command-code 1.21.0 → 1.23.0

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # command-code
 
+## 1.23.0
+
+### Minor Changes
+
+- feat: Add Gemini 3.7 Flash
+
+## 1.22.0
+
+### Minor Changes
+
+- feat(tools): merge read_multiple_files into read_file #3580
+
 ## 1.21.0
 
 - feat: add grok 4.6

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

@@ -35,8 +35,8 @@ These ship with Command Code and are always available. They're read-only - you c
 | **Agent** | **When it runs** | **Tools** |
 | --------- | ---------------- | --------- |
 | **General** | The default when no other agent fits. Research and multi-step tasks. | All tools |
-| **Explore** | Codebase search and understanding that touches many files. | Read-only: `read_file`, `read_directory`, `read_multiple_files`, `grep` |
-| **Plan** | Designing an approach and weighing trade-offs. | `read_file`, `read_multiple_files` |
+| **Explore** | Codebase search and understanding that touches many files. | Read-only: `read_file`, `read_directory`, `grep` |
+| **Plan** | Designing an approach and weighing trade-offs. | `read_file` |
 
 When Command Code delegates without naming an agent, the task goes to **General**.
 
@@ -188,7 +188,7 @@ An agent is a Markdown file. The front matter configures it; the body is the sys
 ---
 name: code-reviewer
 description: Use after writing code to review a diff for bugs and security issues.
-tools: read_file, read_multiple_files, grep, glob
+tools: read_file, grep, glob
 model: claude-sonnet-5
 ---
 
@@ -255,7 +255,7 @@ Common ids by category:
 
 | **Category** | **Tool ids** |
 | ------------ | ------------ |
-| Read-only | `read_file`, `read_directory`, `read_multiple_files`, `grep` |
+| Read-only | `read_file`, `read_directory`, `grep` |
 | Edit | `edit_file`, `write_file` |
 | Execution | `shell_command`, `run_command`, `kill_shell` |
 | Search | `web_search`, `web_fetch` |

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

@@ -63,7 +63,8 @@ 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 |
 |---|---|---|---|---|---|---|
-| `google/gemini-3.6-flash` | Gemini 3.6 Flash | 1M | low, medium, high | $1.5/$7.5 · cache $0.15 | Pro and above | higher-quality coding & agentic workflows, fewer tokens |
+| `google/gemini-3.7-flash` | Gemini 3.7 Flash | 1.05M | low, medium, high | $0.75/$3.75 · cache $0.075 (write $0.04167) | GOAT and above | higher-quality coding & agentic workflows, fewer tokens |
+| `google/gemini-3.6-flash` | Gemini 3.6 Flash | 1M | low, medium, high | $1.5/$7.5 · cache $0.15 | Pro and above | previous Gemini Flash, still fast & capable |
 | `google/gemini-3.5-flash` | Gemini 3.5 Flash | 1M | low, medium, high | $1.5/$9 · cache $0.15 | Pro and above | Pro-level coding proficiency, parallel agentic execution |
 | `google/gemini-3.5-flash-lite` | Gemini 3.5 Flash Lite | 1M | low, medium, high | $0.3/$2.5 · cache $0.03 | Pro and above | upgraded agentic capabilities, ideal for subagents |
 | `google/gemini-3.1-flash-lite` | Gemini 3.1 Flash Lite | 1M | low, medium, high | $0.25/$1.5 · cache $0.03 | Pro and above | high-volume workhorse model with implicit caching |

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

@@ -200,7 +200,7 @@ Use the friendly names, or the exact tool names the model sees:
 | Friendly     | Covers                                                        |
 | :----------- | :----------------------------------------------------------- |
 | `Shell`      | `shell_command`, `monitor_command`, `kill_shell`             |
-| `Read`       | `read_file`, `read_multiple_files`, `read_directory`, `glob`, `grep` |
+| `Read`       | `read_file`, `read_directory`, `glob`, `grep` |
 | `Edit`       | `edit_file`, `write_file`                     |
 | `Write`      | `write_file`                                                 |
 | `WebFetch`   | `web_fetch`                                                  |
@@ -467,7 +467,7 @@ The reasoning behind the behavior, so you don't reverse-engineer it:
 
 Documented edges of the current engine:
 
-- **Wildcard `include` patterns in `read_multiple_files` expand inside the tool**, so an exact-file deny rule (`Read(.env)`) can't match a wildcard include (`*.env`) before expansion. Directory-tree rules (`Read(//etc/**)`) still cover this, because the tool's `targetDirectory` is matched as a touched path.
+- **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.

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

@@ -290,6 +290,7 @@ Valid model ids (the /model catalog — use these EXACT ids):
 - stepfun/Step-3.5-Flash
 - tencent/hy3-paid
 - tencent/Hy3
+- google/gemini-3.7-flash
 - google/gemini-3.6-flash
 - google/gemini-3.5-flash
 - google/gemini-3.5-flash-lite

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

@@ -29,9 +29,14 @@ Read a file as a bounded, line-numbered window. Read-only; never prompts.
 
 | Parameter | Type | Required | Description |
 | --- | --- | --- | --- |
-| `file_path` | string | yes | Absolute path, inside the workspace. |
-| `offset` | number | no | 1-indexed start line. |
-| `limit` | number | no | Max lines to read (default 2000). |
+| `file_path` | string | yes* | Absolute path, inside the workspace. May also be a single glob pattern. |
+| `paths` | string[] | yes* | Read many files at once: absolute paths and/or glob patterns. \*Either `file_path` or `paths` is required. |
+| `offset` | number | no | 1-indexed start line (single-file reads). |
+| `limit` | number | no | Max lines to read (default 2000, single-file reads). |
+| `exclude` | string[] | no | Multi-file reads: glob patterns to skip. |
+| `target_directory` | string | no | Multi-file reads: base directory for relative patterns (default: cwd). |
+| `default_exclude` | boolean | no | Multi-file reads: skip `node_modules`, `dist`, `build`, `.git`, coverage, logs, … (default `true`). |
+| `git_ignore` | boolean | no | Multi-file reads: respect `.gitignore` (default `true`). |
 
 What it does beyond "read a file":
 
@@ -41,19 +46,19 @@ What it does beyond "read a file":
 - **Efficient**: memory-capped streaming reads, and re-reading an unchanged file returns a dedup stub instead of burning context.
 - **Honest about safety**: device and stream paths (`/dev/zero`, `/dev/stdin`, `/proc/<pid>/fd/*`, …) are blocked; every read is recorded in the session's read ledger, which the write tools check later.
 
-### `read_multiple_files`
+#### Multi-file reads
 
-Bulk-read files by glob, concatenated with `// File: <path>` headers.
+Pass `paths` (or a single glob pattern in `file_path`) and the contents come back concatenated under `// File: <path> (<type>)` headers, preceded by a `Read X/Y files` summary:
 
-| Parameter | Type | Required | Description |
-| --- | --- | --- | --- |
-| `include` | string[] | yes | Glob patterns to read. |
-| `exclude` | string[] | no | Glob patterns to skip. |
-| `defaultExclude` | boolean | no | Skip `node_modules`, `dist`, `build`, `.git`, coverage, logs, … (default `true`). |
-| `gitIgnore` | boolean | no | Respect `.gitignore` (default `true`). |
-| `targetDirectory` | string | no | Base directory (default: cwd). |
+```json
+{"paths": ["/repo/src/index.ts", "/repo/src/**/*.test.ts"]}
+```
+
+`file_path` and `paths` are two separate fields on purpose rather than one union-typed field: providers translate JSON-Schema unions inconsistently — Gemini rejects a function declaration whose parameter sets `any_of` alongside `description`/`items`, failing the whole request. `paths` satisfies the schema's `file_path` requirement through the tool's `requiredAlternatives`, so a multi-file call needs no placeholder.
+
+Literal paths are read as named; glob patterns are filtered by `exclude`, the default exclusions and `.gitignore`. Binary files are noted with their type and size instead of being inlined. Per-file errors are reported inline and never fail the whole call; every match is boundary-checked individually (symlink and `..` escapes are dropped); and an aggregate ~100 KB cap (one tool-output budget) reports exactly which files were skipped, so a wide glob narrows instead of flooding the context.
 
-Per-file errors are reported inline and never fail the whole call; every match is boundary-checked individually (symlink and `..` escapes are dropped); an aggregate 1 MB cap reports exactly which files were skipped.
+This absorbed the former `read_multiple_files` tool — one tool schema instead of two keeps roughly 540 tokens out of every request (~1,685 → ~1,147), and models no longer have to choose between two near-identical read tools. Calls that still arrive under the old name are rewritten to `read_file` (its `include` renames onto `paths`, and `targetDirectory` / `gitIgnore` / `defaultExclude` onto the merged schema's snake_case options), so nothing breaks mid-conversation.
 
 ### `read_directory`