November 2026
Nov — Watch conversations live, human handover, and file attachments
3.4.1–3.4.2- Watch a conversation live (
3.4.2) — keep a WebSocket open, send awatchframe, and every message the conversation saves is pushed to you: a reply, an answer from a person on your team, the agent speaking after an outside approval. In the SDK,socket.sendWatch(). - Human handover (
3.4.2) — on a conversation the agent handed to a person on your team, every message says what happened to it inmessage.disposition, and a person’s message carries their name insender.name. Your backend sends the person’s side ashandoverevents. - Live cards in streams (
3.4.2) — acardsevent ahead of the terminalmessagecarries the turn’s cards so far, so you can show them while the reply is still streaming. - File attachments (
3.4.1) — create an upload,PUTthe file, and attach it to a message withfile_urls. In the SDK,messaging.createUpload(). - Usage (
3.4.2) — usage responses addcache_write_tokensandincomplete_usage_calls. - Upgrading the SDK —
3.4.2changes nothing at runtime. In TypeScript, a socket handler that readsseqneeds a'seq' in frameguard, and an exhaustiveswitchneeds the newwatching,silent, andcardscases.
Nov — Release notes, update notices, and fault reports
0.1.109–0.1.113- Report a fault (
0.1.112) —apollo reportfiles an engine, CLI, platform, or docs fault with its evidence, and the CLI files its own crashes and 5xx failures in the background.APOLLO_REPORTS=0turns both off.0.1.113attaches more of what happened, where, and when. - What changed, and what to do (
0.1.111) —apollo release-notessays what changed in the CLI and in the runtime your checkout runs on, and what to do after a version change. After an upgrade,apollo upgradenames the--sincecommand to read. - Told when you fall behind (
0.1.110) — commands now say when a checkout’s skills,AGENTS.md, and schemas came from an older runtime than the one its version runs on, or when a newer runtime is out, with the command to run.apollo skills updaterefreshes them without touching the program.APOLLO_UPDATE_CHECK=0turns the requests off. - Agents stay in your organization (
0.1.109) —apollo agent createrefuses a project outside the organization you’re signed in to, instead of creating the agent there.
apollo report.Nov — The CLI docs catch up: live revisions, scripted chats, and more
0.1.113, including features that
shipped in earlier releases:- Live is one revision —
apollo version live <tag>makes an exact revision live (an older one too — that’s the rollback), and pushing never moves it.lock,unlock,log,label,notes, andfetchround outapollo version;publishremains the one-step lock-and-ship. - Work across versions —
apollo diff <ref> [other],apollo show,apollo restore, andapollo merge-from, plusapollo push --new-versionwhen someone pushed to your version first. - Test like a caller —
apollo chat --caller,--at, and--scriptwith per-turn expectations;apollo thread listfilters; andapollo opento read any of it in the Playground. - And more —
apollo whoami,kb connections,kb resync,kb export,mockdb clone,reset,rows, andguide, corporate proxy support, and the build tree’sspec.yamlwith its capability cards. - Removed flags —
validate --fix,build --evaluate, andevaluate --worldare gone, andregress --judgeis now--explain: every regression is graded, and--explainadds the LLM judge’s explanations.
Nov — Try Beta from any version, under your own name
0.1.108- Any version can try Beta —
apollo version try-betano longer asks you to upgrade first: a version on an older runtime tries Beta as it is, and the rebuild runs on Beta. - Name it —
--label <name>names the new version (default Beta). - Clear when Beta is off — while no Beta runtime is offered, the Beta commands say Beta isn’t available right now, and the TUI hides its Beta options.
October 2026
Oct — Build and try agents on the Beta runtime
0.1.107The Apollo CLI and its TUI can now build and try agents on Beta, the
newest runtime, whenever a Beta runtime is offered:- Build on Beta —
apollo agent create "<name>" --betacreates the agent on Beta. It and every version made from it run there. - Try Beta —
apollo version try-betacopies your version into a new version labelled Beta, runs it on Beta, and rebuilds and evaluates it there. Your own version doesn’t change, and--dry-runshows where it stands first. - BETA badges —
apollo version list,apollo status --check, the TUI header, and the TUI’s Versions view mark every version on Beta. - In the TUI —
Ctrl+K→try-beta, and Build on Beta amongagent-create’s advanced options.
September 2026
Sep — Traces for every agent, and inline with the reply
3.4.0The trace endpoints now answer for agents on the current runtime, not only
runtime v1 agents:- One
Trace, two shapes — every trace carriesruntime("v1"or"v2"). A runtime v2 trace is the runtime’s own turn trace, published as typed sections: what it understood and learned, the sources it read, the passages and citations the reply provably used (passages_used,citations_used), the policies it decided, the checks it passed, and a plain-languagenarrative. - Inline with the reply — set
include_trace: trueon a send, stream, or rerun and the reply carriesmessage.trace_info; no second request. - Reading one runtime v2 interaction — pass the thread as well:
GET /interactions/{interactionId}/trace?thread_id=…(interactionTrace(id, { thread_id })in the SDK). Runtime v1 interactions are read by their id alone, as before. - Unchanged for runtime v1 agents — the same fields as before, plus
runtime: "v1". - In the SDK (3.4.0) —
Traceis now a discriminated union ofRuntimeV1Trace/RuntimeV2Trace(narrow onruntime), with typed section types (RuntimeTraceFact,RuntimeTracePassage, …);include_traceonsendMessage/streamMessage/rerun;Message.trace_info;interactionTrace(id, { thread_id })andthreads.getInteractionTrace(id, { thread_id }). No other method changed. - Scoped to your agent — a thread of another agent answers
404 not_foundon both trace endpoints.
Sep — Apollo CLI: the official command line for Apollo agents
stable · @aui.io/apolloThe Apollo CLI is the operator console for Apollo agents — a scriptable CLI
(apollo <command>) and a full-screen terminal TUI (bare apollo) in one
npm install:- Local-first authoring — agents check out as typed YAML programs
(
bundle/src/) with JSON Schemas, coding-agent skill packs, and the runtime’sAGENTS.md;validate,diff,pull, andpushcomplete the loop. - Runtime testing —
apollo chattalks to the live runtime, including unpushed local edits via--local ., with the full decision trace via--trace;apollo threadinspects conversations. - Server-side authoring —
apollo adviseanswers grounded questions over your checkout,apollo buildruns gated build turns, andapollo evaluateruns the live evaluation suite (simulated callers plus a judge). - Versions, knowledge, and secrets — full version lifecycle
(
version publishis also rollback), knowledge hubs (apollo kb), vault secrets (apollo vault), and a per-agent mock database (apollo mockdb). - Built for coding agents — every command is non-interactive with a
stable
--jsonenvelope and predictable exit codes.
August 2026
Aug — runtime v2 support across the API and SDK
- Thread reads (transcripts, get/rename/list) take a
runtime_versionselector — pass the runtime version the agent runs on (e.g.0.8.0). See Threads and runtime versions. - SSE streams can end with a new
suggestionsevent carrying ready-made follow-up prompts (followup_suggestions, with thethread_idandinteraction_idthey belong to). - Cards carry new optional metadata:
title,capability(which agent capability produced the card), andinstance(the record it’s about). - Streaming is over SSE — one HTTP call per turn, resumable with
Last-Event-ID. WebSocket sessions stay with runtime v1; see Runtime v1 agents for the frame-by-frame mapping. - Sends accept an optional
runtime_versionbuild pin (advanced; normally omit).
Aug — SDK 3.3.5: list filters, fixed and flattened
breakingManagement list methods now take their filter fields directly on the
request — drop the filters: { … } wrapper
(listThreads({ project_id }), listAgents(projectId, { name }),
listVersions(agentId, { status })). The TypeScript compiler points at
every call site.This also fixes a bug where list filters were silently not applied on the
wire in 3.3.4 and earlier — from 3.3.5 they filter reliably. Requests from
older SDK versions keep behaving exactly as they did.Aug — API: choose the sender number on channel threads
POST /messaging/v1/channels/{channel}/threads now accepts an optional
sender_id — the MongoDB ObjectId of a sender you connected in the
Playground. Pass it to start the conversation
from that connected number. Omit it to keep using the platform default
sender.phone_number remains the recipient. When a specific sender is used,
the response includes from so you can confirm which connected number
sent the opener.See Channels and the
SDK messaging client.July 2026
Jul — API: structured card data (json_data)
breakingAgent reply cards now carry the entity in two self-contained
representations: rendered_jsx (unchanged — a ready-to-render JSX string
for React UIs) and the new json_data — the same card as structured JSON,
so you can build your own card UI in any framework (Vue, Angular, mobile).json_data.entity is a flat key–value map of the card’s fields, and
json_data.sub_entities holds nested groups such as product variants.The card’s previous name, category, and parameters fields were
removed — everything you need to render is in json_data.See Cards.Jul — API: agent version on thread lists
GET /management/v1/threads items now include version_tag — the agent
version the conversation ran on. Use it to tell which release of your
agent handled each thread when filtering or auditing conversations.See Management → Threads.Jul — API: new base URL
breakingThe API base URL changed from https://api-v3.aui.io/apollo-api-v2 to
https://api-v3.aui.io/apollo-api. All paths under it are unchanged
(e.g. POST /messaging/v1/messages, POST /management/v1/auth/token).The old base URL keeps working for a few more days to give you time to
migrate, and will then be removed — switch to the new one now.Jul — API: agent_id removed from messaging request bodies
breakingYour agent is now identified by your access token: when you exchange a
publishable key at POST /management/v1/auth/token, the resulting token
already carries the agent. Sending agent_id in the body of
POST /messaging/v1/messages, POST /messaging/v1/messages/stream, or
POST /messaging/v1/threads/{threadId}/rerun is no longer accepted and
returns a validation error (422).Migration: remove agent_id from your messaging request bodies —
responses keep the same shape. See Send messages.Jul — API: channel thread initiation (WhatsApp / SMS)
breakingThe POST /messaging/v1/channels/{channel}/threads request body changed:agent_idwas removed — the agent now comes from your access token.user_ref_idwas renamed touser_id.template_idandcontent_variables(WhatsApp template overrides) were removed — the agent’s configured template is always used;agent_display_nameremains available.
Jul — SDK v3: new clients for the Apollo API
breaking · v3.2@aui.io/aui-client v3 is a full rewrite against the Apollo API. The
single ApolloClient is replaced by two clients, one per credential:ApolloMessagingClient— publishable key, browser-safe. Token exchange and refresh are handled internally; the agent comes from the key, not request bodies. Messaging, channels, and WebSocket sessions.ApolloManagementClient— organization API key, server-side only. Projects, agents, versions, threads, and usage.
createTask is gone (threads auto-create on the
first sendMessage), task_id became thread_id, and the client
defaults to the production API with no environment configuration. See the
SDK upgrade guide.Jul — API: threads, agent variables, welcome message & follow-up suggestions
new- Update a thread —
PATCH /management/v1/threads/{threadId}renames a thread (title); the full updated thread is returned. - Agent variables —
POST /messaging/v1/messagesandPOST /messaging/v1/messages/streamaccept an optionalagent_variablesobject (staticanddynamic) with per-message values for the agent’s configured context variables. - Welcome message —
GET /messaging/v1/welcome-messagereturns your agent’s configured greeting, for opening a conversation UI before the first message. - Follow-up suggestions —
POST /messaging/v1/followup-suggestionsgenerates suggested next prompts from a context you provide.
March 2026
Mar 9 — Agent Builder API Alpha
alpha · Closed to the public- Alpha release of the Agent Builder API — available to select partners only
- Identity, organizations, accounts, and networks (agents) endpoints
- Agent settings read/write: tools, parameters, entities, integrations, rules
- Knowledge base management with file upload and website scraping
- API Workflow integration generator