feat: Created the explore agent for exploring codebases to help answer questions

2026-02-13 15:40:46 -07:00
parent d2e541c5c0
commit 3779b940ae
4 changed files with 693 additions and 0 deletions
@@ -0,0 +1,15 @@
+# Explore
+
+An AI agent specialized in exploring codebases, finding patterns, and understanding project structures.
+
+This agent is designed to be delegated to by the **[Sisyphus](../sisyphus/README.md)** agent to gather information and context. Sisyphus 
+acts as the coordinator/architect, while Explore handles the research and discovery phase.
+
+It can also be used as a standalone tool for understanding codebases and finding specific information.
+
+## Features
+
+- 🔍 Deep codebase exploration and pattern matching
+- 📂 File system navigation and content analysis
+- 🧠 Context gathering for complex tasks
+- 🛡️ Read-only operations for safe investigation
@@ -0,0 +1,74 @@
+name: explore
+description: Fast codebase exploration agent - finds patterns, structures, and relevant files
+version: 1.0.0
+temperature: 0.1
+top_p: 0.95
+
+variables:
+  - name: project_dir
+    description: Project directory to explore
+    default: '.'
+
+global_tools:
+  - fs_read.sh
+  - fs_grep.sh
+  - fs_glob.sh
+  - fs_ls.sh
+
+instructions: |
+  You are a codebase explorer. Your job: Search, find, report. Nothing else.
+  
+  ## Your Mission
+  
+  Given a search task, you:
+  1. Search for relevant files and patterns
+  2. Read key files to understand structure
+  3. Report findings concisely
+  4. Signal completion with EXPLORE_COMPLETE
+  
+  ## File Reading Strategy (IMPORTANT - minimize token usage)
+
+  1. **Find first, read second** - Never read a file without knowing why
+  2. **Use grep to locate** - `fs_grep --pattern "struct User" --include "*.rs"` finds exactly where things are
+  3. **Use glob to discover** - `fs_glob --pattern "*.rs" --path src/` finds files by name
+  4. **Read targeted sections** - `fs_read --path "src/main.rs" --offset 50 --limit 30` reads only lines 50-79
+  5. **Never read entire large files** - If a file is 500+ lines, read the relevant section only
+
+  ## Available Actions
+
+  - `fs_grep --pattern "struct User" --include "*.rs"` - Find content across files
+  - `fs_glob --pattern "*.rs" --path src/` - Find files by name pattern
+  - `fs_read --path "src/main.rs"` - Read a file (with line numbers)
+  - `fs_read --path "src/main.rs" --offset 100 --limit 50` - Read lines 100-149 only
+  - `get_structure` - See project layout
+  - `search_content --pattern "struct User"` - Agent-level content search
+  
+  ## Output Format
+  
+  Always end your response with a findings summary:
+  
+  ```
+  FINDINGS:
+  - [Key finding 1]
+  - [Key finding 2]
+  - Relevant files: [list]
+  
+  EXPLORE_COMPLETE
+  ```
+  
+  ## Rules
+  
+  1. **Be fast** - Don't read every file, read representative ones
+  2. **Be focused** - Answer the specific question asked
+  3. **Be concise** - Report findings, not your process
+  4. **Never modify files** - You are read-only
+  5. **Limit reads** - Max 5 file reads per exploration
+  
+  ## Context
+  - Project: {{project_dir}}
+  - CWD: {{__cwd__}}
+
+conversation_starters:
+  - 'Find how authentication is implemented'
+  - 'What patterns are used for API endpoints'
+  - 'Show me the project structure'
@@ -0,0 +1,157 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+# shellcheck disable=SC1090
+source "$LLM_PROMPT_UTILS_FILE"
+source "$LLM_ROOT_DIR/agents/.shared/utils.sh"
+
+# @env LLM_OUTPUT=/dev/stdout
+# @env LLM_AGENT_VAR_PROJECT_DIR=.
+# @describe Explore agent tools for codebase search and analysis
+
+_project_dir() {
+  local dir="${LLM_AGENT_VAR_PROJECT_DIR:-.}"
+  (cd "${dir}" 2>/dev/null && pwd) || echo "${dir}"
+}
+
+# @cmd Get project structure and layout
+get_structure() {
+  local project_dir
+  project_dir=$(_project_dir)
+  
+  info "Project structure:" >> "$LLM_OUTPUT"
+  echo "" >> "$LLM_OUTPUT"
+  
+  local project_info
+  project_info=$(detect_project "${project_dir}")
+
+  {
+  	echo "Type: $(echo "${project_info}" | jq -r '.type')"
+  	echo ""
+
+  	get_tree "${project_dir}" 3
+  } >> "$LLM_OUTPUT"
+}
+
+# @cmd Search for files by name pattern
+# @option --pattern! File name pattern (e.g., "*.rs", "config*", "*test*")
+search_files() {
+	# shellcheck disable=SC2154
+  local pattern="${argc_pattern}"
+  local project_dir
+  project_dir=$(_project_dir)
+  
+  info "Files matching: ${pattern}" >> "$LLM_OUTPUT"
+  echo "" >> "$LLM_OUTPUT"
+  
+  local results
+  results=$(search_files "${pattern}" "${project_dir}")
+  
+  if [[ -n "${results}" ]]; then
+    echo "${results}" >> "$LLM_OUTPUT"
+  else
+    warn "No files found" >> "$LLM_OUTPUT"
+  fi
+}
+
+# @cmd Search for content in files
+# @option --pattern! Text or regex pattern to search for
+# @option --file-type Filter by file extension (e.g., "rs", "py", "ts")
+search_content() {
+  local pattern="${argc_pattern}"
+  local file_type="${argc_file_type:-}"
+  local project_dir
+  project_dir=$(_project_dir)
+  
+  info "Searching: ${pattern}" >> "$LLM_OUTPUT"
+  echo "" >> "$LLM_OUTPUT"
+  
+  local include_arg=""
+  if [[ -n "${file_type}" ]]; then
+    include_arg="--include=*.${file_type}"
+  fi
+  
+  local results
+  # shellcheck disable=SC2086
+  results=$(grep -rn ${include_arg} "${pattern}" "${project_dir}" 2>/dev/null | \
+    grep -v '/target/' | \
+    grep -v '/node_modules/' | \
+    grep -v '/.git/' | \
+    grep -v '/dist/' | \
+    head -30) || true
+  
+  if [[ -n "${results}" ]]; then
+    echo "${results}" >> "$LLM_OUTPUT"
+  else
+    warn "No matches found" >> "$LLM_OUTPUT"
+  fi
+}
+
+# @cmd Read a file's contents
+# @option --path! Path to the file (relative to project root)
+# @option --lines Maximum lines to read (default: 200)
+read_file() {
+	# shellcheck disable=SC2154
+  local file_path="${argc_path}"
+  local max_lines="${argc_lines:-200}"
+  local project_dir
+  project_dir=$(_project_dir)
+  
+  local full_path="${project_dir}/${file_path}"
+  
+  if [[ ! -f "${full_path}" ]]; then
+    error "File not found: ${file_path}" >> "$LLM_OUTPUT"
+    return 1
+  fi
+
+  {
+  	info "File: ${file_path}"
+  	echo ""
+  } >> "$LLM_OUTPUT"
+  
+  head -n "${max_lines}" "${full_path}" >> "$LLM_OUTPUT"
+  
+  local total_lines
+  total_lines=$(wc -l < "${full_path}")
+  if [[ "${total_lines}" -gt "${max_lines}" ]]; then
+    echo "" >> "$LLM_OUTPUT"
+    warn "... truncated (${total_lines} total lines)" >> "$LLM_OUTPUT"
+  fi
+}
+
+# @cmd Find similar files to a given file (for pattern matching)
+# @option --path! Path to the reference file
+find_similar() {
+  local file_path="${argc_path}"
+  local project_dir
+  project_dir=$(_project_dir)
+  
+  local ext="${file_path##*.}"
+  local dir
+  dir=$(dirname "${file_path}")
+  
+  info "Files similar to: ${file_path}" >> "$LLM_OUTPUT"
+  echo "" >> "$LLM_OUTPUT"
+  
+  local results
+  results=$(find "${project_dir}/${dir}" -maxdepth 1 -type f -name "*.${ext}" \
+    ! -name "$(basename "${file_path}")" \
+    ! -name "*test*" \
+    ! -name "*spec*" \
+    2>/dev/null | head -5)
+  
+  if [[ -n "${results}" ]]; then
+    echo "${results}" >> "$LLM_OUTPUT"
+  else
+    results=$(find "${project_dir}" -type f -name "*.${ext}" \
+      ! -name "$(basename "${file_path}")" \
+      ! -name "*test*" \
+      -not -path '*/target/*' \
+      2>/dev/null | head -5)
+    if [[ -n "${results}" ]]; then
+      echo "${results}" >> "$LLM_OUTPUT"
+    else
+      warn "No similar files found" >> "$LLM_OUTPUT"
+    fi
+  fi
+}