Add Coding Agent Runner community ability#118
Add Coding Agent Runner community ability#118Ju-usc wants to merge 15 commits intoopenhome-dev:devfrom
Conversation
Introduce a WebUI-compatible ability that relays coding tasks to a Codex webhook with confirmation/cancel flow and conversational summaries. Document setup, trigger words, and a minimal Codex-focused /run webhook contract for contributors.
Replace explicit register_capability boilerplate with the template register tag and remove raw open() usage so the ability matches updated validation requirements.
🔀 Branch Merge CheckPR direction: ✅ Passed — |
✅ Ability Validation Passed |
🔍 Lint Results🔧 Auto-formattedSome files were automatically cleaned and formatted with
✅
|
There was a problem hiding this comment.
Pull request overview
This PR adds a new community ability called "Codex Task Runner" that enables voice-triggered execution of coding tasks via an external webhook. The ability implements a confirmation flow before executing tasks, provides conversational spoken summaries of results, and uses placeholder-based webhook configuration for easy deployment.
Changes:
- New voice-controlled ability for remote Codex task execution with confirmation flow and spoken results
- Comprehensive documentation including setup instructions, webhook API contract, and example server implementation
- Configuration via inline constants (WEBHOOK_URL, WEBHOOK_TOKEN) for WebUI-friendly setup
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 6 comments.
| File | Description |
|---|---|
| community/codex-task-runner/main.py | Core ability implementation with conversation flow, webhook calls, and summary generation |
| community/codex-task-runner/README.md | Setup documentation and example webhook server implementation |
| community/codex-task-runner/init.py | Empty package initialization file (standard Python package structure) |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
- Rename folder, class, log tag, and voice prompts to be agent-agnostic - Add _refine_prompt to clean up STT transcription before sending to agent - README shows Claude Code and Codex equally with unified webhook example - End-to-end tested via OpenHome + ngrok + Claude Code webhook
|
@codermohsin Thanks for catching that! I've refactored the ability and fixed the register tag issue:
Let me know if anything else breaks. |
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Juyoung Lee <112113286+Ju-usc@users.noreply.github.com>

Summary
codex-task-runner→coding-agent-runner— works with both Claude Code and Codex_refine_promptcleans up STT transcription before sending to the coding agent_rewrite_for_voicecondenses verbose agent output into 1-2 spoken sentencesValidation
python3 -m py_compile community/coding-agent-runner/main.pypython3 validate_ability.py community/coding-agent-runner