deepagents-code 0.1.2__tar.gz → 0.1.3__tar.gz

{deepagents_code-0.1.2 → deepagents_code-0.1.3}/.gitignore

@@ -138,6 +138,8 @@ celerybeat.pid
 # Environments
 .env
 .envrc
+env.local
+*.env.local
 .venv
 env/
 venv/

deepagents_code-0.1.3/AGENTS.md

@@ -0,0 +1,95 @@
+# `libs/code` agent guide
+
+`deepagents-code` is the interactive coding agent — the Textual REPL, headless `-x` mode, MCP integration, skills, sandbox bootstrap, and slash-command surface. Forked from `deepagents-cli` at the 0.1.0 split.
+
+For monorepo-wide conventions (commit titles, lint, testing, docs, CI, benchmarks), see the root `AGENTS.md`.
+
+## Textual (terminal UI framework)
+
+`deepagents-code` uses [Textual](https://textual.textualize.io/).
+
+**Key Textual resources:**
+
+- **Guide:** https://textual.textualize.io/guide/
+- **Widget gallery:** https://textual.textualize.io/widget_gallery/
+- **CSS reference:** https://textual.textualize.io/styles/
+- **API reference:** https://textual.textualize.io/api/
+
+### Styled text in widgets
+
+Prefer Textual's `Content` (`textual.content`) over Rich's `Text` for widget rendering. `Content` is immutable (like `str`) and integrates natively with Textual's rendering pipeline. Rich `Text` is still correct for code that renders via Rich's `Console.print()` (e.g., `non_interactive.py`, `main.py`).
+
+IMPORTANT: `Content` requires **Textual's** `Style` (`textual.style.Style`) for rendering, not Rich's `Style` (`rich.style.Style`). Mixing Rich `Style` objects into `Content` spans will cause `TypeError` during widget rendering. String styles (`"bold cyan"`, `"dim"`) work for non-link styling. For links, use `TStyle(link=url)`.
+
+**Never use f-string interpolation in Rich markup** (e.g., `f"[bold]{var}[/bold]"`). If `var` contains square brackets, the markup breaks or throws. Use `Content` methods instead:
+
+- `Content.from_markup("[bold]$var[/bold]", var=value)` — for inline markup templates. `$var` substitution auto-escapes dynamic content. **Use when the variable is external/user-controlled** (tool args, file paths, user messages, diff content, error messages from exceptions).
+- `Content.styled(text, "bold")` — single style applied to plain text. No markup parsing. Use for static strings or when the variable is internal/trusted (glyphs, ints, enum-like status values). Avoid `Content.styled(f"..{var}..", style)` when `var` is user-controlled — while `styled` doesn't parse markup, the f-string pattern is fragile and inconsistent with the `from_markup` convention.
+- `Content.assemble("prefix: ", (text, "bold"), " ", other_content)` — for composing pre-built `Content` objects, `(text, style)` tuples, and plain strings. Plain strings are treated as plain text (no markup parsing). Use for structural composition, especially when parts use `TStyle(link=url)`.
+- `content.join(parts)` — like `str.join()` for `Content` objects.
+
+**Decision rule:** if the value could ever come from outside the codebase (user input, tool output, API responses, file contents), use `from_markup` with `$var`. If it's a hardcoded string, glyph, or computed int, `styled` is fine.
+
+### `App.notify()` defaults to `markup=True`
+
+Textual's `App.notify(message)` parses the message string as Rich markup by default. Any dynamic content (exception messages, file paths, user input, command strings) containing brackets `[]`, ANSI escape codes, or `=` will cause a `MarkupError` crash in Textual's Toast renderer. Always pass `markup=False` when the message contains f-string interpolated variables. Hardcoded string literals are safe with the default.
+
+### Rich `console.print()` and number highlighting
+
+`console.print()` defaults to `highlight=True`, which runs `ReprHighlighter` and auto-applies bold + cyan to any detected numbers. This visually overrides subtle styles like `dim` (bold cancels dim in most terminals). Pass `highlight=False` on any `console.print()` call where the content contains numbers and consistent dim/subtle styling matters.
+
+### Textual patterns used in this codebase
+
+- **Workers** (`@work` decorator) for async operations - see [Workers guide](https://textual.textualize.io/guide/workers/)
+- **Message passing** for widget communication - see [Events guide](https://textual.textualize.io/guide/events/)
+- **Reactive attributes** for state management - see [Reactivity guide](https://textual.textualize.io/guide/reactivity/)
+
+### Testing Textual apps
+
+- 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`
+
+## 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`).
+
+## 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`.
+
+- Keep top-level imports in `main.py` and other entry-point modules minimal.
+- Defer heavy imports to the point where they are actually needed (inside functions/methods).
+- To read another package's version without importing it, use `importlib.metadata.version("package-name")`.
+- Feature-gate checks on the startup hot path (before background workers fire) must be lightweight — env var lookups, small file reads. Never pull in expensive modules just to decide whether to skip a feature.
+- When adding logic that already exists elsewhere (e.g., editable-install detection), import the existing cached implementation rather than duplicating it.
+- Features that run shell commands silently must be opt-in, never default-enabled. Gate behind an explicit env var or config key.
+- Background workers that spawn subprocesses must set a timeout to avoid blocking indefinitely.
+
+## CLI help screen
+
+The `deepagents-code --help` screen is hand-maintained in `ui.show_help()`, separate from the argparse definitions in `main.parse_args()`. When adding a new CLI flag, update **both** files. A drift-detection test (`test_args.TestHelpScreenDrift`) fails if a flag is registered in argparse but missing from the help screen.
+
+## Splash screen tips
+
+When adding a user-facing CLI feature (new slash command, keybinding, workflow), add a corresponding tip to the `_TIPS` list in `deepagents_code/widgets/welcome.py`. Tips are shown randomly on startup to help users discover features. Keep tips short and action-oriented (e.g., `"Press ctrl+x to compose prompts in your external editor"`).
+
+## Slash commands
+
+Slash commands are defined as `SlashCommand` entries in the `COMMANDS` tuple in `deepagents_code/command_registry.py`. Each entry declares the command name, description, `bypass_tier` (queue-bypass classification), optional `hidden_keywords` for fuzzy matching, and optional `aliases`. Bypass-tier frozensets and the `SLASH_COMMANDS` autocomplete list are derived automatically — no other file should hard-code command metadata.
+
+To add a new slash command: (1) add a `SlashCommand` entry to `COMMANDS`, (2) set the appropriate `bypass_tier`, (3) add a handler branch in `_handle_command` in `app.py`, (4) run `make lint && make test` — the drift test will catch any mismatch.
+
+## Adding a new model provider
+
+`deepagents-code` supports LangChain-based chat model providers as optional dependencies. To add a new provider, update these files (all entries alphabetically sorted):
+
+1. `deepagents_code/model_config.py` — add `"provider_name": "ENV_VAR_NAME"` to `PROVIDER_API_KEY_ENV`
+2. `pyproject.toml` — add `provider = ["langchain-provider>=X.Y.Z,<N.0.0"]` to `[project.optional-dependencies]` and include it in the `all-providers` composite extra
+3. `tests/unit_tests/test_model_config.py` — add `assert PROVIDER_API_KEY_ENV["provider_name"] == "ENV_VAR_NAME"` to `TestProviderApiKeyEnv.test_contains_major_providers`
+
+**Not required** unless the provider's models have a distinctive name prefix (like `gpt-*`, `claude*`, `gemini*`):
+
+- `detect_provider()` in `config.py` — only needed for auto-detection from bare model names
+- `Settings.has_*` property in `config.py` — only needed if referenced by `detect_provider()` fallback logic
+
+Model discovery, credential checking, and UI integration are automatic once `PROVIDER_API_KEY_ENV` is populated and the `langchain-*` package is installed.

{deepagents_code-0.1.2 → deepagents_code-0.1.3}/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Deep Agents Code Changelog
 
+## [0.1.3](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.2...deepagents-code==0.1.3) (2026-05-20)
+
+### Features
+
+* In-TUI MCP OAuth login with auto-refresh ([#3469](https://github.com/langchain-ai/deepagents/issues/3469)) ([20e38b8](https://github.com/langchain-ai/deepagents/commit/20e38b8ebd8d9aa4697334432f7832a0a07aea3a))
+  * Float unauthorized MCP servers to top and prompt before reconnect ([#3493](https://github.com/langchain-ai/deepagents/issues/3493)) ([2d66580](https://github.com/langchain-ai/deepagents/commit/2d665804131961dfa7e2849248047deec818e4ef))
+  * Disable MCP servers from TUI ([#3501](https://github.com/langchain-ai/deepagents/issues/3501)) ([5725de8](https://github.com/langchain-ai/deepagents/commit/5725de857722dbca768a95bc6d97af5b838a11a9))
+* `/restart` hidden slash command ([#3514](https://github.com/langchain-ai/deepagents/issues/3514)) ([74bdd36](https://github.com/langchain-ai/deepagents/commit/74bdd3688948d8369cdd978590f5a822eabeb12c))
+
+### Bug Fixes
+
+* Persist `_context_tokens` via `after_model` middleware ([#3496](https://github.com/langchain-ai/deepagents/issues/3496)) ([e2bb284](https://github.com/langchain-ai/deepagents/commit/e2bb284e506e0e49a05169fc6de01bdf42350267))
+* Refresh status bar model after recovering from failed startup ([#3511](https://github.com/langchain-ai/deepagents/issues/3511)) ([c96f822](https://github.com/langchain-ai/deepagents/commit/c96f822de187431404d093b852c4a855d3ab8d30))
+
 ## [0.1.2](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.1...deepagents-code==0.1.2) (2026-05-19)
 
 ### Features

deepagents_code-0.1.3/COMMANDS.md

@@ -0,0 +1,44 @@
+<!-- AUTO-GENERATED by scripts/generate_commands_catalog.py — do not edit manually. -->
+# Slash command catalog
+
+Canonical list of slash commands for `deepagents-code`, derived from
+`deepagents_code/command_registry.py`. Run `make commands-catalog` to
+regenerate after editing the registry.
+
+
+## Public (25)
+
+| Command | Aliases | Description |
+| --- | --- | --- |
+| `/agents` |  | Browse and switch between available agents |
+| `/auth` | `/connect` | Manage stored API keys for model providers |
+| `/auto-update` |  | Toggle automatic updates on or off |
+| `/changelog` |  | Open changelog in browser |
+| `/clear` |  | Clear chat and start new thread |
+| `/copy` |  | Copy latest assistant message to clipboard |
+| `/docs` |  | Open documentation in browser |
+| `/editor` |  | Open prompt in external editor ($EDITOR) |
+| `/feedback` |  | Submit a bug report or feature request |
+| `/force-clear` |  | Interrupt active work, clear chat, and start new thread |
+| `/help` |  | Show help |
+| `/mcp` |  | Show MCP servers; `/mcp login <server>` to authenticate, `/mcp reconnect` to load deferred logins, F2 in the viewer to disable/enable a server |
+| `/model` |  | Switch or configure model (--model-params, --default) |
+| `/notifications` |  | Configure startup warning preferences |
+| `/offload` | `/compact` | Free up context window space by offloading older messages |
+| `/quit` | `/q` | Exit app |
+| `/reload` |  | Reload config from environment variables and .env |
+| `/remember` |  | Update memory and skills from conversation |
+| `/skill-creator` |  | Guide for creating effective agent skills |
+| `/theme` |  | Switch color theme |
+| `/threads` |  | Browse and resume previous threads |
+| `/tokens` |  | Token usage |
+| `/trace` |  | Open current thread in LangSmith |
+| `/update` |  | Check for and install updates |
+| `/version` | `/about` | Show version |
+
+## Hidden (2)
+
+Hidden commands not exposed in autocomplete or help. See the `HIDDEN_COMMANDS` docstring in the registry for context.
+
+- `/debug-error`
+- `/restart`

{deepagents_code-0.1.2 → deepagents_code-0.1.3}/Makefile

@@ -1,4 +1,4 @@
-.PHONY: format lint type typecheck test tests integration_test integration_tests test_watch benchmark bench bench-memory help run lint_package lint_tests check_imports coverage
+.PHONY: format lint type typecheck test tests integration_test integration_tests test_watch benchmark bench bench-memory help run lint_package lint_tests check_imports coverage commands-catalog commands-catalog-check
 
 .DEFAULT_GOAL := help
 
@@ -66,6 +66,7 @@ lint lint_diff lint_package lint_tests:
 	[ "$(PYTHON_FILES)" = "" ] || uv run --all-groups ruff check $(PYTHON_FILES)
 	[ "$(PYTHON_FILES)" = "" ] || uv run --all-groups ruff format $(PYTHON_FILES) --diff
 	$(MAKE) type PYTHON_FILES="$(PYTHON_FILES)"
+	uv run --all-groups python scripts/generate_commands_catalog.py --check
 
 type: ## Run type checker
 type typecheck:
@@ -80,6 +81,12 @@ check_imports: ## Check imports
 check_imports: $(shell find deepagents_code -name '*.py')
 	uv run --all-groups python ./scripts/check_imports.py $^
 
+commands-catalog: ## Regenerate COMMANDS.md from the slash-command registry
+	uv run --all-groups python scripts/generate_commands_catalog.py
+
+commands-catalog-check: ## Verify COMMANDS.md matches the slash-command registry
+	uv run --all-groups python scripts/generate_commands_catalog.py --check
+
 ######################
 # HELP
 ######################

{deepagents_code-0.1.2 → deepagents_code-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepagents-code
-Version: 0.1.2
+Version: 0.1.3
 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/
@@ -27,7 +27,7 @@ Classifier: Topic :: Terminals
 Requires-Python: <4.0,>=3.11
 Requires-Dist: aiosqlite<1.0.0,>=0.19.0
 Requires-Dist: deepagents-acp>=0.0.4
-Requires-Dist: deepagents==0.6.2
+Requires-Dist: deepagents==0.6.3
 Requires-Dist: httpx<1.0.0,>=0.28.1
 Requires-Dist: langchain-anthropic<2.0.0,>=1.4.3
 Requires-Dist: langchain-google-genai<5.0.0,>=4.2.2
@@ -154,13 +154,6 @@ curl -LsSf https://langch.in/dcode | bash
 DEEPAGENTS_EXTRAS="nvidia,ollama" curl -LsSf https://langch.in/dcode | bash
 ```
 
-Or install directly with `uv`:
-
-```bash
-# Install with chosen model providers
-uv tool install 'deepagents-code[nvidia,ollama]'
-```
-
 Run:
 
 ```bash

{deepagents_code-0.1.2 → deepagents_code-0.1.3}/README.md

@@ -21,13 +21,6 @@ curl -LsSf https://langch.in/dcode | bash
 DEEPAGENTS_EXTRAS="nvidia,ollama" curl -LsSf https://langch.in/dcode | bash
 ```
 
-Or install directly with `uv`:
-
-```bash
-# Install with chosen model providers
-uv tool install 'deepagents-code[nvidia,ollama]'
-```
-
 Run:
 
 ```bash

{deepagents_code-0.1.2 → deepagents_code-0.1.3}/deepagents_code/__init__.py

@@ -1,4 +1,4 @@
-"""Deep Agents CLI - Interactive AI coding assistant."""
+"""Deep Agents Code - Interactive AI coding assistant."""
 
 from __future__ import annotations
 

{deepagents_code-0.1.2 → deepagents_code-0.1.3}/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__ = "0.1.2"  # x-release-please-version
+__version__ = "0.1.3"  # x-release-please-version
 
 DOCS_URL = "https://docs.langchain.com/oss/python/deepagents/code"
 """URL for `deepagents-code` documentation."""

{deepagents_code-0.1.2 → deepagents_code-0.1.3}/deepagents_code/agent.py

@@ -1100,9 +1100,9 @@ def create_cli_agent(
     agent_middleware = []
     agent_middleware.append(ConfigurableModelMiddleware())
 
-    # Token state: adds _context_tokens to graph state (checkpointed, not
-    # passed to model).  Must be registered before any middleware that might
-    # read the channel.
+    # Token state: declares the `_context_tokens` channel and writes it from
+    # `after_model` based on the latest `AIMessage.usage_metadata`. The CLI
+    # reads it back from `state_values` on thread resume.
     from deepagents_code.token_state import TokenStateMiddleware
 
     agent_middleware.append(TokenStateMiddleware())