56e16d9dea
## What Pins the CLI board glyph's terminal-lane resolve — **the last flagged site in the repo-wide resolver audit.** Two commits: a behaviour-preserving extraction, then the test. ## I was wrong to flag this as unpinnable In #3236 I recorded this site as not pinnable, reasoning that *"extracting a pure helper and testing it would look like coverage and would not be."* That is true of a helper that **receives** the lane set — such a test passes with the resolve blinded, which is exactly the `reads.ts` trap the audit note records. It is **not** true of one that **resolves** it. Building `resolveReliabilityLanes` in #3237 made the distinction obvious: the seam has to contain the resolve, and then blinding fails a test of it. So the flag was too broad, and correcting it closes the site rather than leaving a permanent excuse. That is the same failure mode I corrected in someone else's note earlier today — a caution that hardens into a reason not to look. ## Measured ``` converted: Tests 5 passed (5) blinded: Tests 2 failed | 3 passed (5) ``` The two failures are the **renamed complete** and **renamed archive** lanes. The three survivors are the default-vocabulary control, the active-lane negative, and the degrade path — all of which should survive. ``` task-list-board-columns + bin: 82 passed typecheck clean; lint clean; fnxc-future-dates: none added ``` ## Why the sibling file did not cover it `task-list-board-columns.test.ts` pins `boardColumnsForDisplay`, which decides **which** lanes print. That function takes no lane set, so it cannot fail when this resolve is blinded — and its own header says so honestly. Two tests about the same command, one of which cannot see the other's bug. ## What breaks without the conversion On a board whose complete lane is `shipped`, a finished lane renders `●` — the same glyph as active work. The board says work is in flight when it shipped. Cosmetic next to the blank-board bug this area already fixed, but wrong in the direction an operator reads at a glance. ## Also pinned Two contracts the surrounding comments assert but nothing tested: - **Cards come from the TASKS, not a resolved IR** — a card must never depend on resolution succeeding to be *visible*. Asserted with an unreadable workflow list. - **A failed resolve degrades to the legacy pair**, with an unresolved custom lane rendering as active — the documented fail-open direction. Plus the paired negative: an ACTIVE lane keeps the active glyph under both vocabularies, so widening the terminal set cannot mark the whole board finished. ## Audit complete Every `resolveProjectColumnsForRoles` call site in the repository — `engine`, `core`, `dashboard`, `cli` — has now been blinded individually, and every uncovered one is either pinned or has a recorded reason it cannot be. Nothing is left flagged.
@runfusion/fusion
From rough idea to production code — automatically.
Multi-node agent orchestrator — tasks, agents, missions, git, files, and worktrees, with any model, local or cloud.
runfusion.ai → · GitHub · Docs
Install
Zero install, straight from npm:
npx runfusion.ai
Boots the dashboard. Subcommands forward through (npx runfusion.ai task list, etc). Long form: npx @runfusion/fusion dashboard.
One-line installer (macOS & Linux — auto-picks Homebrew, falls back to npm):
curl -fsSL https://runfusion.ai/install.sh | sh
Homebrew (macOS & Linux):
brew install runfusion/fusion/fusion
Fully-qualified install auto-taps and, on Homebrew 6.0+, trusts only this formula. If short-name install fails with “untrusted tap”, run brew trust --formula runfusion/fusion/fusion then brew install fusion.
npm global:
npm install -g @runfusion/fusion
fn dashboard # or: fusion dashboard
Launch the dashboard
From a shell:
fn dashboard # or: fusion dashboard / npx @runfusion/fusion dashboard
fn dashboard --paused # start with automation paused
fn dashboard --dev # development-mode dashboard + AI engine
fn dashboard --no-engine # web UI only, no AI engine
The dashboard gives you:
- A live kanban board — tasks move through columns automatically as AI works on them
- Task detail view — generated spec, step-by-step progress, reviewer verdicts, full execution log
- Dependency-aware scheduling — declare task dependencies or let the engine infer them
- Auto-merge — on by default; reviewed work squash-merges without you lifting a finger
- Parallel execution — independent tasks run simultaneously in isolated git worktrees
- Self-sustaining board — agents may spawn follow-up tasks; the board feeds itself
Your entire dev environment. On a single pane of glass.
Describe a task in plain language. A triage agent reads your project, understands context, and writes a full PROMPT.md spec — steps, file scope, acceptance criteria. Then Fusion plans, reviews, executes, and reviews again, in an isolated git worktree, with a human approval gate wherever you want one.
One board. Controlled from anywhere. Laptop, Mac mini, Linux server, cloud VM, phone — all connected.
Run an agent company
Import a team. Run it autonomously for weeks. 440+ agents across 16 companies, wired for missions, mailboxes, and inter-agent delegation.
npx companies.sh add paperclipai/companies/gstack
How it works
You create a task with a rough description. A pipeline of specialized agents takes over.
Specification. A triage agent reads your codebase — file structure, existing patterns, related code — and turns your rough idea into a detailed spec. It breaks the work into discrete steps, identifies which files are in scope, writes acceptance criteria, and assigns a complexity rating that determines how aggressively the work gets reviewed.
Scheduling. Tasks declare dependencies on each other. The scheduler builds a dependency graph and starts work only when upstream tasks are done. Independent tasks run in parallel — each in its own isolated git worktree, so there are no conflicts during execution.
Execution & review. An executor agent works through the spec step by step in the worktree. At each step boundary, a separate reviewer agent, with read-only access, independently evaluates the work. The reviewer can approve (continue), request revisions (fix specific issues), or force a rethink (change the approach entirely). Review depth scales with the task's complexity rating: trivial tasks get light checks, complex tasks get thorough multi-pass review.
Merge. When execution finishes and the reviewer signs off, the task moves to In Review:
- Direct merge (default) — automatically squash-merges the completed task branch into your current branch with a clean commit.
- Pull request — automatically creates or links a GitHub PR, waits for reviews/checks, then merges once policy conditions are satisfied.
autoMerge controls whether Fusion performs completion automatically. If disabled, tasks stay in In Review until you finish the merge yourself. For PR-first mode, authenticate GitHub with gh auth login.
Tasks flow through: Triage → Todo → In Progress → In Review → Done.
This execution model is heavily based on Taskplane.
What makes it different
| 🧠 AI specification | Rough idea in, detailed PROMPT.md out — steps, file scope, acceptance criteria. |
| 🔁 Workflow gates | Plan → Review → Execute → Review on every step. Block or pass automatically. |
| 🌳 Worktree isolation | Each task runs in its own branch and worktree. Parallel tasks. Zero conflicts. |
| ⚡ Smart merge | Passing every gate? Fusion squash-merges and moves on. |
| 🛰️ Multi-node mesh | Laptop, server, cloud, phone — all synced. Desktop, mobile, web. |
| 🧩 Any model | Anthropic, OpenAI, Ollama, and more. |
| 🏢 Agent companies | Import pre-built teams — 440+ agents across 16 companies. |
| 📬 Inter-agent messaging | Built-in mailbox between agents. Delegate, clarify, coordinate. |
| 🗺️ Missions | Hierarchical planning with autopilot and validation contracts. |
| 🔓 Open source. MIT. | No vendor lock-in. Run it on your own hardware. |
Working from chat
Manage tasks without leaving the conversation:
"Every ten minutes, analyze the server code for logic the client hasn't implemented yet and create tasks. Tasks may spawn additional tasks, so just add enough to keep the board saturated."
"Create a Fusion task to fix the login redirect bug"
"Add a task for dark mode support, it depends on FN-003"
"What's the status of FN-042"
"Attach screenshot.png to FN-007"
"Pause FN-012 — I want to add more context first"
The Fusion extension exposes tools to create tasks, check progress, attach files, and pause or resume automation.
Standalone CLI
See STANDALONE.md for additional installation and usage options.
Optional provider: Factory AI via Droid CLI
@runfusion/fusion now ships a vendored @fusion/droid-cli extension in the published CLI bundle.
To use it:
- Install the
droidbinary and ensure it is on yourPATH - Authenticate with Droid CLI (
droid auth login) - In Fusion dashboard, go to Settings → Authentication and enable Factory AI — via Droid CLI
- Restart Fusion when prompted so the extension is loaded into the runtime
Once enabled, droid-cli models appear in Fusion model selection.
Maintainer note: workspace plugins in published CLI bundles
When CLI or dashboard runtime code imports workspace plugin packages (for example @fusion-plugin-examples/roadmap), those imports must stay statically analyzable and covered by packages/cli/tsup.config.ts noExternal rules so plugin runtime code is inlined into dist/bin.js.
Do not introduce dynamic or variable module specifiers for workspace plugin runtime paths in the published execution path. If a workspace plugin is needed for bundled auto-install, stage a bundled plugin entry (dist/plugins/<id>/bundled.js) rather than copying raw TypeScript source into dist/.
Full documentation
Architecture details, development setup, and contributor info live in the project README.
License
MIT — see LICENSE.