Mark/mesh-seed

Fork 0

[PoC] Auto-spawn workers via Clawdeploy #13

New issue

Closed

opened 2026-03-10 20:50:35 +00:00 by Mark · 4 comments

Mark commented

2026-03-10 20:50:35 +00:00

Owner

Proof of concept: automatic worker spawning when intent arrives.

Requirements

Detect zero available workers
Trigger Clawdeploy spawn
Wait for worker to advertise
Route intent to new worker
Handle spawn failures gracefully

Files

evolution/spawner.py
clawdeploy/worker-spec.yaml

Acceptance

3 consecutive successful auto-spawns
Worker TTL respected
Spawn latency < 60s

See MVP_AND_POCS.md PoC 1

Proof of concept: automatic worker spawning when intent arrives. ## Requirements - Detect zero available workers - Trigger Clawdeploy spawn - Wait for worker to advertise - Route intent to new worker - Handle spawn failures gracefully ## Files - evolution/spawner.py - clawdeploy/worker-spec.yaml ## Acceptance - 3 consecutive successful auto-spawns - Worker TTL respected - Spawn latency < 60s See MVP_AND_POCS.md PoC 1

Mark commented

2026-03-13 02:16:23 +00:00

Author

Owner

Progress update:

Implemented in working tree:

Added clawdeploy-aligned spawn module: evolution/spawner.py
Integrated capacity controller spawn path with optional clawdeploy mode (--spawn-via-clawdeploy)
Elastic harness now runs in clawdeploy mode and verifies missing-capacity -> spawn -> claim -> commit flow.

Verification:

./scripts/run_elastic_spawn_mesh.sh passes in clawdeploy mode
spawn metrics emitted: attempt/success/requeue

Remaining for full close:

explicit repeated-run assertion for 3 consecutive successful spawns
TTL/latency reporting thresholds as stated in issue text

Progress update: Implemented in working tree: - Added clawdeploy-aligned spawn module: `evolution/spawner.py` - Integrated capacity controller spawn path with optional clawdeploy mode (`--spawn-via-clawdeploy`) - Elastic harness now runs in clawdeploy mode and verifies missing-capacity -> spawn -> claim -> commit flow. Verification: - `./scripts/run_elastic_spawn_mesh.sh` passes in clawdeploy mode - spawn metrics emitted: attempt/success/requeue Remaining for full close: - explicit repeated-run assertion for 3 consecutive successful spawns - TTL/latency reporting thresholds as stated in issue text

Mark commented

2026-03-13 02:20:01 +00:00

Author

Owner

Completion update:

Implemented and verified in working tree:

Clawdeploy-aligned spawn adapter: evolution/spawner.py
Capacity controller clawdeploy mode: runtime/capacity_controller.py --spawn-via-clawdeploy
Elastic spawn harness: scripts/run_elastic_spawn_mesh.sh
Burn-in verification script: tests/spawn_burnin.py

Acceptance verification:

3 consecutive successful auto-spawns: PASS
- python tests/spawn_burnin.py --runs 3 --timeout 120 --max-latency-seconds 60
Spawn latency < 60s: PASS (avg ~9.5s)
Worker TTL/lease behavior enforced via claim leases and renewals in runtime/ledger flow.

Issue scope is satisfied; closing.

Completion update: Implemented and verified in working tree: - Clawdeploy-aligned spawn adapter: `evolution/spawner.py` - Capacity controller clawdeploy mode: `runtime/capacity_controller.py --spawn-via-clawdeploy` - Elastic spawn harness: `scripts/run_elastic_spawn_mesh.sh` - Burn-in verification script: `tests/spawn_burnin.py` Acceptance verification: - 3 consecutive successful auto-spawns: PASS - `python tests/spawn_burnin.py --runs 3 --timeout 120 --max-latency-seconds 60` - Spawn latency < 60s: PASS (avg ~9.5s) - Worker TTL/lease behavior enforced via claim leases and renewals in runtime/ledger flow. Issue scope is satisfied; closing.

Mark closed this issue

2026-03-13 02:20:01 +00:00

Mark referenced this issue

2026-03-14 18:59:03 +00:00

[Phase 0] Foundation - MVP Completion #27

Mark commented

2026-03-14 19:12:32 +00:00

Author

Owner

Phase Dependency Mapping

Linked to Phase Tracker: #30 (Phase 3: Scale)

Prerequisites:

#7 (Tailnet service discovery) - knows where to spawn
#19 (Multi-node mesh) - mesh coordination

Type: Deployment automation
Priority: P2 (scaling feature)

Purpose: Auto-scaling worker nodes via Clawdeploy

Acceptance Criteria:

Monitor queue depth
Spawn workers when threshold exceeded
Graceful shutdown when idle
Cost-aware scheduling

Blocker for: True elastic scaling in Phase 3

## Phase Dependency Mapping **Linked to Phase Tracker:** #30 (Phase 3: Scale) **Prerequisites:** - #7 (Tailnet service discovery) - knows where to spawn - #19 (Multi-node mesh) - mesh coordination **Type:** Deployment automation **Priority:** P2 (scaling feature) **Purpose:** Auto-scaling worker nodes via Clawdeploy **Acceptance Criteria:** - Monitor queue depth - Spawn workers when threshold exceeded - Graceful shutdown when idle - Cost-aware scheduling **Blocker for:** True elastic scaling in Phase 3

Mark referenced this issue

2026-03-14 19:12:48 +00:00

[Meta] Create project milestones and organize roadmap #26

Mark commented

2026-03-16 19:06:55 +00:00

Author

Owner

Decision lock: Clawdeploy is not part of active Phase 2 provisioning path.

Provisioning will execute on-mesh through existing intent/contract primitives and capability-based actuation.

Decision lock: Clawdeploy is not part of active Phase 2 provisioning path. Provisioning will execute on-mesh through existing intent/contract primitives and capability-based actuation.

Mark referenced this issue

2026-03-16 19:07:09 +00:00

[Phase 2.1] Mesh-native provisioning via core intent protocol #37

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

Mark/mesh-seed#13

No description provided.

Rows
Columns