aws-samples / aws-samples/sample-autonomous-cloud-coding-agents
feat(agent): S3-backed Claude SDK session store
- Dominant language
- TypeScript
- Stars
- 143
- Forks
- 46
- Avg merge
- 3d 9h
- Merged PRs (30d)
- 20
Description
**Context:** ROADMAP.md → S3-backed SDK session store (portable transcripts)
---
## Component
Agent (Python runtime)
## Describe the feature
Plumb the Claude Agent SDK **`SessionStore`** to S3 (dedicated bucket or prefix) with:
- Eager flush, IAM-scoped access, conditional part creates, checksums, adaptive retries, structured logging
- Metrics/alarms on transcript mirror failures
- Graceful shutdown (`disconnect` on SIGTERM/cancel) so in-flight frames flush
- Persist **`task_id` ↔ Claude session UUID** (from first `ResultMessage`) for resume on another worker
- Keep agent **`cwd` stable** so SDK-derived `project_key` paths stay predictable
- Plan **compaction** when part count threatens resume latency
- Optional **S3 Express One Zone** when fleet is single-AZ
Complements shipped **Persistent session storage** (`/mnt/workspace` FUSE caches) and end-of-task **trace** upload to `traces/...jsonl.gz`.
## Use case
In-VM caches do not survive worker migration or long pauses. Portable transcripts enable resume, debugging, and compliance without relying solely on end-of-task trace upload.
## Proposed solution
1. S3 prefix per `task_id` + SDK `project_key`; SessionRole scoped writes.
2. Flush on frame boundary; `disconnect` on shutdown.
3. Alarms on mirror failures; structured logging.
4. Compaction when part count threatens resume latency.
5. Optional S3 Express One Zone when fleet is single-AZ.
6. Map first `ResultMessage` session UUID to `task_id` in DynamoDB for cross-worker resume.
## Other information
- Shipped: persistent session storage on `/mnt/workspace`; execution tracing to `traces/...jsonl.gz`.
- Design context: `docs/design/COMPUTE.md`, `docs/design/OBSERVABILITY.md`.
- [ ] This might be a breaking change
Contributor guide
Research direction
Start with ROADMAP.md and the design context in docs/design/COMPUTE.md and docs/design/OBSERVABILITY.md. Then locate the shipped /mnt/workspace session storage and traces/...jsonl.gz upload entry points. Done means an agreed implementation covers portable SessionStore mirroring, cross-worker session mapping, shutdown flushing, failure alarms, retries, and compaction.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws, python
- Domain
- backend, cloud, distributed-systems, observability
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100