clawdie/layered-soul
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
layered-soul/docs/CAPABILITY-ROUTING.md
Sam & Claude 0bb2f8f260 docs: flip to python3=3.11 default (3.12 available); trim the pillow noise 
Per operator decision: stop fighting FreeBSD's PYTHON_DEFAULT=3.11 — python3 is
3.11 everywhere, python3.12 stays available for apps needing newer. This makes
Pillow trivial (py311-pillow imports on python3), so the prior "3.12 floor +
py312-pillow absent + run on 3.11 explicitly" explanation collapses.

- TOOLCHAIN.md: table row + decision section flipped to 3.11-default and cut to a
  few lines (supersedes the 17.jun.2026 "3.12 floor" decision); symlink note now
  says build.sh points python3 at 3.11.
- CAPABILITY-ROUTING.md: trimmed the osa line + worked example — image-render via
  py311-pillow on python3, no version gymnastics.
- HOST-MATRIX.md: trimmed the operator-image image-render/screenshot note.

prettier + layered_soul validate clean. Dates in edited blocks use EU format.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-21 10:12:29 +02:00

5.7 KiB
Raw Blame History

Capability-Based Task Routing

LIVE VS PLANNED. Colibri's capability matcher exists (Colibri daemon) and works for a single-host daemon/agent pool. Cross-host transport is now LIVE (2026-06-19): a socat bridge over Tailscale exposes osa's daemon, and a poller/worker loop runs assigned tasks across hosts — validated on the debby↔osa lane (colibri PR #83). Full capability-scored routing across all three hosts is maturing on top of this transport. Sections below are labelled [LIVE] or [PLANNED].

Principle: a tool that one OS can't support is not a loss — it's a routing constraint. In a multi-agent, multi-OS fleet we don't force every capability onto every host. We let each host advertise what it can do, let each task declare what it needs, and let the scheduler send the task to a host that qualifies. FreeBSD stays lean; the capability simply lives where it's cheap.

[LIVE] What Colibri already provides (single host)

The matching engine exists today in colibri-daemon — this is working, per-host:

  • Agents carry capability tags — agents.capabilities (JSON array) in the store (colibri-store schema); registered via colibri client / --capabilities.
  • Tasks declare requirements — jobs and intake requests carry required_capabilities (colibri intake-task --capabilities <csv>).
  • The scheduler matches — pick_agent(required, agents) scores each idle/active agent with capability_match_score and picks the best fit.
  • Unmatched = parked, not failed — if requirements are non-empty and no online agent matches, pick_agent returns None: the task is created but left unassigned until a capable agent appears.

Note: the daemon itself listens on a local Unix socket only. Cross-host reach is provided by the bridge below, not by the daemon binding a network port directly.

[LIVE] Cross-host topology

Implemented 2026-06-19 (colibri PR #83), using the socat-over-Tailscale approach:

  • socat bridge (colibri_bridge rc.d, daemon(8)-supervised) maps osa's daemon Unix socket to a TCP port on the Tailscale interface only (${OSA_TS_IP}:9190, never 0.0.0.0), with a pf rule on tailscale0. osa is the always-on VPS and hosts the board + orchestrator (hermes-osa); agents on debby/domedog reach it over the tailnet. (debby is an intermittent laptop — a client, never the hub.)
  • Poller/worker loop — colibri_poll.py (filters by agent UUID) and colibri_task_done.py (transition-task), driven on the live 2 min / 5 min cadence by Hermes' internal scheduler (see packaging/freebsd/colibri-agent-loop.md), not OS cron.
  • Validated on the debby↔osa lane (real tasks completed end-to-end). domedog joined 2026-06-19 via the same pattern — a client-side socat shim → osa ${OSA_TS_IP}:9190.
  • Alternative (heavier, not pursued): daemon-to-daemon federation.

[LIVE] Capability vocabulary (initial)

Piece Status Action
Capability vocabulary tags are free-form (rust, python, linux) Agree a shared tag set (below)

Flat, explicit tags — the matcher does exact string comparison, no implied hierarchy. Sourced from the probe and recorded per host in HOST-MATRIX.md.

Category Tags
OS linux, freebsd
Isolation docker, freebsd-jail
Display gui, screenshot, wayland
Hardware gpu, zfs
Runtime python3.12, node24, rust, go
Media ffmpeg, pillow/image-render

Hosts advertise only what they truly have. Actual registered agents (2026-06-19):

  • domedog (Linux, headless): linux, python3.12, rust, go, node, ffmpeg, image-render — the media/compute lane. No screenshot/gui (headless VM), no docker.
  • debby / hermes-debby (Linux): linux, docker, shell, gateway, hermes, tailscale.
  • osa / hermes-osa (FreeBSD): freebsd, shell, gateway, tailscale, rc.d, pf, nginx, acme, hermes — no image-render (headless server; py311-pillow not installed there). The FreeBSD operator image enables it via py311-pillow (below).

[DESIGN] Worked example: the tmux-screenshot skill

This illustrates the routing flow (now runnable over the [LIVE] cross-host topology above):

  1. The FreeBSD operator image ships py311-pillow (clawdie-iso #85), so clawdie-join-hive.sh advertises image-render (Pillow on python3 = 3.11) and screenshot when a display is present.
  2. The skill manifest declares required_capabilities: ["image-render"] (or screenshot).
  3. Both domedog (Linux) and the FreeBSD operator image advertise image-render. screenshot also needs a display, so a headless host (domedog, osa) does not qualify — the operator image, with its XFCE session, does.
  4. Colibri routes the task to a matching host automatically — proven 19.jun.2026: an image-render task routed to domedog; with no match it parks until a capable agent appears.

The capability moved hosts. It was never lost.

See HIVE-ONBOARDING.md for the hive-onboarding vision built on this routing layer, MCP-INTEGRATION.md for connecting agents to the board over MCP, AGENTS.md for the agent matrix, HOST-MATRIX.md for per-host facts, and TOOLCHAIN.md for runtime versions.