Extract parsing, units and criteria into lambda-feedback-packages

.devcontainer/Dockerfile

@@ -0,0 +1,37 @@
+ARG PYTHON_VERSION=3.12
+FROM python:${PYTHON_VERSION}-slim
+
+# Matches the Python version used by GitHub Actions (test-lint.yml, staging-deploy.yml)
+# and the production image (app/Dockerfile), so tests behave the same locally.
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    git \
+    build-essential \
+    curl \
+    ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# Node.js, required to run the Claude Code CLI
+RUN curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
+    && apt-get install -y --no-install-recommends nodejs \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN npm install -g @anthropic-ai/claude-code
+
+# Claude Code refuses --dangerously-skip-permissions as root unless it knows
+# it's already inside an isolated sandbox (this container).
+ENV IS_SANDBOX=1
+
+# Run `claude` in this container with permission prompts bypassed by default,
+# since the container itself (not the CLI) is the safety boundary here. This
+# alias only affects the container image, never the host's `claude` config.
+RUN echo "alias claude='claude --dangerously-skip-permissions'" >> /etc/bash.bashrc
+
+WORKDIR /workspace
+
+COPY app/requirements.txt /tmp/requirements.txt
+RUN pip install --no-cache-dir --upgrade pip \
+    && pip install --no-cache-dir -r /tmp/requirements.txt \
+    && pip install --no-cache-dir pytest flake8
+
+ENV PYTHONPATH=/workspace

.devcontainer/devcontainer.json

@@ -0,0 +1,37 @@
+{
+  "name": "compareExpressions",
+  "build": {
+    "dockerfile": "Dockerfile",
+    "context": ".."
+  },
+  "workspaceFolder": "/workspace",
+  "workspaceMount": "source=${localWorkspaceFolder},target=/workspace,type=bind,consistency=cached",
+
+  "mounts": [
+    "source=${localEnv:HOME}/.claude,target=/root/.claude,type=bind,consistency=cached"
+  ],
+
+  "containerEnv": {
+    "PYTHONPATH": "/workspace",
+    "IS_SANDBOX": "1"
+  },
+
+  "customizations": {
+    "vscode": {
+      "extensions": [
+        "ms-python.python",
+        "ms-python.flake8",
+        "anthropic.claude-code"
+      ],
+      "settings": {
+        "python.defaultInterpreterPath": "/usr/local/bin/python",
+        "python.testing.pytestEnabled": true,
+        "python.testing.pytestArgs": []
+      }
+    }
+  },
+
+  "postCreateCommand": "pip install --no-cache-dir -r app/requirements.txt",
+
+  "remoteUser": "root"
+}

.gitignore

@@ -137,3 +137,18 @@ app/benchmark.py
 app/profiling_examples.py
 
 .idea/
+
+# Extracted packages live here as their own separate git repo
+/compareExpressions-packages/
+
+# OS / editor / local tool files
+.DS_Store
+.vscode/
+.junie/
+.mcp.json
+
+# Local virtual environments (e.g. .venv38)
+.venv*/
+
+# Test reports written by CI
+reports/

README.md

@@ -20,22 +20,26 @@ This version is specifically for python, however the ultimate goal is to make si
    - [Production API Gateway Integrations](https://eu-west-2.console.aws.amazon.com/apigateway/main/develop/integrations/attach?api=cttolq2oph&integration=qpbgva8&region=eu-west-2&routes=0xsoy4q)
 
 4. Merge commits into the default branch
-   - This will trigger the `test-and-deploy.yml` workflow, which will build the docker image, push it to a shared ECR repository, then call the backend `grading-function/ensure` route to build the necessary infrastructure to make the function available from the client app.
+   - This will trigger the `staging-deploy.yml` workflow (and `production-deploy.yml` on release), which will build the docker image, push it to a shared ECR repository, then call the backend `grading-function/ensure` route to build the necessary infrastructure to make the function available from the client app.
 
 5. You are now ready to start developing your function:
 
    - Edit the `app/evaluation.py` file, which ultimately gets called when the function is given the `eval` command
-   - Edit the `app/evaluation_tests.py` file to add tests which get run:
-       - Every time you commit to this repo, before the image is built and deployed 
-       - Whenever the `healthcheck` command is supplied to the deployed function
-   - Edit the `app/docs.md` file to reflect your changes. This file is baked into the function's image, and is made available using the `docs` command. This feature is used to display this function's documentation on our [Documentation](https://lambda-feedback.github.io/Documentation/) website once it's been hooked up!
+   - Add pytest tests to `app/evaluation_test.py`, `app/preview_test.py` or `app/tests/`. They get run:
+       - On every pull request and before the image is built and deployed (`pytest` from the repo root)
+       - Whenever the `healthcheck` command is supplied to the deployed function (via `app/evaluation_tests.py`)
+   - Edit `app/docs/user.md` and `app/docs/dev.md` to reflect your changes. These files are baked into the function's image, and is made available using the `docs` command. This feature is used to display this function's documentation on our [Documentation](https://lambda-feedback.github.io/Documentation/) website once it's been hooked up!
 
 ---
 
 ## How it works
 
 The function is built on top of a custom base layer, [BaseEvaluationFunctionLayer](https://github.com/lambda-feedback/BaseEvalutionFunctionLayer), which tools, tests and schema checking relevant to all evaluation functions.
 
+### Packages
+
+Expression parsing, unit handling and the criteria machinery come from the [lambda-feedback-packages](https://github.com/lambda-feedback/lambda-feedback-packages) repository (currently the `v0.3.0-rc.2` release candidate), installed as git dependencies in `app/requirements.txt`. See the "Packages" section of `app/docs/dev.md` for what each package does and how to develop against a local checkout.
+
 ### Docker & Amazon Web Services (AWS)
 
 The grading scripts are hosted AWS Lambda, using containers to run a docker image of the app. Docker is a popular tool in software development that allows programs to be hosted on any machine by bundling all its requirements and dependencies into a single file called an **image**.
@@ -57,7 +61,7 @@ Once the code passes all these tests, it will then be uploaded to AWS and will b
 ## Pre-requisites
 Although all programming can be done through the GitHub interface, it is recommended you do this locally on your machine. To do this, you must have installed:
 
-- Python 3.8 or higher.
+- Python 3.12 (the version used by CI and the production image).
 
 - GitHub Desktop or the `git` CLI.
 

app/.dockerignore

@@ -0,0 +1,12 @@
+# Build files
+Dockerfile
+.dockerignore
+
+# The base image provides the app package's __init__.py and handler
+__init__.py
+
+# Local and generated files
+**/__pycache__
+**/*.py[cod]
+**/.DS_Store
+**/.pytest_cache

app/Dockerfile

@@ -1,6 +1,4 @@
-# Base image that bundles AWS Lambda Python 3.8 image with some middleware functions
-# FROM base-eval-tmp
-# FROM rabidsheep55/python-base-eval-layer
+# Base image that bundles the AWS Lambda Python image with the lambda-feedback middleware (app.handler)
 FROM ghcr.io/lambda-feedback/baseevalutionfunctionlayer:main-3.12
 
 RUN dnf install -y git findutils && dnf clean all
@@ -13,46 +11,11 @@ ENV PYTHONPATH=/app
 COPY requirements.txt .
 RUN pip3 install -r requirements.txt
 
-# Copy main scripts
-COPY evaluation.py ./app/
-COPY evaluation_test.py ./app/
-COPY preview.py ./app/
-COPY preview_test.py ./app/
-
-# Copy contexts
-COPY context/physical_quantity.py ./app/context/
-COPY context/symbolic.py ./app/context/
-
-# Copy feedback messages
-COPY feedback/physical_quantity.py ./app/feedback/
-COPY feedback/symbolic.py ./app/feedback/
-
-# Copy preview implementations
-COPY preview_implementations/physical_quantity_preview.py ./app/preview_implementations/
-COPY preview_implementations/symbolic_preview.py ./app/preview_implementations/
-
-# Copy tests
-COPY tests/example_test.py ./app/tests/
-COPY tests/physical_quantity_evaluation_test.py ./app/tests/
-COPY tests/physical_quantity_preview_test.py ./app/tests/
-COPY tests/slr_quantity_test.py ./app/tests/
-COPY tests/symbolic_evaluation_test.py ./app/tests/
-COPY tests/symbolic_preview_test.py ./app/tests/
-
-# Copy utility code
-COPY utility/criteria_graph_utilities.py ./app/utility/
-COPY utility/criteria_parsing.py ./app/utility/
-COPY utility/evaluation_result_utilities.py ./app/utility/
-COPY utility/expression_utilities.py ./app/utility/
-COPY utility/physical_quantity_utilities.py ./app/utility/
-COPY utility/preview_utilities.py ./app/utility/
-COPY utility/slr_parsing_utilities.py ./app/utility/
-COPY utility/syntactical_comparison_utilities.py ./app/utility/
-COPY utility/unit_system_conversions.py ./app/utility/
-
-# Copy Documentation
-COPY docs/dev.md ./app/docs/dev.md
-COPY docs/user.md ./app/docs/user.md
+# The healthcheck command runs the pytest suite (see evaluation_tests.py)
+RUN pip3 install pytest
+
+# Copy the evaluation function source, tests and docs (exclusions in .dockerignore)
+COPY . ./app/
 
 # Set permissions so files and directories can be accessed on AWS
 RUN chmod 644 $(find . -type f)

app/conftest.py

@@ -0,0 +1,2 @@
+def pytest_configure(config):
+    config.addinivalue_line("markers", "slow: excluded from the deployed healthcheck (see evaluation_tests.py)")