deepagents-code 0.1.80__tar.gz → 0.1.82__tar.gz

{deepagents_code-0.1.80 → deepagents_code-0.1.82}/CHANGELOG.md

@@ -2,6 +2,45 @@
 
 # Deep Agents Code Changelog
 
+## [0.1.82](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.81...deepagents-code==0.1.82) (2026-10-07)
+
+### Features
+
+- Create persistent thread names automatically or on demand, and rename threads manually. ([#6715](https://github.com/langchain-ai/deepagents/pull/6715), [#6767](https://github.com/langchain-ai/deepagents/pull/6767))
+- Customize terminal tab titles. ([#6768](https://github.com/langchain-ai/deepagents/pull/6768))
+- Distinguish skill reads in the transcript. ([#6825](https://github.com/langchain-ai/deepagents/pull/6825))
+
+### Bug Fixes
+
+- Keep the thread picker open when ownership conflicts occur. ([#6824](https://github.com/langchain-ai/deepagents/pull/6824))
+- Preserve completion markers on remote messages. ([#6831](https://github.com/langchain-ai/deepagents/pull/6831))
+- Extend triple-click selection across blocks. ([#6819](https://github.com/langchain-ai/deepagents/pull/6819))
+- Recommend GPT-6 Luna for auto review. ([#6821](https://github.com/langchain-ai/deepagents/pull/6821))
+- Show editable install status in debug version information. ([#6797](https://github.com/langchain-ai/deepagents/pull/6797))
+
+## [0.1.81](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.80...deepagents-code==0.1.81) (2026-10-06)
+
+### Features
+
+- The agent can now discover marketplace plugins ([#6719](https://github.com/langchain-ai/deepagents/pull/6719)).
+- You can open the effort selector during active runs ([#6724](https://github.com/langchain-ai/deepagents/pull/6724)) and the cost breakdown from the footer ([#6723](https://github.com/langchain-ai/deepagents/pull/6723)).
+- Added `--no-tracing` and an explicit tracing status indicator ([#6721](https://github.com/langchain-ai/deepagents/pull/6721)).
+- Renamed `/summarization-model` to `/offload model` ([#6774](https://github.com/langchain-ai/deepagents/pull/6774)).
+- Highlighted the active line in multiline chat input ([#6746](https://github.com/langchain-ai/deepagents/pull/6746)).
+
+### Bug Fixes
+
+- Use `ChatBedrockConverse` for non-Anthropic Bedrock models ([#6718](https://github.com/langchain-ai/deepagents/pull/6718)).
+- Prevented concurrent writes to local threads ([#6717](https://github.com/langchain-ai/deepagents/pull/6717)).
+- Hook execution now fails closed if its context changes when a run resumes ([#6712](https://github.com/langchain-ai/deepagents/pull/6712)).
+- Improved server-side model catalog, selection, and interactive model metadata handling ([#6773](https://github.com/langchain-ai/deepagents/pull/6773), [#6772](https://github.com/langchain-ai/deepagents/pull/6772)).
+- Isolated stored provider endpoints in workspace models ([#6771](https://github.com/langchain-ai/deepagents/pull/6771)).
+- Reconciled cache expiry during model requests ([#6763](https://github.com/langchain-ai/deepagents/pull/6763)).
+- Preserved dispatch timers across interrupt replays ([#6722](https://github.com/langchain-ai/deepagents/pull/6722)).
+- Collapsed idle subagents and reopened them for new work ([#6782](https://github.com/langchain-ai/deepagents/pull/6782)).
+- Moved debug MCP server details into a modal ([#6720](https://github.com/langchain-ai/deepagents/pull/6720)).
+- Clarified that clearing the chat starts a new thread ([#6726](https://github.com/langchain-ai/deepagents/pull/6726)).
+
 ## [0.1.80](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.79...deepagents-code==0.1.80) (2026-10-01)
 
 ### Features

{deepagents_code-0.1.80 → deepagents_code-0.1.82}/COMMANDS.md

@@ -37,17 +37,17 @@ aliases, descriptions, visibility, or hidden-command metadata.
 | `/mcp` |  | Manage MCP servers and authentication |
 | `/model` |  | Switch models or edit model settings |
 | `/notifications` |  | Review notifications and configure warning settings |
-| `/offload` | `/compact` | Summarize and offload older messages to free context |
+| `/offload` | `/compact` | Offload older messages or choose the summarization model |
 | `/plugins` |  | Manage plugins |
 | `/prompts` |  | Search and reuse a previous prompt |
 | `/quit` | `/q` | Exit app |
 | `/reload` |  | Reload environment and config |
 | `/remember` |  | Save useful context to memory or skills |
+| `/rename` |  | Name this thread or generate a suggested name |
 | `/restart` |  | Restart the agent server |
 | `/rubric` | `/criteria` | Set explicit acceptance criteria for rubric grading |
 | `/scrollbar` |  | Show or hide the chat scrollbar |
 | `/skill-creator` |  | Create or refine agent skills |
-| `/summarization-model` |  | Set the model used for context-compaction summaries |
 | `/theme` |  | Change color theme |
 | `/threads` |  | Browse and resume past threads |
 | `/timestamps` |  | Show or hide message timestamps |

{deepagents_code-0.1.80 → deepagents_code-0.1.82}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: deepagents-code
-Version: 0.1.80
+Version: 0.1.82
 Summary: Terminal coding agent built on the Deep Agents SDK - works with any model, with persistent memory, customizable skills, subagents, and approval controls.
 Project-URL: Homepage, https://www.langchain.com/dcode
 Project-URL: Documentation, https://docs.langchain.com/oss/deepagents/code/overview
@@ -30,7 +30,7 @@ Requires-Python: <4.0,>=3.12
 Requires-Dist: aiosqlite<1.0.0,>=0.22.1
 Requires-Dist: anyio<5.0.0,>=4.14.2
 Requires-Dist: deepagents-acp<1.0.0,>=0.0.10
-Requires-Dist: deepagents==0.7.21
+Requires-Dist: deepagents==0.7.22
 Requires-Dist: fastmcp<5.0.0,>=4.0.0b4
 Requires-Dist: filelock<3.30,>=3.29.7
 Requires-Dist: genai-prices<0.2.0,>=0.1.9
@@ -42,9 +42,9 @@ Requires-Dist: langchain-quickjs<0.4.0,>=0.3.4
 Requires-Dist: langchain<2.0.0,>=1.4.3
 Requires-Dist: langgraph-checkpoint-sqlite<4.0.0,>=3.1.1
 Requires-Dist: langgraph-cli[inmem]<1.0.0,>=0.4.32
-Requires-Dist: langgraph-runtime-inmem<1.0.0,>=0.35.1
-Requires-Dist: langgraph-sdk<1.0.0,>=0.4.5
-Requires-Dist: langsmith[sandbox]>=0.14.2
+Requires-Dist: langgraph-runtime-inmem<1.0.0,>=0.35.2
+Requires-Dist: langgraph-sdk<1.0.0,>=0.4.6
+Requires-Dist: langsmith[sandbox]>=0.14.4
 Requires-Dist: markdownify<2.0.0,>=1.2.3
 Requires-Dist: mcp<3.0.0,>=2.0.0
 Requires-Dist: packaging>=26.2
@@ -67,7 +67,7 @@ Requires-Dist: langchain-agentcore-codeinterpreter<1.0.0,>=0.0.5; extra == 'agen
 Provides-Extra: all-providers
 Requires-Dist: aiohttp<3.15.0,>=3.14.3; extra == 'all-providers'
 Requires-Dist: langchain-anthropic<2.0.0,>=1.7.5; extra == 'all-providers'
-Requires-Dist: langchain-aws<2.0.0,>=1.8.0; extra == 'all-providers'
+Requires-Dist: langchain-aws<2.0.0,>=1.8.1; extra == 'all-providers'
 Requires-Dist: langchain-baseten<1.0.0,>=0.2.4; extra == 'all-providers'
 Requires-Dist: langchain-cohere<1.0.0,>=0.6.0; extra == 'all-providers'
 Requires-Dist: langchain-deepseek<2.0.0,>=1.1.1; extra == 'all-providers'
@@ -76,7 +76,7 @@ Requires-Dist: langchain-google-genai<5.0.0,>=4.4.0; extra == 'all-providers'
 Requires-Dist: langchain-google-vertexai<4.0.0,>=3.2.4; extra == 'all-providers'
 Requires-Dist: langchain-groq<2.0.0,>=1.1.3; extra == 'all-providers'
 Requires-Dist: langchain-huggingface<2.0.0,>=1.2.2; extra == 'all-providers'
-Requires-Dist: langchain-ibm<2.0.0,>=1.1.1; extra == 'all-providers'
+Requires-Dist: langchain-ibm<2.0.0,>=1.1.2; extra == 'all-providers'
 Requires-Dist: langchain-litellm<2.0.0,>=0.11.0; extra == 'all-providers'
 Requires-Dist: langchain-meta<2.0.0,>=0.5.0; extra == 'all-providers'
 Requires-Dist: langchain-mistralai<2.0.0,>=1.1.6; extra == 'all-providers'
@@ -98,7 +98,7 @@ Requires-Dist: langchain-anthropic<2.0.0,>=1.7.5; extra == 'anthropic'
 Provides-Extra: baseten
 Requires-Dist: langchain-baseten<1.0.0,>=0.2.4; extra == 'baseten'
 Provides-Extra: bedrock
-Requires-Dist: langchain-aws<2.0.0,>=1.8.0; extra == 'bedrock'
+Requires-Dist: langchain-aws<2.0.0,>=1.8.1; extra == 'bedrock'
 Provides-Extra: cohere
 Requires-Dist: langchain-cohere<1.0.0,>=0.6.0; extra == 'cohere'
 Provides-Extra: daytona
@@ -114,7 +114,7 @@ Requires-Dist: langchain-groq<2.0.0,>=1.1.3; extra == 'groq'
 Provides-Extra: huggingface
 Requires-Dist: langchain-huggingface<2.0.0,>=1.2.2; extra == 'huggingface'
 Provides-Extra: ibm
-Requires-Dist: langchain-ibm<2.0.0,>=1.1.1; extra == 'ibm'
+Requires-Dist: langchain-ibm<2.0.0,>=1.1.2; extra == 'ibm'
 Provides-Extra: litellm
 Requires-Dist: langchain-litellm<2.0.0,>=0.11.0; extra == 'litellm'
 Provides-Extra: media

{deepagents_code-0.1.80 → deepagents_code-0.1.82}/deepagents_code/_build_info.py

@@ -1,3 +1,3 @@
 """Generated at build time. Do not edit or commit."""
 
-BUILD_COMMIT = "e4c1ffe"
+BUILD_COMMIT = "981c043"

{deepagents_code-0.1.80 → deepagents_code-0.1.82}/deepagents_code/_cli_context.py

@@ -34,7 +34,7 @@ INHERIT_SUMMARIZATION_MODEL = "__dcode_inherit_summarization__"
 """Per-run `summarization_model` value meaning "use the main agent model".
 
 An absent (or `None`) `summarization_model` leaves the graph's startup summary
-model in effect. `/summarization-model clear` needs the stronger statement that
+model in effect. `/offload model clear` needs the stronger statement that
 summaries go back to the main agent model, which this sentinel carries across
 the remote JSON boundary without being mistaken for a model spec.
 """

{deepagents_code-0.1.80 → deepagents_code-0.1.82}/deepagents_code/_js_cost.py

@@ -26,6 +26,7 @@ from deepagents_code.cost_tracking import (
     _merge_cost_breakdowns,
     _parent_checkpoint_scope,
 )
+from deepagents_code.thread_ownership import OWNER_KEY
 
 if TYPE_CHECKING:
     from collections.abc import Awaitable, Callable
@@ -202,6 +203,8 @@ def record_cost_receipt(
             "checkpoint_ns": f"{owner}|receipt:{_digest(namespace)}",
         }
     }
+    if OWNER_KEY in configurable:
+        config["configurable"][OWNER_KEY] = configurable[OWNER_KEY]
     loop = configurable["__deepagents_js_cost_loop"]
     asyncio.run_coroutine_threadsafe(
         _put_receipt(saver, config, owner, amount, breakdown), loop

deepagents_code-0.1.82/deepagents_code/_startup_error.py

@@ -0,0 +1,136 @@
+"""Stderr marker emission used by the langgraph server graph entry point.
+
+Lives in its own module so unit tests can exercise the marker contract
+without triggering `server_graph.make_graph()` at import time.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import sys
+import traceback
+
+logger = logging.getLogger(__name__)
+
+STARTUP_ERROR_MARKER = "DEEPAGENTS_STARTUP_ERROR:"
+"""Stderr marker the parent app scans for in `server._extract_startup_error_marker`
+to upgrade an opaque "Server process exited with code N" into a one-line summary.
+Format is `{STARTUP_ERROR_MARKER}{single-line message}`."""
+
+_STARTUP_ERROR_DETAILS_MARKER = "DEEPAGENTS_STARTUP_ERROR_DETAILS:"
+
+
+def _recovery_details(exc: BaseException) -> dict[str, str | None] | None:
+    """Allowlist recovery fields; never serialize an exception's full state.
+
+    Returns:
+        Recovery details for known errors, or `None` for other failures.
+    """
+    from deepagents_code.model_config import (
+        MissingCredentialsError,
+        MissingProviderPackageError,
+    )
+
+    if isinstance(exc, MissingCredentialsError):
+        return {
+            "type": "MissingCredentialsError",
+            "message": str(exc),
+            "provider": exc.provider,
+            "env_var": exc.env_var,
+        }
+    if isinstance(exc, MissingProviderPackageError):
+        return {
+            "type": "MissingProviderPackageError",
+            "message": str(exc),
+            "provider": exc.provider,
+            "package": exc.package,
+        }
+    return None
+
+
+def _decode_recovery_error(payload: object) -> Exception | None:
+    """Reconstruct only known recovery errors with validated string fields.
+
+    Returns:
+        A typed error, or `None` for unsupported or invalid payloads.
+    """
+    from deepagents_code.model_config import (
+        MissingCredentialsError,
+        MissingProviderPackageError,
+    )
+
+    if not isinstance(payload, dict):
+        return None
+    message, provider = payload.get("message"), payload.get("provider")
+    if not isinstance(message, str) or not isinstance(provider, str) or not provider:
+        return None
+    if payload.get("type") == "MissingCredentialsError":
+        env_var = payload.get("env_var")
+        if env_var is None or isinstance(env_var, str):
+            return MissingCredentialsError(message, provider=provider, env_var=env_var)
+    if payload.get("type") == "MissingProviderPackageError":
+        package = payload.get("package")
+        if isinstance(package, str) and package:
+            return MissingProviderPackageError(
+                message, provider=provider, package=package
+            )
+    return None
+
+
+def startup_error_from_output(output: str, fallback: str) -> Exception:
+    """Restore a typed recovery error, falling back to the ordinary log summary.
+
+    Args:
+        output: Server subprocess output containing startup markers.
+        fallback: Error text for legacy, unknown, or malformed markers.
+
+    Returns:
+        A known model recovery error or a `RuntimeError` with the fallback text.
+    """
+    for line in reversed(output.splitlines()):
+        if _STARTUP_ERROR_DETAILS_MARKER in line:
+            _, encoded = line.split(_STARTUP_ERROR_DETAILS_MARKER, 1)
+            try:
+                error = _decode_recovery_error(json.loads(encoded))
+            except ValueError:
+                break
+            if error is not None:
+                return error
+            break
+    return RuntimeError(fallback)
+
+
+def emit_startup_failure(exc: BaseException) -> None:
+    """Report a server graph startup failure to the parent app process.
+
+    Emits the full traceback for logs/debugging, then a
+    single-line `{STARTUP_ERROR_MARKER}{type}: {summary}` line that
+    `server._extract_startup_error_marker` parses to upgrade an opaque
+    "Server process exited with code N" into an actionable summary.
+    Known credential/package errors also include JSON recovery fields so the
+    client can restore their types without constructing a provider model.
+
+    Args:
+        exc: The exception raised during graph initialization.
+    """
+    logger.critical("Failed to initialize server graph", exc_info=exc)
+    print(  # noqa: T201  # stderr fallback — logger may not reach parent process
+        f"Failed to initialize server graph: {exc}\n{traceback.format_exc()}",
+        file=sys.stderr,
+    )
+    # Marker contract is single-line; guard against multi-line/empty `str(exc)`
+    # and include the type so e.g. `ValueError` and `RuntimeError` are
+    # distinguishable in the parent's truncated summary.
+    exc_lines = str(exc).splitlines()
+    summary = exc_lines[0] if exc_lines else "<no message>"
+    print(  # noqa: T201
+        f"{STARTUP_ERROR_MARKER}{type(exc).__name__}: {summary}",
+        file=sys.stderr,
+    )
+    details = _recovery_details(exc)
+    if details is not None:
+        print(  # noqa: T201  # parent process recovery protocol
+            f"{_STARTUP_ERROR_DETAILS_MARKER}{json.dumps(details)}",
+            file=sys.stderr,
+        )

{deepagents_code-0.1.80 → deepagents_code-0.1.82}/deepagents_code/_textual_patches.py

@@ -39,8 +39,9 @@ upstream.
 
 3. Double-click word selection. Stock Textual selects the entire widget on
     a click chain; these patches narrow a double-click (and double-click
-    drag) to word boundaries. No upstream issue tracks this yet, so it has
-    no removal criterion — it stays until Textual grows native word select.
+    drag) to word boundaries. Holding the third press selects whole blocks
+    while dragging across widgets. No upstream issue tracks this yet, so it
+    stays until Textual grows native word and block selection.
 
 4. Shift-click selection extension. Stock Textual replaces an existing text
     selection on every mouse press, so Shift+click cannot move the active end
@@ -134,6 +135,7 @@ _ESC_PREFIX_LEN = 2
 _DOUBLE_CLICK_CHAIN = 2
 _TRIPLE_CLICK_CHAIN = 3
 _DEEPAGENTS_WORD_SELECT_ACTIVE = "_deepagents_word_select_active"
+_DEEPAGENTS_BLOCK_SELECT_ACTIVE = "_deepagents_block_select_active"
 
 try:
     from textual import events
@@ -417,11 +419,10 @@ else:
 
     def _forward_event_with_word_select(self: Screen, event: Event) -> None:
         if isinstance(event, _events.MouseDown):
-            setattr(
-                self,
-                _DEEPAGENTS_WORD_SELECT_ACTIVE,
-                _is_word_select_start(self, event),
-            )
+            chained = _is_word_select_start(self, event)
+            block_select = chained and self.app._chained_clicks == _DOUBLE_CLICK_CHAIN
+            setattr(self, _DEEPAGENTS_BLOCK_SELECT_ACTIVE, block_select)
+            setattr(self, _DEEPAGENTS_WORD_SELECT_ACTIVE, chained and not block_select)
         try:
             _original_forward_event(self, event)
         finally:
@@ -438,6 +439,12 @@ else:
         # without forcing a same-day patch update.
         if isawaitable(result):
             await result
+        if getattr(self, _DEEPAGENTS_BLOCK_SELECT_ACTIVE, False) and select_state:
+            if select_state.end is None:
+                widget = select_state.start.content_widget
+                if widget is not None:
+                    self.selections = {widget: Selection(None, None)}
+            return
         if not getattr(self, _DEEPAGENTS_WORD_SELECT_ACTIVE, False):
             return
 
@@ -640,8 +647,13 @@ else:
         # Textual stores the new dict before invoking this watcher. Clamp that
         # object synchronously before returning the original watcher's awaitable;
         # assigning `self.selections` here would schedule this watcher again.
+        block_select = getattr(self, _DEEPAGENTS_BLOCK_SELECT_ACTIVE, False)
         for widget, selection in list(selections.items()):
-            clamped = clamp_selection(widget, selection)
+            # Expand before clamping: a partial endpoint at the first source
+            # column would otherwise be dropped as a gutter-only selection.
+            clamped = clamp_selection(
+                widget, Selection(None, None) if block_select else selection
+            )
             if clamped is None:
                 del selections[widget]
             elif clamped != selection:

deepagents_code-0.1.82/deepagents_code/_tool_free.py

@@ -0,0 +1,79 @@
+"""Remove executable tool configuration from isolated model requests."""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from copy import deepcopy
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from langchain_core.language_models import BaseChatModel
+
+_TOOL_OPTIONS = frozenset(
+    {
+        "tools",
+        "tool_choice",
+        "functions",
+        "function_call",
+        "parallel_tool_calls",
+        "mcp_servers",
+    }
+)
+_OPTION_CONTAINERS = ("model_kwargs", "extra_body")
+
+
+def _tool_free_options[K](options: Mapping[K, object]) -> dict[K, object]:
+    """Copy request defaults, including nested provider payload overrides.
+
+    Returns:
+        Options with tool configuration removed.
+    """
+    return {
+        key: (
+            _tool_free_options(value)
+            if key in _OPTION_CONTAINERS and isinstance(value, Mapping)
+            else deepcopy(value)
+        )
+        for key, value in options.items()
+        if key not in _TOOL_OPTIONS
+    }
+
+
+def tool_free_model(model: BaseChatModel) -> BaseChatModel:
+    """Isolate request defaults while sharing the provider's HTTP clients.
+
+    Args:
+        model: Unbound chat model whose defaults should be isolated.
+
+    Returns:
+        A model copy with tool-free provider defaults.
+    """
+    updates: dict[str, object] = {
+        key: _tool_free_options(value)
+        for key in _OPTION_CONTAINERS
+        if isinstance(value := getattr(model, key, None), Mapping)
+    }
+    if hasattr(model, "mcp_servers"):
+        updates["mcp_servers"] = None
+    return model.model_copy(update=updates)
+
+
+def tool_free_settings(
+    model: object, settings: Mapping[str, object]
+) -> dict[str, object]:
+    """Flatten bound defaults with request overrides taking precedence.
+
+    Args:
+        model: Chat model, optionally wrapped in request bindings.
+        settings: Request overrides to apply after bound defaults.
+
+    Returns:
+        Isolated generation settings without tool configuration.
+    """
+    from langchain_core.runnables import RunnableBinding
+
+    merged = dict(settings)
+    while isinstance(model, RunnableBinding):
+        merged = {**model.kwargs, **merged}
+        model = model.bound
+    return _tool_free_options(merged)

{deepagents_code-0.1.80 → deepagents_code-0.1.82}/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__ = "0.1.80"  # x-release-please-version
+__version__ = "0.1.82"  # x-release-please-version
 
 DOCS_URL = "https://docs.langchain.com/oss/python/deepagents/code"
 """URL for `deepagents-code` documentation."""

{deepagents_code-0.1.80 → deepagents_code-0.1.82}/deepagents_code/agent.py

@@ -75,6 +75,7 @@ from deepagents_code._glm_5p2_profile import (
     _ensure_glm_5p2_profile_registered,
     _GlmTerminalStallRecovery,
 )
+from deepagents_code._invocation import invoked_name
 from deepagents_code._paths import (
     PATHS,
     ensure_agent_dir,
@@ -1787,6 +1788,7 @@ def get_system_prompt(
         .replace("{model_identity_section}", model_identity_section)
         .replace("{working_dir_section}", working_dir_section)
         .replace("{skills_path}", skills_path)
+        .replace("{cli_name}", invoked_name())
         .replace("{filesystem_tool_guidance}", filesystem_tool_guidance)
         .replace("{tool_approval_guidance}", tool_approval_guidance)
         .replace("{web_search_tool_guidance}", web_search_tool_guidance)