amosblomqvist
bfa906e2f8
Owner decision 2026-09-22: 'it doesn't make sense to have any default
model configured anywhere; the application is bring your own keys.'
config.ts: MODELS deleted; ModelRole becomes an explicit 9-role union;
DEFAULT_THINKING_ORDER (medium, low, high, minimal, xhigh, max) bakes
the unset-level default — first entry the model supports; explicitly
set levels keep pi's native nearest-clamp.
core/settings-resolution: the factory layer dissolves — the chain is
role override → slot → NOTHING. resolveSettings(record) takes no
factory. Empty chains resolve to null/undefined; a thinkingLevel-only
slot is inert (stored, never run). resolveConversationSpec: chat.model
override over the strong slot, null when both empty. resolveRoleSpec
spans all nine roles for the job/extraction engines.
Refusal envelope (core/settings.ts): modelsNotConfigured(missing) —
{error, code: 'models_not_configured', missing: [slot tiers]} +
ModelsNotConfiguredError with .envelope. Per-need gates, each honest:
- chat-handler: universal turn gate (new + continuing turns) returns
503 before beginTurn — no liveness, no write-ahead persist, no graph
trigger before the gate fires.
- runner.runJob: unresolvable engine lands the job as error with the
envelope wording; no phantom loop, no result steer.
- extraction: refuseIfStagesUnconfigured throws before any stage
(turn-service info-skips so coverage retries next turn; the import
route surfaces per-file code+missing); labeler-less runs skip
cluster naming with a console line and still merge.
Write side: slot entries must carry a model — level-only slot writes
are 400s (absent slot key = clear). piEngineForSpec resolves unset
thinking levels via DEFAULT_THINKING_ORDER; piEngineFor now throws
honestly; thinkingLevelFor/modelIdFor deleted; teacher-agent, pi-run,
visual-maker, pdf-reader all read engine.level.
model-catalog: defaults/slots/rolePins null when the chain is empty
(contracts nullable) — no phantom ids in payloads. Stores drop
MODEL_PINS entirely.
Tests: pin-leaners converted to explicit injection (per-chat model
pins on scripted chats — exactly what the setup flow writes; faux
engines for agent-construction tests). New coverage: the 503 gate
envelope, the runner refusal, the extraction refusal + labeler skip.
Gates: typecheck, lint, 815/815, build.
85 lines
3.5 KiB
TypeScript
85 lines
3.5 KiB
TypeScript
/**
|
|
* Model-catalog contracts (model-control wave, 2026-09-12) — the client-safe
|
|
* shapes of GET /api/models and PUT /api/chats/[id]/settings responses.
|
|
* Pure types; the server projection lives in src/server/model-catalog.ts
|
|
* (which OWNS these shapes — the contract is defined here only so client
|
|
* components never import from the server band).
|
|
*/
|
|
import type { ThinkingLevel } from "@earendil-works/pi-agent-core";
|
|
import type { BackgroundModelRole, ModelSlotName } from "../settings.ts";
|
|
|
|
/** One picker row: everything the UI shows about a model, projected from
|
|
* pi-ai's catalog. Costs are USD per 1M tokens (the same catalog, the same
|
|
* units core/prices.ts's generated table carries). */
|
|
export interface ModelCatalogEntry {
|
|
id: string;
|
|
name: string;
|
|
provider: string;
|
|
reasoning: boolean;
|
|
input: ("text" | "image")[];
|
|
/** The thinking levels this model actually accepts (pi's
|
|
* thinkingLevelMap — e.g. GLM-5.3-flash: low|high|max). The thinking
|
|
* picker lists exactly these; anything else is a lie. */
|
|
supportedLevels: ThinkingLevel[];
|
|
cost: { input: number; output: number; cacheRead: number; cacheWrite: number };
|
|
contextWindow: number;
|
|
maxTokens: number;
|
|
}
|
|
|
|
/** The conversation agents' resolved default (BYOK, owner 2026-09-22): the
|
|
* chat's model override over the STRONG slot — one controller, so one
|
|
* default. thinkingLevel is optional: unset resolves from the baked
|
|
* DEFAULT_THINKING_ORDER at engine build. */
|
|
export interface CatalogDefaults {
|
|
model: { provider: string; id: string };
|
|
thinkingLevel?: ThinkingLevel;
|
|
}
|
|
|
|
/** One background role's RESOLVED pin (BYOK, owner 2026-09-22): what that
|
|
* role actually runs today — role override → tier slot → NOTHING. NULL
|
|
* = the role's chain is empty (the per-need gates refuse its work); the
|
|
* settings UI shows "not configured" from it. */
|
|
export type RolePins = Record<
|
|
BackgroundModelRole,
|
|
{ model: { provider: string; id: string }; thinkingLevel?: ThinkingLevel } | null
|
|
>;
|
|
|
|
/** One slot tier's RESOLVED pin (BYOK, owner 2026-09-22): NULL = the tier
|
|
* holds no model. The settings UI captions each slot row with it and the
|
|
* picker pre-fills from it. */
|
|
export type SlotPins = Record<
|
|
ModelSlotName,
|
|
{ model: { provider: string; id: string }; thinkingLevel?: ThinkingLevel } | null
|
|
>;
|
|
|
|
/** GET /api/models response. */
|
|
export interface ModelCatalogResponse {
|
|
models: ModelCatalogEntry[];
|
|
/** The conversation agents' resolved default — NULL when the
|
|
* conversation chain is empty (no factory floor; the turn gate
|
|
* refuses with 503 models_not_configured). */
|
|
defaults: CatalogDefaults | null;
|
|
/** The six background roles' resolved pins (same resolution the agent
|
|
* factories use — src/server/stores.ts effectiveSettings); NULL per
|
|
* role = chain empty. */
|
|
rolePins: RolePins;
|
|
/** The three slot tiers' resolved pins: role override → slot at tier
|
|
* granularity; effectiveSettings().models verbatim, NULL per unset
|
|
* tier. */
|
|
slots: SlotPins;
|
|
/** Providers with a PRESENT key, and which env var gates each — the
|
|
* model slots wave's federation surface (2026-09-20): the picker lists
|
|
* models from these providers' pi-ai catalogs only. Keyless providers
|
|
* are simply absent (the Keys page is the discovery surface, same
|
|
* discipline as the search engines). */
|
|
providers: CatalogProvider[];
|
|
}
|
|
|
|
/** One row of the providers surface. */
|
|
export interface CatalogProvider {
|
|
id: string;
|
|
/** The env var whose presence federates this provider in. */
|
|
envVar: string;
|
|
/** Whether that var is currently present (env or auth file). */
|
|
keyPresent: boolean;
|
|
} |