Keep conversations, so a useful answer outlives the tab it was asked in

2026-08-08 22:00:58 -04:00
parent df3c4bb369
commit 1e324636e0
3 changed files with 205 additions and 1 deletions
@@ -1150,6 +1150,130 @@ function vv_ai_incidents_for(string $scope, int $max = 4): array {
    return array_slice(array_reverse($hits), 0, max(1, $max));
 }

+// ── Stored conversations ──────────────────────────────────────────────────────
+// Chats live in DATA_DIR, not /tmp, because the point of storing them is that they outlive a
+// reboot — the job files above are deliberately the opposite. One file per conversation, same
+// shape as ai_bugs: a directory of small JSON records is trivially prunable and a corrupt one
+// costs a single chat rather than the whole history.
+//
+// The store is capped, and pruning happens on write rather than on a schedule. Nothing else
+// runs often enough to be trusted with it, and an unbounded directory here would quietly grow
+// for as long as the operator keeps talking to the assistant.
+function vv_ai_chats_dir(): string {
+    $d = DATA_DIR . '/ai_chats';
+    if (!is_dir($d)) @mkdir($d, 0755, true);
+    return $d;
+}
+
+function vv_ai_chats_max(): int {
+    $n = (int)(vv_conf_vars()['AI_CHAT_HISTORY_MAX'] ?? 10);
+    return max(1, min(50, $n));
+}
+
+// Hex-only, for exactly the reason vv_ai_job_path() is: the id composes a path. Ids are minted
+// server-side and the client only ever echoes one back, so anything else is a caller that has
+// no business naming a file here.
+function vv_ai_chat_path(string $id): ?string {
+    if (!preg_match('/^[0-9a-f]{32}$/', $id)) return null;
+    return vv_ai_chats_dir() . '/' . $id . '.json';
+}
+
+// The first thing asked, which is what the operator will recognise the conversation by. Falls
+// back rather than returning empty: a blank row in the list is indistinguishable from a broken
+// one.
+function vv_ai_chat_title(array $messages): string {
+    foreach ($messages as $m) {
+        if (($m['role'] ?? '') !== 'user') continue;
+        $t = trim(preg_replace('/\s+/', ' ', (string)($m['content'] ?? '')));
+        if ($t !== '') return mb_substr($t, 0, 80);
+    }
+    return 'Untitled conversation';
+}
+
+// Newest first, metadata only. The list card renders ten rows and none of them need the
+// transcript — sending every message of every stored chat to draw a sidebar would be the most
+// expensive read on the monitor page.
+function vv_ai_chats_list(): array {
+    $out = [];
+    foreach (glob(vv_ai_chats_dir() . '/*.json') ?: [] as $f) {
+        $d = json_decode(@file_get_contents($f) ?: '', true);
+        if (!is_array($d) || empty($d['id'])) continue;
+        $out[] = [
+            'id'      => $d['id'],
+            'ts'      => (int)($d['ts'] ?? 0),
+            'profile' => (string)($d['profile'] ?? 'chat'),
+            'title'   => (string)($d['title'] ?? 'Untitled conversation'),
+            'turns'   => (int)($d['turns'] ?? count($d['messages'] ?? [])),
+        ];
+    }
+    usort($out, fn($a, $b) => $b['ts'] <=> $a['ts']);
+    return $out;
+}
+
+function vv_ai_chat_read(string $id): ?array {
+    $p = vv_ai_chat_path($id);
+    if ($p === null || !file_exists($p)) return null;
+    $d = json_decode(@file_get_contents($p) ?: '', true);
+    return is_array($d) ? $d : null;
+}
+
+function vv_ai_chat_delete(string $id): bool {
+    $p = vv_ai_chat_path($id);
+    if ($p === null || !file_exists($p)) return false;
+    return @unlink($p);
+}
+
+// Oldest go first, by stored timestamp rather than mtime — a chat that is reopened and continued
+// is rewritten, and ordering on mtime would make "the one I have been using all week" look like
+// the newest thing in the store while a genuinely older thread got dropped in its place.
+function vv_ai_chats_prune(?int $max = null): int {
+    $max  = $max ?? vv_ai_chats_max();
+    $list = vv_ai_chats_list();
+    $n    = 0;
+    foreach (array_slice($list, $max) as $old) {
+        if (vv_ai_chat_delete($old['id'])) $n++;
+    }
+    return $n;
+}
+
+// Writes a whole conversation. An empty id mints one; a known id overwrites in place, which is
+// what makes a continued conversation stay one row in the list instead of breeding a new one per
+// turn. Written to a temp file and renamed, so a reader never sees half a transcript.
+function vv_ai_chat_save(string $id, string $profile, array $messages): array {
+    if (!$messages) return ['ok' => false, 'error' => 'Nothing to save'];
+
+    if ($id === '') $id = bin2hex(random_bytes(16));
+    $p = vv_ai_chat_path($id);
+    if ($p === null) return ['ok' => false, 'error' => 'Invalid chat id'];
+
+    // Preserve the original creation time across rewrites. Ordering the list by last activity
+    // would be defensible, but it would also mean an old thread jumps the queue the moment it is
+    // reopened, and the prune above is written against creation order.
+    $prev    = vv_ai_chat_read($id);
+    $created = (int)($prev['created'] ?? time());
+
+    $rec = [
+        'id'       => $id,
+        'created'  => $created,
+        'ts'       => $created,
+        'updated'  => time(),
+        'profile'  => $profile,
+        'title'    => vv_ai_chat_title($messages),
+        'turns'    => (int)floor(count($messages) / 2),
+        'messages' => $messages,
+    ];
+
+    $tmp = $p . '.tmp';
+    if (@file_put_contents($tmp, json_encode($rec, JSON_PRETTY_PRINT)) === false
+        || !@rename($tmp, $p)) {
+        @unlink($tmp);
+        return ['ok' => false, 'error' => 'Could not write ' . $p];
+    }
+
+    vv_ai_chats_prune();
+    return ['ok' => true, 'id' => $id, 'title' => $rec['title']];
+}
+
 function vv_ai_job_dir(): string {
    if (!is_dir(VV_AI_JOB_DIR)) @mkdir(VV_AI_JOB_DIR, 0700, true);
    return VV_AI_JOB_DIR;