command-code 1.87.3 → 1.88.1

package/CHANGELOG.md

@@ -1,5 +1,21 @@
 # command-code
 
+## 1.88.1
+
+### Patch Changes
+
+- refactor: improved bulk images handling in context
+- fix: `cmd taste push --overwrite` no longer drops learnings from a package file with several heading sections.
+
+## 1.88.0
+
+### Minor Changes
+
+- feat: run background tasks on the active free model to save costs, with a /config toggle to turn it off
+- refactor: improve updater and add manual update hint
+- fix: /config list scrolls when it would outgrow the terminal
+- fix: keep the session alive when an update replaces the install directory mid-session
+
 ## 1.87.3
 
 ### Patch Changes

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

@@ -14,6 +14,7 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
 | `deepseek/deepseek-v4-flash-fast` | DeepSeek V4 Flash Fast | 1M | low, high, max | $0.28/$0.56 · cache $0.07 | Go and above | low-latency V4 Flash deployment |
 | `deepseek/deepseek-v4.1-flash` | DeepSeek V4.1 Flash (latest) | 1M | off, low, high, max | $0.15/$0.6 · cache $0.003 | Go and above | V4.1 hybrid-attention reasoning with vision |
 | `deepseek/deepseek-v4.1-flash-fast` | DeepSeek V4.1 Flash Fast (latest) | 1M | off, low, high, max | $0.16/$0.58 · cache $0.016 | Go and above | High throughput V4.1 Flash |
+| `moonshotai/Kimi-K3.1-Pro` | Kimi K3.1 Pro | 1.05M | low, high, max | $2/$10 · cache $0.2 | Go and above | frontier reasoning & agentic coding with 1M context |
 | `moonshotai/Kimi-K3` | Kimi K3 | 1M | low, high, max | $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 |
@@ -34,8 +35,6 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
 | `xiaomi/mimo-v2.6-pro` | MiMo V2.6 Pro | 1.05M | — | $0.435/$0.87 · cache $0.0036 | Go and above | flagship multimodal agentic coding with 1M context |
 | `xiaomi/mimo-v2.6-pro-ultraspeed` | MiMo V2.6 Pro UltraSpeed | 1.05M | — | $4.35/$8.7 · cache $0.036 | GOAT and above | low-latency serving tier of MiMo V2.6 Pro |
 | `xiaomi/mimo-v2.6-flash` | MiMo V2.6 Flash | 1.05M | — | $0.14/$0.28 · cache $0.0028 | Go and above | efficient multimodal agentic coding with 1M context |
-| `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 |
-| `xiaomi/mimo-v2.5` | MiMo V2.5 | 1M | — | $0.14/$0.28 · cache $0.0028 | Go and above | efficient long-context agentic coding |
 | `Qwen/Qwen3.8-Omni-Flash` | Qwen 3.8 Omni Flash | 1M | low, medium, xhigh | $0.15/$0.47 · cache $0.016 | Go and above | omni-modal understanding & multimedia agentic work |
 | `Qwen/Qwen3.8-Max-Prime` | Qwen 3.8 Max Prime | 1M | low, medium, xhigh | $4/$12 · cache $0.5 (write $5) | GOAT and above | high-speed Qwen 3.8 Max: 1.5–2× faster output |
 | `Qwen/Qwen3.8-Max-0902` | Qwen 3.8 Max 0902 | 1M | low, medium, xhigh | $2/$6 · cache $0.25 | Go and above | upgraded Qwen 3.8 Max: stronger coding & agentic tool use |
@@ -87,6 +86,7 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
 |---|---|---|---|---|---|---|
 | `gpt-6-astra` | GPT-6 Astra | 1.05M | low, medium, high, xhigh, max | $10/$50 · cache $1 (write $12.5) | Max | most capable OpenAI model for demanding reasoning & agents |
 | `gpt-6.1-sol` | GPT-6.1 Sol | 1.05M | low, medium, high, xhigh, max | $2/$10 · cache $0.1 (write $2.5) | Max | near-Astra performance for complex work at a lower cost |
+| `gpt-6.1-terra` | GPT-6.1 Terra | 1.05M | low, medium, high, xhigh, max | $1/$5 · cache $0.05 (write $1.25) | Pro and above | fast, efficient model for visual reasoning, computer use & writing |
 | `gpt-6-sol` | GPT-6 Sol | 1.05M | low, medium, high, xhigh, max | $2/$10 · cache $0.2 (write $2.5) | Pro and above | built for complex coding & agentic workflows |
 | `gpt-6-luna` | GPT-6 Luna | 1.05M | low, medium, high, xhigh, max | $0.1/$0.5 · cache $0.01 (write $0.125) | Go and above | most efficient OpenAI model for focused, high-volume tasks |
 | `gpt-5.6-sol` | GPT-5.6 Sol | 1.05M | low, medium, high, xhigh, max | $5/$30 · cache $0.5 (write $6.25) | GOAT and above | frontier model for complex professional work |

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

@@ -272,6 +272,7 @@ Valid model ids (the /model catalog — use these EXACT ids):
 - claude-haiku-4-5-20251001
 - gpt-6-astra
 - gpt-6.1-sol
+- gpt-6.1-terra
 - gpt-6-sol
 - gpt-6-luna
 - gpt-5.6-sol
@@ -287,6 +288,7 @@ Valid model ids (the /model catalog — use these EXACT ids):
 - deepseek/deepseek-v4-flash-fast
 - deepseek/deepseek-v4.1-flash
 - deepseek/deepseek-v4.1-flash-fast
+- moonshotai/Kimi-K3.1-Pro
 - moonshotai/Kimi-K3
 - moonshotai/Kimi-K2.7-Code
 - moonshotai/Kimi-K2.7-Code-Highspeed
@@ -300,17 +302,13 @@ Valid model ids (the /model catalog — use these EXACT ids):
 - zai-org/GLM-5.1
 - zai-org/GLM-5
 - minimax/minimax-m3.1-flash
-- minimax/minimax-m3.1-flash:free
 - MiniMaxAI/MiniMax-M3
 - MiniMaxAI/MiniMax-M2.7
 - MiniMaxAI/MiniMax-M2.5
 - ornith/ornith-1.5-122b
-- ornith/ornith-1.5-122b:free
 - xiaomi/mimo-v2.6-pro
 - xiaomi/mimo-v2.6-pro-ultraspeed
 - xiaomi/mimo-v2.6-flash
-- xiaomi/mimo-v2.5-pro
-- xiaomi/mimo-v2.5
 - Qwen/Qwen3.8-Omni-Flash
 - Qwen/Qwen3.8-Max-Prime
 - Qwen/Qwen3.8-Max-0902
@@ -455,7 +453,6 @@ A: Join our Discord at https://commandcode.ai/discord, report issues on GitHub,
 How it works:
 - Monthly reset: Request limits reset at the start of each billing cycle.
 - Extra credits: Buy them at model cost any time. Credits roll over and never expire.
-- No AI training: Command Code does not train on your code or store your code snippets unless you choose to share them.
 
 Manage your plan:
 - Purchase credits or subscribe: Studio > Billing at https://commandcode.ai/billing
@@ -473,7 +470,6 @@ Team billing: Billed per seat. Credits are pooled at the team level.
 Enterprise: Enhanced security, compliance, and control. Contact support@commandcode.ai for Enterprise edition.
 
 ## PRIVACY & LEGAL
-- Command Code does not train on your code or store your code snippets unless you choose to share them.
 - Taste processing runs on your codebase and stores learning data in your project and on your local machine only.
 - Privacy Policy: https://commandcode.ai/privacy
 - Terms of Service: https://commandcode.ai/terms

package/dist/bundled/config/references/settings.md

@@ -18,6 +18,7 @@ The executable registry is authoritative. Run `cmd config list --scope effective
 | `image-vision` | user | enum | `ask`, `enabled`, `disabled` | Let a text-only model read attached images by describing them with the vision model ("Ask on first use" prompts the first time you attach an image). |
 | `codemode` | user | enum | `mcp`, `tools`, `off` | The codemode tool lets the model write a short code script that can call several tools and run it in one go: fewer round trips, less raw tool output in context. Scripts never edit, write, or run commands. |
 | `branch-summary-skip-prompt` | user | boolean | `true`, `false` | Never ask about summarizing when switching branches in /tree. |
+| `background-tasks-use-free-model` | user | boolean | `true`, `false` | When your session model is free, switch background tasks (compaction, titles, tool descriptions, etc.) to the free model. Disable it to keep using your saved feature-model choices. |
 | `default-export-format` | user | enum | `html`, `jsonl`, `md` | Format a bare /export (no format or path) writes — an explicit /export html\|jsonl\|md\|<path> always overrides. |
 | `default-share-gist-format` | user | enum | `html`, `jsonl`, `md` | Format a bare /share gist (no format argument) posts — an explicit /share gist html\|jsonl\|md always overrides. |
 | `taste-learning` | user | boolean | `true`, `false` | Learn your coding style from your sessions, user-wide (same setting as /taste). |

package/dist/bundled/mod-builder/reference/ui.md

@@ -215,6 +215,20 @@ The desktop app draws the same surface around the chat composer. Mod code still
 - **Toasts**: the app's own toasts, titled with the mod's name.
 - **Styling**: ansi bold, dim, and the eight element colors map to the app theme; other escape codes (cursor moves, links, 256-color) are dropped.
 
+## In the VS Code extension
+
+The [IDE extension](https://commandcode.ai/docs/ide) loads mods from the same places as the CLI, with one mod host per chat session.
+
+- Mod commands appear in the slash menu. `message` and `prompt` results and thrown errors show in the chat.
+- `notify`, `toast`, `showEntry` and `mod_error` become chat rows. `confirm`, `select` and `input` use the question card.
+- `setStatus` text appears in the VS Code status bar.
+- `cmd.store` shares `~/.commandcode/mods/.store` with the CLI.
+- `/mods` lists loaded and failed mods. `/mods reload [name]` reloads them.
+
+Project mods load only for the trusted workspace folder.
+
+More mods support coming soon.
+
 ## Headless behavior at a glance
 
 | Surface | Interactive TUI | Desktop app | Headless (`-p`) |