The model-control wave (user-decided design, 2026-09-12): ONE controller
for the conversation agents (prober/teacher are functionally one agent);
background sub-agents stay config-pinned. pi-ai owns the registry — the
shipped 366-model OpenRouter catalog (cost, context, modality,
thinkingLevelMap), getSupportedThinkingLevels/clampThinkingLevel for the
per-model thinking truth, and streamSimple's automatic clamp. No second
registry to drift out of sync.
Seams:
- config.ts: ReasoningEffort retired for pi's ThinkingLevel
(off|minimal|low|medium|high|xhigh|max). GLM roles go honest at "low" —
pi's catalog says GLM-5.3-flash accepts exactly low|high|max, and the old
"minimal" was silently clamped to low by streamSimple since the swap;
nothing changes behaviorally. visualMaker → qwen/qwen3.8-flash (fixes
the dead qwen/qwen3.8-max slug — the catalog only ships -0902; also the
user's cost pick, 0.15/0.47 per-1M).
- src/agent/models.ts: piEngineFor(role, settings?) — provider+id resolved
from the catalog, thinking level from settings ?? config, CLAMPED to the
model's supported list (a settings change between models can never send
an invalid level). PiEngine gains `level` (observability/tests).
- ChatRecord.settings {model?: {provider, id}, thinkingLevel?} — written
by PUT /api/chats/[id]/settings (replace-whole, no updatedAt churn),
read by chat-handler at turn composition: agents are stateless per turn,
so the change is next-turn-effective by construction. The turns log
still records the ACTUAL billed model (the honest witness).
- GET /api/models: the configured-provider catalog as client-safe DTOs
(core/contracts/models.ts) + config defaults; a second provider joins
the picker by registering it in piModels() — nothing else changes.
- PUT settings validation gate (src/server/model-catalog.ts): unknown
provider/model or unsupported level → 400 carrying the supported list,
never a silent clamp.
- scripts/sync-pricing.ts: regenerated PRICES/CONTEXT_LIMITS from pi-ai's
shipped openrouter.json (offline; same source as the engine + picker).
All 366 models priced; glm's stale 0.15/0.5 → pi's 0.075/0.25, limit
1310720 → 1048576 — cost is inferred at read time, so history re-prices.
- UI (components/model-picker.tsx): stats-bar right side becomes model +
thinking buttons; menus open ABOVE; fuzzy search over "provider id
name" (core/fuzzy.ts — pi's /model pattern); model rows show name/id/
price/context; the thinking menu lists exactly the chosen model's
supported levels (GLM: low|high|max — no dead options, no "off").
Model switch drops an incompatible pinned level (falls back to config,
which clamps honestly) rather than carrying a 400.
Tests (350/350, +15): catalog projection + defaults, the settings gate,
pi thinking truth pinned against upgrades (glm low|high|max; minimal→low;
off→low — GLM cannot disable thinking), the engine factory's
override/fallback/clamp/throw matrix, fuzzy ranking, store round-trip,
and the re-priced folds (usage, stats bar, activity dock).
Live smoke (disposable driver, deleted): catalog route 366 + defaults;
glm+minimal → 400 + supported; turn 1 billed qwen/qwen3.8-flash under
the override; mid-session switch flipped turn 2 to glm; clear-overrides
restored the config pin. ALL CHECKS PASS on real OpenRouter.
126 lines
4.7 KiB
TypeScript
126 lines
4.7 KiB
TypeScript
"use client";
|
|
|
|
import { useState } from "react";
|
|
import { contextWindow, sessionCost, turnCost, type ChatSettings, type TurnUsage } from "@/src/core";
|
|
import { formatTokens, formatUsd, prettyModel } from "@/components/usage-format";
|
|
import { ModelControl } from "@/components/model-picker";
|
|
|
|
/**
|
|
* The below-composer stats bar (wave 4 observability): the session's
|
|
* money/context footprint as one quiet row beneath the composer —
|
|
* LEFT-aligned: context window + session cost; RIGHT-aligned: model +
|
|
* thinking level. Clicking the left side opens the per-turn detail popover.
|
|
*
|
|
* All folds come from core/prices.ts (sessionCost, contextWindow, turnCost)
|
|
* — no cost math lives here. Absent data renders "—", never zero (the
|
|
* doctrine): no turns yet → every figure is "—"; turns the price table
|
|
* can't price count as unpriced, shown in the popover, never folded into a
|
|
* fake $0. The RIGHT side is the model + thinking control (components/
|
|
* model-picker.tsx): one controller for the conversation agents, backed by
|
|
* pi-ai's catalog; the buttons show the EFFECTIVE model (the record's
|
|
* settings, else config's pin), while the left-side figures still fold the
|
|
* turn log's actual billed models.
|
|
*/
|
|
export function StatsBar({
|
|
turns,
|
|
chatId,
|
|
settings,
|
|
onSettingsSaved,
|
|
}: {
|
|
turns: TurnUsage[];
|
|
chatId: string;
|
|
settings?: ChatSettings;
|
|
onSettingsSaved: (settings: ChatSettings) => void;
|
|
}) {
|
|
const [open, setOpen] = useState(false);
|
|
const ctx = contextWindow({ turns });
|
|
const { cost, unpriced } = sessionCost({ turns });
|
|
// Honest cost: show dollars only when at least one turn priced;
|
|
// otherwise "—" (never a fake $0.0000).
|
|
const pricedCount = turns.length - unpriced;
|
|
const costLabel = pricedCount > 0 ? formatUsd(cost) : "—";
|
|
const lastModel = turns.at(-1)?.model;
|
|
|
|
return (
|
|
<div
|
|
data-testid="stats-bar"
|
|
className="relative flex items-center justify-between gap-3 px-3 pt-1 text-[10px] text-muted-foreground"
|
|
>
|
|
<button
|
|
type="button"
|
|
onClick={() => setOpen((o) => !o)}
|
|
aria-expanded={open}
|
|
title="Session stats — per-turn detail"
|
|
data-testid="stats-summary"
|
|
className="flex items-center gap-1.5 tabular-nums transition-colors hover:text-foreground"
|
|
>
|
|
<span data-testid="stats-context">
|
|
{ctx ? `${formatTokens(ctx.usedTokens)} / ${formatTokens(ctx.limit)}` : "—"}
|
|
</span>
|
|
<span aria-hidden>·</span>
|
|
<span data-testid="stats-cost">{costLabel}</span>
|
|
</button>
|
|
{/* The model + thinking control — one controller for the conversation
|
|
agents (prober/teacher); the record's `turns` above still folds
|
|
the ACTUAL models billed, regardless of what the picker says. */}
|
|
<ModelControl
|
|
chatId={chatId}
|
|
settings={settings}
|
|
onSaved={onSettingsSaved}
|
|
fallbackModelId={lastModel}
|
|
/>
|
|
|
|
{open && (
|
|
<div
|
|
data-testid="stats-detail"
|
|
className="absolute bottom-full left-0 z-40 mb-1.5 w-72 rounded-xl border bg-card p-3 text-xs shadow-xl"
|
|
>
|
|
<div className="mb-2 text-[11px] font-medium uppercase tracking-wide text-muted-foreground">
|
|
Session stats
|
|
</div>
|
|
<div className="flex flex-col gap-1 text-muted-foreground">
|
|
<div className="flex justify-between gap-2">
|
|
<span>Context (last call)</span>
|
|
<span className="tabular-nums text-card-foreground">
|
|
{ctx ? `${formatTokens(ctx.usedTokens)} / ${formatTokens(ctx.limit)}` : "—"}
|
|
</span>
|
|
</div>
|
|
<div className="flex justify-between gap-2">
|
|
<span>Total cost</span>
|
|
<span className="tabular-nums text-card-foreground">{costLabel}</span>
|
|
</div>
|
|
{unpriced > 0 && (
|
|
<div className="flex justify-between gap-2">
|
|
<span>Unpriced turns</span>
|
|
<span className="tabular-nums text-card-foreground">{unpriced}</span>
|
|
</div>
|
|
)}
|
|
</div>
|
|
{turns.length > 0 && (
|
|
<>
|
|
<div className="mb-1 mt-2.5 border-t pt-2 text-[11px] font-medium uppercase tracking-wide text-muted-foreground">
|
|
Turns
|
|
</div>
|
|
<ul className="flex max-h-56 flex-col gap-1 overflow-y-auto">
|
|
{turns.map((turn, i) => {
|
|
const c = turnCost(turn);
|
|
return (
|
|
<li key={`${turn.messageId}-${i}`} className="flex items-center justify-between gap-2">
|
|
<span className="truncate text-muted-foreground">
|
|
#{i + 1} · {prettyModel(turn.model)}
|
|
</span>
|
|
<span className="flex shrink-0 items-center gap-2 tabular-nums text-card-foreground">
|
|
<span className="text-muted-foreground">{turn.steps.length} steps</span>
|
|
<span>{c === null ? "—" : formatUsd(c)}</span>
|
|
</span>
|
|
</li>
|
|
);
|
|
})}
|
|
</ul>
|
|
</>
|
|
)}
|
|
</div>
|
|
)}
|
|
</div>
|
|
);
|
|
} |