broader-vids 0.1.12 → 0.1.14
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/plugin.json +1 -1
- package/README.md +1 -2
- package/docs/ARCHITECTURE.md +21 -5
- package/docs/REFERENCE.md +14 -0
- package/docs/SCORING.md +4 -0
- package/docs/WORKFLOW.md +4 -2
- package/package.json +3 -3
- package/plugin.json +1 -1
- package/python/{broader_vids-0.1.12-py3-none-any.whl → broader_vids-0.1.14-py3-none-any.whl} +0 -0
- package/skills/broader-vids/SKILL.md +4 -0
- package/skills/claude-host.md +1 -1
package/README.md
CHANGED
|
@@ -48,10 +48,9 @@ This command registers an npm backed marketplace and installs the plugin skills
|
|
|
48
48
|
|
|
49
49
|
The desktop app accepts repository URLs in **Add marketplace**. Use the npm command for npm installation. See the [plugin packaging guide](https://developers.openai.com/plugins/build/plugins) for supported sources.
|
|
50
50
|
|
|
51
|
-
|
|
52
51
|
### Experimental Claude Code path
|
|
53
52
|
|
|
54
|
-
Claude Code support is experimental. Static package checks and launcher fixtures cover it. No host acceptance test has been performed.
|
|
53
|
+
Claude Code support is experimental. Static package checks and launcher fixtures cover it. No host acceptance test has been performed. See the [Claude Code installation notes](docs/REFERENCE.md#experimental-claude-code-installation).
|
|
55
54
|
|
|
56
55
|
## Update the plugin
|
|
57
56
|
|
package/docs/ARCHITECTURE.md
CHANGED
|
@@ -239,7 +239,10 @@ See [data directory selection](REFERENCE.md#choose-a-data-directory).
|
|
|
239
239
|
|
|
240
240
|
Onboarding uses an atomic versioned file protected by a separate configuration lease.
|
|
241
241
|
It does not change SQLite schema 12 or the learning revision.
|
|
242
|
-
Preference transfer excludes
|
|
242
|
+
Preference transfer excludes the onboarding file.
|
|
243
|
+
|
|
244
|
+
Verified Bilibili login status also uses atomic file replacement.
|
|
245
|
+
A failed replacement preserves the previous status file.
|
|
243
246
|
Preflight counts unique recommendation exposures against current structured ratings.
|
|
244
247
|
Cleared fields count as incomplete again.
|
|
245
248
|
Its isolated subprocess checks have a deadline and owned process cleanup.
|
|
@@ -327,10 +330,21 @@ Pacing waits count toward an optional saved deadline.
|
|
|
327
330
|
Access failures cancel queued retrieval before another YouTube collector starts.
|
|
328
331
|
The gate preserves request pacing and prevents concurrent reservation of the last request slot.
|
|
329
332
|
Platform locks prevent conflicting recommendation jobs.
|
|
333
|
+
Separate startup reservations cover CLI readiness checks, round creation, execution, and reporting.
|
|
334
|
+
YouTube and Bilibili requests reserve their platforms in a fixed order.
|
|
335
|
+
The CLI releases each reservation when the request ends.
|
|
330
336
|
Short database transactions protect user actions and final result writes.
|
|
331
337
|
Dashboard lookup checks recommendation rounds from newest to oldest and stops at the first usable list.
|
|
332
338
|
Feedback resolves the displayed video evidence before it acquires its database write transaction.
|
|
333
339
|
Earlier pending videos retain their saved topic and depth context.
|
|
340
|
+
Dashboard and calibration responses resolve creator metadata in batches of at most 500 video IDs.
|
|
341
|
+
Each response builds a local creator-rule index. No profile-wide cache retains these objects.
|
|
342
|
+
Creator and tag responses use separate revisions to reject stale updates.
|
|
343
|
+
|
|
344
|
+
New exploration plans create recent-observation lookup indexes when needed.
|
|
345
|
+
Index creation occurs during writable planning, rather than when a database connection opens.
|
|
346
|
+
These derived indexes preserve schema 12 and all observation history.
|
|
347
|
+
Per-invocation planning limits do not replace the saved round allowance.
|
|
334
348
|
|
|
335
349
|
The engine checks profile, feedback, and queue changes before it saves a final recommendation list.
|
|
336
350
|
A conflicting change requires another ranking calculation.
|
|
@@ -348,13 +362,15 @@ YouTube and Bilibili share the same limit of three retries for recoverable candi
|
|
|
348
362
|
The engine saves attempt counts before worker dispatch. Continuation cannot grant an extra attempt.
|
|
349
363
|
Manual cancellation preserves that allowance.
|
|
350
364
|
Exhausted candidates become unavailable while other candidates continue.
|
|
351
|
-
Caption access challenges
|
|
352
|
-
|
|
353
|
-
|
|
365
|
+
Caption access challenges pause the affected platform.
|
|
366
|
+
In a combined round, any platform pause cancels unfinished work on both platforms.
|
|
367
|
+
Completed results remain available. Continuation requires a new user request.
|
|
354
368
|
Reports preserve the first failure separately from later cancellation messages.
|
|
355
369
|
Preparation checkpoints record transfer progress for interrupted-byte accounting.
|
|
356
370
|
Unknown usage retains an explicit upper bound.
|
|
357
|
-
Paused
|
|
371
|
+
Paused assessment and alignment stages can retain a provisional preview without creating exposure history.
|
|
372
|
+
Previews use the saved ranking policy and validated interest mappings.
|
|
373
|
+
Their video-state lookup reads only inspection candidates.
|
|
358
374
|
Batch heartbeats and live elapsed calculations keep progress reports current.
|
|
359
375
|
|
|
360
376
|
## Evidence lifetime
|
package/docs/REFERENCE.md
CHANGED
|
@@ -375,6 +375,11 @@ The combined batch shares worker slots and has no overall time limit by default.
|
|
|
375
375
|
You can set an optional shared limit with `--max-seconds`.
|
|
376
376
|
The limit can exceed 1,800 seconds.
|
|
377
377
|
Its platform jobs retain separate request, media, and model allowances.
|
|
378
|
+
If either platform pauses at any stage, the engine stops unfinished work on both platforms.
|
|
379
|
+
The shared report gives the original platform, stage, and cause.
|
|
380
|
+
Completed results remain available. Continue the batch only when the user requests it.
|
|
381
|
+
Candidate failures that retry or skip without pausing a platform remain nonblocking.
|
|
382
|
+
A published partial list does not cancel unfinished work on the other platform.
|
|
378
383
|
Discovery requests use a separate bounded counter and a ten-minute stage timeout.
|
|
379
384
|
Legacy checkpoints with the former default 1800-second cap continue without that cap.
|
|
380
385
|
Explicit limits saved by this version remain effective during continuation.
|
|
@@ -388,6 +393,13 @@ The engine does not silently substitute global CLI defaults or a preset model.
|
|
|
388
393
|
Accepted effort names are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`, and `ultra`.
|
|
389
394
|
The selected model and CLI must support the requested effort.
|
|
390
395
|
Failed calls consume their allowance.
|
|
396
|
+
Topic-planning calls have a 120-second timeout.
|
|
397
|
+
A timeout automatically uses the next saved planning call, if one remains.
|
|
398
|
+
This retry retains the selected topics, model, effort, and planning policy.
|
|
399
|
+
The default planning allowance remains two calls, including optional subdivision.
|
|
400
|
+
The round keeps this allowance when an invocation uses fewer calls.
|
|
401
|
+
If planning still fails, the recommendation report includes the source failure.
|
|
402
|
+
A model-capacity error requires service availability. It does not indicate a Bilibili sign-in failure.
|
|
391
403
|
The engine does not switch to paid API access automatically.
|
|
392
404
|
|
|
393
405
|
## Continue an incomplete run
|
|
@@ -1361,6 +1373,8 @@ They do not measure isolated model inference time.
|
|
|
1361
1373
|
Paused rounds can show a provisional preview in the digest and dashboard.
|
|
1362
1374
|
The dashboard labels the preview and allows ratings before publication.
|
|
1363
1375
|
That preview does not publish recommendations or change pending membership.
|
|
1376
|
+
It uses the saved duration deduction and any validated interest mappings.
|
|
1377
|
+
A pause during interest alignment can also retain this preview.
|
|
1364
1378
|
|
|
1365
1379
|
Scorecard schemas and validators use the same topic-label length bound of 120 characters.
|
|
1366
1380
|
See the [OpenAI Structured Outputs guide](https://developers.openai.com/api/docs/guides/structured-outputs) for supported schema constraints.
|
package/docs/SCORING.md
CHANGED
|
@@ -253,6 +253,10 @@ Historical snapshots can retain an older overall adjustment.
|
|
|
253
253
|
Published historical lists retain their saved scores.
|
|
254
254
|
Later runs use the current model.
|
|
255
255
|
|
|
256
|
+
Provisional previews use the round's saved ranking policy and validated interest mappings.
|
|
257
|
+
The short-video deduction applies once when the saved policy requires it.
|
|
258
|
+
Previews create no recommendation history.
|
|
259
|
+
|
|
256
260
|
## 6. Structured feedback
|
|
257
261
|
|
|
258
262
|
Topic interest, broad-subject interest, depth fit, and video quality are independent dimensions.
|
package/docs/WORKFLOW.md
CHANGED
|
@@ -257,7 +257,9 @@ Quality evidence can leave a video's quality unknown, which excludes that video
|
|
|
257
257
|
A candidate failure does not cancel unrelated inspections.
|
|
258
258
|
Validation failures share the same three-retry limit and saved call and image allowances.
|
|
259
259
|
Access challenges pause the affected platform.
|
|
260
|
-
|
|
260
|
+
In a combined round, any platform pause cancels unfinished work on both platforms.
|
|
261
|
+
The report identifies the first platform, stage, and cause. Sibling cancellation messages do not replace this cause.
|
|
262
|
+
Completed lists and saved progress remain available. Continuation requires a new user request.
|
|
261
263
|
Final selection first favors candidates that avoid overlap with earlier picks in the same platform list.
|
|
262
264
|
Overlap uses shared search queries, matching primary content topics, and secondary-school course markers.
|
|
263
265
|
Broad subjects alone do not create overlap.
|
|
@@ -287,7 +289,7 @@ Optional local transcription supplies text when captions are unavailable.
|
|
|
287
289
|
If no usable transcript exists, the video still receives a visual assessment using frames and readable burned-in text, with a separate ten-point quality deduction.
|
|
288
290
|
Unsupported speech, sound and continuity properties remain unknown.
|
|
289
291
|
Caption access challenges pause acquisition for the affected platform instead of triggering visual fallback.
|
|
290
|
-
|
|
292
|
+
A combined round cancels remaining downloads and assessments, then saves their progress before returning its report.
|
|
291
293
|
A continuation retains completed assessments and remaining allowances.
|
|
292
294
|
The initial assessment uses up to four distinct frames when captions are available.
|
|
293
295
|
Without captions, new evidence jobs sample up to eight distinct frames across the video.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "broader-vids",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.14",
|
|
4
4
|
"description": "Codex and experimental Claude Code skills for local YouTube/Bilibili recommendations",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"engines": {
|
|
@@ -11,7 +11,7 @@
|
|
|
11
11
|
},
|
|
12
12
|
"files": [
|
|
13
13
|
"bin/",
|
|
14
|
-
"python/broader_vids-0.1.
|
|
14
|
+
"python/broader_vids-0.1.14-*.whl",
|
|
15
15
|
"python/core-requirements.txt",
|
|
16
16
|
"python/evidence-requirements.txt",
|
|
17
17
|
"python/asr-requirements.txt",
|
|
@@ -48,6 +48,6 @@
|
|
|
48
48
|
"tag": "latest"
|
|
49
49
|
},
|
|
50
50
|
"broaderVidsRelease": {
|
|
51
|
-
"sourceCommit": "
|
|
51
|
+
"sourceCommit": "77891a41cf00fddaba2886cd8c3b41d238a664dd"
|
|
52
52
|
}
|
|
53
53
|
}
|
package/plugin.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
|
|
3
3
|
"name": "broader-vids",
|
|
4
|
-
"version": "0.1.
|
|
4
|
+
"version": "0.1.14",
|
|
5
5
|
"description": "Curated YouTube and Bilibili recommendations with bounded quality evidence and local watched/feedback state.",
|
|
6
6
|
"license": "MIT",
|
|
7
7
|
"extensions": {
|
package/python/{broader_vids-0.1.12-py3-none-any.whl → broader_vids-0.1.14-py3-none-any.whl}
RENAMED
|
Binary file
|
|
@@ -126,6 +126,10 @@ For `assessment_insufficient_evidence`, summarize the saved assessment rationale
|
|
|
126
126
|
A successful download does not need all four attempts. Do not download it again solely because its quality score is unknown.
|
|
127
127
|
Do not stop or ask to continue only because the report marks a candidate unavailable.
|
|
128
128
|
Keep nonblocking candidate failures in the final summary instead of interrupting the recommendation request.
|
|
129
|
+
If either platform pauses, the engine cancels unfinished work in the combined round.
|
|
130
|
+
Report the batch's original stop cause, including its platform and stage.
|
|
131
|
+
End the request after reporting the pause. Continue only when the user asks.
|
|
132
|
+
Keep completed lists and saved progress. Do not continue the other platform independently.
|
|
129
133
|
When a round pauses, present its provisional preview if the digest contains one.
|
|
130
134
|
Identify the preview as an assessed subset rather than a published recommendation list.
|
|
131
135
|
Report the first failure and remaining allowances before proposing continuation.
|
package/skills/claude-host.md
CHANGED
|
@@ -29,7 +29,7 @@ For a successful explicit setup request, return the full guide produced by `onbo
|
|
|
29
29
|
|
|
30
30
|
Use the recommendation skill's engine workflow, evidence rules, saved profile, and feedback gate. Run one recommendation command with `--host claude`, the verified `--model` and `--effort`, and the requested platform options.
|
|
31
31
|
|
|
32
|
-
Do not bypass incomplete feedback without the user's explicit choice. Do not reduce requested platform coverage. Report incomplete results as partial and keep candidate failure details accurate. Continue a paused run only when the user asks.
|
|
32
|
+
Do not bypass incomplete feedback without the user's explicit choice. Do not reduce requested platform coverage. Report incomplete results as partial and keep candidate failure details accurate. If either platform pauses, report the original batch cause and end the request. Continue a paused run only when the user asks.
|
|
33
33
|
|
|
34
34
|
## Dashboard
|
|
35
35
|
|