Conversation
SessionManager.ts was deleted but its entry remained in CODEBASE.md. Also corrected CLAUDE.md: memory starter files (facts.md etc.) do not exist as templates — ADK MemoryService creates them automatically. Removed outdated Known Issues entry about memoryTools.ts. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Delete buildSystemPromptWithSkills() — skill prompt building is done inline in agent.ts; function was unused - Refactor addInstalledSkill/removeInstalledSkill to use updateConfig() instead of manual readFileSync/JSON.parse/writeFileSync blocks - Replace hardcoded test prompt in src/index.ts with a brief message directing users to `adk-claw chat` or `adk-claw start` Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Moves the model list out of init.ts into src/lib/models.ts so the upcoming config command can reuse it without duplication. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- chat: interactive terminal loop with /help, /new, /exit slash commands - config show: prints current config with secrets masked (last 4 chars) - config set model|api-key|bot-token: interactive update via prompts - doctor: 11 health checks (config, workspace, API key formats, Telegram and OpenRouter connectivity); exits 1 on critical failures - Update splash screen with the three new commands - Fix Docs URL (was same as GitHub; now points to #readme anchor) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Summary of ChangesHello @MarvelNwachukwu, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request focuses on enhancing the ADK Claw CLI with new commands for interacting with the agent, managing configuration, and running health checks. It also includes some codebase refactoring to improve maintainability and remove unused code. The new CLI commands provide a more user-friendly way to interact with the ADK Claw agent and manage its configuration. Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request significantly enhances the CLI by introducing chat, config, and doctor commands, which greatly improve the project's usability and manageability. The refactoring to centralize configuration logic and model definitions is also a welcome improvement for maintainability. I've identified a critical issue regarding a missing import that would cause a runtime crash, along with several suggestions to improve code quality and consistency, including adjusting the severity of two critical health checks. Please also note that the printHelp function in src/cli/index.ts should be updated to include the new commands, though this was outside the changed lines of the diff.
| const args = process.argv.slice(2); | ||
| const command = args[0]; | ||
|
|
||
| const LOGO = ` |
There was a problem hiding this comment.
The LOGO and printSplash function use pc from picocolors and a VERSION constant, but they are not imported or defined in this file. This will cause a ReferenceError at runtime.
Please add the necessary imports at the top of the file, for example:
import pc from 'picocolors';
// And the import for VERSION if it's not globally available.| check( | ||
| "Telegram API reachable", | ||
| json.ok === true, | ||
| false, |
There was a problem hiding this comment.
The health check for Telegram API reachability is marked as non-critical. Since the agent cannot function without being able to communicate with Telegram, this should be considered a critical failure.
| false, | |
| true, |
| check( | ||
| "OpenRouter API reachable", | ||
| res.ok, | ||
| false, |
There was a problem hiding this comment.
Similar to the Telegram check, the agent's ability to reach the OpenRouter API is essential for its core functionality. This check should be marked as critical.
| false, | |
| true, |
| function printSplash() { | ||
| console.log(LOGO); | ||
| console.log(); | ||
| console.log( | ||
| pc.dim(" Personal AI assistant with memory, Telegram & skills."), | ||
| ); | ||
| console.log(); | ||
| console.log(pc.dim(` v${VERSION}`)); | ||
| console.log(); | ||
| console.log(` ${pc.magenta("init")} Create a new ADK Claw project`); | ||
| console.log(` ${pc.magenta("start")} Start the AI agent`); | ||
| console.log( | ||
| ` ${pc.magenta("chat")} Chat with the agent in your terminal`, | ||
| ); | ||
| console.log(` ${pc.magenta("config")} View and update configuration`); | ||
| console.log(` ${pc.magenta("doctor")} Run health checks`); | ||
| console.log(` ${pc.magenta("skill")} Manage agent skills`); | ||
| console.log(` ${pc.magenta("service")} Manage the systemd user service`); | ||
| console.log(` ${pc.magenta("pairing")} Manage Telegram user pairing`); | ||
| console.log(); | ||
| console.log(pc.dim(` Docs: https://github.com/IQAIcom/adk-claw#readme`)); | ||
| console.log(pc.dim(` GitHub: https://github.com/IQAIcom/adk-claw`)); | ||
| console.log(); | ||
| } |
There was a problem hiding this comment.
The printSplash function is defined but never called. It provides a great overview of the available commands and seems intended as the default view when the CLI is run without arguments. Consider calling this function from main() when no command is provided to improve the user's first experience.
| if (!existsSync(CONFIG_PATH)) { | ||
| p.log.error("ADK Claw is not initialized. Run 'adk-claw init' first."); | ||
| process.exit(1); | ||
| } |
There was a problem hiding this comment.
This logic to check for the existence of config.json is repeated in several of the new CLI command files (e.g., chat.ts, config.ts). To improve maintainability and reduce duplication, consider extracting this into a shared utility function.
For example, you could create a function ensureConfigExists() in a shared utility file:
// in a shared lib/cli-utils.ts file
import { existsSync } from 'node:fs';
import { join } from 'node:path';
import * as p from '@clack/prompts';
export function ensureConfigExists() {
const CONFIG_PATH = join(process.cwd(), '.adk-claw', 'config.json');
if (!existsSync(CONFIG_PATH)) {
p.log.error("ADK Claw is not initialized. Run 'adk-claw init' first.");
process.exit(1);
}
}Then you can just call ensureConfigExists() at the start of each command function that requires it.
1 participant
This pull request focuses on enhancing the ADK Claw CLI with new commands for interacting with the agent, managing configuration, and running health checks. It also includes some codebase refactoring to improve maintainability and remove unused code. The new CLI commands provide a more user-friendly way to interact with the ADK Claw agent and manage its configuration.
Highlights
CLI Enhancements: This PR introduces new CLI commands for interacting with the ADK Claw agent, including a chat interface, configuration management, and health checks.
Configuration Management: The config command allows users to view and update the ADK Claw configuration, including the AI model, API key, and Telegram bot token.
Health Checks: The doctor command runs health checks on the ADK Claw configuration, verifying the existence of required files, the validity of the configuration, and the reachability of external APIs.
Codebase Refactoring: This PR refactors the codebase to improve maintainability and remove unused code, such as the SessionManager service.