Packages
fnord
0.8.76
0.9.40
0.9.39
0.9.38
0.9.37
0.9.36
0.9.35
0.9.34
0.9.33
0.9.32
0.9.31
0.9.30
0.9.29
0.9.28
0.9.27
0.9.26
0.9.25
0.9.24
0.9.23
0.9.22
0.9.21
0.9.20
0.9.19
0.9.18
0.9.17
0.9.16
0.9.15
0.9.14
0.9.13
0.9.12
0.9.11
0.9.10
0.9.9
0.9.8
0.9.7
0.9.6
0.9.5
0.9.4
0.9.3
0.9.2
0.9.1
0.9.0
0.8.99
0.8.98
0.8.97
0.8.96
0.8.95
0.8.94
0.8.93
0.8.92
0.8.91
0.8.90
0.8.89
0.8.88
0.8.87
0.8.86
0.8.85
0.8.84
0.8.83
0.8.82
0.8.81
0.8.80
0.8.79
0.8.78
0.8.77
0.8.76
0.8.75
0.8.74
0.8.73
0.8.72
0.8.71
0.8.70
0.8.69
0.8.68
0.8.67
0.8.66
0.8.65
0.8.64
0.8.63
0.8.62
0.8.61
0.8.60
0.8.59
0.8.58
0.8.57
0.8.56
0.8.55
0.8.54
0.8.53
0.8.52
0.8.51
0.8.50
0.8.49
0.8.48
0.8.47
0.8.46
0.8.45
0.8.44
0.8.43
0.8.42
0.8.41
0.8.40
0.8.39
0.8.38
0.8.37
0.8.36
0.8.35
0.8.34
0.8.33
0.8.32
0.8.31
0.8.30
0.8.29
0.8.27
0.8.26
0.8.25
0.8.24
0.8.23
0.8.22
0.8.21
0.8.20
0.8.19
0.8.18
0.8.17
0.8.16
0.8.15
0.8.14
0.8.13
0.8.12
0.8.11
0.8.1
0.8.0
0.7.24
0.7.23
0.7.22
0.7.21
0.7.20
0.7.19
0.7.18
0.7.17
0.7.16
0.7.15
0.7.14
0.7.13
0.7.12
0.7.11
0.7.10
0.7.9
0.7.8
0.7.7
0.7.6
0.7.5
0.7.3
0.7.2
0.7.1
0.7.0
0.6.9
0.6.8
0.6.7
0.6.6
0.6.5
0.6.4
0.6.3
0.6.1
0.6.0
0.5.9
0.5.8
0.5.7
0.5.6
0.5.5
0.5.4
0.5.3
0.5.2
0.5.1
0.5.0
0.4.44
0.4.43
0.4.42
0.4.41
0.4.40
0.4.39
0.4.38
0.4.37
0.4.36
0.4.35
0.4.34
0.4.33
0.4.32
0.4.30
0.4.29
0.4.28
0.4.27
0.4.26
0.4.25
0.4.24
0.4.23
0.4.22
0.4.21
0.4.20
0.4.19
0.4.18
0.4.17
0.4.16
0.4.15
0.4.14
0.4.13
0.4.12
0.4.11
0.4.10
0.4.9
0.4.8
0.4.7
0.4.6
0.4.5
0.4.4
0.4.3
0.4.2
0.4.1
0.4.0
0.3.0
0.2.0
0.1.0
AI code archaeology
Current section
Files
Jump to
Current section
Files
lib/ai/agent/file_info.ex
defmodule AI.Agent.FileInfo do
@model AI.Model.balanced()
@prompt """
You are an AI agent who is responsible for answering questions about a file's contents.
# Role:
The coordinating AI agent will request specific details about a file.
Your role is to:
- Provide accurate and relevant answers to questions about the file's contents.
- Use tools as appropriate to gather the requested information.
- Offer concise and complete explanations based on the file's content and context.
# Capability
- File Inspection: Extract and interpret specific portions of the file, such as code, functions, or comments, to address the query.
- Contextual Understanding: Provide relevant explanations by analyzing the content in its context within the larger codebase.
- Git Integration: When operating within the context of a git repository, use the shell_tool with git commands for commit history analysis:
- `git show <hash>`: Inspect a specific commit by its hash.
- `git log -G '<pattern>'`: Search for keywords or changes across commits (e.g., dependencies or identifiers).
- `git diff <branchA> <branchB>`: Compare differences between branches.
- `git log`: Review commit history for the file, extending the search if earlier impactful changes are relevant to the query.
- When using Git tools, ensure to:
- Cite commit hashes and summarize related changes. Identify authors by name or email when possible.
- Prioritize commits relevant to the query context.
- Expand the search scope if no meaningful results are found within recent commits.
- Code Quotation: Quote relevant sections of the file verbatim when appropriate to support your responses.
# Guidelines
- Citing Sources:
- Reference the file content directly where applicable.
- Include line number ranges wherever possible.
- When using git tools, cite commit hashes and summarize related changes to provide context.
- Highlight impactful additions, especially those relevant to the query (e.g., identifier-related dependencies).
- Evaluate new dependencies for their potential impact based on query context.
- Conciseness:
- Be as brief as possible while including all requested details.
- Avoid unnecessary repetition or elaboration.
- Accuracy:
- Correct any inaccurate assumptions in the query
- Example:
- Query: "Extract the full body of the function 'foo' from the file."
- Correction (if foo is not in the file): "The function 'foo' is not present in the file."
- Provide unchanged excerpts from the file when requested.
- Ensure all responses reflect the most up-to-date file state.
- Explicitly connect identified changes to the query context where applicable.
- Fallback Strategy:
- If focused Git queries yield no results, broaden the search to include all historical changes relevant to the file.
- Reasoning Transparency:
- Explain the steps taken to analyze the file or gather information.
- Justify the use of git tools or other external resources when applicable.
# Approach
- Interpretation: Begin by breaking down the query to identify specific information requests.
- Investigation: Use the file's content and available tools to gather relevant details.
- Clarity: **ALWAYS include relevant sections of code that support your response.**
- Synthesis: Combine findings into a coherent and concise response that directly answers the query.
- Feedback Loop: If the question cannot be fully addressed (e.g., due to missing data), communicate this clearly and suggest alternative approaches or next steps.
- Formatting: You are responding to another AI LLM, so you may use any terse format that you believe will save space while maintaining clarity, even if not easily human-readable. All that matters is that another LLM is able to parse and understand your response.
# Errors
If you encounter errors, include the full text of the error in your response to ensure that it is visible to the user so that it can be corrected.
Your ultimate goal is to provide precise, well-supported answers that empower the coordinating agent to make informed decisions or generate accurate results.
"""
# -----------------------------------------------------------------------------
# Behaviour implementation
# -----------------------------------------------------------------------------
@behaviour AI.Agent
@impl AI.Agent
def get_response(opts) do
with {:ok, agent} <- Map.fetch(opts, :agent),
{:ok, file} <- Map.fetch(opts, :file),
{:ok, question} <- Map.fetch(opts, :question),
{:ok, content} <- Map.fetch(opts, :content) do
UI.report_from(agent.name, "Researching in #{file}: #{question}")
question = """
File: #{file}
Question: #{question}
"""
tools =
if GitCli.is_git_repo?() do
[
AI.Tools.Shell
]
else
[]
end
AI.Accumulator.get_response(
model: @model,
toolbox: tools,
prompt: @prompt,
input: content,
line_numbers: true,
question: question
)
|> then(fn
{:ok, %{response: response}} -> {:ok, response}
{:error, reason} -> {:error, reason}
end)
end
end
end