@inureyes

Overview

Implement advanced tab completion capabilities for bssh's interactive mode, including remote path completion, command completion based on remote $PATH, and history-based completion suggestions. This will significantly improve the user experience by providing context-aware autocompletion similar to modern shells.

Technical Approach

Architecture Design

The implementation will use rustyline's built-in completion framework with custom completers that leverage SSH channels to fetch remote information. We'll implement a multi-tiered completion system:

1. Completion Engine Architecture

   • Create a composite completer that delegates to specialized completers based on context
   • Cache remote data to minimize SSH round-trips
   • Implement async completion fetching with timeout handling
   • Use a priority system: history > remote paths > remote commands

2. Data Caching Strategy

   • Cache remote $PATH directories and executables for 5 minutes
   • Cache recently accessed directory listings for 1 minute
   • Maintain a sliding window of command history (last 1000 commands)
   • Implement cache invalidation on directory changes

3. Context Detection

   • Parse current command line to determine completion context
   • Detect if completing a command, path, or argument
   • Handle special characters and escape sequences
   • Support both absolute and relative path completion

Key Features

• Tab completion for remote paths with <100ms latency (cached)
• Command completion includes all executables in remote $PATH
• History-based suggestions appear within 50ms
• Completion works correctly across node switches
• Cache persists between sessions

Implementation Phases

Phase 1: Foundation and Architecture

• Create completion module structure at src/completion/mod.rs
• Implement context parser at src/completion/parser.rs
• Create cache manager at src/completion/cache.rs
• Implement SSH data fetcher at src/completion/remote_fetcher.rs

Phase 2: Core Completion Implementations

• Implement remote path completer at src/completion/path_completer.rs
• Implement remote command completer at src/completion/command_completer.rs
• Implement history-based completer at src/completion/history_completer.rs
• Create composite completer at src/completion/composite_completer.rs

Phase 3: Integration with Interactive Mode

• Extend InteractiveCommand to use custom completer
• Add completion configuration to InteractiveConfig
• Implement async completion updates
• Add multi-node completion support

Phase 4: Advanced Features and Optimization

• Implement smart completion features (git, docker, kubectl argument completion)
• Add visual completion enhancements (color-coding, hints, preview)
• Optimize performance (incremental updates, bloom filters, batching)
• Add completion debugging and metrics

Phase 5: Testing & Polish

• Write comprehensive unit tests
• Add integration tests
• Update documentation
• Polish user experience

Dependencies

External Dependencies

• rustyline = "17.0" - Already present, provides completion framework
• Consider adding fuzzy-matcher = "0.3" for fuzzy history matching
• Consider adding lru = "0.12" for LRU cache implementation
• May need shellexpand = "3.1" for path expansion

Internal Dependencies

• Existing SSH client implementation (src/ssh/tokio_client/)
• Existing interactive mode infrastructure (src/commands/interactive.rs)
• Configuration system (src/config.rs)
• Node session management

Success Criteria

Functional Requirements

• Tab completion works for remote paths with <100ms latency (cached)
• Command completion includes all executables in remote $PATH
• History-based suggestions appear within 50ms
• Completion works correctly across node switches
• Cache persists between sessions

Performance Benchmarks

• Initial PATH scan completes within 2 seconds
• Subsequent completions served from cache in <10ms
• Memory usage for caches stays under 50MB
• No blocking of interactive input during completion
• Support for directories with 10,000+ files

User Experience

• Completion feels as responsive as local shell
• Clear visual feedback for completion types
• Intuitive behavior matching user expectations
• Graceful handling of network issues
• Consistent behavior across all nodes

Related Work

• Original task document: .claude/tasks/todo/1_enhanced_tab_completion.md