broader-vids 0.1.11 → 0.1.13
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/docs/REFERENCE.md +20 -5
- package/docs/SCORING.md +47 -46
- package/docs/WORKFLOW.md +4 -2
- package/package.json +3 -3
- package/plugin.json +1 -1
- package/python/{broader_vids-0.1.11-py3-none-any.whl → broader_vids-0.1.13-py3-none-any.whl} +0 -0
- package/skills/broader-vids/SKILL.md +4 -0
- package/skills/claude-host.md +1 -1
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 +393,12 @@ 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
|
+
If planning still fails, the recommendation report includes the source failure.
|
|
401
|
+
A model-capacity error requires service availability. It does not indicate a Bilibili sign-in failure.
|
|
391
402
|
The engine does not switch to paid API access automatically.
|
|
392
403
|
|
|
393
404
|
## Continue an incomplete run
|
|
@@ -1321,13 +1332,17 @@ Continuation preserves an explicit deadline and all cumulative request, media, a
|
|
|
1321
1332
|
|
|
1322
1333
|
YouTube metadata retrieval uses one active watch-page request and starts at least one second apart.
|
|
1323
1334
|
Bilibili metadata retrieval uses at most two concurrent requests and starts at least one second apart.
|
|
1324
|
-
|
|
1325
|
-
These
|
|
1326
|
-
|
|
1327
|
-
|
|
1335
|
+
Both platforms retry temporary metadata failures: HTTP 408, 500, 502, 503, or 504, timeouts, connection resets, and incomplete responses.
|
|
1336
|
+
These failures and Bilibili API code `-404` share one initial attempt and up to three retries per candidate.
|
|
1337
|
+
YouTube's identity-repair retry uses the same allowance. It does not start a separate retry cycle.
|
|
1338
|
+
Retries use the same session, pacing, and request allowance.
|
|
1339
|
+
Recorded failures remain counted when a paused round continues. A new round has its own count.
|
|
1340
|
+
A successful retry returns normal metadata without a score deduction.
|
|
1341
|
+
After retry exhaustion, collection skips and reports that candidate, then fills its lane from other candidates.
|
|
1328
1342
|
Saved eligible candidates and unfinished batches remain available on continuation.
|
|
1329
1343
|
This result does not prove permanent deletion and does not assign a quality score or preference rating.
|
|
1330
|
-
Login errors, access challenges, malformed metadata, and mismatched video identities still pause collection.
|
|
1344
|
+
Login errors, rate limits, access challenges, malformed metadata, and mismatched video identities still pause collection.
|
|
1345
|
+
The engine does not retry HTTP 401, 403, 412, or 429 automatically.
|
|
1331
1346
|
Workers retain server-issued session cookies in memory.
|
|
1332
1347
|
Pacing waits count toward an optional saved time allowance.
|
|
1333
1348
|
The [yt-dlp request-rate guidance](https://github.com/yt-dlp/yt-dlp/wiki/Extractors#common-youtube-errors) recommends longer waits between downloads when rate limits occur.
|
package/docs/SCORING.md
CHANGED
|
@@ -52,22 +52,22 @@ Bilibili additionally requires coins/views >= 0.001 and favorites/views >= 0.002
|
|
|
52
52
|
Missing required metrics fail admission.
|
|
53
53
|
These hard floors use raw rates before the smoothing described below.
|
|
54
54
|
|
|
55
|
-
For metric count
|
|
55
|
+
For metric count $c$, views $v$, and platform baseline $b$, the adjusted rate is
|
|
56
56
|
|
|
57
|
-
|
|
57
|
+
$$
|
|
58
58
|
\widehat r=\frac{c+1000b}{v+1000}.
|
|
59
|
-
|
|
59
|
+
$$
|
|
60
60
|
|
|
61
61
|
The baseline is the middle sorted rate when at least ten valid platform observations exist.
|
|
62
62
|
Otherwise, initial baselines are 0.03 for likes, 0.01 for coins, and 0.02 for favorites.
|
|
63
|
-
The implementation limits the baseline below by
|
|
63
|
+
The implementation limits the baseline below by $10^{-6}$.
|
|
64
64
|
|
|
65
65
|
The metric score is
|
|
66
66
|
|
|
67
|
-
|
|
67
|
+
$$
|
|
68
68
|
e=100\sigma\left(\operatorname{clip}\left(\log\frac{\max(\widehat r,10^{-12})}{b},-8,8\right)\right),
|
|
69
69
|
\qquad \sigma(z)=\frac{1}{1+e^{-z}}.
|
|
70
|
-
|
|
70
|
+
$$
|
|
71
71
|
|
|
72
72
|
The rate-score helper assigns 50 to a missing count or zero denominator.
|
|
73
73
|
Such entries fail the hard admission floors and cannot enter a new recommendation shortlist.
|
|
@@ -147,16 +147,16 @@ Creator reputation does not guarantee a high grade.
|
|
|
147
147
|
Existing scorecards remain stored. New work and cache reuse require rubric 5.
|
|
148
148
|
|
|
149
149
|
An assessed criterion has an integer grade from zero to four.
|
|
150
|
-
Its normalized value is
|
|
150
|
+
Its normalized value is $u_j=\mathrm{grade}_j/4$.
|
|
151
151
|
An unknown criterion uses a prior mean of 0.5 and a separate missingness predictor.
|
|
152
152
|
Its stored grade remains unknown.
|
|
153
153
|
It does not inherit a high grade from another criterion.
|
|
154
154
|
|
|
155
|
-
For duration
|
|
155
|
+
For duration $t$ seconds, the derived initial quality index is
|
|
156
156
|
|
|
157
|
-
|
|
157
|
+
$$
|
|
158
158
|
d=\min(t/3600,1),\qquad Q_0=95\sum_j w_j u_j+5d.
|
|
159
|
-
|
|
159
|
+
$$
|
|
160
160
|
|
|
161
161
|
Length contributes at most five points.
|
|
162
162
|
The contribution rises to one hour and then remains constant.
|
|
@@ -168,7 +168,7 @@ It ignores retrieval origin and accepts only medium- or high-confidence matches.
|
|
|
168
168
|
Accepted matches supply canonical broad-root features for learned lookup.
|
|
169
169
|
Assessed topic labels remain unchanged.
|
|
170
170
|
|
|
171
|
-
The initial interest probability
|
|
171
|
+
The initial interest probability $I_0$ is 0.75 for a domain related to the user's stated interests.
|
|
172
172
|
It is 0.35 for a known unrelated domain and 0.50 when domains are unknown.
|
|
173
173
|
Search-domain labels describe retrieval context.
|
|
174
174
|
They do not prove the video's semantic topic.
|
|
@@ -191,10 +191,10 @@ Current ratings use categorical topic, subject, depth, and quality responses.
|
|
|
191
191
|
The quality model factors its categorical likelihood into logistic events.
|
|
192
192
|
Each event uses a predictor vector and a proper Gaussian prior:
|
|
193
193
|
|
|
194
|
-
|
|
194
|
+
$$
|
|
195
195
|
y_i\sim\operatorname{Bernoulli}(\sigma(o_i+x_i^T\beta)),
|
|
196
196
|
\qquad \beta_j\sim N(0,s_j^2).
|
|
197
|
-
|
|
197
|
+
$$
|
|
198
198
|
|
|
199
199
|
Numerical clipping keeps offsets finite.
|
|
200
200
|
It does not limit the final learned probability.
|
|
@@ -216,20 +216,20 @@ Model version 8 retains its portable parameter groups for exact preference trans
|
|
|
216
216
|
|
|
217
217
|
The initial weighted score is
|
|
218
218
|
|
|
219
|
-
|
|
219
|
+
$$
|
|
220
220
|
B=0.60Q+0.25I+0.05E+0.05R+0.05D.
|
|
221
|
-
|
|
221
|
+
$$
|
|
222
222
|
|
|
223
223
|
All components use a scale from zero to 100.
|
|
224
224
|
Without structured feedback, quality and interest use their initial priors.
|
|
225
225
|
The next section defines the structured replacements.
|
|
226
|
-
|
|
227
|
-
For age
|
|
228
|
-
A missing publication date gives
|
|
226
|
+
$E$ is community response.
|
|
227
|
+
For age $a$ in years, recency is $R=100/(1+a/10)$.
|
|
228
|
+
A missing publication date gives $R=50$.
|
|
229
229
|
|
|
230
|
-
Creator diversity is
|
|
231
|
-
Here,
|
|
232
|
-
The value
|
|
230
|
+
Creator diversity is $D=100/(1+n+0.1h)$.
|
|
231
|
+
Here, $n$ counts this creator in the developing list.
|
|
232
|
+
The value $h$ counts the creator in recent recommendation exposures.
|
|
233
233
|
Randomness enters discovery rather than adding a random final-score bonus.
|
|
234
234
|
This score component measures creator diversity.
|
|
235
235
|
Screening policy 5 also applies a separate diversity rule when it constructs each platform list.
|
|
@@ -246,7 +246,7 @@ It adds no model calls. It cannot guarantee semantic uniqueness when labels or q
|
|
|
246
246
|
Different videos about the same subject can therefore recur.
|
|
247
247
|
A subject match alone does not establish repeated content or equal explanatory depth.
|
|
248
248
|
|
|
249
|
-
Current profiles rank with
|
|
249
|
+
Current profiles rank with $B$, using learned structured quality and interest.
|
|
250
250
|
The initial component weights remain a ranking policy.
|
|
251
251
|
An empty internal overall model does not change this score.
|
|
252
252
|
Historical snapshots can retain an older overall adjustment.
|
|
@@ -278,15 +278,15 @@ The user can remove an exclusion.
|
|
|
278
278
|
### Topic and broad-subject interest
|
|
279
279
|
|
|
280
280
|
Each user-selected topic or subject uses a separate Dirichlet categorical model.
|
|
281
|
-
For initial mean
|
|
281
|
+
For initial mean $b$, its Low/Medium/High prior is
|
|
282
282
|
|
|
283
|
-
|
|
283
|
+
$$
|
|
284
284
|
\alpha=2\left((1-b)^2,\ 2b(1-b),\ b^2\right).
|
|
285
|
-
|
|
285
|
+
$$
|
|
286
286
|
|
|
287
|
-
Use
|
|
288
|
-
Current distinct-video category counts
|
|
289
|
-
The interest index is
|
|
287
|
+
Use $b=0.75$ for an onboarding-related topic or subject and $b=0.35$ otherwise.
|
|
288
|
+
Current distinct-video category counts $n$ give posterior $\operatorname{Dirichlet}(\alpha+n)$.
|
|
289
|
+
The interest index is $100[P(\mathrm{High})+0.5P(\mathrm{Medium})]$.
|
|
290
290
|
|
|
291
291
|
The earliest explicit topic or depth action anchors the topic's parent domains.
|
|
292
292
|
Edits and clears preserve that anchor.
|
|
@@ -312,25 +312,26 @@ Custom topic labels transfer only to matching normalized labels.
|
|
|
312
312
|
|
|
313
313
|
Depth uses an exact categorical model for each observed topic and audience level.
|
|
314
314
|
The responses are want deeper, suitable, and want lighter.
|
|
315
|
-
Their Dirichlet prior is
|
|
316
|
-
For an observed level,
|
|
315
|
+
Their Dirichlet prior is $(0.5,1,0.5)$.
|
|
316
|
+
For an observed level, $s=P(\mathrm{suitable})$ multiplies interest odds by $s/(1-s)$.
|
|
317
317
|
Its prior mean of 0.5 is neutral.
|
|
318
318
|
|
|
319
319
|
For a level without direct feedback, a separate directional model transfers information within that topic.
|
|
320
|
-
Encode introductory, intermediate, and advanced as
|
|
321
|
-
A latent preferred level has prior
|
|
322
|
-
With
|
|
320
|
+
Encode introductory, intermediate, and advanced as $l=0,1,2$.
|
|
321
|
+
A latent preferred level has prior $\mu\sim N(1,1.5^2)$.
|
|
322
|
+
With $w=0.75$, its likelihood is
|
|
323
323
|
|
|
324
|
-
|
|
324
|
+
$$
|
|
325
325
|
P(\mathrm{deeper}\mid\mu,l)=\sigma(\mu-l-w),
|
|
326
326
|
\quad P(\mathrm{lighter}\mid\mu,l)=\sigma(l-\mu-w),
|
|
327
|
-
|
|
328
|
-
|
|
327
|
+
$$
|
|
328
|
+
|
|
329
|
+
$$
|
|
329
330
|
P(\mathrm{suitable}\mid\mu,l)=1-P(\mathrm{deeper})-P(\mathrm{lighter}).
|
|
330
|
-
|
|
331
|
+
$$
|
|
331
332
|
|
|
332
333
|
Adaptive one-dimensional quadrature approximates this posterior.
|
|
333
|
-
The transfer adds
|
|
334
|
+
The transfer adds $\operatorname{logit}(s_{post})-\operatorname{logit}(s_{prior})$ to interest log odds.
|
|
334
335
|
Thus, no feedback gives no adjustment.
|
|
335
336
|
Want deeper shifts preference upward, while want lighter shifts it downward.
|
|
336
337
|
Direct categorical feedback takes precedence when that candidate level receives observations.
|
|
@@ -341,7 +342,7 @@ Its fixed noise width cannot represent every possible response distribution.
|
|
|
341
342
|
The exact categorical consistency result applies to directly observed topic-level groups.
|
|
342
343
|
No unconditional convergence claim applies to transferred scores at an unobserved level.
|
|
343
344
|
|
|
344
|
-
The engine clips depth suitability to
|
|
345
|
+
The engine clips depth suitability to $10^{-12}$ through $1-10^{-12}$ before conversion to log odds.
|
|
345
346
|
Depth does not change quality or domain interest.
|
|
346
347
|
Unknown audience levels retain feedback but do not adjust future scores.
|
|
347
348
|
The model supplies a cited level when the evidence supports one.
|
|
@@ -356,16 +357,16 @@ Duration does not establish audience level.
|
|
|
356
357
|
|
|
357
358
|
The quality model uses two logistic stages:
|
|
358
359
|
|
|
359
|
-
|
|
360
|
+
$$
|
|
360
361
|
a=P(\mathrm{Medium\ or\ High}),\quad b=P(\mathrm{High}\mid\mathrm{not\ Low}).
|
|
361
|
-
|
|
362
|
+
$$
|
|
362
363
|
|
|
363
|
-
The category probabilities are
|
|
364
|
+
The category probabilities are $(1-a,\ a(1-b),\ ab)$.
|
|
364
365
|
A Low response supplies only the first-stage event.
|
|
365
366
|
Medium and High responses also supply the conditional second-stage event.
|
|
366
367
|
This is one categorical likelihood, not duplicate votes or fractional Bernoulli labels.
|
|
367
368
|
|
|
368
|
-
The quality index is
|
|
369
|
+
The quality index is $Q=100[0.5P(\mathrm{Medium})+P(\mathrm{High})]$.
|
|
369
370
|
It represents expected ordinal utility, not a binary approval percentage.
|
|
370
371
|
Initial stage offsets use the quality prior when the retired binary model has no observations.
|
|
371
372
|
Learned corrections can cancel these offsets.
|
|
@@ -451,12 +452,12 @@ They continue to label local videos without adding their old ratings to training
|
|
|
451
452
|
|
|
452
453
|
For a logistic parameter vector, import uses the saved Gaussian approximation as a proper prior:
|
|
453
454
|
|
|
454
|
-
|
|
455
|
+
$$
|
|
455
456
|
\beta\sim N(m_0,\Sigma_0),\qquad
|
|
456
457
|
\log p(\beta\mid D_{\mathrm{new}})
|
|
457
458
|
=-\tfrac12(\beta-m_0)^\top\Sigma_0^{-1}(\beta-m_0)
|
|
458
459
|
+\sum_{i\in D_{\mathrm{new}}}\log p(y_i\mid x_i,\beta)+C.
|
|
459
|
-
|
|
460
|
+
$$
|
|
460
461
|
|
|
461
462
|
The implementation preserves off-diagonal correlations.
|
|
462
463
|
New coefficients receive the usual independent proper priors.
|
|
@@ -511,7 +512,7 @@ Larger models use matrix-free preconditioned conjugate gradients.
|
|
|
511
512
|
Prediction uses finite Gaussian quadrature.
|
|
512
513
|
These are numerical approximations, with conditional asymptotic justification rather than exact finite-sample posterior calculations.
|
|
513
514
|
|
|
514
|
-
For a fixed categorical group, the exact posterior is
|
|
515
|
+
For a fixed categorical group, the exact posterior is $\operatorname{Dirichlet}(\alpha+n)$.
|
|
515
516
|
If that group's distinct-video sample grows under stationary independent responses, empirical proportions converge and posterior variance tends to zero.
|
|
516
517
|
Each topic or level group needs its own coverage.
|
|
517
518
|
The ordinal model also requires positive second-stage frequency and well-specified conditional models.
|
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": "0.1.13",
|
|
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-0.1.13-*.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": "b44359de0922eeb8958c4b061f18d415b9e808c4"
|
|
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": "0.1.13",
|
|
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-0.1.11-py3-none-any.whl → broader_vids-0.1.13-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
|
|