RepoRadar hands-on verification log run_id: cohort-20260714-qwen-code-local-read-agent-workflow entity_id: gh:qwenlm/qwen-code mode: isolated_node started_at: 2026-07-14T05:08:04.657022Z completed_at: 2026-07-14T05:08:10.668655Z duration_seconds: 6.011 installation_setup_minutes_ceiling: 1 command: "C:\Program Files\nodejs\node.EXE" workflow.mjs setup_commands: "C:\Program Files\nodejs\npm.CMD" install --ignore-scripts --no-audit --no-fund --no-save @qwen-code/qwen-code@0.19.9 credential_policy: child environment allowlisted; credential-like variables excluded; known token patterns redacted from retained output network_policy: isolated package resolution may contact package registries; telemetry and Promptfoo sharing disabled; no model/provider credentials supplied fixture_count: 4 artifact_expectation_count: 2 timeout_seconds: 180 timed_out: false exit_code: 1 expected_marker: CHECK_OK cli=qwen requests=2 tool=read_file unchanged=true expected_marker_observed: false result: failed cleanup: Per-check temporary home and work directory removed. ===== FIXTURE MANIFEST ===== package.json: bytes=33 sha256=a90fc33418afa2b9cbf4768524b021135b965ecdf993457505bfae3ac44a8428 fixture/marker.txt: bytes=29 sha256=363fc8c2915bc29265af71bc5eafee4d3387188b2ab871e689624c9d73d17f50 spec.json: bytes=906 sha256=38fc66c03ed91924ff83ba4473ed097082e9fda76db050fa6e2a0c270176c96d workflow.mjs: bytes=12760 sha256=b8780046ce25c254b9a36260ff0c85b9458bdf58067675aae2f60cbbe9ef873b ===== ARTIFACT EVIDENCE ===== result.json: exists=false validation_error=FileNotFoundError: [Errno 2] No such file or directory: '\\AppData\\Local\\Temp\\reporadar-qwen-code-local-read-agent-workflow-zzbo_0yx\\work\\result.json' transcript.json: exists=false validation_error=FileNotFoundError: [Errno 2] No such file or directory: '\\AppData\\Local\\Temp\\reporadar-qwen-code-local-read-agent-workflow-zzbo_0yx\\work\\transcript.json' ===== STDOUT ===== ===== SETUP COMMAND 1 STDOUT ===== added 7 packages in 4s ===== CLI STDOUT ===== ===== STDERR ===== ===== SETUP COMMAND 1 STDERR ===== (node:28240) [DEP0190] DeprecationWarning: Passing args to a child process with shell option true can lead to security vulnerabilities, as the arguments are not escaped, only concatenated. (Use `node.EXE --trace-deprecation ...` to show where the warning was created) ===== CLI STDERR ===== Cannot use both a positional prompt and the --prompt (-p) flag together Usage: qwen [options] [command] Qwen Code - Launch an interactive CLI, use -p/--prompt for non-interactive mode Commands: qwen [query..] Launch Qwen Code CLI [default] qwen mcp Manage MCP servers qwen extensions Manage Qwen Code extensions. qwen auth Configure authentication (removed) qwen hooks Manage Qwen Code hooks (use /hooks in interactive mode). [aliases: hook] qwen channel Manage messaging channels (Telegram, Discord, etc.) qwen review Internal helpers used by the /review skill (PR worktree setup, context fetch, rules loading, presubmit checks, cleanup) qwen serve Run Qwen Code as a local HTTP daemon (Stage 1 experimental: --http-bridge) qwen sessions Manage Qwen Code sessions qwen update Check for Qwen Code updates and install if available Positionals: query Positional prompt. Defaults to one-shot; use -i/--prompt-interactive for interactive. Options: --telemetry Enable telemetry? This flag specifically controls if telemetry is sent. Other --telemetry-* flags set specific values but do not enable telemetry on their own. [deprecated: Use the "telemetry.enabled" setting in settings.json instead. This flag will be removed in a future version.] [boolean] --telemetry-target Set the telemetry target (local or gcp). Overrides settings files. [deprecated: Use the "telemetry.target" setting in settings.json instead. This flag will be removed in a future version.] [string] [choices: "local", "gcp"] --telemetry-otlp-endpoint Set the OTLP endpoint for telemetry. Overrides environment variables and settings files. [deprecated: Use the "telemetry.otlpEndpoint" setting in settings.json instead. This flag will be removed in a future version.] [string] --telemetry-otlp-protocol Set the OTLP protocol for telemetry (grpc or http). Overrides settings files. [deprecated: Use the "telemetry.otlpProtocol" setting in settings.json instead. This flag will be removed in a future version.] [string] [choices: "grpc", "http"] --telemetry-log-prompts Enable or disable logging of user prompts for telemetry. Overrides settings files. [deprecated: Use the "telemetry.logPrompts" setting in settings.json instead. This flag will be removed in a future version.] [boolean] --telemetry-outfile Redirect all telemetry output to the specified file. [deprecated: Use the "telemetry.outfile" setting in settings.json instead. This flag will be removed in a future version.] [string] -d, --debug Run in debug mode? [boolean] [default: false] --bare Minimal mode: skip implicit startup auto-discovery and only honor explicitly provided CLI inputs. [boolean] [default: false] --safe-mode Disable all customizations (context files, hooks, extensions, skills, MCP servers) for troubleshooting. [boolean] --proxy Proxy for Qwen Code, like schema://user:password@host:port [deprecated: Use the "proxy" setting in settings.json instead. This flag will be removed in a future version.] [string] --insecure Skip TLS certificate verification for API connections (for self-signed certs in trusted/lab environments). Equivalent to setting QWEN_TLS_INSECURE=1. WARNING: removes protection against man-in-the-middle attacks. [boolean] [default: false] --chat-recording Enable chat recording to disk. If false, chat history is not saved and --continue/--resume will not work. [boolean] -m, --model Model [string] --fallback-model Fallback model(s) for capacity errors (429/503/529), repeatable or comma-separated (max 3) [array] -p, --prompt Prompt. Appended to input on stdin (if any). [deprecated: Use the positional prompt instead. This flag will be removed in a future version.] [string] -i, --prompt-interactive Execute the provided prompt and continue in interactive mode [string] --system-prompt Override the main session system prompt for this run. Can be combined with --append-system-prompt. [string] --append-system-prompt Append instructions to the main session system prompt for this run. Can be combined with --system-prompt. [string] -s, --sandbox Run in sandbox? [boolean] --sandbox-image Sandbox image URI. [deprecated: Use the "tools.sandboxImage" setting in settings.json instead. This flag will be removed in a future version.] [string] -y, --yolo Automatically accept all actions (aka YOLO mode, see https://www.youtube.com/watch?v=xvFZjo5PgG0 for more details)? [boolean] [default: false] --approval-mode Set the approval mode: plan (plan only), default (prompt for approval), auto-edit (auto-approve edit tools), auto (LLM classifier auto-approves safe actions, blocks risky ones), yolo (auto-approve all tools) [string] [choices: "plan", "default", "auto-edit", "auto", "yolo"] --acp Starts the agent in ACP mode [boolean] --experimental-lsp Enable experimental LSP (Language Server Protocol) feature for code intelligence [boolean] [default: false] --channel Channel identifier (VSCode, ACP, SDK, CI, desktop) [string] [choices: "VSCode", "ACP", "SDK", "CI", "desktop"] --allowed-mcp-server-names Allowed MCP server names [array] --mcp-config MCP server configuration as JSON string or file path. Can be a path to a JSON file or inline JSON with {"mcpServers": {...}} format. [string] --allowed-tools Tools to allow, will bypass confirmation [array] -e, --extensions A list of extensions to use. If not provided, all extensions are used. [array] -l, --list-extensions List all available extensions and exit. [boolean] --include-directories, --add-dir Additional directories to include in the workspace (comma-separated or multiple --include-directories) [array] --openai-logging Enable logging of OpenAI API calls for debugging and analysis [boolean] --openai-logging-dir Custom directory path for OpenAI API logs. Overrides settings files. [string] --openai-api-key OpenAI API key to use for authentication [string] --openai-base-url OpenAI base URL (for custom endpoints) [string] --screen-reader Enable screen reader mode for accessibility. [boolean] --input-format The format consumed from standard input. [string] [choices: "text", "stream-json"] [default: "text"] -o, --output-format The format of the CLI output. [string] [choices: "text", "json", "stream-json"] --include-partial-messages Include partial assistant messages when using stream-json output. [boolean] [default: false] --json-fd File descriptor for structured JSON event output (dual output mode). The TUI renders normally on stdout while JSON events are written to this fd. The caller must provide this fd via spawn stdio configuration. [number] --json-file File path for structured JSON event output (dual output mode). Can be a regular file, FIFO (named pipe), or /dev/fd/N. [string] --json-schema JSON Schema that the model's final output must conform to (headless mode only). Accepts a JSON literal or "@path/to/schema.json". Registers a synthetic `structured_output` tool; the session ends on the first valid call. [string] --input-file File path for receiving remote input commands (bidirectional sync). An external process writes JSONL commands; the TUI watches and processes them. [string] -c, --continue Resume the most recent session for the current project. [boolean] [default: false] -r, --resume Resume a specific session by its ID. Use without an ID to show session picker. [string] --session-id Specify a session ID for this run. [string] --fork-session Create a new forked session from the resumed session. Must be used with --resume or --continue. [boolean] [default: false] --worktree Start the session inside a git worktree at /.qwen/worktrees//. Pass a slug (`--worktree my-feature`), a PR reference (`--worktree=#123` or a full GitHub pull-request URL), or use bare `--worktree` to auto-generate a slug. On exit, the WorktreeExitDialog prompts to keep or remove the worktree. [string] --max-session-turns Maximum number of session turns [number] --max-wall-time Run-level wall-clock budget for headless / unattended runs. Accepts seconds (e.g. `90`), or a duration string with unit (e.g. `30s`, `5m`, `1h`, `1.5h`). Minimum 1s — sub-second values (`500ms`, `0.5`) are rejected as typos; max ~24 days. Aborts the run with exit code 55 when exceeded. [string] --max-tool-calls Maximum cumulative tool calls executed during the run (success or failure; `structured_output` under --json-schema is exempt). Aborts with exit code 55 when exceeded. -1 / unset means no limit; 0 means "no tool calls allowed" (first call aborts). Capped at 1,000,000 to catch typos. [number] --max-subagent-depth Maximum sub-agent nesting depth (1-based levels). 1 keeps sub-agents available but disables nesting; capped at 100. Overrides model.maxSubagentDepth from settings. Defaults to 5. [number] --core-tools Core tool paths [array] --exclude-tools Tools to exclude [array] --disabled-slash-commands Slash command names to hide/disable (comma-separated or repeated). Merged with the `slashCommands.disabled` setting and QWEN_DISABLED_SLASH_COMMANDS. Matched case-insensitively against the final command name. [array] --auth-type Authentication type [string] [choices: "openai", "anthropic", "qwen-oauth", "gemini", "vertex-ai"] -v, --version Show version number [boolean] -h, --help Show help [boolean] file:////AppData/Local/Temp/reporadar-qwen-code-local-read-agent-workflow-zzbo_0yx/work/workflow.mjs:211 if (exit.code !== 0) throw new Error(`CLI exited ${exit.code} signal=${exit.signal}`); ^ Error: CLI exited 1 signal=null at file:////AppData/Local/Temp/reporadar-qwen-code-local-read-agent-workflow-zzbo_0yx/work/workflow.mjs:211:28 at process.processTicksAndRejections (node:internal/process/task_queues:104:5) Node.js v24.15.0 cohort_cache_cleanup: Shared cohort package cache removed. bounded_workflow_intended: false bounded_workflow_completed: false