feat(llm B.1 #27): Test LLM button with classified error diagnostics
Some checks failed
check / cargo check (macos-latest) (push) Has been cancelled
check / cargo check (ubuntu-22.04) (push) Has been cancelled
check / cargo check (windows-latest) (push) Has been cancelled
check / svelte build + lint (push) Has been cancelled

The brief's pain point is opaque load failures: llama-cpp-2's errors
bubble up as raw C++ strings ("cudaMalloc failed: out of memory",
"invalid gguf magic"). A user seeing that has no path to recovery.

New backend command test_llm_model runs a staged diagnostic:
  1. Model not downloaded → `not-downloaded` + download hint.
  2. File size ≤90% of expected → `incomplete` (stalled download)
     + re-download hint. Matters because llama-cpp-2 can segfault
     on truncated GGUF rather than returning cleanly.
  3. Requested model already loaded → `ready`, no side effects.
  4. Otherwise attempt a real load. On failure, classify_llm_load_error
     maps the raw string to one of:
       - load-failed-vram         (OOM / cudaMalloc / allocation)
       - load-failed-corrupt      (GGUF magic / unsupported format)
       - load-failed-permission   (permission denied / access denied)
       - load-failed-other        (catch-all)
     Each category has a prewritten actionable hint pointing at the
     specific Settings surface (tier picker, re-download, file perms).

classify_llm_load_error is pure-string and unit-tested — 8 cases
covering the main categories plus edge cases (OOM alias, Windows
"Access is denied", unknown errors). Ordered narrow-to-broad so
overlap doesn't misclassify.

Settings UI gets a "Test" button in the AI section's action row,
visible whenever the model is downloaded (both downloaded-idle and
loaded states). Shows inline hint below the status line when the
test surfaces one. Refreshes both local and global LLM status after
the test since a successful test implicitly loads the model.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-21 17:04:11 +01:00
parent 70b97c5273
commit a57da0feb5
3 changed files with 257 additions and 0 deletions

View File

@@ -562,6 +562,37 @@
}
}
// Brief item B.1 #27: diagnostic button that classifies LLM setup
// failures into actionable categories. Result shape comes from the
// backend — category / ok / message / hint. `llmTestHint` is held
// separately so we can render it below the one-line status without
// stomping the existing llmStatus string.
let llmTestBusy = $state(false);
let llmTestHint = $state("");
async function testSelectedLlmModel() {
if (llmTestBusy) return;
const modelId = selectedLlmModelId();
llmTestBusy = true;
llmStatus = "Testing...";
llmTestHint = "";
try {
const result = await invoke("test_llm_model", { modelId });
llmStatus = result?.message ?? "Test complete";
llmTestHint = result?.hint ?? "";
// A successful test also means the model was loaded (or was
// already loaded) — refresh both Settings-local and global
// status so the sidebar chip and download/load buttons react.
await refreshLlmStatus();
await refreshGlobalLlmStatus(settings.aiTier);
} catch (err) {
llmStatus = typeof err === "string" ? err : "Test failed";
llmTestHint = "";
} finally {
llmTestBusy = false;
}
}
async function setAiTier(nextTier) {
settings.aiTier = nextTier;
if (nextTier === "off") {
@@ -1412,6 +1443,9 @@
{LLM_MODELS.find((model) => model.id === selectedLlmModelId())?.subtitle || "Local model"}
</p>
<p class="text-[11px] text-text-tertiary mt-1">{llmStatus}</p>
{#if llmTestHint}
<p class="text-[11px] text-accent mt-1">{llmTestHint}</p>
{/if}
</div>
<div class="flex items-center gap-2 flex-wrap">
@@ -1429,12 +1463,24 @@
class="px-3 py-2 rounded-lg bg-accent text-bg text-[12px] hover:bg-accent-hover"
onclick={loadSelectedLlmModel}
>Load</button>
<button
type="button"
class="px-3 py-2 rounded-lg border border-border text-[12px] text-text-secondary hover:text-text disabled:opacity-50"
onclick={testSelectedLlmModel}
disabled={llmTestBusy}
>{llmTestBusy ? "Testing…" : "Test"}</button>
<button
type="button"
class="px-3 py-2 rounded-lg border border-border text-[12px] text-text-secondary hover:text-text"
onclick={deleteSelectedLlmModel}
>Delete</button>
{:else}
<button
type="button"
class="px-3 py-2 rounded-lg border border-border text-[12px] text-text-secondary hover:text-text disabled:opacity-50"
onclick={testSelectedLlmModel}
disabled={llmTestBusy}
>{llmTestBusy ? "Testing…" : "Test"}</button>
<button
type="button"
class="px-3 py-2 rounded-lg border border-border text-[12px] text-text-secondary hover:text-text"