ozan
f01036c646
Merged overlapping posts: - forking-gitea + fork-dont-build → one post about the fork philosophy - fal-image-generation + image-generation-fal → one post about AI art pipeline Rewrote all posts with external/public voice: - Stronger hooks, concrete examples, punchier language - agentic-workflow: restructured around soul files + skills + numbers - agent-harness: clearer framing of 'what an agent harness is' - cloud-harness: tighter narrative about overnight agents - godot-optimisation: same depth, sharper opening - pre-commit-agent: clearer architecture, cost breakdown - studio-cli: reframed around identity/cold-start problem - blog-visual-upgrade: tightened the restyle story 10 posts total (9 markdown + 1 hand-authored HTML)
116 lines
6.3 KiB
Markdown
116 lines
6.3 KiB
Markdown
---
|
|
title: "Agents That Code Overnight: Our $0.80 Cloud Harness with DeepSeek V4 and Pi"
|
|
slug: cloud-harness
|
|
date: "2026-05-26"
|
|
description: "A Pi fork for the brain, a Go orchestrator inside Gitea for overnight batch work, and a browser dashboard for daytime. Agents code while you sleep for about $0.80."
|
|
og_description: "Pi fork + Go orchestrator + browser dashboard. Agents code overnight for $0.80."
|
|
og_image: "https://www.tinqs.com/blog/img/cloud-harness-architecture.png"
|
|
excerpt: "Every coding agent today runs in your terminal. Close the laptop, it stops. We built a cloud harness where agents code overnight for about $0.80 — and you can watch from a browser dashboard."
|
|
author: "Ozan Bozkurt"
|
|
author_initials: "OB"
|
|
author_role: "CTO & Developer, Tinqs"
|
|
---
|
|
Every coding agent today — Claude Code, Codex, Cursor, Pi — has the same limitation: it runs in your terminal. You watch it work. You close the laptop, it stops. There's no way to say "build these eight features overnight" and wake up to pull requests.
|
|
|
|
We built exactly that. A Pi fork for the brain, a Go orchestrator inside our Gitea platform for overnight batch work, and a browser dashboard for daytime. Here's the stack.
|
|
|
|
## The problem with terminal-only agents
|
|
|
|
Claude Code runs on Opus at $15/MTok output. Codex uses GPT-5.5. Running eight agents overnight on either would cost $50-200. That's not sustainable for a four-person studio.
|
|
|
|
DeepSeek V4 Flash costs $0.28/MTok output. Eight overnight tasks: **about $0.80**. The cost differential changes what's possible — from "I'll use this sparingly" to "run it on everything."
|
|
|
|
But cost isn't the only issue. Cloud tools are black boxes. You can't add a Gitea API tool, a fal.ai image generator, or a guardrail that blocks destructive commands. With our own harness, you add an extension and it's live. Agents are not a feature to outsource — they're the product.
|
|
|
|
## Pi — the agent brain
|
|
|
|
[Pi](https://pi.dev) is an open-source coding agent. MIT license, TypeScript, 51k stars. Four core tools (read, write, edit, bash) and an extension system. We forked it and added four extensions:
|
|
|
|
- **tinqs-provider** — routes DeepSeek V4 Flash/Pro through our inference proxy
|
|
- **tinqs-tools** — Gitea REST API, fal.ai image generation, vision model access
|
|
- **tinqs-ci** — reads CI pipeline status, logs, polls for completion
|
|
- **tinqs-guardrail** — 29 safety patterns blocking dangerous commands
|
|
|
|
Each extension is a single TypeScript file. No npm dependencies. The core Pi code is untouched — we only add files.
|
|
|
|
Pi's RPC mode is what makes overnight automation possible. It runs headless, accepting JSON on stdin/stdout. The orchestrator spawns it as a subprocess, sends tasks, receives results. No terminal, no editor UI.
|
|
|
|
## DeepSeek V4 — the LLM
|
|
|
|
DeepSeek V4 Flash through our own inference proxy. OpenAI-compatible API, so Pi treats it like any other provider. The proxy adds:
|
|
|
|
- Redis job queue (10 concurrent workers)
|
|
- Per-user usage tracking
|
|
- System prompt injection for cache-hit optimization
|
|
- Gitea PAT authentication — same token as git push
|
|
|
|
Cost per task: $0.02-0.10 depending on complexity.
|
|
|
|
## Go orchestrator — overnight batch work
|
|
|
|
Inside our Gitea fork we added `modules/agents/` — a Go worker pool that spawns Pi processes, tracks task lifecycle, and streams events over SSE to any connected UI. Six endpoints, same auth as git push:
|
|
|
|
```
|
|
POST /api/v1/agents/tasks — submit a task
|
|
GET /api/v1/agents/tasks — list all tasks
|
|
GET /api/v1/agents/tasks/{id} — get task details
|
|
DELETE /api/v1/agents/tasks/{id} — stop a task
|
|
GET /api/v1/agents/stream — SSE live events
|
|
GET /api/v1/agents/health — orchestrator status
|
|
```
|
|
|
|
The orchestrator lives in the same binary as git — same auth, no extra service to deploy. The intended loop:
|
|
|
|
```
|
|
Orchestrator reads task brief
|
|
→ spawns pi --mode rpc
|
|
→ Pi writes code using DeepSeek V4
|
|
→ Pi pushes branch, calls ci_wait
|
|
→ CI green → Pi opens PR via gitea_api
|
|
→ CI red → Pi reads ci_logs, fixes, retries (≤3)
|
|
→ Human reviews PR, merges
|
|
```
|
|
|
|
## Browser dashboard — daytime UI
|
|
|
|
The orchestrator is for overnight batch work. During the day, you want to see agents, chat with them, and spawn sessions — without living in a terminal.
|
|
|
|
We merged [pi-agent-dashboard](https://github.com/BlackBeltTechnology/pi-agent-dashboard) into the Pi monorepo. One command:
|
|
|
|
```bash
|
|
npm run dashboard:dev
|
|
```
|
|
|
|
Open `localhost:33634` and you get live session streaming (watch tool calls and model output in real time), interactive chat, session spawning in any project folder, and per-session cost tracking. The dashboard talks to Pi sessions over WebSocket on port 9999. Inference uses the same Tinqs proxy as the CLI — one API key, one billing account.
|
|
|
|
```
|
|
Browser (localhost:33634)
|
|
↕ WebSocket (port 9999)
|
|
Pi sessions (interactive or headless)
|
|
↕ OpenAI-compatible API
|
|
Tinqs proxy (tinqs.com/api/v1/ai)
|
|
↕ DeepSeek V4 Flash / Pro
|
|
```
|
|
|
|
## The guardrail
|
|
|
|
The biggest fear with autonomous agents: hallucination. An agent claiming it read a file without calling `read`. Three consecutive turns with no tool calls. Running `aws ec2 terminate-instances` at 3am.
|
|
|
|
The guardrail extension monitors every turn:
|
|
|
|
- **Hallucination detection** — claims without tool calls get corrected
|
|
- **No-tool drift** — three turns with zero tool calls triggers a warning
|
|
- **Command blocking** — 29 patterns covering destructive git, AWS teardown, process killing, production API abuse
|
|
|
|
Guardrails at the platform layer, not the prompt layer. Prompts can be ignored. Platform gates cannot.
|
|
|
|
## What it cost to build
|
|
|
|
About 2,000 lines of Go, 900 lines of TypeScript extensions, 52 tests, plus merging the dashboard into the Pi monorepo. No new servers — Pi is a Node subprocess; the dashboard is another Node process on your machine. The orchestrator is a Go module inside our existing Gitea binary — zero additional infrastructure.
|
|
|
|
---
|
|
|
|
The harness — inference proxy, guardrails, dashboard, orchestrator API — is in place. Agents code while you sleep for pocket change. And because everything runs on your own infrastructure, you control the models, the tools, and the safety rails.
|
|
|
|
*Tinqs Studio is an open platform for game development — git hosting, AI inference, asset generation, and autonomous agents. We're building [Ariki](https://arikigame.com) using the same tools.*
|