Module: PWN::AI::Agent::Mistakes

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

Overview

PWN::AI::Agent::Mistakes is the negative-feedback half of the pwn-ai learning loop. Where Learning records WHAT WORKED and Metrics records HOW OFTEN a tool worked, Mistakes records SPECIFIC FAILURE PATTERNS with a stable fingerprint so the agent can (a) recognise it is repeating itself, (b) be told exactly what not to do again in every future system prompt, and (c) capture the FIX once one is found so the avoidance lesson becomes an actionable correction.

A "mistake" is keyed by sha12(tool + normalised_error). Normalisation strips volatile bits (paths, hex addresses, line numbers, timestamps, UUIDs, PIDs) so "NoMethodError ... at foo.rb:42" and "... at foo.rb:99" collapse to one signature and its :count climbs — that count IS the repeat detector.

Closed loop (why it does NOT repeat mistakes):

Loop.run --(tool failure)---------> Mistakes.record        (persist + count++)
Loop.run --(same sig fails ≥N)----> guard_repeated_failure (uses PERSISTENT count,
                                                          so triggers on the 1st
                                                          recurrence in a new
                                                          session, not the 3rd)
Loop.run --(failure w/ known fix)-> inline "KNOWN FIX: …"  (self-corrects next iter)
Loop.run --(user says "wrong")----> check_user_correction  (flip last outcome + record)
PromptBuilder <-------------------- Mistakes.to_context    (DO-NOT-REPEAT + KNOWN-FIXES)
model --(tool call)---------------> mistakes_record / mistakes_resolve

Constant Summary collapse

MISTAKES_FILE = 
File.join(Dir.home, '.pwn', 'mistakes.json')
REPEAT_THRESHOLD = 
3
SAMPLE_ARGS_MAX =

Lean retention for mistakes.json

160
SNIPPET_MAX = 
160
ERROR_MAX = 
300
SESSIONS_KEEP = 
3
MAX_RESOLVED_KEPT = 
80
RESOLVED_MIN_AGE_DAYS = 
21
FIX_MAX = 
500
CORRECTION_RX = 
/
  \b(
    no[,.]?\s*(that|this|it)?'?s?\s*(wrong|not\s+right|incorrect)|
    still\s+(broken|failing|wrong|not\s+working|doesn'?t\s+work)|
    (that|it|this)\s+(did(n'?t| not)\s+work|failed|is\s+wrong)|
    not\s+what\s+i\s+(asked|meant|wanted)|
    you\s+(made\s+a|got\s+it)\s+(mistake|wrong)|
    same\s+(mistake|error|problem)\s+again|
    try\s+again|redo\s+that|wrong\s+answer|incorrect
  )\b
/ix

Class Method Summary collapse

Class Method Details

.authors ⇒ Object

Author(s)

0day Inc. support@0dayinc.com



658
659
660
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 658

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

.check_user_correction(opts = {}) ⇒ Object

Supported Method Parameters

entry = PWN::AI::Agent::Mistakes.check_user_correction( request: 'required - the incoming user message', session_id: 'optional - session to inspect for the previous answer' )

When the user's new message reads like a correction of the previous answer, this (a) flips the most recent Learning outcome for that session to success:false, and (b) records a mistake with source :user_correction whose "error" is the user's own words. This is the strongest available signal that the agent was WRONG.



463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 463

public_class_method def self.check_user_correction(opts = {})
  request    = opts[:request].to_s
  session_id = opts[:session_id]
  return nil unless correction?(request: request)

  prev = previous_assistant(session_id: session_id)
  Learning.flip_last_outcome(session_id: session_id, reason: request[0, 200]) if defined?(Learning)
  # W1 — stash the rejected answer + user prompt so the NEXT final
  # (the correction) completes a (rejected, chosen) preference pair.
  Thread.current[:pwn_pending_pref] = { prompt: previous_user(session_id: session_id).to_s, rejected: prev.to_s } if defined?(Reward)
  record(
    tool: 'assistant_answer',
    error: "user rejected previous answer: #{request.strip[0, 200]}",
    args: prev.to_s[0, 200],
    session_id: session_id,
    source: :user_correction
  )
rescue StandardError => e
  warn "[pwn-ai/mistakes] check_user_correction swallowed: #{e.class}: #{e.message}"
  nil
end

.correction?(opts = {}) ⇒ Boolean

Supported Method Parameters

bool = PWN::AI::Agent::Mistakes.correction?(request: user_text)

Returns:

  • (Boolean) 


444
445
446
447
448
449
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 444

public_class_method def self.correction?(opts = {})
  req = opts[:request].to_s
  return false if req.strip.empty?

  req.match?(CORRECTION_RX) && req.length < 600
end

.correction_hint(opts = {}) ⇒ Object

Supported Method Parameters

str = PWN::AI::Agent::Mistakes.correction_hint( tool: 'required - tool that just failed', error: 'required - raw error it failed with' )

Called by Loop.run immediately after a failed dispatch. Returns a string to append to the tool result telling the model (a) how many times this exact failure has occurred across ALL sessions, and (b) the recorded fix if one exists — so it can self-correct on the very next iteration instead of re-discovering the fix from scratch.



431
432
433
434
435
436
437
438
439
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 431

public_class_method def self.correction_hint(opts = {})
  m = find(tool: opts[:tool], error: opts[:error])
  return '' unless m

  parts = ["seen #{m[:count]}× across #{Array(m[:sessions]).length} session(s), sig=#{m[:signature]}"]
  parts << 'REGRESSED (previous fix did not hold)' if m[:regressed]
  parts << "KNOWN FIX: #{m[:fix]}" if m[:fix].to_s.strip.length.positive?
  "[pwn-ai/mistakes] #{parts.join(' | ')}"
end

.effective_count(opts = {}) ⇒ Object

Age-weighted count for [REPEATING] threshold — a ×8 signature from 6 months ago on a since-rewritten module decays toward zero.



625
626
627
628
629
630
631
632
633
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 625

public_class_method def self.effective_count(opts = {})
  m = opts[:mistake] || find(signature: opts[:signature])
  return 0 unless m

  days = (Time.now.utc - Time.parse(m[:last_seen].to_s)) / 86_400.0
  (m[:count].to_f * (0.5**(days / 30.0))).ceil
rescue StandardError
  m ? m[:count].to_i : 0
end

.find(opts = {}) ⇒ Object

Supported Method Parameters

entry = PWN::AI::Agent::Mistakes.find( signature: 'optional - exact signature to fetch', tool: 'optional - with error:, compute signature and fetch', error: 'optional - raw error text (used with tool:)' )



119
120
121
122
123
124
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 119

public_class_method def self.find(opts = {})
  sig = opts[:signature] || (opts[:tool] && opts[:error] ? signature(tool: opts[:tool], error: opts[:error]) : nil)
  return nil unless sig

  load[sig.to_sym]
end

.for_tool(opts = {}) ⇒ Object

Supported Method Parameters

rows = PWN::AI::Agent::Mistakes.for_tool( tool: 'required - tool name', unresolved_only: 'optional - default false' )



132
133
134
135
136
137
138
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 132

public_class_method def self.for_tool(opts = {})
  tool = opts[:tool].to_s
  only = opts[:unresolved_only] ? true : false
  rows = load.values.select { |m| m[:tool].to_s == tool }
  rows = rows.reject { |m| m[:resolved] } if only
  rows.sort_by { |m| -m[:count].to_i }
end

.help ⇒ Object

Display Usage for this Module



664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 664

public_class_method def self.help
  puts <<~USAGE
    USAGE:
      PWN::AI::Agent::Mistakes.record(tool: 'shell', error: 'nmpa: command not found', args: '{"command":"nmpa -sV"}')
      PWN::AI::Agent::Mistakes.top(limit: 10, unresolved_only: true)
      PWN::AI::Agent::Mistakes.find(signature: 'abc123def456')
      PWN::AI::Agent::Mistakes.for_tool(tool: 'shell')
      PWN::AI::Agent::Mistakes.resolve(signature: 'abc123def456', fix: 'binary is spelled `nmap`, not `nmpa`')
      PWN::AI::Agent::Mistakes.correction_hint(tool: 'shell', error: err)  # inline self-correct
      PWN::AI::Agent::Mistakes.to_context(limit: 6)                        # injected by PromptBuilder
      PWN::AI::Agent::Mistakes.correction?(request: "no that's wrong")
      PWN::AI::Agent::Mistakes.check_user_correction(request: req, session_id: sid)
      PWN::AI::Agent::Mistakes.signature(tool: 'shell', error: err)
      PWN::AI::Agent::Mistakes.reset

      #{self}.authors
  USAGE
end

.lean!(opts = {}) ⇒ Object

Supported Method Parameters

result = PWN::AI::Agent::Mistakes.lean!( dry_run: 'optional - Boolean (default false)', max_resolved_kept: 'optional - cap on resolved-with-fix records', resolved_min_age_days: 'optional - age before resolved count=1 may drop' )

Compact text fields on every record. Never drops unresolved, regressed, or high-count repeaters. Aged resolved-once fixes may drop after Memory already holds mistake_fix_.



496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 496

public_class_method def self.lean!(opts = {})
  dry = opts[:dry_run] ? true : false
  max_resolved = (opts[:max_resolved_kept] || MAX_RESOLVED_KEPT).to_i
  min_age = (opts[:resolved_min_age_days] || RESOLVED_MIN_AGE_DAYS).to_f
  store = load
  before_bytes = File.exist?(MISTAKES_FILE) ? File.size(MISTAKES_FILE) : 0
  now = Time.now.utc
  compacted = 0
  dropped = []

  store.each_value do |m|
    before = begin
      m.to_json.bytesize
    rescue StandardError
      0
    end
    m[:sample_args] = m[:sample_args].to_s[0, SAMPLE_ARGS_MAX] if m[:sample_args].to_s.bytesize > SAMPLE_ARGS_MAX
    m[:snippet] = m[:snippet].to_s[0, SNIPPET_MAX] if m[:snippet].to_s.bytesize > SNIPPET_MAX
    m[:error] = m[:error].to_s[0, ERROR_MAX] if m[:error].to_s.bytesize > ERROR_MAX
    m[:sessions] = Array(m[:sessions]).compact.uniq.last(SESSIONS_KEEP)
    after = begin
      m.to_json.bytesize
    rescue StandardError
      before
    end
    compacted += 1 if after < before
  end

  age_days = lambda do |m|
    t = m[:resolved_at] || m[:last_seen]
    (now - Time.parse(t.to_s)) / 86_400.0
  rescue StandardError
    0.0
  end

  protected_m = lambda do |m|
    return true unless m[:resolved]
    return true if m[:regressed]
    return true if effective_count(mistake: m) >= REPEAT_THRESHOLD
    return true if m[:count].to_i >= 2 && m[:fix].to_s.strip != ''
    return true if m[:fix].to_s.strip != '' && age_days.call(m) < min_age

    false
  end

  # Drop aged resolved-once when fix lives in Memory or past age
  store.each do |sig, m|
    next if protected_m.call(m)
    next unless m[:resolved] && m[:fix].to_s.strip != '' && m[:count].to_i <= 1
    next unless age_days.call(m) >= min_age

    mem_has = false
    if defined?(PWN::Memory)
      begin
        mem_has = PWN::Memory.load.key?(:"mistake_fix_#{sig}")
      rescue StandardError
        mem_has = false
      end
    end
    # Drop when Memory has the fix OR age is well past (2× min) even without mem key
    dropped << sig.to_s if mem_has || age_days.call(m) >= (min_age * 2)
  end

  dropped.each { |s| store.delete(s.to_sym) } unless dry

  # Cap resolved-with-fix by oldest resolved_at
  resolved = store.select { |_s, m| m[:resolved] && m[:fix].to_s.strip != '' }
  if resolved.size > max_resolved
    excess = resolved.sort_by { |_s, m| m[:resolved_at].to_s }
                     .first(resolved.size - max_resolved)
    excess.each do |sig, m|
      next if m[:regressed] || m[:count].to_i >= 2
      next if effective_count(mistake: m) >= REPEAT_THRESHOLD

      dropped << sig.to_s
      store.delete(sig) unless dry
    end
  end

  save(store: store) unless dry

  open_n = store.values.count { |m| !m[:resolved] }
  {
    compacted_fields: compacted,
    dropped: dropped.uniq.length,
    dropped_sigs: dropped.uniq.first(20),
    remaining: store.size,
    unresolved: open_n,
    bytes_before: before_bytes,
    bytes_after: if dry
                   before_bytes
                 else
                   (File.exist?(MISTAKES_FILE) ? File.size(MISTAKES_FILE) : 0)
                 end,
    dry_run: dry
  }
end

.load ⇒ Object

Supported Method Parameters

store = PWN::AI::Agent::Mistakes.load



62
63
64
65
66
67
68
69
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 62

public_class_method def self.load
  FileUtils.mkdir_p(File.dirname(MISTAKES_FILE))
  return {} unless File.exist?(MISTAKES_FILE)

  JSON.parse(File.read(MISTAKES_FILE), symbolize_names: true)
rescue StandardError
  {}
end

.park(opts = {}) ⇒ Object

2.5 — park unfixable sigs so nightly practice skips them



317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 317

public_class_method def self.park(opts = {})
  sig = opts[:signature].to_s
  raise 'ERROR: signature is required' if sig.empty?

  store = load
  key = sig.to_sym
  raise "ERROR: unknown mistake signature #{sig}" unless store[key]

  store[key][:parked] = true
  store[key][:needs_code_change] = true
  store[key][:park_reason] = opts[:reason].to_s[0, 300]
  store[key][:parked_at] = Time.now.utc.iso8601
  save(store: store)
  store[key]
end

.record(opts = {}) ⇒ Object

Supported Method Parameters

entry = PWN::AI::Agent::Mistakes.record( tool: 'required - tool/component that produced the failure', error: 'required - error text / message', args: 'optional - args that triggered it (stored truncated as sample)', session_id: 'optional - PWN::Sessions id', source: 'optional - :tool | :user_correction | :loop | :model | :heuristic (default :tool)' )

Returns the FULL persisted entry including its cumulative :count so the caller (Loop.run) can drive cross-session repeat detection.



152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 152

public_class_method def self.record(opts = {})
  tool  = opts[:tool].to_s
  error = opts[:error].to_s
  return nil if tool.empty? || error.strip.empty?

  # 1.1 — reward_signal: never inflate count beyond 1 open fingerprint.
  # Sentinel opens one parked sig; further gaps calibrate, not spam.
  if tool == 'reward_signal'
    existing = load.values.select { |e| e[:tool].to_s == 'reward_signal' && !e[:resolved] && !e[:parked] }
    if existing.any? && !opts[:force]
      e = existing.max_by { |x| x[:count].to_i }
      e[:last_seen] = Time.now.utc.iso8601
      e[:count] = e[:count].to_i # freeze
      e[:meta] = (e[:meta] || {}).merge(opts[:meta] || {})
      store = load
      store[e[:signature].to_sym] = e
      save(store: store)
      return e
    end
  end

  sig   = signature(tool: tool, error: error)
  store = load
  key   = sig.to_sym
  now   = Time.now.utc.iso8601
  norm  = normalize_error(error: error)

  m = store[key] ||= {
    signature: sig, tool: tool, error: norm.to_s[0, ERROR_MAX],
    snippet: error.to_s.strip[0, SNIPPET_MAX],
    count: 0, drift_count: 0, first_seen: now, sessions: [],
    resolved: false, fix: nil, source: (opts[:source] || :tool).to_s
  }
  was_resolved = m[:resolved]
  # E1 — env-drift-attributed failures are counted separately so
  # they do NOT push the signature toward [REPEATING]. "The world
  # changed under me" is not the same lesson as "I did it wrong".
  cause = (opts[:cause] || :self).to_sym
  if cause == :env_drift
    m[:drift_count] = m[:drift_count].to_i + 1
    m[:cause] = 'env_drift'
  else
    m[:count] += 1
  end
  m[:last_seen]    = now
  m[:error]        = norm.to_s[0, ERROR_MAX]
  m[:snippet]      = error.to_s.strip[0, SNIPPET_MAX]
  m[:sample_args]  = opts[:args].to_s[0, SAMPLE_ARGS_MAX] if opts[:args]
  m[:sessions]     = (Array(m[:sessions]) + [opts[:session_id]]).compact.uniq.last(SESSIONS_KEEP)
  # 2.2 — recoverable shape for repair routing
  if opts[:shape]
    m[:shape] = opts[:shape].to_s
  elsif defined?(Reward) && Reward.respond_to?(:recoverable_shape)
    m[:shape] ||= Reward.recoverable_shape(err: error).to_s
  end
  m[:needs_code_change] = true if opts[:needs_code_change]
  m[:meta] = (m[:meta] || {}).merge(opts[:meta] || {}) if opts[:meta]
  # A recurrence of a "resolved" mistake means the fix was wrong /
  # incomplete — reopen it so it re-enters the DO-NOT-REPEAT block.
  # Structured fixes with holdout_tests that still pass stay closed.
  if was_resolved && structured_fix_holds?(mistake: m)
    m[:resolved] = true
    m[:regressed] = false
  else
    m[:resolved]  = false
    m[:regressed] = true if was_resolved
  end
  save(store: store)
  m
end

.reset ⇒ Object

Supported Method Parameters

PWN::AI::Agent::Mistakes.reset



597
598
599
600
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 597

public_class_method def self.reset
  FileUtils.rm_f(MISTAKES_FILE)
  {}
end

.resolve(opts = {}) ⇒ Object

Supported Method Parameters

entry = PWN::AI::Agent::Mistakes.resolve( signature: 'required - mistake signature (from mistakes_list / .top)', fix: 'required - what to do INSTEAD next time' )



229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 229

public_class_method def self.resolve(opts = {})
  sig = opts[:signature].to_s
  fix = opts[:fix].to_s
  raise 'ERROR: signature is required' if sig.empty?
  raise 'ERROR: fix is required' if fix.strip.empty?

  store = load
  key   = sig.to_sym
  raise "ERROR: unknown mistake signature #{sig}" unless store[key]

  store[key][:resolved]    = true
  store[key][:regressed]   = false
  store[key][:fix]         = fix.strip[0, FIX_MAX]
  store[key][:resolved_at] = Time.now.utc.iso8601
  # 2.3 — structured fix payload (strategy/tool/args_template/holdouts).
  # Prose-only resolve is why shell sigs regressed after auto-curriculum.
  if opts[:structured].is_a?(Hash)
    s = opts[:structured]
    store[key][:structured_fix] = {
      strategy: s[:strategy].to_s[0, 80],
      tool: s[:tool].to_s[0, 60],
      args_template: s[:args_template],
      holdout_tests: Array(s[:holdout_tests]).first(5),
      winning_trace: s[:winning_trace].to_s[0, 2_000]
    }.compact
  end
  store[key][:parked] = false
  store[key][:needs_code_change] = false if opts[:clear_needs_code_change]
  save(store: store)

  if defined?(PWN::Memory)
    PWN::Memory.remember(
      key: :"mistake_fix_#{sig}",
      value: "AVOID: #{store[key][:tool]} → #{store[key][:error]} — FIX: #{fix.strip[0, 300]}",
      category: :lesson,
      source: :resolve,
      confidence: 0.9,
      importance: 0.9
    )
  end
  # W1/P9 — every resolve is a preference pair. Prefer structured
  # winning_trace (+ strategy/tool) over first-line fix prose so DPO
  # learns tool trajectories, not commentary.
  if defined?(Reward)
    sf = store[key][:structured_fix] || {}
    trace = sf[:winning_trace].to_s.strip
    strat = [sf[:strategy], sf[:tool], sf[:args_template]].compact.map(&:to_s).reject(&:empty?).join(' | ')
    # P21/P25 — only write W1 pairs when we have a real winning_trace.
    # Prose-only resolve still updates Memory lesson + structured_fix;
    # it must NOT flood DPO with fix commentary (shape: :fix_prose).
    if trace.length >= 40
      parts = []
      parts << "STRATEGY: #{strat}" unless strat.empty?
      parts << "WINNING_TRACE:\n#{trace[0, 3_500]}"
      parts << "FIX: #{fix.strip[0, 400]}"
      chosen = parts.join("\n")
      rejected = store[key][:snippet].to_s
      rejected = "FAILING: tool=#{store[key][:tool]} err=#{store[key][:error]}" if rejected.strip.empty?
      Reward.record_preference(
        prompt: "#{store[key][:tool]}: #{store[key][:error]}",
        rejected: rejected,
        chosen: chosen,
        source: :mistakes_resolve,
        shape: :winning_trace,
        meta: { signature: sig, strategy: sf[:strategy], tool: sf[:tool] }.compact
      )
    end
  end
  store[key]
end

.save(opts = {}) ⇒ Object

Supported Method Parameters

PWN::AI::Agent::Mistakes.save(store: hash)



74
75
76
77
78
79
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 74

public_class_method def self.save(opts = {})
  store = opts[:store] ||= {}
  FileUtils.mkdir_p(File.dirname(MISTAKES_FILE))
  atomic_write(path: MISTAKES_FILE, body: JSON.pretty_generate(store))
  store
end

.signature(opts = {}) ⇒ Object

Supported Method Parameters

sig = PWN::AI::Agent::Mistakes.signature( tool: 'required - tool/component name that failed', error: 'required - raw error text (will be normalised)' )



106
107
108
109
110
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 106

public_class_method def self.signature(opts = {})
  tool = opts[:tool].to_s
  norm = normalize_error(error: opts[:error])
  Digest::SHA256.hexdigest("#{tool}|#{norm}")[0, 12]
end

.to_context(opts = {}) ⇒ Object

Supported Method Parameters

ctx = PWN::AI::Agent::Mistakes.to_context(limit: 6)

Injected by PromptBuilder into every system prompt. Emits TWO blocks so the model sees both what NOT to do AND what to do INSTEAD:

KNOWN MISTAKES — unresolved, count-sorted, [REPEATING]/[REGRESSED]
KNOWN FIXES    — resolved entries with their fix, so the correction
               survives even after dropping out of the first list.


343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 343

public_class_method def self.to_context(opts = {})
  limit   = opts[:limit] || 6
  request = opts[:request].to_s
  open_rows = top(limit: limit * 3, unresolved_only: true)
  # 2.6 — request-conditioned rank (sim × recency × count), same idea
  # as exemplars_for. Stops injecting loudest scar (reward_signal ×13)
  # on every unrelated turn.
  open = rank_for_request(rows: open_rows, request: request, limit: limit)
  closed = load.values.select { |m| m[:resolved] && m[:fix] }
  closed = rank_for_request(rows: closed, request: request, limit: limit)
  return '' if open.empty? && closed.empty?

  out = +''
  unless open.empty?
    lines = open.map do |m|
      tags = []
      tags << 'REPEATING' if effective_count(mistake: m) >= REPEAT_THRESHOLD
      tags << 'ENV_DRIFT' if m[:cause].to_s == 'env_drift'
      tags << 'REGRESSED' if m[:regressed]
      tags << 'PARKED' if m[:parked] || m[:needs_code_change]
      tag = tags.empty? ? '' : " [#{tags.join(',')}]"
      fix = m[:fix] ? " — last fix (insufficient): #{m[:fix][0, 100]}" : ''
      shape = m[:shape] ? " shape=#{m[:shape]}" : ''
      "  ✗ [#{m[:signature]}] #{m[:tool]} ×#{m[:count]}#{tag}#{shape}: #{m[:error][0, 140]}#{fix}"
    end
    out << "KNOWN MISTAKES (do NOT repeat — call mistakes_resolve once fixed)\n#{lines.join("\n")}\n"
  end
  unless closed.empty?
    lines = closed.map do |m|
      sf = m[:structured_fix]
      extra = sf ? " strategy=#{sf[:strategy]} tool=#{sf[:tool]}" : ''
      "  ✓ [#{m[:signature]}] #{m[:tool]}: #{m[:error][0, 80]} — FIX: #{m[:fix][0, 140]}#{extra}"
    end
    out << "KNOWN FIXES (apply these instead of repeating the mistake)\n#{lines.join("\n")}\n"
  end
  "#{out}\n"
end

.top(opts = {}) ⇒ Object

Supported Method Parameters

rows = PWN::AI::Agent::Mistakes.top( limit: 'optional - max rows (default 10)', unresolved_only: 'optional - default true' )



306
307
308
309
310
311
312
313
314
 
# File 'lib/pwn/ai/agent/mistakes.rb', line 306

public_class_method def self.top(opts = {})
  limit = opts[:limit] || 10
  only  = opts.key?(:unresolved_only) ? opts[:unresolved_only] : true
  rows  = load.values
  rows  = rows.reject { |m| m[:resolved] } if only
  # 2.5 — practice/curriculum skip engineer-only / parked fingerprints
  rows = rows.reject { |m| m[:parked] || m[:needs_code_change] || m[:tool].to_s == 'reward_signal' } if opts[:practiceable_only]
  rows.sort_by { |m| [-m[:count].to_i, m[:last_seen].to_s] }.first(limit)
end