@hegel-dev/companion 1.0.7 → 1.0.8
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
CHANGED
|
@@ -22,6 +22,7 @@ Runs in milliseconds, zero cost. Always active.
|
|
|
22
22
|
### Layer 2: LLM Deep Analysis (prompt hooks)
|
|
23
23
|
Uses your Cursor subscription models. Optional, configurable.
|
|
24
24
|
|
|
25
|
+
- When you pick a concrete model in settings (anything other than `auto`), setup regenerates `.cursor/hooks.json` so Layer 2 hooks request that routing ID explicitly.
|
|
25
26
|
- Nuanced prompt quality evaluation beyond pattern matching
|
|
26
27
|
- Contextual assessment of whether a prompt has enough detail for its intent
|
|
27
28
|
- AI response review for missing edge cases, security blind spots, and scope creep
|
|
Binary file
|
package/package.json
CHANGED