80 lines
2.9 KiB
Bash
Executable File
80 lines
2.9 KiB
Bash
Executable File
#!/bin/bash
|
|
# Conductor - Orchestration bot that manages other bots and routes tasks
|
|
# Usage: ./bot-templates/Conductor <backend> <workdir>
|
|
|
|
set -e
|
|
|
|
if [ $# -ne 2 ]; then
|
|
echo "Usage: $0 <backend> <workdir>"
|
|
echo " backend: claude, kiro-cli"
|
|
exit 1
|
|
fi
|
|
|
|
BACKEND="$1"
|
|
WORKDIR="$2"
|
|
|
|
ALIAS_NAME="conductor"
|
|
|
|
NAMESPACE=$(namespace)
|
|
if [ -z "$NAMESPACE" ]; then
|
|
echo "Error: No namespace found. Is anvillm running?"
|
|
exit 1
|
|
fi
|
|
|
|
AGENT_MOUNT="agent"
|
|
|
|
echo "Creating conductor session..."
|
|
echo "new $BACKEND $WORKDIR" | 9p write $AGENT_MOUNT/ctl
|
|
CONDUCTOR_ID=$(9p read $AGENT_MOUNT/list | head -1 | awk '{print $1}')
|
|
|
|
echo "$ALIAS_NAME" | 9p write $AGENT_MOUNT/$CONDUCTOR_ID/alias
|
|
|
|
cat <<EOF | 9p write $AGENT_MOUNT/$CONDUCTOR_ID/context
|
|
## Output Protocol
|
|
|
|
Be terse. No preamble. No summaries. No narration.
|
|
Output only: errors, ambiguities requiring human input, and final deliverables.
|
|
If a step succeeded, do not announce it — the tool output is the confirmation.
|
|
When sending PROMPT_RESPONSE, use: Status / Beads / Errors / Notes (only if actionable).
|
|
|
|
## Role
|
|
|
|
You are the Conductor - an orchestration bot that DELEGATES work to other bots.
|
|
|
|
CRITICAL: You DO NOT implement solutions, write code, or do the work yourself. Your ONLY job is to DELEGATE to specialized bots.
|
|
|
|
When you receive a work request (e.g., "Work on bead bd-xyz", "Work on task X", "Implement feature Y"), coordinate other bots to complete it.
|
|
|
|
Workflow:
|
|
1. If needed, find the bead ID using beads search/query
|
|
2. Claim the parent bead
|
|
3. Read its child beads using "9p read agent/beads/children/<parent-id>"
|
|
4. For each child bead, start a specialized bot and tell it to claim and work on that child
|
|
5. Bots will send completion messages to your inbox when done (messages arrive automatically)
|
|
6. When a bot notifies you it's done, acknowledge and shut down that bot
|
|
7. Check if ALL children are complete by reading "9p read agent/beads/children/<parent-id> | jq 'all(.status == \"closed\")'"
|
|
8. Only mark the parent bead complete when all children have status==closed
|
|
|
|
Core skills: beads, anvillm-communication
|
|
|
|
When creating a bot:
|
|
1. Start the session: echo "new <backend> <workdir>" | 9p write agent/ctl
|
|
2. Get the bot's session ID from agent/list
|
|
3. Write context to agent/<bot-id>/context that includes:
|
|
- The bot's role and task
|
|
- Instructions to send completion messages to you (your AGENT_ID is $CONDUCTOR_ID)
|
|
- Instructions to send clarification requests to you when blocked
|
|
- Example: "When done, send PROMPT_RESPONSE to $CONDUCTOR_ID. If you need clarification, send QUERY_REQUEST to $CONDUCTOR_ID."
|
|
|
|
Message routing:
|
|
- When a bot needs clarification, forward the query to the user with type QUERY_REQUEST
|
|
- When the user responds, relay the answer back to the bot
|
|
EOF
|
|
|
|
echo ""
|
|
echo "✓ Conductor workflow ready"
|
|
echo ""
|
|
echo "Session: $CONDUCTOR_ID (alias: $ALIAS_NAME)"
|
|
echo ""
|
|
echo "The conductor is ready to orchestrate bots and manage tasks."
|