Stackchain AI Lab — Agent Engineering Report

Audience: agent engineers · 2026-07-08 · Source of truth: Gitea
Operations active

Current State

InfraGitea 1.22.0, Caddy-free routing
Public URLforge.alexanderwhitestone.com/git/
Orgstackchain
Repos4 active (`hackathon`, `dashboard`, `agent-todo-tracker`, `project-template`)
Active users5 (2 admins onboarded via CLI + 2 promoted via DB + bot)
PipelineCI + RC workflows pushed to mains
LoopIssue → PR → review → merge/no-spam, stale/blocked handled
Creative agentHou3 profile active on Tencent Hy3

Stackchain Dashboard

Repostackchain/stackchain-dashboard
BackendFastAPI context endpoint + suggestion engine
FrontendAdaptive SPA shell with 3-column layout
KanbanHermes board + label sync script wired
Issues#9 epic, #10 context, #11 engine, #12 panels, #13 cache
StatusWIP Backend scaffold shipped

Queue Snapshot

Open issues19 items in `stackchain-hackathon`
P0/P1P0 Pages enablement (blocked on human handoff)
P1#8 Adaptive UI, #10 context, #11 engine, #12 frontend
P2#13 cache, #5 agent-todo, #6 scaffolder
Creative#16 README, #17 overlays, #18 release notes
Open PRs0
Hou3Actively composing deliverable drafts

Operational Constraints

CaddyNo changes for Gitea work
Human touchpointsPrototype review + RC test only
Config`ROOT_URL=https://forge.alexanderwhitestone.com/git/`
Assets`/var/lib/gitea/public/assets/` verified present
Pages APIReturns 404; enablement gated
Cleanup doneDupe users removed, admins promoted

Risk Register

Gitea Pages authMediumSurface as handoff in #14
MemoryMediumWatchdog + serialize workers
Auth driftLowSingle admin path, weekly audit
Workflow driftMediumOne canonical workflow source
Hou3 spamLowSeen-state + max-comment guard

Market Fit Matrix — What We Can Build

ProductMarket SignalFitBuild Order
Adaptive UI dashboardContext-aware developer surfaces are emerging categoryStrongP0
Agent Task HarnessDeterministic multi-agent orchestration is foundationalStrongP1
Agent Memory StoreCross-session memory is table stakes for useful agentsStrongP1
PR Review AgentAutomated review reduces human loadStrongP1
Repo Scaffolder AgentNL project generation lowers onboarding frictionMediumP2
Hou3 creative pipelineLaunch docs/content automationMediumP2
Gitea Pages sitePublic lab landing pageMediumBlocked
Kanban-to-issue syncSingle pane of glassMediumWired

Phase A — 0–48h

Close the Loop

  • Ship adaptive dashboard panels from #8–#13
  • Wire Hou3 output → issues/PRs as real comments
  • Run first full autonomous cycle: branch, impl, PR, self-review, merge
Phase B — 48h–2w

Harden

  • Fill test suites in dashboard + agent-todo-tracker
  • Automate token rotation via cron/Hermes job
  • Profile memory usage before adding more workers
Phase C — 2w+

Scale

  • Multi-repo issue queue across stackchain/*
  • Unique staging targets per RC
  • Separate Hou3 creative queue from code queue

Human Gates

Human ActionTriggerWhat to do
Prototype reviewPR includes preview linkClick, test, comment feedback
RC approvalAutomated tests pass, draft release createdVerify locally, merge release PR
Pages handoffIssue #14 is `blocked`Enable Gitea Pages in UI; confirm URL
3 consecutive failed reviewsAuto-pause in loopSurface in issue, triage, decide path