# Stage 101: CodeGraph & DocGraph (aq101_build_codegraph_and_docgraph / DB-UNIT-06)

Extracts typed file summaries, inputs, outputs, cross-file AST/citation edges, and rich search attributes on a non-blocking ASYNC_ENHANCEMENT track.

- Atomic micro-queue: `aq101_build_codegraph_and_docgraph` (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: AST Imports & Ports, Section & Citation Edges, Async Fleet Labels

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `ast_signature_card_compiler_v1` (Python/TS AST import-export & Markdown/PDF section graph builder)
- **Hybrid (<=1 model call)**: `multilingual_card_summarizer_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `cross_harness_skill_adapter_v1` (Semantic IO relationship & usability annotator)
  - 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

- Map upstream inputs, downstream outputs, and peer file connections across large repos and drives
- Enrich every file with searchable summaries, labels, keys, and usability metadata asynchronously
- Keep the critical-path pipeline running at full speed while fleet workers enrich the graph

## 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