- Adds message_update handler that periodically edits the Zulip
placeholder with partial response text (every ~2s during streaming)
- Sends a 'Thinking...' placeholder to Zulip immediately on DM receipt
- Detects agent busy state and uses deliverAs: 'steer' so subsequent
Zulip DMs steer the conversation mid-stream (like terminal TUI)
- Adds editMessage() to the queue helper (Zulip PATCH /messages/{id})
- sendMessage() now returns the message ID for editing
- Turn_start / agent_end lifecycle tracks agent busy state
- Cleanup: streaming timer properly cleared on shutdown
- Removed spawnSync subprocess (pi -p --mode json) for Zulip DM processing
- Messages now inject directly into the current pi session via
pi.sendUserMessage(), reusing the already-hot LLM — zero cold-start
- agent_end event handler captures assistant response and relays it to Zulip
- Added pending reply queue for ordered delivery of multiple Zulip messages
- Fixed zulip-js import (CJS default export, not named createClient)
- Added types.d.ts for zulip-js with default export declaration
- Updated package.json with yaml dependency, @earendil-works/pi-coding-agent
- Config supports both nested YAML and flat env-var formats
- Removed all subprocess timeout/buffer error paths (no longer needed)
- docs/GITOPS.md: complete workflow from prototype to production
- .gitea/pull_request_template.md: pre-merge checklist for swarm PR review
- scripts/deploy.sh: tag-based deployment to all 6 CTs with health checks
- scripts/rollback.sh: rollback to previous tag
- .gitea/workflows/ci.yml: CI pipeline (activates when Actions runners available)
- .gitignore: prevent config.yaml and secrets from being committed
- .gitattributes: consistent LF line endings across platforms
Abiba (pi)
jerome