hablas-ai 2.2.8 → 2.2.9

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/CHANGELOG.md CHANGED
@@ -1,5 +1,19 @@
1
1
  # Changelog
2
2
 
3
+ ## [2.2.9] — 2026-06-14 · Flow Restore and Final Stable UX Pass
4
+
5
+ ### Changed
6
+ - removed the hidden pre-turn model-assisted task profiler that was adding silent delay before visible thinking began
7
+ - restored lightweight local turn preparation so first-message UX stays fast and predictable again
8
+ - kept the stronger core system prompt, session continuity fix, and vision-in-image-tool architecture intact
9
+ - updated docs to mark `2.2.9` as the new stable closure point
10
+
11
+ ### Verification
12
+ - `npm test` passed
13
+ - `npm run build` passed
14
+ - `npm run lint` passed
15
+ - CLI smoke checks passed for `--help` and `info`
16
+
3
17
  ## [2.2.8] — 2026-06-14 · Stability Finish and Lint-Clean Runtime
4
18
 
5
19
  ### Added
package/README.md CHANGED
@@ -152,7 +152,7 @@ Hablas analyzes a request into one of four internal task kinds:
152
152
  - `analysis`
153
153
  - `implementation`
154
154
 
155
- The runtime now uses **semantic-first task profiling** backed by model judgment and recent conversation context, with heuristic fallback only as a safety net.
155
+ The runtime uses a **lightweight local task profiler** so first-turn latency stays clean and there is no hidden pre-turn model call before Hablas starts responding.
156
156
 
157
157
  Then it decides whether the turn should be:
158
158
  - **direct text execution**