@khanglvm/llm-router 1.0.9 → 1.1.0

package/CHANGELOG.md

@@ -5,6 +5,27 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.1.0] - 2026-03-04
+
+### Added
+- Added full `config --operation=upsert-provider` UX support for subscription providers:
+  - `--type=subscription`
+  - `--subscription-type=chatgpt-codex`
+  - `--subscription-profile=<name>`
+- Added subscription provider coverage tests for config workflows and runtime provider-call behavior.
+- Added `.gitignore` rules for local IDE and deploy temp artifacts (`.idea/`, `.llm-router.deploy.*.wrangler.toml`).
+
+### Changed
+- Updated config summaries and AI-help guidance to include subscription provider details and setup commands.
+- Updated README setup guide with explicit ChatGPT Codex subscription onboarding flow.
+
+### Fixed
+- Fixed subscription status command import path so `llm-router subscription status` works reliably.
+- Fixed subscription provider request path to run standard request translation/mapping before OAuth-backed provider call.
+- Fixed subscription provider config validation and normalization:
+  - subscription providers no longer require `baseUrl`
+  - predefined ChatGPT Codex model list is enforced during normalization.
+
 ## [1.0.9] - 2026-03-03
 
 ### Added
@@ -16,6 +37,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Refactored CLI deploy/runtime handler code into focused modules with cleaner boundaries.
 - Updated provider-call timeout handling to support both `AbortSignal.timeout` and `AbortController` fallback.
 - Documented Worker safety defaults and switched README release/security links to canonical GitHub URLs.
+- Added local start port resolution via `--port`, `LLM_ROUTER_PORT`, or generic `PORT` env variables.
 
 ## [1.0.8] - 2026-02-28
 

package/README.md

@@ -24,7 +24,7 @@ Run `llm-router ai-help` first, then set up and operate llm-router for me using
 
 ## Main Workflow
 
-1. Add Providers + models into llm-router
+1. Add providers + models into llm-router (standard API-key providers or OAuth subscription providers)
 2. Optionally, group models as alias with load balancing and auto fallback support
 3. Start llm-router server, point your coding tool API and model to llm-router
 
@@ -77,10 +77,32 @@ Then follow this order.
 Flow:
 1. `Config manager`
 2. `Add/Edit provider`
-3. Enter provider name, endpoint, API key
-4. Enter model list
+3. Select provider type:
+   - `standard` -> endpoint + API key + model list
+   - `subscription` -> OAuth profile for predefined ChatGPT Codex models
+4. Enter provider details
 5. Save
 
+### 1b) Add Subscription Provider (ChatGPT Codex)
+Commandline example:
+
+```bash
+llm-router config \
+  --operation=upsert-provider \
+  --provider-id=chatgpt \
+  --name="ChatGPT Subscription" \
+  --type=subscription \
+  --subscription-type=chatgpt-codex \
+  --subscription-profile=default
+
+llm-router subscription login --profile=default
+llm-router subscription status --profile=default
+```
+
+Notes:
+- `chatgpt-codex` subscription providers use predefined model IDs managed by llm-router releases.
+- No provider API key or endpoint probing is required for this provider type.
+
 ### 2) Configure Model Fallback (Optional)
 Flow:
 1. `Config manager`
@@ -127,10 +149,18 @@ Flow:
 llm-router start
 ```
 
+Custom port (optional):
+
+```bash
+llm-router start --port=3001
+# or
+LLM_ROUTER_PORT=3001 llm-router start
+```
+
 Local endpoints:
-- Unified: `http://127.0.0.1:8787/route`
-- Anthropic-style: `http://127.0.0.1:8787/anthropic`
-- OpenAI-style: `http://127.0.0.1:8787/openai`
+- Unified: `http://127.0.0.1:<port>/route`
+- Anthropic-style: `http://127.0.0.1:<port>/anthropic`
+- OpenAI-style: `http://127.0.0.1:<port>/openai`
 
 ## Connect your coding tool
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@khanglvm/llm-router",
-  "version": "1.0.9",
+  "version": "1.1.0",
   "description": "Single gateway endpoint for multi-provider LLMs with unified OpenAI+Anthropic format and seamless fallback",
   "keywords": [
     "llm-router",