ai-whisper 0.9.0 → 0.10.0

package/README.md

@@ -59,7 +59,7 @@ You pair any two of four agents — `claude`, `codex`, `ezio`, and `agy`. ai-whi
 - **ezio** *(optional)* — bundled with ai-whisper; mount it with `whisper collab mount ezio`, no separate install.
 - **agy** *(optional)* — the `agy` command (Antigravity CLI), signed in. Mount it with `whisper collab mount agy` (manual-mount parity; no auto-launch via `collab start`).
 - **Node.js 22+**.
-- **An LLM evaluator with credentials** — workflows are gated by it and refuse to start without it. See [Evaluator configuration](docs/evaluator-configuration.md).
+- **An LLM evaluator with credentials** — workflows are gated by it and refuse to start without it. It supports four providers: **Anthropic** (default), a local **Ollama** model, **OpenAI** (and any OpenAI-compatible backend via a `baseURL` — Azure, OpenRouter, vLLM, LM Studio, …), or reusing an **already-mounted agent CLI** (`claude`/`codex`/`agy`) in non-interactive mode (no separate key — it reuses that CLI's own auth). See [Evaluator configuration](docs/evaluator-configuration.md).
 - **tmux** *(optional)* — only for `whisper collab start`, which auto-arranges both agents into panes. The mount flow below does not need it.
 
 > **Platform support:** ai-whisper is terminal-native and Unix-oriented — it drives interactive PTY sessions, so it runs on **macOS and Linux**. It is **not supported natively on Windows**: `whisper collab mount` / `reconnect` require a Unix tty-backed shell and will exit with an error pointing here. On Windows, run ai-whisper inside **[WSL2](https://learn.microsoft.com/windows/wsl/install)** — install Node, your agent CLI, and ai-whisper inside the WSL2 distro and run the commands there, where everything works as-is.

package/dist/bin/broker-daemon.js

@@ -5918,7 +5918,45 @@ function createWorkflowEventBridge(input) {
 import * as crypto3 from "node:crypto";
 import Anthropic from "@anthropic-ai/sdk";
 import { Ollama } from "ollama";
+import OpenAI from "openai";
 import { z as z18 } from "zod";
+
+// src/runtime/agent-cli-presets.ts
+import { spawn as nodeSpawn } from "node:child_process";
+import { accessSync, constants, statSync as statSync3 } from "node:fs";
+import { delimiter, join as join6 } from "node:path";
+var defaultSpawn = (command, args, options) => nodeSpawn(command, [...args], options);
+var PRESETS = {
+  claude: { executable: "claude", execArgs: ["-p"], promptVia: "arg" },
+  codex: { executable: "codex", execArgs: ["exec"], promptVia: "arg" },
+  agy: { executable: "agy", execArgs: ["-p"], promptVia: "arg" }
+};
+function resolveAgentCliInvocation(input) {
+  const preset = PRESETS[input.agent];
+  return {
+    executable: input.executable ?? preset.executable,
+    execArgs: input.execArgs ?? preset.execArgs,
+    promptVia: input.promptVia ?? preset.promptVia
+  };
+}
+function isExecutableOnPath(executable) {
+  const isExecFile = (p) => {
+    try {
+      if (!statSync3(p).isFile()) return false;
+      accessSync(p, constants.X_OK);
+      return true;
+    } catch {
+      return false;
+    }
+  };
+  if (executable.includes("/") || executable.includes("\\")) return isExecFile(executable);
+  const dirs = (process.env.PATH ?? "").split(delimiter).filter(Boolean);
+  const exts = process.platform === "win32" ? ["", ".exe", ".cmd", ".bat"] : [""];
+  return dirs.some((dir) => exts.some((ext) => isExecFile(join6(dir, executable + ext))));
+}
+
+// src/runtime/relay-orchestrator-evaluator.ts
+var defaultOpenAIFactory = (opts) => new OpenAI(opts);
 var baseFields = {
   confidence: z18.number().min(0).max(1),
   reason: z18.string()
@@ -6158,7 +6196,10 @@ function selectBranch(payload) {
   }
   return legacyBranch;
 }
+var ProviderUnavailableError = class extends Error {
+};
 function isProviderUnavailableError(error) {
+  if (error instanceof ProviderUnavailableError) return true;
   if (!(error instanceof Error)) return false;
   const code = error.code;
   if (code === "ECONNREFUSED" || code === "ENOTFOUND" || code === "ETIMEDOUT" || code === "ECONNRESET")
@@ -6222,6 +6263,77 @@ function buildOllamaCaller(config) {
     return { raw: response.message.content };
   };
 }
+function buildOpenAICaller(config) {
+  const client = (config.createClient ?? defaultOpenAIFactory)({
+    apiKey: config.apiKey,
+    ...config.baseURL ? { baseURL: config.baseURL } : {}
+  });
+  const model = config.model;
+  return async function(systemPrompt, payload, jsonSchema) {
+    const response = await client.chat.completions.create({
+      model,
+      messages: [
+        { role: "system", content: systemPrompt },
+        { role: "user", content: JSON.stringify(payload) }
+      ],
+      // Non-strict json_schema: schema-shaped guidance only; branch.parse() is authoritative.
+      // `strict` is intentionally omitted (see spec §5.2.1) — do not set it true.
+      response_format: { type: "json_schema", json_schema: { name: "verdict", schema: jsonSchema } },
+      temperature: 0.3
+    });
+    const raw = response.choices[0]?.message.content ?? "";
+    return {
+      raw,
+      ...typeof response.usage?.prompt_tokens === "number" ? { inputTokens: response.usage.prompt_tokens } : {},
+      ...typeof response.usage?.completion_tokens === "number" ? { outputTokens: response.usage.completion_tokens } : {}
+    };
+  };
+}
+function buildAgentCliCaller(config) {
+  const { executable, execArgs, promptVia } = resolveAgentCliInvocation(config);
+  const spawnImpl = config.spawnImpl ?? defaultSpawn;
+  return function(systemPrompt, payload) {
+    const prompt = `${systemPrompt}
+
+=== INPUT (JSON) ===
+${JSON.stringify(payload)}
+=== END INPUT ===
+
+Reply with ONLY the JSON object described above \u2014 no prose, no code fence.`;
+    return new Promise((resolve2, reject) => {
+      const child = promptVia === "arg" ? spawnImpl(executable, [...execArgs, prompt], { stdio: ["ignore", "pipe", "pipe"] }) : spawnImpl(executable, execArgs, { stdio: ["pipe", "pipe", "pipe"] });
+      let stdout = "";
+      let stderr = "";
+      let settled = false;
+      child.stdout.on("data", (chunk) => {
+        stdout += String(chunk);
+      });
+      child.stderr.on("data", (chunk) => {
+        stderr += String(chunk);
+      });
+      child.on("error", (err) => {
+        if (settled) return;
+        settled = true;
+        reject(new ProviderUnavailableError(`agent-cli spawn failed (${executable}): ${err.message}`));
+      });
+      child.on("close", (code) => {
+        if (settled) return;
+        settled = true;
+        if (code !== 0) {
+          reject(new ProviderUnavailableError(`agent-cli ${executable} exited with code ${code}: ${stderr.trim()}`));
+          return;
+        }
+        resolve2({ raw: stdout });
+      });
+      if (promptVia === "stdin") {
+        child.stdin.on("error", () => {
+        });
+        child.stdin.write(prompt);
+        child.stdin.end();
+      }
+    });
+  };
+}
 function buildSingleProviderCaller(config) {
   if (config.provider === "anthropic") {
     const call2 = buildAnthropicCaller(config);
@@ -6264,6 +6376,46 @@ function buildSingleProviderCaller(config) {
       }
     };
   }
+  if (config.provider === "openai") {
+    const call2 = buildOpenAICaller(config);
+    return async function(payload, branch) {
+      const started = Date.now();
+      let providerResult;
+      try {
+        providerResult = await call2(branch.systemPrompt, payload, branch.jsonSchema);
+      } catch (callErr) {
+        const providerLatencyMs2 = Date.now() - started;
+        return { ok: false, error: callErr instanceof Error ? callErr : new Error(String(callErr)), raw: null, inputTokens: null, outputTokens: null, providerLatencyMs: providerLatencyMs2 };
+      }
+      const providerLatencyMs = Date.now() - started;
+      try {
+        const verdict = branch.parse(providerResult.raw);
+        return { ok: true, verdict, raw: providerResult.raw, inputTokens: providerResult.inputTokens ?? null, outputTokens: providerResult.outputTokens ?? null, providerLatencyMs };
+      } catch (parseErr) {
+        return { ok: false, error: parseErr instanceof Error ? parseErr : new Error(String(parseErr)), raw: providerResult.raw, inputTokens: providerResult.inputTokens ?? null, outputTokens: providerResult.outputTokens ?? null, providerLatencyMs };
+      }
+    };
+  }
+  if (config.provider === "agent-cli") {
+    const call2 = buildAgentCliCaller(config);
+    return async function(payload, branch) {
+      const started = Date.now();
+      let raw;
+      try {
+        ({ raw } = await call2(branch.systemPrompt, payload));
+      } catch (callErr) {
+        const providerLatencyMs2 = Date.now() - started;
+        return { ok: false, error: callErr instanceof Error ? callErr : new Error(String(callErr)), raw: null, inputTokens: null, outputTokens: null, providerLatencyMs: providerLatencyMs2 };
+      }
+      const providerLatencyMs = Date.now() - started;
+      try {
+        const verdict = branch.parse(raw);
+        return { ok: true, verdict, raw, inputTokens: null, outputTokens: null, providerLatencyMs };
+      } catch (parseErr) {
+        return { ok: false, error: parseErr instanceof Error ? parseErr : new Error(String(parseErr)), raw, inputTokens: null, outputTokens: null, providerLatencyMs };
+      }
+    };
+  }
   const call = buildOllamaCaller(config);
   return async function(payload, branch) {
     const started = Date.now();
@@ -6710,8 +6862,8 @@ function writeOwnPidToBrokerDaemon(db, input) {
 }
 
 // src/runtime/evaluator-config.ts
-import { readFileSync as readFileSync2, statSync as statSync3 } from "node:fs";
-import { join as join6 } from "node:path";
+import { readFileSync as readFileSync2, statSync as statSync4 } from "node:fs";
+import { join as join7 } from "node:path";
 
 // src/runtime/state-root.ts
 import os from "node:os";
@@ -6745,7 +6897,7 @@ function warnIfLoosePerms(path2) {
   if (process.platform === "win32") return;
   let mode;
   try {
-    mode = statSync3(path2).mode;
+    mode = statSync4(path2).mode;
   } catch {
     return;
   }
@@ -6773,31 +6925,46 @@ function loadEvaluatorConfig() {
   const root = getStateRoot();
   let dotenv = {};
   try {
-    dotenv = parseDotEnv(readFileSync2(join6(root, ".env"), "utf8"));
+    dotenv = parseDotEnv(readFileSync2(join7(root, ".env"), "utf8"));
   } catch (err) {
     if (err.code !== "ENOENT") throw err;
   }
   const envGet = (k) => process.env[k] ?? dotenv[k];
-  const authPath = join6(root, "auth.json");
+  const authPath = join7(root, "auth.json");
   warnIfLoosePerms(authPath);
   const auth = readJsonFile(authPath, "auth.json");
-  const config = readJsonFile(join6(root, "config.json"), "config.json");
+  const config = readJsonFile(join7(root, "config.json"), "config.json");
   const evalCfg = config?.evaluator ?? {};
   const evalOllama = evalCfg.ollama ?? {};
-  const provider = (envGet("AI_WHISPER_EVALUATOR_PROVIDER") ?? evalCfg.provider) === "ollama" ? "ollama" : "anthropic";
+  const provider = envGet("AI_WHISPER_EVALUATOR_PROVIDER") ?? evalCfg.provider;
+  const resolvedProvider = provider === "ollama" || provider === "openai" || provider === "agent-cli" ? provider : "anthropic";
   const rawFallback = envGet("AI_WHISPER_EVALUATOR_FALLBACK") ?? evalCfg.fallback;
-  const fallback = rawFallback === "anthropic" || rawFallback === "ollama" ? rawFallback : null;
+  const fallback = rawFallback === "anthropic" || rawFallback === "ollama" || rawFallback === "openai" || rawFallback === "agent-cli" ? rawFallback : null;
   const apiKey = envGet("ANTHROPIC_API_KEY") ?? auth?.ANTHROPIC_API_KEY ?? null;
+  const evalOpenai = evalCfg.openai ?? {};
+  const openaiKey = envGet("OPENAI_API_KEY") ?? auth?.OPENAI_API_KEY ?? null;
+  const evalAgentCli = evalCfg.agentCli ?? {};
+  const rawAgent = envGet("AI_WHISPER_EVALUATOR_AGENT_CLI_AGENT") ?? evalAgentCli.agent;
+  const agent = rawAgent === "claude" || rawAgent === "codex" || rawAgent === "agy" ? rawAgent : null;
   return {
-    provider,
+    provider: resolvedProvider,
     fallback,
-    anthropic: {
-      apiKey: apiKey && apiKey.length > 0 ? apiKey : null,
-      model: evalCfg.anthropicModel ?? null
-    },
+    anthropic: { apiKey: apiKey && apiKey.length > 0 ? apiKey : null, model: evalCfg.anthropicModel ?? null },
     ollama: {
       host: envGet("AI_WHISPER_EVALUATOR_OLLAMA_HOST") ?? evalOllama.host ?? null,
       model: envGet("AI_WHISPER_EVALUATOR_OLLAMA_MODEL") ?? evalOllama.model ?? null
+    },
+    openai: {
+      apiKey: openaiKey && openaiKey.length > 0 ? openaiKey : null,
+      model: envGet("AI_WHISPER_EVALUATOR_OPENAI_MODEL") ?? evalOpenai.model ?? null,
+      baseURL: envGet("AI_WHISPER_EVALUATOR_OPENAI_BASE_URL") ?? evalOpenai.baseURL ?? null
+    },
+    agentCli: {
+      agent,
+      executable: evalAgentCli.executable ?? null,
+      execArgs: Array.isArray(evalAgentCli.execArgs) ? evalAgentCli.execArgs : null,
+      promptVia: evalAgentCli.promptVia === "arg" || evalAgentCli.promptVia === "stdin" ? evalAgentCli.promptVia : null,
+      model: evalAgentCli.model ?? null
     }
   };
 }
@@ -6807,6 +6974,21 @@ function computeEvaluatorStatus(cfg, ctx) {
   if (cfg.provider === "anthropic" && cfg.anthropic.apiKey === null) {
     return "missing_anthropic_key";
   }
+  if (cfg.provider === "openai") {
+    if (cfg.openai.apiKey === null) return "missing_openai_key";
+    if (cfg.openai.model === null) return "invalid_config";
+  }
+  if (cfg.provider === "agent-cli") {
+    if (cfg.agentCli.agent === null) return "invalid_config";
+    const { executable } = resolveAgentCliInvocation({
+      agent: cfg.agentCli.agent,
+      executable: cfg.agentCli.executable,
+      execArgs: cfg.agentCli.execArgs,
+      promptVia: cfg.agentCli.promptVia
+    });
+    const exists = (ctx.executableExists ?? isExecutableOnPath)(executable);
+    if (!exists) return "agent_cli_unavailable";
+  }
   return "ready";
 }
 
@@ -6815,7 +6997,9 @@ var NOT_CONFIGURED = {
   provider: "anthropic",
   fallback: null,
   anthropic: { apiKey: null, model: null },
-  ollama: { host: null, model: null }
+  ollama: { host: null, model: null },
+  openai: { apiKey: null, model: null, baseURL: null },
+  agentCli: { agent: null, executable: null, execArgs: null, promptVia: null, model: null }
 };
 function recordEvaluatorStatus(db, input) {
   const status = computeEvaluatorStatus(input.resolved ?? NOT_CONFIGURED, {
@@ -6828,7 +7012,7 @@ function recordEvaluatorStatus(db, input) {
 
 // src/bin/broker-daemon.ts
 import { execFile as execFile2 } from "node:child_process";
-import { join as join7 } from "node:path";
+import { join as join8 } from "node:path";
 
 // src/runtime/cli-package-info.ts
 import { readFileSync as readFileSync3 } from "node:fs";
@@ -6878,7 +7062,7 @@ if (collabId) {
     });
     workflowEventBridge.start();
     eventSocket = await createEventSocketServer({
-      socketPath: join7(getStateSocketsDir(), `events-${collabId}.sock`),
+      socketPath: join8(getStateSocketsDir(), `events-${collabId}.sock`),
       events: [broker.events, externalEvents],
       engineVersion: resolveCliVersion()
     });
@@ -6905,10 +7089,30 @@ function providerConfigFrom(kind) {
     if (!resolved || resolved.anthropic.apiKey === null) return null;
     return { provider: "anthropic", apiKey: resolved.anthropic.apiKey };
   }
+  if (kind === "openai") {
+    if (!resolved || resolved.openai.apiKey === null || resolved.openai.model === null) return null;
+    return {
+      provider: "openai",
+      apiKey: resolved.openai.apiKey,
+      model: resolved.openai.model,
+      ...resolved.openai.baseURL ? { baseURL: resolved.openai.baseURL } : {}
+    };
+  }
+  if (kind === "ollama") {
+    return {
+      provider: "ollama",
+      ...resolved?.ollama.host ? { host: resolved.ollama.host } : {},
+      ...resolved?.ollama.model ? { model: resolved.ollama.model } : {}
+    };
+  }
+  if (!resolved || resolved.agentCli.agent === null) return null;
   return {
-    provider: "ollama",
-    ...resolved?.ollama.host ? { host: resolved.ollama.host } : {},
-    ...resolved?.ollama.model ? { model: resolved.ollama.model } : {}
+    provider: "agent-cli",
+    agent: resolved.agentCli.agent,
+    ...resolved.agentCli.executable ? { executable: resolved.agentCli.executable } : {},
+    ...resolved.agentCli.execArgs ? { execArgs: resolved.agentCli.execArgs } : {},
+    ...resolved.agentCli.promptVia ? { promptVia: resolved.agentCli.promptVia } : {},
+    ...resolved.agentCli.model ? { model: resolved.agentCli.model } : {}
   };
 }
 var collab = broker.control.getCollab(collabId);

package/dist/bin/companion-agent.js

@@ -7506,6 +7506,8 @@ function haxSpawnEnv(base = process.env, transcriptPath) {
   const env = { ...base, HAX_EXTRA_SKILLS_DIR: aiEzioGlobalSkillsDir(base) };
   if (transcriptPath)
     env.HAX_TRANSCRIPT = transcriptPath;
+  if (env.HAX_COMPACT_AUTO === void 0)
+    env.HAX_COMPACT_AUTO = "0";
   return env;
 }
 function spawnHax(options = {}) {
@@ -7828,7 +7830,9 @@ var Session = class {
   async spawnAndPump(options) {
     this._transcriptPath = options.transcriptPath;
     const gen = this.generation;
-    const spawned = (this.options.spawn ?? spawnHax)(options);
+    const overrides = this.options.engineEnvOverrides;
+    const spawnOptions = overrides ? { ...options, env: { ...options.env ?? process.env, ...overrides } } : options;
+    const spawned = (this.options.spawn ?? spawnHax)(spawnOptions);
     this.spawned = spawned;
     spawned.child.on("exit", (code, signal) => {
       if (gen !== this.generation)
@@ -8861,6 +8865,7 @@ function profileEnv(profile, parentEnv) {
     env.HAX_REASONING_EFFORT = profile.effort;
   else
     delete env.HAX_REASONING_EFFORT;
+  env.HAX_COMPACT_AUTO = "1";
   return env;
 }
 function validateProfile(profile, parentEnv) {
@@ -9948,6 +9953,14 @@ function builtinCommands(listCommands) {
     {
       name: "compact",
       summary: "summarize old history and free context",
+      // NOTE (post-hax-sync): upstream hax now ships its own `/compact` slash
+      // command (`agent_compact`) that silently rewrites conversation history
+      // inside the engine. This ezio-owned handler intercepts `/compact` here,
+      // routes it to `ctx.compactor.compactNow()` (the harness-controlled protocol
+      // `compact` control), and returns `action: "handled"` — so the literal text
+      // "/compact" is NEVER forwarded as a raw `submit` to the hax session where
+      // the engine's own slash registry would trigger `agent_compact`.
+      // Do NOT remove this command or change its return path to `action: "submit"`.
       run: async (ctx) => {
         if (!ctx.compactor) {
           ctx.write("compaction unavailable\n");

package/dist/bin/whisper.js

@@ -10548,6 +10548,8 @@ function haxSpawnEnv(base = process.env, transcriptPath) {
   const env = { ...base, HAX_EXTRA_SKILLS_DIR: aiEzioGlobalSkillsDir(base) };
   if (transcriptPath)
     env.HAX_TRANSCRIPT = transcriptPath;
+  if (env.HAX_COMPACT_AUTO === void 0)
+    env.HAX_COMPACT_AUTO = "0";
   return env;
 }
 function spawnHax(options = {}) {
@@ -10870,7 +10872,9 @@ var Session = class {
   async spawnAndPump(options) {
     this._transcriptPath = options.transcriptPath;
     const gen = this.generation;
-    const spawned = (this.options.spawn ?? spawnHax)(options);
+    const overrides = this.options.engineEnvOverrides;
+    const spawnOptions = overrides ? { ...options, env: { ...options.env ?? process.env, ...overrides } } : options;
+    const spawned = (this.options.spawn ?? spawnHax)(spawnOptions);
     this.spawned = spawned;
     spawned.child.on("exit", (code, signal) => {
       if (gen !== this.generation)
@@ -11904,6 +11908,7 @@ function profileEnv(profile, parentEnv) {
     env.HAX_REASONING_EFFORT = profile.effort;
   else
     delete env.HAX_REASONING_EFFORT;
+  env.HAX_COMPACT_AUTO = "1";
   return env;
 }
 function validateProfile(profile, parentEnv) {
@@ -12991,6 +12996,14 @@ function builtinCommands(listCommands) {
     {
       name: "compact",
       summary: "summarize old history and free context",
+      // NOTE (post-hax-sync): upstream hax now ships its own `/compact` slash
+      // command (`agent_compact`) that silently rewrites conversation history
+      // inside the engine. This ezio-owned handler intercepts `/compact` here,
+      // routes it to `ctx.compactor.compactNow()` (the harness-controlled protocol
+      // `compact` control), and returns `action: "handled"` — so the literal text
+      // "/compact" is NEVER forwarded as a raw `submit` to the hax session where
+      // the engine's own slash registry would trigger `agent_compact`.
+      // Do NOT remove this command or change its return path to `action: "submit"`.
       run: async (ctx) => {
         if (!ctx.compactor) {
           ctx.write("compaction unavailable\n");
@@ -13919,10 +13932,10 @@ function compareSemver(a, b) {
 
 // src/generated/ezio-provenance.ts
 var EZIO_PROVENANCE = {
-  ezioCliVersion: "0.2.0-beta.5",
-  ezioGitSha: "09022cd",
-  builtAt: "2026-06-27T22:52:35.353Z",
-  whisperVersion: "0.9.0"
+  ezioCliVersion: "0.3.0",
+  ezioGitSha: "ffd95dc",
+  builtAt: "2026-06-30T04:51:15.900Z",
+  whisperVersion: "0.10.0"
 };
 
 // src/ezio-provenance-types.ts
@@ -17533,8 +17546,43 @@ import Database2 from "better-sqlite3";
 import { existsSync as existsSync15 } from "node:fs";
 
 // src/runtime/evaluator-config.ts
-import { readFileSync as readFileSync10, statSync as statSync4 } from "node:fs";
-import { join as join23 } from "node:path";
+import { readFileSync as readFileSync10, statSync as statSync5 } from "node:fs";
+import { join as join24 } from "node:path";
+
+// src/runtime/agent-cli-presets.ts
+import { spawn as nodeSpawn } from "node:child_process";
+import { accessSync, constants, statSync as statSync4 } from "node:fs";
+import { delimiter, join as join23 } from "node:path";
+var PRESETS = {
+  claude: { executable: "claude", execArgs: ["-p"], promptVia: "arg" },
+  codex: { executable: "codex", execArgs: ["exec"], promptVia: "arg" },
+  agy: { executable: "agy", execArgs: ["-p"], promptVia: "arg" }
+};
+function resolveAgentCliInvocation(input) {
+  const preset = PRESETS[input.agent];
+  return {
+    executable: input.executable ?? preset.executable,
+    execArgs: input.execArgs ?? preset.execArgs,
+    promptVia: input.promptVia ?? preset.promptVia
+  };
+}
+function isExecutableOnPath(executable) {
+  const isExecFile = (p) => {
+    try {
+      if (!statSync4(p).isFile()) return false;
+      accessSync(p, constants.X_OK);
+      return true;
+    } catch {
+      return false;
+    }
+  };
+  if (executable.includes("/") || executable.includes("\\")) return isExecFile(executable);
+  const dirs = (process.env.PATH ?? "").split(delimiter).filter(Boolean);
+  const exts = process.platform === "win32" ? ["", ".exe", ".cmd", ".bat"] : [""];
+  return dirs.some((dir) => exts.some((ext) => isExecFile(join23(dir, executable + ext))));
+}
+
+// src/runtime/evaluator-config.ts
 function parseDotEnv(text) {
   const out = {};
   for (const rawLine of text.split(/\r?\n/)) {
@@ -17556,7 +17604,7 @@ function warnIfLoosePerms(path4) {
   if (process.platform === "win32") return;
   let mode;
   try {
-    mode = statSync4(path4).mode;
+    mode = statSync5(path4).mode;
   } catch {
     return;
   }
@@ -17584,31 +17632,46 @@ function loadEvaluatorConfig() {
   const root = getStateRoot();
   let dotenv = {};
   try {
-    dotenv = parseDotEnv(readFileSync10(join23(root, ".env"), "utf8"));
+    dotenv = parseDotEnv(readFileSync10(join24(root, ".env"), "utf8"));
   } catch (err) {
     if (err.code !== "ENOENT") throw err;
   }
   const envGet = (k) => process.env[k] ?? dotenv[k];
-  const authPath = join23(root, "auth.json");
+  const authPath = join24(root, "auth.json");
   warnIfLoosePerms(authPath);
   const auth = readJsonFile(authPath, "auth.json");
-  const config = readJsonFile(join23(root, "config.json"), "config.json");
+  const config = readJsonFile(join24(root, "config.json"), "config.json");
   const evalCfg = config?.evaluator ?? {};
   const evalOllama = evalCfg.ollama ?? {};
-  const provider = (envGet("AI_WHISPER_EVALUATOR_PROVIDER") ?? evalCfg.provider) === "ollama" ? "ollama" : "anthropic";
+  const provider = envGet("AI_WHISPER_EVALUATOR_PROVIDER") ?? evalCfg.provider;
+  const resolvedProvider = provider === "ollama" || provider === "openai" || provider === "agent-cli" ? provider : "anthropic";
   const rawFallback = envGet("AI_WHISPER_EVALUATOR_FALLBACK") ?? evalCfg.fallback;
-  const fallback = rawFallback === "anthropic" || rawFallback === "ollama" ? rawFallback : null;
+  const fallback = rawFallback === "anthropic" || rawFallback === "ollama" || rawFallback === "openai" || rawFallback === "agent-cli" ? rawFallback : null;
   const apiKey = envGet("ANTHROPIC_API_KEY") ?? auth?.ANTHROPIC_API_KEY ?? null;
+  const evalOpenai = evalCfg.openai ?? {};
+  const openaiKey = envGet("OPENAI_API_KEY") ?? auth?.OPENAI_API_KEY ?? null;
+  const evalAgentCli = evalCfg.agentCli ?? {};
+  const rawAgent = envGet("AI_WHISPER_EVALUATOR_AGENT_CLI_AGENT") ?? evalAgentCli.agent;
+  const agent = rawAgent === "claude" || rawAgent === "codex" || rawAgent === "agy" ? rawAgent : null;
   return {
-    provider,
+    provider: resolvedProvider,
     fallback,
-    anthropic: {
-      apiKey: apiKey && apiKey.length > 0 ? apiKey : null,
-      model: evalCfg.anthropicModel ?? null
-    },
+    anthropic: { apiKey: apiKey && apiKey.length > 0 ? apiKey : null, model: evalCfg.anthropicModel ?? null },
     ollama: {
       host: envGet("AI_WHISPER_EVALUATOR_OLLAMA_HOST") ?? evalOllama.host ?? null,
       model: envGet("AI_WHISPER_EVALUATOR_OLLAMA_MODEL") ?? evalOllama.model ?? null
+    },
+    openai: {
+      apiKey: openaiKey && openaiKey.length > 0 ? openaiKey : null,
+      model: envGet("AI_WHISPER_EVALUATOR_OPENAI_MODEL") ?? evalOpenai.model ?? null,
+      baseURL: envGet("AI_WHISPER_EVALUATOR_OPENAI_BASE_URL") ?? evalOpenai.baseURL ?? null
+    },
+    agentCli: {
+      agent,
+      executable: evalAgentCli.executable ?? null,
+      execArgs: Array.isArray(evalAgentCli.execArgs) ? evalAgentCli.execArgs : null,
+      promptVia: evalAgentCli.promptVia === "arg" || evalAgentCli.promptVia === "stdin" ? evalAgentCli.promptVia : null,
+      model: evalAgentCli.model ?? null
     }
   };
 }
@@ -17618,13 +17681,28 @@ function computeEvaluatorStatus(cfg, ctx) {
   if (cfg.provider === "anthropic" && cfg.anthropic.apiKey === null) {
     return "missing_anthropic_key";
   }
+  if (cfg.provider === "openai") {
+    if (cfg.openai.apiKey === null) return "missing_openai_key";
+    if (cfg.openai.model === null) return "invalid_config";
+  }
+  if (cfg.provider === "agent-cli") {
+    if (cfg.agentCli.agent === null) return "invalid_config";
+    const { executable } = resolveAgentCliInvocation({
+      agent: cfg.agentCli.agent,
+      executable: cfg.agentCli.executable,
+      execArgs: cfg.agentCli.execArgs,
+      promptVia: cfg.agentCli.promptVia
+    });
+    const exists = (ctx.executableExists ?? isExecutableOnPath)(executable);
+    if (!exists) return "agent_cli_unavailable";
+  }
   return "ready";
 }
 function isEvaluatorReady(status) {
   return status === "ready" || status === "unknown";
 }
 function isEvaluatorPreflightBlocked(status) {
-  return status === "missing_anthropic_key" || status === "invalid_config";
+  return status === "missing_anthropic_key" || status === "missing_openai_key" || status === "agent_cli_unavailable" || status === "invalid_config";
 }
 
 // src/commands/collab/status.ts
@@ -17971,7 +18049,7 @@ async function runCollabTell(input) {
 }
 
 // src/runtime/launcher.ts
-import { execSync as execSync3, spawn as nodeSpawn } from "node:child_process";
+import { execSync as execSync3, spawn as nodeSpawn2 } from "node:child_process";
 import { dirname as dirname8, resolve as resolve4 } from "node:path";
 import { fileURLToPath as fileURLToPath5 } from "node:url";
 var __dirname = dirname8(fileURLToPath5(import.meta.url));
@@ -18017,7 +18095,7 @@ function buildRelayMonitorCommand(envPrefix, workspaceRoot) {
   return `AI_WHISPER_WORKSPACE_ROOT=${shellQuote(workspaceRoot)} ${envPrefix} ${shellQuote(process.execPath)} ${shellQuote(relayMonitorBinPath)}`;
 }
 function defaultSpawn(command) {
-  const child = nodeSpawn("sh", ["-c", command], {
+  const child = nodeSpawn2("sh", ["-c", command], {
     detached: true,
     stdio: "ignore"
   });
@@ -18116,9 +18194,17 @@ async function runWorkflowStart(deps) {
       throw new Error(
         'Evaluator is not configured: ANTHROPIC_API_KEY is missing. Add it to ~/.ai-whisper/auth.json as { "ANTHROPIC_API_KEY": "sk-ant-..." } (mode 600), then restart the daemon: whisper collab stop and re-mount. ' + EVALUATOR_README_HINT
       );
+    } else if (evaluatorStatus === "missing_openai_key") {
+      throw new Error(
+        'Evaluator is not configured: OPENAI_API_KEY is missing. Add it to ~/.ai-whisper/auth.json as { "OPENAI_API_KEY": "sk-..." } (mode 600) or export OPENAI_API_KEY, then restart the daemon: whisper collab stop and re-mount. ' + EVALUATOR_README_HINT
+      );
+    } else if (evaluatorStatus === "agent_cli_unavailable") {
+      throw new Error(
+        "Evaluator is not configured: the agent-cli executable was not found on PATH. Install/mount the agent CLI (claude/codex/agy) or set evaluator.agentCli.executable to its absolute path, then restart the daemon: whisper collab stop and re-mount. " + EVALUATOR_README_HINT
+      );
     } else {
       throw new Error(
-        "Evaluator configuration is invalid: ~/.ai-whisper/auth.json or config.json contains malformed JSON. Fix the file, then restart the daemon: whisper collab stop and re-mount. " + EVALUATOR_README_HINT
+        "Evaluator configuration is invalid: a required setting is missing or ~/.ai-whisper/auth.json / config.json contains malformed JSON. For provider=openai set evaluator.openai.model (AI_WHISPER_EVALUATOR_OPENAI_MODEL); for provider=agent-cli set the agent (AI_WHISPER_EVALUATOR_AGENT_CLI_AGENT). Fix the config, then restart the daemon: whisper collab stop and re-mount. " + EVALUATOR_README_HINT
       );
     }
   }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-whisper",
-  "version": "0.9.0",
+  "version": "0.10.0",
   "description": "Terminal-first relay for paired AI coding agents (Claude + Codex), driven by structured workflows.",
   "license": "Apache-2.0",
   "repository": {
@@ -43,6 +43,7 @@
     "nanoid": "^5.1.5",
     "node-pty": "^1.1.0",
     "ollama": "^0.6.3",
+    "openai": "^6.45.0",
     "react": "^19.2.6",
     "string-width": "^8",
     "zod": "^3.24.2"
@@ -52,10 +53,10 @@
     "@types/react": "^19.2.14",
     "ink-testing-library": "^4.0.0",
     "@ai-whisper/adapter-antigravity": "0.0.0",
-    "@ai-whisper/adapter-claude": "0.0.0",
     "@ai-whisper/adapter-codex": "0.0.0",
-    "@ai-whisper/broker": "0.0.0",
+    "@ai-whisper/adapter-claude": "0.0.0",
     "@ai-whisper/adapter-ai-ezio": "0.0.0",
+    "@ai-whisper/broker": "0.0.0",
     "@ai-whisper/companion-core": "0.0.0",
     "@ai-whisper/shared": "0.0.0"
   },