# Stage 76: Cut-Preserving Post-Split (aq76_post_split_epic_vertex / DB-UNIT-05)

Splits any macro-epic DAG node mid-flight into smaller sub-nodes or inserts new adapter/validator nodes while preserving original parent lineage and guaranteeing upstream/downstream edge compatibility.

- Atomic micro-queue: `aq76_post_split_epic_vertex` (visibility: `public_commons`)
- Backing database unit: `DB-UNIT-05` (`Typed Solution Graph & Pareto Composition Core`)
- Database cell: `graph-db.teleon.dev` (`teleon_core.teleon_weighted_graph_edges`, `teleon_core.verified_solution_dags`, `teleon_core.schema_bridge_adapters`)
- Claim row hydration: `single_self_contained_flat_task_row` (100% context inline, normalized writeback)
- Track 2 Sister queue (`SISTER-05`): `sq05-improve-composition-queue.teleon.dev` (Improve planner heuristics, promote recurring agentic subgraphs into cached deterministic macros, and add bridge tools.)
- Lanes: Boundary Port Conservation, Auto Adapter/Validator, Full Split Lineage

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `dijkstra_pareto_type_planner_v1` (Cut-preserving boundary verifier, cycle checker & incumbent-protecting edge rewirer)
- **Hybrid (<=1 model call)**: `single_shim_bridge_synthesizer_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `novel_architecture_composer_v1` (Sub-DAG refinement architect & port-adapter author)
  - Contract: **Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions**

## Database invariants

- Every executable vertex in a composed graph is a Loop; passive files never become model calls.
- Keep the no-extra-material baseline eligible in every Pareto comparison.

## External & internal bot fleet actions

- Split complex DAG stages mid-flight without breaking upstream producers or downstream consumers
- Insert deterministic adapter or anti-leakage validator nodes dynamically on any typed edge
- Protect prior stage incumbents until the post-split sub-DAG proves superior holdout quality

## Sister self-tuning areas

- Promote high-traffic multi-node subgraphs into 0-model-call deterministic macro code_blocks
- Rebalance 6D Pareto cost weights (quality, tokens, latency, reliability, determinism, reuse)
- Add new algebraic port-shim templates and composition routines