command-code 1.73.3 → 1.74.0

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # command-code
 
+## 1.74.0
+
+### Minor Changes
+
+- feat: `cmd acp`. Run Command Code as an Agent Client Protocol agent in ACP clients like Zed.
+- feat: built-in `/acp` mod for help with acp editor setup
+
+## 1.73.4
+
+### Patch Changes
+
+- feat: add max reasoning effort to Space Bunny Alpha
+
 ## 1.73.3
 
 ### Patch Changes

package/dist/bundled/command-code-knowledge/reference/custom-slash-commands.md

@@ -90,7 +90,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 | `/mcp`                                             | Manage MCP server connections                                                     |
 | `/design [mode]`                                   | Design partner: audit, build, compose, and ship UI - bare `/design` browses modes |
 | `/loop [interval] [task]`                          | Run a task now, then repeat it on a fixed or self-paced schedule ([details](https://commandcode.ai/docs/loop)) |
-| `/rc [mode\|off\|status]`                           | Drive this session from Telegram or Discord ([details](https://commandcode.ai/docs/rc))                      |
+| `/rc [mode\|off\|status]`                           | Drive this session from Telegram or Discord ([details](https://commandcode.ai/docs/remote-control))                      |
 | `/import [claude\|codex\|cursor\|pi\|opencode\|gemini]` | Import your setup from another coding agent; bare `/import` imports from all sources |
 | `/taste`                                           | Manage Taste learning and usage                                                   |
 | `/learn-taste`                                     | Learn taste from sessions with other coding agents (Claude Code, Cursor, etc)     |
@@ -167,7 +167,7 @@ Most other commands - `/clear`, `/mode`, `/plan`, `/model`, `/compact`, `/worktr
 
 ### `/rc` in detail
 
-Bare `/rc` opens the picker: platform, setup, permission mode. `/rc default`, `/rc auto-accept` and `/rc yolo` connect straight into a mode. `/rc status` reports what is on, `/rc off` disconnects, and `/rc off clear` also deletes the bot's own messages. `/rc` is refused when the model asks for it and when it arrives from the chat, so the bot cannot change its own token or allowlist. See [`/rc`](https://commandcode.ai/docs/rc) for setup and what the chat can send.
+Bare `/rc` opens the picker: platform, setup, permission mode. `/rc default`, `/rc auto-accept` and `/rc yolo` connect straight into a mode. `/rc status` reports what is on, `/rc off` disconnects, and `/rc off clear` also deletes the bot's own messages. `/rc` is refused when the model asks for it and when it arrives from the chat, so the bot cannot change its own token or allowlist. See [`/rc`](https://commandcode.ai/docs/remote-control) for setup and what the chat can send.
 
 ---
 

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

@@ -60,7 +60,7 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
 
 | Id (use EXACTLY this) | Name | Context | Efforts | $/1M in/out · cache read | Min plan | Best for |
 |---|---|---|---|---|---|---|
-| `stealth/space-bunny-alpha` | Space Bunny Alpha | 1M | low, medium, high | $0/$0 · cache $0 | Go and above | stealth model with 1M context |
+| `stealth/space-bunny-alpha` | Space Bunny Alpha | 1M | low, medium, high, max | $0/$0 · cache $0 | Go and above | stealth model with 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

@@ -88,6 +88,7 @@
 - cmd learn-taste: Learn command structure from repositories
 - cmd mcp: Manage MCP (Model Context Protocol) servers
 - cmd skills: Manage skills from GitHub repositories
+- cmd acp: Run as an ACP agent over stdio (for Zed, etc.)
 - cmd mods: Manage mods (loadable extensions) from npm, git, or local paths
 - cmd login: Login with Command Code account
 - cmd logout: Log out of Command Code
@@ -435,7 +436,7 @@ A: Join our Discord at https://commandcode.ai/discord, report issues on GitHub,
 ## PRICING & LIMITS
 How it works:
 - Monthly reset: Request limits reset at the start of each billing cycle.
-- Auto top-up: Buy extra credits at model cost. Credits roll over and never expire.
+- 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:
@@ -443,8 +444,11 @@ 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 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.
 Premium requests: Any request that uses a premium model (like taste-1) during your coding session.
-When you hit your limit: Continue with auto top-up enabled. Extra credits are purchased at model cost and roll over.
+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.
 Team billing: Billed per seat. Credits are pooled at the team level.