> ## Documentation Index > Fetch the complete documentation index at: https://helloluciallc.com/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI Model Layer OpenAI powers Lucia’s model-assisted reasoning and language refinement. The model layer must remain upgradeable without breaking Lucia’s response contract. *** ## Current Runtime Lucia Engine v0.1.3.6 Development uses: ```text theme={"dark"} gpt-5.6-sol default model (GPT-5.6 Sol) OpenAI Responses API ``` The Lucia Guest Agent Netlify production deployment uses: ```text theme={"dark"} runtime owner: hello-lucia/lucia-guest-agent branch: main source commit: 826a6a14e2fa95bfd60c8008fb0cdc9d846b4231 production URL: https://guest.hellolucia.ai default model: gpt-5.6-sol (GPT-5.6 Sol) production override: VV_AI_MODEL=gpt-5.6-sol source fallback: gpt-5.6-sol model gateway: OpenAI Responses API embeddings model: text-embedding-3-small live provider-returned model proof: gpt-5.6-sol ``` Both surfaces currently use `gpt-5.6-sol`, but they own independent configuration, deployment, and verification boundaries. Engine runtime proof does not establish Guest Agent runtime truth, and Guest Agent proof does not establish Engine runtime truth. The Guest Agent does not expose or persist the Engine's `/admin/operator-focus` runtime-provenance fields. Its live provider-returned model proof is deployment evidence for the Guest Agent only. The purpose is not novelty. The purpose is: ```text theme={"dark"} better reasoning better intent handling future-proof model upgrades controlled API environment ``` *** ## JSON Model Gateway Lucia’s JSON model gateway has migrated from Chat Completions to the OpenAI Responses API. Current Development truth: ```text theme={"dark"} JSON task path → Responses API semantic conversational intent assist → live in Focus Ops GPT-5.6 Sol response refinement → verified context packs with truth/routing guardrails workspace context awareness → active_context.workspace normalized safely guest-facing Lucia → identity/linkage state stays deterministic strict brain quality eval → 178/178 after workspace-context awareness ``` The gateway is infrastructure. It may improve reasoning and language quality, but it must not change Lucia’s public response contract by accident. *** ## Critical Constraint Model upgrades must not break: ```text theme={"dark"} response contract truth-state discipline operator calm routing correctness permission-based CTAs scoped entity routing reminder truth-state prior recommendation memory prior offer context active_context scoping workspace context awareness saved DAW workflow truth-state guest identity/linkage truth-state magic-link verification boundary ``` *** ## Model Does Not Own The model must not own: ```text theme={"dark"} system truth external execution claims route contract identity of records verified completion workspace truth guest verification truth booking-private data access ``` *** ## Model Can Improve The model may improve: ```text theme={"dark"} natural language tone reasoning expression intent sensitivity operator-facing clarity multi-turn interpretation permission-based phrasing emotional containment ``` Model output sits above deterministic truth. Guest identity, booking IDs, stay windows, payment state, task status, route/action safety, and save/completion truth remain system-owned. Guest-facing Lucia follows the same rule: identity\_state, verification\_state, linkage\_state, verification email destination, token validity, and booking-private data access remain system-owned. Workspace context follows the same rule. GPT-5.6 Sol may explain the current surface in natural language, but deterministic context owns the current surface, active booking/task/action, saved DAW workflow state, and whether the underlying issue is still unresolved. *** ## Runtime Provenance Contract The Development `/admin/operator-focus` route exposes runtime and model evidence in the same response that contains Lucia's answer. The public top-level contract remains stable: ```text theme={"dark"} ok data meta ``` `meta.runtime` reports the Engine `service_id`, `environment`, `version`, and `commit_sha`. `meta.model_runtime` reports: ```text theme={"dark"} configured_model resolved_model model_invoked deterministic_path fallback_used tasks ``` The gateway captures the provider-returned `response.model` as task-level `resolved_model`. The top-level resolved model is reported only when the attempted model tasks resolve consistently. Per-task evidence records whether a call was attempted, a provider response arrived, parsing succeeded, fallback was used, and the task status. Interpretation rules: ```text theme={"dark"} no attempted model task → model_invoked=false, deterministic_path=true one or more attempted model tasks → model_invoked=true, deterministic_path=false fallback state → fallback_used=true independently of the two states above ``` A provider-backed success additionally requires successful task evidence, a provider response, parsing success, a resolved model, and no fallback for that task. A provider failure can therefore report `model_invoked=true` and `fallback_used=true`; a client-disabled or no-attempt fallback can report `model_invoked=false`, `deterministic_path=true`, and `fallback_used=true`. A `200` response does not by itself prove model execution or provider success. Consumers must read provenance rather than infer it from the route status or configured model. *** ## Current Upgrade Status The GPT-5.6 Sol default and Responses API gateway are active in Development for Lucia Engine v0.1.3.6. This supersedes the earlier Engine GPT-5.5 Development baseline; the dated GPT-5.5 decision and release entries remain historical evidence. The Guest Agent's independent GPT-5.6 Sol upgrade was live-verified on 2026-07-12. Its prompts, verification flow, routing, schemas, and core SSE events (`start`, `token`, `cta`, `meta`, `done`) were unchanged. Model upgrades are infrastructure changes only when response contract and product behavior remain stable. v0.1.3.6 has not been promoted to Staging yet. *** ## See Also * [03 - Reasoning Model](/lucia/intelligence/reasoning-model) * [02 - Truth State Doctrine](/lucia/foundation/truth-state-doctrine) * [00 - START HERE - Evaluation System](/lucia/evaluation/start-here-evaluation-system) * [11 - Domains and Live Routing](/lucia/infrastructure/domains-and-live-routing) * [00 - START HERE - Guest-Facing Lucia](/lucia/guest-facing-lucia/start-here-guest-facing-lucia)