# Stage 51: Workspace Bundle Compile (aq51_workspace_bundle_compile / DB-UNIT-06)

Compiles verified capabilities into drop-in harness folders (.claude, .codex, .opencode), OCI recipes, and workflow packs with native load verification.

- Atomic micro-queue: `aq51_workspace_bundle_compile` (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: 10-Host Working Dir, HTTP 206 AST Slices, Native Load Proof

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `ast_signature_card_compiler_v1` (Working-directory tree compiler, byte-range slicer & LE-FABRIC-002 load tester)
- **Hybrid (<=1 model call)**: `multilingual_card_summarizer_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `cross_harness_skill_adapter_v1` (Cross-harness integration & MCP/CLI adapter packager)
  - 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

- Emit exact native directory layouts, skill manifests, hooks, and MCP configs without manual glue
- Keep identity, content access, inference funding, tool licensing, and effect authority strictly separate
- Prove the target harness actually parses and loads every packaged component beyond mere file existence

## 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