# Stage 73: Proxy Short-Circuit & Distill (aq73_proxy_short_circuit_and_distill / DB-UNIT-08)

Intercepts opt-in harness traffic at proxy.teleon.dev, answering verified exact/LSH hits in 0 inference calls, enriching misses with D1 context for BYO/hosted models, and queueing recurring misses for distillation.

- Atomic micro-queue: `aq73_proxy_short_circuit_and_distill` (visibility: `public_commons`)
- Backing database unit: `DB-UNIT-08` (`Opt-In Prompt & Inference Wire Proxy Rule Core`)
- Database cell: `telemetry-db.teleon.dev` (`teleon_core.prompt_proxy_rule_sets`, `teleon_core.direct_deterministic_hit_catalog`, `teleon_core.wire_observation_headers`)
- Claim row hydration: `single_self_contained_flat_task_row` (100% context inline, normalized writeback)
- Track 2 Sister queue (`SISTER-08`): `sq08-improve-proxy-queue.teleon.dev` (Tune direct-answer confidence thresholds, context byte budgets, and promote frequent queries to 0-call cards.)
- Lanes: 0-Call Cache Hit, D1 Context Enrich, Miss->Queue Distill

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `wire_metadata_rule_and_direct_responder_v1` (Exact + multi-scale LSH 0-call responder, context injector & secret-scrubbed miss logger)
- **Hybrid (<=1 model call)**: `compact_context_selector_hybrid_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `custom_enterprise_policy_simulator_v1` (Recurring proxy-miss solver & 0-call deterministic answer distiller)
  - Contract: **Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions**

## Database invariants

- Rule evaluation matches metadata only (never prompt prose) with strict deny -> require -> select precedence.
- User BYO provider keys pass only to the user's chosen inference host and never enter Teleon storage.

## External & internal bot fleet actions

- Serve verified deterministic answers immediately to harnesses in 0 model calls
- Inject live D1 Vault, LSH repo, and advisory cards before forwarding to BYO or hosted inference
- Distill recurring scrubbed proxy misses into verified 0-call cache entries

## Sister self-tuning areas

- Tune direct_response_min_score and max_injected_context_bytes per model family
- Promote high-frequency repeated tasks into verified deterministic direct-hit cards
- Add wire codec support and aspect tags for new local/cloud inference endpoints