Use server model defaults for fresh TUI startup (#43177)

## Why

Fresh startup could use saved client model and reasoning settings that differ from the app server's effective configuration. A cleared server model could also leave startup using a stale client model from bootstrap.

## What changed

- Reuse the new-session defaults reader at startup to load `model` and `model_reasoning_effort` through `config/read` before `thread/start`, using the appropriate embedded or remote working directory.
- Preserve explicit CLI and selected-profile settings, then apply managed new-thread defaults with the existing precedence rules.
- When the server has no configured model, select the startup model from its model catalog, falling back to the bootstrap default if the catalog is empty.
- Fall back to local defaults when older servers do not support `config/read`; stop startup before thread creation on other read failures.

## Testing

Add request-level tests for defaults and override precedence, working-directory selection, cleared-model fallback, request ordering, unsupported servers, and read failures.

GitOrigin-RevId: e094ba5d5501fdb34c393a0117b34dd93d8d4f2b
This commit is contained in:
Eric Traut authored and copyberry committed 2026-09-06 07:31:40 +00:00
1 parent 6af345407d
commit 9587c9ef36
6 files changed
+581 -53

No files matched your search

+6
View File
@@ -42,6 +42,12 @@ where
}
}
pub(crate) fn quiet_startup_test_pump() -> StartupDraftPump {
let mut pump = startup_test_pump(std::iter::empty());
pump.events = Box::pin(futures::stream::pending());
pump
}
#[test]
fn startup_draft_renders_full_empty_and_multiline_composer_frames() {
let mut pump = startup_test_pump(std::iter::empty());