2.9 KiB
HANDOFF
What this project is
reply-end-controls is a Telegram-only interaction-control feature.
Its purpose is to add reply-end buttons to assistant replies:
A. 繼續B. 就這樣吧,不需要額外處理
The buttons are meant to:
- capture user intent about whether a conversation should continue
- persist that choice
- influence later assistant behavior
What already works
In openclawtest, the Telegram + OpenClaw PoC has already proven:
- buttons can be attached to assistant replies
- button clicks can be received as callback queries
- callback state can be persisted
- button UI can update
- acknowledgement replies can be sent
- stop/continue can influence later behavior
What environment this currently targets
- Telegram only
- OpenClaw runtime in
openclawtest
This is not yet a clean cross-agent installable package. It is a successful PoC being pushed toward a cleaner reusable path.
Preferred integration seam now
When extending the project, prefer the repo-side OpenClaw adapter path over directly expanding runtime patch logic.
Current preferred seam:
src/adapters/openclaw-plugin-skeleton.tssrc/adapters/openclaw-interactive-handler.tssrc/adapters/openclaw-message-tool.tssrc/adapters/openclaw-state-file.ts
Where to start reading
Read these files first:
INSTALL.mdREADME.mdtelegram-v1-design.mdtelegram-openclaw-poc-plan.mdreports/telegram-openclaw-poc-success.mdreports/openclaw-patch-inventory.mdreports/openclaw-patch-mapping-matrix.mdreports/next-phase-implementation-plan.mdreports/agent-consumable-minimum.md
Fastest operational entrypoints
For another engineering agent, the most useful command entrypoints are now:
bash scripts/install-openclawtest-poc.shnpm run install:openclawtestnpm run apply:openclawtestnpm run refresh:openclawtestnpm run verify:openclawtestnpm run rollback:openclawtestnpm run test
Repo structure
src/core/- reusable state/policy/callback logicsrc/telegram/- Telegram-specific helper logicsrc/adapters/- OpenClaw-facing state bridge codesrc/runtime/- runtime helper layer for current PoC behaviorscripts/- apply / rollback and helper scriptstests/- current unit testsreports/- design notes, PoC success, pluginization reports
What is still fragile
- the live OpenClaw integration still uses runtime patching
- the feature is not yet a clean installable plugin package
- acceptance still includes human verification steps on Telegram UI
If you are the next agent
Your likely next step is not to rediscover the idea.
Your likely next step is to make the current PoC easier to consume by:
- reducing runtime patching
- tightening the apply/verify/rollback path
- making the adapter seam cleaner
Important constraint
Do not mix this project with the governance project.
They are separate workstreams.