Gmer4Lfe
6be765a9bf
Several headers argued the Scheduler dock was deliberately separate, and the Scheduler's help never mentioned the assistant at all — including the fix flow that just changed shape.
1358 lines
66 KiB
PHP
1358 lines
66 KiB
PHP
<?php
|
|
// ═══════════════════════════════════════════════════════════════════════════════════════════════
|
|
// PURPOSE
|
|
// The AI tab's library. Resolves AI configuration, reports the health of the retrieval
|
|
// subsystem for the status banner, runs retrieval against the index, and owns the job-file
|
|
// contract the chat worker and the polling endpoint share.
|
|
//
|
|
// OPERATIONAL MODEL
|
|
// Retrieval is delegated, not reimplemented. AI/lib/search.js already embeds the query,
|
|
// scans the index and applies intent routing; this file shells to that CLI with --json. A
|
|
// second PHP implementation of vector search would be a second set of scoring bugs, and the
|
|
// two would drift the first time the chunker changed.
|
|
//
|
|
// Generation is not performed here. It takes 25-76 seconds and belongs in a detached worker;
|
|
// this file only describes where that worker writes and what the states mean.
|
|
//
|
|
// DESIGN PRINCIPLES
|
|
// Every reported statistic distinguishes "unknown" from "bad".
|
|
// A banner that shows a healthy default when it cannot reach Ollama is worse than one
|
|
// that shows nothing, because the operator stops checking. Each probe returns null when
|
|
// it could not determine the answer.
|
|
//
|
|
// Offload percentage is a first-class metric.
|
|
// size_vram against size is the difference between 74 tok/s and 19 on this hardware, and
|
|
// nothing else on the host surfaces it. It is computed here so the banner and any future
|
|
// watchdog read the same number.
|
|
//
|
|
// Staleness is measured against tracked files, not the filesystem.
|
|
// The index only ever contains git-tracked content, so comparing to an untracked scratch
|
|
// file would report permanent staleness. git ls-files is the same source the indexer uses.
|
|
//
|
|
// Health checks compare configuration against reality, and carry their remedy.
|
|
// "Retrieval failed" is not actionable; "HOST1_OLLAMA_MODEL names a tag that is not
|
|
// installed" is. Every check names the setting to change, because the failures this
|
|
// subsystem actually has are configuration drift — a model pulled, wired into conf, then
|
|
// removed — rather than software faults.
|
|
//
|
|
// Logs are read live, never indexed.
|
|
// They churn constantly, would dominate a 3341-chunk corpus, and embedding similarity
|
|
// retrieves log lines poorly compared with recency and a severity filter. Indexing them
|
|
// would also mean re-embedding every few minutes for content that is stale immediately.
|
|
//
|
|
// OPERATIONAL SAFEGUARDS
|
|
// Read-only. Nothing here writes to the index, the conf, or the job files — it reads state
|
|
// and runs a retrieval query. The worker owns every write.
|
|
//
|
|
// Every external call is time-boxed.
|
|
// Retrieval and the Ollama probes carry explicit timeouts, because this library is
|
|
// loaded by a page render and by a polling endpoint; a hung Ollama must degrade the
|
|
// banner, not hang the tab.
|
|
//
|
|
// Retrieval arguments are validated before they reach the shell.
|
|
// kind is checked against the five real values and k is clamped, then every value is
|
|
// escapeshellarg'd. An unknown kind would match zero rows in SQL and read as "the index
|
|
// has no answer", which is the most misleading failure this subsystem can produce.
|
|
//
|
|
// Tokens are validated as hex before they compose a path.
|
|
// Job files live in a fixed directory and are named from a caller-supplied token; the
|
|
// pattern is what keeps that token from escaping the directory.
|
|
//
|
|
// A missing index is reported, never treated as empty.
|
|
// Empty results and an absent index look identical to a caller that only counts rows,
|
|
// and they need completely different responses from the user.
|
|
//
|
|
// EXPORTS
|
|
// Config vv_ai_enabled(), vv_ai_config()
|
|
// Status vv_ai_stats(), vv_ai_index_stats(), vv_ai_runtime_stats(), vv_ai_index_meta()
|
|
// Models vv_ai_models_available(), vv_ai_models_loaded()
|
|
// Diagnosis vv_ai_health(), vv_ai_recent_logs()
|
|
// Memory vv_ai_memory_path(), vv_ai_memory_read(), vv_ai_memory_write()
|
|
// Retrieval vv_ai_retrieve()
|
|
// Jobs vv_ai_job_dir(), vv_ai_job_path(), vv_ai_job_read()
|
|
//
|
|
// CONFIGURATION
|
|
// master.conf AI_ENABLED, AI_INDEX_DB, AI_SEARCH_K, AI_SEARCH_PER_FILE,
|
|
// AI_REQUEST_TIMEOUT, AI_CONNECT_TIMEOUT
|
|
// host*.conf HOST*_OLLAMA_URL, HOST*_OLLAMA_MODEL, HOST*_OLLAMA_EMBED_MODEL
|
|
// ═══════════════════════════════════════════════════════════════════════════════════════════════
|
|
|
|
require_once __DIR__ . '/config.php';
|
|
|
|
// VV_AI_JOB_DIR and VV_AI_TOKEN_CACHE_DIR are defined in config.php with every other cache path,
|
|
// read from master.conf so this layer and load_config.sh cannot disagree about where they are.
|
|
// Must match what AI/lib/chunk.js actually assigns, and what the AI tab's retrieval-source
|
|
// dropdown offers. All three drifted: the indexer has always produced 'ui' for
|
|
// Plugin/unraid/pages/readme/*.md and the dropdown has always offered it, but this whitelist
|
|
// omitted it — so choosing "WebUI — how the pages work" and asking anything returned
|
|
// "Unknown kind: ui" and no answer at all. The page help was indexed and unreachable through
|
|
// the one filter built to reach it.
|
|
const VV_AI_KINDS = ['header', 'readme', 'manual', 'template', 'doc', 'ui'];
|
|
|
|
// Profiles — what each one is, and what it is allowed to see and do. One table, in one file,
|
|
// read by everything: this endpoint, the worker, and the shared chat include every page renders.
|
|
// vv_ai_profile_can() and friends come from there.
|
|
require_once __DIR__ . '/ai_profiles.php';
|
|
|
|
// Whether a General Chat message is really about this installation. Shared by the deterministic
|
|
// backstop and the handoff, so both agree by construction: a question the backstop would have
|
|
// refused is exactly the one the handoff should escalate, and drift between the two would leave
|
|
// a class of question that is neither answered nor deferred.
|
|
function vv_ai_chat_needs_varaverk(string $question): bool {
|
|
return vv_ai_mentions_varaverk($question)
|
|
|| (bool)preg_match('/\b[\w.-]+\.sh\b|\b[A-Z][A-Z0-9]*(_[A-Z0-9]+)+\b/', $question)
|
|
// Naming something that has a log is as Varaverk-specific as naming a script file, and
|
|
// this is how an operator actually refers to them: "the daily orch", not
|
|
// "daily_sync_maintenance.sh". Without this, "how did the daily orch go" asked in General
|
|
// Chat was refused correctly and then went nowhere — the refusal is right, but the
|
|
// question was answerable one profile up and the handoff could not see that.
|
|
|| vv_ai_resolve_run_target($question) !== '';
|
|
}
|
|
|
|
// Asking for a script to be written, as opposed to asking about one that exists. The verb is
|
|
// required: "what does arr_sync.sh do" names a script and wants documentation, "write me a script
|
|
// that does X" names none and wants code. Getting that backwards in either direction is the whole
|
|
// risk here, so the pattern is anchored on the request rather than on the word "script".
|
|
function vv_ai_wants_code(string $question): bool {
|
|
return (bool)preg_match(
|
|
'/\b(write|create|make|draft|generate|build|give\s+me|need|want)\b[^.?!]{0,40}'
|
|
. '\b(a\s+|an\s+|me\s+a\s+)?(bash\s+|shell\s+|sh\s+)?'
|
|
. '(script|one[- ]?liner|cron\s?job|command|snippet)\b/i',
|
|
$question
|
|
);
|
|
}
|
|
|
|
// Diagnostic phrasing — "why did X fail", "X is broken", "it never runs". Shared with the
|
|
// worker's own gate so the router and the gate cannot disagree about what counts as a diagnosis.
|
|
function vv_ai_is_diagnostic(string $question): bool {
|
|
return (bool)preg_match(
|
|
'/\b(why|fail(ed|ing|ure)?|error|broken?|not work|isn.t work|wrong|stuck|hang|'
|
|
. 'never runs?|didn.t|won.t|debug|troubleshoot|diagnos)/i',
|
|
$question
|
|
);
|
|
}
|
|
|
|
// Which profile should answer a General Chat question, or '' to leave it in chat.
|
|
//
|
|
// One router, ordered most specific first, because these overlap on purpose: "why did the script
|
|
// I asked you to write fail" is diagnostic AND mentions a script, and the operator means the
|
|
// first. The order is the policy.
|
|
//
|
|
// code asked for something to be written. Checked first — it is the only intent that
|
|
// is about a thing that does not exist yet, so nothing else can claim it.
|
|
// troubleshoot something is wrong. Requires diagnostic phrasing AND something Varaverk-shaped
|
|
// to diagnose; "why is the sky blue" is diagnostic phrasing about nothing here.
|
|
// varaverk about this installation, but not a fault and not a request for code.
|
|
//
|
|
// Deliberately conservative: an unrecognised question stays in chat, which is the profile that
|
|
// cannot invent claims about this system. Escalation adds capability, so a wrong escalation costs
|
|
// more than a missed one — and the worker reverts to chat anyway if retrieval comes back empty.
|
|
function vv_ai_route_from_chat(string $question): string {
|
|
if (vv_ai_wants_code($question)) return 'code';
|
|
if (vv_ai_is_diagnostic($question) && vv_ai_chat_needs_varaverk($question)) return 'troubleshoot';
|
|
if (vv_ai_chat_needs_varaverk($question)) return 'varaverk';
|
|
return '';
|
|
}
|
|
|
|
function vv_ai_config(): array {
|
|
static $cfg = null;
|
|
if ($cfg !== null) return $cfg;
|
|
|
|
$vars = vv_conf_vars();
|
|
$host = strtoupper(vv_detect_host());
|
|
|
|
$cfg = [
|
|
'enabled' => strtolower(trim($vars['AI_ENABLED'] ?? 'false')) === 'true',
|
|
'url' => rtrim(trim($vars["{$host}_OLLAMA_URL"] ?? ''), '/'),
|
|
'model' => trim($vars["{$host}_OLLAMA_MODEL"] ?? ''),
|
|
'embed_model' => trim($vars["{$host}_OLLAMA_EMBED_MODEL"] ?? 'nomic-embed-text'),
|
|
'db' => trim($vars['AI_INDEX_DB'] ?? '') ?: AI_DATA_DIR . '/ai_index.db',
|
|
'k' => (int)($vars['AI_SEARCH_K'] ?? 8),
|
|
'per_file' => (int)($vars['AI_SEARCH_PER_FILE'] ?? 3),
|
|
'timeout' => (int)($vars['AI_REQUEST_TIMEOUT'] ?? 240),
|
|
'connect' => (int)($vars['AI_CONNECT_TIMEOUT'] ?? 5),
|
|
];
|
|
// AI_INDEX_DB is written as "$DATA_DIR/ai_index.db" in conf; the shell expands it, PHP does
|
|
// not. Left as a literal it would name a file that cannot exist.
|
|
$cfg['db'] = str_replace(['$DATA_DIR', '${DATA_DIR}'], DATA_DIR, $cfg['db']);
|
|
return $cfg;
|
|
}
|
|
|
|
function vv_ai_enabled(): bool {
|
|
return vv_ai_config()['enabled'];
|
|
}
|
|
|
|
// Index size, coverage and staleness. Staleness compares the newest git-tracked file against
|
|
// the last build: the indexer only ever ingests tracked content, so anything else would report
|
|
// permanent drift.
|
|
function vv_ai_index_stats(): array {
|
|
$cfg = vv_ai_config();
|
|
$out = ['exists' => false, 'chunks' => 0, 'files' => 0, 'size' => 0,
|
|
'built' => null, 'newest_source' => null, 'stale' => null, 'kinds' => []];
|
|
|
|
if (!file_exists($cfg['db'])) return $out;
|
|
$out['exists'] = true;
|
|
$out['size'] = (int)@filesize($cfg['db']);
|
|
|
|
$db = escapeshellarg($cfg['db']);
|
|
$q = fn(string $sql) => trim((string)@shell_exec('sqlite3 ' . $db . ' ' . escapeshellarg($sql) . ' 2>/dev/null'));
|
|
|
|
$out['chunks'] = (int)$q('SELECT COUNT(*) FROM vv_chunks;');
|
|
$out['files'] = (int)$q('SELECT COUNT(*) FROM vv_files;');
|
|
$built = (int)$q('SELECT MAX(indexed) FROM vv_files;');
|
|
$out['built'] = $built ?: null;
|
|
|
|
foreach (explode("\n", $q('SELECT kind, COUNT(*) FROM vv_chunks GROUP BY kind;')) as $line) {
|
|
if (!$line) continue;
|
|
[$k, $n] = array_pad(explode('|', $line, 2), 2, 0);
|
|
if ($k !== '') $out['kinds'][$k] = (int)$n;
|
|
}
|
|
|
|
$newest = trim((string)@shell_exec(
|
|
'cd ' . escapeshellarg(SCRIPTS_DIR) . ' && git ls-files -z 2>/dev/null'
|
|
. ' | xargs -0 stat -c %Y 2>/dev/null | sort -rn | head -1'
|
|
));
|
|
if ($newest !== '') {
|
|
$out['newest_source'] = (int)$newest;
|
|
if ($out['built'] !== null) $out['stale'] = (int)$newest > $out['built'];
|
|
}
|
|
return $out;
|
|
}
|
|
|
|
// Ollama reachability and — the number that matters on this hardware — whether the generation
|
|
// model is fully resident on the GPU. size_vram below size means layers are on the CPU, which
|
|
// costs roughly 4x throughput and is invisible everywhere else.
|
|
function vv_ai_runtime_stats(): array {
|
|
$cfg = vv_ai_config();
|
|
$out = ['reachable' => false, 'loaded' => null, 'offload_pct' => null,
|
|
'context' => null, 'vram_used' => null, 'vram_total' => null, 'gpu' => null];
|
|
|
|
if ($cfg['url'] === '') return $out;
|
|
|
|
$ctx = stream_context_create(['http' => [
|
|
'method' => 'GET', 'timeout' => max(2, $cfg['connect']), 'ignore_errors' => true,
|
|
]]);
|
|
$raw = @file_get_contents($cfg['url'] . '/api/ps', false, $ctx);
|
|
if ($raw === false) return $out;
|
|
$out['reachable'] = true;
|
|
|
|
$ps = json_decode($raw, true);
|
|
foreach ($ps['models'] ?? [] as $m) {
|
|
if (($m['name'] ?? '') !== $cfg['model']) continue;
|
|
$size = (int)($m['size'] ?? 0);
|
|
$vram = (int)($m['size_vram'] ?? 0);
|
|
$out['loaded'] = true;
|
|
$out['context'] = $m['context_length'] ?? null;
|
|
$out['vram_used'] = $vram;
|
|
$out['vram_total'] = $size;
|
|
$out['offload_pct'] = $size > 0 ? (int)round($vram / $size * 100) : null;
|
|
break;
|
|
}
|
|
if ($out['loaded'] === null) $out['loaded'] = false;
|
|
|
|
$gpu = trim((string)@shell_exec(
|
|
'nvidia-smi --query-gpu=name,memory.used,memory.total,utilization.gpu '
|
|
. '--format=csv,noheader,nounits 2>/dev/null | tail -1'
|
|
));
|
|
if ($gpu !== '') {
|
|
$p = array_map('trim', explode(',', $gpu));
|
|
if (count($p) >= 4) {
|
|
$out['gpu'] = ['name' => $p[0], 'mem_used' => (int)$p[1],
|
|
'mem_total' => (int)$p[2], 'util' => (int)$p[3]];
|
|
}
|
|
}
|
|
return $out;
|
|
}
|
|
|
|
// Models Ollama actually has on disk. The configured model naming a tag that does not exist is
|
|
// the single most likely misconfiguration here — it is what happens whenever a model is pulled,
|
|
// wired into conf, and later removed.
|
|
function vv_ai_models_available(): ?array {
|
|
$cfg = vv_ai_config();
|
|
if ($cfg['url'] === '') return null;
|
|
$ctx = stream_context_create(['http' => ['timeout' => max(2, $cfg['connect']), 'ignore_errors' => true]]);
|
|
$raw = @file_get_contents($cfg['url'] . '/api/tags', false, $ctx);
|
|
if ($raw === false) return null;
|
|
$d = json_decode($raw, true);
|
|
if (!isset($d['models'])) return null;
|
|
return array_map(fn($m) => [
|
|
'name' => $m['name'] ?? '',
|
|
'size' => (int)($m['size'] ?? 0),
|
|
], $d['models']);
|
|
}
|
|
|
|
// Currently resident models with their offload split.
|
|
function vv_ai_models_loaded(): ?array {
|
|
$cfg = vv_ai_config();
|
|
if ($cfg['url'] === '') return null;
|
|
$ctx = stream_context_create(['http' => ['timeout' => max(2, $cfg['connect']), 'ignore_errors' => true]]);
|
|
$raw = @file_get_contents($cfg['url'] . '/api/ps', false, $ctx);
|
|
if ($raw === false) return null;
|
|
$d = json_decode($raw, true);
|
|
if (!isset($d['models'])) return null;
|
|
$out = [];
|
|
foreach ($d['models'] as $m) {
|
|
$size = (int)($m['size'] ?? 0);
|
|
$vram = (int)($m['size_vram'] ?? 0);
|
|
$out[] = [
|
|
'name' => $m['name'] ?? '',
|
|
'context' => $m['context_length'] ?? null,
|
|
'size' => $size,
|
|
'vram' => $vram,
|
|
'offload' => $size > 0 ? (int)round($vram / $size * 100) : null,
|
|
];
|
|
}
|
|
return $out;
|
|
}
|
|
|
|
// vv_meta records the embed model and dimensionality the index was built with.
|
|
function vv_ai_index_meta(): array {
|
|
$cfg = vv_ai_config();
|
|
if (!file_exists($cfg['db'])) return [];
|
|
// Columns are k/v, not key/value. Named wrongly this returns nothing and the embedder-match
|
|
// check reports "unrecorded" — a silent pass on the one mismatch that returns confident
|
|
// nonsense rather than an error.
|
|
$raw = trim((string)@shell_exec(
|
|
'sqlite3 ' . escapeshellarg($cfg['db']) . ' ' . escapeshellarg('SELECT k, v FROM vv_meta;') . ' 2>/dev/null'
|
|
));
|
|
$out = [];
|
|
foreach (explode("\n", $raw) as $line) {
|
|
if ($line === '') continue;
|
|
[$k, $v] = array_pad(explode('|', $line, 2), 2, '');
|
|
if ($k !== '') $out[$k] = $v;
|
|
}
|
|
return $out;
|
|
}
|
|
|
|
// Config checked against reality. Each check is ok | warn | bad, with the remedy attached —
|
|
// the point is to name the setting that is wrong, not merely report that something failed.
|
|
function vv_ai_health(): array {
|
|
$cfg = vv_ai_config();
|
|
$checks = [];
|
|
$add = function (string $id, string $label, string $state, string $detail, string $fix = '')
|
|
use (&$checks) {
|
|
$checks[] = ['id' => $id, 'label' => $label, 'state' => $state,
|
|
'detail' => $detail, 'fix' => $fix];
|
|
};
|
|
|
|
$add('enabled', 'AI enabled', $cfg['enabled'] ? 'ok' : 'bad',
|
|
$cfg['enabled'] ? 'AI_ENABLED=true' : 'AI_ENABLED is false',
|
|
$cfg['enabled'] ? '' : 'Set AI_ENABLED=true in master.conf');
|
|
|
|
if (!command_exists_node()) {
|
|
$add('node', 'node runtime', 'bad', 'node not found on PATH',
|
|
'Retrieval shells to AI/lib/cli.js and cannot run without it');
|
|
}
|
|
|
|
if ($cfg['url'] === '') {
|
|
$add('url', 'Ollama URL', 'bad', 'not configured',
|
|
'Set ' . strtoupper(vv_detect_host()) . '_OLLAMA_URL in the host conf');
|
|
return $checks;
|
|
}
|
|
|
|
$avail = vv_ai_models_available();
|
|
if ($avail === null) {
|
|
$add('reach', 'Ollama reachable', 'bad', 'no response from ' . $cfg['url'],
|
|
'Check the Ollama container is running and the URL is correct');
|
|
return $checks;
|
|
}
|
|
$add('reach', 'Ollama reachable', 'ok', $cfg['url']);
|
|
|
|
$names = array_column($avail, 'name');
|
|
|
|
// The configured tag not existing is the failure this whole section is for.
|
|
if ($cfg['model'] === '') {
|
|
$add('gen', 'Generation model', 'bad', 'not configured',
|
|
'Set ' . strtoupper(vv_detect_host()) . '_OLLAMA_MODEL in the host conf');
|
|
} elseif (!vv_ai_model_installed($cfg['model'], $names)) {
|
|
$add('gen', 'Generation model', 'bad', $cfg['model'] . ' is not installed',
|
|
'Either `ollama pull` it, or point _OLLAMA_MODEL at one of: ' . implode(', ', array_slice($names, 0, 4)));
|
|
} else {
|
|
$add('gen', 'Generation model', 'ok', $cfg['model']);
|
|
}
|
|
|
|
if ($cfg['embed_model'] === '' || !vv_ai_model_installed($cfg['embed_model'], $names)) {
|
|
$add('embed', 'Embedding model', 'bad',
|
|
($cfg['embed_model'] ?: 'not configured') . ' is not installed',
|
|
'Retrieval cannot embed a query without it — `ollama pull ' . ($cfg['embed_model'] ?: 'nomic-embed-text') . '`');
|
|
} else {
|
|
$add('embed', 'Embedding model', 'ok', $cfg['embed_model']);
|
|
}
|
|
|
|
$ix = vv_ai_index_stats();
|
|
$meta = vv_ai_index_meta();
|
|
|
|
if (!$ix['exists']) {
|
|
$add('index', 'Index', 'bad', 'not built', 'Run AI/ai_index.sh');
|
|
} else {
|
|
$add('index', 'Index', 'ok', number_format($ix['chunks']) . ' chunks from ' . $ix['files'] . ' files');
|
|
|
|
// A vector built by one embedding model is meaningless to another. Changing the embed
|
|
// model without reindexing does not error — it silently returns nonsense, scored
|
|
// confidently, which is the hardest failure here to notice from the answers alone.
|
|
$builtWith = $meta['embed_model'] ?? '';
|
|
if ($builtWith !== '' && $cfg['embed_model'] !== ''
|
|
&& vv_ai_model_norm($builtWith) !== vv_ai_model_norm($cfg['embed_model'])) {
|
|
$add('embedmatch', 'Index / embedder match', 'bad',
|
|
'index built with ' . $builtWith . ', conf says ' . $cfg['embed_model'],
|
|
'Vectors from different models are not comparable — rerun AI/ai_index.sh --force');
|
|
} else {
|
|
$add('embedmatch', 'Index / embedder match', 'ok', $builtWith ?: 'unrecorded');
|
|
}
|
|
|
|
if ($ix['stale'] === true) {
|
|
$add('fresh', 'Index freshness', 'warn', 'tracked files are newer than the index',
|
|
'Answers may cite code that has changed — rerun AI/ai_index.sh');
|
|
} else {
|
|
$add('fresh', 'Index freshness', 'ok', 'current');
|
|
}
|
|
}
|
|
|
|
$loaded = vv_ai_models_loaded();
|
|
if ($loaded !== null && $cfg['model'] !== '') {
|
|
$hit = null;
|
|
foreach ($loaded as $m) if ($m['name'] === $cfg['model']) { $hit = $m; break; }
|
|
if ($hit === null) {
|
|
$add('resident', 'Model resident', 'warn', 'not loaded — first question will load it');
|
|
} elseif ($hit['offload'] !== null && $hit['offload'] < 100) {
|
|
$add('resident', 'GPU offload', 'bad', $hit['offload'] . '% on GPU — layers on CPU',
|
|
'Roughly 4x slower on this card. Lower num_ctx or use a smaller quant');
|
|
} else {
|
|
$add('resident', 'GPU offload', 'ok', '100% on GPU at ' . ($hit['context'] ?? '?') . ' ctx');
|
|
}
|
|
}
|
|
|
|
return $checks;
|
|
}
|
|
|
|
// Ollama reports tags fully qualified — nomic-embed-text:latest — while conf commonly carries
|
|
// the bare name, and both are valid references. Comparing literally reports an installed model
|
|
// as missing, which is exactly the false alarm that makes a health panel worth ignoring.
|
|
function vv_ai_model_norm(string $name): string {
|
|
$name = trim($name);
|
|
if ($name === '') return '';
|
|
// A colon in the final path segment is a tag; anything else is a registry path.
|
|
$last = substr($name, strrpos($name, '/') === false ? 0 : strrpos($name, '/') + 1);
|
|
return str_contains($last, ':') ? $name : $name . ':latest';
|
|
}
|
|
|
|
function vv_ai_model_installed(string $name, array $available): bool {
|
|
$n = vv_ai_model_norm($name);
|
|
foreach ($available as $m) {
|
|
if (vv_ai_model_norm($m) === $n) return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
function command_exists_node(): bool {
|
|
static $has = null;
|
|
if ($has !== null) return $has;
|
|
return $has = trim((string)@shell_exec('command -v node 2>/dev/null')) !== '';
|
|
}
|
|
|
|
// Recent warnings and errors across the orchestrator logs. Read live rather than indexed:
|
|
// logs churn constantly, would dominate a 3341-chunk index, and embedding similarity retrieves
|
|
// them poorly compared with recency plus a severity filter.
|
|
function vv_ai_recent_logs(int $max = 40): array {
|
|
$dir = '/var/log/varaverk';
|
|
if (!is_dir($dir)) return [];
|
|
|
|
$cmd = 'grep -rhE "\[(ERROR|WARN|CRITICAL|FAILED)\]|✗" ' . escapeshellarg($dir)
|
|
. ' --include="*.log" 2>/dev/null | tail -' . max(1, min($max, 200));
|
|
$raw = (string)@shell_exec($cmd);
|
|
|
|
$out = [];
|
|
foreach (explode("\n", $raw) as $line) {
|
|
$line = trim(preg_replace('/\033\[[0-9;]*[mK]/', '', $line));
|
|
if ($line === '') continue;
|
|
$out[] = mb_substr($line, 0, 300);
|
|
}
|
|
return $out;
|
|
}
|
|
|
|
function vv_ai_stats(): array {
|
|
$cfg = vv_ai_config();
|
|
return [
|
|
'enabled' => $cfg['enabled'],
|
|
'model' => $cfg['model'],
|
|
'embed_model' => $cfg['embed_model'],
|
|
'url' => $cfg['url'],
|
|
'k' => $cfg['k'],
|
|
'index' => vv_ai_index_stats(),
|
|
'runtime' => vv_ai_runtime_stats(),
|
|
'loaded' => vv_ai_models_loaded(),
|
|
'health' => vv_ai_health(),
|
|
'ts' => time(),
|
|
];
|
|
}
|
|
|
|
// ── Shared collection ─────────────────────────────────────────────────────────
|
|
// vv_ai_stats() costs about a second on this host — vv_ai_runtime_stats() alone is 60-480ms
|
|
// depending on how quickly Ollama and nvidia-smi answer, and it was being paid by the AI tab
|
|
// every 30 seconds per open tab, plus again by anything else that wanted the same numbers.
|
|
//
|
|
// So it is collected once, by Tools/api_cache_writer.php, into the 'ai' cache; every surface
|
|
// reads that. This is the same arrangement the monitor and arrs payloads already use and for the
|
|
// same reason — polling faster cannot make the figures newer, it only decides how soon a page
|
|
// notices the writer's update.
|
|
//
|
|
// ?live=1 stays available for the one case that needs it: you changed something and want to see
|
|
// the result rather than a payload written before you changed it.
|
|
function vv_ai_stats_cached(bool $live = false): array {
|
|
if (!$live) {
|
|
$c = vv_cache_read('ai', 300);
|
|
if ($c !== null) return $c;
|
|
}
|
|
return vv_ai_stats();
|
|
}
|
|
|
|
// The Monitor tab's slice of the same collection. Derived rather than collected: taking the AI
|
|
// row's figures from a second call to vv_ai_runtime_stats() would pay the whole cost twice per
|
|
// cache write, and — worse — the dashboard and the AI tab could disagree about whether the model
|
|
// is resident, because they would have asked at different moments.
|
|
//
|
|
// Tokens are deliberately absent. This block once carried today's total for a single line on the
|
|
// AI card; that line is now a card of its own, which fetches the whole ledger from
|
|
// api/ai.php?action=tokens because it shows the week and all-time beside today. Leaving the field
|
|
// here would have run vv_ai_token_stats() on every cache write — once a minute, forever — and
|
|
// discarded all but one number of it that nothing reads.
|
|
function vv_ai_monitor_block(array $stats): array {
|
|
return [
|
|
'model' => $stats['model'] ?? '',
|
|
'runtime' => $stats['runtime'] ?? [],
|
|
'index' => $stats['index'] ?? [],
|
|
];
|
|
}
|
|
|
|
// Retrieval via AI/lib/cli.js. Returns ['ok'=>bool,'results'=>[],'intents'=>[],'error'=>?string].
|
|
function vv_ai_retrieve(string $query, string $kind = '', string $section = '', ?int $k = null): array {
|
|
$cfg = vv_ai_config();
|
|
|
|
if ($query === '') return ['ok' => false, 'error' => 'query is required', 'results' => []];
|
|
if ($cfg['url'] === '') return ['ok' => false, 'error' => 'Ollama URL is not configured', 'results' => []];
|
|
if (!file_exists($cfg['db'])) return ['ok' => false, 'error' => 'No index — run AI/ai_index.sh', 'results' => []];
|
|
if ($kind !== '' && !in_array($kind, VV_AI_KINDS, true)) {
|
|
return ['ok' => false, 'error' => 'Unknown kind: ' . $kind, 'results' => []];
|
|
}
|
|
|
|
$cli = SCRIPTS_DIR . '/AI/lib/cli.js';
|
|
if (!file_exists($cli)) return ['ok' => false, 'error' => 'AI/lib/cli.js not found', 'results' => []];
|
|
|
|
$k = max(1, min($k ?? $cfg['k'], 25));
|
|
|
|
$cmd = 'timeout ' . max(10, $cfg['connect'] * 6) . ' node --no-warnings '
|
|
. escapeshellarg($cli) . ' search'
|
|
. ' --db=' . escapeshellarg($cfg['db'])
|
|
. ' --url=' . escapeshellarg($cfg['url'])
|
|
. ' --model=' . escapeshellarg($cfg['embed_model'])
|
|
. ' --query=' . escapeshellarg($query)
|
|
. ' --k=' . $k
|
|
. ' --per-file=' . max(1, $cfg['per_file'])
|
|
. ($kind !== '' ? ' --kind=' . escapeshellarg($kind) : '')
|
|
. ($section !== '' ? ' --section=' . escapeshellarg($section) : '')
|
|
. ' --json 2>/dev/null';
|
|
|
|
$raw = trim((string)@shell_exec($cmd));
|
|
if ($raw === '') return ['ok' => false, 'error' => 'Retrieval produced no output', 'results' => []];
|
|
|
|
$d = json_decode($raw, true);
|
|
if (!is_array($d) || !isset($d['results'])) {
|
|
return ['ok' => false, 'error' => 'Retrieval returned unparseable output', 'results' => []];
|
|
}
|
|
return ['ok' => true, 'results' => $d['results'], 'intents' => $d['intents'] ?? [],
|
|
'scanned' => $d['scanned'] ?? 0];
|
|
}
|
|
|
|
// ── Question shape ───────────────────────────────────────────────────────────────────────────
|
|
//
|
|
// "Varaverk" is a coined word with no spell-check and an awkward keyboard shape, so it arrives
|
|
// misspelled often — varavrk, veraverk, varavek, varverk. Edit distance catches those without a
|
|
// hand-written pattern that would need extending every time a new typo appears.
|
|
//
|
|
// This is search, not identity. The rule against fuzzy hostname matching is about deciding which
|
|
// machine you are talking to, where a near-miss must never resolve; here a near-miss only widens
|
|
// a document search, and the cost of being wrong is a slightly odd set of passages.
|
|
|
|
function vv_ai_mentions_varaverk(string $q): bool {
|
|
foreach (preg_split('/[^a-z0-9]+/i', mb_strtolower($q), -1, PREG_SPLIT_NO_EMPTY) as $w) {
|
|
if (strlen($w) < 5 || strlen($w) > 12) continue; // bound the comparison window
|
|
if ($w === 'varaverk' || levenshtein($w, 'varaverk') <= 2) return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
// "What is Varaverk", "explain varavrk", "whats this thing do". Intent routing boosts PURPOSE
|
|
// for these, which surfaces every script's one-line purpose and buries the top-level prose that
|
|
// actually defines the system — so the model answers that the context does not define it, while
|
|
// README.md sits in the index unread.
|
|
function vv_ai_is_definitional(string $q): bool {
|
|
if (!vv_ai_mentions_varaverk($q)) return false;
|
|
return (bool)preg_match(
|
|
'/\b(what\'?s?|whats|define|definition|describe|explain|overview|tell me about|'
|
|
. 'purpose of|point of|elevator|in a nutshell)\b/i', $q);
|
|
}
|
|
|
|
// ── Memory ───────────────────────────────────────────────────────────────────────────────────
|
|
//
|
|
// A small operator-maintained file handed to the model at the start of every conversation.
|
|
// Injected, never indexed: it changes constantly, and vector similarity is the wrong retrieval
|
|
// mechanism for "things I was told to remember". Living under DATA_DIR keeps it out of the
|
|
// repository and therefore out of the index by construction.
|
|
|
|
function vv_ai_memory_path(): string {
|
|
$cfg = vv_ai_config();
|
|
$vars = vv_conf_vars();
|
|
$p = trim($vars['AI_MEMORY_FILE'] ?? '');
|
|
$p = str_replace(['$DATA_DIR', '${DATA_DIR}'], DATA_DIR, $p);
|
|
return $p !== '' ? $p : AI_DATA_DIR . '/ai_memory.md';
|
|
}
|
|
|
|
function vv_ai_memory_max(): int {
|
|
$vars = vv_conf_vars();
|
|
$n = (int)($vars['AI_MEMORY_MAX_CHARS'] ?? 4000);
|
|
return max(200, min($n, 20000));
|
|
}
|
|
|
|
// Returns ['text'=>string,'chars'=>int,'truncated'=>bool,'exists'=>bool].
|
|
// Truncates rather than refusing: an over-long memory file should cost its own tail, not the
|
|
// whole conversation, and the notice tells the model its knowledge is incomplete rather than
|
|
// letting it assume it saw everything.
|
|
function vv_ai_memory_read(): array {
|
|
$p = vv_ai_memory_path();
|
|
$max = vv_ai_memory_max();
|
|
|
|
if (!file_exists($p)) return ['text' => '', 'chars' => 0, 'truncated' => false, 'exists' => false];
|
|
|
|
$raw = (string)@file_get_contents($p);
|
|
$len = mb_strlen($raw);
|
|
if ($len <= $max) {
|
|
return ['text' => $raw, 'chars' => $len, 'truncated' => false, 'exists' => true];
|
|
}
|
|
return [
|
|
'text' => mb_substr($raw, 0, $max) . "\n\n[memory truncated at {$max} characters]",
|
|
'chars' => $len,
|
|
'truncated' => true,
|
|
'exists' => true,
|
|
];
|
|
}
|
|
|
|
// Atomic, and refuses to exceed the cap. The cap is a context budget shared with retrieval and
|
|
// reasoning on every turn, so it is enforced on write rather than silently trimmed on read.
|
|
function vv_ai_memory_write(string $text): array {
|
|
$p = vv_ai_memory_path();
|
|
$max = vv_ai_memory_max();
|
|
$len = mb_strlen($text);
|
|
|
|
if ($len > $max) {
|
|
return ['ok' => false, 'error' => "Memory is {$len} characters; the limit is {$max}. "
|
|
. "It is included in every prompt, so it competes with retrieval for context."];
|
|
}
|
|
|
|
$dir = dirname($p);
|
|
if (!is_dir($dir) && !@mkdir($dir, 0755, true)) {
|
|
return ['ok' => false, 'error' => 'Cannot create ' . $dir];
|
|
}
|
|
|
|
$tmp = $p . '.vv.tmp';
|
|
if (@file_put_contents($tmp, $text) === false) {
|
|
return ['ok' => false, 'error' => 'Cannot write ' . $tmp];
|
|
}
|
|
if (!@rename($tmp, $p)) {
|
|
@unlink($tmp);
|
|
return ['ok' => false, 'error' => 'Cannot install ' . $p];
|
|
}
|
|
return ['ok' => true, 'chars' => $len];
|
|
}
|
|
|
|
// ── Token accounting ─────────────────────────────────────────────────────────────────────────
|
|
// One appended row per completed turn: date|time|host|profile|source|prompt|completion|tok_s.
|
|
// Pipe-delimited under data/ to match arr_cleanup_stats.db and bandwidth_history.db rather than
|
|
// inventing a format for one feature.
|
|
//
|
|
// Recording is best-effort and never raises. A turn that answered correctly must not be reported
|
|
// as failed because its accounting row could not be written — the number is the cheap part here
|
|
// and the answer is the expensive one.
|
|
|
|
function vv_ai_token_db(): string {
|
|
$p = str_replace(['$DATA_DIR', '${DATA_DIR}'], DATA_DIR,
|
|
trim(vv_conf_vars()['AI_TOKEN_DB'] ?? ''));
|
|
return $p !== '' ? $p : AI_DATA_DIR . '/ai_token_history.db';
|
|
}
|
|
|
|
function vv_ai_token_retain(): int {
|
|
$n = (int)(vv_conf_vars()['AI_TOKEN_RETAIN_ROWS'] ?? 20000);
|
|
return max(500, min($n, 500000));
|
|
}
|
|
|
|
// LOCK_EX because two turns can finish together — the composer allows a second question while
|
|
// the first is still generating, and each runs in its own detached worker.
|
|
function vv_ai_token_record(string $profile, string $source, int $prompt, int $completion, ?float $tokS): void {
|
|
if ($prompt <= 0 && $completion <= 0) return; // nothing generated; not a turn worth a row
|
|
|
|
$db = vv_ai_token_db();
|
|
$dir = dirname($db);
|
|
if (!is_dir($dir) && !@mkdir($dir, 0755, true)) return;
|
|
|
|
$row = implode('|', [
|
|
date('Y-m-d'), date('H:i:s'),
|
|
vv_detect_host(),
|
|
preg_replace('/[^a-z0-9_-]/i', '', $profile) ?: 'unknown',
|
|
preg_replace('/[^a-z0-9_-]/i', '', $source) ?: 'unknown',
|
|
max(0, $prompt), max(0, $completion),
|
|
$tokS === null ? '' : number_format($tokS, 1, '.', ''),
|
|
]) . "\n";
|
|
|
|
@file_put_contents($db, $row, FILE_APPEND | LOCK_EX);
|
|
vv_ai_token_prune($db);
|
|
}
|
|
|
|
// Pruning is gated on filesize rather than done every turn: filesize() is a stat, whereas
|
|
// reading and rewriting the whole file is not something a chat turn should pay for per message.
|
|
// The threshold is derived from the row cap so raising the cap does not silently disable it.
|
|
function vv_ai_token_prune(string $db): void {
|
|
$keep = vv_ai_token_retain();
|
|
if ((int)@filesize($db) < $keep * 60) return; // ~60 bytes a row, generously
|
|
|
|
$rows = @file($db, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
|
|
if (!is_array($rows) || count($rows) <= $keep) return;
|
|
|
|
$tmp = $db . '.vv.tmp';
|
|
if (@file_put_contents($tmp, implode("\n", array_slice($rows, -$keep)) . "\n") === false) return;
|
|
@rename($tmp, $db);
|
|
}
|
|
|
|
// Partner ledgers pulled by AI/ai_token_sync.sh into tmpfs. Same trick conf_sync.sh uses for
|
|
// partner confs: the reader treats a missing file as "unknown", never as zero.
|
|
//
|
|
// The directory is AI_TOKEN_CACHE_DIR from master.conf, resolved in config.php. It used to be
|
|
// hardcoded here, on the reasoning that the shell side hardcoded it too and so there was no
|
|
// single value to drift away from — true when it was written, and no longer true.
|
|
|
|
// Aggregates the file into today / last 7 days / all time, both overall and per host.
|
|
//
|
|
// Every detected host is present in 'hosts' whether or not it has rows, with 'seen' telling the
|
|
// two apart. A host with no rows is not the same fact as a host with zero tokens, and the page
|
|
// must be able to say "nothing collected here" rather than draw a confident 0.
|
|
function vv_ai_token_stats(): array {
|
|
$db = vv_ai_token_db();
|
|
$today = date('Y-m-d');
|
|
$week = date('Y-m-d', strtotime('-6 days')); // 7 days inclusive of today
|
|
|
|
$blank = ['turns' => 0, 'prompt' => 0, 'completion' => 0, 'total' => 0];
|
|
$out = [
|
|
'exists' => file_exists($db),
|
|
'today' => $blank, 'week' => $blank, 'all' => $blank,
|
|
'hosts' => [], 'profiles' => [], 'sources' => [],
|
|
'first' => null, 'last' => null, 'best_tok_s' => null,
|
|
];
|
|
|
|
$me = vv_detect_host();
|
|
foreach (vv_known_hosts() as $id => $name) {
|
|
$out['hosts'][$id] = ['name' => $name, 'seen' => false, 'self' => $id === $me,
|
|
'synced' => null, 'today' => $blank, 'week' => $blank, 'all' => $blank];
|
|
}
|
|
|
|
// Ledgers to read: our own, plus whatever AI/ai_token_sync.sh has pulled from partners.
|
|
//
|
|
// Each entry carries the host slot it is allowed to contribute rows for. A partner file may
|
|
// only add rows whose host column matches its filename — a ledger copied into the wrong slot,
|
|
// or a partner that somehow cached ours, would otherwise be counted twice against a total
|
|
// that still looked plausible. Our own file is trusted for any host, because it is the only
|
|
// one written here and its host column is written by vv_detect_host().
|
|
$ledgers = [[$db, null]];
|
|
foreach ((array)@glob(VV_AI_TOKEN_CACHE_DIR . '/host*.tokens.db') as $partnerDb) {
|
|
if (!preg_match('/(host\d+)\.tokens\.db$/', $partnerDb, $m)) continue;
|
|
if ($m[1] === $me) continue; // our own ledger is already read above
|
|
$ledgers[] = [$partnerDb, $m[1]];
|
|
if (isset($out['hosts'][$m[1]])) $out['hosts'][$m[1]]['synced'] = @filemtime($partnerDb) ?: null;
|
|
}
|
|
|
|
$add = function (array $b, int $p, int $c): array {
|
|
$b['turns']++; $b['prompt'] += $p; $b['completion'] += $c; $b['total'] += $p + $c;
|
|
return $b;
|
|
};
|
|
|
|
foreach ($ledgers as [$path, $onlyHost]) {
|
|
$fh = @fopen($path, 'r');
|
|
if (!$fh) continue;
|
|
|
|
while (($line = fgets($fh)) !== false) {
|
|
$f = explode('|', rtrim($line, "\r\n"));
|
|
if (count($f) < 8) continue; // partial write, or a format change
|
|
[$date, , $host, $profile, $source, $p, $c, $tokS] = $f;
|
|
if (!preg_match('/^\d{4}-\d{2}-\d{2}$/', $date)) continue;
|
|
if ($onlyHost !== null && $host !== $onlyHost) continue;
|
|
$p = (int)$p; $c = (int)$c;
|
|
|
|
if (!isset($out['hosts'][$host])) {
|
|
// A host in the file that conf no longer lists — renamed, or a row copied in.
|
|
// Shown rather than dropped, so the totals reconcile with the per-host rows.
|
|
$out['hosts'][$host] = ['name' => $host, 'seen' => false, 'self' => false,
|
|
'synced' => null, 'today' => $blank, 'week' => $blank, 'all' => $blank];
|
|
}
|
|
$out['hosts'][$host]['seen'] = true;
|
|
|
|
foreach ([['all', true], ['week', $date >= $week], ['today', $date === $today]] as [$k, $hit]) {
|
|
if (!$hit) continue;
|
|
$out[$k] = $add($out[$k], $p, $c);
|
|
$out['hosts'][$host][$k] = $add($out['hosts'][$host][$k], $p, $c);
|
|
}
|
|
|
|
$out['profiles'][$profile] = ($out['profiles'][$profile] ?? 0) + $p + $c;
|
|
$out['sources'][$source] = ($out['sources'][$source] ?? 0) + $p + $c;
|
|
if ($tokS !== '' && (float)$tokS > (float)($out['best_tok_s'] ?? 0)) $out['best_tok_s'] = (float)$tokS;
|
|
// Min/max rather than first-row/last-row. Appends are chronological in practice, but
|
|
// a file hand-edited, merged or restored out of order would otherwise report a span
|
|
// that reads backwards — and the row cap means the oldest row is not permanent.
|
|
if ($out['first'] === null || $date < $out['first']) $out['first'] = $date;
|
|
if ($out['last'] === null || $date > $out['last']) $out['last'] = $date;
|
|
}
|
|
fclose($fh);
|
|
}
|
|
|
|
arsort($out['profiles']);
|
|
arsort($out['sources']);
|
|
$out['days'] = $out['first'] ? max(1, (int)((strtotime($today) - strtotime($out['first'])) / 86400) + 1) : 0;
|
|
return $out;
|
|
}
|
|
|
|
// ── Scoped lookups for the Scheduler's assistant ──────────────────────────────────────────────
|
|
|
|
// The tail of one named script's log, for the troubleshooting profile. vv_ai_recent_logs()
|
|
// answers "is anything wrong anywhere"; this answers "why did THIS fail", which is a different
|
|
// question and needs the ordinary lines too, not just WARN and ERROR — the last thing a script
|
|
// printed before stopping is usually not labelled as a warning.
|
|
//
|
|
// Contained to LOG_DIR by realpath. The id arrives from a request, and a log path that escaped
|
|
// would read arbitrary files into a model's context.
|
|
function vv_ai_scoped_log(string $id, int $lines = 120): array {
|
|
$rel = preg_replace('/\.sh$/', '', trim($id)) . '.log';
|
|
if ($rel === '' || str_contains($rel, "\0")) return ['ok' => false, 'error' => 'bad id'];
|
|
|
|
$base = realpath(LOG_DIR);
|
|
$path = realpath(LOG_DIR . '/' . $rel);
|
|
if ($base === false || $path === false) return ['ok' => false, 'error' => 'no log yet'];
|
|
if (!str_starts_with($path, $base . '/')) return ['ok' => false, 'error' => 'outside log dir'];
|
|
if (!is_file($path)) return ['ok' => false, 'error' => 'no log yet'];
|
|
|
|
$all = @file($path, FILE_IGNORE_NEW_LINES) ?: [];
|
|
return [
|
|
'ok' => true,
|
|
'path' => $rel,
|
|
'total' => count($all),
|
|
'mtime' => @filemtime($path) ?: null,
|
|
'tail' => array_slice($all, -max(10, min($lines, 400))),
|
|
];
|
|
}
|
|
|
|
// The run record a script's wrapper writes beside its log: how the last run ended, in four
|
|
// fields, without reading a line of the log. "How did it go" is answerable from this alone —
|
|
// status, exit code and the window it ran in — and the log tail then supplies the detail.
|
|
// Separate from vv_ai_scoped_log() because they fail independently: a script killed mid-run
|
|
// leaves a log and no record, and that difference is itself the answer.
|
|
function vv_ai_run_record(string $id): array {
|
|
$rel = preg_replace('/\.sh$/', '', trim($id)) . '.json';
|
|
if ($rel === '' || str_contains($rel, "\0")) return ['ok' => false];
|
|
|
|
$base = realpath(LOG_DIR);
|
|
$path = realpath(LOG_DIR . '/' . $rel);
|
|
if ($base === false || $path === false) return ['ok' => false];
|
|
if (!str_starts_with($path, $base . '/')) return ['ok' => false];
|
|
|
|
$r = json_decode((string)@file_get_contents($path), true);
|
|
if (!is_array($r) || !isset($r['start'])) return ['ok' => false];
|
|
|
|
$start = (int)$r['start'];
|
|
$end = isset($r['end']) ? (int)$r['end'] : 0;
|
|
return [
|
|
'ok' => true,
|
|
'status' => (string)($r['status'] ?? '?'),
|
|
'exit' => isset($r['exit']) ? (int)$r['exit'] : null,
|
|
'start' => $start,
|
|
'end' => $end ?: null,
|
|
'duration' => $end > $start ? $end - $start : null,
|
|
];
|
|
}
|
|
|
|
// Which script a run-outcome question is about, when the operator names it in prose rather than
|
|
// by opening its log. "How did the daily orch go" has to resolve to Orchestrators/daily_sync_
|
|
// maintenance before anything can be attached to the context.
|
|
//
|
|
// Aliases are an explicit table, and matching against real log ids is exact on the underscore
|
|
// tokens — no similarity scoring. The failure mode of a scored match here is attaching the wrong
|
|
// script's log and answering confidently about a run the operator never asked about, which is
|
|
// indistinguishable from a correct answer unless they already knew. Ambiguity returns nothing so
|
|
// the question falls through to ordinary retrieval, which is merely unhelpful rather than wrong.
|
|
function vv_ai_resolve_run_target(string $question): string {
|
|
$q = strtolower($question);
|
|
|
|
static $aliases = [
|
|
'Orchestrators/daily_sync_maintenance' => ['daily orch', 'daily orchestrator',
|
|
'daily sync', 'daily maintenance', 'daily run'],
|
|
'Orchestrators/weekly_sync_maintenance' => ['weekly orch', 'weekly orchestrator',
|
|
'weekly sync', 'weekly maintenance', 'weekly run'],
|
|
'Orchestrators/critical_sync_maintenance' => ['critical orch', 'critical sync', 'critical run'],
|
|
'Orchestrators/intermediate_sync_maintenance' => ['intermediate orch', 'intermediate sync'],
|
|
'Orchestrators/watchdog_orchestrator' => ['watchdog orch', 'watchdog orchestrator',
|
|
'watchdogs'],
|
|
'Orchestrators/transcode_management' => ['transcode orch', 'transcode management'],
|
|
'Orchestrators/array_started' => ['array start', 'array started'],
|
|
'Orchestrators/monthly_maintenance' => ['monthly orch', 'monthly maintenance'],
|
|
'Orchestrators/sunday_morning_coffee_report' => ['coffee report', 'sunday report',
|
|
'sunday morning coffee'],
|
|
];
|
|
foreach ($aliases as $id => $phrases) {
|
|
foreach ($phrases as $p) if (str_contains($q, $p)) return $id;
|
|
}
|
|
|
|
// Anything with a log but no alias — named outright, either as an id or a bare script name.
|
|
//
|
|
// Whole words only. A substring test matched the `ai` log inside the word "f-ai-l", so
|
|
// "why did this run fail" resolved to ai.log and would have attached it to a question about
|
|
// something else entirely. Short ids make that failure common rather than exotic: mail, again,
|
|
// available, maintenance all contain it.
|
|
$hits = [];
|
|
foreach (vv_ai_log_ids() as $id) {
|
|
foreach ([strtolower($id), strtolower(basename($id))] as $needle) {
|
|
if ($needle !== '' && preg_match('/\b' . preg_quote($needle, '/') . '\b/', $q)) {
|
|
$hits[] = $id;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
$hits = array_unique($hits);
|
|
if (count($hits) === 1) return reset($hits);
|
|
|
|
// Longest match wins only when one candidate contains every other — "daily_sync_maintenance"
|
|
// over "sync", not a coin toss between two unrelated scripts.
|
|
if (count($hits) > 1) {
|
|
usort($hits, fn($a, $b) => strlen($b) - strlen($a));
|
|
$longest = $hits[0];
|
|
foreach (array_slice($hits, 1) as $h) {
|
|
if (!str_contains(strtolower($longest), strtolower(basename($h)))) return '';
|
|
}
|
|
return $longest;
|
|
}
|
|
return '';
|
|
}
|
|
|
|
// Every script id that has a log, relative to LOG_DIR and without the extension. One level of
|
|
// nesting, which is how the log tree is actually laid out (Orchestrators/, Plugin/).
|
|
function vv_ai_log_ids(): array {
|
|
$base = realpath(LOG_DIR);
|
|
if ($base === false) return [];
|
|
$ids = [];
|
|
foreach (glob($base . '/*.log') ?: [] as $f) {
|
|
$ids[] = basename($f, '.log');
|
|
}
|
|
foreach (glob($base . '/*/*.log') ?: [] as $f) {
|
|
$ids[] = basename(dirname($f)) . '/' . basename($f, '.log');
|
|
}
|
|
return $ids;
|
|
}
|
|
|
|
// Where a conf key actually lives. Deterministic on purpose: the model should narrate this, not
|
|
// work it out. Searches the host's own conf and master, reports file, line and value.
|
|
//
|
|
// This is the "Jonny" case — someone is sure a setting is in master.conf and it is really in the
|
|
// host conf. Failing to find it is the unhelpful answer; finding it and saying where is the
|
|
// useful one, and neither should depend on the model guessing which file to trust.
|
|
function vv_ai_find_conf_key(string $key): array {
|
|
if (!preg_match('/^[A-Za-z][A-Za-z0-9_]{1,63}$/', $key)) return ['ok' => false];
|
|
|
|
$me = vv_detect_host();
|
|
$order = array_values(array_unique(array_filter([
|
|
$me !== 'unknown' ? $me . '.conf' : null,
|
|
'master.conf',
|
|
])));
|
|
foreach (vv_get_conf_files() as $f) if (!in_array($f, $order, true)) $order[] = $f;
|
|
|
|
// Two passes, active before commented, across every file — not first-match-wins per line.
|
|
// These confs document each setting in a comment block above it, and those blocks contain
|
|
// lines like "# RSYNC_ENABLED=false → ALL rsync stops everywhere". A single pass matched
|
|
// that prose at line 529 and reported the setting as commented out while the live value sat
|
|
// active at line 546. Reporting an enabled setting as disabled is the exact failure this
|
|
// lookup exists to prevent, so the active definition always wins.
|
|
$q = preg_quote($key, '/');
|
|
$files = [];
|
|
foreach ($order as $file) $files[$file] = @file(CONF_DIR . '/' . $file, FILE_IGNORE_NEW_LINES) ?: [];
|
|
|
|
foreach ($files as $file => $lines) {
|
|
foreach ($lines as $i => $line) {
|
|
if (preg_match('/^\s*' . $q . '\s*=/', $line)) {
|
|
return ['ok' => true, 'file' => $file, 'line' => $i + 1,
|
|
'text' => trim($line), 'commented' => false];
|
|
}
|
|
}
|
|
}
|
|
foreach ($files as $file => $lines) {
|
|
foreach ($lines as $i => $line) {
|
|
if (preg_match('/^\s*#\s*' . $q . '\s*=/', $line)) {
|
|
return ['ok' => true, 'file' => $file, 'line' => $i + 1,
|
|
'text' => trim($line), 'commented' => true];
|
|
}
|
|
}
|
|
}
|
|
return ['ok' => false];
|
|
}
|
|
|
|
// One definition of a valid scope, used by every caller. A scope names something in this page's
|
|
// own view state — a conf file, a script, a log. It reaches the model as text and, for the
|
|
// troubleshooting profile, composes a path under LOG_DIR, so `..` is refused outright rather
|
|
// than left for the containment check downstream to catch. That check stays: this is the first
|
|
// gate, not the only one.
|
|
function vv_ai_scope_ok(string $scope): bool {
|
|
if (!preg_match('#^[A-Za-z0-9 ._/-]{1,80}$#', $scope)) return false;
|
|
if (str_contains($scope, '..')) return false;
|
|
return true;
|
|
}
|
|
|
|
// ── AI-filed bug reports ─────────────────────────────────────────────────────────────────────
|
|
// When the troubleshooter concludes the evidence shows a defect in Varaverk itself — not a
|
|
// setting — it files a report here rather than only saying so in a chat window that closes.
|
|
//
|
|
// Filed automatically, with the care put into the guard rather than into a review queue: a
|
|
// report requires a component and a quoted line of evidence, and identical findings collapse
|
|
// onto one record with a seen count. Without that, asking the same question three times files
|
|
// three bugs and the pile becomes noise within a week.
|
|
//
|
|
// Under data/ and therefore gitignored: these quote this installation's logs.
|
|
function vv_ai_bugs_dir(): string {
|
|
$d = AI_DATA_DIR . '/ai_bugs';
|
|
if (!is_dir($d)) @mkdir($d, 0755, true);
|
|
return $d;
|
|
}
|
|
|
|
// Same component + same summary is the same finding. Hashing them means a recurring fault
|
|
// increments a counter instead of breeding files, and the count is itself the signal: seen 40
|
|
// times is a different problem from seen once.
|
|
function vv_ai_bug_file(array $r): string {
|
|
return vv_ai_bugs_dir() . '/' . substr(sha1(strtolower($r['component'] . '|' . $r['summary'])), 0, 12) . '.json';
|
|
}
|
|
|
|
// Does the quoted evidence actually appear in the log the model was shown?
|
|
//
|
|
// The prompt asks for a verbatim line. This checks it, because "manufactured a cause to have
|
|
// one" is the specific failure this profile was warned against and warnings are not guards —
|
|
// the same reason General Chat needed a regex behind its instruction, not just a firmer wording.
|
|
//
|
|
// Whitespace-normalised and matched on the longest quoted fragment: the model reliably keeps the
|
|
// text and unreliably keeps the indentation. A short fragment would match by coincidence, so
|
|
// anything under 25 characters is not treated as a match at all.
|
|
function vv_ai_evidence_in_log(string $evidence, array $tail): bool {
|
|
if (!$tail) return false;
|
|
$norm = fn(string $s) => preg_replace('/\s+/', ' ', trim($s));
|
|
$hay = ' ' . implode(' ⏎ ', array_map($norm, $tail)) . ' ';
|
|
|
|
$frags = array_filter(array_map($norm, preg_split('/\R/', $evidence)),
|
|
fn($l) => mb_strlen($l) >= 25);
|
|
usort($frags, fn($a, $b) => mb_strlen($b) <=> mb_strlen($a));
|
|
foreach (array_slice($frags, 0, 5) as $f) {
|
|
if (str_contains($hay, $f)) return true;
|
|
// Allow a trimmed tail of the fragment — models often drop a trailing clause.
|
|
$head = mb_substr($f, 0, max(25, (int)(mb_strlen($f) * 0.6)));
|
|
if (mb_strlen($head) >= 25 && str_contains($hay, $head)) return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
// Is the named component a real file in this installation? A defect report against a path that
|
|
// does not exist is a confabulation, and it is free to check.
|
|
function vv_ai_component_exists(string $component): bool {
|
|
$c = trim($component);
|
|
if ($c === '' || !vv_ai_scope_ok($c)) return false;
|
|
$base = realpath(SCRIPTS_DIR);
|
|
$p = realpath(SCRIPTS_DIR . '/' . $c);
|
|
return $base !== false && $p !== false && str_starts_with($p, $base . '/') && is_file($p);
|
|
}
|
|
|
|
function vv_ai_bug_write(string $component, string $summary, string $evidence, array $ctx = []): array {
|
|
$component = trim($component);
|
|
$summary = trim($summary);
|
|
$evidence = trim($evidence);
|
|
// Evidence is mandatory. A report that cannot quote the line it is based on is an opinion,
|
|
// and this file exists to hold findings that can be checked.
|
|
if ($component === '' || $summary === '' || $evidence === '') return ['ok' => false];
|
|
if (!vv_ai_scope_ok($component)) return ['ok' => false];
|
|
|
|
// The commit as it was when the fault was seen, not when the report is read. "Is this already
|
|
// fixed" is the first question any maintainer asks, and a version captured later answers a
|
|
// different question. Slot id (host1/host2) rather than the hostname — this text is written
|
|
// to be pasted into a public issue.
|
|
$commit = '';
|
|
$head = @file_get_contents(SCRIPTS_DIR . '/.git/HEAD');
|
|
if (is_string($head) && preg_match('#^ref:\s*(\S+)#', trim($head), $hm)) {
|
|
$commit = substr(trim((string)@file_get_contents(SCRIPTS_DIR . '/.git/' . $hm[1])), 0, 12);
|
|
} elseif (is_string($head)) {
|
|
$commit = substr(trim($head), 0, 12);
|
|
}
|
|
|
|
$rec = [
|
|
'component' => mb_substr($component, 0, 120),
|
|
'summary' => mb_substr($summary, 0, 300),
|
|
'evidence' => mb_substr($evidence, 0, 2000),
|
|
'commit' => $commit,
|
|
'host' => vv_detect_host(),
|
|
'first' => time(),
|
|
'last' => time(),
|
|
'seen' => 1,
|
|
'open' => true,
|
|
'context' => array_slice($ctx, 0, 12),
|
|
];
|
|
$p = vv_ai_bug_file($rec);
|
|
if (is_file($p)) {
|
|
$old = json_decode((string)@file_get_contents($p), true);
|
|
if (is_array($old)) {
|
|
$rec['first'] = $old['first'] ?? $rec['first'];
|
|
$rec['seen'] = (int)($old['seen'] ?? 0) + 1;
|
|
$rec['open'] = $old['open'] ?? true; // dismissing it stays dismissed
|
|
}
|
|
}
|
|
$rec['id'] = basename($p, '.json');
|
|
if (@file_put_contents($p, json_encode($rec, JSON_PRETTY_PRINT)) === false) return ['ok' => false];
|
|
return ['ok' => true, 'id' => $rec['id'], 'seen' => $rec['seen']];
|
|
}
|
|
|
|
function vv_ai_bugs_list(bool $openOnly = true): array {
|
|
$out = [];
|
|
foreach ((array)@glob(vv_ai_bugs_dir() . '/*.json') as $f) {
|
|
$r = json_decode((string)@file_get_contents($f), true);
|
|
if (!is_array($r) || ($openOnly && empty($r['open']))) continue;
|
|
$out[] = $r;
|
|
}
|
|
usort($out, fn($a, $b) => ($b['last'] ?? 0) <=> ($a['last'] ?? 0));
|
|
return $out;
|
|
}
|
|
|
|
function vv_ai_bug_set_open(string $id, bool $open): bool {
|
|
if (!preg_match('/^[0-9a-f]{12}$/', $id)) return false;
|
|
$p = vv_ai_bugs_dir() . '/' . $id . '.json';
|
|
$r = json_decode((string)@file_get_contents($p), true);
|
|
if (!is_array($r)) return false;
|
|
$r['open'] = $open;
|
|
return @file_put_contents($p, json_encode($r, JSON_PRETTY_PRINT)) !== false;
|
|
}
|
|
|
|
// ── Incident journal ─────────────────────────────────────────────────────────────────────────
|
|
// "We have seen this before, and here is what it was." Appended as you work through logs, and
|
|
// fed back the next time the same script is being diagnosed.
|
|
//
|
|
// Deliberately NOT part of the AI index. The index reads git-tracked files only, and this lives
|
|
// under data/ which is gitignored — which is correct twice over: incident notes are about this
|
|
// installation and should not be pushed, and retrieval by similarity is the wrong lookup here.
|
|
// The right question is "what has gone wrong with THIS script before", which is an exact match
|
|
// on the scope, not a vector search. Same reasoning as the standing memory file.
|
|
//
|
|
// Markdown rather than a delimited .db because the useful part is prose — a fix is a sentence,
|
|
// not a field — and it stays hand-editable when a note turns out to be wrong.
|
|
function vv_ai_incidents_path(): string {
|
|
return AI_DATA_DIR . '/ai_incidents.md';
|
|
}
|
|
|
|
// One entry, appended. The symptom is captured from what was being asked; the fix is written by
|
|
// the operator. That split matters: the model's diagnosis is a hypothesis, and writing a
|
|
// hypothesis into institutional memory as fact is how a wrong answer outlives the incident.
|
|
function vv_ai_incident_add(string $scope, string $symptom, string $fix): array {
|
|
$scope = trim($scope);
|
|
$symptom = trim($symptom);
|
|
$fix = trim($fix);
|
|
if ($scope === '' || $fix === '') return ['ok' => false, 'error' => 'scope and fix are required'];
|
|
if (!vv_ai_scope_ok($scope)) return ['ok' => false, 'error' => 'bad scope'];
|
|
|
|
$entry = "\n## " . date('Y-m-d') . ' · ' . $scope . "\n"
|
|
. ($symptom !== '' ? '**Symptom:** ' . mb_substr($symptom, 0, 400) . "\n" : '')
|
|
. '**Fix:** ' . mb_substr($fix, 0, 1200) . "\n";
|
|
|
|
$p = vv_ai_incidents_path();
|
|
if (!is_dir(dirname($p)) && !@mkdir(dirname($p), 0755, true)) {
|
|
return ['ok' => false, 'error' => 'cannot create data dir'];
|
|
}
|
|
if (!file_exists($p)) {
|
|
@file_put_contents($p, "# Incident journal\n\nWhat went wrong, and what actually fixed it."
|
|
. " Written by the operator from the Scheduler assistant; fed back when the same"
|
|
. " script is diagnosed again.\n");
|
|
}
|
|
if (@file_put_contents($p, $entry, FILE_APPEND | LOCK_EX) === false) {
|
|
return ['ok' => false, 'error' => 'cannot write journal'];
|
|
}
|
|
return ['ok' => true];
|
|
}
|
|
|
|
// Past entries for one scope, newest first. Capped hard: this rides in the prompt alongside a
|
|
// 120-line log and retrieved passages, and the context budget is already the tight thing.
|
|
function vv_ai_incidents_for(string $scope, int $max = 4): array {
|
|
$p = vv_ai_incidents_path();
|
|
if ($scope === '' || !is_file($p)) return [];
|
|
|
|
$blocks = preg_split('/^## /m', (string)@file_get_contents($p));
|
|
$want = strtolower(trim($scope));
|
|
$base = strtolower(basename(trim($scope)));
|
|
$hits = [];
|
|
foreach ($blocks as $b) {
|
|
$b = trim($b);
|
|
if ($b === '' || !str_contains($b, "\n")) continue;
|
|
[$head] = explode("\n", $b, 2);
|
|
$head = strtolower($head);
|
|
// Match the scope as written, or its basename — the chip may carry a path where an
|
|
// older entry carried only the script name.
|
|
if (!str_contains($head, $want) && !str_contains($head, $base)) continue;
|
|
$hits[] = '## ' . $b;
|
|
}
|
|
return array_slice(array_reverse($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 {
|
|
$d = AI_DATA_DIR . '/ai_chats';
|
|
if (!is_dir($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),
|
|
// Last activity, as distinct from ts. The list is ordered by creation so the prune
|
|
// order and the visible order agree, but "which conversation was I last in" is a
|
|
// different question and needs the other timestamp to answer it.
|
|
'updated' => (int)($d['updated'] ?? $d['ts'] ?? 0),
|
|
'profile' => (string)($d['profile'] ?? 'chat'),
|
|
'scope' => (string)($d['scope'] ?? ''),
|
|
'title' => (string)($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, string $scope = ''): array {
|
|
if (!$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());
|
|
|
|
// Scope travels with the conversation. A Scheduler thread is bound to what the operator had
|
|
// open — a script, a log, a conf key — and its turns carry log excerpts chosen for that
|
|
// thing. Storing the scope means reopening the thread anywhere restores the context it was
|
|
// reasoned in, rather than silently continuing a troubleshooting conversation against
|
|
// whatever happens to be on screen. The isolation the page enforces in memory becomes a
|
|
// property of the record instead of something lost the moment it is saved.
|
|
$rec = [
|
|
'id' => $id,
|
|
'created' => $created,
|
|
'ts' => $created,
|
|
'updated' => time(),
|
|
'profile' => $profile,
|
|
'scope' => $scope,
|
|
'title' => vv_ai_chat_title($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;
|
|
}
|
|
|
|
// Hex-only, fixed length. The token composes a path, so the pattern is what confines it to the
|
|
// job directory.
|
|
function vv_ai_job_path(string $token): ?string {
|
|
if (!preg_match('/^[0-9a-f]{32}$/', $token)) return null;
|
|
return VV_AI_JOB_DIR . '/' . $token . '.json';
|
|
}
|
|
|
|
function vv_ai_job_read(string $token): ?array {
|
|
$p = vv_ai_job_path($token);
|
|
if ($p === null || !file_exists($p)) return null;
|
|
$d = json_decode(@file_get_contents($p) ?: '', true);
|
|
return is_array($d) ? $d : null;
|
|
}
|