@onyx-robotics/agent 0.1.0
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 +202 -0
- package/README.md +72 -0
- package/bin/onyx.ts +4 -0
- package/package.json +52 -0
- package/scripts/install.sh +115 -0
- package/skills/onyx/SKILL.md +150 -0
- package/src/commands/agent.ts +23 -0
- package/src/commands/branch.ts +96 -0
- package/src/commands/exp.ts +432 -0
- package/src/commands/listen.ts +327 -0
- package/src/commands/login.ts +198 -0
- package/src/commands/profile.ts +112 -0
- package/src/commands/sync.ts +88 -0
- package/src/install.test.ts +38 -0
- package/src/lib/api.ts +227 -0
- package/src/lib/args.ts +68 -0
- package/src/lib/config.ts +148 -0
- package/src/lib/events.ts +97 -0
- package/src/lib/git.ts +57 -0
- package/src/lib/history.ts +272 -0
- package/src/lib/login.ts +233 -0
- package/src/lib/markdown.ts +148 -0
- package/src/lib/metrics.ts +41 -0
- package/src/lib/outbox.ts +173 -0
- package/src/lib/process.ts +73 -0
- package/src/lib/project.ts +42 -0
- package/src/lib/skill-content.ts +1 -0
- package/src/lib/skill.ts +50 -0
- package/src/lib/sync.ts +294 -0
- package/src/lib/tui.ts +364 -0
- package/src/main.ts +84 -0
- package/src/onyx.test.ts +952 -0
- package/src/onyx.ts +92 -0
- package/src/profile.test.ts +472 -0
- package/src/protocol/index.ts +2 -0
- package/src/protocol/local-research.ts +152 -0
- package/src/protocol/research.ts +75 -0
package/LICENSE
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
1
|
+
|
|
2
|
+
Apache License
|
|
3
|
+
Version 2.0, January 2004
|
|
4
|
+
http://www.apache.org/licenses/
|
|
5
|
+
|
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
7
|
+
|
|
8
|
+
1. Definitions.
|
|
9
|
+
|
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
12
|
+
|
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
14
|
+
the copyright owner that is granting the License.
|
|
15
|
+
|
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
17
|
+
other entities that control, are controlled by, or are under common
|
|
18
|
+
control with that entity. For the purposes of this definition,
|
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
20
|
+
direction or management of such entity, whether by contract or
|
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
23
|
+
|
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
25
|
+
exercising permissions granted by this License.
|
|
26
|
+
|
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
28
|
+
including but not limited to software source code, documentation
|
|
29
|
+
source, and configuration files.
|
|
30
|
+
|
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
|
32
|
+
transformation or translation of a Source form, including but
|
|
33
|
+
not limited to compiled object code, generated documentation,
|
|
34
|
+
and conversions to other media types.
|
|
35
|
+
|
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
37
|
+
Object form, made available under the License, as indicated by a
|
|
38
|
+
copyright notice that is included in or attached to the work
|
|
39
|
+
(an example is provided in the Appendix below).
|
|
40
|
+
|
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
47
|
+
the Work and Derivative Works thereof.
|
|
48
|
+
|
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
|
50
|
+
the original version of the Work and any modifications or additions
|
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
52
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
62
|
+
|
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
64
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
65
|
+
subsequently incorporated within the Work.
|
|
66
|
+
|
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
|
73
|
+
|
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
79
|
+
where such license applies only to those patent claims licensable
|
|
80
|
+
by such Contributor that are necessarily infringed by their
|
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
83
|
+
institute patent litigation against any entity (including a
|
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
86
|
+
or contributory patent infringement, then any patent licenses
|
|
87
|
+
granted to You under this License for that Work shall terminate
|
|
88
|
+
as of the date such litigation is filed.
|
|
89
|
+
|
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
92
|
+
modifications, and in Source or Object form, provided that You
|
|
93
|
+
meet the following conditions:
|
|
94
|
+
|
|
95
|
+
(a) You must give any other recipients of the Work or
|
|
96
|
+
Derivative Works a copy of this License; and
|
|
97
|
+
|
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
|
99
|
+
stating that You changed the files; and
|
|
100
|
+
|
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
|
103
|
+
attribution notices from the Source form of the Work,
|
|
104
|
+
excluding those notices that do not pertain to any part of
|
|
105
|
+
the Derivative Works; and
|
|
106
|
+
|
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
|
109
|
+
include a readable copy of the attribution notices contained
|
|
110
|
+
within such NOTICE file, excluding those notices that do not
|
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
|
112
|
+
of the following places: within a NOTICE text file distributed
|
|
113
|
+
as part of the Derivative Works; within the Source form or
|
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
|
115
|
+
within a display generated by the Derivative Works, if and
|
|
116
|
+
wherever such third-party notices normally appear. The contents
|
|
117
|
+
of the NOTICE file are for informational purposes only and
|
|
118
|
+
do not modify the License. You may add Your own attribution
|
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
121
|
+
that such additional attribution notices cannot be construed
|
|
122
|
+
as modifying the License.
|
|
123
|
+
|
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
|
125
|
+
may provide additional or different license terms and conditions
|
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
129
|
+
the conditions stated in this License.
|
|
130
|
+
|
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
134
|
+
this License, without any additional terms or conditions.
|
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
136
|
+
the terms of any separate license agreement you may have executed
|
|
137
|
+
with Licensor regarding such Contributions.
|
|
138
|
+
|
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
141
|
+
except as required for reasonable and customary use in describing the
|
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
143
|
+
|
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
|
153
|
+
|
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
|
159
|
+
incidental, or consequential damages of any character arising as a
|
|
160
|
+
result of this License or out of the use or inability to use the
|
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
163
|
+
other commercial damages or losses), even if such Contributor
|
|
164
|
+
has been advised of the possibility of such damages.
|
|
165
|
+
|
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
169
|
+
or other liability obligations and/or rights consistent with this
|
|
170
|
+
License. However, in accepting such obligations, You may act only
|
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
175
|
+
of your accepting any such warranty or additional liability.
|
|
176
|
+
|
|
177
|
+
END OF TERMS AND CONDITIONS
|
|
178
|
+
|
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
180
|
+
|
|
181
|
+
To apply the Apache License to your work, attach the following
|
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
183
|
+
replaced with your own identifying information. (Don't include
|
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
185
|
+
comment syntax for the file format. We also recommend that a
|
|
186
|
+
file or class name and description of purpose be included on the
|
|
187
|
+
same "printed page" as the copyright notice for easier
|
|
188
|
+
identification within third-party archives.
|
|
189
|
+
|
|
190
|
+
Copyright [yyyy] [name of copyright owner]
|
|
191
|
+
|
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
193
|
+
you may not use this file except in compliance with the License.
|
|
194
|
+
You may obtain a copy of the License at
|
|
195
|
+
|
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
197
|
+
|
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
201
|
+
See the License for the specific language governing permissions and
|
|
202
|
+
limitations under the License.
|
package/README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
1
|
+
# Onyx Agent
|
|
2
|
+
|
|
3
|
+
Open-source agent package for Onyx research workflows.
|
|
4
|
+
|
|
5
|
+
It installs the `onyx` command and the bundled `onyx` agent skill. The command
|
|
6
|
+
is terminal-only: agents make code changes in your existing git repository,
|
|
7
|
+
commit to `onyx/{name}` branches, run repo-local evals, and report experiment
|
|
8
|
+
metadata to the Onyx app.
|
|
9
|
+
|
|
10
|
+
## Install
|
|
11
|
+
|
|
12
|
+
```bash
|
|
13
|
+
curl -fsSL https://onyxresearch.ai/install | sh
|
|
14
|
+
```
|
|
15
|
+
|
|
16
|
+
Then make sure `~/.onyx/bin` is on your `PATH` and run:
|
|
17
|
+
|
|
18
|
+
```bash
|
|
19
|
+
onyx --version
|
|
20
|
+
onyx login
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
Only for local app development, point the agent at a non-production API:
|
|
24
|
+
|
|
25
|
+
```bash
|
|
26
|
+
onyx login --api-url http://localhost:3000
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
## Agent Skill
|
|
30
|
+
|
|
31
|
+
The installer installs the bundled skill automatically. To install it manually:
|
|
32
|
+
|
|
33
|
+
```bash
|
|
34
|
+
onyx agent install-skill
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
To locate the package skill source:
|
|
38
|
+
|
|
39
|
+
```bash
|
|
40
|
+
onyx agent skill-path
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
## Core Workflow
|
|
44
|
+
|
|
45
|
+
```bash
|
|
46
|
+
onyx branch create --name fast-eval --metric score --direction maximize
|
|
47
|
+
onyx exp run
|
|
48
|
+
onyx exp log --description "baseline"
|
|
49
|
+
onyx push
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
The CLI stores local retry state under `.git/onyx/` and flushes it to `/api/v1`
|
|
53
|
+
when connectivity and credentials are available.
|
|
54
|
+
|
|
55
|
+
## Development
|
|
56
|
+
|
|
57
|
+
```bash
|
|
58
|
+
bun install
|
|
59
|
+
bun run typecheck
|
|
60
|
+
bun run lint
|
|
61
|
+
bun test
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
Release binaries are built from Bun standalone executables:
|
|
65
|
+
|
|
66
|
+
```bash
|
|
67
|
+
bun run build:release
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
## License
|
|
71
|
+
|
|
72
|
+
Apache-2.0
|
package/bin/onyx.ts
ADDED
package/package.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "@onyx-robotics/agent",
|
|
3
|
+
"version": "0.1.0",
|
|
4
|
+
"description": "Onyx agent CLI and packaged agent skill for local research workflows.",
|
|
5
|
+
"type": "module",
|
|
6
|
+
"private": false,
|
|
7
|
+
"license": "Apache-2.0",
|
|
8
|
+
"repository": {
|
|
9
|
+
"type": "git",
|
|
10
|
+
"url": "git+https://github.com/onyx-robotics/onyx-agent.git"
|
|
11
|
+
},
|
|
12
|
+
"homepage": "https://onyxresearch.ai",
|
|
13
|
+
"bugs": {
|
|
14
|
+
"url": "https://github.com/onyx-robotics/onyx-agent/issues"
|
|
15
|
+
},
|
|
16
|
+
"bin": {
|
|
17
|
+
"onyx": "./bin/onyx.ts"
|
|
18
|
+
},
|
|
19
|
+
"pi": {
|
|
20
|
+
"skills": [
|
|
21
|
+
"./skills"
|
|
22
|
+
]
|
|
23
|
+
},
|
|
24
|
+
"files": [
|
|
25
|
+
"bin",
|
|
26
|
+
"src",
|
|
27
|
+
"skills",
|
|
28
|
+
"scripts/install.sh",
|
|
29
|
+
"package.json"
|
|
30
|
+
],
|
|
31
|
+
"scripts": {
|
|
32
|
+
"build:release": "bun scripts/build-release.ts",
|
|
33
|
+
"lint": "eslint .",
|
|
34
|
+
"test": "bun test",
|
|
35
|
+
"typecheck": "tsc --noEmit"
|
|
36
|
+
},
|
|
37
|
+
"dependencies": {
|
|
38
|
+
"zod": "^4.1.13"
|
|
39
|
+
},
|
|
40
|
+
"devDependencies": {
|
|
41
|
+
"@eslint/js": "^9.39.2",
|
|
42
|
+
"@types/bun": "^1.3.0",
|
|
43
|
+
"@types/node": "^25.1.0",
|
|
44
|
+
"eslint": "^9.39.2",
|
|
45
|
+
"typescript-eslint": "^8.46.4",
|
|
46
|
+
"typescript": "^5.9.3"
|
|
47
|
+
},
|
|
48
|
+
"exports": {
|
|
49
|
+
".": "./src/onyx.ts",
|
|
50
|
+
"./protocol": "./src/protocol/index.ts"
|
|
51
|
+
}
|
|
52
|
+
}
|
|
@@ -0,0 +1,115 @@
|
|
|
1
|
+
#!/bin/sh
|
|
2
|
+
set -eu
|
|
3
|
+
|
|
4
|
+
REPO="${ONYX_INSTALL_REPO:-onyx-robotics/onyx-agent}"
|
|
5
|
+
VERSION="${ONYX_VERSION:-latest}"
|
|
6
|
+
INSTALL_DIR="${ONYX_INSTALL_DIR:-$HOME/.onyx/bin}"
|
|
7
|
+
BASE_URL="${ONYX_INSTALL_BASE_URL:-https://github.com/$REPO/releases}"
|
|
8
|
+
|
|
9
|
+
detect_target() {
|
|
10
|
+
os="${ONYX_INSTALL_OS:-$(uname -s)}"
|
|
11
|
+
arch="${ONYX_INSTALL_ARCH:-$(uname -m)}"
|
|
12
|
+
|
|
13
|
+
case "$os" in
|
|
14
|
+
Darwin|darwin) os="darwin" ;;
|
|
15
|
+
Linux|linux) os="linux" ;;
|
|
16
|
+
*) echo "Unsupported OS: $os" >&2; exit 1 ;;
|
|
17
|
+
esac
|
|
18
|
+
|
|
19
|
+
case "$arch" in
|
|
20
|
+
arm64|aarch64) arch="arm64" ;;
|
|
21
|
+
x86_64|amd64) arch="x64" ;;
|
|
22
|
+
*) echo "Unsupported architecture: $arch" >&2; exit 1 ;;
|
|
23
|
+
esac
|
|
24
|
+
|
|
25
|
+
if [ "$os" = "linux" ] && [ "$arch" = "x64" ]; then
|
|
26
|
+
echo "linux-x64-baseline"
|
|
27
|
+
return
|
|
28
|
+
fi
|
|
29
|
+
|
|
30
|
+
echo "$os-$arch"
|
|
31
|
+
}
|
|
32
|
+
|
|
33
|
+
target="$(detect_target)"
|
|
34
|
+
asset="onyx-$target"
|
|
35
|
+
|
|
36
|
+
if [ "$VERSION" = "latest" ]; then
|
|
37
|
+
download_base="$BASE_URL/latest/download"
|
|
38
|
+
else
|
|
39
|
+
download_base="$BASE_URL/download/$VERSION"
|
|
40
|
+
fi
|
|
41
|
+
|
|
42
|
+
asset_url="$download_base/$asset"
|
|
43
|
+
checksums_url="$download_base/checksums.txt"
|
|
44
|
+
|
|
45
|
+
if [ "${ONYX_INSTALL_DRY_RUN:-}" = "1" ]; then
|
|
46
|
+
echo "target=$target"
|
|
47
|
+
echo "asset=$asset"
|
|
48
|
+
echo "asset_url=$asset_url"
|
|
49
|
+
echo "checksums_url=$checksums_url"
|
|
50
|
+
echo "install_dir=$INSTALL_DIR"
|
|
51
|
+
exit 0
|
|
52
|
+
fi
|
|
53
|
+
|
|
54
|
+
need() {
|
|
55
|
+
if ! command -v "$1" >/dev/null 2>&1; then
|
|
56
|
+
echo "Missing required command: $1" >&2
|
|
57
|
+
exit 1
|
|
58
|
+
fi
|
|
59
|
+
}
|
|
60
|
+
|
|
61
|
+
need curl
|
|
62
|
+
need grep
|
|
63
|
+
need awk
|
|
64
|
+
|
|
65
|
+
if command -v sha256sum >/dev/null 2>&1; then
|
|
66
|
+
sha_cmd="sha256sum"
|
|
67
|
+
elif command -v shasum >/dev/null 2>&1; then
|
|
68
|
+
sha_cmd="shasum -a 256"
|
|
69
|
+
else
|
|
70
|
+
echo "Missing required command: sha256sum or shasum" >&2
|
|
71
|
+
exit 1
|
|
72
|
+
fi
|
|
73
|
+
|
|
74
|
+
tmp="${TMPDIR:-/tmp}/onyx-install.$$"
|
|
75
|
+
cleanup() {
|
|
76
|
+
rm -rf "$tmp"
|
|
77
|
+
}
|
|
78
|
+
trap cleanup EXIT INT TERM
|
|
79
|
+
mkdir -p "$tmp"
|
|
80
|
+
|
|
81
|
+
echo "Downloading Onyx agent $VERSION for $target..."
|
|
82
|
+
curl -fsSL "$asset_url" -o "$tmp/$asset"
|
|
83
|
+
curl -fsSL "$checksums_url" -o "$tmp/checksums.txt"
|
|
84
|
+
|
|
85
|
+
expected="$(grep " $asset\$" "$tmp/checksums.txt" | awk '{print $1}')"
|
|
86
|
+
if [ -z "$expected" ]; then
|
|
87
|
+
echo "No checksum found for $asset" >&2
|
|
88
|
+
exit 1
|
|
89
|
+
fi
|
|
90
|
+
|
|
91
|
+
actual="$($sha_cmd "$tmp/$asset" | awk '{print $1}')"
|
|
92
|
+
if [ "$actual" != "$expected" ]; then
|
|
93
|
+
echo "Checksum mismatch for $asset" >&2
|
|
94
|
+
exit 1
|
|
95
|
+
fi
|
|
96
|
+
|
|
97
|
+
mkdir -p "$INSTALL_DIR"
|
|
98
|
+
install_path="$INSTALL_DIR/onyx"
|
|
99
|
+
cp "$tmp/$asset" "$install_path"
|
|
100
|
+
chmod 0755 "$install_path"
|
|
101
|
+
|
|
102
|
+
if [ "${ONYX_SKIP_SKILL:-}" != "1" ]; then
|
|
103
|
+
"$install_path" agent install-skill --quiet || true
|
|
104
|
+
fi
|
|
105
|
+
|
|
106
|
+
echo "Installed onyx to $install_path"
|
|
107
|
+
|
|
108
|
+
case ":$PATH:" in
|
|
109
|
+
*":$INSTALL_DIR:"*) ;;
|
|
110
|
+
*)
|
|
111
|
+
echo ""
|
|
112
|
+
echo "Add Onyx to your PATH:"
|
|
113
|
+
echo " export PATH=\"$INSTALL_DIR:\$PATH\""
|
|
114
|
+
;;
|
|
115
|
+
esac
|
|
@@ -0,0 +1,150 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: onyx
|
|
3
|
+
description: Drive the Onyx auto research workflow end-to-end. Use when asked to start, resume, or continue Onyx experiments, run auto research, optimize a metric, work on an Onyx branch, /onyx anything, or keep the Onyx platform updated from local research. Handles setup, the autonomous experiment loop, and recording every attempt — successful or failed — to the Onyx platform (queued in a local outbox when offline).
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Onyx Research
|
|
7
|
+
|
|
8
|
+
Drive an autonomous research loop using the `onyx` CLI as the substrate. You own reasoning, edits, commits, durable notes, and the experiment records the Onyx platform tracks.
|
|
9
|
+
|
|
10
|
+
## Setup
|
|
11
|
+
|
|
12
|
+
1. Ask (or infer):
|
|
13
|
+
- **Goal**
|
|
14
|
+
- **Evaluation**
|
|
15
|
+
- **Metric**, **unit**, **direction** (`maximize` / `minimize`)
|
|
16
|
+
- **Files in scope**
|
|
17
|
+
- **Constraints**
|
|
18
|
+
- **Stop conditions** - eg. `stop after N iterations`, `for 30 minutes`, `until <condition>`, default is no stop condition, loop forever until manually stopped by user
|
|
19
|
+
2. `onyx branch create --name <slug> --metric <name> --unit <unit> --direction <maximize/minimize> --description <goal>`
|
|
20
|
+
- Add `--project-path <projectPath>` when the Onyx project is scoped to a subdirectory.
|
|
21
|
+
3. Read the source files. Understand the workload deeply before writing anything.
|
|
22
|
+
4. Write `<projectPath>/onyx/onyx.md` and `<projectPath>/onyx/eval.sh` (see below). Optionally write `<projectPath>/onyx/checks.sh` when correctness constraints require it. Commit these files.
|
|
23
|
+
5. Run a baseline with `onyx exp run`, then record it with `onyx exp log --description "baseline" --agent-notes '<json>'`, then start looping immediately.
|
|
24
|
+
|
|
25
|
+
### `onyx.md`
|
|
26
|
+
|
|
27
|
+
This is the heart of the session. A fresh agent with no context should be able to read this file and run the loop effectively. Invest time making it excellent.
|
|
28
|
+
|
|
29
|
+
```markdown
|
|
30
|
+
# Onyx Research: <goal>
|
|
31
|
+
|
|
32
|
+
## Objective
|
|
33
|
+
|
|
34
|
+
<Specific description of what we're optimizing and the workload.>
|
|
35
|
+
|
|
36
|
+
## Metrics
|
|
37
|
+
|
|
38
|
+
- **Primary**: <name>, <unit>, <direction> - the optimization target
|
|
39
|
+
- **Secondary**: - independent tradeoff monitors
|
|
40
|
+
- <name>, <unit>, <direction>
|
|
41
|
+
- <name>, <unit>, <direction>
|
|
42
|
+
- ...
|
|
43
|
+
|
|
44
|
+
## How to Run
|
|
45
|
+
|
|
46
|
+
`./onyx/eval.sh` - outputs `METRIC name=number` lines.
|
|
47
|
+
|
|
48
|
+
## Files in Scope
|
|
49
|
+
|
|
50
|
+
<Every file the agent may modify, with a brief note on what it does.>
|
|
51
|
+
|
|
52
|
+
## Off Limits
|
|
53
|
+
|
|
54
|
+
<What must NOT be touched.>
|
|
55
|
+
|
|
56
|
+
## Constraints
|
|
57
|
+
|
|
58
|
+
<Hard rules: tests must pass, no new deps, etc.>
|
|
59
|
+
|
|
60
|
+
## What's Been Tried
|
|
61
|
+
|
|
62
|
+
<High-level strategy notes only: key wins, dead-end THEMES, and architectural
|
|
63
|
+
insights. Do not list individual experiments here - the full per-experiment
|
|
64
|
+
record lives in `onyx exp list` (searchable offline).>
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
Update `onyx.md` periodically - especially the "What's Been Tried" section - so resuming agents have strategic context. For the detailed record of individual attempts, rely on `onyx exp list` instead of duplicating it in `onyx.md`:
|
|
68
|
+
|
|
69
|
+
- `onyx exp list --limit 20` - recent experiments (newest first) with status and metric.
|
|
70
|
+
- `onyx exp list --grep <regex>` - search names, descriptions, agent notes, and output summaries; e.g. `onyx exp list --grep 'cache|memoiz'` before trying a caching idea.
|
|
71
|
+
- `onyx exp list --status failed --json` - full records (agent notes included) for post-mortems.
|
|
72
|
+
|
|
73
|
+
The history cache is hydrated from the Onyx app on `onyx sync`, so after a fresh clone run `onyx sync` once to pull the cross-branch history.
|
|
74
|
+
|
|
75
|
+
### `eval.sh`
|
|
76
|
+
|
|
77
|
+
Bash script (`set -euo pipefail`) that: pre-checks fast (syntax errors in <1s), runs the benchmark, and outputs structured lines to stdout. Keep the script fast - every second is multiplied by hundreds of experiment runs.
|
|
78
|
+
|
|
79
|
+
#### Structured output
|
|
80
|
+
|
|
81
|
+
- `METRIC name=value` - primary metric (must match `onyx branch create`'s `metric name`) and any secondary metrics. Parsed automatically by `onyx exp run`.
|
|
82
|
+
|
|
83
|
+
#### Design the script to inform optimization
|
|
84
|
+
|
|
85
|
+
The script should output **whatever data helps you make better decisions in the next iteration.** Think about what you'll need to see after each experiment run to know where to focus:
|
|
86
|
+
|
|
87
|
+
- Phase timings when the workload has distinct stages
|
|
88
|
+
- Error counts, failure categories, or test names when checks can fail in different ways
|
|
89
|
+
- Memory usage, cache hit rates, or other runtime diagnostics when relevant
|
|
90
|
+
- Anything domain-specific that would help localize regressions or identify bottlenecks
|
|
91
|
+
|
|
92
|
+
The script runs the same code every iteration - but you can **update it during the loop** if you discover you need more signal. Add instrumentation as you learn what matters.
|
|
93
|
+
|
|
94
|
+
#### Agent experiment side notes via `onyx exp log`
|
|
95
|
+
|
|
96
|
+
Use `onyx exp log`'s `--agent-notes` flag to annotate each experiment run with **whatever would help the next iteration make a better decision.** Free-form key/value pairs - you decide what's worth recording. Don't repeat the description or raw output; capture what you'd lose after a context reset.
|
|
97
|
+
|
|
98
|
+
Annotate failures and crashes heavily. If you don't capture what you tried and why it failed, future iterations will waste time re-discovering the same dead ends.
|
|
99
|
+
|
|
100
|
+
### `checks.sh` (optional)
|
|
101
|
+
|
|
102
|
+
Bash script (`set -euo pipefail`) for backpressure/correctness checks: tests, types, lint, etc. **Only create this file when the user's constraints require correctness validation** (e.g., "tests must pass", "types must check").
|
|
103
|
+
|
|
104
|
+
When this file exists:
|
|
105
|
+
|
|
106
|
+
- Runs automatically after every **passing** benchmark in `onyx exp run`.
|
|
107
|
+
- If checks fail, `onyx exp run` reports it clearly - log as `checks_failed`.
|
|
108
|
+
- Its execution time does **NOT** affect the primary metric.
|
|
109
|
+
- A `checks_failed` result is recorded, but never becomes best.
|
|
110
|
+
- Has a separate timeout (default 300s, configurable via `onyx exp run --checks-timeout <seconds>`).
|
|
111
|
+
|
|
112
|
+
When this file does **not** exist, everything behaves exactly as before - no changes to the loop.
|
|
113
|
+
|
|
114
|
+
**Keep output minimal.** Only the last 80 lines of checks output are fed back to the agent on failure. Suppress verbose progress/success output and let only errors through. This keeps context lean and helps the agent pinpoint what broke.
|
|
115
|
+
|
|
116
|
+
```bash
|
|
117
|
+
#!/bin/bash
|
|
118
|
+
set -euo pipefail
|
|
119
|
+
# Example: run tests and typecheck - suppress success output, only show errors
|
|
120
|
+
pnpm test --run --reporter=dot 2>&1 | tail -50
|
|
121
|
+
pnpm typecheck 2>&1 | grep -i error || true
|
|
122
|
+
```
|
|
123
|
+
|
|
124
|
+
## Loop Rules
|
|
125
|
+
|
|
126
|
+
**LOOP FOREVER.** Never ask "should I continue?" - the user expects autonomous work.
|
|
127
|
+
|
|
128
|
+
- **Primary metric is king.** Improved -> build the next experiment from that result. Worse/equal -> leave it recorded and build from the prior best instead. Secondary metrics rarely affect this.
|
|
129
|
+
- **Annotate every run with `--agent-notes`.** Record what you learned - not what you did. What would help the next iteration or a fresh agent resuming this session? Notes are searchable later via `onyx exp list --grep`.
|
|
130
|
+
- **Simpler is better.** Removing code for equal perf = good. Ugly complexity for tiny gain = probably not worth building on.
|
|
131
|
+
- **Don't thrash.** Repeatedly returning to the same idea? Try something structurally different.
|
|
132
|
+
- **Crashes:** fix if trivial, otherwise log and move on. Don't over-invest.
|
|
133
|
+
- **Think longer when stuck.** Re-read source files, study the profiling data, reason about what the CPU is actually doing. The best ideas come from deep understanding, not from trying random variations.
|
|
134
|
+
- **Resuming:** if `onyx.md` exists, read it + git log + `onyx status` + `onyx exp list --limit 20`, continue looping.
|
|
135
|
+
|
|
136
|
+
**NEVER STOP.** The user may be away for hours. Keep going until interrupted.
|
|
137
|
+
|
|
138
|
+
## Git Rules
|
|
139
|
+
|
|
140
|
+
Onyx is append-only: commit every attempt forward on `onyx/{name}`. Do not use `git reset --hard`, auto-revert, or force-push. Experiment metadata is canonical in the Onyx app/API; `.git/onyx/outbox.jsonl` is only an offline retry queue.
|
|
141
|
+
|
|
142
|
+
## Ideas Backlog
|
|
143
|
+
|
|
144
|
+
When you discover complex but promising optimizations that you won't pursue right now, **append them as bullets to `onyx.ideas.md`**. Don't let good ideas get lost.
|
|
145
|
+
|
|
146
|
+
On resume (context limit, crash), check `onyx.ideas.md` - prune stale/tried entries, experiment with the rest. When all paths are exhausted, delete the file and write a final summary.
|
|
147
|
+
|
|
148
|
+
## User Messages During Experiments
|
|
149
|
+
|
|
150
|
+
If the user sends a message while an experiment is running, finish the current `onyx exp run` + `onyx exp log` cycle first, then incorporate their feedback in the next iteration. Don't abandon a running experiment.
|
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
import { optionalFlag, type Args } from "../lib/args"
|
|
2
|
+
import { displaySkillPath, installOnyxSkill } from "../lib/skill"
|
|
3
|
+
|
|
4
|
+
export async function commandAgent(args: Args) {
|
|
5
|
+
const sub = args.positional[1]
|
|
6
|
+
|
|
7
|
+
if (sub === "skill-path") {
|
|
8
|
+
console.log(await displaySkillPath())
|
|
9
|
+
return
|
|
10
|
+
}
|
|
11
|
+
|
|
12
|
+
if (sub === "install-skill") {
|
|
13
|
+
await installOnyxSkill({
|
|
14
|
+
dir: args.options.dir,
|
|
15
|
+
quiet: optionalFlag(args, "quiet"),
|
|
16
|
+
})
|
|
17
|
+
return
|
|
18
|
+
}
|
|
19
|
+
|
|
20
|
+
throw new Error(
|
|
21
|
+
"Usage: onyx agent skill-path | onyx agent install-skill [--dir <path>] [--quiet]"
|
|
22
|
+
)
|
|
23
|
+
}
|