iaurora 1.0.31 → 1.0.32

package/README.md

@@ -2,28 +2,103 @@
   <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/aurora-logo-animated.svg" width="96" height="96" alt="Aurora Logo">
 </p>
 
-<h1 align="center">Aurora Gateway OSS — Open-Source AI Gateway | OpenAI &amp; Anthropic Compatible API</h1>
+<h1 align="center">Aurora — Open-Source AI Gateway</h1>
 
 <p align="center">
   <a href="LICENSE"><img src="https://img.shields.io/github/license/aurorallm/aurora" alt="License" height="20"></a>
   <a href="https://www.npmjs.com/package/iaurora"><img src="https://img.shields.io/npm/v/iaurora" alt="npm" height="20"></a>
-  <!-- <a href="https://codecov.io/gh/aurorallm/aurora"><img src="https://codecov.io/gh/aurorallm/aurora/branch/main/graph/badge.svg" alt="codecov" height="20"></a> -->
   <a href="https://github.com/aurorallm/aurora"><img src="https://img.shields.io/github/stars/aurorallm/aurora" alt="GitHub Stars" height="20"></a>
   <a href="https://discord.gg/AfaFBSU2km"><img src="https://dcbadge.limes.pink/api/server/https://discord.gg/AfaFBSU2km?style=flat" alt="Discord" height="20"></a>
   <img src="https://img.shields.io/docker/pulls/aurorahq/aurora" alt="Docker Pulls" height="20">
   <a href="https://artifacthub.io/packages/search?repo=aurora-gateway"><img src="https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/aurora-gateway" alt="Artifact Hub" height="20"></a>
-
 </p>
-<p align="center"><b>Open-source LLM gateway (OSS edition). One API for every AI provider.</b></p>
 
-<p align="center">Self-hosted. No vendor lock-in. 14 provider types, 30+ LLM providers supported.</p>
+<p align="center"><b>One API for every AI provider. Self-hosted. No vendor lock-in.</b></p>
+
+<p align="center">14 provider types &bull; OpenAI &amp; Anthropic compatible &bull; Built in Go &bull; Apache 2.0</p>
 
 <a href="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/dashboard-overview.png">
-  <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/dashboard-overview.png" alt="Aurora open-source AI gateway admin dashboard showing provider stats and usage metrics" width="100%">
+  <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/dashboard-overview.png" alt="Aurora admin dashboard showing provider stats and usage metrics" width="100%">
 </a>
 
 ---
 
+## What Aurora Does
+
+Aurora sits between your app and LLM providers. Your app sends requests using the standard OpenAI or Anthropic SDK — Aurora routes them to whichever provider you've configured.
+
+```python
+# Before: hardcoded provider
+client = OpenAI(base_url="https://api.openai.com/v1", api_key="sk-...")
+
+# After: Aurora Gateway
+client = OpenAI(base_url="http://localhost:8080/v1", api_key="your-aurora-key")
+```
+
+No SDK changes. No format changes. Just swap the `base_url`.
+
+---
+
+## Features
+
+### Routing & Providers
+
+- **14 provider types** — OpenAI, Anthropic, Gemini, Groq, DeepSeek, OpenRouter, xAI, Z.ai, MiniMax, Azure OpenAI, Oracle, Ollama, vLLM, Jina
+- **Auto-discovery** — set an API key as an env var, restart, provider + all its models appear automatically
+- **Provider pools** — group multiple keys/endpoints, load-balance with round-robin, health-aware failover
+- **Fallback** — automatic failover on 5xx/429, or manual rules mapping failed provider+model to backups
+- **Resilience** — exponential backoff with jitter, circuit breaker per provider (closed → open → half-open)
+- **Multiple instances** — run `OPENAI_EAST_API_KEY` and `OPENAI_WEST_API_KEY` as separate providers
+- **Custom base URLs** — override any provider's endpoint (corporate proxies, regional endpoints)
+- **Passthrough** — `/p/{provider}/*` for full upstream API access (not just chat completions)
+
+### API Surface
+
+- **OpenAI-compatible** — `/v1/chat/completions`, `/v1/embeddings`, `/v1/rerank`, `/v1/models`, `/v1/files`, `/v1/batches`
+- **Responses API** — `/v1/responses` with full CRUD, cancel, input items, compact
+- **Anthropic-compatible** — `/v1/messages`, `/v1/messages/count_tokens` (native Anthropic wire format)
+- **Streaming** — SSE streaming for all endpoints, preserved end-to-end
+
+### Caching
+
+- **Exact cache** — SHA-256 hash match on request, Redis-backed, async writes
+- **Semantic cache** — vector similarity with configurable threshold, supports Qdrant, pgvector, Pinecone, Weaviate
+- **Prompt cache** — forwards `cache_control` to Anthropic/OpenAI/Gemini native prompt caching
+- **Model registry cache** — local filesystem + Redis, offline-safe
+
+### Security & Guardrails
+
+- **Master key** — top-level gateway auth
+- **Managed API keys** — scoped, rate-limited, per-key model authorization, usage stats
+- **PII redaction** — email, phone, SSN, credit card detection and masking
+- **Prompt injection blocking** — detects and blocks injection attempts
+- **System prompt protection** — inject, override, or decorate system prompts
+- **Regex blocking** — custom pattern matching with block or sanitize actions
+- **Length limits** — character/token count enforcement on requests
+
+### Observability
+
+- **Audit logging** — full request/response capture, buffered writes, configurable retention, live SSE stream
+- **Usage analytics** — per-model token counting, cost tracking, daily aggregation by model/user-path
+- **Prometheus metrics** — `aurora_requests_total`, `aurora_request_duration_seconds`, `aurora_requests_in_flight`, plus gateway phase timing
+- **Admin dashboard** — React SPA built into the Go binary: providers, pools, models, aliases, guardrails, cache, usage, audit, auth keys, workflows, console, playground
+
+### Cost Control
+
+- **Token saver** — policy-driven output compression (profiles: concise, caveman, ultra, wenyan)
+- **Pricing management** — per-model pricing overrides, recalculation, import/export
+- **Usage budgets** — per-key usage tracking and limits
+
+### Developer Experience
+
+- **Single binary** — `npm install -g iaurora` or `docker pull aurorahq/aurora`
+- **CLI** — `aurora init`, `aurora models sync/diff/show`, `aurora update`, `aurora uninstall`
+- **Swagger docs** — `/swagger/index.html` (build-tag gated)
+- **Config profiles** — pre-built configs for local, local-power, and team deployments
+- **3-layer config** — code defaults → config.yaml → env vars (env vars win)
+
+---
+
 ## Quick Start
 
 Start routing AI traffic in 60 seconds.
@@ -79,8 +154,10 @@ aurora
 
 ### Option B — inline env vars (no `.env` needed)
 
+<details>
+<summary>Linux / macOS</summary>
+
 ```bash
-# Linux / macOS
 AURORA_MASTER_KEY=your-secure-key \
   OPENAI_API_KEY=sk-... \
   ANTHROPIC_API_KEY=sk-ant-... \
@@ -101,8 +178,13 @@ AURORA_MASTER_KEY=your-secure-key \
   GUARDRAILS_ENABLED=true \
   TOKEN_SAVER_ENABLED=true \
   aurora
+```
+</details>
 
-# Windows PowerShell
+<details>
+<summary>Windows PowerShell</summary>
+
+```powershell
 $env:AURORA_MASTER_KEY="your-secure-key"; `
 $env:OPENAI_API_KEY="sk-..."; `
 $env:ANTHROPIC_API_KEY="sk-ant-..."; `
@@ -123,8 +205,13 @@ $env:METRICS_ENABLED="true"; `
 $env:GUARDRAILS_ENABLED="true"; `
 $env:TOKEN_SAVER_ENABLED="true"; `
 aurora
+```
+</details>
 
-# Windows CMD
+<details>
+<summary>Windows CMD</summary>
+
+```cmd
 set AURORA_MASTER_KEY=your-secure-key ^
   && set OPENAI_API_KEY=sk-... ^
   && set ANTHROPIC_API_KEY=sk-ant-... ^
@@ -146,6 +233,7 @@ set AURORA_MASTER_KEY=your-secure-key ^
   && set TOKEN_SAVER_ENABLED=true ^
   && aurora
 ```
+</details>
 
 ### Option C — Docker
 
@@ -204,26 +292,6 @@ helm upgrade --install aurora ./helm \
   --set providers.groq.enabled=true \
   --set providers.deepseek.apiKey="..." \
   --set providers.deepseek.enabled=true \
-  --set providers.openrouter.apiKey="..." \
-  --set providers.openrouter.enabled=true \
-  --set providers.xai.apiKey="..." \
-  --set providers.xai.enabled=true \
-  --set providers.zai.apiKey="..." \
-  --set providers.zai.enabled=true \
-  --set providers.minimax.apiKey="..." \
-  --set providers.minimax.enabled=true \
-  --set providers.azure.apiKey="..." \
-  --set providers.azure.enabled=true \
-  --set providers.oracle.apiKey="..." \
-  --set providers.oracle.enabled=true \
-  --set providers.ollama.apiKey="..." \
-  --set providers.ollama.enabled=true \
-  --set providers.vllm.apiKey="..." \
-  --set providers.vllm.enabled=true \
-  --set logging.enabled=true \
-  --set metrics.enabled=true \
-  --set guardrails.enabled=true \
-  --set tokenSaver.enabled=true \
   --set redis.enabled=true
 ```
 
@@ -232,15 +300,13 @@ helm upgrade --install aurora ./helm \
 ### Test your gateway
 
 ```bash
+# OpenAI format
 curl http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer your-master-key" \
   -d '{"model":"groq/llama-4-scout-17b-16e-instruct","messages":[{"role":"user","content":"Hello!"}]}'
-```
-
-Anthropic format with streaming enabled:
 
-```bash
+# Anthropic format with streaming
 curl http://localhost:8080/v1/messages \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer your-master-key" \
@@ -251,30 +317,23 @@ curl http://localhost:8080/v1/messages \
     "stream": true,
     "messages": [{"role": "user", "content": "Hello!"}]
   }'
-```
-
-Dashboard: `http://localhost:8080/admin/dashboard`
-
-**Setup guides:** [Website](https://aurorallm.online/) · [npm](https://www.npmjs.com/package/iaurora) · [Docker](https://hub.docker.com/r/aurorahq/aurora) · [Helm/Kubernetes](https://github.com/aurorallm/aurora/tree/main/helm) · [Source](https://github.com/aurorallm/aurora)
-
----
-
-## Enterprise Deployments
 
-Aurora supports enterprise-grade deployments for teams running production AI systems at scale.
-In addition to private networking, custom security controls, and governance, **Aurora Enterprise** unlocks advanced capabilities including SSO, RBAC, tenant isolation, budget enforcement, compliance workflows, and production support.
+# Embeddings
+curl http://localhost:8080/v1/embeddings \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer your-master-key" \
+  -d '{"model":"openai/text-embedding-3-small","input":"Hello world"}'
 
-The Enterprise edition is a separate distribution with a signed license.
+# Reranking (Jina)
+curl http://localhost:8080/v1/rerank \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer your-master-key" \
+  -d '{"model":"jina/jina-reranker-v2-base-multilingual","query":"test","documents":["doc1","doc2"]}'
+```
 
-<a href="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/comparison.png">
-  <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/comparison.png" alt="OSS vs Enterprise comparison" width="100%" style="border-radius:12px;margin:16px 0;">
-</a>
+Dashboard: `http://localhost:8080/admin/dashboard`
 
-<div align="center">
-  <a href="mailto:team.auroragate@gmail.com?subject=Aurora%20Enterprise%20Inquiry" style="display:block;margin-top:5px;">
-    <img src="https://img.shields.io/badge/Email%20Us-Enterprise-5865F2?style=for-the-badge&logo=gmail&logoColor=white" alt="Email Aurora Enterprise" width="200"/>
-  </a>
-</div>
+**Docs:** [aurorallm.online/docs](https://aurorallm.online/docs) · [Website](https://aurorallm.online) · [npm](https://www.npmjs.com/package/iaurora) · [Docker](https://hub.docker.com/r/aurorahq/aurora) · [GitHub](https://github.com/aurorallm/aurora)
 
 ---
 
@@ -282,7 +341,7 @@ The Enterprise edition is a separate distribution with a signed license.
 
 Providers are **auto-discovered from environment variables**. Set any provider's `_API_KEY` and restart — the provider and its default models appear automatically.
 
-> **Security note for public docs:** The env var names listed below are documentation references. Actual secrets go into your **`.env` file** (in `.gitignore`) or your **deployment secrets manager** — never commit them.
+> **Security note:** The env var names below are documentation references. Actual secrets go into your **`.env` file** (in `.gitignore`) or your **deployment secrets manager** — never commit them.
 
 | Provider | Env var | Default base URL | Requires base URL | API key required | Default models |
 |----------|---------|-----------------|-------------------|-----------------|----------------|
@@ -301,7 +360,7 @@ Providers are **auto-discovered from environment variables**. Set any provider's
 | vLLM | `VLLM_API_KEY` | `http://localhost:8000/v1` | No | **No** (optional) | Any served model |
 | Jina (reranker) | `JINA_API_KEY` | — | **Yes** | Yes | `jina-embeddings-v3` |
 
-### Per-provider extras
+### Per-provider configuration
 
 Every provider supports `*_MODELS` to override auto-discovered models:
 
@@ -309,39 +368,36 @@ Every provider supports `*_MODELS` to override auto-discovered models:
 OPENAI_MODELS=gpt-5.6-sol,gpt-5.6-terra,gpt-5.6-luna
 ```
 
-OpenRouter extras:
+Custom base URL:
 
 ```env
-OPENROUTER_SITE_URL=https://github.com/aurorallm/aurora
-OPENROUTER_APP_NAME=Aurora Gateway
+OPENAI_BASE_URL=https://my-corp-openai-proxy.example.com/v1
 ```
 
-Azure requires API version:
+Multiple instances of the same provider (underscores become hyphens in the provider name):
 
 ```env
-AZURE_API_VERSION=2024-10-21
+OPENAI_EAST_API_KEY=sk-...     # → provider: openai-east
+OPENAI_WEST_API_KEY=sk-...     # → provider: openai-west
 ```
 
-### Custom base URL
-
-Override any provider's endpoint:
+Azure requires API version:
 
 ```env
-OPENAI_BASE_URL=https://my-corp-openai-proxy.example.com/v1
+AZURE_API_VERSION=2024-10-21
 ```
 
-### Multiple instances of the same provider
-
-Use suffix notation (underscores become hyphens in the provider name):
+OpenRouter extras:
 
 ```env
-OPENAI_EAST_API_KEY=sk-...     # → provider: openai-east
-OPENAI_WEST_API_KEY=sk-...     # → provider: openai-west
-JINA_API_KEY1=...              # → provider: jina-1
+OPENROUTER_SITE_URL=https://github.com/aurorallm/aurora
+OPENROUTER_APP_NAME=Aurora Gateway
 ```
 
 ---
 
+---
+
 ## Configuration
 
 The gateway loads settings in this priority order (later wins):
@@ -367,10 +423,11 @@ Generated by `aurora init`, every section of `config.yaml` is documented inline:
 | `token_saver` | Output compression |
 | `fallback` | Provider failover rules |
 | `resilience` | Retry + circuit breaker |
+| `workflows` | Policy-based request routing |
 
-### Quick config profiles
+### Config profiles
 
-Aurora ships pre-built config profiles in `configs/editions/`:
+Pre-built configs in `configs/editions/`:
 
 | Profile | File | Use case |
 |---------|------|----------|
@@ -382,30 +439,17 @@ Aurora ships pre-built config profiles in `configs/editions/`:
 export AURORA_CONFIG_PATH=configs/editions/oss.team.example.yaml
 ```
 
-### Configuring across deployment methods
-
-Each env var works in all three deploy modes:
-
-| Variable | `.env` file | Docker `-e` flag | Helm `--set` value |
-|----------|-------------|------------------|---------------------|
-| `PORT` | `PORT=9090` | `-e PORT=9090` | `--set server.port=9090` |
-| `AURORA_MASTER_KEY` | `AURORA_MASTER_KEY=...` | `-e AURORA_MASTER_KEY=...` | `--set auth.masterKey=...` |
-| `OPENAI_API_KEY` | `OPENAI_API_KEY=sk-...` | `-e OPENAI_API_KEY=sk-...` | `--set providers.openai.apiKey=...` |
-| `STORAGE_TYPE` | `STORAGE_TYPE=postgresql` | `-e STORAGE_TYPE=postgresql` | `--set storage.type=postgresql` |
-| `REDIS_URL` | `REDIS_URL=redis://...` | `-e REDIS_URL=redis://...` | `--set cache.redis.url=...` |
-
 ### Complete env var reference
 
-All configurable environment variables, organized by subsystem:
-
-#### Server & Security
+<details>
+<summary>Server & Security</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
 | `PORT` | `8080` | HTTP listening port |
 | `BASE_PATH` | `/` | URL path prefix to mount under |
 | `AURORA_MASTER_KEY` | `""` | Master API key for auth |
-| `BODY_SIZE_LIMIT` | `10M` | Max request body size (e.g. `10M`, `1G`, `500K`) |
+| `BODY_SIZE_LIMIT` | `10M` | Max request body size |
 | `SWAGGER_ENABLED` | `false` | Enable Swagger UI at `/swagger/index.html` |
 | `PPROF_ENABLED` | `false` | Enable pprof at `/debug/pprof/` |
 | `ENABLE_PASSTHROUGH_ROUTES` | `true` | Provider-native passthrough at `/p/{provider}` |
@@ -415,18 +459,22 @@ All configurable environment variables, organized by subsystem:
 | `DISABLE_REQUEST_LOGGING` | `false` | Turn off request logging |
 | `DISABLE_REQUEST_BODY_SNAPSHOT` | `false` | Don't snapshot request bodies |
 | `DISABLE_PASSTHROUGH_SEMANTIC_ENRICHMENT` | `false` | Disable semantic enrichment on passthrough |
+</details>
 
-#### HTTP Client & Proxy
+<details>
+<summary>HTTP Client & Proxy</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
 | `HTTP_TIMEOUT` | `600` | Upstream request timeout (seconds) |
-| `HTTP_RESPONSE_HEADER_TIMEOUT` | `600` | Timeout for upstream response headers (seconds) |
+| `HTTP_RESPONSE_HEADER_TIMEOUT` | `600` | Timeout for upstream response headers |
 | `HTTP_PROXY` | — | HTTP proxy URL for upstream calls |
 | `HTTPS_PROXY` | — | HTTPS proxy URL |
 | `NO_PROXY` | — | Hosts to exclude from proxy |
+</details>
 
-#### Storage
+<details>
+<summary>Storage</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
@@ -436,20 +484,24 @@ All configurable environment variables, organized by subsystem:
 | `POSTGRES_MAX_CONNS` | `10` | PostgreSQL connection pool max |
 | `MONGODB_URL` | — | MongoDB connection string |
 | `MONGODB_DATABASE` | `aurora` | MongoDB database name |
+</details>
 
-#### Model Registry
+<details>
+<summary>Model Registry</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
-| `MODEL_LIST_URL` | `https://github.com/aurorallm/aurora/blob/main/docs-assets/assets/models.json` | External model metadata registry (empty = disabled) |
+| `MODEL_LIST_URL` | `https://github.com/aurorallm/aurora/blob/main/docs-assets/assets/models.json` | External model metadata registry |
 | `MODEL_LIST_LOCAL_PATH` | `data/models.local.json` | Local model registry snapshot path |
 | `MODEL_LIST_USER_OVERRIDES_PATH` | `data/user_pricing.yaml` | User pricing override file |
 | `MODELS_ENABLED_BY_DEFAULT` | `true` | Default enabled state for provider models |
-| `MODEL_OVERRIDES_ENABLED` | `true` | Allow per-model overrides (dashboard editing) |
-| `KEEP_ONLY_ALIASES_AT_MODELS_ENDPOINT` | `false` | Hide provider models from `GET /v1/models`, show only aliases |
-| `CONFIGURED_PROVIDER_MODELS_MODE` | `fallback` | `fallback` or `allowlist` — how configured model lists affect inventory |
+| `MODEL_OVERRIDES_ENABLED` | `true` | Allow per-model overrides |
+| `KEEP_ONLY_ALIASES_AT_MODELS_ENDPOINT` | `false` | Hide provider models, show only aliases |
+| `CONFIGURED_PROVIDER_MODELS_MODE` | `fallback` | `fallback` or `allowlist` |
+</details>
 
-#### Caching
+<details>
+<summary>Caching</summary>
 
 **Model cache:**
 
@@ -475,7 +527,7 @@ All configurable environment variables, organized by subsystem:
 |---------|---------|-------------|
 | `SEMANTIC_CACHE_ENABLED` | `false` | Enable semantic cache |
 | `SEMANTIC_CACHE_THRESHOLD` | `0.92` | Similarity threshold (0-1) |
-| `SEMANTIC_CACHE_PROMPT_SIMILARITY` | `0.90` | Prompt similarity threshold (0-1) |
+| `SEMANTIC_CACHE_PROMPT_SIMILARITY` | `0.90` | Prompt similarity threshold |
 | `SEMANTIC_CACHE_TTL` | `3600` | Entry TTL (seconds) |
 | `SEMANTIC_CACHE_MAX_CONV_MESSAGES` | `3` | Recent conversation messages to embed |
 | `SEMANTIC_CACHE_EXCLUDE_SYSTEM_PROMPT` | `false` | Exclude system prompt from cache key |
@@ -495,20 +547,24 @@ All configurable environment variables, organized by subsystem:
 | `SEMANTIC_CACHE_WEAVIATE_URL` | — | Weaviate URL |
 | `SEMANTIC_CACHE_WEAVIATE_CLASS` | `AuroraSemanticCache` | Weaviate class name |
 | `SEMANTIC_CACHE_WEAVIATE_API_KEY` | — | Weaviate API key |
+</details>
 
-#### Audit Logging
+<details>
+<summary>Audit Logging</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
 | `LOGGING_ENABLED` | `false` | Enable audit log to storage |
-| `LOGGING_LOG_BODIES` | `true` | Log request/response bodies (may contain PII) |
+| `LOGGING_LOG_BODIES` | `true` | Log request/response bodies |
 | `LOGGING_LOG_HEADERS` | `true` | Log headers (sensitive headers redacted) |
 | `LOGGING_ONLY_MODEL_INTERACTIONS` | `true` | Skip health/metrics/admin endpoints |
 | `LOGGING_BUFFER_SIZE` | `1000` | In-memory queue capacity |
 | `LOGGING_FLUSH_INTERVAL` | `5` | Flush interval (seconds) |
 | `LOGGING_RETENTION_DAYS` | `30` | Auto-delete after N days (0 = forever) |
+</details>
 
-#### Usage Tracking
+<details>
+<summary>Usage Tracking</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
@@ -518,30 +574,36 @@ All configurable environment variables, organized by subsystem:
 | `USAGE_BUFFER_SIZE` | `1000` | In-memory queue capacity |
 | `USAGE_FLUSH_INTERVAL` | `5` | Flush interval (seconds) |
 | `USAGE_RETENTION_DAYS` | `90` | Auto-delete after N days (0 = forever) |
+</details>
 
-#### Guardrails
+<details>
+<summary>Guardrails</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
 | `GUARDRAILS_ENABLED` | `false` | Enable content safety filters globally |
 | `ENABLE_GUARDRAILS_FOR_BATCH_PROCESSING` | `false` | Apply guardrails to `/v1/batches` items |
+</details>
 
-#### Metrics
+<details>
+<summary>Metrics</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
 | `METRICS_ENABLED` | `false` | Enable Prometheus `/metrics` endpoint |
 | `METRICS_ENDPOINT` | `/metrics` | Metrics endpoint path |
+</details>
 
-#### Token Saver (output compression)
+<details>
+<summary>Token Saver</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
-| `TOKEN_SAVER_ENABLED` | `false` | Enable caveman-style output compression |
+| `TOKEN_SAVER_ENABLED` | `false` | Enable output compression |
 | `TOKEN_SAVER_ENDPOINTS` | `chat_completions` | Endpoints to apply it to |
 | `TOKEN_SAVER_APPLY_STREAMING` | `true` | Apply to streaming responses |
 | `TOKEN_SAVER_OUTPUT_ENABLED` | `false` | Enable output style/profile |
-| `TOKEN_SAVER_OUTPUT_PROFILE` | `concise` | Output profile name |
+| `TOKEN_SAVER_OUTPUT_PROFILE` | `concise` | Profile: `concise`, `caveman`, `ultra`, `wenyan` |
 | `TOKEN_SAVER_MODELS_INCLUDE` | — | Models to include (comma-separated) |
 | `TOKEN_SAVER_MODELS_EXCLUDE` | — | Models to exclude |
 | `TOKEN_SAVER_PROVIDERS_INCLUDE` | — | Providers to include |
@@ -549,8 +611,10 @@ All configurable environment variables, organized by subsystem:
 | `TOKEN_SAVER_ON_ERROR` | `allow` | Behavior on error: `allow` or `block` |
 | `TOKEN_SAVER_EMIT_HEADERS` | `true` | Emit token-saver headers in response |
 | `TOKEN_SAVER_AUDIT_ENABLED` | `true` | Log token-saver actions |
+</details>
 
-#### Resilience (retry + circuit breaker)
+<details>
+<summary>Resilience</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
@@ -562,15 +626,19 @@ All configurable environment variables, organized by subsystem:
 | `CIRCUIT_BREAKER_FAILURE_THRESHOLD` | `5` | Failures before circuit opens |
 | `CIRCUIT_BREAKER_SUCCESS_THRESHOLD` | `2` | Successes before circuit closes |
 | `CIRCUIT_BREAKER_TIMEOUT` | `30s` | Time before half-open retry |
+</details>
 
-#### Fallback
+<details>
+<summary>Fallback</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
 | `FEATURE_FALLBACK_MODE` | `manual` | Fallback mode: `auto`, `manual`, or `off` |
 | `FALLBACK_MANUAL_RULES_PATH` | — | Path to manual fallback rules JSON |
+</details>
 
-#### Admin & Features
+<details>
+<summary>Admin & Features</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
@@ -581,31 +649,34 @@ All configurable environment variables, organized by subsystem:
 | `CLI_TOOLS_APPLY_ENABLED` | `false` | Allow admin/API to apply tool changes |
 | `WORKFLOW_REFRESH_INTERVAL` | `1m` | Workflow refresh interval from storage |
 | `EDITION` | — | Edition identifier (Enterprise use) |
+</details>
 
-#### Config file path
+<details>
+<summary>Config file path</summary>
 
 | Env var | Default | Description |
 |---------|---------|-------------|
 | `AURORA_CONFIG_PATH` | `configs/config.yaml` | Override path to config YAML |
+</details>
 
 ---
 
 ## CLI Reference
 
-The `aurora` CLI is installed via `npm install -g iaurora`.
+Installed via `npm install -g iaurora`.
 
 | Command | Description |
 |---------|-------------|
-| `aurora init` | Scaffolds `config.yaml`, `.env`, `data/` in the current directory |
-| `aurora` | Starts the gateway server (default port 8080) |
-| `aurora --help` | Show all CLI options |
-
-`aurora init` generates:
-- **`config.yaml`** — Full gateway configuration with inline docs for every section
-- **`.env`** — Environment file for secrets and runtime overrides (based on `.env.template`)
-- **`data/`** — Directory for SQLite database and local model cache
-
-The gateway merges `config.yaml` + `.env`/env vars at startup. Use `config.yaml` for structure and `.env` for secrets/keys.
+| `aurora` | Start the gateway server (default port 8080) |
+| `aurora init` | Scaffold `config.yaml`, `.env`, `data/` in current directory |
+| `aurora update` | Self-update via `npm install -g iaurora@latest` |
+| `aurora uninstall` | Remove via `npm uninstall -g iaurora` |
+| `aurora models sync` | Download upstream model registry to local file |
+| `aurora models diff` | Show pricing diff between upstream and local snapshot |
+| `aurora models show` | Print effective pricing for a model after merging overrides |
+| `aurora -version` | Print version information |
+| `aurora -help` | Show all CLI options and config reference |
+| `aurora -help-json` | Dump env var schema as JSON |
 
 ---
 
@@ -613,33 +684,47 @@ The gateway merges `config.yaml` + `.env`/env vars at startup. Use `config.yaml`
 
 ```text
 aurora/
-├── apps/                  # Application entrypoints
-│   └── aurora/            # Main gateway binary
-├── internal/              # Internal packages
-│   ├── api/               # HTTP handlers, middleware
-│   ├── config/            # Configuration loading and validation
-│   ├── providers/         # Provider implementations (OpenAI, Anthropic, etc.)
-│   ├── storage/           # SQLite, PostgreSQL, MongoDB backends
-│   ├── guardrails/        # Content safety filters
-│   ├── cache/             # Exact and semantic caching
-│   └── analytics/         # Usage tracking and metrics
-├── dashboard-ui/          # React admin dashboard frontend
-├── configs/               # Configuration profiles and examples
-├── docs/                  # Documentation and assets
-├── scripts/               # Build and release scripts
-├── test/                  # Test suites
-└── helm/                  # Kubernetes Helm charts
+├── apps/              # Application entrypoints
+├── internal/          # Core packages (providers, gateway, storage, guardrails, etc.)
+├── dashboard-ui/      # React admin dashboard (Vite)
+├── configs/           # Configuration profiles and examples
+├── docs-assets/       # Images, models.json, assets
+├── helm/              # Kubernetes Helm charts
+├── monitoring/        # Prometheus + Grafana configs
+├── npm/               # npm CLI wrapper
+├── bench-results/     # Benchmark data
+├── release/           # Release scripts
+└── scripts/           # Build and utility scripts
 ```
 
 ---
 
+## Enterprise Deployments
+
+Aurora supports enterprise-grade deployments for teams running production AI systems at scale.
+In addition to private networking, custom security controls, and governance, **Aurora Enterprise** unlocks advanced capabilities including SSO, RBAC, tenant isolation, budget enforcement, compliance workflows, and production support.
+
+The Enterprise edition is a separate distribution with a signed license.
+
+<a href="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/comparison.png">
+  <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/comparison.png" alt="OSS vs Enterprise comparison" width="100%" style="border-radius:12px;margin:16px 0;">
+</a>
+
+<div align="center">
+  <a href="mailto:team.auroragate@gmail.com?subject=Aurora%20Enterprise%20Inquiry" style="display:block;margin-top:5px;">
+    <img src="https://img.shields.io/badge/Email%20Us-Enterprise-5865F2?style=for-the-badge&logo=gmail&logoColor=white" alt="Email Aurora Enterprise" width="200"/>
+  </a>
+</div>
+
+---
+
 ## Documentation
 
-- [Website](https://aurorallm.online/)
-- [CLI Reference](https://github.com/aurorallm/aurora)
-- [Provider Configuration](https://github.com/aurorallm/aurora)
-- [Admin Dashboard](https://github.com/aurorallm/aurora)
-- [Docker Compose & Helm](https://github.com/aurorallm/aurora)
+- [aurorallm.online/docs](https://aurorallm.online/docs) — full documentation
+- [aurorallm.online/docs/getting-started/quickstart](https://aurorallm.online/docs/getting-started/quickstart) — quickstart guide
+- [aurorallm.online/docs/guides](https://aurorallm.online/docs/guides) — provider and integration guides
+- [aurorallm.online/docs/api/overview](https://aurorallm.online/docs/api/overview) — API reference
+- [aurorallm.online/benchmarks](https://aurorallm.online/benchmarks) — performance benchmarks
 
 ---
 
@@ -664,4 +749,4 @@ We welcome contributions of all kinds! Check out the repository to get started:
 
 This project is licensed under the Apache 2.0 License — see the [LICENSE](LICENSE) file for details.
 
-Built with ❤️ by the Aurora team.
+Built by the Aurora team.

package/package.json

@@ -1,5 +1,5 @@
 {
-    "version":  "1.0.31",
+    "version":  "1.0.32",
     "author":  "Aurora Gateway",
     "license":  "Apache-2.0",
     "files":  [