mirror of
https://github.com/rowboatlabs/rowboat.git
synced 2026-07-15 21:11:08 +02:00
fd49334c33
Review feedback: drop the model-layer scheduler (per-call-site interactive/classifier/background priorities, local-provider hostname heuristic) in favor of app-level orchestration: - deferBackgroundTasks flag in models.json, surfaced as a settings toggle; auto-enabled once (UI logic) when the user connects Ollama - ChatActivity counter marked by both chat runtimes (sessions layer and legacy AgentRuntime.trigger) - startWhenPossible/runWhenPossible wrappers around the headless agent runner; all background invocations (knowledge pipeline, live notes, background tasks, scheduled + prebuilt agents) go through them and wait for chat-idle when the flag is set createLanguageModel keeps only the Ollama context-window middleware; the LM Studio capability probe now keys off the provider flavor instead of hostname sniffing. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
65 lines
3.2 KiB
TypeScript
65 lines
3.2 KiB
TypeScript
import { z } from "zod";
|
|
|
|
export const LlmProvider = z.object({
|
|
flavor: z.enum(["openai", "anthropic", "google", "openrouter", "aigateway", "ollama", "openai-compatible", "rowboat"]),
|
|
apiKey: z.string().optional(),
|
|
baseURL: z.string().optional(),
|
|
headers: z.record(z.string(), z.string()).optional(),
|
|
// Context window (in tokens) to request from local runtimes. Ollama defaults
|
|
// to a ~4k window that silently truncates Rowboat's prompts; when unset,
|
|
// local providers get a larger default (see core/models/local.ts).
|
|
contextLength: z.number().int().positive().optional(),
|
|
// Reasoning effort for local thinking models (Ollama `think` parameter).
|
|
// gpt-oss supports the levels directly; other thinking models map
|
|
// low → thinking off, high → thinking on. Defaults to "low" for Ollama —
|
|
// background agents and chat both want snappy responses on local hardware.
|
|
reasoningEffort: z.enum(["low", "medium", "high"]).optional(),
|
|
});
|
|
|
|
// A provider-qualified model reference. `provider` is a provider name as
|
|
// understood by resolveProviderConfig — a BYOK flavor ("ollama", "openai",
|
|
// …) or "rowboat" for the signed-in gateway.
|
|
export const ModelRef = z.object({
|
|
provider: z.string(),
|
|
model: z.string(),
|
|
});
|
|
|
|
// Category overrides accept either a bare model id (legacy: paired with the
|
|
// active default provider) or a provider-qualified ref (hybrid mode: e.g.
|
|
// gateway assistant + local Ollama background agents).
|
|
export const ModelOverride = z.union([z.string(), ModelRef]);
|
|
|
|
export const LlmModelConfig = z.object({
|
|
provider: LlmProvider,
|
|
model: z.string(),
|
|
models: z.array(z.string()).optional(),
|
|
// The user's explicit default assistant model. When set it wins over both
|
|
// the signed-in curated default and the legacy top-level provider/model
|
|
// pair — this is what lets signed-in users default to a BYOK model.
|
|
defaultSelection: ModelRef.optional(),
|
|
// When true, background agent runs (knowledge pipeline, live notes,
|
|
// background tasks) wait until no chat turn is running before starting.
|
|
// Surfaced as a settings checkbox; recommended for local models, where a
|
|
// background run competes with the chat for the same hardware.
|
|
deferBackgroundTasks: z.boolean().optional(),
|
|
providers: z.record(z.string(), z.object({
|
|
apiKey: z.string().optional(),
|
|
baseURL: z.string().optional(),
|
|
headers: z.record(z.string(), z.string()).optional(),
|
|
contextLength: z.number().int().positive().optional(),
|
|
reasoningEffort: z.enum(["low", "medium", "high"]).optional(),
|
|
model: z.string().optional(),
|
|
models: z.array(z.string()).optional(),
|
|
knowledgeGraphModel: z.string().optional(),
|
|
meetingNotesModel: z.string().optional(),
|
|
liveNoteAgentModel: z.string().optional(),
|
|
autoPermissionDecisionModel: z.string().optional(),
|
|
})).optional(),
|
|
// Per-category model overrides. Honored in both modes: when unset,
|
|
// signed-in users get the curated gateway defaults and BYOK users get the
|
|
// assistant model. Read by helpers in core/models/defaults.ts.
|
|
knowledgeGraphModel: ModelOverride.optional(),
|
|
meetingNotesModel: ModelOverride.optional(),
|
|
liveNoteAgentModel: ModelOverride.optional(),
|
|
autoPermissionDecisionModel: ModelOverride.optional(),
|
|
});
|