| """Synthetic task corpus for the Zerolang editing environment.""" |
|
|
| from __future__ import annotations |
|
|
| from .task_builders import ( |
| _branch_literal_task, |
| _call_task, |
| _condition_task, |
| _diagnostic_task, |
| _helper_task, |
| _literal_task, |
| _two_helper_task, |
| ) |
| from .train_tasks import TRAIN_TASKS |
|
|
|
|
| EVAL_TASKS: list[dict[str, Any]] = [ |
| _literal_task( |
| "literal-string-graph-patch", |
| "hello from zero", |
| "hello graph", |
| "Change the printed string from hello from zero to hello graph.", |
| ), |
| _literal_task( |
| "repair-unknown-message", |
| "draft", |
| "fixed by zero", |
| 'Replace the string literal "draft\\n" with "fixed by zero\\n".', |
| ), |
| _literal_task( |
| "literal-status-ready", |
| "status: draft", |
| "status: ready", |
| 'Replace the string literal "status: draft\\n" with "status: ready\\n".', |
| ), |
| _literal_task( |
| "literal-counter-pass", |
| "counter failed", |
| "counter passed", |
| 'Replace the string literal "counter failed\\n" with "counter passed\\n".', |
| ), |
| _literal_task( |
| "literal-agent-graph", |
| "agent used text", |
| "agent used graph", |
| 'Replace the string literal "agent used text\\n" with "agent used graph\\n".', |
| ), |
| *[ |
| _literal_task(task_id, old, new) |
| for task_id, old, new in [ |
| ("literal-alpha-beta", "alpha", "beta"), |
| ("literal-start-finish", "start", "finish"), |
| ("literal-left-right", "left", "right"), |
| ("literal-plan-done", "plan pending", "plan done"), |
| ("literal-state-green", "state: red", "state: green"), |
| ("literal-cache-hot", "cache cold", "cache hot"), |
| ] |
| ], |
| *[ |
| _literal_task(task_id, old, new, goal) |
| for task_id, old, new, goal in [ |
| ( |
| "literal-colon-version", |
| "status: init [v1]", |
| "status: init [v2]", |
| "Update the status bracket code from [v1] to [v2].", |
| ), |
| ( |
| "literal-api-version", |
| "load path /api/v1/health", |
| "load path /api/v2/health", |
| "Switch the printed endpoint from v1 to v2 while keeping the same path.", |
| ), |
| ( |
| "literal-score-number", |
| "score: 42/100", |
| "score: 99/100", |
| "Change the score text from 42 to 99.", |
| ), |
| ( |
| "literal-status-code", |
| "error: [404] failed", |
| "error: [200] resolved", |
| "Edit the status code label from 404 to 200 in brackets.", |
| ), |
| ( |
| "literal-progress-percent", |
| "progress: 50% complete", |
| "progress: 75% complete", |
| "Update the progress percentage from 50 to 75.", |
| ), |
| ( |
| "literal-time-stamp", |
| "time stamp 12:34", |
| "time stamp 13:00", |
| "Change the time from 12:34 to 13:00 in the output string.", |
| ), |
| ( |
| "literal-list-separator", |
| "list [a/b/c]", |
| "list [a-b-c]", |
| "Adjust the list label to use dashes instead of slashes.", |
| ), |
| ( |
| "literal-coordinate-label", |
| "coords (x:1,y:2)", |
| "coords (x:3,y:4)", |
| "Update the coordinate label from (x:1,y:2) to (x:3,y:4).", |
| ), |
| ] |
| ], |
| *[ |
| _branch_literal_task(task_id, helper, old, new) |
| for task_id, helper, old, new in [ |
| ("branch-literal-ready-version", "ready", "ready v1", "ready v2"), |
| ("branch-literal-mode-active", "can_send", "mode: standby", "mode: active"), |
| ("branch-literal-status-ok", "enabled", "status: ok [404]", "status: ok [200]"), |
| ("branch-literal-step-count", "feature_flag", "steps: 1/3 complete", "steps: 2/3 complete"), |
| ("branch-literal-coordinate", "should_emit", "coords (x:1,y:1)", "coords (x:2,y:2)"), |
| ("branch-literal-check-pass", "allow_output", "check: fail", "check: pass"), |
| ("branch-literal-health", "should_log", "health: warn", "health: ok"), |
| ("branch-literal-phase", "gate_open", "phase: draft", "phase: final"), |
| ] |
| ], |
| *[ |
| _helper_task(task_id, helper, source_expr, target_expr, expected, output) |
| for task_id, helper, source_expr, target_expr, expected, output in [ |
| ("helper-score-42", "score", "40 + 1", "40 + 2", 42, "ready"), |
| ("helper-answer-41", "answer", "20 + 20", "20 + 21", 41, "green light"), |
| ("helper-total-18", "total", "30 - 13", "30 - 12", 18, "total ok"), |
| ("helper-count-9", "count", "12 - 4", "12 - 3", 9, "count passed"), |
| ("helper-value-15", "value", "7 + 7", "7 + 8", 15, "value good"), |
| ("helper-limit-24", "limit", "50 - 27", "50 - 26", 24, "limit open"), |
| ("helper-score-31", "score", "15 + 15", "15 + 16", 31, "score matched"), |
| ("helper-answer-8", "answer", "10 - 3", "10 - 2", 8, "done"), |
| ] |
| ], |
| *[ |
| _two_helper_task(task_id, helper, other, source_expr, target_expr, other_expr, expected) |
| for task_id, helper, other, source_expr, target_expr, other_expr, expected in [ |
| ("two-helper-score", "score", "spare", "12 + 9", "13 + 9", "30 - 8", 22), |
| ("two-helper-total", "total", "backup", "40 - 19", "41 - 19", "5 + 7", 22), |
| ("two-helper-count", "count", "idle", "18 + 3", "19 + 3", "14 - 2", 22), |
| ("two-helper-value", "value", "other", "55 - 35", "56 - 35", "6 + 2", 21), |
| ("two-helper-answer", "answer", "spare", "27 - 7", "28 - 7", "8 + 1", 21), |
| ("two-helper-level", "level", "helper", "9 + 10", "10 + 10", "40 - 3", 20), |
| ("two-helper-points", "points", "extra", "64 - 46", "65 - 46", "11 + 4", 19), |
| ("two-helper-result", "result", "unused", "33 - 12", "34 - 12", "2 + 2", 22), |
| ] |
| ], |
| *[ |
| _call_task(task_id, source_args, target_args, expected) |
| for task_id, source_args, target_args, expected in [ |
| ("call-update-five", "1, 1", "4, 1", 5), |
| ("call-update-ten", "7, 1", "7, 3", 10), |
| ("call-update-eleven", "0, 6", "5, 6", 11), |
| ("call-update-twenty", "9, 9", "11, 9", 20), |
| ("call-update-seven", "2, 2", "5, 2", 7), |
| ("call-update-twelve", "10, 0", "10, 2", 12), |
| ("call-update-sixteen", "8, 4", "8, 8", 16), |
| ("call-update-thirteen", "6, 6", "6, 7", 13), |
| ] |
| ], |
| *[ |
| _condition_task(task_id, helper, returned, source_compare, "match found") |
| for task_id, helper, returned, source_compare in [ |
| ("condition-count-four", "count", 4, 1), |
| ("condition-level-nine", "level", 9, 2), |
| ("condition-token-twelve", "token", 12, 8), |
| ("condition-value-fifteen", "value", 15, 10), |
| ("condition-flag-six", "flag", 6, 3), |
| ("condition-score-eleven", "score", 11, 7), |
| ("condition-count-eight", "count", 8, 4), |
| ("condition-marker-fourteen", "marker", 14, 0), |
| ] |
| ], |
| *[ |
| _diagnostic_task(task_id, message) |
| for task_id, message in [ |
| ("diagnostic-starting-up", "starting up"), |
| ("diagnostic-hello-main", "hello from main"), |
| ("diagnostic-message", "diagnostic message"), |
| ("diagnostic-payload-logged", "payload logged"), |
| ("diagnostic-attempt-write", "attempt write"), |
| ("diagnostic-retrying-output", "retrying output"), |
| ("diagnostic-done", "done"), |
| ("diagnostic-needs-raises", "needs raises"), |
| ] |
| ], |
| ] |
|
|
|
|
| SYNTHETIC_TASKS: list[dict[str, Any]] = [*EVAL_TASKS, *TRAIN_TASKS] |
|
|
