Use Claude Code with your ChatGPT, Kimi, Cursor or Grok subscription via a local Anthropic-compatible proxy
Rust
rename to claude-code-proxy and restructure for multi-provider support
Raine Virtac5de572e4d79
diff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex dd503b5..adb780f 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -8,7 +8,7 @@ permissions:contents: writeenv:- BIN_NAME: claude-codex-proxy+ BIN_NAME: claude-code-proxyjobs:build:@@ -80,7 +80,7 @@ jobs:merge-multiple: true- uses: actions/checkout@v5with:- repository: raine/homebrew-claude-codex-proxy+ repository: raine/homebrew-claude-code-proxytoken: ${{ secrets.RELEASE_TOKEN }}path: tap- name: Generate formula and push to tap@@ -88,54 +88,54 @@ jobs:VERSION: ${{ github.ref_name }}run: |VERSION="${VERSION#v}"- SHA_ARM=$(awk '{print $1}' claude-codex-proxy-darwin-arm64.sha256)- SHA_INTEL=$(awk '{print $1}' claude-codex-proxy-darwin-amd64.sha256)- SHA_LINUX_AMD=$(awk '{print $1}' claude-codex-proxy-linux-amd64.sha256)- SHA_LINUX_ARM=$(awk '{print $1}' claude-codex-proxy-linux-arm64.sha256)+ SHA_ARM=$(awk '{print $1}' claude-code-proxy-darwin-arm64.sha256)+ SHA_INTEL=$(awk '{print $1}' claude-code-proxy-darwin-amd64.sha256)+ SHA_LINUX_AMD=$(awk '{print $1}' claude-code-proxy-linux-amd64.sha256)+ SHA_LINUX_ARM=$(awk '{print $1}' claude-code-proxy-linux-arm64.sha256)mkdir -p tap/Formula- cat > tap/Formula/claude-codex-proxy.rb << EOF- class ClaudeCodexProxy < Formula+ cat > tap/Formula/claude-code-proxy.rb << EOF+ class ClaudeCodeProxy < Formuladesc "Local proxy: Claude Code to ChatGPT subscription via Codex Responses API"- homepage "https://github.com/raine/claude-codex-proxy"+ homepage "https://github.com/raine/claude-code-proxy"version "${VERSION}"license "MIT"on_macos doif Hardware::CPU.arm?- url "https://github.com/raine/claude-codex-proxy/releases/download/v${VERSION}/claude-codex-proxy-darwin-arm64.tar.gz"+ url "https://github.com/raine/claude-code-proxy/releases/download/v${VERSION}/claude-code-proxy-darwin-arm64.tar.gz"sha256 "${SHA_ARM}"else- url "https://github.com/raine/claude-codex-proxy/releases/download/v${VERSION}/claude-codex-proxy-darwin-amd64.tar.gz"+ url "https://github.com/raine/claude-code-proxy/releases/download/v${VERSION}/claude-code-proxy-darwin-amd64.tar.gz"sha256 "${SHA_INTEL}"endendon_linux doif Hardware::CPU.arm?- url "https://github.com/raine/claude-codex-proxy/releases/download/v${VERSION}/claude-codex-proxy-linux-arm64.tar.gz"+ url "https://github.com/raine/claude-code-proxy/releases/download/v${VERSION}/claude-code-proxy-linux-arm64.tar.gz"sha256 "${SHA_LINUX_ARM}"else- url "https://github.com/raine/claude-codex-proxy/releases/download/v${VERSION}/claude-codex-proxy-linux-amd64.tar.gz"+ url "https://github.com/raine/claude-code-proxy/releases/download/v${VERSION}/claude-code-proxy-linux-amd64.tar.gz"sha256 "${SHA_LINUX_AMD}"endenddef install- bin.install "claude-codex-proxy"+ bin.install "claude-code-proxy"endtest do- assert_match version.to_s, shell_output("\#{bin}/claude-codex-proxy --version")+ assert_match version.to_s, shell_output("\#{bin}/claude-code-proxy --version")endendEOF- sed -i 's/^ //' tap/Formula/claude-codex-proxy.rb+ sed -i 's/^ //' tap/Formula/claude-code-proxy.rbcd tapgit config user.name "github-actions[bot]"git config user.email "github-actions[bot]@users.noreply.github.com"- git add Formula/claude-codex-proxy.rb- git commit -m "claude-codex-proxy ${VERSION}"+ git add Formula/claude-code-proxy.rb+ git commit -m "claude-code-proxy ${VERSION}"git pull --rebasegit pushdiff --git a/README.md b/README.mdindex 4ff0388..62ea70f 100644--- a/README.md+++ b/README.md@@ -1,10 +1,10 @@-# claude-codex-proxy+# claude-code-proxy-`claude-codex-proxy` lets you use+`claude-code-proxy` lets you use[Claude Code](https://www.anthropic.com/claude-code) with your ChatGPT Plus orPro subscription.-<img src="meta/claude-code-screenshot.webp" alt="Claude Code running through claude-codex-proxy" width="630" />+<img src="meta/claude-code-screenshot.webp" alt="Claude Code running through claude-code-proxy" width="630" />[Quick start](#quick-start) · [How it works](#how-it-works) ·[Configuration](#configuration) · [Limitations](#limitations)@@ -27,30 +27,30 @@ ended up forking it and applying some patches, but would much rather not do it.**Homebrew** (macOS and Linux):```sh-brew install raine/claude-codex-proxy/claude-codex-proxy+brew install raine/claude-code-proxy/claude-code-proxy```**Install script** (macOS and Linux):```sh-curl -fsSL https://raw.githubusercontent.com/raine/claude-codex-proxy/main/scripts/install.sh | bash+curl -fsSL https://raw.githubusercontent.com/raine/claude-code-proxy/main/scripts/install.sh | bash```**Manual:** download a prebuilt binary for your platform from the-[releases page](https://github.com/raine/claude-codex-proxy/releases).+[releases page](https://github.com/raine/claude-code-proxy/releases).### 2. Authenticate with ChatGPTOpen a browser (PKCE flow):```sh-claude-codex-proxy auth login+claude-code-proxy codex auth login```Or, on a headless machine (device code flow):```sh-claude-codex-proxy auth device+claude-code-proxy codex auth device```Either command prints a URL. Sign in with your **ChatGPT Plus/Pro account**. On@@ -60,17 +60,17 @@ locally for reuse by the proxy.Verify it stuck:```sh-claude-codex-proxy auth status+claude-code-proxy codex auth status```### 3. Start the proxy```sh-claude-codex-proxy serve+claude-code-proxy serve```Defaults to `http://127.0.0.1:18765` (loopback only). Override with-`PORT=11435 claude-codex-proxy serve`.+`PORT=11435 claude-code-proxy serve`.### 4. Point Claude Code at it@@ -178,7 +178,7 @@ and the proxy will send `gpt-5.4-mini` upstream.sequenceDiagramautonumberparticipant CC as Claude Code- participant P as claude-codex-proxy+ participant P as claude-code-proxyparticipant AUTH as auth.openai.comparticipant CGX as chatgpt.com/<br/>backend-api/codex@@ -192,7 +192,7 @@ sequenceDiagramendP->>P: translate request<br/>• strip max_tokens / temperature / cache_control<br/>• system blocks → top-level "instructions"<br/>• tool_use.id = call_id (identity)<br/>• prompt_cache_key = session id- P->>CGX: POST /responses<br/>Bearer + ChatGPT-Account-Id + originator=claude-codex-proxy+ P->>CGX: POST /responses<br/>Bearer + ChatGPT-Account-Id + originator=claude-code-proxyCGX-->>P: Responses API SSE<br/>(output_item.*, output_text.delta, function_call_arguments.*, codex.rate_limits, response.completed)P->>P: reducer: typed events<br/>(text/tool start/delta/stop, finish)P-->>CC: Anthropic SSE<br/>(message_start, content_block_*, message_delta, message_stop)@@ -200,35 +200,37 @@ sequenceDiagram## Commands-| Command | Description |-| ----------------------------- | ----------------------------------------- |-| [`serve`](#serve) | Start the proxy on `PORT` (default 18765) |-| [`auth login`](#auth-login) | Browser OAuth (PKCE) |-| [`auth device`](#auth-device) | Device-code OAuth (headless) |-| [`auth status`](#auth-status) | Show account ID and token expiry |-| [`auth logout`](#auth-logout) | Delete stored auth credentials |+| Command | Description |+| ----------------------------------- | ----------------------------------------- |+| [`serve`](#serve) | Start the proxy on `PORT` (default 18765) |+| [`codex auth login`](#auth-login) | Browser OAuth (PKCE) |+| [`codex auth device`](#auth-device) | Device-code OAuth (headless) |+| [`codex auth status`](#auth-status) | Show account ID and token expiry |+| [`codex auth logout`](#auth-logout) | Delete stored auth credentials |---### `serve`Starts the HTTP proxy and blocks. Binds to `127.0.0.1` only. Logs to-`$XDG_STATE_HOME/claude-codex-proxy/proxy.log` (rotated at 20 MiB). Set+`$XDG_STATE_HOME/claude-code-proxy/proxy.log` (rotated at 20 MiB). Set`CCP_LOG_STDERR=1` to mirror log lines to stderr while running.```sh-claude-codex-proxy serve-PORT=11435 claude-codex-proxy serve-CCP_LOG_STDERR=1 claude-codex-proxy serve+claude-code-proxy serve+PORT=11435 claude-code-proxy serve+CCP_LOG_STDERR=1 claude-code-proxy serve```Prints the exact `ANTHROPIC_BASE_URL` / `ANTHROPIC_MODEL` env vars to export on-startup. Refuses to start traffic until `auth login` (or `auth device`) has-stored a token.+startup. Refuses to start traffic until `codex auth login` (or `codex auth+device`) has stored a token.++Selects a provider with `CCP_PROVIDER` (default `codex`).----### `auth login`+### `codex auth login`Runs the PKCE browser flow against `auth.openai.com` using the Codex CLI'sclient ID. Prints a URL, opens a local callback listener on port 1455, waits for@@ -237,7 +239,7 @@ in Keychain on macOS or locally on other platforms. The process exitsautomatically once the tokens are saved.```sh-claude-codex-proxy auth login+claude-code-proxy codex auth login```Sign in with your **ChatGPT Plus/Pro account**, not an OpenAI API account. The@@ -246,27 +248,27 @@ token file includes the extracted `chatgpt_account_id` so the proxy can set the----### `auth device`+### `codex auth device`Same OAuth flow, but for headless machines. Prints a short user code and a URL;you enter the code from any browser on any other device, and the CLI polls`auth.openai.com` until you authorize, then stores the token.```sh-claude-codex-proxy auth device+claude-code-proxy codex auth device```Useful over SSH, inside a container, or on any host that can't open a browser.----### `auth status`+### `codex auth status`Shows whether credentials are stored, the account ID, and how long until theaccess token expires. Non-zero exit if no auth is present.```sh-claude-codex-proxy auth status+claude-code-proxy codex auth status```Example output:@@ -283,16 +285,16 @@ calls.----### `auth logout`+### `codex auth logout`Removes stored auth credentials. On macOS this deletes the Keychain entry. Noserver call is needed; the refresh token just becomes dead.```sh-claude-codex-proxy auth logout+claude-code-proxy codex auth logout```-Run `auth login` again to re-authenticate.+Run `codex auth login` again to re-authenticate.---@@ -313,13 +315,14 @@ Settings are environment variables on the proxy process, not a config file.| Variable | Default | Purpose || ----------------- | ---------------- | -------------------------------------------------- || `PORT` | `18765` | Proxy listen port |+| `CCP_PROVIDER` | `codex` | Upstream provider (`codex`) || `XDG_STATE_HOME` | `~/.local/state` | Base dir for `proxy.log` || `CCP_LOG_STDERR` | unset | Also mirror log lines to stderr || `CCP_LOG_VERBOSE` | unset | Log full request/response bodies + every SSE event |### Files-- `$XDG_STATE_HOME/claude-codex-proxy/proxy.log`: JSON-lines log, rotated at 20+- `$XDG_STATE_HOME/claude-code-proxy/proxy.log`: JSON-lines log, rotated at 20MiB. Secrets (`authorization`, `access`, `refresh`, `id_token`,`ChatGPT-Account-Id`, …) are redacted before write.@@ -348,7 +351,7 @@ Settings are environment variables on the proxy process, not a config file.```shbunx tsc --noEmit # typecheckbun src/cli.ts serve # run locally-tail -f ~/.local/state/claude-codex-proxy/proxy.log | jq .+tail -f ~/.local/state/claude-code-proxy/proxy.log | jq .```**Install a compiled dev build globally:** compile the current working tree to a@@ -356,7 +359,7 @@ binary and place it on your `PATH` without linking:```shmkdir -p ~/.local/bin-bun build ./src/cli.ts --compile --outfile ~/.local/bin/claude-codex-proxy+bun build ./src/cli.ts --compile --outfile ~/.local/bin/claude-code-proxy```## Related projectsdiff --git a/package.json b/package.jsonindex 5506814..fe5f8fd 100644--- a/package.json+++ b/package.json@@ -1,10 +1,10 @@{- "name": "claude-codex-proxy",+ "name": "claude-code-proxy","version": "0.0.2","license": "MIT","type": "module","bin": {- "claude-codex-proxy": "./src/cli.ts"+ "claude-code-proxy": "./src/cli.ts"},"scripts": {"start": "bun run src/cli.ts serve",diff --git a/scripts/install.sh b/scripts/install.shindex c9e731f..2aede83 100755--- a/scripts/install.sh+++ b/scripts/install.sh@@ -1,21 +1,21 @@#!/usr/bin/env bash#-# claude-codex-proxy installation script-# Usage: curl -fsSL https://raw.githubusercontent.com/raine/claude-codex-proxy/main/scripts/install.sh | bash+# claude-code-proxy installation script+# Usage: curl -fsSL https://raw.githubusercontent.com/raine/claude-code-proxy/main/scripts/install.sh | bash## Environment variables:-# CLAUDE_CODEX_PROXY_VERSION - Pin a specific version (e.g., v0.1.0)-# CLAUDE_CODEX_PROXY_INSTALL_DIR - Override install directory (default: /usr/local/bin or ~/.local/bin)+# CLAUDE_CODE_PROXY_VERSION - Pin a specific version (e.g., v0.1.0)+# CLAUDE_CODE_PROXY_INSTALL_DIR - Override install directory (default: /usr/local/bin or ~/.local/bin)## Examples:-# CLAUDE_CODEX_PROXY_VERSION=v0.1.0 bash install.sh-# CLAUDE_CODEX_PROXY_INSTALL_DIR=/opt/bin bash install.sh+# CLAUDE_CODE_PROXY_VERSION=v0.1.0 bash install.sh+# CLAUDE_CODE_PROXY_INSTALL_DIR=/opt/bin bash install.sh#set -e-BIN_NAME="claude-codex-proxy"-REPO="raine/claude-codex-proxy"+BIN_NAME="claude-code-proxy"+REPO="raine/claude-code-proxy"RED='\033[0;31m'GREEN='\033[0;32m'@@ -70,7 +70,7 @@ install_from_release() {tmp_dir=$(mktemp -d)trap 'rm -rf "$tmp_dir"' EXIT- local version="${CLAUDE_CODEX_PROXY_VERSION:-}"+ local version="${CLAUDE_CODE_PROXY_VERSION:-}"if [ -z "$version" ]; thenlog_info "Fetching latest release..."@@ -93,7 +93,7 @@ install_from_release() {echo ""echo "This might be due to network issues or GitHub API rate limits."echo "You can specify a version manually:"- echo " CLAUDE_CODEX_PROXY_VERSION=v0.1.0 bash install.sh"+ echo " CLAUDE_CODE_PROXY_VERSION=v0.1.0 bash install.sh"echo ""exit 1fi@@ -166,7 +166,7 @@ install_from_release() {exit 1fi- local install_dir="${CLAUDE_CODEX_PROXY_INSTALL_DIR:-}"+ local install_dir="${CLAUDE_CODE_PROXY_INSTALL_DIR:-}"if [ -z "$install_dir" ]; thenif [[ -w /usr/local/bin ]]; theninstall_dir="/usr/local/bin"@@ -243,7 +243,7 @@ verify_installation() {echo ""echo "Get started:"- echo " ${BIN_NAME} auth login # authenticate with your ChatGPT account"+ echo " ${BIN_NAME} codex auth login # authenticate with your ChatGPT account"echo " ${BIN_NAME} serve # start the proxy"echo ""echo "Documentation: https://github.com/${REPO}"diff --git a/src/cli.ts b/src/cli.tsindex 1e0775f..6b62788 100755--- a/src/cli.ts+++ b/src/cli.ts@@ -1,10 +1,8 @@#!/usr/bin/env bun-import { runBrowserLogin } from "./auth/pkce.ts"-import { runDeviceLogin } from "./auth/device.ts"-import { persistInitialTokens } from "./auth/manager.ts"-import { loadAuth, authPath, clearAuth } from "./auth/token-store.ts"import { startServer } from "./server.ts"import { createLogger, logDir } from "./log.ts"+import { getProvider, listProviders } from "./providers/registry.ts"+import type { CliHandlers } from "./providers/types.ts"declare const BUILD_VERSION: string | undefinedconst VERSION = typeof BUILD_VERSION === "string" ? BUILD_VERSION : "dev"@@ -12,74 +10,89 @@ const VERSION = typeof BUILD_VERSION === "string" ? BUILD_VERSION : "dev"const log = createLogger("cli")async function main() {- const [, , cmd, sub] = process.argv- if (cmd === "--version" || cmd === "-v" || cmd === "version") {- console.log(`claude-codex-proxy ${VERSION}`)+ const args = process.argv.slice(2)+ const [first, ...rest] = args++ if (first === "--version" || first === "-v" || first === "version") {+ console.log(`claude-code-proxy ${VERSION}`)return}- switch (cmd) {- case "serve":- case undefined: {- const port = Number(process.env.PORT ?? 18765)- startServer({ port })- console.log(`Proxy listening on http://localhost:${port}`)- console.log(`Logs: ${logDir()}/proxy.log`)- console.log()- console.log("Configure Claude Code:")- console.log(` export ANTHROPIC_BASE_URL="http://localhost:${port}"`)- console.log(` export ANTHROPIC_AUTH_TOKEN="anything"`)++ if (!first || first === "serve") {+ const providerName = argFlag(rest, "--provider") ?? process.env.CCP_PROVIDER ?? "codex"+ const provider = getProvider(providerName)+ const port = Number(process.env.PORT ?? 18765)+ startServer({ port, provider })+ console.log(`Proxy listening on http://localhost:${port} (provider: ${provider.name})`)+ console.log(`Logs: ${logDir()}/proxy.log`)+ console.log()+ console.log("Configure Claude Code:")+ console.log(` export ANTHROPIC_BASE_URL="http://localhost:${port}"`)+ console.log(` export ANTHROPIC_AUTH_TOKEN="anything"`)+ if (provider.name === "codex") {console.log(` export ANTHROPIC_MODEL="gpt-5.4"`)- console.log(` export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC="1"`)- return}- case "auth": {- if (sub === "login") {- const tokens = await runBrowserLogin()- const saved = await persistInitialTokens(tokens)- console.log(`Auth saved in ${authPath()}`)- if (saved.accountId) console.log(`Account: ${saved.accountId}`)- process.exit(0)- }- if (sub === "device") {- const tokens = await runDeviceLogin()- const saved = await persistInitialTokens(tokens)- console.log(`Auth saved in ${authPath()}`)- if (saved.accountId) console.log(`Account: ${saved.accountId}`)- process.exit(0)- }- if (sub === "status") {- const auth = await loadAuth()- if (!auth) {- console.log("Not authenticated")- process.exit(1)- }- const ms = auth.expires - Date.now()- console.log(`Account: ${auth.accountId ?? "(none)"}`)- console.log(`Expires: ${new Date(auth.expires).toISOString()} (in ${Math.floor(ms / 1000)}s)`)- console.log(`Storage: ${authPath()}`)- return+ console.log(` export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC="1"`)+ return+ }++ if (listProviders().includes(first)) {+ const provider = getProvider(first)+ await runProviderCommand(provider.name, provider.cli, rest)+ return+ }++ usageAndExit()+}++async function runProviderCommand(name: string, cli: CliHandlers, args: string[]): Promise<void> {+ const [group, sub] = args+ if (group !== "auth") usageAndExit()++ switch (sub) {+ case "login":+ if (!cli.login) {+ console.error(`${name}: browser login not supported`)+ process.exit(2)}- if (sub === "logout") {- await clearAuth()- console.log("Logged out")- return+ await cli.login()+ process.exit(0)+ case "device":+ if (!cli.device) {+ console.error(`${name}: device login not supported`)+ process.exit(2)}- usageAndExit()+ await cli.device()+ process.exit(0)+ case "status":+ await cli.status()+ return+ case "logout":+ await cli.logout()return- }default:usageAndExit()}}+function argFlag(args: string[], flag: string): string | undefined {+ const i = args.indexOf(flag)+ if (i === -1) return undefined+ return args[i + 1]+}+function usageAndExit(): never {+ const providers = listProviders().join("|")console.log(`Usage:- claude-codex-proxy serve Run proxy (PORT env, default 18765)- claude-codex-proxy auth login Browser OAuth (PKCE)- claude-codex-proxy auth device Device-code OAuth- claude-codex-proxy auth status Show current auth- claude-codex-proxy auth logout Clear stored auth- claude-codex-proxy --version Show version+ claude-code-proxy serve [--provider ${providers}] Run proxy (PORT env, default 18765)+ claude-code-proxy <provider> auth login Browser OAuth+ claude-code-proxy <provider> auth device Device-code OAuth+ claude-code-proxy <provider> auth status Show current auth+ claude-code-proxy <provider> auth logout Clear stored auth+ claude-code-proxy --version Show version++Providers: ${providers}+Default provider: ${process.env.CCP_PROVIDER ?? "codex"} (override with CCP_PROVIDER or --provider)`)process.exit(2)}diff --git a/src/log.ts b/src/log.tsindex 2510bfd..8da9a8e 100644--- a/src/log.ts+++ b/src/log.ts@@ -21,7 +21,7 @@ const REDACT_KEYS = new Set([function stateDir(): string {const base = process.env.XDG_STATE_HOME || join(homedir(), ".local", "state")- return join(base, "claude-codex-proxy")+ return join(base, "claude-code-proxy")}export function logDir(): string {diff --git a/src/auth/constants.ts b/src/providers/codex/auth/constants.tssimilarity index 88%rename from src/auth/constants.tsrename to src/providers/codex/auth/constants.tsindex ed8557f..eadfda2 100644--- a/src/auth/constants.ts+++ b/src/providers/codex/auth/constants.ts@@ -3,5 +3,5 @@ export const ISSUER = "https://auth.openai.com"export const CODEX_API_ENDPOINT = "https://chatgpt.com/backend-api/codex/responses"export const OAUTH_PORT = 1455export const OAUTH_REDIRECT_URI = `http://localhost:${OAUTH_PORT}/auth/callback`-export const ORIGINATOR = "claude-codex-proxy"+export const ORIGINATOR = "claude-code-proxy"export const REFRESH_MARGIN_MS = 5 * 60 * 1000diff --git a/src/auth/device.ts b/src/providers/codex/auth/device.tssimilarity index 100%rename from src/auth/device.tsrename to src/providers/codex/auth/device.tsdiff --git a/src/auth/jwt.ts b/src/providers/codex/auth/jwt.tssimilarity index 100%rename from src/auth/jwt.tsrename to src/providers/codex/auth/jwt.tsdiff --git a/src/auth/manager.ts b/src/providers/codex/auth/manager.tssimilarity index 98%rename from src/auth/manager.tsrename to src/providers/codex/auth/manager.tsindex 2ed98df..f157a67 100644--- a/src/auth/manager.ts+++ b/src/providers/codex/auth/manager.ts@@ -8,7 +8,7 @@ let inflight: Promise<StoredAuth> | undefinedexport async function getAuth(): Promise<StoredAuth> {if (!cached) {const stored = await loadAuth()- if (!stored) throw new Error("Not authenticated. Run: claude-codex-proxy auth login")+ if (!stored) throw new Error("Not authenticated. Run: claude-code-proxy codex auth login")cached = stored}if (cached.expires - REFRESH_MARGIN_MS > Date.now()) {diff --git a/src/auth/pkce.ts b/src/providers/codex/auth/pkce.tssimilarity index 100%rename from src/auth/pkce.tsrename to src/providers/codex/auth/pkce.tsdiff --git a/src/auth/token-store.ts b/src/providers/codex/auth/token-store.tssimilarity index 95%rename from src/auth/token-store.tsrename to src/providers/codex/auth/token-store.tsindex b3b6ed7..ae85d48 100644--- a/src/auth/token-store.ts+++ b/src/providers/codex/auth/token-store.ts@@ -9,9 +9,9 @@ export interface StoredAuth {accountId?: string}-const DIR = join(homedir(), ".config", "claude-codex-proxy")+const DIR = join(homedir(), ".config", "claude-code-proxy", "codex")const FILE = join(DIR, "auth.json")-const KEYCHAIN_SERVICE = "claude-codex-proxy"+const KEYCHAIN_SERVICE = "claude-code-proxy.codex"const KEYCHAIN_ACCOUNT = "auth"export async function loadAuth(): Promise<StoredAuth | undefined> {diff --git a/src/codex/client.ts b/src/providers/codex/client.tssimilarity index 92%rename from src/codex/client.tsrename to src/providers/codex/client.tsindex 9046a67..b02d6b7 100644--- a/src/codex/client.ts+++ b/src/providers/codex/client.ts@@ -1,7 +1,7 @@-import { CODEX_API_ENDPOINT, ORIGINATOR } from "../auth/constants.ts"-import { forceRefresh, getAuth } from "../auth/manager.ts"-import { createLogger } from "../log.ts"-import type { ResponsesRequest } from "../translate/request.ts"+import { CODEX_API_ENDPOINT, ORIGINATOR } from "./auth/constants.ts"+import { forceRefresh, getAuth } from "./auth/manager.ts"+import { createLogger } from "../../log.ts"+import type { ResponsesRequest } from "./translate/request.ts"const log = createLogger("codex.client")diff --git a/src/count-tokens.ts b/src/providers/codex/count-tokens.tssimilarity index 97%rename from src/count-tokens.tsrename to src/providers/codex/count-tokens.tsindex db0c5d0..6920069 100644--- a/src/count-tokens.ts+++ b/src/providers/codex/count-tokens.ts@@ -1,5 +1,5 @@import { encode } from "gpt-tokenizer/model/gpt-4o"-import type { AnthropicRequest } from "./anthropic/schema.ts"+import type { AnthropicRequest } from "../../anthropic/schema.ts"import type { ResponsesRequest } from "./translate/request.ts"import { buildInstructions, normalizeContent, toolResultToString } from "./translate/request.ts"diff --git a/src/providers/codex/index.ts b/src/providers/codex/index.tsnew file mode 100644index 0000000..3a16720--- /dev/null+++ b/src/providers/codex/index.ts@@ -0,0 +1,385 @@+import type { AnthropicRequest } from "../../anthropic/schema.ts"+import type { Provider, RequestContext, CliHandlers } from "../types.ts"+import { createLogger } from "../../log.ts"+import {+ assertAllowedModel,+ ModelNotAllowedError,+ resolveModel,+} from "./translate/model-allowlist.ts"+import { translateRequest } from "./translate/request.ts"+import { translateStream } from "./translate/stream.ts"+import { accumulateResponse, UpstreamStreamError } from "./translate/accumulate.ts"+import { mapUsageToAnthropic } from "./translate/reducer.ts"+import { CodexError, postCodex } from "./client.ts"+import { countTokens, countTranslatedTokens } from "./count-tokens.ts"+import { runBrowserLogin } from "./auth/pkce.ts"+import { runDeviceLogin } from "./auth/device.ts"+import { persistInitialTokens } from "./auth/manager.ts"+import { loadAuth, authPath, clearAuth } from "./auth/token-store.ts"++const log = createLogger("provider.codex")+const VERBOSE = !!process.env.CCP_LOG_VERBOSE++interface SessionCountSnapshot {+ reqId: string+ model: string+ messageCount: number+ toolCount: number+ tokens: number+}++interface SessionMessageSnapshot {+ reqId: string+ model: string+ messageCount: number+ toolCount: number+ localInputTokens?: number+ translatedInputTokens?: number+}++interface SessionTimelineState {+ lastCount?: SessionCountSnapshot+ lastMessage?: SessionMessageSnapshot+}++const sessionTimeline = new Map<string, SessionTimelineState>()++function sessionState(sessionId?: string): SessionTimelineState | undefined {+ if (!sessionId) return undefined+ let state = sessionTimeline.get(sessionId)+ if (!state) {+ state = {}+ sessionTimeline.set(sessionId, state)+ }+ return state+}++function usageWindowTokens(usage: {+ input_tokens: number+ output_tokens: number+ cache_creation_input_tokens: number+ cache_read_input_tokens: number+}): number {+ return (+ usage.input_tokens ++ usage.output_tokens ++ usage.cache_creation_input_tokens ++ usage.cache_read_input_tokens+ )+}++function upstreamHeaderSnapshot(headers: Headers): {+ serverModel?: string+ serverReasoningIncluded: boolean+} {+ return {+ serverModel: headers.get("OpenAI-Model") || undefined,+ serverReasoningIncluded: headers.has("X-Reasoning-Included"),+ }+}++function jsonError(status: number, type: string, message: string): Response {+ return new Response(JSON.stringify({ type: "error", error: { type, message } }), {+ status,+ headers: { "content-type": "application/json" },+ })+}++async function handleCountTokens(body: AnthropicRequest, ctx: RequestContext): Promise<Response> {+ const resolvedModel = resolveModel(body.model)+ const translated = translateRequest({ ...body, model: resolvedModel })+ const tokens = countTranslatedTokens(translated)+ const messageCount = body.messages?.length ?? 0+ const toolCount = body.tools?.length ?? 0+ const state = sessionState(ctx.sessionId)+ log.debug("count_tokens", { reqId: ctx.reqId, tokens })+ if (state) {+ state.lastCount = {+ reqId: ctx.reqId,+ model: body.model,+ messageCount,+ toolCount,+ tokens,+ }+ }+ if (VERBOSE) {+ log.info("compaction telemetry", {+ reqId: ctx.reqId,+ phase: "count_tokens",+ sessionId: ctx.sessionId,+ sessionSeq: ctx.sessionSeq,+ model: body.model,+ resolvedModel,+ tokens,+ messageCount,+ toolCount,+ previousMessageReqId: state?.lastMessage?.reqId,+ previousMessageModel: state?.lastMessage?.model,+ previousMessageCount: state?.lastMessage?.messageCount,+ previousMessageToolCount: state?.lastMessage?.toolCount,+ previousMessageLocalInputTokens: state?.lastMessage?.localInputTokens,+ previousMessageTranslatedInputTokens: state?.lastMessage?.translatedInputTokens,+ })+ }+ return new Response(JSON.stringify({ input_tokens: tokens }), {+ headers: { "content-type": "application/json" },+ })+}++async function handleMessages(body: AnthropicRequest, ctx: RequestContext): Promise<Response> {+ const messageId = `msg_${crypto.randomUUID().replace(/-/g, "")}`+ const wantStream = body.stream !== false+ const messageCount = body.messages?.length ?? 0+ const toolCount = body.tools?.length ?? 0+ const contextManagement = body.context_management+ const state = sessionState(ctx.sessionId)++ log.debug("anthropic request", {+ reqId: ctx.reqId,+ model: body.model,+ messageCount,+ toolCount,+ stream: wantStream,+ sessionId: ctx.sessionId,+ requestedMaxTokens: body.max_tokens,+ hasContextManagement: contextManagement !== undefined,+ hasJsonSchemaFormat: body.output_config?.format?.type === "json_schema",+ })+ if (VERBOSE) log.debug("anthropic request body", { reqId: ctx.reqId, body })++ const resolvedModel = resolveModel(body.model)++ try {+ assertAllowedModel(resolvedModel)+ } catch (err) {+ if (err instanceof ModelNotAllowedError) {+ return jsonError(+ 400,+ "invalid_request_error",+ `Model "${body.model}" resolves to unsupported model "${err.model}"`,+ )+ }+ throw err+ }++ const translated = translateRequest({ ...body, model: resolvedModel }, { sessionId: ctx.sessionId })+ const localInputTokens = VERBOSE ? countTokens(body) : undefined+ const translatedInputTokens = VERBOSE ? countTranslatedTokens(translated) : undefined+ if (state) {+ state.lastMessage = {+ reqId: ctx.reqId,+ model: body.model,+ messageCount,+ toolCount,+ localInputTokens,+ translatedInputTokens,+ }+ }+ log.debug("translated request", {+ reqId: ctx.reqId,+ requestedModel: body.model,+ resolvedModel,+ inputItems: translated.input.length,+ tools: translated.tools?.length ?? 0,+ hasInstructions: !!translated.instructions,+ requestedMaxTokens: body.max_tokens,+ hasContextManagement: contextManagement !== undefined,+ promptCacheKey: translated.prompt_cache_key,+ })+ if (VERBOSE) log.debug("translated request body", { reqId: ctx.reqId, body: translated })+ if (VERBOSE) {+ log.info("compaction telemetry", {+ reqId: ctx.reqId,+ phase: "translated_request",+ sessionId: ctx.sessionId,+ sessionSeq: ctx.sessionSeq,+ requestedModel: body.model,+ resolvedModel,+ messageCount,+ toolCount,+ localInputTokens,+ translatedInputTokens,+ inputItems: translated.input.length,+ translatedToolCount: translated.tools?.length ?? 0,+ hasInstructions: !!translated.instructions,+ requestedMaxTokens: body.max_tokens,+ hasContextManagement: contextManagement !== undefined,+ contextManagement,+ previousCountReqId: state?.lastCount?.reqId,+ previousCountModel: state?.lastCount?.model,+ previousCountTokens: state?.lastCount?.tokens,+ previousCountMessageCount: state?.lastCount?.messageCount,+ previousCountToolCount: state?.lastCount?.toolCount,+ })+ }++ let upstream+ try {+ upstream = await postCodex(translated, { sessionId: ctx.sessionId, signal: ctx.signal })+ } catch (err) {+ if (err instanceof CodexError) {+ log.warn("codex error", { reqId: ctx.reqId, status: err.status, detail: err.detail })+ if (err.status === 429) {+ const headers: Record<string, string> = { "content-type": "application/json" }+ if (err.meta?.retryAfter) headers["retry-after"] = err.meta.retryAfter+ return new Response(+ JSON.stringify({+ type: "error",+ error: { type: "rate_limit_error", message: err.detail || err.message },+ }),+ { status: 429, headers },+ )+ }+ const type =+ err.status === 401 || err.status === 403 ? "authentication_error" : "api_error"+ return jsonError(err.status, type, err.detail || err.message)+ }+ throw err+ }++ if (wantStream) {+ const { serverModel, serverReasoningIncluded } = upstreamHeaderSnapshot(upstream.headers)+ const stream = translateStream(upstream.body, {+ messageId,+ model: body.model,+ reqId: ctx.reqId,+ sessionId: ctx.sessionId,+ onFinish: VERBOSE+ ? (finish) => {+ const mappedUsage = finish.usage ? mapUsageToAnthropic(finish.usage) : undefined+ log.info("compaction telemetry", {+ reqId: ctx.reqId,+ phase: "upstream_finish",+ mode: "stream",+ sessionId: ctx.sessionId,+ sessionSeq: ctx.sessionSeq,+ requestedModel: body.model,+ resolvedModel,+ serverModel,+ serverReasoningIncluded,+ messageCount,+ toolCount,+ localInputTokens,+ translatedInputTokens,+ requestedMaxTokens: body.max_tokens,+ hasContextManagement: contextManagement !== undefined,+ contextManagement,+ upstreamInputTokens: finish.usage?.input_tokens ?? 0,+ upstreamOutputTokens: finish.usage?.output_tokens ?? 0,+ upstreamCachedInputTokens: finish.usage?.input_tokens_details?.cached_tokens ?? 0,+ upstreamReasoningTokens:+ finish.usage?.output_tokens_details?.reasoning_tokens ?? 0,+ mappedInputTokens: mappedUsage?.input_tokens ?? 0,+ mappedOutputTokens: mappedUsage?.output_tokens ?? 0,+ mappedCachedInputTokens: mappedUsage?.cache_read_input_tokens ?? 0,+ mappedContextWindowTokens: mappedUsage ? usageWindowTokens(mappedUsage) : 0,+ stopReason: finish.stopReason,+ })+ }+ : undefined,+ })+ return new Response(stream, {+ status: 200,+ headers: {+ "content-type": "text/event-stream",+ "cache-control": "no-cache",+ connection: "keep-alive",+ },+ })+ }++ try {+ const result = await accumulateResponse(upstream.body, { messageId, model: body.model })+ if (VERBOSE) {+ const { serverModel, serverReasoningIncluded } = upstreamHeaderSnapshot(upstream.headers)+ log.info("compaction telemetry", {+ reqId: ctx.reqId,+ phase: "upstream_finish",+ mode: "non_stream",+ sessionId: ctx.sessionId,+ sessionSeq: ctx.sessionSeq,+ requestedModel: body.model,+ resolvedModel,+ serverModel,+ serverReasoningIncluded,+ messageCount,+ toolCount,+ localInputTokens,+ translatedInputTokens,+ requestedMaxTokens: body.max_tokens,+ hasContextManagement: contextManagement !== undefined,+ contextManagement,+ upstreamInputTokens: result.rawUsage?.input_tokens ?? 0,+ upstreamOutputTokens: result.rawUsage?.output_tokens ?? 0,+ upstreamCachedInputTokens: result.rawUsage?.input_tokens_details?.cached_tokens ?? 0,+ upstreamReasoningTokens: result.rawUsage?.output_tokens_details?.reasoning_tokens ?? 0,+ mappedInputTokens: result.response.usage.input_tokens,+ mappedOutputTokens: result.response.usage.output_tokens,+ mappedCachedInputTokens: result.response.usage.cache_read_input_tokens,+ mappedContextWindowTokens: usageWindowTokens(result.response.usage),+ stopReason: result.response.stop_reason,+ })+ }+ return new Response(JSON.stringify(result.response), {+ headers: { "content-type": "application/json" },+ })+ } catch (err) {+ if (err instanceof UpstreamStreamError) {+ log.warn("upstream stream error (non-streaming)", {+ reqId: ctx.reqId,+ kind: err.kind,+ message: err.message,+ })+ if (err.kind === "rate_limit") {+ const headers: Record<string, string> = { "content-type": "application/json" }+ if (err.retryAfterSeconds) headers["retry-after"] = String(err.retryAfterSeconds)+ return new Response(+ JSON.stringify({+ type: "error",+ error: { type: "rate_limit_error", message: err.message },+ }),+ { status: 429, headers },+ )+ }+ return jsonError(502, "api_error", err.message)+ }+ throw err+ }+}++const cli: CliHandlers = {+ async login() {+ const tokens = await runBrowserLogin()+ const saved = await persistInitialTokens(tokens)+ console.log(`Auth saved in ${authPath()}`)+ if (saved.accountId) console.log(`Account: ${saved.accountId}`)+ },+ async device() {+ const tokens = await runDeviceLogin()+ const saved = await persistInitialTokens(tokens)+ console.log(`Auth saved in ${authPath()}`)+ if (saved.accountId) console.log(`Account: ${saved.accountId}`)+ },+ async status() {+ const auth = await loadAuth()+ if (!auth) {+ console.log("Not authenticated")+ process.exit(1)+ }+ const ms = auth.expires - Date.now()+ console.log(`Account: ${auth.accountId ?? "(none)"}`)+ console.log(`Expires: ${new Date(auth.expires).toISOString()} (in ${Math.floor(ms / 1000)}s)`)+ console.log(`Storage: ${authPath()}`)+ },+ async logout() {+ await clearAuth()+ console.log("Logged out")+ },+}++export const codexProvider: Provider = {+ name: "codex",+ handleMessages,+ handleCountTokens,+ cli,+}diff --git a/src/translate/accumulate.ts b/src/providers/codex/translate/accumulate.tssimilarity index 100%rename from src/translate/accumulate.tsrename to src/providers/codex/translate/accumulate.tsdiff --git a/src/translate/model-allowlist.ts b/src/providers/codex/translate/model-allowlist.tssimilarity index 100%rename from src/translate/model-allowlist.tsrename to src/providers/codex/translate/model-allowlist.tsdiff --git a/src/translate/reducer.ts b/src/providers/codex/translate/reducer.tssimilarity index 98%rename from src/translate/reducer.tsrename to src/providers/codex/translate/reducer.tsindex 071b47c..34ce0dd 100644--- a/src/translate/reducer.ts+++ b/src/providers/codex/translate/reducer.ts@@ -1,5 +1,5 @@-import { parseSseStream } from "./sse.ts"-import { createLogger } from "../log.ts"+import { parseSseStream } from "../../../sse.ts"+import { createLogger } from "../../../log.ts"const log = createLogger("translate.reducer")const VERBOSE = !!process.env.CCP_LOG_VERBOSEdiff --git a/src/translate/request.test.ts b/src/providers/codex/translate/request.test.tssimilarity index 96%rename from src/translate/request.test.tsrename to src/providers/codex/translate/request.test.tsindex 43af7af..7362234 100644--- a/src/translate/request.test.ts+++ b/src/providers/codex/translate/request.test.ts@@ -1,5 +1,5 @@import { describe, expect, it } from "bun:test"-import type { AnthropicRequest } from "../anthropic/schema.ts"+import type { AnthropicRequest } from "../../../anthropic/schema.ts"import { translateRequest } from "./request.ts"const baseRequest: AnthropicRequest = {diff --git a/src/translate/request.ts b/src/providers/codex/translate/request.tssimilarity index 99%rename from src/translate/request.tsrename to src/providers/codex/translate/request.tsindex cbd1498..ac0f115 100644--- a/src/translate/request.ts+++ b/src/providers/codex/translate/request.ts@@ -5,7 +5,7 @@ import type {AnthropicRequest,AnthropicTextBlock,AnthropicTool,-} from "../anthropic/schema.ts"+} from "../../../anthropic/schema.ts"// Keep this aligned to the upstream Codex ResponsesApiRequest field set.// Do not add plausible-looking top-level fields without source support or a confirmed live test.diff --git a/src/translate/stream.ts b/src/providers/codex/translate/stream.tssimilarity index 98%rename from src/translate/stream.tsrename to src/providers/codex/translate/stream.tsindex fe78c4f..a9dd438 100644--- a/src/translate/stream.ts+++ b/src/providers/codex/translate/stream.ts@@ -1,5 +1,5 @@-import { encodeSseEvent } from "./sse.ts"-import { createLogger } from "../log.ts"+import { encodeSseEvent } from "../../../sse.ts"+import { createLogger } from "../../../log.ts"import { mapUsageToAnthropic, reduceUpstream, UpstreamStreamError } from "./reducer.ts"const log = createLogger("translate.stream")diff --git a/src/providers/registry.ts b/src/providers/registry.tsnew file mode 100644index 0000000..bbcb39b--- /dev/null+++ b/src/providers/registry.ts@@ -0,0 +1,21 @@+import type { Provider } from "./types.ts"+import { codexProvider } from "./codex/index.ts"++const PROVIDERS: Record<string, Provider> = {+ codex: codexProvider,+}++export function getProvider(name?: string): Provider {+ const key = name ?? process.env.CCP_PROVIDER ?? "codex"+ const p = PROVIDERS[key]+ if (!p) {+ throw new Error(+ `Unknown provider: ${key}. Available: ${Object.keys(PROVIDERS).join(", ")}`,+ )+ }+ return p+}++export function listProviders(): string[] {+ return Object.keys(PROVIDERS)+}diff --git a/src/providers/types.ts b/src/providers/types.tsnew file mode 100644index 0000000..390fb05--- /dev/null+++ b/src/providers/types.ts@@ -0,0 +1,22 @@+import type { AnthropicRequest } from "../anthropic/schema.ts"++export interface RequestContext {+ reqId: string+ sessionId?: string+ sessionSeq?: number+ signal: AbortSignal+}++export interface CliHandlers {+ login?: () => Promise<void>+ device?: () => Promise<void>+ status: () => Promise<void>+ logout: () => Promise<void>+}++export interface Provider {+ name: string+ handleMessages(body: AnthropicRequest, ctx: RequestContext): Promise<Response>+ handleCountTokens(body: AnthropicRequest, ctx: RequestContext): Promise<Response>+ cli: CliHandlers+}diff --git a/src/server.ts b/src/server.tsindex c5f7c83..66fb0fd 100644--- a/src/server.ts+++ b/src/server.ts@@ -1,84 +1,25 @@import { createLogger, logDir } from "./log.ts"import type { AnthropicRequest } from "./anthropic/schema.ts"-import { assertAllowedModel, ModelNotAllowedError, resolveModel } from "./translate/model-allowlist.ts"-import { translateRequest } from "./translate/request.ts"-import { translateStream } from "./translate/stream.ts"-import { accumulateResponse, UpstreamStreamError } from "./translate/accumulate.ts"-import { mapUsageToAnthropic } from "./translate/reducer.ts"-import { CodexError, postCodex } from "./codex/client.ts"-import { countTokens, countTranslatedTokens } from "./count-tokens.ts"+import type { Provider, RequestContext } from "./providers/types.ts"const log = createLogger("server")-const VERBOSE = !!process.env.CCP_LOG_VERBOSEexport interface ServeOptions {port: number+ provider: Provider}-interface SessionCountSnapshot {- reqId: string- model: string- messageCount: number- toolCount: number- tokens: number-}--interface SessionMessageSnapshot {- reqId: string- model: string- messageCount: number- toolCount: number- localInputTokens?: number- translatedInputTokens?: number-}--function usageWindowTokens(usage: {- input_tokens: number- output_tokens: number- cache_creation_input_tokens: number- cache_read_input_tokens: number-}): number {- return (- usage.input_tokens +- usage.output_tokens +- usage.cache_creation_input_tokens +- usage.cache_read_input_tokens- )-}+const sessionSeqs = new Map<string, number>()-function upstreamHeaderSnapshot(headers: Headers): {- serverModel?: string- serverReasoningIncluded: boolean-} {- return {- serverModel: headers.get("OpenAI-Model") || undefined,- serverReasoningIncluded: headers.has("X-Reasoning-Included"),- }-}--interface SessionTimelineState {- seq: number- lastCount?: SessionCountSnapshot- lastMessage?: SessionMessageSnapshot-}--const sessionTimeline = new Map<string, SessionTimelineState>()--function nextSessionTimeline(sessionId?: string): {- state?: SessionTimelineState- sessionSeq?: number-} {- if (!sessionId) return {}- let state = sessionTimeline.get(sessionId)- if (!state) {- state = { seq: 0 }- sessionTimeline.set(sessionId, state)- }- state.seq += 1- return { state, sessionSeq: state.seq }+function nextSessionSeq(sessionId?: string): number | undefined {+ if (!sessionId) return undefined+ const seq = (sessionSeqs.get(sessionId) ?? 0) + 1+ sessionSeqs.set(sessionId, seq)+ return seq}export function startServer(opts: ServeOptions): { stop: () => void; port: number } {+ const { provider } = optsconst server = Bun.serve({hostname: "127.0.0.1",port: opts.port,@@ -87,9 +28,15 @@ export function startServer(opts: ServeOptions): { stop: () => void; port: numbeconst url = new URL(req.url)const start = Date.now()const reqId = crypto.randomUUID()- log.info("request", { reqId, method: req.method, path: url.pathname, query: url.search })+ log.info("request", {+ reqId,+ method: req.method,+ path: url.pathname,+ query: url.search,+ provider: provider.name,+ })try {- const resp = await route(req, url, reqId)+ const resp = await route(req, url, reqId, provider)log.info("response", { reqId, status: resp.status, ms: Date.now() - start })return resp} catch (err) {@@ -98,297 +45,54 @@ export function startServer(opts: ServeOptions): { stop: () => void; port: numbe}},})- log.info("server listening", { port: server.port, logDir: logDir() })+ log.info("server listening", { port: server.port, provider: provider.name, logDir: logDir() })return {port: Number(server.port),stop: () => server.stop(),}}-async function route(req: Request, url: URL, reqId: string): Promise<Response> {+async function route(req: Request, url: URL, reqId: string, provider: Provider): Promise<Response> {if (url.pathname === "/healthz") {- return new Response(JSON.stringify({ ok: true }), {+ return new Response(JSON.stringify({ ok: true, provider: provider.name }), {headers: { "content-type": "application/json" },})}if (req.method === "POST" && url.pathname === "/v1/messages/count_tokens") {- const body = (await req.json()) as AnthropicRequest- const resolvedModel = resolveModel(body.model)- const translated = translateRequest({ ...body, model: resolvedModel })- const tokens = countTranslatedTokens(translated)+ const body = await parseJsonBody(req)+ if (body instanceof Response) return bodyconst sessionId = req.headers.get("x-claude-code-session-id") || undefined- const { state, sessionSeq } = nextSessionTimeline(sessionId)- const messageCount = body.messages?.length ?? 0- const toolCount = body.tools?.length ?? 0- log.debug("count_tokens", { reqId, tokens })- if (state) {- state.lastCount = {- reqId,- model: body.model,- messageCount,- toolCount,- tokens,- }- }- if (VERBOSE) {- log.info("compaction telemetry", {- reqId,- phase: "count_tokens",- path: url.pathname,- sessionId,- sessionSeq,- model: body.model,- resolvedModel,- tokens,- messageCount,- toolCount,- previousMessageReqId: state?.lastMessage?.reqId,- previousMessageModel: state?.lastMessage?.model,- previousMessageCount: state?.lastMessage?.messageCount,- previousMessageToolCount: state?.lastMessage?.toolCount,- previousMessageLocalInputTokens: state?.lastMessage?.localInputTokens,- previousMessageTranslatedInputTokens: state?.lastMessage?.translatedInputTokens,- })+ const ctx: RequestContext = {+ reqId,+ sessionId,+ sessionSeq: nextSessionSeq(sessionId),+ signal: req.signal,}- return new Response(JSON.stringify({ input_tokens: tokens }), {- headers: { "content-type": "application/json" },- })+ return provider.handleCountTokens(body, ctx)}if (req.method === "POST" && url.pathname === "/v1/messages") {- return handleMessages(req, reqId)- }-- return jsonError(404, "not_found", `No route for ${req.method} ${url.pathname}`)-}--async function handleMessages(req: Request, reqId: string): Promise<Response> {- let body: AnthropicRequest- try {- body = (await req.json()) as AnthropicRequest- } catch (err) {- return jsonError(400, "invalid_request_error", `Invalid JSON: ${err}`)- }-- const sessionId = req.headers.get("x-claude-code-session-id") || undefined- const { state, sessionSeq } = nextSessionTimeline(sessionId)- const messageId = `msg_${crypto.randomUUID().replace(/-/g, "")}`- const wantStream = body.stream !== false- const messageCount = body.messages?.length ?? 0- const toolCount = body.tools?.length ?? 0- const contextManagement = body.context_management-- log.debug("anthropic request", {- reqId,- model: body.model,- messageCount,- toolCount,- stream: wantStream,- sessionId,- requestedMaxTokens: body.max_tokens,- hasContextManagement: contextManagement !== undefined,- hasJsonSchemaFormat: body.output_config?.format?.type === "json_schema",- })- if (VERBOSE) log.debug("anthropic request body", { reqId, body })-- const resolvedModel = resolveModel(body.model)-- try {- assertAllowedModel(resolvedModel)- } catch (err) {- if (err instanceof ModelNotAllowedError) {- return jsonError(- 400,- "invalid_request_error",- `Model "${body.model}" resolves to unsupported model "${err.model}"`,- )- }- throw err- }-- const translated = translateRequest({ ...body, model: resolvedModel }, { sessionId })- const localInputTokens = VERBOSE ? countTokens(body) : undefined- const translatedInputTokens = VERBOSE ? countTranslatedTokens(translated) : undefined- if (state) {- state.lastMessage = {- reqId,- model: body.model,- messageCount,- toolCount,- localInputTokens,- translatedInputTokens,- }- }- log.debug("translated request", {- reqId,- requestedModel: body.model,- resolvedModel,- inputItems: translated.input.length,- tools: translated.tools?.length ?? 0,- hasInstructions: !!translated.instructions,- requestedMaxTokens: body.max_tokens,- hasContextManagement: contextManagement !== undefined,- promptCacheKey: translated.prompt_cache_key,- })- if (VERBOSE) log.debug("translated request body", { reqId, body: translated })- if (VERBOSE) {- log.info("compaction telemetry", {+ const body = await parseJsonBody(req)+ if (body instanceof Response) return body+ const sessionId = req.headers.get("x-claude-code-session-id") || undefined+ const ctx: RequestContext = {reqId,- phase: "translated_request",sessionId,- sessionSeq,- requestedModel: body.model,- resolvedModel,- messageCount,- toolCount,- localInputTokens,- translatedInputTokens,- inputItems: translated.input.length,- translatedToolCount: translated.tools?.length ?? 0,- hasInstructions: !!translated.instructions,- requestedMaxTokens: body.max_tokens,- hasContextManagement: contextManagement !== undefined,- contextManagement,- previousCountReqId: state?.lastCount?.reqId,- previousCountModel: state?.lastCount?.model,- previousCountTokens: state?.lastCount?.tokens,- previousCountMessageCount: state?.lastCount?.messageCount,- previousCountToolCount: state?.lastCount?.toolCount,- })- }-- let upstream- try {- upstream = await postCodex(translated, { sessionId, signal: req.signal })- } catch (err) {- if (err instanceof CodexError) {- log.warn("codex error", { reqId, status: err.status, detail: err.detail })- if (err.status === 429) {- const headers: Record<string, string> = { "content-type": "application/json" }- if (err.meta?.retryAfter) headers["retry-after"] = err.meta.retryAfter- return new Response(- JSON.stringify({- type: "error",- error: { type: "rate_limit_error", message: err.detail || err.message },- }),- { status: 429, headers },- )- }- const type =- err.status === 401 || err.status === 403 ? "authentication_error" : "api_error"- return jsonError(err.status, type, err.detail || err.message)+ sessionSeq: nextSessionSeq(sessionId),+ signal: req.signal,}- throw err+ return provider.handleMessages(body, ctx)}- if (wantStream) {- const { serverModel, serverReasoningIncluded } = upstreamHeaderSnapshot(upstream.headers)- const stream = translateStream(upstream.body, {- messageId,- model: body.model,- reqId,- sessionId,- onFinish: VERBOSE- ? (finish) => {- const mappedUsage = finish.usage ? mapUsageToAnthropic(finish.usage) : undefined- log.info("compaction telemetry", {- reqId,- phase: "upstream_finish",- mode: "stream",- sessionId,- sessionSeq,- requestedModel: body.model,- resolvedModel,- serverModel,- serverReasoningIncluded,- messageCount,- toolCount,- localInputTokens,- translatedInputTokens,- requestedMaxTokens: body.max_tokens,- hasContextManagement: contextManagement !== undefined,- contextManagement,- upstreamInputTokens: finish.usage?.input_tokens ?? 0,- upstreamOutputTokens: finish.usage?.output_tokens ?? 0,- upstreamCachedInputTokens: finish.usage?.input_tokens_details?.cached_tokens ?? 0,- upstreamReasoningTokens:- finish.usage?.output_tokens_details?.reasoning_tokens ?? 0,- mappedInputTokens: mappedUsage?.input_tokens ?? 0,- mappedOutputTokens: mappedUsage?.output_tokens ?? 0,- mappedCachedInputTokens: mappedUsage?.cache_read_input_tokens ?? 0,- mappedContextWindowTokens: mappedUsage ? usageWindowTokens(mappedUsage) : 0,- stopReason: finish.stopReason,- })- }- : undefined,- })- return new Response(stream, {- status: 200,- headers: {- "content-type": "text/event-stream",- "cache-control": "no-cache",- connection: "keep-alive",- },- })- }+ return jsonError(404, "not_found", `No route for ${req.method} ${url.pathname}`)+}+async function parseJsonBody(req: Request): Promise<AnthropicRequest | Response> {try {- const result = await accumulateResponse(upstream.body, { messageId, model: body.model })- if (VERBOSE) {- const { serverModel, serverReasoningIncluded } = upstreamHeaderSnapshot(upstream.headers)- log.info("compaction telemetry", {- reqId,- phase: "upstream_finish",- mode: "non_stream",- sessionId,- sessionSeq,- requestedModel: body.model,- resolvedModel,- serverModel,- serverReasoningIncluded,- messageCount,- toolCount,- localInputTokens,- translatedInputTokens,- requestedMaxTokens: body.max_tokens,- hasContextManagement: contextManagement !== undefined,- contextManagement,- upstreamInputTokens: result.rawUsage?.input_tokens ?? 0,- upstreamOutputTokens: result.rawUsage?.output_tokens ?? 0,- upstreamCachedInputTokens: result.rawUsage?.input_tokens_details?.cached_tokens ?? 0,- upstreamReasoningTokens: result.rawUsage?.output_tokens_details?.reasoning_tokens ?? 0,- mappedInputTokens: result.response.usage.input_tokens,- mappedOutputTokens: result.response.usage.output_tokens,- mappedCachedInputTokens: result.response.usage.cache_read_input_tokens,- mappedContextWindowTokens: usageWindowTokens(result.response.usage),- stopReason: result.response.stop_reason,- })- }- return new Response(JSON.stringify(result.response), {- headers: { "content-type": "application/json" },- })+ return (await req.json()) as AnthropicRequest} catch (err) {- if (err instanceof UpstreamStreamError) {- log.warn("upstream stream error (non-streaming)", {- reqId,- kind: err.kind,- message: err.message,- })- if (err.kind === "rate_limit") {- const headers: Record<string, string> = { "content-type": "application/json" }- if (err.retryAfterSeconds) headers["retry-after"] = String(err.retryAfterSeconds)- return new Response(- JSON.stringify({- type: "error",- error: { type: "rate_limit_error", message: err.message },- }),- { status: 429, headers },- )- }- return jsonError(502, "api_error", err.message)- }- throw err+ return jsonError(400, "invalid_request_error", `Invalid JSON: ${err}`)}}diff --git a/src/translate/sse.ts b/src/sse.tssimilarity index 100%rename from src/translate/sse.tsrename to src/sse.ts