command-code 1.88.2 → 1.88.4

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # command-code
 
+## 1.88.4
+
+### Patch Changes
+
+- feat: Set DeepSeek V4.1 Flash as default model
+- fix: retire the free Laguna S 2.1 model
+- refactor: improve cli login instructions
+
+## 1.88.3
+
+### Patch Changes
+
+- chore: bump deps to latest versions
+
 ## 1.88.2
 
 ### Patch Changes

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

@@ -57,14 +57,15 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
 | `thinkingmachines/inkling` | Inkling | 256K | — | $1/$4.05 · cache $0.17 | Go and above | multimodal MoE reasoning |
 | `thinkingmachines/inkling-small` | Inkling Small | 1M | — | $0.5/$1.2 · cache $0.1 | Go and above | lightweight MoE reasoning at lower cost and latency |
 | `reflection/beam:free` | Beam 1.0 | 1.05M | low, medium, high, xhigh, max | $0/$0 · cache $0 | Go and above | reasoning model for coding and agentic workflows |
-| `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 |
 | `inclusionai/ling-3.1-flash` | Ling 3.1 Flash | 262K | low, medium, high | $0.3/$0.9 · cache $0.06 | Go and above | hybrid-reasoning MoE for coding & tool-using agents |
+| `inclusionai/ling-3.1-flash-1019` | Ling 3.1 Flash 1019 | 1M | low, medium, high | $0.3/$0.9 · cache $0.06 | Go and above | hybrid-reasoning MoE for coding & tool-using agents |
 | `mistral/mistral-large-4` | Mistral Large 4 | 524K | low, medium, high | $1.36/$4.18 · cache $0.14 | Go and above | frontier open-weight multimodal model for coding & analysis |
 ## Stealth
 
 | Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
 |---|---|---|---|---|---|---|
 | `stealth/glyph-cluster:free` | Glyph Cluster | 256K | low, medium, high, xhigh | $0/$0 · cache $0 | Go and above | stealth reasoning model in early access |
+| `stealth/crouton-alpha` | Crouton Alpha | 1.05M | low, medium, high, xhigh, max | $0/$0 · cache $0 | Go and above | lightweight stealth model for agentic sub-tasks, 1M context |
 ## Anthropic
 
 | Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |

package/dist/bundled/command-code-knowledge/reference/product-help.md

@@ -339,9 +339,10 @@ Valid model ids (the /model catalog — use these EXACT ids):
 - thinkingmachines/inkling
 - thinkingmachines/inkling-small
 - stealth/glyph-cluster:free
+- stealth/crouton-alpha
 - reflection/beam:free
-- poolside/laguna-s-2.1-free
 - inclusionai/ling-3.1-flash
+- inclusionai/ling-3.1-flash-1019
 - meta/muse-spark-1.1
 - meta/muse-spark-1.2
 - meta/muse-spark-1.2-contributor
@@ -459,9 +460,9 @@ Manage your plan:
 - Track usage: https://commandcode.ai/usage (personal). For an org: https://commandcode.ai/<orgLogin>/settings/usage
 - Manage payment methods: Access billing portal from Studio > Billing
 
-Buying extra credits: Studio > Billing, then Buy Credits. Pick an amount from 5 to 500 credits ($1 of usage each), then pick how to pay: card, Alipay or crypto charged in US Dollars plus a processing fee, or UPI charged in Indian Rupees where it is offered. The payment finishes on Stripe's secure page and the credits land on your balance within moments.
+Buying extra credits: Studio > Billing, then Buy Credits. Pick an amount from 5 to 500 credits ($1 of usage each), then pick how to pay: card, Alipay, WeChat Pay or crypto charged in US Dollars plus a processing fee, or UPI charged in Indian Rupees where it is offered. The payment finishes on Stripe's secure page and the credits land on your balance within moments.
 Buying credits changes nothing else: it never saves a payment method, never changes your default card, and never turns auto reload on.
-Auto reload: A separate opt-in in Studio > Billing that tops your balance up when it runs low. It charges your default card only, so Alipay, crypto and UPI cannot be used for it - add a card there first if none is saved.
+Auto reload: A separate opt-in in Studio > Billing that tops your balance up when it runs low. It charges your default card only, so Alipay, WeChat Pay, crypto and UPI cannot be used for it - add a card there first if none is saved.
 Premium requests: Any request that uses a premium model (like taste-1) during your coding session.
 When you hit your limit: Buy extra credits, or turn on auto reload so a saved card tops you up automatically. Extra credits are purchased at model cost and roll over.
 Switch plans: Upgrade or downgrade anytime from Studio > Billing. Changes take effect next billing cycle.