messygit 0.3.1__tar.gz → 0.4.0__tar.gz

messygit-0.4.0/.github/workflows/test.yml

@@ -0,0 +1,27 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install package with dev dependencies
+        run: pip install -e ".[dev]"
+
+      - name: Run tests
+        run: pytest -q

messygit-0.4.0/ARCHITECTURE.md

@@ -0,0 +1,89 @@
+# Architecture
+
+This document describes the purpose of each file in the `messygit` project.
+
+The package is organized in layers. `ui/` is the shared presentation foundation
+(console, theme, spinner, banner). `commands/` holds the command handlers grouped
+the same way the `help` screen groups them. `agent/` is a self-contained tool-use
+loop. `cli.py` is a thin shell that wires everything together. Dependencies flow
+one way — `ui/` knows nothing about `commands/`, and `commands/` knows nothing
+about `cli` — so there are no import cycles.
+
+## Root
+
+| File                            | Purpose                                                                                                                        |
+| ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
+| `pyproject.toml`                | Package metadata, dependencies (`anthropic`, `click`, `rich`), build system (hatchling), and the `messygit` console script.    |
+| `README.md`                     | User-facing documentation: install, usage, commands, and development instructions.                                             |
+| `ARCHITECTURE.md`               | This file — a per-module map of the codebase.                                                                                   |
+| `CHANGELOG.md`                  | Release notes, generated/updated by the `changelog` command.                                                                   |
+| `.gitignore`                    | Keeps `.venv/`, `__pycache__/`, `dist/`, and `*.egg-info/` out of version control.                                             |
+| `.github/workflows/test.yml`    | Runs `pytest` on every push/PR across Python 3.10–3.13.                                                                         |
+| `.github/workflows/publish.yml` | Builds and publishes to PyPI via trusted publishing on release.                                                                |
+
+## `messygit/` (core package)
+
+| File          | Purpose                                                                                                                                                                                                                                                |
+| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `__init__.py` | Marks the directory as a Python package.                                                                                                                                                                                                              |
+| `cli.py`      | The REPL shell: prints the startup dashboard, runs the prompt loop, owns the `COMMANDS` dispatch table and the `help` screen, and applies the saved theme on launch. Delegates all real work to `commands/`.                                          |
+| `git.py`      | All subprocess calls to `git`. Reads staged diffs (`git diff --cached -U0`), parses them into a compact changed-lines format, filters noise files, handles the large-diff fallback (stat summary + top-N changed files), and runs `add`/`commit`/`push`. |
+| `llm.py`      | Anthropic SDK integration for the (non-agentic) `commit` path. Creates the client, calls `messages.create`, extracts text, and maps SDK exceptions (auth, permission, billing/402) into user-friendly error classes. Exposes helpers reused by `agent/agent.py`. |
+| `config.py`   | Reads/writes `~/.messygit/config.json`: API key (plus `ANTHROPIC_API_KEY` env resolution), theme, model, todo, and the `verbose` flag. Masks keys for display and defines user-facing error messages and exception classes.                            |
+| `models.py`   | The selectable Claude models, their labels, and approximate per-million-token pricing; resolves the active model from config.                                                                                                                        |
+| `usage.py`    | Session-local token-usage tracker (`SESSION_USAGE`) and the billing URL. The API exposes no balance endpoint, so usage/cost are accumulated per session.                                                                                              |
+| `prompts.py`  | The three system prompts — `COMMIT_SYSTEM_PROMPT`, `SUGGESTION_SYSTEM_PROMPT`, `CHANGELOG_SYSTEM_PROMPT` — plus `build_user_prompt`. Each prompt includes anti-hallucination and untrusted-input guardrails.                                          |
+
+## `messygit/ui/` (shared presentation)
+
+| File         | Purpose                                                                                                                                                                  |
+| ------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `theme.py`   | Color palette and theme state. `BRAND`/`BRAND_RGB`/`BANNER_COLOR` are reassigned at runtime by `apply_theme()`, so other modules read them as `theme.BRAND` (never import the name directly). Also `brand_ansi()` and `active_theme()`. |
+| `output.py`  | The shared `console`/`err_console` objects and the small print helpers (`print_error`, `success`, `warn`, `field`).                                                     |
+| `spinner.py` | The threaded `_CharSpinner` loading animation and the `spinner()` factory.                                                                                              |
+| `banner.py`  | The ASCII banner art and its boot animation (`animate_banner`).                                                                                                         |
+
+## `messygit/commands/` (command handlers)
+
+| File              | Purpose                                                                                                                                                  |
+| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `git_cmds.py`     | The git group: `add`, `commit` (AI message + Y/n/e prompt), `push`, `outbox`.                                                                           |
+| `agent_cmds.py`   | The agent group: `suggest` and `changelog`. `_drive()` runs an agent either under a spinner or streaming live (verbose), and records the run's trace.    |
+| `account_cmds.py` | The account group: `config`, `show`, `model`, `tokens`.                                                                                                 |
+| `app_cmds.py`     | The app group: `todo`, `theme`, `verbose`.                                                                                                              |
+| `usage.py`        | Token-usage/cost *display* helpers (`usage_summary`, `print_usage_delta`, `model_pricing`, the high-usage warning). Distinct from the root `usage.py` tracker. |
+| `trace.py`        | The `trace` command. Stores the last agent run's steps and renders them as a panel; also provides `live_reporter()`, the per-step formatter that verbose mode streams. |
+
+## `messygit/agent/` (agentic tool-use subpackage)
+
+| File       | Purpose                                                                                                                                                                                                                            |
+| ---------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `tool.py`  | `Tool` dataclass wrapping a Python callable with a name, description, and parameter schema. `run()` invokes the function; `to_schema()` emits an Anthropic-compatible tool definition.                                            |
+| `tools.py` | Concrete tools: `run_git_tool` (allowlisted read-only git, including tag ranges), `read_file_tool`, `list_directory_tool`, `search_code_tool` (`git grep`), `write_file_tool` (full overwrite), and `edit_file_tool` (unique-match string replace). All file tools reject paths outside the repo root. |
+| `agent.py` | The agentic loop. Sends messages to Claude with tool definitions, dispatches `tool_use` blocks to matching `Tool`s, feeds results back, and iterates up to `max_iterations`. Records each step as a `TraceStep` (optionally streamed via an `on_step` callback) and warns when the iteration cap is hit before finishing. |
+
+## Data flow
+
+```
+User runs `messygit` → cli.py REPL (dispatch table)
+       │
+       ├── "add <files>" / "push" ─────► commands/git_cmds.py ─► git.py
+       ├── "config" / "show" / "model" / "tokens" ─► commands/account_cmds.py ─► config.py / usage.py
+       ├── "todo" / "theme" / "verbose" ─────► commands/app_cmds.py ─► config.py
+       ├── "trace" ─────────────────────► commands/trace.py (render last run)
+       │
+       ├── "commit" ──► commands/git_cmds.py
+       │       │            ├── git.py (staged diff + token budget)
+       │       │            └── llm.py ─► prompts.COMMIT_SYSTEM_PROMPT, config.py (key)
+       │       ▼
+       │   Y/n/e prompt ─► git.py (git commit)
+       │
+       └── "suggest" / "changelog" ──► commands/agent_cmds.py
+               │            └── agent/agent.py (tool-use loop)
+               │                    ├── config.py (key) + models.py
+               │                    ├── prompts.{SUGGESTION,CHANGELOG}_SYSTEM_PROMPT
+               │                    └── agent/tools.py (run_git, read_file, list_directory,
+               │                                        write_file, edit_file)
+               ▼
+           spinner OR live step stream (verbose); steps saved for `trace`
+```

messygit-0.4.0/CHANGELOG.md

@@ -0,0 +1,21 @@
+## [v0.3.2] - 2026-06-20
+### Added
+- Error handling for unknown tools—agent now returns an error result instead of crashing when the model requests a non-existent tool
+- Exception handling for tool execution—tool errors are caught and reported back to the model as error results
+- `outbox` command to display committed but unpushed commits, showing how many commits are ahead of the upstream branch
+- Input validation and security checks for `read_file` and `list_directory` tools to prevent directory traversal attacks
+- Enhanced tool descriptions with detailed documentation of parameters and usage examples
+- Support for `required` field in tool schemas for better validation
+- Comprehensive pytest test suite covering agent tool execution, config management, git diff parsing, LLM error handling, and tool schemas
+- GitHub Actions CI workflow for automated testing across Python 3.10–3.13
+
+### Changed
+- Tool schema generation now includes required field declarations
+- Improved error messages throughout the CLI for better user guidance
+- Tool functions now validate inputs for security and proper error reporting
+
+## [v0.3.1] - 2026-06-20
+
+## [v0.3.0] - 2026-06-20
+
+## [v0.2.1] - 2026-06-20

{messygit-0.3.1 → messygit-0.4.0}/PKG-INFO

@@ -1,26 +1,30 @@
 Metadata-Version: 2.4
 Name: messygit
-Version: 0.3.1
+Version: 0.4.0
 Summary: An AI-powered interactive git CLI with agentic tools for commits, code suggestions, and workflow automation.
 License-Expression: MIT
 Requires-Python: >=3.10
 Requires-Dist: anthropic>=0.39.0
 Requires-Dist: click>=8.0
 Requires-Dist: rich>=13.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == 'dev'
 Description-Content-Type: text/markdown
 
 # messygit
 
-**messygit** is an interactive CLI that turns messy git workflows into clean Conventional Commits — stage, commit, push, and get AI-powered project suggestions, all from one interface powered by [Claude](https://www.anthropic.com/api).
+**messygit** is an interactive CLI that turns messy git workflows into clean Conventional Commits — stage, commit, push, generate changelogs, and get AI-powered project suggestions, all from one interface powered by [Claude](https://www.anthropic.com/api).
 
 ## Why use it
 
 - **Interactive REPL** — one command drops you into a persistent session where you can stage, commit, push, and more without leaving.
 - **AI commit messages** — sends your staged diff to Claude and suggests a clean Conventional Commits subject line.
 - **Project suggestions** — an AI agent inspects your repo and recommends concrete next steps.
+- **Changelog generation** — an agent reads the commits between your two latest tags, drills into unclear ones, categorizes the changes, and writes/updates `CHANGELOG.md`.
+- **See what the agent did** — runs are clean by default; type `trace` to expand the last run's tool calls, or flip `verbose` on to stream each step live.
 - **Token usage & cost** — tracks the tokens each session uses and shows a rough cost estimate, with a one-command jump to billing.
 - **Themed UI** — a colored startup animation and prompt you can recolor with the `theme` command.
-- **Safe by default** — only the staged diff is sent to the model. Your API key is never printed in full.
+- **Safe by default** — only the staged diff is sent for `commit`; agents use read-only git plus repo-scoped file tools that reject paths outside the repository. Your API key is never printed in full.
 
 ## Requirements
 
@@ -94,12 +98,15 @@ Commands are grouped on the `help` screen:
 | `add <file>` or `add .` | Stage files for commit |
 | `commit` | Generate an AI commit message from staged changes, then commit / cancel / edit |
 | `push` | Push commits to remote |
+| `outbox` | Show commits made locally but not yet pushed to the upstream branch |
 
 **messyagent**
 
 | Command | Description |
 |---------|-------------|
 | `suggest` | Get AI-powered next-step suggestions for your project |
+| `changelog` | Generate or update `CHANGELOG.md` from the commits between your two latest tags (requires at least one tag) |
+| `trace` | Show what the last agent run actually did — its tool calls and results |
 
 **account**
 
@@ -116,6 +123,7 @@ Commands are grouped on the `help` screen:
 |---------|-------------|
 | `todo` | Open your todo list in `$EDITOR` (saved to `~/.messygit/todo.md`) |
 | `theme` or `theme <name>` | Change the UI color (run `theme` to list presets) |
+| `verbose` or `verbose on\|off` | Toggle live streaming of agent steps (persists; off by default) |
 | `help` | List available commands |
 | `quit` / `exit` | Exit messygit |
 
@@ -134,6 +142,41 @@ messygit > push
 
 > Tip: run `suggest` for AI next-step ideas, or `theme` to recolor the UI.
 
+### Agent commands & transparency
+
+`suggest` and `changelog` are backed by an agent that uses tools (read-only git,
+file reads, and — for `changelog` — repo-scoped file writes) over several steps.
+
+By default a run shows only a spinner and the final result. Two commands let you
+see inside:
+
+```
+messygit > changelog          # generates/updates CHANGELOG.md
+messygit > trace              # expand what that run just did
+
+╭─ trace · changelog · 4 tool calls ─────────────╮
+│ 1. run_git  tag --sort=-creatordate            │
+│    └ v0.4.0  (+3 more lines)                    │
+│ 2. run_git  log v0.3.2..v0.4.0                  │
+│    └ commit a1b2c3 feat: …  (+12 more lines)    │
+│ 3. read_file  CHANGELOG.md                      │
+│    └ ## [v0.3.2] - 2026-06-20                    │
+│ 4. edit_file  CHANGELOG.md                      │
+│    └ File edited successfully.                   │
+╰─────────────────────────────────────────────────╯
+```
+
+Prefer to watch it happen live? Turn on `verbose` — the same steps stream as the
+agent works (no spinner). The setting persists in `~/.messygit/config.json`:
+
+```
+messygit > verbose on
+Verbose on — agent runs will stream their steps live (no spinner)
+```
+
+`changelog` requires at least one git tag; it documents the range between your two
+most recent tags (or the latest tag to `HEAD` when only one exists).
+
 ### Commit message style
 
 The model follows **Conventional Commits**: `type(scope): description`
@@ -142,7 +185,7 @@ Allowed types: `feat`, `fix`, `docs`, `style`, `refactor`, `test`, `chore`. Subj
 
 ### Token usage & cost
 
-messygit tracks the tokens used by AI commands (`commit`, `suggest`) for the current session and shows a running total after each call. Run `tokens` for a breakdown and a one-key jump to the Anthropic billing console:
+messygit tracks the tokens used by AI commands (`commit`, `suggest`, `changelog`) for the current session and shows a running total after each call. Run `tokens` for a breakdown and a one-key jump to the Anthropic billing console:
 
 ```
 messygit > tokens
@@ -174,6 +217,34 @@ Switch anyway? [y/N]:
 
 Switching to a **more expensive** model prompts for confirmation first. The session cost estimate prices each request at the model used for it, so it stays accurate even if you switch mid-session.
 
+## Development & testing
+
+Install the package with its dev dependencies (pytest), then run the suite:
+
+```bash
+pip install -e ".[dev]"
+pytest -q
+```
+
+The tests live in `tests/` and are pure unit tests — no network calls and no
+API key required (the Anthropic client is simulated). They cover:
+
+| File | What it covers |
+|------|----------------|
+| `tests/config_test.py` | API-key resolution order (env → file), key save/load, theme/model/todo persistence, malformed-config handling |
+| `tests/git_test.py` | The diff parser — noise-file filtering and the compact changed-lines format |
+| `tests/llm_test.py` | Insufficient-balance / billing-error detection and user messaging |
+| `tests/tool_schema_test.py` | Agent tool schemas match the shape the Anthropic Messages API expects |
+| `tests/agent_test.py` | The agent's tool-use loop, driven by a simulated Anthropic client with scripted responses |
+| `tests/trace_test.py` | The `trace` renderer — step numbering, result truncation, empty state, and markup-safety of raw tool output |
+| `tests/verbose_test.py` | The `verbose` setting, the toggle command, and `_drive` choosing live-stream vs. spinner |
+
+### Continuous integration
+
+`.github/workflows/test.yml` runs `pytest` on every push to `main` and on every
+pull request, across Python 3.10–3.13. No secrets are required because the tests
+mock the Anthropic client.
+
 ## Publishing to PyPI
 
 This project uses GitHub Actions with [PyPI trusted publishing](https://docs.pypi.org/trusted-publishers/) — no API tokens needed in your repo.

{messygit-0.3.1 → messygit-0.4.0}/README.md

@@ -1,15 +1,17 @@
 # messygit
 
-**messygit** is an interactive CLI that turns messy git workflows into clean Conventional Commits — stage, commit, push, and get AI-powered project suggestions, all from one interface powered by [Claude](https://www.anthropic.com/api).
+**messygit** is an interactive CLI that turns messy git workflows into clean Conventional Commits — stage, commit, push, generate changelogs, and get AI-powered project suggestions, all from one interface powered by [Claude](https://www.anthropic.com/api).
 
 ## Why use it
 
 - **Interactive REPL** — one command drops you into a persistent session where you can stage, commit, push, and more without leaving.
 - **AI commit messages** — sends your staged diff to Claude and suggests a clean Conventional Commits subject line.
 - **Project suggestions** — an AI agent inspects your repo and recommends concrete next steps.
+- **Changelog generation** — an agent reads the commits between your two latest tags, drills into unclear ones, categorizes the changes, and writes/updates `CHANGELOG.md`.
+- **See what the agent did** — runs are clean by default; type `trace` to expand the last run's tool calls, or flip `verbose` on to stream each step live.
 - **Token usage & cost** — tracks the tokens each session uses and shows a rough cost estimate, with a one-command jump to billing.
 - **Themed UI** — a colored startup animation and prompt you can recolor with the `theme` command.
-- **Safe by default** — only the staged diff is sent to the model. Your API key is never printed in full.
+- **Safe by default** — only the staged diff is sent for `commit`; agents use read-only git plus repo-scoped file tools that reject paths outside the repository. Your API key is never printed in full.
 
 ## Requirements
 
@@ -83,12 +85,15 @@ Commands are grouped on the `help` screen:
 | `add <file>` or `add .` | Stage files for commit |
 | `commit` | Generate an AI commit message from staged changes, then commit / cancel / edit |
 | `push` | Push commits to remote |
+| `outbox` | Show commits made locally but not yet pushed to the upstream branch |
 
 **messyagent**
 
 | Command | Description |
 |---------|-------------|
 | `suggest` | Get AI-powered next-step suggestions for your project |
+| `changelog` | Generate or update `CHANGELOG.md` from the commits between your two latest tags (requires at least one tag) |
+| `trace` | Show what the last agent run actually did — its tool calls and results |
 
 **account**
 
@@ -105,6 +110,7 @@ Commands are grouped on the `help` screen:
 |---------|-------------|
 | `todo` | Open your todo list in `$EDITOR` (saved to `~/.messygit/todo.md`) |
 | `theme` or `theme <name>` | Change the UI color (run `theme` to list presets) |
+| `verbose` or `verbose on\|off` | Toggle live streaming of agent steps (persists; off by default) |
 | `help` | List available commands |
 | `quit` / `exit` | Exit messygit |
 
@@ -123,6 +129,41 @@ messygit > push
 
 > Tip: run `suggest` for AI next-step ideas, or `theme` to recolor the UI.
 
+### Agent commands & transparency
+
+`suggest` and `changelog` are backed by an agent that uses tools (read-only git,
+file reads, and — for `changelog` — repo-scoped file writes) over several steps.
+
+By default a run shows only a spinner and the final result. Two commands let you
+see inside:
+
+```
+messygit > changelog          # generates/updates CHANGELOG.md
+messygit > trace              # expand what that run just did
+
+╭─ trace · changelog · 4 tool calls ─────────────╮
+│ 1. run_git  tag --sort=-creatordate            │
+│    └ v0.4.0  (+3 more lines)                    │
+│ 2. run_git  log v0.3.2..v0.4.0                  │
+│    └ commit a1b2c3 feat: …  (+12 more lines)    │
+│ 3. read_file  CHANGELOG.md                      │
+│    └ ## [v0.3.2] - 2026-06-20                    │
+│ 4. edit_file  CHANGELOG.md                      │
+│    └ File edited successfully.                   │
+╰─────────────────────────────────────────────────╯
+```
+
+Prefer to watch it happen live? Turn on `verbose` — the same steps stream as the
+agent works (no spinner). The setting persists in `~/.messygit/config.json`:
+
+```
+messygit > verbose on
+Verbose on — agent runs will stream their steps live (no spinner)
+```
+
+`changelog` requires at least one git tag; it documents the range between your two
+most recent tags (or the latest tag to `HEAD` when only one exists).
+
 ### Commit message style
 
 The model follows **Conventional Commits**: `type(scope): description`
@@ -131,7 +172,7 @@ Allowed types: `feat`, `fix`, `docs`, `style`, `refactor`, `test`, `chore`. Subj
 
 ### Token usage & cost
 
-messygit tracks the tokens used by AI commands (`commit`, `suggest`) for the current session and shows a running total after each call. Run `tokens` for a breakdown and a one-key jump to the Anthropic billing console:
+messygit tracks the tokens used by AI commands (`commit`, `suggest`, `changelog`) for the current session and shows a running total after each call. Run `tokens` for a breakdown and a one-key jump to the Anthropic billing console:
 
 ```
 messygit > tokens
@@ -163,6 +204,34 @@ Switch anyway? [y/N]:
 
 Switching to a **more expensive** model prompts for confirmation first. The session cost estimate prices each request at the model used for it, so it stays accurate even if you switch mid-session.
 
+## Development & testing
+
+Install the package with its dev dependencies (pytest), then run the suite:
+
+```bash
+pip install -e ".[dev]"
+pytest -q
+```
+
+The tests live in `tests/` and are pure unit tests — no network calls and no
+API key required (the Anthropic client is simulated). They cover:
+
+| File | What it covers |
+|------|----------------|
+| `tests/config_test.py` | API-key resolution order (env → file), key save/load, theme/model/todo persistence, malformed-config handling |
+| `tests/git_test.py` | The diff parser — noise-file filtering and the compact changed-lines format |
+| `tests/llm_test.py` | Insufficient-balance / billing-error detection and user messaging |
+| `tests/tool_schema_test.py` | Agent tool schemas match the shape the Anthropic Messages API expects |
+| `tests/agent_test.py` | The agent's tool-use loop, driven by a simulated Anthropic client with scripted responses |
+| `tests/trace_test.py` | The `trace` renderer — step numbering, result truncation, empty state, and markup-safety of raw tool output |
+| `tests/verbose_test.py` | The `verbose` setting, the toggle command, and `_drive` choosing live-stream vs. spinner |
+
+### Continuous integration
+
+`.github/workflows/test.yml` runs `pytest` on every push to `main` and on every
+pull request, across Python 3.10–3.13. No secrets are required because the tests
+mock the Anthropic client.
+
 ## Publishing to PyPI
 
 This project uses GitHub Actions with [PyPI trusted publishing](https://docs.pypi.org/trusted-publishers/) — no API tokens needed in your repo.

{messygit-0.3.1 → messygit-0.4.0}/messygit/agent/agent.py

@@ -1,3 +1,5 @@
+from dataclasses import dataclass, field
+
 from .tool import Tool
 from anthropic import (
     Anthropic,
@@ -20,21 +22,52 @@ from ..usage import SESSION_USAGE
 
 DEFAULT_MAX_TOKENS = 4096
 
+
+@dataclass
+class TraceStep:
+    """One recorded step of an agent run, for the `trace` command.
+
+    kind == "text": the model's narration (`text` holds it).
+    kind == "tool": a tool call (`name`/`tool_input`/`result`/`is_error`).
+    """
+    kind: str
+    text: str = ""
+    name: str = ""
+    tool_input: dict = field(default_factory=dict)
+    result: str = ""
+    is_error: bool = False
+
+
 class Agent:
     def __init__(self, name: str, system_prompt: str, max_iterations: int, tools: list[Tool]):
         self.name = name
         self.system_prompt = system_prompt
         self.max_iterations = max_iterations
         self.tools = tools
+        # Populated on each run(); read afterwards by the `trace` command.
+        self.steps: list[TraceStep] = []
 
-    def run(self, user_input: str) -> str:
-        """Run the agent."""
+    def run(self, user_input: str, on_step=None) -> str:
+        """Run the agent.
+
+        `on_step`, if given, is called with each TraceStep as it happens (used by
+        verbose mode to stream steps live). The full list is also kept on
+        self.steps for the `trace` command.
+        """
         client = Anthropic(api_key=resolve_api_key())
         model = current_model()
         messages = []
+        self.steps = []
+
+        def record(step: TraceStep) -> None:
+            self.steps.append(step)
+            if on_step is not None:
+                on_step(step)
+
         try:
             messages.append({"role": "user", "content": user_input})
             response = None
+            completed = False
             for i in range(self.max_iterations):
                 response = client.messages.create(
                     model=model.id,
@@ -47,18 +80,38 @@ class Agent:
                 SESSION_USAGE.record(response.usage, model)
                 messages.append({"role": "assistant", "content": response.content})
 
+                for block in response.content:
+                    if getattr(block, "type", None) == "text" and block.text.strip():
+                        record(TraceStep(kind="text", text=block.text.strip()))
+
                 tool_use_blocks = [b for b in response.content if b.type == "tool_use"]
                 if not tool_use_blocks:
+                    completed = True
                     break
 
                 tool_results = []
                 for block in tool_use_blocks:
-                    tool = next(t for t in self.tools if t.name == block.name)
-                    result = tool.run(**block.input)
+                    tool = next((t for t in self.tools if t.name == block.name), None)
+                    if tool is None:
+                        content, is_error = f"Unknown tool: {block.name!r}.", True
+                    else:
+                        try:
+                            content, is_error = str(tool.run(**block.input)), False
+                        except Exception as e:
+                            content = f"Error running tool {block.name!r}: {e}"
+                            is_error = True
+                    record(TraceStep(
+                        kind="tool",
+                        name=block.name,
+                        tool_input=dict(block.input),
+                        result=content,
+                        is_error=is_error,
+                    ))
                     tool_results.append({
                         "type": "tool_result",
                         "tool_use_id": block.id,
-                        "content": str(result),
+                        "content": content,
+                        **({"is_error": True} if is_error else {}),
                     })
                 messages.append({"role": "user", "content": tool_results})
         except AuthenticationError as e:
@@ -79,4 +132,13 @@ class Agent:
             raise
         if not response:
             return "No response from the agent."
-        return _text_from_message(response)
+        text = _text_from_message(response)
+        if not completed:
+            warning = (
+                f"⚠️ Stopped after reaching the {self.max_iterations}-iteration "
+                "limit before finishing. The task is incomplete — any file the "
+                "agent was meant to write may be missing or partial. Try again, "
+                "and consider raising the iteration limit if this recurs."
+            )
+            return f"{warning}\n\n{text}" if text else warning
+        return text

{messygit-0.3.1 → messygit-0.4.0}/messygit/agent/tool.py

@@ -12,17 +12,21 @@ class Tool:
     description: str
     function: Callable[..., Any]
     parameters: dict[str, Any] = field(default_factory=dict)
+    required: list[str] = field(default_factory=list)
 
     def run(self, **kwargs: Any) -> Any:
         return self.function(**kwargs)
 
     def to_schema(self) -> dict[str, Any]:
         """Return an Anthropic-compatible tool schema for API calls."""
+        input_schema: dict[str, Any] = {
+            "type": "object",
+            "properties": self.parameters,
+        }
+        if self.required:
+            input_schema["required"] = self.required
         return {
             "name": self.name,
             "description": self.description,
-            "input_schema": {
-                "type": "object",
-                "properties": self.parameters,
-            },
+            "input_schema": input_schema,
         }