Portal

Beyond the rift, another sky keeps its own thunder.

A PortalCloud ModelCloud Model is a remote, API-backed Animator declared by a provider-specific RuneService Config FileService Config File. It has no container and consumes no local VRAM. Its connector runs inside the trusted VesselEngine RoomEngine Room, where it may read the one Podman secret explicitly mounted for it.

The credential shares that trust boundary: file permissions do not hide it from code already executing inside the VesselEngine Room.

LychD does not own the remote service's lifecycle. PortalCloud Model capabilities are dedicated=False and is_dynamic=False: the OrchestratorStage ManagerStage Manager cannot start, stop, load, or repair the provider.

Portal Roads owns the choice between direct server APIs, BYOK gateways, aggregators, human coding subscriptions, subscription bridges, and local inference. A provider or dashboard appearing there is a candidate classification, not a delivered connector or endorsement.

Egress Is a Deliberate Boundary

Three limits matter:

1. No automatic cloud replay. A failed local call is not replayed through a PortalCloud Model; no current FallbackModel path exists.
2. No probe egress by default. probe = false prevents the registry's optional /models request. The resulting route remains unverified UNKNOWN and cannot receive a grant; the separate PortalCloud Model quarantine also refuses it before transmission.
3. No hidden remote lifecycle. Binding writes no PortalCloud Model Quadlet and contacts no provider. It validates intent, proves named-secret presence, and mounts the reference into the VesselEngine RoomEngine Room.

With probing off, the registry reports the route as UNKNOWN; a declaration alone cannot establish WARM. Enabling it permits the current two-second unauthenticated GET <base_url>/models probe and validation of the returned data[*].id inventory. Malformed inventory or the absence of the declared model id produces ERROR. A credentialed provider can reject this probe even if its ordinary authenticated model call would work.

Read the result as a readiness observation only. It cannot bypass the current all-Portal dispatch quarantine.

State of Work owns the absent egress gate. The documented anonymization PatternWorkflowWorkflow does not authorize transmission.

Qualify disclosure accounting locally

The opt-in closed-diagnostic-recording@1 profile exercises durable decisions and consumed capacity using only the existing closed diagnostic fixture and a concrete local recorder. Its host pins a synthetic export consumer and expected binding independently of the Cut. The acceptance witness must retain consumed host/purpose/Cut limits across new identifiers and service reconstruction, refuse old seals and copied claims, and record exactly the verified bytes. The database retains restricted custody rather than source or candidate bodies.

Run its disposable-PostgreSQL receipts with:

make test-containers CONTAINER_TEST_TARGETS="tests/integration/test_privacy_disclosure_pg.py tests/integration/test_privacy_disclosure_migrations_pg.py"

The command requires the container-test environment described in Contributing. An explicit LYCHD_PRIVACY_TEST_DATABASE_URL selects a disposable database supplied by the operator instead; the profile never selects an application database automatically.

This profile opens no network road and changes no PortalCloud ModelCloud Model grant. Actual peer enrollment, full envelope verification, transport and native wait/adoption remain separate work. Its law is in Security and Persistence; State of Work owns delivery.

Declare and inspect one Portal

This rite assumes a summoned host. Run its commands from the stable Summoning checkout, under the same operator user and XDG environment. For a first installation, begin with Summoning.

1. Admit the provider schema

Resolve the CodexSettings FolderSettings Folder without assuming its home, then add animator to the existing [extensions].builtins list:

CODEX_DIR="${XDG_CONFIG_HOME:-$HOME/.config}/lychd"
vi "$CODEX_DIR/lychd.toml"

Inscribe the provider anchors and inactive samples:

uv run --extra postgres-binary lychd init

The built-in animator extension registers runes/animator/portals/openai/ and runes/animator/portals/google-gemini/. Both use an OpenAI-shaped HTTP interface, while the Connector selects the declared provider's model-profile resolver. Selecting an animator/* runtime also registers the shared PortalCloud ModelCloud Model base.

For another interface, an extension must supply its RuneService Config FileService Config File schema and Connector factory. The schema alone admits declarations, without constructing a runtime or capability. That construction needs one exact PortalDefinition for the concrete schema; there is no anonymous OpenAI-compatible fallback.

2. Seal one credential

Create exactly the name the RuneService Config FileService Config File will reference; never put the value in TOML:

SECRET_NAME=portal_openai_main
read -rsp "Value for $SECRET_NAME: " LYCHD_SECRET
printf '%s' "$LYCHD_SECRET" | podman secret create "$SECRET_NAME" -
podman secret exists "$SECRET_NAME"
unset LYCHD_SECRET SECRET_NAME

For deliberate rotation, use podman secret create --replace, then recreate the VesselEngine RoomEngine Room.

3. Declare one model

Create "$CODEX_DIR/runes/animator/portals/openai/main.toml":

name = "openai-main"
description = "Explicit remote chat capability."
api_key_secret_name = "portal_openai_main"
probe = false

[[models]]
id = "gpt-5.2"

[models.capabilities]
families = ["chat"]
modalities_in = ["text"]
supports_tools = true

[models.generation]
max_tokens = 4096

The openai leaf supplies provider identity and its default URL. Override base_url only for an OpenAI-compatible endpoint. A PortalCloud ModelCloud Model with no [[models]] blocks contributes no capability; LychD does not infer or download a provider catalogue. The endpoint is a root: an existing path prefix is kept when /models is appended, while embedded credentials, query or fragment state, port zero, and out-of-range ports fail validation. Model ids are unique; duplicates fail before registry construction.

PortalCloud Model models use the Pydantic AI profile selected by provider alias and model id, so settings known to be unsupported are omitted rather than forced onto the request. OpenRouter, LiteLLM, and Ollama retain their provider resolvers; Gemini's OpenAI-compatible leaf uses Google's model profile. Generic compatible endpoints and local SoulstonesLocal ModelsLocal Models use a conservative compatibility profile. OpenRouter model ids keep their provider/model prefix. The current Google, LiteLLM, and Ollama aliases reject the Responses surface; OpenAI, OpenRouter, and explicitly compatible generic endpoints may select it. This is not evidence of a native Gemini transport.

4. Bind, restart, and observe

The direct Systemd restart below is a separately chosen operator action under Reanimation’s limits and the separately authorized recovery plan. It bypasses OrchestratorStage ManagerStage Manager admission and lease drain. It is not a delivered CLI fallback: public stop still refuses an active Vessel.

uv run --extra postgres-binary lychd bind --dry-run
uv run --extra postgres-binary lychd bind
systemctl --user restart lychd-vessel.service
uv run --extra postgres-binary lychd status

After binding, distinguish the three observations. Bind verifies the RuneService Config FileService Config File, named secret, and atomic reconciliation of units. CLI status inspects the installation. Neither establishes a provider call or lists its model capabilities.

To inspect registration, open http://127.0.0.1:7134/orchestrator/status in the same-host browser. Under all_capabilities, find the row whose capability_key is openai-main:chat:gpt-5.2. This row establishes that the declared capability was synthesized and registered. Because the example sets probe = false, its phase remains unknown.

A later warm observation would establish readiness of that exact declared binding, without establishing egress eligibility or credentialed invocation. Current DispatcherTraffic ControllerTraffic Controller policy quarantines every PortalCloud ModelCloud Model grant.

The BridgeChatChat has no provider picker. Once the general Egress GatePrivacy FilterPrivacy Filter is delivered, a future attributable end-to-end proof may make this PortalCloud Model the only eligible chat plus tools candidate and send one benign public-safe fixture through a fresh payload-bound decision. Today, do not send that prompt: the current executable proof ends at declaration, bind, and readiness observation because DispatcherTraffic Controller refuses the grant.

Failure and Closure

If the row is absent, check extension activation, the provider anchor, at least one model block, and the VesselEngine RoomEngine Room restart. If a request fails, inspect the VesselEngine Room journal and provider account separately; do not reinterpret passive warmth as a provider response.

Close the sky by removing its routable model declarations, binding the new intent, and restarting the quiescent VesselEngine Room. The named secret may then be rotated or retired under the operator's own secret policy.

Credential custody in Reach

Reach needs a stronger credential boundary than the current Vessel-local Connector supplies. Its deployment profiles must keep the provider secret out of both Reach core and the Discord edge, even when they share a host. The Designed profiles place that one exact provider or peer credential in a separate Provider Gate/egress adapter service, which accepts only typed, egress-admitted attempts.

Until that service boundary and its deployment receipt are delivered, the current Connector cannot serve as a Reach provider path, including in the public VPS profile.

Portal Rune Reference

Each model requires provider-facing id; it may add capability hints and a per-model generation overlay. Operator description belongs to the PortalCloud ModelCloud Model, not each model block. Capability hints default to chat with text admission. Verification may downgrade a declaration, never invent one.