gustavosantos/SLACK_COORD_RELATORIO
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(v2): fix "Validar e executar" bug (real root cause), expand generic-phrase blacklist, add FORCE_SEND

Browse Source 
Root cause found for why the real Slack message showed "→ Validar e
executar" for nearly every ACTIONABLE_NOW ticket: logic/message.js's
ACTION_LABELS map had a hardcoded entry for ACTIONABLE_NOW that always
won over the AI's actual next_action field in shortActionLabel(). The
AI's real, specific, already-validated-as-non-generic next_action (e.g.
"Realizar inventário das máquinas") was being silently discarded for
display purposes on every single message. Fixed by removing the
ACTIONABLE_NOW entry -- it now falls through to the existing
next_action-based fallback (already there, just unreachable for that
class before). UNASSIGNED_ACTIONABLE intentionally keeps its fixed
"Atribuir técnico" label -- that IS the correct display for that class.

logic/classification.js: expanded GENERIC_NEXT_ACTION_PHRASES with the
exact phrase that leaked through ("validar e executar") plus the
mission's additional list (validar chamado, prosseguir atendimento,
executar chamado, tratar chamado, analisar chamado). Bumped
AI_CLASSIFIER_VERSION 3->4 since this changes what next_action values
validate as non-generic -- forces reclassification of any cached
candidate that only passed under the older, narrower blacklist.

n8n/nodes/validate-ai-response.node.js: generic-next-action rejections
now get their own distinct fallback_reason ('generic_or_unsupported_
next_action') instead of being lumped into 'invalid_json', matching the
same pattern already used for the technician-vendor conflict.

logic/slack.js + logic/config.js: added FORCE_SEND (default false).
Manual-triggered runs now never send for real even with SEND_ENABLED=
true in production, unless FORCE_SEND is also explicitly set -- protects
against someone clicking "Execute Workflow" in production and
accidentally re-sending today's digest.

Added format-safety regression tests (no literal backslash-n, URL never
bleeds into the next item's id, no markdown-wrapped URLs) -- verified
these were never actually triggered in a real send (the reported
corruption was n8n's raw JSON data-inspector view, not a delivered
Slack message; both manual runs in question had shouldSend:false).

169/169 tests passing.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Gustavo
2026-08-24 21:49:42 -03:00
co-authored by Claude Sonnet 5
parent 26b06e07d5
commit 124516e64a
10 changed files with 138 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
n8n/nodes/validate-ai-response.node.js
+7 -1
View File
@@ -26,8 +26,14 @@ return responseItems.map((responseItem, index) => {
if (validation.valid) {
aiClassification = validation.data;
} else {
// Motivo especifico e auditavel por que a IA caiu pra fallback -- nao joga tudo em
// "invalid_json" (missao "correcao final", secao 9: decision_reason distinguivel).
const isSemanticConflict = validation.errors.some((e) => e.includes('tecnico interno'));
aiClassification = buildFallbackClassification(isSemanticConflict ? 'ai_semantic_conflict' : 'invalid_json');
const isGenericAction = validation.errors.some((e) => e.includes('generico demais'));
let reason = 'invalid_json';
if (isSemanticConflict) reason = 'ai_semantic_conflict';
else if (isGenericAction) reason = 'generic_or_unsupported_next_action';
aiClassification = buildFallbackClassification(reason);
}
return { json: { ...original, aiClassification } };