Module: PWN::AI::Agent::Metrics

Defined in:
lib/pwn/ai/agent/metrics.rb

Overview

PWN::AI::Agent::Metrics is the telemetry layer of the pwn-ai learning loop. Every tool dispatch performed by PWN::AI::Agent::Loop is recorded here (name, success, duration, last error) and persisted to ~/.pwn/metrics.json.

PromptBuilder re-injects a compact effectiveness summary into the system prompt on every turn, so the model gains awareness of which tools historically succeed vs. fail on THIS host and can adapt its tool selection accordingly. This is one half of the closed feedback loop that lets pwn-ai continuously make itself smarter (the other half is PWN::AI::Agent::Learning).

PER-ENGINE SEGMENTATION

A local Ollama model and a frontier model do NOT have the same per-tool success rate — blending them mis-advises the local model about itself. Every record now also increments an :engines sub-bucket; summary/to_context accept engine: to surface only that engine's telemetry so the TOOL EFFECTIVENESS block becomes a genuine per-engine learned policy.

Constant Summary collapse

METRICS_FILE = 
File.join(Dir.home, '.pwn', 'metrics.json')
HALF_LIFE_DAYS = 
14.0
CUSUM_K = 
0.15
CUSUM_H = 
0.6
WINDOW = 
30

Class Method Summary collapse

Class Method Details

.advantage(opts = {}) ⇒ Object

Supported Method Parameters

a = PWN::AI::Agent::Metrics.advantage(name: 'shell')

C1 — tool.success_rate − global_rate over the rolling window.



203
204
205
206
207
208
209
210
211
212
213
214
 
# File 'lib/pwn/ai/agent/metrics.rb', line 203

public_class_method def self.advantage(opts = {})
  data = load[:tools] || {}
  t    = data[opts[:name].to_s.to_sym]
  return 0.0 unless t

  global = data.values.sum { |v| v[:ok].to_f } / [data.values.sum { |v| v[:calls].to_f }, 1.0].max
  win    = Array(t[:window])
  local  = win.empty? ? (t[:ok].to_f / [t[:calls].to_f, 1.0].max) : (win.sum.to_f / win.length)
  (local - global).round(3)
rescue StandardError
  0.0
end

.authors ⇒ Object

Author(s)

0day Inc. support@0dayinc.com



349
350
351
 
# File 'lib/pwn/ai/agent/metrics.rb', line 349

public_class_method def self.authors
  "AUTHOR(S):\n  0day Inc. <support@0dayinc.com>\n"
end

.calibration(opts = {}) ⇒ Object

Supported Method Parameters

cal = PWN::AI::Agent::Metrics.calibration(engine: :ollama)



260
261
262
263
264
265
266
267
 
# File 'lib/pwn/ai/agent/metrics.rb', line 260

public_class_method def self.calibration(opts = {})
  eng = (opts[:engine] || :global).to_s.to_sym
  c = (load[:calibration] || {})[eng]
  return { n: 0, brier: nil } unless c && c[:n].to_i.positive?

  n = c[:n].to_f
  { n: c[:n], brier: (c[:brier_sum] / n).round(4), mean_predicted: (c[:p_sum] / n).round(3), mean_actual: (c[:a_sum] / n).round(3), overconfidence: ((c[:p_sum] - c[:a_sum]) / n).round(3) }
end

.changepoints(opts = {}) ⇒ Object

Supported Method Parameters

cps = PWN::AI::Agent::Metrics.changepoints

E1 — tools whose CUSUM tripped (success_rate regime change). The caller (Mistakes.record / Curriculum) triggers extro_snapshot + correlate on these so a Mistake caused by env drift is tagged cause: :env_drift and does NOT count toward [REPEATING].



224
225
226
227
228
229
230
231
232
233
234
235
 
# File 'lib/pwn/ai/agent/metrics.rb', line 224

public_class_method def self.changepoints(opts = {})
  within = (opts[:within_secs] || 3_600).to_i
  now = Time.now.utc
  (load[:tools] || {}).filter_map do |name, t|
    cp = t[:changepoint_at]
    next unless cp && (now - Time.parse(cp)) < within

    { name: name.to_s, at: cp, window_rate: Array(t[:window]).sum.to_f / [Array(t[:window]).length, 1].max }
  end
rescue StandardError
  []
end

.help ⇒ Object

Display Usage for this Module



355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
 
# File 'lib/pwn/ai/agent/metrics.rb', line 355

public_class_method def self.help
  puts <<~USAGE
    USAGE:
      PWN::AI::Agent::Metrics.record(name: 'shell', success: true, duration: 0.42, engine: :ollama)
      PWN::AI::Agent::Metrics.summary(limit: 10, engine: :ollama)
      PWN::AI::Agent::Metrics.to_context(limit: 8, engine: :ollama)   # injected by PromptBuilder
      PWN::AI::Agent::Metrics.ucb(name: 'shell')                 # C1 exploration bonus
      PWN::AI::Agent::Metrics.thompson(name: 'shell')            # C1 Beta(ok+1,fail+1) sample
      PWN::AI::Agent::Metrics.advantage(name: 'shell')           # C1 local − global
      PWN::AI::Agent::Metrics.changepoints(within_secs: 3600)    # E1 CUSUM regime changes
      PWN::AI::Agent::Metrics.record_calibration(predicted: 0.8, actual: 1.0, brier: 0.04, engine: :ollama)
      PWN::AI::Agent::Metrics.calibration(engine: :ollama)       # W3 Brier / overconfidence
      PWN::AI::Agent::Metrics.reset
      PWN::AI::Agent::Metrics.load
      PWN::AI::Agent::Metrics.save(metrics: hash)

      #{self}.authors
  USAGE
end

.load ⇒ Object

Supported Method Parameters

metrics = PWN::AI::Agent::Metrics.load



40
41
42
43
44
45
46
47
 
# File 'lib/pwn/ai/agent/metrics.rb', line 40

public_class_method def self.load
  FileUtils.mkdir_p(File.dirname(METRICS_FILE))
  return { tools: {}, updated_at: nil } unless File.exist?(METRICS_FILE)

  JSON.parse(File.read(METRICS_FILE), symbolize_names: true)
rescue StandardError
  { tools: {}, updated_at: nil }
end

.proxy_trust ⇒ Object

P4 helper — Registry.rank calls this so β·advantage is scaled down when the proxy is untrustworthy.



165
166
167
168
169
170
 
# File 'lib/pwn/ai/agent/metrics.rb', line 165

public_class_method def self.proxy_trust
  d = defined?(Reward) && Reward.respond_to?(:proxy_distrust) ? Reward.proxy_distrust : 0.0
  (1.0 - d.to_f).clamp(0.0, 1.0)
rescue StandardError
  1.0
end

.record(opts = {}) ⇒ Object

Supported Method Parameters

PWN::AI::Agent::Metrics.record( name: 'required - tool name that was dispatched', success: 'required - Boolean, did the handler complete without error', duration: 'optional - Float seconds the dispatch took', error: 'optional - String error message when success is false', engine: 'optional - Symbol/String AI engine that chose this tool (segments telemetry)' )



83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
 
# File 'lib/pwn/ai/agent/metrics.rb', line 83

public_class_method def self.record(opts = {})
  name     = opts[:name].to_s
  success  = opts[:success] ? true : false
  duration = opts[:duration].to_f
  error    = opts[:error]
  engine   = opts[:engine].to_s
  return if name.empty?

  metrics = load
  metrics[:tools] ||= {}
  key = name.to_sym
  t = metrics[:tools][key] ||= blank_bucket
  bump(bucket: t, success: success, duration: duration, error: error)
  unless engine.empty?
    t[:engines] ||= {}
    e = t[:engines][engine.to_sym] ||= blank_bucket
    bump(bucket: e, success: success, duration: duration, error: error)
  end
  save(metrics: metrics)
  t
end

.record_calibration(opts = {}) ⇒ Object

Supported Method Parameters

PWN::AI::Agent::Metrics.record_calibration(predicted:, actual:, brier:, engine:)

W3 — plan_first emits p(success); Loop.run calls this with the realised outcome. Tracked per-engine so calibration of the local LoRA vs frontier is comparable.



244
245
246
247
248
249
250
251
252
253
254
255
 
# File 'lib/pwn/ai/agent/metrics.rb', line 244

public_class_method def self.record_calibration(opts = {})
  m = load
  m[:calibration] ||= {}
  eng = (opts[:engine] || :global).to_s.to_sym
  c = m[:calibration][eng] ||= { n: 0, brier_sum: 0.0, p_sum: 0.0, a_sum: 0.0 }
  c[:n]         += 1
  c[:brier_sum] += opts[:brier].to_f
  c[:p_sum]     += opts[:predicted].to_f
  c[:a_sum]     += opts[:actual].to_f
  save(metrics: m)
  c
end

.reset ⇒ Object

Supported Method Parameters

PWN::AI::Agent::Metrics.reset



272
273
274
275
 
# File 'lib/pwn/ai/agent/metrics.rb', line 272

public_class_method def self.reset
  FileUtils.rm_f(METRICS_FILE)
  { tools: {}, updated_at: nil }
end

.save(opts = {}) ⇒ Object

Supported Method Parameters

PWN::AI::Agent::Metrics.save( metrics: 'required - Hash returned by .load / mutated in place' )



54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
 
# File 'lib/pwn/ai/agent/metrics.rb', line 54

public_class_method def self.save(opts = {})
  metrics = opts[:metrics] ||= { tools: {} }
  metrics[:updated_at] = Time.now.utc.iso8601
  FileUtils.mkdir_p(File.dirname(METRICS_FILE))
  # 4.4 — flock + atomic rename
  path = METRICS_FILE
  tmp  = File.join(File.dirname(path), ".#{File.basename(path)}.#{Process.pid}.tmp")
  body = JSON.pretty_generate(metrics)
  File.open(tmp, File::WRONLY | File::CREAT | File::TRUNC, 0o644) do |f|
    f.flock(File::LOCK_EX)
    f.write(body)
    f.flush
    f.fsync
  end
  File.rename(tmp, path)
  metrics
ensure
  FileUtils.rm_f(tmp) if defined?(tmp) && tmp && File.exist?(tmp)
end

.summary(opts = {}) ⇒ Object

Supported Method Parameters

rows = PWN::AI::Agent::Metrics.summary( limit: 'optional - cap number of tools returned (default 25)', engine: 'optional - only that engine's sub-bucket (falls back to global when absent)' )



111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
 
# File 'lib/pwn/ai/agent/metrics.rb', line 111

public_class_method def self.summary(opts = {})
  limit  = opts[:limit] || 25
  engine = opts[:engine].to_s
  tools  = load[:tools] || {}
  rows = tools.map do |name, t|
    b = engine.empty? ? t : (t.dig(:engines, engine.to_sym) || t)
    calls = b[:calls].to_i
    ok    = b[:ok].to_i
    rate  = calls.positive? ? (ok.to_f / calls).round(3) : 0.0
    avg   = calls.positive? ? (b[:total_duration].to_f / calls).round(3) : 0.0
    {
      name: name.to_s,
      calls: calls,
      success_rate: rate,
      avg_duration: avg,
      last_error: b[:last_error],
      last_at: b[:last_at]
    }
  end
  rows.reject { |r| r[:calls].zero? }
      .sort_by { |r| [-r[:calls], -r[:success_rate]] }.first(limit)
end

.thompson(opts = {}) ⇒ Object

Supported Method Parameters

p = PWN::AI::Agent::Metrics.thompson(name: 'shell')

C1 — Thompson sample from Beta(ok+1, fail+1). Naturally balances exploit/explore; used by Registry.rank as the tie-breaker.



191
192
193
194
195
196
 
# File 'lib/pwn/ai/agent/metrics.rb', line 191

public_class_method def self.thompson(opts = {})
  t = (load[:tools] || {})[opts[:name].to_s.to_sym] || blank_bucket
  beta_sample(alpha: t[:ok].to_f + 1.0, beta: t[:fail].to_f + 1.0)
rescue StandardError
  0.5
end

.to_context(opts = {}) ⇒ Object

Supported Method Parameters

ctx = PWN::AI::Agent::Metrics.to_context( limit: 'optional - cap number of tools included (default 8)', engine: 'optional - restrict to one engine's telemetry' )



140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
 
# File 'lib/pwn/ai/agent/metrics.rb', line 140

public_class_method def self.to_context(opts = {})
  limit  = opts[:limit] || 8
  engine = opts[:engine]
  rows   = summary(limit: limit, engine: engine)
  return '' if rows.empty?

  # P4 — when Reward.sentinel says proxy is hacked, haircut displayed
  # success rates so the model does not trust the lie in the prompt.
  distrust = defined?(Reward) && Reward.respond_to?(:proxy_distrust) ? Reward.proxy_distrust : 0.0
  scope = engine.to_s.empty? ? 'historical' : "engine=#{engine}"
  scope = "#{scope}, proxy_distrust=#{distrust.round(2)}" if distrust.positive?
  lines = rows.map do |r|
    rate = r[:success_rate].to_f
    # blend toward 0.5 (uninformative) proportional to distrust
    adj = rate - ((rate - 0.5) * distrust)
    err = r[:last_error] ? " last_err=#{r[:last_error][0, 60]}" : ''
    tag = distrust.positive? ? ' (adj)' : ''
    "  - #{r[:name]}: calls=#{r[:calls]} success=#{(adj * 100).round(1)}%#{tag} avg=#{r[:avg_duration]}s#{err}"
  end
  warn_line = distrust.positive? ? "WARNING: reward proxy diverges from judge — success rates haircut by distrust=#{distrust.round(2)}; prefer judge-scored exemplars over raw rates.\n" : ''
  "#{warn_line}TOOL EFFECTIVENESS (#{scope}, adapt tool choice accordingly)\n#{lines.join("\n")}\n\n"
end

.ucb(opts = {}) ⇒ Object 



172
173
174
175
176
177
178
179
180
181
182
183
 
# File 'lib/pwn/ai/agent/metrics.rb', line 172

public_class_method def self.ucb(opts = {})
  name = opts[:name].to_s
  c    = (opts[:c] || 1.4).to_f
  data = load[:tools] || {}
  t    = data[name.to_sym] || blank_bucket
  n    = [t[:calls].to_f, 1.0].max
  total = [data.values.sum { |v| v[:calls].to_f }, 1.0].max
  mean  = t[:ok].to_f / n
  mean + (c * Math.sqrt(Math.log(total) / n))
rescue StandardError
  1.0
end