← solosystems.dev

jcode, state by state

One small task, a flaky test, walked through every state the harness passes on the way to done. Every screenshot is a real frame rendered by jcode's own replay engine, the same machinery that plays back any saved session as video.

01Prompt in, memory recalled

Before the model reads the prompt, the memory system has already run: each turn is embedded and matched against a graph of past memories, and the hits are injected inline. Here it recalls why the backoff constant is 50ms and how to run this crate's tests, context the model would otherwise burn a turn rediscovering.

jcode session start: user prompt with two auto-recalled memories injected inline

02Streaming begins

The model starts working. The context gauge in the corner tracks exactly what this turn costs; the header shows the provider, model, and MCP state at a glance.

jcode streaming the assistant's first response

03A tool runs

A live tool card: the spinner, the agent's stated intent ("Reproduce the flaky test"), the exact command, and elapsed time. Alt+B would push it to the background and let the agent keep thinking while it runs.

a bash tool call running with intent, command, and elapsed time visible

04The failure is the finding

The test fails, and that is the point: the card flips to an error state with the failing assertion inline, and the agent reads the timing math straight off it. No scrolling through a buried log, the harness renders failure as a first-class state.

failed test tool card showing the assertion failure inline

05Todos with confidence

The agent files its plan through the todo tool, and every item carries a confidence score the harness makes it defend: confidence may only rise in evidence-backed steps, and a completion that spikes straight to 100% gets challenged to go validate.

todo tool call recording the plan with per-item confidence

06The edit, as a diff

File changes render as compact diff cards, +1 -1 on src/retry.rs, expandable to the full diff inline. The git widget on the right tracks the working tree as it changes.

edit tool card showing a one-line diff on src/retry.rs

07Verification, not vibes

The fix isn't claimed, it's hammered: 50 consecutive test runs in a loop. The harness is built around this pattern, agents that design their own verification instead of asking you to check.

verification loop running the test suite 50 times

08Done means verified

The full transcript at rest: prompt, memories, the failing run, the plan, the diff, the 50-run verification, and a final answer that states what was proven rather than what was attempted. All todos closed with completion confidence, or the auto-poke would have sent the agent back to work.

completed session with all tool cards resolved and the final verified answer

Frames rendered headlessly by jcode replay --video from a hand-authored timeline in a scratch project, so the transcript is safe to publish and reproducible. Capture pipeline: tools/harness-walkthrough in the site repo.