Mateo/dev 25 write connecting arcade tools to your llm page

[torresmateo]

Preview here: https://docs-git-mateo-dev-25-write-connecting-arcade-a84eaa-arcade-ai.vercel.app/en/home/connect-arcade-to-your-llm

---

Note

Adds a Python-focused guide for integrating Arcade tools with an LLM and links it in the Guides sidebar.

• Docs:
  • Add app/en/home/connect-arcade-to-your-llm/page.mdx guide covering:
    • Project setup with uv, environment config, and OpenRouter usage.
    • Fetching Arcade tool definitions (formatted.get(..., format="openai")).
    • Helper to authorize and execute tools (tools.authorize, auth.wait_for_completion, tools.execute).
    • Multi-turn ReAct-style loop invoking the LLM (chat.completions.create) with tool calls handling.
    • Simple CLI chat loop and runnable example (uv run main.py).
• Navigation:
  • Update app/en/home/_meta.tsx to add "connect-arcade-to-your-llm" under Guides with title "Integrate Arcade tools into your LLM application".

^{Written by Cursor Bugbot for commit c707a66. This will update automatically on new commits. Configure here.}

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Review	Updated (UTC)
docs	Ready	Preview, Comment	Dec 18, 2025 1:28pm

[cursor]

Bug: Missing assistant message before tool results in history

When the LLM returns tool calls, the code appends tool result messages to history but never appends the assistant message that contained the tool_calls. The OpenAI API (and compatible APIs like OpenRouter) requires the assistant message with tool_calls to appear in the conversation history before the corresponding tool result messages. This will cause an API error on the next iteration of the loop when the malformed history is sent back to the model.

Additional Locations (1)

• app/en/home/connect-arcade-to-your-llm/page.mdx#L386-L400

 

[nearestnabors]

I need more openrouter tokens to actually test that it works, but wanted to share what I have so far!

[cursor]

Bug: Tool result shown as assistant response when max_turns exhausted

When invoke_llm exhausts max_turns while the assistant is still making tool calls, the function returns with a tool response as the last history item. The chat() function then accesses history[-1]["content"] and prints it prefixed with "🤖 Assistant:", displaying raw tool output as if it were the assistant's response. This produces confusing output when many consecutive tool calls are needed.

Additional Locations (1)

• app/en/home/connect-arcade-to-your-llm/page.mdx#L443-L446

 

[nearestnabors]

Still getting the same malformed directory structure after running the commands in step 1:

[torresmateo]

holding the merge until nav is merged
FYI @nearestnabors