11 Commits

Author SHA1 Message Date
76777c98eb
feat: add Matrix appservice bot and platform-agnostic conversation core
Introduce a shared ConversationService (steward/bot/core.py) that owns the
LLM call, history, knowledge-base search, and thread-memory keying behind a
normalized ThreadKey, so both Telegram and Matrix drive the same pipeline.

- Add steward/bot/matrix.py: a mautrix-python appservice bot that receives
  Synapse transactions and replies via the client-server API.
- Refactor telegram.py handlers into thin wrappers over ConversationService.
- Generalize ThreadMemoryStore/ThreadSummary to platform-scoped keys with
  legacy chat_id:thread_id migration.
- Add a matrix config section (homeserver, tokens, room/user allowlists).
- Rewrite main.py as async, starting Telegram and/or Matrix on one event loop.
- Add mautrix>=0.21.0 dependency.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-08-18 21:38:01 +10:00
Daniel
cf65198825
fix: accept CSV telegram ID config (#27)
Co-authored-by: openhands <openhands@all-hands.dev>
2026-07-27 09:21:52 +10:00
Daniel
293591e48a
feat: improve Telegram conversation heuristics (#14)
Co-authored-by: openhands <openhands@all-hands.dev>
2026-07-26 21:39:59 +10:00
Daniel
4099d4aa82
feat: add MCP tool integration via MCPO (#11) 2026-07-26 14:11:07 +10:00
Daniel Wagner
2454d3a956 fix: break long lines in conftest.py to comply with ruff E501
Lines 53-54 in tests/conftest.py exceeded 100 character limit.
Split the system prompt string across multiple lines to fix linting error.
2026-07-26 12:52:16 +10:00
Daniel Wagner
070e967833 test: update test suite for OmegaConf config system
- Add tests/conftest.py with make_settings() helper that maps legacy config
  parameter names to new nested OmegaConf structure
- Update all test files to use the conftest fixture
- All 73 tests now pass with new config system
- Maintains backward compatibility via Settings class properties

Also add AGENTS.md with comprehensive AI agent guidelines:
- Project overview and key technologies
- Directory structure reference
- Development workflow and common tasks
- Testing strategy and patterns
- CI/CD pipeline overview
- Common pitfalls and best practices
- Debugging guide for agents working on the project
2026-07-26 12:48:40 +10:00
copilot-swe-agent[bot]
76c6086db3 feat: MCP/OpenAPI tool calling support 2026-07-25 12:50:39 +00:00
copilot-swe-agent[bot]
867542dd49 feat: knowledge-base memory, Dockerfile, docker-compose, CI/release workflows, PR template 2026-07-25 12:29:21 +00:00
copilot-swe-agent[bot]
c74c8b0d8b feat: thread-aware memory with /flush and /recall commands 2026-07-25 12:09:38 +00:00
copilot-swe-agent[bot]
8759bea963 fix: address code review and CodeQL feedback in tests 2026-07-25 11:49:23 +00:00
copilot-swe-agent[bot]
6862c7d0b8 feat: add NORTH_STAR.md and MVP core loop (Telegram bot + LLM + proposal generator) 2026-07-25 11:47:52 +00:00