python-agent-harness 1.5.6.2__tar.gz → 1.5.6.4__tar.gz

{python_agent_harness-1.5.6.2/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: 1.5.6.2
+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-1.5.6.2 → 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-1.5.6.2 → python_agent_harness-1.5.6.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "python-agent-harness"
-version = "1.5.6.2"
+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-1.5.6.2 → 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__ = "1.5.6.2"
+__version__ = "1.5.6.4"
 
 __all__ = [
     "Client",
     "LLMClient",
     "Session",
     "AgentMode",
-    "LSPConfig",
-    "LSPServerConfig",
     "MCPConfig",
     "MCPManager",
     "MCPServerConfig",

{python_agent_harness-1.5.6.2 → 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-1.5.6.2 → python_agent_harness-1.5.6.4}/python_agent_harness/core/models.py

@@ -5,9 +5,30 @@ from __future__ import annotations
 import base64
 import enum
 import json
+import re
 from dataclasses import dataclass, field
 from typing import Any, Union
 
+# Lone surrogates (\ud800-\udfff) reach a str when a file is decoded with
+# errors="surrogateescape" — which every tool deliberately does, so a
+# non-UTF-8 source file round-trips instead of becoming U+FFFD.  Such a
+# string cannot be encoded to UTF-8, so anything that leaves the process
+# (a JSON request body, a terminal write) must replace them first.
+_SURROGATE_RE = re.compile(r"[\ud800-\udfff]")
+
+
+def api_safe(text: str) -> str:
+    """TEXT with lone surrogates replaced by U+FFFD, safe to serialize.
+
+    The tools read files with ``errors="surrogateescape"``, so a
+    conversation can carry lone surrogates from a non-UTF-8 (Latin-1,
+    GBK, ...) source.  A request body containing one cannot be encoded
+    to UTF-8 — ``httpx`` raised ``UnicodeEncodeError`` — so they are
+    replaced at the OUTBOUND boundary only: the stored history, the
+    session file and the file on disk keep the exact bytes.
+    """
+    return _SURROGATE_RE.sub("\ufffd", text)
+
 
 class AgentMode(enum.Enum):
     BUILD = "build"
@@ -136,7 +157,10 @@ class Message:
     def to_api(self) -> dict[str, Any]:
         d: dict[str, Any] = {"role": self.role}
         if self.content is not None:
-            d["content"] = self._api_content()
+            content = self._api_content()
+            # outbound boundary: a lone surrogate cannot be encoded into
+            # the JSON body (see api_safe)
+            d["content"] = api_safe(content) if isinstance(content, str) else content
         if self.tool_calls:
             d["tool_calls"] = [
                 {
@@ -144,9 +168,13 @@ class Message:
                     "type": "function",
                     "function": {
                         "name": tc.name,
-                        "arguments": tc.arguments
-                        if isinstance(tc.arguments, str)
-                        else json.dumps(tc.arguments, ensure_ascii=False),
+                        # ensure_ascii=False keeps non-ASCII readable;
+                        # api_safe then removes the unencodable surrogates
+                        "arguments": api_safe(
+                            tc.arguments
+                            if isinstance(tc.arguments, str)
+                            else json.dumps(tc.arguments, ensure_ascii=False)
+                        ),
                     },
                 }
                 for tc in self.tool_calls
@@ -188,7 +216,11 @@ class Message:
     @staticmethod
     def _part_to_api(part: ContentPart) -> Any:
         """Serialize one content part to its provider-specific dict."""
-        if isinstance(part, (TextPart, ImagePart)):
+        if isinstance(part, TextPart):
+            # text parts are a second carrier of file content into the
+            # payload, so they need the same outbound treatment
+            return {"type": "text", "text": api_safe(part.text)}
+        if isinstance(part, ImagePart):
             return part.to_api()
         return part
 

{python_agent_harness-1.5.6.2 → 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-1.5.6.2 → python_agent_harness-1.5.6.4}/python_agent_harness/entry/headless.py

@@ -22,6 +22,7 @@ import sys
 import threading
 from typing import Any, TextIO
 
+from ..core.models import api_safe
 from ..io.text_filter import strip_final_check
 from ..session.session import Session
 from .controller import Controller
@@ -58,8 +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.
@@ -105,8 +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.
 
@@ -166,7 +166,13 @@ def final_answer_text(session: Session) -> str:
             continue
         text = strip_final_check(msg.text_without_reasoning()).strip()
         if text:
-            return text
+            # api_safe: the answer is written to stdout (headless prints it
+            # verbatim; --json and serve JSON-encode it), and a lone
+            # surrogate from a restored non-UTF-8 session raised
+            # UnicodeEncodeError there — headless died before writing the
+            # result line, and serve's _write_line SWALLOWED it (it is a
+            # ValueError), reporting success with an empty stream.
+            return api_safe(text)
     return ""
 
 
@@ -295,7 +301,10 @@ def restore_session(controller: Controller, spec: str, err: TextIO) -> bool:
     if not path or not os.path.isfile(path):
         err.write(f"no session found: {spec or 'latest'}\n")
         return False
-    with open(path, encoding="utf-8") as fh:
+    # surrogateescape must mirror SessionPersistence.save: the saved body
+    # may carry lone surrogates (the tools read non-UTF-8 files that way),
+    # and a strict decode raised UnicodeDecodeError here.
+    with open(path, encoding="utf-8", errors="surrogateescape") as fh:
         text = fh.read()
     meta = SessionPersistence.parse_metadata(text)
     body = SessionPersistence.strip_metadata(text)
@@ -417,7 +426,10 @@ def run_headless(
         return 1
     answer = final_answer_text(session)
     if answer:
-        view.out.write(answer + "\n")
+        # api_safe: the answer carries whatever the conversation carried
+        # (a restored non-UTF-8 session), and a strict-UTF-8 stdout
+        # raised UnicodeEncodeError here — losing the result line.
+        view.out.write(api_safe(answer) + "\n")
         view.out.flush()
     return 1 if view.errors else 0
 
@@ -512,7 +524,11 @@ class JsonlView(HeadlessView):
         line = {"seq": self._seq, "protocol": PROTOCOL_VERSION, **payload}
         if self.run_id is not None:
             line["run_id"] = self.run_id
-        self.out.write(json.dumps(line, ensure_ascii=False, default=str) + "\n")
+        # api_safe at the sink: the JSON body is written to the driver's
+        # stdout, and a lone surrogate (restored non-UTF-8 session) made
+        # the write raise UnicodeEncodeError — the run then ended without
+        # its terminal `result` line.
+        self.out.write(api_safe(json.dumps(line, ensure_ascii=False, default=str)) + "\n")
         self.out.flush()
 
     def _emit(self, payload: dict[str, Any]) -> None:

{python_agent_harness-1.5.6.2 → python_agent_harness-1.5.6.4}/python_agent_harness/entry/server.py

@@ -127,6 +127,7 @@ import time
 import uuid
 from typing import Any, TextIO
 
+from ..core.models import api_safe
 from ..session.session import Session
 from .controller import Controller
 from .headless import PROTOCOL_VERSION, JsonlView, _restorable_handler, final_answer_text
@@ -530,7 +531,11 @@ class AgentServer:
         live run lines get ``seq``/``run_id`` via the view's ``_write``.
         """
         text = (
-            json.dumps({"protocol": PROTOCOL_VERSION, **payload}, ensure_ascii=False, default=str)
+            api_safe(
+                json.dumps(
+                    {"protocol": PROTOCOL_VERSION, **payload}, ensure_ascii=False, default=str
+                )
+            )
             + "\n"
         )
         view = self.view
@@ -892,7 +897,19 @@ class AgentServer:
     def _read_ops(self) -> None:
         """The reader loop proper: dispatch ops until EOF/shutdown."""
         while not self._stopped.is_set():
-            line = self.inp.readline()
+            try:
+                line = self.inp.readline()
+            except (UnicodeDecodeError, ValueError, OSError) as e:
+                # Unreadable input must never take the resident process
+                # down.  A single non-UTF-8 byte on a strict-UTF-8 stdin
+                # (the common C.UTF-8/LANG=en_US.UTF-8 container setup)
+                # raised out of serve_forever, which skipped the run drain
+                # below: an in-flight run then emitted NO result line and
+                # its token usage was lost.  Report it as a protocol error
+                # and stop reading, so the drain still runs.  ValueError
+                # covers a stdin closed underneath us.
+                self._error("protocol", f"cannot read op: {e}")
+                break
             if not line:  # EOF: the host closed the pipe
                 break
             line = line.strip()

{python_agent_harness-1.5.6.2 → python_agent_harness-1.5.6.4}/python_agent_harness/io/persistence.py

@@ -195,7 +195,16 @@ class SessionPersistence:
             session_dir().mkdir(parents=True, exist_ok=True)
             content = conversation_text.rstrip("\n") + "\n\n" + self.metadata_block() + "\n"
             tmp = path + ".tmp"
-            Path(tmp).write_text(content, encoding="utf-8")
+            # surrogateescape: the tools deliberately read files with it
+            # (see atomic_write_text / Edit._string_replace), so a
+            # conversation can legitimately carry lone surrogates from a
+            # non-UTF-8 source file.  A strict write raised
+            # UnicodeEncodeError, which is NOT an OSError, so it escaped
+            # auto_save's handler: the turn was never saved and a stray
+            # <name>.md.tmp was left behind.  The matching reads
+            # (headless restore_session, TUI /restore and /sessions) use
+            # the same error handler so the bytes round-trip.
+            Path(tmp).write_text(content, encoding="utf-8", errors="surrogateescape")
             os.replace(tmp, path)
             return path
 

{python_agent_harness-1.5.6.2 → python_agent_harness-1.5.6.4}/python_agent_harness/prompts/agent.md

@@ -56,9 +56,10 @@ 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.
-- 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. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive.
-
+- 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.
 - Tool results and user messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are NOT part of the user's provided input or the tool result.
 
 # Tool usage policy

{python_agent_harness-1.5.6.2 → 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-1.5.6.2 → 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-1.5.6.2 → 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
 
     # ------------------------------------------------------------------
@@ -698,7 +690,11 @@ class Session:
                 self.store.save(text)
                 self._save_error = None
                 return
-            except OSError as e:
+            except (OSError, UnicodeError) as e:
+                # UnicodeError too: a save failure must never escape into
+                # the agent loop (it unwound the run and lost the turn).
+                # The writer uses surrogateescape now, so this is a
+                # defensive net rather than the primary fix.
                 self._save_error = str(e)
                 if attempt == 1:
                     time.sleep(0.2)

{python_agent_harness-1.5.6.2 → 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-1.5.6.2 → 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-1.5.6.2 → 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-1.5.6.2 → 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}"