Skip to content
Agents tracked: 258 Downloads (7d): 219M up 6.1% GitHub stars: 5.5M VS Code installs: 148M Releases (7d): 293 Agent status: 2 with issues Updated Oct 7, 2026
AgentGid

Deep Agents changelog: what's new each month

Every stable Deep Agents release summarised by month: the highlights, new features, improvements, fixes and anything you need to act on. 3 months covered; the current month updates daily.

October 2026 · so far

4 releases: 0.0.9 → 0.1.81

October brought major platform integrations and workflow improvements to Deep Agents. The month saw new chat adapters, scheduling capabilities, and better control over model selection and execution.

Action needed
  • /summarization-model renamed to /offload model

Highlights

  • Added Slack channel adapter with user mentions and paired sender support for secure access.
  • Introduced per-chat model switching with the /model command.
  • Added scheduled jobs with cron expressions and inline subagent execution.
  • Marketplace plugin discovery now available for agents.
  • New sandboxed execution option via environment variable for enhanced security.

New

  • Slack channel adapter with outbound user mentions.
  • Sender pairing for DM access and Slack with pairing code delivery.
  • Per-chat model switching via /model command.
  • Cron expressions and expiry times for scheduled jobs with inline subagent execution.
  • Sandboxed execution mode via DEEPAGENTSTALONSANDBOX.
  • Approved one-off askforhelp consultations.
  • Batch approvals for concurrent tool calls.
  • Marketplace plugin discovery for agents.

Improved

  • Discord slash commands now registered as chat commands with public thread history sharing by guild channel.
  • Cache expiring notifications emitted before prompt cache expires and shared with TUI.
  • Transcript position maintained when opening pickers.
  • Skill paths now use listed locations instead of inference.
  • Skills load their tools only when read, improving performance.
  • Effort selector and cost breakdown now accessible during active runs.
  • Multiline chat input now highlights the active line.
  • Added explicit tracing status indicator and --no-tracing option.

Fixed

  • Stale encoding reset when overwriting text.
  • Product and command names corrected in skill guides.
  • Concurrent writes to local threads prevented.
  • Hook execution now fails closed if context changes when a run resumes.
  • Non-Anthropic Bedrock models now use ChatBedrockConverse.

September 2026

30 releases: 0.7.12 → 0.7.21

September brought major expansions to Deep Agents' capabilities, with significant additions to conversation management, model support, and reliability improvements across all components.

Action needed
  • Subagent mode renamed from handoff to isolated.
  • Task tool calls now reject unknown argument keys instead of silently dropping unexpected input.
  • FileInfo.size now correctly represents file size in bytes across backends.

Highlights

  • Added Discord channel support with improved gateway failure reporting and new chat-scoped conversation history with configurable storage.
  • Introduced subagent conversation forking and flexible subagent execution modes, including background expendable subagents and per-task tool selection.
  • Added GPT-6 Astra support and pricing for Fireworks GLM-5.3 models, plus new MCP configuration tools and hot reload support.
  • Expanded tool capabilities with native streaming PTC tool calls, improved file handling with better truncation explanations, and new /help and /btw commands.
  • Improved workspace isolation, conversation reliability, and MCP safety with better OAuth credential handling and bounded resource operations.

New

  • Subagent conversation forking in the SDK and renaming subagent mode from handoff to isolated.
  • Discord channel support including gateway failure reporting and chat-scoped conversation history with hybrid search.
  • MCP configuration tools, channel-based server authorization, hot reload for MCP configuration, and OAuth/device authentication for Slack and GitHub.
  • Background expendable subagents, fresh subagents, per-task tool selection, and on-demand subagent execution.
  • A /help command, /btw command for isolated side questions, and currenttime tool with timezone-aware wall-clock cron schedules.
  • Inline thread mentions and picker via @@ syntax and targeted conversation deletion support.
  • Cache bust timer in the footer and durable Debug Console cost breakdown with token and cost refresh while viewing.
  • Support for managing tool approvals through tools.json and persistent LangGraph checkpoints.

Improved

  • Renamed subagent mode from handoff to isolated for clarity.
  • General-purpose subagents now default to fork mode and Auto classifier defaults by provider.
  • Improved workspace isolation by resolving project policy per workspace, scoping project dotenv to workspaces, and isolating LangSmith auth.
  • Better workspace configuration with bound conversation support, effective approval mode tracing, and request-time working directory binding.
  • Enhanced MCP reliability with hardened OAuth device-flow, credential handling, and bounded configuration updates.
  • Improved cost-warning behavior by showing session warnings in a modal and suppressing historical warnings when resuming.
  • Made thread browsing and resume flows more resilient with recoverable failures and clearer message count headers.
  • Better large tool result previews that clearly explain clipping or truncation, including byte-cap losses and per-line clipping.

Fixed

  • Fixed glob sorting to tolerate missing modifiedat values and character counting in ls and glob output.
  • Fixed request-time working directory binding and marketplace plugin installs to accept bare relative source paths.
  • Fixed invalid partial tool-call patching and updated imputed ToolMessage content in PatchToolCallsMiddleware.
  • Fixed local voice transcription and embedding retries, and ensured local model downloads persist.
  • Fixed binary content in StateBackend.uploadfiles being tagged as base64.
  • Fixed prompt clipboard word deletion behavior and local MCP cache warming to not block the event loop.

August 2026

30 releases: 0.7.2 → 0.7.11

August brought significant stability improvements and new user-facing features across Deep Agents. The month focused on better context management, expanded model support, and improved session handling.

Action needed
  • deepagents-code now requires Python 3.12 or newer.
  • deepagents-cli is deprecated in favor of managed-deepagents.
  • deepagents-talon now requires Python 3.12 or greater.
  • Replaced Gemini 3.6 Flash with Gemini 3.7 Flash in the model switcher.

Highlights

  • Added /context-doctor command for inspecting and troubleshooting context consumption issues.
  • Introduced Python extension support with discovery, configuration, and runtime hosting capabilities.
  • Expanded model support with new options including Meta Muse Spark, DeepSeek V4 variants, and Baseten GLM models.
  • Improved session persistence with support for resuming and reconfiguring ACP sessions.
  • Enhanced diff readability with word-level highlights and added shell command highlighting in chat input.

New

  • Added /context usage report for inspecting context consumption and cache status row for at-a-glance session state.
  • Added /context-doctor command for diagnosing and troubleshooting context issues.
  • Added /summarization-model command and model picker for configuring the summarization model separately.
  • Added tri-state DEEPAGENTSCODEONBOARDING environment variable for code onboarding control.
  • Added support for managing config from remote sources and DEEPAGENTSHOME environment variable.
  • Added warnings before expensive cold-cache turns and trust user-declared endpoints for cold-cache policies.
  • Added resizable chat input by dragging its top border.
  • Added trace metadata attribution for skill invocations and editable trace metadata support.

Improved

  • Hooks v2 is now generally available with support for loading hooks from installed plugins and multiple lifecycle fixes.
  • Auto approval classifier now supports selecting the classifier model and setting a review timeout.
  • HITL rejection reasons are now framed for the model with easier reject-with-feedback discovery.
  • Price catalog now refreshes hourly in the background with Baseten built-in overrides and local fallback support.
  • Improved diff readability with quieter hunks and word-level highlights.
  • Made /offload server-owned and interruptible with better progress reporting.
  • Improved streaming performance for tool-call arguments to run in linear time.
  • Enhanced chat and footer UI behavior with better visibility during rapid typing and improved MCP footer wrapping.

Fixed

  • Fixed exact-file delete target resolution in the SDK using first-match-wins behavior.
  • Fixed leaked turn coroutines and SQLite handles in session management.
  • Fixed Hooks v2 lifecycle issues including session-end teardown bounding and malformed hook resume handling.
  • Fixed recognition of in-flight trace messages and forced-compaction forks by preserving session IDs.
  • Fixed Auto approval gate path expansion handling and tool argument validation errors are now recoverable.
  • Fixed refreshed local context handling after compaction to reduce cache busts.

Summaries are written automatically from the official release notes (full changelog ↗); check the original notes before relying on a detail. Deep Agents: pricing, features and alternatives · All changelogs