sference-cli 0.0.7__tar.gz → 0.0.9__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.
@@ -0,0 +1,203 @@
1
+ Copyright 2026 sference contributors
2
+
3
+ Apache License
4
+ Version 2.0, January 2004
5
+ http://www.apache.org/licenses/
6
+
7
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
8
+
9
+ 1. Definitions.
10
+
11
+ "License" shall mean the terms and conditions for use, reproduction,
12
+ and distribution as defined by Sections 1 through 9 of this document.
13
+
14
+ "Licensor" shall mean the copyright owner or entity authorized by
15
+ the copyright owner that is granting the License.
16
+
17
+ "Legal Entity" shall mean the union of the acting entity and all
18
+ other entities that control, are controlled by, or are under common
19
+ control with that entity. For the purposes of this definition,
20
+ "control" means (i) the power, direct or indirect, to cause the
21
+ direction or management of such entity, whether by contract or
22
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
23
+ outstanding shares, or (iii) beneficial ownership of such entity.
24
+
25
+ "You" (or "Your") shall mean an individual or Legal Entity
26
+ exercising permissions granted by this License.
27
+
28
+ "Source" form shall mean the preferred form for making modifications,
29
+ including but not limited to software source code, documentation
30
+ source, and configuration files.
31
+
32
+ "Object" form shall mean any form resulting from mechanical
33
+ transformation or translation of a Source form, including but
34
+ not limited to compiled object code, generated documentation,
35
+ and conversions to other media types.
36
+
37
+ "Work" shall mean the work of authorship, whether in Source or
38
+ Object form, made available under the License, as indicated by a
39
+ copyright notice that is included in or attached to the work
40
+ (an example is provided in the Appendix below).
41
+
42
+ "Derivative Works" shall mean any work, whether in Source or Object
43
+ form, that is based on (or derived from) the Work and for which the
44
+ editorial revisions, annotations, elaborations, or other modifications
45
+ represent, as a whole, an original work of authorship. For the purposes
46
+ of this License, Derivative Works shall not include works that remain
47
+ separable from, or merely link (or bind by name) to the interfaces of,
48
+ the Work and Derivative Works thereof.
49
+
50
+ "Contribution" shall mean any work of authorship, including
51
+ the original version of the Work and any modifications or additions
52
+ to that Work or Derivative Works thereof, that is intentionally
53
+ submitted to Licensor for inclusion in the Work by the copyright owner
54
+ or by an individual or Legal Entity authorized to submit on behalf of
55
+ the copyright owner. For the purposes of this definition, "submitted"
56
+ means any form of electronic, verbal, or written communication sent
57
+ to the Licensor or its representatives, including but not limited to
58
+ communication on electronic mailing lists, source code control systems,
59
+ and issue tracking systems that are managed by, or on behalf of, the
60
+ Licensor for the purpose of discussing and improving the Work, but
61
+ excluding communication that is conspicuously marked or otherwise
62
+ designated in writing by the copyright owner as "Not a Contribution."
63
+
64
+ "Contributor" shall mean Licensor and any individual or Legal Entity
65
+ on behalf of whom a Contribution has been received by Licensor and
66
+ subsequently incorporated within the Work.
67
+
68
+ 2. Grant of Copyright License. Subject to the terms and conditions of
69
+ this License, each Contributor hereby grants to You a perpetual,
70
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
71
+ copyright license to reproduce, prepare Derivative Works of,
72
+ publicly display, publicly perform, sublicense, and distribute the
73
+ Work and such Derivative Works in Source or Object form.
74
+
75
+ 3. Grant of Patent License. Subject to the terms and conditions of
76
+ this License, each Contributor hereby grants to You a perpetual,
77
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
78
+ (except as stated in this section) patent license to make, have made,
79
+ use, offer to sell, sell, import, and otherwise transfer the Work,
80
+ where such license applies only to those patent claims licensable
81
+ by such Contributor that are necessarily infringed by their
82
+ Contribution(s) alone or by combination of their Contribution(s)
83
+ with the Work to which such Contribution(s) was submitted. If You
84
+ institute patent litigation against any entity (including a
85
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
86
+ or a Contribution incorporated within the Work constitutes direct
87
+ or contributory patent infringement, then any patent licenses
88
+ granted to You under this License for that Work shall terminate
89
+ as of the date such litigation is filed.
90
+
91
+ 4. Redistribution. You may reproduce and distribute copies of the
92
+ Work or Derivative Works thereof in any medium, with or without
93
+ modifications, and in Source or Object form, provided that You
94
+ meet the following conditions:
95
+
96
+ (a) You must give any other recipients of the Work or
97
+ Derivative Works a copy of this License; and
98
+
99
+ (b) You must cause any modified files to carry prominent notices
100
+ stating that You changed the files; and
101
+
102
+ (c) You must retain, in the Source form of any Derivative Works
103
+ that You distribute, all copyright, patent, trademark, and
104
+ attribution notices from the Source form of the Work,
105
+ excluding those notices that do not pertain to any part of
106
+ the Derivative Works; and
107
+
108
+ (d) If the Work includes a "NOTICE" text file as part of its
109
+ distribution, then any Derivative Works that You distribute must
110
+ include a readable copy of the attribution notices contained
111
+ within such NOTICE file, excluding those notices that do not
112
+ pertain to any part of the Derivative Works, in at least one
113
+ of the following places: within a NOTICE text file distributed
114
+ as part of the Derivative Works; within the Source form or
115
+ documentation, if provided along with the Derivative Works; or,
116
+ within a display generated by the Derivative Works, if and
117
+ wherever such third-party notices normally appear. The contents
118
+ of the NOTICE file are for informational purposes only and
119
+ do not modify the License. You may add Your own attribution
120
+ notices within Derivative Works that You distribute, alongside
121
+ or as an addendum to the NOTICE text from the Work, provided
122
+ that such additional attribution notices cannot be construed
123
+ as modifying the License.
124
+
125
+ You may add Your own copyright statement to Your modifications and
126
+ may provide additional or different license terms and conditions
127
+ for use, reproduction, or distribution of Your modifications, or
128
+ for any such Derivative Works as a whole, provided Your use,
129
+ reproduction, and distribution of the Work otherwise complies with
130
+ the conditions stated in this License.
131
+
132
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
133
+ any Contribution intentionally submitted for inclusion in the Work
134
+ by You to the Licensor shall be under the terms and conditions of
135
+ this License, without any additional terms or conditions.
136
+ Notwithstanding the above, nothing herein shall supersede or modify
137
+ the terms of any separate license agreement you may have executed
138
+ with Licensor regarding such Contributions.
139
+
140
+ 6. Trademarks. This License does not grant permission to use the trade
141
+ names, trademarks, service marks, or product names of the Licensor,
142
+ except as required for reasonable and customary use in describing the
143
+ origin of the Work and reproducing the content of the NOTICE file.
144
+
145
+ 7. Disclaimer of Warranty. Unless required by applicable law or
146
+ agreed to in writing, Licensor provides the Work (and each
147
+ Contributor provides its Contributions) on an "AS IS" BASIS,
148
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
149
+ implied, including, without limitation, any warranties or conditions
150
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
151
+ PARTICULAR PURPOSE. You are solely responsible for determining the
152
+ appropriateness of using or redistributing the Work and assume any
153
+ risks associated with Your exercise of permissions under this License.
154
+
155
+ 8. Limitation of Liability. In no event and under no legal theory,
156
+ whether in tort (including negligence), contract, or otherwise,
157
+ unless required by applicable law (such as deliberate and grossly
158
+ negligent acts) or agreed to in writing, shall any Contributor be
159
+ liable to You for damages, including any direct, indirect, special,
160
+ incidental, or consequential damages of any character arising as a
161
+ result of this License or out of the use or inability to use the
162
+ Work (including but not limited to damages for loss of goodwill,
163
+ work stoppage, computer failure or malfunction, or any and all
164
+ other commercial damages or losses), even if such Contributor
165
+ has been advised of the possibility of such damages.
166
+
167
+ 9. Accepting Warranty or Additional Liability. While redistributing
168
+ the Work or Derivative Works thereof, You may choose to offer,
169
+ and charge a fee for, acceptance of support, warranty, indemnity,
170
+ or other liability obligations and/or rights consistent with this
171
+ License. However, in accepting such obligations, You may act only
172
+ on Your own behalf and on Your sole responsibility, not on behalf
173
+ of any other Contributor, and only if You agree to indemnify,
174
+ defend, and hold each Contributor harmless for any liability
175
+ incurred by, or claims asserted against, such Contributor by reason
176
+ of your accepting any such warranty or additional liability.
177
+
178
+ END OF TERMS AND CONDITIONS
179
+
180
+ APPENDIX: How to apply the Apache License to your work.
181
+
182
+ To apply the Apache License to your work, attach the following
183
+ boilerplate notice, with the fields enclosed by brackets "[]"
184
+ replaced with your own identifying information. (Don't include
185
+ the brackets!) The text should be enclosed in the appropriate
186
+ comment syntax for the file format. We also recommend that a
187
+ file or class name and description of purpose be included on the
188
+ same "printed page" as the copyright notice for easier
189
+ identification within third-party archives.
190
+
191
+ Copyright [yyyy] [name of copyright owner]
192
+
193
+ Licensed under the Apache License, Version 2.0 (the "License");
194
+ you may not use this file except in compliance with the License.
195
+ You may obtain a copy of the License at
196
+
197
+ http://www.apache.org/licenses/LICENSE-2.0
198
+
199
+ Unless required by applicable law or agreed to in writing, software
200
+ distributed under the License is distributed on an "AS IS" BASIS,
201
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
202
+ See the License for the specific language governing permissions and
203
+ limitations under the License.
@@ -1,3 +1,30 @@
1
+ Metadata-Version: 2.4
2
+ Name: sference-cli
3
+ Version: 0.0.9
4
+ Summary: sference command-line interface
5
+ Project-URL: Homepage, https://sference.com
6
+ Project-URL: Repository, https://github.com/s-ference/sference
7
+ Project-URL: Issues, https://github.com/s-ference/sference/issues
8
+ Author: sference
9
+ License-Expression: Apache-2.0
10
+ License-File: LICENSE
11
+ Keywords: batch,cli,inference,llm,openai,sference
12
+ Classifier: Development Status :: 4 - Beta
13
+ Classifier: Environment :: Console
14
+ Classifier: Intended Audience :: Developers
15
+ Classifier: Operating System :: OS Independent
16
+ Classifier: Programming Language :: Python :: 3
17
+ Classifier: Programming Language :: Python :: 3 :: Only
18
+ Classifier: Programming Language :: Python :: 3.10
19
+ Classifier: Programming Language :: Python :: 3.11
20
+ Classifier: Programming Language :: Python :: 3.12
21
+ Classifier: Programming Language :: Python :: 3.13
22
+ Classifier: Topic :: Utilities
23
+ Requires-Python: >=3.10
24
+ Requires-Dist: sference-sdk>=0.0.9
25
+ Requires-Dist: typer>=0.24.1
26
+ Description-Content-Type: text/markdown
27
+
1
28
  # sference CLI
2
29
 
3
30
  Command-line interface for the sference batch API (`sference`). It uses the Python SDK (`sference-sdk`) and is published on PyPI as `sference-cli`.
@@ -5,13 +32,24 @@ Command-line interface for the sference batch API (`sference`). It uses the Pyth
5
32
  ## Installation
6
33
 
7
34
  ```bash
8
- pip install sference-cli
9
- # or isolated install on PATH:
10
35
  uv tool install sference-cli
36
+ ```
37
+
38
+ Fallback:
39
+
40
+ ```bash
41
+ pip install sference-cli
11
42
  # or:
12
43
  pipx install sference-cli
13
44
  ```
14
45
 
46
+ From a clone of this repo:
47
+
48
+ ```bash
49
+ uv sync --package sference-cli
50
+ uv run sference --help
51
+ ```
52
+
15
53
  Then:
16
54
 
17
55
  ```bash
@@ -35,18 +73,18 @@ sference auth me --json
35
73
 
36
74
  ## Quick examples (batches and streams)
37
75
 
38
- Use a `model` string supported by your sference deployment (for self-hosted stacks, match the model your workers consume).
76
+ Use a `model` string supported by your sference deployment.
39
77
 
40
78
  **Batches**
41
79
 
42
80
  ```bash
43
- sference batch submit --input-file ./workload.jsonl --model Qwen/Qwen2.5-7B-Instruct --window 24h
81
+ sference batch submit --input-file ./workload.jsonl --model Qwen/Qwen3.6-35B-A3B --window 24h
44
82
  sference batch status --batch-id <batch_id>
45
83
  sference batch wait --batch-id <batch_id>
46
84
  sference batch results --batch-id <batch_id>
47
85
  sference batch download-results --batch-id <batch_id> --out ./out.jsonl
48
86
  # Submit, wait, print JSONL results on stdout (stderr: progress; resumable cache)
49
- sference batch stream --input-file ./workload.jsonl --model Qwen/Qwen2.5-7B-Instruct --window 24h
87
+ sference batch stream --input-file ./workload.jsonl --model Qwen/Qwen3.6-35B-A3B --window 24h
50
88
  ```
51
89
 
52
90
  **Streams**
@@ -54,38 +92,16 @@ sference batch stream --input-file ./workload.jsonl --model Qwen/Qwen2.5-7B-Inst
54
92
  ```bash
55
93
  sference stream create --name "my-stream" --window 24h
56
94
  sference stream list
57
- sference stream submit --stream-id <stream_id> --input-file ./lines.jsonl --model Qwen/Qwen2.5-7B-Instruct
95
+ sference stream submit --stream-id <stream_id> --input-file ./lines.jsonl --model Qwen/Qwen3.6-35B-A3B
58
96
  sference stream status --stream-id <stream_id>
59
97
  sference responses tail --stream-id <stream_id>
60
98
  ```
61
99
 
62
- ### cURL: OpenAI-compatible `/v1/responses`
63
-
64
- The CLI uses this API for `stream submit` (via `POST /v1/responses`). You can call it directly with the same API key as `sference auth login` (or `SFERENCE_API_KEY`). For self-hosted APIs, set `SFERENCE_BASE_URL` to your API origin.
65
-
66
- ```bash
67
- export TOKEN=sk_... # or: export TOKEN="$SFERENCE_API_KEY"
68
-
69
- RID=$(curl -sS -X POST "${SFERENCE_BASE_URL:-https://api.sference.com}/v1/responses" \
70
- -H "X-API-Key: $TOKEN" \
71
- -H 'Content-Type: application/json' \
72
- -d '{
73
- "model": "Qwen/Qwen2.5-7B-Instruct",
74
- "input": [{"role": "user", "content": "Hello"}],
75
- "metadata": {"completion_window": "24h"}
76
- }' | jq -r '.id')
77
-
78
- curl -sS "${SFERENCE_BASE_URL:-https://api.sference.com}/v1/responses/${RID}" \
79
- -H "X-API-Key: $TOKEN"
80
- ```
81
-
82
100
  ## Environment variables
83
101
 
84
102
  | Variable | Purpose |
85
103
  |----------|---------|
86
104
  | `SFERENCE_API_KEY` | API key (or JWT); overrides `~/.sference/credentials.json` |
87
- | `SFERENCE_BASE_URL` | API base URL (default `https://api.sference.com`) |
88
- | `SFERENCE_CONSOLE_URL` | Console URL for `auth login` browser step (default `https://console.sference.com`) |
89
105
  | `SFERENCE_STREAM_CACHE` | Optional path to the stream resumable-cache file (default `~/.sference/stream_cache.json`) |
90
106
  | `SFERENCE_STREAM_CHECKPOINTS` | Optional path for **`responses tail`** event checkpoints (default `~/.sference/stream_checkpoints.json`) |
91
107
 
@@ -95,7 +111,7 @@ curl -sS "${SFERENCE_BASE_URL:-https://api.sference.com}/v1/responses/${RID}" \
95
111
 
96
112
  | Command | Description |
97
113
  |---------|-------------|
98
- | `sference auth login` | Store an API key (optional `--api-key`, `--console-url`, `--no-browser`) |
114
+ | `sference auth login` | Store an API key (optional `--api-key`, `--no-browser`) |
99
115
  | `sference auth me` | Show current user (`--json` for machine-readable output) |
100
116
 
101
117
  ### Batch
@@ -111,8 +127,6 @@ curl -sS "${SFERENCE_BASE_URL:-https://api.sference.com}/v1/responses/${RID}" \
111
127
  | `sference batch cancel` | Cancel a batch (`--batch-id`, `--json`) |
112
128
  | `sference batch download-results` | Download results JSONL to a file (`--batch-id`, `--out`, `--format jsonl`) |
113
129
 
114
- Global options on most batch commands: `--base-url` (default `https://api.sference.com`).
115
-
116
130
  ### Responses (`/v1/responses`)
117
131
 
118
132
  | Command | Description |
@@ -137,7 +151,7 @@ Long-lived **streams** are separate from **batches**: you create a stream, submi
137
151
  Example JSONL lines for `stream submit` (both accepted):
138
152
 
139
153
  ```json
140
- {"custom_id":"req-1","method":"POST","url":"/v1/chat/completions","body":{"model":"Qwen/Qwen3.5-4B","messages":[{"role":"user","content":"hi"}]}}
154
+ {"custom_id":"req-1","method":"POST","url":"/v1/chat/completions","body":{"model":"Qwen/Qwen3.6-35B-A3B","messages":[{"role":"user","content":"hi"}]}}
141
155
  ```
142
156
 
143
157
  ```json
@@ -164,7 +178,7 @@ sference batch stream --input-file workload.jsonl > results.jsonl
164
178
  Content-only JSONL (model supplied globally):
165
179
 
166
180
  ```bash
167
- sference batch stream --input-file prompts.jsonl --model Qwen/Qwen2.5-7B-Instruct > results.jsonl
181
+ sference batch stream --input-file prompts.jsonl --model Qwen/Qwen3.6-35B-A3B > results.jsonl
168
182
  ```
169
183
 
170
184
  ### Resumable cache
@@ -173,7 +187,7 @@ Batches can take a long time. If you **interrupt** the command (e.g. Ctrl+C) and
173
187
 
174
188
  - Cache file: **`~/.sference/stream_cache.json`** (override with **`SFERENCE_STREAM_CACHE`**).
175
189
  - Key: **SHA-256** of the raw input file bytes (same bytes ⇒ same key, regardless of path).
176
- - Stored fields: `batch_id`, `base_url` (must match current `--base-url`), `created_at`.
190
+ - Stored fields: `batch_id`, `created_at`.
177
191
  - After results are written to stdout, the entry for that input is **removed** so the cache does not grow forever.
178
192
  - If the cached batch no longer exists on the server (404), the cache entry is dropped and a **new** batch is submitted.
179
193
 
@@ -220,4 +234,4 @@ For your own code, see **[`../sdk-python/README.md`](../sdk-python/README.md)**
220
234
  - **`/v1/responses` (sync):** `create_response`, `get_response` (standalone or `metadata.stream_id` for streams)
221
235
  - **Async:** **`AsyncSferenceClient`** — same surface as sync with `await`, plus `iter_responses_events` / `list_responses_events` for completion tailing (`GET /v1/responses/events`)
222
236
 
223
- That README also documents when to prefer **batches** vs **streams** and includes cURL examples.
237
+ That README also documents **`./workload.jsonl`** input and when to prefer **batches** vs **streams**.
@@ -1,12 +1,3 @@
1
- Metadata-Version: 2.4
2
- Name: sference-cli
3
- Version: 0.0.7
4
- Summary: sference command-line interface
5
- Requires-Python: >=3.12
6
- Requires-Dist: sference-sdk>=0.0.7
7
- Requires-Dist: typer>=0.24.1
8
- Description-Content-Type: text/markdown
9
-
10
1
  # sference CLI
11
2
 
12
3
  Command-line interface for the sference batch API (`sference`). It uses the Python SDK (`sference-sdk`) and is published on PyPI as `sference-cli`.
@@ -14,13 +5,24 @@ Command-line interface for the sference batch API (`sference`). It uses the Pyth
14
5
  ## Installation
15
6
 
16
7
  ```bash
17
- pip install sference-cli
18
- # or isolated install on PATH:
19
8
  uv tool install sference-cli
9
+ ```
10
+
11
+ Fallback:
12
+
13
+ ```bash
14
+ pip install sference-cli
20
15
  # or:
21
16
  pipx install sference-cli
22
17
  ```
23
18
 
19
+ From a clone of this repo:
20
+
21
+ ```bash
22
+ uv sync --package sference-cli
23
+ uv run sference --help
24
+ ```
25
+
24
26
  Then:
25
27
 
26
28
  ```bash
@@ -44,18 +46,18 @@ sference auth me --json
44
46
 
45
47
  ## Quick examples (batches and streams)
46
48
 
47
- Use a `model` string supported by your sference deployment (for self-hosted stacks, match the model your workers consume).
49
+ Use a `model` string supported by your sference deployment.
48
50
 
49
51
  **Batches**
50
52
 
51
53
  ```bash
52
- sference batch submit --input-file ./workload.jsonl --model Qwen/Qwen2.5-7B-Instruct --window 24h
54
+ sference batch submit --input-file ./workload.jsonl --model Qwen/Qwen3.6-35B-A3B --window 24h
53
55
  sference batch status --batch-id <batch_id>
54
56
  sference batch wait --batch-id <batch_id>
55
57
  sference batch results --batch-id <batch_id>
56
58
  sference batch download-results --batch-id <batch_id> --out ./out.jsonl
57
59
  # Submit, wait, print JSONL results on stdout (stderr: progress; resumable cache)
58
- sference batch stream --input-file ./workload.jsonl --model Qwen/Qwen2.5-7B-Instruct --window 24h
60
+ sference batch stream --input-file ./workload.jsonl --model Qwen/Qwen3.6-35B-A3B --window 24h
59
61
  ```
60
62
 
61
63
  **Streams**
@@ -63,38 +65,16 @@ sference batch stream --input-file ./workload.jsonl --model Qwen/Qwen2.5-7B-Inst
63
65
  ```bash
64
66
  sference stream create --name "my-stream" --window 24h
65
67
  sference stream list
66
- sference stream submit --stream-id <stream_id> --input-file ./lines.jsonl --model Qwen/Qwen2.5-7B-Instruct
68
+ sference stream submit --stream-id <stream_id> --input-file ./lines.jsonl --model Qwen/Qwen3.6-35B-A3B
67
69
  sference stream status --stream-id <stream_id>
68
70
  sference responses tail --stream-id <stream_id>
69
71
  ```
70
72
 
71
- ### cURL: OpenAI-compatible `/v1/responses`
72
-
73
- The CLI uses this API for `stream submit` (via `POST /v1/responses`). You can call it directly with the same API key as `sference auth login` (or `SFERENCE_API_KEY`). For self-hosted APIs, set `SFERENCE_BASE_URL` to your API origin.
74
-
75
- ```bash
76
- export TOKEN=sk_... # or: export TOKEN="$SFERENCE_API_KEY"
77
-
78
- RID=$(curl -sS -X POST "${SFERENCE_BASE_URL:-https://api.sference.com}/v1/responses" \
79
- -H "X-API-Key: $TOKEN" \
80
- -H 'Content-Type: application/json' \
81
- -d '{
82
- "model": "Qwen/Qwen2.5-7B-Instruct",
83
- "input": [{"role": "user", "content": "Hello"}],
84
- "metadata": {"completion_window": "24h"}
85
- }' | jq -r '.id')
86
-
87
- curl -sS "${SFERENCE_BASE_URL:-https://api.sference.com}/v1/responses/${RID}" \
88
- -H "X-API-Key: $TOKEN"
89
- ```
90
-
91
73
  ## Environment variables
92
74
 
93
75
  | Variable | Purpose |
94
76
  |----------|---------|
95
77
  | `SFERENCE_API_KEY` | API key (or JWT); overrides `~/.sference/credentials.json` |
96
- | `SFERENCE_BASE_URL` | API base URL (default `https://api.sference.com`) |
97
- | `SFERENCE_CONSOLE_URL` | Console URL for `auth login` browser step (default `https://console.sference.com`) |
98
78
  | `SFERENCE_STREAM_CACHE` | Optional path to the stream resumable-cache file (default `~/.sference/stream_cache.json`) |
99
79
  | `SFERENCE_STREAM_CHECKPOINTS` | Optional path for **`responses tail`** event checkpoints (default `~/.sference/stream_checkpoints.json`) |
100
80
 
@@ -104,7 +84,7 @@ curl -sS "${SFERENCE_BASE_URL:-https://api.sference.com}/v1/responses/${RID}" \
104
84
 
105
85
  | Command | Description |
106
86
  |---------|-------------|
107
- | `sference auth login` | Store an API key (optional `--api-key`, `--console-url`, `--no-browser`) |
87
+ | `sference auth login` | Store an API key (optional `--api-key`, `--no-browser`) |
108
88
  | `sference auth me` | Show current user (`--json` for machine-readable output) |
109
89
 
110
90
  ### Batch
@@ -120,8 +100,6 @@ curl -sS "${SFERENCE_BASE_URL:-https://api.sference.com}/v1/responses/${RID}" \
120
100
  | `sference batch cancel` | Cancel a batch (`--batch-id`, `--json`) |
121
101
  | `sference batch download-results` | Download results JSONL to a file (`--batch-id`, `--out`, `--format jsonl`) |
122
102
 
123
- Global options on most batch commands: `--base-url` (default `https://api.sference.com`).
124
-
125
103
  ### Responses (`/v1/responses`)
126
104
 
127
105
  | Command | Description |
@@ -146,7 +124,7 @@ Long-lived **streams** are separate from **batches**: you create a stream, submi
146
124
  Example JSONL lines for `stream submit` (both accepted):
147
125
 
148
126
  ```json
149
- {"custom_id":"req-1","method":"POST","url":"/v1/chat/completions","body":{"model":"Qwen/Qwen3.5-4B","messages":[{"role":"user","content":"hi"}]}}
127
+ {"custom_id":"req-1","method":"POST","url":"/v1/chat/completions","body":{"model":"Qwen/Qwen3.6-35B-A3B","messages":[{"role":"user","content":"hi"}]}}
150
128
  ```
151
129
 
152
130
  ```json
@@ -173,7 +151,7 @@ sference batch stream --input-file workload.jsonl > results.jsonl
173
151
  Content-only JSONL (model supplied globally):
174
152
 
175
153
  ```bash
176
- sference batch stream --input-file prompts.jsonl --model Qwen/Qwen2.5-7B-Instruct > results.jsonl
154
+ sference batch stream --input-file prompts.jsonl --model Qwen/Qwen3.6-35B-A3B > results.jsonl
177
155
  ```
178
156
 
179
157
  ### Resumable cache
@@ -182,7 +160,7 @@ Batches can take a long time. If you **interrupt** the command (e.g. Ctrl+C) and
182
160
 
183
161
  - Cache file: **`~/.sference/stream_cache.json`** (override with **`SFERENCE_STREAM_CACHE`**).
184
162
  - Key: **SHA-256** of the raw input file bytes (same bytes ⇒ same key, regardless of path).
185
- - Stored fields: `batch_id`, `base_url` (must match current `--base-url`), `created_at`.
163
+ - Stored fields: `batch_id`, `created_at`.
186
164
  - After results are written to stdout, the entry for that input is **removed** so the cache does not grow forever.
187
165
  - If the cached batch no longer exists on the server (404), the cache entry is dropped and a **new** batch is submitted.
188
166
 
@@ -229,4 +207,4 @@ For your own code, see **[`../sdk-python/README.md`](../sdk-python/README.md)**
229
207
  - **`/v1/responses` (sync):** `create_response`, `get_response` (standalone or `metadata.stream_id` for streams)
230
208
  - **Async:** **`AsyncSferenceClient`** — same surface as sync with `await`, plus `iter_responses_events` / `list_responses_events` for completion tailing (`GET /v1/responses/events`)
231
209
 
232
- That README also documents when to prefer **batches** vs **streams** and includes cURL examples.
210
+ That README also documents **`./workload.jsonl`** input and when to prefer **batches** vs **streams**.
@@ -0,0 +1,45 @@
1
+ [project]
2
+ name = "sference-cli"
3
+ version = "0.0.9"
4
+ description = "sference command-line interface"
5
+ readme = "README.md"
6
+ requires-python = ">=3.10"
7
+ license = "Apache-2.0"
8
+ license-files = ["LICENSE"]
9
+ authors = [{ name = "sference" }]
10
+ keywords = ["sference", "llm", "inference", "batch", "cli", "openai"]
11
+ classifiers = [
12
+ "Development Status :: 4 - Beta",
13
+ "Environment :: Console",
14
+ "Intended Audience :: Developers",
15
+ "Operating System :: OS Independent",
16
+ "Programming Language :: Python :: 3",
17
+ "Programming Language :: Python :: 3 :: Only",
18
+ "Programming Language :: Python :: 3.10",
19
+ "Programming Language :: Python :: 3.11",
20
+ "Programming Language :: Python :: 3.12",
21
+ "Programming Language :: Python :: 3.13",
22
+ "Topic :: Utilities",
23
+ ]
24
+ dependencies = [
25
+ "typer>=0.24.1",
26
+ "sference-sdk>=0.0.9",
27
+ ]
28
+
29
+ [project.urls]
30
+ Homepage = "https://sference.com"
31
+ Repository = "https://github.com/s-ference/sference"
32
+ Issues = "https://github.com/s-ference/sference/issues"
33
+
34
+ [project.scripts]
35
+ sference = "sference_cli.main:main"
36
+
37
+ [build-system]
38
+ requires = ["hatchling>=1.29.0"]
39
+ build-backend = "hatchling.build"
40
+
41
+ [tool.hatch.build.targets.wheel]
42
+ packages = ["sference_cli"]
43
+
44
+ [tool.hatch.build.targets.sdist]
45
+ include = ["sference_cli", "README.md"]
@@ -39,12 +39,22 @@ app.add_typer(models_app, name="models")
39
39
 
40
40
  CREDENTIALS_PATH = Path.home() / ".sference" / "credentials.json"
41
41
 
42
- DEFAULT_CONSOLE_URL = "https://console.sference.com"
42
+ DEFAULT_CONSOLE_URL = "https://app.sference.com"
43
43
 
44
44
 
45
45
  def _write_token(token: str) -> None:
46
+ # The credential file holds an API key; keep it owner-only (0700 dir / 0600 file)
47
+ # so other local users cannot read it. chmod is a no-op on Windows.
46
48
  CREDENTIALS_PATH.parent.mkdir(parents=True, exist_ok=True)
49
+ try:
50
+ os.chmod(CREDENTIALS_PATH.parent, 0o700)
51
+ except OSError:
52
+ pass
47
53
  CREDENTIALS_PATH.write_text(json.dumps({"token": token}), encoding="utf-8")
54
+ try:
55
+ os.chmod(CREDENTIALS_PATH, 0o600)
56
+ except OSError:
57
+ pass
48
58
 
49
59
 
50
60
  def _read_token() -> str | None:
@@ -61,14 +71,14 @@ def _read_token() -> str | None:
61
71
  return None
62
72
 
63
73
 
64
- def _client(base_url: Optional[str] = None) -> SferenceClient:
74
+ def _client(base_url: Optional[str] = None, *, timeout: float | None = None) -> SferenceClient:
65
75
  # If the caller didn't explicitly pass --base-url, allow SFERENCE_BASE_URL
66
76
  # to override the default.
67
77
  env_base_url = os.environ.get("SFERENCE_BASE_URL")
68
78
  if env_base_url and (base_url is None or base_url == "https://api.sference.com"):
69
79
  _logger.info(f"Using SFERENCE_BASE_URL: {env_base_url}")
70
80
  base_url = env_base_url
71
- return SferenceClient(base_url=base_url, api_key=_read_token())
81
+ return SferenceClient(base_url=base_url, api_key=_read_token(), timeout=timeout)
72
82
 
73
83
 
74
84
  def _ensure_api_credential() -> None:
@@ -142,26 +152,6 @@ def _list_models(*, client: SferenceClient, as_json: bool) -> None:
142
152
  typer.echo(json.dumps(payload, indent=None if as_json else 2))
143
153
 
144
154
 
145
- def _wait_for_response(
146
- client: SferenceClient, response_id: str, *, poll_ms: int, timeout_s: int
147
- ) -> Any:
148
- """Poll GET /v1/responses/{id} until terminal status or timeout."""
149
- deadline = time.time() + max(1, timeout_s)
150
- last: Any = None
151
- while True:
152
- last = _call_api(lambda: client.get_response(response_id))
153
- if hasattr(last, "model_dump"):
154
- d = last.model_dump()
155
- status = d.get("status") if isinstance(d, dict) else None
156
- else:
157
- status = getattr(last, "status", None)
158
- if status in ("completed", "failed", "cancelled"):
159
- return last
160
- if time.time() >= deadline:
161
- return last
162
- time.sleep(max(10, poll_ms) / 1000.0)
163
-
164
-
165
155
  def _mvp_batch_window_only(value: str) -> str:
166
156
  if value != "24h":
167
157
  raise typer.BadParameter('Only "24h" is supported in MVP.', param_hint="--window")
@@ -268,7 +258,7 @@ def auth_login(
268
258
  None,
269
259
  "--console-url",
270
260
  envvar="SFERENCE_CONSOLE_URL",
271
- help="Console base URL for the browser step (default: https://console.sference.com).",
261
+ help="Console base URL for the browser step (default: https://app.sference.com).",
272
262
  ),
273
263
  no_browser: bool = typer.Option(False, "--no-browser", help="Do not open a browser; print the URL and prompt only."),
274
264
  ) -> None:
@@ -352,34 +342,40 @@ def responses_create(
352
342
  "--enable-thinking/--disable-thinking",
353
343
  help="Qwen3: forward to tokenizer apply_chat_template. Omit for tokenizer default.",
354
344
  ),
355
- wait: bool = typer.Option(False, "--wait/--no-wait"),
356
- poll_ms: int = typer.Option(500, "--poll-ms", help="Polling interval when --wait is enabled."),
357
- timeout_s: int = typer.Option(60, "--timeout-s", help="Timeout in seconds when --wait is enabled."),
345
+ background: bool = typer.Option(
346
+ False,
347
+ "--background/--no-background",
348
+ help="Submit asynchronously and return immediately. Default blocks until the response is terminal (matches POST /v1/responses).",
349
+ ),
350
+ timeout: float = typer.Option(
351
+ 600.0,
352
+ "--timeout",
353
+ help="HTTP read timeout in seconds.",
354
+ ),
358
355
  base_url: str = typer.Option("https://api.sference.com"),
359
356
  ) -> None:
360
357
  _ensure_api_credential()
361
- client = _client(base_url)
358
+ client = _client(base_url, timeout=timeout)
362
359
  resp = _call_api(
363
360
  lambda: client.create_response(
364
361
  model=model,
365
362
  input=[{"role": "user", "content": content}],
366
363
  include_reasoning=include_reasoning,
367
364
  enable_thinking=enable_thinking,
365
+ background=background,
368
366
  )
369
367
  )
370
- if wait:
371
- final = _wait_for_response(client, resp.id, poll_ms=poll_ms, timeout_s=timeout_s)
372
- if getattr(final, "status", None) not in ("completed", "failed", "cancelled"):
373
- _print(final.model_dump(), True)
374
- raise typer.Exit(code=1)
375
- resp = final
376
368
  _print(resp.model_dump(), True)
377
369
 
378
370
 
379
371
  @responses_app.command("result")
380
372
  def responses_result(
381
373
  id: str = typer.Option(..., "--id"),
382
- poll_ms: int = typer.Option(500, "--poll-ms", help="Polling interval while waiting for completion."),
374
+ poll_interval: float = typer.Option(
375
+ 0.5,
376
+ "--poll-interval",
377
+ help="Seconds between status polls while waiting for completion.",
378
+ ),
383
379
  base_url: str = typer.Option("https://api.sference.com"),
384
380
  ) -> None:
385
381
  """Wait for a response to reach a terminal status and print the final JSON.
@@ -396,7 +392,7 @@ def responses_result(
396
392
  if status in ("completed", "failed", "cancelled"):
397
393
  _print(d, True)
398
394
  return
399
- time.sleep(max(10, poll_ms) / 1000.0)
395
+ time.sleep(max(0.01, poll_interval))
400
396
  except KeyboardInterrupt:
401
397
  raise typer.Exit(code=130) from None
402
398
 
@@ -415,7 +411,11 @@ def responses_tail(
415
411
  help="Ignore saved checkpoint and start from the latest events page.",
416
412
  ),
417
413
  no_checkpoint: bool = typer.Option(False, "--no-checkpoint", help="Do not read or write checkpoints."),
418
- poll_ms: int = typer.Option(5000, "--poll-ms", help="Long-poll wait_ms when catching up (max 30000)."),
414
+ poll_interval: float = typer.Option(
415
+ 5.0,
416
+ "--poll-interval",
417
+ help="Seconds to long-poll while catching up (capped at 30s server-side).",
418
+ ),
419
419
  base_url: str = typer.Option("https://api.sference.com"),
420
420
  as_json: bool = typer.Option(False, "--json"),
421
421
  ) -> None:
@@ -436,6 +436,7 @@ def responses_tail(
436
436
  if not no_checkpoint and not from_latest:
437
437
  last = load_checkpoint(bu, ck, consumer)
438
438
 
439
+ wait_ms = int(min(poll_interval, 30.0) * 1000)
439
440
  try:
440
441
  while True:
441
442
 
@@ -444,12 +445,12 @@ def responses_tail(
444
445
  stream_id=stream_id,
445
446
  limit=50,
446
447
  starting_after=last,
447
- wait_ms=min(poll_ms, 30000),
448
+ wait_ms=wait_ms,
448
449
  )
449
450
 
450
451
  page = _call_api(fetch)
451
452
  if not page.data:
452
- time.sleep(max(1, poll_ms) / 1000.0)
453
+ time.sleep(max(0.001, poll_interval))
453
454
  continue
454
455
  for ev in page.data:
455
456
  typer.echo(json.dumps(ev.model_dump(), default=str))
@@ -717,7 +718,7 @@ def stream_submit(
717
718
  raise typer.Exit(code=1)
718
719
 
719
720
  if not model:
720
- typer.echo("--model is required for stream submit (e.g., gpt-4o)", err=True)
721
+ typer.echo("--model is required for stream submit (e.g., Qwen/Qwen3.6-35B-A3B)", err=True)
721
722
  raise typer.Exit(code=1)
722
723
 
723
724
  client = _client(base_url)
@@ -1,23 +0,0 @@
1
- [project]
2
- name = "sference-cli"
3
- version = "0.0.7"
4
- description = "sference command-line interface"
5
- readme = "README.md"
6
- requires-python = ">=3.12"
7
- dependencies = [
8
- "typer>=0.24.1",
9
- "sference-sdk>=0.0.7",
10
- ]
11
-
12
- [project.scripts]
13
- sference = "sference_cli.main:main"
14
-
15
- [build-system]
16
- requires = ["hatchling>=1.29.0"]
17
- build-backend = "hatchling.build"
18
-
19
- [tool.hatch.build.targets.wheel]
20
- packages = ["sference_cli"]
21
-
22
- [tool.hatch.build.targets.sdist]
23
- include = ["sference_cli", "README.md"]
File without changes