docs: SSE + metadata + multi-agent routing examples#12
Merged
Conversation
Bug: src/mcp-server.mjs:287 called startConfirmationsServer without wakeScript, so POST /wake on the in-process daemon returned 503 "wake disabled". Standalone bin/iak-mcp-daemon.mjs already wired it. Adds three-key fallback: config.poller.wake_script, then config.poller.nudge_command, then config.wake.script_path. Also wires the macbook.json side: - poller.wake_script -> scripts/claudemb-wake.sh - mcp.remote_agents.@claudemm + mcp.confirmations.peers point at the mini's Tailscale IP 100.97.140.13:8788 - listen.host bound to my Tailscale IP 100.99.150.81 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@claudemm and I patched the same wakeScript bug from two ends and landed on different config keys. Aligning per claudemm's proposal on mcp.confirmations.wake_script (matches where the daemon's other config already lives). Keeping legacy fallbacks (poller.wake_script, poller.nudge_command, wake.script_path) so existing configs keep working. config/macbook.json: removed redundant poller.wake_script entry that my earlier commit added; canonical mcp.confirmations.wake_script is already set under the mcp block. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
README.md: add a "Multi-agent routing (the room as a tool bus)"
subsection under Room Automation. Shows that the existing
`automation.rules` schema already supports per-agent permission gating:
sender + mention + regex filters scope which messages reach which
action; the action.type constrains the side-effect (post / exec /
nudge). To restrict an agent to read-only, drop exec/nudge rules.
skills/thinkoff-agent-platform/SKILL.md: document
GET /api/v1/rooms/{room}/messages/stream (SSE, ~150-300ms latency,
Last-Event-ID resume) and the POST /api/v1/messages metadata JSONB
convention (source / visibility / agent_state / thread / tags).
Implements items 2 + 3 of the ChatGPT roadmap discussion in
thinkoff-development on 2026-05-13. Both features already existed in
code; this is the doc layer that lets new agents discover them.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Documents the existing automation.rules routing engine + SSE + metadata convention. Implements items 2 and 3 of the multi-agent room roadmap discussion from thinkoff-development on 2026-05-13.