openclacky 1.5.21 → 1.5.23

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (110) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +119 -0
  3. data/docs/secretary-prototype.md +286 -0
  4. data/lib/clacky/agent/session_serializer.rb +15 -11
  5. data/lib/clacky/agent.rb +58 -15
  6. data/lib/clacky/agent_config.rb +3 -1
  7. data/lib/clacky/agent_profile.rb +33 -6
  8. data/lib/clacky/billing/platform_billing.rb +9 -0
  9. data/lib/clacky/default_extensions/advisor/README.md +25 -0
  10. data/lib/clacky/default_extensions/advisor/README.zh.md +25 -0
  11. data/lib/clacky/default_extensions/advisor/ext.yml +1 -1
  12. data/lib/clacky/default_extensions/advisor/icon.svg +14 -0
  13. data/lib/clacky/default_extensions/coding/ext.yml +0 -1
  14. data/lib/clacky/default_extensions/computer-use/README.md +48 -0
  15. data/lib/clacky/default_extensions/computer-use/README.zh.md +48 -0
  16. data/lib/clacky/default_extensions/computer-use/ext.yml +1 -1
  17. data/lib/clacky/default_extensions/computer-use/icon.svg +16 -0
  18. data/lib/clacky/default_extensions/ext-studio/ext.yml +0 -1
  19. data/lib/clacky/default_extensions/general/ext.yml +0 -1
  20. data/lib/clacky/default_extensions/git/README.md +41 -0
  21. data/lib/clacky/default_extensions/git/README.zh.md +41 -0
  22. data/lib/clacky/default_extensions/git/ext.yml +1 -1
  23. data/lib/clacky/default_extensions/git/icon.svg +15 -0
  24. data/lib/clacky/default_extensions/git/panels/git/view.js +1960 -399
  25. data/lib/clacky/default_extensions/meeting/README.md +46 -0
  26. data/lib/clacky/default_extensions/meeting/README.zh.md +47 -0
  27. data/lib/clacky/default_extensions/meeting/ext.yml +1 -1
  28. data/lib/clacky/default_extensions/meeting/icon.svg +13 -0
  29. data/lib/clacky/default_extensions/preview/README.md +29 -0
  30. data/lib/clacky/default_extensions/preview/README.zh.md +29 -0
  31. data/lib/clacky/default_extensions/preview/ext.yml +1 -1
  32. data/lib/clacky/default_extensions/preview/icon.svg +13 -0
  33. data/lib/clacky/default_extensions/preview/panels/preview/view.js +199 -34
  34. data/lib/clacky/default_extensions/secretary/agents/secretary.md +41 -0
  35. data/lib/clacky/default_extensions/secretary/agents/worker.md +35 -0
  36. data/lib/clacky/default_extensions/secretary/api/handler.rb +8 -0
  37. data/lib/clacky/default_extensions/secretary/ext.yml +39 -0
  38. data/lib/clacky/default_extensions/secretary/panels/work/view.js +344 -0
  39. data/lib/clacky/default_extensions/secretary/tools/delegate_work.rb +37 -0
  40. data/lib/clacky/default_extensions/secretary/tools/manage_work.rb +22 -0
  41. data/lib/clacky/default_extensions/secretary/tools/yield_work.rb +35 -0
  42. data/lib/clacky/default_extensions/time_machine/README.md +32 -0
  43. data/lib/clacky/default_extensions/time_machine/README.zh.md +32 -0
  44. data/lib/clacky/default_extensions/time_machine/ext.yml +1 -1
  45. data/lib/clacky/default_extensions/time_machine/icon.svg +14 -0
  46. data/lib/clacky/default_skills/channel-manager/SKILL.md +79 -8
  47. data/lib/clacky/default_skills/channel-manager/discord_setup.rb +5 -1
  48. data/lib/clacky/default_skills/channel-manager/weixin_setup.rb +8 -1
  49. data/lib/clacky/default_skills/cron-task-creator/SKILL.md +183 -206
  50. data/lib/clacky/default_skills/cron-task-creator/evals/evals.json +45 -0
  51. data/lib/clacky/default_skills/media-gen/SKILL.md +17 -8
  52. data/lib/clacky/extension/api_extension.rb +10 -2
  53. data/lib/clacky/extension/loader.rb +2 -0
  54. data/lib/clacky/extension/verifier.rb +2 -2
  55. data/lib/clacky/locales/en.rb +14 -0
  56. data/lib/clacky/locales/zh.rb +14 -0
  57. data/lib/clacky/prompts/base.md +1 -1
  58. data/lib/clacky/providers.rb +68 -31
  59. data/lib/clacky/search_config.rb +33 -11
  60. data/lib/clacky/server/channel/adapters/base.rb +18 -0
  61. data/lib/clacky/server/channel/adapters/feishu/message_parser.rb +1 -0
  62. data/lib/clacky/server/channel/adapters/telegram/adapter.rb +1 -0
  63. data/lib/clacky/server/channel/channel_config.rb +185 -48
  64. data/lib/clacky/server/channel/channel_manager.rb +179 -66
  65. data/lib/clacky/server/git_panel.rb +362 -35
  66. data/lib/clacky/server/http_server.rb +530 -181
  67. data/lib/clacky/server/preview.rb +118 -17
  68. data/lib/clacky/server/scheduler.rb +211 -51
  69. data/lib/clacky/server/web_ui_controller.rb +35 -27
  70. data/lib/clacky/session_manager.rb +56 -6
  71. data/lib/clacky/tools/base.rb +7 -1
  72. data/lib/clacky/utils/file_processor.rb +20 -10
  73. data/lib/clacky/utils/mac_app_detector.rb +8 -7
  74. data/lib/clacky/utils/model_pricing.rb +60 -2
  75. data/lib/clacky/utils/windows_app_detector.rb +3 -1
  76. data/lib/clacky/version.rb +1 -1
  77. data/lib/clacky/web/app.css +1114 -205
  78. data/lib/clacky/web/app.js +143 -8
  79. data/lib/clacky/web/auth.js +1 -1
  80. data/lib/clacky/web/components/code-editor.js +73 -4
  81. data/lib/clacky/web/components/composer.js +107 -8
  82. data/lib/clacky/web/components/image-zoom.js +165 -0
  83. data/lib/clacky/web/components/model-picker.js +7 -5
  84. data/lib/clacky/web/components/notify.js +39 -12
  85. data/lib/clacky/web/components/onboard.js +1 -1
  86. data/lib/clacky/web/core/aside.js +60 -3
  87. data/lib/clacky/web/features/billing/view.js +2 -2
  88. data/lib/clacky/web/features/channels/store.js +19 -4
  89. data/lib/clacky/web/features/channels/view.js +92 -28
  90. data/lib/clacky/web/features/extensions/view.js +17 -10
  91. data/lib/clacky/web/features/new-session/store.js +79 -2
  92. data/lib/clacky/web/features/new-session/view.js +516 -75
  93. data/lib/clacky/web/features/skills/store.js +1 -1
  94. data/lib/clacky/web/features/tasks/store.js +5 -3
  95. data/lib/clacky/web/features/tasks/view.js +249 -66
  96. data/lib/clacky/web/features/workspace/store.js +13 -6
  97. data/lib/clacky/web/features/workspace/view.js +340 -214
  98. data/lib/clacky/web/i18n.js +366 -68
  99. data/lib/clacky/web/index.html +196 -165
  100. data/lib/clacky/web/projects.js +37 -4
  101. data/lib/clacky/web/sessions.js +263 -146
  102. data/lib/clacky/web/settings.js +241 -53
  103. data/lib/clacky/web/skills.js +2 -2
  104. data/lib/clacky/web/theme.js +17 -2
  105. data/lib/clacky/web/utils.js +234 -2
  106. data/lib/clacky/web/weixin-qr.html +2 -1
  107. data/lib/clacky/web/ws-dispatcher.js +14 -31
  108. data/lib/clacky/work/service.rb +542 -0
  109. data/lib/clacky/work/store.rb +57 -0
  110. metadata +31 -1
data/lib/clacky/agent.rb CHANGED
@@ -51,6 +51,8 @@ module Clacky
51
51
  :status, :error, :updated_at, :source, :config,
52
52
  :latest_latency, # Hash of latency metrics from the most recent LLM call (see Client#send_messages_with_tools)
53
53
  :reasoning_effort
54
+ attr_accessor :work_service
55
+ attr_reader :tool_registry
54
56
  attr_accessor :pinned
55
57
  attr_accessor :channel_info
56
58
  attr_accessor :project_id
@@ -520,7 +522,7 @@ module Clacky
520
522
  @name = new_name.to_s.strip
521
523
  end
522
524
 
523
- def run(user_input, files: nil, reference_contexts: nil, display_text: nil, created_at: nil, references_display: nil)
525
+ def run(user_input, files: nil, reference_contexts: nil, display_text: nil, created_at: nil)
524
526
  # Initialized here (not mid-body) because run's rescue/ensure are
525
527
  # method-level and must be able to reference them on any exit path.
526
528
  result = nil
@@ -556,7 +558,11 @@ module Clacky
556
558
  @cancel_flag = CancelFlag.new
557
559
 
558
560
  # Start new task for Time Machine
559
- task_id = start_new_task(title: display_text.to_s.empty? ? user_input.to_s : display_text.to_s)
561
+ task_title = display_text.to_s.empty? ? user_input.to_s : display_text.to_s
562
+ if task_title.strip.empty?
563
+ task_title = display_files_for(files).map { |f| f[:name] }.join(", ")
564
+ end
565
+ task_id = start_new_task(title: task_title)
560
566
  run_context = { session_id: @session_id, run_id: task_id.to_s,
561
567
  source: @source.to_s, input_created_at: created_at,
562
568
  observed_at: Time.now.utc.iso8601(6), status: "running" }
@@ -622,7 +628,7 @@ module Clacky
622
628
 
623
629
  append_user_input(user_input, files: files, reference_contexts: reference_contexts,
624
630
  display_text: display_text, created_at: created_at,
625
- references_display: references_display, task_id: task_id)
631
+ task_id: task_id)
626
632
  @total_tasks += 1
627
633
  run_turn_started = true
628
634
 
@@ -641,8 +647,14 @@ module Clacky
641
647
  return result = hook_result[:result]
642
648
  end
643
649
 
650
+ work_context = @work_service&.turn_context(self)
651
+ @history.append(role: "user", content: work_context, system_injected: true, task_id: task_id) if work_context
652
+
644
653
  # Track if ask_user was called
645
654
  awaiting_user_feedback = false
655
+ # A tool handed control back; distinct from finishing a normal reply.
656
+ yielded = false
657
+ notify_user = true
646
658
  # Heuristic sibling of the above: the reply merely ended with a question
647
659
  # mark. Kept separate because it must never reach build_result — the
648
660
  # session status it feeds shows a "waiting" badge to the user, and a
@@ -657,6 +669,7 @@ module Clacky
657
669
  @hooks.trigger(:on_iteration, @iterations)
658
670
 
659
671
  consume_steering_inputs
672
+ @work_service&.guard!(self) if Thread.current[:clacky_work]
660
673
 
661
674
  # Think: LLM reasoning with tool support
662
675
  response = think
@@ -794,9 +807,10 @@ module Clacky
794
807
  # Act: Execute tool calls
795
808
  action_result = act(response[:tool_calls], assistant_message: response.delete(:history_message))
796
809
 
797
- # Check if ask_user was called
798
- if action_result[:awaiting_feedback]
799
- awaiting_user_feedback = true
810
+ notify_user = false if action_result[:notify_user] == false
811
+ if action_result[:awaiting_feedback] || action_result[:end_turn]
812
+ awaiting_user_feedback = !!action_result[:awaiting_feedback]
813
+ yielded = !!action_result[:end_turn]
800
814
  observe(response, action_result[:tool_results])
801
815
  flush_pending_injections
802
816
  break
@@ -834,13 +848,14 @@ module Clacky
834
848
  @input_mutex.synchronize { @accepting_steering = false }
835
849
  notify_input_queue
836
850
  result = build_result(awaiting_user_feedback: awaiting_user_feedback)
851
+ result[:notify_user] = false if !notify_user && !awaiting_user_feedback
837
852
  result[:queue_paused] = true if awaiting_user_feedback || task_interrupted
838
853
  run_context[:reason] = "tool_denied" if task_interrupted
839
854
 
840
855
  # Run skill evolution hooks after main loop completes
841
856
  # Skip if task was interrupted by user (denied tool) or awaiting user feedback
842
857
  # Only for main agent (not subagents) to avoid recursive evolution
843
- unless @is_subagent || task_interrupted || awaiting_user_feedback || turn_unfinished
858
+ unless @is_subagent || task_interrupted || yielded || awaiting_user_feedback || turn_unfinished
844
859
  run_skill_evolution_hooks
845
860
  end
846
861
 
@@ -851,7 +866,7 @@ module Clacky
851
866
  # and only then [OK] Task Complete is printed. No cleanup dance,
852
867
  # no cross-method progress handle holding.
853
868
  # Skip on interrupt / feedback / subagent (self-guarded inside too).
854
- unless @is_subagent || task_interrupted || awaiting_user_feedback || turn_unfinished
869
+ unless @is_subagent || task_interrupted || yielded || awaiting_user_feedback || turn_unfinished
855
870
  run_memory_update_subagent
856
871
  end
857
872
 
@@ -876,7 +891,7 @@ module Clacky
876
891
  # in this same thread. Skipped for subagents and interrupts.
877
892
  # An explicit request for user feedback pauses the goal as well as the
878
893
  # queue. Mere question punctuation still leaves the goal judge in charge.
879
- unless @is_subagent || task_interrupted || awaiting_user_feedback
894
+ unless @is_subagent || task_interrupted || yielded || awaiting_user_feedback
880
895
  continuation = maybe_continue_goal(result)
881
896
  return continuation if continuation
882
897
  end
@@ -959,9 +974,16 @@ module Clacky
959
974
  context.merge(status: status, observed_at: Time.now.utc.iso8601(6)))
960
975
  end
961
976
 
977
+ # Resolved context is model-only; retain only reference metadata for UI/replay.
978
+ private def display_references(contexts)
979
+ Array(contexts).select { |ref| ref.is_a?(Hash) }.map do |ref|
980
+ ref.reject { |key, _| key.to_s == "context" }
981
+ end
982
+ end
983
+
962
984
  # Shared by initial input and steering; only the execution thread writes history.
963
985
  private def append_user_input(user_input, files: nil, reference_contexts: nil,
964
- display_text: nil, created_at: nil, references_display: nil,
986
+ display_text: nil, created_at: nil,
965
987
  task_id: @current_task_id)
966
988
  # Resolve lightweight metadata first, then commit the accepted user turn
967
989
  # before any attachment parser/OCR/sidecar work can block or fail. Session
@@ -980,7 +1002,7 @@ module Clacky
980
1002
  display_text: display_text,
981
1003
  skill_command: skill_command[:found] ? skill_command[:skill_name] : nil,
982
1004
  skill_command_display: skill_command_display,
983
- display_references: Array(references_display).empty? ? nil : references_display
1005
+ display_references: display_references(reference_contexts)
984
1006
  }
985
1007
  if staged
986
1008
  @history.append(message_metadata.merge(
@@ -1178,7 +1200,8 @@ module Clacky
1178
1200
  # Inject referenced past chats (the @mention "send as reference" behavior)
1179
1201
  # as a system_injected message — same mechanism as file references: the LLM
1180
1202
  # sees the context, but replay_history skips it and no user bubble renders.
1181
- Array(reference_contexts).each do |ctx|
1203
+ Array(reference_contexts).each do |reference|
1204
+ ctx = reference.is_a?(Hash) ? (reference[:context] || reference["context"]) : reference
1182
1205
  next if ctx.to_s.strip.empty?
1183
1206
  @history.append({ role: "user", content: ctx, system_injected: true, task_id: task_id })
1184
1207
  end
@@ -1320,7 +1343,8 @@ module Clacky
1320
1343
  source = options.delete(:source) || :web
1321
1344
  notify_input_queue
1322
1345
  @ui.show_user_message(options[:display_text] || entry[:content], created_at: options[:created_at],
1323
- files: options[:files] || [], source: source, steering: true) if @ui&.respond_to?(:show_user_message)
1346
+ files: options[:files] || [], source: source, steering: true,
1347
+ **(!Array(options[:reference_contexts]).any? { |ref| ref.is_a?(Hash) } ? {} : { references: display_references(options[:reference_contexts]) })) if @ui&.respond_to?(:show_user_message)
1324
1348
  run(entry[:content], **options)
1325
1349
  end
1326
1350
 
@@ -1362,7 +1386,8 @@ module Clacky
1362
1386
  end
1363
1387
  committed += 1
1364
1388
  @ui&.show_user_message(options[:display_text] || entry[:content],
1365
- created_at: options[:created_at], files: options[:files] || [], source: source, steering: true) if @ui&.respond_to?(:show_user_message)
1389
+ created_at: options[:created_at], files: options[:files] || [], source: source, steering: true,
1390
+ **(!Array(options[:reference_contexts]).any? { |ref| ref.is_a?(Hash) } ? {} : { references: display_references(options[:reference_contexts]) })) if @ui&.respond_to?(:show_user_message)
1366
1391
  end
1367
1392
  notify_input_queue unless entries.empty?
1368
1393
  !entries.empty?
@@ -1589,6 +1614,8 @@ module Clacky
1589
1614
  feedback = nil
1590
1615
  results = []
1591
1616
  awaiting_feedback = false
1617
+ end_turn = false
1618
+ notify_user = true
1592
1619
 
1593
1620
  tool_calls.each_with_index do |call, index|
1594
1621
  # Resolve tool name: handle case-insensitive and common alias mismatches
@@ -1607,6 +1634,8 @@ module Clacky
1607
1634
  # Tool truly not found — let the rescue below handle it with a clear message
1608
1635
  end
1609
1636
 
1637
+ @work_service&.guard!(self)
1638
+
1610
1639
  # Hook: before_tool_use
1611
1640
  hook_result = @hooks.trigger(:before_tool_use, call)
1612
1641
  if hook_result[:action] == :deny
@@ -1747,6 +1776,8 @@ module Clacky
1747
1776
  result = tool.execute(**args)
1748
1777
  end
1749
1778
 
1779
+ notify_user = false if result.is_a?(Hash) && result[:notify_user] == false
1780
+
1750
1781
  # Hook: after_tool_use
1751
1782
  @hooks.trigger(:after_tool_use, call, result)
1752
1783
 
@@ -1807,6 +1838,16 @@ module Clacky
1807
1838
  end
1808
1839
 
1809
1840
  results << build_success_result(call, result)
1841
+ # Tools may end this turn after committing their result (e.g. a durable wait).
1842
+ if result.is_a?(Hash) && result[:end_turn] == true
1843
+ end_turn = true
1844
+ awaiting_feedback = result[:awaiting_feedback] == true
1845
+ # Settle every call in this batch, but execute nothing after yielding.
1846
+ tool_calls.drop(index + 1).each do |remaining|
1847
+ results << build_denied_result(remaining, "Turn ended; remaining calls were not executed", true)
1848
+ end
1849
+ break
1850
+ end
1810
1851
  rescue StandardError => e
1811
1852
  # Log complete error information to debug_logs for troubleshooting
1812
1853
  @debug_logs << {
@@ -1831,7 +1872,9 @@ module Clacky
1831
1872
  denied: denied,
1832
1873
  feedback: feedback,
1833
1874
  tool_results: results,
1834
- awaiting_feedback: awaiting_feedback
1875
+ awaiting_feedback: awaiting_feedback,
1876
+ end_turn: end_turn,
1877
+ notify_user: notify_user
1835
1878
  }
1836
1879
  end
1837
1880
 
@@ -1255,8 +1255,10 @@ module Clacky
1255
1255
  m = @models.find { |mm| mm["id"] == @current_model_id }
1256
1256
  return m if m
1257
1257
  # id no longer exists (model was deleted). Fall through to other
1258
- # resolution strategies below, and clear the stale id.
1258
+ # resolution strategies below, and clear the stale id. The sub-model
1259
+ # pin belonged to the deleted card's provider, so it goes too.
1259
1260
  @current_model_id = nil
1261
+ @session_model_overlay = nil
1260
1262
  end
1261
1263
 
1262
1264
  default_model = find_model_by_type("default")
@@ -12,6 +12,8 @@ module Clacky
12
12
  # Each user profile directory (opt-in override) contains:
13
13
  # - profile.yml — name, description, skills whitelist
14
14
  # - system_prompt.md — agent-specific system prompt content
15
+ # - base_agent: <extension-agent-id> reuses that agent's rules/tools/panels
16
+ # while retaining this profile's name and additional prompt.
15
17
  #
16
18
  # Global files (shared across all agents) are user-only overrides:
17
19
  # - ~/.clacky/agents/SOUL.md — agent personality/values (else DEFAULT_SOUL)
@@ -43,13 +45,36 @@ module Clacky
43
45
  @profile_data = load_profile_yml
44
46
  @description = @profile_data["description"] || ""
45
47
  @system_prompt_content = load_agent_file("system_prompt.md")
48
+ base = @profile_data["base_agent"].to_s.strip
49
+ unless base.empty?
50
+ @base_unit = result&.agents&.find { |unit| unit.id == base }
51
+ raise ArgumentError, "Base agent '#{base}' is not available from an enabled extension" unless @base_unit
52
+ unless @base_unit.spec["base_agent"].to_s.empty?
53
+ raise ArgumentError, "Chained base_agent references are not supported"
54
+ end
55
+ prompt = @base_unit.spec["prompt_abs"]
56
+ shared = prompt && File.file?(prompt) ? File.read(prompt).strip : ""
57
+ @system_prompt_content = [shared, @system_prompt_content].reject(&:empty?).uniq.join("\n\n")
58
+ end
59
+ end
60
+
61
+ # Extensions can recognize their agent even when a user customizes its name.
62
+ def based_on?(id)
63
+ name == id.to_s || (!!@base_unit && @base_unit.id == id.to_s)
64
+ end
65
+
66
+ # Optional worker profile used for delegated work; user profiles inherit it.
67
+ def work_agent
68
+ value = @profile_data["work_agent"]
69
+ value = @base_unit&.spec&.dig("work_agent") if value.nil?
70
+ value.to_s.strip
46
71
  end
47
72
 
48
73
  # Skills explicitly disabled for this agent, matched by skill identifier.
49
74
  # Declared via `disabled_skills` in profile.yml or the ext agent spec.
50
75
  # @return [Array<String>]
51
76
  def disabled_skills
52
- @disabled_skills ||= Array(@profile_data["disabled_skills"]).map(&:to_s)
77
+ @disabled_skills ||= (Array(@base_unit&.spec&.dig("disabled_skills")) + Array(@profile_data["disabled_skills"])).map(&:to_s).uniq
53
78
  end
54
79
 
55
80
  # Extension tools this agent opts into, via `tools:` in profile.yml or the
@@ -57,15 +82,15 @@ module Clacky
57
82
  # id is a bare tool id in the agent's own container: `tools/<id>.rb`.
58
83
  # @return [Array<String>]
59
84
  def tools
60
- @tools ||= Array(@profile_data["tools"]).map(&:to_s)
85
+ @tools ||= Array((@base_unit ? @base_unit.spec : @profile_data)["tools"]).map(&:to_s)
61
86
  end
62
87
 
63
88
  # Directory of the ext container this agent belongs to, or nil for a user
64
- # profile. Extension tools only exist inside containers, so a user profile
65
- # cannot reference them.
89
+ # profile without a base. A derived profile uses its base container and
90
+ # declared tool set; it cannot add arbitrary cross-container tools.
66
91
  # @return [String, nil]
67
92
  def container_dir
68
- @ext_unit&.dir
93
+ (@base_unit || @ext_unit)&.dir
69
94
  end
70
95
 
71
96
  # Whether a skill is usable by this agent: it must not be in the agent's
@@ -74,7 +99,7 @@ module Clacky
74
99
  # @return [Boolean]
75
100
  def skill_allowed?(skill)
76
101
  return false if disabled_skills.include?(skill.identifier)
77
- skill.allowed_for_agent?(name)
102
+ skill.allowed_for_agent?(name) || (!!@base_unit && skill.allowed_for_agent?(@base_unit.id))
78
103
  end
79
104
 
80
105
  # @param name [String, Symbol] profile name (e.g. "coding", "general")
@@ -207,6 +232,8 @@ module Clacky
207
232
  if @ext_unit
208
233
  return {
209
234
  "name" => @name,
235
+ "base_agent" => @ext_unit.spec["base_agent"],
236
+ "work_agent" => @ext_unit.spec["work_agent"],
210
237
  "description" => @ext_unit.spec["description"],
211
238
  "panels" => @ext_unit.spec["panels"],
212
239
  "skills" => @ext_unit.spec["skills"],
@@ -18,7 +18,10 @@ module Clacky
18
18
  # Retired aliases stay here so usage recorded under them still resolves.
19
19
  ALIAS_TO_REAL = {
20
20
  # deepseek (dsk-)
21
+ # REAL_TO_ALIAS is built with Hash#invert, which keeps the last entry
22
+ # per real id — list the current alias after its retired predecessor.
21
23
  "dsk-deepseek-flash" => "deepseek-flash",
24
+ "dsk-deepseek-v4.1-flash" => "deepseek-flash",
22
25
  "dsk-deepseek-v4-pro" => "deepseek-v4-pro",
23
26
  "dsk-deepseek-v4-flash" => "deepseek-v4-flash",
24
27
  "dsk-deepseek-v4-flash-vision-exp" => "deepseek-v4-flash-vision-exp",
@@ -62,14 +65,20 @@ module Clacky
62
65
  "or-gemini-3-6-flash" => "gemini-3.6-flash",
63
66
  "or-gemini-3-5-flash" => "gemini-3.5-flash",
64
67
  # image generation (or-)
68
+ "or-gemini-nano-banana-2-1" => "gemini-nano-banana-2.1",
65
69
  "or-gemini-3-pro-image" => "gemini-3-pro-image",
66
70
  "or-gemini-3-1-flash-image" => "gemini-3.1-flash-image",
71
+ "or-gemini-3-1-flash-lite-image" => "gemini-3.1-flash-lite-image",
72
+ "or-gpt-image-2-5" => "openai/gpt-image-2.5-sunburst",
73
+ "or-gpt-image-2-5-flare" => "openai/gpt-image-2.5-flare",
67
74
  "or-gpt-image-2" => "openai/gpt-5.4-image-2",
68
75
  # video generation (or-)
69
76
  "or-veo-3" => "veo-3.0-generate-001",
70
77
  "or-veo-3-fast" => "veo-3.0-fast-generate-001",
71
78
  "or-veo-3-1" => "veo-3.1-generate-001",
72
79
  "or-veo-3-1-fast" => "veo-3.1-fast-generate-001",
80
+ "or-veo-3-1-lite" => "veo-3.1-lite-generate-001",
81
+ "or-gemini-omni-flash" => "gemini-omni-1.2-flash",
73
82
  # text-to-speech (or-)
74
83
  "or-tts-gemini-2-5-flash" => "gemini-2.5-flash-tts",
75
84
  "or-tts-gemini-2-5-pro" => "gemini-2.5-pro-tts",
@@ -0,0 +1,25 @@
1
+ # Advisor
2
+
3
+ After each round of work, the AI reviews what it just did and shows **3 suggested next steps** above the input box, so you never have to wonder what to do next.
4
+
5
+ ## How to use
6
+
7
+ 1. Chat with the AI and let it work as usual.
8
+ 2. When a round finishes, a "Next steps" card appears above the input box (it shows a loading state while generating).
9
+ 3. For any suggestion:
10
+ - **Click the text** to fill it into the input box, then edit and send it yourself.
11
+ - **Click "Send now"** to send it to the AI as-is.
12
+ 4. Click **✕ (Dismiss)** to hide the card for this round; it comes back next round.
13
+
14
+ Suggestions usually cover three different directions: continue / fix, verify, and wrap up. Nothing runs automatically — you are always in control.
15
+
16
+ ## Turning it on and off
17
+
18
+ - The **⏻** button on the card turns the advisor off.
19
+ - Turn it back on any time in **Settings → Advisor**.
20
+ - You can also disable the whole extension from Extensions.
21
+
22
+ ## Tips
23
+
24
+ - Suggestions are based only on what actually happened in the round — no invented files or commands.
25
+ - If there is no sensible next step, no card is shown.
@@ -0,0 +1,25 @@
1
+ # 工作建议
2
+
3
+ 每轮任务结束后,AI 会回顾刚完成的工作,在输入框上方给出 **3 条下一步建议**,让你不用想"接下来该做什么"。
4
+
5
+ ## 怎么用
6
+
7
+ 1. 正常和 AI 对话、让它干活。
8
+ 2. 一轮任务完成后,输入框上方会出现「接下来建议」卡片(生成时显示「正在生成建议…」)。
9
+ 3. 对任意一条建议:
10
+ - **点击建议文字**:内容会填进输入框,你可以先修改再发送。
11
+ - **点击「直接发送」**:原样发给 AI,立即执行。
12
+ 4. 不需要时点卡片右上角 **✕(收起本次)**,下一轮会重新出现。
13
+
14
+ 建议通常覆盖三个不同方向:继续 / 修复、验证、收尾。不会自动执行任何操作,一切由你决定。
15
+
16
+ ## 开关
17
+
18
+ - 卡片上的 **⏻** 按钮可一键关闭工作建议。
19
+ - 关闭后可在「设置 → 工作建议」中重新开启。
20
+ - 也可以在扩展管理里整体停用本扩展。
21
+
22
+ ## 小贴士
23
+
24
+ - 建议只基于本轮实际发生的事情生成,不会编造文件或命令。
25
+ - 如果没有合理的下一步,卡片不会出现。
@@ -5,8 +5,8 @@ display_name_zh: 工作建议
5
5
  description: Recommends next steps after each task, based on your own workflow
6
6
  description_zh: 每轮任务结束后,基于你的专属流程推荐下一步工作
7
7
  version: "0.1.0"
8
+ icon: icon.svg
8
9
  author: OpenClacky
9
- homepage: https://www.openclacky.com
10
10
  license: MIT
11
11
  contributes:
12
12
  agents:
@@ -0,0 +1,14 @@
1
+ <svg width="36" height="36" viewBox="0 0 36 36" fill="none" xmlns="http://www.w3.org/2000/svg">
2
+ <defs>
3
+ <linearGradient id="advisor-bg" x1="18" y1="0" x2="18" y2="36" gradientUnits="userSpaceOnUse">
4
+ <stop stop-color="#9F7AEA"/>
5
+ <stop offset="1" stop-color="#7C3AED"/>
6
+ </linearGradient>
7
+ </defs>
8
+ <rect width="36" height="36" fill="url(#advisor-bg)"/>
9
+ <g transform="translate(8 8) scale(0.8333)" stroke="#fff" stroke-width="2.2" stroke-linecap="round" stroke-linejoin="round">
10
+ <path d="M15 14c.2-1 .7-1.7 1.5-2.5 1-.9 1.5-2.2 1.5-3.5A6 6 0 0 0 6 8c0 1 .2 2.2 1.5 3.5.7.7 1.3 1.5 1.5 2.5"/>
11
+ <path d="M9 18h6"/>
12
+ <path d="M10 22h4"/>
13
+ </g>
14
+ </svg>
@@ -3,7 +3,6 @@ name: Coding
3
3
  description: AI coding assistant agent
4
4
  version: "0.1.0"
5
5
  author: OpenClacky
6
- homepage: https://www.openclacky.com
7
6
  license: MIT
8
7
  contributes:
9
8
  agents:
@@ -0,0 +1,48 @@
1
+ # Computer Use
2
+
3
+ Let the AI operate your desktop the way a person would: take a screenshot to see the screen, then click and type. Use it for things the terminal and browser cannot reach.
4
+
5
+ > This extension is **off by default**. Click **Enable** in Extensions to turn it on.
6
+
7
+ ## What it is good for
8
+
9
+ - Native apps, System Settings, installers
10
+ - Dialogs, menu bars and file pickers
11
+ - Anything else that can only be done by clicking on screen
12
+
13
+ For web automation, prefer the built-in browser capability — it is faster and more reliable. Fall back to Computer Use only when the browser cannot do the job.
14
+
15
+ ## Setup
16
+
17
+ **macOS**
18
+
19
+ In **System Settings → Privacy & Security**, grant the app running Clacky (your terminal or the Clacky app):
20
+
21
+ - **Screen Recording** (for screenshots)
22
+ - **Accessibility** (to control mouse and keyboard)
23
+
24
+ You may need to restart that app after granting.
25
+
26
+ **Windows**
27
+
28
+ Run Clacky inside **WSL**, from a logged-in desktop session (not a background service or SSH session). Otherwise screenshots come back black and input goes nowhere.
29
+
30
+ > Plain Linux is not supported.
31
+
32
+ ## How to use
33
+
34
+ Once enabled, just describe the task in plain language, for example:
35
+
36
+ - "Open System Settings and turn the display brightness all the way up"
37
+ - "In the file picker that just opened, select report.pdf on the Desktop"
38
+
39
+ The AI takes a screenshot first, clicks and types by coordinates, and re-checks the screen after each step.
40
+
41
+ ## Troubleshooting
42
+
43
+ Ask the AI to "run the computer-use doctor check". It verifies permissions and environment and tells you what is missing.
44
+
45
+ ## Notes
46
+
47
+ - Avoid using the mouse and keyboard while the AI is working, so you don't interfere with each other.
48
+ - Keep an eye on each step for sensitive actions such as payments or deletions.
@@ -0,0 +1,48 @@
1
+ # 电脑操作
2
+
3
+ 让 AI 像人一样操作你的电脑桌面:截屏看界面,再用鼠标点击、键盘输入。适合处理终端和浏览器够不到的事情。
4
+
5
+ > 本扩展**默认关闭**。在扩展管理中点击「启用」后生效。
6
+
7
+ ## 适合做什么
8
+
9
+ - 操作原生应用、系统设置、安装程序
10
+ - 处理弹窗、菜单栏、文件选择器
11
+ - 其他只能"用手点"的桌面操作
12
+
13
+ 网页上的自动化任务建议优先使用内置的浏览器能力,更快也更稳定;只有浏览器搞不定时再用电脑操作。
14
+
15
+ ## 使用前准备
16
+
17
+ **macOS**
18
+
19
+ 在「系统设置 → 隐私与安全性」中,为运行 Clacky 的程序(如终端或 Clacky 应用)授予:
20
+
21
+ - **屏幕录制**(用于截屏)
22
+ - **辅助功能**(用于控制鼠标和键盘)
23
+
24
+ 授权后可能需要重启该程序。
25
+
26
+ **Windows**
27
+
28
+ 需要在 **WSL** 中运行 Clacky,并且是在已登录的桌面会话里(不能是后台服务或 SSH 远程会话),否则截屏会是黑屏、点击无效。
29
+
30
+ > 纯 Linux 系统暂不支持。
31
+
32
+ ## 怎么用
33
+
34
+ 启用后直接用自然语言描述任务即可,例如:
35
+
36
+ - 「打开系统设置,把显示器亮度调到最高」
37
+ - 「在弹出的文件选择框里选中桌面上的 report.pdf」
38
+
39
+ AI 会先截屏查看当前屏幕,再按坐标点击、输入,每一步之后重新截屏确认结果。
40
+
41
+ ## 遇到问题
42
+
43
+ 对 AI 说「运行 computer-use 的 doctor 自检」,它会检查权限和环境,并告诉你缺什么。
44
+
45
+ ## 注意事项
46
+
47
+ - AI 操作期间请尽量不要动鼠标键盘,以免互相干扰。
48
+ - 涉及付款、删除等敏感操作时,请留意 AI 的每一步。
@@ -5,8 +5,8 @@ display_name_zh: 电脑操作
5
5
  description: Let the AI drive your desktop — macOS, or Windows through WSL — with screenshots, mouse and keyboard.
6
6
  description_zh: 让 AI 直接操作桌面(macOS,或 WSL 下的 Windows)——截屏、鼠标、键盘。
7
7
  version: "0.1.0"
8
+ icon: icon.svg
8
9
  author: OpenClacky
9
- homepage: https://www.openclacky.com
10
10
  license: MIT
11
11
  origin: self
12
12
  enabled_by_default: false
@@ -0,0 +1,16 @@
1
+ <svg width="36" height="36" viewBox="0 0 36 36" fill="none" xmlns="http://www.w3.org/2000/svg">
2
+ <defs>
3
+ <linearGradient id="computeruse-bg" x1="18" y1="0" x2="18" y2="36" gradientUnits="userSpaceOnUse">
4
+ <stop stop-color="#FB9A2C"/>
5
+ <stop offset="1" stop-color="#F26B12"/>
6
+ </linearGradient>
7
+ </defs>
8
+ <rect width="36" height="36" fill="url(#computeruse-bg)"/>
9
+ <g transform="translate(8 8) scale(0.8333)" stroke="#fff" stroke-width="2.2" stroke-linecap="round" stroke-linejoin="round">
10
+ <path d="M14 4.1 12 6"/>
11
+ <path d="m5.1 8-2.9-.8"/>
12
+ <path d="m6 12-1.9 2"/>
13
+ <path d="M7.2 2.2 8 5.1"/>
14
+ <path d="M9.037 9.69a.498.498 0 0 1 .653-.653l11 4.5a.5.5 0 0 1-.074.949l-4.349 1.041a1 1 0 0 0-.74.739l-1.04 4.35a.5.5 0 0 1-.95.074z"/>
15
+ </g>
16
+ </svg>
@@ -3,7 +3,6 @@ name: Extension Studio
3
3
  description: AI-driven workspace for building, debugging, and publishing OpenClacky extensions
4
4
  version: "0.1.0"
5
5
  author: OpenClacky
6
- homepage: https://www.openclacky.com
7
6
  license: MIT
8
7
  contributes:
9
8
  api: api/handler.rb
@@ -3,7 +3,6 @@ name: General
3
3
  description: General-purpose digital employee agent
4
4
  version: "0.1.0"
5
5
  author: OpenClacky
6
- homepage: https://www.openclacky.com
7
6
  license: MIT
8
7
  contributes:
9
8
  agents:
@@ -0,0 +1,41 @@
1
+ # Git
2
+
3
+ A friendly review panel for changes: see exactly which files and lines the AI touched, and review them like a pull request.
4
+
5
+ > The session's working directory must be a Git repository.
6
+
7
+ ## Opening it
8
+
9
+ Switch to the **Git** tab in the session's side panel.
10
+
11
+ ## Choosing what to look at
12
+
13
+ Use the scope dropdown at the top:
14
+
15
+ | Scope | What it shows |
16
+ |---|---|
17
+ | Last turn | Only what the AI changed in its last round (most common) |
18
+ | Uncommitted | Everything changed since the last commit |
19
+ | Unstaged / Staged | Changes split by the Git index |
20
+ | Committed | Commits on the current branch vs. the base branch |
21
+ | Unpushed commits | Commits not yet pushed, one by one |
22
+ | Branch | Compare against any branch |
23
+
24
+ ## Reading the diff
25
+
26
+ - **File tree** on the left lists every changed file. Drag to resize (double-click to reset) or hide it.
27
+ - **Go to file** filters the list by name.
28
+ - **Diff layout**: auto / split / unified — click to switch.
29
+ - **Wrap** long lines when needed.
30
+ - Unchanged code collapses into "N unchanged lines"; click to expand.
31
+ - Very large diffs load on demand — click to show them.
32
+
33
+ ## File actions
34
+
35
+ - **Discard changes**: the revert button on a file header discards that file's changes after a second confirmation. This cannot be undone.
36
+ - **More menu / right-click**: copy path, copy relative path, open in editor, add to chat, reveal in folder, download.
37
+
38
+ ## Tips
39
+
40
+ - Want the AI to keep working on a file? Use **Add to chat** to reference it in the input box.
41
+ - To look back at a single step or roll everything back, pair this with the **Time Machine** extension.
@@ -0,0 +1,41 @@
1
+ # Git 管理
2
+
3
+ 一个直观的改动审阅面板:AI 改了哪些文件、改了哪几行,一眼看清,像审阅代码一样逐个确认。
4
+
5
+ > 需要当前会话的工作目录是一个 Git 仓库。
6
+
7
+ ## 怎么打开
8
+
9
+ 在会话右侧面板中切换到 **「Git 管理」** 标签页。
10
+
11
+ ## 选择查看范围
12
+
13
+ 点击顶部的范围下拉框,可以切换要看的改动:
14
+
15
+ | 范围 | 说明 |
16
+ |---|---|
17
+ | 上一轮 | 只看 AI 上一轮任务改了什么(最常用) |
18
+ | 未提交 | 自上次提交以来的全部改动 |
19
+ | 未暂存 / 已暂存 | 按 Git 暂存区拆分查看 |
20
+ | 已提交 | 当前分支相对基线分支的提交 |
21
+ | 未推送的提交 | 还没 push 到远端的提交,可逐个查看 |
22
+ | 分支 | 选择任意分支进行对比 |
23
+
24
+ ## 浏览改动
25
+
26
+ - **左侧文件树**:列出所有改动文件,可拖动调整宽度(双击复位),也可以收起。
27
+ - **跳转到文件**:输入文件名快速筛选定位。
28
+ - **差异布局**:自动 / 并排 / 行内,点击切换。
29
+ - **自动换行**:长行太多时打开。
30
+ - 未修改的代码会折叠成「N 行未修改」,点击展开。
31
+ - 改动很大的文件会延迟加载,点一下再显示。
32
+
33
+ ## 对文件进行操作
34
+
35
+ - **撤销此文件的改动**:点文件头部的撤销按钮,再次确认后丢弃该文件的改动(不可恢复,请谨慎)。
36
+ - **更多菜单 / 右键**:复制路径、复制相对路径、在编辑器中打开、添加到聊天、打开所在文件夹、下载。
37
+
38
+ ## 小贴士
39
+
40
+ - 想让 AI 针对某个文件继续修改?用「添加到聊天」把它带进输入框。
41
+ - 只想回看 AI 某一步的改动,或整体回退,可配合「时光机」扩展使用。