docs: multi-agent multi-host gap analysis + implementation plan (Sam & Hermes) #84

Merged

clawdie merged 1 commit from docs/multi-agent-host-plan into main

2026-06-20 14:26:37 +02:00

clawdie commented

2026-06-19 17:30:03 +02:00

Owner

What

Gap analysis and implementation plan for the multi-agent multi-host coordination goal, written after pulling PR #83 (cross-host TCP bridge + agent polling loop).

Documents

New: docs/MULTI-AGENT-HOST-PLAN.md — full gap analysis of the multi-host stack (7 gaps identified), 5 implementation phases, immediate scope = Phases 1-2
Updated: docs/PRIORITY-HANDOFF-ISO-SPAWN-COST.md — marks Priorities 2 & 3 done, fixes stale test count (164 → 211), cross-references new plan
Updated: docs/README.md — adds new doc to index

Key findings

The multi-host plane is packaged and documented but untested:

pick_agent only tested with 0-1 agents
claim_task is a blind UPDATE, no concurrency guard
No host/last_seen/heartbeat in agent schema
TCP bridge (socat) completely untested
4 of 17 socket commands have no CLI surface

Immediate scope (Phases 1-2)

Phase	What
1a	`pick_agent` unit tests (partial match, tie-breaking, multi-cap)
1b	Multi-agent board integration test (2 agents, 2 capabilities, verify assignment)
1c	Same-capability multi-task test (session isolation)
2a	Merge `feat/cli-register-agent` branch
2b	Add `claim-task` + `transition-task` to CLI
2c	CLI parse tests

All Linux-testable. 211 tests pass, clippy clean, fmt clean.

## What Gap analysis and implementation plan for the multi-agent multi-host coordination goal, written after pulling PR #83 (cross-host TCP bridge + agent polling loop). ## Documents - **New:** `docs/MULTI-AGENT-HOST-PLAN.md` — full gap analysis of the multi-host stack (7 gaps identified), 5 implementation phases, immediate scope = Phases 1-2 - **Updated:** `docs/PRIORITY-HANDOFF-ISO-SPAWN-COST.md` — marks Priorities 2 & 3 done, fixes stale test count (164 → 211), cross-references new plan - **Updated:** `docs/README.md` — adds new doc to index ## Key findings The multi-host plane is **packaged and documented but untested**: - `pick_agent` only tested with 0-1 agents - `claim_task` is a blind UPDATE, no concurrency guard - No `host`/`last_seen`/heartbeat in agent schema - TCP bridge (socat) completely untested - 4 of 17 socket commands have no CLI surface ## Immediate scope (Phases 1-2) | Phase | What | |-------|------| | 1a | `pick_agent` unit tests (partial match, tie-breaking, multi-cap) | | 1b | Multi-agent board integration test (2 agents, 2 capabilities, verify assignment) | | 1c | Same-capability multi-task test (session isolation) | | 2a | Merge `feat/cli-register-agent` branch | | 2b | Add `claim-task` + `transition-task` to CLI | | 2c | CLI parse tests | All Linux-testable. 211 tests pass, clippy clean, fmt clean.

clawdie added 1 commit 2026-06-19 17:30:06 +02:00

docs: multi-agent multi-host gap analysis + implementation plan (Sam & Hermes)

CI / rust (pull_request) Has been cancelled

Details

CI / markdown (pull_request) Has been cancelled

Details

978bb18011

New doc: docs/MULTI-AGENT-HOST-PLAN.md — gap analysis of the multi-host
coordination stack after PR #83 (socat bridge + Python pollers). Defines 5
phases: Phase 1 (multi-agent task-board tests), Phase 2 (merge CLI surface
gaps), Phase 3 (agent presence schema, deferred), Phase 4 (polling workflow
test, deferred), Phase 5 (TCP bridge validation, FreeBSD-only).

Immediate scope: Phases 1-2, all Linux-testable.

Updated PRIORITY-HANDOFF-ISO-SPAWN-COST.md to mark Priorities 2 (poll_tasks)
and 3 (cost mode enforcement) as done, fix stale test count (164 → 211), and
cross-reference the new plan as the next sprint.

211 tests pass, clippy clean, fmt clean.