feat: add persistent model-aware reasoning effort settings

This commit is contained in:
2026-11-15 18:45:22 -08:00
parent 91c7c0310e
commit 92a16a39c0
22 changed files with 678 additions and 36 deletions
+41 -11
View File
@@ -16,6 +16,7 @@ import { runMultiplexStream, type StreamEvent } from "./llm/streaming.js";
import { getAvailableChatTools, normalizeEnabledChatTools } from "./llm/chat-tools.js";
import { getModelCatalogSnapshot } from "./llm/model-catalog.js";
import { buildQuickQuestionMultiplexRequest } from "./llm/quick-question.js";
import { normalizeReasoningEffort, REASONING_EFFORTS, type ReasoningEffort } from "./llm/reasoning-effort.js";
import { openaiClient } from "./llm/providers.js";
import { serializeProviderFields } from "./llm/provider-ids.js";
import { exaClient } from "./search/exa.js";
@@ -24,6 +25,7 @@ import { searchWorkspace } from "./workspace-search.js";
import { PROVIDERS, type ChatAttachment } from "./llm/types.js";
const ProviderSchema = z.enum(PROVIDERS);
const ReasoningEffortSchema = z.enum(REASONING_EFFORTS).nullable();
const MAX_ADDITIONAL_SYSTEM_PROMPT_CHARS = 12_000;
const MAX_FORK_MESSAGE_SNIPPET_CHARS = 48;
const EnabledToolsSchema = z.array(z.string().trim().min(1).max(80)).max(20).transform((value) => normalizeEnabledChatTools(value));
@@ -209,6 +211,7 @@ const CompletionStreamBody = z
userLocation: z.string().trim().min(1).max(200).optional(),
temperature: z.number().min(0).max(2).optional(),
maxTokens: z.number().int().positive().optional(),
reasoningEffort: ReasoningEffortSchema.optional(),
})
.superRefine((value, ctx) => {
if (value.persist === false && value.chatId) {
@@ -235,6 +238,7 @@ const QuickQuestionStreamBody = z.object({
userLocation: z.string().trim().min(1).max(200).optional(),
temperature: z.number().min(0).max(2).optional(),
maxTokens: z.number().int().positive().optional(),
reasoningEffort: ReasoningEffortSchema.optional(),
});
function mergeAttachmentsIntoMetadata(metadata: unknown, attachments?: ChatAttachment[]) {
@@ -269,16 +273,16 @@ function prependAdditionalSystemPrompt<T extends { messages: IncomingChatMessage
};
}
async function applyStoredChatSettings<T extends { chatId?: string; messages: IncomingChatMessage[]; additionalSystemPrompt?: string; enabledTools?: string[] }>(
async function applyStoredChatSettings<T extends { chatId?: string; provider: string; model: string; messages: IncomingChatMessage[]; additionalSystemPrompt?: string; enabledTools?: string[]; reasoningEffort?: ReasoningEffort | null }>(
body: T
) {
if (!body.chatId || (body.additionalSystemPrompt !== undefined && body.enabledTools !== undefined)) {
if (!body.chatId || (body.additionalSystemPrompt !== undefined && body.enabledTools !== undefined && body.reasoningEffort !== undefined)) {
return prependAdditionalSystemPrompt(body);
}
const chat = await prisma.chat.findUnique({
where: { id: body.chatId },
select: { additionalSystemPrompt: true, enabledTools: true },
select: { additionalSystemPrompt: true, enabledTools: true, reasoningEffort: true, lastUsedProvider: true, lastUsedModel: true },
});
if (!chat) return prependAdditionalSystemPrompt(body);
@@ -286,6 +290,10 @@ async function applyStoredChatSettings<T extends { chatId?: string; messages: In
...body,
additionalSystemPrompt: body.additionalSystemPrompt ?? chat.additionalSystemPrompt ?? undefined,
enabledTools: body.enabledTools ?? normalizeEnabledChatTools(chat.enabledTools),
// Omission inherits only for the saved model; null explicitly resets it.
reasoningEffort: normalizeReasoningEffort(body.provider, body.model, body.reasoningEffort !== undefined
? body.reasoningEffort
: chat.lastUsedProvider === body.provider && chat.lastUsedModel === body.model ? chat.reasoningEffort : null),
});
}
@@ -556,6 +564,7 @@ const chatSummarySelect = {
initiatedModel: true,
lastUsedProvider: true,
lastUsedModel: true,
reasoningEffort: true,
additionalSystemPrompt: true,
enabledTools: true,
projectItems: starredProjectItemsSelect,
@@ -1082,7 +1091,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
} : undefined,
orderBy: [{ updatedAt: "desc" }, { id: "asc" }],
take: limit + 1,
select: { id: true, title: true, parentChatId: true, createdAt: true, updatedAt: true, initiatedProvider: true, initiatedModel: true, lastUsedProvider: true, lastUsedModel: true },
select: { id: true, title: true, parentChatId: true, createdAt: true, updatedAt: true, initiatedProvider: true, initiatedModel: true, lastUsedProvider: true, lastUsedModel: true, reasoningEffort: true },
});
const hasMore = chats.length > limit;
const page = hasMore ? chats.slice(0, limit) : chats;
@@ -1103,6 +1112,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
title: z.string().optional(),
provider: ProviderSchema.optional(),
model: z.string().trim().min(1).optional(),
reasoningEffort: ReasoningEffortSchema.optional(),
additionalSystemPrompt: z.string().max(MAX_ADDITIONAL_SYSTEM_PROMPT_CHARS).optional(),
enabledTools: EnabledToolsSchema.optional(),
messages: z.array(CompletionMessageSchema).optional(),
@@ -1133,6 +1143,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
initiatedModel: body.model,
lastUsedProvider: body.provider,
lastUsedModel: body.model,
reasoningEffort: normalizeReasoningEffort(body.provider, body.model, body.reasoningEffort),
additionalSystemPrompt: normalizeAdditionalSystemPrompt(body.additionalSystemPrompt),
enabledTools: body.enabledTools as any,
messages: body.messages?.length
@@ -1170,6 +1181,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
initiatedModel: true,
lastUsedProvider: true,
lastUsedModel: true,
reasoningEffort: true,
additionalSystemPrompt: true,
enabledTools: true,
userId: true,
@@ -1199,6 +1211,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
initiatedModel: source.initiatedModel,
lastUsedProvider: source.lastUsedProvider,
lastUsedModel: source.lastUsedModel,
reasoningEffort: normalizeReasoningEffort(source.lastUsedProvider, source.lastUsedModel, source.reasoningEffort),
additionalSystemPrompt: source.additionalSystemPrompt,
enabledTools: (source.enabledTools ?? undefined) as any,
userId: source.userId,
@@ -1231,11 +1244,16 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
const Params = z.object({ chatId: z.string() });
const Body = z.object({
title: z.string().trim().min(1).optional(),
provider: ProviderSchema.optional(),
model: z.string().trim().min(1).optional(),
reasoningEffort: ReasoningEffortSchema.optional(),
additionalSystemPrompt: z.string().max(MAX_ADDITIONAL_SYSTEM_PROMPT_CHARS).nullable().optional(),
enabledTools: EnabledToolsSchema.optional(),
});
}).refine((value) => Boolean(value.provider) === Boolean(value.model), "provider and model must be supplied together");
const { chatId } = Params.parse(req.params);
const body = Body.parse(req.body ?? {});
const parsed = Body.safeParse(req.body ?? {});
if (!parsed.success) return app.httpErrors.badRequest(parsed.error.message);
const body = parsed.data;
const data: Record<string, unknown> = {};
if (body.title !== undefined) {
@@ -1244,13 +1262,24 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
}
if (body.additionalSystemPrompt !== undefined) data.additionalSystemPrompt = normalizeAdditionalSystemPrompt(body.additionalSystemPrompt);
if (body.enabledTools !== undefined) data.enabledTools = body.enabledTools;
const updated = await prisma.chat.updateMany({
where: { id: chatId },
data: data as any,
const updated = await prisma.$transaction(async (tx) => {
const current = await tx.chat.findUnique({ where: { id: chatId } });
if (!current) return null;
const provider = body.provider ?? current.lastUsedProvider;
const model = body.model ?? current.lastUsedModel;
if (body.provider !== undefined) {
data.lastUsedProvider = provider;
data.lastUsedModel = model;
}
if (body.provider !== undefined || body.reasoningEffort !== undefined) {
const sameModel = provider === current.lastUsedProvider && model === current.lastUsedModel;
data.reasoningEffort = normalizeReasoningEffort(provider, model, body.reasoningEffort !== undefined
? body.reasoningEffort : sameModel ? current.reasoningEffort : null);
}
return tx.chat.update({ where: { id: chatId }, data: data as any });
});
if (updated.count === 0) return app.httpErrors.notFound("chat not found");
if (!updated) return app.httpErrors.notFound("chat not found");
const chat = await getChatSummary(chatId);
if (!chat) return app.httpErrors.notFound("chat not found");
@@ -1738,6 +1767,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
userLocation: z.string().trim().min(1).max(200).optional(),
temperature: z.number().min(0).max(2).optional(),
maxTokens: z.number().int().positive().optional(),
reasoningEffort: ReasoningEffortSchema.optional(),
});
const parsed = Body.safeParse(req.body);