tau-coding-agent 0.3.9__tar.gz → 0.4.0__tar.gz

{tau_coding_agent-0.3.9/tau_coding_agent.egg-info → tau_coding_agent-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tau-coding-agent
-Version: 0.3.9
+Version: 0.4.0
 Summary: A self-extensible agent CLI with terminal UI, multi-provider LLM support, session management with branching, and a plugin system for tools and commands
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
@@ -32,7 +32,7 @@ Dynamic: license-file
 
 # Tau (τ)
 
-Inspired by [Pi](https://pi.dev), **Tau** brings the same agent framework capabilities to Python developers. A self-extensible agent CLI with a terminal UI, multi-provider LLM support, session management with branching, and a plugin system for tools, commands, and customization.
+A Python reimplementation of [Pi](https://pi.dev), **Tau** brings the same agent framework capabilities to Python developers. A self-extensible agent CLI with a terminal UI, multi-provider LLM support, session management with branching, and a plugin system for tools, commands, and customization.
 
 <p align="center">
   <img src="assets/tui.png" alt="Tau TUI" width="700">
@@ -47,7 +47,7 @@ Start a conversation with the agent in the terminal.
 ### Installation
 
 ```bash
-pip install tau-coding-agent
+uv pip install tau-coding-agent
 ```
 
 Or install from source:

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/README.md

@@ -1,6 +1,6 @@
 # Tau (τ)
 
-Inspired by [Pi](https://pi.dev), **Tau** brings the same agent framework capabilities to Python developers. A self-extensible agent CLI with a terminal UI, multi-provider LLM support, session management with branching, and a plugin system for tools, commands, and customization.
+A Python reimplementation of [Pi](https://pi.dev), **Tau** brings the same agent framework capabilities to Python developers. A self-extensible agent CLI with a terminal UI, multi-provider LLM support, session management with branching, and a plugin system for tools, commands, and customization.
 
 <p align="center">
   <img src="assets/tui.png" alt="Tau TUI" width="700">
@@ -15,7 +15,7 @@ Start a conversation with the agent in the terminal.
 ### Installation
 
 ```bash
-pip install tau-coding-agent
+uv pip install tau-coding-agent
 ```
 
 Or install from source:

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/docs/extension-settings.md

@@ -21,7 +21,7 @@ def register(tau):
     timeout = config.get("timeout_ms", 5000)
 ```
 
-In `~/.tau/settings.json` or `.tau/settings.json`:
+The values are stored in `~/.tau/settings.json` (global) or `.tau/settings.json` (project-local):
 
 ```json
 {
@@ -39,6 +39,71 @@ In `~/.tau/settings.json` or `.tau/settings.json`:
 }
 ```
 
+### Where settings live
+
+Settings for an extension are stored in the `settings` object of its entry inside `extensions.list`. Tau matches entries by path — the path in the list must match the path or directory the extension was loaded from.
+
+**Project-local** — `.tau/settings.json` (only applies in this directory):
+
+```json
+{
+  "extensions": {
+    "list": [
+      {
+        "path": ".tau/extensions/lsp",
+        "settings": {
+          "lsp": true,
+          "eager": [],
+          "servers": {
+            "pyright": { "enabled": true },
+            "ruff": { "enabled": true },
+            "typescript-language-server": { "enabled": false }
+          }
+        }
+      },
+      {
+        "path": ".tau/extensions/voice",
+        "settings": {
+          "enabled": true,
+          "stt_model": "whisper-1",
+          "stt_provider": "openai",
+          "hold_seconds": 2,
+          "sample_rate": 16000
+        }
+      }
+    ]
+  }
+}
+```
+
+**Global** — `~/.tau/settings.json` (applies to every project):
+
+```json
+{
+  "extensions": {
+    "list": [
+      {
+        "path": "~/.tau/extensions/web-search",
+        "settings": {
+          "enabled": true,
+          "engine": "ddgs",
+          "results": 10
+        }
+      },
+      {
+        "path": "~/.tau/extensions/my_ext.py",
+        "settings": {
+          "api_key": "sk-...",
+          "timeout_ms": 5000
+        }
+      }
+    ]
+  }
+}
+```
+
+Both files can coexist — project settings are merged on top of global settings at startup. Extensions loaded from `.tau/extensions/` read from the project file; extensions loaded from `~/.tau/extensions/` read from the global file.
+
 ## Nested Structures
 
 `ExtensionSettings` handles nested configuration just as naturally:
@@ -237,7 +302,147 @@ def register(tau):
 
 Extensions can register settings items that appear as a named sub-panel at the bottom of the interactive `/settings` panel. Users can then edit extension settings from the TUI without touching JSON.
 
-### Basic example
+There are two ways to do this: declare the schema in `manifest.json` (recommended for directory extensions) or register it imperatively with `tau.register_settings()` (useful for single-file extensions).
+
+---
+
+### Option A — manifest.json schema (recommended)
+
+Add a `"settings"` block under the `"tau"` key in `manifest.json`. Tau reads it at load time, builds the `/settings` sub-panel automatically, reads current values from the extension's config, and persists changes back to `settings.json` (reloading just that extension so the change applies live — no restart needed).
+
+```json
+{
+  "tau": {
+    "extensions": ["__init__.py"],
+    "dependencies": ["requests"],
+    "settings": {
+      "title": "Web search",
+      "fields": [
+        {
+          "key": "enabled",
+          "label": "Enabled",
+          "type": "bool",
+          "default": true,
+          "description": "Enable or disable the web search extension."
+        },
+        {
+          "key": "engine",
+          "label": "Search engine",
+          "type": "enum",
+          "values": ["ddgs", "exa", "tavily"],
+          "default": "ddgs",
+          "description": "Which search backend to use."
+        },
+        {
+          "key": "results",
+          "label": "Max results",
+          "type": "int",
+          "default": 10,
+          "min": 1,
+          "max": 50,
+          "description": "Number of results returned per query."
+        },
+        {
+          "key": "api_key",
+          "label": "API key",
+          "type": "secret",
+          "default": "",
+          "description": "Provider API key (stored in settings.json)."
+        },
+        {
+          "key": "exa",
+          "label": "Exa settings",
+          "type": "group",
+          "fields": [
+            {
+              "key": "base_url",
+              "label": "Base URL",
+              "type": "string",
+              "default": "https://api.exa.ai"
+            },
+            {
+              "key": "highlights",
+              "label": "Highlights",
+              "type": "bool",
+              "default": true
+            }
+          ]
+        }
+      ]
+    }
+  }
+}
+```
+
+The corresponding `.tau/settings.json` entry that stores the current values:
+
+```json
+{
+  "extensions": {
+    "list": [
+      {
+        "path": ".tau/extensions/web-search",
+        "settings": {
+          "enabled": true,
+          "engine": "exa",
+          "results": 20,
+          "api_key": "sk-exa-...",
+          "exa": {
+            "base_url": "https://api.exa.ai",
+            "highlights": false
+          }
+        }
+      }
+    ]
+  }
+}
+```
+
+#### Field types
+
+| Type | UI control | Notes |
+|------|-----------|-------|
+| `bool` | Toggle `off` / `on` | Stored as a JSON boolean in settings |
+| `int` | Text input (numeric) | Optional `min` and `max` clamps |
+| `string` | Text input | Optional `pattern` (regex the value must match) |
+| `secret` | Text input | Same as `string`; signals sensitive content |
+| `text` | Text input | Same as `string`; intended for longer values |
+| `enum` or `select` | Cycle through values on Enter | Requires a non-empty `"values"` list |
+| `group` | Opens a nested sub-panel | Contains a `"fields"` list; keys are prefixed |
+
+#### Field properties
+
+| Property | Required | Description |
+|----------|----------|-------------|
+| `key` | Yes | Setting key. Supports dot-notation: `"exa.api_key"` is equivalent to nesting under a `"exa"` group |
+| `label` | Yes | Display text shown in the `/settings` panel |
+| `type` | No (defaults to `string`) | One of the types listed above |
+| `default` | No | Fallback value when the key is absent from settings |
+| `description` | No | Dimmed help text shown below the label |
+| `values` | `enum`/`select` only | List of allowed values to cycle through |
+| `min` / `max` | `int` only | Clamp the entered value to this range |
+| `pattern` | `string`/`secret`/`text` | Regex the value must fully match; invalid input is silently ignored |
+| `fields` | `group` only | Nested list of field definitions |
+
+#### Summary badge
+
+The first top-level `bool` field is automatically used as an on/off summary badge on the extension's parent row in the main `/settings` list. This lets users see at a glance whether an extension is enabled without opening its sub-panel.
+
+#### Dot-notation keys
+
+`"key": "exa.api_key"` at the top level is exactly equivalent to a field with `"key": "api_key"` nested inside a group with `"key": "exa"`. Both read and write the same path in settings:
+
+```json
+{ "exa": { "api_key": "sk-..." } }
+```
+
+Use the explicit `group` type when you want the sub-panel to have a header label. Use dot-notation directly when you just want nested storage without the extra level of UI.
+
+---
+
+### Option B — `tau.register_settings()` (imperative)
+
+#### Basic example
 
 ```python
 from tau.tui.components.settings_modal import SettingItem
@@ -254,7 +459,7 @@ def register(tau):
     ], title="My Extension", on_change=on_change)
 ```
 
-### `tau.register_settings(items, title, on_change)`
+#### `tau.register_settings(items, title, on_change)`
 
 Registers a sub-panel in `/settings` containing the provided items.
 
@@ -264,7 +469,7 @@ Registers a sub-panel in `/settings` containing the provided items.
 | `title` | `str` | The sub-panel title shown in the list |
 | `on_change` | `callable(key, value)` | Called when the user changes a value |
 
-### `SettingItem` fields
+#### `SettingItem` fields
 
 | Field | Type | Description |
 |-------|------|-------------|
@@ -278,7 +483,7 @@ Registers a sub-panel in `/settings` containing the provided items.
 | `submenu_settings` | `list[SettingItem] \| None` | Open a full nested sub-panel with these items (arbitrary depth) |
 | `submenu_on_change` | `callable \| None` | Overrides the parent `on_change` for a nested sub-panel |
 
-### Nested sub-panels
+#### Nested sub-panels
 
 A `SettingItem` with `submenu_settings` opens another level of the settings panel. Nesting can be arbitrarily deep. Use `submenu_on_change` to override the change callback for that level:
 
@@ -298,7 +503,7 @@ tau.register_settings([
 ], title="My Extension", on_change=on_change)
 ```
 
-### `tau.settings.set_extension_config_key(ext_path, key, value)`
+#### `tau.settings.set_extension_config_key(ext_path, key, value)`
 
 Persists a value back to `extensions.list[].settings` in `settings.json`.
 

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tau-coding-agent"
-version = "0.3.9"
+version = "0.4.0"
 description = "A self-extensible agent CLI with terminal UI, multi-provider LLM support, session management with branching, and a plugin system for tools and commands"
 readme = "README.md"
 requires-python = ">=3.12"

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/tau/agent/service.py

@@ -6,6 +6,7 @@ from pathlib import Path
 from typing import TYPE_CHECKING
 
 from tau.agent.types import AgentConfig, AgentContext, AgentPhase, ContextUsage, PromptOptions
+from tau.hooks.engine import CompactionReason as _CompactionReason
 from tau.hooks.engine import MessageEndEvent, MessageRollbackEvent, SavePointEvent, SettledEvent
 from tau.hooks.service import Hooks
 from tau.message.types import (
@@ -15,6 +16,7 @@ from tau.message.types import (
     UserMessage,
 )
 from tau.message.utils import strip_unusable_trailing_assistant
+from tau.session.compaction import ThresholdCompactionStop as _ThresholdCompactionStop
 from tau.session.utils import to_llm_messages as _to_llm_messages
 from tau.tool.types import ToolInvocation, ToolResult
 
@@ -25,10 +27,6 @@ _TOOL_CAP_LINES = 2000         # DEFAULT_MAX_LINES
 _TOOL_LINE_CAP_BYTES = 2 * 1024  # 2 KB — max bytes for a single line
 
 
-from tau.hooks.engine import CompactionReason as _CompactionReason
-from tau.session.compaction import ThresholdCompactionStop as _ThresholdCompactionStop
-
-
 def _fmt_size(n: int) -> str:
     if n < 1024:
         return f"{n}B"
@@ -191,7 +189,8 @@ class Agent:
                 # Walk back to a valid UTF-8 boundary
                 while buf and (buf[-1] & 0xC0) == 0x80:
                     buf = buf[:-1]
-                capped_lines.append(buf.decode("utf-8", errors="replace") + f" …[line truncated: {_fmt_size(lb)} → {_fmt_size(_TOOL_LINE_CAP_BYTES)}]")
+                suffix = f" …[line truncated: {_fmt_size(lb)} → {_fmt_size(_TOOL_LINE_CAP_BYTES)}]"
+                capped_lines.append(buf.decode("utf-8", errors="replace") + suffix)
             else:
                 capped_lines.append(line)
         lines = capped_lines
@@ -209,8 +208,8 @@ class Agent:
 
         omitted = total_bytes - byte_count
         kept.append(
-            f"[truncated: {_fmt_size(omitted)} omitted"
-            f" — {_fmt_size(total_bytes)} total, showing first {len(kept)} lines / {_fmt_size(byte_count)}]"
+            f"[truncated: {_fmt_size(omitted)} omitted — {_fmt_size(total_bytes)} total,"
+            f" showing first {len(kept)} lines / {_fmt_size(byte_count)}]"
         )
         return ToolResult(
             id=result.id,
@@ -258,6 +257,8 @@ class Agent:
                 self._session_manager.append_message(message)
             case ToolMessage():
                 self._session_manager.append_message(message)
+            case UserMessage():
+                self._session_manager.append_message(message)
             case _:
                 pass
 
@@ -369,9 +370,8 @@ class Agent:
         # model change, it came from a different model. Treating its usage/overflow data as
         # a signal for the new model is unreliable (context windows differ), so skip.
         model_change_ts = self._latest_model_change_timestamp()
-        if model_change_ts is not None and last is not None:
-            if last.timestamp <= model_change_ts:
-                return False
+        if model_change_ts is not None and last is not None and last.timestamp <= model_change_ts:
+            return False
 
         forced = last is not None and is_silent_overflow(last, self._context_window)
 
@@ -443,7 +443,9 @@ class Agent:
         if preparation is None:
             return False
         try:
-            await self._apply_compaction(preparation, entries, manual=False, reason=_CompactionReason.Overflow)
+            await self._apply_compaction(
+                preparation, entries, manual=False, reason=_CompactionReason.Overflow
+            )
         except Exception:
             self._compaction_failures += 1
             _log.exception("Overflow-triggered compaction failed")
@@ -501,7 +503,9 @@ class Agent:
             if res.compaction is not None:
                 return res.compaction, True
 
-        await self.hooks.emit(CompactionStartEvent(manual=manual, reason=reason, will_retry=will_retry))
+        await self.hooks.emit(
+            CompactionStartEvent(manual=manual, reason=reason, will_retry=will_retry)
+        )
         result = await _compact(
             preparation, self._engine.llm, custom_instructions=custom_instructions
         )  # type: ignore[arg-type]
@@ -543,6 +547,16 @@ class Agent:
                     if await self._try_overflow_recovery():
                         continue
                     raise
+
+            # A steering / follow-up message can land *after* the engine loop has
+            # already decided to stop: the submit→steer hop runs as a separate
+            # task, so it may enqueue just past the turn's final queue check.
+            # Drain any such leftovers with continuation turns so a mid-flight
+            # message is never silently stranded in the queue.
+            while self._engine.has_pending_messages():
+                self._signal = asyncio.Event()
+                self._engine.llm.api.options.signal = self._signal
+                await self._run_continue()
         finally:
             self._phase = AgentPhase.IDLE
 
@@ -582,3 +596,36 @@ class Agent:
         error = self._engine.state.error_message
         if error is not None:
             raise RuntimeError(f"Agent failed: {error}.")
+
+    async def _run_continue(self) -> None:
+        """Run a continuation turn that drains queued steering/follow-up messages.
+
+        Mirrors ``_run``'s session-sync wiring so messages injected by the engine
+        continuation are persisted and rendered just like a normal turn's.
+
+        Keeps the continuation within the context window the same way the main turn
+        does: auto-compact if needed, then resync the engine's history from the
+        (possibly compacted) session — ``run_continue`` runs from ``state.messages``,
+        which compaction (which only rewrites the session) would otherwise not touch.
+        """
+        await self._check_compaction()
+        session_ctx = self._session_manager.build_session_context()
+        self._engine.state.messages = _to_llm_messages(session_ctx.messages)
+
+        unsubscribe = self.hooks.register(
+            "message_end",
+            lambda event: self._on_message_end(event),
+        )
+        unsubscribe_rollback = self.hooks.register(
+            "message_rollback",
+            lambda event: self._on_message_rollback(event),
+        )
+        try:
+            await self._engine.run_continue(signal=self._signal)
+        finally:
+            unsubscribe()
+            unsubscribe_rollback()
+
+        error = self._engine.state.error_message
+        if error is not None:
+            raise RuntimeError(f"Agent failed: {error}.")

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/tau/builtins/extensions/footer/git.py

@@ -17,7 +17,7 @@ class GitBadge:
         self._text = f"{display} ({branch})" if branch else display
 
     def render(self, width: int) -> list[str]:  # noqa: ARG002
-        from tau.tui.ansi import DIM, RESET
+        from tau.tui.utils import DIM, RESET
 
         return [DIM + self._text + RESET]
 

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/tau/builtins/extensions/footer/model.py

@@ -49,7 +49,7 @@ class ModelBadge:
             self.set_context(tokens, window)
 
     def render(self, width: int) -> list[str]:  # noqa: ARG002
-        from tau.tui.ansi import DIM, RESET
+        from tau.tui.utils import DIM, RESET
 
         if not self._provider and not self._model:
             return []

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/tau/builtins/extensions/header/__init__.py

@@ -10,7 +10,7 @@ if TYPE_CHECKING:
 
 def register(tau: ExtensionAPI) -> None:
     from tau.settings.paths import get_app_name, get_app_version
-    from tau.tui.ansi import BOLD, CYAN, DIM, RESET
+    from tau.tui.utils import BOLD, CYAN, DIM, RESET
     from tau.tui.component import StaticComponent
 
     def _build() -> StaticComponent:

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/tau/builtins/models/text.py

@@ -173,6 +173,35 @@ models = [
         input=_TEXT_IMAGE_VIDEO,
         output=_TEXT,
     ),
+    Model(
+        id="claude-sonnet-4-20250514",
+        name="Claude Sonnet 4.6 (Thinking)",
+        provider="google-antigravity",
+        cost=Cost(),
+        thinking=True,
+        context_window=200_000,
+        input=_TEXT_IMAGE,
+        output=_TEXT,
+    ),
+    Model(
+        id="claude-opus-4-20250514",
+        name="Claude Opus 4.6 (Thinking)",
+        provider="google-antigravity",
+        cost=Cost(),
+        thinking=True,
+        context_window=200_000,
+        input=_TEXT_IMAGE,
+        output=_TEXT,
+    ),
+    Model(
+        id="gpt-oss-120",
+        name="GPT-OSS 120",
+        provider="google-antigravity",
+        cost=Cost(),
+        context_window=128_000,
+        input=_TEXT_IMAGE,
+        output=_TEXT,
+    ),
     # Google Vertex AI (GCP — API key or ADC)
     Model(
         id="gemini-3.1-pro",

tau_coding_agent-0.4.0/tau/builtins/providers/audio.py

@@ -0,0 +1,22 @@
+from tau.inference.provider.types import AudioProvider
+
+providers = [
+    AudioProvider(id="openai", name="OpenAI", api="openai-audio"),
+    AudioProvider(
+        id="openrouter",
+        name="OpenRouter",
+        api="openai-audio",
+        base_url="https://openrouter.ai/api/v1",
+    ),
+    AudioProvider(
+        id="groq", name="Groq", api="openai-audio", base_url="https://api.groq.com/openai/v1"
+    ),
+    AudioProvider(id="google", name="Google", api="gemini-audio"),
+    AudioProvider(id="sarvam", name="Sarvam", api="sarvam-audio", base_url="https://api.sarvam.ai"),
+    AudioProvider(
+        id="elevenlabs",
+        name="ElevenLabs",
+        api="elevenlabs-audio",
+        base_url="https://api.elevenlabs.io",
+    ),
+]

tau_coding_agent-0.4.0/tau/builtins/providers/image.py

@@ -0,0 +1,31 @@
+from tau.inference.provider.types import ImageProvider
+
+providers = [
+    ImageProvider(
+        id="openrouter",
+        name="OpenRouter",
+        api="openrouter-image",
+        base_url="https://openrouter.ai/api/v1",
+    ),
+    ImageProvider(
+        id="openai", name="OpenAI", api="openai-image", base_url="https://api.openai.com/v1"
+    ),
+    ImageProvider(
+        id="together",
+        name="Together AI",
+        api="openai-image",
+        base_url="https://api.together.xyz/v1",
+    ),
+    ImageProvider(
+        id="fireworks",
+        name="Fireworks AI",
+        api="openai-image",
+        base_url="https://api.fireworks.ai/inference/v1",
+    ),
+    ImageProvider(
+        id="google",
+        name="Google",
+        api="gemini-image",
+        base_url="https://generativelanguage.googleapis.com",
+    ),
+]

tau_coding_agent-0.4.0/tau/builtins/providers/video.py

@@ -0,0 +1,11 @@
+from tau.inference.provider.types import VideoProvider
+
+providers = [
+    VideoProvider(id="fal", name="fal.ai", api="fal-video"),
+    VideoProvider(
+        id="openrouter",
+        name="OpenRouter",
+        api="openrouter-video",
+        base_url="https://openrouter.ai/api/v1",
+    ),
+]

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/tau/builtins/tools/edit.py

@@ -79,7 +79,7 @@ def _parse_hunks(diff: str) -> list[list[tuple[str, int, int, str]]]:
 
 
 def _render_edit_result(content: str, opts: Any) -> list[str]:
-    from tau.tui.ansi import DIM, GREEN, RED, RESET
+    from tau.tui.utils import DIM, GREEN, RED, RESET
 
     metadata = opts.metadata or {}
     added = metadata.get("lines_added", 0)

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/tau/builtins/tools/glob.py

@@ -30,7 +30,7 @@ _PREVIEW_LINES = 5
 
 
 def _render_glob_result(content: str, opts: Any) -> list[str]:
-    from tau.tui.ansi import DIM, RESET
+    from tau.tui.utils import DIM, RESET
 
     metadata = opts.metadata or {}
     match_count = metadata.get("match_count", 0)
@@ -143,7 +143,7 @@ class GlobTool(Tool):
             return None
         if proc.returncode not in (0, 1):
             return None
-        return [l for l in proc.stdout.splitlines() if l]
+        return [line for line in proc.stdout.splitlines() if line]
 
     def _python_glob(self, pattern: str, base: Path) -> list[str]:
         return sorted(_glob.glob(str(base / pattern), recursive=True))

{tau_coding_agent-0.3.9 → tau_coding_agent-0.4.0}/tau/builtins/tools/grep.py

@@ -32,7 +32,7 @@ _PREVIEW_LINES = 5
 
 
 def _render_grep_result(content: str, opts: Any) -> list[str]:
-    from tau.tui.ansi import DIM, RESET
+    from tau.tui.utils import DIM, RESET
 
     metadata = opts.metadata or {}
     match_count = metadata.get("match_count", 0)
@@ -134,7 +134,11 @@ class GrepTool(Tool):
             return ToolResult.error(invocation.id, result["output"])
         if result["matches"]:
             return ToolResult.ok(invocation.id, result["output"], metadata=result["metadata"])
-        return ToolResult.ok(invocation.id, f"No matches for pattern: {params.pattern}", metadata=result["metadata"])
+        return ToolResult.ok(
+            invocation.id,
+            f"No matches for pattern: {params.pattern}",
+            metadata=result["metadata"],
+        )
 
     async def _rg(self, params: GrepParams, target: Path) -> dict | None:
         cmd = ["rg", "--line-number", "--no-heading", "--with-filename"]
@@ -151,10 +155,10 @@ class GrepTool(Tool):
             return None
         if proc.returncode not in (0, 1):
             return None
-        lines = [l for l in proc.stdout.splitlines() if l]
+        lines = [ln for ln in proc.stdout.splitlines() if ln]
         truncated = len(lines) > _MAX_MATCHES
         lines = lines[:_MAX_MATCHES]
-        files_with_matches = len({l.split(":")[0] for l in lines})
+        files_with_matches = len({ln.split(":")[0] for ln in lines})
         metadata = {
             "pattern": params.pattern,
             "files_searched": files_with_matches,
@@ -171,7 +175,12 @@ class GrepTool(Tool):
         try:
             regex = re.compile(params.pattern, flags)
         except re.error as e:
-            return {"matches": [], "output": f"Invalid regex pattern: {e}", "metadata": {}, "error": True}
+            return {
+                "matches": [],
+                "output": f"Invalid regex pattern: {e}",
+                "metadata": {},
+                "error": True,
+            }
 
         files: list[Path] = []
         if target.is_file():