Module spec 

Validation spec model (parsed from the TOML the agent points the harness at).

Mirrors tools/scx_forge_agent/spec.toml: [scheduler] (what to build and run), [system] (host/runtime settings), [ai] (model selection), [tracing] (optional perf profiling, event list, and size cap), [workload] (the load to apply, the numeric metric to emit, and how many times to repeat the measurement), and [goal] (what the number means, which direction is better, and the accept threshold). Defaults match the previous Python harness’s .get(...) fallbacks.

Structs

Ai

Goal

Scheduler

Spec

System

Tracing

Workload

Constants

METRIC_NAME

Functions

default_accept_threshold_stddev 🔒

default_build_fix_attempts 🔒

default_direction 🔒

default_duration 🔒

default_max_tool_iterations 🔒

default_max_trace_size 🔒

default_max_turn_seconds 🔒

default_profile 🔒

default_rounds 🔒

default_runs 🔒

default_runtime_fix_attempts 🔒

default_stats_interval 🔒

default_trace_events 🔒

default_true 🔒

default_warmup_time 🔒

parse_size 🔒

Parse a size string into bytes: a plain integer, or an integer with a binary suffix K/M/G (case-insensitive, optional trailing B). 1 K = 1024.