---
title: Changelog | Lightcone
description: API and SDK changes, breaking changes, and our deprecation policy.
---

API-, SDK-, and documentation-relevant changes, newest first. Breaking changes and deprecations are announced here before they take effect. For the full product changelog (dashboard, chat, Canvas, Slack, and platform updates), see [tzafon.ai/changelog](https://www.tzafon.ai/changelog).

## July 2026

**Run Northstar locally on a Mac.** Northstar CUA Fast 1.6 is now available as an MLX 4-bit quantization ([Hugging Face](https://huggingface.co/Tzafon/Northstar-CUA-Fast-1.6-MLX-4bit), Apache 2.0), pairing with the new [MacControlKit](https://github.com/tzafon/MacControlKit) Swift package (Apache 2.0) for on-device screen control. Together they let you build a computer-use agent with no API key, no network, and no cloud computer. See [Run Northstar locally on a Mac](/guides/local-mac-agent/index.md).

**Continuous learning (preview).** Deploy a model that learns from your corrections. Because Lightcone is your inference endpoint, corrective turns in your traffic are captured automatically and folded into a nightly, eval-gated checkpoint by self-distillation, metered as compute units (forward 1 CU, backward 2 CU per 1k tokens). Behind a per-org feature flag; see [Continuous learning](/guides/continuous-learning/index.md). New: `tzafon deploy`, `client.corrections.create`, `client.learning.status`, `client.learning.checkpoints` (+ rollback), and the `X-Lightcone-Training` header.

**Documentation overhaul.**

- New guides: [CLI](/guides/cli/index.md), [Observability](/guides/observability/index.md), [Logins and sessions](/guides/logins-and-sessions/index.md), [Running in production](/guides/production/index.md), [Security and data handling](/guides/security/index.md), [Errors and status codes](/guides/errors/index.md), and [Limits and behaviors](/guides/limits-and-behaviors/index.md), plus a [cookbook](/cookbook/wrap-a-legacy-app-in-an-api/index.md) of production patterns.
- Corrected the models table and the coordinate handling in the [computer-use loop](/guides/cua-protocol/index.md) example (see the April 8 breaking change below).

## June 2026

**Price drop (June 26).** `northstar-cua-fast` input dropped to $0.50/M (was $1.00) and output to $1.50/M (was $5.00), a 50–70% reduction. See [Pricing](/guides/pricing/index.md).

**Tasks API additions** (week of June 8). All new fields are optional and additive; no action required for existing integrations:

- `computer_id`: attach a task to an existing live computer; `on_missing_computer: "restore" | "create_new" | "fail"` controls what happens if it’s gone.
- `context`: seed a new task with recent conversation turns; `thread_id`: group tasks belonging to the same chat.
- `start_url`, `save_session`, `keep_alive`, `max_duration_seconds`, `metadata`, `idempotency_key`: explicit task controls, plus task cancellation and deadline events.
- Computer responses now include `environment_id` when a live computer was created from a saved environment.
- Task SSE streams are resumable: reconnect with the `Last-Event-ID` header and missed events replay. See [Tasks](/guides/tasks#resuming-a-stream/index.md).

**Chat Completions output-token ceiling** (week of June 1). A server-side maximum of 4096 output tokens now applies. Callers already requesting `max_tokens <= 4096` are unaffected.

**Computer lifetime fields renamed.** `timeout_seconds` and `auto_kill` on computer creation are deprecated in favor of `max_lifetime_seconds` and `idle_timeout_enabled`. The deprecated fields still work; requests using them receive `Deprecation` and `Sunset` response headers indicating when support ends.

```
# Before
computer = client.computer.create(kind="browser", timeout_seconds=3600, auto_kill=False)


# After
computer = client.computer.create(kind="browser", max_lifetime_seconds=3600, idle_timeout_enabled=False)
```

```
// Before
const computer = await client.computers.create({ kind: "browser", timeout_seconds: 3600, auto_kill: false });


// After
const computer = await client.computers.create({ kind: "browser", max_lifetime_seconds: 3600, idle_timeout_enabled: false });
```

## April 2026

**April 27.** `tzafon.northstar-medium-alpha` is available in the model picker and via `GET /v1/models`. Usage and billing records now group usage by stable model family while retaining the exact `model_id` for auditability.

**April 20.** TypeScript SDK 0.14.0 published, backward-compatible.

**April 13.** TypeScript SDK 0.13.0 with refreshed `computers`, `computers.exec`, `computers.tabs`, and `responses` resources. The OpenAPI/Swagger reference now matches the v2 API shapes; if you generate your own client from the spec, regenerate it.

**April 8. Breaking: coordinates are no longer pre-scaled** (Python SDK 2.35.0, TypeScript SDK 0.8). The API now returns coordinates in raw **0–999 model space**. Previously, coordinates were scaled to pixels matching your `display_width`/`display_height` before being returned. Denormalize in your code:

```
def to_px(coord, dim):
    return int(coord / 1000 * dim)


x = to_px(action.x, display_width)
y = to_px(action.y, display_height)
```

This affects all `computer_call` actions: click, double-click, right-click, scroll, drag, and any coordinate-based input. See [Coordinates](/guides/coordinates/index.md) and the updated [computer-use loop](/guides/cua-protocol/index.md).

Also April 8: new model `tzafon.northstar-cua-fast-1.2` at the same pricing as `northstar-cua-fast`.

## March 2026

**March 12. Responses API.**

- Multi-turn conversations via `previous_response_id`, with no history management on your end.
- Persistent responses: every response is stored and retrievable via `GET /v1/responses/{id}`; pass `store: false` to opt out (responses created with `store: false` can’t be referenced by `previous_response_id`).
- Computer use via the API, with OpenAI drop-in compatibility: use the OpenAI SDK unchanged with a Lightcone `base_url`.

**March 9. Faster session resume.** Saved-environment snapshots restore faster, including across infrastructure moves.

## Deprecation policy

- Deprecated fields and endpoints keep working through the sunset date announced in the `Deprecation` and `Sunset` response headers, and are listed on this page.
- Pin your model versions (`tzafon.northstar-cua-fast-1.6`, not an unversioned alias) and SDK versions in production; upgrade deliberately rather than tracking latest.
- APIs marked beta can change with notice via this page.

Spotted something wrong, or want a change announced differently? Email <support@tzafon.ai>.

## Next steps

- [**Full product changelog**](https://www.tzafon.ai/changelog): weekly updates across the whole platform
- [**Running in production**](/guides/production/index.md): pinning versions and handling deprecations safely
- [**Errors and status codes**](/guides/errors/index.md): how the API reports failures