nyx/tests/eval_corpus/budget.toml

# Per-cell (cap × lang) budgets for the dynamic-verification eval corpus.
#
# Phase 29 (Track I): replaces the single global Unsupported-rate gate in
# tests/eval_corpus/report.py with per-cell targets. Each cell records the
# largest tolerated rate today plus a deadline date for the next ratchet.
#
# Schema:
#
#   [default]
#   unsupported_rate    = 0.80   # max(Unsupported / total) per cell
#   false_confirmed_rate = 0.02  # max(wrong / Confirmed) per cell
#   repro_stability     = 0.95   # min(stable / Confirmed) per cell
#   ratchet_deadline    = "2026-08-01"
#
#   [[cell]]
#   cap                 = "sqli"
#   lang                = "python"
#   unsupported_rate    = 0.50
#   false_confirmed_rate = 0.02
#   repro_stability     = 0.97
#   ratchet_deadline    = "2026-07-15"
#
# `cap` matches tabulate.py's _CAP_BIT_TABLE / _CAP_RULE_TABLE labels.
# `lang` matches the ext_map values (`python`, `javascript`, …).
# A wildcard `"*"` matches any cell that does not have an exact entry.

[default]
# Inherited by any cell not overridden below.  Aligned with the legacy
# Gate-1 / Gate-2 / Gate-5 thresholds in scripts/m7_ship_gate.sh.
unsupported_rate     = 0.80
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-08-01"

# Python verticals (Phase 12 — most mature; tightest budgets).

[[cell]]
cap = "sqli"
lang = "python"
unsupported_rate     = 0.40
false_confirmed_rate = 0.02
repro_stability      = 0.97
ratchet_deadline     = "2026-07-15"

[[cell]]
cap = "cmdi"
lang = "python"
unsupported_rate     = 0.40
false_confirmed_rate = 0.02
repro_stability      = 0.97
ratchet_deadline     = "2026-07-15"

[[cell]]
cap = "path_traversal"
lang = "python"
unsupported_rate     = 0.50
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-07-15"

[[cell]]
cap = "ssrf"
lang = "python"
unsupported_rate     = 0.50
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-07-15"

[[cell]]
cap = "deserialize"
lang = "python"
unsupported_rate     = 0.60
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-08-01"

# JavaScript / TypeScript (Phase 13 — second-most-mature).

[[cell]]
cap = "sqli"
lang = "javascript"
unsupported_rate     = 0.55
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-08-01"

[[cell]]
cap = "cmdi"
lang = "javascript"
unsupported_rate     = 0.55
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-08-01"

[[cell]]
cap = "ssrf"
lang = "javascript"
unsupported_rate     = 0.60
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-08-01"

[[cell]]
cap = "xss"
lang = "javascript"
unsupported_rate     = 0.70
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-08-15"

[[cell]]
cap = "sqli"
lang = "typescript"
unsupported_rate     = 0.60
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-08-15"

# Java (Phase 14).

[[cell]]
cap = "sqli"
lang = "java"
unsupported_rate     = 0.65
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-08-15"

[[cell]]
cap = "deserialize"
lang = "java"
unsupported_rate     = 0.70
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-09-01"

# Phase 15 / 16 verticals (Go, PHP, Ruby, Rust, C, C++) — newer; broader
# tolerance until their probe-shim splicing follow-ups land.

[[cell]]
cap = "cmdi"
lang = "go"
unsupported_rate     = 0.75
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-09-01"

[[cell]]
cap = "sqli"
lang = "go"
unsupported_rate     = 0.75
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-09-01"

[[cell]]
cap = "cmdi"
lang = "php"
unsupported_rate     = 0.75
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-09-01"

[[cell]]
cap = "deserialize"
lang = "php"
unsupported_rate     = 0.75
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-09-01"

[[cell]]
cap = "cmdi"
lang = "ruby"
unsupported_rate     = 0.75
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-09-01"

[[cell]]
cap = "sqli"
lang = "rust"
unsupported_rate     = 0.80
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-09-15"

[[cell]]
cap = "fmt_string"
lang = "c"
unsupported_rate     = 0.85
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-09-15"

[[cell]]
cap = "memory"
lang = "c"
unsupported_rate     = 0.90
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-10-01"

[[cell]]
cap = "memory"
lang = "cpp"
unsupported_rate     = 0.90
false_confirmed_rate = 0.02
repro_stability      = 0.95
ratchet_deadline     = "2026-10-01"