amosblomqvist
de0c286311
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.
38 lines
1.4 KiB
TypeScript
38 lines
1.4 KiB
TypeScript
/**
|
|
* Fuzzy search scoring (model-control wave, 2026-09-12) — pi's `/model`
|
|
* picker pattern: space-separated tokens, each token must match SOME field
|
|
* (case-insensitive substring), ranked so exact field matches beat
|
|
* prefixes beat buried substrings. Pure core; the picker sorts by score.
|
|
*/
|
|
|
|
/** Score one candidate, or null when any token matches no field.
|
|
* Higher is better; ties break naturally by list order (stable sort).
|
|
*
|
|
* Per-token points: exact field equality 100 · field startsWith 60 ·
|
|
* substring 30 minus a depth penalty (earlier finds win). Whole-query
|
|
* contiguity in one field adds +50 (query "glm flash" vs the id
|
|
* "z-ai/glm-5.3-flash" loses to a model whose id contains "glm flash"
|
|
* verbatim — as it should). */
|
|
export function fuzzyScore(query: string, ...fields: string[]): number | null {
|
|
const tokens = query.trim().toLowerCase().split(/\s+/).filter(Boolean);
|
|
if (tokens.length === 0) return 0;
|
|
const hay = fields.map((f) => f.toLowerCase());
|
|
|
|
let total = 0;
|
|
for (const token of tokens) {
|
|
let best = -1;
|
|
for (const f of hay) {
|
|
if (f === token) best = Math.max(best, 100);
|
|
else if (f.startsWith(token)) best = Math.max(best, 60);
|
|
else {
|
|
const at = f.indexOf(token);
|
|
if (at !== -1) best = Math.max(best, 30 - Math.min(at, 27));
|
|
}
|
|
}
|
|
if (best < 0) return null;
|
|
total += best;
|
|
}
|
|
const joined = tokens.join(" ");
|
|
if (hay.some((f) => f.includes(joined))) total += 50;
|
|
return total;
|
|
} |