prompt_006.log 4.0 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495
  1. ----------
  2. # Task
  3. You are in charge of accomplishing the following task:
  4. Fix typos in bad.txt. Do not ask me for confirmation at any point.
  5. In order to accomplish this goal, you must delegate tasks to one or more agents, who
  6. can do the actual work. A description of each agent is provided below. You MUST
  7. select one of the delegates below to move towards accomplishing the task, and you MUST
  8. provide the correct inputs for the delegate you select.
  9. Note: the delegated agent either returns "finish" or "reject".
  10. - If the action is "finish", but the full task is not done yet, you should
  11. continue to delegate to one of the agents below to until the full task is finished.
  12. - If the action is "reject", it means the delegated agent is not capable of the
  13. task you send to. You should revisit the input you send to the delegate, and consider
  14. whether any other delegate would be able to solve the task. If you cannot find
  15. a proper delegate agent, or the delegate attempts keep failing, call the `reject`
  16. action. In `reason` attribute, make sure you include your attempts (e.g. what agent
  17. you have delegated to, and why they failed).
  18. ## Agents
  19. ### CoderAgent
  20. Given a particular task, and a detailed description of the codebase, accomplishes the task
  21. #### Inputs
  22. {"task": "string", "summary": "string"}
  23. ### CommitWriterAgent
  24. Write a git commit message for files in the git staging area
  25. #### Inputs
  26. {}
  27. ### MathAgent
  28. Solves simple and complex math problems using python
  29. #### Inputs
  30. {"task": "string"}
  31. ### PostgresAgent
  32. Writes and maintains PostgreSQL migrations
  33. #### Inputs
  34. {"task": "string"}
  35. ### RepoExplorerAgent
  36. Generates a detailed summary of an existing codebase
  37. #### Inputs
  38. {}
  39. ### StudyRepoForTaskAgent
  40. Given a particular task, finds and describes all relevant parts of the codebase
  41. #### Inputs
  42. {"task": "string"}
  43. ### TypoFixerAgent
  44. Fixes typos in files in the current working directory
  45. #### Inputs
  46. {"task": "string"}
  47. ### VerifierAgent
  48. Given a particular task, verifies that the task has been completed
  49. #### Inputs
  50. {"task": "string"}
  51. ## History
  52. Here is a recent history of actions you've taken in service of this plan,
  53. as well as observations you've made. This only includes the MOST RECENT
  54. actions and observations--more may have happened before that.
  55. They are time-ordered, with your most recent action at the bottom.
  56. [{"source": "user", "action": "message", "args": {"content": "Fix typos in bad.txt. Do not ask me for confirmation at any point.", "images_urls": null, "wait_for_response": false}}, {"source": "agent", "action": "delegate", "args": {"agent": "TypoFixerAgent", "inputs": {"task": "Fix typos in bad.txt"}, "thought": ""}}, {"source": "agent", "observation": "delegate", "content": "TypoFixerAgent finishes task with summary: {'file': './bad.txt', 'typos_fixed': [{'original': 'typoo', 'corrected': 'typo'}, {'original': 'mor', 'corrected': 'more'}]}", "extras": {"outputs": {"summary": {"file": "./bad.txt", "typos_fixed": [{"original": "typoo", "corrected": "typo"}, {"original": "mor", "corrected": "more"}]}}}}]
  57. If the last item in the history is an error, you should try to fix it. If you
  58. cannot fix it, call the `reject` action.
  59. ## Available Actions
  60. * `delegate` - send a task to another agent from the list provided. Arguments:
  61. * `agent` - the agent to which the task is delegated. MUST match a name in the list of agents provided.
  62. * `inputs` - a dictionary of input parameters to the agent, as specified in the list
  63. * `finish` - if you're absolutely certain that you've completed your task, use the finish action to stop working. Arguments:
  64. * `outputs` - a dictionary representing the outputs of your task, if any
  65. * `reject` - reject the task. Arguments:
  66. * `outputs` - a dictionary with only a `reason` attribute
  67. ## Format
  68. Your response MUST be in JSON format. It must be an object, and it must contain two fields:
  69. * `action`, which is one of the actions specified here
  70. * `args`, which is a map of key-value pairs, specifying the arguments for that action
  71. You MUST NOT include any other text besides the JSON response