Repoint public POST /tokenize at the orchestrator (tokenize -> agent -> restore)
so a single path returns {final, deidentified_prompt, agent_tokenized,
session_id} — matching what Fusion mirrors from the front-end path, and what
openapi.yaml already documents. The granular detector moves to internal
/tokenize-raw (x-api-key protected; the orchestrator calls it). /demo kept as an
alias so the UI keeps working.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Build the AWS side of the HNCB demo end to end (region ap-southeast-1):
- T1 /tokenize + T2 /restore: Lambdas behind a public API Gateway (shared-secret
auth), Presidio detection, random per-request tokens, DynamoDB vault; overlap
resolution so a ROC ID stays TW_ROC_ID.
- T3: Presidio made private (SG-locked to the tokenize Lambda in-VPC; DynamoDB
gateway endpoint); only /tokenize + /restore are public.
- T4: RAG Lambda registered as an MCP tool on an AgentCore Gateway (AWS_IAM/SigV4);
agentcore_setup.sh + a SigV4 MCP invoke test.
- T5: Strands agent deployed to AgentCore Runtime; SigV4 gateway auth, apac
inference profile, pinned deps.
- T6: advisor UI on S3+CloudFront with a Fusion-less demo orchestrator (/demo)
chaining tokenize -> runtime -> restore.
- T7: README runbook + trace check; teardown deletes gateway/runtime/memory/ECR.
Verified live: the cloud AgentCore/Bedrock trace shows only tokens, never the
real name. Secrets stay in gitignored local.auto.tfvars.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
