Skip to content

pi graph v0.1.0

Latest

Choose a tag to compare

@ali-abassi ali-abassi released this 20 Jul 08:16

First public release.

A workflow harness your coding agent builds for itself. You describe the job to Claude Code, Codex, or Pi; the agent writes a steps.yaml graph, picks the model for each node, and runs it. The graph then owns the order, gates, retries, and budget — the model does the work but cannot quietly skip a step.

Runnersteps.yaml as the single execution contract: needs: dependencies, shell and model steps, when: routing, and gate: assertions. Per-node QA with an independent judge and a bounded improve/retest loop. Retry policies, content-addressed caching, and per-node evidence for every run.

Scalepiw batch runs one frozen graph across a corpus with isolated per-item workspaces and receipts. The manifest pins SHA-256 digests of workflow and corpus; --resume fails closed if either changed. Token and cost ceilings are enforced over recorded usage, including failed attempts.

Inspectionpiw detail for a run or one node, piw compare between runs, piw stats, and piw eval to compare models with judges held fixed. Optional local Studio via piw ui.

Guarantees — a model pin that drifts fails the step rather than returning another model's answer. Deterministic orchestration pins configuration and preserves evidence; it does not make LLM output identical between runs.

Full detail in CHANGELOG.md.