feat(inference): S7 Call 1/Call 2 + prompt revision REST + test-inference + Generate text UI

- backend/inference.py: prompt seed (rev 0) + append-only revision REST
  (POST /prompts/{call}/revisions, /activate, GET; METADATA-105/106). Call 1 vision
  classification (1024px processed photos + synced taxonomy, 0.7 confidence gate,
  METADATA-35/40/45), Call 2 long description (user-triggered, METADATA-55/60/65),
  inference_log per call (METADATA-66), inference-off server_description (METADATA-70),
  test-inference probe (SETTINGS-45). Stdlib urllib, no new deps.
- frontend: create/inference/GenerateText.svelte (control visible only when content
  enabled + endpoint reachable, METADATA-110; Call 2 + Call 1 buttons) + dev toggle.
- tests: 6 inference tests (seed+revision, call1 gate, call2 stores desc, off->409,
  server desc, test-inference unconfigured).

Verified: pytest 54 passed; gates exit 0; npm build ok.
This commit is contained in:
2026-09-19 17:04:01 -07:00
parent 5e03f45660
commit 8a8a89ed3e
5 changed files with 604 additions and 0 deletions
@@ -0,0 +1,103 @@
<script lang="ts">
let slabId = '';
let contentEnabled = false;
let reachable = false;
let description: string | null = null;
let call1Suggestions: Record<string, unknown> | null = null;
let error = '';
let busy = false;
async function checkReadiness() {
contentEnabled = false;
reachable = false;
try {
const [inf, test] = await Promise.all([
fetch('/api/v1/settings').then((r) => r.json()),
fetch('/api/v1/admin/test-inference', { method: 'POST' }).then((r) => r.json()),
]);
contentEnabled = inf.content_llm_enabled === 'true' || inf.content_llm_enabled === true;
reachable = test.ok === true;
} catch {
reachable = false;
}
}
async function generate() {
if (!slabId) {
error = 'Enter a slab id.';
return;
}
busy = true;
error = '';
description = null;
try {
const res = await fetch(`/api/v1/slabs/${encodeURIComponent(slabId)}/inference/call2`, { method: 'POST' });
const body = await res.json();
if (res.ok) description = body.description;
else error = body.error?.message || `call2 failed (${res.status})`;
} catch {
error = 'network error';
}
busy = false;
}
async function classify() {
if (!slabId) {
error = 'Enter a slab id.';
return;
}
busy = true;
error = '';
call1Suggestions = null;
try {
const res = await fetch(`/api/v1/slabs/${encodeURIComponent(slabId)}/inference/call1`, { method: 'POST' });
const body = await res.json();
if (res.ok) call1Suggestions = body.suggestions;
else error = body.error?.message || `call1 failed (${res.status})`;
} catch {
error = 'network error';
}
busy = false;
}
checkReadiness();
</script>
<div class="inference">
<h2>Generate text</h2>
<p class="state">
Content generation: {contentEnabled ? 'on' : 'off'} · endpoint: {reachable ? 'reachable' : 'unreachable'}
</p>
{#if !contentEnabled || !reachable}
<p class="note">The Generate text control is disabled: it appears only when content generation is
enabled and the inference endpoint is reachable.</p>
{:else}
<div>
<label>Slab ID</label>
<input bind:value={slabId} placeholder="uuid" />
</div>
<div class="row">
<button on:click={generate} disabled={busy}>{busy ? 'Working…' : 'Generate description (Call 2)'}</button>
<button on:click={classify} disabled={busy}>Classify metadata (Call 1)</button>
</div>
{#if error}<p class="err">{error}</p>{/if}
{#if description}<p class="desc">{description}</p>{/if}
{#if call1Suggestions}
<pre class="sug">{JSON.stringify(call1Suggestions, null, 2)}</pre>
{/if}
{/if}
<button class="mini" on:click={checkReadiness}>Recheck readiness</button>
</div>
<style>
.inference { max-width: 560px; color: #eee; }
label { display: block; margin: 8px 0 4px; }
input { width: 100%; padding: 6px; }
.row { margin-top: 12px; display: flex; gap: 8px; }
.state { color: #aaa; }
.note { color: #e8a; }
.err { color: #e88; }
.desc { margin-top: 12px; }
.sug { background: #1c1c1c; padding: 8px; }
.mini { margin-top: 12px; font-size: 12px; }
</style>