Skip to content

[rig-claude] Improve Claude dynamic-workflow compatibility for rig #344

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pelikhan merged 1 commit into from
Aug 4, 2026
Merged

[rig-claude] Improve Claude dynamic-workflow compatibility for rig #344

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
73 changes: 24 additions & 49 deletions skills/rig/samples/360-parallel-branch-analysis-workflow.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,64 +1,39 @@
# 360 - Parallel Branch Analysis Workflow

Uses `parallel(thunks)` — rig's equivalent of `parallel(thunks)` in Claude
dynamic workflows. `parallel` respects the shared concurrency limiter and
converts failures to `null` holes. Use it instead of `Promise.all` when porting
a Claude dynamic workflow.

```rig
import { agent, p, s, workflow } from "rig";

// Agent role: analyze git branch count and classify active vs stale branches.
const branchHealthAgent = agent({
model: "small",
instructions: p`Analyze git branches and classify active vs stale.

Branch list:
${p.bash("git branch -a 2>/dev/null || echo ''")}
const metric = s.object({ label: s.string, value: s.number });

Count totalBranches (all branches listed). List activeBranches as local branch names (lines not starting with "remotes/").
staleCount = totalBranches - activeBranches.length.`,
output: s.object({
totalBranches: s.int,
staleCount: s.int,
activeBranches: s.array(s.string),
}),
});
// Agent role: measure branch staleness as a labeled metric.
const branchAgent = agent({ model: "small", output: metric,
instructions: p`Count stale/total branches.\n${p.bash("git branch -a 2>/dev/null || echo ''")}` });

@github-actions github-actions Bot Aug 4, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[/grill-with-docs] metric schema declares label: s.string, but neither agent instruction tells the model what value to put there — only numeric counting is described. This risks repair loops or silently hallucinated label values.

💡 Suggestion

Either drop the label field (the caller already knows which agent produced which slot), or explicitly instruct each agent to set it:

const branchAgent = agent({ model: "small", output: metric,
  instructions: p`Emit { label: "stale-branches", value: <stale count> }.\n${p.bash("git branch -a 2>/dev/null || echo ''")}` });

A schema field with no prompt instruction is a latent repair-loop.


// Agent role: analyze git commit frequency over the last 30 days.
const commitFrequencyAgent = agent({
model: "small",
instructions: p`Analyze git commit frequency over the last 30 days.
// Agent role: measure average commits per day over the last 30 days.
const commitAgent = agent({ model: "small", output: metric,
instructions: p`Count commits per day.\n${p.bash("git log --since='30 days ago' --format='%h' 2>/dev/null | wc -l || echo 0")}` });

Commit dates:
${p.bash("git log --since='30 days ago' --format='%ad' --date=short 2>/dev/null || echo ''")}

totalCommits = number of non-empty lines. activeDays = number of unique dates.
averagePerDay = totalCommits / 30.`,
output: s.object({
totalCommits: s.int,
activeDays: s.int,
averagePerDay: s.number,
}),
});

// Workflow role: run branch health and commit frequency agents, then synthesize an overall health rating.
const parallelBranchAnalysisWorkflow = workflow({
meta: { name: "parallelBranchAnalysis", description: "Parallel branch and commit analysis", phases: ["Analyze", "Synthesize"] },
body: async ({ call, phase }) => {
phase("Analyze");
const [branchHealth, commitFrequency] = await Promise.all([
call(branchHealthAgent, "analyze branch health"),
call(commitFrequencyAgent, "analyze commit frequency"),
// Workflow role: run branch and commit agents in parallel, then synthesize a health rating.
const analysis = workflow({
meta: { name: "repoHealth", description: "Parallel repo health analysis", phases: ["Measure", "Rate"] },
body: async ({ call, parallel, phase }) => {
phase("Measure");
const [branches, commits] = await parallel([
() => call(branchAgent, "measure"),
() => call(commitAgent, "measure"),
]);

@github-actions github-actions Bot Aug 4, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[/grill-with-docs] The PR's stated teaching goal is that parallel converts individual failures to null holes, but the sample destructures the result directly without any null guard. Readers learn the API name but not the semantics that justify using it.

💡 Suggestion

Add a brief inline guard to make the null-hole pattern explicit:

const [branches, commits] = await parallel([
  () => call(branchAgent, "measure"),
  () => call(commitAgent, "measure"),
]);
// branches or commits may be null if an agent failed
if (!branches || !commits) return "insufficient-data";

This turns the sample into a real demonstration of the failure-semantic difference versus Promise.all.


phase("Synthesize");
const overallHealth = await call.json(
`Given branchHealth=${JSON.stringify(branchHealth)} and commitFrequency=${JSON.stringify(commitFrequency)},
classify overallHealth as "healthy" (averagePerDay >= 1 and staleCount < 3),
"needs-attention" (averagePerDay < 1 or staleCount >= 3), or "critical" (averagePerDay < 0.1 or staleCount >= 10).`,
phase("Rate");
return call.json(
`branches=${JSON.stringify(branches)} commits=${JSON.stringify(commits)}. Rate as "healthy", "needs-attention", or "critical".`,
s.enum("healthy", "needs-attention", "critical"),
);

return { branchHealth, commitFrequency, overallHealth };
},
});

export default parallelBranchAnalysisWorkflow;

export default analysis;
```
Loading