deepagents-code 0.1.11__tar.gz → 0.1.12__tar.gz

{deepagents_code-0.1.11 → deepagents_code-0.1.12}/.gitignore

@@ -137,6 +137,7 @@ celerybeat.pid
 
 # Environments
 .env
+.env.*
 .envrc
 env.local
 *.env.local
@@ -147,6 +148,20 @@ ENV/
 env.bak/
 venv.bak/
 
+# Local credentials and secrets
+*.pem
+*.key
+*.crt
+*.p12
+*.pfx
+*.jks
+credentials.json
+token.json
+Cookies
+Cookies.db
+cookies.sqlite
+cookies.txt
+
 # Spyder project settings
 .spyderproject
 .spyproject

{deepagents_code-0.1.11 → deepagents_code-0.1.12}/AGENTS.md

@@ -48,11 +48,57 @@ Textual's `App.notify(message)` parses the message string as Rich markup by defa
 
 - Use `textual.pilot` for async UI testing - see [Testing guide](https://textual.textualize.io/guide/testing/)
 - Snapshot testing available for visual regression - see repo `notes/snapshot_testing.md`
+- For modal flows, test the real interaction path with keypresses when possible. Unit tests that call action methods or resume handlers directly can miss focus and modal-stack bugs.
+- Do not open another modal or refocus the base chat input directly inside a modal dismiss callback. Preserve the non-blocking `push_screen(..., callback)` flow and schedule follow-up UI work with `call_after_refresh` so the dismissing modal fully unwinds first.
+- Be cautious replacing `push_screen(..., callback)` with an awaited modal result inside slash-command handlers; awaiting can block the Textual message pump and break keyboard navigation in the active modal.
+
+### Typing and test doubles
+
+When fixing `ty` diagnostics, do not mechanically replace `# type: ignore[...]` with `cast(...)`. First try to improve the actual type shape: narrower annotations, typed futures/callbacks, covariant read-only types such as `Mapping`/`Sequence`, local mock variables, or `monkeypatch.setattr(...)`. Treat `cast("Any", ...)` as a last resort.
+
+For Textual tests that intentionally replace concrete app methods with `MagicMock` or `AsyncMock`, prefer `monkeypatch.setattr(...)` or one small documented dynamic helper over repeated `cast("Any", app)` expressions. Assert on local mock variables instead of re-reading mocked methods from the concrete object when possible.
+
+Casts are acceptable when the type violation is the point of the test (for example, passing a wrong runtime type to exercise defensive validation) or when a third-party overload is narrower than verified runtime behavior. In those cases, keep the cast narrowly scoped and add a short comment explaining why it is intentional.
 
 ## SDK dependency pin
 
 `deepagents-code` pins an exact `deepagents==X.Y.Z` version in `pyproject.toml`. When developing features that depend on new SDK functionality, bump this pin as part of the same PR. A CI check verifies the pin matches the current SDK version at release time (unless bypassed with `dangerous-skip-sdk-pin-check`).
 
+## Local dev installs
+
+Keep the released CLI and editable development CLI separate:
+
+- `dcode` / `deepagents-code` should point at the normal installed tool, typically managed by `uv tool install deepagents-code`.
+- `dcode-dev` should point at a dedicated editable venv under `~/.local/share/dcode-dev`, with a symlink in `~/.local/bin/dcode-dev`.
+
+This uses a manual `uv venv` + `uv pip install -e` rather than `uv sync` or `uv tool install --editable` on purpose: it builds an isolated venv outside the workspace's locked environment, so the dev binary can be re-resolved on demand without disturbing the released tool or the repo's `uv.lock`. `uv pip`/`uv venv` are first-class `uv` subcommands here, not bare `pip`.
+
+`~/.local/bin` must be on your `PATH` for the `dcode-dev` symlink to resolve (`uv tool install` adds its own shim directory automatically, but a hand-rolled symlink does not).
+
+Example setup. The `--python` value is illustrative — any interpreter satisfying the package's `requires-python` (currently `>=3.11`) works; omit the flag to let `uv` pick. Replace `<repo>` with your local checkout path.
+
+```bash
+uv venv ~/.local/share/dcode-dev --python 3.13
+uv pip install --python ~/.local/share/dcode-dev/bin/python -e <repo>/libs/code
+ln -sf ~/.local/share/dcode-dev/bin/dcode ~/.local/bin/dcode-dev
+```
+
+When dependency constraints change in `libs/code/pyproject.toml`, update the dev venv explicitly:
+
+```bash
+uv pip install --python ~/.local/share/dcode-dev/bin/python -e <repo>/libs/code --upgrade
+```
+
+Verify command resolution and editable imports (the `dcode` checks assume the released tool is installed separately, per above):
+
+```bash
+which dcode
+which dcode-dev
+dcode --version
+dcode-dev --version
+~/.local/share/dcode-dev/bin/python -c 'import deepagents_code; print(deepagents_code.__file__)'
+```
+
 ## Startup performance
 
 `deepagents-code` must stay fast to launch. Never import heavy packages (e.g., `deepagents`, LangChain, LangGraph) at module level or in the argument-parsing path. These imports pull in large dependency trees and add seconds to every invocation, including trivial commands like `deepagents-code -v`.

{deepagents_code-0.1.11 → deepagents_code-0.1.12}/CHANGELOG.md

@@ -2,6 +2,36 @@
 
 # Deep Agents Code Changelog
 
+## [0.1.12](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.11...deepagents-code==0.1.12) (2026-06-10)
+
+### Features
+
+* Add `get_current_thread_id` tool ([#3820](https://github.com/langchain-ai/deepagents/issues/3820)) ([18ce094](https://github.com/langchain-ai/deepagents/commit/18ce094b7036796c7e23ce1338f4da56dc2ef126))
+* Guard managed onboarding-name memory block from edits ([#3822](https://github.com/langchain-ai/deepagents/issues/3822)) ([dc0a51f](https://github.com/langchain-ai/deepagents/commit/dc0a51fc81d01b62dc8043148a9fd87099fc9123))
+* Offer restart after restart-capable install ([#3821](https://github.com/langchain-ai/deepagents/issues/3821)) ([e356efe](https://github.com/langchain-ai/deepagents/commit/e356efeff1c8bfb894119cebbb7d3c0853d327a2))
+* Persist `/threads` directory-scope preference ([#3824](https://github.com/langchain-ai/deepagents/issues/3824)) ([51a29f4](https://github.com/langchain-ai/deepagents/commit/51a29f4a0c28c122acae296a0df03bee20474455))
+* Surface gateway key mismatch on `PermissionDeniedError` ([#3813](https://github.com/langchain-ai/deepagents/issues/3813)) ([5bd1ef8](https://github.com/langchain-ai/deepagents/commit/5bd1ef8cb29db781ccbb37755db44ce0ab1d7bd2))
+
+### Bug Fixes
+
+* Surface cached MCP errors as failed tool messages ([#3829](https://github.com/langchain-ai/deepagents/issues/3829)) ([d83b428](https://github.com/langchain-ai/deepagents/commit/d83b428f7f97bc40b9219c02846c2d8b4ccac434))
+* Handle MCP tool errors locally ([#3830](https://github.com/langchain-ai/deepagents/issues/3830)) ([97a7052](https://github.com/langchain-ai/deepagents/commit/97a7052b3eef7ec80bc90a4c3b606deeaf13cb9b))
+* Make non-incognito `!` shell output visible to the model ([#3825](https://github.com/langchain-ai/deepagents/issues/3825)) ([2407bca](https://github.com/langchain-ai/deepagents/commit/2407bca66bac5d199a923a0e58872c813eb006bc))
+* Expose `/restart` slash command ([#3809](https://github.com/langchain-ai/deepagents/issues/3809)) ([64505b8](https://github.com/langchain-ai/deepagents/commit/64505b848868b80213b6da87113cd63890c3d520))
+* Agent retries `gh search` with invalid `mergedAt` field ([#3802](https://github.com/langchain-ai/deepagents/issues/3802)) ([0b683a9](https://github.com/langchain-ai/deepagents/commit/0b683a9435b95bce79d10451868eae54c6a3e88c))
+* Clarify `/restart` message during server startup ([#3823](https://github.com/langchain-ai/deepagents/issues/3823)) ([49ded9e](https://github.com/langchain-ai/deepagents/commit/49ded9ef448dcd263bee07ac15f4904dd342bfa2))
+* Cursor at end when popping queued message to input ([#3832](https://github.com/langchain-ai/deepagents/issues/3832)) ([aa522c9](https://github.com/langchain-ai/deepagents/commit/aa522c94fffb93dc578addb39b4879f779ac5899))
+* Coalesce streamed markdown writes to keep input responsive ([#3819](https://github.com/langchain-ai/deepagents/issues/3819)) ([b45eeeb](https://github.com/langchain-ai/deepagents/commit/b45eeebaf7e6ae6e07b8f9ca521525c66fe14f63))
+* Don't show `"No threads found"` while threads load ([#3815](https://github.com/langchain-ai/deepagents/issues/3815)) ([68e6426](https://github.com/langchain-ai/deepagents/commit/68e64263f590b3244b689664715f354fb3a389cd))
+* Ignore stale cwd warmers in file autocomplete cache ([#3835](https://github.com/langchain-ai/deepagents/issues/3835)) ([9c8c2b2](https://github.com/langchain-ai/deepagents/commit/9c8c2b24853b7b3a7610cbcfc368a6464c0711e0))
+* Offer cwd switch on resume ([#3810](https://github.com/langchain-ai/deepagents/issues/3810)) ([d417f53](https://github.com/langchain-ai/deepagents/commit/d417f530aafa8c77523487393dc3039cc822dc09))
+* Recover from tool errors instead of aborting run ([#3804](https://github.com/langchain-ai/deepagents/issues/3804)) ([45691c5](https://github.com/langchain-ai/deepagents/commit/45691c556105e171c7210c7c10388dc73202a025))
+* Show `/restart` feedback ([#3808](https://github.com/langchain-ai/deepagents/issues/3808)) ([c40bef9](https://github.com/langchain-ai/deepagents/commit/c40bef9b2aaace3909593503b28e8b548bc20014))
+* Standardize search previews and restart status ([#3806](https://github.com/langchain-ai/deepagents/issues/3806)) ([71a6d50](https://github.com/langchain-ai/deepagents/commit/71a6d508b21b275c0c7c6bd2e0752adfba496ea9))
+* Suppress stale update notices ([#3801](https://github.com/langchain-ai/deepagents/issues/3801)) ([db25241](https://github.com/langchain-ai/deepagents/commit/db252411d8ca945aca86429acb644540ec970bdb))
+* Unblock `/remember` in server mode ([#3812](https://github.com/langchain-ai/deepagents/issues/3812)) ([12e00e1](https://github.com/langchain-ai/deepagents/commit/12e00e1a78e2d6be106147a0aa95a518be66849f))
+* Unblock TUI input during `/restart` ([#3826](https://github.com/langchain-ai/deepagents/issues/3826)) ([366cd81](https://github.com/langchain-ai/deepagents/commit/366cd81269e2d3891a477848b774cf51af0cefc0))
+
 ## [0.1.11](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.10...deepagents-code==0.1.11) (2026-06-07)
 
 ### Bug Fixes

{deepagents_code-0.1.11 → deepagents_code-0.1.12}/COMMANDS.md

@@ -6,7 +6,7 @@ Canonical list of slash commands for `deepagents-code`, derived from
 regenerate after editing the registry.
 
 
-## Public (27)
+## Public (28)
 
 | Command | Aliases | Description |
 | --- | --- | --- |
@@ -29,6 +29,7 @@ regenerate after editing the registry.
 | `/quit` | `/q` | Exit app |
 | `/reload` |  | Reload config from environment variables and .env |
 | `/remember` |  | Update memory and skills from conversation |
+| `/restart` |  | Restart the app-owned LangGraph server |
 | `/skill-creator` |  | Guide for creating effective agent skills |
 | `/theme` |  | Switch color theme |
 | `/threads` |  | Browse and resume previous threads |
@@ -38,9 +39,8 @@ regenerate after editing the registry.
 | `/update` |  | Check for and install updates |
 | `/version` | `/about` | Show version |
 
-## Hidden (2)
+## Hidden (1)
 
 Hidden commands not exposed in autocomplete or help. See the `HIDDEN_COMMANDS` docstring in the registry for context.
 
 - `/debug-error`
-- `/restart`

{deepagents_code-0.1.11 → deepagents_code-0.1.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepagents-code
-Version: 0.1.11
+Version: 0.1.12
 Summary: Terminal interface for Deep Agents - interactive AI agent with file operations, shell access, and sub-agent capabilities.
 Project-URL: Homepage, https://docs.langchain.com/oss/python/deepagents/overview
 Project-URL: Documentation, https://reference.langchain.com/python/deepagents/
@@ -31,23 +31,23 @@ Requires-Dist: deepagents==0.6.8
 Requires-Dist: httpx<1.0.0,>=0.28.1
 Requires-Dist: langchain-anthropic<2.0.0,>=1.4.4
 Requires-Dist: langchain-google-genai<5.0.0,>=4.2.4
-Requires-Dist: langchain-mcp-adapters<1.0.0,>=0.2.2
+Requires-Dist: langchain-mcp-adapters<1.0.0,>=0.3.0
 Requires-Dist: langchain-openai<2.0.0,>=1.2.2
 Requires-Dist: langchain<2.0.0,>=1.3.4
 Requires-Dist: langgraph-checkpoint-sqlite<4.0.0,>=3.1.0
 Requires-Dist: langgraph-cli[inmem]<1.0.0,>=0.4.27
 Requires-Dist: langgraph-runtime-inmem<1.0.0,>=0.29.0
 Requires-Dist: langgraph-sdk<1.0.0,>=0.4.2
-Requires-Dist: langsmith[sandbox]>=0.8.8
+Requires-Dist: langsmith[sandbox]>=0.8.11
 Requires-Dist: markdownify<2.0.0,>=1.2.2
 Requires-Dist: packaging>=26.2
 Requires-Dist: pillow<13.0.0,>=12.2.0
 Requires-Dist: prompt-toolkit<4.0.0,>=3.0.52
 Requires-Dist: pyperclip<2.0.0,>=1.11.0
 Requires-Dist: python-dotenv<2.0.0,>=1.2.2
-Requires-Dist: pyyaml>=6.0.0
+Requires-Dist: pyyaml>=6.0.3
 Requires-Dist: requests<3.0.0,>=2.34.2
-Requires-Dist: rich<16.0.0,>=14.0.0
+Requires-Dist: rich<16.0.0,>=15.0.0
 Requires-Dist: tavily-python<1.0.0,>=0.7.25
 Requires-Dist: textual-autocomplete<5.0.0,>=4.0.6
 Requires-Dist: textual-speedups<1.0.0,>=0.2.1
@@ -55,13 +55,13 @@ Requires-Dist: textual<9.0.0,>=8.2.7
 Requires-Dist: tomli-w<2.0.0,>=1.2.0
 Requires-Dist: uuid-utils<1.0.0,>=0.16.0
 Provides-Extra: agentcore
-Requires-Dist: langchain-agentcore-codeinterpreter<1.0.0,>=0.0.3; extra == 'agentcore'
+Requires-Dist: langchain-agentcore-codeinterpreter<1.0.0,>=0.0.4; extra == 'agentcore'
 Provides-Extra: all-providers
 Requires-Dist: langchain-anthropic<2.0.0,>=1.4.4; extra == 'all-providers'
-Requires-Dist: langchain-aws<2.0.0,>=1.5.0; extra == 'all-providers'
+Requires-Dist: langchain-aws<2.0.0,>=1.5.1; extra == 'all-providers'
 Requires-Dist: langchain-baseten<1.0.0,>=0.2.0; extra == 'all-providers'
 Requires-Dist: langchain-cohere<1.0.0,>=0.6.0; extra == 'all-providers'
-Requires-Dist: langchain-deepseek<2.0.0,>=1.0.1; extra == 'all-providers'
+Requires-Dist: langchain-deepseek<2.0.0,>=1.1.0; extra == 'all-providers'
 Requires-Dist: langchain-fireworks<2.0.0,>=1.4.2; extra == 'all-providers'
 Requires-Dist: langchain-google-genai<5.0.0,>=4.2.4; extra == 'all-providers'
 Requires-Dist: langchain-google-vertexai<4.0.0,>=3.2.3; extra == 'all-providers'
@@ -70,30 +70,30 @@ Requires-Dist: langchain-huggingface<2.0.0,>=1.2.2; extra == 'all-providers'
 Requires-Dist: langchain-ibm<2.0.0,>=1.1.0; extra == 'all-providers'
 Requires-Dist: langchain-litellm<2.0.0,>=0.6.6; extra == 'all-providers'
 Requires-Dist: langchain-mistralai<2.0.0,>=1.1.4; extra == 'all-providers'
-Requires-Dist: langchain-nvidia-ai-endpoints<2.0.0,>=1.4.0; extra == 'all-providers'
+Requires-Dist: langchain-nvidia-ai-endpoints<2.0.0,>=1.4.1; extra == 'all-providers'
 Requires-Dist: langchain-ollama<2.0.0,>=1.1.0; extra == 'all-providers'
 Requires-Dist: langchain-openai<2.0.0,>=1.2.2; extra == 'all-providers'
 Requires-Dist: langchain-openrouter<2.0.0,>=0.2.3; extra == 'all-providers'
-Requires-Dist: langchain-perplexity<2.0.0,>=1.3.1; extra == 'all-providers'
+Requires-Dist: langchain-perplexity<2.0.0,>=1.3.2; extra == 'all-providers'
 Requires-Dist: langchain-together<2.0.0,>=0.4.0; extra == 'all-providers'
 Requires-Dist: langchain-xai<2.0.0,>=1.2.2; extra == 'all-providers'
 Provides-Extra: all-sandboxes
-Requires-Dist: langchain-agentcore-codeinterpreter<1.0.0,>=0.0.3; extra == 'all-sandboxes'
-Requires-Dist: langchain-daytona>=0.0.6; extra == 'all-sandboxes'
-Requires-Dist: langchain-modal>=0.0.4; extra == 'all-sandboxes'
+Requires-Dist: langchain-agentcore-codeinterpreter<1.0.0,>=0.0.4; extra == 'all-sandboxes'
+Requires-Dist: langchain-daytona>=0.0.7; extra == 'all-sandboxes'
+Requires-Dist: langchain-modal>=0.0.5; extra == 'all-sandboxes'
 Requires-Dist: langchain-runloop>=0.0.6; extra == 'all-sandboxes'
 Provides-Extra: anthropic
 Requires-Dist: langchain-anthropic<2.0.0,>=1.4.4; extra == 'anthropic'
 Provides-Extra: baseten
 Requires-Dist: langchain-baseten<1.0.0,>=0.2.0; extra == 'baseten'
 Provides-Extra: bedrock
-Requires-Dist: langchain-aws<2.0.0,>=1.5.0; extra == 'bedrock'
+Requires-Dist: langchain-aws<2.0.0,>=1.5.1; extra == 'bedrock'
 Provides-Extra: cohere
 Requires-Dist: langchain-cohere<1.0.0,>=0.6.0; extra == 'cohere'
 Provides-Extra: daytona
-Requires-Dist: langchain-daytona>=0.0.6; extra == 'daytona'
+Requires-Dist: langchain-daytona>=0.0.7; extra == 'daytona'
 Provides-Extra: deepseek
-Requires-Dist: langchain-deepseek<2.0.0,>=1.0.1; extra == 'deepseek'
+Requires-Dist: langchain-deepseek<2.0.0,>=1.1.0; extra == 'deepseek'
 Provides-Extra: fireworks
 Requires-Dist: langchain-fireworks<2.0.0,>=1.4.2; extra == 'fireworks'
 Provides-Extra: google-genai
@@ -109,9 +109,9 @@ Requires-Dist: langchain-litellm<2.0.0,>=0.6.6; extra == 'litellm'
 Provides-Extra: mistralai
 Requires-Dist: langchain-mistralai<2.0.0,>=1.1.4; extra == 'mistralai'
 Provides-Extra: modal
-Requires-Dist: langchain-modal>=0.0.4; extra == 'modal'
+Requires-Dist: langchain-modal>=0.0.5; extra == 'modal'
 Provides-Extra: nvidia
-Requires-Dist: langchain-nvidia-ai-endpoints<2.0.0,>=1.4.0; extra == 'nvidia'
+Requires-Dist: langchain-nvidia-ai-endpoints<2.0.0,>=1.4.1; extra == 'nvidia'
 Provides-Extra: ollama
 Requires-Dist: langchain-ollama<2.0.0,>=1.1.0; extra == 'ollama'
 Provides-Extra: openai
@@ -119,9 +119,9 @@ Requires-Dist: langchain-openai<2.0.0,>=1.2.2; extra == 'openai'
 Provides-Extra: openrouter
 Requires-Dist: langchain-openrouter<2.0.0,>=0.2.3; extra == 'openrouter'
 Provides-Extra: perplexity
-Requires-Dist: langchain-perplexity<2.0.0,>=1.3.1; extra == 'perplexity'
+Requires-Dist: langchain-perplexity<2.0.0,>=1.3.2; extra == 'perplexity'
 Provides-Extra: quickjs
-Requires-Dist: langchain-quickjs<0.2.0,>=0.1.3; extra == 'quickjs'
+Requires-Dist: langchain-quickjs<0.2.0,>=0.1.4; extra == 'quickjs'
 Provides-Extra: runloop
 Requires-Dist: langchain-runloop>=0.0.6; extra == 'runloop'
 Provides-Extra: together

{deepagents_code-0.1.11 → deepagents_code-0.1.12}/deepagents_code/_session_stats.py

@@ -11,7 +11,7 @@ from __future__ import annotations
 from dataclasses import dataclass, field
 from typing import Literal
 
-SpinnerStatus = Literal["Thinking", "Offloading"] | None
+SpinnerStatus = Literal["Thinking", "Offloading", "Loading thread"] | None
 """Valid spinner display states, or `None` to hide."""
 
 

{deepagents_code-0.1.11 → deepagents_code-0.1.12}/deepagents_code/_textual_patches.py

@@ -50,9 +50,9 @@ _DEEPAGENTS_WORD_SELECT_ACTIVE = "_deepagents_word_select_active"
 
 try:
     from textual import events
-    from textual._ansi_sequences import (
-        ANSI_SEQUENCES_KEYS,  # noqa: PLC2701
-        IGNORE_SEQUENCE,  # noqa: PLC2701
+    from textual._ansi_sequences import (  # noqa: PLC2701
+        ANSI_SEQUENCES_KEYS,
+        IGNORE_SEQUENCE,
     )
     from textual._xterm_parser import XTermParser  # noqa: PLC2701
 

{deepagents_code-0.1.11 → deepagents_code-0.1.12}/deepagents_code/_version.py

@@ -2,7 +2,7 @@
 
 # Keep the `x-release-please-version` annotation — release-please uses it to
 # bump `__version__` in sync with `pyproject.toml` on every release PR.
-__version__ = "0.1.11"  # x-release-please-version
+__version__ = "0.1.12"  # x-release-please-version
 
 DOCS_URL = "https://docs.langchain.com/oss/python/deepagents/code"
 """URL for `deepagents-code` documentation."""

{deepagents_code-0.1.11 → deepagents_code-0.1.12}/deepagents_code/agent.py

@@ -965,32 +965,32 @@ def _add_interrupt_on() -> dict[str, InterruptOnConfig]:
     """
     execute_interrupt_config: InterruptOnConfig = {
         "allowed_decisions": ["approve", "reject"],
-        "description": _format_execute_description,  # type: ignore[typeddict-item]  # Callable description narrower than TypedDict expects
+        "description": _format_execute_description,  # ty: ignore[invalid-argument-type]  # Callable description narrower than TypedDict expects
     }
 
     write_file_interrupt_config: InterruptOnConfig = {
         "allowed_decisions": ["approve", "reject"],
-        "description": _format_write_file_description,  # type: ignore[typeddict-item]  # Callable description narrower than TypedDict expects
+        "description": _format_write_file_description,  # ty: ignore[invalid-argument-type]  # Callable description narrower than TypedDict expects
     }
 
     edit_file_interrupt_config: InterruptOnConfig = {
         "allowed_decisions": ["approve", "reject"],
-        "description": _format_edit_file_description,  # type: ignore[typeddict-item]  # Callable description narrower than TypedDict expects
+        "description": _format_edit_file_description,  # ty: ignore[invalid-argument-type]  # Callable description narrower than TypedDict expects
     }
 
     web_search_interrupt_config: InterruptOnConfig = {
         "allowed_decisions": ["approve", "reject"],
-        "description": _format_web_search_description,  # type: ignore[typeddict-item]  # Callable description narrower than TypedDict expects
+        "description": _format_web_search_description,  # ty: ignore[invalid-argument-type]  # Callable description narrower than TypedDict expects
     }
 
     fetch_url_interrupt_config: InterruptOnConfig = {
         "allowed_decisions": ["approve", "reject"],
-        "description": _format_fetch_url_description,  # type: ignore[typeddict-item]  # Callable description narrower than TypedDict expects
+        "description": _format_fetch_url_description,  # ty: ignore[invalid-argument-type]  # Callable description narrower than TypedDict expects
     }
 
     task_interrupt_config: InterruptOnConfig = {
         "allowed_decisions": ["approve", "reject"],
-        "description": _format_task_description,  # type: ignore[typeddict-item]  # Callable description narrower than TypedDict expects
+        "description": _format_task_description,  # ty: ignore[invalid-argument-type]  # Callable description narrower than TypedDict expects
     }
 
     async_subagent_interrupt_config: InterruptOnConfig = {
@@ -1211,6 +1211,18 @@ def create_cli_agent(
             middleware.append(ConfigurableModelMiddleware())
         if restrictive_shell_allow_list is not None:
             middleware.append(ShellAllowListMiddleware(restrictive_shell_allow_list))
+        # Subagents share the on-disk filesystem backend and can edit the user
+        # AGENTS.md, so they get the same managed onboarding-name block guard as
+        # the main agent. Gated on memory because the block only exists when
+        # memory is enabled.
+        if enable_memory:
+            from deepagents_code.memory_guard import ManagedMemoryGuardMiddleware
+
+            middleware.append(
+                ManagedMemoryGuardMiddleware(
+                    [settings.get_user_agent_md_path(assistant_id)]
+                )
+            )
         return middleware
 
     for subagent_meta in list_subagents(
@@ -1254,7 +1266,7 @@ def create_cli_agent(
         custom_subagents.append(general_purpose_subagent)
 
     # Build middleware stack based on enabled features
-    agent_middleware = [
+    agent_middleware: list[AgentMiddleware[Any, Any]] = [
         ConfigurableModelMiddleware(),
         _FilesystemEmptyResultMiddleware(),
     ]
@@ -1290,6 +1302,18 @@ def create_cli_agent(
             )
         )
 
+        # Protect the machine-managed onboarding-name block in the user
+        # AGENTS.md from being rewritten by agent file edits. The block's
+        # markers are HTML comments stripped before injection, so the model
+        # can't see the boundary and would otherwise clobber it.
+        from deepagents_code.memory_guard import ManagedMemoryGuardMiddleware
+
+        agent_middleware.append(
+            ManagedMemoryGuardMiddleware(
+                [settings.get_user_agent_md_path(assistant_id)]
+            )
+        )
+
     # Add skills middleware
     if enable_skills:
         # Lowest to highest precedence:
@@ -1424,7 +1448,7 @@ def create_cli_agent(
         interrupt_on = {}
     else:
         # Full HITL for destructive operations
-        interrupt_on = _add_interrupt_on()  # type: ignore[assignment]  # InterruptOnConfig is compatible at runtime
+        interrupt_on = _add_interrupt_on()  # ty: ignore[invalid-assignment]  # InterruptOnConfig is compatible at runtime
 
     # Set up composite backend with routing
     # For local FilesystemBackend, route large tool results to /tmp to avoid polluting