cassis-cli 1.5.0__tar.gz → 1.5.1__tar.gz

{cassis_cli-1.5.0 → cassis_cli-1.5.1}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: cassis-cli
-Version: 1.5.0
-Summary: Cassis CLI — run Cassis actions (ontology validation, upload and publish) from your CI pipelines
+Version: 1.5.1
+Summary: Validate, test and evaluate your Cassis ontology from your terminal, then publish it
 License: Apache-2.0
 License-File: LICENSE
 License-File: NOTICE
-Keywords: cassis,ontology,ci,text-to-sql
+Keywords: cassis,ontology,cli,ci,text-to-sql
 Author: Cassis
 Author-email: tech.admin@getcassis.com
 Requires-Python: >=3.10,<4.0
@@ -22,13 +22,13 @@ Description-Content-Type: text/markdown
 
 # Cassis CLI
 
-Run Cassis actions from your CI pipelines:
+Validate, test and evaluate your ontology from your terminal, then publish it. The same commands gate your pull requests in CI:
 
 - `cassis ontology check` validates the ontology files in your repository with the exact same checks as the Cassis GitHub PR check (YAML parsing, round-trip, import validation) — so you can gate merges in any CI system, not just GitHub. It then prints advisory **ontology quality warnings** for a tree that parsed — tables not assigned to any domain, joins/metrics pointing at unknown tables or columns, missing table/column descriptions (the same findings `ontology test` reports, without the agent run). In a checkout bound to a project (`project.yml`, `--project`, or `CASSIS_PROJECT_ID`), it also cross-checks the tree against the project's source schema: references to tables or columns the warehouse doesn't have print as **warnings** too — advisory only (the object may simply not be built or synced yet). Warnings never fail the check.
 - `cassis schema pull` downloads the data source's full source schema (as Cassis last introspected it) into `<base-path>/.schema.json` — a **gitignored** local snapshot (the command maintains the ignore entry) with a `pulled_at` stamp. The warehouse stays authoritative; the snapshot is a cache for offline/bulk work — e.g. a coding agent grepping table and column names during a modeling pass instead of paging through the MCP `get_source_schema` tool. Re-run to refresh.
 - `cassis ontology fmt` rewrites the ontology files in canonical form (think `black`/`gofmt` for the ontology), so hand or agent edits pass the round-trip check.
 - `cassis ontology upload` uploads the ontology files to a Cassis project (full replace) and, by default, publishes them immediately as a new version — so a merge to your main branch can go live in one CI step.
-- `cassis ontology pull` downloads the project's unpublished ontology into your repository checkout (full sync — stale local ontology files are pruned), so you can start editing from the current state, or bootstrap a repo that isn't git-synced (e.g. Bitbucket).
+- `cassis ontology pull` downloads the project's unpublished ontology into your repository checkout (full sync — stale local ontology files are pruned), so you can start editing from the current state, or bootstrap a repo that isn't git-synced (e.g. Bitbucket). Pruning only deletes files that are tracked and unmodified in git (i.e. restorable with `git checkout`); untracked or locally modified files are kept and listed, and every deleted path is printed.
 - `cassis ontology pull` and `cassis ontology fmt` also write `<base-path>/AGENTS.md`, the Cassis ontology modeling guide, into the checkout (default `cassis/AGENTS.md`) — a managed file (generated banner; the CLI overwrites local edits) so a repo-aware coding agent loads current Cassis modeling doctrine by convention. It sits inside the ontology directory but is not part of the ontology tree (which is the YAML files plus the domain Markdown files `domains/**/README.md`), so it is never uploaded, validated, or pruned. Commit it alongside your ontology changes. The guide text ships inside the CLI package, so its version tracks the **installed cassis-cli version** — upgrade the CLI (`pip install -U cassis-cli`) and re-run `fmt` to pick up doctrine updates; an unpinned `pip install cassis-cli` in CI gets them automatically. The banner stamps a doctrine version, and the CLI never *downgrades* the file: if the checkout's `AGENTS.md` was written by a newer doctrine (a newer CLI, or Cassis itself on a publish), `fmt`/`pull` leave it in place, print an upgrade notice, and `fmt --check` still passes.
 - The CLI identifies itself to the API (`User-Agent: cassis-cli/<version>`), and successful API responses advertise the newest published version — when you are behind, commands print a one-line upgrade notice on stderr (purely informational; output and exit codes are unchanged).
 - `cassis eval run` runs the project's eval suite against your local ontology files (scored in-memory — nothing is pushed to Cassis) and prints per-question results, so you can test the changes on your git branch before merging.
@@ -73,7 +73,8 @@ cassis ontology check
 cassis ontology check /path/to/checkout
 
 # Download the project's unpublished ontology into the checkout (full sync;
-# review with git diff — pass --no-prune to keep local files it would delete):
+# review with git diff — untracked/modified files are never deleted, and
+# --no-prune keeps even the tracked stale files it would otherwise delete):
 cassis ontology pull --project 019f0000-0000-7000-8000-000000000000
 
 # Upload the ontology to a project and publish it immediately:
@@ -193,9 +194,9 @@ cassis ontology fmt --check
 | 3    | Transport/API error (unreachable API, invalid key, inaccessible project, unexpected response), another run already active, out of credits, or `--timeout` reached |
 
 Commands that send the local tree (`check`, `fmt`, `upload`, `eval run`, `test`) accept up to
-2000 ontology files / 5 MB total — far above real ontologies (a few hundred small
-files). Beyond that the CLI fails fast with exit 2 before uploading anything;
-double-check `--base-path` if you hit it.
+20,000 ontology files / 100 MB total (path + content bytes) — sized for ontologies of
+roughly 10,000 modeled tables. Beyond that the CLI fails fast with exit 2 before
+uploading anything; double-check `--base-path` if you hit it.
 
 `upload` replaces the project's entire ontology with the uploaded tree. A
 never-published project always goes live immediately on first upload (even

{cassis_cli-1.5.0 → cassis_cli-1.5.1}/README.md

@@ -1,12 +1,12 @@
 # Cassis CLI
 
-Run Cassis actions from your CI pipelines:
+Validate, test and evaluate your ontology from your terminal, then publish it. The same commands gate your pull requests in CI:
 
 - `cassis ontology check` validates the ontology files in your repository with the exact same checks as the Cassis GitHub PR check (YAML parsing, round-trip, import validation) — so you can gate merges in any CI system, not just GitHub. It then prints advisory **ontology quality warnings** for a tree that parsed — tables not assigned to any domain, joins/metrics pointing at unknown tables or columns, missing table/column descriptions (the same findings `ontology test` reports, without the agent run). In a checkout bound to a project (`project.yml`, `--project`, or `CASSIS_PROJECT_ID`), it also cross-checks the tree against the project's source schema: references to tables or columns the warehouse doesn't have print as **warnings** too — advisory only (the object may simply not be built or synced yet). Warnings never fail the check.
 - `cassis schema pull` downloads the data source's full source schema (as Cassis last introspected it) into `<base-path>/.schema.json` — a **gitignored** local snapshot (the command maintains the ignore entry) with a `pulled_at` stamp. The warehouse stays authoritative; the snapshot is a cache for offline/bulk work — e.g. a coding agent grepping table and column names during a modeling pass instead of paging through the MCP `get_source_schema` tool. Re-run to refresh.
 - `cassis ontology fmt` rewrites the ontology files in canonical form (think `black`/`gofmt` for the ontology), so hand or agent edits pass the round-trip check.
 - `cassis ontology upload` uploads the ontology files to a Cassis project (full replace) and, by default, publishes them immediately as a new version — so a merge to your main branch can go live in one CI step.
-- `cassis ontology pull` downloads the project's unpublished ontology into your repository checkout (full sync — stale local ontology files are pruned), so you can start editing from the current state, or bootstrap a repo that isn't git-synced (e.g. Bitbucket).
+- `cassis ontology pull` downloads the project's unpublished ontology into your repository checkout (full sync — stale local ontology files are pruned), so you can start editing from the current state, or bootstrap a repo that isn't git-synced (e.g. Bitbucket). Pruning only deletes files that are tracked and unmodified in git (i.e. restorable with `git checkout`); untracked or locally modified files are kept and listed, and every deleted path is printed.
 - `cassis ontology pull` and `cassis ontology fmt` also write `<base-path>/AGENTS.md`, the Cassis ontology modeling guide, into the checkout (default `cassis/AGENTS.md`) — a managed file (generated banner; the CLI overwrites local edits) so a repo-aware coding agent loads current Cassis modeling doctrine by convention. It sits inside the ontology directory but is not part of the ontology tree (which is the YAML files plus the domain Markdown files `domains/**/README.md`), so it is never uploaded, validated, or pruned. Commit it alongside your ontology changes. The guide text ships inside the CLI package, so its version tracks the **installed cassis-cli version** — upgrade the CLI (`pip install -U cassis-cli`) and re-run `fmt` to pick up doctrine updates; an unpinned `pip install cassis-cli` in CI gets them automatically. The banner stamps a doctrine version, and the CLI never *downgrades* the file: if the checkout's `AGENTS.md` was written by a newer doctrine (a newer CLI, or Cassis itself on a publish), `fmt`/`pull` leave it in place, print an upgrade notice, and `fmt --check` still passes.
 - The CLI identifies itself to the API (`User-Agent: cassis-cli/<version>`), and successful API responses advertise the newest published version — when you are behind, commands print a one-line upgrade notice on stderr (purely informational; output and exit codes are unchanged).
 - `cassis eval run` runs the project's eval suite against your local ontology files (scored in-memory — nothing is pushed to Cassis) and prints per-question results, so you can test the changes on your git branch before merging.
@@ -51,7 +51,8 @@ cassis ontology check
 cassis ontology check /path/to/checkout
 
 # Download the project's unpublished ontology into the checkout (full sync;
-# review with git diff — pass --no-prune to keep local files it would delete):
+# review with git diff — untracked/modified files are never deleted, and
+# --no-prune keeps even the tracked stale files it would otherwise delete):
 cassis ontology pull --project 019f0000-0000-7000-8000-000000000000
 
 # Upload the ontology to a project and publish it immediately:
@@ -171,9 +172,9 @@ cassis ontology fmt --check
 | 3    | Transport/API error (unreachable API, invalid key, inaccessible project, unexpected response), another run already active, out of credits, or `--timeout` reached |
 
 Commands that send the local tree (`check`, `fmt`, `upload`, `eval run`, `test`) accept up to
-2000 ontology files / 5 MB total — far above real ontologies (a few hundred small
-files). Beyond that the CLI fails fast with exit 2 before uploading anything;
-double-check `--base-path` if you hit it.
+20,000 ontology files / 100 MB total (path + content bytes) — sized for ontologies of
+roughly 10,000 modeled tables. Beyond that the CLI fails fast with exit 2 before
+uploading anything; double-check `--base-path` if you hit it.
 
 `upload` replaces the project's entire ontology with the uploaded tree. A
 never-published project always goes live immediately on first upload (even

{cassis_cli-1.5.0 → cassis_cli-1.5.1}/cassis_cli/__init__.py

@@ -1,4 +1,7 @@
-"""Cassis CLI — run Cassis actions from your CI pipelines."""
+"""Validate, test and evaluate your ontology from your terminal, then publish it.
+
+The same commands gate your pull requests in CI.
+"""
 
 from importlib.metadata import PackageNotFoundError, version
 

{cassis_cli-1.5.0 → cassis_cli-1.5.1}/cassis_cli/common.py

@@ -2,7 +2,9 @@
 
 from __future__ import annotations
 
+import os
 import re
+import subprocess
 from pathlib import Path
 from typing import Optional
 from uuid import UUID
@@ -20,10 +22,12 @@ EXIT_USAGE = 2
 EXIT_TRANSPORT = 3
 
 # Request ceilings of the /api/ci file-tree endpoints, mirrored so oversized
-# trees fail fast with a clear message before any upload. Source of truth:
+# trees fail fast with a clear message before any upload. Sized for ~10,000
+# modeled tables (a 6,000-table tree is ~8,600 files / ~60 MB). Source of
+# truth: backend/app/services/ontology_check.py, enforced by
 # backend/app/schemas/ci.py (the server's 422 remains the backstop).
-MAX_FILES = 2000
-MAX_TOTAL_BYTES = 5 * 1024 * 1024
+MAX_FILES = 20_000
+MAX_TOTAL_BYTES = 100 * 1024 * 1024
 
 
 def is_ontology_file(rel_path: str) -> bool:
@@ -41,6 +45,42 @@ def is_ontology_file(rel_path: str) -> bool:
     return rel_path.startswith("domains/") and rel_path.endswith("/README.md")
 
 
+def git_file_states(directory: Path) -> Optional[tuple[set[str], set[str]]]:
+    """(tracked, dirty) path sets for files under ``directory``, relative to it.
+
+    ``tracked`` is every git-tracked file below the directory; ``dirty`` the
+    subset whose working-tree content differs from the index (modified or
+    missing). Returns ``None`` when the directory is not inside a git work tree
+    or git is unavailable — callers must then treat every file as
+    unrecoverable and refuse to delete it.
+    """
+    # GIT_OPTIONAL_LOCKS=0: read-only queries must not take the index lock
+    # (and fail) when another git process is running.
+    env = {**os.environ, "GIT_OPTIONAL_LOCKS": "0"}
+    try:
+        tracked_proc = subprocess.run(
+            ["git", "ls-files", "-z"],
+            cwd=directory,
+            env=env,
+            capture_output=True,
+            check=True,
+            text=True,
+        )
+        dirty_proc = subprocess.run(
+            ["git", "ls-files", "-z", "--modified"],
+            cwd=directory,
+            env=env,
+            capture_output=True,
+            check=True,
+            text=True,
+        )
+    except (OSError, subprocess.CalledProcessError, UnicodeDecodeError):
+        return None
+    tracked = {p for p in tracked_proc.stdout.split("\0") if p}
+    dirty = {p for p in dirty_proc.stdout.split("\0") if p}
+    return tracked, dirty
+
+
 def is_legacy_domain_file(rel_path: str) -> bool:
     """Whether a base-relative path is a legacy (pre-Markdown) domain file.
 
@@ -84,7 +124,7 @@ def read_project_id_from_dir(ontology_dir: Path) -> Optional[str]:
     """Return the ``project_id`` recorded in ``<ontology_dir>/project.yml``, or None."""
     try:
         text = (ontology_dir / "project.yml").read_text(encoding="utf-8")
-    except (OSError, UnicodeDecodeError) as _exc:  # `as` keeps black from stripping the parens (3.14-only syntax)
+    except (OSError, UnicodeDecodeError):
         return None
     for line in text.splitlines():
         match = _PROJECT_ID_LINE.match(line.strip())
@@ -171,7 +211,9 @@ def collect_tree(path: Path, base_path: str) -> "tuple[dict[str, str], str]":
         typer.secho(f"No ontology files found under {ontology_dir}.", fg=typer.colors.RED, err=True)
         raise typer.Exit(EXIT_USAGE)
 
-    total_bytes = sum(len(content.encode()) for content in files.values())
+    # Count path bytes too, exactly like the server's _validate_tree_files —
+    # a tree accepted here must never come back as a server-side 422.
+    total_bytes = sum(len(rel.encode()) + len(content.encode()) for rel, content in files.items())
     if len(files) > MAX_FILES or total_bytes > MAX_TOTAL_BYTES:
         typer.secho(
             f"Ontology tree too large: {len(files)} files / {total_bytes / (1024 * 1024):.1f} MB "

{cassis_cli-1.5.0 → cassis_cli-1.5.1}/cassis_cli/main.py

@@ -14,7 +14,10 @@ from cassis_cli.verify import verify
 
 app = typer.Typer(
     no_args_is_help=True,
-    help="Cassis CLI — run Cassis actions from your CI pipelines.",
+    help=(
+        "Cassis CLI: validate, test and evaluate your ontology from your terminal, "
+        "then publish it. The same commands gate your pull requests in CI."
+    ),
 )
 app.add_typer(ontology_app, name="ontology")
 app.add_typer(eval_app, name="eval")

{cassis_cli-1.5.0 → cassis_cli-1.5.1}/cassis_cli/ontology.py

@@ -28,6 +28,7 @@ from cassis_cli.common import (
 )
 from cassis_cli.common import collect_files as _collect_files
 from cassis_cli.common import collect_tree as _collect_tree
+from cassis_cli.common import git_file_states as _git_file_states
 from cassis_cli.common import is_legacy_domain_file as _is_legacy_domain_file
 from cassis_cli.common import require_api_key as _require_api_key
 from cassis_cli.common import resolve_project_id as _resolve_project_id
@@ -197,7 +198,11 @@ def pull(
     prune: bool = typer.Option(
         True,
         "--prune/--no-prune",
-        help="Delete local ontology files that no longer exist in the project's ontology (default: prune).",
+        help=(
+            "Delete local ontology files that no longer exist in the project's ontology "
+            "(default: prune). Only files that are tracked and unmodified in git are "
+            "deleted; untracked or locally modified files are always kept and reported."
+        ),
     ),
     json_output: bool = typer.Option(False, "--json", help="Print a JSON summary of written/deleted files."),
 ) -> None:
@@ -205,7 +210,9 @@ def pull(
 
     Writes the ontology tree under the export path (full sync: files are
     overwritten and, unless --no-prune, stale local ontology files are deleted,
-    so the checkout ends up matching the project exactly). Review the changes with
+    so the checkout ends up matching the project exactly). Pruning never touches
+    files git could not restore: untracked or locally modified files are kept
+    and listed, and every deleted path is named. Review the changes with
     git diff before committing. Exits 0 on success, 2 on usage errors, 3 on
     transport/API errors.
     """
@@ -243,15 +250,38 @@ def pull(
         written.append(rel)
 
     deleted: list[str] = []
+    kept: list[dict[str, str]] = []
     if prune and ontology_dir.is_dir():
         local = _collect_files(ontology_dir)
-        for rel in sorted(set(local) - set(files)):
-            try:
-                (ontology_dir / rel).unlink()
-            except OSError as exc:
-                typer.secho(f"Cannot delete {ontology_dir / rel}: {exc}", fg=typer.colors.RED, err=True)
-                raise typer.Exit(EXIT_USAGE) from exc
-            deleted.append(rel)
+        stale = sorted(set(local) - set(files))
+        if stale:
+            # Only delete what git can restore. An untracked or locally
+            # modified file is user work Cassis has never seen — pruning it
+            # would be unrecoverable data loss (#27).
+            states = _git_file_states(ontology_dir)
+            to_delete: list[str] = []
+            if states is None:
+                kept = [{"path": rel, "reason": "not in a git repository"} for rel in stale]
+            else:
+                tracked, dirty = states
+                for rel in stale:
+                    if rel not in tracked:
+                        kept.append({"path": rel, "reason": "untracked in git"})
+                    elif rel in dirty:
+                        kept.append({"path": rel, "reason": "locally modified"})
+                    else:
+                        to_delete.append(rel)
+            if to_delete and not json_output:
+                typer.echo(f"Deleting {len(to_delete)} stale ontology file(s):")
+                for rel in to_delete:
+                    typer.echo(f"  {base_path}/{rel}")
+            for rel in to_delete:
+                try:
+                    (ontology_dir / rel).unlink()
+                except OSError as exc:
+                    typer.secho(f"Cannot delete {ontology_dir / rel}: {exc}", fg=typer.colors.RED, err=True)
+                    raise typer.Exit(EXIT_USAGE) from exc
+                deleted.append(rel)
 
     # Managed modeling guide: refresh AGENTS.md so a repo-aware agent loads
     # current Cassis doctrine. Not part of the ontology tree (YAML-only), so it
@@ -266,14 +296,31 @@ def pull(
         _warn_newer_guide(base_path)
 
     if json_output:
-        typer.echo(json.dumps({"written": written, "deleted": deleted, "guide_written": guide_written}, indent=2))
+        typer.echo(
+            json.dumps(
+                {"written": written, "deleted": deleted, "kept": kept, "guide_written": guide_written},
+                indent=2,
+            )
+        )
     else:
         summary = f"✓ Pulled {len(written)} files into {ontology_dir}"
         if deleted:
-            summary += f" ({len(deleted)} stale files deleted)"
+            summary += f" ({len(deleted)} stale files deleted, listed above)"
         if guide_written:
             summary += f"; wrote {base_path}/{GUIDE_FILENAME}"
         typer.secho(f"{summary}.", fg=typer.colors.GREEN)
+        if kept:
+            typer.secho(
+                f"Kept {len(kept)} local file(s) not in the project ontology "
+                "(only files tracked and unmodified in git are pruned):",
+                fg=typer.colors.YELLOW,
+            )
+            for entry in kept:
+                typer.secho(f"  {base_path}/{entry['path']} ({entry['reason']})", fg=typer.colors.YELLOW)
+            typer.secho(
+                "  Commit them if they are intentional, or delete them manually.",
+                fg=typer.colors.YELLOW,
+            )
         migrated = sum(1 for rel in deleted if _is_legacy_domain_file(rel))
         if migrated:
             typer.secho(

{cassis_cli-1.5.0 → cassis_cli-1.5.1}/cassis_cli/schema.py

@@ -134,7 +134,7 @@ def ensure_gitignored(ontology_dir: Path) -> None:
     gitignore = ontology_dir / ".gitignore"
     try:
         existing = gitignore.read_text(encoding="utf-8")
-    except (OSError, UnicodeDecodeError) as _exc:  # `as` keeps black from stripping the parens (3.14-only syntax)
+    except (OSError, UnicodeDecodeError):
         existing = ""
     if SNAPSHOT_FILENAME in existing.splitlines():
         return

{cassis_cli-1.5.0 → cassis_cli-1.5.1}/pyproject.toml

@@ -1,11 +1,11 @@
 [project]
 name = "cassis-cli"
-version = "1.5.0"
-description = "Cassis CLI — run Cassis actions (ontology validation, upload and publish) from your CI pipelines"
+version = "1.5.1"
+description = "Validate, test and evaluate your Cassis ontology from your terminal, then publish it"
 readme = "README.md"
 license = { text = "Apache-2.0" }
 authors = [{ name = "Cassis", email = "tech.admin@getcassis.com" }]
-keywords = ["cassis", "ontology", "ci", "text-to-sql"]
+keywords = ["cassis", "ontology", "cli", "ci", "text-to-sql"]
 classifiers = [
     "License :: OSI Approved :: Apache Software License",
     "Environment :: Console",
@@ -43,3 +43,10 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
+
+[tool.black]
+# The package ships for Python >=3.10 (see requires-python above): formatting
+# must target the floor, or black under the monorepo's 3.14 rewrites syntax
+# into 3.14-only forms (e.g. stripping parens from multi-exception `except`).
+line-length = 120
+target-version = ["py310"]