Choose a model and a reasoning effort before a Thread starts

[QuintinBotes]

Replaces #34, which GitHub auto-closed when its base branch was deleted on merging #33. Same work, rebased onto main so the diff is only its own.

LaunchConfig.model already existed and already emitted --model. Nothing ever set it, so the plumbing was there and unreachable: every Thread ran whatever the CLI defaulted to, and the single thing that most changes what a Thread costs was the one thing the composer could not express.

What is new

--effort is confirmed present on the shipped 2.1.220 binary, taking low, medium, high, xhigh, max. It had been assumed to be a slash command only, so this was verified against the binary rather than the docs.

The options are declared by the adapter, not listed in the UI

The rule the mode picker already follows: a control offering a choice the runtime would reject is worse than one offering none. AgentRuntime::launch_options() returns empty by default, so a runtime that takes neither draws no controls, and Codex does not get a picker full of Claude aliases.

Models are aliases, not pinned identifiers, because claude --help documents them as tracking whatever is current. A pinned claude-opus-4-1 rots in the worst way: the old name still resolves, so it fails by quietly running last year's model rather than by erroring.

The effort list has to be exact, and a test pins it. An unrecognised --effort value is only a warning — the CLI prints one line, falls back to the default, and runs anyway. A typo there yields a session that appears to run at the requested effort and does not.

Details

• The alias and the model it resolved to are shown together once the session reports back, since they differ and the difference is the cost.
• An empty selection means "whatever the profile already chooses" and is never sent as an empty flag value.
• Switching profile clears both, because a profile can switch runtime.
• launch_options rides on agents_overview, not agents_discovery: the composer draws before anything is probed.

Verified against the real binary: on this account --model sonnet resolves to claude-sonnet-5.