---
title: "ADR-320: A run shows the model the provider named"
manual: "LLM Foundation"
version: "main"
permalink: "https://docs.typo3.org/permalink/netresearch/nr-llm:adr-320@main"
source: "Adr/Adr320ARunShowsTheModelTheProviderReported.rst"
rendered: "2026-11-18T02:03:14+00:00"
---

# ADR-320: A run shows the model the provider named {#adr-320}

-   *Status:* Accepted
-   *Date:* 2026-11-17
-   *Authors:* Netresearch DTT GmbH

## Context {#context}

Every provider call of a run carries the run's uuid as its correlation id
([ADR-153](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-153@main)), and the run timeline joins the telemetry rows of
that id. A row names the provider and model the call was sent to and, after a
fallback, the ones that served it.

Since [ADR-174](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-174@main) the same row also stores `response_model`:
the model the provider named on its response. That need not be the model the
call asked for. An alias such as `gpt-5` resolves to a dated snapshot, and
which snapshot answered is the fact that separates a model change from a skill
or input change when two runs of the same configuration answer differently.
`TelemetryRepository::findByCorrelation()` did not read the column, so
the timeline could not show it.

## Decision {#decision}

1.  `TelemetryRepository::findByCorrelation()` reads `response_model`
    and `TelemetryCall` carries it as `responseModel`.
1.  A provider-call row of the timeline shows it as `reportedModel` when it
    is not empty and differs from the model the call was sent to: the serving
    model after a fallback, the requested one otherwise. This is the rule the
    serving pair already follows; a repetition of the name already shown is
    left out.
1.  Nothing is derived from it. The timeline shows what the provider said; it
    does not decide whether the answer came from an acceptable model.

## Consequences {#consequences}

● An administrator can read on the run which snapshot of a model answered
each call, and tell two runs apart whose configuration and requested model are
equal.

◐ The value is metadata like the rest of the row: an identifier, never content
of the call. The timeline stays metadata only at every privacy level.

◑ The column is `''` wherever the call produced no usage block: a cache hit,
a failed call, the specialized operations and a plain streamed chat (see
[ADR-174](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-174@main)). Where a provider's answer names no model, the
adapter reports the requested id instead. The timeline shows nothing in both
cases, which cannot be told apart from a provider that repeated the requested
name.

◑ The value is what the adapter reports. `GeminiProvider` reports the
model id of the request and never reads one from the response, so a Gemini
call never shows `reportedModel`. The same holds for any provider that
names the alias it was sent, not the snapshot behind it.
