@ljoukov/llm 3.0.1 → 3.0.2

package/README.md

@@ -9,7 +9,7 @@ Unified TypeScript wrapper over:
 
 - **OpenAI Responses API** (`openai`)
 - **Google Gemini via Vertex AI** (`@google/genai`)
-- **Fireworks chat-completions models** (`kimi-k2.5`, `glm-5`, `minimax-m2.1`)
+- **Fireworks chat-completions models** (`kimi-k2.5`, `glm-5`, `minimax-m2.1`, `gpt-oss-120b`)
 - **ChatGPT subscription models** via `chatgpt-*` model ids (reuses Codex auth store, or a token provider)
 
 Designed around a single streaming API that yields:
@@ -34,6 +34,8 @@ See Node.js docs on environment variables and dotenv files: https://nodejs.org/a
 ### OpenAI
 
 - `OPENAI_API_KEY`
+- `OPENAI_RESPONSES_WEBSOCKET_MODE` (`auto` | `off` | `only`, default: `auto`)
+- `OPENAI_BASE_URL` (optional; defaults to `https://api.openai.com/v1`)
 
 ### Gemini (Vertex AI)
 
@@ -86,20 +88,24 @@ refresh-token rotation and serves short-lived access tokens.
 - `CHATGPT_AUTH_TOKEN_PROVIDER_URL` (example: `https://chatgpt-auth.<your-domain>`)
 - `CHATGPT_AUTH_API_KEY` (shared secret; sent as `Authorization: Bearer ...` and `x-chatgpt-auth: ...`)
 - `CHATGPT_AUTH_TOKEN_PROVIDER_STORE` (`kv` or `d1`, defaults to `kv`)
+- `CHATGPT_RESPONSES_WEBSOCKET_MODE` (`auto` | `off` | `only`, default: `auto`)
 
-This repo includes a Cloudflare Workers token provider implementation in `chatgpt-auth/worker/`.
+This repo includes a Cloudflare Workers token provider implementation in `workers/chatgpt-auth/`.
 
-To seed the worker with a fresh OAuth token set via browser login:
+If `CHATGPT_AUTH_TOKEN_PROVIDER_URL` + `CHATGPT_AUTH_API_KEY` are set, `chatgpt-*` models will fetch tokens from the
+token provider and will not read the local Codex auth store.
 
-```bash
-npm run chatgpt-auth:seed -- --worker-url https://chatgpt-auth.<your-domain>
-```
+### Responses transport
 
-The CLI opens `auth.openai.com`, captures the localhost OAuth callback, exchanges the code, calls `POST /v1/seed`,
-then resolves a smoke model from `GET /backend-api/codex/models` and runs a post-seed inference check (disable with `--skip-smoke-check`).
+For OpenAI and `chatgpt-*` model paths, this library now tries **Responses WebSocket transport first** and falls back
+to HTTP/SSE automatically when needed.
 
-If `CHATGPT_AUTH_TOKEN_PROVIDER_URL` + `CHATGPT_AUTH_API_KEY` are set, `chatgpt-*` models will fetch tokens from the
-token provider and will not read the local Codex auth store.
+- `auto` (default): try WebSocket first, then fall back to SSE
+- `off`: use SSE only
+- `only`: require WebSocket (no fallback)
+
+When fallback is triggered by an unsupported WebSocket upgrade response (for example `426`), the library keeps using
+SSE for the rest of the process to avoid repeated failing upgrade attempts.
 
 ## Usage
 
@@ -272,7 +278,7 @@ console.log(result.text);
 
 ### Fireworks
 
-Use Fireworks model ids directly (for example `kimi-k2.5`, `glm-5`, `minimax-m2.1`):
+Use Fireworks model ids directly (for example `kimi-k2.5`, `glm-5`, `minimax-m2.1`, `gpt-oss-120b`):
 
 ```ts
 import { generateText } from "@ljoukov/llm";