feat: Implement workflow generation command with YAML validation and LLM integration

package.json

@@ -40,7 +40,7 @@
     "build": "tsc && cp src/voice/ui.html dist/voice/",
     "dev": "tsc --watch",
     "start": "node dist/index.js",
-    "test": "node --test test/*.test.ts --experimental-strip-types"
+    "test": "node --experimental-strip-types --experimental-loader=./test/ts-resolve-hook.mjs --no-warnings --test test/*.test.ts"
   },
   "engines": {
     "node": ">=20"

spec/schemas/workflow.schema.json

@@ -0,0 +1,69 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://gitclaw.dev/spec/workflow.schema.json",
+  "title": "GitClaw SkillFlow Workflow",
+  "description": "A SkillFlow workflow: a named sequence of steps, where each step invokes a skill with a prompt. Runtime semantics are defined by src/workflows.ts.",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["name", "description", "steps"],
+  "properties": {
+    "name": {
+      "type": "string",
+      "description": "Kebab-case identifier for the workflow. Used as the file name.",
+      "pattern": "^[a-z0-9]+(-[a-z0-9]+)*$"
+    },
+    "description": {
+      "type": "string",
+      "description": "One-line description of what the workflow does.",
+      "minLength": 1
+    },
+    "steps": {
+      "type": "array",
+      "description": "Ordered list of steps. Steps execute top-to-bottom.",
+      "minItems": 1,
+      "items": { "$ref": "#/definitions/step" }
+    }
+  },
+  "definitions": {
+    "step": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["skill", "prompt"],
+      "properties": {
+        "id": {
+          "type": "string",
+          "description": "Optional snake_case identifier for the step. Used when other steps reference this one via depends_on.",
+          "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$"
+        },
+        "skill": {
+          "type": "string",
+          "description": "Name of an installed skill (kebab-case) the step will invoke. Must match an entry in the agent's skills/ directory, or 'approval' for a human-review step.",
+          "pattern": "^[a-z0-9]+(-[a-z0-9]+)*$"
+        },
+        "prompt": {
+          "type": "string",
+          "description": "The natural-language instruction passed to the skill for this step.",
+          "minLength": 1
+        },
+        "channel": {
+          "type": "string",
+          "description": "Optional channel/destination for the step output (e.g. a Slack channel name).",
+          "minLength": 1
+        },
+        "depends_on": {
+          "type": "array",
+          "description": "Optional list of step ids that must complete before this step runs.",
+          "items": {
+            "type": "string",
+            "pattern": "^[a-z0-9]+(_[a-z0-9]+)*$"
+          },
+          "uniqueItems": true
+        },
+        "requires_approval": {
+          "type": "boolean",
+          "description": "If true, the workflow pauses for human approval before this step runs."
+        }
+      }
+    }
+  }
+}

src/commands/workflow.ts

@@ -0,0 +1,188 @@
+import { mkdir, readFile, writeFile } from "fs/promises";
+import { join, resolve } from "path";
+import { discoverSkills } from "../skills.js";
+import { validateWorkflow } from "../utils/schemas.js";
+import { generateWorkflow, type LlmClient } from "../utils/workflow-generator.js";
+
+interface GenerateFlags {
+	dir: string;
+	prompt?: string;
+	refine?: string;
+	model?: string;
+	apiKey?: string;
+	dryRun: boolean;
+}
+
+const RED = (s: string) => `\x1b[31m${s}\x1b[0m`;
+const GREEN = (s: string) => `\x1b[32m${s}\x1b[0m`;
+const DIM = (s: string) => `\x1b[2m${s}\x1b[0m`;
+const BOLD = (s: string) => `\x1b[1m${s}\x1b[0m`;
+
+const MAX_RETRIES = 2;
+
+function printHelp(): void {
+	console.log(`${BOLD("gitclaw workflow")} — generate SkillFlow workflows from natural language
+
+Usage:
+  gitclaw workflow generate [options]
+
+Options:
+  -d, --dir <path>        Agent directory (default: current directory)
+  -p, --prompt <text>     Natural-language description of the workflow (required)
+      --refine <file>     Refine an existing workflow YAML by applying --prompt as an instruction
+  -m, --model <spec>      LLM model in provider:model form (default: openai:gpt-4o)
+      --api-key <key>     API key for the provider (falls back to OPENAI_API_KEY or <PROVIDER>_API_KEY)
+      --dry-run           Print the generated YAML to stdout instead of writing a file
+  -h, --help              Show this help message
+
+Examples:
+  gitclaw workflow generate -p "every morning summarize unread emails and post to Slack"
+  gitclaw workflow generate -p "add a human approval step before the Slack post" --refine workflows/morning-digest.yaml
+`);
+}
+
+function parseFlags(argv: string[]): GenerateFlags {
+	const flags: GenerateFlags = { dir: process.cwd(), dryRun: false };
+	for (let i = 0; i < argv.length; i++) {
+		const a = argv[i];
+		switch (a) {
+			case "-d":
+			case "--dir":
+				flags.dir = argv[++i];
+				break;
+			case "-p":
+			case "--prompt":
+				flags.prompt = argv[++i];
+				break;
+			case "--refine":
+				flags.refine = argv[++i];
+				break;
+			case "-m":
+			case "--model":
+				flags.model = argv[++i];
+				break;
+			case "--api-key":
+				flags.apiKey = argv[++i];
+				break;
+			case "--dry-run":
+				flags.dryRun = true;
+				break;
+			case "-h":
+			case "--help":
+				printHelp();
+				process.exit(0);
+				break;
+			default:
+				if (!a.startsWith("-") && flags.prompt === undefined) {
+					flags.prompt = a;
+				} else {
+					console.error(RED(`Unknown option: ${a}`));
+					process.exit(2);
+				}
+		}
+	}
+	return flags;
+}
+
+function slugify(name: string): string {
+	const cleaned = name
+		.toLowerCase()
+		.trim()
+		.replace(/[^a-z0-9-]+/g, "-")
+		.replace(/^-+|-+$/g, "")
+		.replace(/-+/g, "-");
+	return cleaned || "workflow";
+}
+
+export interface RunGenerateOptions {
+	flags: GenerateFlags;
+	llm?: LlmClient;
+}
+
+export async function runGenerate(opts: RunGenerateOptions): Promise<{ filePath?: string; yaml: string; }> {
+	const { flags } = opts;
+	if (!flags.prompt || !flags.prompt.trim()) {
+		throw new Error("--prompt is required");
+	}
+
+	const agentDir = resolve(flags.dir);
+	const skills = await discoverSkills(agentDir);
+
+	let previousWorkflow: string | undefined;
+	if (flags.refine) {
+		const refinePath = resolve(agentDir, flags.refine);
+		previousWorkflow = await readFile(refinePath, "utf-8");
+	}
+
+	let promptForLlm = flags.prompt.trim();
+	let lastErrors: string[] = [];
+	let yaml = "";
+
+	for (let attempt = 0; attempt <= MAX_RETRIES; attempt++) {
+		console.error(DIM(attempt === 0 ? "Generating workflow..." : `Retry ${attempt}/${MAX_RETRIES} — fixing validation errors...`));
+		yaml = await generateWorkflow({
+			prompt: promptForLlm,
+			skills,
+			previousWorkflow,
+			model: flags.model,
+			apiKey: flags.apiKey,
+			llm: opts.llm,
+		});
+		const result = validateWorkflow(yaml);
+		if (result.valid) {
+			lastErrors = [];
+			break;
+		}
+		lastErrors = result.errors;
+		if (attempt < MAX_RETRIES) {
+			promptForLlm =
+				`${flags.prompt.trim()}\n\nThe previous attempt failed schema validation. Fix these errors and return the full YAML again:\n` +
+				result.errors.map((e) => `- ${e}`).join("\n");
+		}
+	}
+
+	if (lastErrors.length > 0) {
+		console.error(RED("\nWorkflow validation failed after retries:"));
+		for (const e of lastErrors) console.error(RED(`  - ${e}`));
+		console.error(DIM("\nLast generated YAML:\n"));
+		console.error(yaml);
+		throw new Error("Validation failed after retries");
+	}
+
+	if (flags.dryRun) {
+		process.stdout.write(yaml.endsWith("\n") ? yaml : yaml + "\n");
+		return { yaml };
+	}
+
+	// Parse the validated YAML to get the workflow name for the file path.
+	const validated = validateWorkflow(yaml).data!;
+	const slug = slugify(validated.name);
+	const workflowsDir = join(agentDir, "workflows");
+	await mkdir(workflowsDir, { recursive: true });
+	const filePath = join(workflowsDir, `${slug}.yaml`);
+	await writeFile(filePath, yaml.endsWith("\n") ? yaml : yaml + "\n", "utf-8");
+	console.error(GREEN(`\nWrote workflow to ${filePath}`));
+	return { filePath, yaml };
+}
+
+export async function handleWorkflowCommand(argv: string[]): Promise<void> {
+	// argv is the raw process.argv tail starting at the 'workflow' token.
+	// argv[0] === "workflow"; argv[1] is the sub-command.
+	const sub = argv[1];
+	if (!sub || sub === "-h" || sub === "--help") {
+		printHelp();
+		return;
+	}
+	if (sub !== "generate") {
+		console.error(RED(`Unknown subcommand: ${sub}`));
+		printHelp();
+		process.exit(2);
+	}
+	const flags = parseFlags(argv.slice(2));
+	try {
+		await runGenerate({ flags });
+	} catch (err: any) {
+		console.error(RED(`\nError: ${err?.message ?? String(err)}`));
+		process.exit(1);
+	}
+}

src/index.ts

@@ -22,6 +22,7 @@ import { initLocalSession } from "./session.js";
 import type { LocalSession } from "./session.js";
 import { startVoiceServer } from "./voice/server.js";
 import { handlePluginCommand } from "./plugin-cli.js";
+import { handleWorkflowCommand } from "./commands/workflow.js";
 import { context as otelContext } from "@opentelemetry/api";
 import {
 	initTelemetry,
@@ -301,6 +302,12 @@ async function ensureRepo(dir: string, model?: string): Promise<string> {
 }
 
 async function main(): Promise<void> {
+	// Handle workflow subcommand: gitclaw workflow <generate|...>
+	if (process.argv[2] === "workflow") {
+		await handleWorkflowCommand(process.argv.slice(2));
+		return;
+	}
+
 	// Handle plugin subcommand: gitclaw plugin <install|list|remove|...>
 	if (process.argv[2] === "plugin") {
 		const allArgs = process.argv.slice(3);