Commit Graph
4 Commits
Author SHA1 Message Date
GustavoandClaude Sonnet 5 00a42db269 fix(v2): AI_FALLBACK replaces the ACTIONABLE_NOW-with-confidence-0 lie, normalize null-like strings
Fallback (ai_disabled, ai_error, invalid_json, ai_max_candidates_cap --
any candidate the AI never actually analyzed) now produces classification
'AI_FALLBACK', an explicit technical state that is never part of the
11-class enum sent to OpenAI (the AI itself can never legitimately return
it). Previously it silently claimed ACTIONABLE_NOW with confidence 0,
which made unanalyzed tickets indistinguishable from genuinely confirmed
ones at the classification-label level.

Also normalizes blocker_type/waiting_for when the model returns the
literal string "null"/"none"/"n/a"/"" instead of JSON null -- done
once, in the validation layer (logic/classification.js), not scattered
around the workflow.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-24 16:49:22 -03:00
GustavoandClaude Sonnet 5 a99a25cb1a feat(v2): complete n8n workflow template (36 nodes) covering full V2 pipeline + shadow branch
- 14 new Code node drivers implementing the pipeline stages: normalize
  candidates, build context SQL, merge context + hash, decide AI need,
  prepare AI prompt, validate AI response, AI-disabled fallback, reuse
  cached classification, compute score, select top 10, prepare memory/
  envio records, build message/digest, compare legacy x V2, debug panel.
- Consolidated the two context queries (followups/tasks) into a single
  UNION ALL query tagged by tipo, and added a "Merge - Unir Shadow"
  synchronization node before comparing legacy x V2: n8n does not
  guarantee relative execution order between sibling branches that only
  share an early common ancestor, so cross-branch data was only safe to
  read by name once a real Merge node forced both to complete first.
- Reordered score calculation before the memory upsert (score is needed
  in the persisted row) and turned both Data Table writes into
  side-effect branches that fan out from the main path instead of
  gating it, so the Data Table node's own output shape never needs to
  carry the full pipeline state forward.
- Fixed a duplicate-identifier bug in the build script: score.js's
  require('./cooldown') survived inlining and collided with
  cooldown.js's own computeCooldown function in the same Code node
  scope. build-workflow.js now strips inter-module requires when
  inlining, and a new test syntax-checks every generated jsCode string
  plus asserts no leftover require() calls.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-24 15:31:44 -03:00
GustavoandClaude Sonnet 5 00bb89f4f4 feat(v2): candidate pool SQL (admin exclusion preserved, no hard LIMIT 10) + verbatim legacy SQL for shadow mode
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-24 15:19:39 -03:00
GustavoandClaude Sonnet 5 1eb1f80b4f chore: baseline import of existing Coordenador GLPI V1 project
Snapshot of the pre-existing, working V1 automation (n8n workflow +
SQL query + docker-compose + README) exactly as found on disk, before
any V2 changes. .env is intentionally not tracked (gitignored,
contains local secrets).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-24 15:00:26 -03:00