--- title: "ADR-275: A model record carries its reasoning profile" manual: "LLM Foundation" version: "main" permalink: "https://docs.typo3.org/permalink/netresearch/nr-llm:adr-275@main" source: "Adr/Adr275AModelRecordCarriesItsReasoningProfile.rst" rendered: "2026-11-12T15:41:35+00:00" --- # ADR-275: A model record carries its reasoning profile {#adr-275} - *Status:* Accepted - *Date:* 2026-11-09 - *Amends:* [ADR-203](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-203@main); [ADR-160](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-160@main) - *Authors:* Netresearch DTT GmbH ## Context {#context} The OpenAI adapter decides three things per model from a table in code, `OpenAiModelProfiles`: whether the model is a reasoning model (then sampling parameters such as `temperature` are not sent), which `reasoning_effort` values it accepts, and whether its tool calls go through Chat Completions or Responses ([ADR-203](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-203@main)). A model the table does not name needs a release before it works. On 2026-11-09 `gpt-6.1-terra` was such a model. It was listed by `GET /v1/models` and missing from the table, so a configured temperature and every tool call failed with HTTP 400. The same measurement showed the table itself wrong: OpenAI refuses `max` for every GPT-6 model, although the model pages list it (the receipt is in `specs/provider-profile-matrix.md`). No source can replace the table completely: - OpenAI's model object carries `id`, `object`, `created`, `owned_by` and `shutdown_date`. It states no reasoning, effort or tool capability. - OpenRouter's public `GET /api/v1/models` states per model a `reasoning` object (`mandatory`, `supported_efforts`) and `supported_parameters`. For the five GPT-6 models it agrees with OpenAI's own answers on reasoning, on a non-default `temperature` being unsupported, and on whether `none` is accepted (`mandatory: false` exactly where `none` works). It disagrees on the scale: it lists `max` for all five, which OpenAI refuses. It also lists `tools` for `gpt-6.1-terra`, which direct Chat Completions refuses: OpenRouter describes its own endpoint, not OpenAI's routes. - symfony/ai (`main` at `1fc422e47d`, 2026-11-06) keeps a hand-written OpenAI catalogue of about 70 models, throws `ModelNotFoundException` for any other name and accepts additional models through its constructor; `gpt-6.1-terra` is missing there too. Its OpenRouter bridge reads the live model list instead. ## Decision {#decision} ### 1\. The profile is resolved per model record, in this order {#1-the-profile-is-resolved-per-model-record-in-this-order} 1. **Operator override** on the model record: reasoning yes/no, an effort scale, a tool route. Each field is optional; an empty field defers to the next source. 1. **The bundled measured table** (`OpenAiModelProfiles`) for an exact family name or a dated snapshot of it. 1. **The discovered profile** stored on the record by the last discovery run, with its source (next section). 1. **The family default** in code, such as the GPT-6 default: reasoning, tools through Responses, no effort scale. 1. **Unknown**: not a reasoning model, legacy route, no effort. The bundled table outranks discovered data because each of its rows was measured against the API; a third party's catalogue may describe its own endpoint instead. The operator outranks everything because the operator can measure their own deployment, which no table can. ### 2\. The tool route is never discovered {#2-the-tool-route-is-never-discovered} Whether tools go through Chat Completions or Responses comes only from the operator, the bundled table or the family default. Neither source above states it for OpenAI's own endpoints; OpenRouter's `tools` flag describes OpenRouter. ### 3\. What each discovery source may set {#3-what-each-discovery-source-may-set} - **A provider's own model API**, where it states reasoning data about the endpoint being called: OpenRouter's `reasoning` object for a model configured on an OpenRouter provider. Reasoning yes/no and the effort scale are stored as OpenRouter states them, because they describe the endpoint the request goes to. Source `CapabilitySource::Discovery`. - **OpenRouter's public catalogue as metadata for a direct OpenAI model**, matched by `openai/`. Only reasoning yes/no is stored, never the scale, because the scale was measured to differ. Source `CapabilitySource::ThirdPartyCatalog`, a new case: folding it into `Discovery` would claim the called provider confirmed it, which is the conflation [ADR-160](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-160@main) exists to prevent. - No other discoverer stores a reasoning profile. Mistral, Gemini, Anthropic, Groq and Ollama listings state no reasoning flag the adapters consume. The third-party lookup is **off by default** and switched on in the extension configuration. It runs during model discovery only, never while a request is being sent, and sends no credential and no content: it is one anonymous `GET` of a public list. A failed lookup stores nothing and leaves the record as it was. ### 4\. Storage follows ADR-160's provenance pattern {#4-storage-follows-adr-160-s-provenance-pattern} The operator fields and the discovered fields are separate columns, so a discovery run never overwrites an operator decision and the backend can show which one applies. A missing discovered value is stored as empty, not as "no": "not measured" and "measured: not a reasoning model" stay different facts. ### 5\. Consumers {#5-consumers} - `OpenAiProvider` resolves the profile through the record when the adapter was created from a model record (`ProviderAdapterRegistry::createAdapterFromModel()`), and through the table alone otherwise, as before. - The configuration form's parameter constraints use the same resolved profile, so a reasoning model is not offered a temperature. - The model module shows the resolved profile and where each part came from. ## Consequences {#consequences} - A new OpenAI model works without a release once an operator sets its profile. The opt-in catalogue lookup supplies only the reasoning flag: for a model outside the known families it does not move tool calls to Responses and sets no effort scale, so a model that needs either still needs the operator to set the tool route or the scale. - The bundled table stays the place for measured facts and still needs a change when OpenAI changes a model; the operator override covers the time until then. - `CapabilitySource` gains a case. Code that matches on it exhaustively must handle the new value. - OpenRouter's data can be wrong for OpenRouter too; it is shown with its source and date, and an operator override corrects it. - The resolved profile applies only to adapter types served by `OpenAiProvider` (OpenAI, Azure OpenAI, Together, Fireworks, Perplexity, custom). An OpenRouter model's discovered profile is shown on the record and applied nowhere: OpenRouter's `reasoning` means the model can produce reasoning tokens, not that it refuses sampling parameters, and its adapter sends `temperature` regardless. - An OpenRouter-configured model's stored effort scale is recorded, but the OpenRouter adapter does not send an effort yet; that is a separate change.