betahi-copilot-bridge 0.20.1 → 0.20.3

package/README.md

@@ -1,34 +1,15 @@
 <h1 align="center">copilot-bridge</h1>
 
 <p align="center">
-  <a href="https://www.npmjs.com/package/betahi-copilot-bridge"><img src="https://img.shields.io/npm/v/betahi-copilot-bridge.svg?v=0.20.0" alt="npm version"></a>
+  <a href="https://www.npmjs.com/package/betahi-copilot-bridge"><img src="https://img.shields.io/npm/v/betahi-copilot-bridge.svg?v=0.20.3" alt="npm version"></a>
   <a href="https://github.com/betahi/copilot-bridge/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/betahi-copilot-bridge.svg" alt="license"></a>
 </p>
 
 > Use GitHub Copilot as a local OpenAI/Anthropic-compatible API, so [Codex CLI](https://developers.openai.com/codex/cli), [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview) and Continue can talk to Copilot with minimal configuration.
 
-> [!WARNING]
-> This is a reverse-engineered bridge for the GitHub Copilot API. It is not
-> supported by GitHub, and may break unexpectedly. Use at your own risk.
-
-> [!WARNING]
-> **GitHub Security Notice:**
-> Excessive automated or scripted use of Copilot (including rapid or bulk
-> requests, such as via automated tools) may trigger GitHub's abuse-detection
-> systems. You may receive a warning from GitHub Security, and further
-> anomalous activity could result in temporary suspension of your Copilot
-> access.
->
-> GitHub prohibits use of their servers for excessive automated bulk activity
-> or any activity that places undue burden on their infrastructure.
->
-> Please review:
->
-> - [GitHub Acceptable Use Policies](https://docs.github.com/site-policy/acceptable-use-policies/github-acceptable-use-policies#4-spam-and-inauthentic-activity-on-github)
-> - [GitHub Copilot Terms](https://docs.github.com/site-policy/github-terms/github-terms-for-additional-products-and-features#github-copilot)
->
-> Use this bridge responsibly to avoid account restrictions. The
-> `--rate-limit <seconds>` flag is provided to help throttle upstream traffic.
+> [!CAUTION]
+> This is an unofficial bridge for the GitHub Copilot API and may break if the
+> upstream API changes.
 
 ## Demo
 
@@ -50,10 +31,6 @@ npx betahi-copilot-bridge@latest auth
 npx betahi-copilot-bridge@latest start
 ```
 
-`start` flags: `--host`, `--port`, `--show-token`, `--debug`,
-`--no-codex-setup`, `--select-model`, `--no-prompt`,
-`--rate-limit <seconds>`, `--wait`.
-
 After startup the banner prints a **Usage Viewer** link of the form
 `https://betahi.github.io/copilot-bridge?endpoint=http://127.0.0.1:4142/usage`,
 which renders the Copilot quota snapshot (chat / completions / premium
@@ -65,22 +42,18 @@ The bridge exposes both adapter-style endpoints (`/v1/responses`,
 LiteLLM, Continue, Cline and Aider work out of the box. CORS is enabled
 globally for browser-based clients.
 
-`--rate-limit N` enforces a minimum of N seconds between upstream
-requests (anti–abuse-detection throttle). Add `--wait` to block instead
-of returning HTTP 429 when the window has not elapsed.
-
-`--debug` enables extra upstream error diagnostics in console logs.
-- Includes: token limits, stream mode, tool count, invalid tool names, and suspicious tool-schema paths.
-- Does not include: request messages, prompt text, bearer tokens, tool descriptions, or the full request body.
-
-**Review or redact debug logs before sharing them publicly.**
-
 ## Configure Codex CLI
 
 `start` writes a managed block into **`~/.codex/config.toml`**. You don't edit
-this block; the bridge regenerates it on every start.
+between the markers; the bridge regenerates that block on every start. To pin
+the **default model** for `codex` (without passing `-m` every time), add your
+top-level keys above the managed block:
 
 ```toml
+# User defaults; edit these freely.
+model = "gpt-5.3-codex"
+model_reasoning_effort = "high"
+
 # >>> copilot-bridge managed block — auto-generated, do not edit between markers >>>
 model_provider = "bridge"
 model_supports_reasoning_summaries = true
@@ -94,37 +67,21 @@ requires_openai_auth = false
 # <<< copilot-bridge managed block — edits outside this block are preserved <<<
 ```
 
-To pin the **default model** for `codex` (without passing `-m` every time),
-edit the **top of the same file** — outside the markers. The bridge preserves
-these keys across rewrites:
-
-```toml
-model = "gpt-5.3-codex"
-model_reasoning_effort = "high"
-```
-
-That's it — `codex exec '...'` will now route through the bridge to Copilot.
-
-Use `--no-codex-setup` to skip the managed-block writer entirely (e.g. if you
-manage `~/.codex/config.toml` yourself).
+Use `--no-codex-setup` to skip this writer if you manage
+`~/.codex/config.toml` yourself.
 
 ### Codex warning: "Model metadata ... not found"
 
-This is a Codex client-side metadata warning, not a bridge routing failure.
-Requests can still complete through the bridge.
+This is a Codex client-side metadata warning, not a bridge routing failure, requests can still complete through the bridge.
 
-For `claude-opus-4.6-1m`, upstream still enforces a 1,000,000-token prompt
+For 1M models, upstream still enforces a 1,000,000-token prompt
 limit (about 900k succeeds; around 1,000,046 is rejected as too long).
 
 ## Configure Claude Code
 
-Bridge endpoints: `POST /v1/messages`, `POST /v1/messages/count_tokens`.
-
-`copilot-bridge start` automatically writes `ANTHROPIC_BASE_URL` (and a dummy
-`ANTHROPIC_AUTH_TOKEN` if absent) into **`~/.claude/settings.json`**, so
-`claude` works the moment the bridge is listening — even on a different host
-or port. Pass `--no-claude-setup` to skip this. All other keys in your
-settings file (model overrides, plugins, marketplaces) are preserved.
+`copilot-bridge start` writes `ANTHROPIC_BASE_URL` and a dummy
+`ANTHROPIC_AUTH_TOKEN` into **`~/.claude/settings.json`**. Other settings are
+preserved; use `--no-claude-setup` to skip this writer.
 
 Minimal recommended config is:
 
@@ -146,12 +103,12 @@ the bridge maps it to the real Copilot `-1m` model upstream:
 ```json
 {
   "env": {
-    "ANTHROPIC_MODEL": "claude-opus-4.7-[1m]",
+    "ANTHROPIC_MODEL": "claude-opus-4.7-[1m]"
   }
 }
 ```
 
-Optional slot-specific:
+Slot-specific overrides:
 
 ```json
 {
@@ -171,6 +128,44 @@ project-local `.claude/settings.json` and `.claude/settings.local.json` and
 applied to Claude requests only when the model supports reasoning. If it is not
 configured, Claude requests do not infer or attach a reasoning effort.
 
+## Start flags
+
+Common:
+
+| Flag | Purpose |
+| ---- | ------- |
+| `--host <host>` | Bind address. Defaults to `127.0.0.1`. |
+| `--port <port>` | Listen port. Overrides `$PORT` and the port inferred from Claude settings. |
+| `--model <model>` | Override the request model for this bridge process only; does not edit config files. |
+| `--rate-limit <seconds>` | Enforce a minimum delay between upstream requests. |
+| `--wait` | With `--rate-limit`, wait instead of returning HTTP 429. |
+
+Codex:
+
+| Flag | Purpose |
+| ---- | ------- |
+| `--no-codex-setup` | Skip writing the managed block into `~/.codex/config.toml`. |
+| `--no-prompt` | Never prompt for a Codex default model. |
+
+Claude:
+
+| Flag | Purpose |
+| ---- | ------- |
+| `--no-claude-setup` | Skip writing `ANTHROPIC_BASE_URL` into `~/.claude/settings.json`. |
+
+Diagnostics:
+
+| Flag | Purpose |
+| ---- | ------- |
+| `--debug` | Print extra upstream error diagnostics. |
+| `--show-token` | Print GitHub and Copilot tokens during startup. Sensitive; use only for local debugging. |
+
+`--debug` enables extra upstream error diagnostics in console logs.
+- Includes: token limits, stream mode, tool count, invalid tool names, and suspicious tool-schema paths.
+- Does not include: request messages, prompt text, bearer tokens, tool descriptions, or the full request body.
+
+**Review or redact debug logs before sharing them publicly.**
+
 ## Environment overrides
 
 | Variable                   | Purpose                                              |
@@ -181,8 +176,6 @@ configured, Claude requests do not infer or attach a reasoning effort.
 | `COPILOT_VSCODE_VERSION`   | Override the VS Code version sent upstream.          |
 | `MODEL_REASONING_EFFORT`   | Claude-side reasoning effort override.              |
 
-
-
 ## Supported models
 
 The bridge resolves aliases and clamps reasoning effort to what each model
@@ -265,6 +258,11 @@ Adding another CLI: drop a new translator under `src/bridges/<client>/`,
 reuse `src/services/copilot/` for upstream calls, register routes in
 `src/server.ts`, and add tests under `tests/`.
 
+## Acknowledgements
+
+Claude Code bridge notes inspired by
+[ericc-ch/copilot-api](https://github.com/ericc-ch/copilot-api). Respect.
+
 ## License
 
 MIT — see [LICENSE](./LICENSE).

package/dist/main.js

@@ -417,22 +417,6 @@ async function applyClaudeConfig(input) {
 	};
 }
 
-//#endregion
-//#region src/lib/claude-launch.ts
-const shellQuote = (value) => `'${value.replaceAll("'", "'\\''")}'`;
-const pickClaudeLaunchDefaults = (availableModels, preferredModel) => {
-	return { model: preferredModel && availableModels.includes(preferredModel) ? preferredModel : availableModels.includes("gpt-5.3-codex") ? "gpt-5.3-codex" : availableModels[0] ?? "gpt-5.3-codex" };
-};
-const buildClaudeLaunchCommand = (input) => {
-	const env = {
-		ANTHROPIC_BASE_URL: input.baseUrl,
-		ANTHROPIC_AUTH_TOKEN: "dummy",
-		DISABLE_NON_ESSENTIAL_MODEL_CALLS: "1",
-		CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC: "1"
-	};
-	return `${Object.entries(env).map(([key, value]) => `${key}=${shellQuote(value)}`).join(" ")} && claude --model ${shellQuote(input.model)}`;
-};
-
 //#endregion
 //#region src/lib/codex-config.ts
 const BEGIN_MARK = "# >>> copilot-bridge managed block — auto-generated, do not edit between markers >>>";
@@ -1353,7 +1337,11 @@ chatCompletionRoutes.post("/", async (c) => {
 	try {
 		await checkRateLimit();
 		const payload = await c.req.json();
-		const response = await createChatCompletions(c.var.config, payload, { client: "generic" });
+		const effectivePayload = runtimeState.modelOverride ? {
+			...payload,
+			model: runtimeState.modelOverride
+		} : payload;
+		const response = await createChatCompletions(c.var.config, effectivePayload, { client: "generic" });
 		if (isNonStreaming(response)) return c.json(response);
 		return streamSSE(c, async (stream) => {
 			for await (const chunk of response) await stream.writeSSE(chunk);
@@ -2197,9 +2185,13 @@ messageRoutes.post("/", async (c) => {
 	}
 	const anthropicPayload = await c.req.json();
 	const claudeSettings = await getClaudeSettings();
-	const upstreamModel = translateModelName(anthropicPayload.model, claudeSettings);
+	const effectivePayload = runtimeState.modelOverride ? {
+		...anthropicPayload,
+		model: runtimeState.modelOverride
+	} : anthropicPayload;
+	const upstreamModel = translateModelName(effectivePayload.model, claudeSettings);
 	const toolNameMapper = createAnthropicToolNameMapper(anthropicPayload.tools, { ...getToolNameMapperOptionsForModel(upstreamModel) });
-	const openAIPayload = translateToOpenAI(anthropicPayload, claudeSettings, toolNameMapper);
+	const openAIPayload = translateToOpenAI(effectivePayload, claudeSettings, toolNameMapper);
 	try {
 		const response = await createChatCompletions(config, openAIPayload, { client: "claude" });
 		if (isNonStreamingResponse(response)) return c.json(translateToAnthropic(response, toolNameMapper));
@@ -2254,7 +2246,11 @@ messageRoutes.post("/count_tokens", async (c) => {
 	try {
 		const anthropicBeta = c.req.header("anthropic-beta");
 		const anthropicPayload = await c.req.json();
-		const openAIPayload = translateToOpenAI(anthropicPayload, await getClaudeSettings());
+		const claudeSettings = await getClaudeSettings();
+		const openAIPayload = translateToOpenAI(runtimeState.modelOverride ? {
+			...anthropicPayload,
+			model: runtimeState.modelOverride
+		} : anthropicPayload, claudeSettings);
 		const selectedModel = resolveModel(openAIPayload.model);
 		if (!selectedModel) {
 			consola.warn(`Model ${openAIPayload.model} not found in registry, returning fallback token count`);
@@ -2718,7 +2714,11 @@ responsesRoutes.post("/", async (c) => {
 		if (error instanceof RateLimitError) return c.json({ error: { message: error.message } }, 429);
 		throw error;
 	}
-	const payload = normalizeCodexResponsesRequest(await c.req.json(), await readConfiguredCodexReasoningEffort());
+	const rawPayload = await c.req.json();
+	const payload = normalizeCodexResponsesRequest(runtimeState.modelOverride ? {
+		...rawPayload,
+		model: runtimeState.modelOverride
+	} : rawPayload, await readConfiguredCodexReasoningEffort());
 	const provider = getCopilotProviderContext(c.get("config"));
 	const search = new URL(c.req.url).search;
 	const capability = getModelCapability(payload.model);
@@ -2920,15 +2920,9 @@ const start = defineCommand({
 			default: true,
 			description: "Skip writing ANTHROPIC_BASE_URL into ~/.claude/settings.json."
 		},
-		"claude-code": {
-			type: "boolean",
-			default: false,
-			description: "Print a one-shot `export ... && claude` command and do not modify user config files."
-		},
-		"select-model": {
-			type: "boolean",
-			default: false,
-			description: "Force the model picker even when ~/.codex/config.toml already has a model."
+		model: {
+			type: "string",
+			description: "Override the request model for this bridge process only."
 		},
 		prompt: {
 			type: "boolean",
@@ -2973,9 +2967,12 @@ const start = defineCommand({
 		consola.info(`copilot base url: ${config.copilotBaseUrl}`);
 		const baseUrl = `http://${config.host}:${config.port}`;
 		const codexConfigPath = CODEX_DEFAULTS.configPath;
-		const isClaudeCodeMode = Boolean(args["claude-code"]);
-		if (isClaudeCodeMode) consola.info("--claude-code mode: not modifying ~/.claude/settings.json or ~/.codex/config.toml");
-		if (!isClaudeCodeMode && args["claude-setup"]) try {
+		const requestedModel = args.model !== void 0 ? String(args.model) : void 0;
+		if (requestedModel) {
+			runtimeState.modelOverride = requestedModel;
+			consola.info(`Runtime model override: ${requestedModel}`);
+		} else delete runtimeState.modelOverride;
+		if (args["claude-setup"]) try {
 			const claudeResult = await applyClaudeConfig({
 				baseUrl,
 				configPath: claudeConfigPath
@@ -2996,7 +2993,7 @@ const start = defineCommand({
 			else if (capability?.reasoning) consola.info(`codex model_reasoning_effort not set; leaving reasoning effort unset for ${chosenModel}`);
 			else consola.info(`codex model_reasoning_effort not set; leaving reasoning effort unset for ${chosenModel}`);
 		}
-		if (!isClaudeCodeMode && args["codex-setup"]) try {
+		if (args["codex-setup"]) try {
 			const result = await applyCodexConfig({
 				baseUrl: `${baseUrl}/v1`,
 				configPath: codexConfigPath,
@@ -3026,7 +3023,7 @@ const start = defineCommand({
 			``,
 			`  https://betahi.github.io/copilot-bridge?endpoint=${baseUrl}/usage`
 		].join("\n"));
-		if (!isClaudeCodeMode && args.prompt && finalPickable.length > 0 && (args["select-model"] || !chosenModel)) {
+		if (args.prompt && finalPickable.length > 0 && !chosenModel && !requestedModel) {
 			const defaultId = chosenModel && finalPickable.includes(chosenModel) ? chosenModel : finalPickable.includes("gpt-5.3-codex") ? "gpt-5.3-codex" : finalPickable[0];
 			const selected = await consola.prompt(`Select a model for codex (writes to ${codexConfigPath})`, {
 				type: "select",
@@ -3051,26 +3048,6 @@ const start = defineCommand({
 				}
 			}
 		}
-		if (isClaudeCodeMode) {
-			const defaults = pickClaudeLaunchDefaults(finalPickable, chosenModel);
-			let selectedModel = defaults.model;
-			if (args.prompt && finalPickable.length > 0) selectedModel = await consola.prompt("Select a model to use with Claude Code", {
-				type: "select",
-				options: finalPickable,
-				initial: defaults.model
-			});
-			const command = buildClaudeLaunchCommand({
-				baseUrl,
-				model: selectedModel
-			});
-			consola.box([
-				"Claude one-shot command",
-				"",
-				`  ${command}`,
-				"",
-				"  The bridge verified this path with explicit --model; current Claude CLI did not reliably honor ANTHROPIC_MODEL env defaults."
-			].join("\n"));
-		}
 		await new Promise((resolve, reject) => {
 			server.on("close", resolve);
 			server.on("error", reject);