command-code 1.4.5 → 1.4.6

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 +1,12 @@
1
1
  # command-code
2
2
 
3
+ ## 1.4.6
4
+
5
+ ### Patch Changes
6
+
7
+ - feat: add Qwen 3.7 Flash
8
+ - fix: retry mid-stream connection drops instead of killing the turn
9
+
3
10
  ## 1.4.5
4
11
 
5
12
  ### Patch Changes
@@ -28,6 +28,7 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
28
28
  | `Qwen/Qwen3.6-Plus` | Qwen 3.6 Plus | — | — | $0.5/$3 | agentic coding & reasoning |
29
29
  | `Qwen/Qwen3.7-Max` | Qwen 3.7 Max | 1M | — | $2.5/$7.5 | frontier coding & long-horizon agent execution |
30
30
  | `Qwen/Qwen3.7-Plus` | Qwen 3.7 Plus | 1M | — | $0.4/$1.6 | agentic coding & reasoning at lower cost |
31
+ | `Qwen/Qwen3.7-Flash` | Qwen 3.7 Flash | 1M | — | $0.03/$0.13 | fast low-cost agentic coding & reasoning |
31
32
  | `stepfun/Step-3.7-Flash` | Step 3.7 Flash | 256K | — | $0.2/$1.15 | multimodal sparse-MoE reasoning |
32
33
  | `stepfun/Step-3.5-Flash` | Step 3.5 Flash | 1M | — | $0.1/$0.3 | fast sparse-MoE agentic reasoning |
33
34
  | `tencent/hy3-paid` | Tencent Hy3 | 262K | — | $0.14/$0.58 | sparse-MoE reasoning & agentic tool use |
@@ -285,6 +285,7 @@ Valid model ids (the /model catalog — use these EXACT ids):
285
285
  - Qwen/Qwen3.6-Plus
286
286
  - Qwen/Qwen3.7-Max
287
287
  - Qwen/Qwen3.7-Plus
288
+ - Qwen/Qwen3.7-Flash
288
289
  - stepfun/Step-3.7-Flash
289
290
  - stepfun/Step-3.5-Flash
290
291
  - tencent/hy3-paid