diff options
| author | Agando <roduccomm@gmail.com> | 2026-11-06 11:45:21 +0100 |
|---|---|---|
| committer | Agando <roduccomm@gmail.com> | 2026-11-06 11:45:21 +0100 |
| commit | 03143a6e88832d06c7b08cdbf8de96ba79bda7d6 (patch) | |
| tree | a82db0d323e36aec94587332b263e2be9fd062c3 /modules/ext/media.js | |
| parent | 15b42d6379484bb3f439eb5d7f77f12877f74497 (diff) | |
release(v4.6.150): commit the module work that has been live but uncommitted
Operator commit-approve, 2026-11-06. These changes have been served since
2026-11-02/03 while git HEAD still stamped v4.6.146, so the mirror published a
tree four builds behind the running instance and the release tag named the
wrong build.
module-orchestrator.js — orchestrate-parallel reported success it could not
prove. Results are now recorded by sub-task id through a resultSink handed to
delegateTask (harvest matched by currentTask/lastTask strings, which a later
delegation on the same agent overwrote, losing finished work as "agent not
found"); the tally counts summaries with status ok instead of
Promise.allSettled resolutions (a spawn refusal fulfils with undefined and used
to print green); and a busy agent is no longer reused at pool cap, where two
siblings erased each other's lease. Guard:
modules/test/test-orchestrator-parallel-harvest.js (16 cases, reproduces the
one-agent three-sub-task cap case that printed 3/3 succeeded).
module-billing.js — the balance said "not signed in — newOS4 sends no session
token", which was already false: the browser sends the HttpOnly cookie and
parse_bearer_token() falls back to it. `cost` is on by default (the flag was
opt-in and nobody knew the command existed; `cost off` opts out) and the
command now prints today's platform spend from GET /api/billing/usage?days=1
alongside the session estimate.
modules/ext/webdav.js — the inline WebView detector missed "Version/4.0"
Android WebViews, including the operator's own phone, so the login offered a
Telegram widget that cannot complete there. It now delegates to
modules/wx11-tg-webview.js when the page loaded it and keeps a matching
fallback (wv token, Version/4.0-Android, Telegram, FBAN/Instagram/Line).
modules/ext/media.js — text analysis model renamed deepseek-v4-flash ->
deepseek-v4.1-flash in both the field and the printed label.
main.html + module-loader.js — v4.6.146 -> v4.6.150 in LATEST_VER and the three
asset queries; core-bundle.js rebuilt (rebuild-bundles.py reports it already
in sync, 1,250,569 bytes).
Verified: node --check on all six scripts and the new test; the 16-case
orchestrator guard passes against the deployed bundle (ORCH_SRC=...); bundle
rebuild is a no-op; core-bundle.js?v=v4.6.150 answers 200.
Diffstat (limited to 'modules/ext/media.js')
| -rw-r--r-- | modules/ext/media.js | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/modules/ext/media.js b/modules/ext/media.js index 5723e27..bdc50e2 100644 --- a/modules/ext/media.js +++ b/modules/ext/media.js @@ -1,13 +1,13 @@ // newOS4 Media Analysis Module (v4.5.79) // Commands: analyze <path> [--flags] // Uses gemini-3-flash-preview:cloud for vision (images, video frames) -// Uses deepseek-v4-flash:cloud for text analysis (audio features, summaries) +// Uses deepseek-v4.1-flash:cloud for text analysis (audio features, summaries) class MediaModule { constructor() { this.commands = {}; this.terminal = null; this._visionModel = 'gemini-3-flash-preview:cloud'; - this._textModel = 'deepseek-v4-flash:cloud'; + this._textModel = 'deepseek-v4.1-flash:cloud'; this._maxFrames = 10; // max video frames to analyze this._frameInterval = 5; // seconds between video frames } @@ -118,7 +118,7 @@ class MediaModule { } // Send features to text model for AI interpretation - this.terminal.print('\n🤖 AI interpretation (deepseek-v4-flash)...', 'info'); + this.terminal.print('\n🤖 AI interpretation (deepseek-v4.1-flash)...', 'info'); const prompt = `Analyze these audio features and describe what the audio likely sounds like. Consider the genre, mood, and characteristics: Duration: ${features.duration.toFixed(1)}s |