euron-code 0.4.0__tar.gz → 0.4.2__tar.gz

{euron_code-0.4.0 → euron_code-0.4.2}/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## 0.4.2 (2026-11-05)
+
+### Changed
+- Documentation and messages describe what Euron Code does for you, without internal service details.
+
+## 0.4.1 (2026-11-05)
+
+### Fixed
+- Pasting text with emoji into a Windows terminal crashed the prompt ("surrogates not allowed") and
+  then failed every request. Text is now repaired before it is saved or sent.
+
+### Changed
+- Clearer privacy wording; the limits section shows the daily allowance and where to track usage.
+
 ## 0.4.0 (2026-11-05)
 
 ### Run the app, not just the tests

{euron_code-0.4.0 → euron_code-0.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: euron-code
-Version: 0.4.0
+Version: 0.4.2
 Summary: Euron Code: an agentic coding assistant in your terminal for Euron Plus and Super 30 students.
 Project-URL: Homepage, https://euron.one/code-agent
 Author-email: Euron <contact@euron.one>
@@ -105,8 +105,7 @@ That's it. Press **Esc** to stop it, **Ctrl-D** to quit.
   improve `EURON.md`.
 - **Context management.** Old tool output is cleared and long conversations are summarised before
   they fill the context, so it never runs out mid-task. Long answers continue by themselves.
-- **Token saving.** Unchanged files are not re-read, big files are read in parts, the prompt is kept
-  cache-friendly for the servers.
+- **Token saving.** Unchanged files are not re-read and big files are read in parts.
 - **Local cache.** `.euron/cache/` remembers the repo map and file list, so new sessions start fast.
   Safe to delete; never holds secrets; git-ignored.
 - **Runs your app.** It can start your dev server in the background, check it answers
@@ -167,23 +166,21 @@ Shift+Tab cycles default -> acceptEdits -> plan, and reaches bypass only if you
 
 ## Where your data goes
 
-- Your prompts and the code the agent reads are processed on GPUs Euron rents from Vast.ai hosts. They
-  are not logged. The host operator could technically see them, so never paste secrets.
-- Images you attach are sent to Google Gemini to be described in text for the coding model; they are not
-  stored. You are told this the first time you attach one.
+- Your code stays on your computer.
+- Images you attach are turned into a text description by Euron's image understanding and are not stored.
 - One login at a time: signing in on another computer signs this one out.
+- Don't paste passwords or API keys into prompts.
 
 ## Limits and value
 
-Your plan has a token allowance per **day**, **week**, **month** and **year** (Super 30 has a bigger one).
-`/usage` (or `euron usage`) shows each with a bar, what is left and when it refills, in your local time.
-Days, weeks (Monday), months and years start at midnight IST. If a limit is reached, Euron Code says
-which one and when it refills; nothing else breaks.
+**10 million AI tokens. Every day.** Build more. Experiment more. Create without constantly worrying
+about tokens. Included with Euron Plus and Super 30.
 
-It also shows what your usage is worth at a reference price, for example "Used today: 412,300 tokens
-≈ $1.07 (₹94) at Claude Sonnet 5.5 API list prices · included in your plan", and what your monthly
-allowance is worth. That is what the same tokens would cost on a paid API. **It is not a bill: you
-pay nothing extra.**
+<sub>Up to 10 million tokens per day, subject to fair-use policies, model availability, and plan limits.</sub>
+
+Track everything with `/usage` (or `euron usage`) and at https://euron.one/code-agent/usage: what you
+used today, this week, this month and this year, what is left and when it refills, in your local time.
+If a limit is reached, Euron Code says which one and when it refills; nothing else breaks.
 
 ## Run and check your app
 
@@ -221,7 +218,7 @@ running Euron Code in another terminal, you are asked whether to take over (`-p
 The approval page approves for whichever Euron account is signed in on euron.one in that browser, so
 to switch accounts sign in there with the other account first (or open the link in a private window).
 If no browser opens (SSH, WSL), copy the link it prints. The key is kept in the system keychain, or in
-`~/.euron/credentials.json` (readable only by you). To revoke a key on the server, delete it at
+`~/.euron/credentials.json` (readable only by you). To revoke a login, remove it at
 https://euron.one/code-agent.
 
 Optional extras: `pip install "euron-code[images]"` (image resizing, clipboard), `"euron-code[postgres]"`,
@@ -244,7 +241,7 @@ Optional extras: `pip install "euron-code[images]"` (image resizing, clipboard),
 | `/help` | list commands, your own commands and skills, and the shortcuts |
 | `/status`, `/whoami` | account, key, API, model, mode, session, uptime, quota |
 | `/usage` (`/users`) | quota per period, refill times, value, sessions, tasks, cache share, last 30 days |
-| `/cost`, `/context` | session tokens, server cache, savings, session value; what fills the context |
+| `/cost`, `/context` | what this session used; what fills the context |
 | `/model [id]`, `/effort` | pick or set the model; reasoning effort |
 | `/compact [focus]`, `/clear` | summarise to free context; start fresh |
 | `/resume [id]`, `/rewind`, `/export [file]` | saved sessions; undo the last turn; save as Markdown |
@@ -393,7 +390,7 @@ Hooks are your own shell commands that run at fixed points. Put them in `setting
 | `Stop` | when the model finishes its answer | stderr goes to the model and it continues (at most twice) |
 
 Any other non-zero exit is shown as a warning and blocks nothing. `matcher` is a regular expression
-over the tool name; Claude Code names (`Edit`, `Write`, `MultiEdit`, `Read`, `Bash`, `Grep`, `Glob`,
+over the tool name; common names (`Edit`, `Write`, `MultiEdit`, `Read`, `Bash`, `Grep`, `Glob`,
 `WebFetch`) and Euron Code names (`edit_file`, `bash`, ...) both work. The command runs in the project
 folder with `cmd.exe` on Windows and `sh` elsewhere, and gets one JSON object on stdin: `event`,
 `session_id`, `cwd`, `tool_name`, `tool_input`, `tool_output` (PostToolUse) or `prompt`. Environment:
@@ -408,31 +405,22 @@ always run.
 
 ## Context and tokens (automatic)
 
-The default model has a 32k-token context and writes at most about 8k tokens per step. Euron Code
-manages that the way Claude Code does, with nothing to set up:
-
-- **Room for the answer.** An output budget (about 8k) is always kept free; "100% full" means the
-  prompt leaves no more than that. Each request asks for as many output tokens as really fit, and a
-  request that would not fit is compacted first.
-- **Clearing.** From 50% full, tool outputs are replaced with one-line stubs, biggest and oldest first,
-  until it is under 40%. The latest step is never touched, and each stub says what to re-read (for
-  example `read_file src/app.py lines 1-200`). The note shows real numbers: "freed 9,400 tokens,
-  now 38%".
-- **Summary.** At 70%, or when the next request would not fit, older messages are summarised: the task,
-  decisions, files changed, commands and results, the last error and open todos.
-- **Long answers and big edits.** An answer cut by the output limit continues by itself. A tool call cut
-  in the middle (a huge file write) is never run; the model is asked to make the change in smaller
-  steps. If the model spent its whole budget thinking, it retries with less reasoning.
+Euron Code manages the conversation for you, with nothing to set up:
+
+- **Always room to answer.** Each request leaves space for the reply; a conversation that is getting
+  full is tidied up first.
+- **Clearing.** Old tool output is replaced with one-line notes that say what to re-read (for example
+  `read_file src/app.py lines 1-200`), so the agent keeps going without losing track.
+- **Summary.** Long conversations are summarised: the task, decisions, files changed, commands and
+  results, the last error and open todos.
+- **Long answers and big edits.** An answer that gets cut off continues by itself. A huge edit that gets
+  cut off is never applied half-way; the change is made in smaller steps instead.
 - **Reasoning effort** is `medium` by default and `low` for quick follow-ups ("thanks", "continue");
   change it with `/effort low|medium|high`.
-- **Reads.** `read_file` reads 200 lines at a time and stops before about 6k tokens; a file over 2,000
-  lines returns an outline of its definitions first. Re-reading an unchanged file returns a one-line
-  note instead of the content.
-- **Cache-friendly.** The system prompt and tool list never change during a session, so the servers can
-  reuse their prefix cache; changing data goes at the end of your message.
+- **Reads.** Files are read in parts; a very large file returns an outline first. Re-reading an
+  unchanged file returns a one-line note instead of the content.
 
-`/cost` and `/context` show what was sent, how much the server served from its cache, and how many
-tokens these measures kept out of the context.
+`/cost` and `/context` show what this session used and what fills the context.
 
 ## Non-interactive use (scripts, CI)
 
@@ -493,9 +481,8 @@ the connection itself is opened read-only. To let it write (local dev databases
 | `webFetch` | `true` | allow the web page tool (it still asks per site) |
 | `db.connections.<name>` | | database DSNs |
 
-Environment variables: `EURON_CODE_API` (gateway URL, default
-`https://api.euron.one/api/v1/code-agent`), `EURON_API_KEY` (use a key without logging in, for CI),
-`EURON_HOME` (instead of `~/.euron`), `EURON_NO_BROWSER=1`.
+Environment variables: `EURON_API_KEY` (use a key without logging in, for CI), `EURON_HOME` (instead of
+`~/.euron`), `EURON_NO_BROWSER=1`.
 
 ## In VS Code
 
@@ -531,13 +518,11 @@ and the keychain.
 
 ## Privacy and safety
 
-- Your files are only sent as part of the conversation with Euron's model (on GPUs Euron rents from
-  Vast.ai, not logged), and only what the agent reads; attached images go to Google Gemini to be described
-  and are not stored. There is no telemetry.
+- Your code stays on your computer: only the parts the agent reads are sent, as part of the conversation
+  with Euron's model. Attached images are turned into text by Euron's image understanding and are not
+  stored.
 - Your key is never printed in full and never logged.
 - Edits and commands ask first. Files outside the project folder always ask, even to read.
-- Each request carries a random session id and task id so your usage page can count sessions and
-  tasks. Nothing else about the conversation is stored by the gateway.
 - Hooks are commands you configure; project hooks only run after you trust them.
 - Text inside your files, web pages and command output is treated as data, not instructions.
 

{euron_code-0.4.0 → euron_code-0.4.2}/README.md

@@ -39,8 +39,7 @@ That's it. Press **Esc** to stop it, **Ctrl-D** to quit.
   improve `EURON.md`.
 - **Context management.** Old tool output is cleared and long conversations are summarised before
   they fill the context, so it never runs out mid-task. Long answers continue by themselves.
-- **Token saving.** Unchanged files are not re-read, big files are read in parts, the prompt is kept
-  cache-friendly for the servers.
+- **Token saving.** Unchanged files are not re-read and big files are read in parts.
 - **Local cache.** `.euron/cache/` remembers the repo map and file list, so new sessions start fast.
   Safe to delete; never holds secrets; git-ignored.
 - **Runs your app.** It can start your dev server in the background, check it answers
@@ -101,23 +100,21 @@ Shift+Tab cycles default -> acceptEdits -> plan, and reaches bypass only if you
 
 ## Where your data goes
 
-- Your prompts and the code the agent reads are processed on GPUs Euron rents from Vast.ai hosts. They
-  are not logged. The host operator could technically see them, so never paste secrets.
-- Images you attach are sent to Google Gemini to be described in text for the coding model; they are not
-  stored. You are told this the first time you attach one.
+- Your code stays on your computer.
+- Images you attach are turned into a text description by Euron's image understanding and are not stored.
 - One login at a time: signing in on another computer signs this one out.
+- Don't paste passwords or API keys into prompts.
 
 ## Limits and value
 
-Your plan has a token allowance per **day**, **week**, **month** and **year** (Super 30 has a bigger one).
-`/usage` (or `euron usage`) shows each with a bar, what is left and when it refills, in your local time.
-Days, weeks (Monday), months and years start at midnight IST. If a limit is reached, Euron Code says
-which one and when it refills; nothing else breaks.
+**10 million AI tokens. Every day.** Build more. Experiment more. Create without constantly worrying
+about tokens. Included with Euron Plus and Super 30.
 
-It also shows what your usage is worth at a reference price, for example "Used today: 412,300 tokens
-≈ $1.07 (₹94) at Claude Sonnet 5.5 API list prices · included in your plan", and what your monthly
-allowance is worth. That is what the same tokens would cost on a paid API. **It is not a bill: you
-pay nothing extra.**
+<sub>Up to 10 million tokens per day, subject to fair-use policies, model availability, and plan limits.</sub>
+
+Track everything with `/usage` (or `euron usage`) and at https://euron.one/code-agent/usage: what you
+used today, this week, this month and this year, what is left and when it refills, in your local time.
+If a limit is reached, Euron Code says which one and when it refills; nothing else breaks.
 
 ## Run and check your app
 
@@ -155,7 +152,7 @@ running Euron Code in another terminal, you are asked whether to take over (`-p
 The approval page approves for whichever Euron account is signed in on euron.one in that browser, so
 to switch accounts sign in there with the other account first (or open the link in a private window).
 If no browser opens (SSH, WSL), copy the link it prints. The key is kept in the system keychain, or in
-`~/.euron/credentials.json` (readable only by you). To revoke a key on the server, delete it at
+`~/.euron/credentials.json` (readable only by you). To revoke a login, remove it at
 https://euron.one/code-agent.
 
 Optional extras: `pip install "euron-code[images]"` (image resizing, clipboard), `"euron-code[postgres]"`,
@@ -178,7 +175,7 @@ Optional extras: `pip install "euron-code[images]"` (image resizing, clipboard),
 | `/help` | list commands, your own commands and skills, and the shortcuts |
 | `/status`, `/whoami` | account, key, API, model, mode, session, uptime, quota |
 | `/usage` (`/users`) | quota per period, refill times, value, sessions, tasks, cache share, last 30 days |
-| `/cost`, `/context` | session tokens, server cache, savings, session value; what fills the context |
+| `/cost`, `/context` | what this session used; what fills the context |
 | `/model [id]`, `/effort` | pick or set the model; reasoning effort |
 | `/compact [focus]`, `/clear` | summarise to free context; start fresh |
 | `/resume [id]`, `/rewind`, `/export [file]` | saved sessions; undo the last turn; save as Markdown |
@@ -327,7 +324,7 @@ Hooks are your own shell commands that run at fixed points. Put them in `setting
 | `Stop` | when the model finishes its answer | stderr goes to the model and it continues (at most twice) |
 
 Any other non-zero exit is shown as a warning and blocks nothing. `matcher` is a regular expression
-over the tool name; Claude Code names (`Edit`, `Write`, `MultiEdit`, `Read`, `Bash`, `Grep`, `Glob`,
+over the tool name; common names (`Edit`, `Write`, `MultiEdit`, `Read`, `Bash`, `Grep`, `Glob`,
 `WebFetch`) and Euron Code names (`edit_file`, `bash`, ...) both work. The command runs in the project
 folder with `cmd.exe` on Windows and `sh` elsewhere, and gets one JSON object on stdin: `event`,
 `session_id`, `cwd`, `tool_name`, `tool_input`, `tool_output` (PostToolUse) or `prompt`. Environment:
@@ -342,31 +339,22 @@ always run.
 
 ## Context and tokens (automatic)
 
-The default model has a 32k-token context and writes at most about 8k tokens per step. Euron Code
-manages that the way Claude Code does, with nothing to set up:
-
-- **Room for the answer.** An output budget (about 8k) is always kept free; "100% full" means the
-  prompt leaves no more than that. Each request asks for as many output tokens as really fit, and a
-  request that would not fit is compacted first.
-- **Clearing.** From 50% full, tool outputs are replaced with one-line stubs, biggest and oldest first,
-  until it is under 40%. The latest step is never touched, and each stub says what to re-read (for
-  example `read_file src/app.py lines 1-200`). The note shows real numbers: "freed 9,400 tokens,
-  now 38%".
-- **Summary.** At 70%, or when the next request would not fit, older messages are summarised: the task,
-  decisions, files changed, commands and results, the last error and open todos.
-- **Long answers and big edits.** An answer cut by the output limit continues by itself. A tool call cut
-  in the middle (a huge file write) is never run; the model is asked to make the change in smaller
-  steps. If the model spent its whole budget thinking, it retries with less reasoning.
+Euron Code manages the conversation for you, with nothing to set up:
+
+- **Always room to answer.** Each request leaves space for the reply; a conversation that is getting
+  full is tidied up first.
+- **Clearing.** Old tool output is replaced with one-line notes that say what to re-read (for example
+  `read_file src/app.py lines 1-200`), so the agent keeps going without losing track.
+- **Summary.** Long conversations are summarised: the task, decisions, files changed, commands and
+  results, the last error and open todos.
+- **Long answers and big edits.** An answer that gets cut off continues by itself. A huge edit that gets
+  cut off is never applied half-way; the change is made in smaller steps instead.
 - **Reasoning effort** is `medium` by default and `low` for quick follow-ups ("thanks", "continue");
   change it with `/effort low|medium|high`.
-- **Reads.** `read_file` reads 200 lines at a time and stops before about 6k tokens; a file over 2,000
-  lines returns an outline of its definitions first. Re-reading an unchanged file returns a one-line
-  note instead of the content.
-- **Cache-friendly.** The system prompt and tool list never change during a session, so the servers can
-  reuse their prefix cache; changing data goes at the end of your message.
+- **Reads.** Files are read in parts; a very large file returns an outline first. Re-reading an
+  unchanged file returns a one-line note instead of the content.
 
-`/cost` and `/context` show what was sent, how much the server served from its cache, and how many
-tokens these measures kept out of the context.
+`/cost` and `/context` show what this session used and what fills the context.
 
 ## Non-interactive use (scripts, CI)
 
@@ -427,9 +415,8 @@ the connection itself is opened read-only. To let it write (local dev databases
 | `webFetch` | `true` | allow the web page tool (it still asks per site) |
 | `db.connections.<name>` | | database DSNs |
 
-Environment variables: `EURON_CODE_API` (gateway URL, default
-`https://api.euron.one/api/v1/code-agent`), `EURON_API_KEY` (use a key without logging in, for CI),
-`EURON_HOME` (instead of `~/.euron`), `EURON_NO_BROWSER=1`.
+Environment variables: `EURON_API_KEY` (use a key without logging in, for CI), `EURON_HOME` (instead of
+`~/.euron`), `EURON_NO_BROWSER=1`.
 
 ## In VS Code
 
@@ -465,13 +452,11 @@ and the keychain.
 
 ## Privacy and safety
 
-- Your files are only sent as part of the conversation with Euron's model (on GPUs Euron rents from
-  Vast.ai, not logged), and only what the agent reads; attached images go to Google Gemini to be described
-  and are not stored. There is no telemetry.
+- Your code stays on your computer: only the parts the agent reads are sent, as part of the conversation
+  with Euron's model. Attached images are turned into text by Euron's image understanding and are not
+  stored.
 - Your key is never printed in full and never logged.
 - Edits and commands ask first. Files outside the project folder always ask, even to read.
-- Each request carries a random session id and task id so your usage page can count sessions and
-  tasks. Nothing else about the conversation is stored by the gateway.
 - Hooks are commands you configure; project hooks only run after you trust them.
 - Text inside your files, web pages and command output is treated as data, not instructions.
 

{euron_code-0.4.0 → euron_code-0.4.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "euron-code"
-version = "0.4.0"
+version = "0.4.2"
 description = "Euron Code: an agentic coding assistant in your terminal for Euron Plus and Super 30 students."
 readme = "README.md"
 requires-python = ">=3.9"

{euron_code-0.4.0 → euron_code-0.4.2}/src/euron_code/__init__.py

@@ -1,3 +1,3 @@
 """Euron Code: an agentic coding assistant for the terminal."""
 
-__version__ = "0.4.0"
+__version__ = "0.4.2"

{euron_code-0.4.0 → euron_code-0.4.2}/src/euron_code/activity.py

@@ -64,7 +64,7 @@ def phase_from_comment(comment: Optional[str]) -> Optional[str]:
     m = QUEUED.search(comment)
     if m:
         n = int(m.group(1))
-        return "waiting for a GPU slot" + (f" ({n} ahead)" if n else " (next in line)")
+        return "waiting for capacity" + (f" ({n} ahead)" if n else " (next in line)")
     if "previous request" in comment:
         return "waiting for your previous request to finish"
     return None

{euron_code-0.4.0 → euron_code-0.4.2}/src/euron_code/agent.py

@@ -100,7 +100,7 @@ def repair_json(raw: str):
 
 
 def parse_inline_tool_calls(content: str):
-    """Fallback for servers without a tool parser: Qwen emits <tool_call>{json}</tool_call>.
+    """Fallback for servers without a tool parser: some models emit <tool_call>{json}</tool_call>.
     Slightly broken JSON is repaired; unparseable calls become an error result, never a crash."""
     calls = []
     for m in TOOL_CALL_TAG.finditer(content):
@@ -272,6 +272,8 @@ class Agent:
 
     # ---------------------------------------------------------- public
     def run_turn(self, user_text: str, max_turns: Optional[int] = None) -> TurnResult:
+        from euron_code import textsafe
+        user_text = textsafe.clean(user_text)  # emoji pasted into a Windows console (surrogates)
         if self.is_subagent:
             return self._run_turn(user_text, max_turns)
         self._ui_hook("turn_started")

{euron_code-0.4.0 → euron_code-0.4.2}/src/euron_code/api.py

@@ -19,6 +19,7 @@ from typing import Any, Callable, Dict, Iterator, List, Optional, Tuple
 
 import httpx
 
+from euron_code import textsafe
 from euron_code import __version__, config
 
 NO_PLUS_MESSAGE = (
@@ -366,7 +367,7 @@ class Client:
     def chat(self, payload: Dict[str, Any]) -> Dict[str, Any]:
         """Non-streaming completion (used for compaction summaries)."""
         with self._lock:
-            body = dict(payload)
+            body = textsafe.clean_obj(dict(payload))
             body["stream"] = False
             data = self._json("POST", "/v1/chat/completions", json=body, headers=self._chat_headers())
             self.takeover_once = False
@@ -383,7 +384,7 @@ class Client:
             raise EuronError("Internal error: a model request is already running.")
         q: "queue.Queue[Tuple[str, Any]]" = queue.Queue()
         holder: Dict[str, Any] = {}
-        body = dict(payload)
+        body = textsafe.clean_obj(dict(payload))
         body["stream"] = True
         body.setdefault("stream_options", {"include_usage": True})
 

{euron_code-0.4.0 → euron_code-0.4.2}/src/euron_code/attachments.py

@@ -130,7 +130,7 @@ def load_image(path: Path) -> Tuple[Dict, str]:
     return {"type": "image_url", "image_url": {"url": url}}, note
 
 
-IMAGE_PRIVACY = ("Images you attach are sent to Google Gemini to be described in text for the coding model; "
+IMAGE_PRIVACY = ("Images are turned into a text description by Euron's image understanding and are not stored; "
                  "they are not stored. Don't attach images that show secrets.")
 
 

{euron_code-0.4.0 → euron_code-0.4.2}/src/euron_code/config.py

@@ -17,7 +17,7 @@ from typing import Any, Dict, List, Optional, Tuple
 
 DEFAULT_BASE_URL = "https://api.euron.one/api/v1/code-agent"
 
-#: Context window and output cap of the default model (Qwen3.6-27B, see BENCHMARK_RESULTS.md).
+#: Context window and output cap of the default model.
 DEFAULT_CONTEXT_WINDOW = 32768
 DEFAULT_MAX_OUTPUT = 8192
 

{euron_code-0.4.0 → euron_code-0.4.2}/src/euron_code/doctor.py

@@ -1,88 +1,88 @@
-"""`euron doctor`: check the local setup and the connection to Euron Code."""
-
-from __future__ import annotations
-
-import os
-import platform
-import sys
-from typing import List, Tuple
-
-import httpx
-from rich.markup import escape
-
-from euron_code import __version__, api, config, credentials
-from euron_code.tools.search import ripgrep_path
-from euron_code.tools.shell import detect_shell
-
-OK, WARN, FAIL = "ok", "warn", "fail"
-
-
-def run_checks() -> List[Tuple[str, str, str]]:
-    checks: List[Tuple[str, str, str]] = []
-    v = sys.version_info
-    checks.append(("Python", OK if v >= (3, 9) else FAIL,
-                   f"{platform.python_version()} ({sys.executable})"))
-    checks.append(("euron-code", OK, __version__))
-    checks.append(("Platform", OK, f"{platform.system()} {platform.release()} {platform.machine()}"))
-    url = config.base_url()
-    src = "EURON_CODE_API" if os.environ.get("EURON_CODE_API") else "default"
-    checks.append(("API base URL", OK, f"{url} ({src})"))
-
-    # connectivity: any HTTP answer means the gateway is reachable
-    try:
-        r = httpx.get(url + "/v1/models", timeout=10.0, headers={"User-Agent": api.user_agent()})
-        checks.append(("Connectivity", OK, f"reachable (HTTP {r.status_code})"))
-        reachable = True
-    except httpx.HTTPError as e:
-        checks.append(("Connectivity", FAIL, f"cannot reach {url}: {type(e).__name__}"))
-        reachable = False
-
-    cred = credentials.load(url)
-    if cred is None:
-        checks.append(("Login", WARN, "not logged in; run `euron login`"))
-    else:
-        checks.append(("Login", OK, f"key {credentials.mask_key(cred.api_key)} in {credentials.where(url)}"))
-        if reachable:
-            c = api.Client(api_key=cred.api_key, base_url=url)
-            try:
-                me = c.me(use_cache=False)
-                access = me.get("access") or {}
-                if access.get("entitled"):
-                    q = me.get("quota") or {}
-                    checks.append(("Entitlement", OK, f"{api.plan_label(access)}; "
-                                   f"{q.get('remainingToday', '?'):,} tokens left today"
-                                   if isinstance(q.get("remainingToday"), int) else api.plan_label(access)))
-                else:
-                    checks.append(("Entitlement", FAIL, api.NO_PLUS_MESSAGE))
-            except api.AuthError:
-                checks.append(("Entitlement", FAIL, "the saved key was rejected (401); run `euron login`"))
-            except api.EuronError as e:
-                checks.append(("Entitlement", WARN, f"could not check: {e.message}"))
-            finally:
-                c.close()
-
-    rg = ripgrep_path()
-    checks.append(("ripgrep", OK if rg else WARN, rg or "not found; grep uses the slower Python fallback"))
-    checks.append(("Keyring", OK if "unavailable" not in credentials.keyring_backend_name() else WARN,
-                   credentials.keyring_backend_name()))
-    kind, exe = detect_shell(config.load_user_settings().get("shell"))
-    checks.append(("Shell", OK, f"{kind} ({exe})"))
-    term = os.environ.get("TERM_PROGRAM") or os.environ.get("TERM") or ("Windows console" if os.name == "nt" else "?")
-    checks.append(("Terminal", OK if sys.stdout.isatty() else WARN,
-                   f"{term}{'' if sys.stdout.isatty() else ' (output is not a terminal)'}"))
-    checks.append(("Config", OK, f"{config.user_settings_path()}"))
-    return checks
-
-
-def doctor(ui) -> int:
-    checks = run_checks()
-    style = {OK: "[green]OK  [/green]", WARN: "[yellow]WARN[/yellow]", FAIL: "[red]FAIL[/red]"}
-    for name, st, detail in checks:
-        ui.info(f"{style[st]} {name:<14} {escape(detail)}")
-    fails = [c for c in checks if c[1] == FAIL]
-    ui.info("")
-    if fails:
-        ui.info(f"[red]{len(fails)} problem(s) found.[/red]")
-        return 1
-    ui.info("[green]All checks passed.[/green]")
-    return 0
+"""`euron doctor`: check the local setup and the connection to Euron Code."""
+
+from __future__ import annotations
+
+import os
+import platform
+import sys
+from typing import List, Tuple
+
+import httpx
+from rich.markup import escape
+
+from euron_code import __version__, api, config, credentials
+from euron_code.tools.search import ripgrep_path
+from euron_code.tools.shell import detect_shell
+
+OK, WARN, FAIL = "ok", "warn", "fail"
+
+
+def run_checks() -> List[Tuple[str, str, str]]:
+    checks: List[Tuple[str, str, str]] = []
+    v = sys.version_info
+    checks.append(("Python", OK if v >= (3, 9) else FAIL,
+                   f"{platform.python_version()} ({sys.executable})"))
+    checks.append(("euron-code", OK, __version__))
+    checks.append(("Platform", OK, f"{platform.system()} {platform.release()} {platform.machine()}"))
+    url = config.base_url()
+    src = "EURON_CODE_API" if os.environ.get("EURON_CODE_API") else "default"
+    checks.append(("API base URL", OK, f"{url} ({src})"))
+
+    # connectivity: any HTTP answer means the gateway is reachable
+    try:
+        r = httpx.get(url + "/v1/models", timeout=10.0, headers={"User-Agent": api.user_agent()})
+        checks.append(("Connectivity", OK, f"reachable (HTTP {r.status_code})"))
+        reachable = True
+    except httpx.HTTPError as e:
+        checks.append(("Connectivity", FAIL, f"cannot reach {url}: {type(e).__name__}"))
+        reachable = False
+
+    cred = credentials.load(url)
+    if cred is None:
+        checks.append(("Login", WARN, "not logged in; run `euron login`"))
+    else:
+        checks.append(("Login", OK, f"key {credentials.mask_key(cred.api_key)} in {credentials.where(url)}"))
+        if reachable:
+            c = api.Client(api_key=cred.api_key, base_url=url)
+            try:
+                me = c.me(use_cache=False)
+                access = me.get("access") or {}
+                if access.get("entitled"):
+                    q = me.get("quota") or {}
+                    checks.append(("Entitlement", OK, f"{api.plan_label(access)}; "
+                                   f"{q.get('remainingToday', '?'):,} tokens left today"
+                                   if isinstance(q.get("remainingToday"), int) else api.plan_label(access)))
+                else:
+                    checks.append(("Entitlement", FAIL, api.NO_PLUS_MESSAGE))
+            except api.AuthError:
+                checks.append(("Entitlement", FAIL, "the saved key was rejected (401); run `euron login`"))
+            except api.EuronError as e:
+                checks.append(("Entitlement", WARN, f"could not check: {e.message}"))
+            finally:
+                c.close()
+
+    rg = ripgrep_path()
+    checks.append(("ripgrep", OK if rg else WARN, rg or "not found; grep uses the slower Python fallback"))
+    checks.append(("Keyring", OK if "unavailable" not in credentials.keyring_backend_name() else WARN,
+                   credentials.keyring_backend_name()))
+    kind, exe = detect_shell(config.load_user_settings().get("shell"))
+    checks.append(("Shell", OK, f"{kind} ({exe})"))
+    term = os.environ.get("TERM_PROGRAM") or os.environ.get("TERM") or ("Windows console" if os.name == "nt" else "?")
+    checks.append(("Terminal", OK if sys.stdout.isatty() else WARN,
+                   f"{term}{'' if sys.stdout.isatty() else ' (output is not a terminal)'}"))
+    checks.append(("Config", OK, f"{config.user_settings_path()}"))
+    return checks
+
+
+def doctor(ui) -> int:
+    checks = run_checks()
+    style = {OK: "[green]OK  [/green]", WARN: "[yellow]WARN[/yellow]", FAIL: "[red]FAIL[/red]"}
+    for name, st, detail in checks:
+        ui.info(f"{style[st]} {name:<14} {escape(detail)}")
+    fails = [c for c in checks if c[1] == FAIL]
+    ui.info("")
+    if fails:
+        ui.info(f"[red]{len(fails)} problem(s) found.[/red]")
+        return 1
+    ui.info("[green]All checks passed.[/green]")
+    return 0