command-code 1.53.0 → 1.54.0
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/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,21 @@
|
|
|
1
1
|
# command-code
|
|
2
2
|
|
|
3
|
+
## 1.54.0
|
|
4
|
+
|
|
5
|
+
### Minor Changes
|
|
6
|
+
|
|
7
|
+
- feat: command code has first-class herdr support (#4704)
|
|
8
|
+
- feat: command code has first-class herdr support (#4704)
|
|
9
|
+
|
|
10
|
+
## 1.53.1
|
|
11
|
+
|
|
12
|
+
### Patch Changes
|
|
13
|
+
|
|
14
|
+
- feat: Set default compaction model to DeepSeek V4.1 Flash in /config
|
|
15
|
+
- fix: byok reasoning effort control improvement
|
|
16
|
+
- feat: show Extra Credits separately in the /usage summary line
|
|
17
|
+
- fix: remove the "$X left" credits field from the /usage summary line
|
|
18
|
+
|
|
3
19
|
## 1.53.0
|
|
4
20
|
|
|
5
21
|
### Minor Changes
|
|
@@ -10,7 +10,7 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
|
|
|
10
10
|
|---|---|---|---|---|---|---|
|
|
11
11
|
| `deepseek/deepseek-v4-pro` | DeepSeek V4 Pro (latest) | 1M | high, max | $0.66/$1.98 · cache $0.022 | Go and above | hybrid-attention long-context reasoning |
|
|
12
12
|
| `deepseek/deepseek-v4-flash` | DeepSeek V4 Flash (latest) | 1M | high, max | $0.15/$0.6 · cache $0.003 | Go and above | fast hybrid-attention reasoning |
|
|
13
|
-
| `deepseek/deepseek-v4-flash-vision-exp` | DeepSeek V4 Flash Vision (exp) | 1M | high, max | $0.
|
|
13
|
+
| `deepseek/deepseek-v4-flash-vision-exp` | DeepSeek V4 Flash Vision (exp) | 1M | high, max | $0.15/$0.6 · cache $0.003 | Go and above | fast hybrid-attention reasoning with vision |
|
|
14
14
|
| `deepseek/deepseek-v4-flash-fast` | DeepSeek V4 Flash Fast | 1M | low, high, max | $0.28/$0.56 · cache $0.07 | Go and above | low-latency V4 Flash deployment |
|
|
15
15
|
| `deepseek/deepseek-v4.1-flash` | DeepSeek V4.1 Flash | 1M | low, high, max | $0.15/$0.6 · cache $0.003 | Go and above | V4.1 hybrid-attention reasoning with vision |
|
|
16
16
|
| `moonshotai/Kimi-K3` | Kimi K3 | 1M | low, high, max | $3/$15 · cache $0.3 | Go and above | long-horizon coding & knowledge work with 1M context |
|