limbo-code 0.1.9__tar.gz → 0.1.11__tar.gz

{limbo_code-0.1.9 → limbo_code-0.1.11}/.github/workflows/test.yml

@@ -25,12 +25,24 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
 
+      # grep hard-depends on ripgrep (no Python fallback since LIM-24).
+      - name: Install ripgrep
+        run: sudo apt-get install -y ripgrep
+
       # Install from uv.lock so CI renders snapshots with the exact same
       # textual/rich/syrupy versions the baselines were generated with.
+      # Dev tools (pytest/ruff/mypy) are a PEP 735 dependency group and are
+      # installed by default — no --extra flag.
       - name: Install dependencies
-        run: uv sync --frozen --extra dev
+        run: uv sync --frozen
         env:
           UV_PYTHON: ${{ matrix.python-version }}
 
       - name: Run tests
         run: uv run python -m pytest -v
+
+      - name: Lint
+        run: uv run ruff check src tests
+
+      - name: Type check
+        run: uv run mypy src

{limbo_code-0.1.9 → limbo_code-0.1.11}/AGENTS.md

@@ -2,15 +2,19 @@
 
 **Limbo** is a minimal terminal AI coding agent (Python 3.11+, Textual). Users converse with an LLM in a TUI to explore, read, edit, and write code via 7 tools.
 
-**Tools execute immediately — no confirmation flow.** Guardrails: a workdir fence on file tools (+ session-scoped grants from user-mentioned paths), a sensitive-file blocklist on `read`, and a heuristic dangerous-command filter on `bash` (rejects matches outright; bypassable via subshells/variables — documented in the tool description).
+**Tools execute immediately — no confirmation flow.** Convenience guardrails (not a security boundary): a workdir scope on file tools (+ session-scoped grants from user-mentioned paths), a sensitive-file skip list shared by `read`/`grep`/`find`, and a heuristic dangerous-command filter on `bash` (best-effort, rejects matches outright; `bash` is otherwise not covered by any guardrail).
 
 ## Quick Start
 
 ```bash
-pip install -e .
-limbo --workdir /path/to/project   # config: ~/.limbo/config.toml
+uv sync                               # installs runtime + dev tools (PEP 735 dev group, on by default)
+uv run limbo --workdir /path/to/project   # config: ~/.limbo/config.toml
 ```
 
+Prefer `uv` over `pip`: dev tools (pytest/ruff/mypy) are a `[dependency-groups]`
+group, NOT an extra — `pip install -e ".[dev]"` no longer exists. `pip install -e .`
+still works for a runtime-only install.
+
 ## Architecture
 
 ```
@@ -25,6 +29,8 @@ src/limbo/
 ├── model_switch.py   # /model domain logic: validate, swap client, persist (UI is an adapter)
 ├── prompt.py         # System-prompt assembly (tools section derived from the registry)
 ├── steer.py          # Mid-turn steer queue (LIM-20): queueing semantics, cancel boundary
+├── goal.py           # /goal closed-loop state machine, prompt templates, verify executor (LIM-40)
+├── goal_driver.py    # /goal orchestrator (frontend-agnostic, non-UI): turn → verify → next round
 ├── sessions.py       # Session JSONL save/load/list/export
 ├── trace.py          # Append-only JSONL run log (sessions/traces/)
 ├── skills.py         # SKILL.md discovery (user + project dirs)
@@ -33,7 +39,7 @@ src/limbo/
 │                     # openai_client.py, anthropic_client.py, responses_client.py, retry.py, sse.py,
 │                     # usage.py (token accounting: usage normalization + prompt-size estimation),
 │                     # scaffold.py (plumbing shared by dialect clients: credentials, retry, images)
-├── tools/            # base.py (BaseTool + fence + truncation), registry.py (dispatch, grants),
+├── tools/            # base.py (BaseTool + path guardrail + truncation), registry.py (dispatch, grants),
 │                     # mutation_queue.py (per-file locks), ignore.py (.gitignore),
 │                     # read/bash/edit/write/grep/find/ls.py
 └── ui/               # app.py + app.tcss (ALL styles here; theme vars only, no bare hex),
@@ -47,7 +53,7 @@ src/limbo/
 - `Agent.run()` yields `AgentEvent`: `TextDelta`, `ThinkingDelta`, `ToolCallRequest`, `ToolResultEvent`, `ErrorEvent`, `CompactionEvent`, `UsageUpdate`, `SteerEvent`
 - Loop top: auto-compaction check → steer drain → LLM call. Turn ends on a tool-call-free response; `max_iterations` (default 50) cancels pending calls with placeholder results
 - Tool calls in one turn run **concurrently** (`[tools] parallel`); results stream in completion order, recorded in source order; same-file mutations serialized by `mutation_queue`
-- `finish_reason` `length`/`max_tokens` → whole batch failed without execution, model re-issues
+- `finish_reason` `length`/`max_tokens` → whole batch failed without execution; the error result names the effective `max_tokens` and steers the model to write large scripts via `write` instead of re-issuing the same call. 3 consecutive length stops abort the turn with actionable guidance (trace `kind=length_stop_loop`); a text-only truncated response emits a "may be incomplete" warning
 - Mid-turn user input queues as *steer* (LIM-20): injected at loop top, or as turn-end follow-up
 - Reasoning is stored on assistant messages and replayed per dialect (Anthropic thinking signatures, Kimi `reasoning_content`, Responses encrypted items)
 - Usage counters normalize in `llm/usage.py` (`input_tokens`+`cache_read`, `prompt_tokens`, DeepSeek cache hits) and feed the compaction trigger via `PromptSizeEstimator`
@@ -61,6 +67,7 @@ Providers/models live in `llm/catalog.py`; unknown models get generic OpenAI-com
              # max_tokens, thinking_effort, max_retries, timeout, ...
 [tools]      # bash_enabled = true, parallel = true
 [compaction] # enabled, reserve_tokens = 16384, keep_recent_tokens = 20000
+[goal]       # max_rounds = 10, verify_timeout_ms = 600000
 [safety]     # dangerous_commands, sensitive_files, auto_grant_user_paths
 [ui]         # theme, show_banner
 [providers.<id>]  # base_url / api_key / api_key_env / headers
@@ -72,7 +79,9 @@ Skills: `~/.limbo/skills/<name>/SKILL.md` (user) and `<workdir>/.agents/skills/<
 
 ## UI
 
-Single column: status bar (state/elapsed/tokens/model/workdir/queued) → scrolling chat flow (user `❯`, streaming Markdown, tool cards, errors) → input box (Enter submits, Shift+Enter newline, paste markers, `ctrl+v` image attach) → hint line. Slash commands: `/sessions /new /export /compact /model /help /2048` + skill commands. After palette changes run `python scripts/check_contrast.py` (≥ 4.5:1).
+Single column: status bar (state/elapsed/tokens/model/workdir/queued + rainbow 🎯GOAL badge while a goal loop runs) → scrolling chat flow (user `❯`, streaming Markdown, tool cards, errors) → input box (Enter submits, Shift+Enter newline, paste markers, `ctrl+v` image attach) → hint line. Slash commands: `/sessions /new /export /compact /model /help /2048 /goal` + skill commands. After palette changes run `python scripts/check_contrast.py` (≥ 4.5:1).
+
+`/goal <text>` starts closed-loop mode (LIM-40): the first round is a proposal round — the model explores the repo and proposes acceptance command(s) in a `<verify_proposal>` block; the user confirms in a picker (accept / edit / skip), then `GoalDriver` (non-UI, shared by any frontend) runs each round as a complete `Agent.run()` turn and executes the verify command; exit 0 ends the loop, otherwise the failure output is fed back verbatim into the next round until `max_rounds`, when a no-tool wrap-up turn summarizes and any user message resumes with a fresh budget. Goal state persists on `SessionMeta.goal`. Esc during verify cancels the subprocess.
 
 ## Key Decisions
 
@@ -83,9 +92,17 @@ Single column: status bar (state/elapsed/tokens/model/workdir/queued) → scroll
 ## Testing
 
 ```bash
-pytest tests/ -v                  # pytest-asyncio, respx HTTP mocks, pytest-textual-snapshot
-ruff check src tests && mypy src  # lint + type check
-pytest --snapshot-update          # after intentional visual changes; review the SVG diff
+make check                          # single entrypoint: sync + tests + lint + type check
+```
+
+Or individually — always `python -m pytest`, never bare `uv run pytest` (which
+silently falls through to a global pytest on PATH when the venv lacks pytest):
+
+```bash
+uv sync                             # first time / after pulling; dev group is default
+uv run python -m pytest tests/ -v   # pytest-asyncio, respx HTTP mocks, pytest-textual-snapshot
+uv run ruff check src tests && uv run mypy src  # lint + type check
+uv run python -m pytest --snapshot-update  # after intentional visual changes; review the SVG diff
 ```
 
 ## Adding Things

limbo_code-0.1.11/Makefile

@@ -0,0 +1,23 @@
+# Single entrypoint for dev checks — humans and agents should only need
+# `make check`. Dev tools (pytest/ruff/mypy) are a PEP 735 dependency group,
+# so plain `uv sync` installs them.
+#
+# Note: tests run via `uv run python -m pytest`, NOT `uv run pytest` — the
+# latter silently falls through to a global pytest on PATH when the venv
+# lacks pytest, which can run the suite against the wrong source tree.
+
+.PHONY: sync test lint typecheck check
+
+sync:
+	uv sync
+
+test:
+	uv run python -m pytest tests/ -v
+
+lint:
+	uv run ruff check src tests
+
+typecheck:
+	uv run mypy src
+
+check: sync test lint typecheck

{limbo_code-0.1.9 → limbo_code-0.1.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: limbo-code
-Version: 0.1.9
+Version: 0.1.11
 Summary: A minimal terminal AI coding agent
 Requires-Python: >=3.11
 Requires-Dist: httpx>=0.27
@@ -10,14 +10,6 @@ Requires-Dist: pygments>=2.17
 Requires-Dist: textual>=8.0
 Requires-Dist: toml>=0.10
 Requires-Dist: tomlkit>=0.13
-Provides-Extra: dev
-Requires-Dist: mypy>=1.10; extra == 'dev'
-Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
-Requires-Dist: pytest-textual-snapshot>=1.0; extra == 'dev'
-Requires-Dist: pytest>=8.0; extra == 'dev'
-Requires-Dist: respx>=0.21; extra == 'dev'
-Requires-Dist: ruff>=0.4; extra == 'dev'
-Requires-Dist: types-pygments>=2.17; extra == 'dev'
 Description-Content-Type: text/markdown
 
 # Limbo
@@ -29,7 +21,7 @@ A minimal terminal AI coding agent.
 Requires Python 3.11 or later.
 
 ```bash
-pip install -e .
+pip install limbo-code
 ```
 
 ## Configure
@@ -39,7 +31,7 @@ Create `~/.limbo/config.toml`:
 ```toml
 [llm]
 api_key = "your-api-key"
-model = "deepseek-chat"
+model = "deepseek-v4-pro"
 base_url = "https://api.deepseek.com/v1"
 ```
 
@@ -226,23 +218,24 @@ flight.
 ## Safety
 
 Limbo executes every tool call immediately, without asking for confirmation.
-File tools (`read`, `edit`, `write`, `grep`, `find`, `ls`) are bounded to the
-current working directory and reject paths that escape it, including via
-symlinks. The boundary check resolves the path before each operation, so a
-symlink swapped between the check and the operation (a time-of-check-to-time-of-use
-race) could escape the workdir. **This is a known limitation for the MVP.**
+
+File tools (`read`, `edit`, `write`, `grep`, `find`, `ls`) are scoped to the
+current working directory plus any session grants (paths the user mentions in
+a message), and `read`/`grep`/`find` skip a small blocklist of sensitive files
+(`.env`, SSH keys) to avoid leaking secrets into the model context by accident.
+**These are convenience guardrails against accidents, not a security boundary.**
+The path check resolves the path before each operation, so a symlink swapped
+between the check and the operation (a time-of-check-to-time-of-use race) could
+escape it.
 
 Bash is an exception: it is started in the working directory but is **not**
-sandboxed. Commands can `cd ..`, use absolute paths, and read or write outside
-the workdir. In addition, commands that match dangerous patterns such as `rm`
-or `git reset --hard` are **rejected outright**.
-The pattern list is configurable but cannot be disabled from the UI. Bash
-commands are filtered with a simple heuristic, but that filter can be bypassed
-by subshells (`bash -c 'rm -rf /'`), command substitution (`$(rm -rf /)`),
-variable indirection, options before the command name
-(`git -C /foo reset --hard`), variable assignments before the command name
-(`VAR=1 rm -rf /`), and similar shell constructs. Only run Limbo with
-trusted commands and in repositories you can afford to modify or lose.
+covered by any of these guardrails. Commands can `cd ..`, use absolute paths,
+and read or write outside the workdir. Commands that match dangerous patterns
+such as `rm` or `git reset --hard` are **rejected outright** by a best-effort
+heuristic filter — ordinary shell constructs can bypass it, so it only
+protects against accidents. The pattern list is configurable but cannot be
+disabled from the UI. Only run Limbo with trusted commands and in
+repositories you can afford to modify or lose.
 
 If you need to work with untrusted projects, disable the bash tool entirely:
 
@@ -253,15 +246,25 @@ bash_enabled = false
 
 ## Development
 
-Run tests:
+Set up the environment (dev tools are a PEP 735 dependency group, so plain
+`uv sync` installs pytest/ruff/mypy — no `--extra` flag):
+
+```bash
+uv sync
+```
+
+Run everything (sync + tests + lint + type check) with one command:
 
 ```bash
-pytest tests/ -v
+make check
 ```
 
-Run linting and type checks:
+Or run the pieces individually. Always use `python -m pytest`: `uv run pytest`
+silently falls through to a global pytest on PATH when the venv lacks pytest,
+which can run the suite against the wrong source tree.
 
 ```bash
-ruff check src tests
-mypy src
+uv run python -m pytest tests/ -v   # tests
+uv run ruff check src tests         # lint
+uv run mypy src                     # type check
 ```

{limbo_code-0.1.9 → limbo_code-0.1.11}/README.md

@@ -7,7 +7,7 @@ A minimal terminal AI coding agent.
 Requires Python 3.11 or later.
 
 ```bash
-pip install -e .
+pip install limbo-code
 ```
 
 ## Configure
@@ -17,7 +17,7 @@ Create `~/.limbo/config.toml`:
 ```toml
 [llm]
 api_key = "your-api-key"
-model = "deepseek-chat"
+model = "deepseek-v4-pro"
 base_url = "https://api.deepseek.com/v1"
 ```
 
@@ -204,23 +204,24 @@ flight.
 ## Safety
 
 Limbo executes every tool call immediately, without asking for confirmation.
-File tools (`read`, `edit`, `write`, `grep`, `find`, `ls`) are bounded to the
-current working directory and reject paths that escape it, including via
-symlinks. The boundary check resolves the path before each operation, so a
-symlink swapped between the check and the operation (a time-of-check-to-time-of-use
-race) could escape the workdir. **This is a known limitation for the MVP.**
+
+File tools (`read`, `edit`, `write`, `grep`, `find`, `ls`) are scoped to the
+current working directory plus any session grants (paths the user mentions in
+a message), and `read`/`grep`/`find` skip a small blocklist of sensitive files
+(`.env`, SSH keys) to avoid leaking secrets into the model context by accident.
+**These are convenience guardrails against accidents, not a security boundary.**
+The path check resolves the path before each operation, so a symlink swapped
+between the check and the operation (a time-of-check-to-time-of-use race) could
+escape it.
 
 Bash is an exception: it is started in the working directory but is **not**
-sandboxed. Commands can `cd ..`, use absolute paths, and read or write outside
-the workdir. In addition, commands that match dangerous patterns such as `rm`
-or `git reset --hard` are **rejected outright**.
-The pattern list is configurable but cannot be disabled from the UI. Bash
-commands are filtered with a simple heuristic, but that filter can be bypassed
-by subshells (`bash -c 'rm -rf /'`), command substitution (`$(rm -rf /)`),
-variable indirection, options before the command name
-(`git -C /foo reset --hard`), variable assignments before the command name
-(`VAR=1 rm -rf /`), and similar shell constructs. Only run Limbo with
-trusted commands and in repositories you can afford to modify or lose.
+covered by any of these guardrails. Commands can `cd ..`, use absolute paths,
+and read or write outside the workdir. Commands that match dangerous patterns
+such as `rm` or `git reset --hard` are **rejected outright** by a best-effort
+heuristic filter — ordinary shell constructs can bypass it, so it only
+protects against accidents. The pattern list is configurable but cannot be
+disabled from the UI. Only run Limbo with trusted commands and in
+repositories you can afford to modify or lose.
 
 If you need to work with untrusted projects, disable the bash tool entirely:
 
@@ -231,15 +232,25 @@ bash_enabled = false
 
 ## Development
 
-Run tests:
+Set up the environment (dev tools are a PEP 735 dependency group, so plain
+`uv sync` installs pytest/ruff/mypy — no `--extra` flag):
+
+```bash
+uv sync
+```
+
+Run everything (sync + tests + lint + type check) with one command:
 
 ```bash
-pytest tests/ -v
+make check
 ```
 
-Run linting and type checks:
+Or run the pieces individually. Always use `python -m pytest`: `uv run pytest`
+silently falls through to a global pytest on PATH when the venv lacks pytest,
+which can run the suite against the wrong source tree.
 
 ```bash
-ruff check src tests
-mypy src
+uv run python -m pytest tests/ -v   # tests
+uv run ruff check src tests         # lint
+uv run mypy src                     # type check
 ```

{limbo_code-0.1.9 → limbo_code-0.1.11}/docs/session-management.md

@@ -26,7 +26,7 @@
 JSONL，首行为 meta，后续为消息行。**向后兼容**：无 meta 行的旧文件可正常加载。
 
 ```jsonl
-{"type":"meta","id":"20260720-103000-123456-42","workdir":"/path/to/proj","model":"deepseek-chat","title":"修复 grep 工具 bug","created_at":"...","updated_at":"..."}
+{"type":"meta","id":"20260720-103000-123456-42","workdir":"/path/to/proj","model":"deepseek-v4-pro","title":"修复 grep 工具 bug","created_at":"...","updated_at":"..."}
 {"role":"system","content":"..."}
 {"role":"user","content":"..."}
 {"role":"assistant","content":"...","tool_calls":[...]}
@@ -107,7 +107,7 @@ append-only，崩溃/打断最多丢失写入中的一条）。`/export` 默认
 | `llm_response` | `duration`、`ttft`、`finish_reason`、`usage`（原始用量，含 provider 缓存字段）、`cached_tokens`（归一化缓存命中）、content/reasoning 长度、tool_calls 摘要 |
 | `llm_error` | `exception_type`、`error`、`traceback` |
 | `tool_call` / `tool_result` | `id`、`name`、`arguments`、`success`、`output`/`error`、耗时；崩溃时带 `exception_type` + `traceback` |
-| `error` | `kind`（如 max_iterations）、`message` |
+| `error` | `kind`（如 max_iterations / length_stop / length_stop_loop）、`message` |
 | `turn_end` | `iterations`、`duration`、`status`（completed） |
 | `session_save_error` | `error` |
 

{limbo_code-0.1.9 → limbo_code-0.1.11}/pyproject.toml

@@ -16,7 +16,11 @@ dependencies = [
     "pygments>=2.17",
 ]
 
-[project.optional-dependencies]
+[dependency-groups]
+# Dev tools live in a PEP 735 dependency group (not an extra) so `uv sync`
+# installs them by default — no `--extra`/`--group` flag needed. Always run
+# tests via `uv run python -m pytest` so a missing venv fails loudly instead
+# of silently falling through to a global pytest on PATH.
 dev = [
     "pytest>=8.0",
     "pytest-asyncio>=0.23",