ai/byre
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 10 Wiki Activity

Add review workflows, tree-shaped workflows and a workflow editor

Browse Source
This commit is contained in:
Ian Gulliver
2026-10-20 18:52:04 -07:00
parent 9869fad988
commit f2188c53eb
31 changed files with 2179 additions and 863 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/agents/kb/workflow-files.md
+25 -20
View File
@@ -1,36 +1,41 @@
The YAML format of a workflow's file, which read_workflow returns and save_workflow takes: stages, after, base, model and teams.
# Workflow files
A workflow's file is YAML: an optional `description`, then `stages`. The workflow's name is not in the file. Unknown fields are refused.
A workflow's file is YAML: an optional `description`, an optional `kind`, then `steps`, which run in order. The workflow's name is not in the file. Unknown fields are refused.
| Field | Meaning |
`kind` is `task` (the default) or `review`. A task workflow runs on a brief, each stage as its own task. A review workflow is what a project names (with `set_review_workflow`) to review its tasks' snapshots: each stage is one reviewer agent on its `model`, given the task's change and its stage's `prompt` (what to look for); a stage after others also gets their reviews. Its stages can't use `agents`, and it may end with several stages.
Each step is exactly one of:
| Step | Meaning |
|---|---|
| `stage` | A stage, by its name: one line, unique in the workflow. It runs as its own task, with `model` or `agents`, and `prompt`. |
| `order` | A list of steps run one after another. |
| `parallel` | A list of branches run at the same time, each a step (an `order` for a branch of several). |
A stage gets the outputs of the stages that end the step before it: the last stage of an `order`, or the last stage of every branch of a `parallel`. A stage with nothing before it starts from the brief.
| Stage field | Meaning |
|---|---|
| `name` | One line, unique in the workflow. |
| `after` | The names of the stages whose outputs it gets; it starts once all of them have finished. Absent means the previous stage in the list, and for the first stage none, so a file without `after` is a chain. `[]` means it starts from the brief. |
| `base` | `parent`, the default: branch from the commit its one `after` stage finished at, or for a stage with none, from where the workflow was started. `main`: branch from the default branch. Refused on a stage with more than one `after` stage, which always branches from the default branch and is told the branches it can merge. |
| `model` | Also picks the vendor: `gpt-*` models run on Codex, `gemini-*` models on Antigravity, every other model on Claude Code. |
| `prompt` | The stage agent's instructions. |
| `agents` | In place of `model`: a list of at least two, each with `name`, `model` and `prompt`, that runs the stage as a team. They work in the stage's one task and worktree and talk through a shared board; each gets the stage's `prompt` and then its own, and the first agent finishes the stage. |
Every stage runs as its own task. Exactly one stage is final (no other stage comes after it), and cycles are refused.
Where a stage's task branches from follows from the shape. A stage after exactly one stage starts from the commit that stage finished at. A stage after a `parallel` starts from the default branch and is told the branches it can merge. A stage with nothing before it starts where the workflow was started. The workflow must end with one stage, which finishes it. An `order` or `parallel` can't be empty.
```yaml
description: Build a change, review and test it in parallel, then fix what they found.
stages:
- name: Build
steps:
- stage: Build
model: claude-opus-5-5
prompt: Implement the brief.
- name: Review
after: [Build]
model: gpt-6.1-sol
prompt: Review the Build stage's work and list the problems.
- name: Test
after: [Build]
model: gemini-4-argon-high
prompt: Exercise the change and report what fails.
- name: Fix
after: [Review, Test]
- parallel:
- stage: Review
model: gpt-6.1-sol
prompt: Review the Build stage's work and list the problems.
- stage: Test
model: gemini-4-argon-high
prompt: Exercise the change and report what fails.
- stage: Fix
agents:
- name: fixer
model: claude-opus-5-5