footprinter-cli 1.0.0rc2__tar.gz → 1.0.0rc4__tar.gz

{footprinter_cli-1.0.0rc2/footprinter_cli.egg-info → footprinter_cli-1.0.0rc4}/PKG-INFO

@@ -1,22 +1,29 @@
 Metadata-Version: 2.2
 Name: footprinter-cli
-Version: 1.0.0rc2
-Summary: Index your files, emails, browser history, and chats locally. Give AI agents controlled access via MCP.
+Version: 1.0.0rc4
+Summary: A local context layer for your files, browser history, chats, and email — searchable, user-owned, MCP-served.
 Author: SwellCity Group
 License: MIT
 Project-URL: Homepage, https://github.com/swellcitygroup/footprinter
 Project-URL: Repository, https://github.com/swellcitygroup/footprinter
 Project-URL: Issues, https://github.com/swellcitygroup/footprinter/issues
-Keywords: indexer,mcp,metadata,model-context-protocol,file-indexing,sqlite
-Classifier: Development Status :: 5 - Production/Stable
+Project-URL: Documentation, https://github.com/swellcitygroup/footprinter/blob/main/README.md
+Project-URL: Changelog, https://github.com/swellcitygroup/footprinter/blob/main/CHANGELOG.md
+Keywords: indexer,mcp,metadata,model-context-protocol,file-indexing,sqlite,context-engineering,personal-information-management
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX :: Linux
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Classifier: Topic :: System :: Archiving
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Topic :: Database
+Classifier: Topic :: Text Processing :: Indexing
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -47,11 +54,9 @@ Requires-Dist: httpx<1.0,>=0.27.0; extra == "dev"
 
 [![Tests](https://github.com/swellcitygroup/footprinter/actions/workflows/test.yml/badge.svg)](https://github.com/swellcitygroup/footprinter/actions/workflows/test.yml)
 
-**Index your files, conversations, browser history, and more through connector plugins. Search across everything. Give AI assistants structured context via [MCP](https://modelcontextprotocol.io/).**
+**A local context layer for your files, browser history, chats, and email — searchable, user-owned, and served to AI agents through [MCP](https://modelcontextprotocol.io/).**
 
-Every conversation with an AI assistant starts from zero. It doesn't know what files you've been editing, what you were researching yesterday, or what conversations you had last week. You either paste context in manually or the AI operates blind.
-
-Footprinter fixes that. It scans your work into a local SQLite database, links related items across sources, and exposes the result through MCP — so Claude Desktop, or any MCP-compatible assistant, can search your files, find related conversations, and understand the shape of your work. No copy-pasting. No cloud. Everything stays on your machine.
+Your work lives across a filesystem, a browser, an inbox, a chat history, and whatever other tools you reach for. Footprinter indexes those sources into a single local store, organizes them into the projects and groupings *you* define, and serves the result to AI agents through a governed access layer. You control what the agent can see. Everything stays on your machine.
 
 ## Install
 
@@ -95,6 +100,7 @@ Once configured, Claude can search your files, browse projects, and find related
 | **Local files** | Path, type, size, timestamps, content hash |
 | **Browser history** | Safari and Chrome — URLs, titles, visit times |
 | **Chat exports** | Claude and ChatGPT conversation exports |
+| **Email** | Subject, sender, recipients, body, timestamps — ingested via [connector plugins](#connectors) |
 | **Documents** | PDF, Word, Excel, PowerPoint content (with `[parse]` extra) |
 | **Semantic embeddings** | Conceptual similarity across all sources (with `[semantic]` extra) |
 
@@ -160,10 +166,10 @@ Sources are scanned into SQLite with bidirectional links connecting local files
 
 ## Documentation
 
-- [Interfaces](reference/interfaces.md) — CLI commands, MCP tools, Python API
-- [Data Model](reference/data-model.md) — database schema
-- [Pipeline](reference/pipeline.md) — indexing stages and configuration
-- [Access Control](reference/mcp-access-control.md) — MCP security model
+- [Interfaces](https://github.com/swellcitygroup/footprinter/blob/main/reference/interfaces.md) — CLI commands, MCP tools, Python API
+- [Data Model](https://github.com/swellcitygroup/footprinter/blob/main/reference/data-model.md) — database schema
+- [Pipeline](https://github.com/swellcitygroup/footprinter/blob/main/reference/pipeline.md) — indexing stages and configuration
+- [Access Control](https://github.com/swellcitygroup/footprinter/blob/main/reference/mcp-access-control.md) — MCP security model
 
 ## Contributing
 
@@ -200,7 +206,7 @@ pytest tests/ -v --tb=short
 4. Run the test suite
 5. Submit a PR targeting `main`
 
-Never commit API keys, tokens, or credentials. Report security vulnerabilities privately — see [SECURITY.md](SECURITY.md).
+Never commit API keys, tokens, or credentials. Report security vulnerabilities privately — see [SECURITY.md](https://github.com/swellcitygroup/footprinter/blob/main/SECURITY.md).
 
 ### Pull request expectations
 
@@ -211,13 +217,13 @@ Never commit API keys, tokens, or credentials. Report security vulnerabilities p
 
 All PRs are reviewed by the maintainer. Expect reviews within one week. CI must pass before review begins.
 
-No Contributor License Agreement required. By submitting a PR, you agree your contribution is licensed under the project's [MIT License](LICENSE).
+No Contributor License Agreement required. By submitting a PR, you agree your contribution is licensed under the project's [MIT License](https://github.com/swellcitygroup/footprinter/blob/main/LICENSE).
 
 ## Community
 
-- [Code of Conduct](CODE_OF_CONDUCT.md)
-- [Security Policy](SECURITY.md)
+- [Code of Conduct](https://github.com/swellcitygroup/footprinter/blob/main/CODE_OF_CONDUCT.md)
+- [Security Policy](https://github.com/swellcitygroup/footprinter/blob/main/SECURITY.md)
 
 ## License
 
-MIT — see [LICENSE](LICENSE).
+MIT — see [LICENSE](https://github.com/swellcitygroup/footprinter/blob/main/LICENSE).

{footprinter_cli-1.0.0rc2 → footprinter_cli-1.0.0rc4}/README.md

@@ -2,11 +2,9 @@
 
 [![Tests](https://github.com/swellcitygroup/footprinter/actions/workflows/test.yml/badge.svg)](https://github.com/swellcitygroup/footprinter/actions/workflows/test.yml)
 
-**Index your files, conversations, browser history, and more through connector plugins. Search across everything. Give AI assistants structured context via [MCP](https://modelcontextprotocol.io/).**
+**A local context layer for your files, browser history, chats, and email — searchable, user-owned, and served to AI agents through [MCP](https://modelcontextprotocol.io/).**
 
-Every conversation with an AI assistant starts from zero. It doesn't know what files you've been editing, what you were researching yesterday, or what conversations you had last week. You either paste context in manually or the AI operates blind.
-
-Footprinter fixes that. It scans your work into a local SQLite database, links related items across sources, and exposes the result through MCP — so Claude Desktop, or any MCP-compatible assistant, can search your files, find related conversations, and understand the shape of your work. No copy-pasting. No cloud. Everything stays on your machine.
+Your work lives across a filesystem, a browser, an inbox, a chat history, and whatever other tools you reach for. Footprinter indexes those sources into a single local store, organizes them into the projects and groupings *you* define, and serves the result to AI agents through a governed access layer. You control what the agent can see. Everything stays on your machine.
 
 ## Install
 
@@ -50,6 +48,7 @@ Once configured, Claude can search your files, browse projects, and find related
 | **Local files** | Path, type, size, timestamps, content hash |
 | **Browser history** | Safari and Chrome — URLs, titles, visit times |
 | **Chat exports** | Claude and ChatGPT conversation exports |
+| **Email** | Subject, sender, recipients, body, timestamps — ingested via [connector plugins](#connectors) |
 | **Documents** | PDF, Word, Excel, PowerPoint content (with `[parse]` extra) |
 | **Semantic embeddings** | Conceptual similarity across all sources (with `[semantic]` extra) |
 
@@ -115,10 +114,10 @@ Sources are scanned into SQLite with bidirectional links connecting local files
 
 ## Documentation
 
-- [Interfaces](reference/interfaces.md) — CLI commands, MCP tools, Python API
-- [Data Model](reference/data-model.md) — database schema
-- [Pipeline](reference/pipeline.md) — indexing stages and configuration
-- [Access Control](reference/mcp-access-control.md) — MCP security model
+- [Interfaces](https://github.com/swellcitygroup/footprinter/blob/main/reference/interfaces.md) — CLI commands, MCP tools, Python API
+- [Data Model](https://github.com/swellcitygroup/footprinter/blob/main/reference/data-model.md) — database schema
+- [Pipeline](https://github.com/swellcitygroup/footprinter/blob/main/reference/pipeline.md) — indexing stages and configuration
+- [Access Control](https://github.com/swellcitygroup/footprinter/blob/main/reference/mcp-access-control.md) — MCP security model
 
 ## Contributing
 
@@ -155,7 +154,7 @@ pytest tests/ -v --tb=short
 4. Run the test suite
 5. Submit a PR targeting `main`
 
-Never commit API keys, tokens, or credentials. Report security vulnerabilities privately — see [SECURITY.md](SECURITY.md).
+Never commit API keys, tokens, or credentials. Report security vulnerabilities privately — see [SECURITY.md](https://github.com/swellcitygroup/footprinter/blob/main/SECURITY.md).
 
 ### Pull request expectations
 
@@ -166,13 +165,13 @@ Never commit API keys, tokens, or credentials. Report security vulnerabilities p
 
 All PRs are reviewed by the maintainer. Expect reviews within one week. CI must pass before review begins.
 
-No Contributor License Agreement required. By submitting a PR, you agree your contribution is licensed under the project's [MIT License](LICENSE).
+No Contributor License Agreement required. By submitting a PR, you agree your contribution is licensed under the project's [MIT License](https://github.com/swellcitygroup/footprinter/blob/main/LICENSE).
 
 ## Community
 
-- [Code of Conduct](CODE_OF_CONDUCT.md)
-- [Security Policy](SECURITY.md)
+- [Code of Conduct](https://github.com/swellcitygroup/footprinter/blob/main/CODE_OF_CONDUCT.md)
+- [Security Policy](https://github.com/swellcitygroup/footprinter/blob/main/SECURITY.md)
 
 ## License
 
-MIT — see [LICENSE](LICENSE).
+MIT — see [LICENSE](https://github.com/swellcitygroup/footprinter/blob/main/LICENSE).

{footprinter_cli-1.0.0rc2 → footprinter_cli-1.0.0rc4}/footprinter/access.py

@@ -59,7 +59,7 @@ ENTITY_META: dict[str, dict[str, Any]] = {
         "has_permissions": True,
         "has_status": True,
         "has_project_id": True,
-        "has_client_id": False,
+        "has_client_id": True,
         "has_account": True,
         "path_column": "path",
     },
@@ -89,7 +89,7 @@ ENTITY_META: dict[str, dict[str, Any]] = {
         "has_permissions": False,
         "has_status": False,
         "has_project_id": True,
-        "has_client_id": False,
+        "has_client_id": True,
         "has_account": False,
         "path_column": "path",
     },
@@ -219,27 +219,40 @@ def _get_ids_for_scope(conn: sqlite3.Connection, scope: str) -> dict[str, list[i
 
     if prefix == "client":
         client_id = int(value)
-        result = {}
+        # Gather ids per entity type as dicts (insertion-ordered sets) so we
+        # can union the project cascade with direct client_id matches without
+        # double-stamping entities reachable via both paths.
+        id_sets: dict[str, dict[int, None]] = {}
         # The client itself
         row = conn.execute("SELECT id FROM clients WHERE id = ?", (client_id,)).fetchone()
         if row:
-            result["client"] = [row["id"]]
+            id_sets["client"] = {row["id"]: None}
         # Projects under this client
         proj_rows = conn.execute("SELECT id FROM projects WHERE client_id = ?", (client_id,)).fetchall()
         proj_ids = [r["id"] for r in proj_rows]
         if proj_ids:
-            result["project"] = proj_ids
-        # Recurse: gather children of each project
+            id_sets["project"] = {pid: None for pid in proj_ids}
+        # Cascade: children of each project
         for pid in proj_ids:
-            proj_children = _get_ids_for_scope(conn, f"project:{pid}")
-            for etype, ids in proj_children.items():
+            for etype, ids in _get_ids_for_scope(conn, f"project:{pid}").items():
                 if etype in ("project", "client"):
-                    continue  # already handled
-                if etype in result:
-                    result[etype].extend(ids)
-                else:
-                    result[etype] = list(ids)
-        return result
+                    continue
+                id_sets.setdefault(etype, {}).update({i: None for i in ids})
+        # Direct: entities with a client_id FK of their own (files, folders,
+        # emails, chats). Union with the cascade; dedup via the dict keys.
+        for etype, meta in ENTITY_META.items():
+            if etype in ("client", "project"):
+                continue
+            if not meta["has_client_id"]:
+                continue
+            table = meta["table"]
+            where = "client_id = ?"
+            if meta["has_status"]:
+                where += " AND status != 'removed'"
+            rows = conn.execute(f"SELECT id FROM {table} WHERE {where}", (client_id,)).fetchall()
+            if rows:
+                id_sets.setdefault(etype, {}).update({r["id"]: None for r in rows})
+        return {etype: list(ids) for etype, ids in id_sets.items()}
 
     # Single entity: file:42, email:10, etc.
     if prefix in ENTITY_META:

{footprinter_cli-1.0.0rc2 → footprinter_cli-1.0.0rc4}/footprinter/cli/__init__.py

@@ -29,15 +29,8 @@ def main(argv=None) -> None:
 
     if argv is None:
         argv = _sys.argv[1:]
-    from footprinter.paths import is_test_mode
     from footprinter.source_registry import ConfigError as _ConfigError
 
-    if is_test_mode():
-        print(
-            "\033[33m⚠ Test mode active — data at ~/.footprinter/.test-env/\033[0m",
-            file=_sys.stderr,
-        )
-
     from footprinter import __version__
     from footprinter.cli._common import FORMATTER
 

{footprinter_cli-1.0.0rc2 → footprinter_cli-1.0.0rc4}/footprinter/cli/_common.py

@@ -32,6 +32,11 @@ console = Console()
 
 class FootprinterHelpFormatter(argparse.RawDescriptionHelpFormatter):
     def _format_usage(self, usage, actions, groups, prefix):
+        # argparse calls this with prefix="" when computing subparser prog
+        # prefixes; returning the Usage-wrapped string there would compound
+        # "Usage: Usage: fp …" at every nesting level.
+        if prefix == "":
+            return self._prog
         return f"\nUsage: {self._prog}\n\n"
 
 

{footprinter_cli-1.0.0rc2 → footprinter_cli-1.0.0rc4}/footprinter/cli/ingest.py

@@ -244,6 +244,7 @@ def _run_with_logging(
     orchestrator,
     *,
     pipes=None,
+    refresh_source=None,
     mode,
     quiet=False,
     verbose=False,
@@ -253,7 +254,11 @@ def _run_with_logging(
 ):
     """Shared run helper: Rich Progress, file logging, run record, cleanup.
 
-    If ``pipes`` is not provided, defaults to the ``"all"`` pipeline.
+    Dispatch target:
+      - ``refresh_source`` set → orchestrator.run_refresh(refresh_source)
+      - ``pipes`` set → orchestrator.run_pipes(pipes)
+      - neither → orchestrator.run_pipeline("all")
+
     Shows a stage counter ("Stage 2/5: local_files") and intra-stage
     progress counts for adapters that report them via on_progress.
     """
@@ -299,8 +304,11 @@ def _run_with_logging(
         )
 
         # Resolve stage list for counter display
-        stage_list = pipes
-        if stage_list is None:
+        if refresh_source is not None:
+            stage_list = orchestrator.refresh_pipes.get(refresh_source, [])
+        elif pipes is not None:
+            stage_list = pipes
+        else:
             stage_list = orchestrator.runner.pipelines.get("all", [])
         total_stages = len(stage_list)
         stage_index = [0]  # mutable counter for closures
@@ -381,7 +389,14 @@ def _run_with_logging(
                 detail_part = f"  {details}" if details else ""
                 console.print(f"  {icon} {stage}{detail_part}  [dim]({elapsed:.1f}s)[/dim]")
 
-        if pipes:
+        if refresh_source is not None:
+            orchestrator.run_refresh(
+                refresh_source,
+                on_pipe_start=on_start,
+                on_pipe_end=on_end,
+                on_progress=on_progress,
+            )
+        elif pipes:
             orchestrator.run_pipes(
                 pipes,
                 on_pipe_start=on_start,
@@ -439,6 +454,13 @@ def _ingest_pipeline(args) -> None:
     verbose = getattr(args, "verbose", False)
     mode_str = "full" if orchestrator.full_mode else "incremental"
 
+    if pipes is not None:
+        try:
+            orchestrator.runner.validate_pipes(pipes)
+        except ValueError as e:
+            console.print(f"[red]Error:[/red] {e}")
+            sys.exit(1)
+
     try:
         _run_with_logging(
             orchestrator,
@@ -526,6 +548,7 @@ def _ingest_refresh(args) -> None:
     source = args.source
     valid_sources = list(refresh_pipes.keys())
 
+    # Early source validation (before lock/log setup) for a clean exit on bad input.
     if source not in refresh_pipes:
         console.print(f"[red]Error:[/red] Unknown refresh source: {source}")
         console.print(f"Valid sources: {', '.join(valid_sources)}")
@@ -538,9 +561,11 @@ def _ingest_refresh(args) -> None:
     mode_str = "full" if orchestrator.full_mode else "incremental"
 
     try:
+        # Route through orchestrator.run_refresh so access_resolution (a POST_PIPE)
+        # runs inline — run_pipes rejects POST_PIPES by design.
         _run_with_logging(
             orchestrator,
-            pipes=stages,
+            refresh_source=source,
             mode=mode_str,
             quiet=quiet,
             verbose=verbose,

{footprinter_cli-1.0.0rc2 → footprinter_cli-1.0.0rc4}/footprinter/cli/setup.py

@@ -7,8 +7,6 @@ Usage:
     fp setup --check          # Validate existing configuration
     fp setup --hooks          # Install git hooks (sets core.hooksPath)
     fp setup --reset          # Clear data and re-run wizard
-    fp setup --seed-samples   # Load sample data for exploration
-    fp setup --clear-samples  # Remove sample data
 """
 
 import argparse
@@ -50,15 +48,11 @@ from footprinter.cli._prompt import (
 from footprinter.cli.ingest import _run_with_logging
 from footprinter.ingest.orchestrator import DataPipelineOrchestrator
 from footprinter.paths import (
-    _TEST_ENV_NAME,
-    _TEST_MARKER_NAME,
     get_bundled_path,
     get_chroma_path,
     get_config_path,
     get_db_path,
     get_log_path,
-    get_real_home,
-    is_test_mode,
 )
 from footprinter.source_registry import ConfigError, get_config
 
@@ -196,10 +190,6 @@ def register(subparsers) -> None:
             "examples:\n"
             "  fp setup                   Run the interactive wizard\n"
             "  fp setup --check           Validate existing configuration\n"
-            "  fp setup --seed-samples    Load sample data for exploration\n"
-            "  fp setup --clear-samples   Remove sample data\n"
-            "  fp setup --test            Start throwaway test environment\n"
-            "  fp setup --endtest         End test mode\n"
             "  fp setup mcp --claude      Configure MCP for Claude Desktop\n"
             "  fp setup folders add ~/Work/newdir\n"
             "\n"
@@ -225,26 +215,6 @@ def register(subparsers) -> None:
         action="store_true",
         help="Clear database and vector store, then re-run setup wizard",
     )
-    parser.add_argument(
-        "--test",
-        action="store_true",
-        help="Start test mode — throwaway environment, zero risk to production data",
-    )
-    parser.add_argument(
-        "--endtest",
-        action="store_true",
-        help="End test mode — remove test environment, return to production data",
-    )
-    parser.add_argument(
-        "--seed-samples",
-        action="store_true",
-        help="Load sample data for exploration (tagged source='sample')",
-    )
-    parser.add_argument(
-        "--clear-samples",
-        action="store_true",
-        help="Remove all sample data and policies",
-    )
 
     subs = parser.add_subparsers(dest="setup_action", metavar="COMMAND", title="commands (one required)")
 
@@ -361,31 +331,10 @@ def _handle_setup_inner(args) -> None:
             console.print("[yellow]Usage: fp setup folders add|remove[/yellow]")
         return
 
-    if getattr(args, "seed_samples", False):
-        _do_seed_samples()
-        return
-
-    if getattr(args, "clear_samples", False):
-        _do_clear_samples()
-        return
-
-    if getattr(args, "test", False):
-        _start_test_mode()
-        return
-
-    if getattr(args, "endtest", False):
-        _end_test_mode()
-        return
-
     if getattr(args, "reset", False):
         db_path = get_db_path()
         chroma_path = get_chroma_path()
 
-        if is_test_mode():
-            console.print(
-                "[yellow]Note: you are in test mode — this will reset the test environment, not production.[/yellow]"
-            )
-
         console.print(
             "[bold yellow]This will delete all indexed data.[/bold yellow]\nConfig and credentials are preserved."
         )
@@ -417,101 +366,6 @@ def _handle_setup_inner(args) -> None:
         run_interactive_wizard()
 
 
-# ---------------------------------------------------------------------------
-# Sample data helpers
-# ---------------------------------------------------------------------------
-
-
-def _do_seed_samples() -> None:
-    """Seed sample data for exploration."""
-    from footprinter.cli._sample_seed import seed_samples
-
-    conn = _get_db_connection()
-    if conn is None:
-        console.print("[red]No database found.[/red] Run 'fp setup' first.")
-        return
-
-    try:
-        result = seed_samples(conn)
-        console.print(
-            f"[green]Sample data seeded:[/green] "
-            f"{result['files_created']} files, "
-            f"{result['policies_seeded']} policies"
-        )
-        console.print("  [dim]See: fp setup --clear-samples to remove[/dim]")
-    except Exception as e:  # Intentional broad catch: setup wizard step must not crash
-        console.print(f"[yellow]Sample seeding failed: {e}[/yellow]")
-    finally:
-        conn.close()
-
-
-def _do_clear_samples() -> None:
-    """Remove all sample data and policies."""
-    from footprinter.cli._sample_seed import clear_samples
-
-    conn = _get_db_connection()
-    if conn is None:
-        console.print("[red]No database found.[/red]")
-        return
-
-    try:
-        result = clear_samples(conn)
-        console.print(
-            f"[green]Sample data cleared:[/green] "
-            f"{result['files_removed']} files, "
-            f"{result['folders_removed']} folders, "
-            f"{result['policies_removed']} policies removed"
-        )
-    except Exception as e:  # Intentional broad catch: setup wizard step must not crash
-        console.print(f"[yellow]Sample clearing failed: {e}[/yellow]")
-    finally:
-        conn.close()
-
-
-# ---------------------------------------------------------------------------
-# Test mode helpers
-# ---------------------------------------------------------------------------
-
-
-def _start_test_mode() -> None:
-    """Create a throwaway test environment with its own data + config."""
-    real_home = get_real_home()
-    marker = real_home / _TEST_MARKER_NAME
-    test_env = real_home / _TEST_ENV_NAME
-
-    if marker.is_file():
-        console.print("[yellow]Test mode already active — wiping previous environment.[/yellow]")
-        if test_env.exists():
-            shutil.rmtree(test_env)
-
-    test_env.mkdir(parents=True, exist_ok=True)
-
-    # Copy production config so the test environment inherits settings.
-    prod_config = real_home / "config.yaml"
-    if prod_config.is_file():
-        shutil.copy2(prod_config, test_env / "config.yaml")
-
-    marker.write_text(str(test_env))
-    console.print(f"[green]Test mode started.[/green] Data at {test_env}")
-    run_interactive_wizard()
-
-
-def _end_test_mode() -> None:
-    """Remove test environment and marker, returning to production data."""
-    real_home = get_real_home()
-    marker = real_home / _TEST_MARKER_NAME
-
-    if not marker.is_file():
-        console.print("[dim]Not in test mode — nothing to do.[/dim]")
-        return
-
-    test_env_path = Path(marker.read_text().strip())
-    if test_env_path.exists():
-        shutil.rmtree(test_env_path)
-    marker.unlink()
-    console.print("[green]Test mode ended.[/green] Back to production data.")
-
-
 # ---------------------------------------------------------------------------
 # Standalone entry point (fp setup)
 # ---------------------------------------------------------------------------
@@ -572,17 +426,6 @@ def main():
     remove_parser = folders_sub.add_parser("remove", help="Remove a directory from config")
     remove_parser.add_argument("path", help="Directory path to remove")
 
-    parser.add_argument(
-        "--seed-samples",
-        action="store_true",
-        help="Load sample data for exploration (tagged source='sample')",
-    )
-    parser.add_argument(
-        "--clear-samples",
-        action="store_true",
-        help="Remove all sample data and policies",
-    )
-
     args = parser.parse_args()
 
     if args.subcommand == "mcp":
@@ -599,11 +442,7 @@ def main():
             folders_parser.print_help()
             return
 
-    if args.seed_samples:
-        _do_seed_samples()
-    elif args.clear_samples:
-        _do_clear_samples()
-    elif getattr(args, "hooks", False):
+    if getattr(args, "hooks", False):
         sys.exit(install_git_hooks())
     elif args.check:
         sys.exit(check_existing_config())
@@ -978,10 +817,6 @@ def run_interactive_wizard():
     seed_access_policies()
     mcp_configured = offer_setup_claude()
 
-    # Optional: seed sample data
-    if Confirm.ask("\nSeed sample data for exploration?", default=False):
-        _do_seed_samples()
-
     # Phase 6: Summary
     _print_phase(6, 6, "Summary")
     print_summary(

{footprinter_cli-1.0.0rc2 → footprinter_cli-1.0.0rc4}/footprinter/cli/status.py

@@ -233,24 +233,6 @@ def _query_all_counts(cursor, counts: dict) -> dict:
     except sqlite3.OperationalError:
         counts["last_run"] = None
 
-    # Fallback: if no ingests, try MAX(indexed_at) from files
-    if counts["last_run"] is None:
-        try:
-            cursor.execute("SELECT MAX(indexed_at) FROM files")
-            row = cursor.fetchone()
-            if row and row[0]:
-                counts["last_run"] = {
-                    "mode": "unknown",
-                    "pipe": "unknown",
-                    "started_at": row[0],
-                    "completed_at": None,
-                    "items_processed": counts["files_total"],
-                    "errors": 0,
-                    "status": "unknown",
-                    "elapsed_seconds": None,
-                }
-        except sqlite3.OperationalError:
-            pass
 
     return counts
 

{footprinter_cli-1.0.0rc2 → footprinter_cli-1.0.0rc4}/footprinter/ingest/orchestrator.py

@@ -95,6 +95,12 @@ class DataPipelineOrchestrator:
             )
         return self._dispatch_pipes(pipes, on_pipe_start, on_pipe_end, on_progress)
 
+    def run_refresh(self, source: str, on_pipe_start=None, on_pipe_end=None, on_progress=None) -> List[Dict]:
+        """Execute a refresh group. Shares _dispatch_pipes with run_pipeline so POST_PIPES run inline."""
+        if source not in self.refresh_pipes:
+            raise ValueError(f"Unknown refresh source: {source}. Available: {', '.join(self.refresh_pipes.keys())}")
+        return self._dispatch_pipes(self.refresh_pipes[source], on_pipe_start, on_pipe_end, on_progress)
+
     def _dispatch_pipes(self, pipes, on_pipe_start, on_pipe_end, on_progress) -> List[Dict]:
         self.runner.full_mode = self.full_mode
         mode = "full" if self.full_mode else "incremental"

{footprinter_cli-1.0.0rc2 → footprinter_cli-1.0.0rc4}/footprinter/ingest/pipe_runner.py

@@ -159,6 +159,20 @@ class PipeRunner:
 
         return result
 
+    def validate_pipes(self, pipes: List[str]) -> None:
+        """Raise ValueError for unknown pipe names. Pure check, no side effects.
+
+        Exposed so callers that need to fail before starting UI output
+        (progress bars, headers) can pre-flight without duplicating the
+        unknown-pipe rule.
+        """
+        unknown = [s for s in pipes if s not in self.all_pipes]
+        if unknown:
+            raise ValueError(
+                f"Unknown pipe(s): {', '.join(unknown)}. "
+                f"Valid pipes: {', '.join(self.user_pipes)}"
+            )
+
     def run_pipes(
         self,
         pipes: List[str],
@@ -173,9 +187,7 @@ class PipeRunner:
         Raises ValueError for unknown pipe names. Stops on fatal errors
         (database/config error_type), continues on runtime errors.
         """
-        unknown = [s for s in pipes if s not in self.all_pipes]
-        if unknown:
-            raise ValueError(f"Unknown pipe(s): {', '.join(unknown)}. Valid pipes: {', '.join(self.user_pipes)}")
+        self.validate_pipes(pipes)
 
         results = []