lcode-cli 0.36.0__tar.gz → 0.37.0__tar.gz

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/CHANGELOG.md

@@ -6,6 +6,19 @@ All notable changes to lcode are documented here. The format follows
 
 ## [Unreleased]
 
+## [0.37.0] - 2026-10-20
+
+### Added
+
+- Ollama's cloud models (tags ending in `cloud`, such as `minimax-m3.1-flash:cloud`) work as the
+  main model or as the stronger model when stuck, and lcode says what they are: what it sends goes
+  to ollama.com and is billed per token. The stronger-model panel said "free, on this machine" for
+  them; it now says ollama.com and shows the cost. A request Ollama refuses because it isn't signed
+  in says to run `ollama signin` (in Docker, with your container's name), and lcode skips the
+  local loading and GPU checks for them. The docs explain the setup and list the cloud models that
+  call tools, with prices and published coding scores: see
+  [Cloud models through Ollama](https://nasser1941.github.io/lcode/models/#cloud-models-through-ollama).
+
 ## [0.36.0] - 2026-10-18
 
 ### Changed
@@ -810,7 +823,8 @@ 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/v0.36.0...HEAD
+[Unreleased]: https://github.com/nasser1941/lcode/compare/v0.37.0...HEAD
+[0.37.0]: https://github.com/nasser1941/lcode/compare/v0.36.0...v0.37.0
 [0.36.0]: https://github.com/nasser1941/lcode/compare/v0.35.1...v0.36.0
 [0.35.1]: https://github.com/nasser1941/lcode/compare/v0.35.0...v0.35.1
 [0.35.0]: https://github.com/nasser1941/lcode/compare/v0.34.0...v0.35.0

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: lcode-cli
-Version: 0.36.0
+Version: 0.37.0
 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/

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/docs/configuration.md

@@ -45,7 +45,7 @@ lcode config path                      # print the file location
 | `notify_after` | `30` | Seconds a request runs before it notifies |
 | `review` | `off` | Before the answer, [review a change](usage.md#a-review-before-the-answer) against the request and send problems back to the model: `auto` or `off` |
 | `checks` | `auto` | Run the project's [checks](usage.md#checks-before-done) after a request changed files: `auto` (found from the project), `off`, or a command |
-| `escalate_model` | — | A [stronger model](usage.md#a-stronger-model-when-stuck) to ask, with your OK, when the model is stuck: `anthropic/…`, `openai/…`, `xai/…` (keys from `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `XAI_API_KEY`), `ollama/<model>`, or `custom/<model>` with `escalate_url` |
+| `escalate_model` | — | A [stronger model](usage.md#a-stronger-model-when-stuck) to ask, with your OK, when the model is stuck: `anthropic/…`, `openai/…`, `xai/…` (keys from `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `XAI_API_KEY`), `ollama/<model>` (a local model, or an [Ollama cloud model](models.md#cloud-models-through-ollama) like `ollama/glm-5.3-flash:cloud`), or `custom/<model>` with `escalate_url` |
 | `escalate_url` | — | Its server, when it isn't the provider's usual one: another Ollama, or any OpenAI-compatible API |
 | `escalate_price` | — | Its price in dollars per million tokens, input/output (e.g. `3/15`), for the cost shown before each use |
 | `repeat_limit` | `3` | Identical tool calls with identical results before lcode [steps in](how-it-works.md#when-the-model-repeats-itself); `0` turns it off, along with the checks for [unreachable sites](how-it-works.md#when-a-site-cant-be-reached) and [thinking in circles](how-it-works.md#when-a-reply-goes-nowhere) |

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/docs/models.md

@@ -85,6 +85,104 @@ context; set `--context` yourself. If a model prints tool calls as text instead
 lcode tries to recover them, but results are usually worse. To propose a model for the catalog, see
 [Contributing](contributing.md#adding-a-model-to-the-catalog).
 
+## Cloud models through Ollama
+
+Ollama also offers models that run on its own servers, with tags that end in `cloud`, such as
+`minimax-m3.1-flash:cloud`. Your Ollama passes the requests on, so lcode uses them like an installed
+model: as the main model, or as the [stronger model to ask when stuck](usage.md#a-stronger-model-when-stuck).
+What changes:
+
+- **Your code leaves the machine.** What lcode sends (your requests and the files it reads) goes to
+  ollama.com. lcode says so when a session starts, when you switch to one, and in `lcode doctor`.
+- **It's billed per token** to your ollama.com account (some models are free for a while).
+- **It needs an ollama.com account** and a connection to ollama.com.
+
+### Setting one up
+
+1. **Sign your Ollama in** to your ollama.com account, once. It prints a link to open in the
+   browser:
+
+    === "Ollama installed normally"
+
+        ```bash
+        ollama signin
+        ```
+
+    === "Ollama in Docker"
+
+        ```bash
+        docker exec -it <container> ollama signin
+        ```
+
+        `lcode doctor` shows this command with your container's name once a cloud model is set.
+
+2. **Add the model.** This stores a small reference, not the weights:
+
+    ```bash
+    ollama pull minimax-m3.1-flash:cloud      # in Docker: docker exec <container> ollama pull …
+    ```
+
+3. **Use it** as the main model, or as the stronger model when stuck:
+
+    ```bash
+    lcode --model minimax-m3.1-flash:cloud --context 256k    # or pick it by number in /models
+
+    lcode config set escalate_model ollama/minimax-m3.1-flash:cloud
+    lcode config set escalate_price 0.15/0.60                 # its price in/out, for the cost shown
+    ```
+
+    As the main model, give the context yourself: lcode defaults to 32K for models outside its
+    catalog. A larger window costs more, since every step sends the conversation again (the
+    repeated part at the lower *cached* price). As the stronger model, only a short brief goes out,
+    and only when you say yes: the panel shows `Where: … at ollama.com` and the cost.
+
+If a request fails with *this Ollama isn't signed in to an ollama.com account*, run the sign-in
+command the message shows.
+
+### Cheap coding models in Ollama's cloud
+
+The cloud models that call tools, cheapest first. Prices are in dollars per million tokens, from
+[ollama.com](https://ollama.com/search?c=cloud) on 2026-10-20. Check a model's page before you
+rely on a price: they change.
+
+- **TB 2.1** is the Terminal-Bench 2.1 score as published on the model's page. The makers measured
+  it themselves, in different setups, so it's a rough guide, not a ranking. A dash means the page
+  gives none.
+- **One question** is the most a question to the stronger model costs: a 15K-token brief, plus
+  lcode's 4K-token cap on the answer.
+- **DeepSeek** charges less off-peak. Its prices read off-peak / peak.
+
+| Model | Input | Cached | Output | Context | TB 2.1 | One question |
+|---|---|---|---|---|---|---|
+| `glm-5.3-flash:cloud` | $0.15 | $0.03 | $0.50 | 1M | 84.3 | $0.004 |
+| `minimax-m3.1-flash:cloud` | $0.15 | $0.015 | $0.60 | 976K | — | $0.005 |
+| `deepseek-v4.1-flash:cloud` | $0.15 / $0.30 | $0.003 / $0.006 | $0.60 / $1.20 | 1M | 90.6 | $0.005–$0.009 |
+| `minimax-m2.7:cloud` | $0.30 | $0.06 | $1.20 | 200K | — | $0.009 |
+| `nemotron-3-ultra:cloud` | $0.10 | $0.10 | $3.00 | 256K | — | $0.014 |
+| `mistral-large-3:675b-cloud` | $0.50 | — | $1.50 | 256K | — | $0.014 |
+| `minimax-m3:cloud` | $0.60 | $0.12 | $2.40 | 512K | — | $0.019 |
+| `mistral-large-4:cloud` | $0.68 | $0.07 | $2.09 | 1M | — | $0.019 |
+| `deepseek-v4-pro:cloud` | $0.66 / $1.32 | $0.022 / $0.044 | $1.98 / $3.96 | 1M | 87.9 | $0.018–$0.036 |
+| `kimi-k2.6:cloud` | $0.95 | $0.16 | $4.00 | 256K | — | $0.031 |
+| `kimi-k2.7-code:cloud` | $0.95 | $0.19 | $4.00 | 256K | — | $0.031 |
+| `muse-spark-open:cloud` | $1.25 | $0.15 | $4.25 | 1M | — | $0.036 |
+| `glm-5.2:cloud` | $1.40 | $0.26 | $4.40 | 976K | 81.0 | $0.039 |
+| `glm-5.3:cloud` | $1.40 | $0.26 | $4.40 | 1M | 88.2 | $0.039 |
+| `kimi-k3:cloud` | $3.00 | $0.30 | $15.00 | 1M | 88.3 | $0.106 |
+
+- **For the stronger model, the first three cost under a cent a question.**
+  - `deepseek-v4.1-flash` has the highest published score (90.6, DeepSeek's own measurement).
+  - `glm-5.3-flash` is the cheapest.
+  - `minimax-m3.1-flash` is free until 22 October 2026.
+- **GLM-5.3, DeepSeek V4 Pro and Kimi K3** publish similar scores (88.2, 87.9, 88.3) for 4 to 25
+  times the price.
+- **Not in the table:** `beam`, `gemma4:31b-cloud`, `nemotron-3-super`, `nemotron-3-nano` and
+  `clef` have cloud versions too, but list no price on their pages. Clef is an image model, not a
+  coding one.
+
+To set a price for the cost shown, use the input/output pair from the table, e.g.
+`lcode config set escalate_price 0.15/0.50` for `glm-5.3-flash:cloud`.
+
 ## Choosing a context window
 
 The **context window** is how much text the model can see at once: the conversation, files it has

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/docs/quickstart.md

@@ -12,7 +12,7 @@ lcode
 
 ```text
 ╭──────────────────────────────────────────────╮
-│ lcode v0.36.0 — local coding agent           │
+│ lcode v0.37.0 — local coding agent           │
 │                                              │
 │ model    lcode-qwen3.6-35b                   │
 │ context  256K tokens                         │

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/docs/usage.md

@@ -219,7 +219,8 @@ would have to read the whole conversation again. On a small GPU that's tens of s
 ## A stronger model when stuck
 
 Some problems are beyond a local model. When it's stuck, lcode can ask a stronger one for
-advice: a cloud model with your API key, or a bigger local model. The local model gets the advice
+advice: a cloud model with your API key, one of [Ollama's cloud models](models.md#cloud-models-through-ollama)
+(less than a cent a question for some), or a bigger local model. The local model gets the advice
 and carries on with its own tools. It's off until you choose the model:
 
 ```bash
@@ -227,6 +228,7 @@ lcode config set escalate_model anthropic/<model>   # with ANTHROPIC_API_KEY in
 lcode config set escalate_model openai/<model>      # OPENAI_API_KEY
 lcode config set escalate_model xai/<model>         # XAI_API_KEY
 lcode config set escalate_model ollama/qwen3.8-27b  # a bigger local model: free, and nothing leaves
+lcode config set escalate_model ollama/glm-5.3-flash:cloud  # Ollama's cloud, after `ollama signin`
 lcode config set escalate_price 3/15                # dollars per million tokens in/out, for the cost
 ```
 
@@ -257,7 +259,8 @@ a stronger model can't reach it either. You can also ask at any time: `/escalate
 - **Keys** come from environment variables, are read when needed, and go only to their own
   provider. lcode never stores them.
 - **Cost.** The token count is always shown; the price only when you set `escalate_price`, since
-  prices change. A local model is free.
+  prices change. A local model is free; an Ollama cloud model isn't, and the panel says it goes to
+  ollama.com.
 - **Another server:** `escalate_url` points at another Ollama (`ollama/<model>`) or any OpenAI
   API (`custom/<model>`, key in `LCODE_ESCALATE_API_KEY`).
 - `lcode -p` can't ask, so it doesn't escalate unless you add `--escalate`, which is your OK for

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/src/lcode/__init__.py

@@ -3,7 +3,7 @@
 From a program: `from lcode import Session` (see lcode.api).
 """
 
-__version__ = "0.36.0"
+__version__ = "0.37.0"
 
 API = ("Session", "Result", "Options", "SetupError")
 

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/src/lcode/agent.py

@@ -45,6 +45,7 @@ from lcode import (
 from lcode import context as context_tools
 from lcode import memory as memory_notes
 from lcode.checkpoints import Checkpoints
+from lcode.cloud import is_cloud
 from lcode.config import format_tokens
 from lcode.jobs import Jobs
 from lcode.mcp import McpManager
@@ -1011,8 +1012,8 @@ class Agent:
     def before_request(self, progress: Progress) -> residency.LoadWatch | None:
         """Set the status line for what comes before the first token: loading the model if it isn't in memory
         (watched until it is), then reading the prompt. Returns the watch while the model loads."""
-        if getattr(self.ollama, "kind", "ollama") != "ollama":
-            return None
+        if getattr(self.ollama, "kind", "ollama") != "ollama" or is_cloud(self.settings.model):
+            return None  # another server loads models itself; an Ollama cloud model isn't loaded here at all
         model, context = self.settings.model, self.settings.context
         fresh = max(0, conversation_chars(self.messages) - self.sent_chars) // 3
         where = residency.placement(self.ollama, model)

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/src/lcode/cli.py

@@ -21,6 +21,7 @@ from rich.table import Table
 from lcode import __version__, backends, catalog, config, limits, web
 from lcode.agent import Settings
 from lcode.catalog import ModelSpec
+from lcode.cloud import is_cloud, signin_command
 from lcode.config import ConfigError, format_tokens, parse_context
 from lcode.hardware import Hardware, detect
 from lcode.ollama import MIN_VERSION, Ollama, OllamaError, redact, version_tuple
@@ -384,6 +385,13 @@ def cmd_doctor(args) -> None:
     try:
         model, spec = resolve_model(ollama, cfg["model"])
         line("Model", f"{cfg['model']} → {model}", True)
+        if is_cloud(model):
+            line(
+                "",
+                "runs in Ollama's cloud: what lcode sends goes to ollama.com, billed per token, and this Ollama "
+                f"must be signed in once: {signin_command(ollama.host)}",
+                None,
+            )
         ctx, note = choose_context(ollama, model, spec, cfg["context"], hw)
         if spec:
             from lcode.subagents import parallel_slots

lcode_cli-0.37.0/src/lcode/cloud.py

@@ -0,0 +1,46 @@
+"""Ollama's cloud models: tags like `minimax-m3.1-flash:cloud` run on ollama.com, through the local Ollama.
+
+They look like any installed model to lcode (Ollama lists them, and they chat and call tools), but nothing about
+them is local: what lcode sends goes to ollama.com, it's billed per token, and it needs the Ollama signed in to an
+ollama.com account (`ollama signin`). So lcode says so where it matters (`lcode doctor`, the start of a session, the
+stronger-model panel), skips what only makes sense for a local model (loading it into memory, GPU fit), and turns
+Ollama's bare `Unauthorized` into the command that fixes it.
+"""
+
+from __future__ import annotations
+
+
+def is_cloud(model: str | None) -> bool:
+    """Whether an Ollama model name is one of Ollama's cloud models: its tag is `cloud` or ends with `-cloud`."""
+    name = (model or "").strip().lower()
+    if ":" not in name:
+        return False
+    tag = name.rsplit(":", 1)[1]
+    return tag == "cloud" or tag.endswith("-cloud")
+
+
+def signin_command(host: str) -> str:
+    """How to sign the Ollama at `host` in to ollama.com: inside its container when it runs in Docker."""
+    try:
+        from lcode import update
+
+        container = update.find_container(host) if update.docker_available() else None
+    except Exception:  # Docker missing, or not answering: the plain command is still right for most installs
+        container = None
+    return f"docker exec -it {container.name} ollama signin" if container else "ollama signin"
+
+
+def unauthorized(model: str, host: str) -> str:
+    """The error for a cloud model that Ollama refused: what it means and the command to run."""
+    return (
+        f"{model} runs in Ollama's cloud (ollama.com), and this Ollama isn't signed in to an ollama.com account. "
+        f"Sign it in with `{signin_command(host)}`, then try again."
+    )
+
+
+def notice(model: str) -> str:
+    """What to know when a cloud model is lcode's main model."""
+    return (
+        f"{model} runs in Ollama's cloud: what lcode sends (your requests and the files it reads) goes to "
+        "ollama.com, and Ollama bills it per token."
+    )

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/src/lcode/escalate.py

@@ -23,6 +23,7 @@ from rich.panel import Panel
 from rich.text import Text
 
 from lcode import context as context_tools
+from lcode.cloud import is_cloud
 from lcode.ollama import Ollama, OllamaError, redact
 
 if TYPE_CHECKING:
@@ -76,14 +77,23 @@ class Target:
     @property
     def cloud(self) -> bool:
         """Paid per token: a cloud provider, or an OpenAI-compatible API elsewhere."""
-        return self.provider in ("openai", "anthropic", "xai") or (self.provider == "custom" and not self.local)
+        return (
+            self.provider in ("openai", "anthropic", "xai")
+            or (self.provider == "custom" and not self.local)
+            or (self.provider == "ollama" and is_cloud(self.model))  # an Ollama cloud model runs on ollama.com
+        )
 
     @property
     def where(self) -> str:
+        if self.provider == "ollama" and is_cloud(self.model):
+            return "ollama.com, through " + ("this machine's Ollama" if self.local else self._host())
         if self.url:
-            return re.sub(r"^https?://", "", redact(self.url)).split("/")[0]
+            return self._host()
         return "this machine"
 
+    def _host(self) -> str:
+        return re.sub(r"^https?://", "", redact(self.url)).split("/")[0]
+
 
 def target(setting: str | None, url: str | None = None) -> Target | None:
     """The stronger model from the settings (None: escalation is off). Raises EscalateError for a bad setting."""
@@ -105,6 +115,8 @@ def target(setting: str | None, url: str | None = None) -> Target | None:
         raise EscalateError(f"escalate_model {setting!r} names no model")
     if provider == "custom" and not url:
         raise EscalateError("a custom/… escalate_model needs escalate_url, the server's OpenAI-compatible address")
+    if provider == "ollama" and is_cloud(model):
+        name = "Ollama cloud"
     return Target(provider, model.strip(), (url or base).rstrip("/"), key_env, f"{model.strip()} ({name})")
 
 

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/src/lcode/ollama.py

@@ -9,6 +9,8 @@ from urllib.parse import urlsplit, urlunsplit
 
 import requests
 
+from lcode.cloud import is_cloud, unauthorized
+
 MIN_VERSION = (0, 30, 0)  # first release that runs the Qwen3.5/3.6 hybrid-attention architecture
 
 
@@ -49,6 +51,8 @@ class Ollama:
             r = requests.post(self._url(path), json=payload, timeout=timeout)
         except requests.RequestException as e:
             raise OllamaError(f"cannot reach Ollama at {redact(self.host)}: {e}") from e
+        if r.status_code == 401 and is_cloud(payload.get("model")):
+            raise OllamaError(unauthorized(payload["model"], self.host))
         if r.status_code != 200:
             raise OllamaError(f"Ollama {path} failed ({r.status_code}): {r.text[:300]}")
         return r.json()
@@ -164,6 +168,8 @@ class Ollama:
         if on_open:
             on_open(r)
         with r:
+            if r.status_code == 401 and is_cloud(payload.get("model")):
+                raise OllamaError(unauthorized(payload["model"], self.host))
             if r.status_code != 200:
                 raise OllamaError(f"Ollama error {r.status_code}: {r.text[:500]}")
             for line in r.iter_lines():

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/src/lcode/repl.py

@@ -45,6 +45,8 @@ from lcode import memory as memory_notes
 from lcode.agent import AUTO_COMPACT_RATIO, INIT_PROMPT, Agent
 from lcode.catalog import MIN_USEFUL_CONTEXT
 from lcode.checkpoints import Checkpoint, CheckpointError, Restore
+from lcode.cloud import is_cloud
+from lcode.cloud import notice as cloud_notice
 from lcode.config import PERMISSION_MODES, STATE_DIR, ConfigError, format_tokens, parse_context
 from lcode.hardware import Hardware
 from lcode.ollama import OllamaError
@@ -876,6 +878,8 @@ def switch_model(agent: Agent, wanted: str, hardware: Hardware) -> None:
     agent._vision = False  # the model that looks at images goes with the model: decide again
     agent.messages[0]["content"] = agent.system_prompt()
     c.print(f"[green]Switched to {name}[/] (context {format_tokens(s.context)}).")
+    if is_cloud(name):
+        agent.say(cloud_notice(name))
     warning = residency.dense_warning(agent.ollama, name, s.context, hardware)
     if warning:
         agent.say(warning, warning=True)
@@ -1256,6 +1260,8 @@ def repl(agent: Agent, prompt: str | None, hardware: Hardware, cont: bool = Fals
         run_safely(agent, prompt)
         return
     banner(agent)
+    if is_cloud(agent.settings.model):
+        agent.say(cloud_notice(agent.settings.model))
     warning = residency.dense_warning(agent.ollama, agent.settings.model, agent.settings.context, hardware)
     if warning:
         agent.say(warning, warning=True)
@@ -1286,6 +1292,8 @@ def repl(agent: Agent, prompt: str | None, hardware: Hardware, cont: bool = Fals
 
 def preload(agent: Agent, session: PromptSession | None = None) -> None:
     """Start loading the model in the background so the first answer comes sooner; the status bar says so."""
+    if is_cloud(agent.settings.model):
+        return  # it runs on ollama.com: there's nothing to load here
     where = residency.placement(agent.ollama, agent.settings.model)
     if where is not None and (not where.context or where.context == agent.settings.context):
         return  # already in memory

{lcode_cli-0.36.0 → lcode_cli-0.37.0}/src/lcode/residency.py

@@ -15,6 +15,7 @@ import time
 from dataclasses import dataclass
 
 from lcode import catalog
+from lcode.cloud import is_cloud
 from lcode.ollama import OllamaError
 
 GB = 1e9
@@ -97,6 +98,8 @@ def expected_share(model: str, context: int, hardware) -> float | None:
 
 def dense_warning(ollama, model: str, context: int, hardware) -> str:
     """For a dense model that won't fit on the GPU: what that means and what to do. Empty otherwise."""
+    if is_cloud(model):
+        return ""  # it runs on ollama.com
     if hardware is None or hardware.unified or is_moe(ollama, model) is not False:
         return ""
     spec = catalog.find(model)

lcode_cli-0.37.0/tests/test_cloud.py

@@ -0,0 +1,86 @@
+"""Ollama's cloud models (tags like minimax-m3.1-flash:cloud): lcode says where they run and what they cost,
+skips what only makes sense for a local model, and says how to sign in when Ollama refuses them."""
+
+import threading
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+
+import pytest
+
+from conftest import output
+from lcode import cloud, escalate, residency
+from lcode.hardware import Hardware
+from lcode.ollama import Ollama, OllamaError
+from lcode.repl import handle_command, preload
+
+LAPTOP = Hardware("linux", "x", 31, "RTX 4080 Laptop", 12)
+
+
+def test_cloud_tags_are_recognized():
+    for name in ("minimax-m3.1-flash:cloud", "deepseek-v4-pro:0813-cloud", "mistral-large-3:675b-cloud", "X:CLOUD"):
+        assert cloud.is_cloud(name), name
+    for name in ("qwen3.6:35b-a3b-coding", "lcode-qwen3.6-35b", "my-cloud-model:latest", "cloud", None, ""):
+        assert not cloud.is_cloud(name), name
+
+
+class Refuses(BaseHTTPRequestHandler):
+    def log_message(self, *args):
+        pass
+
+    def do_POST(self):
+        body = b'{"error":"Unauthorized"}'
+        self.send_response(401)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(body)))
+        self.end_headers()
+        self.wfile.write(body)
+
+
+@pytest.fixture
+def refusing_ollama(monkeypatch):
+    monkeypatch.setattr(cloud, "signin_command", lambda host: "docker exec -it my-ollama ollama signin")
+    server = ThreadingHTTPServer(("127.0.0.1", 0), Refuses)
+    threading.Thread(target=server.serve_forever, daemon=True).start()
+    yield Ollama(f"http://127.0.0.1:{server.server_address[1]}")
+    server.shutdown()
+
+
+def test_an_ollama_that_isnt_signed_in_says_how_to_fix_it(refusing_ollama):
+    payload = {"model": "minimax-m3.1-flash:cloud", "messages": [{"role": "user", "content": "hi"}]}
+    with pytest.raises(OllamaError) as streamed:
+        list(refusing_ollama.chat_stream(payload))
+    with pytest.raises(OllamaError) as asked:
+        refusing_ollama.chat(payload)
+    for error in (streamed.value, asked.value):
+        assert "runs in Ollama's cloud (ollama.com)" in str(error)
+        assert "`docker exec -it my-ollama ollama signin`" in str(error)
+    with pytest.raises(OllamaError, match="Ollama error 401"):  # a local model keeps the plain error
+        list(refusing_ollama.chat_stream({**payload, "model": "qwen3.6:35b-a3b-coding"}))
+
+
+def test_the_stronger_model_panel_tells_where_a_cloud_model_runs_and_what_it_costs():
+    t = escalate.target("ollama/minimax-m3.1-flash:cloud")
+    assert t.label == "minimax-m3.1-flash:cloud (Ollama cloud)" and t.cloud
+    assert t.where == "ollama.com, through this machine's Ollama"
+    assert escalate.cost_line(t, 12000, None).startswith("unknown: set escalate_price")
+    assert escalate.cost_line(t, 12000, (0.15, 0.6)).startswith("about $0.002 to $0.004")
+    remote = escalate.target("ollama/glm-5.3-flash:cloud", "http://gpu-box:11434")
+    assert remote.where == "ollama.com, through gpu-box:11434"
+    local = escalate.target("ollama/qwen3.8-27b")
+    assert not local.cloud and local.where == "this machine"
+    assert escalate.cost_line(local, 12000, None) == "free: it runs on this machine"
+
+
+def test_a_cloud_model_skips_what_only_a_local_model_needs(make_agent):
+    agent = make_agent(model="minimax-m3.1-flash:cloud")
+    agent.ollama.load = lambda *a, **k: pytest.fail("nothing to load: it runs on ollama.com")
+    preload(agent)
+    assert agent.before_request(progress=None) is None
+    assert residency.dense_warning(agent.ollama, "minimax-m3.1-flash:cloud", 262144, LAPTOP) == ""
+
+
+def test_switching_to_a_cloud_model_says_where_the_code_goes(agent, monkeypatch):
+    agent.ollama.installed_names = lambda: {"lcode-qwen3.6-35b", "minimax-m3.1-flash:cloud"}
+    handle_command(agent, "/model minimax-m3.1-flash:cloud", LAPTOP)
+    text = " ".join(output(agent).split())
+    assert "Switched to minimax-m3.1-flash:cloud" in text
+    assert "runs in Ollama's cloud: what lcode sends (your requests and the files it reads) goes to ollama.com" in text