footprinter-cli 1.0.1__tar.gz → 1.0.3__tar.gz

{footprinter_cli-1.0.1/footprinter_cli.egg-info → footprinter_cli-1.0.3}/PKG-INFO

@@ -1,13 +1,14 @@
 Metadata-Version: 2.2
 Name: footprinter-cli
-Version: 1.0.1
+Version: 1.0.3
 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
-Project-URL: Documentation, https://github.com/swellcitygroup/footprinter/blob/main/README.md
+Project-URL: Homepage, https://github.com/harringjohn/footprinter-cli
+Project-URL: Repository, https://github.com/harringjohn/footprinter-cli
+Project-URL: Issues, https://github.com/harringjohn/footprinter-cli/issues
+Project-URL: Documentation, https://github.com/harringjohn/footprinter-cli/blob/main/README.md
+Project-URL: Changelog, https://github.com/harringjohn/footprinter-cli/blob/main/CHANGELOG.md
 Keywords: indexer,mcp,metadata,model-context-protocol,file-indexing,sqlite,context-engineering,personal-information-management
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
@@ -51,11 +52,12 @@ Requires-Dist: httpx<1.0,>=0.27.0; extra == "dev"
 
 # Footprinter
 
-[![Tests](https://github.com/swellcitygroup/footprinter/actions/workflows/test.yml/badge.svg)](https://github.com/swellcitygroup/footprinter/actions/workflows/test.yml)
+[![Tests](https://github.com/harringjohn/footprinter-cli/actions/workflows/test.yml/badge.svg)](https://github.com/harringjohn/footprinter-cli/actions/workflows/test.yml)
+[![PyPI](https://img.shields.io/pypi/v/footprinter-cli)](https://pypi.org/project/footprinter-cli/)
 
 **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/).**
 
-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.
+Your work lives across filesystems, browsers, inboxes, chat histories, and other tools. 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.
 
 ## Prerequisites
 
@@ -69,13 +71,13 @@ The fastest path on a clean machine is the install script — it ensures Python
 
 ```bash
 # Base install (CLI + MCP + HTTP API)
-curl -fsSL https://raw.githubusercontent.com/swellcitygroup/footprinter/main/scripts/release/install.sh | bash
+curl -fsSL https://raw.githubusercontent.com/harringjohn/footprinter-cli/main/scripts/release/install.sh | bash
 
 # Full install (adds semantic search + document parsing)
-curl -fsSL https://raw.githubusercontent.com/swellcitygroup/footprinter/main/scripts/release/install-full.sh | bash
+curl -fsSL https://raw.githubusercontent.com/harringjohn/footprinter-cli/main/scripts/release/install-full.sh | bash
 ```
 
-If you prefer to manage the install yourself, use **pipx** (recommended) — modern macOS Python ships PEP 668 enabled, which blocks bare `pip install`:
+If you prefer to manage the install yourself, use **pipx** (recommended) — it isolates Footprinter and sidesteps the macOS install caveats noted below:
 
 ```bash
 brew install pipx
@@ -84,6 +86,11 @@ pipx install footprinter-cli
 pipx install 'footprinter-cli[full]'   # with semantic + parse
 ```
 
+> **macOS caveats for manual installs:**
+> - **zsh** treats `[...]` as a glob, so keep the single quotes around any bracketed extras specifier (e.g. `'footprinter-cli[full]'`). Without quotes you'll see `zsh: no matches found`.
+> - **System and Homebrew Python** ship with PEP 668 enabled, which blocks bare `pip install` outside a venv. Use pipx (above) instead.
+> - **python.org-distributed Python** doesn't enforce PEP 668, so a bare `pip install footprinter-cli` outside pipx or a venv may succeed but place `fp` in `/Library/Frameworks/Python.framework/Versions/<x.y>/bin`, which isn't on `PATH` by default. Use pipx (above) or the install script.
+
 Inside an existing venv, `pip` works as expected:
 
 ```bash
@@ -153,7 +160,7 @@ Once configured, Claude can search your files, browse projects, and find related
 | **Documents** | PDF, Word, Excel, PowerPoint content (with `[parse]` extra) |
 | **Semantic embeddings** | Conceptual similarity across all sources (with `[semantic]` extra) |
 
-What lands in the database — and when — is controlled by the **content storage tier** you opt into. By default, Footprinter only indexes metadata; it does not read your file content until you explicitly enable it. See [Content Storage](https://github.com/swellcitygroup/footprinter/blob/main/reference/content-storage.md) for the full breakdown.
+What lands in the database — and when — is controlled by the **content storage tier** you opt into. By default, Footprinter only indexes metadata; it does not read your file content until you explicitly enable it. See [Content Storage](https://github.com/harringjohn/footprinter-cli/blob/main/reference/content-storage.md) for the full breakdown.
 
 Additional sources are available through [connector plugins](#connectors).
 
@@ -171,9 +178,9 @@ All commands use the `fp` entry point.
 | `fp mcp` | MCP server and access policies |
 | `fp api` | Start the HTTP API server |
 | `fp view` | Browse indexed data (files, folders, projects, clients, chats, emails, visits) |
-| `fp upsert` | Create or update records and assign relationships |
+| `fp upsert` | Create/update records, assign relationships, or soft-delete via `--status removed` |
 | `fp data` | Export data, generate templates, or import metadata corrections |
-| `fp delete` | Soft-delete a record |
+| `fp delete` | Hard-delete a super entity (irreversible) |
 | `fp vectorize` | Manage per-record vectorization control |
 | `fp doctor` | Post-install health check (Python version, install location, FDA, MCP wiring) |
 | `fp uninstall` | Remove Footprinter — MCP entry, user data, package |
@@ -206,22 +213,22 @@ Sources are scanned into SQLite with bidirectional links connecting local files
 
 ## Documentation
 
-- [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
-- [Content Storage](https://github.com/swellcitygroup/footprinter/blob/main/reference/content-storage.md) — metadata vs. snippet vs. full-content tiers
-- [Access Control](https://github.com/swellcitygroup/footprinter/blob/main/reference/mcp-access-control.md) — MCP security model
+- [Interfaces](https://github.com/harringjohn/footprinter-cli/blob/main/reference/interfaces.md) — CLI commands, MCP tools, Python API
+- [Data Model](https://github.com/harringjohn/footprinter-cli/blob/main/reference/data-model.md) — database schema
+- [Pipeline](https://github.com/harringjohn/footprinter-cli/blob/main/reference/pipeline.md) — indexing stages and configuration
+- [Content Storage](https://github.com/harringjohn/footprinter-cli/blob/main/reference/content-storage.md) — metadata vs. snippet vs. full-content tiers
+- [Access Control](https://github.com/harringjohn/footprinter-cli/blob/main/reference/mcp-access-control.md) — MCP security model
 
 ## Contributing
 
-Bug fixes, documentation, and tests welcome. For new features or architectural changes, [open an issue](https://github.com/swellcitygroup/footprinter/issues) first to discuss the approach.
+Bug fixes, documentation, and tests welcome. For new features or architectural changes, [open an issue](https://github.com/harringjohn/footprinter-cli/issues) first to discuss the approach.
 
 Connector plugins use an internal API that isn't stable yet — we're not accepting connector contributions at this time.
 
 ### Development setup
 
 ```bash
-git clone https://github.com/swellcitygroup/footprinter.git
+git clone https://github.com/harringjohn/footprinter-cli.git
 cd footprinter
 python3 -m venv venv
 ./venv/bin/pip install -e ".[dev]"
@@ -247,7 +254,7 @@ python3 -m venv venv
 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](https://github.com/swellcitygroup/footprinter/blob/main/SECURITY.md).
+Never commit API keys, tokens, or credentials. Report security vulnerabilities privately — see [SECURITY.md](https://github.com/harringjohn/footprinter-cli/blob/main/SECURITY.md).
 
 ### Pull request expectations
 
@@ -258,13 +265,13 @@ 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](https://github.com/swellcitygroup/footprinter/blob/main/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/harringjohn/footprinter-cli/blob/main/LICENSE).
 
 ## Community
 
-- [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)
+- [Code of Conduct](https://github.com/harringjohn/footprinter-cli/blob/main/CODE_OF_CONDUCT.md)
+- [Security Policy](https://github.com/harringjohn/footprinter-cli/blob/main/SECURITY.md)
 
 ## License
 
-MIT — see [LICENSE](https://github.com/swellcitygroup/footprinter/blob/main/LICENSE).
+MIT — see [LICENSE](https://github.com/harringjohn/footprinter-cli/blob/main/LICENSE).

{footprinter_cli-1.0.1 → footprinter_cli-1.0.3}/README.md

@@ -1,10 +1,11 @@
 # Footprinter
 
-[![Tests](https://github.com/swellcitygroup/footprinter/actions/workflows/test.yml/badge.svg)](https://github.com/swellcitygroup/footprinter/actions/workflows/test.yml)
+[![Tests](https://github.com/harringjohn/footprinter-cli/actions/workflows/test.yml/badge.svg)](https://github.com/harringjohn/footprinter-cli/actions/workflows/test.yml)
+[![PyPI](https://img.shields.io/pypi/v/footprinter-cli)](https://pypi.org/project/footprinter-cli/)
 
 **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/).**
 
-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.
+Your work lives across filesystems, browsers, inboxes, chat histories, and other tools. 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.
 
 ## Prerequisites
 
@@ -18,13 +19,13 @@ The fastest path on a clean machine is the install script — it ensures Python
 
 ```bash
 # Base install (CLI + MCP + HTTP API)
-curl -fsSL https://raw.githubusercontent.com/swellcitygroup/footprinter/main/scripts/release/install.sh | bash
+curl -fsSL https://raw.githubusercontent.com/harringjohn/footprinter-cli/main/scripts/release/install.sh | bash
 
 # Full install (adds semantic search + document parsing)
-curl -fsSL https://raw.githubusercontent.com/swellcitygroup/footprinter/main/scripts/release/install-full.sh | bash
+curl -fsSL https://raw.githubusercontent.com/harringjohn/footprinter-cli/main/scripts/release/install-full.sh | bash
 ```
 
-If you prefer to manage the install yourself, use **pipx** (recommended) — modern macOS Python ships PEP 668 enabled, which blocks bare `pip install`:
+If you prefer to manage the install yourself, use **pipx** (recommended) — it isolates Footprinter and sidesteps the macOS install caveats noted below:
 
 ```bash
 brew install pipx
@@ -33,6 +34,11 @@ pipx install footprinter-cli
 pipx install 'footprinter-cli[full]'   # with semantic + parse
 ```
 
+> **macOS caveats for manual installs:**
+> - **zsh** treats `[...]` as a glob, so keep the single quotes around any bracketed extras specifier (e.g. `'footprinter-cli[full]'`). Without quotes you'll see `zsh: no matches found`.
+> - **System and Homebrew Python** ship with PEP 668 enabled, which blocks bare `pip install` outside a venv. Use pipx (above) instead.
+> - **python.org-distributed Python** doesn't enforce PEP 668, so a bare `pip install footprinter-cli` outside pipx or a venv may succeed but place `fp` in `/Library/Frameworks/Python.framework/Versions/<x.y>/bin`, which isn't on `PATH` by default. Use pipx (above) or the install script.
+
 Inside an existing venv, `pip` works as expected:
 
 ```bash
@@ -102,7 +108,7 @@ Once configured, Claude can search your files, browse projects, and find related
 | **Documents** | PDF, Word, Excel, PowerPoint content (with `[parse]` extra) |
 | **Semantic embeddings** | Conceptual similarity across all sources (with `[semantic]` extra) |
 
-What lands in the database — and when — is controlled by the **content storage tier** you opt into. By default, Footprinter only indexes metadata; it does not read your file content until you explicitly enable it. See [Content Storage](https://github.com/swellcitygroup/footprinter/blob/main/reference/content-storage.md) for the full breakdown.
+What lands in the database — and when — is controlled by the **content storage tier** you opt into. By default, Footprinter only indexes metadata; it does not read your file content until you explicitly enable it. See [Content Storage](https://github.com/harringjohn/footprinter-cli/blob/main/reference/content-storage.md) for the full breakdown.
 
 Additional sources are available through [connector plugins](#connectors).
 
@@ -120,9 +126,9 @@ All commands use the `fp` entry point.
 | `fp mcp` | MCP server and access policies |
 | `fp api` | Start the HTTP API server |
 | `fp view` | Browse indexed data (files, folders, projects, clients, chats, emails, visits) |
-| `fp upsert` | Create or update records and assign relationships |
+| `fp upsert` | Create/update records, assign relationships, or soft-delete via `--status removed` |
 | `fp data` | Export data, generate templates, or import metadata corrections |
-| `fp delete` | Soft-delete a record |
+| `fp delete` | Hard-delete a super entity (irreversible) |
 | `fp vectorize` | Manage per-record vectorization control |
 | `fp doctor` | Post-install health check (Python version, install location, FDA, MCP wiring) |
 | `fp uninstall` | Remove Footprinter — MCP entry, user data, package |
@@ -155,22 +161,22 @@ Sources are scanned into SQLite with bidirectional links connecting local files
 
 ## Documentation
 
-- [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
-- [Content Storage](https://github.com/swellcitygroup/footprinter/blob/main/reference/content-storage.md) — metadata vs. snippet vs. full-content tiers
-- [Access Control](https://github.com/swellcitygroup/footprinter/blob/main/reference/mcp-access-control.md) — MCP security model
+- [Interfaces](https://github.com/harringjohn/footprinter-cli/blob/main/reference/interfaces.md) — CLI commands, MCP tools, Python API
+- [Data Model](https://github.com/harringjohn/footprinter-cli/blob/main/reference/data-model.md) — database schema
+- [Pipeline](https://github.com/harringjohn/footprinter-cli/blob/main/reference/pipeline.md) — indexing stages and configuration
+- [Content Storage](https://github.com/harringjohn/footprinter-cli/blob/main/reference/content-storage.md) — metadata vs. snippet vs. full-content tiers
+- [Access Control](https://github.com/harringjohn/footprinter-cli/blob/main/reference/mcp-access-control.md) — MCP security model
 
 ## Contributing
 
-Bug fixes, documentation, and tests welcome. For new features or architectural changes, [open an issue](https://github.com/swellcitygroup/footprinter/issues) first to discuss the approach.
+Bug fixes, documentation, and tests welcome. For new features or architectural changes, [open an issue](https://github.com/harringjohn/footprinter-cli/issues) first to discuss the approach.
 
 Connector plugins use an internal API that isn't stable yet — we're not accepting connector contributions at this time.
 
 ### Development setup
 
 ```bash
-git clone https://github.com/swellcitygroup/footprinter.git
+git clone https://github.com/harringjohn/footprinter-cli.git
 cd footprinter
 python3 -m venv venv
 ./venv/bin/pip install -e ".[dev]"
@@ -196,7 +202,7 @@ python3 -m venv venv
 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](https://github.com/swellcitygroup/footprinter/blob/main/SECURITY.md).
+Never commit API keys, tokens, or credentials. Report security vulnerabilities privately — see [SECURITY.md](https://github.com/harringjohn/footprinter-cli/blob/main/SECURITY.md).
 
 ### Pull request expectations
 
@@ -207,13 +213,13 @@ 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](https://github.com/swellcitygroup/footprinter/blob/main/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/harringjohn/footprinter-cli/blob/main/LICENSE).
 
 ## Community
 
-- [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)
+- [Code of Conduct](https://github.com/harringjohn/footprinter-cli/blob/main/CODE_OF_CONDUCT.md)
+- [Security Policy](https://github.com/harringjohn/footprinter-cli/blob/main/SECURITY.md)
 
 ## License
 
-MIT — see [LICENSE](https://github.com/swellcitygroup/footprinter/blob/main/LICENSE).
+MIT — see [LICENSE](https://github.com/harringjohn/footprinter-cli/blob/main/LICENSE).

{footprinter_cli-1.0.1 → footprinter_cli-1.0.3}/footprinter/access.py

@@ -46,7 +46,7 @@ def _is_inherit_source(source: str) -> bool:
 #   table:          SQL table name
 #   has_visibility: has mcp_view column
 #   has_permissions: has mcp_read column
-#   has_status:     has status column (filter WHERE status != 'removed')
+#   has_status:     has status column (filter WHERE status = 'listed')
 #   has_project_id: has project_id FK
 #   has_client_id:  has client_id FK
 #   has_account:    has account column
@@ -129,7 +129,7 @@ def _get_all_ids(conn: sqlite3.Connection, entity_type: str) -> list[int]:
     meta = ENTITY_META[entity_type]
     table = meta["table"]
     if meta["has_status"]:
-        rows = conn.execute(f"SELECT id FROM {table} WHERE status != 'removed'").fetchall()
+        rows = conn.execute(f"SELECT id FROM {table} WHERE status = 'listed'").fetchall()
     else:
         rows = conn.execute(f"SELECT id FROM {table}").fetchall()
     return [r["id"] for r in rows]
@@ -162,7 +162,7 @@ def _get_ids_for_scope(conn: sqlite3.Connection, scope: str) -> dict[str, list[i
             table = meta["table"]
             where = "account = ?"
             if meta["has_status"]:
-                where += " AND status != 'removed'"
+                where += " AND status = 'listed'"
             rows = conn.execute(f"SELECT id FROM {table} WHERE {where}", (value,)).fetchall()
             ids = [r["id"] for r in rows]
             if ids:
@@ -183,7 +183,7 @@ def _get_ids_for_scope(conn: sqlite3.Connection, scope: str) -> dict[str, list[i
             table = meta["table"]
             where = f"{path_col} LIKE ? ESCAPE '\\'"
             if meta["has_status"]:
-                where += " AND status != 'removed'"
+                where += " AND status = 'listed'"
             rows = conn.execute(
                 f"SELECT id FROM {table} WHERE {where}",
                 (escaped + "%",),
@@ -210,7 +210,7 @@ def _get_ids_for_scope(conn: sqlite3.Connection, scope: str) -> dict[str, list[i
             table = meta["table"]
             where = "project_id = ?"
             if meta["has_status"]:
-                where += " AND status != 'removed'"
+                where += " AND status = 'listed'"
             rows = conn.execute(f"SELECT id FROM {table} WHERE {where}", (project_id,)).fetchall()
             ids = [r["id"] for r in rows]
             if ids:
@@ -248,7 +248,7 @@ def _get_ids_for_scope(conn: sqlite3.Connection, scope: str) -> dict[str, list[i
             table = meta["table"]
             where = "client_id = ?"
             if meta["has_status"]:
-                where += " AND status != 'removed'"
+                where += " AND status = 'listed'"
             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})

footprinter_cli-1.0.3/footprinter/api/__init__.py

@@ -0,0 +1,4 @@
+"""Footprinter HTTP API — FastAPI routers calling the service layer."""
+
+MAX_LIMIT = 200
+"""Upper bound for `limit` query params on HTTP list/search endpoints."""

{footprinter_cli-1.0.1 → footprinter_cli-1.0.3}/footprinter/api/entities.py

@@ -4,6 +4,7 @@ from typing import Optional
 
 from fastapi import APIRouter, Depends, HTTPException, Query
 
+from footprinter.api import MAX_LIMIT
 from footprinter.api.db import get_conn
 from footprinter.services import (
     chat_service,
@@ -36,7 +37,7 @@ def list_files(
     source: Optional[str] = Query(None, description="Comma-separated source filter"),
     status: Optional[str] = Query(None, description="Comma-separated status filter"),
     content_type: Optional[str] = None,
-    limit: int = 50,
+    limit: int = Query(50, ge=1, le=MAX_LIMIT),
     page: int = 1,
 ):
     source_list = [s.strip() for s in source.split(",")] if source else None
@@ -71,7 +72,7 @@ def list_emails(
     has_attachments: Optional[bool] = None,
     sort_by: str = "received_at",
     order: str = "desc",
-    limit: int = 50,
+    limit: int = Query(50, ge=1, le=MAX_LIMIT),
     page: int = 1,
 ):
     return email_service.list_(
@@ -105,7 +106,7 @@ def list_chats(
     sort_by: str = "modified_at",
     order: str = "desc",
     status: Optional[str] = Query(None, description="Comma-separated status filter"),
-    limit: int = 50,
+    limit: int = Query(50, ge=1, le=MAX_LIMIT),
     page: int = 1,
 ):
     status_list = [s.strip() for s in status.split(",")] if status else None
@@ -137,7 +138,7 @@ def list_projects(
     status: Optional[str] = Query(None, description="Comma-separated status filter"),
     client: Optional[str] = None,
     project_type: Optional[str] = None,
-    limit: int = 50,
+    limit: int = Query(50, ge=1, le=MAX_LIMIT),
     page: int = 1,
 ):
     include_list = [s.strip() for s in include.split(",")] if include else None
@@ -172,7 +173,7 @@ def list_clients(
     conn=Depends(get_conn),
     include: Optional[str] = Query(None, description="Comma-separated includes"),
     status: Optional[str] = Query(None, description="Comma-separated status filter"),
-    limit: int = 50,
+    limit: int = Query(50, ge=1, le=MAX_LIMIT),
     page: int = 1,
 ):
     include_list = [s.strip() for s in include.split(",")] if include else None
@@ -216,16 +217,19 @@ def list_folders(
     project_id: Optional[int] = None,
     depth: Optional[int] = 1,
     include_hidden: bool = False,
+    status: Optional[str] = Query(None, description="Comma-separated status filter"),
     sort_by: str = "size",
-    limit: int = 50,
+    limit: int = Query(50, ge=1, le=MAX_LIMIT),
     page: int = 1,
 ):
+    status_list = [s.strip() for s in status.split(",")] if status else None
     return folder_service.list_(
         conn,
         role=Role.ADMIN,
         project_id=project_id,
         depth=depth,
         include_hidden=include_hidden,
+        status=status_list,
         sort_by=sort_by,
         limit=limit,
         page=page,
@@ -241,7 +245,11 @@ def get_folder(folder_id: int, conn=Depends(get_conn)):
 
 
 @router.get("/visits")
-def list_visits(conn=Depends(get_conn), limit: int = 50, page: int = 1):
+def list_visits(
+    conn=Depends(get_conn),
+    limit: int = Query(50, ge=1, le=MAX_LIMIT),
+    page: int = 1,
+):
     return visit_service.list_(conn, role=Role.ADMIN, limit=limit, page=page)
 
 

{footprinter_cli-1.0.1 → footprinter_cli-1.0.3}/footprinter/api/search.py

@@ -4,6 +4,7 @@ from typing import Optional
 
 from fastapi import APIRouter, Depends, Query
 
+from footprinter.api import MAX_LIMIT
 from footprinter.api.db import get_conn
 from footprinter.services import search_service
 from footprinter.services.roles import Role
@@ -20,7 +21,7 @@ def search(
     client: Optional[str] = None,
     date_from: Optional[str] = None,
     date_to: Optional[str] = None,
-    limit: int = 50,
+    limit: int = Query(50, ge=1, le=MAX_LIMIT),
     account: Optional[str] = None,
     sender: Optional[str] = None,
     days_back: Optional[int] = None,

{footprinter_cli-1.0.1 → footprinter_cli-1.0.3}/footprinter/api/semantic.py

@@ -2,6 +2,7 @@
 
 from fastapi import APIRouter, Depends, HTTPException, Query
 
+from footprinter.api import MAX_LIMIT
 from footprinter.api.db import get_conn
 from footprinter.services import semantic_service
 from footprinter.services.roles import Role
@@ -16,7 +17,7 @@ def semantic_search(
     conn=Depends(get_conn),
     query: str = Query(..., min_length=3, description="Search query (minimum 3 characters)"),
     source: str = Query("all", description="Source to search: chats, files, or all"),
-    limit: int = 10,
+    limit: int = Query(10, ge=1, le=MAX_LIMIT),
 ):
     """Semantic (vector) search across indexed content."""
     if source not in _VALID_SOURCES:

{footprinter_cli-1.0.1 → footprinter_cli-1.0.3}/footprinter/bundled/config.example.yaml

@@ -17,7 +17,7 @@ browsers:
 #
 # Files matching these patterns are NEVER scanned — they don't appear in the
 # database at all. This is different from hidden files (dot-files/dot-directories),
-# which ARE scanned and indexed with status='hidden' so they appear in the catalog
+# which ARE scanned and indexed with status='unlisted' so they appear in the catalog
 # but are excluded from Drive sync.
 #
 # Two tiers: always (all folders), sensitive (all folders)
@@ -41,8 +41,11 @@ exclusions:
     - ".*/\\.sfdx/.*"            # Salesforce DX CLI
     - ".*/\\.docker/.*"          # Docker config
     - ".*/\\.cumulusci/.*"       # CumulusCI cache
+    - ".*/\\.browser_state/.*"   # Playwright/Puppeteer browser state
+    - ".*/\\.context/.*"         # IDE/agent context directories
+    - ".*/\\.ai-dev/.*"          # AI dev tool scratch dirs
     # Home-level Claude dirs only (keep .claude within Work/Personal)
-    - "^~/\\.claude/.*"           # Home-level .claude
+    - "^~/\\.claude/.*"           # Home-level .claude (includes session-env snapshots)
     - "^~/\\.claude-worktrees/.*" # Home-level .claude-worktrees
     # Git internals (but NOT .gitignore, .gitattributes - those are kept)
     - ".*/\\.git/.*"             # Git internal directory contents
@@ -75,9 +78,12 @@ exclusions:
 # Indexing configuration - INDEX ALL FILE TYPES
 indexing:
   supported_extensions: []  # Empty = index ALL file types
-  max_file_size_mb: 0       # 0 = no size limit (index everything)
+  max_file_size_mb: 50      # MB; 0 = no size limit. 50 is generous for prose/docs.
   lookback_days: 14         # Browser history window (days back to index)
   content_snippets: false   # Extract file/email content previews for keyword search
+  # `fp ingest --preview` (FPR-1723) — pre-scan summary tuning
+  preview_top_n: 10                # rows shown for top files / top directories
+  preview_size_threshold_mb: 50    # files at or above this size are flagged as outliers
 
 # Semantic search — stores content as embeddings in a local ChromaDB database
 # Enables finding files and chats by meaning, not just keywords
@@ -101,6 +107,11 @@ vectorization:
     - .txt
     - .pdf
     - .docx
+  # Maximum file size (MB) eligible for vectorization. Applies even when
+  # indexing.max_file_size_mb is 0 (no limit). Chunking a multi-GB file
+  # produces millions of chunks and can OOM the host — this guardrail is
+  # always on. Skipped files appear in the post-ingest summary.
+  max_vectorize_size_mb: 100
   # Chunk size in characters — tuned for MiniLM-L6-v2 (256-token input window).
   # ~1000 chars ≈ 250 tokens. Larger chunks get silently truncated by the model,
   # meaning content past the window is invisible to semantic search.
@@ -115,17 +126,19 @@ vectorization:
   # but not embedded in the vector store.
   #
   # Common exclusions — system caches, IDE output, and tool output that
-  # match text file extensions but contain no meaningful prose content:
-  #   - "**/Photos Library.photoslibrary/**"  # macOS Spotlight index cache (.txt)
-  #   - "**/.claude/debug/**"                 # Claude Code debug logs
-  #   - "**/.claude/paste-cache/**"           # Claude Code paste cache
-  #   - "**/.claude/cache/**"                 # Claude Code cache
-  #   - "**/.claude/projects/**"              # Claude Code session data
-  #   - "**/.claude/plans/**"                 # Claude Code auto-generated plans
-  #   - "**/.claude/plugins/**"              # Claude Code plugin cache
-  #   - "**/.cci/**"                          # CumulusCI cache
-  #   - "**/.context/**"                      # IDE context directories
-  exclude_patterns: []
+  # match text file extensions but contain no meaningful prose content.
+  exclude_patterns:
+    - "**/Photos Library.photoslibrary/**"  # macOS Spotlight index cache (.txt)
+    - "**/.claude/debug/**"                 # Claude Code debug logs
+    - "**/.claude/paste-cache/**"           # Claude Code paste cache
+    - "**/.claude/cache/**"                 # Claude Code cache
+    - "**/.claude/projects/**"              # Claude Code session data
+    - "**/.claude/plans/**"                 # Claude Code auto-generated plans
+    - "**/.claude/plugins/**"               # Claude Code plugin cache
+    - "**/.cci/**"                          # CumulusCI cache
+    - "**/.context/**"                      # IDE context directories
+    - "**/.github/**"                       # GitHub workflow files (FTS-only)
+    - "**/.ai-dev/**"                       # AI dev tool scratch dirs
 
 # Source registry seeds — loaded into the sources table on init
 # Connector sources added by: fp connect install <name>

{footprinter_cli-1.0.1 → footprinter_cli-1.0.3}/footprinter/cli/__init__.py

@@ -29,10 +29,9 @@ def main(argv=None) -> None:
 
     if argv is None:
         argv = _sys.argv[1:]
-    from footprinter.source_registry import ConfigError as _ConfigError
-
     from footprinter import __version__
     from footprinter.cli._common import FORMATTER
+    from footprinter.source_registry import ConfigError as _ConfigError
 
     parser = argparse.ArgumentParser(
         prog="fp",

{footprinter_cli-1.0.1 → footprinter_cli-1.0.3}/footprinter/cli/_common.py

@@ -49,16 +49,7 @@ C_ERROR = "red"
 C_INFO = "cyan"
 C_DIM = "dim"
 
-VALID_STATUSES = frozenset(
-    {
-        "active",
-        "paused",
-        "completed",
-        "abandoned",
-        "archived",
-        "merged",
-    }
-)
+VALID_STATUSES = frozenset({"listed", "unlisted", "removed"})
 
 ALLOWED_TABLES = frozenset({"clients", "projects"})
 ALLOWED_COLUMNS = frozenset({"name", "project_name"})
@@ -113,7 +104,7 @@ def open_database(db_path=None):
 
     Like ``open_db`` but yields the full ``Database`` wrapper instead of a
     raw ``sqlite3.Connection``.  Use this when callers need methods only
-    available on the wrapper (e.g. ``ChatDedup``).
+    available on the wrapper.
 
     Exits with code 1 if the database file does not exist.
     """

{footprinter_cli-1.0.1 → footprinter_cli-1.0.3}/footprinter/cli/_policy_helpers.py

@@ -128,7 +128,7 @@ def check_file_path(conn: sqlite3.Connection, path: str, json_output: bool, verb
     expanded = os.path.expanduser(os.path.normpath(path))
 
     row = conn.execute(
-        "SELECT id, name, project_id FROM files WHERE path = ? AND status != 'removed'",
+        "SELECT id, name, project_id FROM files WHERE path = ? AND status = 'listed'",
         (expanded,),
     ).fetchone()
 
@@ -200,7 +200,7 @@ def check_folder(conn: sqlite3.Connection, path: str, json_output: bool, verbose
         expanded += os.sep
 
     rows = conn.execute(
-        "SELECT id, name FROM files WHERE path LIKE ? AND status != 'removed'",
+        "SELECT id, name FROM files WHERE path LIKE ? AND status = 'listed'",
         (expanded + "%",),
     ).fetchall()