refactor: remove retired agent provider integration
This commit is contained in:
+5
-4
@@ -1,7 +1,7 @@
|
||||
# Sybil Server
|
||||
|
||||
Backend API for:
|
||||
- LLM multiplexer (OpenAI Responses / Anthropic / xAI Chat Completions-compatible Grok / Gemini / Hermes Agent)
|
||||
- LLM multiplexer (OpenAI Responses / Anthropic / xAI Chat Completions-compatible Grok / Gemini)
|
||||
- Personal chat database (chats/messages + LLM call log)
|
||||
|
||||
## Stack
|
||||
@@ -18,6 +18,10 @@ npm run dev
|
||||
|
||||
Migrations are applied automatically on server startup (`prisma migrate deploy`).
|
||||
|
||||
Historical provider IDs are stored as strings so retiring an integration does not make saved chats or call logs unreadable. The API validates new requests against the supported provider list and returns `null` for unsupported saved provider selections. These columns remain SQLite `TEXT`; no data rewrite is required.
|
||||
|
||||
Inline Sybil Agent completions identify their response provider as `sybil-agent`. Release native clients that accept this response identity before deploying the server change; older clients that decode completion metadata with the selectable-provider enum cannot decode it. See the [streaming contract](../docs/api/streaming-chat.md).
|
||||
|
||||
Open docs: `http://localhost:8787/docs`
|
||||
|
||||
API contract docs for clients:
|
||||
@@ -44,9 +48,6 @@ If `ADMIN_TOKEN` is not set, the server runs in open mode (dev).
|
||||
- `ANTHROPIC_API_KEY`
|
||||
- `XAI_API_KEY`
|
||||
- `GEMINI_API_KEY`
|
||||
- `HERMES_AGENT_API_BASE_URL` (`http://127.0.0.1:8642/v1` by default; include the `/v1` suffix)
|
||||
- `HERMES_AGENT_API_KEY` (enables the Hermes Agent provider; set to Hermes `API_SERVER_KEY`, or any non-empty value if that local server does not require auth)
|
||||
- `HERMES_AGENT_MODEL` (optional fallback/override model id; defaults client-side to `hermes-agent`)
|
||||
- `EXA_API_KEY`
|
||||
- `BRAVE_SEARCH_API_KEY` (required when `CHAT_WEB_SEARCH_ENGINE=brave`)
|
||||
- `CHAT_WEB_SEARCH_ENGINE` (`exa` by default; `brave` and `searxng` are also supported for chat tool calls only)
|
||||
|
||||
@@ -9,14 +9,6 @@ datasource db {
|
||||
url = env("DATABASE_URL")
|
||||
}
|
||||
|
||||
enum Provider {
|
||||
openai
|
||||
anthropic
|
||||
xai
|
||||
gemini
|
||||
hermes_agent @map("hermes-agent")
|
||||
}
|
||||
|
||||
enum MessageRole {
|
||||
system
|
||||
user
|
||||
@@ -54,9 +46,11 @@ model Chat {
|
||||
title String?
|
||||
titleGenerationPending Boolean @default(false)
|
||||
|
||||
initiatedProvider Provider?
|
||||
// Historical provider IDs remain readable after an integration is retired.
|
||||
// Accepted request IDs are validated by the API, not a storage enum.
|
||||
initiatedProvider String?
|
||||
initiatedModel String?
|
||||
lastUsedProvider Provider?
|
||||
lastUsedProvider String?
|
||||
lastUsedModel String?
|
||||
|
||||
additionalSystemPrompt String?
|
||||
@@ -103,7 +97,7 @@ model LlmCall {
|
||||
chat Chat @relation(fields: [chatId], references: [id], onDelete: Cascade)
|
||||
chatId String
|
||||
|
||||
provider Provider
|
||||
provider String
|
||||
model String
|
||||
|
||||
// request/response snapshots for debugging + replay
|
||||
|
||||
@@ -9,6 +9,8 @@ const clientDir = join(rootDir, "node_modules", ".prisma", "client");
|
||||
const clientIndex = join(clientDir, "index.js");
|
||||
const prismaJs = join(rootDir, "node_modules", "prisma", "build", "index.js");
|
||||
const genericEngine = join(clientDir, "libquery_engine.node");
|
||||
const schemaFile = join(rootDir, "prisma", "schema.prisma");
|
||||
const generatedSchemaFile = join(clientDir, "schema.prisma");
|
||||
|
||||
function parseExpectedEngineFiles() {
|
||||
if (!existsSync(clientIndex)) return [];
|
||||
@@ -39,7 +41,8 @@ function runPrismaGenerate() {
|
||||
let expectedFiles = parseExpectedEngineFiles();
|
||||
let missingFiles = missingEngineFiles(expectedFiles);
|
||||
|
||||
if (!expectedFiles.length || missingFiles.length) {
|
||||
const schemaChanged = !existsSync(generatedSchemaFile) || readFileSync(schemaFile, "utf8") !== readFileSync(generatedSchemaFile, "utf8");
|
||||
if (schemaChanged || !expectedFiles.length || missingFiles.length) {
|
||||
runPrismaGenerate();
|
||||
expectedFiles = parseExpectedEngineFiles();
|
||||
missingFiles = missingEngineFiles(expectedFiles);
|
||||
|
||||
@@ -11,13 +11,6 @@ const OptionalUrlSchema = z.preprocess(
|
||||
z.string().trim().url().optional()
|
||||
);
|
||||
|
||||
const DEFAULT_HERMES_AGENT_API_BASE_URL = "http://127.0.0.1:8642/v1";
|
||||
|
||||
const HermesAgentApiBaseUrlSchema = z.preprocess(
|
||||
(value) => (typeof value === "string" && value.trim() === "" ? undefined : value),
|
||||
z.string().trim().url().default(DEFAULT_HERMES_AGENT_API_BASE_URL)
|
||||
);
|
||||
|
||||
const ChatWebSearchEngineSchema = z.preprocess(
|
||||
(value) => {
|
||||
if (typeof value !== "string") return value;
|
||||
@@ -67,9 +60,6 @@ const EnvSchema = z.object({
|
||||
ANTHROPIC_API_KEY: z.string().optional(),
|
||||
XAI_API_KEY: z.string().optional(),
|
||||
GEMINI_API_KEY: z.string().optional(),
|
||||
HERMES_AGENT_API_BASE_URL: HermesAgentApiBaseUrlSchema,
|
||||
HERMES_AGENT_API_KEY: OptionalTrimmedStringSchema,
|
||||
HERMES_AGENT_MODEL: OptionalTrimmedStringSchema,
|
||||
SYBIL_AGENT_BASE_URL: z.string().url().default("http://sybil-agent:8788"),
|
||||
SYBIL_AGENT_API_KEY: OptionalTrimmedStringSchema,
|
||||
// Off until a deliberate server opt-in plus per-installation user consent.
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
import type { FastifyBaseLogger } from "fastify";
|
||||
import {
|
||||
fetchProviderCatalogModels,
|
||||
getProviderCatalogFallbackModels,
|
||||
listModelCatalogProviders,
|
||||
} from "./provider-adapters.js";
|
||||
import type { Provider } from "./types.js";
|
||||
@@ -49,9 +48,8 @@ async function refreshProviderModels(provider: Provider, logger?: FastifyBaseLog
|
||||
} catch (err: any) {
|
||||
const message = err?.message ?? String(err);
|
||||
const previous = modelCatalog[provider];
|
||||
const fallbackModels = getProviderCatalogFallbackModels(provider);
|
||||
modelCatalog[provider] = {
|
||||
models: previous?.models.length ? previous.models : fallbackModels,
|
||||
models: previous?.models ?? [],
|
||||
loadedAt: previous?.loadedAt ?? null,
|
||||
error: message,
|
||||
};
|
||||
|
||||
@@ -2,12 +2,7 @@ import { performance } from "node:perf_hooks";
|
||||
import { prisma } from "../db.js";
|
||||
import { buildToolLogMessageData } from "./chat-tools.js";
|
||||
import { getProviderChatAdapter } from "./provider-adapters.js";
|
||||
import { toPrismaProvider } from "./provider-ids.js";
|
||||
import type { MultiplexRequest, MultiplexResponse, Provider } from "./types.js";
|
||||
|
||||
function asProviderEnum(p: Provider) {
|
||||
return toPrismaProvider(p);
|
||||
}
|
||||
import type { MultiplexRequest, MultiplexResponse } from "./types.js";
|
||||
|
||||
export async function runMultiplex(req: MultiplexRequest): Promise<MultiplexResponse> {
|
||||
const t0 = performance.now();
|
||||
@@ -17,7 +12,7 @@ export async function runMultiplex(req: MultiplexRequest): Promise<MultiplexResp
|
||||
const call = await prisma.llmCall.create({
|
||||
data: {
|
||||
chatId,
|
||||
provider: asProviderEnum(req.provider) as any,
|
||||
provider: req.provider,
|
||||
model: req.model,
|
||||
request: req as any,
|
||||
},
|
||||
@@ -28,14 +23,14 @@ export async function runMultiplex(req: MultiplexRequest): Promise<MultiplexResp
|
||||
prisma.chat.update({
|
||||
where: { id: chatId },
|
||||
data: {
|
||||
lastUsedProvider: asProviderEnum(req.provider) as any,
|
||||
lastUsedProvider: req.provider,
|
||||
lastUsedModel: req.model,
|
||||
},
|
||||
}),
|
||||
prisma.chat.updateMany({
|
||||
where: { id: chatId, initiatedProvider: null },
|
||||
data: {
|
||||
initiatedProvider: asProviderEnum(req.provider) as any,
|
||||
initiatedProvider: req.provider,
|
||||
initiatedModel: req.model,
|
||||
},
|
||||
}),
|
||||
|
||||
@@ -8,8 +8,7 @@ import { completeWithChatCompletionsApi, streamWithChatCompletionsApi } from "./
|
||||
import { completeWithGeminiApi, streamWithGeminiApi } from "./protocols/gemini-api.js";
|
||||
import { completeWithMessagesApi, streamWithMessagesApi } from "./protocols/messages-api.js";
|
||||
import { completeWithResponsesApi, streamWithResponsesApi } from "./protocols/responses-api.js";
|
||||
import { env } from "../env.js";
|
||||
import { anthropicClient, geminiClient, hermesAgentClient, isHermesAgentConfigured, openaiClient, xaiClient } from "./providers.js";
|
||||
import { anthropicClient, geminiClient, openaiClient, xaiClient } from "./providers.js";
|
||||
import type { ChatMessage, Provider } from "./types.js";
|
||||
|
||||
type ProviderAdapterParams = {
|
||||
@@ -37,9 +36,7 @@ type ChatProtocol = {
|
||||
};
|
||||
|
||||
type ModelCatalogSpec = {
|
||||
enabled?: () => boolean;
|
||||
fetchModels(client: any): Promise<string[]>;
|
||||
fallbackModels?: () => string[];
|
||||
sortModels?: (models: string[]) => string[];
|
||||
};
|
||||
|
||||
@@ -48,7 +45,7 @@ type ProviderBackendSpec = {
|
||||
plainProtocol: ChatProtocol;
|
||||
toolProtocol?: ChatProtocol;
|
||||
managedTools?: boolean;
|
||||
modelCatalog?: ModelCatalogSpec;
|
||||
modelCatalog: ModelCatalogSpec;
|
||||
};
|
||||
|
||||
const chatCompletionsProtocol: ChatProtocol = {
|
||||
@@ -226,23 +223,6 @@ const backendSpecs: Record<Provider, ProviderBackendSpec> = {
|
||||
sortModels: preferGeminiModels,
|
||||
},
|
||||
},
|
||||
"hermes-agent": {
|
||||
createClient: hermesAgentClient,
|
||||
plainProtocol: chatCompletionsProtocol,
|
||||
managedTools: false,
|
||||
modelCatalog: {
|
||||
enabled: isHermesAgentConfigured,
|
||||
async fetchModels(client) {
|
||||
const page = await client.models.list();
|
||||
const models = modelIdsFromListResponse(page);
|
||||
if (env.HERMES_AGENT_MODEL) models.push(env.HERMES_AGENT_MODEL);
|
||||
return models;
|
||||
},
|
||||
fallbackModels() {
|
||||
return env.HERMES_AGENT_MODEL ? [env.HERMES_AGENT_MODEL] : [];
|
||||
},
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
const providerChatAdapters: Record<Provider, ProviderChatAdapter> = Object.fromEntries(
|
||||
@@ -264,21 +244,11 @@ export function describeProviderChatBackend(provider: Provider, enabledTools?: s
|
||||
}
|
||||
|
||||
export function listModelCatalogProviders(): Provider[] {
|
||||
return (Object.entries(backendSpecs) as [Provider, ProviderBackendSpec][])
|
||||
.filter(([, spec]) => {
|
||||
const catalog = spec.modelCatalog;
|
||||
return catalog !== undefined && catalog.enabled?.() !== false;
|
||||
})
|
||||
.map(([provider]) => provider);
|
||||
return Object.keys(backendSpecs) as Provider[];
|
||||
}
|
||||
|
||||
export async function fetchProviderCatalogModels(provider: Provider) {
|
||||
const spec = backendSpecs[provider].modelCatalog;
|
||||
if (!spec) return [];
|
||||
const models = uniqSorted(await spec.fetchModels(backendSpecs[provider].createClient()));
|
||||
return spec.sortModels ? spec.sortModels(models) : models;
|
||||
}
|
||||
|
||||
export function getProviderCatalogFallbackModels(provider: Provider) {
|
||||
return uniqSorted(backendSpecs[provider].modelCatalog?.fallbackModels?.() ?? []);
|
||||
}
|
||||
|
||||
@@ -1,43 +1,21 @@
|
||||
import type { Provider } from "./types.js";
|
||||
import { PROVIDERS, type Provider } from "./types.js";
|
||||
|
||||
type PrismaProvider = Exclude<Provider, "hermes-agent"> | "hermes_agent";
|
||||
|
||||
const apiToPrismaProvider = {
|
||||
openai: "openai",
|
||||
anthropic: "anthropic",
|
||||
xai: "xai",
|
||||
gemini: "gemini",
|
||||
"hermes-agent": "hermes_agent",
|
||||
} as const satisfies Record<Provider, PrismaProvider>;
|
||||
|
||||
const prismaToApiProvider = {
|
||||
openai: "openai",
|
||||
anthropic: "anthropic",
|
||||
xai: "xai",
|
||||
gemini: "gemini",
|
||||
hermes_agent: "hermes-agent",
|
||||
"hermes-agent": "hermes-agent",
|
||||
} as const satisfies Record<PrismaProvider | "hermes-agent", Provider>;
|
||||
|
||||
export function toPrismaProvider(provider: Provider): PrismaProvider {
|
||||
return apiToPrismaProvider[provider];
|
||||
}
|
||||
|
||||
export function fromPrismaProvider(provider: unknown): Provider | null {
|
||||
if (provider === null || provider === undefined) return null;
|
||||
return prismaToApiProvider[provider as keyof typeof prismaToApiProvider] ?? null;
|
||||
export function parseProvider(provider: unknown): Provider | null {
|
||||
return typeof provider === "string" && PROVIDERS.includes(provider as Provider) ? provider as Provider : null;
|
||||
}
|
||||
|
||||
export function serializeProviderFields<T extends Record<string, any>>(value: T): T {
|
||||
const next: Record<string, any> = { ...value };
|
||||
if ("initiatedProvider" in next) {
|
||||
next.initiatedProvider = fromPrismaProvider(next.initiatedProvider);
|
||||
next.initiatedProvider = parseProvider(next.initiatedProvider);
|
||||
if (!next.initiatedProvider && "initiatedModel" in next) next.initiatedModel = null;
|
||||
}
|
||||
if ("lastUsedProvider" in next) {
|
||||
next.lastUsedProvider = fromPrismaProvider(next.lastUsedProvider);
|
||||
next.lastUsedProvider = parseProvider(next.lastUsedProvider);
|
||||
if (!next.lastUsedProvider && "lastUsedModel" in next) next.lastUsedModel = null;
|
||||
}
|
||||
if ("provider" in next) {
|
||||
next.provider = fromPrismaProvider(next.provider);
|
||||
next.provider = parseProvider(next.provider);
|
||||
}
|
||||
if (Array.isArray(next.calls)) {
|
||||
next.calls = next.calls.map((call: Record<string, any>) => serializeProviderFields(call));
|
||||
|
||||
@@ -21,18 +21,6 @@ export function geminiClient() {
|
||||
};
|
||||
}
|
||||
|
||||
export function isHermesAgentConfigured() {
|
||||
return Boolean(env.HERMES_AGENT_API_KEY);
|
||||
}
|
||||
|
||||
export function hermesAgentClient() {
|
||||
if (!env.HERMES_AGENT_API_KEY) throw new Error("HERMES_AGENT_API_KEY not set");
|
||||
return new OpenAI({
|
||||
apiKey: env.HERMES_AGENT_API_KEY,
|
||||
baseURL: env.HERMES_AGENT_API_BASE_URL,
|
||||
});
|
||||
}
|
||||
|
||||
export function anthropicClient() {
|
||||
if (!env.ANTHROPIC_API_KEY) throw new Error("ANTHROPIC_API_KEY not set");
|
||||
return new Anthropic({ apiKey: env.ANTHROPIC_API_KEY });
|
||||
|
||||
@@ -5,7 +5,6 @@ import {
|
||||
type ToolExecutionEvent,
|
||||
} from "./chat-tools.js";
|
||||
import { getProviderChatAdapter } from "./provider-adapters.js";
|
||||
import { toPrismaProvider } from "./provider-ids.js";
|
||||
import type { MultiplexRequest, Provider } from "./types.js";
|
||||
|
||||
type StreamUsage = {
|
||||
@@ -36,7 +35,7 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator
|
||||
? await prisma.llmCall.create({
|
||||
data: {
|
||||
chatId,
|
||||
provider: toPrismaProvider(req.provider) as any,
|
||||
provider: req.provider,
|
||||
model: req.model,
|
||||
request: req as any,
|
||||
},
|
||||
@@ -49,14 +48,14 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator
|
||||
prisma.chat.update({
|
||||
where: { id: chatId },
|
||||
data: {
|
||||
lastUsedProvider: toPrismaProvider(req.provider) as any,
|
||||
lastUsedProvider: req.provider,
|
||||
lastUsedModel: req.model,
|
||||
},
|
||||
}),
|
||||
prisma.chat.updateMany({
|
||||
where: { id: chatId, initiatedProvider: null },
|
||||
data: {
|
||||
initiatedProvider: toPrismaProvider(req.provider) as any,
|
||||
initiatedProvider: req.provider,
|
||||
initiatedModel: req.model,
|
||||
},
|
||||
}),
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
export const PROVIDERS = ["openai", "anthropic", "xai", "gemini", "hermes-agent"] as const;
|
||||
export const PROVIDERS = ["openai", "anthropic", "xai", "gemini"] as const;
|
||||
|
||||
export type Provider = (typeof PROVIDERS)[number];
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { fromPrismaProvider } from "./llm/provider-ids.js";
|
||||
import { parseProvider } from "./llm/provider-ids.js";
|
||||
|
||||
function record(value: unknown): Record<string, unknown> {
|
||||
return value && typeof value === "object" && !Array.isArray(value) ? value as Record<string, unknown> : {};
|
||||
@@ -18,7 +18,7 @@ export function withMessageGenerations<T extends { role: string; metadata: unkno
|
||||
for (const call of calls) {
|
||||
const requestId = record(call.request).clientRequestId;
|
||||
if (typeof requestId !== "string" || !requestId || call.error !== null || call.latencyMs === null) continue;
|
||||
const provider = fromPrismaProvider(call.provider);
|
||||
const provider = parseProvider(call.provider);
|
||||
if (!provider || !call.model.trim()) continue;
|
||||
byRequest.set(requestId, byRequest.has(requestId) ? null : { provider, model: call.model });
|
||||
}
|
||||
|
||||
@@ -17,13 +17,13 @@ import { getAvailableChatTools, normalizeEnabledChatTools } from "./llm/chat-too
|
||||
import { getModelCatalogSnapshot } from "./llm/model-catalog.js";
|
||||
import { buildQuickQuestionMultiplexRequest } from "./llm/quick-question.js";
|
||||
import { openaiClient } from "./llm/providers.js";
|
||||
import { serializeProviderFields, toPrismaProvider } from "./llm/provider-ids.js";
|
||||
import { serializeProviderFields } from "./llm/provider-ids.js";
|
||||
import { exaClient } from "./search/exa.js";
|
||||
import { isFreshSearchCacheHit, normalizeSearchQuery } from "./search-cache.js";
|
||||
import { searchWorkspace } from "./workspace-search.js";
|
||||
import type { ChatAttachment } from "./llm/types.js";
|
||||
import { PROVIDERS, type ChatAttachment } from "./llm/types.js";
|
||||
|
||||
const ProviderSchema = z.enum(["openai", "anthropic", "xai", "gemini", "hermes-agent"]);
|
||||
const ProviderSchema = z.enum(PROVIDERS);
|
||||
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));
|
||||
@@ -335,7 +335,7 @@ function executeActiveAgentAsideStream(chatId: string, body: z.infer<typeof Comp
|
||||
type: "meta",
|
||||
chatId,
|
||||
callId: null,
|
||||
provider: "hermes-agent",
|
||||
provider: "sybil-agent",
|
||||
model: "sybil-agent",
|
||||
agentAside: true,
|
||||
});
|
||||
@@ -815,7 +815,7 @@ function completeChatSubmissionStream(
|
||||
type: "meta",
|
||||
chatId,
|
||||
callId: null,
|
||||
provider: agentAside ? "hermes-agent" : body.provider,
|
||||
provider: agentAside ? "sybil-agent" : body.provider,
|
||||
model: agentAside ? "sybil-agent" : body.model,
|
||||
...(agentAside ? { agentAside: true } : {}),
|
||||
});
|
||||
@@ -1129,9 +1129,9 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
|
||||
const chat = await prisma.chat.create({
|
||||
data: {
|
||||
title: body.title,
|
||||
initiatedProvider: body.provider ? (toPrismaProvider(body.provider) as any) : undefined,
|
||||
initiatedProvider: body.provider,
|
||||
initiatedModel: body.model,
|
||||
lastUsedProvider: body.provider ? (toPrismaProvider(body.provider) as any) : undefined,
|
||||
lastUsedProvider: body.provider,
|
||||
lastUsedModel: body.model,
|
||||
additionalSystemPrompt: normalizeAdditionalSystemPrompt(body.additionalSystemPrompt),
|
||||
enabledTools: body.enabledTools as any,
|
||||
@@ -1761,7 +1761,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
|
||||
const completedAgentAside = Boolean((completed.metadata as Record<string, unknown> | null)?.agentAside === true);
|
||||
return {
|
||||
chatId: body.chatId,
|
||||
provider: completedAgentAside ? "hermes-agent" : body.provider,
|
||||
provider: completedAgentAside ? "sybil-agent" : body.provider,
|
||||
model: completedAgentAside ? "sybil-agent" : body.model,
|
||||
message: {
|
||||
role: "assistant",
|
||||
@@ -1778,7 +1778,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
|
||||
await storeAgentAsideReply(body.chatId, content, body.clientRequestId);
|
||||
return {
|
||||
chatId: body.chatId,
|
||||
provider: "hermes-agent",
|
||||
provider: "sybil-agent",
|
||||
model: "sybil-agent",
|
||||
message: { role: "assistant", content, name: "Sybil Agent", agentAside: true },
|
||||
};
|
||||
|
||||
@@ -58,7 +58,7 @@ test("mention invokes only the inline Agent, stores both sides, and replays by r
|
||||
};
|
||||
const first = await app.inject({ method: "POST", url: "/v1/chat-completions", headers: auth, payload: body });
|
||||
assert.equal(first.statusCode, 200, first.body);
|
||||
assert.equal(first.json().provider, "hermes-agent");
|
||||
assert.equal(first.json().provider, "sybil-agent");
|
||||
assert.equal(first.json().message.name, "Sybil Agent");
|
||||
assert.equal(first.json().message.agentAside, true);
|
||||
assert.equal(first.json().message.content, "Synthetic Sybil reply");
|
||||
@@ -66,7 +66,7 @@ test("mention invokes only the inline Agent, stores both sides, and replays by r
|
||||
|
||||
const retry = await app.inject({ method: "POST", url: "/v1/chat-completions", headers: auth, payload: body });
|
||||
assert.equal(retry.statusCode, 200, retry.body);
|
||||
assert.equal(retry.json().provider, "hermes-agent");
|
||||
assert.equal(retry.json().provider, "sybil-agent");
|
||||
assert.equal(retry.json().message.name, "Sybil Agent");
|
||||
assert.equal(retry.json().message.agentAside, true);
|
||||
assert.equal(retry.json().message.content, "Synthetic Sybil reply");
|
||||
@@ -224,9 +224,12 @@ test("streamed mention is idempotent and identifies the inline Agent", async ()
|
||||
const retry = streamingApp.inject({ method: "POST", url: "/v1/chat-completions/stream", headers: auth, payload });
|
||||
finish("Synthetic streamed reply");
|
||||
const [firstResponse, retryResponse] = await Promise.all([first, retry]);
|
||||
for (const response of [firstResponse, retryResponse]) {
|
||||
const completedReplay = await streamingApp.inject({ method: "POST", url: "/v1/chat-completions/stream", headers: auth, payload });
|
||||
for (const response of [firstResponse, retryResponse, completedReplay]) {
|
||||
assert.equal(response.statusCode, 200, response.body);
|
||||
assert.match(response.body, /"agentAside":true/);
|
||||
assert.match(response.body, /"provider":"sybil-agent"/);
|
||||
assert.match(response.body, /"model":"sybil-agent"/);
|
||||
assert.match(response.body, /Synthetic streamed reply/);
|
||||
}
|
||||
assert.equal(calls, 1);
|
||||
|
||||
@@ -125,13 +125,13 @@ test("plain Chat Completions stream does not send Sybil-managed tools", async ()
|
||||
const events = await collectEvents(
|
||||
streamWithChatCompletionsApi({
|
||||
client: client as any,
|
||||
model: "hermes-agent",
|
||||
model: "grok-test",
|
||||
messages: [{ role: "user", content: "Say hi" }],
|
||||
enabledTools: [],
|
||||
})
|
||||
);
|
||||
|
||||
assert.equal(requestBody.model, "hermes-agent");
|
||||
assert.equal(requestBody.model, "grok-test");
|
||||
assert.equal(requestBody.stream, true);
|
||||
assert.equal("tools" in requestBody, false);
|
||||
assert.deepEqual(
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
import { env } from "../src/env.js";
|
||||
import { describeProviderChatBackend, fetchProviderCatalogModels } from "../src/llm/provider-adapters.js";
|
||||
import { describeProviderChatBackend, fetchProviderCatalogModels, listModelCatalogProviders } from "../src/llm/provider-adapters.js";
|
||||
|
||||
for (const { name, listedModels, expectedModels } of [
|
||||
{
|
||||
@@ -47,6 +47,7 @@ for (const { name, listedModels, expectedModels } of [
|
||||
}
|
||||
|
||||
test("provider backend registry selects chat protocol and managed-tool mode", () => {
|
||||
assert.deepEqual(listModelCatalogProviders(), ["openai", "anthropic", "xai", "gemini"]);
|
||||
assert.deepEqual(describeProviderChatBackend("openai", []), {
|
||||
provider: "openai",
|
||||
protocol: "chat-completions",
|
||||
@@ -77,10 +78,4 @@ test("provider backend registry selects chat protocol and managed-tool mode", ()
|
||||
managedTools: true,
|
||||
enabledTools: ["web_search"],
|
||||
});
|
||||
assert.deepEqual(describeProviderChatBackend("hermes-agent", ["web_search"]), {
|
||||
provider: "hermes-agent",
|
||||
protocol: "chat-completions",
|
||||
managedTools: false,
|
||||
enabledTools: [],
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,14 +1,26 @@
|
||||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
import { fromPrismaProvider, serializeProviderFields, toPrismaProvider } from "../src/llm/provider-ids.js";
|
||||
import { parseProvider, serializeProviderFields } from "../src/llm/provider-ids.js";
|
||||
import { PROVIDERS } from "../src/llm/types.js";
|
||||
|
||||
test("Hermes Agent provider id maps between API and Prisma enum forms", () => {
|
||||
assert.equal(toPrismaProvider("hermes-agent"), "hermes_agent");
|
||||
assert.equal(fromPrismaProvider("hermes_agent"), "hermes-agent");
|
||||
assert.equal(toPrismaProvider("gemini"), "gemini");
|
||||
assert.equal(fromPrismaProvider("gemini"), "gemini");
|
||||
assert.deepEqual(serializeProviderFields({ initiatedProvider: "hermes_agent", lastUsedProvider: "gemini" }), {
|
||||
initiatedProvider: "hermes-agent",
|
||||
lastUsedProvider: "gemini",
|
||||
test("only supported provider IDs can become active selections", () => {
|
||||
for (const provider of PROVIDERS) assert.equal(parseProvider(provider), provider);
|
||||
for (const provider of [null, undefined, "retired-provider", "sybil-agent", "toString", {}]) {
|
||||
assert.equal(parseProvider(provider), null);
|
||||
}
|
||||
});
|
||||
|
||||
test("retired saved selections are cleared without changing historical call records", () => {
|
||||
const record = {
|
||||
initiatedProvider: "retired-provider", initiatedModel: "old-model",
|
||||
lastUsedProvider: "gemini", lastUsedModel: "current-model",
|
||||
calls: [{ provider: "retired-provider", model: "old-model", request: { provider: "retired-provider" } }],
|
||||
};
|
||||
assert.deepEqual(serializeProviderFields(record), {
|
||||
initiatedProvider: null, initiatedModel: null,
|
||||
lastUsedProvider: "gemini", lastUsedModel: "current-model",
|
||||
calls: [{ provider: null, model: "old-model", request: { provider: "retired-provider" } }],
|
||||
});
|
||||
assert.equal(record.initiatedProvider, "retired-provider");
|
||||
assert.equal(record.calls[0]!.provider, "retired-provider");
|
||||
});
|
||||
|
||||
@@ -0,0 +1,80 @@
|
||||
import assert from "node:assert/strict";
|
||||
import { execFileSync } from "node:child_process";
|
||||
import { mkdtempSync, rmSync } from "node:fs";
|
||||
import { tmpdir } from "node:os";
|
||||
import { dirname, join, resolve } from "node:path";
|
||||
import test from "node:test";
|
||||
import { fileURLToPath } from "node:url";
|
||||
import Fastify from "fastify";
|
||||
import sensible from "@fastify/sensible";
|
||||
import { PROVIDERS } from "../src/llm/types.js";
|
||||
|
||||
const serverRoot = resolve(dirname(fileURLToPath(import.meta.url)), "..");
|
||||
const databaseDir = mkdtempSync(join(tmpdir(), "sybil-provider-retirement-"));
|
||||
process.env.DATABASE_URL = `file:${join(databaseDir, "test.db")}`;
|
||||
process.env.ADMIN_TOKEN = "provider-retirement-test-token";
|
||||
execFileSync(process.execPath, [join(serverRoot, "node_modules/prisma/build/index.js"), "migrate", "deploy"], {
|
||||
cwd: serverRoot, env: { ...process.env, PRISMA_HIDE_UPDATE_MESSAGE: "1" }, stdio: "pipe",
|
||||
});
|
||||
const [{ registerRoutes }, { prisma }] = await Promise.all([import("../src/routes.js"), import("../src/db.js")]);
|
||||
const app = Fastify({ logger: false });
|
||||
await app.register(sensible);
|
||||
await registerRoutes(app, { agentInlineInvoker: async () => { throw new Error("Unsupported requests must not invoke the Agent"); } });
|
||||
await app.ready();
|
||||
const auth = { authorization: "Bearer provider-retirement-test-token" };
|
||||
test.after(async () => { await app.close(); await prisma.$disconnect(); rmSync(databaseDir, { recursive: true, force: true }); });
|
||||
|
||||
test("catalog and request validation expose only the remaining LLM providers", async () => {
|
||||
const catalog = await app.inject({ method: "GET", url: "/v1/models", headers: auth });
|
||||
assert.equal(catalog.statusCode, 200);
|
||||
assert.deepEqual(Object.keys(catalog.json().providers), [...PROVIDERS]);
|
||||
const before = await prisma.chat.count();
|
||||
for (const provider of ["retired-provider", "sybil-agent"]) {
|
||||
for (const url of ["/v1/chats", "/v1/chat-completions", "/v1/chat-completions/stream", "/v1/quick-questions/stream"]) {
|
||||
const response = await app.inject({ method: "POST", url, headers: auth, payload: {
|
||||
provider, model: "test-model", messages: [{ role: "user", content: "@sybil test" }], question: "test",
|
||||
} });
|
||||
assert.equal(response.statusCode, 400, `${url}: ${response.body}`);
|
||||
}
|
||||
}
|
||||
assert.equal(await prisma.chat.count(), before);
|
||||
assert.equal(await prisma.llmCall.count(), 0);
|
||||
for (const provider of PROVIDERS) {
|
||||
const response = await app.inject({ method: "POST", url: "/v1/chats", headers: auth, payload: { provider, model: "test-model" } });
|
||||
assert.equal(response.statusCode, 200, response.body);
|
||||
assert.equal(response.json().chat.lastUsedProvider, provider);
|
||||
}
|
||||
});
|
||||
|
||||
test("existing text provider IDs remain readable and forkable without relabeling history", async () => {
|
||||
const chat = await prisma.chat.create({ data: {
|
||||
title: "Archived provider conversation",
|
||||
initiatedProvider: "retired-provider", initiatedModel: "archived-model",
|
||||
lastUsedProvider: "retired-provider", lastUsedModel: "archived-model",
|
||||
messages: { create: { role: "assistant", content: "Original saved answer", metadata: { clientRequestId: "old-request" } } },
|
||||
calls: { create: { provider: "retired-provider", model: "archived-model", request: { provider: "retired-provider", clientRequestId: "old-request" }, latencyMs: 1 } },
|
||||
}, include: { messages: true, calls: true } });
|
||||
const detail = await app.inject({ method: "GET", url: `/v1/chats/${chat.id}`, headers: auth });
|
||||
assert.equal(detail.statusCode, 200, detail.body);
|
||||
const saved = detail.json().chat;
|
||||
for (const key of ["initiatedProvider", "initiatedModel", "lastUsedProvider", "lastUsedModel"]) assert.equal(saved[key], null);
|
||||
assert.equal(saved.messages[0].content, "Original saved answer");
|
||||
assert.equal(saved.messages[0].metadata.generation, undefined);
|
||||
assert.equal(saved.calls[0].provider, null);
|
||||
assert.equal(saved.calls[0].request.provider, "retired-provider");
|
||||
for (const url of ["/v1/chats", "/v1/workspace-items", "/v1/chats?limit=50"]) {
|
||||
const response = await app.inject({ method: "GET", url, headers: auth });
|
||||
assert.equal(response.statusCode, 200, `${url}: ${response.body}`);
|
||||
const rows = response.json().chats ?? response.json().items;
|
||||
assert.equal(rows.find((row: any) => row.id === chat.id).lastUsedProvider, null);
|
||||
}
|
||||
const fork = await app.inject({ method: "POST", url: `/v1/chats/${chat.id}/fork`, headers: auth, payload: {} });
|
||||
assert.equal(fork.statusCode, 200, fork.body);
|
||||
const forkDetail = await app.inject({ method: "GET", url: `/v1/chats/${fork.json().chat.id}`, headers: auth });
|
||||
assert.equal(forkDetail.statusCode, 200, forkDetail.body);
|
||||
assert.equal(forkDetail.json().chat.lastUsedProvider, null);
|
||||
assert.equal(forkDetail.json().chat.messages[0].content, "Original saved answer");
|
||||
const stored = await prisma.chat.findUniqueOrThrow({ where: { id: chat.id }, include: { calls: true } });
|
||||
assert.equal(stored.lastUsedProvider, "retired-provider");
|
||||
assert.equal(stored.calls[0]!.provider, "retired-provider");
|
||||
});
|
||||
Reference in New Issue
Block a user