Files
chatSummaries/README.md
T
lyuksovannyyandClaude Opus 5.5 16bf8de84c
Publish plugin / publish (push) Successful in 3s
Inject the summary card only once the answer starts streaming
Pressing Summarize used to inject a status card immediately, at a guessed
anchor, and move it once the fetch returned. Any failure before the model
answered (fetch error, empty history, unreachable host, bad key, HTTP error)
then left an error bubble in the chat and had already scrolled the user away
from where they were reading.

The pipeline is now fetch -> stream -> card. A bulletin acknowledges the
press; every failure before the first chunk is a bulletin only and leaves the
chat untouched. On the first chunk the card is created with its final anchor
and virtual id and placed strictly after the newest analyzed message. If that
message is not loaded, the chat is asked to load it and placement retries; the
card never falls back to the chat bottom. Placement then hard-jumps the layout
manager to the card's row: scrollToMessageId only smooth-scrolls from cell
positions that are stale right after an insert. The provisional anchor and
reanchor() machinery is gone.

The row is reserved with INSERT .. DO NOTHING, so re-summarizing a saved range
no longer blanks its text before the new answer arrives; a fresh row whose
stream breaks is deleted instead of left empty.

Also:
- Finished summaries end with #aisummaries as a native TL_iv.textHashtag
  (rendered by RichMessageLayout like a hashtag entity) and carry a plain-text
  body with a TL_messageEntityHashtag.
- Deleting a card (MessagesController.deleteMessages, all overloads) removes
  its saved row and the card, with a "Summary deleted" bulletin.
- Settings show the saved summary count and approximate size, and a confirmed
  "Clear all summaries" action.
- Version 1.1.0.

Verified on device: no card before streaming, correct placement and jump,
restore on reopen, deletion, and the hashtag rendering. Telegram's search is
server-side, so local cards do not appear in its results.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 23:19:06 +02:00

220 lines
12 KiB
Markdown

# exteraGram Plugin Base
A build toolchain and ADB automation for writing [exteraGram](https://exteragram.app) 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.
## What the plugin does
**Summarize** (⋮ → Plugins → Summarize, or hold the unread button) runs in this order:
1. A bulletin confirms the press, then the history is fetched.
2. The transcript streams to the configured OpenAI-compatible endpoint.
3. Only when the first chunk arrives is a summary card injected, directly after the newest
analyzed message. If that message is not loaded (an offset, or history scrolled away),
the chat is asked to load it first. The chat then jumps to the card once.
4. Reasoning and answer stream into the card. The finished summary ends with a native
`#aisummaries` hashtag and is saved to a local SQLite store, from which it is restored
whenever the chat is reopened.
Any failure before step 3 (fetch error, empty history, unreachable host, bad key, HTTP
error) is reported as a bulletin only: the chat is not modified and the view does not move.
A failure mid-stream is written onto the card, and a summary saved earlier for the same
range is kept.
Deleting a card like any other message removes its saved row. The settings page shows how
many summaries are saved and roughly how much space they take, and offers **Clear all
summaries** (with a confirmation step).
Summaries exist only on this device, so Telegram's own search, which runs on the server,
does not find them, including a search for `#aisummaries`.
## 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,
forgetting a summary when its card is deleted)
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/ ADB debug-loop automation and the git hooks (see below)
docs/sdk-notes.md condensed SDK API surface gathered from the official docs
```
## The three commands that matter
```bash
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`.
Its first run in a clone also enables the repo's git hooks (see
[Git hooks and versioning](#git-hooks-and-versioning)).
## 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 the
`tcp:42690` port forward (and `tcp:5678` with `--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…]` — watches `src/` and `plugin.json`, redeploys on change
(uses `inotifywait` if available, otherwise polls).
- `scripts/logs.sh [-c] [-t] [-g PATTERN]` — streams logcat for the running app (`-t` for the
raw Chaquopy stdio tags, `-g` to grep, `-c` to 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. Requires `debugpy` (vscode) or
`pydevd-pycharm` (pycharm) present in the app's Python runtime — add it to `requirements` in
`plugin.json` if it's missing.
- `scripts/fetch-sdk-stubs.sh [--beta]` — downloads the latest SDK type stubs into `stubs/`
for editor autocomplete.
## Git hooks and versioning
`scripts/pre-commit` bumps the patch number of `version` in `plugin.json` on every commit
(`1.0.0` → `1.0.1`) and stages it into that same commit. `scripts/post-commit` re-stages
`plugin.json` afterwards, because commits of a file selection (`git commit -- <paths>`, which
some IDEs use) are built from a temporary index and would otherwise leave it looking modified.
**The hooks enable themselves.** Git never activates hooks from repository content, so a
fresh clone, or a repo created from this template, starts without them. The first run of
`tools/bundle.py` fixes that by running `git config core.hooksPath scripts`, and every
workflow runs it: directly, or through `scripts/deploy.sh` and `scripts/watch.sh`. That
includes `--check`, so after cloning run
```bash
python3 tools/bundle.py --check
```
once, before your first commit. A commit made before any build runs without the hooks.
`bundle.py` leaves `core.hooksPath` alone when it is already set (so pointing it elsewhere on
purpose sticks), skips the step in CI (whenever `CI` is set) and outside a git work tree, and
never fails a build over it. To turn the hooks off for a clone, run
`git config core.hooksPath .git/hooks`; `git config --unset core.hooksPath` only lasts
until the next build.
The bump is skipped when:
- the commit message contains `[no bump]`, `[skip bump]`, `[no version bump]` or
`[skip version]` (case-insensitive; `nobump`, `no-bump` and `no_bump` also work),
- `NO_BUMP=1` (or `GIT_NO_BUMP=1`) is set, e.g. `NO_BUMP=1 git commit`, which is the only way
for commits written in an editor, since their message doesn't exist yet when the hook runs,
- `version` in `plugin.json` already differs from `HEAD` (you bumped it by hand, e.g. for a
minor or major release),
- a merge, rebase, cherry-pick or revert is in progress.
Because every version change publishes a release (see below), a normal commit + push to
`main` ships a new patch release. Use a stop word for commits that should not.
## 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. With the git hooks enabled every commit bumps it,
so every push of a normal commit cuts a new patch 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
1. Run `python3 tools/bundle.py --check` once. It enables the git hooks that auto-bump the
version on commit (see [Git hooks and versioning](#git-hooks-and-versioning)).
2. Edit `plugin.json` (id, name, description, etc.).
3. Write your plugin under `src/`, with `src/main.py` as the entry module (absolute imports
only — it's executed at plugin-module top level, not inside a package).
4. `python3 tools/bundle.py --release && python3 tools/verify_bundle.py dist/<id>.plugin`
(substitute your `id` from `plugin.json`).
5. `bash scripts/deploy.sh --enable` with a device connected.