@datacore-one/mcp 1.1.2 → 1.3.0
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.
- package/README.md +27 -1
- package/dist/index.js +1597 -67
- package/dist/index.js.map +1 -1
- package/package.json +3 -2
- package/packs/dips-v1/engrams.yaml +2241 -2241
package/README.md
CHANGED
|
@@ -86,7 +86,7 @@ Mode is auto-detected. If you have a full [Datacore](https://github.com/datacore
|
|
|
86
86
|
|
|
87
87
|
Override with environment variables: `DATACORE_PATH` (full) or `DATACORE_CORE_PATH` (core).
|
|
88
88
|
|
|
89
|
-
## Tools (
|
|
89
|
+
## Tools (18 core + 3 full-mode)
|
|
90
90
|
|
|
91
91
|
### Session
|
|
92
92
|
|
|
@@ -114,6 +114,7 @@ Override with environment variables: `DATACORE_PATH` (full) or `DATACORE_CORE_PA
|
|
|
114
114
|
| `datacore.promote` | Activate candidate engrams |
|
|
115
115
|
| `datacore.feedback` | Signal whether engrams were helpful (single or batch) |
|
|
116
116
|
| `datacore.forget` | Retire an engram by ID or search |
|
|
117
|
+
| `datacore.resolve` | Resolve engagement events (reconsolidations, discoveries, challenges) |
|
|
117
118
|
|
|
118
119
|
### Packs
|
|
119
120
|
|
|
@@ -184,6 +185,28 @@ datacore.packs.export -- export your engrams as a pack
|
|
|
184
185
|
|
|
185
186
|
Bundled starter packs are installed automatically on first run.
|
|
186
187
|
|
|
188
|
+
## Engagement System
|
|
189
|
+
|
|
190
|
+
Datacore includes an optional engagement layer that tracks your AI's learning progress through XP, tiers, and gameplay mechanics. Enable it in `config.yaml`:
|
|
191
|
+
|
|
192
|
+
```yaml
|
|
193
|
+
engagement:
|
|
194
|
+
enabled: true
|
|
195
|
+
inline_xp: false # show XP gains inline in tool responses
|
|
196
|
+
```
|
|
197
|
+
|
|
198
|
+
When enabled, you earn XP for learning actions (creating engrams, giving feedback, reviewing contradictions). The system surfaces:
|
|
199
|
+
|
|
200
|
+
- **Reconsolidations** — detects contradictions between engrams and prompts you to defend, revise, or retire
|
|
201
|
+
- **Discoveries** — finds unexpected connections across knowledge domains
|
|
202
|
+
- **Challenges** — weekly goals that reward consistent usage
|
|
203
|
+
|
|
204
|
+
Progress is visible in `datacore.session.start` and `datacore.status`. Use `datacore.resolve` to act on reconsolidations, discoveries, and challenges.
|
|
205
|
+
|
|
206
|
+
Tiers: Seed (0 XP) -> Cipher (100) -> Sage (500) -> Adept (1200) -> Visionary (2500) -> Oracle (5000).
|
|
207
|
+
|
|
208
|
+
All engagement is gated behind `engagement.enabled` — when disabled, behavior is identical to v1.2.
|
|
209
|
+
|
|
187
210
|
## Configuration
|
|
188
211
|
|
|
189
212
|
### Environment Variables
|
|
@@ -214,6 +237,9 @@ search:
|
|
|
214
237
|
snippet_length: 500 # chars around match
|
|
215
238
|
hints:
|
|
216
239
|
enabled: true # include _hints in tool responses for agent guidance
|
|
240
|
+
engagement:
|
|
241
|
+
enabled: true # enable XP, tiers, and gameplay mechanics
|
|
242
|
+
inline_xp: false # show XP gains inline in tool responses
|
|
217
243
|
```
|
|
218
244
|
|
|
219
245
|
All fields have defaults -- the file is optional.
|