Module: PWN::AI::Agent::Loop

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

Overview

The agent conversation loop:

build system prompt → call LLM with tools → if tool_calls: dispatch,
append role:'tool' results, loop → else: return text.

This replaces the regex-ReAct in PWN::Plugins::REPL :pwn_ai_hook with native function-calling. State (memory, skills, sessions) is all externalised — Loop.run is stateless aside from the messages array it builds.

NEGATIVE-FEEDBACK CLOSURE

Loop.run is where "learn from mistakes, don't repeat them" is actually enforced. On EVERY failed dispatch it:

1. Records the (tool, normalised_error) fingerprint into
 PWN::AI::Agent::Mistakes with a PERSISTENT cross-session count.
2. Reads that count back and, if it OR the in-turn count reaches
 REPEAT_THRESHOLD, prepends a hard "REPEATED FAILURE — change
 approach" guard to the tool result the model sees next.
3. Appends Mistakes.correction_hint (seen N×, sig, KNOWN FIX: …)
 so a previously-discovered fix is handed straight back to the
 model on the FIRST recurrence in a new session — it does not
 have to fail 3× again to re-learn what it already knew.

PromptBuilder.mistakes_block re-injects the top open mistakes and top known fixes into the system prompt of every future turn.

COMPLETION

The original request is the completion signal. TaskSummarizer and Policy are advisory (compass / rank). Loop keeps calling CORE_TOOLS until that request is done or truly blocked, then stops.

LOCAL-MODEL SCAFFOLDING

When the active engine is :ollama (or the corresponding :agent flags are set) Loop.run additionally:

* threads request → PromptBuilder for relevance-ranked MEMORY,
* threads request → Registry.definitions(relevance:) for a slimmed
tool set (:tool_router),
* splices Learning.exemplars_for(request:) between system and user
as few-shot behaviour retrieval,
* runs a plan-then-act pre-pass (:plan_first) so the model
externalises a tool plan before its first dispatch,
* escalates to a frontier persona for a 3-line corrective hint
once ≥ ESCALATE_AFTER_FAILS in-turn failures accumulate
(:escalation_persona) — the local model still produces the final
answer so Learning/Metrics stay attributed to :ollama.

Constant Summary collapse

DEFAULT_MAX_ITERS = 
777
ESCALATE_AFTER_FAILS = 
4
BOUNCE_FAIL_KEYS = 
%w[
  unsatisfied incomplete_final empty_final evidence_final
].freeze
ENGINE_MODS = 
{
  openai: 'PWN::AI::OpenAI',
  grok: 'PWN::AI::Grok',
  ollama: 'PWN::AI::Ollama',
  openwebui: 'PWN::AI::OpenWebUI',
  anthropic: 'PWN::AI::Anthropic',
  gemini: 'PWN::AI::Gemini'
}.freeze
HOT_WINDOW_SECS =

P17 — true when RECENT unresolved agent_loop / assistant_answer budget fingerprints dominate Mistakes.top. Sliding window + auto-cool so the loop's own exhaust-path Mistakes.record cannot permanently latch hot (scar 8ec3303ed69e self-latch). Do NOT deepen caps; cool the detector.

48 * 3600
HOT_COOL_MAX_RECENT =

<=1 budget hit in window => cooled (not hot)

1
PARK_COOL_SECS =

P17 rate-based cool/park for permanent budget scars (8ec3303ed69e). Leaves scar open but parks it so it stops dominating Mistakes.top. Resolve is rate-based only (external / after multi-day cool) — never because a guard patch landed. PARK_COOL_SECS (24h) is intentionally shorter than HOT_WINDOW (48h): once hot?=false, a single cooled scar must not keep owning Mistakes.top for another full day.

24 * 3600
PRIVILEGED_TOOLSETS = 
%w[cron swarm].freeze
SNAPSHOT_STALE_SECS = 
6 * 3600
INCOMPLETE_FINAL_RX =

P28 — incomplete / handoff finals: model emitted text-only before the goal was done ("shall I proceed?", "next step:", "want me to…"). Loop.run treats no-tool_calls as FINAL; this detector lets us refuse that handoff and keep the tool loop alive for multi-step autonomy.

Local/thinking models (gemma/Qwen abliterated etc.) often emit a monologue that NARRATES the next tool ("Wait, let's try hping3…") without producing native tool_calls or shell(...). Treat that as incomplete too so the loop re-pressures tools instead of FINAL.

/
  \b(shall\s+i|should\s+i|may\s+i|can\s+i|want\s+me\s+to|do\s+you\s+want\s+me|
     next\s+single\s+step|next\s+step\s*:|awaiting\s+your\s+(ok|approval|go-ahead|confirmation)|
     if\s+you(?:'d|\s+would)\s+like\s+me\s+to|say\s+the\s+word|confirm\s+(before|and\s+i)|
     ready\s+to\s+proceed|ok\s+to\s+(proceed|continue|apply)|proceed\?|
     continue\?|before\s+i\s+(apply|change|run|continue|proceed)|
     once\s+you\s+(confirm|approve)|let\s+me\s+know\s+if|
     i(?:'ll|\s+will)\s+wait\b|waiting\s+for\s+(your\s+)?(go|ok|approval|confirmation)
  )\b
/ix
MONOLOGUE_TOOL_INTENT_RX =

Narrated-intent monologue without a structured tool call. Distinct from INCOMPLETE_FINAL_RX (polite handoff to the human).

/
  \b(
    wait[,\s]+let'?s\s+try|
    let'?s\s+try\s+(one|to|again|hping|nmap|ping|sudo|shell|running|checking)|
    i\s+(?:will|'ll)\s+(?:just\s+)?(?:try|run|check|probe|scan|use)\b|
    actually,?\s+i\s+will\b|
    one\s+more\s+thing\b|
    if\s+it\s+fails\b.{0,80}\bthen\s+we\s+can\b|
    verification\s+complete\b|
    report\s+that\s+(?:the\s+)?verification\s+failed\b
  )
/ix
ACT_REQUEST_RX = 
/
  \b(write|create|implement|fix|patch|replace|refactor|overwrite|
     add (?:a |the )?|update|install|delete|remove|rename|
     regenerate|rebuild|document)
  \b
/ix
FORCED_WRAP_RX = 
/
  forced\s+to\s+a\s+final|were\s+not\s+written|not\s+written\s+to\s+disk|
  resume\s+from\s+the\s+table|remaining\s+block|
  were\s+not\s+applied|not\s+applied\s+in\s+this\s+turn|
  (?:do\s+that\s+)?next\s+time
/ix
LOOKUP_REQUEST_RX = 
/
  \b(what\s+is\s+my|hostname|uname|cwd|whoami|status|version|how\s+many)\b
/ix
SKILLS_CATALOG_RX = 
/
  \bskills?\b.{0,40}\b(available|installed|loaded|catalog|list)\b |
  \b(what|which|list)\b.{0,40}\bskills?\b
/ix
HOST_PATH_RX =

Real filesystem paths only — not https://host.tld (that was matching //host.tld).

%r{(?:(?<![.:/])/(?!/)|\./)[\w./-]+\.\w+}
BROWSER_REQUEST_RX = 
/
  TransparentBrowser|browser_obj|\bdevtools\b|
  \b(navigate|dump_links|headless_?chrome|watir)\b
/ix
HOWTO_RX =

Request intent for routing (how-to vs act/recon vs pure recall/greeting). Local models thrash when pure explanation/recall/greeting asks are force-planned into multi-step host probes or multi-tool session archaeology. :howto → answer with explanation only (no plan_first / no live recon). :recall → prior-turn / vague memory cue; cheap path only. :greeting → short hello / light smalltalk; deterministic ack, no tools. :recon_act → live discovery (same tool loop as :act; no auth gate). :act → general agent work with tools.

/
  \b(
    how\s+to|how\s+do\s+i|how\s+can\s+i|how\s+would\s+i|how\s+does\s+one|
    what\s+is\s+the\s+(?:syntax|command|usage|flag|option)|
    explain\s+how|show\s+me\s+how|examples?\s+of\s+using|
    manual\s+for|usage\s+of|syntax\s+for|man\s+page
  )\b
/ix
RECALL_RX =

Pure prior-turn recall — must never enter plan_first / multi-tool loops. Covers both "what did I just say?" (user) and "how did you respond?" / "what did you just say?" (assistant) so last-turn injection is used.

/
  \A\s*(
    what\s+did\s+i\s+(just\s+)?say\??|
    what\s+did\s+i\s+(just\s+)?(?:ask|type|write|request)\??|
    what\s+was\s+my\s+last\s+(?:request|message|question|prompt|turn)\??|
    what\s+was\s+(?:the\s+)?(?:previous|prior|last)\s+(?:thing\s+i\s+said|request|message|turn)\??|
    remind\s+me\s+what\s+i\s+(?:just\s+)?(?:said|asked)\??|
    repeat\s+(?:my\s+)?(?:last|previous)\s+(?:request|message)\??|
    say\s+that\s+again\??|
    recollection\s+test\??|
    memory\s+recall\s+test\??|
    how\s+did\s+you\s+respond(?:\s+to\s+what\s+i\s+(?:just\s+)?(?:said|asked))?\??|
    how\s+did\s+you\s+(?:just\s+)?(?:answer|reply)(?:\s+to\s+(?:me|that|my\s+last))?\??|
    what\s+(?:was|is)\s+your\s+(?:last|previous|prior)\s+(?:answer|response|reply)\??|
    what\s+did\s+you\s+(?:just\s+)?(?:say|answer|reply|respond)\??|
    remind\s+me\s+what\s+you\s+(?:just\s+)?(?:said|answered|replied)\??|
    repeat\s+your\s+(?:last|previous)\s+(?:answer|response|reply)\??
  )\s*\z
/ix
VAGUE_MEMORY_RX =

Broader "use your memory / prior context" cues. Still cheap: inject last turn + at most one memory_recall; never multi-step plans.

/
  \b(
    what\s+did\s+i\s+(just\s+)?(?:say|ask|type|request)|
    what\s+was\s+my\s+last|
    how\s+did\s+you\s+respond|
    what\s+did\s+you\s+(?:just\s+)?(?:say|answer|reply|respond)|
    what\s+(?:was|is)\s+your\s+(?:last|previous|prior)\s+(?:answer|response|reply)|
    (?:without\s+looking\s+up).{0,40}(?:session|discussing|talking)|
    (?:from\s+)?(?:memory|context|earlier|previously|prior\s+turn)|
    (?:do\s+you\s+)?remember\s+what\s+(?:i|you)|
    recall\s+(?:what|my|your|the\s+last)|
    last\s+thing\s+(?:i|you)\s+said
  )\b
/ix
LAST_SESSION_RX = 
/\b(?:in|from|of)\s+(?:the\s+)?(?:last|previous|prior)\s+session\b|\blast\s+session\b/i
GREETING_RX =

Pure greeting / light smalltalk — never full :act tool loop. Anchored short forms only so "hi, please scan X" stays :act/:recon_act. Do NOT echo weather or invent social filler; answer_greeting is fixed.

/
  \A\s*(
    (?:hi|hello|howdy|hey|yo|sup|hiya|greetings)(?:\s*[.!?]*)?
    (?:\s*,?\s*(?:there|all|folks|team|everyone|y'?all))?
    |
    good\s+(?:morning|afternoon|evening|day|night)(?:\s*[.!?]*)?
    |
    (?:hi|hello|howdy|hey)(?:\s*[.!?*,]*)?\s+
    (?:it'?s|its|it\s+is)\s+
    (?:cloudy|sunny|rainy|raining|foggy|windy|stormy|nice|cold|hot|warm|
       beautiful|gloomy|overcast|clear|chilly|humid|snow(?:ing|y)?)
    (?:\s+out(?:\s+there)?)?(?:\s*[.!?]*)?
    |
    (?:hi|hello|howdy|hey)(?:\s*[.!?*,]*)?\s+
    (?:the\s+weather\s+is\s+\w+|what'?s\s+up|how\s+are\s+you|
       how'?s\s+it\s+going|how\s+goes\s+it)
    (?:\s*[.!?]*)?
  )\s*\z
/ix
LIVE_RECON_RX = 
/
  \b(
    (?:find|discover|enumerate|scan|sweep|probe|map)\s+
    (?:live\s+)?(?:hosts?|ips?|targets?|subnet|network|range)|
    live\s+hosts?\s+(?:can\s+you\s+)?find|
    what\s+live\s+hosts|
    ping\s+sweep\s+(?:of\s+)?(?:this|the|my)\s+
    |(?:run|do|perform)\s+(?:a\s+)?(?:ping\s+)?sweep
    |scan\s+(?:this|the|my)\s+(?:subnet|network|lan|range)
  )\b
/ix

Class Method Summary collapse

Class Method Details

.authors ⇒ Object

Author(s)

0day Inc. support@0dayinc.com



2633
2634
2635
 
# File 'lib/pwn/ai/agent/loop.rb', line 2633

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

.catalog_lookup?(opts = {}) ⇒ Boolean

True only when the ask needs a live host/file/browser effect. World-knowledge questions ("what color is a cherry") do not.

Returns:

  • (Boolean) 


476
477
478
479
480
481
482
483
484
485
486
 
# File 'lib/pwn/ai/agent/loop.rb', line 476

public_class_method def self.catalog_lookup?(opts = {})
  request = opts[:request].to_s.strip
  return false if request.empty?
  return false if request.length > 120
  return false if request.match?(ACT_REQUEST_RX)
  return false if request.match?(HOWTO_RX)

  request.match?(SKILLS_CATALOG_RX)
rescue StandardError
  false
end

.debug_on?(opts = {}) ⇒ Boolean

Returns:

  • (Boolean) 


65
66
67
68
69
70
71
72
73
74
 
# File 'lib/pwn/ai/agent/loop.rb', line 65

public_class_method def self.debug_on?(opts = {})
  return true if opts[:debug]
  return true if defined?(PWN::Plugins::Log) && PWN::Plugins::Log.debug_enabled?

  pry_on = defined?(Pry) && Pry.respond_to?(:config) &&
           Pry.config.respond_to?(:pwn_ai_debug) && Pry.config.pwn_ai_debug
  return true if pry_on

  false
end

.help ⇒ Object

Display Usage for this Module



2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
 
# File 'lib/pwn/ai/agent/loop.rb', line 2639

public_class_method def self.help
  puts <<~USAGE
    USAGE:
      final = PWN::AI::Agent::Loop.run(
        request: 'what does `id` return on this host?',
        session_id: PWN::Sessions.create[:id],
        enabled_toolsets: %w[terminal pwn memory skills],
        on_tool: ->(name, args, result) { puts "→ \#{name}: \#{result[0,1_024]}" },
        system_role_content: 'You are a helpful assistant that can call tools to answer questions.'
      )
      # Live task summaries (default ON): BEFORE each tool *collection*,
      # on_tool('task', high_level_brief, '') — one-to-many with real tools.
      # Task lines never carry a result payload (no result row in the TUI).
      # so repl.rb prints name=task with arg_preview=summary. Also coalesce bursts into
      # via on_tool only: [ ts → pwn-ai → task ] <brief> (no [pwn-ai/task] prefix)
      # Toggle via PWN::Env[:ai][:agent]:
      #   task_summary: true|false
      #   task_summary_every: 5          # emit every N tools
      #   task_summary_interval_s: 8.0   # or every N seconds
      #   task_summary_verbose: false

      Supported engines: #{ENGINE_MODS.keys.join(', ')}
      Set PWN::Env[:ai][:active] to choose.

      Intent routing (all engines; critical for ollama/openwebui):
        how-to / usage questions → text-only explanation (no tools, no plan_first)
        pure prior-turn recall ("what did I just say?") → answer_recall (no tools)
        pure greeting / light smalltalk → answer_greeting (no tools, no weather echo)
        live sweeps are host-work goals like any other — pwn-ai does not
        decide authorization
      Local-model scaffolding (PWN::Env[:ai][:agent]):
        :plan_first          - Boolean, plan-then-act pre-pass (default: local engine :ollama/:openwebui)
        :tool_router         - Boolean/nil, slim Registry.definitions (nil=auto on for ollama)
        :escalation_persona  - Swarm persona name for frontier corrective hints when stuck
        :critic              - S3 constitutional critic before every final (Boolean)
        :red_team_plan       - S4 adversarial plan review after plan_first (Boolean)
        :counterfactual      - S2 A/B branch on REPEAT_THRESHOLD → DPO pair (Boolean)
        :hindsight           - C3 HER-relabel failures (Boolean, default true)
        :policy              - R5 live tabular Q / REINFORCE (Boolean, default true; advisory only)
        :verify_as_reward    - E3 ground every final via extro_verify (Boolean)

      P28 autonomy: incomplete-final detector refuses mid-goal handoffs.
      Loop.run keeps CORE_TOOLS until may_finalize? — there is no
      iteration-budget abort.

      #{self}.authors
  USAGE
end

.needs_host_work?(opts = {}) ⇒ Boolean

Returns:

  • (Boolean) 


505
506
507
508
509
510
511
512
513
514
 
# File 'lib/pwn/ai/agent/loop.rb', line 505

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

  true
rescue StandardError
  false
end

.ollama_wire_messages(opts = {}) ⇒ Object

Supported Method Parameters

wire = PWN::AI::Agent::Loop.ollama_wire_messages( messages: 'required - in-memory OpenAI-ish messages (may have String args)' )

Returns a deep-copied array safe for Ollama / Open WebUI ollama/api/chat:

  • parses JSON-string function.arguments into Hash/Array objects
  • coerces nil assistant content to '' when tool_calls present (Open WebUI GenerateChatCompletionForm rejects content:null alone)
  • drops _native_content / _text_tool_coerced / thinking private keys
  • stringifies Hash/Array message content (tool results) to JSON text


1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
 
# File 'lib/pwn/ai/agent/loop.rb', line 1074

public_class_method def self.ollama_wire_messages(opts = {})
  messages = opts[:messages]
  Array(messages).filter_map do |m|
    next unless m.is_a?(Hash)

    role = (m[:role] || m['role']).to_s
    out = { role: role }

    tcs = m[:tool_calls] || m['tool_calls']
    wired_tcs = nil
    if tcs
      wired_tcs = Array(tcs).filter_map { |tc| ollama_wire_tool_call(tool_call: tc) }
      out[:tool_calls] = wired_tcs unless wired_tcs.empty?
    end

    if m.key?(:content) || m.key?('content')
      content = m.key?(:content) ? m[:content] : m['content']
      out[:content] = case content
                      when nil
                        # Open WebUI: null content without tool_calls 400s;
                        # with tool_calls prefer "" over null.
                        wired_tcs && !wired_tcs.empty? ? '' : nil
                      when String then content
                      when Hash, Array then JSON.generate(content)
                      else content.to_s
                      end
    elsif wired_tcs && !wired_tcs.empty?
      out[:content] = ''
    end

    name = m[:name] || m['name']
    out[:name] = name.to_s if name && !name.to_s.empty?

    tcid = m[:tool_call_id] || m['tool_call_id']
    out[:tool_call_id] = tcid.to_s if tcid && !tcid.to_s.empty?

    out
  end
end

.openai_wire_messages(opts = {}) ⇒ Object

Supported Method Parameters

wire = PWN::AI::Agent::Loop.openai_wire_messages( messages: 'required - in-memory OpenAI-ish messages (may have Hash args / internal keys)' )

Returns a deep-copied array safe for OpenAI / xAI chat.completions:

  • drops _native_content / _text_tool_coerced / thinking private keys
  • stringifies function.arguments maps
  • coerces Hash/non-string content to JSON/string (nil kept for assistant tool turns)


1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
 
# File 'lib/pwn/ai/agent/loop.rb', line 1158

public_class_method def self.openai_wire_messages(opts = {})
  messages = opts[:messages]
  Array(messages).filter_map do |m|
    next unless m.is_a?(Hash)

    role = (m[:role] || m['role']).to_s
    out = { role: role }

    if m.key?(:content) || m.key?('content')
      content = m.key?(:content) ? m[:content] : m['content']
      out[:content] = case content
                      when nil then nil
                      when String then content
                      when Hash, Array then JSON.generate(content)
                      else content.to_s
                      end
    end

    name = m[:name] || m['name']
    out[:name] = name.to_s if name && !name.to_s.empty?

    tcid = m[:tool_call_id] || m['tool_call_id']
    out[:tool_call_id] = tcid.to_s if tcid && !tcid.to_s.empty?

    tcs = m[:tool_calls] || m['tool_calls']
    if tcs
      wired = Array(tcs).filter_map { |tc| openai_wire_tool_call(tool_call: tc) }
      out[:tool_calls] = wired unless wired.empty?
    end

    out
  end
end

.request_intent(opts = {}) ⇒ Object 



1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
 
# File 'lib/pwn/ai/agent/loop.rb', line 1624

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

  # Pure greeting / weather smalltalk before how-to/recon/act.
  # Deterministic short-circuit — never freeform model weather echo.
  return :greeting if req.match?(GREETING_RX)

  # Pure prior-turn recall before how-to/recon (short, decisive).
  return :recall if req.match?(RECALL_RX)

  # Vague memory cues that are still "about the prior turn" and not
  # general work ("remember what we decided about nmap and implement it"
  # stays :act because it pairs memory with a doing verb outside the cue).
  if req.match?(VAGUE_MEMORY_RX) && !req.match?(HOWTO_RX) && !req.match?(LIVE_RECON_RX)
    doing = req.match?(
      /\b(implement|fix|patch|refactor|run|execute|scan|write|edit|
          change|deploy|install|build|compile|commit|push)\b/ix
    )
    return :recall unless doing
  end

  if req.match?(LAST_SESSION_RX) && !req.match?(HOWTO_RX) && !req.match?(LIVE_RECON_RX)
    doing = req.match?(
      /\b(implement|fix|patch|refactor|run|execute|scan|write|edit|
          change|deploy|install|build|compile|commit|push)\b/ix
    )
    return :recall unless doing
  end

  # Live-action recon takes precedence over bare "how to" when both appear
  # only if the user clearly asks the agent to do the sweep here.
  live = req.match?(LIVE_RECON_RX) && req.match?(
    /\b(can\s+you|could\s+you|please|go\s+ahead|now|on\s+this\s+host|
        this\s+subnet|this\s+network|find\s+(?:for\s+me|me)|discover)\b/ix
  )
  return :recon_act if live || (req.match?(LIVE_RECON_RX) && !req.match?(HOWTO_RX))
  return :howto if req.match?(HOWTO_RX)
  # Interrogative documentation without "how to"
  if req.match?(/\b(what\s+(?:flags?|options?|switches?)|usage|syntax)\b/i) &&
     !req.match?(/\b(run|execute|scan|find|discover)\b/i)
    return :howto
  end

  :act
rescue StandardError
  :act
end

.run(opts = {}) ⇒ Object

Supported Method Parameters

final = PWN::AI::Agent::Loop.run( request: 'required - what the human typed', session_id: 'optional - PWN::Sessions id (transcript is appended to it)', enabled_toolsets: 'optional - subset of Registry.toolsets, or nil for all', on_tool: 'optional - ->(name, args, result) callback for live UI', system_role_content: 'optional - override default system prompt (built from session_id if not provided)' )



2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
 
# File 'lib/pwn/ai/agent/loop.rb', line 2219

public_class_method def self.run(opts = {})
  request = opts[:request].to_s
  session_id = opts[:session_id]
  on_tool = opts[:on_tool]
  i = 0
  tools_called = 0
  engine_s = 0.0
  final_chars = 0
  start_debug_session(opts)
  loud_debug_tui!(debug: opts[:debug])
  debug_progress(msg: "Loop.run start request=#{request[0, 240]}", debug: opts[:debug])
  nested = defined?(TurnFinalizer) && TurnFinalizer.user_path?
  TurnFinalizer.enter_user_path! if defined?(TurnFinalizer)
  engine = active_engine
  local  = local_engine?(engine: engine)

  # Cheap intent/kind FIRST - before PromptBuilder / Registry / TaskSummarizer
  # so greetings, FYIs, how-tos, recall, and simple Qs never pay the fat path.
  intent = request_intent(request: request)
  if defined?(OpenGoal) && OpenGoal.resume?(request: request)
    prior = OpenGoal.current
    if prior && !prior[:request].to_s.strip.empty?
      request = prior[:request].to_s
      opts[:request] = request
      intent = request_intent(request: request)
    end
  elsif !nested && defined?(OpenGoal) && needs_host_work?(request: request) &&
        !%i[greeting howto recall].include?(intent)
    OpenGoal.begin!(request: request, session_id: session_id)
  end
  Thread.current[:pwn_request_intent] = intent
  Thread.current[:pwn_extinguished] = {}
  debug_progress(msg: "intent=#{intent} engine=#{engine}", debug: opts[:debug])
  expose_current_session(session_id: session_id)
  Mistakes.check_user_correction(request: request, session_id: session_id) if defined?(Mistakes)

  cheap = opts[:force_tools] != true && %i[greeting howto recall].include?(intent)

  if intent == :greeting && opts[:force_tools] != true
    debug_progress(msg: 'path=greeting', debug: opts[:debug])
    quiet_debug_tui!(debug: opts[:debug], reason: 'greeting')
    txt = answer_greeting(
      request: request,
      session_id: session_id
    )
    final_chars = txt.to_s.length
    debug_final_text!(text: txt, debug: opts[:debug])
    return txt
  end

  # Thin system prompt only for remaining cheap paths (howto/recall).
  if cheap
    system_role_content = opts[:system_role_content]
    if system_role_content.nil? || system_role_content.to_s.empty?
      system_role_content = PWN::AI::Agent::PromptBuilder.build(
        session_id: session_id,
        request: request,
        thin: true
      )
      opts[:system_role_content] = system_role_content
    end
    if intent == :howto
      debug_progress(msg: 'path=howto', debug: opts[:debug])
      quiet_debug_tui!(debug: opts[:debug], reason: 'howto')
      txt = answer_howto(
        request: request,
        session_id: session_id,
        system_role_content: system_role_content
      )
      final_chars = txt.to_s.length
      debug_final_text!(text: txt, debug: opts[:debug])
      return txt
    end
    if intent == :recall
      debug_progress(msg: 'path=recall', debug: opts[:debug])
      quiet_debug_tui!(debug: opts[:debug], reason: 'recall')
      txt = answer_recall(
        request: request,
        session_id: session_id,
        system_role_content: system_role_content
      )
      final_chars = txt.to_s.length
      debug_final_text!(text: txt, debug: opts[:debug])
      return txt
    end
  end

  # --- act / recon / autonomous_goal: full context + tools ---
  # Reuse precomputed kind so TaskSummarizer.fresh does not classify twice.
  ts_state = (TaskSummarizer.fresh(request: request) if defined?(TaskSummarizer) && TaskSummarizer.enabled? && Thread.current[:pwn_reflect_depth].to_i.zero?)
  system_role_content = opts[:system_role_content] ||= PWN::AI::Agent::PromptBuilder.build(
    session_id: session_id,
    request: request
  )

  Registry.discover
  maybe_refresh_extro_snapshot!
  opts[:enabled_toolsets] = default_interactive_toolsets(request: request) unless opts.key?(:enabled_toolsets)

  # R5 — open the live MDP episode BEFORE the first Registry.rank so
  # Q(s,a) can advise this turn. Planning still owns the task list.
  if defined?(PWN::AI::Agent::Policy) && Policy.respond_to?(:begin_episode)
    Policy.begin_episode(
      session_id: session_id,
      request: request,
      intent: intent,
      engine: engine,
      ts_state: ts_state
    )
  end

  # Initial tool pool from the user request (bootstrap only). After
  # TaskSummarizer.emit_plan! we re-rank using English tangible tasks
  # so generated tasks — not the bare request — drive which tools
  # the model may call.
  # CORE_TOOLS is the default action space. Extra schemas are
  # opt-in via enabled_toolsets + core_only: false.
  core_only = opts.fetch(:core_only, true)
  tools = Registry.definitions(
    enabled: opts[:enabled_toolsets],
    relevance: request,
    core_only: core_only,
    intent: intent
  )
  no_tools = Array(tools).empty?
  Thread.current[:pwn_loop_no_tools] = no_tools
  messages = [{ role: 'system', content: system_role_content }]
  messages.concat(Learning.exemplars_for(request: request)) if local && defined?(Learning) && Learning.respond_to?(:exemplars_for)
  messages.concat(
    session_chat_history(session_id: session_id, skip_request: request)
  )
  messages << { role: 'user', content: request }
  append_session(session_id: session_id, role: 'user', content: request)

  trivia = world_knowledge?(request: request)
  catalog = catalog_lookup?(request: request)
  browse = request_need(request: request) == :browse
  skip_compass = trivia || catalog || no_tools || browse
  # Trivia / catalog / browse do not get an implement-shaped
  # English compass. Inventing "apply code/host changes" there
  # keeps the model on a Navigate task after the page already loaded.
  task_summary_plan!(state: ts_state, request: request, on_tool: on_tool) if defined?(TaskSummarizer) && !skip_compass
  # Re-bind tools from English plan so task list is the sole driver of
  # tool exposure/ranking (Registry keyword router + CORE).
  if ts_state.is_a?(Hash) && defined?(TaskSummarizer) && TaskSummarizer.respond_to?(:relevance_query)
    rq = TaskSummarizer.relevance_query(state: ts_state, request: request)
    unless rq.to_s.strip.empty?
      tools = Registry.definitions(
        enabled: opts[:enabled_toolsets],
        relevance: rq,
        core_only: core_only,
        intent: intent
      )
    end
  end
  # English-task-as-primary: inject tangible tasks only for host work.
  inject_task_focus!(messages: messages, state: ts_state, force: true, request: request) unless skip_compass
  predicted = nil
  Thread.current[:pwn_plan_predicted] = nil
  cal_state = calibration_state
  force_plan = cal_state[:force_plan]
  skip_plan = %i[howto recall greeting].include?(intent) || trivia || catalog || no_tools || browse
  did_plan = false
  if !skip_plan && (force_plan || agent_flag(key: :plan_first, default: local) || budget_exhaustion_hot?) && !Array(tools).empty?
    predicted = plan_first(messages: messages, request: request, ts_state: ts_state)
    did_plan = true
    # P22 — prefer explicit return; fall back to thread stash
    predicted = Thread.current[:pwn_plan_predicted] if predicted.nil?
    # unify_plan! may have rewritten English tasks — force refresh focus.
    # Re-rank tools from (possibly unified) English plan; never from
    # PLAN: tool-call scaffold jargon (unify_plan! refuses that).
    if ts_state.is_a?(Hash) && defined?(TaskSummarizer) && TaskSummarizer.respond_to?(:relevance_query)
      rq = TaskSummarizer.relevance_query(state: ts_state, request: request)
      unless rq.to_s.strip.empty?
        tools = Registry.definitions(
          enabled: opts[:enabled_toolsets],
          relevance: rq,
          core_only: core_only,
          intent: intent
        )
      end
    end
    inject_task_focus!(messages: messages, state: ts_state, force: true, request: request) unless skip_compass
  end
  debug_progress(msg: "plan_first=#{did_plan} trivia=#{trivia} catalog=#{catalog} browse=#{browse}")
  if force_plan && cal_state[:cal] && !skip_plan
    messages << {
      role: 'user',
      content: "[pwn-ai/w3] engine=#{active_engine} is overconfident " \
               "(brier=#{cal_state[:cal][:brier]}, overconf=#{cal_state[:cal][:overconfidence]}). " \
               'Prefer high-judge exemplars, verify claims, and avoid speculative tool calls.'
    }
  end

  turn_fails = Hash.new(0)
  escalated  = false
  maybe_park_budget_scars!
  maybe_extinguish_parked!

  i = 0
  loop do
    i += 1
    # 3.1 — compact history on local so tool dumps don't fill num_ctx
    compact_history!(messages: messages) if local
    # English-task-as-primary: when plan_idx advanced, tell the model
    # which plain-English task is active before the next tool batch.
    inject_task_focus!(messages: messages, state: ts_state, request: request) unless skip_compass

    t0 = Time.now
    msg = call_engine(messages: messages, tools: tools, ts_state: ts_state)
    engine_s += (Time.now - t0)
    PWN::Plugins::TTYSpinner.halt_all! if defined?(PWN::Plugins::TTYSpinner)
    if msg.nil?
      task_summary_flush!(state: ts_state, on_tool: on_tool)
      debug_progress(msg: 'engine returned no message')
      quiet_debug_tui!(reason: 'engine_empty')
      txt = '[pwn-ai] engine returned no message'
      debug_final_text!(text: txt)
      final_chars = txt.length
      return txt
    end

    calls = Array(msg[:tool_calls])
    text  = msg[:content].to_s

    # Belt-and-suspenders: plain-text shell(...) / tool forms from local
    # models under weak TEMPLATE {{ .Prompt }} become real tool_calls.
    if calls.empty? && !text.strip.empty? &&
       defined?(Dispatch) && Dispatch.respond_to?(:tool_calls_from_text)
      coerced = Dispatch.tool_calls_from_text(text: text)
      if coerced.any?
        wired = coerced.map { |tc| openai_wire_tool_call(tool_call: tc) }
        msg = msg.merge(tool_calls: wired, content: nil, _text_tool_coerced: true)
        calls = wired
        text = ''
        warn "[pwn-ai/loop] coerced #{wired.length} text tool call(s) on iter=#{i}" if local
      end
    end

    # Empty-final guard (local/thinking models): Ollama sometimes
    # returns done_reason=stop with eval_count<=1, empty content, no
    # tool_calls — historically surface as a blank TUI reply. Do NOT
    # commit that as the answer; drop the empty assistant turn,
    # inject a one-shot nudge, and keep iterating.
    if calls.empty? && text.strip.empty?
      warn "[pwn-ai/loop] empty final from #{engine} on iter=#{i}; nudging" if local
      messages << {
        role: 'user',
        content: 'Your previous reply was empty (no tool_calls and no content). ' \
                 'Either call a tool now, or write the final answer for the user as plain text. ' \
                 'Do not reply with an empty message.'
      }
      turn_fails['empty_final'] += 1
      debug_progress(msg: "bounce empty_final snippet=#{debug_snippet(text: text)}")
      next
    end

    messages << msg

    if calls.empty?
      # P28 — refuse polite mid-goal handoffs so multi-step tasks stay autonomous.
      if incomplete_final?(text: text, last_iter: false)
        turn_fails['incomplete_final'] += 1
        warn "[pwn-ai/loop] incomplete final on iter=#{i}; continuing autonomously"
        debug_progress(msg: "bounce incomplete_final snippet=#{debug_snippet(text: text)}")
        messages << {
          role: 'user',
          content: '[pwn-ai/p28] That reply was incomplete (handoff or narrated next step). ' \
                   'Do NOT monologue about what you will try. Do NOT ask the user to ' \
                   'confirm. Emit NATIVE tool_calls NOW (e.g. shell with a concrete ' \
                   'command). Never print shell(...) as plain text. Only emit a final ' \
                   'answer when the request is complete or truly blocked with evidence.'
        }
        next
      end
      unless may_finalize?(
        request: request,
        messages: messages,
        text: text
      )
        turn_fails['unsatisfied'] += 1
        warn "[pwn-ai/loop] original request not evidenced on iter=#{i}; continuing"
        debug_progress(msg: "bounce unsatisfied snippet=#{debug_snippet(text: text)}")
        messages << {
          role: 'user',
          content: '[pwn-ai] The original request is not evidenced yet. ' \
                   'Keep calling CORE_TOOLS (shell, pwn_eval) until that request is ' \
                   'done or truly blocked. Do not declare completion from a listing alone.'
        }
        next
      end
      debug_progress(msg: "final accepted chars=#{text.to_s.length}")
      quiet_debug_tui!(reason: 'final')
      debug_final_text!(text: text)
      final_chars = text.to_s.length
      append_session(session_id: session_id, role: 'assistant', content: text)
      Learning.auto_introspect(session_id: session_id, request: request, final: text, predicted: predicted, plan: ts_state && ts_state[:plan], ts_state: ts_state) if defined?(Learning) && !nested && !no_tools && should_auto_introspect?(local: local, turn_fails: turn_fails, iter: i)
      maybe_finish_policy(session_id: session_id, proxy_ok: true, ts_state: ts_state)
      task_summary_flush!(state: ts_state, on_tool: on_tool)
      OpenGoal.clear! if defined?(OpenGoal) && !nested
      return text
    end

    # One executive task brief for the whole collection, then the
    # individual tool lines. pwn-ai → task is one-to-many with tools.
    task_summary_about_to!(
      state: ts_state,
      tools: calls.map do |tool_call|
        {
          name: tool_call.dig(:function, :name).to_s,
          args: tool_call.dig(:function, :arguments)
        }
      end,
      request: request,
      on_tool: on_tool
    )

    calls.each do |tc|
      name    = tc.dig(:function, :name).to_s
      args    = tc.dig(:function, :arguments)
      entry   = Registry.lookup(name: name)
      started = Time.now
      argv_s = args.is_a?(String) ? args.to_s : args.inspect
      debug_progress(msg: "tool #{name} start:\n#{argv_s}", keep_newlines: true, cap: 0, tee: nil)
      if Thread.current[:pwn_extinguished].is_a?(Hash) && Thread.current[:pwn_extinguished][name]
        raw = JSON.generate(
          success: false,
          error: "extinguished_repeat: #{name} already failed this signature this turn — change args or tool",
          result: { stdout: '', stderr: "extinguished_repeat: #{name}", exit: 2 }
        )
      else
        raw = Dispatch.call(tool_call: tc)
      end
      tools_called += 1
      tele    = record_metrics(name: name, started: started, raw: raw, args: args, session_id: session_id, engine: engine, ts_state: ts_state)
      result  = Result.condition(content: raw, entry: entry)

      unless tele[:ok]
        fkey = Digest::SHA256.hexdigest("#{name}|#{args}")[0, 16]
        turn_fails[fkey] += 1
        persist = tele.dig(:mistake, :count).to_i
        count   = [turn_fails[fkey], persist].max
        hint    = defined?(Mistakes) ? Mistakes.correction_hint(tool: name, error: tele[:err] || raw[0, 300]) : ''
        # S2 — counterfactual A/B: at the repeat threshold, fork an
        # alt-persona branch, judge both, inject the winner. Real
        # advantage estimation; (loser, winner) → DPO preference.
        thresh = defined?(Mistakes) ? Mistakes::REPEAT_THRESHOLD : 3
        # P17 — never fork counterfactual when budget fingerprints dominate:
        # CF is another mini agent loop and is the #1 amplifier of
        # iteration-budget exhaustion on this host.
        if count >= thresh && !escalated && defined?(Curriculum) && !budget_exhaustion_hot?
          cf = (turn_fails["cf:#{fkey}"] += 1) == 1 ? Curriculum.counterfactual(request: request, name: name, args: args, error: tele[:err] || raw[0, 200], hint: hint) : nil
          hint = "#{hint}\n[pwn-ai/counterfactual] branch #{cf[:branch]} (score=#{cf[:score].round(2)}): #{cf[:content]}" if cf
        end
        result = guard_repeated_failure(name: name, count: count, hint: hint, result: result, mistake: tele[:mistake], args: args, shape: tele.dig(:mistake, :shape))
      end

      on_tool&.call(name, args, result)
      debug_tool_io!(name: name, args: args, result: result)
      task_summary_record!(state: ts_state, name: name, args: args, result: result, on_tool: on_tool)

      messages << {
        role: 'tool',
        tool_call_id: tc[:id] || tc['id'] || "call_#{i}",
        name: name,
        content: result
      }
      append_session(
        session_id: session_id,
        role: 'tool',
        content: "#{name} → #{result[0, 1_024]}"
      )
    end

    # Do not inject "stop calling tools". Long goals keep CORE_TOOLS
    # until may_finalize? — the original request is the only signal.

    next unless local && !escalated && dispatch_fail_n(turn_fails: turn_fails) >= ESCALATE_AFTER_FAILS

    hint = escalate(request: request, turn_fails: turn_fails, session_id: session_id)
    if hint
      messages << { role: 'tool', tool_call_id: "escalation_#{i}", name: 'frontier_hint', content: hint }
      append_session(session_id: session_id, role: 'tool', content: "frontier_hint → #{hint[0, 1_024]}")
    end
    escalated = true
  end
rescue Interrupt
  Thread.current[:pwn_log_progress] = false
  if defined?(PWN::Plugins::Log) && PWN::Plugins::Log.respond_to?(:note_interrupt!)
    PWN::Plugins::Log.note_interrupt!(where: 'CTRL+C', which_self: self)
  else
    debug_progress(msg: 'Interrupt CTRL+C')
  end
  raise
rescue StandardError => e
  if defined?(PWN::Plugins::Log) && PWN::Plugins::Log.respond_to?(:note_exception!)
    PWN::Plugins::Log.note_exception!(error: e, where: 'Loop.run', which_self: self)
  else
    debug_progress(msg: "exception Loop.run #{e.class}: #{e.message}\n#{Array(e.backtrace).join("\n")}", keep_newlines: true, cap: 0)
  end
  raise
ensure
  Thread.current[:pwn_loop_no_tools] = nil
  finish_debug_request!(
    iter: i,
    tools_called: tools_called,
    engine_s: engine_s,
    final_chars: final_chars
  )
  TurnFinalizer.leave_user_path! if defined?(TurnFinalizer)
end

.world_knowledge?(opts = {}) ⇒ Boolean

Returns:

  • (Boolean) 


488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
 
# File 'lib/pwn/ai/agent/loop.rb', line 488

public_class_method def self.world_knowledge?(opts = {})
  request = opts[:request].to_s.strip
  return false if request.empty?
  return false if request.length > 120
  return false if catalog_lookup?(request: request)
  return false if request.match?(ACT_REQUEST_RX)
  return false if request.match?(LOOKUP_REQUEST_RX)
  return false if request.match?(HOST_PATH_RX)
  return false if request.match?(BROWSER_REQUEST_RX)
  return false if request.match?(HOWTO_RX)
  return false if request.match?(%r{\b(this\s+(?:host|machine|box|system|subnet|file|repo)|/opt/|implement|scan|hosts?)\b}i)

  request.match?(/\A(?:what|why|who|when|where|which|how)\b/i)
rescue StandardError
  false
end