lcode-cli 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

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__ = "0.2.2"

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/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/repl.py

@@ -21,7 +21,7 @@ from rich.table import Table
 from rich.text import Text
 
 from lcode import __version__, catalog, limits, sessions, web
-from lcode.agent import INIT_PROMPT, Agent
+from lcode.agent import AUTO_COMPACT_RATIO, INIT_PROMPT, Agent
 from lcode.catalog import MIN_USEFUL_CONTEXT
 from lcode.config import PERMISSION_MODES, STATE_DIR, ConfigError, format_tokens, parse_context
 from lcode.hardware import Hardware
@@ -35,8 +35,8 @@ COMMANDS = {
     "/rename": "Name this session so you can find it later, e.g. /rename auth refactor",
     "/resume": "Resume a saved session: pick from a list, or /resume <number|name> (/resume all: every folder)",
     "/compact": "Summarize the conversation to free context (optional: what to focus on)",
-    "/context": "Show context-window usage",
-    "/ctx": "Show or change the context window, e.g. /ctx 128k",
+    "/context": "Show context usage and change the window size: pick from a list, or /context 128k",
+    "/ctx": "Shortcut for /context",
     "/model": "Show or switch model, e.g. /model qwen3.5-9b",
     "/models": "List models and how they fit this machine",
     "/think": "Toggle model reasoning on/off",
@@ -145,6 +145,114 @@ def banner(agent: Agent) -> None:
     )
 
 
+CONTEXT_CHOICES = (16384, 32768, 65536, 131072, 262144, 524288, 1048576)
+
+
+def context_options(agent: Agent, hardware: Hardware) -> list[dict]:
+    """The context sizes this model supports, with how each one fits this machine."""
+    s = agent.settings
+    spec = catalog.find(s.model)
+    try:
+        max_ctx = agent.ollama.max_context(s.model) or (spec.max_context if spec else None)
+    except OllamaError:
+        max_ctx = spec.max_context if spec else None
+    sizes = {c for c in CONTEXT_CHOICES if not max_ctx or c <= max_ctx} | {s.context}
+    if max_ctx:
+        sizes.add(max_ctx)
+    learned = limits.get(s.model)
+    recommended = limits.cap(s.model, spec.fit(hardware)[0]) if spec and spec.fit(hardware)[0] else None
+    options = []
+    for size in sorted(sizes):
+        if spec:
+            memory = spec.memory_gib(size)
+            if hardware.unified:
+                fit = "fits" if memory <= hardware.budget_gib - catalog.HEADROOM_GIB else "too large"
+            elif hardware.gpu and memory <= hardware.vram_gib:
+                fit = "on GPU"
+            elif memory <= hardware.budget_gib - catalog.HEADROOM_GIB:
+                fit = "GPU + RAM" if spec.moe else "GPU + RAM, slow"
+            else:
+                fit = "too large"
+            note = f"~{memory:.0f} GB · {fit}"
+        else:
+            note = "no memory estimate for this model"
+        if learned and size > learned:
+            note += " · ran out of memory here before"
+        options.append({"size": size, "note": note, "current": size == s.context, "recommended": size == recommended})
+    return options
+
+
+def context_command(agent: Agent, arg: str, hardware: Hardware) -> None:
+    """Show context usage and change the window size, from a list or directly (/context 128k)."""
+    c, s = agent.console, agent.settings
+    c.print(
+        f"In use: {format_tokens(agent.ctx_used)} of {format_tokens(s.context)} tokens "
+        f"({100 * agent.ctx_used / s.context:.0f}%) in {len(agent.messages)} message"
+        f"{'' if len(agent.messages) == 1 else 's'}; auto-compacts at 85%."
+    )
+    if arg:
+        try:
+            apply_context(agent, parse_context(arg), hardware)
+        except ConfigError as e:
+            c.print(f"[red]{e}[/]")
+        return
+    options = context_options(agent, hardware)
+    table = Table(title=f"Context window for {s.model}", title_justify="left", header_style="bold")
+    table.add_column("#", justify="right", style="cyan")
+    table.add_column("Size", justify="right")
+    table.add_column("Memory · fit")
+    table.add_column("")
+    for i, option in enumerate(options, 1):
+        marks = []
+        if option["current"]:
+            marks.append("[bold]current[/]")
+        if option["recommended"]:
+            marks.append("[cyan]recommended[/]")
+        table.add_row(str(i), format_tokens(option["size"]), option["note"], ", ".join(marks))
+    c.print(table)
+    try:
+        answer = input(f"  Choose a number, a size like 96k, or press Enter to keep {format_tokens(s.context)}: ")
+    except EOFError:
+        return
+    answer = answer.strip()
+    if not answer:
+        c.print(f"Keeping {format_tokens(s.context)}.")
+        return
+    if answer.isdigit() and 1 <= int(answer) <= len(options):
+        size = options[int(answer) - 1]["size"]
+    else:
+        try:
+            size = parse_context(answer)
+        except ConfigError as e:
+            c.print(f"[red]{e}[/]")
+            return
+    apply_context(agent, size, hardware)
+
+
+def apply_context(agent: Agent, size: int, hardware: Hardware) -> None:
+    c, s = agent.console, agent.settings
+    if size == s.context:
+        c.print(f"The context window is already {format_tokens(size)}.")
+        return
+    if agent.has_conversation() and agent.ctx_used > AUTO_COMPACT_RATIO * size:
+        c.print(
+            f"This conversation uses {format_tokens(agent.ctx_used)} tokens, too much for {format_tokens(size)}; "
+            "summarizing it first."
+        )
+        try:
+            agent.compact()
+        except OllamaError as e:
+            c.print(f"[red]Couldn't summarize the conversation, so the context stays the same: {e}[/]")
+            return
+    c.print(agent.set_context(size))
+    spec = catalog.find(s.model)
+    if spec and spec.memory_gib(s.context) > hardware.budget_gib:
+        c.print(
+            f"[yellow]~{spec.memory_gib(s.context):.0f} GB needed but ~{hardware.budget_gib:.0f} GB available; "
+            "this may run out of memory, in which case lcode falls back to a smaller size.[/]"
+        )
+
+
 def web_status(agent: Agent) -> str:
     if agent.settings.web == "off":
         return "off"
@@ -196,28 +304,8 @@ def handle_command(agent: Agent, line: str, hardware: Hardware) -> bool:
             resume_session(agent, info)
     elif cmd == "/compact":
         agent.compact(arg)
-    elif cmd == "/context":
-        c.print(
-            f"Context: {format_tokens(agent.ctx_used)} of {format_tokens(s.context)} tokens "
-            f"({100 * agent.ctx_used / s.context:.1f}%) in {len(agent.messages)} messages; "
-            "auto-compacts at 85%."
-        )
-    elif cmd == "/ctx":
-        if not arg:
-            spec = catalog.find(s.model)
-            extra = f" · model maximum {format_tokens(spec.max_context)}" if spec else ""
-            c.print(f"Context window: {format_tokens(s.context)} tokens{extra}. Change it with /ctx 128k")
-        else:
-            try:
-                c.print(agent.set_context(parse_context(arg)))
-            except ConfigError as e:
-                c.print(f"[red]{e}[/]")
-            spec = catalog.find(s.model)
-            if spec and spec.memory_gib(s.context) > hardware.budget_gib:
-                c.print(
-                    f"[yellow]~{spec.memory_gib(s.context):.0f} GB needed but ~{hardware.budget_gib:.0f} GB "
-                    "available; this may run out of memory.[/]"
-                )
+    elif cmd in ("/context", "/ctx"):
+        context_command(agent, arg, hardware)
     elif cmd == "/models":
         print_models(agent.ollama, hardware, s.model)
     elif cmd == "/model":

{lcode_cli-0.2.0.dist-info → lcode_cli-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: lcode-cli
-Version: 0.2.0
+Version: 0.2.2
 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/
@@ -124,7 +124,7 @@ lcode
 | `lcode --model qwen3.5-9b --context 128k` | pick a model and context window for this session |
 | `lcode models` / `lcode doctor` | what fits this machine / check the installation |
 | `/rename`, `/resume` | name the current session, resume a saved one |
-| `/model`, `/ctx 128k`, `/compact`, `/help` | switch model, resize context, summarize, list commands |
+| `/model`, `/context`, `/compact`, `/help` | switch model, resize the context window (pick from a list), summarize, list commands |
 
 ## Models
 
@@ -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.dist-info → lcode_cli-0.2.2.dist-info}/RECORD

@@ -1,6 +1,6 @@
-lcode/__init__.py,sha256=_z-t2_EZYD-CKWphVqbpoHxiZaiXC0IANqgUDmhabQM,117
+lcode/__init__.py,sha256=f69CJWRNbXrayd_uWS82hWDQJcvsIH6fRtjvpXj-I8s,117
 lcode/__main__.py,sha256=s5N5pryX2FAu93GGZ3FxUrIXHWGzxz66lKUoaV_h8Ws,35
-lcode/agent.py,sha256=HYbmZVkEGmWxEtnQRKexGXzCpcdFRK3-YkJJoH3PJ80,23499
+lcode/agent.py,sha256=ppO9sMxymIVvFPeHS-5hqTyryQYBOK_0OAucaX6SeWU,24535
 lcode/catalog.py,sha256=pZ1azX9OH2r4JE2c6E5OfwywpgS39-W2oXzoCHJhmtM,4141
 lcode/cli.py,sha256=bvKv_5SGJgy8bkY-zFpXwyNACiGa6nu_n16ems_Vmq8,20103
 lcode/config.py,sha256=ZyddgIZ9TaHAcJSW_A8o7qFQbp1s2RHmsbFzOzEjV4o,5894
@@ -8,14 +8,14 @@ lcode/hardware.py,sha256=2VbknZCxTZJwJUD8YWdQ7ryEQo_LcjtoOBOHOU9Y0fw,3085
 lcode/limits.py,sha256=oJzVQoMyTZ0_Fkpu5t3qxrf9v7Hv9S8U8BRQR5M1aKA,1237
 lcode/models.toml,sha256=lt2G64zzo_Ryxv2ISRSNZoVD_JqCqYqsM01n8WoXGs8,4098
 lcode/ollama.py,sha256=fELwqw7xqLH9TM7XvdI1pxqYZFeIRJBv-VSz9REdvwA,6516
-lcode/permissions.py,sha256=0HekNT4dupfSQTL58_8uNBrelldAvD2xB5kLehOy9QA,3928
+lcode/permissions.py,sha256=wJKwhJQx44AzjOFZCWwM4M2oUlPFUNYI2cIVfoBGGgc,3898
 lcode/render.py,sha256=gMvf4W3qkLUJ4Vot3az_hP_zRDAItJC9pP-68dHFkfA,1375
-lcode/repl.py,sha256=xmeX00g17OyznlGT2H8l-qIT68fPfm1EqhX_3uBHvew,16380
+lcode/repl.py,sha256=1InDmkMz286vuCOwRHNCTdBih_KekYkM4Ol52_g7C4s,20001
 lcode/sessions.py,sha256=wOR-J0EHgJxLSPboKPHnvBcp5VTUYTj3tZWgpsa6-K4,4013
 lcode/tools.py,sha256=97wPiabQuztMr4qsMgf_beNAFfraxSlU2195QJffFkg,25835
 lcode/web.py,sha256=vyxKbSRJTl1Lj3hj7Yd_NwTgbv0Xi6dup2YfUXjqp-Y,14579
-lcode_cli-0.2.0.dist-info/METADATA,sha256=g_YEh-2iFj2G9bSGAlOHIWrjoLNUnSxTpabdhg7abB0,8842
-lcode_cli-0.2.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-lcode_cli-0.2.0.dist-info/entry_points.txt,sha256=pZ_uDQ98UzVAHUQeXn5HeyQWKGSH3r3T5aPHuSB89eI,41
-lcode_cli-0.2.0.dist-info/licenses/LICENSE,sha256=JWjmoL7nNIC1XUa-dZm2hwLUgjUQMFo6k8APb0idNzs,1074
-lcode_cli-0.2.0.dist-info/RECORD,,
+lcode_cli-0.2.2.dist-info/METADATA,sha256=XQ3SNVJtZ6MAxIM90xpJVSLQ17uCvulOJ00kyhSNbco,9232
+lcode_cli-0.2.2.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+lcode_cli-0.2.2.dist-info/entry_points.txt,sha256=pZ_uDQ98UzVAHUQeXn5HeyQWKGSH3r3T5aPHuSB89eI,41
+lcode_cli-0.2.2.dist-info/licenses/LICENSE,sha256=JWjmoL7nNIC1XUa-dZm2hwLUgjUQMFo6k8APb0idNzs,1074
+lcode_cli-0.2.2.dist-info/RECORD,,