fix(server): send Codex the effort shown as default when a turn names none - #544

…ingdotgg#9921)

Fork adaptation: Fork #544 builds the Codex adapter after the provider snapshot so it can read each model's default effort, so the adapter and the text generation that now reads the snapshot's models are both created after it.

(cherry picked from commit a92161a)
Upstream-PR: 9921

> [!NOTE]
> New Codex threads start on GPT-6.1-Sol at medium effort. GPT-6.1-Sol
is listed as a current model with a "New" badge, and GPT-6-Sol moves to
legacy models. The effort picker now marks the effort that a turn
without an explicit choice actually runs at.

## Problem

OpenAI released GPT-6.1-Sol today. Codex CLI 0.159.0 lists it, but styal
filed it under legacy models, because the model manifest's current Codex
list only knew GPT-6-Sol. New Codex threads still defaulted to
GPT-6-Sol.

The effort picker also misreported the effort a new thread runs at. It
marked the effort Codex's catalog calls default, which is Low for
GPT-6.1-Sol and GPT-5.6-Sol. But a turn without an explicit effort sends
the collaboration mode's `medium` fallback, which overrides the catalog
default. An untouched GPT-6.1-Sol thread showed Low and ran at Medium.

Medium is also the effort to start at. In the independent FrontierCode
1.1 run through Codex, GPT-6.1-Sol scores 45.5 at low and 50.2 at
medium, with no gain above medium, for $0.36 per task at medium.
OpenAI's DeepSWE numbers show the same step from low to medium (64.4% to
73.0%).

## Change

- **Manifest:** `gpt-6.1-sol` replaces `gpt-6-sol` in the current Codex
models, and a `providers.codex` catalog entry gives it a `new` badge.
`classifyModels` now copies a catalog entry's badge onto a model that
Codex discovers. The entry can only badge or classify a model; it never
adds one that Codex doesn't list.
- **Default model:** `DEFAULT_MODEL` is `gpt-6.1-sol`. The preference
order is now GPT-6.1-Sol, GPT-6-Sol, GPT-6-Astra, then older models, so
Codex CLIs before 0.159.0 keep GPT-6-Sol.
- **Default effort:** `mapCodexModelCapabilities` marks `medium` as
styal's default whenever the model supports it, instead of Codex's
catalog default. Today that matches what untouched turns run at, because
the collaboration mode falls back to the same constant.
#544 makes the server send the
shown default explicitly. Only GPT-6.1-Sol and GPT-5.6-Sol show a
different default than before; the other current models already
defaulted to Medium in Codex's catalog.
- **Fork docs:** updated the `codex-default-model` ledger entry and the
styal differences page. Upstream still defaults to GPT-6-Astra at
`2cbc24f`.

This is written for the fork rather than imported. Upstream has an open
PR that adds the same manifest entry and badge support:
pingdotgg#14294. Upstream intake will
meet that change in `ModelManifest.ts` and `model-manifest.json`.

Installed styal servers fetch the model manifest from `main`, so after
merge they list GPT-6.1-Sol as current and GPT-6-Sol as legacy without
an update. The badge, the new default and the effort default need the
new server.

## Validation

- **Live run on a dev server** with isolated worktree state and Codex
CLI 0.159.0, using a separate `CODEX_HOME` so the global Codex install
and its cache were untouched:
- A new draft opens on **GPT-6.1-Sol · Medium**. The picker lists
GPT-6.1-Sol first with a New badge, and GPT-6-Sol under legacy models.
- A thread created with `gpt-6.1-sol` and no effort option answered a
real prompt. The server trace shows `sendTurn` with `provider.model:
gpt-6.1-sol`, and Codex's thread settings recorded `effort: "medium"`.
That is the run where the composer, before this change, showed Low.
- With Homebrew Codex 0.158.0, which doesn't list GPT-6.1-Sol, new
threads fell back to GPT-6-Sol.
- **Before:** the same setup on `main` opens new threads on GPT-6-Sol
and files GPT-6.1-Sol under legacy models.
- **Tests:** `ModelManifest.test.ts` covers badging discovered models.
`CodexProvider.test.ts` covers the medium effort default and the
GPT-6.1-Sol → GPT-6-Sol → GPT-6-Astra preference. The Codex provider,
adapter, session runtime and manifest suites pass. Three npm-update
tests in `CodexDriver.test.ts` fail locally on this machine; they fail
the same way on `main`.
- **Checks:** server and contracts typecheck; ledger check passes.
- **Not verified:** mobile. It reads the same provider snapshot and was
not run.

| Before (`main`) | After |
| --- | --- |
| ![Model picker on main: GPT-6-Sol default, GPT-6.1-Sol filed under
legacy](https://github.com/user-attachments/assets/c8fe8de8-a98b-46fd-8706-c877fb49bd5f)
| ![Model picker: GPT-6.1-Sol first with a New badge, GPT-6-Sol under
legacy](https://github.com/user-attachments/assets/8dfba26c-3041-4cf3-9b0a-fbb73882f010)
|

![Effort picker for GPT-6.1-Sol with Medium marked
default](https://github.com/user-attachments/assets/8ccb6466-d8fa-446b-9eb2-c23d8b6a294e)

---
Written by an agent (Claude Code, claude-opus-5-5).

…ingdotgg#9921)

Fork adaptation: Fork #544 builds the Codex adapter after the provider snapshot so it can read each model's default effort, so the adapter and the text generation that now reads the snapshot's models are both created after it. The manifest's legacy check keeps fork #543's catalog lookup helper and adds the Codex family fallback to it.

(cherry picked from commit a92161a)
Upstream-PR: 9921