hablas-ai 2.0.0 → 2.0.2
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 +17 -0
- package/README.md +26 -0
- package/dist/index.js +108 -105
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,22 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## [2.0.2] — 2026-06-12 · Implementation Routing and Tool-Enforcement Fix
|
|
4
|
+
|
|
5
|
+
### Fixed
|
|
6
|
+
- Implementation requests are now classified more robustly, including common typos like `craet`.
|
|
7
|
+
- Architecture-only requests no longer get misrouted into implementation just because they mention engineering context.
|
|
8
|
+
- Implementation turns now explicitly require real workspace tool usage.
|
|
9
|
+
- If the model tries to answer an implementation task with inline code only and no tool calls, Hablas now forces a second attempt through the tool path instead of accepting the fake completion.
|
|
10
|
+
|
|
11
|
+
## [2.0.1] — 2026-06-12 · Setup Flow Restore
|
|
12
|
+
|
|
13
|
+
### Changed
|
|
14
|
+
- Restored the classic two-choice setup flow for the CLI.
|
|
15
|
+
- Brought back:
|
|
16
|
+
1. **Hablas Integrated Engine** — ready-made NVIDIA-backed setup with preselected model
|
|
17
|
+
2. **Custom Provider** — user-provided provider and key flow
|
|
18
|
+
- First launch now auto-runs setup again when no saved config exists.
|
|
19
|
+
|
|
3
20
|
## [2.0.0] — 2026-06-12 · Full Single-Agent Rebuild
|
|
4
21
|
|
|
5
22
|
This release replaces the old stable product surface with a new one built around a strict single-agent direction.
|
package/README.md
CHANGED
|
@@ -44,6 +44,32 @@ Requirements:
|
|
|
44
44
|
|
|
45
45
|
## Usage
|
|
46
46
|
|
|
47
|
+
### First run / setup
|
|
48
|
+
|
|
49
|
+
On first launch, Hablas now offers the restored classic setup flow:
|
|
50
|
+
|
|
51
|
+
1. **Hablas Integrated Engine**
|
|
52
|
+
- ready-made
|
|
53
|
+
- preconfigured NVIDIA-backed endpoint
|
|
54
|
+
- selected model already configured
|
|
55
|
+
- user just chooses option 1
|
|
56
|
+
|
|
57
|
+
2. **Custom Provider**
|
|
58
|
+
- Ollama
|
|
59
|
+
- OpenAI
|
|
60
|
+
- Groq
|
|
61
|
+
- OpenRouter
|
|
62
|
+
- Together
|
|
63
|
+
- DeepSeek
|
|
64
|
+
- custom OpenAI-compatible API
|
|
65
|
+
- NVIDIA NIM
|
|
66
|
+
|
|
67
|
+
You can also run setup manually anytime:
|
|
68
|
+
|
|
69
|
+
```bash
|
|
70
|
+
hablas --setup
|
|
71
|
+
```
|
|
72
|
+
|
|
47
73
|
### Interactive
|
|
48
74
|
|
|
49
75
|
```bash
|