@wb200/mgrep 0.1.10
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/LICENSE +201 -0
- package/README.md +288 -0
- package/dist/commands/login.js +28 -0
- package/dist/commands/login.js.map +1 -0
- package/dist/commands/search.js +191 -0
- package/dist/commands/search.js.map +1 -0
- package/dist/commands/watch.js +134 -0
- package/dist/commands/watch.js.map +1 -0
- package/dist/commands/watch_mcp.js +77 -0
- package/dist/commands/watch_mcp.js.map +1 -0
- package/dist/index.js +36 -0
- package/dist/index.js.map +1 -0
- package/dist/install/claude-code.js +71 -0
- package/dist/install/claude-code.js.map +1 -0
- package/dist/install/codex.js +116 -0
- package/dist/install/codex.js.map +1 -0
- package/dist/install/droid.js +191 -0
- package/dist/install/droid.js.map +1 -0
- package/dist/install/opencode.js +161 -0
- package/dist/install/opencode.js.map +1 -0
- package/dist/lib/config.js +216 -0
- package/dist/lib/config.js.map +1 -0
- package/dist/lib/context.js +35 -0
- package/dist/lib/context.js.map +1 -0
- package/dist/lib/file.js +154 -0
- package/dist/lib/file.js.map +1 -0
- package/dist/lib/git.js +167 -0
- package/dist/lib/git.js.map +1 -0
- package/dist/lib/logger.js +80 -0
- package/dist/lib/logger.js.map +1 -0
- package/dist/lib/model-studio.js +205 -0
- package/dist/lib/model-studio.js.map +1 -0
- package/dist/lib/store.js +639 -0
- package/dist/lib/store.js.map +1 -0
- package/dist/lib/sync-helpers.js +51 -0
- package/dist/lib/sync-helpers.js.map +1 -0
- package/dist/lib/utils.js +300 -0
- package/dist/lib/utils.js.map +1 -0
- package/dist/lib/warning.js +34 -0
- package/dist/lib/warning.js.map +1 -0
- package/dist/plugins/mgrep/.claude-plugin/plugin.json +9 -0
- package/dist/plugins/mgrep/hooks/hook.json +27 -0
- package/dist/plugins/mgrep/hooks/mgrep_watch.py +55 -0
- package/dist/plugins/mgrep/hooks/mgrep_watch_kill.py +50 -0
- package/dist/plugins/mgrep/skills/mgrep/SKILL.md +59 -0
- package/package.json +74 -0
package/LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright [2025] [Mixedbread AI]
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
package/README.md
ADDED
|
@@ -0,0 +1,288 @@
|
|
|
1
|
+
<div align="center">
|
|
2
|
+
<h1>mgrep</h1>
|
|
3
|
+
<p><em>Semantic code search powered by local LanceDB embeddings — feels as immediate as <code>grep</code>.</em></p>
|
|
4
|
+
<a href="https://www.npmjs.com/package/@wb200/mgrep"><img src="https://badge.fury.io/js/%40wb200%2Fmgrep.svg" alt="npm version" /></a>
|
|
5
|
+
<a href="https://opensource.org/licenses/Apache-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="License: Apache 2.0" /></a>
|
|
6
|
+
</div>
|
|
7
|
+
|
|
8
|
+
## Why mgrep?
|
|
9
|
+
|
|
10
|
+
- Natural-language search that feels as immediate as `grep`.
|
|
11
|
+
- Semantic search over your local codebase — no cloud upload of source code required.
|
|
12
|
+
- Smooth background indexing via `mgrep watch`, designed to detect and keep up-to-date everything that matters inside any git repository.
|
|
13
|
+
- First-class coding agent integrations (Claude Code, Codex, OpenCode, Factory Droid).
|
|
14
|
+
- Built for agents and humans alike: quiet output, thoughtful defaults, and escape hatches everywhere.
|
|
15
|
+
|
|
16
|
+
```bash
|
|
17
|
+
# index once
|
|
18
|
+
mgrep watch
|
|
19
|
+
|
|
20
|
+
# then ask your repo things in natural language
|
|
21
|
+
mgrep "where do we set up auth?"
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
## Quick Start
|
|
25
|
+
|
|
26
|
+
1. **Install**
|
|
27
|
+
```bash
|
|
28
|
+
npm install -g @wb200/mgrep # or pnpm / bun
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
2. **Set API keys**
|
|
32
|
+
```bash
|
|
33
|
+
export DEEPINFRA_API_KEY=your_deepinfra_key # for embeddings & rerank
|
|
34
|
+
export DASHSCOPE_API_KEY=your_dashscope_key # for synthesized answers
|
|
35
|
+
```
|
|
36
|
+
- **DeepInfra**: Sign up at [deepinfra.com](https://deepinfra.com) — used for Qwen3 embeddings and reranking.
|
|
37
|
+
- **Alibaba Cloud DashScope (Singapore)**: Sign up at [dashscope.aliyuncs.com](https://dashscope-intl.aliyuncs.com) — used for the Responses API (answers and agentic planning). Only required if you use `--answer` or `--agentic`.
|
|
38
|
+
|
|
39
|
+
3. **Validate your configuration**
|
|
40
|
+
```bash
|
|
41
|
+
mgrep validate
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
4. **Index a project**
|
|
45
|
+
```bash
|
|
46
|
+
cd path/to/repo
|
|
47
|
+
mgrep watch
|
|
48
|
+
```
|
|
49
|
+
`watch` performs an initial sync, respects `.gitignore`, then keeps the local LanceDB store updated as files change.
|
|
50
|
+
|
|
51
|
+
5. **Search anything**
|
|
52
|
+
```bash
|
|
53
|
+
mgrep "where do we set up auth?" src/lib
|
|
54
|
+
mgrep -m 25 "store schema"
|
|
55
|
+
```
|
|
56
|
+
Searches default to the current working directory unless you pass a path.
|
|
57
|
+
|
|
58
|
+
## Using it with Coding Agents
|
|
59
|
+
|
|
60
|
+
> [!NOTE]
|
|
61
|
+
> **Default Limits**: mgrep enforces default limits to ensure optimal performance:
|
|
62
|
+
> - **Maximum file size**: 4MB per file
|
|
63
|
+
> - **Maximum file count**: 10,000 files per directory
|
|
64
|
+
>
|
|
65
|
+
> These limits can be customized via CLI flags (`--max-file-size`, `--max-file-count`),
|
|
66
|
+
> environment variables, or config files. See the [Configuration](#configuration) section for details.
|
|
67
|
+
|
|
68
|
+
`mgrep` supports assisted installation commands for many agents:
|
|
69
|
+
- `mgrep install-claude-code` for Claude Code
|
|
70
|
+
- `mgrep install-opencode` for OpenCode
|
|
71
|
+
- `mgrep install-codex` for Codex
|
|
72
|
+
- `mgrep install-droid` for Factory Droid
|
|
73
|
+
|
|
74
|
+
## When to use what
|
|
75
|
+
|
|
76
|
+
`mgrep` complements `grep`, not replaces it. The best code search combines both.
|
|
77
|
+
|
|
78
|
+
| Use `grep` (or `ripgrep`) for... | Use `mgrep` for... |
|
|
79
|
+
| --- | --- |
|
|
80
|
+
| **Exact Matches** | **Intent Search** |
|
|
81
|
+
| Symbol tracing, Refactoring, Regex | Code exploration, Feature discovery, Onboarding |
|
|
82
|
+
|
|
83
|
+
## mgrep as Subagent
|
|
84
|
+
|
|
85
|
+
For complex questions that require information from multiple sources, `mgrep` can act as a subagent that automatically refines queries and performs multiple searches.
|
|
86
|
+
|
|
87
|
+
```bash
|
|
88
|
+
# Enable agentic search for complex multi-part questions
|
|
89
|
+
mgrep --agentic "What are the yearly numbers for 2020, 2021, 2022, 2023, 2024?"
|
|
90
|
+
|
|
91
|
+
# Combine with --answer for a synthesized response from multiple sources
|
|
92
|
+
mgrep --agentic -a "How does authentication work and where is it configured?"
|
|
93
|
+
```
|
|
94
|
+
|
|
95
|
+
When `--agentic` is enabled, mgrep will:
|
|
96
|
+
- Automatically break down complex queries into sub-queries
|
|
97
|
+
- Perform multiple searches to gather comprehensive results
|
|
98
|
+
- Combine findings from different parts of your codebase
|
|
99
|
+
|
|
100
|
+
## Commands at a Glance
|
|
101
|
+
|
|
102
|
+
| Command | Purpose |
|
|
103
|
+
| --- | --- |
|
|
104
|
+
| `mgrep` / `mgrep search <pattern> [path]` | Natural-language search with many `grep`-style flags (`-i`, `-r`, `-m`...). |
|
|
105
|
+
| `mgrep watch` | Index current repo and keep the local store in sync via file watchers. |
|
|
106
|
+
| `mgrep validate` | Validate DeepInfra and Alibaba Cloud API key configuration. |
|
|
107
|
+
| `mgrep install-claude-code` | Add the mgrep MCP plugin to Claude Code. |
|
|
108
|
+
| `mgrep install-opencode` | Add mgrep to OpenCode. |
|
|
109
|
+
| `mgrep install-codex` | Add mgrep to Codex. |
|
|
110
|
+
| `mgrep install-droid` | Add mgrep hooks/skills to Factory Droid. |
|
|
111
|
+
|
|
112
|
+
### mgrep search
|
|
113
|
+
|
|
114
|
+
`mgrep search` is the default command. It searches the current directory for a pattern.
|
|
115
|
+
|
|
116
|
+
| Option | Description |
|
|
117
|
+
| --- | --- |
|
|
118
|
+
| `-m <max_count>` | The maximum number of results to return |
|
|
119
|
+
| `-c`, `--content` | Show content of the results |
|
|
120
|
+
| `-a`, `--answer` | Generate an answer to the question based on the results |
|
|
121
|
+
| `--agentic` | Enable agentic search to automatically refine queries and perform multiple searches |
|
|
122
|
+
| `-s`, `--sync` | Sync the local files to the store before searching |
|
|
123
|
+
| `-d`, `--dry-run` | Dry run the search process (no actual file syncing) |
|
|
124
|
+
| `--no-rerank` | Disable reranking of search results |
|
|
125
|
+
| `--max-file-size <bytes>` | Maximum file size in bytes to upload (overrides config) |
|
|
126
|
+
| `--max-file-count <count>` | Maximum number of files to upload (overrides config) |
|
|
127
|
+
|
|
128
|
+
All search options can also be configured via environment variables (see [Environment Variables](#environment-variables) section below).
|
|
129
|
+
|
|
130
|
+
**Examples:**
|
|
131
|
+
```bash
|
|
132
|
+
mgrep "What code parsers are available?" # search in the current directory
|
|
133
|
+
mgrep "How are chunks defined?" src/models # search in the src/models directory
|
|
134
|
+
mgrep -m 10 "maximum concurrent workers" # limit results to 10
|
|
135
|
+
mgrep -a "What code parsers are available?" # generate an answer based on results
|
|
136
|
+
mgrep --agentic -a "How does the sync pipeline work?" # agentic multi-query answer
|
|
137
|
+
```
|
|
138
|
+
|
|
139
|
+
### mgrep watch
|
|
140
|
+
|
|
141
|
+
`mgrep watch` indexes the current repository and keeps the local LanceDB store in sync via file watchers.
|
|
142
|
+
|
|
143
|
+
It respects the current `.gitignore`, as well as a `.mgrepignore` file in the root of the repository. The `.mgrepignore` file follows the same syntax as the [`.gitignore`](https://git-scm.com/docs/gitignore) file.
|
|
144
|
+
|
|
145
|
+
| Option | Description |
|
|
146
|
+
| --- | --- |
|
|
147
|
+
| `-d`, `--dry-run` | Dry run the watch process (no actual file syncing) |
|
|
148
|
+
| `--max-file-size <bytes>` | Maximum file size in bytes to upload (overrides config) |
|
|
149
|
+
| `--max-file-count <count>` | Maximum number of files to upload (overrides config) |
|
|
150
|
+
|
|
151
|
+
**Examples:**
|
|
152
|
+
```bash
|
|
153
|
+
mgrep watch # index the current repository and watch for changes
|
|
154
|
+
mgrep watch --max-file-size 1048576 # limit uploads to files under 1MB
|
|
155
|
+
mgrep watch --max-file-count 5000 # limit sync to 5000 changed files or fewer
|
|
156
|
+
```
|
|
157
|
+
|
|
158
|
+
## Architecture
|
|
159
|
+
|
|
160
|
+
- Files are chunked and embedded locally using Qwen3-Embedding via DeepInfra, then stored in a LanceDB vector database under `~/.mgrep/lancedb/`.
|
|
161
|
+
- Searches combine vector similarity (ANN) and full-text search (BM25), fused with Reciprocal Rank Fusion.
|
|
162
|
+
- Reranking uses Qwen3-Reranker via DeepInfra and is enabled by default (disable with `--no-rerank`).
|
|
163
|
+
- Synthesized answers and agentic query planning use Alibaba Cloud DashScope (Qwen3.5-plus) via the Responses API.
|
|
164
|
+
- All embeddings and indexes are stored locally — only API calls to DeepInfra/DashScope leave your machine.
|
|
165
|
+
|
|
166
|
+
## Configuration
|
|
167
|
+
|
|
168
|
+
mgrep can be configured via config files, environment variables, or CLI flags.
|
|
169
|
+
|
|
170
|
+
### Config File
|
|
171
|
+
|
|
172
|
+
Create a `.mgreprc.yaml` (or `.mgreprc.yml`) in your project root for local configuration, or `~/.config/mgrep/config.yaml` (or `config.yml`) for global configuration.
|
|
173
|
+
|
|
174
|
+
```yaml
|
|
175
|
+
# Maximum file size in bytes to upload (default: 4MB)
|
|
176
|
+
maxFileSize: 5242880
|
|
177
|
+
|
|
178
|
+
# Maximum number of files to sync (upload/delete) per operation (default: 10000)
|
|
179
|
+
maxFileCount: 5000
|
|
180
|
+
|
|
181
|
+
# Concurrency for sync operations (default: 20)
|
|
182
|
+
syncConcurrency: 10
|
|
183
|
+
|
|
184
|
+
# Override the embedding model (default: Qwen/Qwen3-Embedding-4B)
|
|
185
|
+
embedModel: Qwen/Qwen3-Embedding-4B
|
|
186
|
+
|
|
187
|
+
# Embedding dimensions (default: 2560)
|
|
188
|
+
embedDimensions: 2560
|
|
189
|
+
|
|
190
|
+
# Override the rerank model (default: Qwen/Qwen3-Reranker-4B)
|
|
191
|
+
rerankModel: Qwen/Qwen3-Reranker-4B
|
|
192
|
+
|
|
193
|
+
# Override the LLM model for answers (default: qwen3.5-plus)
|
|
194
|
+
llmModel: qwen3.5-plus
|
|
195
|
+
|
|
196
|
+
# Custom LanceDB storage path (default: ~/.mgrep/lancedb)
|
|
197
|
+
lancedbPath: /path/to/lancedb
|
|
198
|
+
```
|
|
199
|
+
|
|
200
|
+
**Configuration precedence** (highest to lowest):
|
|
201
|
+
1. CLI flags (`--max-file-size`, `--max-file-count`)
|
|
202
|
+
2. Environment variables (`MGREP_MAX_FILE_SIZE`, `MGREP_MAX_FILE_COUNT`, …)
|
|
203
|
+
3. Local config file (`.mgreprc.yaml` in project directory)
|
|
204
|
+
4. Global config file (`~/.config/mgrep/config.yaml`)
|
|
205
|
+
5. Default values
|
|
206
|
+
|
|
207
|
+
## Environment Variables
|
|
208
|
+
|
|
209
|
+
### API Keys
|
|
210
|
+
|
|
211
|
+
- `DEEPINFRA_API_KEY`: DeepInfra API key for embeddings and reranking (required)
|
|
212
|
+
- `DASHSCOPE_API_KEY`: Alibaba Cloud DashScope API key for responses (required for `--answer` / `--agentic`)
|
|
213
|
+
|
|
214
|
+
### Store
|
|
215
|
+
|
|
216
|
+
- `MGREP_STORE`: Override the default store name (default: `mgrep`)
|
|
217
|
+
- `MGREP_LANCEDB_PATH`: Override the LanceDB storage path
|
|
218
|
+
|
|
219
|
+
### Search Options
|
|
220
|
+
|
|
221
|
+
- `MGREP_MAX_COUNT`: Maximum number of results to return (default: `10`)
|
|
222
|
+
- `MGREP_CONTENT`: Show content of the results (set to `1` or `true` to enable)
|
|
223
|
+
- `MGREP_ANSWER`: Generate an answer based on the results (set to `1` or `true` to enable)
|
|
224
|
+
- `MGREP_AGENTIC`: Enable agentic search (set to `1` or `true` to enable)
|
|
225
|
+
- `MGREP_SYNC`: Sync files before searching (set to `1` or `true` to enable)
|
|
226
|
+
- `MGREP_DRY_RUN`: Enable dry run mode (set to `1` or `true` to enable)
|
|
227
|
+
- `MGREP_RERANK`: Enable reranking (set to `0` or `false` to disable, default: enabled)
|
|
228
|
+
|
|
229
|
+
### Sync Options
|
|
230
|
+
|
|
231
|
+
- `MGREP_MAX_FILE_SIZE`: Maximum file size in bytes to upload (default: `4194304` / 4MB)
|
|
232
|
+
- `MGREP_MAX_FILE_COUNT`: Maximum number of files to sync per operation (default: `10000`)
|
|
233
|
+
- `MGREP_SYNC_CONCURRENCY`: Concurrency for sync operations (default: `20`)
|
|
234
|
+
|
|
235
|
+
### Model Options
|
|
236
|
+
|
|
237
|
+
- `MGREP_EMBED_MODEL`: Embedding model to use (default: `Qwen/Qwen3-Embedding-4B`)
|
|
238
|
+
- `MGREP_EMBED_DIMENSIONS`: Embedding dimensions (default: `2560`)
|
|
239
|
+
- `MGREP_RERANK_MODEL`: Rerank model to use (default: `Qwen/Qwen3-Reranker-4B`)
|
|
240
|
+
- `MGREP_LLM_MODEL`: LLM model for answers (default: `qwen3.5-plus`)
|
|
241
|
+
|
|
242
|
+
**Examples:**
|
|
243
|
+
```bash
|
|
244
|
+
# Set default max results to 25
|
|
245
|
+
export MGREP_MAX_COUNT=25
|
|
246
|
+
mgrep "search query"
|
|
247
|
+
|
|
248
|
+
# Always show content in results
|
|
249
|
+
export MGREP_CONTENT=1
|
|
250
|
+
mgrep "search query"
|
|
251
|
+
|
|
252
|
+
# Disable reranking globally
|
|
253
|
+
export MGREP_RERANK=0
|
|
254
|
+
mgrep "search query"
|
|
255
|
+
```
|
|
256
|
+
|
|
257
|
+
Note: Command-line options always override environment variables.
|
|
258
|
+
|
|
259
|
+
## Development
|
|
260
|
+
|
|
261
|
+
```bash
|
|
262
|
+
pnpm install
|
|
263
|
+
pnpm build # TypeScript compile
|
|
264
|
+
pnpm test # bats integration tests
|
|
265
|
+
pnpm format # biome formatting + linting
|
|
266
|
+
pnpm typecheck # type-check without emitting
|
|
267
|
+
```
|
|
268
|
+
|
|
269
|
+
The executable lives at `dist/index.js` (built from TypeScript via `tsc`).
|
|
270
|
+
|
|
271
|
+
### Testing
|
|
272
|
+
|
|
273
|
+
```bash
|
|
274
|
+
pnpm test
|
|
275
|
+
```
|
|
276
|
+
|
|
277
|
+
Tests are written using [bats](https://bats-core.readthedocs.io/en/stable/) and use a `TestStore` in-memory backend so no real API keys are required.
|
|
278
|
+
|
|
279
|
+
## Troubleshooting
|
|
280
|
+
|
|
281
|
+
- **API key errors**: Run `mgrep validate` to check your `DEEPINFRA_API_KEY` and `DASHSCOPE_API_KEY` are correctly set and working.
|
|
282
|
+
- **Watcher feels slow**: Lower `syncConcurrency` in your config if you're hitting API rate limits, or raise it for faster initial sync on large repos.
|
|
283
|
+
- **Store schema mismatch**: If you change `embedModel` or `embedDimensions`, delete the store directory (`~/.mgrep/lancedb/<store-name>/`) and re-index with `mgrep watch`.
|
|
284
|
+
- **Unknown option errors**: Unrecognized flags now produce an error — check `mgrep --help` for supported options.
|
|
285
|
+
|
|
286
|
+
## License
|
|
287
|
+
|
|
288
|
+
Apache-2.0. See the [LICENSE](https://opensource.org/licenses/Apache-2.0) file for details.
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
import { intro, outro } from "@clack/prompts";
|
|
2
|
+
import chalk from "chalk";
|
|
3
|
+
import { Command } from "commander";
|
|
4
|
+
import { loadConfig } from "../lib/config.js";
|
|
5
|
+
import { createModelStudioConfig, ModelStudioClient, } from "../lib/model-studio.js";
|
|
6
|
+
export async function loginAction() {
|
|
7
|
+
intro(chalk.bold("🔐 Provider Configuration Check"));
|
|
8
|
+
try {
|
|
9
|
+
const config = loadConfig(process.cwd());
|
|
10
|
+
const client = new ModelStudioClient(createModelStudioConfig({
|
|
11
|
+
embedModel: config.embedModel,
|
|
12
|
+
embedDimensions: config.embedDimensions,
|
|
13
|
+
rerankModel: config.rerankModel,
|
|
14
|
+
llmModel: config.llmModel,
|
|
15
|
+
}));
|
|
16
|
+
await client.validate();
|
|
17
|
+
outro(chalk.green(`Configuration looks valid. Embeddings=${config.embedModel} (${config.embedDimensions} dims), rerank=${config.rerankModel}, responses=${config.llmModel}.`));
|
|
18
|
+
}
|
|
19
|
+
catch (error) {
|
|
20
|
+
const message = error instanceof Error ? error.message : String(error);
|
|
21
|
+
console.error(message);
|
|
22
|
+
process.exit(1);
|
|
23
|
+
}
|
|
24
|
+
}
|
|
25
|
+
export const validate = new Command("validate")
|
|
26
|
+
.description("Validate the DeepInfra and Alibaba Cloud provider configuration")
|
|
27
|
+
.action(loginAction);
|
|
28
|
+
//# sourceMappingURL=login.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"login.js","sourceRoot":"","sources":["../../src/commands/login.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,KAAK,EAAE,KAAK,EAAE,MAAM,gBAAgB,CAAC;AAC9C,OAAO,KAAK,MAAM,OAAO,CAAC;AAC1B,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,EACL,uBAAuB,EACvB,iBAAiB,GAClB,MAAM,wBAAwB,CAAC;AAEhC,MAAM,CAAC,KAAK,UAAU,WAAW;IAC/B,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,iCAAiC,CAAC,CAAC,CAAC;IAErD,IAAI,CAAC;QACH,MAAM,MAAM,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC,CAAC;QACzC,MAAM,MAAM,GAAG,IAAI,iBAAiB,CAClC,uBAAuB,CAAC;YACtB,UAAU,EAAE,MAAM,CAAC,UAAU;YAC7B,eAAe,EAAE,MAAM,CAAC,eAAe;YACvC,WAAW,EAAE,MAAM,CAAC,WAAW;YAC/B,QAAQ,EAAE,MAAM,CAAC,QAAQ;SAC1B,CAAC,CACH,CAAC;QAEF,MAAM,MAAM,CAAC,QAAQ,EAAE,CAAC;QAExB,KAAK,CACH,KAAK,CAAC,KAAK,CACT,yCAAyC,MAAM,CAAC,UAAU,KAAK,MAAM,CAAC,eAAe,kBAAkB,MAAM,CAAC,WAAW,eAAe,MAAM,CAAC,QAAQ,GAAG,CAC3J,CACF,CAAC;IACJ,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,MAAM,OAAO,GAAG,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;QACvE,OAAO,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;QACvB,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IAClB,CAAC;AACH,CAAC;AAED,MAAM,CAAC,MAAM,QAAQ,GAAG,IAAI,OAAO,CAAC,UAAU,CAAC;KAC5C,WAAW,CACV,iEAAiE,CAClE;KACA,MAAM,CAAC,WAAW,CAAC,CAAC"}
|