova Lite | $0.06 / $0.24 | Bedrock 94% cheaper — strong migration case; 3.5 Flash is 5x more expensive than old 2.5 Flash | -| Gemini 3.5 Flash (GA) | $1.50 / $9.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | Gemini 33% cheaper — but Sonnet leads on agentic reliability | +| Gemini 3.5 Flash (GA) | $1.50 / $9.00 | Claude Sonnet 5 | $3.00 / $15.00 | Gemini 33% cheaper — but Sonnet leads on agentic reliability | | Gemini 3.1 Flash-Lite | $0.25 / $1.50 | Nova Lite | $0.06 / $0.24 | Bedrock 76% cheaper | | Gemini 3.1 Flash-Lite | $0.25 / $1.50 | Nova Micro | $0.035 / $0.14 | Bedrock 88% cheaper | | Gemini 2.5 Flash | $0.30 / $2.50 | Nova Lite | $0.06 / $0.24 | Bedrock 88% cheaper | -| Gemini 2.5 Flash Thinking | $0.30 / $0.60–$3.50 (varies by thinking budget) | Claude Sonnet 4.6 with extended thinking | $3.00 / $15.00 | Depends on thinking budget — at full thinking ($3.50/M output) Sonnet 4.6 is comparable; at low thinking ($0.60/M output) Gemini is cheaper. Profile actual thinking token usage before recommending. | +| Gemini 2.5 Flash Thinking | $0.30 / $0.60–$3.50 (varies by thinking budget) | Claude Sonnet 5 with extended thinking | $3.00 / $15.00 | Depends on thinking budget — at full thinking ($3.50/M output) Sonnet 5 is comparable; at low thinking ($0.60/M output) Gemini is cheaper. Profile actual thinking token usage before recommending. | | Gemini 2.0 Flash | $0.10 / $0.40 | Nova Micro | $0.035 / $0.14 | Bedrock 65% cheaper | | Gemini Flash 1.5 | **Legacy — EOL Sep 24, 2025. Migrate to Gemini 3.5 Flash.** | Nova Lite | $0.06 / $0.24 | If still in use, migrate source model first; strong Bedrock cost case once on 3.5 Flash | @@ -90,7 +92,7 @@ Gemini 3.5 Flash is now GA (May 2026) — the current flagship Flash model. Gemi | Gemini Model | Price (in/out per 1M) | Best Bedrock Match | Bedrock Price | Winner | | ----------------------- | -------------------------------------------------------------------- | ------------------- | --------------- | ---------------------------------------------------------------- | -| Gemini 1.5 Pro | **Legacy — EOL Sep 24, 2025. Migrate to Gemini 2.5 Pro or 3.x Pro.** | Claude Sonnet 4.6 | $3.00 / $15.00 | If still in use, migrate source model first | +| Gemini 1.5 Pro | **Legacy — EOL Sep 24, 2025. Migrate to Gemini 2.5 Pro or 3.x Pro.** | Claude Sonnet 5 | $3.00 / $15.00 | If still in use, migrate source model first | | text-bison / chat-bison | Legacy | Llama 4 Scout | $0.17 / $0.66 | Bedrock (better quality + cheaper) | | text-embedding-004 | $0.025 / N/A | Titan Embeddings V2 | $0.02 / N/A | Bedrock 20% cheaper | | imagen-* | Varies | Nova Canvas | $0.04-$0.08/img | Titan Image Gen v2 is Legacy (EOL Jun 30, 2026); use Nova Canvas | @@ -106,8 +108,8 @@ _Percentages are blended savings using a 2:1 input-to-output token ratio. Actual Gemini 3.1 Pro Preview matches or beats Opus 4.6 on most reasoning benchmarks at less than half the cost. Be transparent: - If user needs **general reasoning/coding quality** → Gemini 3.1 Pro is competitive or better. Migration case is weak unless driven by AWS consolidation. -- If user needs **agentic reliability** (real-world multi-step tasks) → **Claude Sonnet 4.6** still leads on GDPval. This is the honest differentiator. -- If user needs **maximum reasoning on hardest problems** → **Claude Opus 4.7** ($5/$25 headline on-demand, same tier as Opus 4.6) — use the latest [Claude on Bedrock](https://aws.amazon.com/bedrock/pricing/) model card for benchmark deltas vs Gemini; Opus 4.6 remains a same-price alternative where batch or regional availability matters. +- If user needs **agentic reliability** (real-world multi-step tasks) → **Claude Sonnet 5** still leads on GDPval. This is the honest differentiator. +- If user needs **maximum reasoning on hardest problems** → **Claude Opus 4.8** ($5/$25 headline on-demand, same tier as Opus 4.6) — use the latest [Claude on Bedrock](https://aws.amazon.com/bedrock/pricing/) model card for benchmark deltas vs Gemini; Opus 4.6 remains a same-price alternative where batch or regional availability matters. ### Speed-First @@ -120,7 +122,7 @@ Gemini Flash → **Nova Micro** (<200ms, text-only, cheapest), **Haiku 4.5** (<4 ### Balanced -- Gemini 3.1 Pro → **Nova 2 Pro** (-14% cost, AWS-native) or **Claude Sonnet 4.6** (+31% cost, stronger agentic reliability) +- Gemini 3.1 Pro → **Nova 2 Pro** (-14% cost, AWS-native) or **Claude Sonnet 5** (+31% cost, stronger agentic reliability) - Gemini 2.5 Pro → **Nova 2 Pro** (+10% cost, AWS-native) or **Nova Pro** (-62% cost) - Gemini 3 Pro → **Llama 4 Maverick** (-63%), **Nova Pro** (+20%) @@ -138,7 +140,7 @@ Gemini Flash → **Nova Micro** (<200ms, text-only, cheapest), **Haiku 4.5** (<4 | Llama 4 Maverick | $109 (-64%) | | Llama 4 Scout | $75 (-75%) | | Nova Pro | $360 (+20%) | -| Claude Sonnet 4.6 | $1,575 (+425%) | +| Claude Sonnet 5 | $1,575 (+425%) | **High (10-100M tokens/day):** Cost optimization critical. Recommend multi-model tiered approach. Llama 4 Maverick/Scout or Nova for output-heavy workloads. @@ -146,7 +148,7 @@ Gemini Flash → **Nova Micro** (<200ms, text-only, cheapest), **Haiku 4.5** (<4 - Simple tasks (60% of traffic) → Nova Micro or Llama 4 Scout - Moderate tasks (30% of traffic) → Llama 4 Maverick or Nova Pro -- Complex tasks (10% of traffic) → Claude Sonnet 4.6 +- Complex tasks (10% of traffic) → Claude Sonnet 5 --- @@ -154,8 +156,8 @@ Gemini Flash → **Nova Micro** (<200ms, text-only, cheapest), **Haiku 4.5** (<4 | Gemini Model | Monthly | Best Bedrock Match | Monthly | Difference | | ------------------------------- | ------- | ------------------------------ | ------- | ---------- | -| Gemini 3.1 Pro Preview ($2/$12) | $1,200 | Claude Sonnet 4.6 ($3/$15) | $1,575 | +24% | -| Gemini 3.1 Pro Preview ($2/$12) | $1,200 | Claude Opus 4.7 / 4.6 ($5/$25) | $2,625 | +54% | +| Gemini 3.1 Pro Preview ($2/$12) | $1,200 | Claude Sonnet 5 ($3/$15) | $1,575 | +24% | +| Gemini 3.1 Pro Preview ($2/$12) | $1,200 | Claude Opus 4.8 ($5/$25) | $2,625 | +54% | | Gemini 3.1 Pro Preview ($2/$12) | $1,200 | Nova 2 Pro ($1.38/$11.00) | $1,032 | -14% | | Gemini 3 Pro ($0.50/$3.00) | $300 | Llama 4 Maverick ($0.24/$0.97) | $109 | -64% | | Gemini 3 Pro ($0.50/$3.00) | $300 | Llama 4 Scout ($0.17/$0.66) | $75 | -75% | 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 700f38a8..ddee5c3d 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 @@ -10,6 +10,8 @@ Verify all pricing via AWS Pricing MCP or `references/shared/pricing-cache.md`. **Model lifecycle:** Before recommending any Bedrock model, check `references/shared/ai-model-lifecycle.md`. Do not recommend Legacy models as primary selections for new migrations. Legacy models are annotated below where they appear. +**Recommend defaults (Jul 2026):** Claude Sonnet 5 (`anthropic.claude-sonnet-5`) for balanced/flagship; Claude Opus 4.8 for hardest reasoning; Claude Haiku 4.5 for cost/speed. Sonnet 5 intro pricing is **$2/$10 through Aug 31, 2026**, then $3/$15 — comparison tables below use the steady-state $3/$15 rate unless noted. Do not default to Claude Fable 5. + --- ## Key Insight: The Landscape Has Changed (April 2026) @@ -32,7 +34,7 @@ GPT-5.5 is the first fully retrained base model since GPT-4.5. Natively omnimoda | OpenAI Model | Price (in/out per 1M) | Best Bedrock Match | Bedrock Price | Winner | | ------------ | --------------------- | -------------------- | -------------- | ------------------- | | GPT-5.5 | $5.00 / $30.00 | Claude Opus 4.6 | $5.00 / $25.00 | Bedrock 17% cheaper | -| GPT-5.5 | $5.00 / $30.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | Bedrock 53% cheaper | +| GPT-5.5 | $5.00 / $30.00 | Claude Sonnet 5 | $3.00 / $15.00 | Bedrock 53% cheaper | | GPT-5.5 Pro | $30.00 / $180.00 | Nova 2 Pro (Preview) | $1.38 / $11.00 | Bedrock 95% cheaper | > **Token efficiency caveat:** OpenAI reports GPT-5.5 uses ~40% fewer output tokens on Codex-style tasks vs GPT-5.4. Effective cost increase over GPT-5.4 is ~50% (not 100%) for coding workloads. For non-coding workloads, the full 2× price applies. @@ -43,7 +45,7 @@ Percentages below are blended savings using a 2:1 input-to-output token ratio. G | OpenAI Model | Price (in/out per 1M) | Best Bedrock Match | Bedrock Price | Winner | | ------------ | --------------------- | -------------------- | -------------- | ------------------- | -| GPT-5.4 | $2.50 / $15.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | OpenAI 5% cheaper | +| GPT-5.4 | $2.50 / $15.00 | Claude Sonnet 5 | $3.00 / $15.00 | OpenAI 5% cheaper | | GPT-5.4 Mini | $0.75 / $4.50 | Nova Lite | $0.06 / $0.24 | Bedrock 94% cheaper | | GPT-5.4 Nano | $0.20 / $1.25 | Nova Micro | $0.035 / $0.14 | Bedrock 87% cheaper | | GPT-5.4 Pro | $30.00 / $180.00 | Nova 2 Pro (Preview) | $1.38 / $11.00 | Bedrock 94% cheaper | @@ -54,8 +56,8 @@ Percentages below are blended savings using a 2:1 input-to-output token ratio. | OpenAI Model | Price (in/out per 1M) | Best Bedrock Match | Bedrock Price | Winner | | --------------- | --------------------- | --------------------- | -------------- | ------------------- | -| GPT-5.2 | $1.75 / $14.00 | Claude Opus 4.7 / 4.6 | $5.00 / $25.00 | OpenAI 50% cheaper | -| GPT-5.1 / GPT-5 | $1.25 / $10.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | OpenAI 40% cheaper | +| GPT-5.2 | $1.75 / $14.00 | Claude Opus 4.8 | $5.00 / $25.00 | OpenAI 50% cheaper | +| GPT-5.1 / GPT-5 | $1.25 / $10.00 | Claude Sonnet 5 | $3.00 / $15.00 | OpenAI 40% cheaper | | GPT-5 Mini | $0.25 / $2.00 | Nova Lite | $0.06 / $0.24 | Bedrock 86% cheaper | | GPT-5 Nano | $0.05 / $0.40 | Nova Micro | $0.035 / $0.14 | Bedrock 58% cheaper | @@ -74,7 +76,7 @@ Percentages below are blended savings using a 2:1 input-to-output token ratio. | OpenAI Model | Price (in/out per 1M) | Best Bedrock Match | Bedrock Price | Winner | | ------------ | --------------------- | ------------------ | -------------- | ------------------- | -| GPT-4.1 | $2.00 / $8.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | OpenAI 43% cheaper | +| GPT-4.1 | $2.00 / $8.00 | Claude Sonnet 5 | $3.00 / $15.00 | OpenAI 43% cheaper | | GPT-4.1 Mini | $0.40 / $1.60 | Nova Lite | $0.06 / $0.24 | Bedrock 85% cheaper | | GPT-4.1 Nano | $0.10 / $0.40 | Nova Micro | $0.035 / $0.14 | Bedrock 65% cheaper | @@ -82,7 +84,7 @@ Percentages below are blended savings using a 2:1 input-to-output token ratio. | OpenAI Model | Price (in/out per 1M) | Best Bedrock Match | Bedrock Price | Winner | | ------------ | --------------------- | ------------------ | -------------- | ------------------- | -| GPT-4o | $2.50 / $10.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | OpenAI 29% cheaper | +| GPT-4o | $2.50 / $10.00 | Claude Sonnet 5 | $3.00 / $15.00 | OpenAI 29% cheaper | | GPT-4o Mini | $0.15 / $0.60 | Nova Lite | $0.06 / $0.24 | Bedrock 60% cheaper | ### Reasoning Models (o-series) @@ -95,14 +97,14 @@ Percentages below are blended savings using a 2:1 input-to-output token ratio. | o3-pro | $20.00 / $80.00 | Nova 2 Pro (Preview) | $1.38 / $11.00 | Bedrock 87% cheaper | | o1 | $15.00 / $60.00 | Nova 2 Pro (Preview) | $1.38 / $11.00 | Bedrock 83% cheaper | | o3 | $2.00 / $8.00 | DeepSeek-R1 | $1.35 / $5.40 | Bedrock 32% cheaper | -| o4-mini / o3-mini / o1-mini | $1.10 / $4.40 | Claude Sonnet 4.6 | $3.00 / $15.00 | OpenAI 69% cheaper | +| o4-mini / o3-mini / o1-mini | $1.10 / $4.40 | Claude Sonnet 5 | $3.00 / $15.00 | OpenAI 69% cheaper | ### Legacy Models | OpenAI Model | Price (in/out per 1M) | Best Bedrock Match | Bedrock Price | Winner | | ------------- | --------------------- | ------------------ | -------------- | ----------------------------------------- | -| GPT-4 Turbo | $10.00 / $30.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | Bedrock 58% cheaper | -| GPT-4 | $30.00 / $60.00 | Claude Sonnet 4.6 | $3.00 / $15.00 | Bedrock 82% cheaper | +| GPT-4 Turbo | $10.00 / $30.00 | Claude Sonnet 5 | $3.00 / $15.00 | Bedrock 58% cheaper | +| GPT-4 | $30.00 / $60.00 | Claude Sonnet 5 | $3.00 / $15.00 | Bedrock 82% cheaper | | GPT-3.5 Turbo | $0.50 / $1.50 | Llama 4 Maverick | $0.24 / $0.97 | Bedrock 42% cheaper + much better quality | ### OpenAI Models on Bedrock (gpt-oss) @@ -124,7 +126,7 @@ _Percentages are blended savings using a 2:1 input-to-output token ratio. Actual **Migrate to Bedrock if:** -- Using GPT-5.5 flagship → Bedrock 17% cheaper on output via Opus 4.6 ($5/$25 vs $5/$30); Sonnet 4.6 is 53% cheaper +- Using GPT-5.5 flagship → Bedrock 17% cheaper on output via Opus 4.6 ($5/$25 vs $5/$30); Sonnet 5 is 53% cheaper - Using Pro/expensive models (GPT-5.5 Pro, GPT-5.4 Pro, o1-pro) → 87-98% savings via Nova 2 Pro - Using Mini/Nano models at high volume → 87-94% savings via Nova Lite/Micro - Using legacy GPT-4/3.5 → 42-82% savings @@ -136,7 +138,7 @@ _Percentages are blended savings using a 2:1 input-to-output token ratio. Actual **Consider staying on OpenAI if:** - Using GPT-5.5 for omnimodal (audio/video) → Claude is text+image only; GPT-5.5 has native audio/video -- Using GPT-5.4 flagship → only 5% cheaper than Sonnet 4.6; marginal either way +- Using GPT-5.4 flagship → only 5% cheaper than Sonnet 5; marginal either way - Using mid-tier flagships (GPT-5, GPT-4.1, o3, o4-mini) → OpenAI 29-69% cheaper - Low volume (<$500/mo) where absolute savings are small - Heavily integrated with OpenAI ecosystem (Assistants API, gpt-image, Whisper, Realtime) @@ -172,7 +174,7 @@ If the application uses the OpenAI Python/JS SDK directly (`from openai import O 1. Set `OPENAI_BASE_URL=https://bedrock-mantle.{region}.api.aws/v1` 2. Set `OPENAI_API_KEY=` — use a Bedrock API key, **not** your existing OpenAI API key -3. Change model string (e.g., `gpt-5.4` → `anthropic.claude-sonnet-4-6` or `openai.gpt-oss-120b`) +3. Change model string (e.g., `gpt-5.4` → `anthropic.claude-sonnet-5` or `openai.gpt-oss-120b`) **Hard gates before recommending Mantle:** @@ -205,17 +207,17 @@ Assistants API and Responses API are different surfaces. Do not treat all Assist **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 +### GPT-5.4 → Claude Sonnet 5 -Near price parity (~5% difference). Migration case is driven by AWS consolidation, agentic reliability, or prompt caching — not cost. Both have ~200K+ context. Low risk. +Near price parity (~5% difference). Migration case is driven by AWS consolidation, agentic reliability, or prompt caching — not cost. Sonnet 5 has 1M context. Low risk. ### GPT-5.4 Mini/Nano → Nova Lite/Micro 87-94% savings. Strong cost case at any volume. Nova Lite (300K context) covers most GPT-5.4 Mini use cases. -### GPT-4/4 Turbo → Claude Sonnet 4.6 +### GPT-4/4 Turbo → Claude Sonnet 5 -70-90% savings, similar or better quality, longer context (200K vs 128K). Low risk. +70-90% savings, similar or better quality, longer context (1M vs 128K). Low risk. ### GPT-3.5 Turbo → Llama 4 Maverick @@ -243,7 +245,7 @@ Tier by complexity: simple → Nova Micro/Llama 4 Scout (60%), moderate → Llam - Simple tasks (60%) → Nova Micro or Llama 4 Scout - Moderate tasks (30%) → Llama 4 Maverick or Nova Pro -- Complex tasks (10%) → Claude Sonnet 4.6 +- Complex tasks (10%) → Claude Sonnet 5 --- diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/design-ref-agentic-to-agentcore.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/design-ref-agentic-to-agentcore.md index 1344b87b..25742693 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/design-ref-agentic-to-agentcore.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/design-ref-agentic-to-agentcore.md @@ -108,7 +108,7 @@ from strands import Agent from strands.models import BedrockModel agent = Agent( - model=BedrockModel(model_id="us.anthropic.claude-sonnet-4-6-20250514-v1:0"), + model=BedrockModel(model_id="us.anthropic.claude-sonnet-5"), tools=[web_search, calculator, file_read], # your existing tool functions with @tool decorator system_prompt="Your existing system prompt here" ) diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/design-ref-harness.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/design-ref-harness.md index aab77a2c..97e22d05 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/design-ref-harness.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/design-refs/design-ref-harness.md @@ -132,7 +132,7 @@ When Harness path is selected, write this to `aws-design-ai.json`: **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-4-6-20250514-v1:0`) +- `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 above - `harness_config.source_model_provider` — `"open_ai"` or `"google"` based on `summary.ai_source` diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify-ai-only.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify-ai-only.md index 681cceb5..44c4b4e6 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify-ai-only.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/clarify/clarify-ai-only.md @@ -124,11 +124,11 @@ Interpret → `ai_framework` array. Default: auto-detect, fallback `["direct"]`. | Answer | Model Impact | | -------- | ----------------------------------------------------------- | -| Quality | Claude Sonnet 4.6 primary; Opus 4.7 / 4.6 for hardest tasks | +| Quality | Claude Sonnet 5 primary; Opus 4.8 for hardest tasks | | Speed | Claude Haiku 4.5; also Nova Micro/Lite | | Cost | Claude Haiku 4.5 or Nova Micro | | Special | Deferred to Q10 | -| Balanced | Claude Sonnet 4.6 | +| Balanced | Claude Sonnet 5 | Interpret → `ai_priority`. Default: E → `"balanced"`. @@ -164,20 +164,20 @@ _Skip when:_ `models[].model_id` is populated in `ai-workload-profile.json` — | Source | Baseline Recommendation | Pricing Context | | -------------- | --------------------------------- | ---------------------------------- | | Gemini Flash | Claude Haiku 4.5 ($1/$5) | Strong savings | -| Gemini Pro | Claude Sonnet 4.6 ($3/$15) | Comparable tier | +| Gemini Pro | Claude Sonnet 5 ($3/$15) | Comparable tier | | GPT-3.5 Turbo | Claude Haiku 4.5 ($1/$5) | Faster and cheaper | -| GPT-4/4 Turbo | Claude Sonnet 4.6 ($3/$15) | Major savings (GPT-4T: $10/$30) | -| GPT-4o | Claude Sonnet 4.6 ($3/$15) | Modest savings on output | -| GPT-5.4 | Claude Sonnet 4.6 ($3/$15) | ~5% cheaper on OpenAI; near parity | +| GPT-4/4 Turbo | Claude Sonnet 5 ($3/$15) | Major savings (GPT-4T: $10/$30) | +| GPT-4o | Claude Sonnet 5 ($3/$15) | Modest savings on output | +| GPT-5.4 | Claude Sonnet 5 ($3/$15) | ~5% cheaper on OpenAI; near parity | | GPT-5.4 Mini | Nova Lite ($0.06/$0.24) | 94% cheaper on Bedrock | | GPT-5.4 Nano | Nova Micro ($0.035/$0.14) | 87% cheaper on Bedrock | | GPT-5.4 Pro | Nova 2 Pro ($1.38/$11) | 94% cheaper on Bedrock | -| GPT-5/5.x | Claude Sonnet 4.6 ($3/$15) | Savings story is quality, not cost | -| GPT-5 flagship | Claude Opus 4.7 / 4.6 ($5/$25) | Cheaper than GPT-5 Pro ($15/$120) | -| o-series | Sonnet 4.6 with extended thinking | o1 $15/$60 → significant savings | +| GPT-5/5.x | Claude Sonnet 5 ($3/$15) | Savings story is quality, not cost | +| GPT-5 flagship | Claude Opus 4.8 ($5/$25) | Cheaper than GPT-5 Pro ($15/$120) | +| o-series | Sonnet 5 with extended thinking | o1 $15/$60 → significant savings | | Claude (any) | Same model on Bedrock | Client swap only — no model change | -Override examples: GPT-4 + Q2=cost → Haiku; Flash + Q10=extended thinking → Sonnet; GPT-4o + Q10=speech → Nova 2 Sonic; GPT-5.5 + Q2=cost → Sonnet 4.6. +Override examples: GPT-4 + Q2=cost → Haiku; Flash + Q10=extended thinking → Sonnet; GPT-4o + Q10=speech → Nova 2 Sonic; GPT-5.5 + Q2=cost → Sonnet 5. Interpret → `ai_model_baseline`. Default: auto-detect, fallback Q2 priority-based. @@ -256,7 +256,7 @@ Present with concrete anchors: Critical = autocomplete/live chat; Important = ch | Answer | Impact | | --------- | ------------------------------------------------------------ | | Critical | Haiku/Nova Micro; streaming required; provisioned throughput | -| Important | Sonnet 4.6 with streaming; standard on-demand | +| Important | Sonnet 5 with streaming; standard on-demand | | Flexible | Any model; batch inference for cost savings | Interpret → `ai_latency`. Default: B → `"important"`. @@ -270,8 +270,8 @@ Present with concrete examples: Simple = classify/extract/summarize; Moderate = | Answer | Impact | | -------- | ----------------------------------------------------------------------------- | | Simple | Haiku/Nova Micro sufficient; significant cost savings | -| Moderate | Sonnet 4.6 recommended; Haiku may suffice with prompt engineering | -| Complex | Sonnet 4.6 required; extended thinking considered; Opus 4.7 / 4.6 for hardest | +| Moderate | Sonnet 5 recommended; Haiku may suffice with prompt engineering | +| Complex | Sonnet 5 required; extended thinking considered; Opus 4.8 for hardest | Interpret → `ai_complexity`. Default: B → `"moderate"`. 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 5ddc42cf..3c2d808b 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 @@ -211,11 +211,11 @@ Present with concrete anchors: Quality = legal analysis/code gen; Speed = autoco | Answer | Recommendation Impact | | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| Best quality/reasoning | Claude Sonnet 4.6 (latest, highest reasoning in Sonnet family) — primary; Claude Opus 4.7 for the most demanding reasoning tasks (same headline on-demand $5/$25 as Opus 4.6 on standard Bedrock pricing); Claude Opus 4.6 remains a valid alternative | +| Best quality/reasoning | Claude Sonnet 5 (latest, highest reasoning in Sonnet family) — primary; Claude Opus 4.8 for the most demanding reasoning tasks (same headline on-demand $5/$25 as Opus 4.6 on standard Bedrock pricing); Claude Opus 4.6 remains a valid alternative | | Fastest speed | Claude Haiku 4.5 — lowest latency in Claude family; also consider Amazon Nova Micro/Lite for cost-optimized speed | | Lowest cost | Claude Haiku 4.5 or Amazon Nova Micro — lowest cost per token | | Specialized capability | Deferred to Q17 to determine which model | -| Balanced | Claude Sonnet 4.6 as default balanced recommendation | +| Balanced | Claude Sonnet 5 as default balanced recommendation | Interpret → `ai_priority`. Default: E → `"balanced"`. @@ -236,14 +236,14 @@ Interpret → `ai_priority`. Default: E → `"balanced"`. | Answer | Recommendation Impact | | ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| Function calling / Tool use | Claude Sonnet 4.6 — best-in-class tool use on Bedrock via structured JSON tool schemas; supports parallel tool calls and multi-turn tool use | +| Function calling / Tool use | Claude Sonnet 5 — best-in-class tool use on Bedrock via structured JSON tool schemas; supports parallel tool calls and multi-turn tool use | | Ultra-long context (> 300K tokens) | Claude Sonnet/Opus 4.6 long-context SKUs where available (standard on-demand for 4.6 matches base tier in US East N. Virginia per [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/)); or Llama 4 Scout (10M), Llama 4 Maverick (1M), Nova 2 Pro/Lite (1M) for very large native context windows | -| 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. | +| Extended thinking / Chain-of-thought | Claude Sonnet 5 with extended thinking mode; Claude Opus 4.8 for most complex reasoning | +| Prompt caching | Claude Sonnet 5 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 AgentCore (Harness); multi-agent orchestration guidance included | +| Agentic workflows | Claude Sonnet 5 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 | +| Multimodal with image generation | Claude Sonnet 5 (vision) + Amazon Nova Canvas for generation | | Real-time conversational speech | Amazon Nova 2 Sonic recommended for speech-to-speech; latency guidance included | | None | Default recommendation from Q16 priority stands | @@ -308,29 +308,29 @@ Establishes baseline Bedrock recommendation. **Override hierarchy:** Q17 special | Source Model | Baseline Bedrock Recommendation | Pricing Context | | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Gemini 3.5 Flash (GA) | Nova Lite ($0.06/$0.24) — 94% cheaper | Gemini 3.5 Flash is $1.50/$9.00 — 5x more expensive than old 2.5 Flash; Nova Lite is the cost-equivalent; very strong migration case | -| Gemini 3.5 Flash Thinking | Claude Sonnet 4.6 with extended thinking ($3/$15) | At $1.50/$9.00 base + thinking tokens, Sonnet 4.6 is comparable or cheaper at full thinking; profile actual thinking usage before committing | +| Gemini 3.5 Flash Thinking | Claude Sonnet 5 with extended thinking ($3/$15) | At $1.50/$9.00 base + thinking tokens, Sonnet 5 is comparable or cheaper at full thinking; profile actual thinking usage before committing | | Gemini 3.1 Flash-Lite | Nova Micro ($0.035/$0.14) — 88% cheaper; or Nova Lite ($0.06/$0.24) — 76% cheaper | Gemini 3.1 Flash-Lite is $0.25/$1.50; strong Bedrock cost case | | Gemini 2.5 Flash (standard) | Nova Lite ($0.06/$0.24) — 88% cheaper | Gemini 2.5 Flash is $0.30/$2.50; Nova Lite is the cost-equivalent; strong migration case | -| Gemini 2.5 Flash Thinking | Claude Sonnet 4.6 with extended thinking ($3/$15) | Thinking output pricing on Gemini 2.5 Flash ranges $0.60–$3.50/M depending on thinking budget; at full thinking budget Sonnet 4.6 is comparable or cheaper; flag that thinking token costs vary and user should profile their actual thinking budget usage before committing | +| Gemini 2.5 Flash Thinking | Claude Sonnet 5 with extended thinking ($3/$15) | Thinking output pricing on Gemini 2.5 Flash ranges $0.60–$3.50/M depending on thinking budget; at full thinking budget Sonnet 5 is comparable or cheaper; flag that thinking token costs vary and user should profile their actual thinking budget usage before committing | | Gemini 2.5 Pro | Nova 2 Pro ($1.38/$11) — 9% cheaper; or Nova Pro ($0.80/$3.20) — 62% cheaper | Gemini 2.5 Pro is $1.25/$10; migration case is cost + AWS consolidation | -| Gemini 3 Pro / 3.1 Pro | Claude Sonnet 4.6 ($3/$15) — agentic reliability; or Nova 2 Pro ($1.38/$11) — cost | Gemini 3.1 Pro is $2/$12 — cheaper than Sonnet 4.6; migration case is agentic reliability and AWS ecosystem, NOT cost. Be honest: Gemini 3.1 Pro leads on general benchmarks. | +| Gemini 3 Pro / 3.1 Pro | Claude Sonnet 5 ($3/$15) — agentic reliability; or Nova 2 Pro ($1.38/$11) — cost | Gemini 3.1 Pro is $2/$12 — cheaper than Sonnet 5; migration case is agentic reliability and AWS ecosystem, NOT cost. Be honest: Gemini 3.1 Pro leads on general benchmarks. | | Gemini Flash 1.5 / 2.0 (older) | Nova Lite ($0.06/$0.24) or Nova Micro ($0.035/$0.14) — **flag Gemini 1.5 Flash as EOL (Sep 2025); recommend upgrading source model to 3.5 Flash before or alongside migration** | Strong Bedrock cost savings; 1.5 Flash is past EOL so migration is doubly urgent | -| Gemini Pro 1.5 (older) | Claude Sonnet 4.6 ($3/$15) — **flag Gemini 1.5 Pro as EOL (Sep 2025); recommend upgrading source model to 3.1 Pro before or alongside migration** | 1.5 Pro is past EOL; migration to Bedrock and source model upgrade should be planned together | +| Gemini Pro 1.5 (older) | Claude Sonnet 5 ($3/$15) — **flag Gemini 1.5 Pro as EOL (Sep 2025); recommend upgrading source model to 3.1 Pro before or alongside migration** | 1.5 Pro is past EOL; migration to Bedrock and source model upgrade should be planned together | | GPT-3.5 Turbo | Claude Haiku 4.5 ($1/$5) — cost-equivalent | Haiku is faster and cheaper | -| GPT-4 / GPT-4 Turbo | Claude Sonnet 4.6 ($3/$15) — quality equivalent | Major savings: GPT-4 Turbo is $10/$30 vs Sonnet $3/$15 | -| GPT-4o | Claude Sonnet 4.6 ($3/$15) — performance equivalent | Modest savings on output; input slightly higher on Bedrock | -| GPT-5.4 | Claude Sonnet 4.6 ($3/$15) — near price parity | GPT-5.4 is $2.50/$15 — ~5% cheaper; migration case is AWS consolidation, not cost | +| GPT-4 / GPT-4 Turbo | Claude Sonnet 5 ($3/$15) — quality equivalent | Major savings: GPT-4 Turbo is $10/$30 vs Sonnet $3/$15 | +| GPT-4o | Claude Sonnet 5 ($3/$15) — performance equivalent | Modest savings on output; input slightly higher on Bedrock | +| GPT-5.4 | Claude Sonnet 5 ($3/$15) — near price parity | GPT-5.4 is $2.50/$15 — ~5% cheaper; migration case is AWS consolidation, not cost | | GPT-5.4 Mini | Nova Lite ($0.06/$0.24) — massive cost savings | 94% cheaper on Bedrock; strong migration case | | GPT-5.4 Nano | Nova Micro ($0.035/$0.14) — massive cost savings | 87% cheaper on Bedrock; strong migration case | | GPT-5.4 Pro | Nova 2 Pro ($1.38/$11) — flagship reasoning on AWS | 94% cheaper on Bedrock; strongest migration case | -| GPT-5 / GPT-5.x (older) | Claude Sonnet 4.6 ($3/$15) — performance equivalent | GPT-5 is $1.25/$10 — savings story is quality/features, not cost | +| GPT-5 / GPT-5.x (older) | Claude Sonnet 5 ($3/$15) — performance equivalent | GPT-5 is $1.25/$10 — savings story is quality/features, not cost | | GPT-5 (flagship use case) | Claude Opus 4.6 ($5/$25) — flagship-to-flagship | Opus still cheaper than GPT-5 Pro ($15/$120) | | GPT-5.5 | Claude Opus 4.6 ($5/$25) — flagship-to-flagship | Bedrock 17% cheaper on output ($25 vs $30); same input price | -| GPT-5.5 (cost-sensitive) | Claude Sonnet 4.6 ($3/$15) — 53% cheaper | Strong cost case; Sonnet leads on agentic reliability | +| GPT-5.5 (cost-sensitive) | Claude Sonnet 5 ($3/$15) — 53% cheaper | Strong cost case; Sonnet leads on agentic reliability | | GPT-5.5 Pro | Nova 2 Pro ($1.38/$11) — flagship reasoning on AWS | 95% cheaper on Bedrock; strongest migration case | -| o-series (o1, o3) | Claude Sonnet 4.6 with extended thinking; Opus 4.6 for most demanding | o1 is $15/$60 — significant savings with Sonnet 4.6 at $3/$15 | +| o-series (o1, o3) | Claude Sonnet 5 with extended thinking; Opus 4.6 for most demanding | o1 is $15/$60 — significant savings with Sonnet 5 at $3/$15 | -**Override examples:** GPT-4 + Q16=cost → Haiku; Flash + Q17=extended thinking → Sonnet; GPT-4o + Q17=speech → Nova 2 Sonic; GPT-3.5 + Q22=complex → Sonnet; GPT-5 + Q16=balanced → Sonnet; GPT-5.5 + Q16=cost → Sonnet 4.6; Gemini 2.5 Flash Thinking + Q16=cost → Nova Lite (if thinking budget is low) or Sonnet 4.6 (if full thinking mode). +**Override examples:** GPT-4 + Q16=cost → Haiku; Flash + Q17=extended thinking → Sonnet; GPT-4o + Q17=speech → Nova 2 Sonic; GPT-3.5 + Q22=complex → Sonnet; GPT-5 + Q16=balanced → Sonnet; GPT-5.5 + Q16=cost → Sonnet 5; Gemini 2.5 Flash Thinking + Q16=cost → Nova Lite (if thinking budget is low) or Sonnet 5 (if full thinking mode). Interpret → `ai_model_baseline`. Default: auto-detect from code, fallback Q16 priority-based. @@ -374,7 +374,7 @@ Present with concrete anchors: Critical = autocomplete/live chat/real-time trans | Answer | Recommendation Impact | | ------------------ | ------------------------------------------------------------------------------------------------- | | Critical (< 500ms) | Claude Haiku 4.5 or Nova Micro; streaming required; provisioned throughput for consistent latency | -| Important (< 2s) | Claude Sonnet 4.6 with streaming; standard on-demand acceptable | +| Important (< 2s) | Claude Sonnet 5 with streaming; standard on-demand acceptable | | Flexible (2–10s) | Any model; batch inference considered for cost savings at high volume | Interpret → `ai_latency`. Default: B → `"important"`. @@ -392,8 +392,8 @@ Present with concrete examples: Simple = classify/extract/summarize; Moderate = | Answer | Recommendation Impact | | -------- | ------------------------------------------------------------------------------------------------- | | Simple | Claude Haiku 4.5 or Nova Micro sufficient; significant cost savings vs larger models | -| Moderate | Claude Sonnet 4.6 recommended; Haiku may suffice with prompt engineering | -| Complex | Claude Sonnet 4.6 required; extended thinking considered; Claude Opus 4.7 / 4.6 for hardest tasks | +| Moderate | Claude Sonnet 5 recommended; Haiku may suffice with prompt engineering | +| Complex | Claude Sonnet 5 required; extended thinking considered; Claude Opus 4.8 for hardest tasks | Interpret → `ai_complexity`. Default: B → `"moderate"`. 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 adf17484..05508df9 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 @@ -518,19 +518,19 @@ If user opts in, present Q-E1–Q-E2 (defined in **Category E — Migration Post | 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 migration | Q19 = GPT-5.5 | Claude Opus 4.6 — Bedrock 17% cheaper on output; or Sonnet 5 for 53% savings | | GPT-5.5 Pro migration | Q19 = GPT-5.5 Pro | Nova 2 Pro — 95% cheaper on Bedrock | -| GPT-5.4 migration | Q19 = GPT-5.4 | Claude Sonnet 4.6 — near price parity; AWS consolidation | +| GPT-5.4 migration | Q19 = GPT-5.4 | Claude Sonnet 5 — near price parity; AWS consolidation | | GPT-5.4 Mini/Nano migration | Q19 = GPT-5.4 Mini or Nano | Nova Lite/Micro — 87-94% cheaper on Bedrock | -| GPT-4 Turbo migration | Q19 = GPT-4 Turbo | Claude Sonnet 4.6 — 70% cheaper on input | -| o-series migration | Q19 = o-series | Claude Sonnet 4.6 with extended thinking | +| GPT-4 Turbo migration | Q19 = GPT-4 Turbo | Claude Sonnet 5 — 70% cheaper on input | +| o-series migration | Q19 = o-series | Claude Sonnet 5 with extended thinking | | High-volume cost-critical AI | Q18 = High + cost critical | Nova Micro or Haiku 4.5 + provisioned throughput | -| Reasoning/agent workload | Q17 = Extended thinking | Claude Sonnet 4.6 extended thinking; Opus 4.6 for hardest | +| Reasoning/agent workload | Q17 = Extended thinking | Claude Sonnet 5 extended thinking; Opus 4.6 for hardest | | Speech-to-speech AI | Q17 = Real-time speech | Nova 2 Sonic | | RAG workload | Q17 = RAG optimization | Bedrock Knowledge Bases + Titan Embeddings | -| Vision workload | Q20 = Vision required | Claude Sonnet 4.6 (multimodal) | +| Vision workload | Q20 = Vision required | Claude Sonnet 5 (multimodal) | | Latency-critical AI | Q21 = Critical | Haiku 4.5 or Nova Micro + streaming | -| Complex reasoning tasks | Q22 = Complex | Claude Sonnet 4.6; Opus 4.6 for hardest | +| Complex reasoning tasks | Q22 = Complex | Claude Sonnet 5; Opus 4.6 for hardest | --- 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 207ec341..85a8fe57 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 @@ -172,7 +172,7 @@ If `ai_token_volume` is `"high"`, generate a `tiered_strategy`: | ---- | ------- | ---------------------------- | ---------------------------------------------------- | | 1 | 60% | Nova Micro or Llama 4 Scout | Classification, extraction, short answers, routing | | 2 | 30% | Llama 4 Maverick or Nova Pro | Summarization, moderate generation, Q&A with context | -| 3 | 10% | Claude Sonnet 4.6 | Reasoning, long-form, agentic tasks, tool use | +| 3 | 10% | Claude Sonnet 5 | Reasoning, long-form, agentic tasks, tool use | Set `tiered_strategy: null` for low/medium volume. diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/discover/discover-preview.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/discover/discover-preview.md index 202e6aa0..848665ab 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/discover/discover-preview.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/discover/discover-preview.md @@ -85,14 +85,14 @@ from `references/shared/pricing-cache.md` (Source Provider Pricing + Bedrock Mod | Source model pattern | Bedrock equivalent | Bedrock model ID | | ----------------------------------------------- | -------------------------- | ------------------------------------------ | -| `gpt-4o`, `gpt-4.1`, `gpt-5.*` flagship | Claude Sonnet 4.6 | `anthropic.claude-sonnet-4-6` | +| `gpt-4o`, `gpt-4.1`, `gpt-5.*` flagship | Claude Sonnet 5 | `anthropic.claude-sonnet-5` | | `gpt-4o-mini`, `gpt-4.1-mini`, `gpt-5.*-mini` | Claude Haiku 4.5 | `anthropic.claude-haiku-4-5-20251001-v1:0` | | `gpt-3.5-turbo`, `gpt-4.1-nano`, `gpt-5.*-nano` | Amazon Nova Micro | `amazon.nova-micro-v1:0` | -| `o3`, `o4-mini`, reasoning models | Claude Sonnet 4.6 | `anthropic.claude-sonnet-4-6` | -| `gemini-2.5-pro`, `gemini-3.*-pro` | Claude Sonnet 4.6 | `anthropic.claude-sonnet-4-6` | +| `o3`, `o4-mini`, reasoning models | Claude Sonnet 5 | `anthropic.claude-sonnet-5` | +| `gemini-2.5-pro`, `gemini-3.*-pro` | Claude Sonnet 5 | `anthropic.claude-sonnet-5` | | `gemini-2.5-flash`, `gemini-2.0-flash` | Claude Haiku 4.5 | `anthropic.claude-haiku-4-5-20251001-v1:0` | | `gemini-2.0-flash-lite` | Amazon Nova Lite | `amazon.nova-lite-v1:0` | -| `claude-3-5-sonnet`, `claude-sonnet-*` | Claude Sonnet 4.6 | `anthropic.claude-sonnet-4-6` | +| `claude-3-5-sonnet`, `claude-sonnet-*` | Claude Sonnet 5 | `anthropic.claude-sonnet-5` | | `claude-3-5-haiku`, `claude-haiku-*` | Claude Haiku 4.5 | `anthropic.claude-haiku-4-5-20251001-v1:0` | | `claude-3-opus`, `claude-opus-*` | Claude Opus 4.6 | `anthropic.claude-opus-4-6-v1` | | `text-embedding-*`, `*-embedding-*` | Amazon Titan Embeddings v2 | `amazon.titan-embed-text-v2:0` | @@ -157,8 +157,8 @@ Write `$MIGRATION_DIR/migration-preview.json`: "source_model": "gpt-4o", "source_input_per_1m": 2.50, "source_output_per_1m": 10.00, - "bedrock_equivalent": "Claude Sonnet 4.6", - "bedrock_model_id": "anthropic.claude-sonnet-4-6", + "bedrock_equivalent": "Claude Sonnet 5", + "bedrock_model_id": "anthropic.claude-sonnet-5", "bedrock_input_per_1m": 3.00, "bedrock_output_per_1m": 15.00, "cost_direction": "higher" diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-ai.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-ai.md index c42f8300..f018683b 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-ai.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-ai.md @@ -59,7 +59,7 @@ Based on `ai-workload-profile.json` → `integration.pattern` and `integration.l | Vertex AI (Go) | aws-sdk-go-v2 bedrockruntime | `aiplatform` → `bedrockruntime.Converse()` | | Vertex AI (Java) | AWS SDK BedrockRuntimeClient | `GenerativeModel` → `BedrockRuntimeClient.converse()` | | OpenAI SDK | boto3 Bedrock Converse API | `client.chat.completions.create()` → `bedrock.converse()` (if Mantle unavailable) | -| LiteLLM | LiteLLM config change | `model="gpt-4o"` → `model="bedrock/anthropic.claude-sonnet-4-6"` | +| LiteLLM | LiteLLM config change | `model="gpt-4o"` → `model="bedrock/anthropic.claude-sonnet-5"` | | LangChain | langchain_aws | `ChatOpenAI`/`ChatVertexAI` → `ChatBedrock` | | LlamaIndex | llama_index.llms.bedrock_converse | `Vertex` → `BedrockConverse` | diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-artifacts-ai.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-artifacts-ai.md index 84ab5d6b..a02908a6 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-artifacts-ai.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-artifacts-ai.md @@ -702,7 +702,7 @@ resource "aws_ce_anomaly_subscription" "bedrock_alert" { # Tags on these profiles appear in Cost Explorer; tags on API calls do not. # copy_from must be a full foundation-model ARN or cross-region inference profile ARN. # For Claude models, use the cross-region inference profile ARN format: -# arn:aws:bedrock:{region}:{account_id}:inference-profile/us.anthropic.claude-sonnet-4-6 +# arn:aws:bedrock:{region}:{account_id}:inference-profile/us.anthropic.claude-sonnet-5 # For Amazon Nova models, use: # arn:aws:bedrock:{region}:{account_id}:inference-profile/us.amazon.nova-pro-v1:0 # [AGENT: generate one block per model in aws-design-ai.json → ai_architecture.bedrock_models[]] @@ -714,7 +714,7 @@ resource "aws_bedrock_inference_profile" "primary" { copy_from = "arn:aws:bedrock:${data.aws_region.current.name}:${data.aws_caller_identity.current.account_id}:inference-profile/{cross_region_inference_profile_id}" # AGENT: replace {cross_region_inference_profile_id} with the correct ID from # aws-design-ai.json bedrock_models[].aws_model_id, prefixed with "us." for US regions - # e.g., us.anthropic.claude-sonnet-4-6 or us.amazon.nova-pro-v1:0 + # e.g., us.anthropic.claude-sonnet-5 or us.amazon.nova-pro-v1:0 } tags = { diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-artifacts-report.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-artifacts-report.md index f1b534df..2ddab4e9 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-artifacts-report.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/phases/generate/generate-artifacts-report.md @@ -689,7 +689,7 @@ These move from "example in the fixture" to enforced gate. See `references/share 5. **Accessible tables and diagrams.** Every table has a `
Monthly token volume and cost for the recommended model.
ComponentVolumeCost
What matters most for your AI workloads? Quality User answerClaude Sonnet 4.6 recommended over lower-cost modelsClaude Sonnet 5 recommended over lower-cost models
Detected: Cloud SQL ZONAL → single-AZ availability
` and `scope="col"` on header cells. The architecture diagram is wrapped in `
` with a `
` text alternative. 6. **State the verdict.** The decision summary includes a one-sentence recommendation banner (e.g. "Recommendation: Migrate, phased over 10 weeks — ~$497/mo savings, BigQuery deferred") in addition to the `path_label` badges. 7. **Reader vocabulary in the executive flow.** Artifact filenames (`estimation-infra.json`) and Terraform resource IDs (`aws_guardduty_detector.baseline`) are internal build vocabulary. Use them only in the technical appendices (`appendix-services`, `appendix-costs`, `appendix-security`, `appendix-artifacts`, etc.). In the executive flow (`decision-summary`, `exec-tco`, `exec-costs`, `exec-services`, `exec-architecture`, `exec-security-teaser`, `what-if-scenarios`, `exec-timeline`, `exec-risks`), name things by what the reader controls — "the generated security baseline", "the infrastructure cost estimate", "workshop scenario comparison" — not by the file or resource that produced them. Rewrite tooling-availability notes (e.g. "awsknowledge MCP not invoked") to reader-facing impact, or drop them. The validator fails on a `*.json` artifact filename or an `aws_.` Terraform ID inside any `exec-*`, `what-if-scenarios`, or `decision-summary` section. -8. **One name per concept.** Use a single consistent label for each recommended choice across the whole report. The recommended Bedrock model and the chosen cost tier keep the same name in the verdict, tables, and appendices (always "Claude Sonnet 4.6 (recommended)", always "Balanced"). Do not alternate "recommended / selected target / design target / projected" for the same item — one label is how the reader keeps their bearings. +8. **One name per concept.** Use a single consistent label for each recommended choice across the whole report. The recommended Bedrock model and the chosen cost tier keep the same name in the verdict, tables, and appendices (always "Claude Sonnet 5 (recommended)", always "Balanced"). Do not alternate "recommended / selected target / design target / projected" for the same item — one label is how the reader keeps their bearings. 9. **Ordered action lists.** In `decision-summary`, `Key decisions ahead` and `Next steps` MUST use `
    `, not `
      `. The validator fails when either heading is followed by a bullet list. `Migrate if` / `Stay if` remain unordered lists. > **Section IDs are stable anchors, not placement hints.** Some `appendix-*` IDs render in the executive flow on purpose (notably `appendix-assumptions`). Do not rename IDs to match position — the validator and TOC key on them. diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/ai-model-lifecycle.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/ai-model-lifecycle.md index 04dd3070..4bbd49b7 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/ai-model-lifecycle.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/ai-model-lifecycle.md @@ -54,19 +54,19 @@ Check the [model lifecycle page](https://docs.aws.amazon.com/bedrock/latest/user | Model | Model ID | EOL Date | Days to EOL | Status | Active Replacement | | -------------------- | ------------------------------------------- | ------------ | ----------- | ------------ | --------------------------- | -| Claude 3 Sonnet | `anthropic.claude-3-sonnet-20240229-v1:0` | Jul 30, 2026 | 13 | **excluded** | Claude Sonnet 4.5 / 4.6 | -| Claude 3.5 Sonnet v1 | `anthropic.claude-3-5-sonnet-20240620-v1:0` | Jul 30, 2026 | 13 | **excluded** | Claude Sonnet 4.5 / 4.6 | -| Claude 3.5 Sonnet v2 | `anthropic.claude-3-5-sonnet-20241022-v2:0` | Jul 30, 2026 | 13 | **excluded** | Claude Sonnet 4.5 / 4.6 | +| Claude 3 Sonnet | `anthropic.claude-3-sonnet-20240229-v1:0` | Jul 30, 2026 | 13 | **excluded** | Claude Sonnet 5 / 4.6 | +| Claude 3.5 Sonnet v1 | `anthropic.claude-3-5-sonnet-20240620-v1:0` | Jul 30, 2026 | 13 | **excluded** | Claude Sonnet 5 / 4.6 | +| Claude 3.5 Sonnet v2 | `anthropic.claude-3-5-sonnet-20241022-v2:0` | Jul 30, 2026 | 13 | **excluded** | Claude Sonnet 5 / 4.6 | | Command R / R+ | `cohere.command-r-v1:0` / `plus` | Aug 19, 2026 | 33 | **excluded** | — | | Claude 3 Haiku | `anthropic.claude-3-haiku-20240307-v1:0` | Sep 10, 2026 | 55 | **excluded** | Claude Haiku 4.5 | | Nova Premier v1 | `amazon.nova-premier-v1:0` | Sep 14, 2026 | 59 | **excluded** | Nova 2 Pro (Preview) | | Nova Sonic v1 | `amazon.nova-sonic-v1:0` | Sep 14, 2026 | 59 | **excluded** | Nova 2 Sonic | | Nova Canvas v1 | `amazon.nova-canvas-v1:0` | Sep 30, 2026 | 75 | **excluded** | Stability AI (see note) | | Nova Reel v1 | `amazon.nova-reel-v1:0` / `v1:1` | Sep 30, 2026 | 75 | **excluded** | — | -| Claude Sonnet 4 | `anthropic.claude-sonnet-4-20250514-v1:0` | Oct 14, 2026 | 89 | **excluded** | Claude Sonnet 4.5 / 4.6 / 5 | +| Claude Sonnet 4 | `anthropic.claude-sonnet-4-20250514-v1:0` | Oct 14, 2026 | 89 | **excluded** | Claude Sonnet 5 / 4.6 | | Jamba 1.5 Large | `ai21.jamba-1-5-large-v1:0` | Nov 26, 2026 | 132 | legacy | — | | Jamba 1.5 Mini | `ai21.jamba-1-5-mini-v1:0` | Nov 26, 2026 | 132 | legacy | — | -| Claude Opus 4.1 | `anthropic.claude-opus-4-1-20250805-v1:0` | Jan 8, 2027 | 175 | legacy | Claude Opus 4.6 / 4.8 | +| Claude Opus 4.1 | `anthropic.claude-opus-4-1-20250805-v1:0` | Jan 8, 2027 | 175 | legacy | Claude Opus 4.8 / 4.6 | **Removed (past EOL as of Jul 17, 2026):** diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/pricing-cache.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/pricing-cache.md index 533d91a9..edf4cf7a 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/pricing-cache.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/pricing-cache.md @@ -366,7 +366,7 @@ Serverless inference: $0.0000200 per second per GB memory. ## Bedrock Models (On-Demand) -**Anthropic Claude (Standard on-demand)** figures below match **US East (N. Virginia)** on [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/) as of cache refresh. **Claude Fable 5** is the most expensive Anthropic model at $10/$50 per 1M tokens (Mythos-class). **Claude Opus 4.8** keeps the same $5/$25 rate as Opus 4.6/4.7. **Claude Sonnet 5** launched June 30 with introductory pricing of $2/$10 through Aug 31, 2026, then $3/$15 (same as Sonnet 4.6). **Claude Opus 4.7** lists the same headline on-demand input/output as **Opus 4.6** on that page; confirm **batch** availability per model (Opus 4.7 batch was **not** listed on the global cross-region table when this row was added). **Claude Opus 4.1** entered **Legacy** on Jul 8, 2026 (EOL Jan 8, 2027). **Batch**, **prompt cache** (5m / 1h write + cache read), and **geo / in-region cross-region** rows on that page can differ; e.g. **US East (Ohio)** cross-region inference for Claude Sonnet 4.6 is listed at **$3.30 / $16.50** per 1M input/output (≈10% above N. Virginia). Long-context SKUs **do not** all use the same multiplier: **Sonnet 4.6** and **Opus 4.6** long-context modes share the same on-demand rates as the non–long-context rows on the standard table; **Sonnet 4.5** and **Sonnet 4** long-context rows are priced higher on that same table. +**Anthropic Claude (Standard on-demand)** figures below match **US East (N. Virginia)** on [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/) as of cache refresh. **Recommend defaults (new migrations):** Claude Sonnet 5 (flagship), Claude Opus 4.8 (hardest reasoning), Claude Haiku 4.5 (cost/speed). Do not default to Claude Fable 5 (frontier). **Claude Fable 5** is the most expensive Anthropic model at $10/$50 per 1M tokens (Mythos-class). **Claude Opus 4.8** keeps the same $5/$25 rate as Opus 4.6/4.7. **Claude Sonnet 5** launched June 30 with introductory pricing of $2/$10 through Aug 31, 2026, then $3/$15 (same as Sonnet 4.6). **Claude Opus 4.7** lists the same headline on-demand input/output as **Opus 4.6** on that page; confirm **batch** availability per model (Opus 4.7 batch was **not** listed on the global cross-region table when this row was added). **Claude Opus 4.1** entered **Legacy** on Jul 8, 2026 (EOL Jan 8, 2027). **Batch**, **prompt cache** (5m / 1h write + cache read), and **geo / in-region cross-region** rows on that page can differ; e.g. **US East (Ohio)** cross-region inference for Claude Sonnet 4.6 is listed at **$3.30 / $16.50** per 1M input/output (≈10% above N. Virginia). Long-context SKUs **do not** all use the same multiplier: **Sonnet 4.6** and **Opus 4.6** long-context modes share the same on-demand rates as the non–long-context rows on the standard table; **Sonnet 4.5** and **Sonnet 4** long-context rows are priced higher on that same table. ### Multi-provider quick reference (per 1M tokens) diff --git a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/retarget-gotchas.md b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/retarget-gotchas.md index 5da4d40d..b11d62df 100644 --- a/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/retarget-gotchas.md +++ b/migrate/plugins/migration-to-aws/skills/gcp-to-aws/references/shared/retarget-gotchas.md @@ -51,7 +51,7 @@ These are real issues startups hit when keeping their existing framework and swa ### Model configuration format -**Problem:** CrewAI uses LiteLLM under the hood for model routing. The model string format for Bedrock is `bedrock/model-id` (e.g., `bedrock/us.anthropic.claude-sonnet-4-6-20250514-v1:0`). Getting the format wrong produces cryptic LiteLLM errors. +**Problem:** CrewAI uses LiteLLM under the hood for model routing. The model string format for Bedrock is `bedrock/model-id` (e.g., `bedrock/us.anthropic.claude-sonnet-5`). Getting the format wrong produces cryptic LiteLLM errors. **Fix:** Use the exact format: `bedrock/{full_model_id}`. Set `AWS_REGION_NAME` environment variable. Verify with a simple LiteLLM test call before running the full crew. @@ -65,7 +65,7 @@ These are real issues startups hit when keeping their existing framework and swa **Problem:** CrewAI's `Process.hierarchical` requires the manager model to reliably delegate tasks. Some Bedrock models (especially smaller ones like Nova Lite, Llama variants) are less reliable at hierarchical delegation than GPT-4o or Claude Sonnet. -**Fix:** For hierarchical processes, use Claude Sonnet 4.6 as the manager model (best tool-use reliability on Bedrock). Specialist agents can use cheaper models. Don't use Nova Micro or Llama Scout as the manager in hierarchical crews. +**Fix:** For hierarchical processes, use Claude Sonnet 5 as the manager model (best tool-use reliability on Bedrock). Specialist agents can use cheaper models. Don't use Nova Micro or Llama Scout as the manager in hierarchical crews. ### Memory and context window @@ -87,7 +87,7 @@ These are real issues startups hit when keeping their existing framework and swa **Problem:** AutoGen's `GroupChat` uses the model to select the next speaker. This is a meta-task that requires the model to understand the conversation flow and pick the right agent. Claude handles this well; smaller Bedrock models may select speakers inconsistently. -**Fix:** Use Claude Sonnet 4.6 for the GroupChat manager. If using a cheaper model, consider switching to `round_robin` or custom `speaker_selection_method` instead of model-based selection. +**Fix:** Use Claude Sonnet 5 for the GroupChat manager. If using a cheaper model, consider switching to `round_robin` or custom `speaker_selection_method` instead of model-based selection. ### Code execution sandbox @@ -129,7 +129,7 @@ These are real issues startups hit when keeping their existing framework and swa ### Prompt sensitivity -**Problem:** Prompts optimized for GPT-4o may not perform identically on Claude Sonnet 4.6. Claude tends to be more literal and instruction-following; GPT-4o is more "creative" with ambiguous instructions. System prompts that rely on GPT-4o's implicit behaviors may need adjustment. +**Problem:** Prompts optimized for GPT-4o may not perform identically on Claude Sonnet 5. Claude tends to be more literal and instruction-following; GPT-4o is more "creative" with ambiguous instructions. System prompts that rely on GPT-4o's implicit behaviors may need adjustment. **Fix:** Test your top 20 most-used prompts on the target Bedrock model. Adjust prompts that produce degraded output. Claude generally responds better to explicit, structured instructions with clear formatting requirements. diff --git a/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/references/helpers/resolve-bedrock-model-id/resolve-bedrock-model-id.md b/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/references/helpers/resolve-bedrock-model-id/resolve-bedrock-model-id.md index 2e61d479..09a0aa74 100644 --- a/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/references/helpers/resolve-bedrock-model-id/resolve-bedrock-model-id.md +++ b/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/references/helpers/resolve-bedrock-model-id/resolve-bedrock-model-id.md @@ -9,7 +9,7 @@ the user to choose when the match is ambiguous. ## Input - `plan_model_id`: the target_model_id from the migration plan - (e.g., `anthropic.claude-sonnet-4-6-20250514-v1:0`) + (e.g., `anthropic.claude-sonnet-5`) - `region`: the AWS region from your context (e.g., `us-east-1`) ## Procedure diff --git a/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/bedrock_pricing.py b/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/bedrock_pricing.py index 10d9b186..58c45f31 100644 --- a/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/bedrock_pricing.py +++ b/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/bedrock_pricing.py @@ -43,11 +43,17 @@ def parse_price_dimensions(price_item: dict) -> dict: STATIC_FALLBACK = { "anthropic.claude-haiku-4-5-20251001-v1:0": {"input_per_1k_usd": 0.001, "output_per_1k_usd": 0.005}, "us.anthropic.claude-haiku-4-5-20251001-v1:0": {"input_per_1k_usd": 0.001, "output_per_1k_usd": 0.005}, + # Recommend default + "anthropic.claude-sonnet-5": {"input_per_1k_usd": 0.002, "output_per_1k_usd": 0.010}, + "us.anthropic.claude-sonnet-5": {"input_per_1k_usd": 0.002, "output_per_1k_usd": 0.010}, + # Still Active — existing workloads / fallbacks + "anthropic.claude-sonnet-4-6": {"input_per_1k_usd": 0.003, "output_per_1k_usd": 0.015}, + "us.anthropic.claude-sonnet-4-6": {"input_per_1k_usd": 0.003, "output_per_1k_usd": 0.015}, "anthropic.claude-sonnet-4-6-20250514-v1:0": {"input_per_1k_usd": 0.003, "output_per_1k_usd": 0.015}, "us.anthropic.claude-sonnet-4-6-20250514-v1:0": {"input_per_1k_usd": 0.003, "output_per_1k_usd": 0.015}, - "us.anthropic.claude-sonnet-4-6": {"input_per_1k_usd": 0.003, "output_per_1k_usd": 0.015}, - "anthropic.claude-opus-4-8-20250610-v1:0": {"input_per_1k_usd": 0.005, "output_per_1k_usd": 0.025}, - "us.anthropic.claude-opus-4-8-20250610-v1:0": {"input_per_1k_usd": 0.005, "output_per_1k_usd": 0.025}, + # Opus 4.8 has no dated foundation-model ID on the model card — suffix-less only. + "anthropic.claude-opus-4-8": {"input_per_1k_usd": 0.005, "output_per_1k_usd": 0.025}, + "us.anthropic.claude-opus-4-8": {"input_per_1k_usd": 0.005, "output_per_1k_usd": 0.025}, "amazon.nova-micro-v1:0": {"input_per_1k_usd": 0.000035, "output_per_1k_usd": 0.00014}, "amazon.nova-lite-v1:0": {"input_per_1k_usd": 0.00006, "output_per_1k_usd": 0.00024}, "amazon.nova-pro-v1:0": {"input_per_1k_usd": 0.0008, "output_per_1k_usd": 0.0032}, @@ -64,7 +70,7 @@ def _static_fallback(model_id: str) -> dict | None: entry = STATIC_FALLBACK.get(model_id) if entry: return {**entry, "available": True, "note": "static fallback (PriceList API had no entry)"} - # Try stripping the version suffix for a partial match (e.g. us.anthropic.claude-sonnet-4-6) + # Try stripping the version suffix for a partial match (e.g. us.anthropic.claude-sonnet-5) base = model_id.rsplit("-v", 1)[0] if "-v" in model_id else model_id for key, val in STATIC_FALLBACK.items(): if key.startswith(base): diff --git a/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/test_bedrock_pricing.py b/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/test_bedrock_pricing.py index bbb92210..475e06a0 100644 --- a/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/test_bedrock_pricing.py +++ b/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/test_bedrock_pricing.py @@ -42,10 +42,16 @@ def test_static_fallback_opus_4_8_rate_is_5_and_25_per_1m(): def test_static_fallback_partial_match(): - # us.anthropic.claude-sonnet-4-6 (no version suffix) should match - out = bp._static_fallback("us.anthropic.claude-sonnet-4-6") + # us.anthropic.claude-sonnet-5 (no version suffix) should match intro rates + out = bp._static_fallback("us.anthropic.claude-sonnet-5") assert out is not None assert out["available"] is True + assert out["input_per_1k_usd"] == 0.002 + assert out["output_per_1k_usd"] == 0.010 + +def test_static_fallback_keeps_sonnet_4_6(): + out = bp._static_fallback("us.anthropic.claude-sonnet-4-6") + assert out is not None assert out["input_per_1k_usd"] == 0.003 def test_static_fallback_unknown_returns_none(): @@ -57,7 +63,7 @@ def test_display_name_guess_derives_pricing_api_display_names(): # The Pricing API's 'model' attribute holds display names, not model ids. assert bp.display_name_guess("us.anthropic.claude-haiku-4-5-20251001-v1:0") == "Claude Haiku 4.5" assert bp.display_name_guess("amazon.nova-lite-v1:0") == "Nova Lite" - assert bp.display_name_guess("anthropic.claude-sonnet-4-6-20250514-v1:0") == "Claude Sonnet 4.6" + assert bp.display_name_guess("anthropic.claude-sonnet-5") == "Claude Sonnet 5" def test_parse_price_dimensions_ignores_cache_dimensions(): diff --git a/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/test_validate_result.py b/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/test_validate_result.py index 4d4876bc..9b88cd4e 100644 --- a/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/test_validate_result.py +++ b/migrate/plugins/migration-to-aws/skills/llm-to-bedrock/scripts/test_validate_result.py @@ -64,7 +64,7 @@ def validate(name, data): "eval_report_path": "/repo/.saws-migrate/eval-results/", "pass_rate": 0.89, "total_cases": 9, "failures": 1, "notes": "live_source_baseline_used_model: \n1 prompt needs manual review.", - "live_source_baseline": True, "judge_model": "claude-opus-4-7", + "live_source_baseline": True, "judge_model": "claude-opus-4-8", "source_baseline_quality": "good", }