broader-vids 0.1.3 → 0.1.5
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/README.md +37 -85
- package/bin/broader-vids.cjs +17 -1
- package/docs/ARCHITECTURE.md +6 -3
- package/docs/REFERENCE.md +17 -1
- package/docs/SCORING.md +5 -4
- package/docs/WORKFLOW.md +2 -2
- package/package.json +3 -3
- package/plugin.json +1 -1
- package/python/{broader_vids-0.1.3-py3-none-any.whl → broader_vids-0.1.5-py3-none-any.whl} +0 -0
package/README.md
CHANGED
|
@@ -1,33 +1,31 @@
|
|
|
1
1
|
# Broader Vids
|
|
2
2
|
|
|
3
|
-
Broader Vids provides an alternative recommendation algorithm for YouTube and Bilibili.
|
|
4
|
-
It combines your interests, exploration of unfamiliar topics, video quality, and feedback.
|
|
3
|
+
Broader Vids provides an alternative recommendation algorithm for YouTube and Bilibili. It combines your interests, exploration of unfamiliar topics, and video quality.
|
|
5
4
|
|
|
6
|
-
**
|
|
7
|
-
You can
|
|
8
|
-
Each complete round recommends ten videos per selected platform.
|
|
5
|
+
**Your dashboard ratings calibrate the plugin’s internal scoring models to your preferences.**
|
|
6
|
+
You can exclude creators and tags from future rounds. Each complete round recommends ten videos per selected platform.
|
|
9
7
|
|
|
10
|
-
The plugin runs locally through Codex CLI or Codex in the ChatGPT desktop app.
|
|
11
|
-
|
|
8
|
+
The plugin runs locally through Codex CLI or Codex in the ChatGPT desktop app. Recommendations appear in chat. A local dashboard manages ratings, exclusions, and preferences.
|
|
9
|
+
|
|
10
|
+
## Requirements
|
|
11
|
+
|
|
12
|
+
Use Windows, PowerShell, Node.js 20 or later with npm, UV, and Codex CLI signed in with ChatGPT. Installation and recommendations require internet access.
|
|
12
13
|
|
|
13
14
|
## Install the plugin
|
|
14
15
|
|
|
15
|
-
|
|
16
|
-
Installation and recommendations require internet access.
|
|
17
|
-
Choose one installation method. Neither method requires a checkout, build, or local folder selection.
|
|
16
|
+
Choose one of these three remote installation routes. You do not need a repository checkout or a local build.
|
|
18
17
|
|
|
19
|
-
###
|
|
18
|
+
### ChatGPT desktop app
|
|
20
19
|
|
|
21
20
|
1. Open the plugin marketplace controls in Codex.
|
|
22
|
-
2. Select **Add marketplace** and its repository or Git URL option.
|
|
21
|
+
2. Select **Add marketplace** and choose its repository or Git URL option.
|
|
23
22
|
3. Enter `https://github.com/antidemosthenes/broader-vids`.
|
|
24
|
-
4. Add or sync the marketplace.
|
|
25
|
-
5.
|
|
26
|
-
6. Start a new conversation.
|
|
23
|
+
4. Add or sync the marketplace. Then install **Broader Vids**.
|
|
24
|
+
5. Start a new conversation.
|
|
27
25
|
|
|
28
|
-
The GitHub repository
|
|
26
|
+
The GitHub repository provides the catalog. The catalog downloads the plugin package from npm.
|
|
29
27
|
|
|
30
|
-
###
|
|
28
|
+
### Codex CLI from GitHub
|
|
31
29
|
|
|
32
30
|
Run these commands in PowerShell:
|
|
33
31
|
|
|
@@ -38,7 +36,7 @@ codex plugin add broader-vids@broader-vids
|
|
|
38
36
|
|
|
39
37
|
Start a new conversation after installation.
|
|
40
38
|
|
|
41
|
-
###
|
|
39
|
+
### npm
|
|
42
40
|
|
|
43
41
|
Run this command in PowerShell:
|
|
44
42
|
|
|
@@ -46,88 +44,42 @@ Run this command in PowerShell:
|
|
|
46
44
|
npx --yes broader-vids@latest plugin install
|
|
47
45
|
```
|
|
48
46
|
|
|
49
|
-
This command registers an npm
|
|
50
|
-
It installs the skills and dashboard, not only the terminal launcher.
|
|
51
|
-
It does not require the GitHub catalog.
|
|
52
|
-
Restart the desktop app or start a new Codex CLI conversation after installation.
|
|
47
|
+
This command registers an npm backed marketplace and installs the plugin skills and dashboard. Start a new conversation after installation.
|
|
53
48
|
|
|
54
|
-
The app
|
|
55
|
-
Use the npm command above for that installation route.
|
|
56
|
-
See the [official packaging guide](https://developers.openai.com/plugins/build/plugins) for supported plugin sources.
|
|
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.
|
|
57
50
|
|
|
58
51
|
## Update the plugin
|
|
59
52
|
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
```powershell
|
|
63
|
-
codex plugin marketplace upgrade broader-vids
|
|
64
|
-
codex plugin add broader-vids@broader-vids
|
|
65
|
-
```
|
|
66
|
-
|
|
67
|
-
For an npm installation, repeat the installation command:
|
|
68
|
-
|
|
69
|
-
```powershell
|
|
70
|
-
npx --yes broader-vids@latest plugin install
|
|
71
|
-
```
|
|
72
|
-
|
|
73
|
-
In the desktop app, refresh the marketplace and select the current Broader Vids release.
|
|
74
|
-
If the app provides no update action, use the terminal commands for your installation method.
|
|
75
|
-
Start a new conversation and run setup after an update.
|
|
76
|
-
Setup installs the matching engine and preserves your saved profile.
|
|
77
|
-
Finish active recommendations and close the dashboard before updating.
|
|
78
|
-
|
|
79
|
-
## Set up and request recommendations
|
|
80
|
-
|
|
81
|
-
Use this procedure for either platform or both:
|
|
53
|
+
Follow [Update an installed plugin](docs/REFERENCE.md#update-an-installed-plugin) for update steps.
|
|
82
54
|
|
|
83
|
-
|
|
84
|
-
2. Choose YouTube, Bilibili, or both.
|
|
85
|
-
3. Choose calibrated starter preferences, enter your interests, or import a preference file.
|
|
86
|
-
4. Complete the dependency and access checks. Setup gives repair steps for required failures.
|
|
87
|
-
5. Invoke the recommendation skill. Review the links and summaries in chat.
|
|
88
|
-
6. Open the dashboard to mark watched videos and rate their topic, subject, depth, and quality.
|
|
89
|
-
7. Request another round when you want more recommendations.
|
|
55
|
+
## Set up and use Broader Vids
|
|
90
56
|
|
|
91
|
-
|
|
92
|
-
Saving ratings updates the local preference and quality models.
|
|
93
|
-
Their learned weights affect screening and final ranking in later rounds.
|
|
94
|
-
Creator and tag exclusions apply to the next new round.
|
|
95
|
-
The dashboard **Preferences** page lets you edit interests and import or export preferences and learned weights.
|
|
96
|
-
Before a new round, incomplete feedback prompts you to open the dashboard or continue.
|
|
57
|
+
Start a new conversation and invoke the setup skill. Choose YouTube, Bilibili, or both. Then choose starter preferences, enter interests, or import a preference file. Setup checks dependencies and access. It gives repair steps when a required check fails.
|
|
97
58
|
|
|
98
|
-
|
|
99
|
-
YouTube tag rules match available creator-supplied keyword tags, which differ from visible hashtags.
|
|
100
|
-
Bilibili rules match its video tags.
|
|
101
|
-
Search queries use English for YouTube and Simplified Chinese for Bilibili.
|
|
59
|
+
Invoke the recommendation skill to request a round. Review recommendations in chat. Open the dashboard to mark videos as watched and rate topic, subject, depth, and quality. Ratings update local preference and quality models. Their learned weights affect later rounds. Creator and tag exclusions apply to the next new round.
|
|
102
60
|
|
|
103
61
|
| Action | Skill command | Purpose |
|
|
104
62
|
| --- | --- | --- |
|
|
105
|
-
| Setup | `$broader-vids-setup` | Choose platforms and preferences
|
|
106
|
-
| Recommendations | `$broader-vids` | Request
|
|
107
|
-
| Dashboard | `$broader-vids-dashboard` | Rate videos
|
|
108
|
-
| Reset | `$broader-vids-reset` | Preview removal of preferences, weights, ratings, and histories
|
|
109
|
-
| Clean | `$broader-vids-clean` | Preview removal of all managed
|
|
110
|
-
|
|
111
|
-
Use the
|
|
112
|
-
|
|
113
|
-
You can also ask: “Use Broader Vids to recommend videos” or “Use Broader Vids to open my dashboard.”
|
|
63
|
+
| Setup | `$broader-vids-setup` | Choose platforms and preferences. Install tools and check access. |
|
|
64
|
+
| Recommendations | `$broader-vids` | Request videos for your saved platforms. |
|
|
65
|
+
| Dashboard | `$broader-vids-dashboard` | Rate videos. Manage exclusions and preferences. |
|
|
66
|
+
| Reset | `$broader-vids-reset` | Preview removal of preferences, weights, ratings, and histories. Keep tools and sign-in. |
|
|
67
|
+
| Clean | `$broader-vids-clean` | Preview removal of all managed data, including tools and sign-in. |
|
|
68
|
+
|
|
69
|
+
Use the skill commands shown in your host's skill menu. Some hosts add the plugin namespace, such as `$broader-vids:broader-vids-dashboard`. You can also ask Broader Vids to recommend videos or open the dashboard.
|
|
70
|
+
|
|
114
71
|
Reset and Clean require confirmation. Neither action uninstalls the plugin.
|
|
115
72
|
|
|
116
73
|
## Bilibili access and exclusions
|
|
117
74
|
|
|
118
|
-
Bilibili
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
|
|
75
|
+
Bilibili needs manual sign-in for full video evidence. Setup opens a separate browser. Keep it open after sign-in, then report completion in chat. Broader Vids checks the session and closes the browser. You can switch accounts from the dashboard.
|
|
76
|
+
|
|
77
|
+
Broader Vids imports your account blacklist after sign-in checks and before new rounds. Imported creator exclusions combine with your manual exclusions. A failed sync keeps the last complete copy. Use **Sync blacklist** in the dashboard to retry.
|
|
78
|
+
|
|
79
|
+
## Architecture and guides
|
|
123
80
|
|
|
124
|
-
|
|
125
|
-
Imported creator exclusions combine with your manual exclusions.
|
|
126
|
-
A failed sync preserves the last complete copy.
|
|
127
|
-
Use **Sync blacklist** in the dashboard to retry.
|
|
81
|
+
The Node launcher manages a versioned local Python engine, which stores profile data locally and serves the dashboard.
|
|
128
82
|
|
|
129
|
-
|
|
130
|
-
The [reference](docs/REFERENCE.md) covers terminal commands, troubleshooting, local builds, and maintenance.
|
|
131
|
-
The [architecture](docs/ARCHITECTURE.md) describes the launcher, engine, and local storage.
|
|
83
|
+
Read the [workflow](docs/WORKFLOW.md) for recommendation steps. Read the [scoring guide](docs/SCORING.md) for ranking and learning. The [reference](docs/REFERENCE.md) covers commands, troubleshooting, updates, and maintenance. The [architecture guide](docs/ARCHITECTURE.md) describes the launcher, engine, and local storage.
|
|
132
84
|
|
|
133
85
|
License: [MIT](LICENSE).
|
package/bin/broader-vids.cjs
CHANGED
|
@@ -101,6 +101,21 @@ function commandIndex(args) {
|
|
|
101
101
|
return -1;
|
|
102
102
|
}
|
|
103
103
|
|
|
104
|
+
function validateSetupArguments(args, index) {
|
|
105
|
+
for (let item = index + 1; item < args.length; item += 1) {
|
|
106
|
+
const value = args[item];
|
|
107
|
+
if (value === "--asr" || value === "--evidence") continue;
|
|
108
|
+
if (value === "--data-dir") {
|
|
109
|
+
item += 1;
|
|
110
|
+
continue;
|
|
111
|
+
}
|
|
112
|
+
if (value.startsWith("--data-dir=")) continue;
|
|
113
|
+
throw new Error(
|
|
114
|
+
"Use setup with optional --evidence, --asr, and --data-dir PATH.",
|
|
115
|
+
);
|
|
116
|
+
}
|
|
117
|
+
}
|
|
118
|
+
|
|
104
119
|
function invoke(command, args) {
|
|
105
120
|
const result = spawnSync(command, args, {
|
|
106
121
|
stdio: "inherit",
|
|
@@ -306,7 +321,8 @@ function main(args = process.argv.slice(2)) {
|
|
|
306
321
|
if (result.status === "partial") process.exitCode = 2;
|
|
307
322
|
return;
|
|
308
323
|
}
|
|
309
|
-
if (args[
|
|
324
|
+
if (args[index] === "setup") {
|
|
325
|
+
validateSetupArguments(args, index);
|
|
310
326
|
const sourceWheel = bundledWheel(packageRoot, manifest.version);
|
|
311
327
|
const wheelRoot = path.dirname(sourceWheel);
|
|
312
328
|
return withSetup(root, () => {
|
package/docs/ARCHITECTURE.md
CHANGED
|
@@ -68,6 +68,7 @@ broader-vids/
|
|
|
68
68
|
asr-requirements.txt Locked transcription dependencies
|
|
69
69
|
*.whl Generated engine package, excluded from Git
|
|
70
70
|
scripts/
|
|
71
|
+
release.py Build, verify, and synchronize release artifacts
|
|
71
72
|
release_ci.py Patch planning, publication checks, and GitHub assets
|
|
72
73
|
versioning.py Validated release metadata synchronization
|
|
73
74
|
test.py Isolated parallel regression runner
|
|
@@ -174,6 +175,7 @@ Refresh requests carry a read version and a mutation generation.
|
|
|
174
175
|
Only one refresh group runs at a time.
|
|
175
176
|
A refresh requested during an active read waits until that read finishes.
|
|
176
177
|
Old video records stay in browser memory only while the server returns them, an earlier list uses them, or they have an unsaved rating draft.
|
|
178
|
+
The interface removes saved-status notes and inspector positions when their videos leave all retained lists and drafts.
|
|
177
179
|
The interface rejects responses from before a newer mutation.
|
|
178
180
|
It pauses background refresh while the tab is hidden or a write is active.
|
|
179
181
|
Refresh preserves active controls and pane positions.
|
|
@@ -261,7 +263,8 @@ Preference transfer accepts format 4 with learning model version 8 and feature v
|
|
|
261
263
|
Manual creator rules transfer separately from learning parameters and replace the manual lists transactionally on import.
|
|
262
264
|
The export omits account-specific blacklist copies and sign-in data.
|
|
263
265
|
It includes a bounded exploration summary with at most 1,024 nodes and aggregate counts and round ages.
|
|
264
|
-
It
|
|
266
|
+
It includes watched video IDs without titles, ratings, or recommendation records.
|
|
267
|
+
Import adds their watched state without clearing local video states.
|
|
265
268
|
It does not change SQLite schema 12.
|
|
266
269
|
A completed `preference_import` job stores the imported parameter baseline and local feedback cutoff.
|
|
267
270
|
Fitting combines that baseline with active ratings saved after the cutoff.
|
|
@@ -275,11 +278,11 @@ Input validation runs once per terminal or HTTP request.
|
|
|
275
278
|
Failed imports remove unused recovery files.
|
|
276
279
|
Import also removes obsolete model caches while preserving models referenced by recommendations or frozen evaluations.
|
|
277
280
|
An uncertain commit retains its recovery file.
|
|
278
|
-
|
|
281
|
+
Preference recovery files reside in `backups/` and include prior watched IDs and manual creator rules.
|
|
279
282
|
The dashboard uses authenticated local POST operations for export, preview, and import.
|
|
280
283
|
The transfer dialog preserves rating drafts and blocks stale polling responses during an operation.
|
|
281
284
|
|
|
282
|
-
Evidence corrections add derived records.
|
|
285
|
+
Evidence corrections add derived records, including the current missing-caption deduction.
|
|
283
286
|
They do not overwrite original scorecards or user ratings.
|
|
284
287
|
|
|
285
288
|
The Preferences page uses `preferences.js` to coordinate `/api/interests` and the preference-transfer endpoints.
|
package/docs/REFERENCE.md
CHANGED
|
@@ -807,6 +807,10 @@ Dashboard browser tests require Playwright and a supported local browser.
|
|
|
807
807
|
Local Windows browser tests use installed Edge by default.
|
|
808
808
|
CI installs the Playwright Chromium headless shell on both operating systems.
|
|
809
809
|
Set `BROADER_VIDS_TEST_BROWSER=chromium` to use that browser locally.
|
|
810
|
+
Windows CI first installs the headless browser without changing system components.
|
|
811
|
+
If installation fails, it retries with the required system dependencies.
|
|
812
|
+
Linux CI installs those dependencies before tests.
|
|
813
|
+
Both paths retain browser validation and the full test suite.
|
|
810
814
|
Linux tests use Playwright Chromium. Install its browser and system dependencies before running tests:
|
|
811
815
|
|
|
812
816
|
```bash
|
|
@@ -970,6 +974,10 @@ Publication jobs accept the intentionally skipped duplicate checks on automatic
|
|
|
970
974
|
They still require successful preparation and stop after cancellation. GitHub assets also require successful npm publication.
|
|
971
975
|
Tag creation and GitHub release assets use separate jobs with `contents: write` permission.
|
|
972
976
|
The workflow publishes the verified archive under `latest`, then checks public registry integrity.
|
|
977
|
+
Registry verification allows up to five minutes for npm processing and tag propagation.
|
|
978
|
+
The wait uses bounded requests and reports progress.
|
|
979
|
+
A verification timeout can occur after npm accepts the package.
|
|
980
|
+
Check the public version before retrying. Rerun failed jobs to reuse a matching published archive and finish the GitHub release.
|
|
973
981
|
It creates a GitHub release with the archives, manifest, and checksums after npm publication succeeds.
|
|
974
982
|
It retains workflow artifacts for seven days.
|
|
975
983
|
|
|
@@ -1076,6 +1084,7 @@ Its `installed` status does not mean onboarding is complete.
|
|
|
1076
1084
|
Use the guided setup skill to configure interests, choose platforms, and check access.
|
|
1077
1085
|
`setup --evidence` also installs browser and media tools.
|
|
1078
1086
|
`setup --asr` includes those tools and transcription dependencies.
|
|
1087
|
+
Setup rejects unsupported options before it changes the profile or runtime.
|
|
1079
1088
|
The receipt records `core`, `evidence`, and `asr` only when setup installed those groups, with each group's requirements-file digest.
|
|
1080
1089
|
Setup requires Node.js 20 or later and UV.
|
|
1081
1090
|
It does not use an npm postinstall script.
|
|
@@ -1214,7 +1223,14 @@ Continue only after you restore access.
|
|
|
1214
1223
|
Browser sign-in is not imported automatically. Increasing the request cap does not repair an access challenge.
|
|
1215
1224
|
They share one request counter and retain the existing access checks.
|
|
1216
1225
|
Video downloads omit audio unless transcription requires it.
|
|
1217
|
-
|
|
1226
|
+
The engine checks selected-stream sizes before transfer.
|
|
1227
|
+
It uses reported exact sizes, reported estimates, or duration multiplied by bitrate, in that order.
|
|
1228
|
+
Transcription downloads include both video and audio in this check.
|
|
1229
|
+
If the estimate exceeds the remaining allowance, the engine tries a smaller offered format within the existing resolution and audio rules.
|
|
1230
|
+
When partial media exists, continuation resolves saved format IDs against fresh metadata and checks their codecs and resolution.
|
|
1231
|
+
If the original selection is unavailable, the engine skips the candidate and removes its owned partial files.
|
|
1232
|
+
Cumulative download charges remain unchanged.
|
|
1233
|
+
Unknown sizes still use the transfer byte limit.
|
|
1218
1234
|
Transfer checkpoints record observed bytes and bound unreported bytes after interruption.
|
|
1219
1235
|
Reports identify conservative byte charges as upper bounds.
|
|
1220
1236
|
|
package/docs/SCORING.md
CHANGED
|
@@ -162,10 +162,10 @@ Search-domain labels describe retrieval context.
|
|
|
162
162
|
They do not prove the video's semantic topic.
|
|
163
163
|
|
|
164
164
|
New AI topic labels must be short subject names, with at most 120 characters and 12 words.
|
|
165
|
-
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
|
|
165
|
+
Fresh assessments and reads of saved scorecards omit unusable topic labels before validation.
|
|
166
|
+
The filter removes obvious citations, instructions, control characters, and editing notes from the label lists.
|
|
167
|
+
The engine retains the raw model response and preserves numeric quality scores, saved ratings, and explicit user targets.
|
|
168
|
+
Remaining schema or evidence errors use the existing bounded assessment fix workflow.
|
|
169
169
|
This check detects common formatting errors. It does not prove that a topic correctly describes the video.
|
|
170
170
|
|
|
171
171
|
Source links, repost declarations, `中配`, and YouDub disclosures inform originality assessment.
|
|
@@ -388,6 +388,7 @@ A new response type requires new holdout coverage.
|
|
|
388
388
|
Training on released labels does not replace the earlier test result.
|
|
389
389
|
|
|
390
390
|
Evidence maintenance adds derived feature records after source checks.
|
|
391
|
+
Corrections include the current missing-caption deduction, which replaces any earlier deduction.
|
|
391
392
|
They preserve original ratings, scorecards, and captured features.
|
|
392
393
|
Incomplete source metadata can pause quality fitting.
|
|
393
394
|
Maintenance uses retained frames and captions without downloading replacement media.
|
package/docs/WORKFLOW.md
CHANGED
|
@@ -6,7 +6,7 @@ See the [terminal reference](REFERENCE.md) for commands.
|
|
|
6
6
|
|
|
7
7
|
## 1. Complete setup and check readiness
|
|
8
8
|
|
|
9
|
-
Use the [
|
|
9
|
+
Use the [update procedure](REFERENCE.md#update-an-installed-plugin) to update an installed plugin.
|
|
10
10
|
Finish active work before updating. Start a new conversation and run setup to prepare the matching engine.
|
|
11
11
|
Setup preserves the existing profile unless you explicitly request Reset or Clean.
|
|
12
12
|
|
|
@@ -131,7 +131,7 @@ The two-platform command runs these paths with shared workers and an optional to
|
|
|
131
131
|
```mermaid
|
|
132
132
|
flowchart TD
|
|
133
133
|
S["Recommendation request"] --> T{"Onboarding complete?"}
|
|
134
|
-
T -- No --> U["Introduce features; choose platforms; import preferences or enter interests"]
|
|
134
|
+
T -- No --> U["Introduce features; choose platforms; choose a starter, import preferences, or enter interests"]
|
|
135
135
|
U --> V["Install required tools and check selected platform access"]
|
|
136
136
|
V -- "Failure: repair and retry" --> V
|
|
137
137
|
V --> W["Record setup completion"]
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "broader-vids",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.5",
|
|
4
4
|
"description": "Codex skill and local YouTube/Bilibili recommendations with quality evidence and feedback",
|
|
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-0.1.5-*.whl",
|
|
15
15
|
"python/core-requirements.txt",
|
|
16
16
|
"python/evidence-requirements.txt",
|
|
17
17
|
"python/asr-requirements.txt",
|
|
@@ -46,6 +46,6 @@
|
|
|
46
46
|
"tag": "latest"
|
|
47
47
|
},
|
|
48
48
|
"broaderVidsRelease": {
|
|
49
|
-
"sourceCommit": "
|
|
49
|
+
"sourceCommit": "575b8bfeb556af08e68e46a103f441beb5745406"
|
|
50
50
|
}
|
|
51
51
|
}
|
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": "0.1.5",
|
|
5
5
|
"description": "Curated YouTube and Bilibili recommendations with bounded quality evidence and local watched/feedback state.",
|
|
6
6
|
"license": "MIT",
|
|
7
7
|
"extensions": {
|
|
index 958ab96..94c5e68 100644
|
|
|
Binary file
|