command-code 1.47.0 → 1.47.1

package/CHANGELOG.md

@@ -1,8 +1,15 @@
 # command-code
 
+## 1.47.1
+
+### Patch Changes
+
+- feat: improve provider/model config handling
+
 ## 1.47.0
 
 - fix: mark Grok 4.6 as vision-capable
+- feat: read_file reads Word, PowerPoint, Excel, OpenDocument, RTF, EPUB and PDF files as Markdown, windowed like text, in single and multi-file reads; a scanned PDF names its image-only pages and the pdftoppm command to render them. The converter installs into the user cache on the first document read instead of shipping with the CLI.
 
 ## 1.46.0
 
@@ -10,7 +17,6 @@
 
 - feat: auto compact improvements
 - feat: Add browser sign in through local callback server
-- feat: read_file now reads documents. Word, PowerPoint, Excel, OpenDocument, RTF, EPUB and PDF files are extracted to Markdown.
 
 ## 1.45.0
 

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

@@ -6,7 +6,7 @@ BYOK is currently in beta and subject to improvements.
 
 Bring your own provider and use it in Command Code CLI. Any OpenAI or Anthropic compactible API can serve models in Command Code. You can bring your key from hosted providers (DeepSeek, OpenRouter, Vercel AI Gateway), local servers (Ollama, vLLM), or other coding agent's APIs.
 
-## BYOK Providers
+## BYOK providers
 
 You can connect to any external provider in Command Code, requests go straight from your machine to that provider's endpoint with your key, never through Command Code's servers.
 
@@ -286,7 +286,7 @@ or persist it in `~/.commandcode/config.json`:
 
 What it guarantees:
 
-- **No telemetry, anywhere.** Trace exporters, lifecycle events, telemetry identity, and machine fingerprinting are all off. (`DO_NOT_TRACK=1` also stops all of these, including fingerprinting; local-only additionally blocks the non-telemetry backend traffic below.)
+- **No telemetry, anywhere.** Trace exporters, lifecycle events, telemetry identity, and machine fingerprinting are all off. (`DO_NOT_TRACK=1` also stops all of these, including fingerprinting; local-only also blocks the non-telemetry backend traffic below.)
 - **No billing reads.** The plan/credits prefetches never run; model pickers treat the absent plan as unrestricted and your providers gate access themselves.
 - **A refusal transport.** The session's backend transport is replaced with one that throws a clear `LocalOnlyError` naming the route and the switch. Nothing can reach Command Code including a model id that would otherwise fall through to the Command Code provider.
 

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

@@ -16,7 +16,7 @@ Type `/` at the start of the input to open the command menu:
 
 ---
 
-## Built-in Commands
+## Built-in commands
 
 Every built-in command, grouped by area. Aliases are shown in parentheses on the canonical command; optional arguments in `[brackets]`, alternatives separated by `|`.
 
@@ -39,7 +39,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 | `/exit` (`/quit`)              | Exit Command Code                                                                                     |
 | `/reload`                      | Restart Command Code and resume this session (applies a staged update)                                |
 
-### Context & Compaction
+### Context & compaction
 
 | **Command**     | **Description**                              |
 | --------------- | -------------------------------------------- |
@@ -49,7 +49,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 | `/memory`       | Manage Command Code memory                   |
 | `/init`         | Initialize AGENTS.md for this project        |
 
-### Modes & Planning
+### Modes & planning
 
 | **Command**                          | **Description**                                                                    |
 | ------------------------------------ | ---------------------------------------------------------------------------------- |
@@ -71,7 +71,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 	reachable through the explicit `--yolo` launch flag, which also adds it to
 	the shift+tab mode cycle.
 
-### Models & Providers
+### Models & providers
 
 | **Command**       | **Description**                                                                          |
 | ----------------- | ---------------------------------------------------------------------------------------- |
@@ -81,7 +81,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 | `/login`          | Log in to Command Code or a provider                                                     |
 | `/logout`         | Log out of Command Code or a provider                                                    |
 
-### Extensibility & Integrations
+### Extensibility & integrations
 
 | **Command**                                        | **Description**                                                                   |
 | -------------------------------------------------- | --------------------------------------------------------------------------------- |
@@ -102,7 +102,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 | `/add-dir <directory>`                     | Add directory to workspace context                 |
 | `/worktree [name\|list\|remove <name>]`    | Create, list, or switch git worktrees              |
 
-### Billing & Account
+### Billing & account
 
 | **Command** | **Description**                              |
 | ----------- | -------------------------------------------- |
@@ -122,7 +122,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 | `/changelog [all]` | See what's new in Command Code (`all` for the full history)    |
 | `/learn`           | Open the Command Code learn hub in your browser                |
 | `/update`          | Update Command Code to the latest version                      |
-| `/feedback [title]` (alias `/issue`) | Report a bug or share feedback — opens a prefilled GitHub issue |
+| `/feedback [title]` (alias `/issue`) | Report a bug or share feedback; opens a prefilled GitHub issue |
 | `/trace`           | Copy the current trace id; required for support debugging      |
 | `/copy`            | Copy the last response to the clipboard                        |
 
@@ -136,7 +136,7 @@ Every built-in command, grouped by area. Aliases are shown in parentheses on the
 
 `/effort` only opens its selector when the current model supports reasoning effort levels; otherwise it prints a notice that effort isn't supported for that model.
 
-`/theme` offers three values. `dark` and `light` pin a palette; `auto` — the default — automatically detects your terminal's background color at startup (OSC 11, falling back to `COLORFGBG`) and uses light or dark to match. A terminal that won't report its background falls back to dark.
+`/theme` offers three values. `dark` and `light` pin a palette; `auto`, the default, automatically detects your terminal's background color at startup (OSC 11, falling back to `COLORFGBG`) and uses light or dark to match. A terminal that won't report its background falls back to dark.
 
 ### Commands with meaningful default actions when bare
 
@@ -161,7 +161,7 @@ Most other commands - `/clear`, `/mode`, `/plan`, `/model`, `/compact`, `/worktr
 
 ---
 
-## Custom Slash Commands
+## Custom slash commands
 
 Custom slash commands let you save frequently used prompts as markdown files. Define a command once, then run it anytime with dynamic arguments.
 

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

@@ -18,7 +18,7 @@ Run Command Code non-interactively in scripts, CI/CD pipelines, and automation w
 
 ---
 
-## Basic Usage
+## Basic usage
 
 Use the `-p` (or `--print`) flag to run in headless mode:
 
@@ -30,9 +30,9 @@ Always wrap your query in quotes. Unquoted multi-word queries cause argument par
 
 ---
 
-## Input Methods
+## Input methods
 
-### Direct Argument
+### Direct argument
 
 Pass your query directly after the `-p` flag:
 
@@ -40,7 +40,7 @@ Pass your query directly after the `-p` flag:
 cmd -p "refactor the auth module"
 ```
 
-### Piped Stdin
+### Piped stdin
 
 Pipe input from another command or file:
 
@@ -80,10 +80,10 @@ Only use `--yolo` in trusted environments. It allows Command Code to modify file
 
 **Permissions**
 	Headless runs still go through the permission engine. The complete guide
-	covers `dont-ask` — the fail-closed allowlist mode built for CI — plus rule
+	covers `dont-ask`, the fail-closed allowlist mode built for CI, plus rule
 	syntax and the decision ladder.
 
-## Tool Calls
+## Tool calls
 
 Headless mode supports multi-turn tool execution. Command Code can read files, search code, and (with permissions) edit files and run commands, just like [interactive mode](https://commandcode.ai/docs/interactive-mode).
 
@@ -146,7 +146,7 @@ Parse line by line rather than buffering the whole stream. The event list grows
 
 ---
 
-## Sessions & Resuming
+## Sessions & resuming
 
 Each headless run persists its transcript to disk, so you can chain follow-up queries that keep prior context. Headless sessions are tagged separately and stay **hidden** from the interactive `/resume` menu and from interactive `--continue` - automation never pollutes your interactive history.
 
@@ -187,7 +187,7 @@ cmd --resume 9f4e1c0a-...
 
 ---
 
-## Exit Codes
+## Exit codes
 
 Use exit codes to handle results in scripts and CI/CD:
 
@@ -217,7 +217,7 @@ fi
 
 ---
 
-## Shell Script
+## Shell script
 
 ```bash
 #!/bin/bash
@@ -228,7 +228,7 @@ CHANGED=$(git diff --name-only HEAD~1)
 echo "Document these changed files: $CHANGED" | cmd -p --skip-onboarding
 ```
 
-## Piping Output
+## Piping output
 
 Headless mode is pipe-friendly. Output goes to stdout, errors and warnings go to stderr:
 
@@ -245,7 +245,7 @@ SUMMARY=$(cmd -p "summarize this codebase in one paragraph")
 
 ---
 
-## Related Flags
+## Related flags
 
 Flags useful for headless and automated workflows:
 
@@ -257,7 +257,7 @@ Flags useful for headless and automated workflows:
 | `-r, --resume <id>` | Resume a specific headless session by id (no bare picker in print mode) |
 | `--verbose` | Print the resolved session id to stderr (for chaining `--resume`) |
 | `--max-turns <number>` | Maximum conversation turns in print mode (default: `100`, no upper bound) |
-| `--tools-all` | Enable every tool, including the ones headless runs disable - see [Tool Calls](#tool-calls) |
+| `--tools-all` | Enable every tool, including the ones headless runs disable - see [Tool calls](#tool-calls) |
 | `--tools-enable <names>` | Enable specific withheld tools by name (comma-separated, repeatable) |
 | `-m, --model <model>` | Run on a specific model this session |
 | `--effort <level>` | Set reasoning effort (`low`, `medium`, `high`, …) |

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

@@ -440,12 +440,12 @@ Use this to pick the right field for the audience you want to reach.
 
 | **Field** | **User (TUI)** | **Model** |
 | --------- | :------------: | :-------: |
-| `stopReason` | ✓ | - |
-| `systemMessage` | ✓ | - |
-| `permissionDecisionReason` (Pre) | ✓ | ✓ (when denying) |
-| `reason` (Post / Stop) | ✓ | ✓ (Post & Stop when `decision: "block"`; an `exit 2` retry feeds stderr instead) |
-| `additionalContext` | - | ✓ (appended before next turn) |
-| `stderr` (exit 2) | ✓ first line | ✓ (full text fed to model on retry, all events) |
+| `stopReason` |  |  |
+| `systemMessage` |  |  |
+| `permissionDecisionReason` (Pre) |  |  |
+| `reason` (Post / Stop) |  |  (Post & Stop when `decision: "block"`; an `exit 2` retry feeds stderr instead) |
+| `additionalContext` |  |  |
+| `stderr` (exit 2) |  |  (full text fed to model on retry, all events) |
 
 Rule of thumb: for machine-style detail the model should act on verbatim, use `exit 2` + stderr. For natural-language revision guidance, use Stop's `reason`. For a user-only notice, use `systemMessage` or `stopReason`.
 
@@ -680,7 +680,7 @@ Try to run this shell command: rm -rf /tmp/cmd-hook-demo
 
 Expected result:
 
-- ❌ The command is blocked before it runs (it matches the `rm -rf /` pattern, even though the target is harmless).
+-  The command is blocked before it runs (it matches the `rm -rf /` pattern, even though the target is harmless).
 - The agent sees *"Command matched a dangerous pattern. Policy forbids…"* and moves on without retrying.
 
 **How it works**
@@ -746,7 +746,7 @@ Read the .env file in my home directory
 
 Expected result:
 
-- ✅ The read is allowed. The hook never blocks it.
+-  The read is allowed. The hook never blocks it.
 - The agent receives the injected note *"SENSITIVE READ: …/.env. Redact any keys or tokens before quoting from this file."* and refuses to paste the full contents.
 
 **How it works**
@@ -811,7 +811,7 @@ Create a new file called config.txt with some test data
 
 Expected result:
 
-- ✅ The file is created.
+-  The file is created.
 - The hook appends one line to `.commandcode/write-audit.log`.
 - Verify with `cat .commandcode/write-audit.log`. You should see a tab-separated line (timestamp, session ID, file path).
 
@@ -866,7 +866,7 @@ Then tell me you're done.
 
 Expected result:
 
-- ✅ The command runs as normal.
+-  The command runs as normal.
 - The hook appends one line to `/tmp/cmd-shell.log`.
 - Verify with `cat /tmp/cmd-shell.log`. Each entry in `/tmp/cmd-shell.log` has the shape (fields are tab-separated):
 
@@ -936,7 +936,7 @@ Then tell me you're done.
 
 Expected result: the turn is blocked, the agent retries on its own, and it finishes once the marker is gone. Step by step:
 
-- ❌ **First turn:** the assistant finishes → the hook greps → finds the `DO NOT SHIP` marker → exits `2` with the matching lines on stderr. A gray Stop frame appears in the feed:
+-  **First turn:** the assistant finishes → the hook greps → finds the `DO NOT SHIP` marker → exits `2` with the matching lines on stderr. A gray Stop frame appears in the feed:
 
 ```text
   Ran 1 stop hook
@@ -944,7 +944,7 @@ Expected result: the turn is blocked, the agent retries on its own, and it finis
 ```
 
 - The engine feeds that stderr text back to the model as a user-role message and re-runs the turn.
-- ✅ **Second turn:** the assistant removes the marker and adds error handling. The hook fires again with `stop_hook_active: true` → exits `0`. The turn ends.
+-  **Second turn:** the assistant removes the marker and adds error handling. The hook fires again with `stop_hook_active: true` → exits `0`. The turn ends.
 
 If the hook keeps blocking (e.g. it's broken), the engine caps retries at 3 and ends the turn with `Stop hook retry cap reached (3). Ending turn. Same outcome ×4. Fix or disable: ./.commandcode/hooks/no-ship-gate.sh`.
 
@@ -1027,7 +1027,7 @@ Hooks are the right tool when you need **deterministic, out-of-model enforcement
 
 ### Writing safe hooks
 
-- **Parse stdin with `jq -r`, never `eval`:** Everything in `tool_input` came from the model and should be treated as untrusted.
+- **Parse stdin with `jq -r`, never `eval`.** Everything in `tool_input` came from the model and should be treated as untrusted.
 - **Quote every variable** before passing it to shell. The [`deny-dangerous.sh`](#block-dangerous-bash-commands) example uses `grep -qE` on a quoted `printf`, never `eval $cmd`.
 - **Keep `timeout` tight** (10 seconds or less for sync hooks). A slow hook blocks the tool call and makes Command Code feel laggy.
 - **Prefer `additionalContext` over `systemMessage`** when guiding the model, and `systemMessage` when explaining a policy violation to the user.
@@ -1085,9 +1085,9 @@ The log file only exists while `--debug` is active and appends across sessions,
 
 Hooks fire on **every** matching tool call. A slow hook means added latency on every matching tool call.
 
-- **Keep hooks fast:** Well under a second. Users notice lag immediately.
-- **Push slow work to `PostToolUse`:** It runs after the tool completes and in parallel, so slowness there doesn't block the agent.
-- **Move truly slow work out of process:** If you need to talk to a SIEM or policy server, send a fire-and-forget HTTP request or append to a local log. Don't block on the round trip.
+- **Keep hooks fast.** Well under a second. Users notice lag immediately.
+- **Push slow work to `PostToolUse`.** It runs after the tool completes and in parallel, so slowness there doesn't block the agent.
+- **Move truly slow work out of process.** If you need to talk to a SIEM or policy server, send a fire-and-forget HTTP request or append to a local log. Don't block on the round trip.
 
 ---
 

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

@@ -2,7 +2,7 @@
 
 # Memory
 
-Memory is the instructions Command Code carries into every turn without you repeating them — conventions, architecture notes, the commands your project actually uses. It lives in plain markdown files named `AGENTS.md`.
+Memory is the instructions Command Code carries into every turn without you repeating them: conventions, architecture notes, the commands your project actually uses. It lives in plain markdown files named `AGENTS.md`.
 
 ---
 
@@ -45,15 +45,15 @@ to it deserve review like any other project convention.
 
 ## Where memory files live
 
-Command Code reads **three tiers**, and every one that exists is loaded — they add up, they don't replace each other.
+Command Code reads **three tiers**, and every one that exists is loaded; they add up, they don't replace each other.
 
 | Tier | Location | Use it for |
 | ---- | -------- | ---------- |
 | **User** | `~/.commandcode/AGENTS.md` | Your personal preferences, across every project |
-| **Project** | `<project>/AGENTS.md` or `<project>/.commandcode/AGENTS.md` | Team-shared project instructions — commit this |
+| **Project** | `<project>/AGENTS.md` or `<project>/.commandcode/AGENTS.md` | Team-shared project instructions; commit this |
 | **Subdirectory** | `<subdir>/AGENTS.md` or `<subdir>/.commandcode/AGENTS.md` | Rules for one package or area of a monorepo |
 
-They're assembled in that order — user, project, then subdirectory — each block headed by its source path, so the model always knows which file a rule came from. Later blocks are more specific, so a package-level convention naturally reads as a refinement of the project-level one.
+They're assembled in that order (user, project, then subdirectory), each block headed by its source path, so the model always knows which file a rule came from. Later blocks are more specific, so a package-level convention naturally reads as a refinement of the project-level one.
 
 Command Code reads `AGENTS.md`, not `CLAUDE.md`. If you're coming from another
 agent, [`/import`](https://commandcode.ai/docs/import) brings your memory files over and
@@ -61,7 +61,7 @@ rewrites references to point at the right filename.
 
 ### Project memory
 
-Both `<project>/AGENTS.md` and `<project>/.commandcode/AGENTS.md` are checked, in that order — the **first one that exists** is used, not both. Put it at the repo root if you want it visible; put it in `.commandcode/` if you'd rather keep the root clean.
+Both `<project>/AGENTS.md` and `<project>/.commandcode/AGENTS.md` are checked, in that order; the **first one that exists** is used, not both. Put it at the repo root if you want it visible; put it in `.commandcode/` if you'd rather keep the root clean.
 
 ### Subdirectory memory
 
@@ -76,7 +76,7 @@ repo/
         └── server.ts     a file in this directory
 ```
 
-Only directories **inside** your project count — a sibling tree that happens to share a path prefix is never pulled in.
+Only directories **inside** your project count; a sibling tree that happens to share a path prefix is never pulled in.
 
 ---
 
@@ -102,9 +102,9 @@ Personal shell aliases: @~/.commandcode/shell-notes.md
 
 Memory is part of the **system prompt**, not the conversation. That has a few consequences worth knowing:
 
-- **It's re-read every request.** Edit `AGENTS.md` mid-session and the next turn picks it up — no restart needed. `/context` flags the row as *(modified, refreshes next request)* until then.
+- **It's re-read every request.** Edit `AGENTS.md` mid-session and the next turn picks it up, no restart needed. `/context` flags the row as *(modified, refreshes next request)* until then.
 - **It survives compaction.** Because it isn't conversation, it's never summarized away. See [Context & Compaction](https://commandcode.ai/docs/context).
-- **It costs tokens on every turn.** `/context` shows exactly how many under the **Memory** row. A memory file that has grown into a wiki is a real, recurring cost — keep it to standing rules, and use `@path` imports for the long-form material so it's only there when it's relevant.
+- **It costs tokens on every turn.** `/context` shows exactly how many under the **Memory** row. A memory file that has grown into a wiki is a real, recurring cost. Keep it to standing rules, and use `@path` imports for the long-form material so it's only there when it's relevant.
 
 ---
 
@@ -131,7 +131,7 @@ Memory is part of the **system prompt**, not the conversation. That has a few co
 
 ## See also
 
-- [Taste](https://commandcode.ai/docs/taste) — learned style, as opposed to written rules.
-- [Skills](./skills.md) — instructions that load only when a task calls for them.
-- [Context & Compaction](https://commandcode.ai/docs/context) — what memory costs per request.
-- [Import](https://commandcode.ai/docs/import) — bring memory files from another agent.
+- [Taste](https://commandcode.ai/docs/taste): learned style, as opposed to written rules.
+- [Skills](./skills.md): instructions that load only when a task calls for them.
+- [Context & Compaction](https://commandcode.ai/docs/context): what memory costs per request.
+- [Import](https://commandcode.ai/docs/import): bring memory files from another agent.

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

@@ -240,8 +240,8 @@ Command Code parses shell operators, so `Shell(git status)` does **not** grant `
 
 The lists are matched differently on purpose - failing toward a prompt is the safe direction:
 
-- **Deny and ask match aggressively:** they see through leading env vars (`FOO=bar rm -rf x` matches `Shell(rm *)`), process wrappers (`timeout 30 …`, `nice …`), and every subcommand; an unparseable command is matched against the raw string; path matching folds case (on macOS/Windows `.ENV` opens `.env`) and fires when either the path or its symlink target matches.
-- **Allow matches conservatively:** no env stripping (`PATH=/tmp git status` does **not** match `Shell(git status:*)`); a compound command allows only when *every* subcommand matches; an unparseable command never auto-allows; path matching is case-exact and needs **both** the path and its symlink target to match.
+- **Deny and ask match aggressively.** They see through leading env vars (`FOO=bar rm -rf x` matches `Shell(rm *)`), process wrappers (`timeout 30 …`, `nice …`), and every subcommand; an unparseable command is matched against the raw string; path matching folds case (on macOS/Windows `.ENV` opens `.env`) and fires when either the path or its symlink target matches.
+- **Allow matches conservatively.** No env stripping (`PATH=/tmp git status` does **not** match `Shell(git status:*)`); a compound command allows only when *every* subcommand matches; an unparseable command never auto-allows; path matching is case-exact and needs **both** the path and its symlink target to match.
 
 ### MCP and sub-agents
 
@@ -347,7 +347,7 @@ Every tool call falls through one fixed ladder. First rung that matches wins:
        ASK   (DENY in dont-ask)
 ```
 
-Read that top to bottom and two things fall out. **Deny beats ask beats allow**, in every mode. And `bypass` sits at rung 9 — *after* your rules, the external-directory gate, and the circuit breaker — so `--yolo` skips ordinary prompts and the sensitive-write prompt, but never your explicit rules and never the root/home breaker.
+Read that top to bottom and two things fall out. **Deny beats ask beats allow**, in every mode. And `bypass` sits at rung 9, *after* your rules, the external-directory gate, and the circuit breaker, so `--yolo` skips ordinary prompts and the sensitive-write prompt, but never your explicit rules and never the root/home breaker.
 
 The long form of each rung:
 
@@ -468,10 +468,10 @@ The reasoning behind the behavior, so you don't reverse-engineer it:
 Documented edges of the current engine:
 
 - **Wildcard patterns in a multi-file `read_file` call expand inside the tool**, so an exact-file deny rule (`Read(.env)`) can't match a wildcard entry (`*.env`) before expansion. Directory-tree rules (`Read(//etc/**)`) still cover this, because the call's `target_directory` (or the first absolute entry) is matched as a touched path.
-- **No strict read allowlist:** `allow: ["Read(src/**)"]` doesn't deny reads outside `src/**` - reads are free by default; only `ask`/`deny` restrict them. A deny-everything-not-listed read mode is out of scope as a separate change.
-- **Shell path args aren't external-dir gated:** `cat /outside/file` follows shell rules and the mode, not the workspace boundary. Gate it with `deny: ["Shell(cat /outside/*)"]`-style rules.
-- **An allow rule never matches an opaque command:** if the parser can't fully understand a command, it can still be deny/ask-matched against the raw string, but never auto-allows - it prompts.
-- **Parameter rules only see parameters the model sends:** an omitted parameter never matches.
+- **No strict read allowlist.** `allow: ["Read(src/**)"]` doesn't deny reads outside `src/**` - reads are free by default; only `ask`/`deny` restrict them. A deny-everything-not-listed read mode is out of scope as a separate change.
+- **Shell path args aren't external-dir gated.** `cat /outside/file` follows shell rules and the mode, not the workspace boundary. Gate it with `deny: ["Shell(cat /outside/*)"]`-style rules.
+- **An allow rule never matches an opaque command.** If the parser can't fully understand a command, it can still be deny/ask-matched against the raw string, but never auto-allows - it prompts.
+- **Parameter rules only see parameters the model sends.** An omitted parameter never matches.
 
 ---
 

package/dist/bundled/command-code-knowledge/reference/plan-mode.md

@@ -2,7 +2,7 @@
 
 # Plan Mode
 
-Plan mode is where the agent thinks before it touches anything. It explores read-only, writes a plan, and hands it to you in a review surface. You comment, it revises, you approve — then implementation starts.
+Plan mode is where the agent thinks before it touches anything. It explores read-only, writes a plan, and hands it to you in a review surface. You comment, it revises, you approve, then implementation starts.
 
 ---
 
@@ -15,13 +15,13 @@ Plan mode is where the agent thinks before it touches anything. It explores read
 
 Or press `shift+tab` until the banner reads **plan**, or launch with `cmd --plan`.
 
-In plan mode the agent can read files, search, and reason. It **cannot** edit files, run shell commands, or apply patches. When it's done it writes the plan to `~/.commandcode/plans/<name>.md` and opens **plan review** — a GitHub-style reader where one line is always selected, you leave inline comments, and you resolve with a verb:
+In plan mode the agent can read files, search, and reason. It **cannot** edit files, run shell commands, or apply patches. When it's done it writes the plan to `~/.commandcode/plans/<name>.md` and opens **plan review**, a GitHub-style reader where one line is always selected, you leave inline comments, and you resolve with a verb:
 
 | Key | Verb |
 | --- | ---- |
-| `ctrl+r` | **Submit review** — send your comments back; the agent revises the plan |
-| `ctrl+a` | **Approve** — start implementing |
-| `esc` | **Cancel** — the plan stays saved; reopen it with `/plans` |
+| `ctrl+r` | **Submit review**: send your comments back; the agent revises the plan |
+| `ctrl+a` | **Approve**: start implementing |
+| `esc` | **Cancel**: the plan stays saved; reopen it with `/plans` |
 
 ---
 
@@ -32,7 +32,7 @@ Plan mode is one rung on the permission-mode cycle. `shift+tab` moves between th
 | Mode | File edits | Shell commands | Use it when |
 | ---- | ---------- | -------------- | ----------- |
 | **plan** | Blocked | Blocked | Exploring, designing, reviewing sensitive flows |
-| **default** | Prompt for approval | Prompt for approval | Controlled iteration — the everyday mode |
+| **default** | Prompt for approval | Prompt for approval | Controlled iteration, the everyday mode |
 | **auto-accept** | Applied directly | Run directly | The approach is clear and you're iterating fast |
 
 Two modes sit off the cycle. `dont-ask` is selected from settings or `--permission-mode dont-ask`, and `shift+tab` from it moves to `auto-accept` and rejoins the normal cycle. `bypass` is only reachable by launching with `--yolo`, which also adds it to the cycle as a fourth rung (`plan` → `bypass` → `default`).
@@ -69,12 +69,12 @@ The usual loop: start in **plan**, explore and agree on the approach, approve th
 
 ## 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.
+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.
 
-- **One mode: REVIEW.** Read line by line, comment on any line, resolve with a verb. There is no separate "edit mode" — plan edits go through your `$EDITOR`.
+- **One mode: REVIEW.** Read line by line, comment on any line, resolve with a verb. There is no separate "edit mode"; plan edits go through your `$EDITOR`.
 - **Plans persist.** Every plan is saved to `~/.commandcode/plans/` as markdown and indexed, so canceling a review never throws the plan away.
-- **Comments are review artifacts, not plan text.** They live in a sidecar overlay and only reach the agent inside a prompt — they are never written into the plan document.
-- **Review rounds.** When the agent revises a plan, the next round diffs against the last one — changed lines render green so you re-review only what moved.
+- **Comments are review artifacts, not plan text.** They live in a sidecar overlay and only reach the agent inside a prompt; they are never written into the plan document.
+- **Review rounds.** When the agent revises a plan, the next round diffs against the last one: changed lines render green so you re-review only what moved.
 - **Deterministic.** A harness backstop guarantees the review is offered even when a weaker model writes a plan and simply stops.
 
 ### How it works
@@ -131,16 +131,16 @@ Inside the reader one line is always selected, comments pin inline under their l
 
 All of these open the same surface, scoped to a plan written during the **current session**.
 
-1. **Finishing plan mode.** The agent writes the plan and calls `exit_plan_mode`, which opens plan review as the approval surface — the plan *is* the approval prompt. Approving here can also switch you into auto-accept mode so implementation runs without further prompts.
+1. **Finishing plan mode.** The agent writes the plan and calls `exit_plan_mode`, which opens plan review as the approval surface: the plan *is* the approval prompt. Approving here can also switch you into auto-accept mode so implementation runs without further prompts.
 2. **Asking for it.** Outside plan mode, say *"review plan"* / *"open plan review"*. The agent calls the `plan_review` tool, which opens the panel for the most recent plan file, instead of pasting the plan back as a wall of text.
 3. **`/plan-review`.** Jumps straight into a review of this session's latest plan.
-4. **`/plans`.** Opens the full-screen plan browser — every plan from this session and past sessions, with status badges, comment counts, and search. `/plans <name>` jumps straight into a named plan.
+4. **`/plans`.** Opens the full-screen plan browser: every plan from this session and past sessions, with status badges, comment counts, and search. `/plans <name>` jumps straight into a named plan.
 
-**The automatic backstop.** Some models write a plan file and stop without ever presenting it. When a run ends naturally with a plan that was written but never reviewed (in **default** or **plan** mode), the harness presents the review panel itself. Approving continues the run with an instruction to implement; declining lets the run end so you can steer. Modes that mean "don't interrupt me" — auto-accept, bypass, and dont-ask — skip the backstop.
+**The automatic backstop.** Some models write a plan file and stop without ever presenting it. When a run ends naturally with a plan that was written but never reviewed (in **default** or **plan** mode), the harness presents the review panel itself. Approving continues the run with an instruction to implement; declining lets the run end so you can steer. Modes that mean "don't interrupt me" (auto-accept, bypass, and dont-ask) skip the backstop.
 
 ### Reading and commenting
 
-The reader renders the plan like a document — headings, code, quotes, and tables styled per line. Long lines **wrap** at a comfortable reading width (80 columns when there's room, otherwise 60) rather than truncating.
+The reader renders the plan like a document: headings, code, quotes, and tables styled per line. Long lines **wrap** at a comfortable reading width (80 columns when there's room, otherwise 60) rather than truncating.
 
 **Navigating:**
 
@@ -149,9 +149,9 @@ The reader renders the plan like a document — headings, code, quotes, and tabl
 | `↑` / `↓` | Move one line; past the last line drops onto the review verbs |
 | `PgUp` / `PgDn` (`Fn+↑/↓` on Mac) | Page up/down one viewport, like `less` |
 | `Home` / `End` (`Fn+←/→` on Mac) | Jump to the first / last line |
-| `ctrl+n` / `ctrl+p` | Jump between marked lines — your comments, plus changed lines in a revised plan |
+| `ctrl+n` / `ctrl+p` | Jump between marked lines: your comments, plus changed lines in a revised plan |
 
-**Commenting** is Figma-style — start typing on a line and a draft box opens inline, directly under that line, exactly where it will sit once pinned.
+**Commenting** is Figma-style: start typing on a line and a draft box opens inline, directly under that line, exactly where it will sit once pinned.
 
 | Key | Action |
 |-----|--------|
@@ -175,7 +175,7 @@ Trigger a verb by chord from anywhere, or arrow onto it and press `Enter`.
 |------|-------|--------------|
 | **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. |
-| **Execute plan** *(browser surface)* | `ctrl+e` | Executes the plan as written — from the `/plans` browser this is itself an approval. |
+| **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. |
 
 If you press Approve with comments still pending, Command Code asks rather than guessing:
@@ -184,7 +184,7 @@ If you press Approve with comments still pending, Command Code asks rather than
 Approve  (•) with N comments as notes    ( ) original plan · discard comments
 ```
 
-**With comments as notes** sends them as a follow-up user turn — non-blocking notes the agent implements against. **Original plan** approves it clean and drops the comments. `←/→` switches, `Enter` confirms, `esc` backs out.
+**With comments as notes** sends them as a follow-up user turn: non-blocking notes the agent implements against. **Original plan** approves it clean and drops the comments. `←/→` switches, `Enter` confirms, `esc` backs out.
 
 ### Review rounds and versioning
 
@@ -194,7 +194,7 @@ Each time you **Submit review**, Command Code:
 2. Bumps the plan's version and clears your pending comments (they were all handed to the agent in one prompt).
 3. Lets the agent revise the plan, overwriting the live file.
 
-When the revised plan comes back (version > 1), the reader **diffs it against the previous round's snapshot**. Changed lines render **green**, and the badge line reports `round N · M lines changed` — so a second review means re-reading only what actually moved. `ctrl+n`/`ctrl+p` jump between those changed lines.
+When the revised plan comes back (version > 1), the reader **diffs it against the previous round's snapshot**. Changed lines render **green**, and the badge line reports `round N · M lines changed`, so a second review means re-reading only what actually moved. `ctrl+n`/`ctrl+p` jump between those changed lines.
 
 ---
 
@@ -208,11 +208,11 @@ When the revised plan comes back (version > 1), the reader **diffs it against th
 
 Every plan carries a status:
 
-- **pending** — written but not yet taken through review.
-- **approved** — you approved it and moved to implementation.
-- **not-implemented** — you canceled the review; the plan is kept for later reading, commenting, and revision.
+- **pending**: written but not yet taken through review.
+- **approved**: you approved it and moved to implementation.
+- **not-implemented**: you canceled the review; the plan is kept for later reading, commenting, and revision.
 
-Because a canceled plan is recorded rather than discarded, planning never feels throwaway — reopen it any time with `/plans`. Writes to `~/.commandcode/plans/*.md` never prompt for permission in any mode, and only `.md` files there get that exemption, so the plans directory can't double as a scratchpad.
+Because a canceled plan is recorded rather than discarded, planning never feels throwaway; reopen it any time with `/plans`. Writes to `~/.commandcode/plans/*.md` never prompt for permission in any mode, and only `.md` files there get that exemption, so the plans directory can't double as a scratchpad.
 
 ---
 
@@ -251,6 +251,6 @@ Because a canceled plan is recorded rather than discarded, planning never feels
 
 ## See also
 
-- [Permissions](./permissions.md) — the rule syntax and decision model behind every mode.
-- [Checkpoints](./sessions.md) — rewind after an approved plan is implemented.
-- [Tools](./tools.md) and [Slash Commands](./custom-slash-commands.md) — the full references.
+- [Permissions](./permissions.md): the rule syntax and decision model behind every mode.
+- [Checkpoints](./sessions.md): rewind after an approved plan is implemented.
+- [Tools](./tools.md) and [Slash Commands](./custom-slash-commands.md): the full references.