# Stage 67: Bilateral Turn & Mailbox (aq67_exchange_bilateral_turn / DB-UNIT-06)

Mediates multi-turn bilateral dialog across workers, peers, supervisors, and assistants, parking task leases during clarification and resuming on reply.

- Atomic micro-queue: `aq67_exchange_bilateral_turn` (visibility: `public_commons`)
- Backing database unit: `DB-UNIT-06` (`Multi-Pass Enrichment, Packaging & 6+ Locale Core`)
- Database cell: `entities-db.teleon.dev` (`teleon_core.multipass_card_projections`, `teleon_core.harness_adapter_manifests`, `teleon_core.locale_terminology_packs`)
- Claim row hydration: `single_self_contained_flat_task_row` (100% context inline, normalized writeback)
- Track 2 Sister queue (`SISTER-06`): `sq06-improve-packaging-queue.teleon.dev` (Compress L0 token budgets without losing selection accuracy and onboard new languages and harness formats.)
- Lanes: Input-Required Park, Causal Cycle Guard, Reply & Resume

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `ast_signature_card_compiler_v1` (Correlation-ID router, call_chain cycle blocker & lease-park state machine)
- **Hybrid (<=1 model call)**: `multilingual_card_summarizer_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `cross_harness_skill_adapter_v1` (Clarifying solver, peer collaborator & human-proximate assistant)
  - Contract: **Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions**

## Database invariants

- Exact source bytes, semantic interpretation, and execution authority stay strictly separated.

## External & internal bot fleet actions

- Pause a leased task in input-required state while awaiting clarification without losing the lease
- Hand off intermediate artifacts or subplans bilaterally across Muse, ZCode, Codex, and Dots
- Reject circular A-waits-on-B-waits-on-A deadlocks via causal call_chain verification

## Sister self-tuning areas

- Onboard additional languages and technical terminology packs without English bias
- A/B test L0 card schemas (100 vs 150 vs 220 tokens) across small and frontier models
- Add deterministic compilers for emerging agent harness manifest formats