feat(models): strong/cheap/vision model slots + multi-provider engine federation

Model slots wave (2026-09-20), chunk B:

- settings: new `models` section {strong, cheap, vision} slots (each
  field independent, same shape as a role override); ROLE_SLOT maps all
  nine roles to tiers (strong=prober+teacher, cheap=researcher/
  demoBuilder/extractor/auditor/labeler, vision=visualMaker+pdfReader);
  resolution chain per role: override → slot → factory pin.
- config: ModelSpec gains provider (all pins openrouter, the BYOK
  default); MODEL_PINS in stores.ts now spans all nine roles (the strong
  slot's factory rep IS the prober pin).
- engine: piModels() registers EVERY builtin provider catalog;
  piEngineForSpec(resolved spec) is the new engine factory (pi-ai
  resolves per-provider keys from env itself); piEngineFor stays as the
  config-pin fallback. chat-handler resolves the conversation chain
  (chat override → strong slot → pin) and injects engineFor into the job
  runner, closing the old gap where per-role overrides never reached
  job engines.
- /api/models: models federate ONLY keyed providers (providers surface
  with keyPresent, env-wins, fresh per call); slots (resolved tier pins)
  join rolePins; catalogDefaultsFor inherits the strong slot; the models
  settings section gets the same catalog gate as chat.
- pricing: PRICES/CONTEXT_LIMITS uniformly keyed provider:id
  (regenerated from ALL pi-ai catalogs, 1354 keys); usage stamps
  (TurnUsage, JobUsage, extraction stages) switch to provider:id —
  owner decision: no legacy compat, old stamps render unpriced.
This commit is contained in:
amosblomqvist
2026-09-22 00:14:56 +03:00
parent f1373d5de5
commit f9e3a4c43d
26 changed files with 3529 additions and 912 deletions
+4 -2
View File
@@ -86,7 +86,8 @@ export const GRAPH_CONTEXT_TOKENS_STOPS = [0, 64, 256, 1024, 4096, 16384] as con
* billed (CallUsage per agent step). Steps, not a sum: cost and context
* folds happen at read time (core/prices.ts). */
export interface ExtractionStageUsage {
/** The OpenRouter model id that ran this stage. */
/** The model that ran this stage, provider-qualified ("provider:id" —
* model slots wave, 2026-09-20; matches PRICES' uniform keys). */
model: string;
steps: CallUsage[];
}
@@ -142,7 +143,8 @@ export interface TurnUsage {
* entry to the transcript (the block this turn "belongs" to). */
messageId: string;
at: string;
/** The OpenRouter model id that ran the turn. */
/** The model that ran the turn, provider-qualified ("provider:id" —
* model slots wave, 2026-09-20; matches PRICES' uniform keys). */
model: string;
/** One entry per agent step (model call) in this turn. */
steps: CallUsage[];