deeprefine-cli 0.1.4__tar.gz → 0.1.5__tar.gz

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 (21) hide show
  1. {deeprefine_cli-0.1.4/deeprefine_cli.egg-info → deeprefine_cli-0.1.5}/PKG-INFO +22 -13
  2. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/README.md +21 -12
  3. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/SKILL.md +12 -4
  4. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5/deeprefine_cli.egg-info}/PKG-INFO +22 -13
  5. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/SKILL.md +12 -4
  6. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/__init__.py +1 -1
  7. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/pyproject.toml +1 -1
  8. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/LICENSE +0 -0
  9. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/MANIFEST.in +0 -0
  10. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/SOURCES.txt +0 -0
  11. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/dependency_links.txt +0 -0
  12. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/entry_points.txt +0 -0
  13. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/requires.txt +0 -0
  14. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/top_level.txt +0 -0
  15. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/adapter_graphify.py +0 -0
  16. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/cli.py +0 -0
  17. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/history.py +0 -0
  18. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/installers.py +0 -0
  19. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/paths.py +0 -0
  20. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/refine_runner.py +0 -0
  21. {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/setup.cfg +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: deeprefine-cli
3
- Version: 0.1.4
3
+ Version: 0.1.5
4
4
  Summary: CLI and Cursor skill to refine graphify knowledge graphs with DeepRefine
5
5
  Author: HKUST-KnowComp
6
6
  License-Expression: MIT
@@ -29,8 +29,8 @@ Dynamic: license-file
29
29
  # DeepRefine-Skill
30
30
 
31
31
 
32
- [![PyPi](https://img.shields.io/badge/PyPi-v0.1.4-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.4/)
33
- [![Python](https://img.shields.io/badge/Python-3.10,3.11,3.12-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.4/)
32
+ [![PyPi](https://img.shields.io/badge/PyPi-v0.1.5-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.5/)
33
+ [![Python](https://img.shields.io/badge/Python-3.10,3.11,3.12-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.5/)
34
34
  [![Paper](https://img.shields.io/badge/Paper-DeepRefine-b31b1b.svg)](https://arxiv.org/pdf/2605.10488)
35
35
  [![Project](https://img.shields.io/badge/Project-DeepRefine-green.svg)](https://github.com/HKUST-KnowComp/DeepRefine)
36
36
 
@@ -38,7 +38,7 @@ Dynamic: license-file
38
38
 
39
39
  Type `/deeprefine` in your AI coding assistant after you've built a **[graphify](https://github.com/safishamsi/graphify)** knowledge base — it patches `graphify-out/graph.json` from your session's query history to evolve your LLM-Wiki.
40
40
 
41
- Works in **Cursor** (install the skill once with `deeprefine cursor install`). The same workflow is available from any terminal via the `deeprefine` CLI ([`deeprefine-cli` on PyPI](https://pypi.org/project/deeprefine-cli/)).
41
+ Works in **Cursor** (install the skill once with `deeprefine cursor install`). In Cursor, `/deeprefine` runs in **agent-native mode** (no extra API key needed). The runtime CLI (`deeprefine refine`) is still available for vLLM/API execution.
42
42
 
43
43
  ```
44
44
  /deeprefine
@@ -62,15 +62,14 @@ graphify-out/
62
62
  ```
63
63
 
64
64
  > **Standalone repo.** Model code (`autorefiner`, `atlas_rag`) lives in a separate [DeepRefine](https://github.com/HKUST-KnowComp/DeepRefine) checkout.
65
- > `pip install deeprefine-cli` ships the CLI and `SKILL.md`. `deeprefine refine` still needs DeepRefine + `atlastune`, with default inference from your current API model setup; you can override with custom base URL and API key.
65
+ > `pip install deeprefine-cli` ships the CLI and `SKILL.md`. In Cursor, `/deeprefine` uses agent-native refinement; `deeprefine refine` uses DeepRefine runtime (vLLM/API) when you explicitly choose CLI execution.
66
66
 
67
67
  ---
68
68
 
69
- ## Roadmap
69
+ ## News
70
70
 
71
- **Inference today:** default to your current API model setup.
72
-
73
- **Optional:** set custom OpenAI-compatible base URL and API key for LLM / embeddings.
71
+ - [2026/6/2] deeprefine-cli v0.1.5 has been released! Agent-native `/deeprefine` flow + clearer CLI/Agent split.
72
+ - [2026/6/2] deeprefine-cli v0.1.4 has been released! Customize your LLM api.
74
73
 
75
74
  ---
76
75
 
@@ -82,7 +81,7 @@ graphify-out/
82
81
  | 2 | `pip install deeprefine-cli` |
83
82
  | 3 | `deeprefine cursor install` in your KB project |
84
83
  | 4 | (Optional) start local vLLM, or use your API provider |
85
- | 5 | `deeprefine history add` `deeprefine refine` |
84
+ | 5 | Cursor chat: `/deeprefine` *(auto uses/adds query context)*; CLI mode: `history add` + `refine` |
86
85
 
87
86
  ```bash
88
87
  # 1) DeepRefine (once)
@@ -111,11 +110,21 @@ export DEEPREFINE_EMBED_MODEL=your_embed_model
111
110
  # export DEEPREFINE_API_KEY=your_shared_api_key
112
111
  # optional model overrides:
113
112
 
114
- # 5) Refine
113
+ # 5a) Refine in Cursor chat (agent-native, recommended)
114
+ # type in chat:
115
+ # /deeprefine
116
+
117
+ # 5b) Refine in terminal / CLI (manual flow)
115
118
  deeprefine history add --query "your question"
116
119
  deeprefine refine
117
120
  ```
118
121
 
122
+ In **Cursor chat** (agent):
123
+
124
+ ```text
125
+ /deeprefine
126
+ ```
127
+
119
128
  ---
120
129
 
121
130
  ## Pipeline
@@ -257,8 +266,8 @@ deeprefine cursor install
257
266
  |:-:|--------|
258
267
  | 1 | `graphify .` or `/graphify .` → `graphify-out/graph.json` |
259
268
  | 2 | `graphify query "..."` |
260
- | 3 | `deeprefine history add --query "..."` |
261
- | 4 | `deeprefine refine` or `/deeprefine` |
269
+ | 3 | Cursor chat: `/deeprefine` *(recommended; no manual `history add` needed)* |
270
+ | 4 | CLI alternative: `deeprefine history add --query "..."` `deeprefine refine` |
262
271
  | 5 | *(optional)* `graphify query "..."` to verify |
263
272
 
264
273
  ---
@@ -3,8 +3,8 @@
3
3
  # DeepRefine-Skill
4
4
 
5
5
 
6
- [![PyPi](https://img.shields.io/badge/PyPi-v0.1.4-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.4/)
7
- [![Python](https://img.shields.io/badge/Python-3.10,3.11,3.12-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.4/)
6
+ [![PyPi](https://img.shields.io/badge/PyPi-v0.1.5-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.5/)
7
+ [![Python](https://img.shields.io/badge/Python-3.10,3.11,3.12-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.5/)
8
8
  [![Paper](https://img.shields.io/badge/Paper-DeepRefine-b31b1b.svg)](https://arxiv.org/pdf/2605.10488)
9
9
  [![Project](https://img.shields.io/badge/Project-DeepRefine-green.svg)](https://github.com/HKUST-KnowComp/DeepRefine)
10
10
 
@@ -12,7 +12,7 @@
12
12
 
13
13
  Type `/deeprefine` in your AI coding assistant after you've built a **[graphify](https://github.com/safishamsi/graphify)** knowledge base — it patches `graphify-out/graph.json` from your session's query history to evolve your LLM-Wiki.
14
14
 
15
- Works in **Cursor** (install the skill once with `deeprefine cursor install`). The same workflow is available from any terminal via the `deeprefine` CLI ([`deeprefine-cli` on PyPI](https://pypi.org/project/deeprefine-cli/)).
15
+ Works in **Cursor** (install the skill once with `deeprefine cursor install`). In Cursor, `/deeprefine` runs in **agent-native mode** (no extra API key needed). The runtime CLI (`deeprefine refine`) is still available for vLLM/API execution.
16
16
 
17
17
  ```
18
18
  /deeprefine
@@ -36,15 +36,14 @@ graphify-out/
36
36
  ```
37
37
 
38
38
  > **Standalone repo.** Model code (`autorefiner`, `atlas_rag`) lives in a separate [DeepRefine](https://github.com/HKUST-KnowComp/DeepRefine) checkout.
39
- > `pip install deeprefine-cli` ships the CLI and `SKILL.md`. `deeprefine refine` still needs DeepRefine + `atlastune`, with default inference from your current API model setup; you can override with custom base URL and API key.
39
+ > `pip install deeprefine-cli` ships the CLI and `SKILL.md`. In Cursor, `/deeprefine` uses agent-native refinement; `deeprefine refine` uses DeepRefine runtime (vLLM/API) when you explicitly choose CLI execution.
40
40
 
41
41
  ---
42
42
 
43
- ## Roadmap
43
+ ## News
44
44
 
45
- **Inference today:** default to your current API model setup.
46
-
47
- **Optional:** set custom OpenAI-compatible base URL and API key for LLM / embeddings.
45
+ - [2026/6/2] deeprefine-cli v0.1.5 has been released! Agent-native `/deeprefine` flow + clearer CLI/Agent split.
46
+ - [2026/6/2] deeprefine-cli v0.1.4 has been released! Customize your LLM api.
48
47
 
49
48
  ---
50
49
 
@@ -56,7 +55,7 @@ graphify-out/
56
55
  | 2 | `pip install deeprefine-cli` |
57
56
  | 3 | `deeprefine cursor install` in your KB project |
58
57
  | 4 | (Optional) start local vLLM, or use your API provider |
59
- | 5 | `deeprefine history add` `deeprefine refine` |
58
+ | 5 | Cursor chat: `/deeprefine` *(auto uses/adds query context)*; CLI mode: `history add` + `refine` |
60
59
 
61
60
  ```bash
62
61
  # 1) DeepRefine (once)
@@ -85,11 +84,21 @@ export DEEPREFINE_EMBED_MODEL=your_embed_model
85
84
  # export DEEPREFINE_API_KEY=your_shared_api_key
86
85
  # optional model overrides:
87
86
 
88
- # 5) Refine
87
+ # 5a) Refine in Cursor chat (agent-native, recommended)
88
+ # type in chat:
89
+ # /deeprefine
90
+
91
+ # 5b) Refine in terminal / CLI (manual flow)
89
92
  deeprefine history add --query "your question"
90
93
  deeprefine refine
91
94
  ```
92
95
 
96
+ In **Cursor chat** (agent):
97
+
98
+ ```text
99
+ /deeprefine
100
+ ```
101
+
93
102
  ---
94
103
 
95
104
  ## Pipeline
@@ -231,8 +240,8 @@ deeprefine cursor install
231
240
  |:-:|--------|
232
241
  | 1 | `graphify .` or `/graphify .` → `graphify-out/graph.json` |
233
242
  | 2 | `graphify query "..."` |
234
- | 3 | `deeprefine history add --query "..."` |
235
- | 4 | `deeprefine refine` or `/deeprefine` |
243
+ | 3 | Cursor chat: `/deeprefine` *(recommended; no manual `history add` needed)* |
244
+ | 4 | CLI alternative: `deeprefine history add --query "..."` `deeprefine refine` |
236
245
  | 5 | *(optional)* `graphify query "..."` to verify |
237
246
 
238
247
  ---
@@ -5,7 +5,7 @@ description: >-
5
5
  Reafiner based on session query history. Use when the user runs /deeprefine,
6
6
  asks to improve the graphify KB after Q&A, or wants to patch graph.json from
7
7
  failed retrieval queries.
8
- disable-model-invocation: true
8
+ disable-model-invocation: false
9
9
  ---
10
10
 
11
11
  # DeepRefine (graphify)
@@ -36,16 +36,24 @@ Inference defaults to your current API model setup (`OPENAI_API_KEY` or `DEEPREF
36
36
 
37
37
  Optional: local vLLM from DeepRefine (embedding `8128`, refine model `8134`; see `scripts/vllm_serve/`).
38
38
 
39
- ## `/deeprefine`
39
+ ## `/deeprefine` (agent-native)
40
40
 
41
41
  From the **KB project root** (with `graphify-out/graph.json`):
42
42
 
43
43
  ```bash
44
44
  deeprefine history add --query "..." # after graph Q&A
45
- deeprefine refine # all pending queries
45
+ /deeprefine # run inside agent (no extra API key)
46
46
  ```
47
47
 
48
- Do not hand-edit `graph.json` for refinement.
48
+ What the agent should do when `/deeprefine` is invoked:
49
+
50
+ 1. Load pending queries from `graphify-out/.deeprefine/history.jsonl`.
51
+ 2. Read `graphify-out/graph.json`.
52
+ 3. Propose and apply minimal graph updates directly to `graph.json` for unresolved queries.
53
+ 4. Write a timestamped log to `graphify-out/.deeprefine/refinement_results_*.jsonl`.
54
+ 5. Mark processed history items as `refined: true`.
55
+
56
+ Use `deeprefine refine` CLI only when explicitly asked to run DeepRefine runtime (vLLM/API).
49
57
 
50
58
  ## Paths
51
59
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: deeprefine-cli
3
- Version: 0.1.4
3
+ Version: 0.1.5
4
4
  Summary: CLI and Cursor skill to refine graphify knowledge graphs with DeepRefine
5
5
  Author: HKUST-KnowComp
6
6
  License-Expression: MIT
@@ -29,8 +29,8 @@ Dynamic: license-file
29
29
  # DeepRefine-Skill
30
30
 
31
31
 
32
- [![PyPi](https://img.shields.io/badge/PyPi-v0.1.4-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.4/)
33
- [![Python](https://img.shields.io/badge/Python-3.10,3.11,3.12-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.4/)
32
+ [![PyPi](https://img.shields.io/badge/PyPi-v0.1.5-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.5/)
33
+ [![Python](https://img.shields.io/badge/Python-3.10,3.11,3.12-blue.svg)](https://pypi.org/project/deeprefine-cli/0.1.5/)
34
34
  [![Paper](https://img.shields.io/badge/Paper-DeepRefine-b31b1b.svg)](https://arxiv.org/pdf/2605.10488)
35
35
  [![Project](https://img.shields.io/badge/Project-DeepRefine-green.svg)](https://github.com/HKUST-KnowComp/DeepRefine)
36
36
 
@@ -38,7 +38,7 @@ Dynamic: license-file
38
38
 
39
39
  Type `/deeprefine` in your AI coding assistant after you've built a **[graphify](https://github.com/safishamsi/graphify)** knowledge base — it patches `graphify-out/graph.json` from your session's query history to evolve your LLM-Wiki.
40
40
 
41
- Works in **Cursor** (install the skill once with `deeprefine cursor install`). The same workflow is available from any terminal via the `deeprefine` CLI ([`deeprefine-cli` on PyPI](https://pypi.org/project/deeprefine-cli/)).
41
+ Works in **Cursor** (install the skill once with `deeprefine cursor install`). In Cursor, `/deeprefine` runs in **agent-native mode** (no extra API key needed). The runtime CLI (`deeprefine refine`) is still available for vLLM/API execution.
42
42
 
43
43
  ```
44
44
  /deeprefine
@@ -62,15 +62,14 @@ graphify-out/
62
62
  ```
63
63
 
64
64
  > **Standalone repo.** Model code (`autorefiner`, `atlas_rag`) lives in a separate [DeepRefine](https://github.com/HKUST-KnowComp/DeepRefine) checkout.
65
- > `pip install deeprefine-cli` ships the CLI and `SKILL.md`. `deeprefine refine` still needs DeepRefine + `atlastune`, with default inference from your current API model setup; you can override with custom base URL and API key.
65
+ > `pip install deeprefine-cli` ships the CLI and `SKILL.md`. In Cursor, `/deeprefine` uses agent-native refinement; `deeprefine refine` uses DeepRefine runtime (vLLM/API) when you explicitly choose CLI execution.
66
66
 
67
67
  ---
68
68
 
69
- ## Roadmap
69
+ ## News
70
70
 
71
- **Inference today:** default to your current API model setup.
72
-
73
- **Optional:** set custom OpenAI-compatible base URL and API key for LLM / embeddings.
71
+ - [2026/6/2] deeprefine-cli v0.1.5 has been released! Agent-native `/deeprefine` flow + clearer CLI/Agent split.
72
+ - [2026/6/2] deeprefine-cli v0.1.4 has been released! Customize your LLM api.
74
73
 
75
74
  ---
76
75
 
@@ -82,7 +81,7 @@ graphify-out/
82
81
  | 2 | `pip install deeprefine-cli` |
83
82
  | 3 | `deeprefine cursor install` in your KB project |
84
83
  | 4 | (Optional) start local vLLM, or use your API provider |
85
- | 5 | `deeprefine history add` `deeprefine refine` |
84
+ | 5 | Cursor chat: `/deeprefine` *(auto uses/adds query context)*; CLI mode: `history add` + `refine` |
86
85
 
87
86
  ```bash
88
87
  # 1) DeepRefine (once)
@@ -111,11 +110,21 @@ export DEEPREFINE_EMBED_MODEL=your_embed_model
111
110
  # export DEEPREFINE_API_KEY=your_shared_api_key
112
111
  # optional model overrides:
113
112
 
114
- # 5) Refine
113
+ # 5a) Refine in Cursor chat (agent-native, recommended)
114
+ # type in chat:
115
+ # /deeprefine
116
+
117
+ # 5b) Refine in terminal / CLI (manual flow)
115
118
  deeprefine history add --query "your question"
116
119
  deeprefine refine
117
120
  ```
118
121
 
122
+ In **Cursor chat** (agent):
123
+
124
+ ```text
125
+ /deeprefine
126
+ ```
127
+
119
128
  ---
120
129
 
121
130
  ## Pipeline
@@ -257,8 +266,8 @@ deeprefine cursor install
257
266
  |:-:|--------|
258
267
  | 1 | `graphify .` or `/graphify .` → `graphify-out/graph.json` |
259
268
  | 2 | `graphify query "..."` |
260
- | 3 | `deeprefine history add --query "..."` |
261
- | 4 | `deeprefine refine` or `/deeprefine` |
269
+ | 3 | Cursor chat: `/deeprefine` *(recommended; no manual `history add` needed)* |
270
+ | 4 | CLI alternative: `deeprefine history add --query "..."` `deeprefine refine` |
262
271
  | 5 | *(optional)* `graphify query "..."` to verify |
263
272
 
264
273
  ---
@@ -5,7 +5,7 @@ description: >-
5
5
  Reafiner based on session query history. Use when the user runs /deeprefine,
6
6
  asks to improve the graphify KB after Q&A, or wants to patch graph.json from
7
7
  failed retrieval queries.
8
- disable-model-invocation: true
8
+ disable-model-invocation: false
9
9
  ---
10
10
 
11
11
  # DeepRefine (graphify)
@@ -36,16 +36,24 @@ Inference defaults to your current API model setup (`OPENAI_API_KEY` or `DEEPREF
36
36
 
37
37
  Optional: local vLLM from DeepRefine (embedding `8128`, refine model `8134`; see `scripts/vllm_serve/`).
38
38
 
39
- ## `/deeprefine`
39
+ ## `/deeprefine` (agent-native)
40
40
 
41
41
  From the **KB project root** (with `graphify-out/graph.json`):
42
42
 
43
43
  ```bash
44
44
  deeprefine history add --query "..." # after graph Q&A
45
- deeprefine refine # all pending queries
45
+ /deeprefine # run inside agent (no extra API key)
46
46
  ```
47
47
 
48
- Do not hand-edit `graph.json` for refinement.
48
+ What the agent should do when `/deeprefine` is invoked:
49
+
50
+ 1. Load pending queries from `graphify-out/.deeprefine/history.jsonl`.
51
+ 2. Read `graphify-out/graph.json`.
52
+ 3. Propose and apply minimal graph updates directly to `graph.json` for unresolved queries.
53
+ 4. Write a timestamped log to `graphify-out/.deeprefine/refinement_results_*.jsonl`.
54
+ 5. Mark processed history items as `refined: true`.
55
+
56
+ Use `deeprefine refine` CLI only when explicitly asked to run DeepRefine runtime (vLLM/API).
49
57
 
50
58
  ## Paths
51
59
 
@@ -1,3 +1,3 @@
1
1
  """DeepRefine agent skill: refine graphify graph.json via Reafiner."""
2
2
 
3
- __version__ = "0.1.4"
3
+ __version__ = "0.1.5"
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "deeprefine-cli"
7
- version = "0.1.4"
7
+ version = "0.1.5"
8
8
  description = "CLI and Cursor skill to refine graphify knowledge graphs with DeepRefine"
9
9
  readme = "README.md"
10
10
  license = "MIT"
File without changes
File without changes