Merge remote-tracking branch 'origin/main' into nm/upgrade-sdk

.github/workflows/build.yaml

@@ -4,11 +4,13 @@ name: build
 on:
   pull_request:
     paths:
-     - computer-use-demo/**
+      - .github/**
+      - computer-use-demo/**
   push:
     branches:
       - main
     paths:
+      - .github/**
       - computer-use-demo/**
 jobs:
   build:
@@ -86,7 +88,7 @@ jobs:
         uses: docker/build-push-action@v5
         with:
           platforms: linux/${{ matrix.platform }}
-          context: .
+          context: computer-use-demo
           push: true
           tags: ${{ env.PUSH_TAGS }}
           cache-from: type=gha,scope=computer-use-${{ matrix.platform }}

.github/workflows/tests.yaml

@@ -1,9 +1,15 @@
 name: tests
 on:
-  pull_request: {}
+  pull_request:
+    paths:
+      - .github/**
+      - computer-use-demo/**
   push:
     branches:
       - main
+    paths:
+      - .github/**
+      - computer-use-demo/**
 jobs:
   ruff:
     runs-on: ubuntu-latest

.pre-commit-config.yaml

@@ -0,0 +1,24 @@
+files: ^computer-use-demo/
+default_stages: [pre-commit, pre-push]
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
+    hooks:
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.6.7
+    hooks:
+      - id: ruff
+        name: Run `ruff` to autofix lint errors
+        args: [--fix-only]
+      - id: ruff
+        name: Run `ruff` to format code
+        entry: ruff format --force-exclude
+      - id: ruff
+        name: Run `ruff` to lint code
+  - repo: https://github.com/RobertCraigie/pyright-python
+    rev: v1.1.384
+    hooks:
+      - id: pyright

computer-use-demo/README.md

@@ -14,7 +14,7 @@
 
 This repository helps you get started with computer use on Claude, with reference implementations of:
 
-* Build files to create a Docker container with all nescessary dependencies
+* Build files to create a Docker container with all necessary dependencies
 * A computer use agent loop using the Anthropic API, Bedrock, or Vertex to access the updated Claude 3.5 Sonnet model
 * Anthropic-defined computer use tools
 * A streamlit app for interacting with the agent loop
@@ -43,14 +43,7 @@ docker run \
     -it ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest
 ```
 
-Once the container is running, open your browser to [http://localhost:8080](http://localhost:8080) to access the combined interface that includes both the agent chat and desktop view.
-
-The container stores settings like API key and custom system prompt in `~/.anthropic/`. Mount this directory to persist these settings between container runs.
-
-Alternative access points:
-- Streamlit interface only: [http://localhost:8501](http://localhost:8501)
-- Desktop view only: [http://localhost:6080/vnc.html](http://localhost:6080/vnc.html)
-- Direct VNC connection: `vnc://localhost:5900` (for VNC clients)
+Once the container is running, see the [Accessing the demo app](#accessing-the-demo-app) section below for instructions on how to connect to the interface.
 
 ### Bedrock
 
@@ -74,6 +67,8 @@ docker run \
     -it ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest
 ```
 
+Once the container is running, see the [Accessing the demo app](#accessing-the-demo-app) section below for instructions on how to connect to the interface.
+
 #### Option 2: Use an access key and secret
 
 ```bash
@@ -93,7 +88,10 @@ docker run \
     -it ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest
 ```
 
+Once the container is running, see the [Accessing the demo app](#accessing-the-demo-app) section below for instructions on how to connect to the interface.
+
 ### Vertex
+
 You'll need to pass in Google Cloud credentials with appropriate permissions to use Claude on Vertex.
 
 ```bash
@@ -112,11 +110,27 @@ docker run \
     -p 8080:8080 \
     -it computer-use-demo
 ```
+
+Once the container is running, see the [Accessing the demo app](#accessing-the-demo-app) section below for instructions on how to connect to the interface.
+
 This example shows how to use the Google Cloud Application Default Credentials to authenticate with Vertex.
 
 You can also set `GOOGLE_APPLICATION_CREDENTIALS` to use an arbitrary credential file, see the [Google Cloud Authentication documentation](https://cloud.google.com/docs/authentication/application-default-credentials#GAC) for more details.
 
+### Accessing the demo app
+
+Once the container is running, open your browser to [http://localhost:8080](http://localhost:8080) to access the combined interface that includes both the agent chat and desktop view.
+
+The container stores settings like the API key and custom system prompt in `~/.anthropic/`. Mount this directory to persist these settings between container runs.
+
+Alternative access points:
+
+- Streamlit interface only: [http://localhost:8501](http://localhost:8501)
+- Desktop view only: [http://localhost:6080/vnc.html](http://localhost:6080/vnc.html)
+- Direct VNC connection: `vnc://localhost:5900` (for VNC clients)
+
 ## Screen size
+
 Environment variables `WIDTH` and `HEIGHT` can be used to set the screen size. For example:
 
 ```bash
@@ -137,6 +151,7 @@ We do not recommend sending screenshots in resolutions above [XGA/WXGA](https://
 Relying on the image resizing behavior in the API will result in lower model accuracy and slower performance than implementing scaling in your tools directly. The `computer` tool implementation in this project demonstrates how to scale both images and coordinates from higher resolutions to the suggested resolutions.
 
 ## Development
+
 ```bash
 ./setup.sh  # configure venv, install development dependencies, and install pre-commit hooks
 docker build . -t computer-use-demo:local  # manually build the docker image (optional)
@@ -151,4 +166,5 @@ docker run \
     -p 8080:8080 \
     -it computer-use-demo:local  # can also use ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest
 ```
+
 The docker run command above mounts the repo inside the docker image, such that you can edit files from the host. Streamlit is already configured with auto reloading.

pyproject.toml

@@ -0,0 +1,4 @@
+[tool.pyright]
+venvPath = "computer-use-demo"
+venv = ".venv"
+useLibraryCodeForTypes = false