command-code 1.32.2 → 1.33.1
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 +1,25 @@
|
|
|
1
1
|
# command-code
|
|
2
2
|
|
|
3
|
+
## 1.33.1
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- fix: a providers.json provider named after a catalog vendor no longer hijacks that vendor's models
|
|
8
|
+
- feat: m3 tool calling improvements
|
|
9
|
+
|
|
10
|
+
## Unreleased
|
|
11
|
+
|
|
12
|
+
### Patch Changes
|
|
13
|
+
|
|
14
|
+
- fix: give MiniMax M3 Free its full tool set instead of deferred tools
|
|
15
|
+
- fix: /reload no longer stacks the welcome banner on each reload
|
|
16
|
+
|
|
17
|
+
## 1.33.0
|
|
18
|
+
|
|
19
|
+
### Minor Changes
|
|
20
|
+
|
|
21
|
+
- feat: add MiniMax M3 Free and M2.7 Free
|
|
22
|
+
|
|
3
23
|
## 1.32.2
|
|
4
24
|
|
|
5
25
|
### Patch Changes
|
|
@@ -23,6 +23,8 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
|
|
|
23
23
|
| `zai-org/GLM-5` | GLM-5 | 200K | — | $1/$3.2 · cache $0.2 | Go and above | multi-mode thinking & long-range planning |
|
|
24
24
|
| `MiniMaxAI/MiniMax-M3` | MiniMax M3 | 1M | — | $0.3/$1.2 · cache $0.06 | Go and above | frontier coding, agents & native multimodality |
|
|
25
25
|
| `MiniMaxAI/MiniMax-M2.7` | MiniMax M2.7 | — | — | $0.3/$1.2 · cache $0.06 | Go and above | end-to-end software engineering agent |
|
|
26
|
+
| `minimax/minimax-m3-free` | MiniMax M3 | 1M | — | $0/$0 · cache $0 | Go and above | frontier coding, agents & native multimodality |
|
|
27
|
+
| `minimax/minimax-m2.7-free` | MiniMax M2.7 | 197K | — | $0/$0 · cache $0 | Go and above | end-to-end software engineering agent |
|
|
26
28
|
| `MiniMaxAI/MiniMax-M2.5` | MiniMax M2.5 | 200K | — | $0.3/$1.2 · cache $0.03 | Go and above | cross-platform full-stack agentic dev |
|
|
27
29
|
| `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 |
|
|
28
30
|
| `xiaomi/mimo-v2.5` | MiMo V2.5 | 1M | — | $0.14/$0.28 · cache $0.0028 | Go and above | efficient long-context agentic coding |
|
|
@@ -40,11 +42,6 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
|
|
|
40
42
|
| `thinkingmachines/inkling` | Inkling | 256K | — | $1/$4.05 · cache $0.17 | Go and above | multimodal MoE reasoning |
|
|
41
43
|
| `thinkingmachines/inkling-small` | Inkling Small | 1M | — | $0.5/$1.2 · cache $0.1 | Go and above | lightweight MoE reasoning at lower cost and latency |
|
|
42
44
|
| `poolside/laguna-s-2.1-free` | Laguna S 2.1 | 256K | — | $0/$0 · cache $0 | Go and above | open-weight agentic coding and long-horizon work |
|
|
43
|
-
## Stealth
|
|
44
|
-
|
|
45
|
-
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
|
|
46
|
-
|---|---|---|---|---|---|---|
|
|
47
|
-
| `stealth/ox-alpha` | Ox Alpha | 1.05M | low, high, max | $0/$0 · cache $0 | Go and above | long-horizon coding, agentic work & visual context |
|
|
48
45
|
## Anthropic
|
|
49
46
|
|
|
50
47
|
| Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
|
|
@@ -308,7 +308,8 @@ Valid model ids (the /model catalog — use these EXACT ids):
|
|
|
308
308
|
- nvidia/nemotron-3-ultra-550b-a55b
|
|
309
309
|
- poolside/laguna-s-2.1-free
|
|
310
310
|
- inclusionai/ling-3.0-flash-free
|
|
311
|
-
-
|
|
311
|
+
- minimax/minimax-m3-free
|
|
312
|
+
- minimax/minimax-m2.7-free
|
|
312
313
|
A BYO-provider id (from a configured custom provider) also works and is passed through as-is.
|
|
313
314
|
|
|
314
315
|
WHEN THE USER ASKS YOU TO CREATE AN AGENT (e.g. "make a changelog agent with a cheap model"):
|