@khalilgharbaoui/opencode-claude-code-plugin 0.9.0 → 0.9.2

package/README.md

@@ -1,5 +1,7 @@
 # @khalilgharbaoui/opencode-claude-code-plugin
 
+[![npm](https://img.shields.io/npm/v/@khalilgharbaoui/opencode-claude-code-plugin.svg)](https://www.npmjs.com/package/@khalilgharbaoui/opencode-claude-code-plugin)
+
 An [opencode](https://opencode.ai) plugin that wraps the **Claude Code CLI** (`claude`) and routes model traffic through it instead of the Anthropic HTTP API. You get to use opencode's UI, agents, MCP, and permission system while authenticating and billing through whichever method `claude` is logged into (Pro/Max plan, Bedrock, Vertex, or API key).
 
 > Maintained fork of [`unixfox/opencode-claude-code-plugin`](https://github.com/unixfox/opencode-claude-code-plugin). Published as `@khalilgharbaoui/opencode-claude-code-plugin` on npm.
@@ -101,16 +103,21 @@ This plugin drives Claude Code headlessly (`claude --print`), which Anthropic bi
 | Pro | $20 |
 | Max 5x | $100 |
 | Max 20x | $200 |
-| Team Standard | $20/seat |
-| Team Premium | $100/seat |
-| Enterprise (Standard seats) | none |
+| Team (Standard seats) | $20 |
+| Team (Premium seats) | $100 |
+| Enterprise (usage-based) | $20 |
+| Enterprise (seat-based Premium seats) | $200 |
+
+Credits are **per user, not pooled** across a team, and Standard seats on seat-based Enterprise plans aren't eligible. See Anthropic's [Agent SDK credit article](https://support.claude.com/en/articles/15036540-use-the-claude-agent-sdk-with-your-claude-plan) for the authoritative table.
 
 What this means for plugin users:
 
-- **Claim the credit once.** It's a one-time opt-in via your Claude account (claim emails started going out June 8, 2026); after that it refreshes every billing cycle. Unused credit does not roll over.
+- **Claim the credit once.** It's a one-time opt-in via your Claude account; eligible users get an email with claim instructions before June 15, 2026. After that it refreshes every billing cycle, and unused credit does not roll over.
+- **Agent SDK usage drains the credit first**, before any other source.
 - **When the credit runs out, plugin requests stop** until the next billing cycle — unless you enable usage credits in your Claude account, in which case overflow is billed at standard API rates.
 - **The credit is denominated in dollars at standard API rates**, so the Price × column above maps directly to how fast each model drains it — Fable 5 / Mythos 5 burn it 10× faster than Haiku, 2× faster than Opus 4.8.
 - **API-key auth is unaffected.** If your `claude` CLI authenticates with an Anthropic API key / Console billing instead of a subscription, nothing changes — pay-as-you-go as before.
+- **Watch for a stray `ANTHROPIC_API_KEY`.** If that variable (or `ANTHROPIC_AUTH_TOKEN`) is present in your environment, Claude Code uses it and bills pay-as-you-go — silently bypassing the subscription credit even when `claude` is logged into a plan. The plugin logs a one-time warning when it detects a key. To force subscription auth, set `ignoreAnthropicApiKey: true`, which strips the key from the `claude` spawn environment.
 - **Interactive Claude Code in your terminal is unaffected.** The change targets programmatic usage only: the Agent SDK, `claude -p`, Claude Code GitHub Actions, and third-party apps like this plugin.
 
 Two related dates:
@@ -209,6 +216,7 @@ The account model IDs are internally suffixed, for example `claude-sonnet-4-6@wo
 | `multiStepContinuation` | boolean | `true` | Append a system-prompt hint nudging Claude to chain tool calls within one turn instead of pausing between subtasks. Each opencode turn boundary requires the user to manually press "continue", so for multi-step tasks this reduces friction. Set `false` to disable. |
 | `autoContinueIncompleteTurns` | boolean \| `"smart"` | `"smart"` | Smartly continue incomplete Claude CLI results inside the same opencode turn. Reduces manual "continue" presses when Claude ends after reasoning/tool activity without a useful final answer. Set `false` to disable. |
 | `compactionModel` | string | `"claude-haiku-4-5"` | Model used when opencode invokes `/compact`. Override per-process via the `CLAUDE_CODE_COMPACTION_MODEL` env var (env wins over config). See [Compaction](#compaction). |
+| `ignoreAnthropicApiKey` | boolean | `false` | Strip `ANTHROPIC_API_KEY` / `ANTHROPIC_AUTH_TOKEN` from every spawned `claude` process so it authenticates with your logged-in subscription instead of pay-as-you-go API billing. The plugin warns once at startup whenever an API key is detected, regardless of this setting. See [Billing](#billing-change-june-15-2026-agent-sdk-credit). |
 | `interactive` | boolean | `false` | **Experimental.** Drive the interactive `claude` TUI (subscription billing) instead of headless `--print`. Requires opencode running under Bun with PTY support; silently falls back to headless otherwise. Env: `CLAUDE_CODE_INTERACTIVE_TRANSPORT=1`. See [Interactive transport](#interactive-transport-experimental). |
 | `interactiveBypass` | boolean | `false` | Deprecated/no-op with `interactive`: Claude Code's TUI shows a manual safety confirmation for `bypassPermissions`, so the plugin intentionally does not pass it. |
 | `interactiveAllowTools` | string[] | `["Bash", "Edit", "Write", "Read", "WebFetch"]` | With `interactive`: built-in tools pre-allowed without prompting (replaces the default list). MCP server wildcards (`mcp__<server>__*`) are always added from the bridged config. |
@@ -269,10 +277,6 @@ Set `interactiveSystemPrompt: false` only for diagnostics. While disabled, the i
 - **Turn timeout:** a turn that produces no terminal stop within 30 minutes is reported honestly as an error result (visible truncation), not silently ended.
 - `/compact` always uses the headless transport regardless of this setting.
 
-### Known issue
-
-- **Fresh sessions can hang at startup.** With `interactive: true`, starting a brand-new opencode session (under Bun) can leave the TUI blank and unresponsive before you can type. Resuming an existing session (`opencode --continue`) works, and once a session is running the transport is stable. Until this is fixed, leave `interactive` unset (headless default) if you hit it. Tracked for a follow-up release.
-
 ---
 
 ## Selective tool proxy

package/dist/index.d.ts

@@ -167,6 +167,7 @@ interface ClaudeCodeConfig {
     multiStepContinuation?: boolean;
     autoContinueIncompleteTurns?: boolean | "smart";
     compactionModel?: string;
+    ignoreAnthropicApiKey?: boolean;
     logging?: LoggingConfig;
 }
 interface LoggingConfig {
@@ -267,6 +268,17 @@ interface ClaudeCodeProviderSettings {
      * (see opencode's agent docs).
      */
     proxyTools?: string[];
+    /**
+     * Strip `ANTHROPIC_API_KEY` / `ANTHROPIC_AUTH_TOKEN` from the environment of
+     * every spawned `claude` process. When an API key is present, Claude Code
+     * authenticates with it (pay-as-you-go Console billing) instead of the
+     * logged-in Pro/Max subscription — silently bypassing the Agent SDK plan
+     * credit. Set this to `true` to force the CLI to fall back to its stored
+     * subscription auth. Defaults to `false` (the key is passed through, so
+     * deliberate API-key users are unaffected). Regardless of this setting, the
+     * plugin logs a one-time warning at startup when an API key is detected.
+     */
+    ignoreAnthropicApiKey?: boolean;
     /**
      * Routing for Claude's built-in `WebSearch` tool.
      *

package/dist/index.js

@@ -1252,11 +1252,15 @@ function envFlagEnabled(value) {
 function isClaudeThinkingDisabled() {
   return envFlagEnabled(process.env.CLAUDE_CODE_DISABLE_THINKING) || envFlagEnabled(process.env.CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING);
 }
-function claudeSpawnEnv() {
+function claudeSpawnEnv(opts) {
   const env = {
     ...process.env,
     TERM: "xterm-256color"
   };
+  if (opts?.ignoreAnthropicApiKey) {
+    delete env.ANTHROPIC_API_KEY;
+    delete env.ANTHROPIC_AUTH_TOKEN;
+  }
   if (!isClaudeThinkingDisabled() && process.env.CLAUDE_CODE_SHOW_THINKING_SUMMARIES === void 0) {
     env.CLAUDE_CODE_SHOW_THINKING_SUMMARIES = "1";
   }
@@ -1304,13 +1308,13 @@ function deleteClaudeSessionId(key) {
   if (claudeSessionId) clearLedger(claudeSessionId);
   claudeSessions.delete(key);
 }
-function spawnClaudeProcess(cliPath, cliArgs, cwd, sessionKey2, proxyServer, mcpHash, systemPromptFile) {
+function spawnClaudeProcess(cliPath, cliArgs, cwd, sessionKey2, proxyServer, mcpHash, systemPromptFile, ignoreAnthropicApiKey) {
   evictIfNeeded();
   log.info("spawning new claude process", { cliPath, cliArgs, cwd, sessionKey: sessionKey2 });
   const proc = spawn(cliPath, cliArgs, {
     cwd,
     stdio: ["pipe", "pipe", "pipe"],
-    env: claudeSpawnEnv(),
+    env: claudeSpawnEnv({ ignoreAnthropicApiKey }),
     shell: process.platform === "win32"
   });
   const lineEmitter = new EventEmitter();
@@ -1501,6 +1505,7 @@ var ClaudeSession = class {
       model: opts.model,
       settingSources: opts.settingSources,
       extraArgs: opts.extraArgs ?? [],
+      ignoreAnthropicApiKey: opts.ignoreAnthropicApiKey,
       cols: opts.cols ?? 200,
       rows: opts.rows ?? 50,
       bootMinMs: opts.bootMinMs ?? 3e3,
@@ -1544,7 +1549,8 @@ var ClaudeSession = class {
       env: {
         ...process.env,
         CLAUDE_CONFIG_DIR: this.o.configDir,
-        TERM: "xterm-256color"
+        TERM: "xterm-256color",
+        ...this.o.ignoreAnthropicApiKey ? { ANTHROPIC_API_KEY: void 0, ANTHROPIC_AUTH_TOKEN: void 0 } : {}
       },
       terminal: {
         cols: this.o.cols,
@@ -1868,7 +1874,8 @@ function spawnInteractiveProcess(opts) {
     // Default null = normal CLAUDE.md + settings load, matching what the
     // headless spawn does. "" (skip everything) is for fast e2e runs only.
     settingSources: opts.settingSources === void 0 ? null : opts.settingSources,
-    extraArgs
+    extraArgs,
+    ignoreAnthropicApiKey: opts.ignoreAnthropicApiKey
   });
   log.info("prepared interactive claude session", {
     cwd: opts.cwd,
@@ -2576,7 +2583,7 @@ function isAskUserQuestionTool(name) {
   const n = name.toLowerCase();
   return n === "askuserquestion" || n === "ask_user_question";
 }
-var ASK_USER_QUESTION_DENY_MESSAGE = "Your question and its options have already been presented to the operator verbatim. Stop now: end your turn without calling any more tools and without answering the question yourself. Wait for the operator's reply, which arrives as the next user message. Do not guess, assume, or proceed on their behalf.";
+var ASK_USER_QUESTION_DENY_MESSAGE = "Your question and its options have already been presented to the operator verbatim. This is NOT a cancellation or a refusal \u2014 the operator simply has not answered yet. Stop now: end your turn without calling any more tools and without answering the question yourself. Do not say the question was cancelled, skipped, or declined, and do not guess, assume, or proceed on their behalf. Wait for the operator's reply, which arrives as the next user message.";
 function denyMessageForTool(toolName, configuredDenyMessage) {
   if (isAskUserQuestionTool(toolName)) return ASK_USER_QUESTION_DENY_MESSAGE;
   return configuredDenyMessage ?? `Denied by opencode-claude-code policy for tool ${toolName}`;
@@ -2652,6 +2659,7 @@ function shouldAutoContinueIncompleteTurn(state, snapshot) {
   if (state.enabled === false) return { continue: false, reason: "disabled" };
   if (snapshot.isError) return { continue: false, reason: "error" };
   if (state.aborted) return { continue: false, reason: "aborted" };
+  if (state.sawAskUserQuestion) return { continue: false, reason: "question" };
   if (snapshot.stopReason) {
     return {
       continue: false,
@@ -3307,7 +3315,9 @@ var ClaudeCodeLanguageModel = class {
     const proc = spawn2(this.config.cliPath, cliArgs, {
       cwd,
       stdio: ["pipe", "pipe", "pipe"],
-      env: claudeSpawnEnv(),
+      env: claudeSpawnEnv({
+        ignoreAnthropicApiKey: this.config.ignoreAnthropicApiKey
+      }),
       shell: process.platform === "win32"
     });
     if (systemPromptFile) {
@@ -3718,7 +3728,8 @@ ${plan}
                 model: effectiveModelId,
                 mcpConfigPaths: mcp.paths,
                 permissionsAllow: allow,
-                systemPromptFile
+                systemPromptFile,
+                ignoreAnthropicApiKey: self.config.ignoreAnthropicApiKey
               });
               ap.mcpHash = mcp.bridgedHash;
               setActiveProcess(sk, ap);
@@ -3803,7 +3814,8 @@ ${plan}
                 sk,
                 spawnProxyServer,
                 spawnMcpHash,
-                spawnSystemPromptFile
+                spawnSystemPromptFile,
+                self.config.ignoreAnthropicApiKey
               );
               proc = ap.proc;
               lineEmitter = ap.lineEmitter;
@@ -4103,6 +4115,7 @@ ${plan}
                   } catch {
                   }
                   if (isAskUserQuestionTool(tc.name)) {
+                    autoContinueState.sawAskUserQuestion = true;
                     const askId = startTextBlock();
                     controller.enqueue({
                       type: "text-delta",
@@ -5199,6 +5212,21 @@ function pickOpencodeDirectory(input) {
   if (isUsableDirectory(ctx.worktree)) return ctx.worktree;
   return void 0;
 }
+var warnedAnthropicApiKey = false;
+function warnIfAnthropicApiKey(ignore) {
+  if (warnedAnthropicApiKey) return;
+  if (!process.env.ANTHROPIC_API_KEY && !process.env.ANTHROPIC_AUTH_TOKEN) return;
+  warnedAnthropicApiKey = true;
+  if (ignore) {
+    log.warn(
+      "ANTHROPIC_API_KEY/ANTHROPIC_AUTH_TOKEN detected; stripping it from claude spawns (ignoreAnthropicApiKey) so requests use your subscription auth, not pay-as-you-go API billing."
+    );
+  } else {
+    log.warn(
+      "ANTHROPIC_API_KEY/ANTHROPIC_AUTH_TOKEN detected; claude may bill as pay-as-you-go API usage instead of your subscription / Agent SDK credit. Set provider option `ignoreAnthropicApiKey: true` to force subscription auth."
+    );
+  }
+}
 function createClaudeCode(settings = {}) {
   if (settings.logging) {
     configureLogger({
@@ -5208,6 +5236,7 @@ function createClaudeCode(settings = {}) {
       level: settings.logging.level ?? "info"
     });
   }
+  warnIfAnthropicApiKey(settings.ignoreAnthropicApiKey);
   const cliPath = settings.cliPath ?? process.env.CLAUDE_CLI_PATH ?? "claude";
   const providerName = settings.providerID ?? settings.name ?? "claude-code";
   const proxyTools = settings.proxyTools ?? ["Bash", "Edit", "Write", "WebFetch"];
@@ -5234,6 +5263,7 @@ function createClaudeCode(settings = {}) {
       multiStepContinuation: settings.multiStepContinuation ?? true,
       autoContinueIncompleteTurns: settings.autoContinueIncompleteTurns ?? "smart",
       compactionModel: settings.compactionModel,
+      ignoreAnthropicApiKey: settings.ignoreAnthropicApiKey,
       interactive: settings.interactive,
       interactiveBypass: settings.interactiveBypass,
       interactiveAllowTools: settings.interactiveAllowTools,