The publish step set GITEA_TOKEN from the org-level API_TOKEN secret, but
the Actions runner injects its own GITEA_TOKEN into every step and that
value overrides a step-level env: entry of the same name. The org secret
was silently ignored and the job failed.
Pass the secret as RELEASE_TOKEN instead, which the runner does not
reserve, and read that name in release.py. --token-env makes the source
configurable, so the runner-provided GITEA_TOKEN can still be used
deliberately by passing --token-env GITEA_TOKEN.
Trigger the release workflow on pushes to main, not just on v* tags, so
every push leaves a downloadable .plugin attached to the current version.
The version in plugin.json decides what happens: a new version creates
tag v<version> and a new release, while an unchanged version rebuilds the
existing release and replaces its attachment. The tag is never moved, so
it keeps pointing at the commit that first introduced that version, but
the release notes are refreshed to name the commit the build came from.
Hand-pushed v* tags and manual runs are unaffected and still use the tag
verbatim.
Replace the sample plugin with an AI chat summarizer that renders its
output as a native RichMessage injected into the chat.
Summarization pipeline:
- Fetch chat/topic history via paginated TL requests.
- Send a system prompt, the user's instructions and an anonymized JSON
transcript as three separate roles. Only message text and attachment
names leave the device; senders and message ids are replaced by
indices, and out-of-range reply parents are included with negative ids
so replies keep their context.
- Stream the response over SSE, reading reasoning from reasoning_content,
reasoning or inline <think> tags.
- Substitute the model's {userN}/{msgN} placeholders back into real names
and deep links. Placeholders are used instead of Markdown links because
a half-streamed link renders as broken literal text.
Rendering:
- Compile Markdown into TL_iv page blocks (headings, lists, quotes, code,
dividers, inline styles) since the app's own converter works off
Android Spanned spans rather than Markdown source.
- Show progress stages immediately on click, animate reasoning while it
streams, then collapse it into a tappable details block.
- Attribute the card to a client-side mock sender and insert it directly
after the newest analyzed message, scrolling it into view.
Persistence:
- Store summaries in SQLite keyed by (dialog, topic, anchor) and
re-inject them when the chat is reopened.
Also add tools/release.py and a Gitea workflow that builds, verifies and
publishes dist/<id>.plugin to the Releases tab, and extend
tools/verify_bundle.py to 104 offline checks covering the transcript,
streaming, rendering, injection and storage behaviour.
lyuksovannyy
exteraGramPlugins