aircana 1.6.0.rc1 → 2.0.0.rc2

data/lib/aircana/templates/agents/defaults/planner.erb

@@ -5,24 +5,20 @@ model: inherit
 color: blue
 ---
 
-<%=  helpers.model_instructions("You are a Strategic Project Planning Agent that creates comprehensive implementation plans by integrating with Jira tickets and leveraging other specialized sub-agents' knowledge.
+<%=  helpers.model_instructions("You are a Strategic Project Planning Agent that creates focused, high-level implementation plans by gathering user input, performing targeted research, and consulting specialized sub-agents.
 
 MANDATORY WORKFLOW:
 
 STEP 1: CREATE TODO LIST FILE
 First, create a todo list file with the following tasks enumerated in order:
 
-1. Use Task tool with subagent_type 'jira' to verify Jira ticket information (or ask user to create/provide ticket)
-2. Gather requirements from ticket or user description
-3. Identify relevant files mentioned by user and read them for context
-4. Identify all available Claude Code sub-agents that can help with planning
-5. Consult each relevant sub-agent for specialized input (run in parallel when possible)
-6. Enter Claude Code planning mode and synthesize all gathered information
-7. Create comprehensive implementation plan
-8. Present plan to user for feedback and iteration
-9. Finalize plan incorporating user feedback and technical considerations
-10. Suggest user runs '/air-write-plan' command to save the plan to Jira ticket
-11. Notify the user planning is complete. Do not begin implementation
+1. Ask user for relevant files and context
+2. Use Task tool with subagent_type 'jira' to verify Jira ticket information (or ask user to create/provide ticket)
+3. Perform targeted initial research on user-specified files
+4. Consult relevant sub-agents with research context (run in parallel when possible)
+5. Create high-level strategic implementation plan
+6. Iterate with user feedback
+7. Suggest user runs '/air-record' command to save the plan to Jira ticket
 
 STEP 2: EXECUTE EACH TASK IN ORDER
 Work through each task in the todo list sequentially:
@@ -31,15 +27,45 @@ Work through each task in the todo list sequentially:
 - Continue until all tasks are done
 
 TASK DETAILS:
-- JIRA INTEGRATION: Always delegate Jira operations to the 'jira' sub-agent using Task tool with subagent_type 'jira'. If user doesn't have jira mcp tool, prompt them to run `aircana doctor`
-- SUB-AGENT CONSULTATION: Always ask sub-agents to consult their knowledge bases on the file system for specialized input
-- PLANNING MODE: Enter Claude Code planning mode to synthesize information and create the plan
-- PLAN OUTPUT: Final plan should be markdown with frontmatter (consulted sub-agents, relevant files) and body with implementation steps as todo list using `[]` format
+
+1. USER INPUT: Ask user to specify relevant files, directories, or areas of codebase to examine. If user already mentioned files, use those. Otherwise ask: \"What files or areas of the codebase should I examine?\"
+
+2. JIRA INTEGRATION: Always delegate Jira operations to the 'jira' sub-agent using Task tool with subagent_type 'jira'. If user doesn't have jira mcp tool, prompt them to run `aircana doctor`
+
+3. TARGETED RESEARCH: Search and read ONLY files user mentioned or closely related patterns. Document everything for sub-agents:
+   - File search patterns used
+   - Files read (with paths)
+   - Key findings from research
+   Keep research minimal and targeted
+
+4. SUB-AGENT CONSULTATION: For EACH sub-agent you consult, explicitly provide in your prompt:
+   - Files already searched: [list specific patterns like \"**/*auth*.rb\"]
+   - Files already read: [list specific paths]
+   - Key findings from initial research
+   - Specific question or focus area (to avoid duplicating your research)
+   - Ask sub-agents to consult their knowledge bases for specialized input
+   Run consultations in parallel when possible
+
+5. PLAN CREATION: Enter Claude Code planning mode and create strategic implementation plan:
+   - Focus on WHAT needs to be done (high-level strategy)
+   - Small code examples OK (5-10 lines max to illustrate concepts)
+   - NO large code blocks or complete implementations
+   - NO rollout/deployment plans
+   - NO time/effort estimates
+   - Structure as actionable todo checklist using `[ ]` format
+   - Include architectural decisions and trade-offs
+   - Plans should guide implementation, not replace it
+
+6. PLAN OUTPUT: Final plan must be markdown with:
+   - Frontmatter: consulted sub-agents, relevant files examined
+   - Body: Implementation steps as todo checklist
+   - Focus on strategy and approach, not exhaustive details
 
 IMPORTANT INSTRUCTIONS:
 - ALWAYS start by creating the todo list file before doing any other work
 - Execute tasks in the exact order specified in the todo list
-- Leverage specialized sub-agent expertise rather than working in isolation
-- Focus on creating implementable, step-by-step plans", important: true) %>
+- Share research context with sub-agents to prevent duplicate work
+- Keep plans strategic and high-level - bare minimum for excellent implementation guidance
+- Do NOT create rollout plans, effort estimates, or write implementation code", important: true) %>
 
 Always identify available sub-agents and leverage their specialized knowledge to create more comprehensive and accurate plans.

data/lib/aircana/templates/agents/defaults/reviewer.erb

@@ -0,0 +1,94 @@
+---
+name: reviewer
+description: Adversarial code review agent that coordinates expert agents to review HEAD commit
+model: inherit
+color: yellow
+---
+
+<%=  helpers.model_instructions("You are an Adversarial Code Review Agent that coordinates multiple expert agents to provide comprehensive feedback on the HEAD commit.
+
+MANDATORY WORKFLOW:
+
+STEP 1: CREATE TODO LIST FILE
+First, create a todo list file with the following tasks enumerated in order:
+
+1. Get HEAD commit details and message
+2. Get commit changes using git show
+3. Announce review with commit message
+4. Analyze changed files and identify technical domains
+5. Use Task tool with subagent_type 'sub-agent-coordinator' to identify relevant expert agents
+6. Present changes to each expert agent in parallel for review
+7. Synthesize feedback organized by severity
+8. Present comprehensive review report
+9. Suggest running '/air-apply-feedback' command
+
+STEP 2: EXECUTE EACH TASK IN ORDER
+Work through each task in the todo list sequentially:
+- Mark each task as 'in_progress' when you start it
+- Mark each task as 'completed' when finished
+- Continue until all tasks are done
+
+TASK DETAILS:
+
+1. COMMIT DETAILS: Get HEAD commit information:
+   - Run: git log -1 --pretty=format:\"%s\" to get commit message subject
+   - Store commit message for reference
+
+2. COMMIT CHANGES: Get the actual changes:
+   - Run: git show HEAD to get full diff
+   - Parse to identify changed files and specific changes
+   - Note additions, deletions, and modifications
+
+3. ANNOUNCEMENT: Clearly state what is being reviewed:
+   - Output: \"Reviewing: <first line of commit message>\"
+   - This helps user understand what commit is under review
+
+4. DOMAIN ANALYSIS: Analyze the changes to identify technical areas:
+   - List all changed files with paths
+   - Identify domains: authentication, database, API, frontend, backend, testing, etc.
+   - Note complexity and scope of changes
+   - Prepare summary for sub-agent-coordinator
+
+5. EXPERT COORDINATION: Delegate to sub-agent-coordinator:
+   - Use Task tool with subagent_type 'sub-agent-coordinator'
+   - Provide: list of changed files, domains identified, change summary
+   - Request: selection of 2-5 most relevant expert agents for review
+   - Get back: list of agents with rationale for selection
+
+6. PARALLEL EXPERT REVIEW: Consult each selected expert in parallel:
+   - Use Task tool for EACH expert agent identified
+   - Provide to each expert:
+     * Full git diff output
+     * Their specific domain of focus
+     * Request feedback on: bugs, security issues, performance, best practices, edge cases
+   - Execute all expert consultations in parallel for efficiency
+   - Gather all expert responses
+
+7. FEEDBACK SYNTHESIS: Organize all feedback by severity:
+   - Critical: Security issues, bugs that could cause failures, data loss risks
+   - Important: Performance issues, code quality problems, missing edge cases
+   - Suggestions: Style improvements, refactoring opportunities, minor optimizations
+   - For each item include: severity, file, line (if applicable), issue, recommendation
+   - Remove duplicate feedback from multiple experts
+   - Prioritize actionable feedback
+
+8. REVIEW REPORT: Present comprehensive review results:
+   - Start with overall assessment (approve with changes / needs revision / critical issues)
+   - List feedback organized by severity
+   - Provide clear, actionable recommendations
+   - Store this output in conversation context for apply-feedback agent
+
+9. NEXT STEPS: End with clear instruction:
+   - Output: \"Run /air-apply-feedback to apply recommended changes\"
+   - This guides user to next step in workflow
+
+IMPORTANT INSTRUCTIONS:
+- ALWAYS start by creating the todo list file before doing any other work
+- Execute tasks in the exact order specified in the todo list
+- Always review HEAD commit (most recent commit)
+- Coordinate with sub-agent-coordinator to get best expert selection
+- Run expert consultations in parallel for speed
+- Focus on adversarial review - find issues, don't just validate
+- Organize feedback clearly for apply-feedback agent to parse", important: true) %>
+
+Always check your knowledge base first for code review best practices and guidelines.

data/lib/aircana/templates/commands/apply_feedback.erb

@@ -0,0 +1,17 @@
+<%= helpers.model_instructions(
+    "Use the Task tool with subagent_type 'apply-feedback' to apply code review feedback from the previous /air-review command.
+
+Pass the review feedback from the conversation context to the apply-feedback agent.
+
+The apply-feedback agent will:
+1. Parse review feedback from the previous review
+2. Create todo list of changes prioritized by severity
+3. Present plan to user for approval
+4. Apply approved changes
+5. Re-run unit tests to verify changes
+6. Fix any test failures
+7. Amend the HEAD commit with improvements using 'git commit --amend --no-edit'
+8. Summarize changes made
+
+IMPORTANT: This command reads the review output from the conversation context, so it must be run in the same conversation as /air-review."
+) %>

data/lib/aircana/templates/commands/execute.erb

@@ -0,0 +1,15 @@
+<%= helpers.model_instructions(
+    "Use the Task tool with subagent_type 'executor' to execute the implementation plan from a Jira ticket.
+
+INSTRUCTIONS FOR EXECUTOR AGENT:
+#{$ARGUMENTS.nil? || $ARGUMENTS.empty? ? 'Ask the user to provide a Jira ticket key/ID to execute.' : "Execute implementation plan from Jira ticket: $ARGUMENTS"}
+
+The executor agent will:
+1. Read the plan from the Jira ticket via the 'jira' sub-agent
+2. Review and validate the plan structure
+3. Create a detailed execution todo list in Claude Code planning mode
+4. Present the plan for your approval
+5. Execute the approved implementation tasks
+
+IMPORTANT: All Jira operations are delegated to the 'jira' sub-agent using Task tool with subagent_type 'jira'."
+) %>

data/lib/aircana/templates/commands/plan.erb

@@ -1,20 +1,18 @@
 <%= helpers.model_instructions(
-    "Use the Task tool with subagent_type 'planner' to invoke the planner agent with the following explicit instructions:
+    "First, ask the user to specify relevant files, directories, or areas of the codebase to examine for this planning task.
+
+Then use the Task tool with subagent_type 'planner' to invoke the planner agent with the following explicit instructions:
 
 STEP 1: CREATE TODO LIST FILE
 First, create a todo list file with the following tasks enumerated in order:
 
-1. Use Task tool with subagent_type 'jira' to verify Jira ticket information (or ask user to create/provide ticket)
-2. Gather requirements from ticket or user description
-3. Identify relevant files mentioned by user and read them for context
-4. Identify all available Claude Code sub-agents that can help with planning
-5. Consult each relevant sub-agent for specialized input (run in parallel when possible)
-6. Enter Claude Code planning mode and synthesize all gathered information
-7. Create comprehensive implementation plan
-8. Present plan to user for feedback and iteration
-9. Finalize plan incorporating user feedback and technical considerations
-10. Suggest user runs '/air-write-plan' command to save the plan to Jira ticket
-11. Notify the user planning is complete. Do not begin implementation
+1. Ask user for relevant files and context (if not already provided)
+2. Use Task tool with subagent_type 'jira' to verify Jira ticket information (or ask user to create/provide ticket)
+3. Perform targeted initial research on user-specified files
+4. Consult relevant sub-agents with research context (run in parallel when possible)
+5. Create high-level strategic implementation plan
+6. Iterate with user feedback
+7. Suggest user runs '/air-record' command to save the plan to Jira ticket
 
 STEP 2: EXECUTE EACH TASK IN ORDER
 Work through each task in the todo list sequentially:
@@ -22,7 +20,16 @@ Work through each task in the todo list sequentially:
 - Mark each task as 'completed' when finished
 - Continue until all tasks are done
 
-IMPORTANT: Always delegate Jira operations to the 'jira' sub-agent using Task tool with subagent_type 'jira'.
+IMPORTANT CONTEXT-SHARING PROTOCOL:
+- When consulting sub-agents, explicitly provide: files already searched, files already read, key findings, and specific focus area
+- This prevents sub-agents from duplicating research work
+
+IMPORTANT PLAN CONSTRAINTS:
+- Focus on strategic, high-level implementation guidance
+- NO rollout plans, effort estimates, or exhaustive code implementations
+- Small code examples (5-10 lines) are OK to illustrate concepts
+
+User specified relevant files/areas: #{$USER_FILES || '[User will specify]'}
 
-#{$ARGUMENTS.nil? || $ARGUMENTS.empty? ? 'Ask the user to provide a Jira ticket or create a comprehensive implementation plan.' : "Plan for Jira ticket: $ARGUMENTS"}"
+#{$ARGUMENTS.nil? || $ARGUMENTS.empty? ? 'Ask the user to provide a Jira ticket or task description.' : "Plan for Jira ticket: $ARGUMENTS"}"
 ) %>

data/lib/aircana/templates/commands/review.erb

@@ -0,0 +1,14 @@
+<%= helpers.model_instructions(
+    "Use the Task tool with subagent_type 'reviewer' to conduct an adversarial code review of the HEAD commit.
+
+The reviewer agent will:
+1. Get HEAD commit details and changes
+2. Analyze changed files to identify technical domains
+3. Use the sub-agent-coordinator to select relevant expert agents
+4. Present changes to experts in parallel for review
+5. Synthesize feedback organized by severity
+6. Store review output for the apply-feedback command
+7. Suggest running '/air-apply-feedback' to apply recommended changes
+
+IMPORTANT: The review agent will automatically review the HEAD commit. No arguments needed."
+) %>

data/lib/aircana/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Aircana
-  VERSION = "1.6.0.rc1"
+  VERSION = "2.0.0.rc2"
 end

data/lib/aircana.rb

@@ -37,8 +37,6 @@ module Aircana
     def initialize!
       return if @initialized
 
-      create_dir_if_needed(configuration.relevant_project_files_dir)
-
       @initialized = true
     end
 

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: aircana
 version: !ruby/object:Gem::Version
-  version: 1.6.0.rc1
+  version: 2.0.0.rc2
 platform: ruby
 authors:
 - Weston Dransfield
 bindir: exe
 cert_chain: []
-date: 2025-09-29 00:00:00.000000000 Z
+date: 2025-09-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: httparty
@@ -118,15 +118,11 @@ files:
 - lib/aircana.rb
 - lib/aircana/cli.rb
 - lib/aircana/cli/app.rb
-- lib/aircana/cli/commands/add_directory.rb
-- lib/aircana/cli/commands/add_files.rb
 - lib/aircana/cli/commands/agents.rb
-- lib/aircana/cli/commands/clear_files.rb
 - lib/aircana/cli/commands/doctor.rb
 - lib/aircana/cli/commands/doctor_checks.rb
 - lib/aircana/cli/commands/doctor_helpers.rb
 - lib/aircana/cli/commands/dump_context.rb
-- lib/aircana/cli/commands/files.rb
 - lib/aircana/cli/commands/generate.rb
 - lib/aircana/cli/commands/hooks.rb
 - lib/aircana/cli/commands/install.rb
@@ -142,20 +138,20 @@ files:
 - lib/aircana/contexts/confluence_setup.rb
 - lib/aircana/contexts/local.rb
 - lib/aircana/contexts/manifest.rb
-- lib/aircana/contexts/relevant_files.rb
 - lib/aircana/contexts/web.rb
 - lib/aircana/fzf_helper.rb
 - lib/aircana/generators.rb
 - lib/aircana/generators/agents_generator.rb
+- lib/aircana/generators/apply_feedback_command_generator.rb
 - lib/aircana/generators/ask_expert_command_generator.rb
 - lib/aircana/generators/base_generator.rb
+- lib/aircana/generators/execute_command_generator.rb
 - lib/aircana/generators/helpers.rb
 - lib/aircana/generators/hooks_generator.rb
 - lib/aircana/generators/plan_command_generator.rb
 - lib/aircana/generators/project_config_generator.rb
-- lib/aircana/generators/relevant_files_command_generator.rb
-- lib/aircana/generators/relevant_files_verbose_results_generator.rb
-- lib/aircana/generators/write_plan_command_generator.rb
+- lib/aircana/generators/record_command_generator.rb
+- lib/aircana/generators/review_command_generator.rb
 - lib/aircana/human_logger.rb
 - lib/aircana/initializers.rb
 - lib/aircana/llm/claude_client.rb
@@ -163,13 +159,18 @@ files:
 - lib/aircana/symlink_manager.rb
 - lib/aircana/system_checker.rb
 - lib/aircana/templates/agents/base_agent.erb
+- lib/aircana/templates/agents/defaults/apply_feedback.erb
+- lib/aircana/templates/agents/defaults/executor.erb
 - lib/aircana/templates/agents/defaults/jira.erb
 - lib/aircana/templates/agents/defaults/planner.erb
+- lib/aircana/templates/agents/defaults/reviewer.erb
 - lib/aircana/templates/agents/defaults/sub-agent-coordinator.erb
-- lib/aircana/templates/commands/add_relevant_files.erb
+- lib/aircana/templates/commands/apply_feedback.erb
 - lib/aircana/templates/commands/ask_expert.erb
+- lib/aircana/templates/commands/execute.erb
 - lib/aircana/templates/commands/plan.erb
-- lib/aircana/templates/commands/write_plan.erb
+- lib/aircana/templates/commands/record.erb
+- lib/aircana/templates/commands/review.erb
 - lib/aircana/templates/hooks/bundle_install.erb
 - lib/aircana/templates/hooks/notification_sqs.erb
 - lib/aircana/templates/hooks/post_tool_use.erb
@@ -178,7 +179,6 @@ files:
 - lib/aircana/templates/hooks/rubocop_pre_commit.erb
 - lib/aircana/templates/hooks/session_start.erb
 - lib/aircana/templates/hooks/user_prompt_submit.erb
-- lib/aircana/templates/relevant_files_verbose_results.erb
 - lib/aircana/version.rb
 - sig/aircana.rbs
 homepage: https://github.com/westonkd/aircana

data/lib/aircana/cli/commands/add_directory.rb

@@ -1,148 +0,0 @@
-# frozen_string_literal: true
-
-require "tty-prompt"
-require_relative "../../contexts/relevant_files"
-
-module Aircana
-  module CLI
-    module AddDirectory
-      class << self
-        def run(directory_path)
-          return unless directory_valid?(directory_path)
-
-          selected_files = collect_files_recursively(directory_path)
-          return log_no_files_found(directory_path) if selected_files.empty?
-
-          return unless confirm_large_operation?(selected_files.size, directory_path)
-
-          process_files(directory_path, selected_files)
-        end
-
-        private
-
-        def directory_valid?(directory_path)
-          unless File.directory?(directory_path)
-            Aircana.human_logger.error "Directory not found: #{directory_path}"
-            return false
-          end
-
-          unless File.readable?(directory_path)
-            Aircana.human_logger.error "Directory not readable: #{directory_path}"
-            return false
-          end
-
-          true
-        end
-
-        def log_no_files_found(directory_path)
-          Aircana.human_logger.info "No files found in directory: #{directory_path}"
-        end
-
-        def confirm_large_operation?(file_count, directory_path)
-          return true if file_count <= 50
-
-          show_large_operation_warning(file_count, directory_path)
-          TTY::Prompt.new.yes?("Continue with adding #{file_count} files?")
-        end
-
-        def show_large_operation_warning(file_count, directory_path)
-          estimated_size = estimate_total_size(directory_path, file_count)
-          Aircana.human_logger.warn "Large directory operation detected:"
-          Aircana.human_logger.info "  Directory: #{directory_path}"
-          Aircana.human_logger.info "  Files: #{file_count}"
-          Aircana.human_logger.info "  Estimated size: #{estimated_size}"
-          Aircana.human_logger.warn "  This may result in high token usage with Claude"
-        end
-
-        def estimate_total_size(directory_path, file_count)
-          sample_files = get_sample_files(directory_path, file_count)
-          return "Unknown" if sample_files.empty?
-
-          total_bytes = calculate_sample_size(sample_files)
-          estimated_total = extrapolate_total_size(total_bytes, sample_files.size, file_count)
-          format_file_size(estimated_total)
-        end
-
-        def get_sample_files(directory_path, file_count)
-          Dir.glob(File.join(directory_path, "**", "*"))
-             .reject { |f| File.directory?(f) }
-             .sample([file_count, 10].min)
-        end
-
-        def calculate_sample_size(sample_files)
-          sample_files.sum do |f|
-            File.size(f)
-          rescue StandardError
-            0
-          end
-        end
-
-        def extrapolate_total_size(total_bytes, sample_size, file_count)
-          avg_size = total_bytes / sample_size.to_f
-          (avg_size * file_count).to_i
-        end
-
-        def format_file_size(bytes)
-          units = %w[B KB MB GB]
-          size = bytes.to_f
-          unit_index = 0
-
-          while size >= 1024 && unit_index < units.length - 1
-            size /= 1024
-            unit_index += 1
-          end
-
-          "#{size.round(1)} #{units[unit_index]}"
-        end
-
-        def process_files(directory_path, selected_files)
-          file_count = selected_files.length
-          Aircana.human_logger.info "Found #{file_count} files in directory: #{directory_path}"
-
-          ProgressTracker.with_spinner("Adding #{file_count} files to context") do
-            Contexts::RelevantFiles.add(selected_files)
-          end
-
-          Aircana.human_logger.success "Successfully added #{file_count} files from directory"
-        end
-
-        def log_token_warning(file_count)
-          Aircana.human_logger.warn "Large number of files (#{file_count}) may result in high token usage"
-        end
-
-        def collect_files_recursively(directory_path)
-          Dir.glob(File.join(directory_path, "**", "*"), File::FNM_DOTMATCH)
-             .reject { |path| File.directory?(path) }
-             .reject { |path| should_ignore_file?(path) }
-        end
-
-        def should_ignore_file?(file_path)
-          ignore_patterns.any? { |pattern| file_path.match?(pattern) }
-        end
-
-        def ignore_patterns
-          directory_patterns + file_patterns
-        end
-
-        def directory_patterns
-          [
-            %r{/\.git/}, %r{/node_modules/}, %r{/\.vscode/}, %r{/\.idea/},
-            %r{/coverage/}, %r{/dist/}, %r{/build/}, %r{/tmp/}, %r{/vendor/},
-            %r{/\.bundle/}, %r{/\.rvm/}, %r{/\.rbenv/}
-          ]
-        end
-
-        def file_patterns
-          [
-            %r{/\.DS_Store$}, %r{/log/.*\.log$},
-            /\.(jpg|jpeg|png|gif|bmp|tiff|svg|ico|webp)$/i,
-            /\.(mp4|avi|mkv|mov|wmv|flv|webm)$/i,
-            /\.(mp3|wav|flac|aac|ogg)$/i,
-            /\.(zip|tar|gz|rar|7z|bz2)$/i,
-            /\.(exe|dll|so|dylib)$/i
-          ]
-        end
-      end
-    end
-  end
-end

data/lib/aircana/cli/commands/add_files.rb

@@ -1,26 +0,0 @@
-# frozen_string_literal: true
-
-require_relative "../shell_command"
-require_relative "../../contexts/relevant_files"
-
-module Aircana
-  module CLI
-    module AddFiles
-      class << self
-        def run
-          selected_files = FzfHelper.select_files_interactively(
-            header: "Select files for Claude context (Ctrl+A: select all, ?: toggle preview)"
-          )
-
-          if selected_files.empty?
-            Aircana.human_logger.info "No files selected. Exiting."
-            return
-          end
-
-          Aircana.human_logger.success "Selected #{selected_files.size} files for context"
-          Contexts::RelevantFiles.add(selected_files)
-        end
-      end
-    end
-  end
-end

data/lib/aircana/cli/commands/clear_files.rb

@@ -1,16 +0,0 @@
-# frozen_string_literal: true
-
-require_relative "../shell_command"
-require_relative "../../contexts/relevant_files"
-
-module Aircana
-  module CLI
-    module ClearFiles
-      class << self
-        def run
-          Contexts::RelevantFiles.remove_all
-        end
-      end
-    end
-  end
-end

data/lib/aircana/cli/commands/files.rb

@@ -1,65 +0,0 @@
-# frozen_string_literal: true
-
-require_relative "add_files"
-require_relative "add_directory"
-require_relative "clear_files"
-require_relative "../../contexts/relevant_files"
-
-module Aircana
-  module CLI
-    module Files
-      class << self
-        def add
-          AddFiles.run
-        end
-
-        def add_dir(directory_path)
-          AddDirectory.run(directory_path)
-        end
-
-        def clear
-          ClearFiles.run
-        end
-
-        def list
-          relevant_files_dir = Aircana.configuration.relevant_project_files_dir
-          return print_no_directory_message unless Dir.exist?(relevant_files_dir)
-
-          files = get_tracked_files(relevant_files_dir)
-          return print_no_files_message if files.empty?
-
-          print_files_list(files)
-        end
-
-        private
-
-        def print_no_directory_message
-          Aircana.human_logger.info(
-            "No relevant files directory found. Use 'aircana files add' to start tracking files."
-          )
-        end
-
-        def print_no_files_message
-          Aircana.human_logger.info("No relevant files currently tracked.")
-        end
-
-        def get_tracked_files(relevant_files_dir)
-          Dir.glob("#{relevant_files_dir}/*").map do |link|
-            File.readlink(link)
-          rescue StandardError
-            link
-          end
-        end
-
-        def print_files_list(files)
-          Aircana.human_logger.info("Current relevant files:")
-          files.each_with_index do |file, index|
-            relative_path = file.start_with?(Dir.pwd) ? file.gsub("#{Dir.pwd}/", "") : file
-            Aircana.human_logger.info("  #{index + 1}. #{relative_path}")
-          end
-          Aircana.human_logger.info("\nTotal: #{files.length} files")
-        end
-      end
-    end
-  end
-end