Introduce component-based licensing: Serena GPL-3.0-or-later, SolidLSP MIT

The repository is licensed per component. SolidLSP (src/solidlsp,
test/solidlsp, test/resources) remains MIT-licensed and independently
reusable; the Serena application (src/serena, src/interprompt, scripts,
test/serena, docs) is licensed under GPL-3.0-or-later starting with the v2
licensing transition. The change is not retroactive: all releases and
commits up to v1.7.0 / 74c38a65 (tag mit-final) remain available under MIT.

Since MIT is GPL-compatible, a distribution combining both (such as the
serena-agent package) is as a whole subject to GPL-3.0-or-later, while the
SolidLSP files themselves stay MIT and can be extracted and used separately
under MIT terms. The distribution metadata therefore declares
GPL-3.0-or-later, with both license texts shipped alongside it.

Serena originally began under the GPL (v2) and was switched to MIT in
May 2025 following community requests. We consider that change a mistake;
the substantial changes in v2 make this the appropriate time to revert it.
We want the best version of Serena to remain free.

Changes:
* LICENSE is now the licensing overview; canonical license texts live in
  LICENSES/ (MIT.txt is the previous LICENSE verbatim, GPL-3.0-or-later.txt
  is the unmodified FSF text)
* pyproject.toml declares the PEP 639 license expression
  "GPL-3.0-or-later" and bundles LICENSE and LICENSES/* as license files;
  the deprecated MIT classifier is dropped and flake.nix declares gpl3Plus;
  README has per-component license badges and a License section
* SPDX-License-Identifier headers in all Python sources under src/ and
  scripts/, added by the new idempotent scripts/add_spdx_headers.py, which
  gen_prompt_factory.py also uses to keep the header on the generated
  module; existing third-party notices are preserved
* CLA.md: Contributor License Agreement (contributor retains copyright;
  grants a perpetual, irrevocable license including relicensing under any
  terms, incl. proprietary/commercial; patent grant; authority
  representations), to be enforced repository-wide via cla-assistant.io
* CONTRIBUTING.md, PR template and a new docs page explain the licensing
  boundary and the CLA workflow

scripts/add_spdx_headers.py

@@ -0,0 +1,95 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+"""
+Adds SPDX-License-Identifier headers to Python source files according to the component
+licensing structure documented in LICENSE.
+
+Idempotent: files that already contain an SPDX identifier are left untouched.
+Existing copyright notices and module docstrings are never modified; the identifier is
+inserted after any shebang/encoding lines and after a leading module docstring (if present).
+"""
+
+import ast
+import sys
+from dataclasses import dataclass
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parent.parent
+SPDX_PREFIX = "# SPDX-License-Identifier:"
+
+
+@dataclass(frozen=True)
+class LicensedTree:
+    """A directory tree whose Python files fall under a single license."""
+
+    relative_path: str
+    spdx_id: str
+
+
+TREES = [
+    LicensedTree("src/solidlsp", "MIT"),
+    LicensedTree("src/serena", "GPL-3.0-or-later"),
+    LicensedTree("src/interprompt", "GPL-3.0-or-later"),
+    LicensedTree("scripts", "GPL-3.0-or-later"),
+]
+
+
+def _header_end_line(source: str) -> int:
+    """
+    Determines the 0-based line index at which the SPDX line is to be inserted, i.e. after
+    shebang/encoding lines and after a leading module docstring.
+    """
+    lines = source.splitlines(keepends=True)
+    idx = 0
+    while idx < len(lines) and (lines[idx].startswith("#!") or (lines[idx].startswith("#") and "coding" in lines[idx])):
+        idx += 1
+    try:
+        module = ast.parse(source)
+    except SyntaxError:
+        return idx
+    if (
+        module.body
+        and isinstance(module.body[0], ast.Expr)
+        and isinstance(module.body[0].value, ast.Constant)
+        and isinstance(module.body[0].value.value, str)
+    ):
+        return max(idx, module.body[0].end_lineno)
+    return idx
+
+
+def add_header(path: Path, spdx_id: str) -> bool:
+    """Adds the SPDX header to the given file; returns whether the file was modified."""
+    with path.open(encoding="utf-8", newline="") as f:
+        source = f.read()
+    if SPDX_PREFIX in source:
+        return False
+
+    # keep empty files (e.g. package markers) untouched
+    if not source.strip():
+        return False
+
+    # insert header, keeping the file's newline convention
+    newline = "\r\n" if "\r\n" in source else "\n"
+    lines = source.splitlines(keepends=True)
+    idx = _header_end_line(source)
+    header = f"{SPDX_PREFIX} {spdx_id}{newline}"
+    if idx < len(lines) and lines[idx].strip() != "":
+        header += newline
+    lines.insert(idx, header)
+    path.write_text("".join(lines), encoding="utf-8", newline="")
+    return True
+
+
+def main() -> None:
+    modified = 0
+    for tree in TREES:
+        for path in sorted((ROOT / tree.relative_path).rglob("*.py")):
+            if "__pycache__" in path.parts:
+                continue
+            if add_header(path, tree.spdx_id):
+                modified += 1
+                print(f"{tree.spdx_id:18} {path.relative_to(ROOT)}")
+    print(f"{modified} file(s) modified", file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()

scripts/agno_agent.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
 from agno.models.anthropic.claude import Claude
 from agno.models.google.gemini import Gemini
 from agno.os import AgentOS

scripts/build_news_json.py

@@ -7,6 +7,7 @@ Usage:
 This reads all .html files from the `news/` directory and creates
 `news/news.json` containing a mapping of news IDs to HTML content strings.
 """
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 import json
 import os

scripts/bump_version.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
 from __future__ import annotations
 
 import logging

scripts/demo_cli_call.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
 from serena.cli import top_level
 
 if __name__ == "__main__":

scripts/demo_diagnostics.py

@@ -5,6 +5,7 @@ The script creates a temporary Python file inside this repository, introduces on
 shows file and symbol diagnostics, then introduces another warning and verifies that the
 second edit reports only the newly introduced warning.
 """
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 import json
 import shutil

scripts/demo_find_defining_symbol.py

@@ -1,6 +1,7 @@
 """
 Demonstrates both defining-symbol tools on the Python test repository.
 """
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 import json
 import re

scripts/demo_find_implementing_symbol.py

@@ -1,6 +1,7 @@
 """
 Demonstrates FindImplementationsTool on the Go test repository.
 """
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 import json
 from pathlib import Path

scripts/demo_progressive_tool_shortening.py

@@ -5,6 +5,7 @@ printing the full result, then progressively tighter max_answer_chars
 to show the successive shortening stages. Both LSP and JetBrains backends
 are tested (JB is skipped if no IDE is running).
 """
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 import json
 from pprint import pprint

scripts/demo_run_tools.py

@@ -2,6 +2,7 @@
 This script demonstrates how to use Serena's tools locally, useful
 for testing or development. Here the tools will be operation the serena repo itself.
 """
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 import json
 from pathlib import Path

scripts/gen_prompt_factory.py

@@ -1,9 +1,11 @@
 """
 Autogenerates the `prompt_factory.py` module
 """
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 from pathlib import Path
 
+from add_spdx_headers import add_header
 from sensai.util import logging
 
 from interprompt import autogenerate_prompt_factory_module
@@ -13,11 +15,15 @@ log = logging.getLogger(__name__)
 
 
 def main():
+    target_module_path = Path(REPO_ROOT) / "src" / "serena" / "generated" / "generated_prompt_factory.py"
     autogenerate_prompt_factory_module(
         prompts_dir=PROMPT_TEMPLATES_DIR_INTERNAL,
-        target_module_path=str(Path(REPO_ROOT) / "src" / "serena" / "generated" / "generated_prompt_factory.py"),
+        target_module_path=str(target_module_path),
     )
 
+    # re-add the license header, which the (externally maintained) generator template does not include
+    add_header(target_module_path, "GPL-3.0-or-later")
+
 
 if __name__ == "__main__":
     logging.run_main(main)

scripts/live_test_grok.py

@@ -32,6 +32,7 @@ Usage::
     uv run python scripts/live_test_grok.py --skip-unit   # skip the pytest smoke run
     uv run python scripts/live_test_grok.py --help        # all options
 """
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 import argparse
 import json

scripts/mcp_server.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
 from serena.cli import top_level
 
 if __name__ == "__main__":

scripts/memory_graph.py

@@ -1,4 +1,5 @@
 """Generates a GraphML file of the memory reference structure for a given project."""
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 import argparse
 import xml.etree.ElementTree as ET

scripts/print_language_list.py

@@ -1,6 +1,7 @@
 """
 Prints the list of supported languages, for use in the project.yml template
 """
+# SPDX-License-Identifier: GPL-3.0-or-later
 
 from solidlsp.ls_config import LanguageServerId
 

scripts/print_mode_context_options.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
 from serena.config.context_mode import SerenaAgentContext, SerenaAgentMode
 
 if __name__ == "__main__":

scripts/print_tool_overview.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
 from serena.agent import ToolRegistry
 
 if __name__ == "__main__":

scripts/profile_tool_call.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
 import cProfile
 from pathlib import Path
 from typing import Literal

scripts/update_downloaded_dependency_hashes.py

@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
 from sensai.util import logging
 
 from solidlsp.language_servers.eclipse_jdtls import EclipseJDTLS