Fix model mapping to prefer the longest matching prefix

Cargo.toml

@@ -22,7 +22,7 @@ tower = { version = "0.5", features = ["util"] }
 tower-http = { version = "0.6", features = ["fs"] }
 reqwest = { version = "0.13", default-features = false, features = ["json", "rustls", "stream", "form"] }
 serde = { version = "1", features = ["derive"] }
-serde_json = "1"
+serde_json = { version = "1", features = ["preserve_order"] }
 serde_norway = "0.9"
 futures-util = "0.3"
 async-stream = "0.3"
@@ -33,5 +33,6 @@ chrono = { version = "0.4", features = ["clock"] }
 tracing = "0.1"
 tracing-subscriber = { version = "0.3", features = ["env-filter"] }
 tiktoken-rs = "0.7"
+dialoguer = { version = "0.11", default-features = false, features = ["fuzzy-select"] }
 
 [dev-dependencies]

README.md

@@ -13,15 +13,22 @@ This is a Rust backend port of the
 # Build
 cargo build --release
 
-# Run (first run starts GitHub Device Flow auth if no token is configured)
+# Run — on first launch in a terminal this opens the interactive setup wizard
 ./target/release/ghc-proxy
 
-# Generate the default config file and exit
+# Re-run the setup wizard at any time
+./target/release/ghc-proxy --setup
+
+# Generate the default config file non-interactively and exit
 ./target/release/ghc-proxy --config
 ```
 
-On first run the proxy initiates **GitHub Device Flow** authentication if no
-`GITHUB_TOKEN` environment variable is set and no saved token is found.
+On a first run with no config file, when launched from a terminal, the proxy
+opens an **interactive setup wizard** that signs you in to GitHub (Device Flow),
+fetches the live model catalog, and helps you configure model mappings. In
+headless or piped contexts the wizard is skipped: the proxy falls back to GitHub
+Device Flow auth (or a `*_TOKEN` environment variable) and a default config
+file.
 
 ## Features
 
@@ -39,18 +46,23 @@ On first run the proxy initiates **GitHub Device Flow** authentication if no
 - **Orphaned `tool_use_id` recovery** — retries with offending tool results
   stripped when the upstream returns the corresponding 400 error.
 - **Request analytics dashboard** at `/` and a request browser at `/requests`.
+- **Interactive setup wizard** (`--setup`, or first launch in a terminal):
+  GitHub sign-in, live model catalog, and model-mapping configuration.
+- **1M-context support** — forwards the `anthropic-beta: context-1m-2025-08-07`
+  header for models whose catalog advertises an extended context window.
 
 ## CLI Options
 
 ```
 ghc-proxy [options]
 
-  -s, --setup             Show the setup guide and write/update the config file
-      --claudecode        Include Claude Code setup instructions (use with --setup)
+  -s, --setup             Launch the interactive setup wizard (sign in + map models)
+      --claudecode        Configure Claude Code (~/.claude/settings.json) to use this proxy (with --setup)
   -d, --default           Reset config to defaults during setup
   -p, --port <port>       Port to listen on (default: 8314)
   -a, --address <addr>    Address to listen on (default: 127.0.0.1)
-  -c, --config            Generate default config file
+      --account-type <t>  Account tier: individual | business | enterprise
+  -c, --config            Generate the default config file (non-interactive)
   -v, --version           Show version
   -h, --help              Show help
 ```
@@ -59,14 +71,32 @@ ghc-proxy [options]
 
 A GitHub token is resolved in this order:
 
-1. `GITHUB_TOKEN` environment variable.
+1. `COPILOT_GITHUB_TOKEN`, then `GH_TOKEN`, then `GITHUB_TOKEN` environment
+   variables (matching the GitHub Copilot SDK precedence).
 2. Saved token file at `<config-dir>/github_token.txt`.
-3. Interactive GitHub Device Flow (the resulting token is saved for reuse).
+3. Interactive GitHub Device Flow (the resulting token is saved for reuse, with
+   `0600` permissions on Unix).
 
 The GitHub token is exchanged for a short-lived **Copilot token** via
 `https://api.github.com/copilot_internal/v2/token`, which is refreshed
 automatically before it expires.
 
+## Setup Wizard
+
+Running `ghc-proxy --setup` — or launching the proxy for the first time from a
+terminal with no config file — opens an interactive wizard that:
+
+1. Prompts for the **server settings** (listen address, port, account tier).
+2. Signs in to GitHub via **Device Flow** and saves the token.
+3. Fetches the **live model catalog** and lets you map the `opus` / `sonnet` /
+   `haiku` aliases to specific models (or keep the recommended defaults).
+4. Optionally configures **Claude Code** to route through the proxy.
+
+The wizard only runs when attached to a terminal, so headless and CI launches
+are unaffected (they fall back to environment/file tokens and a default config).
+Pass `--default` to start the wizard from built-in defaults, or `--claudecode`
+to include the Claude Code step automatically.
+
 ## Configuration
 
 Config file: `~/.ghc-tunnel/config.yaml` (`%APPDATA%/ghc-tunnel/config.yaml`
@@ -77,7 +107,7 @@ address: 127.0.0.1
 port: 8314
 debug: false
 account_type: individual            # individual | business | enterprise
-vscode_version: "1.115.0"
+vscode_version: "1.123.0"
 api_version: "2025-05-01"
 copilot_version: "0.44.0"
 model_mappings:
@@ -153,6 +183,7 @@ cargo clippy     # lint
 | File | Responsibility |
 |------|----------------|
 | `src/main.rs` | CLI parsing and server startup |
+| `src/setup.rs` | Interactive first-run setup wizard |
 | `src/config.rs` | Config dir, YAML config, defaults, model-mapping defaults |
 | `src/auth.rs` | GitHub token resolution (env/file/Device Flow), Copilot token exchange |
 | `src/state.rs` | Shared state, token refresh, upstream header construction |
@@ -171,19 +202,25 @@ The proxy authenticates to GitHub Copilot by impersonating the official
 identity headers that the real client sends to `api.githubcopilot.com`
 (`Editor-Version`, `Editor-Plugin-Version`, `User-Agent`,
 `Copilot-Integration-Id`, `OpenAI-Intent`, `X-Interaction-Type`,
-`X-GitHub-Api-Version`, etc.). These are built in
-`AppState::copilot_headers` / `github_headers` (`src/state.rs`) from the
+`X-GitHub-Api-Version`, `openai-organization`, plus a persisted
+`vscode-machineid` and a per-session `vscode-sessionid`, etc.). These are built
+in `AppState::copilot_headers` / `github_headers` (`src/state.rs`) from the
 version strings in `src/config.rs`.
 
+For Anthropic-native `/v1/messages` requests, the proxy also forwards the
+`anthropic-beta: context-1m-2025-08-07` header for models whose catalog
+advertises a context window larger than 200K tokens, unlocking the 1M-token
+tier the same way the official client does.
+
 GitHub may reject requests that report stale client versions, so these values
 occasionally need refreshing. The source of truth is the now open-source
 [`microsoft/vscode-copilot-chat`](https://github.com/microsoft/vscode-copilot-chat)
-repository:
+extension and the VS Code Marketplace:
 
 | Config value | Where to read it |
 |--------------|------------------|
-| `copilot_version` | `version` field in the extension's `package.json` |
-| `vscode_version` | `engines.vscode` baseline in `package.json` |
+| `copilot_version` | latest `GitHub.copilot-chat` version on the VS Code Marketplace (or the `version` field in the extension's `package.json`) |
+| `vscode_version` | latest VS Code stable release (`https://update.code.visualstudio.com/api/releases/stable`) |
 | `api_version` | `X-GitHub-Api-Version` constant in `src/platform/networking/common/networking.ts` |
 
 After updating the constants in `src/config.rs`, run the test suite (the header
@@ -195,13 +232,15 @@ example values in this README.
 This Rust port focuses on the **core proxy behavior**: authentication, token
 management, model translation, all four API surfaces with streaming, content
 filtering, retry, the CLI, and the dashboard. The following `ghc-tunnel`
-auxiliary features are intentionally **not** ported: the fully interactive
-setup wizard, OneDrive config sync, the ACP code agent, Codex config
-auto-repair, and the persistent on-disk analytics database. `--setup` prints a
-setup guide and writes/updates the config file (re-rendering it with the current
-values, applying any CLI overrides, or resetting to defaults with `--default`),
-even when a config file already exists; `--claudecode` adds Claude Code
-integration guidance. The dashboard lists all supported models alongside the
+auxiliary features are intentionally **not** ported: OneDrive config sync, the
+ACP code agent, Codex config auto-repair, and the persistent on-disk analytics
+database. `--setup` launches an interactive wizard (GitHub sign-in, live model
+catalog, model-mapping configuration) and writes/updates the config file; in
+headless or piped contexts it instead re-renders the config non-interactively,
+applying any CLI overrides or resetting to defaults with `--default`.
+`--claudecode` patches `~/.claude/settings.json`, merging
+`env.ANTHROPIC_BASE_URL` so Claude Code routes through this proxy (existing
+settings are preserved). The dashboard lists all supported models alongside the
 request statistics.
 
 ## License

src/config.rs

@@ -10,13 +10,14 @@ use std::path::PathBuf;
 /// Kept in sync with the `engines.vscode` baseline of the latest
 /// `microsoft/vscode-copilot-chat` release (see "Mimicking the Copilot client"
 /// in the README for how to refresh these values).
-pub const VSCODE_VERSION: &str = "1.115.0";
+pub const VSCODE_VERSION: &str = "1.123.0";
 /// Default GitHub Copilot API version header value (`X-GitHub-Api-Version`),
-/// matching the latest documented Copilot REST API version.
-pub const API_VERSION: &str = "2026-03-10";
+/// matching the `X-GitHub-Api-Version` constant in the Copilot Chat client
+/// source (`src/platform/networking/common/networking.ts`).
+pub const API_VERSION: &str = "2025-05-01";
 /// Default Copilot Chat plugin version string, matching the `version` field of
 /// the latest `microsoft/vscode-copilot-chat` release.
-pub const COPILOT_VERSION: &str = "0.44.0";
+pub const COPILOT_VERSION: &str = "0.48.1";
 
 /// Default model name that Claude "opus"/"sonnet" requests are mapped to.
 pub const DEFAULT_OPUS: &str = "claude-opus-4.7-1m";