# Stage 85: Public Scenario Frameworks First (aq85_public_scenario_frameworks_first / DB-UNIT-18)

Wraps 7 public scenario frameworks (Meta ARE/Gaia2, NVIDIA NeMo, Snowflake AWM, DeepMind Concordia, CAMEL OASIS, Mesa, OpenEnv) to generate thousands of situated stack/industry worlds BEFORE Problemize.

- Atomic micro-queue: `aq85_public_scenario_frameworks_first` (visibility: `public_commons`)
- Backing database unit: `DB-UNIT-18` (`Causal Scenario Foundry, Simulation Federation & Opportunity Core`)
- Database cell: `entities-db.teleon.dev` (`teleon_core.scenario_ir_manifests`, `teleon_core.world_hidden_truth_vault`, `teleon_core.actor_observation_views`, `teleon_core.opportunity_hypotheses`)
- Claim row hydration: `single_self_contained_flat_task_row` (100% context inline, normalized writeback)
- Track 2 Sister queue (`SISTER-18`): `sq18-improve-scenarios-queue.teleon.dev` (Enforce POET minimal-criterion solvability bands, audit SPDX simulator licenses, and turn production failures into regression worlds.)
- Lanes: Meta ARE / Gaia2 & NeMo, Concordia / OASIS / Mesa, Situated Worlds Before Problemize

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `mesa_amlsim_and_sql_state_world_compiler_v1` (Coprime stack/regime/fault world compiler & framework adapter selector)
- **Hybrid (<=1 model call)**: `autoplay_explore_first_scenario_synthesizer_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `multi_engine_concordia_oasis_and_foresight_author_v1` (Situated legacy-vs-modern enterprise & social world architect)
  - Contract: **Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions**

## Database invariants

- Investigator and solver views never access world_hidden_truth_vault or derive test fixtures from detector rules.
- Every suspicious or failure scenario pairs with a matched benign counterfactual and abstention control.
- Opportunity and problem generation stays decoupled from pre-selected solution promotion.

## External & internal bot fleet actions

- Generate thousands of concrete stack/industry worlds (e.g. PHP+z/OS DB2 vs Rust+Kafka) first
- Select Meta ARE, NeMo, Snowflake AWM, Concordia, OASIS, Mesa, or OpenEnv per world physics
- Fan situated worlds directly into aq04_problemize_situations for stack-grounded problems

## Sister self-tuning areas

- Enforce POET solvability bands and family-level train/holdout lineage splits (DIM-01, DIM-02)
- Wrap permissive simulation adapters (MIT/Apache-2.0/BSD-3) while blocking copyleft or BSL traps (DIM-03)
- Convert verified production traces and failed experiments into permanent regression scenarios (DIM-06, DIM-07)