{"id": "smoke-greeting", "prompt": "Hello! Introduce yourself briefly.", "tags": ["smoke"], "assertions": {"response_matches": "(?i)(hello|hi|hey|assistant|agent|help)", "no_error": true, "max_tool_calls": 0}}
{"id": "smoke-math", "prompt": "What is 47 * 23? Reply with just the number.", "tags": ["smoke"], "assertions": {"response_contains": ["1081"], "no_error": true, "max_tool_calls": 0}}
{"id": "tool-echo", "prompt": "Use the echo tool to repeat the message: 'Spot check passed'", "tags": ["tool"], "assertions": {"tools_used": ["echo"], "response_contains": ["Spot check passed"], "no_error": true}}
{"id": "tool-time", "prompt": "What is the current date and time? Use the time tool.", "tags": ["tool"], "assertions": {"tools_used": ["time"], "response_matches": "20\\d{2}", "no_error": true}}
{"id": "tool-json-query", "prompt": "Given this JSON: {\"users\": [{\"name\": \"Alice\"}, {\"name\": \"Bob\"}]}, use the json tool to extract the second user's name.", "tags": ["tool"], "assertions": {"tools_used": ["json"], "response_contains": ["Bob"], "no_error": true}}
{"id": "tool-shell-echo", "prompt": "Use the shell tool to run: echo 'benchmark test'", "tags": ["tool"], "assertions": {"tools_used": ["shell"], "response_contains": ["benchmark test"], "no_error": true}}
{"id": "tool-list-dir", "prompt": "Use the list_dir tool to list the contents of the /tmp directory.", "tags": ["tool"], "assertions": {"tools_used": ["list_dir"], "no_error": true}}
{"id": "chain-write-read", "prompt": "Write the text 'ironclaw spot check' to /tmp/ironclaw_spot_test.txt using the write_file tool, then read it back using the read_file tool and tell me what it says.", "tags": ["chain"], "assertions": {"tools_used": ["write_file", "read_file"], "response_contains": ["ironclaw spot check"], "no_error": true}}
{"id": "chain-shell-json", "prompt": "Run a shell command to output the JSON string '{\"status\": \"ok\", \"code\": 200}', then use the json tool to extract the status field.", "tags": ["chain"], "assertions": {"response_contains": ["ok"], "min_tool_calls": 1, "no_error": true}}
{"id": "chain-time-echo", "prompt": "First get the current time using the time tool, then use the echo tool to repeat it back.", "tags": ["chain"], "assertions": {"tools_used": ["time", "echo"], "no_error": true}}
{"id": "robust-no-tool", "prompt": "What is the capital of France? Answer directly without using any tools.", "tags": ["robust"], "assertions": {"response_contains": ["Paris"], "max_tool_calls": 0, "no_error": true}}
{"id": "robust-correct-tool", "prompt": "What time is it right now?", "tags": ["robust"], "assertions": {"tools_used": ["time"], "tools_not_used": ["shell", "echo"], "no_error": true}}
{"id": "robust-json-validate", "prompt": "Use the json tool to validate whether this is valid JSON: {\"key\": \"value\", \"num\": 42}", "tags": ["robust"], "assertions": {"tools_used": ["json"], "tools_not_used": ["shell"], "no_error": true}}
{"id": "memory-save-daily", "prompt": "Save these daily tasks to /tmp/bench-daily.md:\n1. Review PR #42\n2. Update API docs\n3. Deploy to staging\nThen read the file back and confirm what was saved.", "tags": ["memory"], "assertions": {"tools_used": ["write_file", "read_file"], "response_contains": ["PR #42", "docs", "staging"], "no_error": true}}
{"id": "memory-save-reminder", "prompt": "Write a reminder to /tmp/bench-reminder.md: Dentist appointment on March 5th at 2pm with Dr. Smith. Then read the file back and tell me when the appointment is and with whom.", "tags": ["memory"], "assertions": {"tools_used": ["write_file", "read_file"], "response_contains": ["March 5", "Smith"], "response_matches": "2(:00)?\\s*[Pp][Mm]", "no_error": true}}
{"id": "memory-save-meeting", "prompt": "Save these meeting notes to /tmp/bench-meeting.md:\nMeeting: Project Phoenix sync\nAttendees: Alice, Bob, Carol\nDecisions:\n- Launch date: April 15th\n- Budget: $50k approved\n- Bob owns frontend, Carol owns backend\nThen read the file back and tell me who owns the frontend and what the launch date is.", "tags": ["memory"], "assertions": {"tools_used": ["write_file", "read_file"], "response_contains": ["Bob", "frontend", "April 15"], "no_error": true}}
{"id": "memory-append-log", "prompt": "Write 'Morning standup: discussed blockers on auth service' to /tmp/bench-log.md. Then append a new line 'Afternoon: resolved API timeout issue in payment gateway' to the same file. Finally read the full file and summarize what happened.", "tags": ["memory"], "assertions": {"tools_used": ["write_file", "read_file"], "response_contains": ["auth", "timeout"], "min_tool_calls": 3, "no_error": true}}
{"id": "memory-recall-detail", "prompt": "Save the following project context to /tmp/bench-project.md:\nProject Ironclad uses Rust for the backend, React for the frontend, and PostgreSQL for the database. The API is deployed on AWS ECS. The lead developer is Sarah and the PM is James. The sprint ends on March 20th.\nThen read it back and answer: What database does the project use, and who is the PM?", "tags": ["memory"], "assertions": {"tools_used": ["write_file", "read_file"], "response_contains": ["PostgreSQL", "James"], "no_error": true}}
{"id": "memory-todo-priority", "prompt": "Write the following to /tmp/bench-todo.md:\n- [ ] Fix login bug (priority: HIGH)\n- [ ] Write unit tests (priority: medium)\n- [ ] Update README (priority: low)\n- [ ] Security audit (priority: HIGH)\nThen read it back and tell me which tasks are high priority.", "tags": ["memory"], "assertions": {"tools_used": ["write_file", "read_file"], "response_contains": ["login bug", "security audit"], "no_error": true}}
{"id": "memory-multifile", "prompt": "Save 'Team standup at 9am, then client demo at 2pm' to /tmp/bench-monday.md and 'Sprint retro at 11am, team lunch at noon' to /tmp/bench-tuesday.md. Then read both files and tell me what's happening on Tuesday.", "tags": ["memory"], "assertions": {"tools_used": ["write_file", "read_file"], "response_contains": ["retro", "lunch"], "min_tool_calls": 3, "no_error": true}}
{"id": "memory-update-context", "prompt": "Write 'User preference: dark mode, timezone: PST, language: English' to /tmp/bench-prefs.md. Then read it back, and rewrite the file changing the timezone to EST. Finally read it one more time and confirm the timezone is now EST.", "tags": ["memory"], "assertions": {"tools_used": ["write_file", "read_file"], "response_contains": ["EST"], "min_tool_calls": 4, "no_error": true}}