> ## Documentation Index > Fetch the complete documentation index at: https://docs.devin.ai/llms.txt > Use this file to discover all available pages before exploring further. # Devin SDK changelog > Release notes for each Devin SDK beta: @cognition-ai/sdk, ai-sdk, cloudflare-agents and harness-devin, with links to the published versions on npm. The packages release together on the `beta` dist-tag and should be kept on the same version. Published versions are listed on npm: [`@cognition-ai/sdk`](https://www.npmjs.com/package/@cognition-ai/sdk?activeTab=versions), [`@cognition-ai/ai-sdk`](https://www.npmjs.com/package/@cognition-ai/ai-sdk?activeTab=versions), [`@cognition-ai/cloudflare-agents`](https://www.npmjs.com/package/@cognition-ai/cloudflare-agents?activeTab=versions), [`@cognition-ai/harness-devin`](https://www.npmjs.com/package/@cognition-ai/harness-devin?activeTab=versions). The [examples repository](https://github.com/COG-GTM/devin-sdk-examples) is tagged `v` for each release. **0.0.1-beta.7** September 29, 2026 Model discovery for local sessions. Install with `npm install @cognition-ai/sdk@beta`; all four packages are at `0.0.1-beta.7`. **`@cognition-ai/sdk`** * New `LocalSession.models()` returns the models and Fusion pairings the CLI accepts for the session (`options`, each with an `id`, display `name` and `supportsImages` when the CLI reports it) and the model in effect (`current`). It reads the `model` config option the CLI already returns on `session/new`, `session/load` and `session/set_config_option`, so it tracks the CLI version and account without a separate call, and replaces `devin models list` as the way to find valid `Fusion({ leader, sidekick })` inputs. See [Models and Fusion](https://docs.devin.ai/sdk/guides/local-sessions.md#models-and-fusion). * New `session.configOptions` on every session exposes the raw ACP config options the agent last reported, typed as `SessionConfigOption[]` (with `SessionConfigSelectOption` values). * `setModel` rejects a model or pairing the CLI does not advertise with a new `ModelRejectedError` carrying the id (`model`) and the CLI's explanation (`reason`), and leaves the current model in place. Previously the call failed with a bare `Invalid params` JSON-RPC error whose reason was only in `error.data`. `SessionStartupError` from a `createSession({ model })` that fails the same way now has the `ModelRejectedError` as its `cause`. `setModel` also refreshes `models().current` from the CLI's response. **`@cognition-ai/ai-sdk`**, **`@cognition-ai/cloudflare-agents`**, **`@cognition-ai/harness-devin`**: no changes beyond the SDK dependency. **Examples**: no code changes; the [examples repository](https://github.com/COG-GTM/devin-sdk-examples) is at `v0.0.1-beta.7`. Published packages: [`@cognition-ai/sdk`](https://www.npmjs.com/package/@cognition-ai/sdk/v/0.0.1-beta.7), [`@cognition-ai/ai-sdk`](https://www.npmjs.com/package/@cognition-ai/ai-sdk/v/0.0.1-beta.7), [`@cognition-ai/cloudflare-agents`](https://www.npmjs.com/package/@cognition-ai/cloudflare-agents/v/0.0.1-beta.7), [`@cognition-ai/harness-devin`](https://www.npmjs.com/package/@cognition-ai/harness-devin/v/0.0.1-beta.7). **0.0.1-beta.6** September 22, 2026 ACP version selection. Install with `npm install @cognition-ai/sdk@beta`; all four packages are at `0.0.1-beta.6`. **`@cognition-ai/sdk`** * New `acpVersion` option on `createDevin`, `CloudDevin.connect` and `LocalDevin.start`, typed as `AcpProtocolVersion` (`1 | 2`). Pass `acpVersion: 1` to require [ACP v1](https://agentclientprotocol.com/protocol/initialization) on either transport; the SDK then sends only v1 `initialize` fields and rejects an agent that selects v2. The default, `acpVersion: 2`, is unchanged: it offers v2 and still accepts an agent that selects v1. The selected version is exposed as `devin.protocolVersion`. See [Choosing the ACP version](https://docs.devin.ai/sdk/how-it-works.md#choosing-the-acp-version). * Session methods follow the negotiated version, so application code does not change: `loadSession` uses `session/load` on v1 and `session/resume` on v2, and `await turn` completes from the prompt result on v1 and the idle `state_update` on v2. `turn_state` events and the cloud `replay: "tail"` / `"none"` load options remain v2-only. * Fixed: a local connection whose ACP negotiation was rejected kept its stdio listeners and JSON-RPC responders. `LocalDevin.start` and `LocalDevin.connect` now close the connection before rethrowing, and `CloudDevin.connect` closes its socket on handshake errors. Custom `LocalDevin.connect` streams should expose `off()` alongside `on()` so the SDK can detach its listeners; streams with only `on()` still work, but keep inert listeners attached. **`@cognition-ai/ai-sdk`**, **`@cognition-ai/cloudflare-agents`**, **`@cognition-ai/harness-devin`**: no changes beyond the SDK dependency. **Examples**: the [quickstart](https://docs.devin.ai/sdk/examples/quickstart.md) programs accept `--acp-v1`. The other examples need no code changes; the [examples repository](https://github.com/COG-GTM/devin-sdk-examples) is at `v0.0.1-beta.6`. Published packages: [`@cognition-ai/sdk`](https://www.npmjs.com/package/@cognition-ai/sdk/v/0.0.1-beta.6), [`@cognition-ai/ai-sdk`](https://www.npmjs.com/package/@cognition-ai/ai-sdk/v/0.0.1-beta.6), [`@cognition-ai/cloudflare-agents`](https://www.npmjs.com/package/@cognition-ai/cloudflare-agents/v/0.0.1-beta.6), [`@cognition-ai/harness-devin`](https://www.npmjs.com/package/@cognition-ai/harness-devin/v/0.0.1-beta.6). **0.0.1-beta.5** September 22, 2026 Install with `npm install @cognition-ai/sdk@beta`; all four packages are at `0.0.1-beta.5`. **Fix: session MCP servers** * `@cognition-ai/sdk` accepts `mcpServers` on `createSession`, `loadSession`, and `attach` for local and cloud sessions. These methods previously sent an empty MCP server list. * The public `McpServer` type describes stdio, HTTP, and SSE configurations. The SDK adds `type: "stdio"` to untagged stdio servers for ACP v2 without changing caller input. * The SDK and `@cognition-ai/harness-devin` update their CLI dependency to `3000.11.1`. This CLI build registers the MCP servers supplied through ACP. See [local MCP configuration](https://docs.devin.ai/sdk/guides/local-sessions.md#mcp-servers) and [cloud MCP configuration](https://docs.devin.ai/sdk/guides/cloud-sessions.md#mcp-servers). Cloud tool availability depends on the ACP endpoint. Published packages: [`@cognition-ai/sdk`](https://www.npmjs.com/package/@cognition-ai/sdk/v/0.0.1-beta.5), [`@cognition-ai/ai-sdk`](https://www.npmjs.com/package/@cognition-ai/ai-sdk/v/0.0.1-beta.5), [`@cognition-ai/cloudflare-agents`](https://www.npmjs.com/package/@cognition-ai/cloudflare-agents/v/0.0.1-beta.5), [`@cognition-ai/harness-devin`](https://www.npmjs.com/package/@cognition-ai/harness-devin/v/0.0.1-beta.5). **0.0.1-beta.4** September 19, 2026 Client-level tracing and a public API cleanup. Install with `npm install @cognition-ai/sdk@beta`; every package is at `0.0.1-beta.4`. **`@cognition-ai/sdk`** * Tracing is now set once on the client: pass `tracing: traceSessions({ tracer })` from `@cognition-ai/sdk/tracing` to `createDevin`, `LocalDevin.start`, `LocalDevin.connect` or `CloudDevin.connect`. Every session the client creates, loads, attaches or launches is traced, and prompts are recorded from every prompt method (`send`, `run`, `stream`, `streamUpdates`, `postMessage`), so `recordPrompt` is no longer needed. Cloud messages sent from other clients, such as the web app, are traced as their own turns. History replayed on load or attach is not exported again. A session can add metadata and tags with its own `tracing` option, or opt out with `tracing: false`. `traceSession` keeps its API for tracing a single session. See [Tracing](https://docs.devin.ai/sdk/guides/tracing.md). * Fixed: a cloud turn's final reply, which can arrive after the turn goes idle, was added to the next turn's trace output. * Fixed: when the agent connection drops, sessions now get the same `ConnectionClosedError` as pending requests, with the specific reason (for example `Connection to the agent closed: read ECONNRESET`). * `OutputNotification`, `ShowModalNotification`, `RevertStepInfo`, `RevertStepsUpdatedNotification` and `RevertHistoryRewoundNotification` are now generated from the ACP schema. `RevertStepInfo` gains `stepId`, its optional id fields and `firstRemovedUserMessageId` accept `null`, and `OutputNotification.level` is optional. * New `LocalDevin.spawn(cliPath, options?, env?)` starts a given CLI binary with the given environment, without `start()`'s API key and state directory handling. * New `toolCallText(call)` and `isToolCallInputFinal(call)` helpers. * `bundledCliPath` and `cliPackageName` are no longer exported. Use `resolveCliPath()`. **`@cognition-ai/ai-sdk`** * The `devin-status` and `devin-lifecycle` data part types are derived from the SDK's `StatusEvent` and `LifecycleEvent`. **`@cognition-ai/harness-devin`** * Fixed: a tool call first announced by a permission request now streams like any other tool call, and keeps `nativeName` for mapped tools (`exec` shown as `bash`, `find_file_by_name` shown as `glob`). * The bridge starts the CLI with `LocalDevin.spawn`, so spawn failures get the SDK's clearer error messages. **`@cognition-ai/cloudflare-agents`**: no changes beyond the SDK dependency. **Examples**: the [examples repository](https://github.com/COG-GTM/devin-sdk-examples) is at `v0.0.1-beta.4`. The examples need no code changes for this release. **0.0.1-beta.3** September 18, 2026 Tracing and Fusion models. Install with `npm install @cognition-ai/sdk@beta`; every package is at `0.0.1-beta.3`. **`@cognition-ai/sdk`** * New `traceSession(session)` at `@cognition-ai/sdk/tracing` records a session as OpenTelemetry spans: one `agent` span per turn, one `generation` span per model request (tokens, cache reads and writes, request id, time to first token, cost when the agent reports it) and one `tool` span per tool call. It uses `@opentelemetry/api` (an optional peer dependency), so your application configures the provider and exporter, for example Langfuse's `LangfuseSpanProcessor`. See [Tracing](https://docs.devin.ai/sdk/guides/tracing.md). * New `Fusion({ leader, sidekick })` for local sessions: `createSession({ model: Fusion({ leader: "claude-opus-5-max", sidekick: "swe-2-high" }) })`, and the same on `LocalDevin.start` and `session.setModel`. Plain model ids such as `"fusion-adaptive"` still work, and the CLI rejects pairings it doesn't list. See [Models and Fusion](https://docs.devin.ai/sdk/guides/local-sessions.md#models-and-fusion). * The generated Cognition ACP schema is refreshed from the CLI. The CLI no longer sends the `restart` stop cause, so `AgentStopCause.Restart` and `AgentStoppedNotification.restartReason` are removed; code that checks `cause === "restart"` can drop that branch. **`@cognition-ai/ai-sdk`**, **`@cognition-ai/cloudflare-agents`**, **`@cognition-ai/harness-devin`**: no changes beyond the SDK dependency. **0.0.1-beta.2** September 14, 2026 Two new packages, cloud sessions on edge runtimes, and cancellable turns. Install with `npm install @cognition-ai/sdk@beta`; every package is at `0.0.1-beta.2`. **New: `@cognition-ai/ai-sdk`** — Devin session events as [AI SDK UI message streams](https://ai-sdk.dev/docs/ai-sdk-ui/stream-protocol), so a `useChat` route is `createUIMessageStreamResponse({ stream: toUIMessageStream(session.stream(toPromptInput(messages))) })`. Messages and thoughts become text and reasoning parts, tool calls `dynamic-tool` parts carrying the SDK's `ToolCallDetail`, plans and pull requests `data-devin-*` parts. Also `toUIMessages(replay)` for reloading history, `endWhenIdle` for `resumeStream()`, `devinSessionMetadata()`, and `ToolApprovals` for answering permission requests as AI SDK tool approvals. Runs on every runtime the SDK does. See [AI SDK UI](https://docs.devin.ai/sdk/ai-sdk/overview.md). **New: `@cognition-ai/cloudflare-agents`** — a Devin cloud session behind a [Cloudflare Agents](https://developers.cloudflare.com/agents/) `AIChatAgent`: `export class DevinChat extends DevinChatAgent {}` gives one Devin session per chat Durable Object, with one queued turn per message, stop, permission requests as tool approvals, `startOver()`, `importSession(id)` to continue a session from the Devin app, and recovery across Durable Object restarts. Agent state carries the session id and URL, status, activity, plan and pull requests. See [Cloudflare Agents](https://docs.devin.ai/sdk/cloudflare-agents/overview.md) and the [Cloudflare Agents chat example](https://docs.devin.ai/sdk/examples/cloudflare-agents.md). **`@cognition-ai/sdk`** * Cloud sessions run on edge runtimes: Cloudflare Workers and Deno 2.5+. The ACP socket uses the runtime's built-in `WebSocket` (a `fetch` upgrade on Workers) and the `ws` dependency is gone; runtimes whose `WebSocket` can't send headers (browsers, Vercel Edge, older Deno) get a `DevinError` from `connect()`. `CloudDevin.attachTo()` now takes a WHATWG-style socket. See [Where it runs](https://docs.devin.ai/sdk/guides/cloud-sessions.md#where-it-runs). * `session.stream()`, `streamUpdates()`, `send()`, `postMessage()` and `run()` accept `{ signal }`. Aborting cancels the Devin turn right away (`stopReason: "cancelled"`); pass a route's `request.signal` so a client stop cancels the turn. See [Cancelling a turn](https://docs.devin.ai/sdk/guides/cloud-sessions.md#cancelling-a-turn). * `ToolCall.detail` gains `computer_use` — Devin's browser and desktop automation on the cloud, with typed `actions` — which was `other` before. See [Streaming events](https://docs.devin.ai/sdk/guides/streaming-events.md#tool-calls-the-same-on-both-agents). * A structured `run()` whose turn stops without finishing (cancelled, refusal, max tokens) resolves with that `stopReason` instead of rejecting with "The turn produced no JSON to validate"; reading `outcome.output` on such an outcome throws. See [Structured output](https://docs.devin.ai/sdk/guides/launch-and-structured-output.md#structured-output). **`@cognition-ai/ai-sdk`** (first release; fixes found while building the Cloudflare example) * `toUIMessageStream` no longer opens a second reasoning part when the cloud restates a finished thought with only whitespace changes, which showed every thought twice. * `ToolApprovals.respond()` also answers denials stored as `output-denied`, as Cloudflare's `AIChatAgent` records them. **`@cognition-ai/cloudflare-agents`** (first release) * A turn drops updates for tool calls that belong to an earlier message: stopping a turn does not stop the command Devin was running, and its late completion used to fold the stopped reply into the next one. **`@cognition-ai/harness-devin`** — no changes beyond the SDK dependency. **Examples** — the [examples repository](https://github.com/COG-GTM/devin-sdk-examples) is at `v0.0.1-beta.2` with a new [Cloudflare Agents chat](https://docs.devin.ai/sdk/examples/cloudflare-agents.md); the quickstart prints `computer_use` tool calls; session-board no longer needs `ws`. See [which examples need beta.2](https://docs.devin.ai/sdk/examples/overview.md#running-any-of-them). **0.0.1-beta.1** September 11, 2026 The first public beta of `@cognition-ai/sdk` and `@cognition-ai/harness-devin`. Install with `npm install @cognition-ai/sdk@beta`; see [Quickstart](https://docs.devin.ai/sdk/quickstart.md). **`@cognition-ai/sdk`** * `createDevin()` connects to the cloud unless `cwd` is passed; nothing else in the environment picks the mode. Local sessions require an API key (`apiKey` or `DEVIN_API_KEY`) and fail before spawning the CLI without one. See [How it works](https://docs.devin.ai/sdk/how-it-works.md). * Local sessions run the bundled CLI with their own config, session store and cache under `~/.devin-sdk` (`stateDir`), isolated from an interactive Devin CLI on the same machine. The bundled CLI platform packages are pinned to `3000.6.11`. * Cloud sessions can be scoped to repositories: `createSession({ repos })`, or `session.setRepos()` before the first prompt. Repositories the organization cannot access reject with a `DevinError`. * `launchSession(prompt, { session, turn })` on cloud and local clients returns `{ session, turn }` once the first prompt is accepted. See [Launch and structured output](https://docs.devin.ai/sdk/guides/launch-and-structured-output.md). * Session-wide events: `session.events()` and `session.updates()` deliver every live update for a session — including turns started from the web app or another process — as typed `SessionEvent`s (`status`, `activity`, `lifecycle`, `typing`, `pull_request`, …). `session.meta` exposes the latest session snapshot, and `listSessions()` results carry typed `_meta`. See [Watching sessions](https://docs.devin.ai/sdk/guides/watching-sessions.md). * `ToolCall.detail` normalizes what each tool call is and what it was given (`exec`, `read`, `write`, `edit`, `mcp`, `permission_request`, `ask_user_question`, …) across local and cloud agents. * `attach()` is available on every client; `LoadedSession` is the shared result type and every session option type extends `SessionOptions`. The ACP `state_update` surfaces as a typed `turn_state` event. * Structured output parsing no longer fails on ` ```json ` blocks whose string values contain fenced code, and `thought_delta` events no longer repeat reasoning already streamed. * The `CognitionAcp` escape hatch exports every Cognition ACP method constant, params/response type and error code, for `session.extRequest()` / `devin.extRequest()`. **`@cognition-ai/harness-devin`** * `createDevin({ baseUrl })` (default `DEVIN_API_URL`) selects the Devin deployment the in-sandbox CLI talks to. * Setup phases are reported as `info` diagnostics (`devin.bridge.attach|spawn|ready`, `devin.cli`, `devin.session`, `devin.session.ready`, `devin.prompt`) so hosts can show progress before the first token. See [Diagnostics](https://docs.devin.ai/sdk/harness/diagnostics.md). * The bridge holds back a `tool-call` part until the CLI has finished streaming the call's input, fixing `AI_InvalidToolInputError` on builtin tool calls. * Aborting a turn (`abortSignal`) leaves the session cleanly promptable, and a parked bridge that cannot be reattached is reported as a `warn` diagnostic and replaced instead of colliding on the port. * The sandbox bootstrap assets are embedded in the module, so the adapter works when a bundler (a Next.js server bundle, a Vercel deployment) inlines it. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.