OpenAI-compatible streaming tool calls fail when function.name arrives in a later chunk

[wattmto]

Description

OpenAI-compatible streaming tool calls can fail when a provider/model sends the first tool_calls delta with an id and function.arguments, but without function.name, and then sends function.name in a later delta.

OpenCode currently treats the first partial tool-call delta as invalid and throws:

AI_InvalidResponseDataError: Expected 'function.name' to be a string.

This appears to be a streaming parser robustness issue. OpenAI-compatible streaming responses may split tool-call fields across deltas, so a partial chunk should be accumulated until enough data exists to emit the tool call.

This is similar in spirit to vercel/ai#6687, where provider-specific OpenAI-compatible tool-call chunks were valid after accumulation but failed because the parser expected a more complete shape too early.

Expected Behavior

The following streamed chunks should be accumulated into a single valid tool call:

{
  "id": "call_123",
  "type": "function",
  "function": {
    "name": "bash",
    "arguments": "{\"command\": \"ls -la\"}"
  }
}

OpenCode should execute the bash tool after the function.name and complete JSON arguments have been received.

Actual Behavior

OpenCode throws before the later chunk containing function.name is processed:

AI_InvalidResponseDataError: Expected 'function.name' to be a string.

Minimal Reproduction

This mock OpenAI-compatible SSE stream reproduces the chunk ordering. The key part is the second chunk: it contains id, type, and function.arguments, but no function.name. The third chunk then provides function.name.

const chunks = [
  `data: {"choices":[{"finish_reason":null,"index":0,"delta":{"role":"assistant","content":null}}]}`,
  `data: {"choices":[{"finish_reason":null,"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_123","type":"function","function":{"arguments":""}}]}}]}`,
  `data: {"choices":[{"finish_reason":null,"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_123","type":"function","function":{"name":"bash","arguments":"{"}}]}}]}`,
  `data: {"choices":[{"finish_reason":null,"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\u0022command\\u0022"}}]}}]}`,
  `data: {"choices":[{"finish_reason":null,"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":": \\u0022ls -la\\u0022}"}}]}}]}`,
  `data: {"choices":[{"finish_reason":"tool_calls","index":0,"delta":{}}]}`,
  `data: [DONE]`,
]

const stream = new ReadableStream({
  start(controller) {
    for (const chunk of chunks) {
      controller.enqueue(new TextEncoder().encode(`${chunk}\n\n`))
    }
    controller.close()
  },
})

const response = new Response(stream, {
  status: 200,
  headers: { "Content-Type": "text/event-stream" },
})

A parser that consumes this response should delay validation/emission of the tool call until function.name has arrived and the accumulated arguments are complete.

Raw SSE Stream

data: {"choices":[{"finish_reason":null,"index":0,"delta":{"role":"assistant","content":null}}]}

data: {"choices":[{"finish_reason":null,"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_123","type":"function","function":{"arguments":""}}]}}]}

data: {"choices":[{"finish_reason":null,"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_123","type":"function","function":{"name":"bash","arguments":"{"}}]}}]}

data: {"choices":[{"finish_reason":null,"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\u0022command\\u0022"}}]}}]}

data: {"choices":[{"finish_reason":null,"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":": \\u0022ls -la\\u0022}"}}]}}]}

data: {"choices":[{"finish_reason":"tool_calls","index":0,"delta":{}}]}

data: [DONE]

Suggested Fix Direction

Accumulate partial tool-call deltas by index/id and only emit/validate the tool call once function.name is available. If the stream finishes and a pending tool call still has no function.name, then it should remain an invalid response.

Related

• Similar parser robustness issue in Vercel AI SDK: Tool Calls Fail with Empty Arguments in OpenAI-Compatible Provider vercel/ai#6687
• Existing OpenCode report with captured local-model stream: Weird error with toolcalling on local model #6649

[github-actions]

This issue might be a duplicate of existing issues. Please check:

• Weird error with toolcalling on local model #6649: Same root cause and identical error message (AI_InvalidResponseDataError: Expected 'function.name' to be a string.) with the same chunk ordering pattern — function.name arriving in a later delta than function.arguments. You referenced this issue yourself; it may be worth consolidating there.

[wattmto]

Closing because this minimum reproduction targets the upstream OpenAI-compatible streaming parser behavior and should be filed against vercel/ai instead.