docs: add AI agent framework implementation plan#1
Merged
Conversation
16-task plan across 8 phases: SQLite memory with FTS5, platform abstraction layer, markdown skill system, agent core extraction, tokio-cron scheduler, cargo feature flags, and integration. https://claude.ai/code/session_01HCJirZ2E5csJzeo13285a1
Transform from Telegram-only chatbot into a modular AI agent framework: - memory/: SQLite-backed persistent conversations + knowledge base with hybrid vector (sqlite-vec) + FTS5 search using Reciprocal Rank Fusion. Embeddings via configurable OpenAI-compatible API with graceful FTS5-only fallback when not configured. - platform/: Platform abstraction layer with IncomingMessage types. Telegram adapter refactored from bot.rs. - agent.rs: Platform-agnostic agentic loop with memory tools (remember, recall, search_memory) exposed to the LLM. - skills/: Markdown-based skill loader. Skills are natural-language instructions injected into the system prompt at runtime. - scheduler/: Background task scheduler using tokio-cron-scheduler. - config.rs: Extended with memory, skills, and embedding sections. https://claude.ai/code/session_01HCJirZ2E5csJzeo13285a1
In rusqlite >= 0.32, execute_batch errors when statements return rows. PRAGMA journal_mode=WAL always returns the resulting mode as a result row, causing "Execute returned results - did you mean to call query?" at startup. Use query_row instead to properly handle the returned value. https://claude.ai/code/session_01HCJirZ2E5csJzeo13285a1
blocking_lock() on tokio::sync::Mutex panics when called from within an async runtime. Changed run_migrations to a static method that takes a &Connection directly, called before wrapping in Arc<Mutex<>>. https://claude.ai/code/session_01HCJirZ2E5csJzeo13285a1
…memory module - Added rustbot.db to .gitignore to prevent tracking of the database file. - Updated the model in config.example.toml to "qwen/qwen3-embedding-8b" for embedding configuration. - Enhanced README to include optional embedding configuration details. - Modified memory module to implement schema metadata for embedding dimensions and improved table creation logic for vector search.
…ules - Enhanced readability by adjusting line breaks and indentation in `agent.rs`, `main.rs`, `mcp.rs`, `tools.rs`, `memory/conversations.rs`, `memory/embeddings.rs`, `memory/knowledge.rs`, `memory/mod.rs`, `platform/mod.rs`, `platform/telegram.rs`, `scheduler/mod.rs`, `skills/loader.rs`, and `skills/mod.rs`. - Consolidated chained method calls for better clarity and maintainability. - Added `#[allow(dead_code)]` annotations to unused functions and structs to suppress warnings.
chinkan
added a commit
that referenced
this pull request
Feb 20, 2026
docs: add AI agent framework implementation plan
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
16-task plan across 8 phases: SQLite memory with FTS5, platform
abstraction layer, markdown skill system, agent core extraction,
tokio-cron scheduler, cargo feature flags, and integration.
https://claude.ai/code/session_01HCJirZ2E5csJzeo13285a1