Test fixes for many plugins

README.md

@@ -1,6 +1,6 @@
 # abx-plugins
 
-ArchiveBox-compatible plugin suite (hooks, config schemas, binaries manifests).
+ArchiveBox-compatible plugin suite (hooks and config schemas).
 
 This package contains only plugin assets and a tiny helper to locate them.
 It does **not** depend on Django or ArchiveBox.
@@ -11,7 +11,7 @@ It does **not** depend on Django or ArchiveBox.
 from abx_plugins import get_plugins_dir
 
 plugins_dir = get_plugins_dir()
-# scan plugins_dir for plugins/*/config.json, binaries.jsonl, on_* hooks
+# scan plugins_dir for plugins/*/config.json and on_* hooks
 ```
 
 Tools like `abx-dl` and ArchiveBox can discover plugins from this package
@@ -24,7 +24,7 @@ without symlinks or environment-variable tricks.
 Each plugin lives under `plugins/<name>/` and may include:
 
 - `config.json` (optional) - config schema
-- `binaries.jsonl` (optional) - binary manifests
+- `on_Crawl*install*` hooks (optional) - dependency/binary install records
 - `on_*` hook scripts (required to do work)
 
 Hooks run with:
@@ -43,6 +43,78 @@ Hooks run with:
 - `PERSONAS_DIR` - persona profiles root (default: `~/.config/abx/personas`)
 - `ACTIVE_PERSONA` - persona name (default: `Default`)
 
+### Install hook contract (concise)
+
+Lifecycle:
+
+1. `on_Crawl__*install*` declares crawl dependencies.
+2. `on_Binary__*install*` resolves/installs one binary with one provider.
+
+`on_Crawl` output (dependency declaration):
+
+```json
+{"type":"Binary","name":"yt-dlp","binproviders":"pip,brew,apt,env","overrides":{"pip":{"packages":["yt-dlp[default]"]}},"machine_id":"<optional>"}
+```
+
+`on_Binary` input/output:
+
+- CLI input should accept `--binary-id`, `--machine-id`, `--name` (plus optional provider args).
+- Output should emit installed facts like:
+
+```json
+{"type":"Binary","name":"yt-dlp","abspath":"/abs/path","version":"2025.01.01","sha256":"<optional>","binprovider":"pip","machine_id":"<recommended>","binary_id":"<recommended>"}
+```
+
+Optional machine patch record:
+
+```json
+{"type":"Machine","config":{"PATH":"...","NODE_MODULES_DIR":"...","CHROME_BINARY":"..."}}
+```
+
+Semantics:
+
+- `stdout`: JSONL records only
+- `stderr`: human logs/debug
+- exit `0`: success or intentional skip
+- exit non-zero: hard failure
+
+State/OS:
+
+- working dir: `CRAWL_DIR/<plugin>/`
+- durable install root: `LIB_DIR` (e.g. npm prefix, pip venv, puppeteer cache)
+- providers: `apt` (Debian/Ubuntu), `brew` (macOS/Linux), many hooks currently assume POSIX paths
+
+### Snapshot hook contract (concise)
+
+Lifecycle:
+
+- runs once per snapshot, typically after crawl setup
+- common Chrome flow: crawl browser/session -> `chrome_tab` -> `chrome_navigate` -> downstream extractors
+
+State:
+
+- output cwd is usually `SNAP_DIR/<plugin>/`
+- hooks may read sibling outputs via `../<plugin>/...`
+
+Output records:
+
+- terminal record is usually:
+
+```json
+{"type":"ArchiveResult","status":"succeeded|skipped|failed","output_str":"path-or-message"}
+```
+
+- discovery hooks may also emit `Snapshot` and `Tag` records before `ArchiveResult`
+- search indexing hooks are a known exception and may use exit code + stderr without `ArchiveResult`
+
+Semantics:
+
+- `stdout`: JSONL records
+- `stderr`: diagnostics/logging
+- exit `0`: succeeded or skipped
+- exit non-zero: failed
+- current nuance: some skip/transient paths emit no JSONL and rely only on exit code
+
 ### Event JSONL interface (bbus-style, no dependency)
 
 Hooks emit JSONL events to stdout. They do **not** need to import `bbus`.

abx_plugins/__init__.py

@@ -3,12 +3,11 @@
 from __future__ import annotations
 
 from pathlib import Path
-from importlib import resources
 
 
 def get_plugins_dir() -> Path:
     """Return the filesystem path to the bundled plugins directory."""
-    return Path(resources.files(__name__) / "plugins")
+    return Path(__file__).resolve().parent / "plugins"
 
 
 __all__ = ["get_plugins_dir"]

abx_plugins/plugins/accessibility/tests/test_accessibility.py

@@ -13,12 +13,13 @@
 
 import pytest
 
+pytestmark = pytest.mark.usefixtures("ensure_chrome_test_prereqs")
+
 from abx_plugins.plugins.chrome.tests.chrome_test_helpers import (
     chrome_session,
     get_test_env,
     get_plugin_dir,
     get_hook_script,
-    chrome_test_url,
 )
 
 

abx_plugins/plugins/apt/on_Binary__13_apt_install.py

@@ -16,10 +16,7 @@
 import sys
 
 import rich_click as click
-from abx_pkg import Binary, AptProvider, BinProviderOverrides
-
-# Fix pydantic forward reference issue
-AptProvider.model_rebuild()
+from abx_pkg import AptProvider, Binary
 
 
 @click.command()

abx_plugins/plugins/apt/tests/test_apt_provider.py

@@ -8,7 +8,6 @@
 """
 
 import json
-import os
 import shutil
 import subprocess
 import sys

abx_plugins/plugins/archivedotorg/on_Snapshot__08_archivedotorg.bg.py

@@ -15,7 +15,9 @@
 import json
 import os
 import sys
+from importlib import import_module
 from pathlib import Path
+from typing import Any
 
 import rich_click as click
 
@@ -51,8 +53,8 @@ def log(message: str) -> None:
         print(f'[archivedotorg] {message}', file=sys.stderr)
 
     try:
-        import requests
-    except ImportError:
+        requests: Any = import_module('requests')
+    except ModuleNotFoundError:
         return False, None, 'requests library not installed'
 
     timeout = get_env_int('ARCHIVEDOTORG_TIMEOUT') or get_env_int('TIMEOUT', 60)

abx_plugins/plugins/archivedotorg/tests/test_archivedotorg.py

@@ -12,7 +12,10 @@
 import pytest
 
 PLUGIN_DIR = Path(__file__).parent.parent
-ARCHIVEDOTORG_HOOK = next(PLUGIN_DIR.glob('on_Snapshot__*_archivedotorg.*'), None)
+_ARCHIVEDOTORG_HOOK = next(PLUGIN_DIR.glob('on_Snapshot__*_archivedotorg.*'), None)
+if _ARCHIVEDOTORG_HOOK is None:
+    raise FileNotFoundError(f"Hook not found in {PLUGIN_DIR}")
+ARCHIVEDOTORG_HOOK = _ARCHIVEDOTORG_HOOK
 TEST_URL = 'https://example.com'
 
 def test_hook_script_exists():

abx_plugins/plugins/brew/on_Binary__12_brew_install.py

@@ -18,10 +18,7 @@
 import sys
 
 import rich_click as click
-from abx_pkg import Binary, BrewProvider, BinProviderOverrides
-
-# Fix pydantic forward reference issue
-BrewProvider.model_rebuild()
+from abx_pkg import Binary, BrewProvider
 
 
 @click.command()