Production-readiness cycle. Classifier was excessively conservative (real Run A: ACTIONABLE_NOW/UNASSIGNED_ACTIONABLE both 0) and made concrete semantic mistakes on real tickets: - #34419: technician "Rafael Brito" (internal) classified as WAITING_VENDOR waiting_for -- an internal technician is not a vendor. - #37389: ticket had concrete open tasks ("Realizar um inventário das máquinas", "Alinhar o dia...") but was classified INSUFFICIENT_CONTEXT. - Generic next_action ("Revisar chamado") repeated across unrelated tickets, proving nothing about real actionability. Rewrote the system prompt (n8n/nodes/prepare-ai-prompt.node.js) with: practical actionability definition ("suporte consegue fazer algo util agora", explicit inclusion list); contatar-vs-aguardar distinction with examples; WAITING_* requires positive evidence (action already taken AND external dependency still open); technician-vs-vendor distinction citing the TECNICO context field; STATUS Planejado alone != blocked/scheduled; SCHEDULED requires an explicit date/window; mandatory chronological interpretation (most recent apontamento wins over a superseded old blocker); next_action must be concrete, with explicit accepted/rejected examples; INSUFFICIENT_CONTEXT bar raised (ask "is there a diagnostic step available even without full info" first). n8n/nodes/prepare-ai-prompt.node.test.js: 10 new tests asserting each rule's text is still present in the prompt (deterministic proxy -- behavioral proof comes from the real DEV run, inspected manually). logic/classification.js: added AI_CLASSIFIER_VERSION=3 (stamped on every valid classification); added a deterministic safety net (not just a prompt hope) -- isWaitingForInternalTechnician() rejects WAITING_VENDOR when waiting_for matches the ticket's own TECNICO field, routing to a new fallback_reason 'ai_semantic_conflict' instead of accepting a known-wrong semantic classification; added next_action genericness rejection (isGenericNextAction) for ACTIONABLE_NOW/UNASSIGNED_ACTIONABLE only. n8n/nodes/validate-ai-response.node.js: now passes the ticket into validateAiClassification() so the technician guard has the facts it needs. logic/cache.js: added buildCacheKey(contextHash, classifierVersion) -> "<hash>:v<version>", stored in the same last_context_hash column (no schema migration) -- bumping AI_CLASSIFIER_VERSION now forces a cache miss on every ticket without manually clearing the Data Table. n8n/nodes/decide-needs-ai.node.js / prepare-memoria-analise-record.node.js updated to compute/persist the composite key. logic/config.js: AI_MAX_CANDIDATES default raised 30->60 (now equals CANDIDATE_POOL_SIZE) -- no candidate should go unanalyzed by an artificial cap now that Run B already proved the cache makes repeat runs cheap; AI_FALLBACK stays reserved for real provider failures. Also added SEND_ENABLED (default false) and ENVIRONMENT config fields for the real Slack send gate (used by logic/slack.js, next commit). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
54 lines
2.2 KiB
JavaScript
54 lines
2.2 KiB
JavaScript
// @requires config.js cache.js classification.js
|
|
// Instancia bloqueia $env em Code nodes -- config vem do node "Config - Coordenador GLPI v2".
|
|
const config = parseConfig($('Config - Coordenador GLPI v2').first().json);
|
|
const now = Date.now();
|
|
|
|
// $input vem do Merge - Aguardar Memoria (so existe para GARANTIR que os candidatos e a
|
|
// memoria ja foram buscados antes deste node rodar); os dados de verdade sao lidos por nome.
|
|
const items = $('Code - Mesclar Contexto e Calcular Hash').all().map((item) => item.json); // { ticket, contextHash }
|
|
const memoryRows = $('Data Table - Buscar Memoria').all().map((item) => item.json);
|
|
const memoryByTicket = {};
|
|
for (const row of memoryRows) memoryByTicket[String(row.ticket_id)] = row;
|
|
|
|
const withDecision = items.map((item) => {
|
|
const memory = memoryByTicket[String(item.ticket.id)] || null;
|
|
// Chave de cache = conteudo do chamado + versao do classificador (logic/cache.js). Bump de
|
|
// AI_CLASSIFIER_VERSION forca cache miss em TODO chamado, mesmo sem nenhuma mudanca real no
|
|
// GLPI -- sem precisar apagar a Data Table na mao (missao "finalizacao para producao", secao 12).
|
|
const cacheKey = buildCacheKey(item.contextHash, AI_CLASSIFIER_VERSION);
|
|
const analysis = needsReanalysis({ memory, currentHash: cacheKey, now });
|
|
return {
|
|
ticket: item.ticket, contextHash: item.contextHash, cacheKey, memory, needsAiReason: analysis.reason, needsAiRaw: analysis.needsAi,
|
|
};
|
|
});
|
|
|
|
const needingAi = withDecision
|
|
.filter((item) => item.needsAiRaw)
|
|
.sort((a, b) => (Number(b.ticket.score_criticidade) || 0) - (Number(a.ticket.score_criticidade) || 0));
|
|
|
|
const allowedIds = new Set(needingAi.slice(0, config.aiMaxCandidates).map((item) => item.ticket.id));
|
|
|
|
return withDecision.map((item) => {
|
|
let resolucao;
|
|
if (!item.needsAiRaw) {
|
|
resolucao = 'cache';
|
|
} else if (allowedIds.has(item.ticket.id)) {
|
|
resolucao = 'ia';
|
|
} else {
|
|
resolucao = 'fallback_cap';
|
|
}
|
|
return {
|
|
json: {
|
|
ticket: item.ticket,
|
|
contextHash: item.contextHash,
|
|
cacheKey: item.cacheKey,
|
|
memory: item.memory,
|
|
needsAiReason: item.needsAiReason,
|
|
resolucao,
|
|
precisa_ia: resolucao === 'ia',
|
|
config,
|
|
now,
|
|
},
|
|
};
|
|
});
|