mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-11-02 12:12:17 +00:00
c00acb36a0
* 🌌 feat: Add GPT-6 Astra Support Registers OpenAI's GPT-6 Astra (`gpt-6-astra`) as a first-class model on the canonical OpenAI endpoint. Every model-specific behavior Astra requires — Responses routing for tool calls, stripping the sampling and logprob parameters it rejects, and substituting the `none`/`minimal` reasoning efforts it does not accept — lands in `@librechat/agents` (danny-avila/agents#506) rather than here. None of it is expressible at configuration time: tools bind after `getOpenAIConfig` runs, and LangChain's request builders emit `temperature`/`top_p` from instance fields regardless of what this layer sets. Keeping it in the SDK also means the routing gate can be the documented rule (tools present) instead of the over-approximation the config-time GPT-5.6 path is forced into. What is left here is registration: - 1,050,000-token context window and 128K max output - Model dropdown (config.ts) and the `OPENAI_MODELS` example - Standard pricing: $10/M input, $1/M cached input, $12.50/M cache writes, $50/M output - The >272K long-context tier, which LibreChat already supports through `premiumTokenValues`/`premiumCacheTokenValues`: 2x input and cache rates and 1.5x output for the full request Batch/Flex (50%) and Fast mode (2x) have no representation in the pricing model today and are not introduced here; they apply per-request rather than per-model, so they need a request-shape signal this layer does not yet carry. Tests pin the pricing against the documented multipliers rather than restating the literals — cache writes as 1.25x input, and the premium tier as 2x/1.5x of standard — plus threshold behavior either side of 272K, and that `gpt-6-astra` resolves to its own key for snapshots and provider-prefixed ids instead of collapsing onto a shorter `gpt-6` match. Resolves #15560 Ref: https://developers.openai.com/api/docs/models/gpt-6-astra Ref: https://developers.openai.com/api/docs/guides/latest-model * 🧪 test: Guard the GPT-6 Astra Max Output Entry [Copilot] The Astra tests asserted the context window but not the 128K max output added alongside it in `anthropicMaxOutputs`' OpenAI counterpart, so that entry could regress silently. The gpt-5.6 tier test above covers both, and the delete-the-fix check showed the gap: removing the source entries failed only the context assertions. Assert `getModelMaxOutputTokens` alongside `getModelMaxTokens`, and fold the snapshot/prefix cases into one loop so both dimensions are covered for every id shape rather than only the bare one. Verified by deleting just the max-output entry: both Astra tests now fail where previously neither did. * 🪧 feat: Declare the First-Party OpenAI Endpoint to the Agents SDK The agents SDK gates GPT-6 Astra's request constraints — Responses-only tool calls, rejected sampling parameters, unsupported reasoning efforts — on knowing it is talking to the first-party OpenAI surface, and defaults them off. It takes that as a declaration rather than inferring it, because a base URL cannot answer the question: only this layer knows whether a URL is a faithful first-party route, a gateway, or a proxy with its own semantics. That decision already exists here, in `isCanonicalOpenAIBaseURL`, used by the GPT-5.6 Responses default. Declaring it from the same checks keeps it in one place instead of duplicating it downstream where the two could drift — and if the endpoint logic ever moves, it moves once. `firstPartyEndpoint` is declared on `OAIClientOptions` alongside the other agents SDK fields this layer already sets (`promptCache`, `_lc_stream_delay`, `includeReasoningContent`), so it typechecks against the current published SDK and is consumed once the SDK release lands. Two backward-compatibility expectations gain the field. That is the intended signal: they assert the full emitted config precisely so a new field cannot slip through unnoticed. * 🗂 fix: Keep GPT-6 Astra Out of the Assistants Catalogs [Codex P2] `sharedOpenAIModels` feeds `defaultModels[assistants]` and `[azureAssistants]` as well as the OpenAI and agents catalogs. Astra serves tool calls only from the Responses API, and the Assistants endpoints do not route through `getOpenAILLMConfig`, so listing it there offered a configuration the provider rejects. Astra now sits in its own `responsesOnlyOpenAIModels` list, spread into the OpenAI and agents catalogs only. Agents keeps it deliberately: that path does go through `getOpenAILLMConfig`. * 🎚 fix: Route GPT-6 Astra to the Responses API at Config Time [Codex P1] `max_tokens` was shaped into `max_completion_tokens` here, from `llmConfig.useResponsesApi`, while the agents SDK switched Astra to the Responses API later at invocation time — so the request reached an endpoint expecting `max_output_tokens` and was rejected. Deciding the API here fixes that, and generalizes: any field whose shape depends on the endpoint has the same problem, so the choice has to precede the shaping. It also lands before Azure replaces `llmConfig.model` with a deployment name, which is the only point that still knows the real model id. Unlike the GPT-5.6 rule above, this does not depend on reasoning parameters. Astra serves tool calls only from Responses, and OpenAI recommends Responses for it generally, so a static decision loses nothing — which was the reason the SDK was deciding it dynamically. The existing guards carry over: OpenRouter, custom gateways, and an explicit `dropParams` opt-out keep their configured path. The agents SDK is still required, for the request shaping Astra needs on either API (danny-avila/agents#506); it no longer decides routing. * 🏷 fix: Record the Served Model Before Azure Overwrites It [Codex P1] `llmConfig.model` is unconditionally replaced with the Azure deployment name, so the agents SDK received an alias and could not tell which model it was talking to — a deployment not literally named `gpt-6-astra` got none of the request shaping Astra requires. Records the real id in `servedModel` immediately before the overwrite, which is the last point that still knows it. The SDK prefers it over `model` when deciding which model-specific constraints apply (danny-avila/agents#506). Set for every first-party Azure request rather than only Astra: "what this deployment serves" is a fact this layer knows and the SDK decides what to do with, and keeping model-specific knowledge out of here is the point of the split. The backward-compatibility expectation gains the field, which is that test doing its job. * 🎛 fix: Do Not Let a reasoning_effort Drop Disable Astra Routing [Codex P1] The Astra routing reused the GPT-5.6 opt-out wholesale, which treats `dropParams: ['reasoning_effort']` as opting out of the Responses API. That holds for the 5.6 default, which routes *because* of reasoning — removing the effort removes its reason to route. Astra's routing is not reasoning-driven, so a rule clearing an unsupported stored effort silently put it back on Chat Completions, where its tool calls fail. Astra now honors only an explicit `useResponsesApi` drop. Reusing the guard without re-deriving whether each clause applied was the error. * ✂️ fix: Scope GPT-6 Astra to the First-Party OpenAI Endpoint [Codex P1 + P2] Two findings, both Azure, resolved by removing the Azure support rather than extending it. Azure's first-party hosts do not satisfy `isCanonicalOpenAIBaseURL`, so a configured `*.openai.azure.com` was neither routed to Responses nor declared first-party; and moving Astra out of `sharedOpenAIModels` also removed it from the Azure chat fallback, since `getOpenAIModels({ azure: true })` resolves through `defaultModels[azureAssistants]`. Both are moot once the scope is right: OpenAI does not document Astra as available on Azure OpenAI. Its model page lists the API and OpenAI's own subscription plans, with no third-party cloud surface. The Azure handling was support for a deployment the model is not documented to reach, and it produced most of the review findings on this branch and its agents SDK counterpart. Routing and the first-party declaration are now scoped to `EModelEndpoint.openAI`, and the Azure-only `servedModel` recording is gone along with its SDK counterpart. Astra staying out of the Azure catalogs is now the intended outcome rather than a regression. * 🚫 fix: Keep Astra Out of the Initial Azure Catalog [Codex P1] `initialModelsConfig` feeds the OpenAI catalog to Azure OpenAI as well, so scoping Astra to the first-party OpenAI endpoint left it advertised on Azure anyway — and being first in the list, it could become the default selection where no prior choice exists. The server's Azure fallback already excludes it, so the client would offer a model the server then rejects. The Azure initial catalog now uses the OpenAI list minus the Responses-only models, following the same scoping decision the routing guard makes. The initial Assistants catalog was already safe: `fitlerAssistantModels` requires `gpt-4` or `gpt-3.5`, which Astra does not match. Pinned that in a test rather than leaving it to a regex written for another purpose. * ⬆️ chore: Bump `@librechat/agents` to 3.7.20 for GPT-6 Astra Constraints
146 lines
4.5 KiB
JSON
146 lines
4.5 KiB
JSON
{
|
|
"name": "@librechat/backend",
|
|
"version": "v0.8.8-rc2",
|
|
"description": "",
|
|
"scripts": {
|
|
"start": "echo 'please run this from the root directory'",
|
|
"server-dev": "echo 'please run this from the root directory'",
|
|
"test": "cross-env NODE_ENV=test jest",
|
|
"b:test": "NODE_ENV=test bun jest",
|
|
"test:ci": "jest --ci --logHeapUsage",
|
|
"add-balance": "node ./add-balance.js",
|
|
"list-balances": "node ./list-balances.js",
|
|
"user-stats": "node ./user-stats.js",
|
|
"create-user": "node ./create-user.js",
|
|
"invite-user": "node ./invite-user.js",
|
|
"ban-user": "node ./ban-user.js",
|
|
"delete-user": "node ./delete-user.js"
|
|
},
|
|
"repository": {
|
|
"type": "git",
|
|
"url": "git+https://github.com/danny-avila/LibreChat.git"
|
|
},
|
|
"keywords": [],
|
|
"author": "",
|
|
"license": "ISC",
|
|
"_moduleAliases": {
|
|
"~": "."
|
|
},
|
|
"imports": {
|
|
"~/*": "./*"
|
|
},
|
|
"bugs": {
|
|
"url": "https://github.com/danny-avila/LibreChat/issues"
|
|
},
|
|
"homepage": "https://librechat.ai",
|
|
"dependencies": {
|
|
"@anthropic-ai/vertex-sdk": "^0.16.0",
|
|
"@aws-sdk/client-bedrock-runtime": "^3.1013.0",
|
|
"@aws-sdk/client-cloudfront": "^3.1042.0",
|
|
"@aws-sdk/client-s3": "^3.980.0",
|
|
"@aws-sdk/cloudfront-signer": "^3.1036.0",
|
|
"@aws-sdk/credential-providers": "^3.1045.0",
|
|
"@aws-sdk/s3-request-presigner": "^3.758.0",
|
|
"@azure/identity": "^4.13.1",
|
|
"@azure/search-documents": "^12.0.0",
|
|
"@azure/storage-blob": "^12.30.0",
|
|
"@google/genai": "^2.8.0",
|
|
"@keyv/redis": "5.1.6",
|
|
"@librechat/agents": "^3.7.20",
|
|
"@librechat/api": "*",
|
|
"@librechat/data-schemas": "*",
|
|
"@microsoft/microsoft-graph-client": "^3.0.7",
|
|
"@modelcontextprotocol/sdk": "^1.30.0",
|
|
"@node-saml/passport-saml": "^5.1.0",
|
|
"@opentelemetry/api": "^1.9.0",
|
|
"@opentelemetry/instrumentation-express": "^0.56.0",
|
|
"@opentelemetry/instrumentation-http": "^0.207.0",
|
|
"@opentelemetry/instrumentation-ioredis": "^0.55.0",
|
|
"@opentelemetry/instrumentation-mongodb": "^0.60.0",
|
|
"@opentelemetry/instrumentation-mongoose": "^0.54.0",
|
|
"@opentelemetry/instrumentation-undici": "^0.18.0",
|
|
"@opentelemetry/resources": "^2.6.1",
|
|
"@opentelemetry/sdk-node": "^0.221.0",
|
|
"@opentelemetry/semantic-conventions": "^1.39.0",
|
|
"@opentelemetry/winston-transport": "^0.28.0",
|
|
"@redis/client": "5.10.0",
|
|
"@smithy/node-http-handler": "^4.4.5",
|
|
"ai-tokenizer": "^1.0.6",
|
|
"axios": "^1.20.0",
|
|
"bcryptjs": "^2.4.3",
|
|
"compression": "^1.8.1",
|
|
"connect-redis": "^8.1.0",
|
|
"cookie": "^0.7.2",
|
|
"cookie-parser": "^1.4.7",
|
|
"cors": "^2.8.5",
|
|
"dedent": "^1.5.3",
|
|
"dotenv": "^16.0.3",
|
|
"eventsource": "^3.0.2",
|
|
"express": "^5.2.1",
|
|
"express-mongo-sanitize": "^2.2.0",
|
|
"express-rate-limit": "^8.5.1",
|
|
"express-session": "^1.18.2",
|
|
"express-static-gzip": "^2.2.0",
|
|
"file-type": "^21.3.2",
|
|
"firebase": "^11.0.2",
|
|
"form-data": "^4.0.4",
|
|
"get-stream": "^6.0.1",
|
|
"handlebars": "^4.7.9",
|
|
"https-proxy-agent": "^7.0.6",
|
|
"ioredis": "^5.3.2",
|
|
"js-yaml": "^4.2.0",
|
|
"jsonwebtoken": "^9.0.0",
|
|
"jszip": "^3.10.1",
|
|
"jwks-rsa": "^3.2.0",
|
|
"keyv": "5.6.0",
|
|
"keyv-file": "^5.1.2",
|
|
"klona": "^2.0.6",
|
|
"librechat-data-provider": "*",
|
|
"lodash": "^4.17.23",
|
|
"mammoth": "^1.11.0",
|
|
"mathjs": "^15.2.0",
|
|
"meilisearch": "^0.38.0",
|
|
"memorystore": "^1.6.7",
|
|
"mime": "^3.0.0",
|
|
"module-alias": "^2.2.3",
|
|
"mongodb": "^6.14.2",
|
|
"mongoose": "^8.24.1",
|
|
"multer": "^2.3.0",
|
|
"nanoid": "^3.3.18",
|
|
"node-fetch": "^2.7.0",
|
|
"nodemailer": "^9.0.1",
|
|
"ollama": "^0.5.0",
|
|
"openai": "5.8.2",
|
|
"openid-client": "^6.5.0",
|
|
"passport": "^0.6.0",
|
|
"passport-apple": "^2.0.2",
|
|
"passport-discord": "^0.1.4",
|
|
"passport-facebook": "^3.0.0",
|
|
"passport-github2": "^0.1.12",
|
|
"passport-google-oauth20": "^2.0.0",
|
|
"passport-jwt": "^4.0.1",
|
|
"passport-ldapauth": "^3.0.1",
|
|
"passport-local": "^1.0.0",
|
|
"pdfjs-dist": "^5.4.624",
|
|
"prom-client": "^15.1.3",
|
|
"rate-limit-redis": "^4.2.0",
|
|
"re2js": "^2.8.6",
|
|
"sanitize-html": "^2.17.7",
|
|
"sharp": "^0.35.3",
|
|
"ua-parser-js": "^1.0.36",
|
|
"undici": "^7.29.0",
|
|
"winston": "^3.11.0",
|
|
"winston-daily-rotate-file": "^5.0.0",
|
|
"xlsx": "https://cdn.sheetjs.com/xlsx-0.20.3/xlsx-0.20.3.tgz",
|
|
"yauzl": "^3.2.1",
|
|
"zod": "^3.22.4"
|
|
},
|
|
"devDependencies": {
|
|
"@babel/preset-env": "^7.29.5",
|
|
"@types/sanitize-html": "^2.16.1",
|
|
"jest": "^30.2.0",
|
|
"mongodb-memory-server": "^11.0.1",
|
|
"nodemon": "^3.1.14",
|
|
"supertest": "^7.1.0"
|
|
}
|
|
}
|