pwn 0.5.706 → 0.5.708

data/spec/lib/pwn/ai/agent/policy_spec.rb

@@ -131,13 +131,24 @@ describe PWN::AI::Agent::Policy do
     grind = described_class.observe_step(
       action: 'shell', ok: true, session_id: 'en_credit', ts_state: ts
     )
-    ts[:plan_idx] = 1
-    ts[:evidence_blob] = 'rg hit locate the source lib/task_summarizer.rb patched later'
+    poc = "/tmp/pwn-policy-#{Process.pid}.poc"
+    File.write(poc, 'poc')
+    Thread.current[:pwn_loop_deliverables] = {
+      paths: [],
+      min_seconds: 0,
+      skills: [],
+      proofs: [poc],
+      hosts: [],
+      techniques: []
+    }
     advance = described_class.observe_step(
       action: 'shell', ok: true, session_id: 'en_credit', ts_state: ts
     )
-    expect(advance[:reward].to_f).to be > grind[:reward].to_f
+    expect(advance[:reward].to_f).to eq(0.0)
+    expect(grind[:reward].to_f).to eq(0.0)
   ensure
+    FileUtils.rm_f(poc) if defined?(poc)
+    Thread.current[:pwn_loop_deliverables] = nil
     described_class.reset
     FileUtils.remove_entry(tmp) if tmp && Dir.exist?(tmp)
   end
@@ -214,7 +225,7 @@ describe PWN::AI::Agent::Policy do
     FileUtils.remove_entry(tmp) if tmp && Dir.exist?(tmp)
   end
 
-  describe 'Hermes episode handoff' do
+  describe 'episode handoff' do
     it 'detach_episode! snapshots and clears current_episode' do
       tmp = Dir.mktmpdir
       stub_const('PWN::AI::Agent::Policy::POLICY_FILE', File.join(tmp, 'policy.json'))
@@ -233,6 +244,36 @@ describe PWN::AI::Agent::Policy do
       expect(described_class.current_episode[:session_id]).to eq('detach1')
     ensure
       described_class.attach_episode!(episode: nil)
+      described_class.reset
+      FileUtils.remove_entry(tmp) if tmp && Dir.exist?(tmp)
     end
   end
+
+  it 'observe_step does not pay per successful tool call' do
+    tmp = Dir.mktmpdir
+    stub_const('PWN::AI::Agent::Policy::POLICY_FILE', File.join(tmp, 'policy.json'))
+    stub_const('PWN::AI::Agent::Policy::TRAJECTORY_FILE', File.join(tmp, 'policy_traj.jsonl'))
+    described_class.reset
+    allow(described_class).to receive(:enabled?).and_return(true)
+    PWN::Env[:ai] ||= {}
+    PWN::Env[:ai][:agent] ||= {}
+    PWN::Env[:ai][:agent][:policy] = true
+    described_class.begin_episode(session_id: 'p0_step', request: 'scan', kind: :autonomous_goal, engine: :grok)
+    first = described_class.observe_step(action: 'shell', ok: true, session_id: 'p0_step')
+    expect(first[:reward].to_f).to eq(0.0)
+    8.times { described_class.observe_step(action: 'shell', ok: true, session_id: 'p0_step') }
+    extra = described_class.observe_step(action: 'shell', ok: true, session_id: 'p0_step')
+    expect(extra[:reward].to_f).to be_within(0.001).of(-0.01)
+    fin = described_class.finish(session_id: 'p0_step', score: 0.9, confidence: 1.0, verdict: :solved)
+    expect(fin[:score].to_f).to eq(0.9)
+    expect(fin[:return]).not_to be_nil
+  ensure
+    described_class.reset
+    FileUtils.remove_entry(tmp) if tmp && Dir.exist?(tmp)
+  end
+
+  it 'terminal reward is judge score scaled by confidence, not step hygiene' do
+    expect(described_class.send(:terminal_reward, score: 1.0, confidence: 0.5)).to be_within(0.01).of(0.5)
+    expect(described_class.send(:terminal_reward, score: 0.0, confidence: 1.0)).to be_within(0.01).of(-1.0)
+  end
 end

data/spec/lib/pwn/ai/agent/reward_spec.rb

@@ -328,3 +328,75 @@ describe PWN::AI::Agent::Reward do
     expect(src).to include('quiet: true')
   end
 end
+
+describe 'PWN::AI::Agent::Reward vs TUI plan' do
+  it 'does not let a TUI plan_cover_low haircut a high-evidence original-request answer' do
+    stub_const('PWN::AI::Agent::Reward::SENTINEL_FILE', File.join(Dir.mktmpdir, 's.json'))
+    allow(PWN::AI::Agent::Reward).to receive(:reflect_available?).and_return(false)
+    plan = [
+      'Load and review rules of engagement, submission criteria, and the full in-scope subdomain list',
+      'Inventory applicable unauthenticated testing skills and techniques',
+      'Enumerate and resolve all in-scope subdomains and map reachable services',
+      'Fingerprint stacks, configurations, and exposure on every subdomain',
+      'Run exhaustive unauthenticated analysis across the full attack surface',
+      'Prioritize and deep-dive each promising lead to confirm exploitability',
+      'Develop evidence-backed proof-of-concept demonstrations',
+      'Combine related weaknesses into higher-impact attack chains',
+      'Assign evidence-backed severity and filter to submission-eligible issues',
+      'Use graphical applications where they improve validation',
+      'Compile submission-ready writeups with reproduction steps',
+      'Re-verify each finding still reproduces and present the final set'
+    ]
+    final = <<~TXT
+      Path-backed answer for the original request. Hosts scanned: 10.9.8.7 and 10.9.8.8.
+      Verified complete. Evidence in /tmp/pwn-eval-hosts.json. 12 hosts live. rspec passed.
+    TXT
+    klass = PWN::AI::Agent::Reward
+    v = klass.judge(
+      request: 'what live hosts can you find on this box and write /tmp/pwn-eval-hosts.json',
+      final: final,
+      plan: plan,
+      trace: [
+        '{"success":true,"result":{"stdout":"10.9.8.7 up","exit":0},"effect":"eval"}',
+        '{"success":true,"result":{"stdout":"wrote /tmp/pwn-eval-hosts.json","exit":0},"effect":"write"}'
+      ],
+      commit: false
+    )
+    expect(v[:source].to_s).to eq 'heuristic'
+    expect(v[:score]).to be >= 0.6
+    expect(v[:verdict].to_s).to eq 'solved'
+    args = {
+      request: 'what live hosts can you find on this box and write /tmp/pwn-eval-hosts.json',
+      final: final,
+      trace: [
+        '{"success":true,"result":{"stdout":"10.9.8.7 up","exit":0},"effect":"eval"}',
+        '{"success":true,"result":{"stdout":"wrote /tmp/pwn-eval-hosts.json","exit":0},"effect":"write"}'
+      ]
+    }
+    base = klass.send(:evidence_prior, **args)
+    mixed = klass.send(:evidence_prior, **args, plan: plan)
+    expect(mixed[:score]).to eq(base[:score])
+  end
+
+  it 'always grades the original request even when a stub compass or TUI plan is supplied' do
+    stub_const('PWN::AI::Agent::Reward::SENTINEL_FILE', File.join(Dir.mktmpdir, 's.json'))
+    allow(PWN::AI::Agent::Reward).to receive(:reflect_available?).and_return(false)
+    klass = PWN::AI::Agent::Reward
+    src = File.read(klass.method(:judge).source_location.first)
+    expect(src).not_to include('llm_judge(request: request, final: final, trace: trace, plan: opts[:plan])')
+    expect(src).not_to include('heuristic_judge(request: request, final: final, trace: trace, plan: opts[:plan])')
+    request = 'using hping3 what live hosts can you find in this subnet and write /tmp/x.json'
+    final = 'Live hosts: 10.1.2.3. Verified. Wrote /tmp/x.json. 4 hosts up. rspec passed.'
+    trace = [
+      '{"success":true,"result":{"stdout":"10.1.2.3 up","exit":0},"effect":"eval"}',
+      '{"success":true,"result":{"stdout":"wrote /tmp/x.json","exit":0},"effect":"write"}'
+    ]
+    a = klass.judge(request: request, final: final, trace: trace, commit: false)
+    b = klass.judge(request: request, final: final, trace: trace, plan: ['Carry out the core work'], commit: false)
+    c = klass.judge(request: request, final: final, trace: trace, plan: ['Enumerate subdomains', 'Compile writeups'], commit: false)
+    expect(a[:score]).to eq(b[:score])
+    expect(b[:score]).to eq(c[:score])
+    expect(a[:score]).to be >= 0.6
+    expect(a[:verdict].to_s).to eq('solved')
+  end
+end

data/spec/lib/pwn/ai/agent/scoreboard_roadmap_spec.rb

@@ -0,0 +1,61 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+require 'tmpdir'
+require 'fileutils'
+
+describe 'scoreboard roadmap gates' do
+  it 'heuristic judge never stamps solved 0.9 from overlap' do
+    v = PWN::AI::Agent::Reward.send(
+      :heuristic_judge,
+      request: 'how does the feedback loop work in pwn-ai',
+      final: 'The feedback loop in pwn-ai works via a keep-working harness. ' * 8,
+      trace: ['{"success":false,"error":"PATH=/usr/bin"}']
+    )
+    expect(v[:source].to_s).to eq('heuristic')
+    expect(v[:score].to_f).to be < 0.9
+    expect(v[:score].to_f).to be <= 0.70
+  end
+
+  it 'promote_to_success requires two of ORM, verify, critic' do
+    expect(PWN::AI::Agent::Reward.promote_to_success?(orm: true, verify: false, critic: false)).to be false
+    expect(PWN::AI::Agent::Reward.promote_to_success?(orm: true, verify: true, critic: false)).to be true
+    expect(PWN::AI::Agent::Reward.promote_to_success?(orm: false, verify: true, critic: true)).to be true
+  end
+
+  it 'calibration_green? is overconfidence at or below 0.08 with enough samples' do
+    stub_const('PWN::AI::Agent::Metrics::METRICS_FILE', File.join(Dir.mktmpdir, 'metrics.json'))
+    PWN::AI::Agent::Metrics.reset
+    expect(PWN::AI::Agent::Metrics.calibration_green?).to be false
+    12.times { PWN::AI::Agent::Metrics.record_calibration(predicted: 0.52, actual: 0.50, brier: 0.0004, engine: :grok) }
+    expect(PWN::AI::Agent::Metrics.calibration_green?).to be true
+    12.times { PWN::AI::Agent::Metrics.record_calibration(predicted: 0.87, actual: 0.49, brier: 0.1444, engine: :ollama) }
+    expect(PWN::AI::Agent::Metrics.calibration_green?).to be false
+  end
+
+  it 'policy is off when calibration is red' do
+    stub_const('PWN::AI::Agent::Metrics::METRICS_FILE', File.join(Dir.mktmpdir, 'metrics.json'))
+    PWN::AI::Agent::Metrics.reset
+    12.times { PWN::AI::Agent::Metrics.record_calibration(predicted: 0.87, actual: 0.49, brier: 0.1444, engine: :grok) }
+    PWN::Env[:ai] ||= {}
+    PWN::Env[:ai][:agent] ||= {}
+    PWN::Env[:ai][:agent][:policy] = true
+    expect(PWN::AI::Agent::Policy.enabled?).to be false
+  end
+
+  it 'mistakes to_context defaults to fixes only' do
+    src = File.read(PWN::AI::Agent::Mistakes.method(:to_context).source_location.first)
+    expect(src).to match(/fixes_only|KNOWN FIXES/)
+    expect(src).to match(/include_open|full/)
+  end
+
+  it 'skills catalog is names only without skill bodies' do
+    src = File.read(PWN::AI::Agent::PromptBuilder.method(:build).source_location.first)
+    expect(src).to match(/skills_block/)
+    expect(src).not_to match(/meta\[:content\]\.to_s\[0,\s*1200\]/)
+  end
+
+  it 'curriculum reclassify_backlog exists' do
+    expect(PWN::AI::Agent::Curriculum).to respond_to(:reclassify_backlog)
+  end
+end

data/spec/lib/pwn/reports/csv_spec.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe PWN::Reports::CSV do
+  it 'should display information for authors' do
+    authors_response = PWN::Reports::CSV
+    expect(authors_response).to respond_to :authors
+  end
+
+  it 'should display information for existing help method' do
+    help_response = PWN::Reports::CSV
+    expect(help_response).to respond_to :help
+  end
+
+  it 'should respond to generate' do
+    expect(PWN::Reports::CSV).to respond_to :generate
+  end
+end

data/spec/lib/pwn/reports/formats_spec.rb

@@ -0,0 +1,90 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+require 'json'
+require 'csv'
+require 'tmpdir'
+
+describe 'PWN::Reports format generators' do
+  let(:payload) do
+    {
+      title: 'PWN Format Spec',
+      report_name: 'pwn_format_spec',
+      executive_summary: 'One finding.',
+      findings: [
+        {
+          id: 'CFG-001',
+          title: 'Missing Security Headers',
+          severity: 'Low',
+          cvss: 4.3,
+          description: 'No X-Frame-Options',
+          poc: 'GET /',
+          recommendation: 'Add headers'
+        }
+      ]
+    }
+  end
+
+  {
+    PDF: { ext: 'pdf', const: 'PDF' },
+    HTML: { ext: 'html', const: 'HTML' },
+    Markdown: { ext: 'md', const: 'Markdown' },
+    XML: { ext: 'xml', const: 'XML' },
+    CSV: { ext: 'csv', const: 'CSV' },
+    JSON: { ext: 'json', const: 'JSON' }
+  }.each do |label, meta|
+    describe "PWN::Reports::#{meta[:const]}" do
+      it 'responds to generate, authors, and help' do
+        klass = PWN::Reports.const_get(meta[:const])
+        expect(klass).to respond_to(:generate)
+        expect(klass).to respond_to(:authors)
+        expect(klass).to respond_to(:help)
+      end
+
+      it "writes a .#{meta[:ext]} report via generate" do
+        klass = PWN::Reports.const_get(meta[:const])
+        Dir.mktmpdir('pwn_report_fmt') do |dir|
+          path = klass.generate(
+            dir_path: dir,
+            report_name: 'pwn_format_spec',
+            results_hash: payload
+          )
+          expect(path).to eq(File.join(dir, "pwn_format_spec.#{meta[:ext]}"))
+          expect(File.file?(path)).to eq(true)
+          expect(File.size(path)).to be > 0
+          body = File.binread(path)
+          case label
+          when :PDF
+            expect(body.start_with?('%PDF')).to eq(true)
+          when :HTML
+            expect(body).to match(/<!DOCTYPE html>/i)
+            expect(body).to include('Missing Security Headers')
+          when :Markdown
+            expect(body).to include('# PWN Format Spec')
+            expect(body).to include('Missing Security Headers')
+          when :XML
+            expect(body).to include('<?xml')
+            expect(body).to include('Missing Security Headers')
+          when :CSV
+            rows = CSV.parse(body)
+            expect(rows.first).to include('title')
+            expect(body).to include('Missing Security Headers')
+          when :JSON
+            parsed = JSON.parse(body)
+            expect(parsed['title']).to eq('PWN Format Spec')
+            expect(parsed['findings'].first['id']).to eq('CFG-001')
+          end
+        end
+      end
+    end
+  end
+
+  it 'honours an explicit path: override' do
+    Dir.mktmpdir('pwn_report_path') do |dir|
+      out = File.join(dir, 'custom.json')
+      path = PWN::Reports::JSON.generate(path: out, results_hash: payload)
+      expect(path).to eq(out)
+      expect(JSON.parse(File.read(out))['title']).to eq('PWN Format Spec')
+    end
+  end
+end

data/spec/lib/pwn/reports/html_spec.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe PWN::Reports::HTML do
+  it 'should display information for authors' do
+    authors_response = PWN::Reports::HTML
+    expect(authors_response).to respond_to :authors
+  end
+
+  it 'should display information for existing help method' do
+    help_response = PWN::Reports::HTML
+    expect(help_response).to respond_to :help
+  end
+
+  it 'should respond to generate' do
+    expect(PWN::Reports::HTML).to respond_to :generate
+  end
+end

data/spec/lib/pwn/reports/json_spec.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe PWN::Reports::JSON do
+  it 'should display information for authors' do
+    authors_response = PWN::Reports::JSON
+    expect(authors_response).to respond_to :authors
+  end
+
+  it 'should display information for existing help method' do
+    help_response = PWN::Reports::JSON
+    expect(help_response).to respond_to :help
+  end
+
+  it 'should respond to generate' do
+    expect(PWN::Reports::JSON).to respond_to :generate
+  end
+end

data/spec/lib/pwn/reports/markdown_spec.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe PWN::Reports::Markdown do
+  it 'should display information for authors' do
+    authors_response = PWN::Reports::Markdown
+    expect(authors_response).to respond_to :authors
+  end
+
+  it 'should display information for existing help method' do
+    help_response = PWN::Reports::Markdown
+    expect(help_response).to respond_to :help
+  end
+
+  it 'should respond to generate' do
+    expect(PWN::Reports::Markdown).to respond_to :generate
+  end
+end

data/spec/lib/pwn/reports/pdf_spec.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe PWN::Reports::PDF do
+  it 'should display information for authors' do
+    authors_response = PWN::Reports::PDF
+    expect(authors_response).to respond_to :authors
+  end
+
+  it 'should display information for existing help method' do
+    help_response = PWN::Reports::PDF
+    expect(help_response).to respond_to :help
+  end
+
+  it 'should respond to generate' do
+    expect(PWN::Reports::PDF).to respond_to :generate
+  end
+end

data/spec/lib/pwn/reports/xml_spec.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe PWN::Reports::XML do
+  it 'should display information for authors' do
+    authors_response = PWN::Reports::XML
+    expect(authors_response).to respond_to :authors
+  end
+
+  it 'should display information for existing help method' do
+    help_response = PWN::Reports::XML
+    expect(help_response).to respond_to :help
+  end
+
+  it 'should respond to generate' do
+    expect(PWN::Reports::XML).to respond_to :generate
+  end
+end

data/third_party/pwn_rdoc.jsonl

@@ -40,10 +40,12 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.ollama_create Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.ollama_create`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.practice Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.practice`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.practice_kpi Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.practice_kpi`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.practice_poc_ok? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.practice_poc_ok?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.practice_skip? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.practice_skip?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.preference_balance Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.preference_balance`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.preference_diet_gate Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.preference_diet_gate`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.python_site_package_roots Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.python_site_package_roots`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.reclassify_backlog Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.reclassify_backlog`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.red_team_plan Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.red_team_plan`: Supported Method Parameters\n\nhint = PWN::AI::Agent::Curriculum.red_team_plan(\n\nrequest: 'required - user goal',\nplan: 'required - numbered plan text from plan_first'\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.reflect_available? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.reflect_available?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Curriculum.repeating_trend Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Curriculum.repeating_trend`: "}]}
@@ -328,6 +330,7 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.call_engine Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.call_engine`: Supported Method Parameters\n\nmsg = PWN::AI::Agent::Loop.call_engine(\n\nmessages: 'required - OpenAI-format messages array',\ntools: 'optional - OpenAI tools array'\n\n)\n\nReturns a normalised assistant message hash:\n\n{ role: 'assistant', content: String|nil,\n  tool_calls: [ {id:, type:'function', function:{name:, arguments:}} ],\n  _native_content: <provider raw>  (when adapter needs round-trip) }\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.catalog_lookup? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.catalog_lookup?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.chat_response_history Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.chat_response_history`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.checkpoint_result Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.checkpoint_result`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.compact_history! Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.compact_history!`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.debug_final_text! Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.debug_final_text!`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.debug_msgs_line Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.debug_msgs_line`: "}]}
@@ -377,6 +380,7 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.ollama_wire_tool_call Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.ollama_wire_tool_call`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.openai_wire_messages Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.openai_wire_messages`: Supported Method Parameters\n\nwire = PWN::AI::Agent::Loop.openai_wire_messages(\n\nmessages: 'required - in-memory OpenAI-ish messages (may have Hash args / internal keys)'\n\n)\n\nReturns a deep-copied array safe for OpenAI / xAI chat.completions:\n\ndrops _native_content / _text_tool_coerced / thinking private keys\n\nstringifies function.arguments maps\n\ncoerces Hash/non-string content to JSON/string (nil kept for assistant tool turns)\n\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.openai_wire_tool_call Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.openai_wire_tool_call`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.operator_bound_refusal Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.operator_bound_refusal`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.parse_contract Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.parse_contract`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.parse_tool_arguments Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.parse_tool_arguments`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.payload_sig Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.payload_sig`: "}]}
@@ -392,6 +396,8 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.run Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.run`: Supported Method Parameters\n\nfinal = PWN::AI::Agent::Loop.run(\n\nrequest: 'required - what the human typed',\nsession_id: 'optional - PWN::Sessions id (transcript is appended to it)',\nenabled_toolsets: 'optional - subset of Registry.toolsets, or nil for all',\non_tool: 'optional - ->(name, args, result) callback for live UI',\nsystem_role_content: 'optional - override default system prompt (built from session_id if not provided)'\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.session_chat_history Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.session_chat_history`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.should_auto_introspect? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.should_auto_introspect?`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.spill_tool_body Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.spill_tool_body`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.spill_tool_history! Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.spill_tool_history!`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.stamped_effect Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.stamped_effect`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.start_debug_session Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.start_debug_session`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.stringify_tool_arguments Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.stringify_tool_arguments`: "}]}
@@ -404,6 +410,7 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.tool_effects Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.tool_effects`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.wait_trace_step! Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.wait_trace_step!`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.world_knowledge? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.world_knowledge?`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.wrap_untrusted_tool Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.wrap_untrusted_tool`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Loop.write_verified? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Loop.write_verified?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.advantage Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.advantage`: Supported Method Parameters\n\na = PWN::AI::Agent::Metrics.advantage(name: ‘shell’)\n\nC1 — tool.success_rate − global_rate over the rolling window.\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.authors Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}
@@ -411,11 +418,12 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.blank_bucket Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.blank_bucket`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.bump Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.bump`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.calibration Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.calibration`: Supported Method Parameters\n\ncal = PWN::AI::Agent::Metrics.calibration(engine: :ollama)\n"}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.calibration_green? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.calibration_green?`: Supported Method Parameters\n\nPWN::AI::Agent::Metrics.reset\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.changepoints Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.changepoints`: Supported Method Parameters\n\ncps = PWN::AI::Agent::Metrics.changepoints\n\nE1 — 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].\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.decay Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.decay`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.effective_rate Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.effective_rate`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.gamma_sample Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.gamma_sample`: "}]}
-{"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.health_line Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.health_line`: Supported Method Parameters\n\nPWN::AI::Agent::Metrics.reset\n"}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.health_line Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.health_line`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.help Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.help`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.judge_confidence Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.judge_confidence`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.judge_rate Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.judge_rate`: "}]}
@@ -429,6 +437,8 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.record_step_reward Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.record_step_reward`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.reset Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.reset`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.save Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.save`: Supported Method Parameters\n\nPWN::AI::Agent::Metrics.save(\n\nmetrics: 'required - Hash returned by .load / mutated in place'\n\n)\n"}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.scale_prediction Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.scale_prediction`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.scoreboard Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.scoreboard`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.summary Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.summary`: Supported Method Parameters\n\nrows = PWN::AI::Agent::Metrics.summary(\n\nlimit: 'optional - cap number of tools returned (default 25)',\nengine: 'optional - only that engine\\'s sub-bucket (falls back to global when absent)'\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.thompson Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.thompson`: Supported Method Parameters\n\np = PWN::AI::Agent::Metrics.thompson(name: ‘shell’)\n\nC1 — Thompson sample from Beta(ok+1, fail+1). Naturally balances exploit/explore; used by Registry.rank as the tie-breaker.\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Metrics.to_context Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Metrics.to_context`: Supported Method Parameters\n\nctx = PWN::AI::Agent::Metrics.to_context(\n\nlimit: 'optional - cap number of tools included (default 8)',\nengine: 'optional - restrict to one engine\\'s telemetry'\n\n)\n"}]}
@@ -479,6 +489,7 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Policy.bump_visit! Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Policy.bump_visit!`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Policy.cold? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Policy.cold?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Policy.completeness_bin Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Policy.completeness_bin`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Policy.contract_fields_met Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Policy.contract_fields_met`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Policy.current_episode Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Policy.current_episode`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Policy.current_state Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Policy.current_state`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Policy.detach_episode! Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Policy.detach_episode!`: "}]}
@@ -531,6 +542,7 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::PromptBuilder.host_line Usage"},{"role":"assistant","content":"`PWN::AI::Agent::PromptBuilder.host_line`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::PromptBuilder.host_load_block Usage"},{"role":"assistant","content":"`PWN::AI::Agent::PromptBuilder.host_load_block`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::PromptBuilder.learning_block Usage"},{"role":"assistant","content":"`PWN::AI::Agent::PromptBuilder.learning_block`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::PromptBuilder.memory_asked? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::PromptBuilder.memory_asked?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::PromptBuilder.memory_block Usage"},{"role":"assistant","content":"`PWN::AI::Agent::PromptBuilder.memory_block`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::PromptBuilder.metrics_block Usage"},{"role":"assistant","content":"`PWN::AI::Agent::PromptBuilder.metrics_block`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::PromptBuilder.mistakes_block Usage"},{"role":"assistant","content":"`PWN::AI::Agent::PromptBuilder.mistakes_block`: "}]}
@@ -612,6 +624,7 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Reward.preference_balance Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Reward.preference_balance`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Reward.preferences Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Reward.preferences`: Supported Method Parameters\n\nrows = PWN::AI::Agent::Reward.preferences(limit: 500, source: nil)\n"}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Reward.prm Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Reward.prm`: Supported Method Parameters\n\nsteps = PWN::AI::Agent::Reward.prm(\n\nrequest: 'required - user goal',\nsession_id: 'optional - session to score in place',\ntrace: 'optional - Array of {name:, args:, result:} or Strings'\n\n)\n\nReturns [{idx:, step:, reward: -1|0|1}, …] and, when session_id is given, rewrites each tool line in the transcript with a ‘[step_reward=N]` prefix so exemplars_for / distill_skill can keep only reward>0 steps (C4 minimal sufficient trace).\n"}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::Reward.promote_to_success? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Reward.promote_to_success?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Reward.proxy_distrust Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Reward.proxy_distrust`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Reward.record_preference Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Reward.record_preference`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::Reward.record_sentinel Usage"},{"role":"assistant","content":"`PWN::AI::Agent::Reward.record_sentinel`: "}]}
@@ -743,6 +756,7 @@
 {"messages":[{"role":"user","content":"PWN::AI::Agent::ToolGuard.present? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::ToolGuard.present?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::ToolGuard.protect_core_constants! Usage"},{"role":"assistant","content":"`PWN::AI::Agent::ToolGuard.protect_core_constants!`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::ToolGuard.protect_http! Usage"},{"role":"assistant","content":"`PWN::AI::Agent::ToolGuard.protect_http!`: "}]}
+{"messages":[{"role":"user","content":"PWN::AI::Agent::ToolGuard.refuse_copied_persist? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::ToolGuard.refuse_copied_persist?`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::ToolGuard.reset_timeout_budget Usage"},{"role":"assistant","content":"`PWN::AI::Agent::ToolGuard.reset_timeout_budget`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::ToolGuard.reset_timeout_budget! Usage"},{"role":"assistant","content":"`PWN::AI::Agent::ToolGuard.reset_timeout_budget!`: "}]}
 {"messages":[{"role":"user","content":"PWN::AI::Agent::ToolGuard.shell_bash? Usage"},{"role":"assistant","content":"`PWN::AI::Agent::ToolGuard.shell_bash?`: "}]}
@@ -2478,20 +2492,45 @@
 {"messages":[{"role":"user","content":"PWN::Plugins::Zaproxy.stop Usage"},{"role":"assistant","content":"`PWN::Plugins::Zaproxy.stop`: Supported Method Parameters\n\nPWN::Plugins::Zaproxy.stop(\n\nzap_obj: 'required - zap_obj returned from #open method'\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::Plugins::Zaproxy.tamper Usage"},{"role":"assistant","content":"`PWN::Plugins::Zaproxy.tamper`: Supported Method Parameters\n\nPWN::Plugins::Zaproxy.tamper(\n\nzap_obj: 'required - zap_obj returned from #open method',\ndomain: 'required - FQDN to tamper (e.g. test.domain.local)',\nenabled: 'optional - boolean (defaults to true)'\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::Plugins::Zaproxy.zap_rest_call Usage"},{"role":"assistant","content":"`PWN::Plugins::Zaproxy.zap_rest_call`: Supported Method Parameters\n\nzap_rest_call(\n\nzap_obj: 'required zap_obj returned from #start method',\nrest_call: 'required rest call to make per the schema',\nhttp_method: 'optional HTTP method (defaults to GET)\nhttp_body: 'optional HTTP body sent in HTTP methods that support it e.g. POST'\n\n)\n"}]}
-{"messages":[{"role":"user","content":"PWN::Reports.authors Usage"},{"role":"assistant","content":"`PWN::Reports.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}
+{"messages":[{"role":"user","content":"PWN::Reports.authors Usage"},{"role":"assistant","content":"`PWN::Reports.authors`: "}]}
 {"messages":[{"role":"user","content":"PWN::Reports.help Usage"},{"role":"assistant","content":"`PWN::Reports.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports.report_payload Usage"},{"role":"assistant","content":"`PWN::Reports.report_payload`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports.resolve_path Usage"},{"role":"assistant","content":"`PWN::Reports.resolve_path`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports.stringify_keys Usage"},{"role":"assistant","content":"`PWN::Reports.stringify_keys`: "}]}
 {"messages":[{"role":"user","content":"PWN::Reports::AIRedTeam.authors Usage"},{"role":"assistant","content":"`PWN::Reports::AIRedTeam.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::AIRedTeam.generate Usage"},{"role":"assistant","content":"`PWN::Reports::AIRedTeam.generate`: Supported Method Parameters\n\nPWN::Reports::AIRedTeam.generate(\n\ndir_path: 'optional - Directory path to save the report (defaults to .)',\nresults_hash: 'optional - Hash containing the results of the AI RedTeam analysis (defaults to empty hash structure)',\nreport_name: 'optional - Name of the report file (defaults to current directory name)'\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::AIRedTeam.help Usage"},{"role":"assistant","content":"`PWN::Reports::AIRedTeam.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::CSV.authors Usage"},{"role":"assistant","content":"`PWN::Reports::CSV.authors`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::CSV.generate Usage"},{"role":"assistant","content":"`PWN::Reports::CSV.generate`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::CSV.help Usage"},{"role":"assistant","content":"`PWN::Reports::CSV.help`: "}]}
 {"messages":[{"role":"user","content":"PWN::Reports::Fuzz.authors Usage"},{"role":"assistant","content":"`PWN::Reports::Fuzz.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::Fuzz.generate Usage"},{"role":"assistant","content":"`PWN::Reports::Fuzz.generate`: Supported Method Parameters\n\nPWN::Reports::Fuzz.generate(\n\ndir_path: dir_path,\nresults_hash: results_hash,\nchar_encoding: 'optional - character encoding returned by PWN::Plugins::Char.list_encoders (defaults to UTF-8)'\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::Fuzz.help Usage"},{"role":"assistant","content":"`PWN::Reports::Fuzz.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::HTML.authors Usage"},{"role":"assistant","content":"`PWN::Reports::HTML.authors`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::HTML.generate Usage"},{"role":"assistant","content":"`PWN::Reports::HTML.generate`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::HTML.h Usage"},{"role":"assistant","content":"`PWN::Reports::HTML.h`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::HTML.help Usage"},{"role":"assistant","content":"`PWN::Reports::HTML.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::HTML.summary_html Usage"},{"role":"assistant","content":"`PWN::Reports::HTML.summary_html`: "}]}
 {"messages":[{"role":"user","content":"PWN::Reports::HTMLFooter.authors Usage"},{"role":"assistant","content":"`PWN::Reports::HTMLFooter.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::HTMLFooter.generate Usage"},{"role":"assistant","content":"`PWN::Reports::HTMLFooter.generate`: Supported Method Parameters\n\nPWN::Reports::HTMLFooter.generate(\n\ncolumn_names: 'required - array of column names to use in the report table',\ndriver_src_uri: 'required - pwn driver source code uri',\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::HTMLFooter.help Usage"},{"role":"assistant","content":"`PWN::Reports::HTMLFooter.help`: "}]}
 {"messages":[{"role":"user","content":"PWN::Reports::HTMLHeader.authors Usage"},{"role":"assistant","content":"`PWN::Reports::HTMLHeader.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::HTMLHeader.generate Usage"},{"role":"assistant","content":"`PWN::Reports::HTMLHeader.generate`: Supported Method Parameters\n\nPWN::Reports::HTMLHeader.generate(\n\ncolumn_names: 'required - array of column names to use in the report table',\ndriver_src_uri: 'required - pwn driver source code uri',\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::HTMLHeader.help Usage"},{"role":"assistant","content":"`PWN::Reports::HTMLHeader.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::JSON.authors Usage"},{"role":"assistant","content":"`PWN::Reports::JSON.authors`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::JSON.generate Usage"},{"role":"assistant","content":"`PWN::Reports::JSON.generate`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::JSON.help Usage"},{"role":"assistant","content":"`PWN::Reports::JSON.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::Markdown.authors Usage"},{"role":"assistant","content":"`PWN::Reports::Markdown.authors`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::Markdown.generate Usage"},{"role":"assistant","content":"`PWN::Reports::Markdown.generate`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::Markdown.help Usage"},{"role":"assistant","content":"`PWN::Reports::Markdown.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::PDF.assemble_pdf Usage"},{"role":"assistant","content":"`PWN::Reports::PDF.assemble_pdf`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::PDF.authors Usage"},{"role":"assistant","content":"`PWN::Reports::PDF.authors`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::PDF.generate Usage"},{"role":"assistant","content":"`PWN::Reports::PDF.generate`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::PDF.help Usage"},{"role":"assistant","content":"`PWN::Reports::PDF.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::PDF.pdf_escape Usage"},{"role":"assistant","content":"`PWN::Reports::PDF.pdf_escape`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::PDF.pdf_stream Usage"},{"role":"assistant","content":"`PWN::Reports::PDF.pdf_stream`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::PDF.render_pdf Usage"},{"role":"assistant","content":"`PWN::Reports::PDF.render_pdf`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::PDF.wrap_line Usage"},{"role":"assistant","content":"`PWN::Reports::PDF.wrap_line`: "}]}
 {"messages":[{"role":"user","content":"PWN::Reports::Phone.authors Usage"},{"role":"assistant","content":"`PWN::Reports::Phone.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::Phone.generate Usage"},{"role":"assistant","content":"`PWN::Reports::Phone.generate`: Supported Method Parameters\n\nPWN::Reports::Phone.generate(\n\ndir_path: dir_path,\nresults_hash: results_hash\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::Phone.help Usage"},{"role":"assistant","content":"`PWN::Reports::Phone.help`: "}]}
@@ -2501,6 +2540,10 @@
 {"messages":[{"role":"user","content":"PWN::Reports::URIBuster.authors Usage"},{"role":"assistant","content":"`PWN::Reports::URIBuster.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::URIBuster.generate Usage"},{"role":"assistant","content":"`PWN::Reports::URIBuster.generate`: Supported Method Parameters\n\nPWN::Reports::URIBuster.generate(\n\ndir_path: dir_path,\nresults_hash: results_hash\n\n)\n"}]}
 {"messages":[{"role":"user","content":"PWN::Reports::URIBuster.help Usage"},{"role":"assistant","content":"`PWN::Reports::URIBuster.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::XML.authors Usage"},{"role":"assistant","content":"`PWN::Reports::XML.authors`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::XML.generate Usage"},{"role":"assistant","content":"`PWN::Reports::XML.generate`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::XML.help Usage"},{"role":"assistant","content":"`PWN::Reports::XML.help`: "}]}
+{"messages":[{"role":"user","content":"PWN::Reports::XML.safe_tag Usage"},{"role":"assistant","content":"`PWN::Reports::XML.safe_tag`: "}]}
 {"messages":[{"role":"user","content":"PWN::SAST.authors Usage"},{"role":"assistant","content":"`PWN::SAST.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}
 {"messages":[{"role":"user","content":"PWN::SAST.help Usage"},{"role":"assistant","content":"`PWN::SAST.help`: "}]}
 {"messages":[{"role":"user","content":"PWN::SAST::AMQPConnectAsGuest.authors Usage"},{"role":"assistant","content":"`PWN::SAST::AMQPConnectAsGuest.authors`: Author(s)\n\n0day Inc. <support@0dayinc.com>\n"}]}