per-session models: every session owns its model + thinking level from birth

The reported bug (2026-09-28): every chat ran glm-5.3-flash regardless of
any pick, while composer and settings UIs agreed with each other and lied
about the run. Root cause: a fossil default-settings record (settings.json
chat section, frozen pre-slots-wave) was stamped verbatim into every new
chat at birth by the new-session flow, and resolveConversationSpec prefers
the per-chat record over the strong slot forever.

Owner redesign — models are per session, always; the strong slot is the
new-session default:

- POST /api/chats stamps the newborn verbatim from the strong slot
  (model + thinking level); no client settings PUT on create anymore
- the composer control is dual-bound: in-session it reads/writes the
  session's own record (GET /api/chats/:id, PUT .../settings); on the
  draft surfaces it binds the strong slot (picking there = changing the
  default)
- thinking levels follow the identical mechanics (confirmed by owner)
- the zombie default-settings system dies whole: useDefaultSettings,
  /api/settings/defaults, src/store/default-settings.ts, the chat
  section of UserSettings (sanitizer strips fossil copies), the legacy
  default-settings.json fold, and DEFAULT_SETTINGS_FILE
- catalogDefaultsFor collapses to the strong slot alone
- thinking display for a legacy unstamped session resolves exactly like
  the engine (session ?? strong ?? model ladder)

Tests: new chat-birth-stamp suite pins the stamp, the unconfigured boot,
the unset level, and the copy-not-live-view regression; defaults pins
rewritten strong-only; legacy-migration suite deleted.
This commit is contained in:
amosblomqvist
2026-09-28 23:30:11 +03:00
parent 1f5e21a674
commit 3e9a85d60f
27 changed files with 336 additions and 491 deletions
+10 -25
View File
@@ -86,11 +86,10 @@ describe("the model catalog projection", () => {
// the record is empty (defaults/slots NULL), on the owner's machine
// configured slots must surface exactly as configured.
const record = readSettings();
const chat = record?.chat;
const strong = effectiveSettings().models.strong;
if (chat?.model || strong) {
assert.ok(defaults, "a configured chain yields a default");
assert.deepEqual(defaults!.model, chat?.model ?? { provider: strong!.provider, id: strong!.id });
if (strong) {
assert.ok(defaults, "a configured strong slot yields a default");
assert.deepEqual(defaults!.model, { provider: strong.provider, id: strong.id });
} else {
assert.equal(defaults, null);
}
@@ -105,29 +104,15 @@ describe("the model catalog projection", () => {
}
});
it("defaults: the chat section over the strong slot; null when both empty (BYOK)", () => {
assert.equal(catalogDefaultsFor(undefined, null), null);
it("defaults: the strong slot verbatim; null when unset (BYOK, per-session models 2026-09-28)", () => {
assert.equal(catalogDefaultsFor(null), null);
const strong = { provider: "openrouter", id: "z-ai/glm-5.3-flash", thinkingLevel: "low" as const };
const d = catalogDefaultsFor(undefined, strong);
const d = catalogDefaultsFor(strong);
assert.deepEqual(d, { model: { provider: "openrouter", id: "z-ai/glm-5.3-flash" }, thinkingLevel: "low" });
assert.deepEqual(catalogDefaultsFor({ model: { provider: "openrouter", id: "qwen/qwen3.8-flash" }, thinkingLevel: "high" }, strong), {
model: { provider: "openrouter", id: "qwen/qwen3.8-flash" },
thinkingLevel: "high",
});
// partial: only the model chosen → level falls back to the slot's
const partial = catalogDefaultsFor({ model: { provider: "openrouter", id: "qwen/qwen3.8-flash" } }, strong);
assert.ok(partial);
assert.equal(partial!.thinkingLevel, "low");
// thinkingLevel-only record: model untouched
assert.deepEqual(catalogDefaultsFor({ thinkingLevel: "minimal" }, strong), {
model: { provider: "openrouter", id: "z-ai/glm-5.3-flash" },
thinkingLevel: "minimal",
});
// chat.model with NO strong slot: the conversation runs on it alone
assert.deepEqual(
catalogDefaultsFor({ model: { provider: "openrouter", id: "qwen/qwen3.8-flash" } }, null),
{ model: { provider: "openrouter", id: "qwen/qwen3.8-flash" } },
);
// No level stored → the model alone reports (the level resolves at
// engine build from DEFAULT_THINKING_ORDER).
const bare = catalogDefaultsFor({ provider: "openrouter", id: "qwen/qwen3.8-flash" });
assert.deepEqual(bare, { model: { provider: "openrouter", id: "qwen/qwen3.8-flash" } });
});
it("toModelDto projects the raw catalog model verbatim", () => {