amosblomqvist
1d45d77303
One shot per chat, fired at the first turn's onFinish: the session's topic (its only typed message) is embedded as an EmbeddingGemma retrieval query; the semantically closest graph propositions are selected under the session's token budget (pure budget, no similarity threshold — the decided doctrine) and delivered as a marker-only steer through the wake pipeline, queuing behind pending questions like every sub-agent result. - contracts: ChatSettings.graphContextTokens (default 1024, max 4096, step 128, 0 = off); GraphContextData + graphContextText; the graph-context JobKind + buildGraphContextSteer (id steer_ctx_<chatId>) - core/graph-context.ts: brute-force cosine top-K, greedy chars/4 fill under budget, most-recent UnderstandingLevel fold, count cap 64, parse-don't-cast at the marker seam - server: embedQuery (role-asymmetric query format, same warm singleton — vector-space parity by construction); the runner (startGraphContext- Injection one-shot gates; runGraphContextJob validates ledger parity); wake branches (chatIdOf/jobIdOf, finalizeJob done, recoverStaleJobs re-deliver or contextRespawn); abortJob kills context jobs SILENTLY (nothing was promised in the lesson); turn-service trigger seam - adapter: data-graph-context flattens to the canonical block (malformed parts have no model face) - UI: the budget slider (home dock + /chat/new draft, the session-data strip); the quiet SystemLine "~537 · 10 propositions"; dock kind "Knowledge context"; model-picker PUT now spreads settings (a model pick can no longer clear the sibling override) Live-smoked end to end on the real embedder + real GLM: seeded ledger (10 propositions), session on "modal logic: possible worlds and the necessity box" — job in the dock, queued behind the prober's question, delivered on the answer, SystemLine in the transcript, wake turn reads the block and continues the probe. Gates: tsc, lint, 459/459, build.
70 lines
2.9 KiB
TypeScript
70 lines
2.9 KiB
TypeScript
import { getChat, validateChatSettings, stores } from "@/src/server";
|
|
import type { ThinkingLevel } from "@earendil-works/pi-agent-core";
|
|
import { GRAPH_CONTEXT_TOKENS_MAX, type ChatSettings } from "@/src/core";
|
|
|
|
/**
|
|
* The per-chat model control (model-control wave): replace-whole settings —
|
|
* the picker sends the complete desired object ({} clears all overrides and
|
|
* returns the chat to config.ts's pin). Validation is the catalog gate
|
|
* (src/server/model-catalog.ts): unknown provider/model or an unsupported
|
|
* thinking level is a 400 carrying the supported list, never a silent clamp
|
|
* — the user must see what the model actually accepts. Effective next turn
|
|
* by construction (agents are stateless per turn).
|
|
*/
|
|
export async function PUT(req: Request, { params }: { params: Promise<{ id: string }> }) {
|
|
const { id } = await params;
|
|
if (!getChat(id)) return Response.json({ error: "Not found" }, { status: 404 });
|
|
|
|
const body = (await req.json().catch(() => null)) as
|
|
| { model?: { provider?: unknown; id?: unknown }; thinkingLevel?: unknown; graphContextTokens?: unknown }
|
|
| null;
|
|
if (!body || typeof body !== "object") {
|
|
return Response.json({ error: "Invalid JSON body" }, { status: 400 });
|
|
}
|
|
const settings: ChatSettings = {};
|
|
if (body.model !== undefined) {
|
|
if (
|
|
typeof body.model !== "object" ||
|
|
body.model === null ||
|
|
typeof body.model.provider !== "string" ||
|
|
typeof body.model.id !== "string"
|
|
) {
|
|
return Response.json({ error: "model must be {provider, id}" }, { status: 400 });
|
|
}
|
|
settings.model = { provider: body.model.provider, id: body.model.id };
|
|
}
|
|
if (body.thinkingLevel !== undefined) {
|
|
if (typeof body.thinkingLevel !== "string") {
|
|
return Response.json({ error: "thinkingLevel must be a string" }, { status: 400 });
|
|
}
|
|
settings.thinkingLevel = body.thinkingLevel as ThinkingLevel;
|
|
}
|
|
// Graph context injection budget (vision-context-injection.md): integer
|
|
// tokens, 0 (off) to GRAPH_CONTEXT_TOKENS_MAX, no silent clamping — the
|
|
// slider is the only writer, and it only ever sends multiples of the step.
|
|
if (body.graphContextTokens !== undefined) {
|
|
if (
|
|
typeof body.graphContextTokens !== "number" ||
|
|
!Number.isInteger(body.graphContextTokens) ||
|
|
body.graphContextTokens < 0 ||
|
|
body.graphContextTokens > GRAPH_CONTEXT_TOKENS_MAX
|
|
) {
|
|
return Response.json(
|
|
{ error: `graphContextTokens must be an integer between 0 and ${GRAPH_CONTEXT_TOKENS_MAX}` },
|
|
{ status: 400 },
|
|
);
|
|
}
|
|
settings.graphContextTokens = body.graphContextTokens;
|
|
}
|
|
|
|
const verdict = validateChatSettings(settings);
|
|
if (!verdict.ok) {
|
|
return Response.json({ error: verdict.error, supported: verdict.supported }, { status: 400 });
|
|
}
|
|
|
|
// Replace-whole persists the validated object verbatim — no merges, so a
|
|
// stale client can never resurrect a cleared override.
|
|
stores.chatStore.saveSettings(id, settings);
|
|
return Response.json({ settings });
|
|
}
|