v1.6.0

This release focuses on **usage + cost tracking** and **stream cancellation** (FastAPI + terminal demo), with improved **hot reload**, more reliable **event/history handling** (timestamps, orphan cleanup, LiteLLM ID normalization), and docs/test stabilization.

If you’re new to Agency Swarm, here’s what that means:

- **Streaming cancellation**: When you stream a response (token-by-token), you can stop it early—useful when you already have the answer or want to avoid spending extra tokens.
- **Hot reload (terminal demo)**: Like FastAPI, the terminal demo now auto-restarts on local .py or .md file changes, so you can iterate faster.
- **Usage + cost tracking**: FastAPI responses and the terminal demo now include token totals and an **estimated** USD cost (multi-agent runs included). We use the real model prices, including models supported by LiteLLM.
- **More reliable history**: Messages keep the timestamp from when they were emitted, orphaned tool calls/outputs are removed, and LiteLLM placeholder IDs are normalized. 
---

## Features
* **Add Token Usage + Cost Tracking** (FastAPI + terminal demo; multi-agent aware) by @ArtemShatokhin in https://github.com/VRSEN/agency-swarm/pull/489
  - **What you get**: A `usage` summary with request count, token breakdown, and estimated cost.
  - **Where you’ll see it**: Returned by FastAPI endpoints and tracked in the terminal demo (use `/cost`, and it’s also printed on exit).
  - **Multi-agent aware**: Includes tokens/cost from the main agent **and** any sub-agent calls made during the run.
* **Add Stream Cancellation support** for FastAPI and terminal demo hot reload by @ArtemShatokhin in https://github.com/VRSEN/agency-swarm/pull/469
  - **FastAPI streaming**: The stream emits a `run_id` early; clients can cancel an in-flight run via a cancel endpoint. If the client disconnects, the run is cancelled automatically.
  - **Cancel modes**: `immediate` (stop right away) and `after_turn` (finish the current turn, then stop).
  - **Terminal demo hot reload**: Watches for `.py` and `.md` changes and restarts automatically during local development.
* **Add Cancel Feature to the Terminal Demo** by @ArtemShatokhin in https://github.com/VRSEN/agency-swarm/pull/474
  - **How to use it**: Press `ESC` during streaming to cancel the current response.
  - **Cleaner history after cancel**: The demo filters out duplicate/orphaned tool call messages so the saved chat stays valid and replayable.
 
---

## Improvements
* Improve Terminal Tool Formatting by @ArtemShatokhin in https://github.com/VRSEN/agency-swarm/pull/471
* Capture and assign timestamps at event emission time by @ArtemShatokhin in https://github.com/VRSEN/agency-swarm/pull/485
  - **What changed**: Each event/message now gets its timestamp when it’s emitted during streaming (not later during persistence).
  - **Why it matters**: Sorting and replaying history is more consistent across streaming, saved threads, and UIs.
  - **Tool timelines**: Hosted tool result preservation messages inherit the tool call’s timestamp for more accurate “when did this happen?” debugging.
  - **Orphan cleanup**: Before saving history, the framework drops orphaned tool calls/outputs (e.g. a tool call without its matching output) to avoid replay errors.
* Add user_context forwarding to FastAPI endpoints by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/470
* Added include_search_results assignment to automatically created tools by @ArtemShatokhin in https://github.com/VRSEN/agency-swarm/pull/468
* Add nest asyncio patch to IPython tool to simplify async function execution by @ArtemShatokhin in https://github.com/VRSEN/agency-swarm/pull/494

---

## Fixes
* LiteLLM fake id handling by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/479
  - **Problem**: Some LiteLLM / Chat Completions streams reuse a placeholder id (`__fake_id__`) across many output items, which breaks consumers that key by item id.
  - **Fix**: Placeholder ids are rewritten into stable per-item ids (tool calls prefer `call_id`), so deduplication and message linking behave predictably.
* fix: normalize LiteLLM placeholder ids by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/491
* fix: normalize agent template names and harden file cleanup by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/480
* Updated mcp error handling to match default function tool behavior by @ArtemShatokhin in https://github.com/VRSEN/agency-swarm/pull/487
* Fix copilot demo packaging by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/476
* fix: restore copilot demo streaming by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/484
* fix: make sync APIs safe inside running event loop by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/496

---

## Refactors / Chores
* refactor: enforce codebase consistency across imports, types, and structure by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/483
* Refactor: Consolidate File Utilities and Cleanup Imports by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/482
* set default truncation="auto" and update openai-agents to 0.6.2 by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/475
* chore: update default model to gpt-5.1 by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/477
* chore: deprecate agent send_message_tool_class by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/472
* Update model references to gpt-5.2 by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/495

---

## Documentation
* Improve docs by @VRSEN in https://github.com/VRSEN/agency-swarm/pull/467
* updated pricing section with new plans and credits system by @MykhailoShchuka in https://github.com/VRSEN/agency-swarm/pull/486

---

## Tests

These test changes focus on **stability** and **determinism** to reduce intermittent failures in CI.

* Fix context sharing integration test determinism by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/481
* Tests: stabilization and fixes by @bonk1t in https://github.com/VRSEN/agency-swarm/pull/488

---

**Full Changelog**: https://github.com/VRSEN/agency-swarm/compare/v1.5.0...v1.6.0