command-code 1.32.2-rc.0 → 1.32.2

package/CHANGELOG.md

@@ -1,10 +1,11 @@
 # command-code
 
-## 1.32.2-rc.0
+## 1.32.2
 
 ### Patch Changes
 
-- feat: RC release
+- fix: model picker improvements in byok
+- fix: session no longer wedges when a tool result carries malformed content
 
 ## 1.32.1
 

package/dist/bundled/command-code-knowledge/reference/byok.md

@@ -141,12 +141,14 @@ Every field is optional but we recommend adding `contextWindow` as a bare minimu
 | `contextWindow` | number > 0 | Tokens. Compat alias: `limit.context` (`contextWindow` wins when both are set)  Default: 200K|
 | `maxOutput` | number > 0 | Tokens. Compat alias: `limit.output` |
 | `reasoning` | boolean | `true` assumes the efforts `low` / `medium` / `high`; `false` declares none |
-| `reasoningEfforts` | string[] | Exact valid set: `low` \| `medium` \| `high` \| `xhigh` \| `max`. Unknown levels are dropped with a warning naming that set |
+| `reasoningEfforts` | string[] | Exact valid set: `low` \| `medium` \| `high` \| `xhigh` \| `max`. Unknown levels are dropped with a warning |
 | `cost` | object | $ per 1M tokens: `input`, `output`, `cacheRead`, `cacheWrite` (snake_case `cache_read` / `cache_write` accepted); `0` is valid for free models |
 | `options` | object | Extra request-body params merged into every call for this model (`temperature`, `top_p`, …) |
 
 A non-object model value skips that model with a warning; sibling models survive.
 
+Reasoning efforts are auto-detected for known providers. If not added automatically, the onus to add them manually is on the user. Declare the supported efforts in the model's `reasoningEfforts` field inside the `~/.commandcode/providers.json` file.
+
 ---
 
 ## Example provider config
@@ -325,6 +327,15 @@ What stops working, by design: Command Code catalog (gateway) models, `/share`,
                 </p>
             )
         },
+        {
+            id: 'faq-reasoning-effort',
+            question: 'How do I add reasoning effort support for a custom provider?',
+            answer: (
+                <p>
+                    For a custom provider, you need to declare the supported efforts in the model's <code>reasoningEfforts</code> field in <code>~/.commandcode/providers.json</code>. They are automatically added for known providers, but if not available, they need to be added manually.
+                </p>
+            )
+        },
         {
             id: 'faq-same-id',
             question: 'What if a model id exists on Command Code and my provider?',

package/dist/bundled/command-code-knowledge/reference/models.md

@@ -10,7 +10,7 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
 |---|---|---|---|---|---|---|
 | `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 |
 | `deepseek/deepseek-v4-flash` | DeepSeek V4 Flash (latest) | 1M | high, max | $0.22/$0.66 · cache $0.007 | Go and above | fast hybrid-attention reasoning |
-| `deepseek/deepseek-v4-flash-vision-exp` | DeepSeek V4 Flash Vision (exp) | 1M | high, max | $0.22/$0.66 · cache $0.01 | Go and above | fast hybrid-attention reasoning with vision |
+| `deepseek/deepseek-v4-flash-vision-exp` | DeepSeek V4 Flash Vision (exp) | 1M | high, max | $0.22/$0.66 · cache $0.007 | Go and above | fast hybrid-attention reasoning with vision |
 | `moonshotai/Kimi-K3` | Kimi K3 | 1M | — | $3/$15 · cache $0.3 | Go and above | long-horizon coding & knowledge work with 1M context |
 | `moonshotai/Kimi-K2.7-Code` | Kimi K2.7 Code | 256K | — | $0.95/$4 · cache $0.19 | Go and above | improved long-horizon coding with vision |
 | `moonshotai/Kimi-K2.7-Code-Highspeed` | Kimi K2.7 Code HighSpeed | 262K | — | $1.9/$8 · cache $0.38 | Go and above | high-speed long-horizon coding with vision |