Files
Maxim 9a103a0348 chore(examples): put the AgentCore example on uv projects (#6672)
## What

Converts `examples/integrations/agentcore` from unlocked
`requirements.txt` files to uv projects (`pyproject.toml` + `uv.lock`),
matching every other Python integration example in this repo.

## Why

The example already used uv as an *installer* — the agent images are
built from `ghcr.io/astral-sh/uv` and ran `uv pip install -r
requirements.txt` — but nothing was locked, so each image build
re-resolved transitive dependencies against whatever PyPI had that day.

That had already drifted into a hard break. `langgraph==1.0.10rc1`
resolved alongside a `langgraph-prebuilt` that reads `ExecutionInfo` off
`langgraph.runtime`, which 1.0.x does not export, so the LangGraph agent
raised `ImportError` at container start.

## The migration

- Both agents get a `pyproject.toml` + `uv.lock`; the Dockerfiles
install with `uv sync --locked` and run out of `/app/.venv`.
- LangGraph agent moves to `langgraph==1.1.6` / `langchain==1.2.15`, the
pair used by `examples/integrations/langgraph-python`, which resolves
the import failure. `langchain` was previously `>=0.3.0` while the code
uses the 1.x `create_agent` API.
- Four packages that shipped code imports directly were declared nowhere
and survived only as transitives: `boto3` (both agents, via
`agents/utils/ssm.py`), `PyJWT` (langgraph, via `agents/utils/auth.py`),
`langchain-core` (langgraph, via `tools/todos.py`), `botocore` (root,
via `scripts/utils.py`). All now declared; no resolved version changed.
- `aws-opentelemetry-distro` moves from a loose second `uv pip install`
into the locked set.
- The example root gets a project for the `scripts/` helpers. Their
`requirements.txt` listed the dependencies but nothing installed it, so
`uv run scripts/test-agent.py` — the command that script's own docstring
gives — failed on a missing `requests`.
- Deploy and local-dev scripts call `uv run` instead of bare `python3`;
preflight checks for `uv` rather than `python3`.

## Terraform

The docker-mode image hash read `patterns/<pattern>/requirements.txt`,
`patterns/utils`, a root-level `gateway/` and `tools/`, and a root
`pyproject.toml` — none of which exist here. `filesha256` on a missing
file is a plan-time error. Repointed at `agents/<pattern>` and
`agents/utils`, now hashing `pyproject.toml` and `uv.lock`.

The hash then had to exclude the virtualenv the migration creates:
`fileset(pattern_dir, "**/*.py")` saw 3114 files instead of 5, and the
computed hash differed depending on whether a developer had ever run the
agent locally — feeding `replace_triggered_by` and forcing a runtime
replacement. Measured: `5f9a98ef…` with a venv present vs `bacab1e1…`
without, on identical committed sources. The fix filters `.venv/` and
`venv/` and produces the clean-checkout digest in both cases.

## Review

Five review rounds plus a promotion audit, and nine defects this
migration introduced were found and fixed before merge. Each fix was
verified by running the thing, not by reading it:

- The image hash sweeping the local virtualenv (above).
- The undeclared direct dependencies (above).
- `scripts/test-agent.py` piped the child's output and never drained it,
deadlocking the agent, while the startup-timeout branch blocked forever
on a read — the only channel carrying uv's lockfile-drift error.
- `--local` treated any listener on port 8080 as the agent, so a foreign
process produced "Agent started successfully" while the real child died.
Adopting a running process is now explicit opt-in.
- The documented invocation contract had drifted across the two READMEs
and both scripts' usage text; a single reconciliation pass now owns all
of them, and every documented command was executed to confirm it works.
- The Terraform README named the CloudFormation deploy script, which
cannot read a Terraform deployment.
- Two `.env.example` entries parsed as their own trailing comment text
under Docker Compose.
- The build context shipped 898 MB of local-only artifacts (measured);
now 11 kB.
- Assorted comment and message inaccuracies, including a container env
block whose comment attributed a runtime-critical variable to uv.

## Repository hygiene

Two fixes the pre-merge gates surfaced rather than the review rounds:

- `oxfmt` on the example README and `tofu fmt` on the Terraform locals
file. The README break was introduced by this branch; the Terraform one
predates it but sits in a file this branch edits.
- The Terraform ignore rules were anchored to the top level, so the
provider cache `terraform init` writes beside every *nested* module was
fully stageable — a measured 834 MB one `git add -A` from being
committed. Switched to unanchored patterns, matching what this branch
already did for the virtualenv layout. Verified with `git check-ignore`
that the nested cache and lock file are now covered, tfstate and tfvars
still are, and no tracked file is caught by the wider patterns.

## Not addressed

Roughly 90 further findings are real but pre-existing and belong to four
follow-up subjects, listed in full in the review ledger:

- **Terraform module repair** — `terraform validate` fails on five
undeclared resources, so this module cannot plan at all. Zip mode
references an entry point and a packager directory that do not exist.
- **test-agent AG-UI correctness** — the request body fails
`RunAgentInput.model_validate` on both agents, and the response decoder
parses a pre-AG-UI format, so failures print nothing and exit 0.
- **README accuracy** — a `docs/` directory that does not exist, a wrong
Node floor, a teardown block whose second command never runs.
- **Deploy-script hardening** —
`infra-terraform/scripts/deploy-frontend.py` requires a Terraform output
nothing declares, so it exits 1 every run; the README now says so rather
than presenting it as a working path.

## Verification

Both images built for `linux/arm64` and the agent module imported inside
each, after every fix cycle. `uv lock --check` clean on all three
projects. Every documented command executed from its documented
directory. The virtualenv hash filter, the build-context reduction, the
pipe deadlock, the port-adoption fix and the env-file parsing were each
verified by measurement with before/after output. No repo CI job builds
or lints this example, so these local runs are the only coverage that
exists.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-08-26 21:36:43 +02:00
..

CopilotKit + AWS AgentCore

Chat UI with generative charts, shared-state todo canvas, and inline tool rendering — deployed on AWS Bedrock AgentCore. Pick LangGraph or Strands.

Prerequisites

Tool Version
AWS CLI configured (aws configure)
Node.js 18+
uv any recent release
Docker running

The Python side is managed entirely by uv — it provisions the interpreter, so there is no separate Python install step.

Deploy to AWS

  1. Create your config:

    cp config.yaml.example config.yaml
    # Edit config.yaml — set stack_name_base and admin_user_email
    
  2. Deploy:

    ./deploy-langgraph.sh                    # LangGraph agent (infra + frontend)
    ./deploy-langgraph.sh --skip-frontend    # infra/agent only
    ./deploy-langgraph.sh --skip-backend     # frontend only
    # or
    ./deploy-strands.sh                      # AWS Strands agent
    ./deploy-strands.sh --skip-frontend
    ./deploy-strands.sh --skip-backend
    
  3. Open the Amplify URL printed at the end. Sign in with your email.

Local Development

cd docker
cp .env.example .env
# Fill in AWS creds — STACK_NAME, MEMORY_ID, and aws-exports.json are auto-resolved
./up.sh --build
  • Frontend → hot reloads on save (volume mount + Vite)
  • Agent → rebuild on changes: docker compose up --build agent
  • Browserhttp://localhost:3000, auth redirects back to localhost

The full chain runs locally: browser:3000 → bridge:3001 → agent:8080. AWS is only used for Memory and Gateway (SSM/OAuth2).

See docs/LOCAL_DEVELOPMENT.md for full details.

Agent dependencies

Each single-agent directory under agents/langgraph-single-agent/ and strands-single-agent/ — is its own uv project with its own uv.lock, and the Dockerfiles install with uv sync --locked — so the image gets exactly the dependency set in the lockfile, not whatever resolves that day. agents/utils/ is the exception: it is shared source that both Dockerfiles COPY in, not a project, so it has no pyproject.toml or lockfile of its own and anything it imports must be declared in each agent that copies it.

cd agents/langgraph-single-agent
uv add some-package        # or edit pyproject.toml, then: uv lock

Either way, commit the updated uv.lock alongside pyproject.toml. Terraform hashes both, so a dependency change retriggers the image build on the next apply.

What's inside

Piece What it does
frontend/ Vite + React with CopilotKit chat, charts, todo canvas
agents/langgraph-single-agent/ LangGraph agent with tools + shared todo state
agents/strands-single-agent/ Strands agent with tools + shared todo state
pyproject.toml / uv.lock Dependencies for the scripts/ helpers
infra-cdk/ CDK: Cognito, AgentCore, CopilotKit Lambda bridge, Amplify
infra-terraform/ Terraform equivalent — see infra-terraform/README.md
docker/ Local dev via Docker Compose
docs/ LOCAL_DEVELOPMENT.md, LOCAL_DOCKER_TESTING.md

Architecture

Browser → API Gateway → CopilotKit Lambda (Node.js, AG-UI bridge)
                              ↓
                        AgentCore Runtime
                              ↓
                    langgraph_agent.py / strands_agent.py
                              ↓ MCP (OAuth2 M2M)
                        AgentCore Gateway → Lambda tools

Auth: Cognito OIDC → Bearer token forwarded from browser through Lambda to AgentCore.

Tear down

cd infra-cdk && npx cdk@latest destroy --all --output ../cdk.out-lg   # LangGraph stack
cd infra-cdk && npx cdk@latest destroy --all --output ../cdk.out-st   # Strands stack

Docs