feat: ecosystem submodules, CI improvements, and EasyCLA compliance

.claude/.gitignore

@@ -1,2 +1,2 @@
-# Local settings that shouldn't be committed
-settings.local.json
+# Local settings that shouldn't be committed
+settings.local.json

.config/mise/config.toml

@@ -24,6 +24,24 @@ bun = "1.3.8"
 # JSON Schema CLI (https://github.com/sourcemeta/jsonschema)
 jsonschema = "latest"
 
+# ===== Initialization Tasks =====
+[tasks.init]
+description = "Initialize development environment. Use --ci for CI environments."
+run = """
+#!/usr/bin/env bash
+set -e
+
+if [[ "$1" == "--ci" ]]; then
+    # CI mode: shallow clone submodules for faster checkout
+    echo "Initializing in CI mode (shallow submodules)..."
+    git submodule update --init --recursive --depth 1
+else
+    # Development mode: full clone
+    echo "Initializing development environment..."
+    git submodule update --init --recursive
+fi
+"""
+
 # ===== Formatting Tasks =====
 [tasks.fmt]
 description = "Format all code"
@@ -130,3 +148,33 @@ description = "Run TypeScript type checking on website"
 run = "npm run typecheck"
 dir = "website"
 depends = ["website:install"]
+
+# ===== Submodule Tasks =====
+[tasks."submodules:init"]
+description = "Initialize and fetch all submodules (first-time or after clone without --recurse-submodules)"
+run = "git submodule update --init --recursive"
+
+[tasks."submodules:update"]
+description = "Update each submodule to the commit recorded in the superproject"
+run = "git submodule update --recursive"
+
+[tasks."submodules:status"]
+description = "Show submodule status (commit, branch, dirty state)"
+run = "git submodule status"
+
+[tasks."submodules:pull"]
+description = "Pull latest in each submodule (superproject ref unchanged until you commit)"
+run = "git submodule foreach 'git pull origin main'"
+
+[tasks."submodules:add"]
+description = "Add a new submodule under ecosystem/. Usage: mise run submodules:add -- <name> [url]"
+run = "python .config/mise/tasks/submodules/add.py"
+
+# ===== CI Tasks =====
+[tasks."ci:prepare-cli-workspace"]
+description = "Prepare Cargo workspace for CLI-only build (excludes morphir-live)"
+run = "python .config/mise/tasks/ci/prepare_cli_workspace.py"
+
+[tasks."ci:validate-docs"]
+description = "Validate documentation files"
+run = "python .config/mise/tasks/ci/validate_docs.py"

.config/mise/tasks/ci/prepare_cli_workspace.py

@@ -0,0 +1,81 @@
+#!/usr/bin/env python3
+"""
+Prepare Cargo workspace for morphir CLI build.
+
+This script modifies Cargo.toml to exclude morphir-live (which has conflicting
+dependencies) and regenerates the lockfile for CLI-only builds.
+
+Usage:
+    python prepare_cli_workspace.py
+"""
+
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+
+def main() -> int:
+    """Prepare workspace for CLI-only build."""
+    repo_root = Path(__file__).resolve().parents[4]
+    cargo_toml = repo_root / "Cargo.toml"
+    cargo_lock = repo_root / "Cargo.lock"
+
+    print("Preparing workspace for morphir CLI build...")
+
+    # Read current Cargo.toml
+    content = cargo_toml.read_text()
+
+    # Update members to only include morphir crate
+    content = re.sub(
+        r'members\s*=\s*\["crates/\*"\]',
+        'members = ["crates/morphir"]',
+        content,
+    )
+
+    # Update default-members to only include morphir
+    content = re.sub(
+        r'default-members\s*=\s*\["crates/morphir-live",\s*"crates/morphir"\]',
+        'default-members = ["crates/morphir"]',
+        content,
+    )
+
+    # Write modified Cargo.toml
+    cargo_toml.write_text(content)
+    print("  Updated Cargo.toml to exclude morphir-live")
+
+    # Remove existing lockfile
+    if cargo_lock.exists():
+        cargo_lock.unlink()
+        print("  Removed existing Cargo.lock")
+
+    # Generate fresh lockfile
+    print("  Generating fresh lockfile...")
+    result = subprocess.run(
+        ["cargo", "generate-lockfile"],
+        cwd=repo_root,
+        capture_output=True,
+        text=True,
+    )
+    if result.returncode != 0:
+        print(f"Error generating lockfile: {result.stderr}", file=sys.stderr)
+        return 1
+
+    # Update extism to latest compatible version
+    print("  Updating extism to latest compatible version...")
+    result = subprocess.run(
+        ["cargo", "update", "-p", "extism"],
+        cwd=repo_root,
+        capture_output=True,
+        text=True,
+    )
+    if result.returncode != 0:
+        print(f"Warning: Could not update extism: {result.stderr}", file=sys.stderr)
+        # Don't fail - extism update is optional
+
+    print("Workspace prepared for CLI build!")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.config/mise/tasks/ci/validate_docs.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+"""
+Validate documentation files.
+
+This script performs quick validation checks on markdown and documentation
+files without making slow HTTP requests to verify external links.
+
+Usage:
+    python validate_docs.py
+"""
+
+import sys
+from pathlib import Path
+
+
+def main() -> int:
+    """Validate documentation files."""
+    repo_root = Path(__file__).resolve().parents[4]
+
+    print("Validating documentation files...")
+
+    # Collect markdown files
+    md_files = list(repo_root.glob("**/*.md"))
+
+    # Exclude common non-doc directories
+    excluded_dirs = {".git", "node_modules", "target", ".mise", "dist", "build"}
+    md_files = [
+        f
+        for f in md_files
+        if not any(excluded in f.parts for excluded in excluded_dirs)
+    ]
+
+    if not md_files:
+        print("  No markdown files found")
+        return 0
+
+    print(f"  Found {len(md_files)} markdown files")
+
+    # Quick validation - just verify files are readable
+    errors = []
+    for md_file in md_files[:50]:  # Check first 50 files to keep it fast
+        try:
+            content = md_file.read_text(encoding="utf-8")
+            # Basic check: file is not empty or just whitespace
+            if not content.strip():
+                errors.append(f"  Empty file: {md_file.relative_to(repo_root)}")
+        except UnicodeDecodeError:
+            errors.append(f"  Encoding error: {md_file.relative_to(repo_root)}")
+        except Exception as e:
+            errors.append(f"  Error reading {md_file.relative_to(repo_root)}: {e}")
+
+    if errors:
+        print("\nValidation issues:")
+        for error in errors:
+            print(error)
+        # Don't fail on empty files, just warn
+        print("\nValidation completed with warnings")
+    else:
+        print("  All checked files are valid")
+
+    print("Documentation validation passed!")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.config/mise/tasks/submodules/add.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+"""
+Add a new git submodule under ecosystem/.
+
+Usage: mise run submodules:add -- <name> [url]
+  name: Submodule directory name (e.g. morphir-go, morphir-elm). Required.
+  url:  Clone URL. If omitted, defaults to https://github.com/finos/<name>.git
+
+Example:
+  mise run submodules:add -- morphir-go
+  mise run submodules:add -- morphir-elm https://github.com/finos/morphir-elm.git
+"""
+
+from __future__ import annotations
+
+import os
+import re
+import subprocess
+import sys
+
+
+def main() -> int:
+    args = [a for a in sys.argv[1:] if a != "--"]
+    if not args:
+        print("Usage: mise run submodules:add -- <name> [url]", file=sys.stderr)
+        print("  name: submodule directory under ecosystem/ (e.g. morphir-go)", file=sys.stderr)
+        print("  url:  optional; defaults to https://github.com/finos/<name>.git", file=sys.stderr)
+        return 1
+
+    name = args[0].strip()
+    if not name:
+        print("Error: name cannot be empty", file=sys.stderr)
+        return 1
+
+    # Basic sanity: name should look like a repo name (no path separators, no scheme)
+    if re.search(r"[/\\:]", name) or name.startswith("."):
+        print("Error: name should be a simple directory name (e.g. morphir-go)", file=sys.stderr)
+        return 1
+
+    url = args[1].strip() if len(args) > 1 else f"https://github.com/finos/{name}.git"
+
+    repo_root = subprocess.run(
+        ["git", "rev-parse", "--show-toplevel"],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    if repo_root.returncode != 0:
+        print("Error: must run from inside a git repository", file=sys.stderr)
+        return 1
+
+    root = repo_root.stdout.strip()
+    ecosystem_dir = os.path.join(root, "ecosystem")
+    path = os.path.join(ecosystem_dir, name)
+
+    if not os.path.isdir(ecosystem_dir):
+        print(f"Error: ecosystem directory not found: {ecosystem_dir}", file=sys.stderr)
+        return 1
+
+    if os.path.exists(path):
+        print(f"Error: path already exists: {path}", file=sys.stderr)
+        return 1
+
+    cmd = ["git", "submodule", "add", url, f"ecosystem/{name}"]
+    print(f"Running: {' '.join(cmd)}")
+    result = subprocess.run(cmd, cwd=root)
+    if result.returncode != 0:
+        return result.returncode
+
+    print("")
+    print("Next: add the new submodule to ecosystem/README.md and ecosystem/AGENTS.md.")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.gitattributes

@@ -1,3 +1,6 @@
+# Normalize line endings to LF for cross-platform consistency (avoids CRLF/LF noise on Windows)
+* text=auto eol=lf
+
 *.lockb binary diff=lockb
 
 # Use bd merge for beads JSONL files