Change Logs

Change logs for the Concurrence API, Agent Forge, Web Platform, and SDK ecosystem.

Find product updates for the Platform and Classic APIs, Scribe, Developer Console, SDKs, and Agent Forge. Each entry explains the change and any action needed for an existing integration.

Package entries use published release versions and dates. Unnumbered entries follow product announcements or source changes; availability depends on the deployment and setup requirements in the linked guide. Older entries retain the behavior of their time.

October 2026

• Hosts and SDK: the *.platform.amigo.ai hosts no longer resolve; use the concurrence.com hosts. Platform SDK 0.113.1 defaults to them and adds identityBaseUrl; 0.114.1 yields the new state_transition and state stream events.

• Platform: streamed text turns end with state_transition and state frames before done; a long tool turn keeps waiting while the agent works on it; a closed conversation's transcript stays readable; a text conversation keeps its history after more than 24 hours idle in the US region; a text tool call that returns an error, such as a vendor's 4xx or 5xx, counts as failed; conversation text events moved to the conversation-scoped event stream; runs list iMessage and WhatsApp, and channel=text is removed; the gap-scanner settings operations are removed.

• Voice and text: a verified caller's record reads stay on their own record or a household member's that names them; every call opens with an AI and recording notice; a self-harm message on text gets the crisis-line script; every text reply passes a reply check before it is sent; when nothing can connect a caller to a person, the agent tells them how to reach the team; gpt_realtime gets crisis guidance that asks for the line in the first reply to any sign, hints included, and silence check-ins with hangup.

• Platform: integration endpoints declare their writes; raw SQL reads only the workspace's own customer data; skill result schemas, custom ai_query metrics, and production eval metric keys are validated on save; voice quality metrics count voice calls only.

• Voice: patient context loads only after the caller's name and date of birth match one record; dynamic transfers dial only approved_destinations; calls with no TTS setting speak ElevenLabs eleven_v4_turbo; Sonic 3 and 3.5 pins speak Sonic 3.6; a crisis resource, a spoken-reply check, and a recognizer failover are on for every service.

• Voice: the observer and test-call WebSockets take credentials only in Sec-WebSocket-Protocol; a workspace can hold 5 test calls at once; the agent uses the caller's timezone, with a new workspace timezone setting.

• Testing: simulations, test caller numbers, and test credentials run tools in simulation mode; simulation pass rates leave out grading errors; simulation run and case lists page and filter on the server; judge verdicts drop score_label.

• Platform: the connector runner is retired, along with data-source sync, the gap-scanner preview and scan, and sync-health fields; runs add search and a dormant status, and voice runs use the call start time; conversations add a paged turns read; the event stream can scope to one conversation; 422 errors no longer echo submitted values; integration URLs must be public HTTPS and redirects are not followed.

• Analytics: quality metrics judge transcripts; the metric list returns one latest row per series and pages with continuation_token; Platform Claude calls run on the 5.5 models.

• Platform: a model rejection fails a text turn at once with a non-retryable 502; overlapping turns get distinct turn_id values; engage tool turns on GPT-5.4 and later run at reasoning_effort none, and saving a higher engage effort for those models returns 422.

• Platform: integration endpoint input_schema follows the tool-schema subset; function and data-query invoke argument errors return 422 instead of 503; the world entity list works without entity_type; simulation recommendations return suggestions again; the Insights Agent stays on one model.

• Voice: retired Claude pins on skills and model preferences run on the 5.5 models; realtime and realtime transcription model allowlists drop retired ids with 422; the service tts_model field is removed; gpt_realtime calls record voice minutes and call count.

• Platform: streamed turns and the session WebSocket send keepalive pings every 15 seconds; the session WebSocket stays open across turns; run lookup by run_id works for conversation runs of any age; the FHIR bundle builder is removed.

• Platform: a close ends every in-flight text turn, and streamed turns end with typed terminal frames.

• Voice: ElevenLabs defaults to eleven_v4_turbo, retired ElevenLabs pins move to it, and only stability applies on it; OpenAI speech recognition uses gpt-transcribe.

• Voice: retired Cartesia models speak Sonic 3.6; an ElevenLabs barge-in trims history to what the caller heard; live call context validation errors no longer echo submitted values.

• Voice: a trusted backend can set verified context on a live call for context-bound tools, and voice tools bound to a declared but unset key refuse to run until it is set. Sonic 3.6 is the default Cartesia model. On the realtime runtime, bindings resolve across the whole graph and an interrupted transfer still runs.

• Voice: the direct Voice Agent session-event route no longer accepts workspace API keys; use the Platform session injection operation. The /test-call WebSocket always runs in the credential's workspace.

• Platform: closing a conversation ends its streamed turn with a non-retryable error frame; outbound call idempotency is claimed before dialing; runs filter by service; workspace queries pass colons inside string literals through as text.

• Platform: streamed text turns emit token events on existing conversations. Render them as a preview and commit the final message.

• Channels: email use cases select an inbound_mode, replacing accepts_cold_inbound. The SMS registered-content check reads recent thread context.

• Scribe: writeback status fields, carried values on note reads, provider edits that take precedence over carried values, and session create requires timezone.

• Console: the All runs table filters by service; magic-link sign-in waits for a click; the connector pages are removed; retried Playground turns run once.

Browse the dated API updates and Console updates.

September 2026

• Platform: context aliases, companion-skill bindings, service-scoped memory, intake-source deletion, and intake document tags.

• Channels: voice forwarding allowlists, iMessage send and opt-out controls, and participant audio handling.

• Scribe: structured note edits with version checks and retry guidance during maintenance.

• Console and testing: Evaluate navigation, managed channel request forms, reusable voice-test personas, clearer run details, a Beta Usage page, conversation context fields in the text Playground, and voice settings limited to Cartesia and ElevenLabs.

Browse the dated API updates and Console and voice-testing updates. For migration steps, see Current Upgrade Guidance.

September 19, 2026: Concurrence Rebrand

Amigo is now Concurrence. The documentation uses the new identity at docs.concurrence.com; existing page paths and bookmarks continue to work.

Keep using the API endpoints, credentials, package names, imports, environment variables, and wire identifiers specified by your integration. The name change does not rename those contracts. See Rebrand and Compatibility.

Maintaining an Integration

Start with Current Upgrade Guidance to identify changes that affect your API, package, and workflow. Follow the Developer Guide for current setup and migration steps, and use the API Reference for operation schemas. The API and web changelogs link to older releases in their archives.

Current SDK Packages

Package registry snapshot checked on October 15, 2026 (UTC). Recheck the linked registries when selecting an upgrade; SDK source can include changes that are not yet in a published package.

SDK	Package	Published version
Platform TypeScript SDK	@amigo-ai/platform-sdk	0.114.1
Classic TypeScript SDK	@amigo-ai/sdk	2.1.0
Classic Python SDK	amigo-sdk	2.0.1
Scribe TypeScript SDK	@concurrence-hq/scribe-typescript-sdk	1.5.1

The npm latest tag for @amigo-ai/sdk points to 2.1.0; the 1.1.x versions remain deprecated. Review the September compatibility changes, pin the version you have tested, and keep Classic packages separate from @amigo-ai/platform-sdk.

Platform 0.114.1 is published on npm. Since 0.113.1 the package defaults to https://platform.api-us.concurrence.com for REST and https://identity.api-us.concurrence.com for client.tokens and device-code login, because the *.platform.amigo.ai hosts no longer resolve. A client that sets baseUrl sends client.tokens requests there too, so set identityBaseUrl with it. 0.114.1 also yields artifact, state_transition, and state events from streamTurn(). 0.112.0 removed client.workspaceDatabase, client.desktopSessions, client.tasks, and client.settings.gapScanner; 0.111.0 removed the data-source sync and gap-scanner preview and scan methods, whose operations were retired with the connector runner. Upgrading from 0.108.x also picks up the breaking type changes in 0.109.1, including the removal of service_id from outbound call requests; see the October package releases. The Scribe SDK now publishes as @concurrence-hq/scribe-typescript-sdk; @amigo-ai/scribe-typescript-sdk is deprecated at 0.15.1.

The experimental Forge MCP tool is published separately as @amigo-ai/forge-tools 0.1.14. It uses Classic organization credentials and is not the Platform SDK or the Agent Forge CLI. See the September package maintenance notes.

Changelog Areas

Changelog	Coverage	Latest numbered release
Concurrence API	Classic, Platform, and Scribe APIs	v0.9.557
Web Platform	Developer Console, Admin Portal, and managed voice testing	v2.201.96
SDK Ecosystem	TypeScript and Python packages	Per package; see the snapshot above
Agent Forge CLI	CLI and configuration management	v0.1.74, published September 15, 2026

Versioning Policy

Numbered entries use the version published for that product. Each SDK package and Agent Forge has its own version track; web releases use sequential numbering. Review the migration notes for each upgrade, including breaking changes indicated by Semantic Versioning.

Newer unnumbered API and web entries can appear after the latest numbered release listed above. Their announcement or source-change dates do not establish rollout to every deployment; follow the linked guide's availability and setup requirements.