lcode-cli 0.2.0__tar.gz → 0.2.1__tar.gz

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/CHANGELOG.md

@@ -6,6 +6,15 @@ All notable changes to lcode are documented here. The format follows
 
 ## [Unreleased]
 
+## [0.2.1] - 2026-09-29
+
+### Fixed
+
+- File edits and writes failed with "IndexError: list index out of range" in the default `ask`
+  permission mode, a regression in 0.2.0. `auto-edit` and `yolo` modes were not affected.
+- Slow models no longer look stuck: the status line keeps counting the elapsed time while the model
+  thinks, answers or silently writes a long file into a tool call, and reminds you that Ctrl+C stops it.
+
 ## [0.2.0] - 2026-09-29
 
 ### Added
@@ -98,7 +107,8 @@ 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/v0.2.0...HEAD
+[Unreleased]: https://github.com/nasser1941/lcode/compare/v0.2.1...HEAD
+[0.2.1]: https://github.com/nasser1941/lcode/compare/v0.2.0...v0.2.1
 [0.2.0]: https://github.com/nasser1941/lcode/compare/v0.1.2...v0.2.0
 [0.1.2]: https://github.com/nasser1941/lcode/compare/v0.1.1...v0.1.2
 [0.1.1]: https://github.com/nasser1941/lcode/compare/v0.1.0...v0.1.1

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: lcode-cli
-Version: 0.2.0
+Version: 0.2.1
 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/
@@ -150,8 +150,8 @@ What `lcode setup` picks for common machines:
 | NVIDIA 8–24 GB + 32 GB RAM | qwen3.6-35b | 256K |
 | NVIDIA 8 GB + 16 GB RAM | gpt-oss-20b | 64K |
 
-On an RTX 4080 Laptop GPU (12 GB) the default model generates 50–60 tokens/s at 256K context, and
-qwen3.5-9b 64 tokens/s at 128K. See
+At 256K context the default model generates 50–55 tokens/s on an RTX 4080 Laptop GPU (12 GB) and
+45 tokens/s on an M4 Pro Mac with 48 GB. See
 [Models & context windows](https://nasser1941.github.io/lcode/models/) for memory estimates and
 tuning.
 
@@ -165,11 +165,13 @@ fills up. Details: [How it works](https://nasser1941.github.io/lcode/how-it-work
 
 ## Roadmap
 
-- More models in the catalog, with community test reports ([request one](https://github.com/nasser1941/lcode/issues/new?template=model_request.yml))
-- Measured Apple Silicon performance numbers
-- MCP (Model Context Protocol) tool servers
-- Web fetch and search tools
-- Packaging on PyPI and Homebrew
+See the pinned [Roadmap issue](https://github.com/nasser1941/lcode/issues/10). Next up:
+
+- [`/undo` and automatic checkpoints](https://github.com/nasser1941/lcode/issues/4)
+- [`lcode bench`: score models on your own hardware](https://github.com/nasser1941/lcode/issues/5)
+- [MCP tool servers](https://github.com/nasser1941/lcode/issues/6)
+- [Homebrew formula](https://github.com/nasser1941/lcode/issues/8) and an [optional sandbox for shell commands](https://github.com/nasser1941/lcode/issues/9)
+- 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-0.2.0 → lcode_cli-0.2.1}/README.md

@@ -117,8 +117,8 @@ What `lcode setup` picks for common machines:
 | NVIDIA 8–24 GB + 32 GB RAM | qwen3.6-35b | 256K |
 | NVIDIA 8 GB + 16 GB RAM | gpt-oss-20b | 64K |
 
-On an RTX 4080 Laptop GPU (12 GB) the default model generates 50–60 tokens/s at 256K context, and
-qwen3.5-9b 64 tokens/s at 128K. See
+At 256K context the default model generates 50–55 tokens/s on an RTX 4080 Laptop GPU (12 GB) and
+45 tokens/s on an M4 Pro Mac with 48 GB. See
 [Models & context windows](https://nasser1941.github.io/lcode/models/) for memory estimates and
 tuning.
 
@@ -132,11 +132,13 @@ fills up. Details: [How it works](https://nasser1941.github.io/lcode/how-it-work
 
 ## Roadmap
 
-- More models in the catalog, with community test reports ([request one](https://github.com/nasser1941/lcode/issues/new?template=model_request.yml))
-- Measured Apple Silicon performance numbers
-- MCP (Model Context Protocol) tool servers
-- Web fetch and search tools
-- Packaging on PyPI and Homebrew
+See the pinned [Roadmap issue](https://github.com/nasser1941/lcode/issues/10). Next up:
+
+- [`/undo` and automatic checkpoints](https://github.com/nasser1941/lcode/issues/4)
+- [`lcode bench`: score models on your own hardware](https://github.com/nasser1941/lcode/issues/5)
+- [MCP tool servers](https://github.com/nasser1941/lcode/issues/6)
+- [Homebrew formula](https://github.com/nasser1941/lcode/issues/8) and an [optional sandbox for shell commands](https://github.com/nasser1941/lcode/issues/9)
+- 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-0.2.0 → lcode_cli-0.2.1}/docs/index.md

@@ -82,8 +82,8 @@ until the task is done, asking before it changes anything.
 
 | Platform | Recommended hardware | Default choice |
 |---|---|---|
-| **Ubuntu / Linux** with NVIDIA GPU | 12 GB+ VRAM and 32 GB RAM | Qwen3.6 35B-A3B at 256K context |
-| **macOS on Apple Silicon** (M1–M4) | 48 GB+ unified memory | Qwen3.6 35B-A3B at 256K context |
+| **Ubuntu / Linux** with NVIDIA GPU | 12 GB+ VRAM and 32 GB RAM | Qwen3.6 35B-A3B at 256K context (50–55 tok/s on 12 GB) |
+| **macOS on Apple Silicon** (M1–M4) | 48 GB+ unified memory | Qwen3.6 35B-A3B at 256K context (45 tok/s on an M4 Pro) |
 | Smaller machines (16–24 GB Mac, 8 GB GPU) | — | Qwen3.5 9B / 4B with a smaller context |
 
 See [Models & context windows](models.md) for the full catalog and how lcode sizes models to your

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/docs/models.md

@@ -138,7 +138,7 @@ results on your machine are welcome in the
 | Mac with M4, 16 GB | ~11 GB | qwen3.5-9b | 64K | fast |
 | Mac with M4 / M4 Pro, 24 GB | ~16 GB | qwen3.5-9b | 256K | fast |
 | Mac with M4 Pro / M4 Max, 36 GB | ~24 GB | qwen3.6-35b | 64K | fast |
-| Mac with M4 Pro, 48 GB | ~36 GB | qwen3.6-35b | 256K | fast |
+| Mac with M4 Pro, 48 GB | ~36 GB | qwen3.6-35b | 256K | fast (measured: 45 tok/s) |
 | Mac with M4 Max, 64–128 GB | 48–96 GB | qwen3.6-35b | 256K | fast |
 | NVIDIA 8 GB + 16 GB RAM | ~16 GB | gpt-oss-20b | 64K | good (experts in RAM) |
 | NVIDIA 8–16 GB + 32 GB RAM | 32–40 GB | qwen3.6-35b | 256K | good (experts in RAM) |
@@ -200,7 +200,10 @@ The small models on the same GPU (a bug-fix task: read, run the failing tests, e
 Dense models slow down about 3x once they no longer fit in VRAM, which is why lcode sizes their
 context to stay on the GPU.
 
-Apple Silicon numbers are not measured yet; please share yours.
+On a Mac with an **Apple M4 Pro and 48 GB** of unified memory (reported by a user, Ollama 0.34), lcode
+picks the same `qwen3.6-35b` at 256K context and generates **45 tokens/s**, running entirely on the
+GPU's share of unified memory. Results from other Macs are very welcome in the
+[model reports](https://github.com/nasser1941/lcode/issues/new?template=model_request.yml).
 
 ### Tips for Macs
 

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/docs/quickstart.md

@@ -12,7 +12,7 @@ lcode
 
 ```text
 ╭──────────────────────────────────────────────╮
-│ lcode v0.2.0 — local coding agent            │
+│ lcode v0.2.1 — local coding agent            │
 │                                              │
 │ model    lcode-qwen3.6-35b                   │
 │ context  256K tokens                         │

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/src/lcode/__init__.py

@@ -1,3 +1,3 @@
 """lcode — a local-first terminal coding agent powered by open-weight models via Ollama."""
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/src/lcode/agent.py

@@ -101,6 +101,29 @@ def git_info(cwd: Path) -> str:
         return "unknown"
 
 
+class Progress:
+    """The status line under a running request.
+
+    It is re-rendered on every spinner frame, so the elapsed time keeps moving even when no text
+    arrives, for example while the model writes a long file into a tool call.
+    """
+
+    def __init__(self) -> None:
+        self.started = self.last_chunk = time.time()
+        self.phase = "Thinking"
+        self.chars = 0
+
+    def update(self, phase: str, text: str) -> None:
+        self.phase, self.chars, self.last_chunk = phase, self.chars + len(text), time.time()
+
+    def __rich__(self) -> Text:
+        now = time.time()
+        phase = self.phase if now - self.last_chunk < 3 else "Working"
+        return Text.from_markup(
+            f"[cyan]{phase}…[/] [dim]({self.chars // 4} tokens, {now - self.started:.0f}s · Ctrl+C to stop)[/]"
+        )
+
+
 @dataclass
 class Settings:
     model: str  # Ollama model name to call
@@ -301,35 +324,41 @@ class Agent:
         """Stream one model response, rendering thinking/content live. Returns the assistant message."""
         content, thinking, tool_calls, final = "", "", [], {}
         md = MarkdownStreamer(self.console)
-        status = self.console.status("[cyan]Thinking…[/]", spinner="dots")
-        status.start()
-        spinning, printed_thinking, t0 = True, False, time.time()
+        progress = Progress()
+        status = None
+        printed_thinking = False
+
+        def start_spinner() -> None:
+            nonlocal status
+            if status is None:
+                status = self.console.status(progress, spinner="dots")
+                status.start()
 
         def stop_spinner() -> None:
-            nonlocal spinning
-            if spinning:
+            nonlocal status
+            if status is not None:
                 status.stop()
-                spinning = False
+                status = None
 
+        start_spinner()
         try:
             for chunk in self.chat(self.messages, self.tool_schemas(), self.settings.think):
                 msg = chunk.get("message", {})
                 if msg.get("thinking"):
                     thinking += msg["thinking"]
+                    progress.update("Thinking", msg["thinking"])
                     if self.settings.show_thinking:
-                        stop_spinner()
+                        stop_spinner()  # raw text is printed as it streams
                         self.console.print(Text(msg["thinking"], style="dim italic"), end="")
                         printed_thinking = True
-                    else:
-                        status.update(
-                            f"[cyan]Thinking…[/] [dim]({len(thinking) // 4} tokens, {time.time() - t0:.0f}s)[/]"
-                        )
                 if msg.get("content"):
-                    stop_spinner()
                     if printed_thinking:
                         self.console.print("\n")
                         printed_thinking = False
                     content += msg["content"]
+                    progress.update("Writing", msg["content"])
+                    # Finished markdown blocks print above the spinner, which keeps running meanwhile.
+                    start_spinner()
                     md.feed(msg["content"])
                 if msg.get("tool_calls"):
                     tool_calls.extend(msg["tool_calls"])

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/src/lcode/permissions.py

@@ -71,7 +71,7 @@ class Permissions:
         if self.mode == "yolo" or key in self.always or (kind == "edit" and self.mode == "auto-edit"):
             return True, ""
         self.console.print(Panel(body, title=title, title_align="left", border_style="yellow"))
-        scope = {"edit": "file edits", "bash": key.split(":", 1)[1], "web": key.split(":", 1)[1]}[kind]
+        scope = "file edits" if kind == "edit" else key.split(":", 1)[-1]
         try:
             answer = input(f"  Allow? [y]es / [a]lways for '{scope}' this session / [n]o (+ optional reason): ")
         except EOFError:

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/tests/test_agent.py

@@ -149,6 +149,18 @@ def test_malformed_tool_calls_give_up_eventually(make_agent):
         agent.run_turn("write a.py")
 
 
+def test_progress_line_keeps_counting_without_chunks(monkeypatch):
+    from lcode.agent import Progress
+
+    clock = [1000.0]
+    monkeypatch.setattr("lcode.agent.time.time", lambda: clock[0])
+    progress = Progress()
+    progress.update("Writing", "x" * 400)
+    assert progress.__rich__().plain.startswith("Writing… (100 tokens, 0s")
+    clock[0] += 125  # the model is silently writing a tool call
+    assert progress.__rich__().plain.startswith("Working… (100 tokens, 125s")
+
+
 def test_mentions_attach_files(agent):
     text = agent.expand_mentions("explain @src/pkg/math.py please, mail me@example.com")
     assert '<file path="src/pkg/math.py">' in text

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/tests/test_permissions.py

@@ -59,3 +59,12 @@ def test_always_and_modes(monkeypatch):
     assert perms.request("edit", "edit", "Edit", "diff")[0]
     perms.cycle()
     assert perms.mode == "yolo"
+
+
+@pytest.mark.parametrize(("kind", "key"), [("edit", "edit"), ("bash", "bash:rm"), ("web", "web:search")])
+def test_every_kind_can_ask_and_remember(monkeypatch, kind, key):
+    perms = Permissions(Console(file=io.StringIO()), "ask")
+    monkeypatch.setattr("builtins.input", lambda _: "a")
+    assert perms.request(key, kind, "Title", "body") == (True, "")
+    monkeypatch.setattr("builtins.input", lambda _: pytest.fail("should not ask again"))
+    assert perms.request(key, kind, "Title", "body") == (True, "")

{lcode_cli-0.2.0 → lcode_cli-0.2.1}/tests/test_tools.py

@@ -127,3 +127,14 @@ def test_truncate_keeps_head_and_tail():
     text = "a" * 50 + "b" * 50
     out = truncate(text, limit=30)
     assert out.startswith("a" * 20) and out.endswith("b" * 10) and "truncated" in out
+
+
+def test_edits_in_ask_mode(make_agent, repo: Path, monkeypatch):
+    """Regression: file edits used to crash with IndexError whenever lcode asked for permission."""
+    agent = make_agent(mode="ask")
+    monkeypatch.setattr("builtins.input", lambda _: "y")
+    assert agent.tools.run("write_file", {"path": "NOTES.md", "content": "# Notes\n"}).startswith("Created")
+    agent.tools.run("read_file", {"path": "src/pkg/math.py"})
+    out = agent.tools.run("edit_file", {"path": "src/pkg/math.py", "old_string": "a - b", "new_string": "b - a"})
+    assert out.startswith("Edited src/pkg/math.py")
+    assert "return b - a" in (repo / "src/pkg/math.py").read_text()