- Fix the demo knowledge provider's tokenizer: a plain [a-z0-9]+ regex silently dropped accented characters, splitting French words like "véhicule" into "v" + "hicule" and mangling retrieval for nearly every French query. Now matches the Latin-1 accented range too. - Reweight section scoring so the body match (the actual substance of a section) outranks a heading/title match (a shallow structural hint) rather than the reverse -- confirmed via the brief's exact validation question that the old weighting misranked the damage procedure behind a topically-adjacent document in all three languages (nl-BE: a checkout section; en-GB/fr-BE: the return procedure), purely because a generic word like "vehicle"/"voertuig" happened to sit in a heading/title. - Remove leftover "MobilityOps" and "PoC" mentions from 5 English and 4 NL/FR procedure documents -- knowledge-base prose is visible UI content and was missed by the earlier rebrand. - Add regression tests: the brief's exact NL/EN/FR damage question must ground on the damage procedure as the *primary* source (not just appear in the top 3), and no procedure file may contain "MobilityOps" or "PoC". 151 backend tests, Ruff, mypy green. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
643 B
643 B
document_id, title, version, effective_date, department, status
| document_id | title | version | effective_date | department | status |
|---|---|---|---|---|---|
| booking-conflict-procedure | Booking conflict procedure | 1.2 | 2026-06-20 | Operations | active |
Booking conflict procedure
1. Detection
Two reserved or active bookings for the same vehicle may not overlap. Imported legacy conflicts must be flagged as data-quality issues.
2. Resolution
Operations reviews both bookings, confirms source-system ownership and reassigns or cancels one booking in the authoritative booking system. Fleet Ops records the reviewed outcome.
3. Safety
Do not automatically cancel a customer booking based only on an inferred conflict.