command-code 1.27.2 → 1.28.1

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 +1,17 @@
1
1
  # command-code
2
2
 
3
+ ## 1.28.1
4
+
5
+ ### Patch Changes
6
+
7
+ - fix: support reasoning effort (low/medium/xhigh) on Qwen 3.8 27B
8
+
9
+ ## 1.28.0
10
+
11
+ ### Minor Changes
12
+
13
+ - Add Qwen 3.8 27B
14
+
3
15
  ## 1.27.2
4
16
 
5
17
  ### Patch Changes
@@ -14,12 +26,9 @@
14
26
 
15
27
  ## 1.27.0
16
28
 
17
- ### Patch Changes
29
+ ### Minor Changes
18
30
 
19
31
  - feat: add GPT-5.6 Sol at 50% off in GOAT and above
20
-
21
- ### Patch Changes
22
-
23
32
  - fix: refresh the version banner after `/reload`
24
33
 
25
34
  ## 1.26.0
@@ -26,6 +26,7 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
26
26
  | `xiaomi/mimo-v2.5-pro` | MiMo V2.5 Pro | 1M | — | $0.435/$0.87 · cache $0.0036 | Go and above | high-capability long-context agentic coding |
27
27
  | `xiaomi/mimo-v2.5` | MiMo V2.5 | 1M | — | $0.14/$0.28 · cache $0.0028 | Go and above | efficient long-context agentic coding |
28
28
  | `Qwen/Qwen3.8-Max` | Qwen 3.8 Max | 1M | low, medium, xhigh | $2/$6 · cache $0.25 (write $2.5) | Go and above | autonomous long-horizon coding & professional work |
29
+ | `Qwen/Qwen3.8-27B` | Qwen 3.8 27B | 262K | low, medium, xhigh | $0.4/$3 · cache $0.04 | Go and above | compact vision-language coding & agentic work |
29
30
  | `Qwen/Qwen3.7-Max` | Qwen 3.7 Max | 1M | — | $2.5/$7.5 · cache $0.5 (write $3.13) | Go and above | frontier coding & long-horizon agent execution |
30
31
  | `Qwen/Qwen3.7-Plus` | Qwen 3.7 Plus | 1M | — | $0.4/$1.6 · cache $0.08 (write $0.5) | Go and above | agentic coding & reasoning at lower cost |
31
32
  | `Qwen/Qwen3.7-Flash` | Qwen 3.7 Flash | 1M | — | $0.03/$0.13 · cache $0.006 (write $0.038) | Go and above | fast low-cost agentic coding & reasoning |
@@ -286,6 +286,7 @@ Valid model ids (the /model catalog — use these EXACT ids):
286
286
  - Qwen/Qwen3.7-Max
287
287
  - Qwen/Qwen3.7-Plus
288
288
  - Qwen/Qwen3.8-Max
289
+ - Qwen/Qwen3.8-27B
289
290
  - Qwen/Qwen3.7-Flash
290
291
  - stepfun/Step-3.7-Flash
291
292
  - stepfun/Step-3.5-Flash