# Stage 92: Surgical Revise & Reopen (aq92_revise_and_verify_clean_reopen / DB-UNIT-06)

Applies surgical parametric revisions to targeted scene, motion, or audio nodes while preserving 80%+ untouched asset SWHIDs and verifying byte-level clean-container reopen portability in 0 model calls.

- Atomic micro-queue: `aq92_revise_and_verify_clean_reopen` (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: Untouched SWHID Guard, 5-Gate Byte Oracle, Clean-Room Reopen

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `ast_signature_card_compiler_v1` (Parameter-to-file dependency reviser & 5-gate XML/glTF/USD/Godot/WAV byte reopen verifier)
- **Hybrid (<=1 model call)**: `multilingual_card_summarizer_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `cross_harness_skill_adapter_v1` (Mid-flight art-direction pivot solver & workstation-path confinement repairer)
  - 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

- Recompile only files owned by mutated parameters so unchanged 3D, Godot, and audio blobs keep exact SWHIDs
- Verify zero /Users/, /home/, or file:// leaks and zero external fetch calls inside standalone labs
- Confirm valid SVG XML, glTF 2.0 indices, balanced OpenUSD prims, Godot res:// confinement, and RIFF PCM headers

## 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