workspace | Path | str | None | None; Base directory, followed by an identity partition; PANDAPROBE_REFLECT_WORKSPACE overrides the default |
trace_visibility_timeout | float | 30.0; Wait for terminal persisted trace evidence |
evaluation_timeout | float | 120.0; Evaluation create/wait budgets |
poll_interval | float | 1.0; Poll interval |
evaluation_max_runs | int | None | None; Optional creation-attempt cap per UTC day |
evaluation_max_traces | int | 32; Maximum trace references for one execution |
evaluation_sample_rate | float | 1.0; Fraction admitted by deterministic execution-ID sampling |
max_concurrency | int | 4; Concurrent evaluation orchestration per runtime |
cooldown_seconds | float | 60.0; Repeated failure-signature cooldown |
reflection_timeout | float | 60.0; Host reflection continuation deadline |
shutdown_timeout | float | 5.0; Bounded cancellation wait |
reflection_max_commands | int | 8; Tool-call allowance at the reflection checkpoint |
shell_timeout | float | 5.0; Interpreter call deadline |
shell_max_commands | int | 2000; Interpreter command limit |
shell_max_loop_iterations | int | 5000; Interpreter loop limit |
shell_memory_bytes | int | 16 * 1024 * 1024; Interpreter memory |
command_max_bytes | int | 16 * 1024; Tool command input |
output_max_bytes | int | 12 * 1024; One tool response |
execution_output_max_bytes | int | 96 * 1024; Cumulative output, including guard/error replies |
context_max_bytes | int | 8 * 1024; Active notes |
rule_max_bytes | int | 8 * 1024; One rule |
rules_max_bytes | int | 512 * 1024; Active rule corpus |
rules_max_count | int | 256; Active rule count |
evidence_max_bytes | int | 64 * 1024; Assigned diagnostic presentation |
thresholds | dict[str, float] | factory: lambda: {'task_completion': 0.5, 'coherence': 0.5}; Primary metrics and strict failure thresholds |
diagnostic_metrics | tuple[str, ...] | ('tool_correctness', 'argument_correctness'); Follow-up diagnosis after a notice |
stall_window | int | 5; Score-history window |
minimum_progress | float | 0.02; Stall variation cutoff |
regression_drop | float | 0.15; Previous-score drop cutoff |
validation_min_cases | int | 3; Distinct paired cases |
validation_min_improvement | float | 0.05; Mean non-protected metric improvement |
validation_regression_tolerance | float | 0.02; Allowed per-case metric decrease |
validation_timeout | float | 120.0; Replay collection deadline |