hud-python 0.3.5__py3-none-any.whl → 0.4.0__py3-none-any.whl

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.

Potentially problematic release.


This version of hud-python might be problematic. Click here for more details.

Files changed (192) hide show
  1. hud/__init__.py +22 -89
  2. hud/agents/__init__.py +17 -0
  3. hud/agents/art.py +101 -0
  4. hud/agents/base.py +599 -0
  5. hud/{mcp → agents}/claude.py +373 -321
  6. hud/{mcp → agents}/langchain.py +250 -250
  7. hud/agents/misc/__init__.py +7 -0
  8. hud/{agent → agents}/misc/response_agent.py +80 -80
  9. hud/{mcp → agents}/openai.py +352 -334
  10. hud/agents/openai_chat_generic.py +154 -0
  11. hud/{mcp → agents}/tests/__init__.py +1 -1
  12. hud/agents/tests/test_base.py +742 -0
  13. hud/agents/tests/test_claude.py +324 -0
  14. hud/{mcp → agents}/tests/test_client.py +363 -324
  15. hud/{mcp → agents}/tests/test_openai.py +237 -238
  16. hud/cli/__init__.py +617 -0
  17. hud/cli/__main__.py +8 -0
  18. hud/cli/analyze.py +371 -0
  19. hud/cli/analyze_metadata.py +230 -0
  20. hud/cli/build.py +427 -0
  21. hud/cli/clone.py +185 -0
  22. hud/cli/cursor.py +92 -0
  23. hud/cli/debug.py +392 -0
  24. hud/cli/docker_utils.py +83 -0
  25. hud/cli/init.py +281 -0
  26. hud/cli/interactive.py +353 -0
  27. hud/cli/mcp_server.py +756 -0
  28. hud/cli/pull.py +336 -0
  29. hud/cli/push.py +379 -0
  30. hud/cli/remote_runner.py +311 -0
  31. hud/cli/runner.py +160 -0
  32. hud/cli/tests/__init__.py +3 -0
  33. hud/cli/tests/test_analyze.py +284 -0
  34. hud/cli/tests/test_cli_init.py +265 -0
  35. hud/cli/tests/test_cli_main.py +27 -0
  36. hud/cli/tests/test_clone.py +142 -0
  37. hud/cli/tests/test_cursor.py +253 -0
  38. hud/cli/tests/test_debug.py +453 -0
  39. hud/cli/tests/test_mcp_server.py +139 -0
  40. hud/cli/tests/test_utils.py +388 -0
  41. hud/cli/utils.py +263 -0
  42. hud/clients/README.md +143 -0
  43. hud/clients/__init__.py +16 -0
  44. hud/clients/base.py +354 -0
  45. hud/clients/fastmcp.py +202 -0
  46. hud/clients/mcp_use.py +278 -0
  47. hud/clients/tests/__init__.py +1 -0
  48. hud/clients/tests/test_client_integration.py +111 -0
  49. hud/clients/tests/test_fastmcp.py +342 -0
  50. hud/clients/tests/test_protocol.py +188 -0
  51. hud/clients/utils/__init__.py +1 -0
  52. hud/clients/utils/retry_transport.py +160 -0
  53. hud/datasets.py +322 -192
  54. hud/misc/__init__.py +1 -0
  55. hud/{agent → misc}/claude_plays_pokemon.py +292 -283
  56. hud/otel/__init__.py +35 -0
  57. hud/otel/collector.py +142 -0
  58. hud/otel/config.py +164 -0
  59. hud/otel/context.py +536 -0
  60. hud/otel/exporters.py +366 -0
  61. hud/otel/instrumentation.py +97 -0
  62. hud/otel/processors.py +118 -0
  63. hud/otel/tests/__init__.py +1 -0
  64. hud/otel/tests/test_processors.py +197 -0
  65. hud/server/__init__.py +5 -5
  66. hud/server/context.py +114 -0
  67. hud/server/helper/__init__.py +5 -0
  68. hud/server/low_level.py +132 -0
  69. hud/server/server.py +166 -0
  70. hud/server/tests/__init__.py +3 -0
  71. hud/settings.py +73 -79
  72. hud/shared/__init__.py +5 -0
  73. hud/{exceptions.py → shared/exceptions.py} +180 -180
  74. hud/{server → shared}/requests.py +264 -264
  75. hud/shared/tests/test_exceptions.py +157 -0
  76. hud/{server → shared}/tests/test_requests.py +275 -275
  77. hud/telemetry/__init__.py +25 -30
  78. hud/telemetry/instrument.py +379 -0
  79. hud/telemetry/job.py +309 -141
  80. hud/telemetry/replay.py +74 -0
  81. hud/telemetry/trace.py +83 -0
  82. hud/tools/__init__.py +33 -34
  83. hud/tools/base.py +365 -65
  84. hud/tools/bash.py +161 -137
  85. hud/tools/computer/__init__.py +15 -13
  86. hud/tools/computer/anthropic.py +437 -420
  87. hud/tools/computer/hud.py +376 -334
  88. hud/tools/computer/openai.py +295 -292
  89. hud/tools/computer/settings.py +82 -0
  90. hud/tools/edit.py +314 -290
  91. hud/tools/executors/__init__.py +30 -30
  92. hud/tools/executors/base.py +539 -532
  93. hud/tools/executors/pyautogui.py +621 -619
  94. hud/tools/executors/tests/__init__.py +1 -1
  95. hud/tools/executors/tests/test_base_executor.py +338 -338
  96. hud/tools/executors/tests/test_pyautogui_executor.py +165 -165
  97. hud/tools/executors/xdo.py +511 -503
  98. hud/tools/{playwright_tool.py → playwright.py} +412 -379
  99. hud/tools/tests/__init__.py +3 -3
  100. hud/tools/tests/test_base.py +282 -0
  101. hud/tools/tests/test_bash.py +158 -152
  102. hud/tools/tests/test_bash_extended.py +197 -0
  103. hud/tools/tests/test_computer.py +425 -52
  104. hud/tools/tests/test_computer_actions.py +34 -34
  105. hud/tools/tests/test_edit.py +259 -240
  106. hud/tools/tests/test_init.py +27 -27
  107. hud/tools/tests/test_playwright_tool.py +183 -183
  108. hud/tools/tests/test_tools.py +145 -157
  109. hud/tools/tests/test_utils.py +156 -156
  110. hud/tools/types.py +72 -0
  111. hud/tools/utils.py +50 -50
  112. hud/types.py +136 -89
  113. hud/utils/__init__.py +10 -16
  114. hud/utils/async_utils.py +65 -0
  115. hud/utils/design.py +168 -0
  116. hud/utils/mcp.py +55 -0
  117. hud/utils/progress.py +149 -149
  118. hud/utils/telemetry.py +66 -66
  119. hud/utils/tests/test_async_utils.py +173 -0
  120. hud/utils/tests/test_init.py +17 -21
  121. hud/utils/tests/test_progress.py +261 -225
  122. hud/utils/tests/test_telemetry.py +82 -37
  123. hud/utils/tests/test_version.py +8 -8
  124. hud/version.py +7 -7
  125. hud_python-0.4.0.dist-info/METADATA +474 -0
  126. hud_python-0.4.0.dist-info/RECORD +132 -0
  127. hud_python-0.4.0.dist-info/entry_points.txt +3 -0
  128. {hud_python-0.3.5.dist-info → hud_python-0.4.0.dist-info}/licenses/LICENSE +21 -21
  129. hud/adapters/__init__.py +0 -8
  130. hud/adapters/claude/__init__.py +0 -5
  131. hud/adapters/claude/adapter.py +0 -180
  132. hud/adapters/claude/tests/__init__.py +0 -1
  133. hud/adapters/claude/tests/test_adapter.py +0 -519
  134. hud/adapters/common/__init__.py +0 -6
  135. hud/adapters/common/adapter.py +0 -178
  136. hud/adapters/common/tests/test_adapter.py +0 -289
  137. hud/adapters/common/types.py +0 -446
  138. hud/adapters/operator/__init__.py +0 -5
  139. hud/adapters/operator/adapter.py +0 -108
  140. hud/adapters/operator/tests/__init__.py +0 -1
  141. hud/adapters/operator/tests/test_adapter.py +0 -370
  142. hud/agent/__init__.py +0 -19
  143. hud/agent/base.py +0 -126
  144. hud/agent/claude.py +0 -271
  145. hud/agent/langchain.py +0 -215
  146. hud/agent/misc/__init__.py +0 -3
  147. hud/agent/operator.py +0 -268
  148. hud/agent/tests/__init__.py +0 -1
  149. hud/agent/tests/test_base.py +0 -202
  150. hud/env/__init__.py +0 -11
  151. hud/env/client.py +0 -35
  152. hud/env/docker_client.py +0 -349
  153. hud/env/environment.py +0 -446
  154. hud/env/local_docker_client.py +0 -358
  155. hud/env/remote_client.py +0 -212
  156. hud/env/remote_docker_client.py +0 -292
  157. hud/gym.py +0 -130
  158. hud/job.py +0 -773
  159. hud/mcp/__init__.py +0 -17
  160. hud/mcp/base.py +0 -631
  161. hud/mcp/client.py +0 -312
  162. hud/mcp/tests/test_base.py +0 -512
  163. hud/mcp/tests/test_claude.py +0 -294
  164. hud/task.py +0 -149
  165. hud/taskset.py +0 -237
  166. hud/telemetry/_trace.py +0 -347
  167. hud/telemetry/context.py +0 -230
  168. hud/telemetry/exporter.py +0 -575
  169. hud/telemetry/instrumentation/__init__.py +0 -3
  170. hud/telemetry/instrumentation/mcp.py +0 -259
  171. hud/telemetry/instrumentation/registry.py +0 -59
  172. hud/telemetry/mcp_models.py +0 -270
  173. hud/telemetry/tests/__init__.py +0 -1
  174. hud/telemetry/tests/test_context.py +0 -210
  175. hud/telemetry/tests/test_trace.py +0 -312
  176. hud/tools/helper/README.md +0 -56
  177. hud/tools/helper/__init__.py +0 -9
  178. hud/tools/helper/mcp_server.py +0 -78
  179. hud/tools/helper/server_initialization.py +0 -115
  180. hud/tools/helper/utils.py +0 -58
  181. hud/trajectory.py +0 -94
  182. hud/utils/agent.py +0 -37
  183. hud/utils/common.py +0 -256
  184. hud/utils/config.py +0 -120
  185. hud/utils/deprecation.py +0 -115
  186. hud/utils/misc.py +0 -53
  187. hud/utils/tests/test_common.py +0 -277
  188. hud/utils/tests/test_config.py +0 -129
  189. hud_python-0.3.5.dist-info/METADATA +0 -284
  190. hud_python-0.3.5.dist-info/RECORD +0 -120
  191. /hud/{adapters/common → shared}/tests/__init__.py +0 -0
  192. {hud_python-0.3.5.dist-info → hud_python-0.4.0.dist-info}/WHEEL +0 -0
@@ -1,80 +1,80 @@
1
- import json
2
- import os
3
- from typing import Literal, Optional
4
-
5
- from openai import AsyncOpenAI
6
-
7
- ResponseType = Literal["STOP", "CONTINUE"]
8
-
9
-
10
- class ResponseAgent:
11
- """
12
- An assistant that helps determine whether an agent should stop or continue
13
- based on the agent's final response message.
14
- """
15
-
16
- def __init__(self, api_key: Optional[str] = None):
17
- self.api_key = api_key or os.environ.get("OPENAI_API_KEY")
18
- if not self.api_key:
19
- raise ValueError(
20
- "OpenAI API key must be provided or set as OPENAI_API_KEY environment variable"
21
- )
22
-
23
- self.client = AsyncOpenAI(api_key=self.api_key)
24
-
25
- self.system_prompt = """
26
- You are an assistant that helps determine the appropriate response to an agent's message.
27
-
28
- You will receive messages from an agent that is performing tasks for a user.
29
- Your job is to analyze these messages and respond with one of the following:
30
-
31
- - STOP: If the agent indicates it has successfully completed a task, even if phrased as a question
32
- like "I have entered the right values into this form. Would you like me to do anything else?"
33
- or "Here is the website. Is there any other information you need?"
34
-
35
- - CONTINUE: If the agent is asking for clarification before proceeding with a task
36
- like "I'm about to clear cookies from this website. Would you like me to proceed?"
37
- or "I've entered the right values into this form. Would you like me to continue with the rest of the task?"
38
-
39
- Respond ONLY with one of these two options.
40
- """
41
-
42
- async def determine_response(self, agent_message: str) -> ResponseType:
43
- """
44
- Determine whether the agent should stop or continue based on its message.
45
-
46
- Args:
47
- agent_message: The message from the agent
48
-
49
- Returns:
50
- ResponseType: Either "STOP" or "CONTINUE"
51
- """
52
- try:
53
- response = await self.client.chat.completions.create(
54
- model="gpt-4o",
55
- messages=[
56
- {"role": "system", "content": self.system_prompt},
57
- {
58
- "role": "user",
59
- "content": f"Agent message: {agent_message}\n\nWhat is the appropriate response?",
60
- },
61
- ],
62
- temperature=0.1, # Low temperature for more deterministic responses
63
- max_tokens=5, # We only need a short response
64
- )
65
-
66
- response_text = response.choices[0].message.content
67
- if not response_text:
68
- return "CONTINUE"
69
-
70
- response_text = response_text.strip().upper()
71
-
72
- # Validate the response
73
- if "STOP" in response_text:
74
- return "STOP"
75
- else:
76
- return "CONTINUE"
77
-
78
- except Exception as e:
79
- print(f"Error determining response: {e}")
80
- return "CONTINUE" # Default to continue on error
1
+ from __future__ import annotations
2
+
3
+ import os
4
+ from typing import Literal
5
+
6
+ from openai import AsyncOpenAI
7
+
8
+ ResponseType = Literal["STOP", "CONTINUE"]
9
+
10
+
11
+ class ResponseAgent:
12
+ """
13
+ An assistant that helps determine whether an agent should stop or continue
14
+ based on the agent's final response message.
15
+ """
16
+
17
+ def __init__(self, api_key: str | None = None) -> None:
18
+ self.api_key = api_key or os.environ.get("OPENAI_API_KEY")
19
+ if not self.api_key:
20
+ raise ValueError(
21
+ "OpenAI API key must be provided or set as OPENAI_API_KEY environment variable"
22
+ )
23
+
24
+ self.client = AsyncOpenAI(api_key=self.api_key)
25
+
26
+ self.system_prompt = """
27
+ You are an assistant that helps determine the appropriate response to an agent's message.
28
+
29
+ You will receive messages from an agent that is performing tasks for a user.
30
+ Your job is to analyze these messages and respond with one of the following:
31
+
32
+ - STOP: If the agent indicates it has successfully completed a task, even if phrased as a question
33
+ like "I have entered the right values into this form. Would you like me to do anything else?"
34
+ or "Here is the website. Is there any other information you need?"
35
+
36
+ - CONTINUE: If the agent is asking for clarification before proceeding with a task
37
+ like "I'm about to clear cookies from this website. Would you like me to proceed?"
38
+ or "I've entered the right values into this form. Would you like me to continue with the rest of the task?"
39
+
40
+ Respond ONLY with one of these two options.
41
+ """ # noqa: E501
42
+
43
+ async def determine_response(self, agent_message: str) -> ResponseType:
44
+ """
45
+ Determine whether the agent should stop or continue based on its message.
46
+
47
+ Args:
48
+ agent_message: The message from the agent
49
+
50
+ Returns:
51
+ ResponseType: Either "STOP" or "CONTINUE"
52
+ """
53
+ try:
54
+ response = await self.client.chat.completions.create(
55
+ model="gpt-4o",
56
+ messages=[
57
+ {"role": "system", "content": self.system_prompt},
58
+ {
59
+ "role": "user",
60
+ "content": f"Agent message: {agent_message}\n\nWhat is the appropriate response?", # noqa: E501
61
+ },
62
+ ],
63
+ temperature=0.1, # Low temperature for more deterministic responses
64
+ max_tokens=5, # We only need a short response
65
+ )
66
+
67
+ response_text = response.choices[0].message.content
68
+ if not response_text:
69
+ return "CONTINUE"
70
+
71
+ response_text = response_text.strip().upper()
72
+
73
+ # Validate the response
74
+ if "STOP" in response_text:
75
+ return "STOP"
76
+ else:
77
+ return "CONTINUE"
78
+
79
+ except Exception:
80
+ return "CONTINUE" # Default to continue on error