0.35.0

What's Changed

Added

• New ai-devkit agent console command that launches a live multi-agent terminal UI (TUI) with an agent list pane, conversation preview, chat input, and status footer for monitoring and interacting with multiple running agents simultaneously by @codeaholicguy in #88

Changed

• Converted all packages (cli, agent-manager, channel-connector, memory) from CommonJS to ES Modules, migrated the test runner from Jest to Vitest, and upgraded project dependencies by @codeaholicguy in #87
• Tightened the clarification requirements in the dev-lifecycle skill's SKILL.md and updated new-requirement, review-design, and review-requirements references; improved the check-status.sh script.

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.34.0...cli@0.35.0

0.34.0

What's changed

Added

• Added ai-devkit docs init-feature <name> to initialize date-prefixed feature docs for configured phases using the current local date, with optional --json output for agents and scripts.
• Added lint support for date-prefixed feature docs while preserving compatibility with legacy feature-{name}.md docs.

Changed

• Updated lifecycle command templates and the dev-lifecycle skill to initialize feature docs through docs init-feature and reference latest matching YYYY-MM-DD-feature-{name}.md docs.

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.33.0...cli@0.34.0

0.33.0

What's Changed

Added

• ai-devkit agent session detail now shows detailed historical session information and conversation history, with --json, --type, --full, --tail, and --verbose options.
• ai-devkit channel connect telegram --name <name> now supports multiple named Telegram channel configurations, including duplicate-token protection and persisted authorized chat IDs #84 by @codeaholicguy
• ai-devkit channel start <name> --agent <name> --daemon can run channel bridges in the background, with bridge process tracking, log paths, status reporting, and ai-devkit channel stop [name] support #85 by @codeaholicguy

Changed

• ai-devkit channel list and ai-devkit channel status now show authorization and live bridge state for configured channels.

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.32.0...cli@0.33.0

0.32.0

What's changed

Added

• ai-devkit agent send --wait now supports --stdin and piped input, allowing automation scripts to pass prompts without a positional message argument.
• ai-devkit agent send --wait now supports --timeout <milliseconds> to configure the maximum wait time for an agent response.
• ai-devkit agent send --wait --json now emits structured JSON with target metadata, the prompt, captured response messages, elapsed time, and final status.
• Added documentation and FAQ content for automating programmatic agent calls with agent send --wait.

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.31.0...cli@0.32.0

0.31.0

What's Changed

Added

• feat(cli): add wait mode to agent send by @codeaholicguy in #83

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.30.0...cli@0.31.0

0.30.0

What's Changed

Added

• feat(agent-manager): add OpenCode adapter for agent control by @nothingrotf in #82
• The document-code skill now offers an HTML artifact alongside its markdown output.

Fixed

• agent-manager now prefers the PID-file live status when resolving Claude Code agent state, improving accuracy of agent list output.
• agent-manager now matches Claude Code's lossy project directory encoding when resolving session paths, fixing session discovery for paths that Claude Code re-encodes.

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.29.0...cli@0.30.0

0.29.0

What's changed

Added

• ai-devkit init now accepts -y, --yes to run without prompts (required for agent/CI contexts where stdin is not a TTY).
• channel-connector's Telegram adapter now renders Markdown to Telegram-flavored HTML with an automatic plain-text fallback when Telegram rejects the formatted payload.
• The channel command now surfaces polling-loop errors and emits diagnostic logs to help debug long-running channel sessions.

Changed

• The dev-lifecycle skill's prerequisite step now invokes ai-devkit init -a -e claude --built-in --yes so agents (e.g., OpenCode in a fresh worktree) cannot block on interactive prompts when .ai-devkit.json is missing.
• The debug skill has been renamed to structured-debug across the registry, templates, and docs to clarify its purpose.
• The capture-knowledge skill has been renamed to document-code across the registry, templates, and docs to better reflect its purpose.
• Updated the CLI's built-in skill list to reflect the structured-debug and document-code renames.

Fixed

• agent-manager now matches resumed Claude Code sessions by parsing the --resume <uuid> argument, fixing detection of sessions started via claude --resume.

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.28.0...cli@0.29.0

0.28.0

What's Changed

Added

• Add agent sessions command to list historical sessions by @codeaholicguy in #79
• Added new security-review skill for security-focused review workflows.
• Added Playwright CLI entry to the skills registry.
• Added Google skills repository to registry.json.

Changed

• agent-manager now strips the Claude Code tag from session output.
• Improved the dev-lifecycle skill's execute phase guidance.
• Updated branding across CLI command templates, command files, and skills.

Fixed

• Added an AppleScript escape utility in agent-manager to handle quoting safely.
• Switched agent-manager session finding to use native fs instead of shelling out via exec.

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.27.0...cli@0.28.0

0.27.0

What's Changed

Fixed

• fix(security): validate FEATURE arg in check-status.sh to prevent path traversal by @xiaolai in #66
• fixed execAsync calls to use array arguments instead of string interpolation, preventing potential shell injection.

Changed

• Split SkillManager into dedicated SkillIndex and SkillRegistry modules for better separation of concerns.
• Extracted session parsing logic from ClaudeCodeAdapter into a standalone ClaudeSessionParser utility.
• Added withErrorHandler utility for consistent error handling across CLI commands (agent, channel, memory, skill).
• Added getAdapter() method to AgentManager, reducing adapter resolution duplication in CLI commands.
• Updated all try-catch blocks to use unknown error type for type safety.
• Renamed environment code references for consistency across CLI (init, Config, EnvironmentSelector, TemplateManager).
• Removed stray console.log statements, cleaned up tests, and added .editorconfig.

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.26.0...cli@0.27.0

0.26.0

What's Changed

Added

• Added GeminiCliAdapter to the agent manager so ai-devkit agent list and ai-devkit agent detail can discover and inspect running Gemini CLI sessions, with process detection, session discovery via projectHash matching, and content normalization for Gemini's polymorphic message format. By @nnhhoang in #70.
• Added GeminiCliAdapter to the channel command for Gemini CLI channel operations.

Fixed

• Hardened git utility functions against shell injection.
• Added validation for skill paths to prevent invalid path traversal in SkillManager.

Changed

• Cleaned up duplicate command templates (capture-knowledge, debug, simplify-implementation) from both root commands/ and packages/cli/templates/commands/.

Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.25.0...cli@0.26.0