ghc-proxy 0.10.0 → 0.10.2

package/README.md

@@ -2,39 +2,51 @@
 
 [![npm](https://img.shields.io/npm/v/ghc-proxy)](https://www.npmjs.com/package/ghc-proxy)
 [![CI](https://github.com/wxxb789/ghc-proxy/actions/workflows/ci.yml/badge.svg)](https://github.com/wxxb789/ghc-proxy/actions/workflows/ci.yml)
-[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://github.com/wxxb789/ghc-proxy/blob/master/LICENSE)
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://github.com/wxxb789/ghc-proxy/blob/main/LICENSE)
 
 A proxy that turns your GitHub Copilot subscription into an OpenAI and Anthropic compatible API. Use it to power [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview), [Cursor](https://www.cursor.com/), or any tool that speaks the OpenAI Chat Completions, OpenAI Responses, or Anthropic Messages protocol.
 
 > [!WARNING]
 > Reverse-engineered, unofficial, may break at any time. Excessive use can trigger GitHub abuse detection. **Use at your own risk.**
 
-**TL;DR** — Install [Bun](https://bun.com/docs/installation), then run:
-
-```bash
-bunx ghc-proxy@latest start
-```
+**TL;DR** — Choose either supported runtime:
+
+```bash
+# Bun >= 1.4
+bunx --bun ghc-proxy@latest start
+
+# Node.js >= 24
+npx ghc-proxy@latest start
+```
 
 ## Prerequisites
 
 Before you start, make sure you have:
 
-1. **Bun** (>= 1.3) -- a fast JavaScript runtime used to run the proxy
-   - **Windows:** `winget install --id Oven-sh.Bun`
-   - **Other platforms:** see the [official installation guide](https://bun.com/docs/installation)
-2. **A GitHub Copilot subscription** -- individual, business, or enterprise
+1. **One supported JavaScript runtime:**
+   - **Bun >= 1.4:** `winget install --id Oven-sh.Bun` on Windows, or see the [official installation guide](https://bun.com/docs/installation)
+   - **Node.js >= 24:** install the latest LTS release from the [official Node.js download page](https://nodejs.org/en/download)
+2. **A GitHub Copilot subscription** -- individual, business, or enterprise
 
 ## Quick Start
 
-1. Start the proxy:
-
-       bunx ghc-proxy@latest start
+1. Start the proxy with your chosen runtime:
+
+   ```bash
+   # Bun
+   bunx --bun ghc-proxy@latest start
+
+   # Node.js
+   npx ghc-proxy@latest start
+   ```
 
 2. On the first run, you will be guided through GitHub's device-code authentication flow. Follow the prompts to authorize the proxy.
 
 3. Once authenticated, the proxy starts on **`http://localhost:4141`** and is ready to accept requests.
 
-That's it. Any tool that supports the OpenAI or Anthropic API can now point to `http://localhost:4141`.
+That's it. Any tool that supports the OpenAI or Anthropic API can now point to `http://localhost:4141`.
+
+The examples below use `bunx --bun`. If you chose Node.js, replace `bunx --bun` with `npx`; the published CLI and commands are the same.
 
 > **Tip:** If you set `--rate-limit`, add `--wait` to queue requests instead of rejecting them with 429 when the cooldown has not elapsed yet. See [Rate Limiting](#rate-limiting) for details.
 
@@ -45,7 +57,7 @@ This is the most common use case. There are two ways to set it up:
 ### Option A: One-command launch
 
 ```bash
-bunx ghc-proxy@latest start --claude-code
+bunx --bun ghc-proxy@latest start --claude-code
 ```
 
 This starts the proxy, opens an interactive model picker, and prints a ready-to-paste environment command. Run that command in another terminal to launch Claude Code with the correct configuration.
@@ -73,7 +85,7 @@ Create or edit `~/.claude/settings.json` (this applies globally to all projects)
 Then simply start the proxy and use Claude Code as usual:
 
 ```bash
-bunx ghc-proxy@latest start
+bunx --bun ghc-proxy@latest start
 ```
 
 **What each environment variable does:**
@@ -96,24 +108,24 @@ See the [Claude Code settings docs](https://docs.anthropic.com/en/docs/claude-co
 ghc-proxy uses a subcommand structure:
 
 ```bash
-bunx ghc-proxy@latest start          # Start the proxy server
-bunx ghc-proxy@latest auth           # Run GitHub auth flow without starting the server
-bunx ghc-proxy@latest check-usage    # Show your Copilot usage/quota in the terminal
-bunx ghc-proxy@latest debug          # Print diagnostic info (version, paths, token status)
-bunx ghc-proxy@latest selfcheck      # Probe tokenizer chunks and Bun/Node runtime contracts in the packaged bundle
+bunx --bun ghc-proxy@latest start          # Start the proxy server
+bunx --bun ghc-proxy@latest auth           # Run GitHub auth flow without starting the server
+bunx --bun ghc-proxy@latest check-usage    # Show your Copilot usage/quota in the terminal
+bunx --bun ghc-proxy@latest debug          # Print diagnostic info (version, paths, token status)
+bunx --bun ghc-proxy@latest selfcheck      # Probe tokenizer chunks and Bun/Node runtime contracts in the packaged bundle
 ```
 
 ### `start` Options
 
 | Option | Alias | Default | Description |
 |--------|-------|---------|-------------|
-| `--port` | `-p` | `4141` | Port to listen on |
+| `--port` | `-p` | `4141` | Port to listen on (`1..65535`; malformed or zero values fail before startup) |
 | `--verbose` | `-v` | `false` | Enable verbose logging |
 | `--account-type` | `-a` | `individual` | `individual`, `business`, or `enterprise` |
 | `--rate-limit` | `-r` | -- | Minimum seconds between requests |
 | `--wait` | `-w` | `false` | Queue requests instead of rejecting with 429 when `--rate-limit` cooldown has not elapsed (requires `--rate-limit`) |
 | `--manual` | -- | `false` | Manually approve each request |
-| `--github-token` | `-g` | -- | Pass a GitHub token directly (from `auth`) |
+| `--github-token` | `-g` | -- | Use a GitHub token for this process only (normally obtained with `auth`); this flag does not persist it to `config.json` |
 | `--claude-code` | `-c` | `false` | Generate a Claude Code launch command |
 | `--show-token` | -- | `false` | Display tokens on auth and refresh |
 | `--dump-failed-payloads` | `-D` | `false` | Dump failed `/responses` payloads on upstream 400 errors for debugging. Can also be enabled with `DUMP_FAILED_PAYLOADS=1`. |
@@ -133,13 +145,13 @@ If you want to throttle how often the proxy forwards requests:
 
 ```bash
 # Enforce a 30-second cooldown between requests
-bunx ghc-proxy@latest start --rate-limit 30
+bunx --bun ghc-proxy@latest start --rate-limit 30
 
 # Same, but queue requests instead of returning 429
-bunx ghc-proxy@latest start --rate-limit 30 --wait
+bunx --bun ghc-proxy@latest start --rate-limit 30 --wait
 
 # Manually approve every request (useful for debugging)
-bunx ghc-proxy@latest start --manual
+bunx --bun ghc-proxy@latest start --manual
 ```
 
 `--wait` only takes effect when `--rate-limit` is also set. Without `--rate-limit`, there is no cooldown to wait on and `--wait` has no effect.
@@ -149,8 +161,8 @@ bunx ghc-proxy@latest start --manual
 If you have a GitHub Business or Enterprise Copilot plan, pass `--account-type`:
 
 ```bash
-bunx ghc-proxy@latest start --account-type business
-bunx ghc-proxy@latest start --account-type enterprise
+bunx --bun ghc-proxy@latest start --account-type business
+bunx --bun ghc-proxy@latest start --account-type enterprise
 ```
 
 This routes requests to the correct Copilot API endpoint for your plan. See the [GitHub docs on network routing](https://docs.github.com/en/enterprise-cloud@latest/copilot/managing-copilot/managing-github-copilot-in-your-organization/managing-access-to-github-copilot-in-your-organization/managing-github-copilot-access-to-your-organizations-network#configuring-copilot-subscription-based-network-routing-for-your-enterprise-or-organization) for details.
@@ -160,17 +172,17 @@ This routes requests to the correct Copilot API endpoint for your plan. See the
 If your organization uses GitHub Enterprise Cloud (`*.ghe.com`), the standard GitHub device login URL differs from `github.com`. Pass your company's GHE domain on first auth:
 
 ```bash
-bunx ghc-proxy@latest start --account-type enterprise --ghe-domain company.ghe.com
+bunx --bun ghc-proxy@latest start --account-type enterprise --ghe-domain company.ghe.com
 ```
 
 Or authenticate first, then start without the flag on subsequent runs:
 
 ```bash
 # First run (authenticates and persists the domain)
-bunx ghc-proxy@latest auth --ghe-domain company.ghe.com
+bunx --bun ghc-proxy@latest auth --ghe-domain company.ghe.com
 
 # Later runs (domain is read from persisted config)
-bunx ghc-proxy@latest start --account-type enterprise
+bunx --bun ghc-proxy@latest start --account-type enterprise
 ```
 
 The proxy normalizes and persists the GHE domain automatically after a successful authentication, so you only need to pass `--ghe-domain` on the first run or when switching tenants.
@@ -189,30 +201,31 @@ All fields are optional. The full schema:
 
 | Field | Type | Default | Description |
 |-------|------|---------|-------------|
-| `githubToken` | `string` | -- | Persisted GitHub token. Normally written automatically by `auth` / `--github-token`; you rarely set this by hand |
-| `modelRewrites` | `{ from, to }[]` | -- | Glob-pattern model substitution rules (see [Model Rewrites](#model-rewrites)) |
-| `modelFallback` | `object` | -- | Override default model fallbacks (see [Customizing Fallbacks](#customizing-fallbacks)) |
+| `githubToken` | `string` | unset | Persisted GitHub token. The device-code flow (`auth` or first startup) writes it automatically; `start --github-token` is runtime-only and does not write this field |
+| `modelRewrites` | `{ from, to }[]` | `[]` | Glob-pattern model substitution rules (see [Model Rewrites](#model-rewrites)) |
+| `modelFallback` | `object` | built-in family defaults | Override default model fallbacks (see [Customizing Fallbacks](#customizing-fallbacks)) |
 | `modelFallback.claudeOpus` | `string` | `claude-opus-5` | Fallback for `claude-opus-*` models |
 | `modelFallback.claudeSonnet` | `string` | `claude-sonnet-5` | Fallback for `claude-sonnet-*` models |
 | `modelFallback.claudeHaiku` | `string` | `claude-haiku-4.5` | Fallback for `claude-haiku-*` models |
-| `smallModel` | `string` | -- | Target model for compact request routing (see [Small-Model Routing](#small-model-routing)) |
+| `smallModel` | `string` | unset | Target model for compact request routing (see [Small-Model Routing](#small-model-routing)) |
 | `compactUseSmallModel` | `boolean` | `false` | Route compact/summarization requests to `smallModel` |
 | `useFunctionApplyPatch` | `boolean` | `true` | Rewrite `apply_patch` custom tool as function tool on Responses path |
 | `responsesApiAutoCompactInput` | `boolean` | `false` | Automatically trim Responses `input` to the latest `compaction` item |
 | `responsesApiAutoContextManagement` | `boolean` | `false` | Automatically inject Responses `context_management` for selected models |
-| `responsesApiContextManagementModels` | `string[]` | -- | Models eligible for auto-injected Responses `context_management` |
-| `responsesApiParameterFilters` | `{ models, params }[]` | -- | Extra rules to strip request parameters on the Responses boundary (see [Responses Parameter Filters](#responses-parameter-filters)) |
-| `responsesApiParameterFiltersReplaceDefault` | `boolean` | `false` | Disable the built-in reasoning-model default rule so only your `responsesApiParameterFilters` apply |
-| `responsesOfficialEmulator` | `boolean` | `false` | Enable local OpenAI-style Responses state emulation for `previous_response_id`, `conversation`, retrieve, input_items, delete, and input_tokens |
-| `responsesOfficialEmulatorTtlSeconds` | `number` | `14400` | In-memory TTL for locally emulated Responses state |
-| `modelReasoningEfforts` | `Record<string, string>` | -- | Per-model reasoning effort defaults for Anthropic-to-Responses translation. Each value must be one of `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, or `max` (ascending) |
+| `responsesApiContextManagementModels` | `string[]` | `[]` | Models eligible for auto-injected Responses `context_management` |
+| `responsesApiParameterFilters` | `{ models, params }[]` | `[]` | Extra rules to strip request parameters on the Responses boundary; the built-in reasoning-model rule remains active unless replaced (see [Responses Parameter Filters](#responses-parameter-filters)) |
+| `responsesApiParameterFiltersReplaceDefault` | `boolean` | `false` | Disable the built-in reasoning-model default rule so only your `responsesApiParameterFilters` apply |
+| `chatCompletionsUseMaxCompletionTokens` | `string[]` | `[]` | Extra model globs that rename Chat Completions `max_tokens` to `max_completion_tokens`; adds to the built-in `gpt-5.4` / `gpt-5.4-*` rules |
+| `responsesOfficialEmulator` | `boolean` | `false` | Enable local OpenAI-style Responses state emulation for `previous_response_id`, `conversation`, retrieve, input_items, delete, and input_tokens |
+| `responsesOfficialEmulatorTtlSeconds` | `number` | `14400` | In-memory TTL for locally emulated Responses state |
+| `modelReasoningEfforts` | `Record<string, string>` | `{}`; unlisted models use `high` | Per-model reasoning effort defaults for Anthropic-to-Responses translation. Each value must be one of `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, or `max` (ascending) |
 | `upstreamQueueConcurrency` | `number` | `10` | Maximum concurrent Copilot upstream requests |
 | `upstreamQueueMaxRetries` | `number` | `1` | Maximum retries across capacity and approved pre-connection failures (`0..2`) |
 | `upstreamRecoveryBudgetSeconds` | `number` | `60` | Shared recovery deadline after the first retryable outcome or active-cooldown encounter (`1..120` seconds) |
-| `overloadFallbacks` | `Record<string, string>` | -- | Exact effective-model mappings for one opt-in fallback dispatch after terminal model `529`; absent means disabled |
+| `overloadFallbacks` | `Record<string, string>` | `{}` (disabled) | Exact effective-model mappings for one opt-in fallback dispatch after terminal model `529` |
 | `upstreamQueueBaseDelaySeconds` | `number` | `2` | Base delay (seconds) for upstream retry backoff when `Retry-After` is absent |
 | `upstreamQueueMaxDelaySeconds` | `number` | `60` | Maximum computed backoff (seconds); does not clamp `Retry-After` |
-| `gheDomain` | `string` | -- | GitHub Enterprise Cloud company domain (persisted automatically after GHE.com auth) |
+| `gheDomain` | `string` | unset | GitHub Enterprise Cloud company domain (persisted automatically after GHE.com auth) |
 
 Example:
 
@@ -229,9 +242,10 @@ Example:
   "compactUseSmallModel": true,
   "useFunctionApplyPatch": true,
   "responsesApiAutoCompactInput": false,
-  "responsesApiAutoContextManagement": false,
-  "responsesApiContextManagementModels": ["gpt-5", "gpt-5-mini"],
-  "responsesOfficialEmulator": false,
+  "responsesApiAutoContextManagement": false,
+  "responsesApiContextManagementModels": ["gpt-5", "gpt-5-mini"],
+  "chatCompletionsUseMaxCompletionTokens": [],
+  "responsesOfficialEmulator": false,
   "responsesOfficialEmulatorTtlSeconds": 14400,
   "modelReasoningEfforts": {
     "gpt-5": "high",
@@ -359,9 +373,11 @@ The proxy authenticates with GitHub using the [device code OAuth flow](https://d
 
 When the Copilot token response includes `endpoints.api`, `ghc-proxy` now prefers that runtime API base automatically instead of relying only on the configured account type. This keeps enterprise/business routing aligned with the endpoint GitHub actually returned for the current token.
 
-Incoming requests hit an [Elysia](https://elysiajs.com/) server. `chat/completions` requests are validated, normalized into the shared planning pipeline, and then forwarded to Copilot. `responses` requests use a native Responses path with explicit compatibility policies. `messages` requests are routed per-model and can use native Anthropic passthrough, the Responses translation path, or the existing chat-completions fallback. The translator tracks exact vs lossy vs unsupported behavior explicitly; see the [Messages Routing and Translation Guide](./docs/messages-routing-and-translation.md) and the [Anthropic Translation Matrix](./docs/anthropic-translation-matrix.md) for the current support surface.
-
-For Anthropic `search_result` blocks, current live probes show Copilot native `/v1/messages` accepts top-level search results and pure search-result tool outputs, but rejects top-level `citations` and mixed text/search-result tool output arrays. The native path sanitizes those known rejection cases, while translated paths flatten search results to text.
+Incoming requests hit an [Elysia](https://elysiajs.com/) server. `chat/completions` requests are validated, normalized into the shared planning pipeline, and then forwarded to Copilot. `responses` requests use a native Responses path with explicit compatibility policies. `messages` requests are routed per-model and can use native Anthropic passthrough, the Responses translation path, or the existing chat-completions fallback. The translator tracks exact vs lossy vs unsupported behavior explicitly; see the [Messages Routing and Translation Guide](./docs/messages-routing-and-translation.md) and the [Anthropic Translation Matrix](./docs/anthropic-translation-matrix.md) for the current support surface.
+
+The built-in, read-only Dashboard projects process health, model routing, behavior, and recent request lifecycle metadata without storing request or response content. See [Dashboard Observability](./docs/design/dashboard-observability.md).
+
+For Anthropic `search_result` blocks, an April 17, 2026 probe against `claude-opus-4.6` on Copilot native `/v1/messages` accepted top-level search results and pure search-result tool outputs, but rejected top-level `citations` and mixed text/search-result tool output arrays. The native path sanitizes those observed rejection cases, while translated paths flatten search results to text; re-run the probe before treating that dated upstream result as universal.
 
 ### Request Routing
 
@@ -402,22 +418,37 @@ This keeps the existing chat pipeline stable while allowing newer Copilot models
 | `POST` | `/v1/messages` | Messages API with per-model routing across native Messages, Responses translation, or chat-completions fallback |
 | `POST` | `/v1/messages/count_tokens` | Token counting |
 
-**Utility:**
+**Utility:**
 
 | Method | Path | Description |
 |--------|------|-------------|
 | `GET`  | `/health` | Liveness/readiness probe — returns `{ status, copilotToken, modelsLoaded, version }` |
 | `GET`  | `/usage` | Copilot quota / usage monitoring |
-| `GET`  | `/token` | Inspect the current Copilot token |
-
-> **Note:** The `/v1/` prefix is optional for OpenAI-compatible endpoints (`/chat/completions`, `/responses`, `/models`, `/embeddings`). Anthropic endpoints (`/v1/messages`, `/v1/messages/count_tokens`) require the `/v1` prefix. The utility endpoints (`/health`, `/usage`, `/token`) are root-only and not exposed under `/v1`.
+| `GET`  | `/token` | Inspect the current Copilot token |
+
+**Local Dashboard (read-only):**
+
+| Method | Path | Description |
+|--------|------|-------------|
+| `GET` | `/dashboard` | Dashboard application |
+| `GET` | `/dashboard/styles.css` | Dashboard stylesheet |
+| `GET` | `/dashboard/app.js` | Dashboard client script |
+| `GET` | `/dashboard/api/overview` | Process, authentication, quota, request, and queue summary |
+| `GET` | `/dashboard/api/models` | Upstream model metadata and effective proxy capabilities |
+| `GET` | `/dashboard/api/behavior` | Active routing, compatibility policies, strategies, and effect counters |
+| `GET` | `/dashboard/api/requests` | Active requests and the most recent 256 completed request summaries |
+
+Dashboard routes are restricted to local access and return `403` when the peer, request host, or supplied `Origin` fails the loopback/same-origin checks. They are excluded from request history and access logging. See [Dashboard Observability](./docs/design/dashboard-observability.md) for the projection and security contract.
+
+> **Note:** The `/v1/` prefix is optional for OpenAI-compatible endpoints (`/chat/completions`, `/responses` and its resource routes, `/models`, `/embeddings`). Anthropic endpoints (`/v1/messages`, `/v1/messages/count_tokens`) require the `/v1` prefix. The utility and Dashboard endpoints are root-only and not exposed under `/v1`.
 
 ## Responses Compatibility
 
 `/v1/responses` is designed to stay close to the OpenAI wire format while making Copilot limitations explicit:
 
-- requests are validated before any mutation
-- common official request fields such as `conversation`, `previous_response_id`, `max_tool_calls`, `truncation`, `user`, `prompt`, and `text` are now modeled explicitly instead of relying on loose passthrough alone
+- requests are validated before any mutation
+- client-supplied `top_k` is rejected with `400` on the OpenAI Chat Completions and Responses boundaries because neither official OpenAI schema defines it; clients that send it by mistake receive an explicit error instead of a silent drop. Anthropic Messages `top_k` remains supported and is preserved when the proxy translates that request internally for Copilot
+- common official request fields such as `conversation`, `previous_response_id`, `max_tool_calls`, `truncation`, `user`, `prompt`, and `text` are now modeled explicitly instead of relying on loose passthrough alone
 - official `text.format` options are modeled explicitly, including `text`, `json_object`, and `json_schema`
 - an opt-in `responsesOfficialEmulator` mode adds in-memory OpenAI-style state for `previous_response_id`, `conversation`, `GET /responses/{id}`, `GET /responses/{id}/input_items`, `DELETE /responses/{id}`, and `POST /responses/input_tokens`
 - emulator state is memory-only and expires after `responsesOfficialEmulatorTtlSeconds` (default `14400`, or 4 hours)
@@ -427,9 +458,9 @@ This keeps the existing chat pipeline stable while allowing newer Copilot models
 - automatic trimming of Responses `input` to the latest `compaction` item is disabled by default and only applies when `responsesApiAutoCompactInput` is `true`
 - reasoning defaults for Anthropic -> Responses translation can be tuned with `modelReasoningEfforts`
 - request parameters that a model rejects (e.g. `temperature`/`top_p` on reasoning models) are stripped on the Responses boundary rather than leaked upstream as a `400`; see [Responses Parameter Filters](#responses-parameter-filters)
-- built-in web search (`web_search`, `web_search_preview`, and their dated variants) is forwarded to Copilot rather than blocked; every `/responses` model probed accepts it and runs a real search, see [docs/research/responses-web-search.md](docs/research/responses-web-search.md)
-- external image URLs on the Responses path fail explicitly with `400`; use `file_id` or data URL image input instead
-- official `input_file` and `item_reference` input items are modeled explicitly and validated before forwarding
+- built-in web search (`web_search`, `web_search_preview`, and their dated variants) is forwarded to Copilot rather than blocked; every `/responses` model reached by the August 4, 2026 acceptance sweep accepted the tool, while functional search execution was verified on `gpt-5.6-sol` and `gpt-5.6-terra`, see [docs/research/responses-web-search.md](docs/research/responses-web-search.md)
+- external image URLs on the Responses path fail explicitly with `400`; use `file_id` or data URL image input instead
+- official `input_file` and `item_reference` input items are modeled explicitly and validated, but the verified Copilot GPT Responses boundary is stateless: it rejects `store: true` and cannot resolve returned item IDs on later requests. The proxy deliberately applies a proxy-wide `store: false` policy, removes all `item_reference` items before dispatch, and removes `function_call_output` items whose `call_id` has no matching `function_call` in the same input array. Without the optional emulator, a caller that requested storage still receives a successful stateless response; retrieve/delete/continuation semantics are available only from the local emulator
 
 Example opt-in configuration for these two Responses-specific policies:
 
@@ -451,7 +482,7 @@ Some Copilot models reject request parameters that the OpenAI wire format allows
 
 This is expressed as a small rule engine that runs on both the native `/v1/responses` path and the `/v1/messages` → Responses translation path:
 
-- **Built-in default rule:** any model that advertises `reasoning_effort` has `temperature` and `top_p` stripped. This covers the whole reasoning family (including future point releases like `gpt-5.4-mini`) with no configuration.
+- **Built-in default rule:** any model that advertises `reasoning_effort` has `temperature` stripped. It also has `top_p` stripped except for `*-codex` / `*-codex-*` models, which are exempt because the July 26, 2026 probe found the tested Codex model accepted `top_p` while its reasoning-model siblings rejected it. This exemption narrows only the built-in rule; an operator rule can still strip `top_p`.
 - **`responsesApiParameterFilters`:** add your own rules. Each rule is `{ "models": [glob, ...], "params": [name, ...] }`; every rule whose `models` glob matches the resolved model contributes its `params`. Rules are **added** to the default (the union of parameters is stripped). Model globs use the same `*` wildcard as `modelRewrites`.
 - **`responsesApiParameterFiltersReplaceDefault`:** set to `true` to disable the built-in reasoning-model rule, so only your `responsesApiParameterFilters` apply — use this to fully **overwrite** the default behavior.
 
@@ -461,7 +492,7 @@ Stripped parameters are removed entirely (never sent as `null`), because upstrea
 {
   "responsesApiParameterFilters": [
     { "models": ["gpt-5*", "o1*"], "params": ["temperature", "top_p"] },
-    { "models": ["some-model"], "params": ["top_k"] }
+    { "models": ["some-model"], "params": ["service_tier"] }
   ],
   "responsesApiParameterFiltersReplaceDefault": false
 }
@@ -469,63 +500,91 @@ Stripped parameters are removed entirely (never sent as `null`), because upstrea
 
 ## Docker
 
-Pre-built images are available on GHCR:
-
-```bash
-docker pull ghcr.io/wxxb789/ghc-proxy
-docker run -p 4141:4141 ghcr.io/wxxb789/ghc-proxy
-```
-
-Or build locally:
-
-```bash
-docker build -t ghc-proxy .
-mkdir -p ./copilot-data
-docker run -p 4141:4141 -v $(pwd)/copilot-data:/root/.local/share/ghc-proxy ghc-proxy
-```
-
-Authentication and settings are persisted in `copilot-data/config.json` so they survive container restarts.
-
-You can also pass a GitHub token via environment variable. The container [entrypoint](entrypoint.sh) forwards `GH_TOKEN` to `start --github-token`, so this is Docker-specific — the proxy binary itself does not read `GH_TOKEN` from the environment (outside Docker, use the `--github-token` flag or a persisted `config.json`):
-
-```bash
-docker run -p 4141:4141 -e GH_TOKEN=your_token ghcr.io/wxxb789/ghc-proxy
-```
-
-To run the one-time device-code auth flow inside the container instead (writes the token into the mounted data volume):
-
-```bash
-docker run -it -v $(pwd)/copilot-data:/root/.local/share/ghc-proxy ghc-proxy --auth
-```
-
-Docker Compose:
+Pre-built images are available on GHCR:
+
+```bash
+docker pull ghcr.io/wxxb789/ghc-proxy
+docker volume create ghc-proxy-data
+docker run --rm -p 127.0.0.1:4141:4141 \
+  -v ghc-proxy-data:/home/bun/.local/share/ghc-proxy \
+  ghcr.io/wxxb789/ghc-proxy
+```
+
+Or build locally:
+
+```bash
+docker build -t ghc-proxy .
+docker volume create ghc-proxy-data
+docker run --rm -p 127.0.0.1:4141:4141 \
+  -v ghc-proxy-data:/home/bun/.local/share/ghc-proxy \
+  ghc-proxy
+```
+
+Authentication and settings are persisted in the `ghc-proxy-data` volume so they survive container restarts. The proxy does not provide API authentication. Keep the port bound to loopback as shown; any non-loopback deployment needs an authenticated TLS reverse proxy or a firewall that restricts access.
+
+Run the device-code authentication flow once against the same volume:
+
+```bash
+docker run --rm -it \
+  -v ghc-proxy-data:/home/bun/.local/share/ghc-proxy \
+  ghcr.io/wxxb789/ghc-proxy auth
+```
+
+The legacy `--auth` container argument remains supported, but `auth` is the standard CLI subcommand:
+
+```bash
+docker run --rm -it \
+  -v ghc-proxy-data:/home/bun/.local/share/ghc-proxy \
+  ghcr.io/wxxb789/ghc-proxy --auth
+```
+
+You can also pass a GitHub token via `GH_TOKEN`. The container [entrypoint](entrypoint.sh) forwards a non-empty value only when starting the proxy, as `start --github-token`:
+
+```bash
+docker run --rm -p 127.0.0.1:4141:4141 \
+  -v ghc-proxy-data:/home/bun/.local/share/ghc-proxy \
+  -e GH_TOKEN=your_token \
+  ghcr.io/wxxb789/ghc-proxy
+```
+
+Docker Compose:
 
 ```yaml
 services:
-  ghc-proxy:
-    image: ghcr.io/wxxb789/ghc-proxy
-    ports:
-      - '4141:4141'
-    environment:
-      - GH_TOKEN=your_token_here
-    restart: unless-stopped
-```
-
-## Running from Source
-
-```bash
+  ghc-proxy:
+    image: ghcr.io/wxxb789/ghc-proxy
+    ports:
+      - '127.0.0.1:4141:4141'
+    volumes:
+      - ghc-proxy-data:/home/bun/.local/share/ghc-proxy
+    environment:
+      - GH_TOKEN=your_token_here
+    restart: unless-stopped
+
+volumes:
+  ghc-proxy-data:
+```
+
+## Running from Source
+
+Repository development uses Bun >= 1.4 even if you run the published package with Node.js.
+
+```bash
 git clone https://github.com/wxxb789/ghc-proxy.git
 cd ghc-proxy
-bun install
-bun run dev
+bun install
+bun run dev              # Start with --watch
+# Or use the production-style source command:
+bun run start
 ```
 
 ## Development
 
 ```bash
-bun install              # Install dependencies
-bun run dev              # Start with --watch
-bun run build            # Build with tsdown
+bun install              # Install dependencies
+bun run dev              # Start with --watch
+bun run start            # Start without --watch
+bun run build            # Build with tsdown
 bun run lint             # ESLint
 bun run typecheck        # tsc --noEmit
 bun test                 # Run tests

package/dist/{GptEncoding-DdY2evDX.mjs → GptEncoding-DGbju5p-.mjs}

@@ -76,7 +76,7 @@ function getSpecialTokenRegex(tokens) {
 }
 //#endregion
 //#region node_modules/gpt-tokenizer/esm/BytePairEncodingCore.js
-const emptyBuffer = new Uint8Array(0);
+const emptyBuffer = /* @__PURE__ */ new Uint8Array(0);
 const decoder = new TextDecoder("utf8");
 var BytePairEncodingCore = class {
 	mergeableBytePairRankCount;
@@ -674,7 +674,7 @@ function Cl100KBase(bytePairRankDecoder) {
 	return {
 		tokenSplitRegex: CL100K_TOKEN_SPLIT_REGEX,
 		bytePairRankDecoder,
-		specialTokensEncoder: new Map([
+		specialTokensEncoder: /* @__PURE__ */ new Map([
 			[EndOfText, 100257],
 			[FimPrefix, 100258],
 			[FimMiddle, 100259],
@@ -745,7 +745,7 @@ function P50KBase(bytePairRankDecoder) {
 		expectedVocabularySize: 50281,
 		tokenSplitRegex: R50K_TOKEN_SPLIT_REGEX,
 		bytePairRankDecoder,
-		specialTokensEncoder: new Map([[EndOfText, 50256]])
+		specialTokensEncoder: /* @__PURE__ */ new Map([[EndOfText, 50256]])
 	};
 }
 //#endregion
@@ -754,7 +754,7 @@ function P50KEdit(bytePairRankDecoder) {
 	return {
 		tokenSplitRegex: R50K_TOKEN_SPLIT_REGEX,
 		bytePairRankDecoder,
-		specialTokensEncoder: new Map([
+		specialTokensEncoder: /* @__PURE__ */ new Map([
 			[EndOfText, 50256],
 			[FimPrefix, 50281],
 			[FimMiddle, 50282],
@@ -769,7 +769,7 @@ function R50KBase(bytePairRankDecoder) {
 		expectedVocabularySize: 50257,
 		tokenSplitRegex: R50K_TOKEN_SPLIT_REGEX,
 		bytePairRankDecoder,
-		specialTokensEncoder: new Map([[EndOfText, 50256]])
+		specialTokensEncoder: /* @__PURE__ */ new Map([[EndOfText, 50256]])
 	};
 }
 //#endregion
@@ -883,11 +883,13 @@ var GptEncoding = class GptEncoding {
 		}
 	}
 	static getEncodingApi(encodingName, getMergeableRanks) {
-		return new GptEncoding(getEncodingParams(encodingName, getMergeableRanks));
+		const modelParams = getEncodingParams(encodingName, getMergeableRanks);
+		return new GptEncoding(modelParams);
 	}
 	static getEncodingApiForModel(modelName, getMergeableRanks, modelSpec) {
+		const modelParams = getEncodingParams(modelToEncodingMap[modelName] ?? "o200k_base", getMergeableRanks);
 		return new GptEncoding({
-			...getEncodingParams(modelToEncodingMap[modelName] ?? "o200k_base", getMergeableRanks),
+			...modelParams,
 			modelName,
 			modelSpec
 		});
@@ -950,7 +952,7 @@ var GptEncoding = class GptEncoding {
 		const chatStartToken = this.specialTokensEncoder.get(ImStart);
 		const chatEndToken = this.specialTokensEncoder.get(ImEnd);
 		if (chatStartToken === void 0 || chatEndToken === void 0) throw new Error(`Model '${model}' does not support chat.`);
-		const allowedSpecial = new Set([ImSep]);
+		const allowedSpecial = /* @__PURE__ */ new Set([ImSep]);
 		const { messageSeparator, roleSeparator } = params;
 		const encodedMessageSeparator = messageSeparator.length > 0 ? this.encode(messageSeparator) : [];
 		const encodedRoleSeparator = roleSeparator.length > 0 ? this.encode(roleSeparator, { allowedSpecial }) : [];
@@ -1098,4 +1100,4 @@ var GptEncoding = class GptEncoding {
 //#endregion
 export { ImStart as _, FimPrefix as a, HarmonyChannel as c, HarmonyMessage as d, HarmonyReturn as f, ImSep as g, ImEnd as h, FimMiddle as i, HarmonyConstrain as l, HarmonyStartOfText as m, EndOfPrompt as n, FimSuffix as o, HarmonyStart as p, EndOfText as r, HarmonyCall as s, GptEncoding as t, HarmonyEnd as u, ALL_SPECIAL_TOKENS as v, DEFAULT_MERGE_CACHE_SIZE as y };
 
-//# sourceMappingURL=GptEncoding-DdY2evDX.mjs.map
+//# sourceMappingURL=GptEncoding-DGbju5p-.mjs.map

package/dist/{cl100k_base-ChJqEXhP.mjs → cl100k_base-CR_-ZzWY.mjs}

@@ -1,4 +1,4 @@
-import { _ as ImStart, a as FimPrefix, c as HarmonyChannel, d as HarmonyMessage, f as HarmonyReturn, g as ImSep, h as ImEnd, i as FimMiddle, l as HarmonyConstrain, m as HarmonyStartOfText, n as EndOfPrompt, o as FimSuffix, p as HarmonyStart, r as EndOfText, s as HarmonyCall, t as GptEncoding, u as HarmonyEnd, v as ALL_SPECIAL_TOKENS, y as DEFAULT_MERGE_CACHE_SIZE } from "./GptEncoding-DdY2evDX.mjs";
+import { _ as ImStart, a as FimPrefix, c as HarmonyChannel, d as HarmonyMessage, f as HarmonyReturn, g as ImSep, h as ImEnd, i as FimMiddle, l as HarmonyConstrain, m as HarmonyStartOfText, n as EndOfPrompt, o as FimSuffix, p as HarmonyStart, r as EndOfText, s as HarmonyCall, t as GptEncoding, u as HarmonyEnd, v as ALL_SPECIAL_TOKENS, y as DEFAULT_MERGE_CACHE_SIZE } from "./GptEncoding-DGbju5p-.mjs";
 //#region node_modules/gpt-tokenizer/esm/bpeRanks/cl100k_base.js
 const c0 = [
 	"!",
@@ -101368,4 +101368,4 @@ const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator,
 //#endregion
 export { ALL_SPECIAL_TOKENS, DEFAULT_MERGE_CACHE_SIZE, EndOfPrompt, EndOfText, FimMiddle, FimPrefix, FimSuffix, HarmonyCall, HarmonyChannel, HarmonyConstrain, HarmonyEnd, HarmonyMessage, HarmonyReturn, HarmonyStart, HarmonyStartOfText, ImEnd, ImSep, ImStart, clearMergeCache, countTokens, decode, decodeAsyncGenerator, decodeGenerator, api as default, encode, encodeChat, encodeChatGenerator, encodeGenerator, estimateCost, isWithinTokenLimit, setMergeCacheSize, vocabularySize };
 
-//# sourceMappingURL=cl100k_base-ChJqEXhP.mjs.map
+//# sourceMappingURL=cl100k_base-CR_-ZzWY.mjs.map