command-code 1.82.0 → 1.82.2

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # command-code
 
+## 1.82.2
+
+### Patch Changes
+
+- feat: retire ling 3.1 flash free
+- feat: Add todo checklist as a built-in mod, disabled by default
+
+## 1.82.1
+
+### Patch Changes
+
+- refactor: remove language selection from CLI onboarding
+
 ## 1.82.0
 
 ### Minor Changes

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

@@ -61,7 +61,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 | `/plans [name]`                      | Browse, review, and annotate saved plans; bare `/plans` opens the browser          |
 | `/plan-review`                       | Open this session's latest plan in review                                          |
 | `/goal <objective>\|clear\|status`   | Set an objective for the agent to work towards autonomously                        |
-| `/todos`                             | Manage the session todo list - `c` completes the selected item, `x` removes it, `a` clears the list |
+| `/todos`                             | Manage the session todo list (needs the `todos` mod: `cmd mods enable todos`)      |
 | `/review [pr-number]`                | Review a pull request                                                              |
 | `/pr-comments`                       | Fetch all PR comments for current branch                                           |
 
@@ -151,7 +151,7 @@ Most commands are **blocked mid-turn** - mode flips, session switches, model cha
 - `/trace` - capture the live trace id of the running turn (its main purpose)
 - `/session-file` - read-only session facts
 - `/copy` - clipboard only
-- `/todos` (also `ctrl+x`) - edits local todo state, most useful mid-turn while a plan is being driven
+- `/todos` (also `ctrl+x`) - edits local todo state, most useful mid-turn while a plan is being driven (needs the `todos` mod enabled)
 - `/exit` / `/quit` - always available
 - `/goal clear` - stops the goal loop; the current step finishes, then the loop stops. Setting a **new** goal mid-turn is refused with a busy notice.
 

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

@@ -100,7 +100,7 @@ cmd -p "..." --tools-all
 CMD_TOOLS_ALL_ENABLE=true cmd -p "..."
 
 # Only enable the ones you name (comma-separated, repeatable)
-cmd -p "..." --tools-enable ask_user_question,todo_write
+cmd -p "..." --tools-enable ask_user_question
 CMD_TOOLS_ASK_USER_QUESTION_ENABLE=true cmd -p "..."
 ```
 

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

@@ -55,7 +55,7 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
 | `thinkingmachines/inkling-small` | Inkling Small | 1M | — | $0.5/$1.2 · cache $0.1 | Go and above | lightweight MoE reasoning at lower cost and latency |
 | `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 |
+| `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 |
 | `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
 

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

@@ -54,7 +54,7 @@
 - /export [path]: Export session — /export [html|jsonl|md] or a file path
 - /changelog: See what's new in Command Code
 - /hotkeys: Show all keyboard shortcuts
-- /todos: Manage the session todo list — x to remove an item, c to clear
+- /todos: Manage the session todo list — c completes an item, x removes it, a completes all (needs the `todos` mod: `cmd mods enable todos`)
 - /loop [interval] [task]: Re-run a task on fixed intervals, or let the agent pace itself
 - /rc: Remote-control this session from Telegram or Discord
 - /plan [task]: Enter plan mode; `/plan <task>` plans that task
@@ -342,7 +342,7 @@ Valid model ids (the /model catalog — use these EXACT ids):
 - nvidia/nemotron-3-ultra-550b-a55b
 - poolside/laguna-s-2.1-free
 - inclusionai/ling-3.0-flash-sante:free
-- inclusionai/ling-3.1-flash:free
+- inclusionai/ling-3.1-flash
 - stealth/glyph-cluster:free
 A BYO-provider id (from a configured custom provider) also works and is passed through as-is.
 

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

@@ -228,8 +228,29 @@ Resolves ports to pids via `lsof` (or `Get-NetTCPConnection` on Windows), reconc
 
 ## Work state & task management
 
+### `task_create` / `task_update` / `task_list` / `task_get`
+
+A durable, dependency-aware task ledger for coordination-heavy work - tasks persist across restarts with stable ids, three states, owners, metadata, and `blockedBy`/`blocks` edges.
+
+- **`task_create`** - `subject` (required), `description` (required), `activeForm`, `blockedBy`, `blocks`, `metadata`.
+- **`task_update`** - `taskId` (required), `status` (`pending` | `in_progress` | `completed` | `deleted`), `subject`, `description`, `activeForm`, `owner`, `metadata` (merge; null deletes a key), `addBlockedBy` / `addBlocks` / `removeBlockedBy` / `removeBlocks`. Completing a task reports which tasks it unblocked.
+- **`task_list`** - optional `status` filter; shows unresolved blockers and a tally.
+- **`task_get`** - `taskId` (required); full detail.
+
+All four are plan-safe - capturing a plan as tasks *is* planning.
+
+### `task_output` (alias)
+
+Retired into `shell_output`. Calls to this name still work: they run as `shell_output` with `wait: "exit"` carried, so "block until the task settles" keeps its meaning. Use `shell_output` directly in new work.
+
+### `task_stop`
+
+Stop a tracked background task by `taskId`. Signals the whole process group, flips the registry state, and distinguishes "unknown id" from "already finished."
+
 ### `todo_write`
 
+Provided by the opt-in `todos` built-in mod, which is **disabled by default** - enable it with `cmd mods enable todos` (`-g` for user scope) and it appears on the next session or `/reload`. While the mod is disabled the model never sees this tool.
+
 The session checklist - the same list you manage with `/todos` and see in the TODOS panel.
 
 | Parameter | Type | Required | Description |
@@ -286,25 +307,6 @@ A single edit in a single place. The agent makes it.
 
 One command, immediate result. A checklist around it adds a panel and no information.
 
-### `task_create` / `task_update` / `task_list` / `task_get`
-
-A durable, dependency-aware task ledger for coordination-heavy work - tasks persist across restarts with stable ids, three states, owners, metadata, and `blockedBy`/`blocks` edges.
-
-- **`task_create`** - `subject` (required), `description` (required), `activeForm`, `blockedBy`, `blocks`, `metadata`.
-- **`task_update`** - `taskId` (required), `status` (`pending` | `in_progress` | `completed` | `deleted`), `subject`, `description`, `activeForm`, `owner`, `metadata` (merge; null deletes a key), `addBlockedBy` / `addBlocks` / `removeBlockedBy` / `removeBlocks`. Completing a task reports which tasks it unblocked.
-- **`task_list`** - optional `status` filter; shows unresolved blockers and a tally.
-- **`task_get`** - `taskId` (required); full detail.
-
-All four are plan-safe - capturing a plan as tasks *is* planning.
-
-### `task_output` (alias)
-
-Retired into `shell_output`. Calls to this name still work: they run as `shell_output` with `wait: "exit"` carried, so "block until the task settles" keeps its meaning. Use `shell_output` directly in new work.
-
-### `task_stop`
-
-Stop a tracked background task by `taskId`. Signals the whole process group, flips the registry state, and distinguishes "unknown id" from "already finished."
-
 ---
 
 ## Scheduling & waiting

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

@@ -188,10 +188,10 @@ Command Code's own features ride this exact API. First-party providers (`provide
 {"mods": {"disabled": ["provider-copilot", "update-notice", "titling", "learning"]}}
 ```
 
-A built-in can also ship **opt-in** - off by default; `cmd mods list --builtin` marks it `off by default`. Enable mods with `cmd mods enable <name>` (project level; `-g` for the user level), which adds it to the `enabled` key in the settings file:
+Some built-ins are **opt-in** and are disabled by default; `cmd mods list --builtin` marks them `disabled by default`. The session todo checklist (`todo_write`, the TODOS panel, `/todos`, `ctrl+x`) is the `todos` mod: enable it with `cmd mods enable todos` (project level; `-g` for the user level), which adds it to the `enabled` key in the settings file:
 
 ```json
-{"mods": {"enabled": ["<name>"]}}
+{"mods": {"enabled": ["todos"]}}
 ```
 
 `cmd mods disable <name>` disables the mod. A disable in any settings file wins and keeps the mod disabled. The change takes effect on the next session or `/reload`; see [Enable/Disable a mod](https://commandcode.ai/docs/mods#enabledisable-a-mod).

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

@@ -119,10 +119,10 @@ cmd mods disable review-guard        # disable in this project
 cmd mods enable review-guard -g      # enable at the user level
 ```
 
-They work for discovered files, installed packages, and the disable-able built-ins (`provider-copilot`, `update-notice`, `titling`, `learning` etc). The `cmd mods disable` command adds the name to `mods.disabled`; `cmd mods enable` removes it from there and, for an opt-in built-in, adds it to `mods.enabled`:
+They work for discovered files, installed packages, and the disable-able built-ins (`provider-copilot`, `update-notice`, `titling`, `learning` etc). The `cmd mods disable` command adds the name to `mods.disabled`; `cmd mods enable` removes it from there and, for an opt-in built-in such as `todos`, adds it to `mods.enabled`:
 
 ```json
-{"mods": {"disabled": ["review-guard"], "enabled": ["<opt-in-built-in>"]}}
+{"mods": {"disabled": ["review-guard"], "enabled": ["todos"]}}
 ```
 
 Disabling a mod anywhere will keep a mod disabled. Command Code reads the user, project, and project-local (`.commandcode/settings.local.json`) settings file, and a `mods.disabled` entry in any of them keeps the mod off, even when another file enables it. So when another settings file still disables the mod you enable, the command does not report success: it names that file, gives the one fix, and exits 1 so a script's `&&` chain stops:
@@ -136,7 +136,7 @@ $ cmd mods enable review-guard
 
 A disable in `settings.local.json` has to be removed by hand; no command writes to that file.
 
-**A project you have not used yet:** Project settings are read only once Command Code has run in that project, the same gate project mods follow. Enabling or disabling there still saves the setting, which applies once you start Command Code in the project; use `-g` to apply it at the user level right away.
+**A project you have not used yet:** Project settings are read only once Command Code has run in that project, the same gate project mods follow. Enabling or disabling there still saves the setting, which applies once you start Command Code in the project; use `-g` to apply it at the user level right away. `cmd mods list --builtin` marks a built-in whose state changes then, for example `enabled · disabled once you start Command Code here`.
 
 ## Trust and safety