lcode-cli 0.16.0__tar.gz → 0.17.0__tar.gz

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/CHANGELOG.md

@@ -6,6 +6,27 @@ All notable changes to lcode are documented here. The format follows
 
 ## [Unreleased]
 
+## [0.17.0] - 2026-10-06
+
+### Added
+
+- `/commit` writes a commit message in the repository's style, from the diff, the conversation
+  and recent commits, and commits once you approve it. It commits what you staged, or every
+  change except files the model thinks are unrelated and files that may hold secrets.
+- `/review [base]` reviews the uncommitted changes, or the branch against a base, and reports
+  findings with `path:line`. The model can read but not change anything during a review.
+- `/pr [base]` pushes the branch and opens a GitHub pull request with `gh` after you approve the
+  title and description; commits made on `main` itself go to a new branch.
+- A command of your own called `commit`, `review` or `pr` replaces the built-in one.
+- `lcode --worktree [NAME]` (`-w`) runs the session in a git worktree on its own branch, so
+  several sessions can work on one repository at once. It's removed at the end if nothing
+  changed. See [Git workflow](https://nasser1941.github.io/lcode/git/).
+
+### Fixed
+
+- With another model server, `/ctx` no longer says the model reloads: it changes how much of the
+  server's context window lcode uses.
+
 ## [0.16.0] - 2026-10-05
 
 ### Added
@@ -398,7 +419,8 @@ First public release.
 - `AGENTS.md` project instructions and `/init` to generate them.
 - One-line installer for Linux and macOS.
 
-[Unreleased]: https://github.com/nasser1941/lcode/compare/v0.16.0...HEAD
+[Unreleased]: https://github.com/nasser1941/lcode/compare/v0.17.0...HEAD
+[0.17.0]: https://github.com/nasser1941/lcode/compare/v0.16.0...v0.17.0
 [0.16.0]: https://github.com/nasser1941/lcode/compare/v0.15.0...v0.16.0
 [0.15.0]: https://github.com/nasser1941/lcode/compare/v0.14.0...v0.15.0
 [0.14.0]: https://github.com/nasser1941/lcode/compare/v0.13.0...v0.14.0

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: lcode-cli
-Version: 0.16.0
+Version: 0.17.0
 Summary: A local-first terminal coding agent powered by open-weight models on your own GPU or Mac, via Ollama.
 Project-URL: Homepage, https://nasser1941.github.io/lcode/
 Project-URL: Documentation, https://nasser1941.github.io/lcode/
@@ -101,6 +101,9 @@ through [Ollama](https://ollama.com), and when it needs current information it c
 - **Remembers what matters.** Corrections, decisions and where things live carry over to the next
   session as short notes, saved by the model, by you (`/remember`) or by a quick check at the end
   of a session. Not whole conversations, and never secrets.
+- **Git workflow.** `/commit` writes messages in your repository's style, `/review` checks the
+  changes with `file:line` findings, `/pr` opens the pull request, each after you approve it, and
+  `lcode --worktree` runs parallel sessions on one repository.
 - **Bring your own model.** Eight curated open-weight models, all tested end to end, or any Ollama model
   with tool calling. Or use LM Studio, llama.cpp, vLLM or MLX instead of Ollama.
 - **MCP servers, ready to go.** Connect Jira and Confluence, GitHub, AWS, Google Drive, Grafana,
@@ -208,8 +211,8 @@ fills up. Details: [How it works](https://nasser1941.github.io/lcode/how-it-work
 
 See the pinned [Roadmap issue](https://github.com/nasser1941/lcode/issues/10). Next up:
 
-- [Git workflow: /commit, /review, /pr and parallel worktrees](https://github.com/nasser1941/lcode/issues/50)
 - [Automation: JSON output, a Python API and a GitHub Action for self-hosted runners](https://github.com/nasser1941/lcode/issues/48)
+- [Editor integration through the Agent Client Protocol](https://github.com/nasser1941/lcode/issues/49)
 - More models in the catalog, and test reports from your hardware ([report one](https://github.com/nasser1941/lcode/issues/new?template=model_request.yml))
 
 ## Contributing

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/README.md

@@ -65,6 +65,9 @@ through [Ollama](https://ollama.com), and when it needs current information it c
 - **Remembers what matters.** Corrections, decisions and where things live carry over to the next
   session as short notes, saved by the model, by you (`/remember`) or by a quick check at the end
   of a session. Not whole conversations, and never secrets.
+- **Git workflow.** `/commit` writes messages in your repository's style, `/review` checks the
+  changes with `file:line` findings, `/pr` opens the pull request, each after you approve it, and
+  `lcode --worktree` runs parallel sessions on one repository.
 - **Bring your own model.** Eight curated open-weight models, all tested end to end, or any Ollama model
   with tool calling. Or use LM Studio, llama.cpp, vLLM or MLX instead of Ollama.
 - **MCP servers, ready to go.** Connect Jira and Confluence, GitHub, AWS, Google Drive, Grafana,
@@ -172,8 +175,8 @@ fills up. Details: [How it works](https://nasser1941.github.io/lcode/how-it-work
 
 See the pinned [Roadmap issue](https://github.com/nasser1941/lcode/issues/10). Next up:
 
-- [Git workflow: /commit, /review, /pr and parallel worktrees](https://github.com/nasser1941/lcode/issues/50)
 - [Automation: JSON output, a Python API and a GitHub Action for self-hosted runners](https://github.com/nasser1941/lcode/issues/48)
+- [Editor integration through the Agent Client Protocol](https://github.com/nasser1941/lcode/issues/49)
 - More models in the catalog, and test reports from your hardware ([report one](https://github.com/nasser1941/lcode/issues/new?template=model_request.yml))
 
 ## Contributing

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/docs/commands.md

@@ -46,7 +46,8 @@ Report bugs first, with `path:line`, then missing tests. Don't change any files.
 | `~/.config/lcode/commands/<name>.md` | For every repository |
 
 The file name is the command's name. A repository's command overrides one of yours with the same
-name; built-in commands such as `/help` can't be replaced.
+name. A command called `review`, `commit` or `pr` replaces lcode's [built-in one](git.md), so a team
+can use its own checklist; other built-in commands such as `/help` can't be replaced.
 
 ## Skills
 

lcode_cli-0.17.0/docs/git.md

@@ -0,0 +1,98 @@
+# Git workflow
+
+The everyday git steps, without spelling them out each time:
+- **`/commit`** writes a message in your repository's style;
+- **`/review`** checks the changes before you commit or merge;
+- **`/pr`** opens a pull request;
+- **`lcode --worktree`** runs several sessions on one repository without them getting in each other's way.
+
+lcode never commits, pushes or opens a pull request until you say yes, also in `yolo` mode.
+
+## /commit
+
+```text
+❯ /commit
+╭─ Commit message ───────────────────────────────────────────────╮
+│ feat: add median()                                             │
+│                                                                │
+│ Add a median() function to stats.py and its tests. It raises   │
+│ ValueError on empty input, consistent with mean().             │
+╰────────────────────────────────────────────────────────────────╯
+  Files stats.py, test_stats.py
+  Left out (unrelated, the model thinks): debug.log
+  [y] commit · [e] edit the message · [n] cancel: y
+✓ Committed fecd803 feat: add median()
+```
+
+- **What goes in.**
+  - If you staged files (`git add`), exactly those.
+  - Otherwise every changed and new file, except:
+    - files the model thinks are unrelated to the work, listed so you can see them;
+    - files that may hold secrets (`.env`, `*.pem`, keys, credentials and the like). These only go in when you stage them yourself.
+- **The message.** It's written from the diff, from what the conversation knows about why you made the change, and from the repository's recent commits: their prefixes, tense, length and trailers. `/commit mention ticket ABC-12` adds your own notes.
+- **Editing.** `e` opens the message in your editor (`$EDITOR`).
+- **Hooks.** Your git hooks run as usual: a failing pre-commit hook stops the commit and shows why.
+
+## /review
+
+| | Reviews |
+|---|---|
+| `/review` | The uncommitted changes if any tracked file changed; otherwise the branch's changes compared with the default branch (`main`) |
+| `/review develop` | The branch, and any uncommitted changes, compared with `develop` |
+
+The model reads the code around the changes where it needs to. During a review it can't change
+files or run commands that change anything. It reports findings with `path:line`, the kind of
+problem (bug, test, security or clarity), what's wrong and how to fix it, most important first:
+
+```text
+stats.py:18 — bug
+The even-length median is broken: for median([1, 3, 2, 4]) the old code returns 2.5, the new
+code returns 3. Revert line 18 to (s[mid - 1] + s[mid]) / 2.
+
+test_stats.py:13 — test
+test_median() asserts median([1, 3, 2, 4]) == 2.5, so it fails with this change.
+```
+
+Then ask it to fix what you agree with, in the same conversation.
+
+**Your own checklist:** put review guidelines in `AGENTS.md` or in a [skill](commands.md#skills),
+and the review follows them. To replace `/review` entirely, write a
+[command](commands.md#commands) of your own called `review`. The same goes for `/commit` and `/pr`.
+
+## /pr
+
+Pushes the branch and opens a GitHub pull request. It needs the [GitHub CLI](https://cli.github.com),
+signed in with `gh auth login`.
+
+- **Into which branch.** The default branch, or the one you name: `/pr develop`. Anything else you
+  type is a note for the description: `/pr develop link it to #12`.
+- **Before you start.** Commit first: `/pr` stops while there are uncommitted changes.
+- **Commits made on `main` itself** go to a new branch named after the change. Your local `main`
+  still has them, so reset it once the pull request is merged.
+- **The title and description** are written from the commits, the diff and the conversation, and
+  follow the repository's pull request template if it has one. You see them before anything is
+  pushed: `y` to push and open, `e` to edit, `n` to stop.
+- **A branch with an open pull request:** `/pr` offers to push the new commits instead.
+
+## Parallel sessions: lcode --worktree
+
+```bash
+lcode --worktree fix-login     # a session on a new branch fix-login, in a folder of its own
+lcode -w                       # the same, with a generated name
+```
+
+A [git worktree](https://git-scm.com/docs/git-worktree) is a second working folder of the same
+repository, on its own branch. Sessions in different worktrees can edit, test and commit at the
+same time without touching each other's files, or yours.
+
+- **Where it starts.** The worktree starts from your current commit. Uncommitted changes in your
+  own folder don't come along.
+- **Where it lives.** lcode keeps worktree folders in `~/.local/state/lcode/worktrees/` and prints
+  the path. They're outside the repository so the model can't mistake your folder for its own.
+- **When the session ends.**
+  - If nothing changed (no commits and no uncommitted changes), the worktree and its branch are
+    removed.
+  - Otherwise it stays, and lcode tells you how to continue (`lcode --worktree fix-login` again),
+    merge it (`git merge fix-login`) or remove it.
+- **What's separate.** Sessions (`/resume`, `lcode -c`) and [checkpoints](usage.md#undo-and-checkpoints)
+  belong to each worktree. [Memory notes](memory.md) are shared with the repository.

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/docs/quickstart.md

@@ -12,7 +12,7 @@ lcode
 
 ```text
 ╭──────────────────────────────────────────────╮
-│ lcode v0.16.0 — local coding agent           │
+│ lcode v0.17.0 — local coding agent           │
 │                                              │
 │ model    lcode-qwen3.6-35b                   │
 │ context  256K tokens                         │

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/docs/usage.md

@@ -20,6 +20,7 @@ lcode mcp [catalog|add|list] # connect MCP servers: Jira, GitHub, AWS, databases
 | `-r, --repo DIR` | Work in another directory |
 | `-c, --continue` | Continue the most recently used session in this directory |
 | `--resume [SESSION]` | Resume a saved session: pick from a list, or give its number, name or id |
+| `-w, --worktree [NAME]` | Work in a [git worktree](git.md#parallel-sessions-lcode-worktree) of its own, on branch NAME; removed at the end if nothing changed |
 | `--plan` | Start in [plan mode](#plan-mode): agree on a plan before anything changes |
 | `--auto-edit` | Apply file edits without asking (commands still ask) |
 | `--yolo` | Never ask for permission |
@@ -74,6 +75,9 @@ reasoning is on.
 | `/mode [ask\|plan\|auto-edit\|yolo]` | Set the permission mode |
 | `/cd DIR` | Change the working directory |
 | `/todos` | Show the model's task list |
+| `/commit [notes]` | [Commit](git.md#commit) the changes with a message in the repository's style, once you approve it |
+| `/review [base]` | [Review](git.md#review) the uncommitted changes, or the branch against a base |
+| `/pr [base] [notes]` | Push the branch and open a GitHub [pull request](git.md#pr), once you approve it |
 | `/exit` | Quit |
 
 ## What the model can do

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/mkdocs.yml

@@ -95,6 +95,7 @@ nav:
       - Memory: memory.md
       - Subagents: agents.md
       - Commands and skills: commands.md
+      - Git workflow: git.md
       - Code intelligence: lsp.md
       - Repository map and code search: search.md
       - Models & context windows: models.md

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/pyproject.toml

@@ -84,6 +84,7 @@ ignore = [
 "src/lcode/codesearch.py" = ["E501"]
 "src/lcode/bench_backend.py" = ["E501"]
 "src/lcode/backends.py" = ["E501"]
+"src/lcode/gitflow.py" = ["E501"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/src/lcode/__init__.py

@@ -1,3 +1,3 @@
 """lcode — a local-first terminal coding agent powered by open-weight models via Ollama."""
 
-__version__ = "0.16.0"
+__version__ = "0.17.0"

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/src/lcode/agent.py

@@ -130,7 +130,14 @@ def git_info(cwd: Path) -> str:
             return "not a git repository"
         changed = git("status", "--short").stdout.strip().splitlines()
         log = git("log", "--oneline", "-5").stdout.strip() or "(no commits)"
-        return f"branch {branch.stdout.strip()}, {len(changed)} changed file(s)\nRecent commits:\n{log}"
+        dirs = git("rev-parse", "--path-format=absolute", "--git-dir", "--git-common-dir").stdout.split()
+        worktree = (
+            "\nThis folder is a git worktree, separate from the repository's main checkout: read, change and "
+            "commit files only here, with paths inside this folder."
+            if len(dirs) == 2 and dirs[0] != dirs[1]
+            else ""
+        )
+        return f"branch {branch.stdout.strip()}, {len(changed)} changed file(s){worktree}\nRecent commits:\n{log}"
     except (OSError, subprocess.TimeoutExpired):
         return "unknown"
 
@@ -242,6 +249,7 @@ class Agent:
         # Set on subagents (see lcode.subagents):
         self.allowed_tools: set[str] | None = None  # None: every tool
         self.read_only = False  # only read-only shell commands
+        self.no_changes = ""  # set during a review: why nothing may change (read-only tools only)
         self.cancel: threading.Event | None = None  # set from another thread to stop
         self.on_tool = None  # called with (name, arguments) before each tool runs
         self.response = None  # the streaming response, so another thread can abort it
@@ -931,4 +939,6 @@ class Agent:
         else:
             note = ""
         self.settings.context = tokens
+        if getattr(self.ollama, "kind", "ollama") != "ollama":  # the server keeps its own window
+            return f"lcode now uses {format_tokens(tokens)} tokens of the context window{note}, and summarizes sooner."
         return f"Context window set to {format_tokens(tokens)} tokens{note}. The model reloads on the next request."

{lcode_cli-0.16.0 → lcode_cli-0.17.0}/src/lcode/cli.py

@@ -626,6 +626,17 @@ def cmd_chat(args) -> None:
     cwd = Path(args.repo).expanduser().resolve()
     if not cwd.is_dir():
         fail(f"not a directory: {cwd}")
+    worktree = None
+    if args.worktree is not None:
+        from lcode import gitflow
+
+        try:
+            worktree = gitflow.start_worktree(cwd, args.worktree)
+        except gitflow.GitError as e:
+            fail(f"--worktree: {e}")
+        cwd = worktree.cwd
+        state = "a new worktree" if worktree.created_branch else "the worktree"
+        console.print(f"[dim]Working in {state} {worktree.path}, on branch {escape(worktree.branch)}.[/]")
     ollama = connect(cfg)
     hw = detect()
     check_ollama(ollama, hw)
@@ -714,6 +725,8 @@ def cmd_chat(args) -> None:
             agent.mcp.close()
         if agent.sandbox:
             agent.sandbox.stop()
+        if worktree is not None:
+            console.print(f"[dim]{escape(worktree.finish())}[/]")
 
 
 def build_parser() -> argparse.ArgumentParser:
@@ -736,6 +749,14 @@ def build_parser() -> argparse.ArgumentParser:
         metavar="SESSION",
         help="resume a saved session: pick from a list, or give its number, name or id",
     )
+    parser.add_argument(
+        "-w",
+        "--worktree",
+        nargs="?",
+        const="",
+        metavar="NAME",
+        help="work in a git worktree of its own, on branch NAME (new, or continue one); removed if nothing changed",
+    )
     parser.add_argument("--plan", action="store_true", help="start in plan mode: agree on a plan before any change")
     parser.add_argument("--auto-edit", action="store_true", help="apply file edits without asking")
     parser.add_argument("--yolo", action="store_true", help="never ask for permission (edits and commands)")