v1.5.0 — One Does Not Simply Call an MCP

What's Changed

Features

• add ToolFactory.from_mcp to convert MCP servers into validated tools by @ArtemShatokhin in #453
• enable OpenAPI schema generation for tools by @bonk1t in #446
• add server_url to run_fastapi for better schema generation by @ArtemShatokhin in #465

Fixes and improvements

• fix: correct guardrail streaming persistence and refactor execution modules by @bonk1t in #434
• fix: normalize basetool error output by @bonk1t in #455
• fix: prevent streaming context override mutation by @bonk1t in #457
• improvement: move timeout into a tool input field by @ArtemShatokhin in #456
• improvement: simplified model definition in litellm doc by @ArtemShatokhin in #463

Dependencies

• bump openai-agents to 0.6.0 by @bonk1t in #458

Docs

• add n8n integration docs by @dumitruPuggle in #464
• update n8n integration documentation to include notes on self-h… by @dumitruPuggle in #466

Full Changelog: v1.4.1...v1.5.0

v1.4.1

What's Changed

• fix: package visualization templates by @bonk1t in #454
• docs: link starter template across quick starts by @bonk1t in #443

Full Changelog: v1.4.0...v1.4.1

v1.4.0 Built-in Tools and CLI Improvements

🚀 Features

Built-in Tools & CLI Import

Introduces built-in tools — IPythonInterpreter, PersistentShellTool, and LoadFileAttachment — along with a new import-tool CLI command.
Includes improvements to file handling, agent template generation, and documentation/navigation for built-ins.

• Add built-in tools and CLI import command (#442) by @ArtemShatokhin
  • CLI: import-tool command to list/copy built-ins into a project
  • Docs: new Built-in Tools page with cross-links

Terminal Demo Improvements

Major UX upgrade for the terminal demo (Agency.terminal_demo()) with interactive dropdowns and autocomplete.

• Terminal demo improvements (#432) by @ArtemShatokhin
  • Added keyboard-navigable dropdown for / commands and @agent mentions
  • Improved agent parsing, error handling, and handoff logic
  • Added autocomplete, new key bindings (Tab, Esc, Enter), and refined styling
  • Updated integration tests for all new behaviors

---

🛠 Fixes and Improvements

• Improve IPython tool isolation (#448) by @ArtemShatokhin
• Add working directory as a separate IPython tool input (#452) by @ArtemShatokhin
• Additional improvements: improve agent file handling by skipping subfolders, detecting empty directories, and optimizing vector store creation.

---

📘 Docs

• Added Widget Integration documentation (#427) by @MykhailoShchuka

---

🧑‍💻 New Contributors

• @MykhailoShchuka made their first contribution in #427

---

Full Changelog: v1.3.1 → v1.4.0

v1.3.1

What's Changed

• fix: ensure openapi tools serialize schema payloads by @bonk1t in #430
• fix: add object serialization to visualize function, move serialize() to util by @ArtemShatokhin in #426
• refactor: adopt sdk response models by @bonk1t in #424
• refactor: simplify citation extraction by @bonk1t in #431

Full Changelog: v1.3.0...v1.3.1

v1.3.0 — Multimodal Tool Outputs

Features

• Support multimodal tool outputs, bump the Agents SDK to 0.4.1 by @bonk1t in #383
• Use agency name as a default trace name by @ArtemShatokhin in #404
• Group runs in a single trace by @ArtemShatokhin in #411
• get_response_stream returns run response wrapper by @bonk1t in #400. See "Streaming API update" below for more details.
• Expanded imports from Agents SDK into the framework by @ArtemShatokhin in #402

Improvements & Fixes

• Improved mention parsing in the terminal demo, update show_reasoning default value by @ArtemShatokhin in #403
• fix: streamline vector store ingestion waits by @bonk1t in #423
• fix: propagate run_config trace ids by @ArtemShatokhin in #413
• fix: unblock streaming final futures by @bonk1t in #414
• fix: set callerAgent for hosted tool system messages during agent→agent runs by @ArtemShatokhin in #420

Docs

• docs: update API reference to match Agency and Agent APIs by @ArtemShatokhin #416
• Revise README for clarity and updates by @bonk1t in #422
• Fixed formatting issue in validation doc by @ArtemShatokhin in #412

Streaming API update

• Agency.get_response_stream and Agent.get_response_stream now return a StreamingRunResponse immediately instead of an awaitable coroutine.
• Existing async for iteration keeps working, but calling await on these methods now raises TypeError because they are synchronous.

Updated usage:

stream = agent.get_response_stream(...)
async for event in stream:
...
final_result = await stream.wait_final_result()

Drop the leading await when obtaining the stream. Callers that previously wrote await agent.get_response_stream(...) must adopt the pattern above.

Full Changelog: v1.2.1...v1.3.0

v1.2.1

What's Changed

• fix: support async context in MCP proxy by @bonk1t in #406
• Prepare the release 1.2.1 by @bonk1t in #407

Full Changelog: v1.2.0...v1.2.1

v1.2.0 — FastAPI Capability Metadata, State Isolation, Vector-Store Sync Hardening

Features

• FastAPI integration: provide per-agent capability metadata (tools, reasoning, hosted tools) by @bonk1t in #397
• FastAPI integration: support DRY_RUN env variable so agent metadata can be served without initialization / API keys by @ArtemShatokhin in #398
• handoffs (backwards-compatible): move reminder customization onto Agent.handoff_reminder, add a dedicated examples/handoffs.py, and update communication-flow docs by @ArtemShatokhin in #388 and by @bonk1t in #399

Improvements & Fixes

• fix: isolate agent runtime state per agency by @bonk1t in #396
• fix: isolate send_message pending guard per thread manager by @bonk1t in #394
• fixes: add vector-store file cleanup, timestamp reconciliation, and resilient ID parsing so stale artifacts and OpenAI ID mismatches no longer break sync jobs by @ArtemShatokhin in #393 and @bonk1t in #395
• fix: harden mcp shutdown handling by @bonk1t in #401

Dependencies

• deps: upgrade the OpenAI Agents SDK from 0.2.9 to 0.3.3 (plus pinned transitive updates) to include streaming fixes and other improvements by @bonk1t in #369

Docs

• docs: rename "open-source models" to "third-party models", fix GitHub references by @bonk1t in #391
• docs/examples: expand hybrid communication flow guidance and align tutorials with the new handoff reminder APIs by @ArtemShatokhin in #388

Full Changelog: v1.1.0...v1.2.0

v1.1.0 — Create-agent-template CLI & v0 Migrator; Handoff Reminders + Guardrail Upgrades

Features

• feat(fastapi): auto-generate chat titles from request context and harden guardrail/output_type interplay by @ArtemShatokhin in #362
• cli: add agent template creation workflow for new projects by @ArtemShatokhin in #380
• cli(v0 migration): port settings.json agents into v1 projects by @ArtemShatokhin in #374
• terminal demo: add /resume persistence command by @bonk1t in #340
• terminal demo: add show_reasoning parameter to control reasoning traces display by @bonk1t in #342

Note: some terminal demo improvements were introduced in 1.0.2.

Improvements & Fixes

• guardrails: preserve prior assistant output across retry cycles without run_data by @bonk1t in #365
• guardrails: ensure input wrappers apply regardless of guardrail name by @bonk1t in #370
• handoffs: inject a reminder system message whenever agents transfer control by @ArtemShatokhin in #366
• metadata: surface the running agency-swarm version on the FastAPI metadata endpoint by @bonk1t in #373
• files: reuse existing vector-store directories and skip utility files during ingestion by @ArtemShatokhin in #385 and #382
• cli: tighten error handling, exit codes, and AGENTS.md compliance for migrate-agent flows by @bonk1t in #386
• terminal: fix reference routing for agents with repeating name patterns by @ArtemShatokhin in #363
• fix: add tsx runner support and resolve build failures by @bonk1t in #392

Docs

• docs: remove legacy v0 mentions and polish navigation by @ArtemShatokhin in #371
• docs: refresh MCP demo guidance, agent initialization, and max_tokens usage by @bonk1t in #375
• docs: align BaseTool examples with the async run context pattern by @bonk1t in #384
• docs: add coverage badge and trim outdated Colab reference by @bonk1t in 5792830

Tests

• tests: broaden coverage across tool factory, BaseTool, MCP server, persistence, and FastAPI logging by @ArtemShatokhin in #378
• tests: refactor FastAPI logging middleware integration to run in-process and disable tracing noise by @bonk1t in #379
• tests: stabilize file attachment expectations in integration suite by @ArtemShatokhin in #377

Security

• security: upgrade Next.js dependency to 15.4.7+ to address upstream vulnerability by @bonk1t in aac33f0

Full Changelog: v1.0.2...v1.1.0

v1.0.2

Improvements

• feat(mcp): add persistent MCP manager to maintain connections with MCP servers by @ArtemShatokhin in #355
• feat(terminal): add /resume persistence command; split demo into focused modules by @bonk1t in #340
• feat: add show_reasoning parameter to control reasoning traces display by @bonk1t in #342
• agency: reject global model parameter by @bonk1t in #353
• guardrails: avoid double-wrapping in FastAPI by @ArtemShatokhin in #343
• guardrails: adjust how guardrail messages are added to history by @ArtemShatokhin in #346
• prompts: ensure shared instructions lead agent prompts by @bonk1t in #351
• tools: update BaseTool context usage; add reasoning event warning by @ArtemShatokhin in #352
• messages: add message_origin parameter to system messages by @ArtemShatokhin in #347

Refactors

• refactor(agency): agent execution system for better modularity and maintainability; refactor tests by @bonk1t in #349

Fixes

• fix(mcp): persistent MCP manager driver reuse by @bonk1t in #356
• fix(handoff): incorrect agent assignment for handoff tool call output by @ArtemShatokhin in #341
• fix(ui): launcher chat persistence; strict compact client by @bonk1t in #354

Tests

• tests: verify message_origin assignment by @ArtemShatokhin in #348

Handoff

• improve handoff handling and name parsing logic by @ArtemShatokhin in #360

Full Changelog: v1.0.1...v1.0.2

v1.0.1

What's Changed

Agent API & Defaults

• [backwards-compatible] agents: rename return_input_guardrail_errors -> throw_input_guardrail_error by @bonk1t in #330
• Added default model assignment to agent init by @ArtemShatokhin in #338
• Updated handoff tool to include unedited agent name and recipient_agent field by @ArtemShatokhin in #337

Terminal & UI

• Improve Terminal Demo: Support commands: compact summarize, reset by @bonk1t in #331
• terminal_demo: enable reasoning summaries and render in console by @bonk1t in #335
• Fixed reasoning duplication in terminal demo by @ArtemShatokhin in #336
• Updated handoff name display in terminal demo by @ArtemShatokhin in #332
• ui(console): improve ConsoleEventAdapter rendering by @bonk1t in a775841
• ui(launcher): reuse entry agent sync client in /compact; add unit test to ensure model passthrough and non-OpenAI path by @bonk1t in 434c9dc
• ui/terminal: compact uses OpenAI minimal reasoning when model contains 'gpt'; keep provider string intact; retain ID sanitization; integration test unchanged by @bonk1t in 89b93b3
• fix: enable terminal_demo slash menu with prompt-toolkit dependency by @bonk1t in 9981feb

Streaming & Messaging

• refactor: make streaming event handling non-destructive by @bonk1t in 13840d2
• streaming: add ensure_event_agent_metadata and use in SendMessage to avoid overwriting agent attribution during sub-agent forwarding by @bonk1t in 6c8e023
• feat: add ExtraParams support to SendMessage for clean field customization by @bonk1t in 8356ee6

FastAPI Integration

• fix: FastAPI integration additional_instructions parameter support by @bonk1t in #328

Tests & Stability

• tests: stabilize integration test flakes by @bonk1t in #333
• tests: migrate fin_agency agents from v0.x to v1.x pattern by @bonk1t in d471366
• test: fix ConsoleEventAdapter handoff_agent initialization in test fixture by @bonk1t in 06d97a9

Docs & Examples

• Updated examples and docs by @ArtemShatokhin and @bonk1t in #326 and #327
• Updated multi_agent_workflow example by @ArtemShatokhin in #329
• docs(AGENTS): prioritize running relevant tests first; reserve make ci for final verification by @bonk1t in a7ab748

Other

• Bug fixes and updates by @ArtemShatokhin in #334

Full Changelog: v1.0.0...v1.0.1