hablas-ai 2.2.2 → 2.2.4

package/CHANGELOG.md

@@ -1,25 +1,28 @@
 # Changelog
 
-## [2.2.2] — 2026-06-12 · System Prompt Strength Rebuild
+## [2.2.4] — 2026-06-12 · Response Presentation and Personality Refinement
 
 ### Changed
-- Rebuilt the single-agent system prompt at a deeper architectural level.
-- Replaced weaker phrase-driven prompt behavior with a stronger role / mission / behavior-class / tool-contract structure.
-- Strengthened the prompt across all major execution domains:
-  - product reasoning
-  - architecture reasoning
-  - implementation
-  - debugging
-  - review
-  - devops thinking
-  - web and asset acquisition
-- Strengthened tool discipline and anti-fake-completion rules.
-- Reduced dependence on brittle literal examples and pushed the prompt toward generalized intent interpretation.
+- Improved final response presentation toward a more executive structure.
+- Assistant markdown rendering is now richer, including better table rendering and stronger section visibility.
+- Hablas personality was warmed up without turning fluffy: still technical and direct, but less cold and more partner-like.
+- Final-response contract in the system prompt now explicitly prefers clearer completion sections and better next-step suggestions.
 
-## [2.2.1] — 2026-06-12 · Runtime Persistence and Web-Search Crash Fix
+### Added
+- formal improvement backlog document for tracked UX and personality issues.
+
+## [2.2.3] — 2026-06-12 · Trusted Image Pipeline and UX Phase Labels
+
+### Added
+- `search_image_candidates` tool for ranking image candidates before download
+- `inspect_image` tool for checking remote or local image candidates before adoption
+- richer phase labels during tool-driven execution such as analysis, candidate selection, download, and verification
+
+### Changed
+- strengthened the system prompt around image handling so Hablas prefers ranking and inspection before downloading assets
+- upgraded tool box styling toward a cleaner premium terminal presentation
+- download flow now attempts to resolve direct image candidates from HTML pages automatically
 
 ### Fixed
-- Restored the missing project-state import in the interactive runtime that caused `ensureProjectStateDir is not defined` at startup.
-- Fixed the web-search follow-up crash path by restoring the missing large-web token constant and the associated output-preservation path.
-- Project session state is now saved after slash commands as well as normal turns.
-- Read-cache preservation is now actually written back after successful `read_file` operations and invalidated when related files change.
+- image selection pipeline is less brute-force and less dependent on blind download retries
+- image inspection can now work on local assets as well as remote sources

package/README.md

@@ -92,12 +92,16 @@ hablas run "read package.json and tell me the version"
 ### Web and asset workflow
 Hablas now keeps the professional web tool chain active:
 - `web_search`
+- `search_image_candidates`
+- `inspect_image`
 - `scrape_url`
 - `extract_links`
 - `download_asset`
 
 This means Hablas can:
 - search the web for references and assets
+- rank image candidates before downloading
+- inspect a remote or local image candidate before adoption
 - inspect pages and extract links
 - download real images/files into the project when appropriate
 - preserve full file reads in-context so long files are not silently cut into tiny fragments that force rereads