Follow-up turn + previousResponseId + client tool call → "No tool call found for function call output with call_id"

Important limitations

• This may be one public report, not widespread demand.
• Current independent report count: 1.
• This is currently a single independent report. It has not passed clustering or human review as a verified signal.
• No market size, willingness to pay, competition, or trend claims are inferred here.

What was reported

Who is affected

Application developer using the reported software

Job to be done

Run tests reliably

Workflow

- `packages/openai/src/responses/openai-responses-language-model.test.ts` adds a regression test that fails with the primary provider error until the call and output remain paired.

Desired outcome

It looks like the intent (per #15795's own description — "Plain client-executed function calls must NOT be [sent as item_reference]… the matching function_call_output can only reference the call by call_id") was that plain client tool calls should fall through to the unconditional `function_call` push further down, so they pair with their output by `call_id` regardless of `store`/`previousResponseId`.

Severity

Not enough evidence yet.

Urgency

Not enough evidence yet.

Evidence indicators

What would upgrade this

• Additional independent reports from distinct communities or authors.
• Human clustering into a review signal, then explicit publication approval.
• Counter-evidence review and durable original-source verification.

Original source

Open the original public report