Two bugs visible in a device log. "injector: anchor 0 not loaded, skipping insert" was a regression from the previous commit. _newest_visible_message_id returns 0 when the offset reaches past the loaded window, and the strict anchor check then refused to place the card, so pressing Summarize appeared to do nothing at all. Before that commit anchor 0 silently matched a date separator, which is why it went unnoticed. A live card is the user's only feedback that the press registered, so it must always appear: try the exact anchor, then id ordering, then the bottom of the chat, and let reanchor() move it once the analyzed range is known. Restoring saved summaries stays strict, since nothing corrects their position later. _newest_visible_message_id also falls back to the oldest loaded message rather than returning 0. The unread button prefilled a smaller range on each press -- 1000, then 15, then 75, with ~1100 unread. Viewing a chat calls MessagesController.markDialogAsRead, so dialog.unread_count decays while the chat is open and no longer describes the backlog the user wants summarized. Resolve the count from the unread divider instead, which is what the app's own button uses (onPageDownClicked branches on createUnreadMessageAfterId) and which does not decay while the chat stays open, and keep the largest value seen per chat so a later press never prefills less than an earlier one. Both are covered by tests that fail against the previous behaviour: the strict anchor path reports inserted=True while leaving no card in the list, and the unread resolver reproduces exactly 1100, 15, 75.
exteraGram Plugin Base
A build toolchain and ADB automation for writing exteraGram plugins
as ordinary multi-file Python projects instead of hand-maintaining one giant .py file.
How exteraGram plugins actually work
A plugin, as exteraGram loads it, is exactly one Python file on the device:
/data/user/0/com.exteragram.messenger/files/plugins/<plugin_id>.py. The distribution
convention names the same content <id>.plugin.
The app reads plugin metadata statically via AST — it looks for top-level constant
assignments (__id__, __name__, __description__, __author__, __version__,
__icon__, __app_version__, __sdk_version__, __requirements__) without executing the
file. Only __id__ and __name__ are required.
The file must define exactly one class inheriting BasePlugin (from base_plugin import BasePlugin). Lifecycle methods (on_plugin_load, on_plugin_unload, create_settings) and
hooks (on_send_message_hook, pre_request_hook, post_request_hook, on_update_hook(s),
on_app_event) are all called by the host; hooks must be registered inside
on_plugin_load (e.g. self.add_on_send_message_hook()). A hook returns a
HookResult(strategy=HookStrategy.MODIFY, params=params) to apply changes, or a bare
HookResult() to pass through. Settings rows returned from create_settings come from
ui.settings (Header, Input, Switch, Text, Selector, Divider) and persist through
self.get_setting/self.set_setting. Logging goes through android_utils.log; Chaquopy also
redirects sys.stdout/sys.stderr to the logcat tags python.stdout/python.stderr.
This repo does not use the official Elyx/ElyxBuilder archive format — see
docs/sdk-notes.md for why.
Repo layout
plugin.json single source of truth for plugin metadata
src/ the plugin, written as an ordinary Python package
main.py entry module — exactly one BasePlugin subclass, absolute imports only
config.py setting keys, defaults and tunables
diagnostics.py bounded in-memory log, mirrored to a file (logcat is restricted here)
providers/ endpoint settings, prompt assembly and SSE streaming
services/ history fetch, anonymized transcript, markdown→RichMessage, injection, SQLite store
hooks/ Xposed hooks (unread-button entry points, summary restore on chat open)
ui/ summarize dialog, bulletin and theme helpers
tools/
bundle.py compiles plugin.json + src/ into dist/<id>.plugin
devclient.py speaks the on-device dev-server protocol (127.0.0.1:42690)
verify_bundle.py offline harness that proves a built bundle behaves correctly, no phone needed
release.py publishes a built bundle to a Gitea release (used by CI)
.gitea/workflows/ CI that builds, verifies and publishes the .plugin to Releases
scripts/ bash automation for the ADB debug loop (see below)
docs/sdk-notes.md condensed SDK API surface gathered from the official docs
The three commands that matter
python3 tools/bundle.py --release # compile src/ -> dist/<id>.plugin
python3 tools/verify_bundle.py dist/<id>.plugin # offline proof the bundle works, no device needed
bash scripts/deploy.sh --enable # build (--dev) + push to a connected device + enable + reload
bundle.py walks src/ recursively, embeds every .py file's source and dotted module name
into a compressed, base64-encoded payload, and appends a small runtime preamble that installs
a private import hook (scoped to a per-module __builtins__ dict, never touching
sys.modules) so cross-module and cross-package imports resolve exactly as they would if the
files were still on disk. --dev (the default) embeds absolute local paths so a debugger
resolves breakpoints against your real source files; --release embeds repo-relative paths
for distribution. Both modes produce byte-reproducible output for a given src/ + plugin.json.
Device prerequisites
- exteraGram 12.5.1+.
- In-app: Preferences → Plugins → enable the plugin engine, then enable developer mode.
- USB debugging enabled, device authorized (
adb devices).
Release-build APKs disallow adb run-as, so you cannot adb push a file straight into the
app's private plugin directory. The on-device dev server (tools/devclient.py,
scripts/deploy.sh) is the actual install path — it talks to the running app over a TCP
socket forwarded with adb forward, and the app writes the file into its own storage.
ADB automation
All scripts live in scripts/, are runnable from any working directory, and honor the
standard ANDROID_SERIAL env var for device selection.
scripts/adb-connect.sh [--debug]— starts adb, waits for the device, (re)creates thetcp:42690port forward (andtcp:5678with--debug), pings the dev server.scripts/deploy.sh [--release] [--enable] [--no-connect]— bundles, connects, writes the plugin to the device, optionally enables it, reloads it.scripts/watch.sh [deploy args…]— watchessrc/andplugin.json, redeploys on change (usesinotifywaitif available, otherwise polls).scripts/logs.sh [-c] [-t] [-g PATTERN]— streams logcat for the running app (-tfor the raw Chaquopy stdio tags,-gto grep,-cto clear first).scripts/debug.sh start|stop [--platform vscode|pycharm]— forwards the debugger port and tells the dev server to start/stop the in-app debugger. Requiresdebugpy(vscode) orpydevd-pycharm(pycharm) present in the app's Python runtime — add it torequirementsinplugin.jsonif it's missing.scripts/fetch-sdk-stubs.sh [--beta]— downloads the latest SDK type stubs intostubs/for editor autocomplete.
Publishing a release
.gitea/workflows/release.yml builds, verifies and publishes the .plugin to the repo's
Releases tab on every push to main. dist/ is gitignored, so the artifact is always built
by CI rather than committed.
The version field in plugin.json is the single source of truth:
Push to main with… |
Result |
|---|---|
a new version |
creates tag v<version> and a new release |
the same version |
rebuilds the existing release, replacing its attachment |
So every push leaves a downloadable build attached to the current version, and bumping
version is what cuts a new release. Pushing a v* tag by hand still works and uses that
tag verbatim, as does a manual run (Actions → Publish plugin → Run workflow).
Every path runs --check, builds with --release, and gates the upload on
verify_bundle.py, so a bundle that fails verification is never published. A rebuild
replaces the attachment rather than piling up duplicates, and refreshes the release notes to
name the commit it came from. The tag itself is never moved: it keeps pointing at the commit
that first introduced that version.
Authentication uses secrets.API_TOKEN, an organisation-level Actions secret holding a user
token with the write:repository scope (which covers releases). Set it once under
Org → Settings → Actions → Secrets and every repo in the organisation inherits it; a
repo-level secret of the same name takes precedence if one repo ever needs different
credentials.
The workflow passes it to release.py as RELEASE_TOKEN, not GITEA_TOKEN. The Actions
runner injects its own GITEA_TOKEN into every step, and that value overrides a step-level
env: entry of the same name, so the org secret would be silently ignored.
If the org secret does not reach a repository the publish still works: release.py tries
RELEASE_TOKEN first and then falls back to the runner's GITEA_TOKEN, which can publish
releases in its own repository, and prints which one it used. An organisation secret is only
exposed to a repository that has Actions enabled, so check Repo → Settings → Actions if a
repo unexpectedly falls back.
If you would rather not manage a token at all, that injected GITEA_TOKEN can create
releases in its own repo: pass --token-env GITEA_TOKEN and drop the org secret. It is
scoped to the single job and expires with it, so it is the safer default; API_TOKEN is what
you want when publishing needs to reach beyond this repo.
Writing your own plugin
- Edit
plugin.json(id, name, description, etc.). - Write your plugin under
src/, withsrc/main.pyas the entry module (absolute imports only — it's executed at plugin-module top level, not inside a package). python3 tools/bundle.py --release && python3 tools/verify_bundle.py dist/<id>.plugin(substitute youridfromplugin.json).bash scripts/deploy.sh --enablewith a device connected.