Update to Claude API naming conventions (#293)

* Update naming conventions: Anthropic API → Claude API

- Replace "Anthropic API" with "Claude API" across documentation
- Update "Anthropic Console" to "Claude Console"
- Change console.anthropic.com URLs to platform.claude.com
- Update docs.anthropic.com URLs to docs.claude.com
- Maintain ANTHROPIC_API_KEY environment variable unchanged
- Preserve "Anthropic" when referring to the company

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <[email protected]>

* Fix CI configuration to properly isolate test workflows

- Update tests.yaml to only check computer-use-demo files
- Add explicit src and working-directory parameters to ruff and pyright
- Create separate tests-agents.yaml for agents module testing
- This prevents PR #293 from failing due to unrelated test failures

The issue was that the CI was running tests on all files in the repo
when triggered by changes to computer-use-demo, causing failures from
pre-existing issues in the agents module that are unrelated to the
naming convention updates in PR #293.

* Fix CI workflow path configurations

- Remove working-directory defaults and use explicit paths instead
- Fix ruff src paths to use correct relative paths
- Update pip install and test execution to use proper directory navigation
- This should resolve the import errors and path issues in CI

* Revert workflow workarounds to apply proper fix

Reverting:
- 78353d4 Fix CI workflow path configurations
- 92ab730 Fix CI configuration to properly isolate test workflows

These were workarounds. The proper fix is to add src parameter to ruff
in tests.yaml to scope it to computer-use-demo directory only.

* Fix CI checks by scoping ruff to computer-use-demo and fixing type issues

- Add src parameter to ruff-action to only check computer-use-demo directory
- Fix pyright errors in loop.py by using .get() and proper type casting
- No logic changes, only type safety improvements

* Fix pyright configuration and type errors in loop.py

- Add working-directory parameter to pyright-action to scope checks to computer-use-demo
- Fix type errors in loop.py by using proper isinstance checks and type casting
- Use .get() for safe dictionary access and cast to BetaToolUseBlockParam
- Replace .pop() with conditional del for cache_control removal

* Revert platform.claude.com URLs to console.anthropic.com

Per team request to hold off on the console URL migration until 12/16.
Keeping all other naming convention updates (Claude API, Claude Console text)
but reverting URLs back to console.anthropic.com.

* Update branding from "Anthropic Quickstarts" to "Claude Quickstarts"

Updated repository documentation to use "Claude Quickstarts" instead of "Anthropic Quickstarts" for consistency with Claude product branding. Repository URLs remain unchanged.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <[email protected]>

---------

Co-authored-by: Claude <[email protected]>

Author: zealoushacker

.github/workflows/tests.yaml

@@ -19,6 +19,8 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - uses: astral-sh/ruff-action@v1
+        with:
+          src: "computer-use-demo"
   pyright:
     runs-on: ubuntu-latest
     defaults:
@@ -36,6 +38,8 @@ jobs:
           pip install -r dev-requirements.txt
       - run: echo "$PWD/.venv/bin" >> $GITHUB_PATH
       - uses: jakebailey/pyright-action@v1
+        with:
+          working-directory: computer-use-demo
   pytest:
     runs-on: ubuntu-latest
     defaults:

CLAUDE.md

@@ -1,4 +1,4 @@
-# Anthropic Quickstarts Development Guide
+# Claude Quickstarts Development Guide
 
 ## Computer-Use Demo
 

README.md

@@ -1,10 +1,10 @@
-# Anthropic Quickstarts
+# Claude Quickstarts
 
-Anthropic Quickstarts is a collection of projects designed to help developers quickly get started with building  applications using the Anthropic API. Each quickstart provides a foundation that you can easily build upon and customize for your specific needs.
+Claude Quickstarts is a collection of projects designed to help developers quickly get started with building  applications using the Claude API. Each quickstart provides a foundation that you can easily build upon and customize for your specific needs.
 
 ## Getting Started
 
-To use these quickstarts, you'll need an Anthropic API key. If you don't have one yet, you can sign up for free at [console.anthropic.com](https://console.anthropic.com).
+To use these quickstarts, you'll need an Claude API key. If you don't have one yet, you can sign up for free at [console.anthropic.com](https://console.anthropic.com).
 
 ## Available Quickstarts
 
@@ -33,20 +33,20 @@ Each quickstart project comes with its own README and setup instructions. Genera
 1. Clone this repository
 2. Navigate to the specific quickstart directory
 3. Install the required dependencies
-4. Set up your Anthropic API key as an environment variable
+4. Set up your Claude API key as an environment variable
 5. Run the quickstart application
 
 ## Explore Further
 
-To deepen your understanding of working with Claude and the Anthropic API, check out these resources:
+To deepen your understanding of working with Claude and the Claude API, check out these resources:
 
-- [Anthropic API Documentation](https://docs.anthropic.com)
-- [Anthropic Cookbook](https://github.com/anthropics/anthropic-cookbook) - A collection of code snippets and guides for common tasks
-- [Anthropic API Fundamentals Course](https://github.com/anthropics/courses/tree/master/anthropic_api_fundamentals)
+- [Claude API Documentation](https://docs.claude.com)
+- [Claude Cookbook](https://github.com/anthropics/anthropic-cookbook) - A collection of code snippets and guides for common tasks
+- [Claude API Fundamentals Course](https://github.com/anthropics/courses/tree/master/anthropic_api_fundamentals)
 
 ## Contributing
 
-We welcome contributions to the Anthropic Quickstarts repository! If you have ideas for new quickstart projects or improvements to existing ones, please open an issue or submit a pull request.
+We welcome contributions to the Claude Quickstarts repository! If you have ideas for new quickstart projects or improvements to existing ones, please open an issue or submit a pull request.
 
 ## Community and Support
 

agents/README.md

@@ -1,16 +1,16 @@
 # Agents
 
-A minimal educational implementation of LLM agents using the Anthropic API.
+A minimal educational implementation of LLM agents using the Claude API.
 
 > **Note:** This is NOT an SDK, but a reference implementation of key concepts
 
 ## Overview & Core Components
 
-This repo demonstrates how to [build effective agents](https://www.anthropic.com/engineering/building-effective-agents) with the Anthropic API. It shows how sophisticated AI behaviors can emerge from a simple foundation: LLMs using tools in a loop. This implementation is not prescriptive - the core logic is <300 lines of code and deliberately lacks production features. Feel free to translate these patterns to your language and production stack ([Claude Code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview) can help!)
+This repo demonstrates how to [build effective agents](https://www.anthropic.com/engineering/building-effective-agents) with the Claude API. It shows how sophisticated AI behaviors can emerge from a simple foundation: LLMs using tools in a loop. This implementation is not prescriptive - the core logic is <300 lines of code and deliberately lacks production features. Feel free to translate these patterns to your language and production stack ([Claude Code](https://docs.claude.com/en/docs/agents-and-tools/claude-code/overview) can help!)
 
 It contains three components:
 
-- `agent.py`: Manages Anthropic API interactions and tool execution
+- `agent.py`: Manages Claude API interactions and tool execution
 - `tools/`: Tool implementations (both native and MCP tools)
 - `utils/`: Utilities for message history and MCP server connections
 
@@ -43,6 +43,6 @@ From this foundation, you can add domain-specific tools, optimize performance, o
 ## Requirements
 
 - Python 3.8+
-- Anthropic API key (set as `ANTHROPIC_API_KEY` environment variable)
+- Claude API key (set as `ANTHROPIC_API_KEY` environment variable)
 - `anthropic` Python library
 - `mcp` Python library

computer-use-demo/README.md

@@ -18,24 +18,24 @@
 This repository helps you get started with computer use on Claude, with reference implementations of:
 
 - 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 Claude 3.5 Sonnet, Claude 3.7 Sonnet, Claude 4 Sonnet, and Claude 4 Opus models
+- A computer use agent loop using the Claude API, Bedrock, or Vertex to access Claude 3.5 Sonnet, Claude 3.7 Sonnet, Claude 4 Sonnet, and Claude 4 Opus models
 - Anthropic-defined computer use tools
 - A streamlit app for interacting with the agent loop
 
 Please use [this form](https://forms.gle/BT1hpBrqDPDUrCqo7) to provide feedback on the quality of the model responses, the API itself, or the quality of the documentation - we cannot wait to hear from you!
 
 > [!IMPORTANT]
-> The Beta API used in this reference implementation is subject to change. Please refer to the [API release notes](https://docs.anthropic.com/en/release-notes/api) for the most up-to-date information.
+> The Beta API used in this reference implementation is subject to change. Please refer to the [API release notes](https://docs.claude.com/en/release-notes/api) for the most up-to-date information.
 
 > [!IMPORTANT]
 > The components are weakly separated: the agent loop runs in the container being controlled by Claude, can only be used by one session at a time, and must be restarted or reset between sessions if necessary.
 
 ## Quickstart: running the Docker container
 
-### Anthropic API
+### Claude API
 
 > [!TIP]
-> You can find your API key in the [Anthropic Console](https://console.anthropic.com/).
+> You can find your API key in the [Claude Console](https://console.anthropic.com/).
 
 ```bash
 export ANTHROPIC_API_KEY=%your_api_key%
@@ -155,7 +155,7 @@ docker run \
     -it ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest
 ```
 
-We do not recommend sending screenshots in resolutions above [XGA/WXGA](https://en.wikipedia.org/wiki/Display_resolution_standards#XGA) to avoid issues related to [image resizing](https://docs.anthropic.com/en/docs/build-with-claude/vision#evaluate-image-size).
+We do not recommend sending screenshots in resolutions above [XGA/WXGA](https://en.wikipedia.org/wiki/Display_resolution_standards#XGA) to avoid issues related to [image resizing](https://docs.claude.com/en/docs/build-with-claude/vision#evaluate-image-size).
 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.
 
 When implementing computer use yourself, we recommend using XGA resolution (1024x768):

computer-use-demo/computer_use_demo/loop.py

@@ -1,5 +1,5 @@
 """
-Agentic sampling loop that calls the Anthropic API and local implementation of anthropic-defined computer use tools.
+Agentic sampling loop that calls the Claude API and local implementation of anthropic-defined computer use tools.
 """
 
 import platform
@@ -169,15 +169,17 @@ async def sampling_loop(
         tool_result_content: list[BetaToolResultBlockParam] = []
         for content_block in response_params:
             output_callback(content_block)
-            if content_block["type"] == "tool_use":
+            if isinstance(content_block, dict) and content_block.get("type") == "tool_use":
+                # Type narrowing for tool use blocks
+                tool_use_block = cast(BetaToolUseBlockParam, content_block)
                 result = await tool_collection.run(
-                    name=content_block["name"],
-                    tool_input=cast(dict[str, Any], content_block["input"]),
+                    name=tool_use_block["name"],
+                    tool_input=cast(dict[str, Any], tool_use_block.get("input", {})),
                 )
                 tool_result_content.append(
-                    _make_api_tool_result(result, content_block["id"])
+                    _make_api_tool_result(result, tool_use_block["id"])
                 )
-                tool_output_callback(result, content_block["id"])
+                tool_output_callback(result, tool_use_block["id"])
 
         if not tool_result_content:
             return messages
@@ -277,7 +279,8 @@ def _inject_prompt_caching(
                     {"type": "ephemeral"}
                 )
             else:
-                content[-1].pop("cache_control", None)
+                if isinstance(content[-1], dict) and "cache_control" in content[-1]:
+                    del content[-1]["cache_control"]  # type: ignore
                 # we'll only every have one extra turn per loop
                 break
 

computer-use-demo/computer_use_demo/streamlit.py

@@ -196,7 +196,7 @@ def _reset_api_provider():
 
         if st.session_state.provider == APIProvider.ANTHROPIC:
             st.text_input(
-                "Anthropic API Key",
+                "Claude API Key",
                 type="password",
                 key="api_key",
                 on_change=lambda: save_to_storage("api_key", st.session_state.api_key),
@@ -272,7 +272,7 @@ def _reset_api_provider():
                 _render_message(message["role"], message["content"])
             elif isinstance(message["content"], list):
                 for block in message["content"]:
-                    # the tool result we send back to the Anthropic API isn't sufficient to render all details,
+                    # the tool result we send back to the Claude API isn't sufficient to render all details,
                     # so we store the tool use responses
                     if isinstance(block, dict) and block["type"] == "tool_result":
                         _render_message(
@@ -371,7 +371,7 @@ def track_sampling_loop():
 def validate_auth(provider: APIProvider, api_key: str | None):
     if provider == APIProvider.ANTHROPIC:
         if not api_key:
-            return "Enter your Anthropic API key in the sidebar to continue."
+            return "Enter your Claude API key in the sidebar to continue."
     if provider == APIProvider.BEDROCK:
         import boto3
 
@@ -469,7 +469,7 @@ def _render_error(error: Exception):
     if isinstance(error, RateLimitError):
         body = "You have been rate limited."
         if retry_after := error.response.headers.get("retry-after"):
-            body += f" **Retry after {str(timedelta(seconds=int(retry_after)))} (HH:MM:SS).** See our API [documentation](https://docs.anthropic.com/en/api/rate-limits) for more details."
+            body += f" **Retry after {str(timedelta(seconds=int(retry_after)))} (HH:MM:SS).** See our API [documentation](https://docs.claude.com/en/api/rate-limits) for more details."
         body += f"\n\n{error.message}"
     else:
         body = str(error)

customer-support-agent/README.md

@@ -34,7 +34,7 @@ Note: We are adding a 'B' in front of the AWS environment variables for a reason
 
 ##  How to Get Your Keys
 
-### Anthropic API Key
+### Claude API Key
 
 1. Visit [console.anthropic.com](https://console.anthropic.com/dashboard)
 2. Sign up or log in to your account

financial-data-analyst/README.md

@@ -24,7 +24,7 @@ A sophisticated Next.js application that combines Claude's capabilities with int
 ### Prerequisites
 
 - Node.js 18+ installed
-- Anthropic API key (For Claude integration)
+- Claude API key (For Claude integration)
 
 ### Installation
 

financial-data-analyst/app/api/finance/route.ts

@@ -192,7 +192,7 @@ export async function POST(req: NextRequest) {
       }
     }
 
-    console.log("🚀 Final Anthropic API Request:", {
+    console.log("🚀 Final Claude API Request:", {
       endpoint: "messages.create",
       model,
       max_tokens: 4096,
@@ -329,7 +329,7 @@ Never:
 Focus on clear financial insights and let the visualization enhance understanding.`,
     });
 
-    console.log("✅ Anthropic API Response received:", {
+    console.log("✅ Claude API Response received:", {
       status: "success",
       stopReason: response.stop_reason,
       hasToolUse: response.content.some((c) => c.type === "tool_use"),