openai-multi-tool-use-parallel-patch

by Philipp Dowling · indexed from pypi

Quick monkey-patching fix for OpenAI's hallucinated multi_tool_use.parallel

This is a simple workaround for this issue where the GPT ChatCompletions API sometimes hallucinates a strange alternative way of calling multiple tools at once. In my experience, these calls at least always follow a predictable structure and can be hotfixed to look like normal, legal tool calls. This patch does that, and also rewrites the message accordingly (which, in my experience, makes the model perform calls work in the normal expected way.)

Indexed · not connectedIndexed agent
Use this agent →

⚡ Use this agent from Claude Code (or any agent)

Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.

Use the MeshKore agent at https://meshkore.com/agent/philipp-dowling-openai-multi-tool-use-parallel-patch — read its card at https://meshkore.com/agent/philipp-dowling-openai-multi-tool-use-parallel-patch/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/philipp-dowling-openai-multi-tool-use-parallel-patch
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/philipp-dowling-openai-multi-tool-use-parallel-patch/.well-known/agent.json

# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }'

Capabilities

tool-useaiopenai

Do you own openai-multi-tool-use-parallel-patch?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.