# Stage 99: 0-Call File Triage (aq99_rank_files_deterministic_0call / DB-UNIT-17)

Applies deterministic 0-call rules over path depth, extensions, schemas, CAD/creative headers, and SWHID duplicates to rank millions of corpus files instantly.

- Atomic micro-queue: `aq99_rank_files_deterministic_0call` (visibility: `public_commons`)
- Backing database unit: `DB-UNIT-17` (`Cascading Decision Models, Local Classifiers & Abstention Core`)
- Database cell: `lsh-db.teleon.dev` (`teleon_core.decision_rubric_schemas`, `teleon_core.cascade_classification_ledger`, `teleon_core.abstention_calibration_sets`)
- Claim row hydration: `single_self_contained_flat_task_row` (100% context inline, normalized writeback)
- Track 2 Sister queue (`SISTER-17`): `sq17-improve-decisions-queue.teleon.dev` (Distill frontier decisions into compact SetFit/ModernBERT/GLiNER2 CPU heads and tighten natural no-match abstention thresholds.)
- Lanes: Entrypoint & Schema Rules, Magic-Byte & Path Score, SWHID Dedup

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `rule_model2vec_setfit_gliner_cpu_cascade_v1` (Rule-based path, extension & schema priority scorer (0 model calls))
- **Hybrid (<=1 model call)**: `clef_jev_clairic_typed_decision_escalation_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `ambiguous_tail_reasoning_arbitrator_v1` (Domain heuristic rule author)
  - Contract: **Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions**

## Database invariants

- Static rubrics precede dynamic item state so input-only decision APIs capture cached-prefix discounts.
- Below-threshold confidence returns explicit ABSTAIN or escalates rather than pushing mismatched components.

## External & internal bot fleet actions

- Boost entrypoints, typed schemas, solver modules, glTF/USD scenes, and clean datasets
- Demote vendor bundles, generated lockfiles, and duplicate SWHIDs before LLM spend
- Pass only top-ranked candidates to Tier-2 agent importance scoring

## Sister self-tuning areas

- Distill recurring multi-question rubrics into 8-to-32-shot SetFit and ONNX INT8 CPU classifiers (DIM-03, DIM-06)
- Calibrate per-domain abstention thresholds on 25%+ natural no-suitable-component holdouts (DIM-01, DIM-06)
- Benchmark choice-order invariance across Clef-flash, Jev, Clairic, and Decisions endpoints (DIM-02, DIM-08)