command-code 1.74.1 → 1.74.2

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # command-code
 
+## 1.74.2
+
+### Patch Changes
+
+- chore: retire the two free stealth preview models, Space Bunny Alpha and Pixel Canary
+
 ## 1.74.1
 
 ### Patch Changes

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

@@ -276,7 +276,7 @@ The `model` field takes any id you'd pass to `/model`. To find one:
 
 Use ids exactly as `--list-models` prints them. Examples: `claude-opus-4-8`, `claude-sonnet-5`, `claude-haiku-4-5`, `moonshotai/kimi-k2.6`, `zai-org/glm-5.2`.
 
-Omitting `model` is the same as `model: inherit` - the agent follows the session's `/model`. Pinning a model gives the agent its own prompt cache, so a slow planner and a fast implementer don't thrash each other's.
+Omitting `model` is the same as `model: inherit` - the agent follows the model the conversation is running on: the session's `/model`, or the [planning or implementation model](https://commandcode.ai/docs/settings#planning-and-implementation-models) while one is active. Pinning a model gives the agent its own prompt cache, so a slow planner and a fast implementer don't thrash each other's.
 
 ### Reasoning effort
 

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

@@ -75,7 +75,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 
 | **Command**       | **Description**                                                                          |
 | ----------------- | ---------------------------------------------------------------------------------------- |
-| `/model [id]`     | Switch between Command Code models - `/model <id>` applies directly, bare opens a picker |
+| `/model [id]`     | Switch between Command Code models - `/model <id>` applies directly, bare opens a picker. For a separate model while planning and after approving, see [planning and implementation models](https://commandcode.ai/docs/settings#planning-and-implementation-models) |
 | `/effort [level]` | Set reasoning effort for the current model (levels depend on the model)                  |
 | `/connect`      | Connect to AI providers. Command Code, [BYOK providers](./byok.md) and API keys |
 | `/login`          | Log in to Command Code or a provider                                                     |

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

@@ -56,11 +56,6 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
 | `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-3.0-flash-sante:free` | Ling 3.0 Flash Sante | 262K | — | $0/$0 · cache $0 | Go and above | health & medicine tuned lightweight-MoE, still strong on code |
 | `inclusionai/ling-3.1-flash:free` | Ling 3.1 Flash | 262K | low, medium, high | $0/$0 · cache $0 | Go and above | hybrid-reasoning MoE for coding & tool-using agents |
-## Stealth
-
-| 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, 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/plan-mode.md

@@ -67,6 +67,32 @@ The usual loop: start in **plan**, explore and agree on the approach, approve th
 
 ---
 
+## A model for each phase
+
+Planning and implementing want different things: a strong reasoner to explore and design, a fast, cheap coder to grind through the edits. Set a **planning** and an **implementation** model and Command Code switches between them for you:
+
+- **Planning** runs while the session is in plan mode: exploring the codebase and writing the plan.
+- **Implementation** takes over the moment you approve the plan, mid-run, on the very next turn.
+
+```json
+{
+	"featureModels": {
+		"planning": "zai-org/glm-5.3",
+		"implementation": "deepseek/deepseek-v4-pro"
+	}
+}
+```
+
+Put that in `~/.commandcode/config.json` or any `settings.json` layer, or pick them in `/config` → **Feature models** → **Planning** / **Implementation**. Both are optional; an unset one runs on your session model.
+
+The status row shows which phase you are in, `planning: GLM-5.3` then `implementing: DeepSeek V4 Pro (latest)`, and approving posts `Plan handoff — now implementing with deepseek-v4-pro.` Leaving plan mode **without** approving (`shift+tab`, `/mode:default`, or `/mode:accept-edits`) keeps you on the session model, and picking anything with `/model` stands both lanes down until the next planning round.
+
+**Planning and implementation models**
+	When each lane applies, how it interacts with `/model`, `/effort`, and
+	sub-agents, and what happens when a lane's model isn't on your plan.
+
+---
+
 ## Plan review
 
 Plan review turns a plan into a first-class, persistent artifact you can read, comment on, revise, and approve, instead of a block of text that scrolls away.
@@ -174,7 +200,7 @@ Trigger a verb by chord from anywhere, or arrow onto it and press `Enter`.
 | Verb | Chord | What it does |
 |------|-------|--------------|
 | **Submit review** | `ctrl+r` | The agent takes your pending comments, revises the plan, and re-presents it for another round. Only shown when you have pending comments. |
-| **Approve** *(approval surface)* | `ctrl+a` | Executes the plan and begins implementation. |
+| **Approve** *(approval surface)* | `ctrl+a` | Executes the plan and begins implementation, on your [implementation model](#a-model-for-each-phase) if one is set. |
 | **Execute plan** *(browser surface)* | `ctrl+e` | Executes the plan as written; from the `/plans` browser this is itself an approval. |
 | **Cancel** / **Back** | `esc` | Ends the review. In plan mode the plan stays saved and you keep refining; from the browser it returns to the list. |
 
@@ -253,4 +279,5 @@ Because a canceled plan is recorded rather than discarded, planning never feels
 
 - [Permissions](./permissions.md): the rule syntax and decision model behind every mode.
 - [Checkpoints](./sessions.md): rewind after an approved plan is implemented.
+- [Planning and implementation models](https://commandcode.ai/docs/settings#planning-and-implementation-models): the full rules for the per-phase models.
 - [Tools](./tools.md) and [Slash Commands](./custom-slash-commands.md): the full references.

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

@@ -335,8 +335,6 @@ Valid model ids (the /model catalog — use these EXACT ids):
 - poolside/laguna-s-2.1-free
 - inclusionai/ling-3.0-flash-sante:free
 - inclusionai/ling-3.1-flash:free
-- stealth/space-bunny-alpha
-- stealth/pixel-canary
 A BYO-provider id (from a configured custom provider) also works and is passed through as-is.
 
 WHEN THE USER ASKS YOU TO CREATE AN AGENT (e.g. "make a changelog agent with a cheap model"):