ltcai 5.1.0 → 5.2.0

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.
Files changed (27) hide show
  1. package/README.md +45 -39
  2. package/docs/CHANGELOG.md +36 -2355
  3. package/docs/V4_1_VALIDATION_REPORT.md +1 -1
  4. package/docs/V4_3_PRODUCT_HARDENING_REPORT.md +2 -2
  5. package/docs/V4_5_1_VALIDATION_REPORT.md +2 -1
  6. package/frontend/src/pages/Library.tsx +29 -4
  7. package/lattice_brain/__init__.py +1 -1
  8. package/lattice_brain/runtime/multi_agent.py +1 -1
  9. package/latticeai/__init__.py +1 -1
  10. package/latticeai/api/marketplace.py +2 -2
  11. package/latticeai/api/models.py +20 -4
  12. package/latticeai/core/marketplace.py +1 -1
  13. package/latticeai/core/workspace_os.py +18 -4
  14. package/latticeai/services/model_capability_registry.py +483 -0
  15. package/latticeai/services/model_catalog.py +99 -96
  16. package/latticeai/services/model_recommendation.py +12 -1
  17. package/package.json +1 -1
  18. package/scripts/verify_hf_model_registry.py +308 -0
  19. package/src-tauri/Cargo.lock +1 -1
  20. package/src-tauri/Cargo.toml +1 -1
  21. package/src-tauri/tauri.conf.json +1 -1
  22. package/static/app/asset-manifest.json +5 -5
  23. package/static/app/assets/index-CQmHhk8Q.css +2 -0
  24. package/static/app/assets/{index-DONOJfMn.js → index-DsnfomFs.js} +1 -1
  25. package/static/app/assets/{index-DONOJfMn.js.map → index-DsnfomFs.js.map} +1 -1
  26. package/static/app/index.html +2 -2
  27. package/static/app/assets/index-DuYYT2oh.css +0 -2
package/README.md CHANGED
@@ -33,7 +33,15 @@ Brain use from the Admin Console. Korean and English UI copy share the same
33
33
  underlying Brain, so language preference changes the interface, not your data.
34
34
 
35
35
  External package registries are owner-published and can lag behind this GitHub
36
- Release. Release uploads must use the exact v5.1.0 artifact filenames below.
36
+ Release. Release uploads must use the exact v5.2.0 artifact filenames below.
37
+
38
+ **5.2.0 major update**: Structured model capability registry + automated HF
39
+ verification (scripts/verify_hf_model_registry.py) + expanded modern multimodal
40
+ candidates. User-facing recommendations are narrowed to current load-ready
41
+ families; registry-only candidates stay visible for verification transparency
42
+ until config/tokenizer/load readiness is confirmed. Frontend now shows verified
43
+ status, modality badges, hardware fit notes, and explicit download/load
44
+ strategies before consent. See RELEASE.md and docs/CHANGELOG.md.
37
45
 
38
46
  ## Living Brain Flow
39
47
 
@@ -42,17 +50,17 @@ Release. Release uploads must use the exact v5.1.0 artifact filenames below.
42
50
  First launch opens to Login only. The local profile is the beginning of the
43
51
  Brain, not a dashboard, graph, or setup grid. The first screen frames Lattice as
44
52
  a durable knowledge home where models are replaceable and ownership stays with
45
- the user. v5.1.0 also prevents an email typo or wrong saved-user password from
46
- silently creating a new empty Brain.
53
+ the user. v5.2.0 adds a transparent verified model registry, load-ready catalog,
54
+ and workspace-scoped marketplace install state.
47
55
 
48
- ![Login](output/release/v5.1.0/screenshots/01-login.png)
56
+ ![Login](output/release/v5.2.0/screenshots/01-login.png)
49
57
 
50
58
  ### 2. Environment Analysis
51
59
 
52
60
  Lattice reads the machine locally and summarizes what kind of Brain this
53
61
  computer can support.
54
62
 
55
- ![Environment Analysis](output/release/v5.1.0/screenshots/02-environment-analysis.png)
63
+ ![Environment Analysis](output/release/v5.2.0/screenshots/02-environment-analysis.png)
56
64
 
57
65
  ### 3. Recommended Models
58
66
 
@@ -60,7 +68,7 @@ The model step is a short recommendation list. It avoids catalog noise and keeps
60
68
  runtime/install details behind clear user consent. Users who do not know which
61
69
  model to choose can start with the recommended model in one click.
62
70
 
63
- ![Recommended Models](output/release/v5.1.0/screenshots/03-recommended-models.png)
71
+ ![Recommended Models](output/release/v5.2.0/screenshots/03-recommended-models.png)
64
72
 
65
73
  ### 4. Install And Load
66
74
 
@@ -69,7 +77,7 @@ and load progress. No model download or runtime install starts silently, and the
69
77
  screen explains that large downloads may take minutes without inventing fake ETA
70
78
  data.
71
79
 
72
- ![Install and Load](output/release/v5.1.0/screenshots/04-install-load-progress.png)
80
+ ![Install and Load](output/release/v5.2.0/screenshots/04-install-load-progress.png)
73
81
 
74
82
  ### 5. Brain Chat
75
83
 
@@ -78,7 +86,7 @@ stays present while the user types, recalls context, and receives responses. The
78
86
  home now includes a compact Brain overview for recent memories, older memories,
79
87
  and major topics, plus saved-to-memory feedback after chat.
80
88
 
81
- ![Brain Chat Home](output/release/v5.1.0/screenshots/05-brain-chat-home.png)
89
+ ![Brain Chat Home](output/release/v5.2.0/screenshots/05-brain-chat-home.png)
82
90
 
83
91
  ## Brain Depths
84
92
 
@@ -87,26 +95,26 @@ while revealing more structure.
87
95
 
88
96
  | Depth | Experience | Evidence |
89
97
  | --- | --- | --- |
90
- | Level 1 | Living Brain presence | ![Living Brain Level 1](output/release/v5.1.0/screenshots/06-living-brain-level-1.png) |
91
- | Level 2 | Memory Layer | ![Memory Layer](output/release/v5.1.0/screenshots/07-memory-layer.png) |
92
- | Level 3 | Knowledge Layer | ![Knowledge Layer](output/release/v5.1.0/screenshots/08-knowledge-layer.png) |
93
- | Level 4 | Relationship Layer | ![Relationship Layer](output/release/v5.1.0/screenshots/09-relationship-layer.png) |
94
- | Level 5 | Knowledge Graph with nodes, edges, search, and focus detail | ![Knowledge Graph Layer](output/release/v5.1.0/screenshots/10-knowledge-graph-layer.png) |
98
+ | Level 1 | Living Brain presence | ![Living Brain Level 1](output/release/v5.2.0/screenshots/06-living-brain-level-1.png) |
99
+ | Level 2 | Memory Layer | ![Memory Layer](output/release/v5.2.0/screenshots/07-memory-layer.png) |
100
+ | Level 3 | Knowledge Layer | ![Knowledge Layer](output/release/v5.2.0/screenshots/08-knowledge-layer.png) |
101
+ | Level 4 | Relationship Layer | ![Relationship Layer](output/release/v5.2.0/screenshots/09-relationship-layer.png) |
102
+ | Level 5 | Knowledge Graph with nodes, edges, search, and focus detail | ![Knowledge Graph Layer](output/release/v5.2.0/screenshots/10-knowledge-graph-layer.png) |
95
103
 
96
104
  Walkthrough:
97
105
 
98
- ![v5.1.0 Living Brain walkthrough](output/release/v5.1.0/gifs/v5.1.0-living-brain-walkthrough.gif)
106
+ ![v5.2.0 Living Brain walkthrough](output/release/v5.2.0/gifs/v5.2.0-living-brain-walkthrough.gif)
99
107
 
100
108
  Model setup status evidence:
101
109
 
102
- ![Model setup status](output/release/v5.1.0/screenshots/11-model-setup-status.png)
110
+ ![Model setup status](output/release/v5.2.0/screenshots/11-model-setup-status.png)
103
111
 
104
112
  Separate admin console evidence:
105
113
 
106
- ![Admin Console](output/release/v5.1.0/screenshots/12-admin-console.png)
114
+ ![Admin Console](output/release/v5.2.0/screenshots/12-admin-console.png)
107
115
 
108
116
  Screenshot index and capture notes:
109
- [output/release/v5.1.0/SCREENSHOT_INDEX.md](output/release/v5.1.0/SCREENSHOT_INDEX.md)
117
+ [output/release/v5.2.0/SCREENSHOT_INDEX.md](output/release/v5.2.0/SCREENSHOT_INDEX.md)
110
118
 
111
119
  ## Architecture At A Glance
112
120
 
@@ -136,7 +144,7 @@ Screenshot index and capture notes:
136
144
  rebuild controls live under the separate `#/admin` console. Admin history,
137
145
  audit, stats, and sensitivity reads honor the active workspace when present.
138
146
 
139
- See [ARCHITECTURE.md](ARCHITECTURE.md) for the detailed v5.1.0 architecture.
147
+ See [ARCHITECTURE.md](ARCHITECTURE.md) for the detailed v5.2.0 architecture.
140
148
 
141
149
  ## Installation
142
150
 
@@ -168,15 +176,17 @@ pip install "ltcai[local]"
168
176
 
169
177
  ## Release Artifacts
170
178
 
171
- Validated v5.1.0 artifacts:
179
+ Validated 5.2.0 artifacts (current release):
172
180
 
173
- - `dist/ltcai-5.1.0-py3-none-any.whl`
174
- - `dist/ltcai-5.1.0.tar.gz`
175
- - `ltcai-5.1.0.tgz`
176
- - `dist/ltcai-5.1.0.vsix`
177
- - `src-tauri/target/release/bundle/dmg/Lattice AI_5.1.0_aarch64.dmg`
181
+ - `dist/ltcai-5.2.0-py3-none-any.whl`
182
+ - `dist/ltcai-5.2.0.tar.gz`
183
+ - `ltcai-5.2.0.tgz`
184
+ - `dist/ltcai-5.2.0.vsix`
185
+ - `src-tauri/target/release/bundle/dmg/Lattice AI_5.2.0_aarch64.dmg`
178
186
 
179
- Attach only those exact files to the GitHub Release. Do not upload `dist/*`.
187
+ Attach only those exact files to the GitHub Release. Do not upload a wildcard
188
+ from the `dist` directory. Historical artifact references in release history are
189
+ intentionally preserved.
180
190
 
181
191
  ## Local Development
182
192
 
@@ -203,7 +213,7 @@ npm run test:unit
203
213
  npm run test:integration
204
214
  npm run test:visual
205
215
  npm run desktop:tauri:check
206
- node scripts/run_python.mjs scripts/wheel_smoke.py --wheel dist/ltcai-5.1.0-py3-none-any.whl
216
+ node scripts/run_python.mjs scripts/wheel_smoke.py --wheel dist/ltcai-5.2.0-py3-none-any.whl
207
217
  npm pack --dry-run
208
218
  npm run docs:check-links
209
219
  ```
@@ -219,7 +229,7 @@ npm run docs:check-links
219
229
  - Agent/workflow simulation without a loaded LLM is deterministic and does not call a model.
220
230
  It is labeled as LLM-free/model-free rather than presented as autonomous model
221
231
  success.
222
- - Historical artifacts can remain in `dist/`; uploads must use exact v5.1.0
232
+ - Historical artifacts can remain in `dist/`; uploads must use exact target version (e.g. 5.2.0)
223
233
  filenames.
224
234
 
225
235
  ## Release History
@@ -234,20 +244,10 @@ npm run docs:check-links
234
244
  | 4.6.0 | Living Brain Experience: made Brain plus conversation the home product, added an animated living Brain presence, and moved graph exploration to the deepest intentional layer |
235
245
  | 4.5.1 | Product Reimagining RC: replaced the desktop shell, navigation model, onboarding journey, first-viewport hierarchy, and visual system while preserving capabilities and local-first architecture |
236
246
  | 4.5.0 | Product Experience Recovery RC: restored first-run setup, workspace/model onboarding, explicit model install/download/validate/load flow, Gemma 4 runtime compatibility gating, Basic-mode polish, and graph discoverability |
237
- | 4.4.0 | Brain Engine Extraction: Brain Core physically moved into `lattice_brain` with isolation tests |
238
- | 4.3.3 | Dead-Code Cleanup Release |
239
- | 4.3.2 | Product Polish & Graph UX Overhaul RC |
240
- | 4.3.1 | End-User Audit Repair RC |
241
- | 4.3.0 | Portability & Product Hardening RC |
242
- | 4.2.0 | Brain Core & Storage Rebuild |
243
- | 4.1.0 | Frontend & Desktop Rebuild |
244
- | 4.0.1 | Digital Brain maintenance |
245
- | 4.0.0 | Digital Brain Platform foundation |
246
- | 3.0.0 | v3 local-first AI workspace platform |
247
247
 
248
248
  ## Current Documentation
249
249
 
250
- - [ARCHITECTURE.md](ARCHITECTURE.md) - v5.1.0 architecture.
250
+ - [ARCHITECTURE.md](ARCHITECTURE.md) - v5.2.0 architecture.
251
251
  - [docs/WHY_LATTICE.md](docs/WHY_LATTICE.md) - why Lattice AI exists.
252
252
  - [docs/TRUST_MODEL.md](docs/TRUST_MODEL.md) - local-first trust model.
253
253
  - [PRIVACY.md](PRIVACY.md) - privacy and external communication policy.
@@ -256,10 +256,16 @@ npm run docs:check-links
256
256
  - [FEATURE_STATUS.md](FEATURE_STATUS.md) - current feature status and historical
257
257
  status ledger.
258
258
  - [RELEASE_NOTES.md](RELEASE_NOTES.md) - release notes index.
259
- - [RELEASE_NOTES_v5.1.0.md](RELEASE_NOTES_v5.1.0.md) - v5.1.0 Product Trust & Clarity release notes.
259
+ - [RELEASE.md](RELEASE.md) - current v5.2.0 release notes and historical release history.
260
+ - [RELEASE_NOTES_v5.2.0.md](RELEASE_NOTES_v5.2.0.md) - v5.2.0 user-focused model transformation release notes.
260
261
  - [RELEASE_NOTES_v5.0.0.md](RELEASE_NOTES_v5.0.0.md) - v5.0.0 multilingual foundation history.
262
+ - [RELEASE_NOTES_v4.7.2.md](RELEASE_NOTES_v4.7.2.md) - v4.7.2 intuitive Brain UX history.
263
+ - [RELEASE_NOTES_v4.7.1.md](RELEASE_NOTES_v4.7.1.md) - v4.7.1 admin operations history.
264
+ - [RELEASE_NOTES_v4.7.0.md](RELEASE_NOTES_v4.7.0.md) - v4.7.0 admin separation history.
261
265
  - [RELEASE_NOTES_v4.6.1.md](RELEASE_NOTES_v4.6.1.md) - v4.6.1 release refresh history.
262
266
  - [RELEASE_NOTES_v4.6.0.md](RELEASE_NOTES_v4.6.0.md) - v4.6.0 Living Brain history.
267
+ - [RELEASE_NOTES_v4.5.1.md](RELEASE_NOTES_v4.5.1.md) - v4.5.1 product reimagining history.
268
+ - [RELEASE_NOTES_v4.5.0.md](RELEASE_NOTES_v4.5.0.md) - v4.5.0 product recovery history.
263
269
  - [RELEASE.md](RELEASE.md) - release checklist and exact artifact guidance.
264
270
  - [SECURITY.md](SECURITY.md) - security posture.
265
271
  - [docs/CHANGELOG.md](docs/CHANGELOG.md) - changelog.