hablas-ai 2.2.3 → 2.2.5

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.
Files changed (3) hide show
  1. package/CHANGELOG.md +25 -23
  2. package/dist/index.js +115 -103
  3. package/package.json +1 -1
package/CHANGELOG.md CHANGED
@@ -1,33 +1,35 @@
1
1
  # Changelog
2
2
 
3
- ## [2.2.3] — 2026-06-12 · Trusted Image Pipeline and UX Phase Labels
3
+ ## [2.2.5] — 2026-06-13 · Models Pagination and Startup Redesign
4
4
 
5
5
  ### Added
6
- - `search_image_candidates` tool for ranking image candidates before download
7
- - `inspect_image` tool for checking remote or local image candidates before adoption
8
- - richer phase labels during tool-driven execution such as analysis, candidate selection, download, and verification
6
+ - `/models` paging support:
7
+ - `/models`
8
+ - `/models 2`
9
+ - `/models <query>`
10
+ - `/models <query> 2`
11
+ - active model marker in paged model browsing
9
12
 
10
13
  ### Changed
11
- - strengthened the system prompt around image handling so Hablas prefers ranking and inspection before downloading assets
12
- - upgraded tool box styling toward a cleaner premium terminal presentation
13
- - download flow now attempts to resolve direct image candidates from HTML pages automatically
14
+ - rebuilt the startup screen into a cleaner three-layer structure:
15
+ - identity
16
+ - environment
17
+ - action hints
18
+ - reduced startup clutter and noisy helper lines
19
+ - connection summary is now more compact and readable
14
20
 
15
- ### Fixed
16
- - image selection pipeline is less brute-force and less dependent on blind download retries
17
- - image inspection can now work on local assets as well as remote sources
21
+ ### Notes
22
+ This release completes backlog items:
23
+ - M-001 — models pagination / browsing UX
24
+ - M-002 — startup screen / first-view redesign
18
25
 
19
- ## [2.2.2] — 2026-06-12 · System Prompt Strength Rebuild
26
+ ## [2.2.4] — 2026-06-12 · Response Presentation and Personality Refinement
20
27
 
21
28
  ### Changed
22
- - Rebuilt the single-agent system prompt at a deeper architectural level.
23
- - Replaced weaker phrase-driven prompt behavior with a stronger role / mission / behavior-class / tool-contract structure.
24
- - Strengthened the prompt across all major execution domains:
25
- - product reasoning
26
- - architecture reasoning
27
- - implementation
28
- - debugging
29
- - review
30
- - devops thinking
31
- - web and asset acquisition
32
- - Strengthened tool discipline and anti-fake-completion rules.
33
- - Reduced dependence on brittle literal examples and pushed the prompt toward generalized intent interpretation.
29
+ - Improved final response presentation toward a more executive structure.
30
+ - Assistant markdown rendering is now richer, including better table rendering and stronger section visibility.
31
+ - Hablas personality was warmed up without turning fluffy: still technical and direct, but less cold and more partner-like.
32
+ - Final-response contract in the system prompt now explicitly prefers clearer completion sections and better next-step suggestions.
33
+
34
+ ### Added
35
+ - formal improvement backlog document for tracked UX and personality issues.