{ "schema": "acpx.session.v1", "acpx_record_id": "agent:claude:acp:70d44181-7c11-4f39-b715-a254f4ddacd7:oneshot:271990e8-2d6b-4f1d-a2ff-6585c9b8fa64", "acp_session_id": "5c05fa30-0530-489c-98ee-442381760a53", "agent_command": "npx -y @agentclientprotocol/claude-agent-acp@^0.25.0", "cwd": "/home/lagoon3/.openclaw/workspace/ai-usage-dashboard", "name": "agent:claude:acp:70d44181-7c11-4f39-b715-a254f4ddacd7", "created_at": "2026-04-13T12:57:28.877Z", "last_used_at": "2026-04-13T12:58:46.744Z", "last_seq": 0, "last_request_id": "80e33f87-43f9-4a3f-a6c3-78f4b551b3df", "event_log": { "active_path": "/home/lagoon3/.acpx/sessions/agent%3Aclaude%3Aacp%3A70d44181-7c11-4f39-b715-a254f4ddacd7%3Aoneshot%3A271990e8-2d6b-4f1d-a2ff-6585c9b8fa64.stream.ndjson", "segment_count": 5, "max_segment_bytes": 67108864, "max_segments": 5, "last_write_error": null }, "closed": true, "closed_at": "2026-04-13T12:58:46.880Z", "pid": 1635290, "agent_started_at": "2026-04-13T12:57:29.375Z", "last_prompt_at": "2026-04-13T12:57:41.011Z", "protocol_version": 1, "agent_capabilities": { "_meta": { "claudeCode": { "promptQueueing": true } }, "promptCapabilities": { "image": true, "embeddedContext": true }, "mcpCapabilities": { "http": true, "sse": true }, "loadSession": true, "sessionCapabilities": { "fork": {}, "list": {}, "resume": {}, "close": {} } }, "title": null, "messages": [ { "User": { "id": "f5ebbee7-24cb-4b65-8b1b-15b90de5086c", "content": [ { "Text": "[Mon 2026-04-13 21:57 GMT+9] 이번에는 작업 범위를 아주 좁게 해서 `doctor-command`에 Claude credential 상태 표시만 추가해줘. 다른 건 하지 말고, 커밋도 하지 말 것.\n\n현재 이미 있는 것:\n- Claude credential reader/mapper/provider export\n- `status-service`에 `buildClaudeSnapshot()` + `claude` 필드 추가\n- status-service 테스트 통과\n\n이번 목표:\n1. `packages/agent/src/cli/doctor-command.js`에 Claude credential 상태 표시 추가\n2. 출력은 최소한 아래 정보면 충분\n - credentials path\n - found\n - parsed\n - authSource (`claude-cli-import`)\n3. 가능하면 doctor용 작은 pure helper를 추가해서 테스트 가능하게 할 것\n4. `packages/agent/test/...` 쪽에 관련 테스트 추가\n\n중요:\n- live network 호출 금지\n- 기존 doctor의 Codex 경로는 최대한 안 건드리기\n- 너무 큰 리팩터링 금지\n- node:test 사용\n\n테스트 최소 시나리오:\n- Claude credential 있음 -> path/found/parsed/authSource가 보임\n- Claude credential 없음 -> found/parsed false\n\n출력 형식:\n- 추가/수정 파일 목록\n- doctor에 추가된 표시 내용 요약\n- 추가한 테스트 요약\n\n정말 이것만 해줘." } ] } }, { "Agent": { "content": [ { "Thinking": { "text": "Let me look at the existing doctor-command.js and status-service.js to understand what's already there.", "signature": null } }, { "ToolUse": { "id": "toolu_01CWsxG12BBkdnKENK68Uq2Z", "name": "Find `packages/agent/src/cli/doctor-command.js`", "raw_input": "{\"pattern\":\"packages/agent/src/cli/doctor-command.js\"}", "input": { "pattern": "packages/agent/src/cli/doctor-command.js" }, "is_input_complete": true, "thought_signature": null } }, { "ToolUse": { "id": "toolu_01GmKrUhBEnuFDi4pSod55wb", "name": "Find `packages/agent/src/services/status-service.js`", "raw_input": "{\"pattern\":\"packages/agent/src/services/status-service.js\"}", "input": { "pattern": "packages/agent/src/services/status-service.js" }, "is_input_complete": true, "thought_signature": null } }, { "ToolUse": { "id": "toolu_01KTpU3Ev6ePvcz77cFnDEys", "name": "Read packages/agent/src/cli/doctor-command.js", "raw_input": "{\"file_path\":\"/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/src/cli/doctor-command.js\"}", "input": { "file_path": "/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/src/cli/doctor-command.js" }, "is_input_complete": true, "thought_signature": null } }, { "ToolUse": { "id": "toolu_01UAfsF13Cgdb5KV6tJLScqH", "name": "Read packages/agent/src/services/status-service.js", "raw_input": "{\"file_path\":\"/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/src/services/status-service.js\"}", "input": { "file_path": "/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/src/services/status-service.js" }, "is_input_complete": true, "thought_signature": null } }, { "Thinking": { "text": "Now let me look at the claude credentials reader and the existing test files.", "signature": null } }, { "Text": "Now let me look at the claude credentials reader and existing test files." }, { "ToolUse": { "id": "toolu_01R7QQcQFGtpzpxbUDMEd8Pa", "name": "Find `packages/provider-adapters/src/claude/*.js`", "raw_input": "{\"pattern\":\"packages/provider-adapters/src/claude/*.js\"}", "input": { "pattern": "packages/provider-adapters/src/claude/*.js" }, "is_input_complete": true, "thought_signature": null } }, { "ToolUse": { "id": "toolu_01TGoSLSnpz5QpJg45kmsX3z", "name": "Find `packages/agent/test/**/*.test.js`", "raw_input": "{\"pattern\":\"packages/agent/test/**/*.test.js\"}", "input": { "pattern": "packages/agent/test/**/*.test.js" }, "is_input_complete": true, "thought_signature": null } }, { "ToolUse": { "id": "toolu_011PWbvLRXKHuPa8PV3ozBrf", "name": "Read packages/provider-adapters/src/claude/read-claude-credentials.js", "raw_input": "{\"file_path\":\"/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/provider-adapters/src/claude/read-claude-credentials.js\"}", "input": { "file_path": "/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/provider-adapters/src/claude/read-claude-credentials.js" }, "is_input_complete": true, "thought_signature": null } }, { "ToolUse": { "id": "toolu_01Wvd7JQuaPoKLQppV2LDQXM", "name": "Read packages/agent/test/services/status-service.test.js", "raw_input": "{\"file_path\":\"/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/services/status-service.test.js\"}", "input": { "file_path": "/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/services/status-service.test.js" }, "is_input_complete": true, "thought_signature": null } }, { "Thinking": { "text": "Now I have enough context. I need to:\n\n1. Add Claude credential status display to `doctor-command.js` - add a `claude` subcommand or add it to the default output\n2. Add a pure helper function for formatting the Claude snapshot (testable)\n3. Add tests in `packages/agent/test/cli/doctor-command.test.js`\n\nLooking at the doctor command, the default command shows generic info. I should add `doctor claude` subcommand similar to `doctor codex`. I'll also add a small display in the main doctor summary.\n\nLet me think about the design:\n- Add `claude` as a subcommand: `ai-usage-agent doctor claude`\n\n\n- Import the existing `buildClaudeSnapshot` from status-service and create a `formatClaudeSection` pure function that takes a snapshot and returns formatted lines\n- Add the `doctor claude` subcommand handler and also include Claude info in the main doctor output\n- Write tests specifically for the `formatClaudeSection` function to ensure it handles the snapshot data correctly with and without credentials", "signature": null } }, { "Text": "Now I have all the context. I'll add:\n1. `formatClaudeSection()` pure helper in `doctor-command.js` (exported for testing)\n2. `doctor claude` subcommand + Claude summary in main doctor output\n3. Test file for the new helper" }, { "ToolUse": { "id": "toolu_01PRuiLwz2nruEP7tty32skM", "name": "Edit packages/agent/src/cli/doctor-command.js", "raw_input": "{\"replace_all\":false,\"file_path\":\"/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/src/cli/doctor-command.js\",\"old_string\":\"import { resolveAgentConfigPath } from '../config/config-path.js';\\nimport { loadAuthStore, saveAuthStore, upsertProviderAccount } from '../auth/auth-store.js';\\nimport { resolveAccount } from '../auth/account-resolver.js';\\nimport { refreshCodexToken } from '../../../provider-adapters/src/codex/index.js';\\n\\nexport async function runDoctorCommand(subcommand, args = []) {\\n if (subcommand === 'codex') {\\n await runDoctorCodex(args);\\n return;\\n }\\n\\n console.log('ai-usage-agent doctor');\\n console.log('---------------------');\\n console.log(`예상 설정 파일 경로: ${resolveAgentConfigPath()}`);\\n console.log('향후 점검 예정 항목:');\\n console.log('- provider auth 존재 여부');\\n console.log('- config 유효성');\\n console.log('- endpoint 호출 가능 여부');\\n console.log('');\\n console.log('서브커맨드:');\\n console.log(' ai-usage-agent doctor codex codex 계정 상태 점검');\\n console.log(' ai-usage-agent doctor codex --refresh-live 실제 refresh token 재발급 시도');\\n console.log(' ai-usage-agent doctor codex --account 특정 계정 지정');\\n}\",\"new_string\":\"import { resolveAgentConfigPath } from '../config/config-path.js';\\nimport { loadAuthStore, saveAuthStore, upsertProviderAccount } from '../auth/auth-store.js';\\nimport { resolveAccount } from '../auth/account-resolver.js';\\nimport { refreshCodexToken } from '../../../provider-adapters/src/codex/index.js';\\nimport { buildClaudeSnapshot } from '../services/status-service.js';\\nimport { resolveClaudeCredentialsPath } from '../../../provider-adapters/src/claude/read-claude-credentials.js';\\n\\n/**\\n * Pure helper: format Claude credential snapshot as display lines.\\n * Exported for testing.\\n */\\nexport function formatClaudeSection(snapshot) {\\n const lines = [];\\n lines.push('Claude credential 상태:');\\n lines.push(` credentialsPath: ${snapshot.credentialsPath}`);\\n lines.push(` found: ${snapshot.found}`);\\n lines.push(` parsed: ${snapshot.parsed}`);\\n lines.push(` authSource: ${snapshot.authSource}`);\\n return lines;\\n}\\n\\nexport async function runDoctorCommand(subcommand, args = []) {\\n if (subcommand === 'codex') {\\n await runDoctorCodex(args);\\n return;\\n }\\n\\n if (subcommand === 'claude') {\\n runDoctorClaude();\\n return;\\n }\\n\\n const claudeSnapshot = buildClaudeSnapshot(resolveClaudeCredentialsPath());\\n\\n console.log('ai-usage-agent doctor');\\n console.log('---------------------');\\n console.log(`예상 설정 파일 경로: ${resolveAgentConfigPath()}`);\\n console.log('');\\n for (const line of formatClaudeSection(claudeSnapshot)) {\\n console.log(line);\\n }\\n console.log('');\\n console.log('서브커맨드:');\\n console.log(' ai-usage-agent doctor codex codex 계정 상태 점검');\\n console.log(' ai-usage-agent doctor codex --refresh-live 실제 refresh token 재발급 시도');\\n console.log(' ai-usage-agent doctor codex --account 특정 계정 지정');\\n console.log(' ai-usage-agent doctor claude claude credential 상태 점검');\\n}\\n\\nfunction runDoctorClaude() {\\n const snapshot = buildClaudeSnapshot(resolveClaudeCredentialsPath());\\n console.log('ai-usage-agent doctor claude');\\n console.log('----------------------------');\\n for (const line of formatClaudeSection(snapshot)) {\\n console.log(line);\\n }\\n if (!snapshot.found) {\\n console.log('');\\n console.log('⚠ Claude credential을 찾지 못했습니다.');\\n console.log(` 예상 경로: ${snapshot.credentialsPath}`);\\n console.log(' Claude CLI로 먼저 로그인했는지 확인하세요.');\\n }\\n}\"}", "input": { "replace_all": false, "file_path": "/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/src/cli/doctor-command.js", "old_string": "import { resolveAgentConfigPath } from '../config/config-path.js';\nimport { loadAuthStore, saveAuthStore, upsertProviderAccount } from '../auth/auth-store.js';\nimport { resolveAccount } from '../auth/account-resolver.js';\nimport { refreshCodexToken } from '../../../provider-adapters/src/codex/index.js';\n\nexport async function runDoctorCommand(subcommand, args = []) {\n if (subcommand === 'codex') {\n await runDoctorCodex(args);\n return;\n }\n\n console.log('ai-usage-agent doctor');\n console.log('---------------------');\n console.log(`예상 설정 파일 경로: ${resolveAgentConfigPath()}`);\n console.log('향후 점검 예정 항목:');\n console.log('- provider auth 존재 여부');\n console.log('- config 유효성');\n console.log('- endpoint 호출 가능 여부');\n console.log('');\n console.log('서브커맨드:');\n console.log(' ai-usage-agent doctor codex codex 계정 상태 점검');\n console.log(' ai-usage-agent doctor codex --refresh-live 실제 refresh token 재발급 시도');\n console.log(' ai-usage-agent doctor codex --account 특정 계정 지정');\n}", "new_string": "import { resolveAgentConfigPath } from '../config/config-path.js';\nimport { loadAuthStore, saveAuthStore, upsertProviderAccount } from '../auth/auth-store.js';\nimport { resolveAccount } from '../auth/account-resolver.js';\nimport { refreshCodexToken } from '../../../provider-adapters/src/codex/index.js';\nimport { buildClaudeSnapshot } from '../services/status-service.js';\nimport { resolveClaudeCredentialsPath } from '../../../provider-adapters/src/claude/read-claude-credentials.js';\n\n/**\n * Pure helper: format Claude credential snapshot as display lines.\n * Exported for testing.\n */\nexport function formatClaudeSection(snapshot) {\n const lines = [];\n lines.push('Claude credential 상태:');\n lines.push(` credentialsPath: ${snapshot.credentialsPath}`);\n lines.push(` found: ${snapshot.found}`);\n lines.push(` parsed: ${snapshot.parsed}`);\n lines.push(` authSource: ${snapshot.authSource}`);\n return lines;\n}\n\nexport async function runDoctorCommand(subcommand, args = []) {\n if (subcommand === 'codex') {\n await runDoctorCodex(args);\n return;\n }\n\n if (subcommand === 'claude') {\n runDoctorClaude();\n return;\n }\n\n const claudeSnapshot = buildClaudeSnapshot(resolveClaudeCredentialsPath());\n\n console.log('ai-usage-agent doctor');\n console.log('---------------------');\n console.log(`예상 설정 파일 경로: ${resolveAgentConfigPath()}`);\n console.log('');\n for (const line of formatClaudeSection(claudeSnapshot)) {\n console.log(line);\n }\n console.log('');\n console.log('서브커맨드:');\n console.log(' ai-usage-agent doctor codex codex 계정 상태 점검');\n console.log(' ai-usage-agent doctor codex --refresh-live 실제 refresh token 재발급 시도');\n console.log(' ai-usage-agent doctor codex --account 특정 계정 지정');\n console.log(' ai-usage-agent doctor claude claude credential 상태 점검');\n}\n\nfunction runDoctorClaude() {\n const snapshot = buildClaudeSnapshot(resolveClaudeCredentialsPath());\n console.log('ai-usage-agent doctor claude');\n console.log('----------------------------');\n for (const line of formatClaudeSection(snapshot)) {\n console.log(line);\n }\n if (!snapshot.found) {\n console.log('');\n console.log('⚠ Claude credential을 찾지 못했습니다.');\n console.log(` 예상 경로: ${snapshot.credentialsPath}`);\n console.log(' Claude CLI로 먼저 로그인했는지 확인하세요.');\n }\n}" }, "is_input_complete": true, "thought_signature": null } }, { "Text": "Now add the test file:" }, { "ToolUse": { "id": "toolu_014Pv2foS9E1o8y8behiQAXF", "name": "ls /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/", "raw_input": "{\"command\":\"ls /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/\",\"description\":\"List test directory structure\"}", "input": { "command": "ls /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/", "description": "List test directory structure" }, "is_input_complete": true, "thought_signature": null } }, { "ToolUse": { "id": "toolu_01Hvng8ReYLUf5pcaZcS2MiR", "name": "ls /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/cli/", "raw_input": "{\"command\":\"ls /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/cli/\",\"description\":\"List CLI test files\"}", "input": { "command": "ls /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/cli/", "description": "List CLI test files" }, "is_input_complete": true, "thought_signature": null } }, { "ToolUse": { "id": "toolu_01Nyn9Da5TjJZZxR7ARzcYXa", "name": "Write packages/agent/test/cli/doctor-command.test.js", "raw_input": "{\"file_path\":\"/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/cli/doctor-command.test.js\",\"content\":\"import { describe, it } from 'node:test';\\nimport assert from 'node:assert/strict';\\n\\nimport { formatClaudeSection } from '../../src/cli/doctor-command.js';\\n\\n// ---------------------------------------------------------------------------\\n// formatClaudeSection — pure display helper\\n// ---------------------------------------------------------------------------\\n\\ndescribe('formatClaudeSection', () => {\\n const FAKE_PATH = '/home/user/.claude/.credentials.json';\\n\\n it('includes credentialsPath in output', () => {\\n const snapshot = {\\n credentialsPath: FAKE_PATH,\\n found: true,\\n parsed: true,\\n authSource: 'claude-cli-import',\\n };\\n const lines = formatClaudeSection(snapshot);\\n assert.ok(lines.some((l) => l.includes(FAKE_PATH)));\\n });\\n\\n it('shows found=true and parsed=true when credentials exist', () => {\\n const snapshot = {\\n credentialsPath: FAKE_PATH,\\n found: true,\\n parsed: true,\\n authSource: 'claude-cli-import',\\n };\\n const lines = formatClaudeSection(snapshot);\\n assert.ok(lines.some((l) => l.includes('found') && l.includes('true')));\\n assert.ok(lines.some((l) => l.includes('parsed') && l.includes('true')));\\n assert.ok(lines.some((l) => l.includes('authSource') && l.includes('claude-cli-import')));\\n });\\n\\n it('shows found=false and parsed=false when credentials are absent', () => {\\n const snapshot = {\\n credentialsPath: FAKE_PATH,\\n found: false,\\n parsed: false,\\n authSource: 'claude-cli-import',\\n };\\n const lines = formatClaudeSection(snapshot);\\n assert.ok(lines.some((l) => l.includes('found') && l.includes('false')));\\n assert.ok(lines.some((l) => l.includes('parsed') && l.includes('false')));\\n });\\n\\n it('returns an array with at least 4 lines', () => {\\n const snapshot = {\\n credentialsPath: FAKE_PATH,\\n found: false,\\n parsed: false,\\n authSource: 'claude-cli-import',\\n };\\n const lines = formatClaudeSection(snapshot);\\n assert.ok(lines.length >= 4);\\n });\\n});\\n\"}", "input": { "file_path": "/home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/cli/doctor-command.test.js", "content": "import { describe, it } from 'node:test';\nimport assert from 'node:assert/strict';\n\nimport { formatClaudeSection } from '../../src/cli/doctor-command.js';\n\n// ---------------------------------------------------------------------------\n// formatClaudeSection — pure display helper\n// ---------------------------------------------------------------------------\n\ndescribe('formatClaudeSection', () => {\n const FAKE_PATH = '/home/user/.claude/.credentials.json';\n\n it('includes credentialsPath in output', () => {\n const snapshot = {\n credentialsPath: FAKE_PATH,\n found: true,\n parsed: true,\n authSource: 'claude-cli-import',\n };\n const lines = formatClaudeSection(snapshot);\n assert.ok(lines.some((l) => l.includes(FAKE_PATH)));\n });\n\n it('shows found=true and parsed=true when credentials exist', () => {\n const snapshot = {\n credentialsPath: FAKE_PATH,\n found: true,\n parsed: true,\n authSource: 'claude-cli-import',\n };\n const lines = formatClaudeSection(snapshot);\n assert.ok(lines.some((l) => l.includes('found') && l.includes('true')));\n assert.ok(lines.some((l) => l.includes('parsed') && l.includes('true')));\n assert.ok(lines.some((l) => l.includes('authSource') && l.includes('claude-cli-import')));\n });\n\n it('shows found=false and parsed=false when credentials are absent', () => {\n const snapshot = {\n credentialsPath: FAKE_PATH,\n found: false,\n parsed: false,\n authSource: 'claude-cli-import',\n };\n const lines = formatClaudeSection(snapshot);\n assert.ok(lines.some((l) => l.includes('found') && l.includes('false')));\n assert.ok(lines.some((l) => l.includes('parsed') && l.includes('false')));\n });\n\n it('returns an array with at least 4 lines', () => {\n const snapshot = {\n credentialsPath: FAKE_PATH,\n found: false,\n parsed: false,\n authSource: 'claude-cli-import',\n };\n const lines = formatClaudeSection(snapshot);\n assert.ok(lines.length >= 4);\n });\n});\n" }, "is_input_complete": true, "thought_signature": null } }, { "Text": "Now verify the tests pass:" }, { "ToolUse": { "id": "toolu_01VaQV7KRxgkNAEALLUEei1i", "name": "node --test packages/agent/test/cli/doctor-command.test.js 2>&1", "raw_input": "{\"command\":\"node --test packages/agent/test/cli/doctor-command.test.js 2>&1\",\"description\":\"Run doctor-command tests\"}", "input": { "command": "node --test packages/agent/test/cli/doctor-command.test.js 2>&1", "description": "Run doctor-command tests" }, "is_input_complete": true, "thought_signature": null } }, { "Text": "모두 통과. 기존 테스트도 확인:" }, { "ToolUse": { "id": "toolu_012KVqoMChBd7x6yBHTRxr1g", "name": "node --test packages/agent/test/services/status-service.test.js 2>&1", "raw_input": "{\"command\":\"node --test packages/agent/test/services/status-service.test.js 2>&1\",\"description\":\"Run status-service tests\"}", "input": { "command": "node --test packages/agent/test/services/status-service.test.js 2>&1", "description": "Run status-service tests" }, "is_input_complete": true, "thought_signature": null } }, { "Text": "모두 통과.\n\n---\n\n**수정/추가 파일:**\n- `packages/agent/src/cli/doctor-command.js` — 수정\n- `packages/agent/test/cli/doctor-command.test.js` — 신규\n\n**doctor에 추가된 표시 내용:**\n- `doctor claude` 서브커맨드 추가 → `credentialsPath / found / parsed / authSource` 출력, 미발견 시 경고 메시지\n- 기본 `doctor` 실행 시에도 Claude credential 요약 한 블록 추가\n- `formatClaudeSection(snapshot)` — 순수 함수로 추출, 파일시스템/네트워크 호출 없음\n\n**추가한 테스트 (4개, 모두 통과):**\n- credentials 있음 → `found: true`, `parsed: true`, `authSource: claude-cli-import` 라인 포함\n- credentials 없음 → `found: false`, `parsed: false` 라인 포함\n- 항상 `credentialsPath` 포함\n- 출력 라인 수 ≥ 4" } ], "tool_results": { "toolu_01CWsxG12BBkdnKENK68Uq2Z": { "tool_use_id": "toolu_01CWsxG12BBkdnKENK68Uq2Z", "tool_name": "Find `packages/agent/src/cli/doctor-command.js`", "is_error": false, "content": { "Text": "packages/agent/src/cli/doctor-command.js" }, "output": "packages/agent/src/cli/doctor-command.js" }, "toolu_01GmKrUhBEnuFDi4pSod55wb": { "tool_use_id": "toolu_01GmKrUhBEnuFDi4pSod55wb", "tool_name": "Find `packages/agent/src/services/status-service.js`", "is_error": false, "content": { "Text": "packages/agent/src/services/status-service.js" }, "output": "packages/agent/src/services/status-service.js" }, "toolu_01KTpU3Ev6ePvcz77cFnDEys": { "tool_use_id": "toolu_01KTpU3Ev6ePvcz77cFnDEys", "tool_name": "Read packages/agent/src/cli/doctor-command.js", "is_error": false, "content": { "Text": "1\timport { resolveAgentConfigPath } from '../config/config-path.js';\n2\timport { loadAuthStore, saveAuthStore, upsertProviderAccount } from '../auth/auth-store.js';\n3\timport { resolveAccount } from '../auth/account-resolver.js';\n4\timport { refreshCodexToken } from '../../../provider-adapters/src/codex/index.js';\n5\t\n6\texport async function runDoctorCommand(subcommand, args = []) {\n7\t if (subcommand === 'codex') {\n8\t await runDoctorCodex(args);\n9\t return;\n10\t }\n11\t\n12\t console.log('ai-usage-agent doctor');\n13\t console.log('---------------------');\n14\t console.log(`예상 설정 파일 경로: ${resolveAgentConfigPath()}`);\n15\t console.log('향후 점검 예정 항목:');\n16\t console.log('- provider auth 존재 여부');\n17\t console.log('- config 유효성');\n18\t console.log('- endpoint 호출 가능 여부');\n19\t console.log('');\n20\t console.log('서브커맨드:');\n21\t console.log(' ai-usage-agent doctor codex codex 계정 상태 점검');\n22\t console.log(' ai-usage-agent doctor codex --refresh-live 실제 refresh token 재발급 시도');\n23\t console.log(' ai-usage-agent doctor codex --account 특정 계정 지정');\n24\t}\n25\t\n26\tasync function runDoctorCodex(args) {\n27\t const options = parseDoctorCodexOptions(args);\n28\t\n29\t console.log('ai-usage-agent doctor codex');\n30\t console.log('---------------------------');\n31\t\n32\t // ── Load store and resolve account ────────────────────────────────\n33\t const store = await loadAuthStore();\n34\t const provider = store.providers['openai-codex'];\n35\t\n36\t if (!provider || !provider.accounts || provider.accounts.length === 0) {\n37\t console.log('openai-codex 계정이 없습니다. `ai-usage-agent auth login codex`로 먼저 로그인하세요.');\n38\t return;\n39\t }\n40\t\n41\t const refreshableAccounts = provider.accounts.filter((account) => {\n42\t if (account.status === 'disabled') return false;\n43\t if (account.raw?.mock === true) return false;\n44\t if (!account.tokens?.refreshToken) return false;\n45\t return true;\n46\t });\n47\t\n48\t const candidateAccounts = options.account ? provider.accounts : refreshableAccounts;\n49\t\n50\t const { account, reason } = resolveAccount(candidateAccounts, {\n51\t accountIdentifier: options.account,\n52\t });\n53\t\n54\t if (!account) {\n55\t if (!options.account && provider.accounts.length > 0 && refreshableAccounts.length === 0) {\n56\t console.log('refresh 가능한 real 계정을 찾지 못했습니다.');\n57\t console.log('mock 계정만 있거나 refreshToken이 없는 계정만 존재합니다.');\n58\t console.log('`ai-usage-agent auth login codex --live-exchange`로 real token을 먼저 저장하세요.');\n59\t return;\n60\t }\n61\t\n62\t console.log(`계정을 찾을 수 없습니다. (reason: ${reason})`);\n63\t return;\n64\t }\n65\t\n66\t console.log(`대상 계정: ${account.accountKey}`);\n67\t console.log(`선택 이유: ${reason}`);\n68\t console.log(`email: ${account.email}`);\n69\t console.log(`authType: ${account.authType}`);\n70\t console.log(`source: ${account.source}`);\n71\t console.log(`expiresAt: ${account.expiresAt ?? '(없음)'}`);\n72\t\n73\t // ── Mock account guard ────────────────────────────────────────────\n74\t const isMock = account.raw?.mock === true || !account.tokens?.refreshToken;\n75\t\n76\t if (isMock) {\n77\t console.log('');\n78\t console.log('⚠ 이 계정은 mock이거나 refreshToken이 없습니다.');\n79\t console.log(' refresh 시도를 건너뜁니다.');\n80\t if (!account.tokens?.refreshToken) {\n81\t console.log(' (tokens.refreshToken이 존재하지 않음)');\n82\t }\n83\t if (account.raw?.mock) {\n84\t console.log(' (raw.mock = true)');\n85\t }\n86\t return;\n87\t }\n88\t\n89\t console.log(`refreshToken 존재: 예`);\n90\t\n91\t // ── Refresh: opt-in only ──────────────────────────────────────────\n92\t if (!options.refreshLive) {\n93\t console.log('');\n94\t console.log('refresh 상태 확인만 수행합니다. (dry-run)');\n95\t console.log('실제 refresh를 시도하려면 --refresh-live 옵션을 추가하세요.');\n96\t\n97\t if (account.expiresAt) {\n98\t const now = new Date();\n99\t const expires = new Date(account.expiresAt);\n100\t const remainingMs = expires.getTime() - now.getTime();\n101\t if (remainingMs <= 0) {\n102\t console.log(`⚠ 토큰이 만료되었습니다. (${account.e..." }, "output": "1\timport { resolveAgentConfigPath } from '../config/config-path.js';\n2\timport { loadAuthStore, saveAuthStore, upsertProviderAccount } from '../auth/auth-store.js';\n3\timport { resolveAccount } from '../auth/account-resolver.js';\n4\timport { refreshCodexToken } from '../../../provider-adapters/src/codex/index.js';\n5\t\n6\texport async function runDoctorCommand(subcommand, args = []) {\n7\t if (subcommand === 'codex') {\n8\t await runDoctorCodex(args);\n9\t return;\n10\t }\n11\t\n12\t console.log('ai-usage-agent doctor');\n13\t console.log('---------------------');\n14\t console.log(`예상 설정 파일 경로: ${resolveAgentConfigPath()}`);\n15\t console.log('향후 점검 예정 항목:');\n16\t console.log('- provider auth 존재 여부');\n17\t console.log('- config 유효성');\n18\t console.log('- endpoint 호출 가능 여부');\n19\t console.log('');\n20\t console.log('서브커맨드:');\n21\t console.log(' ai-usage-agent doctor codex codex 계정 상태 점검');\n22\t console.log(' ai-usage-agent doctor codex --refresh-live 실제 refresh token 재발급 시도');\n23\t console.log(' ai-usage-agent doctor codex --account 특정 계정 지정');\n24\t}\n25\t\n26\tasync function runDoctorCodex(args) {\n27\t const options = parseDoctorCodexOptions(args);\n28\t\n29\t console.log('ai-usage-agent doctor codex');\n30\t console.log('---------------------------');\n31\t\n32\t // ── Load store and resolve account ────────────────────────────────\n33\t const store = await loadAuthStore();\n34\t const provider = store.providers['openai-codex'];\n35\t\n36\t if (!provider || !provider.accounts || provider.accounts.length === 0) {\n37\t console.log('openai-codex 계정이 없습니다. `ai-usage-agent auth login codex`로 먼저 로그인하세요.');\n38\t return;\n39\t }\n40\t\n41\t const refreshableAccounts = provider.accounts.filter((account) => {\n42\t if (account.status === 'disabled') return false;\n43\t if (account.raw?.mock === true) return false;\n44\t if (!account.tokens?.refreshToken) return false;\n45\t return true;\n46\t });\n47\t\n48\t const candidateAccounts = options.account ? provider.accounts : refreshableAccounts;\n49\t\n50\t const { account, reason } = resolveAccount(candidateAccounts, {\n51\t accountIdentifier: options.account,\n52\t });\n53\t\n54\t if (!account) {\n55\t if (!options.account && provider.accounts.length > 0 && refreshableAccounts.length === 0) {\n56\t console.log('refresh 가능한 real 계정을 찾지 못했습니다.');\n57\t console.log('mock 계정만 있거나 refreshToken이 없는 계정만 존재합니다.');\n58\t console.log('`ai-usage-agent auth login codex --live-exchange`로 real token을 먼저 저장하세요.');\n59\t return;\n60\t }\n61\t\n62\t console.log(`계정을 찾을 수 없습니다. (reason: ${reason})`);\n63\t return;\n64\t }\n65\t\n66\t console.log(`대상 계정: ${account.accountKey}`);\n67\t console.log(`선택 이유: ${reason}`);\n68\t console.log(`email: ${account.email}`);\n69\t console.log(`authType: ${account.authType}`);\n70\t console.log(`source: ${account.source}`);\n71\t console.log(`expiresAt: ${account.expiresAt ?? '(없음)'}`);\n72\t\n73\t // ── Mock account guard ────────────────────────────────────────────\n74\t const isMock = account.raw?.mock === true || !account.tokens?.refreshToken;\n75\t\n76\t if (isMock) {\n77\t console.log('');\n78\t console.log('⚠ 이 계정은 mock이거나 refreshToken이 없습니다.');\n79\t console.log(' refresh 시도를 건너뜁니다.');\n80\t if (!account.tokens?.refreshToken) {\n81\t console.log(' (tokens.refreshToken이 존재하지 않음)');\n82\t }\n83\t if (account.raw?.mock) {\n84\t console.log(' (raw.mock = true)');\n85\t }\n86\t return;\n87\t }\n88\t\n89\t console.log(`refreshToken 존재: 예`);\n90\t\n91\t // ── Refresh: opt-in only ──────────────────────────────────────────\n92\t if (!options.refreshLive) {\n93\t console.log('');\n94\t console.log('refresh 상태 확인만 수행합니다. (dry-run)');\n95\t console.log('실제 refresh를 시도하려면 --refresh-live 옵션을 추가하세요.');\n96\t\n97\t if (account.expiresAt) {\n98\t const now = new Date();\n99\t const expires = new Date(account.expiresAt);\n100\t const remainingMs = expires.getTime() - now.getTime();\n101\t if (remainingMs <= 0) {\n102\t console.log(`⚠ 토큰이 만료되었습니다. (${account.e..." }, "toolu_01UAfsF13Cgdb5KV6tJLScqH": { "tool_use_id": "toolu_01UAfsF13Cgdb5KV6tJLScqH", "tool_name": "Read packages/agent/src/services/status-service.js", "is_error": false, "content": { "Text": "1\timport fs from 'node:fs';\n2\timport { createDefaultConfig } from '../config/default-config.js';\n3\timport { resolveAgentConfigPath } from '../config/config-path.js';\n4\timport { fetchCodexUsage, getDefaultAuthProfilesPath, readCodexAuthProfiles } from '../../../provider-adapters/src/codex/index.js';\n5\timport { resolveClaudeCredentialsPath, readClaudeCredentials } from '../../../provider-adapters/src/claude/read-claude-credentials.js';\n6\timport { SCHEMA_VERSION } from '../../../schemas/src/index.js';\n7\timport { loadAuthStore, saveAuthStore, upsertProviderAccount } from '../auth/auth-store.js';\n8\timport { resolveDefaultAccount } from '../auth/account-resolver.js';\n9\t\n10\tconst CODEX_PROVIDER_ID = 'openai-codex';\n11\t\n12\texport async function getStatusSnapshot() {\n13\t const configPath = resolveAgentConfigPath();\n14\t const config = loadConfig(configPath);\n15\t const codex = await getCodexSnapshot(config);\n16\t const claude = buildClaudeSnapshot(resolveClaudeCredentialsPath());\n17\t\n18\t return {\n19\t schemaVersion: SCHEMA_VERSION,\n20\t configPath,\n21\t providers: config.providers,\n22\t sync: config.sync,\n23\t codex,\n24\t claude,\n25\t };\n26\t}\n27\t\n28\t/**\n29\t * Exported for testing: build a Claude credential status snapshot.\n30\t * readFn is injectable so tests don't touch the filesystem.\n31\t */\n32\texport function buildClaudeSnapshot(credentialsPath, readFn = readClaudeCredentials) {\n33\t const credentials = readFn(credentialsPath);\n34\t const found = credentials !== null;\n35\t return {\n36\t detected: found,\n37\t authSource: 'claude-cli-import',\n38\t credentialsPath,\n39\t found,\n40\t parsed: found,\n41\t };\n42\t}\n43\t\n44\tasync function getCodexSnapshot(config) {\n45\t if (!config.providers?.codex?.enabled) {\n46\t return {\n47\t enabled: false,\n48\t authProfilesPath: getDefaultAuthProfilesPath(),\n49\t snapshots: []\n50\t };\n51\t }\n52\t\n53\t // Auth source priority: agent-store (real tokens) > openclaw-import (fallback)\n54\t const { profiles, authSource } = await resolveCodexProfiles();\n55\t const snapshots = [];\n56\t\n57\t for (const profile of profiles) {\n58\t try {\n59\t snapshots.push(await fetchCodexUsage(profile));\n60\t } catch (error) {\n61\t snapshots.push(createCodexFailureSnapshot(profile, error));\n62\t }\n63\t }\n64\t\n65\t return {\n66\t enabled: true,\n67\t authSource,\n68\t authProfilesPath: authSource === 'openclaw-import' ? getDefaultAuthProfilesPath() : null,\n69\t snapshots\n70\t };\n71\t}\n72\t\n73\t/**\n74\t * Resolve Codex profiles with priority: agent-store > openclaw-import.\n75\t *\n76\t * Agent-store accounts with real tokens (non-mock) are preferred.\n77\t * Falls back to OpenClaw auth-profiles.json if no real agent-store accounts exist.\n78\t */\n79\tasync function resolveCodexProfiles() {\n80\t // 1. Try agent-store first\n81\t const agentProfiles = await getAgentStoreProfiles();\n82\t\n83\t // 2. Fallback: OpenClaw auth-profiles.json\n84\t const openclawProfiles = agentProfiles.length === 0 ? readCodexAuthProfiles() : [];\n85\t return selectCodexAuthSource(agentProfiles, openclawProfiles);\n86\t}\n87\t\n88\t/**\n89\t * Exported for testing: given pre-resolved profile lists, return the active\n90\t * source and its profiles. No I/O — pure selection logic.\n91\t */\n92\texport function selectCodexAuthSource(agentProfiles, openclawProfiles) {\n93\t if (agentProfiles.length > 0) {\n94\t return { profiles: agentProfiles, authSource: 'agent-store' };\n95\t }\n96\t return { profiles: openclawProfiles, authSource: 'openclaw-import' };\n97\t}\n98\t\n99\t/**\n100\t * Exported for testing: filter an accounts array down to real (non-mock) active\n101\t * accounts. No I/O — pure predicate logic.\n102\t */\n103\texport function filterRealCodexAccounts(accounts) {\n104\t return (accounts ?? []).filter(\n105\t (a) => a.status !== 'disabled'\n106\t && a.tokens?.accessToken\n107\t && !a.raw?.mock\n108\t && !a.tokens.accessToken.startsWith('mock-')\n109\t );\n110\t}\n111\t\n112\t/**\n113\t * Load real (non-mock) Codex accounts from agent au..." }, "output": "1\timport fs from 'node:fs';\n2\timport { createDefaultConfig } from '../config/default-config.js';\n3\timport { resolveAgentConfigPath } from '../config/config-path.js';\n4\timport { fetchCodexUsage, getDefaultAuthProfilesPath, readCodexAuthProfiles } from '../../../provider-adapters/src/codex/index.js';\n5\timport { resolveClaudeCredentialsPath, readClaudeCredentials } from '../../../provider-adapters/src/claude/read-claude-credentials.js';\n6\timport { SCHEMA_VERSION } from '../../../schemas/src/index.js';\n7\timport { loadAuthStore, saveAuthStore, upsertProviderAccount } from '../auth/auth-store.js';\n8\timport { resolveDefaultAccount } from '../auth/account-resolver.js';\n9\t\n10\tconst CODEX_PROVIDER_ID = 'openai-codex';\n11\t\n12\texport async function getStatusSnapshot() {\n13\t const configPath = resolveAgentConfigPath();\n14\t const config = loadConfig(configPath);\n15\t const codex = await getCodexSnapshot(config);\n16\t const claude = buildClaudeSnapshot(resolveClaudeCredentialsPath());\n17\t\n18\t return {\n19\t schemaVersion: SCHEMA_VERSION,\n20\t configPath,\n21\t providers: config.providers,\n22\t sync: config.sync,\n23\t codex,\n24\t claude,\n25\t };\n26\t}\n27\t\n28\t/**\n29\t * Exported for testing: build a Claude credential status snapshot.\n30\t * readFn is injectable so tests don't touch the filesystem.\n31\t */\n32\texport function buildClaudeSnapshot(credentialsPath, readFn = readClaudeCredentials) {\n33\t const credentials = readFn(credentialsPath);\n34\t const found = credentials !== null;\n35\t return {\n36\t detected: found,\n37\t authSource: 'claude-cli-import',\n38\t credentialsPath,\n39\t found,\n40\t parsed: found,\n41\t };\n42\t}\n43\t\n44\tasync function getCodexSnapshot(config) {\n45\t if (!config.providers?.codex?.enabled) {\n46\t return {\n47\t enabled: false,\n48\t authProfilesPath: getDefaultAuthProfilesPath(),\n49\t snapshots: []\n50\t };\n51\t }\n52\t\n53\t // Auth source priority: agent-store (real tokens) > openclaw-import (fallback)\n54\t const { profiles, authSource } = await resolveCodexProfiles();\n55\t const snapshots = [];\n56\t\n57\t for (const profile of profiles) {\n58\t try {\n59\t snapshots.push(await fetchCodexUsage(profile));\n60\t } catch (error) {\n61\t snapshots.push(createCodexFailureSnapshot(profile, error));\n62\t }\n63\t }\n64\t\n65\t return {\n66\t enabled: true,\n67\t authSource,\n68\t authProfilesPath: authSource === 'openclaw-import' ? getDefaultAuthProfilesPath() : null,\n69\t snapshots\n70\t };\n71\t}\n72\t\n73\t/**\n74\t * Resolve Codex profiles with priority: agent-store > openclaw-import.\n75\t *\n76\t * Agent-store accounts with real tokens (non-mock) are preferred.\n77\t * Falls back to OpenClaw auth-profiles.json if no real agent-store accounts exist.\n78\t */\n79\tasync function resolveCodexProfiles() {\n80\t // 1. Try agent-store first\n81\t const agentProfiles = await getAgentStoreProfiles();\n82\t\n83\t // 2. Fallback: OpenClaw auth-profiles.json\n84\t const openclawProfiles = agentProfiles.length === 0 ? readCodexAuthProfiles() : [];\n85\t return selectCodexAuthSource(agentProfiles, openclawProfiles);\n86\t}\n87\t\n88\t/**\n89\t * Exported for testing: given pre-resolved profile lists, return the active\n90\t * source and its profiles. No I/O — pure selection logic.\n91\t */\n92\texport function selectCodexAuthSource(agentProfiles, openclawProfiles) {\n93\t if (agentProfiles.length > 0) {\n94\t return { profiles: agentProfiles, authSource: 'agent-store' };\n95\t }\n96\t return { profiles: openclawProfiles, authSource: 'openclaw-import' };\n97\t}\n98\t\n99\t/**\n100\t * Exported for testing: filter an accounts array down to real (non-mock) active\n101\t * accounts. No I/O — pure predicate logic.\n102\t */\n103\texport function filterRealCodexAccounts(accounts) {\n104\t return (accounts ?? []).filter(\n105\t (a) => a.status !== 'disabled'\n106\t && a.tokens?.accessToken\n107\t && !a.raw?.mock\n108\t && !a.tokens.accessToken.startsWith('mock-')\n109\t );\n110\t}\n111\t\n112\t/**\n113\t * Load real (non-mock) Codex accounts from agent au..." }, "toolu_01R7QQcQFGtpzpxbUDMEd8Pa": { "tool_use_id": "toolu_01R7QQcQFGtpzpxbUDMEd8Pa", "tool_name": "Find `packages/provider-adapters/src/claude/*.js`", "is_error": false, "content": { "Text": "packages/provider-adapters/src/claude/read-claude-credentials.js\npackages/provider-adapters/src/claude/map-claude-credentials.js\npackages/provider-adapters/src/claude/index.js" }, "output": "packages/provider-adapters/src/claude/read-claude-credentials.js\npackages/provider-adapters/src/claude/map-claude-credentials.js\npackages/provider-adapters/src/claude/index.js" }, "toolu_01TGoSLSnpz5QpJg45kmsX3z": { "tool_use_id": "toolu_01TGoSLSnpz5QpJg45kmsX3z", "tool_name": "Find `packages/agent/test/**/*.test.js`", "is_error": false, "content": { "Text": "packages/agent/test/auth/auth-store.test.js\npackages/agent/test/auth/account-resolver.test.js\npackages/agent/test/auth/token-claims.test.js\npackages/agent/test/services/status-service.test.js" }, "output": "packages/agent/test/auth/auth-store.test.js\npackages/agent/test/auth/account-resolver.test.js\npackages/agent/test/auth/token-claims.test.js\npackages/agent/test/services/status-service.test.js" }, "toolu_011PWbvLRXKHuPa8PV3ozBrf": { "tool_use_id": "toolu_011PWbvLRXKHuPa8PV3ozBrf", "tool_name": "Read packages/provider-adapters/src/claude/read-claude-credentials.js", "is_error": false, "content": { "Text": "1\timport fs from 'node:fs';\n2\timport path from 'node:path';\n3\timport os from 'node:os';\n4\t\n5\tconst DEFAULT_CREDENTIALS_PATH = path.join(\n6\t os.homedir(),\n7\t '.claude',\n8\t '.credentials.json'\n9\t);\n10\t\n11\texport function resolveClaudeCredentialsPath(base = os.homedir()) {\n12\t return path.join(base, '.claude', '.credentials.json');\n13\t}\n14\t\n15\texport function parseClaudeCredentials(raw) {\n16\t if (!raw || typeof raw !== 'object') {\n17\t return null;\n18\t }\n19\t const oauth = raw.claudeAiOauth;\n20\t if (!oauth || typeof oauth !== 'object') {\n21\t return null;\n22\t }\n23\t return oauth;\n24\t}\n25\t\n26\texport function readClaudeCredentials(credentialsPath = DEFAULT_CREDENTIALS_PATH) {\n27\t if (!fs.existsSync(credentialsPath)) {\n28\t return null;\n29\t }\n30\t const raw = JSON.parse(fs.readFileSync(credentialsPath, 'utf8'));\n31\t return parseClaudeCredentials(raw);\n32\t}\n33\t\n34\texport function getDefaultCredentialsPath() {\n35\t return DEFAULT_CREDENTIALS_PATH;\n36\t}\n37\t" }, "output": "1\timport fs from 'node:fs';\n2\timport path from 'node:path';\n3\timport os from 'node:os';\n4\t\n5\tconst DEFAULT_CREDENTIALS_PATH = path.join(\n6\t os.homedir(),\n7\t '.claude',\n8\t '.credentials.json'\n9\t);\n10\t\n11\texport function resolveClaudeCredentialsPath(base = os.homedir()) {\n12\t return path.join(base, '.claude', '.credentials.json');\n13\t}\n14\t\n15\texport function parseClaudeCredentials(raw) {\n16\t if (!raw || typeof raw !== 'object') {\n17\t return null;\n18\t }\n19\t const oauth = raw.claudeAiOauth;\n20\t if (!oauth || typeof oauth !== 'object') {\n21\t return null;\n22\t }\n23\t return oauth;\n24\t}\n25\t\n26\texport function readClaudeCredentials(credentialsPath = DEFAULT_CREDENTIALS_PATH) {\n27\t if (!fs.existsSync(credentialsPath)) {\n28\t return null;\n29\t }\n30\t const raw = JSON.parse(fs.readFileSync(credentialsPath, 'utf8'));\n31\t return parseClaudeCredentials(raw);\n32\t}\n33\t\n34\texport function getDefaultCredentialsPath() {\n35\t return DEFAULT_CREDENTIALS_PATH;\n36\t}\n37\t" }, "toolu_01Wvd7JQuaPoKLQppV2LDQXM": { "tool_use_id": "toolu_01Wvd7JQuaPoKLQppV2LDQXM", "tool_name": "Read packages/agent/test/services/status-service.test.js", "is_error": false, "content": { "Text": "1\timport { describe, it } from 'node:test';\n2\timport assert from 'node:assert/strict';\n3\t\n4\timport {\n5\t selectCodexAuthSource,\n6\t filterRealCodexAccounts,\n7\t buildClaudeSnapshot,\n8\t} from '../../src/services/status-service.js';\n9\t\n10\t// ---------------------------------------------------------------------------\n11\t// filterRealCodexAccounts\n12\t// ---------------------------------------------------------------------------\n13\t\n14\tdescribe('filterRealCodexAccounts', () => {\n15\t it('keeps an active account with a real access token', () => {\n16\t const accounts = [\n17\t {\n18\t accountKey: 'codex:alice',\n19\t status: 'active',\n20\t tokens: { accessToken: 'real-token-abc' },\n21\t },\n22\t ];\n23\t const result = filterRealCodexAccounts(accounts);\n24\t assert.equal(result.length, 1);\n25\t assert.equal(result[0].accountKey, 'codex:alice');\n26\t });\n27\t\n28\t it('excludes accounts whose accessToken starts with \"mock-\"', () => {\n29\t const accounts = [\n30\t {\n31\t accountKey: 'codex:mock-user',\n32\t status: 'active',\n33\t tokens: { accessToken: 'mock-token-xyz' },\n34\t },\n35\t ];\n36\t assert.equal(filterRealCodexAccounts(accounts).length, 0);\n37\t });\n38\t\n39\t it('excludes accounts with raw.mock set to true', () => {\n40\t const accounts = [\n41\t {\n42\t accountKey: 'codex:mock-flagged',\n43\t status: 'active',\n44\t tokens: { accessToken: 'some-token' },\n45\t raw: { mock: true },\n46\t },\n47\t ];\n48\t assert.equal(filterRealCodexAccounts(accounts).length, 0);\n49\t });\n50\t\n51\t it('excludes disabled accounts even with a real token', () => {\n52\t const accounts = [\n53\t {\n54\t accountKey: 'codex:disabled',\n55\t status: 'disabled',\n56\t tokens: { accessToken: 'real-token' },\n57\t },\n58\t ];\n59\t assert.equal(filterRealCodexAccounts(accounts).length, 0);\n60\t });\n61\t\n62\t it('excludes accounts with no accessToken', () => {\n63\t const accounts = [{ accountKey: 'codex:no-token', status: 'active', tokens: {} }];\n64\t assert.equal(filterRealCodexAccounts(accounts).length, 0);\n65\t });\n66\t\n67\t it('handles null/undefined gracefully', () => {\n68\t assert.equal(filterRealCodexAccounts(null).length, 0);\n69\t assert.equal(filterRealCodexAccounts(undefined).length, 0);\n70\t });\n71\t\n72\t it('returns only real accounts when mixed with mock ones', () => {\n73\t const accounts = [\n74\t { accountKey: 'codex:real', status: 'active', tokens: { accessToken: 'real-token' } },\n75\t { accountKey: 'codex:mock', status: 'active', tokens: { accessToken: 'mock-token' } },\n76\t { accountKey: 'codex:flagged', status: 'active', tokens: { accessToken: 'token' }, raw: { mock: true } },\n77\t ];\n78\t const result = filterRealCodexAccounts(accounts);\n79\t assert.equal(result.length, 1);\n80\t assert.equal(result[0].accountKey, 'codex:real');\n81\t });\n82\t});\n83\t\n84\t// ---------------------------------------------------------------------------\n85\t// selectCodexAuthSource — auth source selection priority\n86\t// ---------------------------------------------------------------------------\n87\t\n88\tdescribe('selectCodexAuthSource', () => {\n89\t const agentProfile = { id: 'codex:alice', accessToken: 'real-token' };\n90\t const openclawProfile = { id: 'openclaw-profile', accessToken: 'oc-token' };\n91\t\n92\t it('uses agent-store when real agent profiles exist', () => {\n93\t const result = selectCodexAuthSource([agentProfile], [openclawProfile]);\n94\t assert.equal(result.authSource, 'agent-store');\n95\t assert.deepStrictEqual(result.profiles, [agentProfile]);\n96\t });\n97\t\n98\t it('falls back to openclaw-import when agent profiles list is empty', () => {\n99\t const result = selectCodexAuthSource([], [openclawProfile]);\n100\t assert.equal(result.authSource, 'openclaw-import');\n101\t assert.deepStrictEqual(result.profiles, [openclawProfile]);\n102\t });\n103\t\n104\t it('returns openclaw-import with empty profiles when bo..." }, "output": "1\timport { describe, it } from 'node:test';\n2\timport assert from 'node:assert/strict';\n3\t\n4\timport {\n5\t selectCodexAuthSource,\n6\t filterRealCodexAccounts,\n7\t buildClaudeSnapshot,\n8\t} from '../../src/services/status-service.js';\n9\t\n10\t// ---------------------------------------------------------------------------\n11\t// filterRealCodexAccounts\n12\t// ---------------------------------------------------------------------------\n13\t\n14\tdescribe('filterRealCodexAccounts', () => {\n15\t it('keeps an active account with a real access token', () => {\n16\t const accounts = [\n17\t {\n18\t accountKey: 'codex:alice',\n19\t status: 'active',\n20\t tokens: { accessToken: 'real-token-abc' },\n21\t },\n22\t ];\n23\t const result = filterRealCodexAccounts(accounts);\n24\t assert.equal(result.length, 1);\n25\t assert.equal(result[0].accountKey, 'codex:alice');\n26\t });\n27\t\n28\t it('excludes accounts whose accessToken starts with \"mock-\"', () => {\n29\t const accounts = [\n30\t {\n31\t accountKey: 'codex:mock-user',\n32\t status: 'active',\n33\t tokens: { accessToken: 'mock-token-xyz' },\n34\t },\n35\t ];\n36\t assert.equal(filterRealCodexAccounts(accounts).length, 0);\n37\t });\n38\t\n39\t it('excludes accounts with raw.mock set to true', () => {\n40\t const accounts = [\n41\t {\n42\t accountKey: 'codex:mock-flagged',\n43\t status: 'active',\n44\t tokens: { accessToken: 'some-token' },\n45\t raw: { mock: true },\n46\t },\n47\t ];\n48\t assert.equal(filterRealCodexAccounts(accounts).length, 0);\n49\t });\n50\t\n51\t it('excludes disabled accounts even with a real token', () => {\n52\t const accounts = [\n53\t {\n54\t accountKey: 'codex:disabled',\n55\t status: 'disabled',\n56\t tokens: { accessToken: 'real-token' },\n57\t },\n58\t ];\n59\t assert.equal(filterRealCodexAccounts(accounts).length, 0);\n60\t });\n61\t\n62\t it('excludes accounts with no accessToken', () => {\n63\t const accounts = [{ accountKey: 'codex:no-token', status: 'active', tokens: {} }];\n64\t assert.equal(filterRealCodexAccounts(accounts).length, 0);\n65\t });\n66\t\n67\t it('handles null/undefined gracefully', () => {\n68\t assert.equal(filterRealCodexAccounts(null).length, 0);\n69\t assert.equal(filterRealCodexAccounts(undefined).length, 0);\n70\t });\n71\t\n72\t it('returns only real accounts when mixed with mock ones', () => {\n73\t const accounts = [\n74\t { accountKey: 'codex:real', status: 'active', tokens: { accessToken: 'real-token' } },\n75\t { accountKey: 'codex:mock', status: 'active', tokens: { accessToken: 'mock-token' } },\n76\t { accountKey: 'codex:flagged', status: 'active', tokens: { accessToken: 'token' }, raw: { mock: true } },\n77\t ];\n78\t const result = filterRealCodexAccounts(accounts);\n79\t assert.equal(result.length, 1);\n80\t assert.equal(result[0].accountKey, 'codex:real');\n81\t });\n82\t});\n83\t\n84\t// ---------------------------------------------------------------------------\n85\t// selectCodexAuthSource — auth source selection priority\n86\t// ---------------------------------------------------------------------------\n87\t\n88\tdescribe('selectCodexAuthSource', () => {\n89\t const agentProfile = { id: 'codex:alice', accessToken: 'real-token' };\n90\t const openclawProfile = { id: 'openclaw-profile', accessToken: 'oc-token' };\n91\t\n92\t it('uses agent-store when real agent profiles exist', () => {\n93\t const result = selectCodexAuthSource([agentProfile], [openclawProfile]);\n94\t assert.equal(result.authSource, 'agent-store');\n95\t assert.deepStrictEqual(result.profiles, [agentProfile]);\n96\t });\n97\t\n98\t it('falls back to openclaw-import when agent profiles list is empty', () => {\n99\t const result = selectCodexAuthSource([], [openclawProfile]);\n100\t assert.equal(result.authSource, 'openclaw-import');\n101\t assert.deepStrictEqual(result.profiles, [openclawProfile]);\n102\t });\n103\t\n104\t it('returns openclaw-import with empty profiles when bo..." }, "toolu_01PRuiLwz2nruEP7tty32skM": { "tool_use_id": "toolu_01PRuiLwz2nruEP7tty32skM", "tool_name": "Edit packages/agent/src/cli/doctor-command.js", "is_error": false, "content": { "Text": "The file /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/src/cli/doctor-command.js has been updated successfully." }, "output": "The file /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/src/cli/doctor-command.js has been updated successfully." }, "toolu_014Pv2foS9E1o8y8behiQAXF": { "tool_use_id": "toolu_014Pv2foS9E1o8y8behiQAXF", "tool_name": "ls /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/", "is_error": false, "content": { "Text": "auth\ncli\nservices" }, "output": "auth\ncli\nservices" }, "toolu_01Hvng8ReYLUf5pcaZcS2MiR": { "tool_use_id": "toolu_01Hvng8ReYLUf5pcaZcS2MiR", "tool_name": "ls /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/cli/", "is_error": false, "content": { "Text": "(Bash completed with no output)" }, "output": "(Bash completed with no output)" }, "toolu_01Nyn9Da5TjJZZxR7ARzcYXa": { "tool_use_id": "toolu_01Nyn9Da5TjJZZxR7ARzcYXa", "tool_name": "Write packages/agent/test/cli/doctor-command.test.js", "is_error": false, "content": { "Text": "File created successfully at: /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/cli/doctor-command.test.js" }, "output": "File created successfully at: /home/lagoon3/.openclaw/workspace/ai-usage-dashboard/packages/agent/test/cli/doctor-command.test.js" }, "toolu_01VaQV7KRxgkNAEALLUEei1i": { "tool_use_id": "toolu_01VaQV7KRxgkNAEALLUEei1i", "tool_name": "node --test packages/agent/test/cli/doctor-command.test.js 2>&1", "is_error": false, "content": { "Text": "▶ formatClaudeSection\n ✔ includes credentialsPath in output (0.851322ms)\n ✔ shows found=true and parsed=true when credentials exist (0.234944ms)\n ✔ shows found=false and parsed=false when credentials are absent (0.185593ms)\n ✔ returns an array with at least 4 lines (0.153617ms)\n✔ formatClaudeSection (3.509397ms)\nℹ tests 4\nℹ suites 1\nℹ pass 4\nℹ fail 0\nℹ cancelled 0\nℹ skipped 0\nℹ todo 0\nℹ duration_ms 77.969741" }, "output": "▶ formatClaudeSection\n ✔ includes credentialsPath in output (0.851322ms)\n ✔ shows found=true and parsed=true when credentials exist (0.234944ms)\n ✔ shows found=false and parsed=false when credentials are absent (0.185593ms)\n ✔ returns an array with at least 4 lines (0.153617ms)\n✔ formatClaudeSection (3.509397ms)\nℹ tests 4\nℹ suites 1\nℹ pass 4\nℹ fail 0\nℹ cancelled 0\nℹ skipped 0\nℹ todo 0\nℹ duration_ms 77.969741" }, "toolu_012KVqoMChBd7x6yBHTRxr1g": { "tool_use_id": "toolu_012KVqoMChBd7x6yBHTRxr1g", "tool_name": "node --test packages/agent/test/services/status-service.test.js 2>&1", "is_error": false, "content": { "Text": "▶ filterRealCodexAccounts\n ✔ keeps an active account with a real access token (0.94957ms)\n ✔ excludes accounts whose accessToken starts with \"mock-\" (0.162266ms)\n ✔ excludes accounts with raw.mock set to true (0.156618ms)\n ✔ excludes disabled accounts even with a real token (0.224501ms)\n ✔ excludes accounts with no accessToken (0.227876ms)\n ✔ handles null/undefined gracefully (0.166543ms)\n ✔ returns only real accounts when mixed with mock ones (0.181298ms)\n✔ filterRealCodexAccounts (4.299825ms)\n▶ selectCodexAuthSource\n ✔ uses agent-store when real agent profiles exist (0.871528ms)\n ✔ falls back to openclaw-import when agent profiles list is empty (0.216171ms)\n ✔ returns openclaw-import with empty profiles when both lists are empty (0.233761ms)\n✔ selectCodexAuthSource (1.603156ms)\n▶ buildClaudeSnapshot\n ✔ returns detected=true and authSource=claude-cli-import when credentials are found (0.288859ms)\n ✔ returns detected=false when credentials are not found (0.214939ms)\n ✔ always includes credentialsPath in the snapshot (0.234342ms)\n✔ buildClaudeSnapshot (0.92058ms)\nℹ tests 13\nℹ suites 3\nℹ pass 13\nℹ fail 0\nℹ cancelled 0\nℹ skipped 0\nℹ todo 0\nℹ duration_ms 89.922738" }, "output": "▶ filterRealCodexAccounts\n ✔ keeps an active account with a real access token (0.94957ms)\n ✔ excludes accounts whose accessToken starts with \"mock-\" (0.162266ms)\n ✔ excludes accounts with raw.mock set to true (0.156618ms)\n ✔ excludes disabled accounts even with a real token (0.224501ms)\n ✔ excludes accounts with no accessToken (0.227876ms)\n ✔ handles null/undefined gracefully (0.166543ms)\n ✔ returns only real accounts when mixed with mock ones (0.181298ms)\n✔ filterRealCodexAccounts (4.299825ms)\n▶ selectCodexAuthSource\n ✔ uses agent-store when real agent profiles exist (0.871528ms)\n ✔ falls back to openclaw-import when agent profiles list is empty (0.216171ms)\n ✔ returns openclaw-import with empty profiles when both lists are empty (0.233761ms)\n✔ selectCodexAuthSource (1.603156ms)\n▶ buildClaudeSnapshot\n ✔ returns detected=true and authSource=claude-cli-import when credentials are found (0.288859ms)\n ✔ returns detected=false when credentials are not found (0.214939ms)\n ✔ always includes credentialsPath in the snapshot (0.234342ms)\n✔ buildClaudeSnapshot (0.92058ms)\nℹ tests 13\nℹ suites 3\nℹ pass 13\nℹ fail 0\nℹ cancelled 0\nℹ skipped 0\nℹ todo 0\nℹ duration_ms 89.922738" } } } } ], "updated_at": "2026-04-13T12:58:46.739Z", "cumulative_token_usage": {}, "request_token_usage": {}, "acpx": { "available_commands": [ "update-config", "debug", "simplify", "batch", "loop", "schedule", "claude-api", "compact", "context", "heapdump", "init", "review", "security-review", "extra-usage", "insights" ] } }