python-agent-harness 1.5.6.3__tar.gz → 1.5.6.4__tar.gz

{python_agent_harness-1.5.6.3/python_agent_harness.egg-info → python_agent_harness-1.5.6.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-agent-harness
-Version: 1.5.6.3
+Version: 1.5.6.4
 Summary: A lightweight, hackable mini-OpenCode written in Python.
 Author-email: Huming Chen <chenhuming@gmail.com>
 License-Expression: MIT
@@ -74,7 +74,7 @@ Edit `~/.config/python-agent-harness/config.json` and set your `base_url`, `api_
 - **FSM-driven execution** — explicit `WAIT` / `TOOL` / `TRET` / `SUPERVISE` / `DONE` / `ERRS` / `ABRT` states. Completion supervision nudges the model when it stops early; failed tool calls are sanitized. Transient API failures (`429` / `5xx`) retry with exponential backoff. Auth-expired codes (configurable via `AUTH_REFRESH_STATUS_CODES` in `config.py`; defaults to `[401, 502]`) trigger automatic API key re-read from config/env.
 - **Context management** — CJK-aware token estimation, per-model context windows, automatic compaction at 70% usage.
 - **Image & text attachments** — attach with `@path` (e.g. `@screenshot.png`, `@README.md`): images (PNG/JPEG/GIF/WebP, up to 20 MB) become multimodal `image_url` parts; text files are inlined. Web URLs supported for images.
-- **Coding tools** — `Agent`, `TodoWrite`, `Glob`, `Grep`, `Read`, `Insert`, `Edit` (incl. unified diffs), `Write`, `Mkdir`, `Bash`, `Skill`, `Question`, `LSP`, `PlanExit`. Read-only tool rounds (`Read`, `Glob`, `Grep`, `Skill`, `LSP`) dispatch concurrently; async tools (`Bash`, `Agent`) can also run concurrently. Results always delivered in emitted order.
+- **Coding tools** — `Agent`, `TodoWrite`, `Glob`, `Grep`, `Read`, `Edit` (incl. unified diffs), `Write`, `Bash`, `Skill`, `Question`, `PlanExit`. Read-only tool rounds (`Read`, `Glob`, `Grep`, `Skill`) dispatch concurrently; async tools (`Bash`, `Agent`) can also run concurrently. Results always delivered in emitted order.
 - **Plan / Build modes** — plan mode is read-only except for the per-session plan file.
 - **Persistent sessions** — auto-saved after every response to `~/.local/share/python-agent-harness/sessions/`, with LLM-generated titles and `/restore --latest` / `/sessions`.
 - **Focused TUI** — Rich-based with pinned status bar, Todos panel, inline diff rendering, and a `prompt_toolkit` editor with history and completion. `Esc+Enter` submits, `Ctrl-D` quits, `Ctrl-C` cancels.
@@ -191,7 +191,6 @@ All LLM settings live in `~/.config/python-agent-harness/config.json`. Environme
 - **`subagent_llm`** — LLM config for `Agent` tool. Unset values inherit from `llm`. Set `profile` to reuse a `models` entry. Precedence: profile > `subagent_llm` > `llm` > env vars.
 - **`default_agent`** — agent name to use at session start (must exist in `prompts/agents/`). `null` = built-in default.
 - **`paths.context_path` / `paths.skill_path`** — locations for context files and skills. Default: project-local `contexts/` and `skills/`.
-- **`lsp.servers`** — per-extension LSP server overrides for the `LSP` tool. Keys are extensions (`.py`, `.cpp`); each has `command` (argv) and optional `language_id`. Layers on top of `DEFAULT_SERVERS` in `lsp/manager.py`.
 - **`mcp.servers`** — MCP server config (requires `[mcp]` extra). Each supports `transport`, `command`, `args`, `env`, `url`, `headers`, `parallel`, `timeout`, `enabled`.
 - **`headless` / `serve`** — optional budget limits: `max_rounds` (LLM rounds) and `timeout` (wall-clock seconds). `--max-rounds` / `--timeout` override per call; `<= 0` or `null` disables. Unset = unlimited.
 - **Precedence** — code defaults < config file < `OPENAI_*` env vars. Sub-agents also support `OPENAI_SUBAGENT_*` (`_BASE_URL`, `_API_KEY`, `_MODEL`).

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/README.md

@@ -40,7 +40,7 @@ Edit `~/.config/python-agent-harness/config.json` and set your `base_url`, `api_
 - **FSM-driven execution** — explicit `WAIT` / `TOOL` / `TRET` / `SUPERVISE` / `DONE` / `ERRS` / `ABRT` states. Completion supervision nudges the model when it stops early; failed tool calls are sanitized. Transient API failures (`429` / `5xx`) retry with exponential backoff. Auth-expired codes (configurable via `AUTH_REFRESH_STATUS_CODES` in `config.py`; defaults to `[401, 502]`) trigger automatic API key re-read from config/env.
 - **Context management** — CJK-aware token estimation, per-model context windows, automatic compaction at 70% usage.
 - **Image & text attachments** — attach with `@path` (e.g. `@screenshot.png`, `@README.md`): images (PNG/JPEG/GIF/WebP, up to 20 MB) become multimodal `image_url` parts; text files are inlined. Web URLs supported for images.
-- **Coding tools** — `Agent`, `TodoWrite`, `Glob`, `Grep`, `Read`, `Insert`, `Edit` (incl. unified diffs), `Write`, `Mkdir`, `Bash`, `Skill`, `Question`, `LSP`, `PlanExit`. Read-only tool rounds (`Read`, `Glob`, `Grep`, `Skill`, `LSP`) dispatch concurrently; async tools (`Bash`, `Agent`) can also run concurrently. Results always delivered in emitted order.
+- **Coding tools** — `Agent`, `TodoWrite`, `Glob`, `Grep`, `Read`, `Edit` (incl. unified diffs), `Write`, `Bash`, `Skill`, `Question`, `PlanExit`. Read-only tool rounds (`Read`, `Glob`, `Grep`, `Skill`) dispatch concurrently; async tools (`Bash`, `Agent`) can also run concurrently. Results always delivered in emitted order.
 - **Plan / Build modes** — plan mode is read-only except for the per-session plan file.
 - **Persistent sessions** — auto-saved after every response to `~/.local/share/python-agent-harness/sessions/`, with LLM-generated titles and `/restore --latest` / `/sessions`.
 - **Focused TUI** — Rich-based with pinned status bar, Todos panel, inline diff rendering, and a `prompt_toolkit` editor with history and completion. `Esc+Enter` submits, `Ctrl-D` quits, `Ctrl-C` cancels.
@@ -157,7 +157,6 @@ All LLM settings live in `~/.config/python-agent-harness/config.json`. Environme
 - **`subagent_llm`** — LLM config for `Agent` tool. Unset values inherit from `llm`. Set `profile` to reuse a `models` entry. Precedence: profile > `subagent_llm` > `llm` > env vars.
 - **`default_agent`** — agent name to use at session start (must exist in `prompts/agents/`). `null` = built-in default.
 - **`paths.context_path` / `paths.skill_path`** — locations for context files and skills. Default: project-local `contexts/` and `skills/`.
-- **`lsp.servers`** — per-extension LSP server overrides for the `LSP` tool. Keys are extensions (`.py`, `.cpp`); each has `command` (argv) and optional `language_id`. Layers on top of `DEFAULT_SERVERS` in `lsp/manager.py`.
 - **`mcp.servers`** — MCP server config (requires `[mcp]` extra). Each supports `transport`, `command`, `args`, `env`, `url`, `headers`, `parallel`, `timeout`, `enabled`.
 - **`headless` / `serve`** — optional budget limits: `max_rounds` (LLM rounds) and `timeout` (wall-clock seconds). `--max-rounds` / `--timeout` override per call; `<= 0` or `null` disables. Unset = unlimited.
 - **Precedence** — code defaults < config file < `OPENAI_*` env vars. Sub-agents also support `OPENAI_SUBAGENT_*` (`_BASE_URL`, `_API_KEY`, `_MODEL`).

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "python-agent-harness"
-version = "1.5.6.3"
+version = "1.5.6.4"
 description = "A lightweight, hackable mini-OpenCode written in Python."
 authors = [
     {name = "Huming Chen", email = "chenhuming@gmail.com"}

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/__init__.py

@@ -3,20 +3,17 @@
 from .core.models import AgentMode, ImagePart, Message, TextPart, ToolCall, ToolSpec
 from .entry.cli import main  # noqa: F401  (public lib surface: main entry point)
 from .llm.client import Client, LLMClient
-from .lsp.config import LSPConfig, LSPServerConfig
 from .mcp.config import MCPConfig, MCPServerConfig
 from .mcp.manager import MCPManager
 from .session.session import Session
 
-__version__ = "1.5.6.3"
+__version__ = "1.5.6.4"
 
 __all__ = [
     "Client",
     "LLMClient",
     "Session",
     "AgentMode",
-    "LSPConfig",
-    "LSPServerConfig",
     "MCPConfig",
     "MCPManager",
     "MCPServerConfig",

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/core/agent.py

@@ -552,6 +552,20 @@ class AgentLoop:
                         self._just_compacted = True
                         self.info["compacted"] = True
                         return
+                    # Compaction failed (empty summary, no reducible
+                    # prompts, or an exception -- see ContextManager.
+                    # compact): the history is unchanged, so without a
+                    # guard the next WAIT round sees the same
+                    # above-trigger ratio and compacts again, re-billing
+                    # the summary request every round for nothing.
+                    # Remember the current ratio as the floor -- reusing
+                    # the same mechanism as the "still above trigger
+                    # after a successful compaction" case above -- so
+                    # the guard below suppresses re-compaction until the
+                    # context grows meaningfully past it, at which point
+                    # a retry is warranted (the conversation really did
+                    # grow) rather than a no-op loop.
+                    self._compaction_floor = ratio
             else:
                 self._compaction_floor = None
             self._just_compacted = False

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/entry/cli.py

@@ -45,11 +45,6 @@ def make_session(
     settings = config.load_llm_config(config_path)
     paths = config.load_paths_config(config_path)
     mcp_config = config.load_mcp_config(config_path)
-    # Validate lsp.servers eagerly so a malformed override fails fast at
-    # session start (with a clear message) instead of poisoning the first
-    # LSP tool call mid-session.  The LSP manager re-reads it lazily via
-    # config_path; this call only surfaces config errors early.
-    config.load_lsp_config(config_path)
     model = model or settings["model"]
     # resolve sub-agent overrides against the EFFECTIVE main settings
     # (so a CLI/caller model override is inherited too when the
@@ -345,14 +340,6 @@ def cmd_config(args: argparse.Namespace) -> int:
             print(f"  {pattern}: {size}")
     else:
         print("context_windows: (none configured — built-in table in config.py applies)")
-    # Show LSP server overrides (per-extension, layered over the built-ins)
-    lsp_config = config.load_lsp_config(args.path)
-    if lsp_config.servers:
-        print("lsp servers:")
-        for ext, server in sorted(lsp_config.servers.items()):
-            print(f"  {ext}: language_id={server.language_id}, command={' '.join(server.command)}")
-    else:
-        print("lsp servers: (none configured — built-in DEFAULT_SERVERS in lsp/manager.py applies)")
     # Show default agent
     default_agent = config.load_default_agent(args.path)
     print(f"default_agent: {default_agent or '(default: agent.md)'}")

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/entry/headless.py

@@ -59,8 +59,8 @@ def _as_error(value: Any) -> dict[str, Any]:
     ``HeadlessView.errors`` accumulates whatever the notifier passed:
     the agent loop sends a structured ``{"code", "message"}`` for
     classified failures (``budget``/``timeout``), other sites send a
-    plain string whose code is then derived from the text, and the LSP
-    client sends a ``{"message": ...}`` dict.  A nested
+    plain string whose code is then derived from the text, and some
+    callers send a ``{"message": ...}`` dict.  A nested
     ``{"error": {...}}`` shape is unwrapped; a dict carrying only a
     ``code`` falls back to that code for its message so the two never
     disagree on emptiness.
@@ -106,8 +106,7 @@ def error_display_text(value: Any) -> str:
 
     ``notify("error", ...)`` carries either a plain message string or a
     structured ``{"code", "message"}`` payload (the agent loop sends
-    the latter where the outcome is known; the LSP client sends a
-    ``{"message": ...}`` dict too).  Views render this rather than the
+    the latter where the outcome is known).  Views render this rather than the
     raw value, so a structured error does not reach a human as a dict
     repr.
 

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/prompts/agent.md

@@ -56,6 +56,7 @@ The user will primarily request you perform software engineering tasks. This inc
 - Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.
 - Implement the solution using all tools available to you
 - Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.
+- Test edge cases to ensure your solution is robust.
 - VERY IMPORTANT:
   - When you have completed a task, you MUST run the lint and typecheck commands (e.g. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to AGENTS.md so that you will know to run it next time.
   - NEVER commit changes unless the user explicitly asks you to.

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/prompts/agents/reviewer.md

@@ -3,9 +3,7 @@ name: reviewer
 exclude_tools:
   - Bash
   - Edit
-  - Insert
   - Write
-  - Mkdir
 ---
 
 # Role and Behavior

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/session/config.py

@@ -6,7 +6,6 @@ import json
 import os
 from pathlib import Path
 
-from ..lsp.config import LSPConfig
 from ..mcp.config import MCPConfig
 
 # ---- context management -------------------------------------------------
@@ -88,14 +87,11 @@ DEFAULT_TOOLS: list[str] = [
     "Glob",
     "Grep",
     "Read",
-    "Insert",
     "Edit",
     "Write",
-    "Mkdir",
     "Bash",
     "Skill",
     "Question",
-    "LSP",
 ]
 
 # ---- tool output limits --------------------------------------------------------
@@ -261,15 +257,6 @@ CONFIG_TEMPLATE = """\
     "context_path": null,
     "skill_path": null
   }},
-  "lsp": {{
-    "_comment": "Optional per-extension LSP server overrides. Keys are file extensions (e.g. '.py', '.cpp'); 'command' is the server argv; 'language_id' defaults to the extension without the dot. These override the built-in DEFAULT_SERVERS table. Remove this section to use only the built-ins. The server binary must be on PATH. The '.example' entry below is inert (no such extension) — copy it to a real extension like '.cpp' to activate.",
-    "servers": {{
-      ".example": {{
-        "command": ["clangd", "--background-index", "--clang-tidy"],
-        "language_id": "cpp"
-      }}
-    }}
-  }},
   "mcp": {{
     "_comment": "Optional MCP servers (requires: pip install -e '.[mcp]'). Each server's tools become agent tools named mcp__<server>__<tool>. Transports: stdio (spawn command+args, pass through env var names), streamable-http / sse (connect to url, optional headers). 'parallel: true' marks read-only servers whose tools may run concurrently; default is serial. 'timeout' bounds connects, discovery and calls (seconds).",
     "servers": {{
@@ -526,31 +513,6 @@ def load_mcp_config(path: str | os.PathLike | None = None) -> MCPConfig:
     return MCPConfig.from_dict(section.get("servers"))
 
 
-def load_lsp_config(path: str | os.PathLike | None = None) -> LSPConfig:
-    """Load per-extension LSP server overrides from the config file.
-
-    Reads the optional ``lsp.servers`` object (keyed by file extension,
-    e.g. ``".py"``) and returns an ``LSPConfig`` (empty when the file
-    has no ``lsp`` section or no servers). These entries layer on top of
-    the built-in ``DEFAULT_SERVERS`` table in ``lsp/manager.py``.
-
-    Malformed entries raise ValueError so config errors surface at
-    session start rather than the first LSP call.
-    """
-    data = _read_config(path)
-    section = data.get("lsp") or {}
-    if not isinstance(section, dict):
-        raise ValueError(f"config file {_config_path(path)}: lsp must be an object")
-    servers = section.get("servers") or {}
-    if not isinstance(servers, dict):
-        raise ValueError(f"config file {_config_path(path)}: lsp.servers must be an object")
-    try:
-        return LSPConfig.from_dict(servers)
-    except ValueError as e:
-        # Re-raise with the config-file path for a clearer message.
-        raise ValueError(f"config file {_config_path(path)}: {e}") from e
-
-
 def load_models_config(path: str | os.PathLike | None = None) -> dict[str, dict]:
     """Load named LLM profiles from the config file's ``models`` object.
 

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/session/session.py

@@ -370,7 +370,7 @@ class Session:
         # write_file/create_directory), so plan mode stays read-only
         # by refusing every mcp__ tool.
         if self.plan_mode.is_plan and (
-            name in ("Write", "Edit", "Insert", "Mkdir", "Bash") or name.startswith("mcp__")
+            name in ("Write", "Edit", "Bash") or name.startswith("mcp__")
         ):
             blocked = self._plan_blocked(name, args)
             if blocked:
@@ -467,16 +467,8 @@ class Session:
                 ),
                 self.project_dir,
             )
-        if name in ("Edit", "Insert"):
+        if name == "Edit":
             return resolve_path(str(args.get("path", "")), self.project_dir)
-        if name == "Mkdir":
-            # Mirrors Mkdir.run: only the parent is ~-expanded.
-            return os.path.realpath(
-                os.path.join(
-                    resolve_path(str(args.get("parent", "")), self.project_dir),
-                    str(args.get("name", "")),
-                )
-            )
         return None
 
     # ------------------------------------------------------------------

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/tools/__init__.py

@@ -9,10 +9,9 @@ from .base import PendingToolResult, Registry, Tool, ToolContext
 from .bash import Bash
 from .edit import Edit
 from .edit_mac import EditMac
-from .filesystem import GlobTool, Grep, Insert, Mkdir, Read, Write
+from .filesystem import GlobTool, Grep, Read, Write
 from .glob_mac import GlobMac
 from .grep_mac import GrepMac
-from .lsp import LSP
 from .mcp import MCPTool, mcp_tools_from_manager, normalize_mcp_result
 from .planexit import PlanExit
 from .question import Question
@@ -32,10 +31,7 @@ __all__ = [
     "GlobTool",
     "Grep",
     "GrepMac",
-    "Insert",
-    "LSP",
     "MCPTool",
-    "Mkdir",
     "PlanExit",
     "Question",
     "Read",
@@ -60,14 +56,11 @@ def default_registry() -> Registry:
     for tool in (
         AgentTool(),
         TodoWrite(),
-        LSP(),
         glob_tool,
         grep_tool,
         Read(),
-        Insert(),
         edit_tool,
         Write(),
-        Mkdir(),
         bash_tool,
         Skill(),
         Question(),

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/tools/base.py

@@ -165,8 +165,7 @@ class ToolContext:
     def config_path(self) -> str | None:
         """Path to the active config file (None = default resolution).
 
-        Tools that read the config file (e.g. the LSP tool, which loads
-        per-extension server overrides) use this so a session started
+        Tools that read the config file use this so a session started
         with ``--config PATH`` reads the same file.
         """
         if self.session:

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/tools/bash.py

@@ -217,6 +217,8 @@ class Bash(Tool):
 - Commands that truly require shell execution
 - Running builds, tests, or development servers
 - System administration tasks
+- Creating empty directories: use `mkdir -p <path>` (idempotent; `Write`
+  already creates parent directories for any file it writes)
 
 **When NOT to use `Bash`:**
 - File operations → use `Read`, `Write`, `Edit`, `Glob`, `Grep` instead

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/tools/diffapply.py

@@ -227,7 +227,7 @@ def _apply_section(section: _Section, cwd: str, fallback_path: str | None) -> tu
     # realpath BEFORE writing (the same resolution diff_targets applies):
     # the write goes through atomic_write_text, whose os.replace would
     # otherwise overwrite a symlink with a regular file and leave the real
-    # target untouched.  Edit/Insert/Write resolve their own paths already.
+    # target untouched.  Edit/Write resolve their own paths already.
     target = os.path.realpath(_resolve_target(section.new_path, cwd, fallback_path))
     if not os.path.isfile(target):
         return False, f"target file does not exist: {target}"

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/tools/edit.py

@@ -98,7 +98,10 @@ class Edit(Tool):
         "fenced code block).\n"
         "- The file paths within the diff (e.g. '--- a/filename' "
         "'+++ b/filename') must be appropriate for the `path`.\n\n"
-        'To simply insert text at some line, use the "Insert" tool instead.'
+        "To insert text at a specific point, use string-replacement mode: "
+        "match a unique nearby line as `old_str` and include it plus the new "
+        "text in `new_str`.  To add content to a brand-new or empty file, use "
+        'the "Write" tool instead.'
     )
     parameters = {
         "type": "object",

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/tools/filesystem.py

@@ -5,7 +5,7 @@ tools — atomic file replacement (``atomic_write_text``), spooling
 oversized tool results to temp files (`gptel-agent--truncate-buffer`
 parity), git-root detection, and the ``natnump`` predicate — and
 re-exports the tool classes that live in per-tool modules (`read.py`,
-`glob.py`, `grep.py`, `edit.py`, `write.py`, `insert.py`, `mkdir.py`),
+`glob.py`, `grep.py`, `edit.py`, `write.py`),
 so existing imports such as ``from .tools.filesystem import Read``
 keep working.
 
@@ -19,7 +19,7 @@ NOTE: these filesystem tools are intentionally SYNCHRONOUS.  Only Bash
 and Agent are `:async t` in gptel-agent; sync tools run one at a time in
 the model-emitted order.  Do NOT be tempted to port every tool to async
 for parallelism: tools can depend on one another's side effects within a
-single round (e.g. Write/Mkdir then Read/Edit the same path, or Edit then
+single round (e.g. Write then Read/Edit the same path, or Edit then
 Grep the just-changed file).  Running them concurrently would introduce
 read-after-write races and non-deterministic results.  Keep filesystem
 tools synchronous so ordering — and therefore correctness — is preserved.
@@ -34,7 +34,6 @@ from __future__ import annotations
 
 import contextlib
 import os
-import re
 import shutil  # noqa: F401  (mock target for tests)
 import stat
 import subprocess  # noqa: F401  (mock target for tests)
@@ -42,7 +41,6 @@ import tempfile
 import threading
 import time
 import uuid
-from collections.abc import Callable, Iterator
 from pathlib import Path
 from typing import TypeGuard
 
@@ -138,90 +136,6 @@ def _natnump(n: object) -> TypeGuard[int]:
     return isinstance(n, int) and not isinstance(n, bool) and n >= 0
 
 
-def _glob_to_regex(pattern: str) -> str:
-    """Translate a pathlib-style glob pattern into a :mod:`re` pattern.
-
-    Follows :mod:`fnmatch` conventions with two deliberate deviations:
-    ``*`` does not cross path separators (unlike :func:`fnmatch.fnmatch`)
-    and ``**`` matches any number of directories (including none).  A
-    pattern without any glob metacharacters is escaped, so plain names
-    match exactly.
-    """
-    i, n = 0, len(pattern)
-    out: list[str] = []
-    while i < n:
-        c = pattern[i]
-        if c == "*":
-            if pattern[i : i + 2] == "**":
-                i += 2
-                if pattern[i : i + 1] == "/":
-                    i += 1
-                out.append("(?:.*/)?")
-                continue
-            out.append("[^/]*")
-            i += 1
-        elif c == "?":
-            out.append("[^/]")
-            i += 1
-        elif c == "[":
-            end = _find_glob_class_end(pattern, i)
-            if end is None:
-                out.append(re.escape(c))
-                i += 1
-            else:
-                # The class body is regex-compatible as-is (\], \\, ranges,
-                # and member brackets mean the same thing in both dialects);
-                # only the negation sigil differs (! -> ^).
-                body = pattern[i + 1 : end]
-                if body.startswith("!"):
-                    body = "^" + body[1:]
-                out.append("[" + body + "]")
-                i = end + 1
-        else:
-            out.append(re.escape(c))
-            i += 1
-    return "".join(out)
-
-
-def _find_glob_class_end(pattern: str, start: int) -> int | None:
-    """Index of the ``]`` closing the char class opened at ``start``.
-
-    Mirrors glob semantics: a ``]`` immediately after ``[`` (or ``[!``)
-    is a literal bracket, and backslash escapes are honoured.
-    """
-    i = start + 1
-    if i < len(pattern) and pattern[i] == "!":
-        i += 1
-    if i < len(pattern) and pattern[i] == "]":
-        i += 1
-    while i < len(pattern):
-        if pattern[i] == "\\" and i + 1 < len(pattern):
-            i += 2
-        elif pattern[i] == "]":
-            return i
-        else:
-            i += 1
-    return None
-
-
-def _walk_files(root: Path, onerror: Callable[[OSError], object] | None = None) -> Iterator[Path]:
-    """Depth-first file iterator that never raises on traversal errors.
-
-    Wraps :func:`os.walk` with ``onerror`` so unreadable directories are
-    reported instead of silently swallowed, and wraps the whole iteration
-    in a try/except so a scan that dies mid-flight still yields the
-    entries collected so far (mirroring the 3.13+ ``pathlib`` scan
-    behaviour on every supported version).
-    """
-    try:
-        for dirpath, _dirnames, filenames in os.walk(root, onerror=onerror, followlinks=False):
-            for name in filenames:
-                yield Path(dirpath) / name
-    except OSError as e:
-        if onerror is not None:
-            onerror(e)
-
-
 def _git_root(path: str) -> str | None:
     d = Path(path).resolve()
     for parent in [d, *d.parents]:
@@ -236,11 +150,11 @@ def atomic_write_text(path: str, content: str) -> None:
     """Replace PATH's contents with CONTENT atomically.
 
     THE single write path for every tool that rewrites a file (``Edit``,
-    ``Insert``, ``Write``, and the pure-Python diff applier), so the four
+    ``Write``, and the pure-Python diff applier), so the three
     callers cannot drift apart.  It lives in this module with the other
-    shared helpers, and the four callers import it LAZILY (inside the
+    shared helpers, and the three callers import it LAZILY (inside the
     method that writes) rather than at module level, because this module
-    re-imports ``edit``/``write``/``insert``/``diffapply`` at its bottom
+    re-imports ``edit``/``write``/``diffapply`` at its bottom
     for the compatibility re-exports: a module-level import here would
     close the cycle on a half-initialised module (``tools/__init__``
     loads ``edit`` first, whose import of this module would then ask the
@@ -286,7 +200,7 @@ def atomic_write_text(path: str, content: str) -> None:
     - PATH must already be symlink-resolved.  ``os.replace`` onto a
       symlink overwrites the LINK with a regular file, where an in-place
       write would have followed it.  Every caller resolves the real path
-      first (``Edit``/``Insert``/``Write`` via ``os.path.realpath`` on
+      first (``Edit``/``Write`` via ``os.path.realpath`` on
       entry, ``_apply_section`` on its resolved target).
     - Hard links are broken: the new content lands on a new inode, so
       other links to the old inode keep the old content.
@@ -332,8 +246,6 @@ from .glob import GlobTool, _git_glob_results  # noqa: E402
 from .glob_mac import GlobMac  # noqa: E402
 from .grep import Grep, _grep_out  # noqa: E402
 from .grep_mac import GrepMac  # noqa: E402
-from .insert import Insert  # noqa: E402
-from .mkdir import Mkdir  # noqa: E402
 from .read import Read  # noqa: E402
 from .write import Write  # noqa: E402
 # isort: on
@@ -344,8 +256,6 @@ __all__ = [
     "GlobTool",
     "Grep",
     "GrepMac",
-    "Insert",
-    "Mkdir",
     "Read",
     "Write",
     "MAX_OUTPUT",

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/tools/grep.py

@@ -31,7 +31,6 @@ class Grep(Tool):
 **When NOT to use `Grep`:**
 - Searching for files by name → use `Glob`
 - Reading known file contents → use `Read`
-- Navigating a known code symbol (its definition, references, implementations, type info, or call hierarchy) → use `LSP` (semantically correct; `Grep` matches text, not symbols)
 - open-ended search that may require multiple rounds of globbing and grepping → use `Agent`
 
 **How to use `Grep`:**

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/tui/core.py

@@ -202,7 +202,7 @@ class Tui(RenderMixin, InputMixin, CommandMixin):
                 # old bare "error" so the user sees WHAT failed; the
                 # red styling comes from "error" appearing in the text.
                 # A structured {"code", "message"} payload (budget /
-                # timeout outcomes, LSP failures) is unwrapped by the
+                # timeout outcomes) is unwrapped by the
                 # shared helper — rendering the dict would both look
                 # wrong and lose the detail.
                 detail = error_display_text(data) if data else ""

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness/tui/render.py

@@ -563,7 +563,19 @@ class RenderMixin:
         cells); line 2 gets the full terminal width.  Newlines in the
         message are flattened, words break at spaces where possible,
         and anything beyond two lines is truncated with an ellipsis.
+
+        The status is the one display path that reaches the terminal
+        unsanitized: it is set from endpoint/MCP error text
+        (``error_display_text``) and ``_on_log`` messages (``agent
+        error: {e}``, ``compaction failed: {e}``, ``MCP: [{server}]
+        {err}``), any of which can carry a hostile server's escape
+        sequences.  Strip them here -- the single sink for every status
+        source -- mirroring the sibling paths (tool name, history rows)
+        that already call ``sanitize_terminal``.  Sanitizing BEFORE the
+        newline flatten below keeps a stray OSC introducer from hiding
+        the rest of the line.
         """
+        msg = sanitize_terminal(msg)
         msg = " ".join(msg.splitlines())
         width = self.console.width or 80
         avail1 = max(1, width - used - 1)

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4/python_agent_harness.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-agent-harness
-Version: 1.5.6.3
+Version: 1.5.6.4
 Summary: A lightweight, hackable mini-OpenCode written in Python.
 Author-email: Huming Chen <chenhuming@gmail.com>
 License-Expression: MIT
@@ -74,7 +74,7 @@ Edit `~/.config/python-agent-harness/config.json` and set your `base_url`, `api_
 - **FSM-driven execution** — explicit `WAIT` / `TOOL` / `TRET` / `SUPERVISE` / `DONE` / `ERRS` / `ABRT` states. Completion supervision nudges the model when it stops early; failed tool calls are sanitized. Transient API failures (`429` / `5xx`) retry with exponential backoff. Auth-expired codes (configurable via `AUTH_REFRESH_STATUS_CODES` in `config.py`; defaults to `[401, 502]`) trigger automatic API key re-read from config/env.
 - **Context management** — CJK-aware token estimation, per-model context windows, automatic compaction at 70% usage.
 - **Image & text attachments** — attach with `@path` (e.g. `@screenshot.png`, `@README.md`): images (PNG/JPEG/GIF/WebP, up to 20 MB) become multimodal `image_url` parts; text files are inlined. Web URLs supported for images.
-- **Coding tools** — `Agent`, `TodoWrite`, `Glob`, `Grep`, `Read`, `Insert`, `Edit` (incl. unified diffs), `Write`, `Mkdir`, `Bash`, `Skill`, `Question`, `LSP`, `PlanExit`. Read-only tool rounds (`Read`, `Glob`, `Grep`, `Skill`, `LSP`) dispatch concurrently; async tools (`Bash`, `Agent`) can also run concurrently. Results always delivered in emitted order.
+- **Coding tools** — `Agent`, `TodoWrite`, `Glob`, `Grep`, `Read`, `Edit` (incl. unified diffs), `Write`, `Bash`, `Skill`, `Question`, `PlanExit`. Read-only tool rounds (`Read`, `Glob`, `Grep`, `Skill`) dispatch concurrently; async tools (`Bash`, `Agent`) can also run concurrently. Results always delivered in emitted order.
 - **Plan / Build modes** — plan mode is read-only except for the per-session plan file.
 - **Persistent sessions** — auto-saved after every response to `~/.local/share/python-agent-harness/sessions/`, with LLM-generated titles and `/restore --latest` / `/sessions`.
 - **Focused TUI** — Rich-based with pinned status bar, Todos panel, inline diff rendering, and a `prompt_toolkit` editor with history and completion. `Esc+Enter` submits, `Ctrl-D` quits, `Ctrl-C` cancels.
@@ -191,7 +191,6 @@ All LLM settings live in `~/.config/python-agent-harness/config.json`. Environme
 - **`subagent_llm`** — LLM config for `Agent` tool. Unset values inherit from `llm`. Set `profile` to reuse a `models` entry. Precedence: profile > `subagent_llm` > `llm` > env vars.
 - **`default_agent`** — agent name to use at session start (must exist in `prompts/agents/`). `null` = built-in default.
 - **`paths.context_path` / `paths.skill_path`** — locations for context files and skills. Default: project-local `contexts/` and `skills/`.
-- **`lsp.servers`** — per-extension LSP server overrides for the `LSP` tool. Keys are extensions (`.py`, `.cpp`); each has `command` (argv) and optional `language_id`. Layers on top of `DEFAULT_SERVERS` in `lsp/manager.py`.
 - **`mcp.servers`** — MCP server config (requires `[mcp]` extra). Each supports `transport`, `command`, `args`, `env`, `url`, `headers`, `parallel`, `timeout`, `enabled`.
 - **`headless` / `serve`** — optional budget limits: `max_rounds` (LLM rounds) and `timeout` (wall-clock seconds). `--max-rounds` / `--timeout` override per call; `<= 0` or `null` disables. Unset = unlimited.
 - **Precedence** — code defaults < config file < `OPENAI_*` env vars. Sub-agents also support `OPENAI_SUBAGENT_*` (`_BASE_URL`, `_API_KEY`, `_MODEL`).

{python_agent_harness-1.5.6.3 → python_agent_harness-1.5.6.4}/python_agent_harness.egg-info/SOURCES.txt

@@ -30,10 +30,6 @@ python_agent_harness/io/persistence.py
 python_agent_harness/io/text_filter.py
 python_agent_harness/llm/__init__.py
 python_agent_harness/llm/client.py
-python_agent_harness/lsp/__init__.py
-python_agent_harness/lsp/client.py
-python_agent_harness/lsp/config.py
-python_agent_harness/lsp/manager.py
 python_agent_harness/mcp/__init__.py
 python_agent_harness/mcp/client.py
 python_agent_harness/mcp/config.py
@@ -69,10 +65,7 @@ python_agent_harness/tools/glob.py
 python_agent_harness/tools/glob_mac.py
 python_agent_harness/tools/grep.py
 python_agent_harness/tools/grep_mac.py
-python_agent_harness/tools/insert.py
-python_agent_harness/tools/lsp.py
 python_agent_harness/tools/mcp.py
-python_agent_harness/tools/mkdir.py
 python_agent_harness/tools/planexit.py
 python_agent_harness/tools/question.py
 python_agent_harness/tools/read.py