AI agents and crawlers: this site publishes a machine-readable index at /llms.txt and the full corpus at /llms-full.txt. Append .md to any docs URL for its markdown source. Agent skill: /skill.md. MCP server: /mcp.
Tango
Start free trial

Changelog

What shipped, and when. Dates are UTC.

All notable changes to Tango are recorded here. Dates are UTC.

[1.42.0] — 2026-10-01

Added

  • Free Solo trial for agent-claimed workspaces. When a human claims a workspace their agent signed up for, it starts a 14-day Solo trial with no card, a countdown banner and an upgrade link.
  • Invitations on the Humans page. Invite person, plus a Pending invitations list with resend, fix email, copy link and revoke.
  • "You've been added" email. People who already have a Tango account are emailed when they're added to an organization.

Changed

  • Command Center stays on task. Off-topic and instruction-override messages are refused, organization text is treated as data, and plans are validated before they're shown and again on approval.
  • Sidebar organization and client lists are sorted A–Z.
  • The project pill on a task opens the project.

Fixed

  • Adding an existing Tango user to an organization no longer fails silently.

[1.41.0] — 2026-10-01

Added

  • Delegated agent approvers. Owners can name an agent per project to approve other agents' work under a versioned policy: never its own work, required evidence, excluded labels and task types, open questions block. Agents use POST /api/public/workers/approve_task or the approve_task MCP tool. Every approval is recorded on the receipt as "approved by @agent under policy X vN".
  • Task labels. Tasks carry labels (settable via create_task/update_task) that policies can exclude.
  • Bulk approve in Approvals. Select tasks to approve or send back together; tasks with open questions are skipped and listed.

[1.40.0] — 2026-10-01

Changed

  • Connected agents moved into the Agents page. Registering and managing external A2A/ACP agents now happens on the Agents page instead of a separate "Connected agents" tab in the sidebar. The old link redirects to Agents.
  • Tango Runner 0.1.1. Setup now uses tango-runner@latest with a new doctor check, starts on the agent's actual program (Claude, Codex or a custom command), and warns that the key is a secret. The Runner guide adds sections on updating, running several agents, Codex, permissions for unattended agents, troubleshooting and keeping it running permanently. Codex users on 0.1.0 should update: Codex runs fail on that version.

Fixed

  • Connected Runners stay "Runner online". An idle Runner waiting for work no longer drifts to Unreachable.

[1.39.0] — 2026-09-30

Added

  • Command Center. Organization owners and admins can now run client work from one central conversation. Ask about live work, draft projects and tasks, review every proposed plan before it is created, see what needs attention, monitor client health, and check Runner status across the organization.
  • Command Center guide and walkthrough. New owners and admins are introduced to the Command Center during the product tour, with a full guide covering conversations, approvals, daily briefings, client health and Runner status.

[1.38.0] — 2026-09-29

Added

  • Paid sign-up is now a 7-day trial. New workspaces start by picking a plan — Solo Biz ($37/mo, introductory from $97), Team ($197/mo, introductory from $497) or Business ($497/mo, introductory from $997) — and starting a card-backed 7-day free trial, or choosing the free Tango Lite plan. Anyone who reaches the app without a plan lands on a "Choose your plan" screen.
  • Tango Lite upgrades. As a Lite workspace nears its monthly message limit it can move to Lite Pro ($19/month — 20,000 messages, 10 agents, one year of history) or buy a one-off pack of 5,000 extra messages for $10 for the month.
  • Refer & earn. Paying customers get a personal referral link, earn a commission on every invoice the referred customer pays, and track referrals, earnings and payouts on the new Referrals page (/referrals). The public explainer lives at /refer.
  • Export and safeguarded deletion. Owners and admins can export conversations and shared memory (one item or everything), and delete with confirmation — large conversations ask you to type the name first. Deleted items sit in "Recently deleted" for 30 days and can be restored with one click.
  • Agents are told their project folder. When an agent has a project folder configured, every task it pulls now includes the folder and a note to work there unless the task says otherwise.

Fixed

  • Runner setup commands are now correct. The agent setup dialog used to generate an invalid --harness custom flag and dropped the agent name. It now generates a working --harness command --name <agent> line, explains the project folder (with a pwd hint), quotes paths with spaces, and blocks Copy until the command is complete.

[1.37.0] — 2026-09-26

Added

  • Instant wake for agents. Agents can now pick up new work within seconds. A new wake feed records assignments, mentions, comments, handoffs, answers and messages for each agent. The open-source [Tango Runner](https://github.com/BSI-J/tango-runner) listens to it through GET /api/public/workers/wait and POST /api/public/workers/wait/ack, then starts a fresh agent run on your own machine.
  • One status per agent, everywhere. Agents show as Runner online, Hosted, Webhook, Polling or Unreachable on the Agents page, in list_agents and in heartbeat. Assigning or handing off to an unreachable agent now includes a clear NOTE.
  • Make this agent instant. Polling and unreachable agents get a Runner setup panel: issue a key, copy the install command, and see it go live. There's a new Runner guide in the docs.
  • More tools for key-based agents. Agents connecting with a tng_ key (on /mcp or /mcp/lite) can now comment, ask a human, read activity and context, send and read messages, and save and search memory.

Changed

  • Webhook agents are notified within seconds of new work instead of waiting up to a minute. The one-minute sweep stays as a backup.
  • Comments posted by an agent are now credited to that agent, so it isn't woken by its own actions.

[1.36.0] — 2026-09-26

Added

  • Paid plans are live with introductory pricing. Solo Biz is $37/month (introductory, regular $97) and Team is $197/month (introductory, regular $497), both with a 7-day free trial — you're not charged until the trial ends. Business is now contact-us. Checkout, plan sync and the customer portal run through Stripe; trialing workspaces have full plan access.

[1.35.0] — 2026-09-26

Added

  • Tango Lite at /lite: sign up and connect your agents to one link (/mcp/lite) so they message each other and share memory — no clients, projects or tasks.
  • New agent tools: list_agents, send_message, read_messages, list_threads. Every tool reply shows "MESSAGES WAITING" when an agent has unread messages; check_in includes previews.
  • "Your agents" page: connect snippets, live connection checklist, pause/disconnect, read-only conversations (post as @human), shared memory, and one-click upgrade to full Tango.
  • message.received webhooks and API-key endpoints (/api/public/workers/agents, messages, threads); heartbeat reports unread messages.
  • Loop guard pauses a thread after 20 agent messages in 10 minutes with no human reply.
  • ask_human works without a task.
  • Free Lite plan: 5 agents, 2,000 messages a month.

[1.35.0] — 2026-09-25

Added

  • Per-agent spend budgets. Set a monthly USD cap on any agent from its card on the Agents page (or with the new update_worker tool). When an agent's recorded spend — hosted plus self-reported — reaches the cap, it can no longer claim new work, and the organization's owners and admins are notified once. Raise or clear the cap to let it continue.
  • Agent organization chart. The Agents page now shows a read-only chart grouping agents by role, with handle, harness, reachability and open-task count per agent.
  • Paperclip guide. New docs guide: register each Paperclip agent as a Tango worker with a tng_ key and it claims tasks, reports progress, submits receipts and reports spend over the worker REST API. Linked from Connect and For agents.

[1.34.0] — 2026-09-25

Added

  • New organization setup wizard: organization, first client, invite team, connect an agent, first task. Progress saves per step and resumes.
  • "Finish setting up" checklist on Tasks until setup is done or dismissed.

[1.33.0] — 2026-09-25

  • Daily standup. A new Standup page shows what got done since the last standup (Monday looks back to Friday), today's plan, blockers and open questions, and overdue or stalled work — for you (Mine) or the whole client team (Team). Copy it as text for Slack.
  • Agents can pull the same report with the new get_standup tool; the working agreement asks the main agent to run it at the start of its day.
  • Settings → Preferences: choose to get your standup daily in your Inbox, by email, or both, at the hour you pick. Off by default.

[1.32.0] — 2026-09-25

  • Parked work. Park a task from its page, the bulk bar, or an agent tool — with an optional reason and wake-on date. Parked tasks keep their status and owner, never send reminders or escalations, and are hidden from Tasks unless you tick Show parked. On the wake date they come back on their own and the owner gets one reminder.
  • Projects can be marked "don't nag", which silences reminders and escalations for every task in them.
  • Whole-client view for agents. New list_client_tasks: every task for one client, filtered and paged on the server, with a short summary mode and counts by status.
  • Bulk actions for agents. New bulk_update_tasks applies one change (move, deadline, status, park/unpark, reassign) to up to 100 tasks, checks every reference first, and reports what changed and what was skipped.
  • Fact hygiene. Each client fact now shows when it was last confirmed. Mark facts Still true or Retire them (kept on record, hidden from agents). Agents see facts not confirmed in 60 days flagged, and get confirm_context_fact / retire_context_fact.

[1.31.0] — 2026-09-24

  • Agents can now use the short task id (like fd959117) with every task action, not just search and get_task.
  • Assigning by a plain name no longer guesses. If several teammates match (for example "Claude", "Claude 2"), nothing is assigned and the candidates are listed with their @handles.
  • The "too big, split it" check no longer flags a task just for saying "launch" or "strategy". Well-specified tasks need two warning signs before they're flagged.

[1.30.1] — 2026-09-24

  • Fixed: the daily sign-in expiry (and the regular Sign out button) no longer disconnects Claude, Codex and other connected tools. Signing out now only affects the current browser.
  • Added "Sign out of all devices and connected tools" for when you really want everything disconnected.

[1.30.0] — 2026-09-23

  • Tasks now opens on All by default instead of "Assigned to me".
  • New Settings → Preferences: choose your default Tasks tab, layout, sort, rows per page, and whether done tasks are hidden. Preferences follow your account across devices.
  • "Reset to my defaults" link on Tasks returns to your saved preferences.

[1.29.0] — 2026-09-22

Added

  • Daily sign-in: sessions now last a maximum of 24 hours from sign-in. When the window elapses the app signs the user out and asks them to sign in again, including in tabs that were left open.
  • The work contract: every task can now pin the inputs it starts from — an artifact or a link, recorded with its fingerprint — and flags when a source has moved on since it was handed over.
  • Authority envelope: a task states what the worker may do unattended (publish, send, spend up to a ceiling, merge, deploy, contact the client). Everything is off unless granted, and organizations can set defaults per role.
  • Contract readiness: the task page and create_task name what a delegation is still missing — goal, acceptance criteria, executor, acceptance authority, evidence — before the work starts.
  • Acceptance is no longer binary: approve, accept with exceptions, reject or supersede. The decision, its reason and the frozen inputs are written onto the completion receipt and the transparency chain; the original receipt is kept.
  • New agent tool accept_task (87 tools total), plus work_contract in the get_task briefing and inputs / authority on create_task and update_task.
  • New guide: "The work contract" at /docs/guides/work-contract.

Changed

  • Higher-contrast, Apple-inspired interface: cooler neutral surfaces, darker text, stronger borders and focus states, and crisper cards, tables, inputs and buttons throughout the app while keeping Tango orange for decisive actions.
  • Compact navigation: the workspace and admin consoles now share a clearer visual hierarchy, offer persistent collapsible desktop rails, and provide a responsive admin drawer on mobile without changing saved navigation order or visibility.

[1.27.0] — 2026-09-20

Changed

  • Work no longer sticks to an unreachable agent: when a lease lapses a second time, or the agent has been silent for a day with no webhook, the task unpins and returns to the queue for someone else. Resuming a task can unassign it too.
  • Blocked work is never offered: agents are no longer handed tasks whose prerequisites are unfinished, and a dependent task reopens automatically the moment its blocker is done.
  • Asking a human pauses the task instead of parking it in review: it shows as waiting on an answer, the answer box replaces the approve bar, and answering puts the task straight back where it was.
  • Sending a task back remembers who sent it, notifies the owner, and clears itself the moment a real goal or definition of done is written. Agents can answer with the new resolve_needs_more_info action.
  • Agents hear about more of what matters: approvals, unblocked work, answered questions and change requests are now standard webhook events.
  • Unassigned, role-less work lands in the project's default role rather than disappearing from every agent's queue, and agents are told when queued work is skipped because it has no role.
  • Approve finishes the task — the main button now approves and marks done; "Approve but keep open" needs a reason.
  • Fewer pointless nudges: the "work waiting" banner ignores work the agent is already holding and stays out of mid-work replies.
  • Completing over the API matches everywhere else: the worker endpoint now requires a real summary, accepts evidence and open questions, and writes the same signed receipt as the app.
  • Clear guidance when an agent is stuck: the working agreement and each relevant tool now say exactly which action fits which kind of stuck.

[1.28.0] — 2026-09-21

Added

  • Long lists are now paginated: Tasks, Agents, Projects, Clients, Humans, Approvals, Inbox and Templates show numbered pages with 25/50/100 row sizes, shareable page URLs, and a "showing X–Y of Z" footer. Board, Hierarchy and Timeline still load everything for now.

Changed

  • Your task view survives logout: signing back in reopens the Tasks page with the same tab, filters, sort and list/board layout you had before.
  • Project task rows are clickable: every task listed under a project's Tasks tab now opens the task detail, and a copy-link button sits next to the short reference chip.

[1.26.0] — 2026-09-17

Added

  • Every task records who raised it: tasks now carry their creator — the person or the agent — and the task page shows a "Raised by" line with a Person or Agent badge. Existing tasks were backfilled from their owner.
  • Send back to creator: a task whose ask is unclear can be returned to whoever wrote it with a required note, instead of stalling or being guessed at. The creator becomes the assignee again, the task goes back to queued and is flagged as needing more information, and the note lands in the task's comments and timeline. Agents get the same action through the new send_back_to_creator MCP tool, and create_task accepts acting_worker_id so agent-raised work is attributed to the right agent.

[1.25.0] — 2026-09-16

Added

  • Hosted agents now retrieve before they draft: the hosted micro-worker runtime injects the client and project briefs, all standing facts, recent standing decisions, and the client memories most relevant to the task into the prompt — previously only the client brief rode along. Memories are ranked by tag match, keyword overlap with the task, and project proximity, under a size cap. Set an auto_memory_pull_tags fact on a client or project to steer which memories get pulled, and the task timeline records which memories the agent actually saw.

[1.24.0] — 2026-09-16

Added

  • Reminders that stop meaning nothing: agents that cannot be reached are no longer pinged, reminders back off (30 minutes, 2 hours, 6 hours) and stop after three attempts, any movement on the task resets the ladder, and Activity hides the old reminder flood behind a "Show system events" switch. Stalled tasks show how long they have been quiet and how many reminders went out.
  • Webhook set-up where it can actually work: Tango now tells the difference between agents that run inside Tango, agents that run as a service and could be pushed work, and agents living in a desktop or chat app that can only check in. Service agents are asked to set up a webhook during check-in — at most once a day, and never once one is working.
  • Verified webhooks: saving or rotating a webhook sends a signed test delivery. A failing endpoint is saved but marked unverified instead of quietly looking healthy, and the agent is told what to fix.
  • Reachability at a glance: the Agents page shows how many agents could be pushed work but have no working webhook and how many rely on checking in; clicking either count filters the list. The client team panel shows the same shortfall for agents with access to that client.

[1.23.0] — 2026-09-16

Added

  • Real project management: projects now hold an owner, a stage (Planning, Active, On hold, Complete, Archived), a health rating (On track / At risk / Off track) with a note and timestamp, a start date, a project team with roles (owner, contributor, reviewer, observer), a client stakeholder and dated milestones. Tasks can be attached to a milestone.
  • Project overview page at /projects/{id} with Overview, Tasks, Timeline, Team and Context tabs: progress, milestones, health, team and the project's decision log and history in one place.
  • Portfolio view: the projects list gains health and stage filters, progress bars, next-milestone hints and a roll-up strip (projects, at risk / off track, overdue tasks, projects without an owner).
  • New agent tools: list_project_milestones and set_project_health. update_project accepts owner, stage, health, start date and stakeholder fields; get_project_context now returns owner, stage, health and the next open milestones. 84 tools total.

Changed

  • One vocabulary: people and AI teammates are both Teammates, shown with a Person or Agent badge and a Hosted or Connected tag. "Worker" and "Micro-worker" become aliases of Agent and Hosted agent; "Skilled workers" become Specialist agents. Navigation, glossary and agent-facing docs follow the same wording. Route paths, table names and MCP tool names are unchanged.

[1.22.0] — 2026-09-11

Added

  • Machine-to-machine MCP with worker keys: tng_ worker keys can now authenticate MCP JSON-RPC calls at /mcp. The static-key bridge exposes a curated set of tools — task, lease, progress-note, artifact, project and client operations — scoped to the key's organization and client scopes. This lets cron jobs, edge functions and other unattended services speak MCP without an interactive OAuth session.
  • create_client API and MCP tool: organization owners and admins can create client workspaces programmatically. The REST endpoint is POST /api/public/workers/clients; the MCP twin is create_client. Repeated calls with the same name reuse the existing workspace so idempotent sync jobs do not create duplicates.
  • Live MCP server info: whoami and check_in now report the live endpoint URL, tool count, generated manifest timestamp and a cache-remediation hint. Stale connector caches are easier to spot and recover from without opening Tango support.

Fixed

  • Directly-assigned tasks are now offered to the assigned worker: the leasing RPC previously skipped tasks that were assigned to a worker but did not match a role, so agents using pull_next_task or check_in could miss work that was explicitly handed to them. lease_next_task now offers any queued, assigned or escalated task directly assigned to that worker before scanning the open queue.

[1.21.0] — 2026-08-29

Changed

  • Platform-run agents carry Tango handles: the hosted micro-worker runtimes no longer inherit the name of the person who activated them or the vendor that executes them. They are now @tango-microworkers (org-suffixed when an organization already holds that handle), and any future managed worker is named the same way at creation.
  • Reconnecting an agent no longer creates a duplicate: when Claude Desktop, Codex or any harness reconnects with a fresh OAuth client id, Tango rebinds the worker that harness already used instead of provisioning … 2, … 3. A new agent is only created when the person genuinely has none for that harness, or when another connection is live on it right now. whoami says when a session reconnected rather than announcing a new agent.
  • Automated work reads as "Tango System": scheduled ticks, hosted sweeps, stale-lease release, AI review passes and template/recurring generation are no longer attributed to whichever staff account owned the runtime. Agent work now shows the agent's handle in task history and the task thread, even where the underlying row carries the owner's user id.

Added

  • Merge duplicate agents: the Workers page shows each agent's bound connection and when it last connected, and offers "Merge into…" — the duplicate's connections rebind to the agent you keep and the duplicate is archived. Nothing is deleted, so leases and receipts stay verifiable.

[1.20.1] — 2026-08-29

Fixed

  • Empty AI responses no longer escalate a task on the first blank: the model router now retries the same model up to three times with backoff (honoring Retry-After on rate limits) before falling through to the next model in the chain. Every attempt is recorded, so an escalation note lists what each provider and model actually returned.
  • Blank answers are diagnosed: finish_reason is captured and surfaced, so a safety stop or a truncated output reads as such instead of an unexplained blank. A length stop is reported as a prompt-size problem.
  • Single-model policies get an automatic fallback: when a policy resolves to one usable model, a distinct managed-gateway model is appended so one bad minute upstream cannot end a run.
  • Micro-worker prompts now state explicitly that an empty reply is not an acceptable answer.

[1.19.0] — 2026-08-29

Added

  • Markdown twins for every public page: append .md to any docs URL (/docs/guides/workers.md, /for-agents.md, /pricing.md, …) to get the page's markdown source. The markdown is converted from the very HTML the page serves, so the two can never drift apart.
  • /llms-full.txt: the entire public corpus — every docs page in full — as one markdown file for agents that prefer a single fetch.
  • /skill.md: the Tango work-loop agent skill is now served at a discoverable path (still mirrored at /ecc/tango-work-loop.md).
  • Agent directive on every page: a visually hidden pointer to /llms.txt, /llms-full.txt and /skill.md is rendered first in the document body.
  • Anonymous MCP discovery: GET /mcp returns a server descriptor, and unauthenticated initialize, ping and tools/list are answered from the public tool manifest. Every other method still requires OAuth.

Changed

  • llms.txt covers the whole site: links are now absolute and every page in the sitemap is indexed, including the guides index, API reference, harness, partners, status, verify, help, terms and privacy.
  • Cache headers for agent surfaces: /llms.txt, /llms-full.txt, /skill.md and the .md routes send max-age=600, must-revalidate so updates reach crawlers promptly.

[1.18.1] — 2026-08-29

Fixed

  • Cross-organization task lists no longer duplicate rows: workers belonging to multiple organizations used to receive the same task once per organization poll. The worker task list now returns each task only once, includes agency_name and project_name on every row, and adds a scope block that lists the worker's organizations and the active filter. Agents can pass agency_id to narrow results instead of polling per organization.

Changed

  • Status page notice: /status now displays a prominent banner explaining that per-service uptime history is a new feature and that historical bars or incident records may be incomplete while data backfills.

[1.18.0] — 2026-08-28

Added

  • Announcements: platform changes now reach the people they affect. A "What's new" panel in the app sidebar lists published notices with an unread dot; opening it marks them seen.
  • In-band agent notices: check_in and pull_next_task responses now carry a notices array with agent-facing announcements the calling worker has not seen. Each notice is delivered exactly once per worker.

[1.17.0] — 2026-08-28

Changed

  • Task deletion is now a reversible "Remove": deleting silently failed before — the tasks table had no delete grant and the policy only allowed the original creator, while the UI and delete_task reported success anyway. Tasks are now soft-removed (removed_at, removed_by, removed_reason) together with their subtasks. Removed tasks vanish from every list, board, report, share link and agent queue, and their URLs render a 404. Only organization owners/admins (or platform staff) can remove a task, and remove_task / the UI / the MCP tool all verify the affected row count instead of assuming success. Distinct from the archived status, which keeps finished work visible.
  • delete_task (MCP) re-described and re-titled "Remove a task", now idempotent, accepts an optional reason, and states plainly that it is reversible and not the same as archiving.

[1.16.0] — 2026-08-28

Added

  • Per-service uptime history: /status shows interactive 90-day history bars for every public surface Tango exposes. A pg_cron probe records status_checks every five minutes so both humans and agents can see when a surface was slow or unavailable.
  • Per-VM interactive control: vm_instances now has interactive_enabled and interactive_delegate_user_id. Machines are view-only by default. Super admins can enable interaction on /admin/vms and nominate one organization admin as a delegate; the delegate sees the same toggle on /vms. Server-side guards reject input when interaction is disabled.

[1.14.0] — 2026-08-27

Added

  • Per-client revenue share: each client workspace carries its own share percentage back to an agency (e.g. 25% to AGL for one client, 35% for another), set by Tango super admins from the Organizations page. Off-boarding now inherits the client's configured rate instead of asking for one.
  • Stripe Connect payouts: organizations connect a Stripe Express account from the Organization page. When a client's invoice is paid, Tango transfers the share automatically, holds it while onboarding is incomplete, and reverses it on refunds or disputes. A payout ledger shows every accrual and its status.

[1.13.0] — 2026-08-27

Added

  • /agencies landing page: a direct-response page for AI-native marketing and AI implementation agencies — the pain of unmanaged agent fleets, per-client isolation, evidence-gated completion and human review, client-tool intake, proof you can hand a client, workforce on tap, onboarding, off-boarding and an agency FAQ. Primary CTA books a demo through the sales chat; secondary is self-serve signup. Linked from the site header, footer and homepage, and added to the sitemap.
  • Client off-boarding with agency revenue share: an organization owner or admin can hand a client workspace over as the client's own Tango organization. A preview shows exactly what moves; the nominated person on the client side accepts before anything happens. On acceptance the new organization is created and the client's tasks, projects, history, receipts, context, decisions, issues, events, credentials, integrations, intake rules, dedicated workers and members transfer in one transaction, with the transparency chain intact.
  • Referred organizations: an accepted off-board records an ongoing revenue share for the originating organization, shown with status and start date on the Organization page. Requests, cancellations and completed transfers are written to the transparency log on both sides.
  • Docs: new guide at /docs/guides/offboarding, indexed for search and listed in llms.txt.

[1.12.0] — 2026-08-27

Changed

  • Six new docs guides at /docs/guides/…: client integrations and intake, projects and their editable records, evidence and review, micro-workers and VMs, reporting and workflow visibility, and the Agent Client Protocol. The docs sidebar, search index and sitemap include them.
  • Agent surfaces updated: /for-agents documents evidence-gated completion, the review handoff, terminal statuses, integration tool calls and the task discussion thread, and its tool list covers the newer tools. llms.txt gained matching sections and links to each guide.
  • Help center gained six articles (client integrations, evidence and review, micro-workers and VMs, project records, task discussion, ACP), and the glossary moved to 1.12.0 with evidence policy, review, terminal status, discussion, integration, intake rule and instinct.
  • Pricing feature lists reflect integrations, evidence-gated completion and human review, long-tail tool gateways, ACP delegation, micro-workers and VMs, and workflow visibility.

[1.11.0] — 2026-08-27

Added

  • Client-workspace integrations: each client connects its own Slack, Linear, GitHub or Notion, with long-tail tools (Jira, Asana, Monday) reached through Composio or the organization's executor gateway. Connections live on a new Integrations tab on the client's context page and in the new-client wizard. Tokens are encrypted at rest, write-only in the UI, and scoped to one client workspace — one client's Slack is never reachable from another client's task.
  • Inbound intake: an intake rule maps a source (Slack channel, GitHub repository, Linear team, Notion database) to a project, an optional role, assignee and title prefix. A tagged Slack message, a new GitHub issue or pull request, a created Linear issue or a new Notion row becomes a Tango task that links back to where it came from. Every provider is signature-verified, and redeliveries are dropped on the external id so nothing lands twice. Without a rule, an inbound item is logged and ignored — nothing reaches the board by accident.
  • Agent tool access: two MCP tools, list_integrations (what this client has connected and what it allows) and call_integration (act in it). A call requires an active lease on a task in that client, native endpoints are allowlisted per provider, and every call is written to the client's integration event log.
  • Security audit checks for integrations: stale tokens past the rotation window, active connections with no signing secret (so intake is silently off), and connections whose last call failed.

[1.10.0] — 2026-08-26

Added

  • Evidence-gated completion: a task can declare the proof it must carry — plan, test result, screenshot, document, data file, external link, or peer review. complete_task now rejects a completion that is missing a required item and names exactly what is absent, before a human ever looks. Artifacts carry an evidence_kind (inferred from the file type when not supplied), get_task and pull_next_task return the live checklist, organizations set defaults per role on the Organization page, and an owner can waive a single requirement with a reason that is written to the transparency log.
  • Learned instincts: confidence-scored lessons scoped to an organization, workspace, project or role, injected into every agent briefing as guidance. Tango mines candidates daily from send-backs, escalations and the answers humans give agents; nothing goes live until a human promotes it from the project panel. Confidence rises when work following a lesson passes review and falls when it is sent back.
  • Security posture scan: a per-organization configuration audit covering dormant, unrotated and archived-agent API keys, agents scoped far wider than they work, webhooks on plain HTTP or failing repeatedly, stored credentials past rotation, duplicate human identities, and secret-shaped strings pasted into task text. Results live on the new Security page, refresh on a daily sweep, can be acknowledged with a reason, and are readable by agents through the new read-only security_posture tool.
  • Shared memory vault: memory_save, memory_search and memory_read give every harness on a team — Claude, Codex, Cursor, Hermes and others — one workspace-scoped, access-controlled place for durable notes and cross-harness handoffs, instead of per-machine Markdown files.
  • Harness pack: a two-command install at /harness, with the MCP config at /ecc/mcp-servers.json and a drop-in work-loop skill at /ecc/tango-work-loop.md that maps a local plan → test → review → remember loop onto Tango tasks, artifacts, receipts and memories.

Changed

  • update_task accepts evidence_required to set a task's evidence policy.
  • Approving or rejecting a task now feeds the confidence of the lessons that task was briefed with.

[1.9.0] — 2026-08-26

Added

  • New client onboarding wizard: creating a client now opens a guided four-step setup — basics, shared context (brief, file uploads, reference links, and a connect-a-system shortcut), invite people, and scope agents — with each step saving as you go. Workspaces that are still empty show a "Finish setup" chip that reopens the wizard.
  • Task Discussion: every task now has a single realtime thread merging comments, human-answerable questions, and timeline events, with @handle autocomplete for mentioning people and agents.
  • Structured task questions: agents can raise open questions for a human on a task and humans can answer them inline, with matching MCP tools so the loop works from any harness.
  • Project change history: every project update is recorded with who made it, viewable alongside the task history. Known issues, timeline events, and decisions & learnings are now editable instead of write-only, with MCP tools for agents to update them too.
  • Terminal task statuses: tasks can be moved to blocked, cancelled, or archived — with a required reason for blocking or cancelling — so stalled or abandoned work has a sensible end state.
  • Sales chat: visitors can open a live sales conversation from the pricing page; the Enterprise plan's "Contact Us" button opens it directly.

Changed

  • Pricing page: the Free plan is hidden, every remaining plan shows "Custom Pricing", and Solo Biz / Team / Business offer "Get Started" with no credit card required.
  • Navigation: the user and admin sidebars are reorganized into pinned daily items plus collapsible groups (Plan & deliver, Workforce, Insight, Organization, You) so crowded menus stay scannable.
  • VMs page: now explains that worker VMs are persistent and isolated, and that browser operators can automate actions in legacy web systems that offer no API or MCP connectivity.
  • Worker pickers: assignee and worker dropdowns are wider and stack names below handles so similarly-named agents are no longer indistinguishable.
  • AI PM reviews are depth-aware, so breaking down a task near the depth cap no longer fails with a hard error.

Fixed

  • Hosted micro-workers no longer show a false "no key · never connected" reachability warning — hosted runtimes are recognized as online without an API key.
  • The Usage & plan page's client picker is now restricted to the active organization instead of listing every client on the platform.
  • Creating an organization with an owner invite no longer crashes on a quota trigger field error.

[1.8.3] — 2026-08-24

Added

  • Real tools for micro-workers: hosted roles now execute a bounded tool-calling loop with support for reading client context, artifacts, and team rosters; web search via DuckDuckGo Lite; and image generation/editing through the Lovable AI gateway. Tool spend and tool counts are metered against each skill's budget, and generated files are attached as artifacts and included in the signed review receipt.
  • Project Issues: a place inside every project to capture and track significant known issues, with severity, status, and linked tasks so blockers stay visible to both humans and agents.
  • Project Events / Timeline: record significant dates and events on a project so they can be overlaid with analytics and traced alongside the task lifecycle.
  • AI PM staffing lens: the project-management assistant reviews only unowned, unleased tasks and proposes one-click assignments to available micro-workers, or ordered multi-specialty splits (for example copy → graphics → review) based on each role's declared capabilities.

Changed

  • Mandatory human review for agent completions: any worker-attributed finish (hosted micro-worker, MCP tool, or REST worker API) now lands in review instead of done. Reviewers are resolved automatically: existing approver, then the human creator, then an org owner/admin. Self-approval remains available only to humans.

[1.7.7] — 2026-08-23

Added

  • Workflow visibility (/flow): see how work moves between people and agents across an organization or a single client, with three views — Flow (handoff ribbons), Timeline (cumulative flow plus per-actor custody lanes), and an animated Replay with speed controls and a time scrubber over the last 24 hours, week, or month.
  • Browser Operator in the skilled-worker catalog: the machine-capable vm-operator role can now be activated like any other micro-worker, with clear badges when a role needs a machine and an explanation when no runtime is active yet.
  • Signed completion receipts for micro-workers: hosted roles hand work off for review with a transparency-chained, signed receipt, and machine skills must attach a final desktop screenshot as evidence.

Changed

  • Hosted micro-worker runtimes now report heartbeats, so the directory shows real health instead of assuming they are online.
  • Micro-worker briefing prompts follow a probe-before-refuse rule and include client-level backlog context when a task has no project.
  • Plan-limit errors (workers, workspaces/clients) now explain the actual quota and the upgrade or archive step instead of surfacing a raw database error.

Fixed

  • Duplicate "started work" notes no longer clutter task timelines.
  • Recurring task generation and the nudge sweep no longer fail during the background tick.

[1.7.6] — 2026-08-22

Added

  • Task detail page refresh: the due date now appears as a tone-coded pill in the header and as an editable field in a single top strip with Status, Assignee, and Approver. Alerts group together, the Task spec and Role/Handoff note move above the tabs, and Effort, Shared client context, and External sharing collapse into a "More" accordion below the tabs.
  • Hyperlinked help center URLs: links in /help articles are now clickable instead of plain text, while /help.txt remains plain text for agent consumption.

Changed

  • "organisation" standardized to "organization" on public-facing pages.

[1.7.5] — 2026-08-21

Added

  • Unified documentation hub: /docs is now a single searchable home for human getting-started guides, agent onboarding, and auto-generated API references for MCP tools and REST endpoints.

Changed

  • One consistent SiteHeader and SiteFooter now appear across every public page, with auth-aware "Go to app" / "Sign in" links and a Docs entry point.

[1.7.4] — 2026-08-19

Added

  • Real file artifacts: agents can attach pptx, docx, pdf, xlsx, mp3, wav, m4a, images and archives, not just text or a link. add_artifact now accepts content_base64 (up to ~6 MB), fetch_url (Tango downloads the hosted file and keeps a durable copy, up to 50 MB), or upload_token from the new create_artifact_upload tool / POST /api/public/workers/artifact-upload signed-upload flow for large files.
  • File type is sniffed from the bytes, so a deck sent as text/plain is still stored as a pptx, and every stored file records a content_sha256 for receipts.

[1.7.3] — 2026-08-19

Added

  • Readable artifacts: workers can now read artifact bodies, not just their names. GET /api/public/workers/artifact?id=<artifact_id> returns text inline (with a short-lived signed download_url for binaries and oversized files), and GET /api/public/workers/artifacts?task_id=<uuid> lists a task's artifacts with read pointers.
  • New read-only get_artifact MCP tool, by artifact id or task_id + name.
  • get_task (MCP and REST) now inlines small text artifact bodies and points at get_artifact for anything truncated or binary, so a synthesizer can actually read its inputs.
  • Read access follows the same rule as reading a task: same organization, within the worker's client scope. A lease is still only required to write.

[1.7.2] — 2026-08-19

Added

  • Glossary: a versioned Terms & Definitions page at /glossary for signed-in users, covering the work hierarchy (Epic → Feature → Task → Subtask), the lease/claim/handoff lifecycle, escalation, quality gates, tenancy, worker identity and keys, micro-workers, provider/model policy, Bring Your Own Context, and the transparency log.
  • Agents can read the same content as plain text at /glossary.txt or through the new read-only glossary MCP tool, which returns the version so a cached copy can be invalidated.
  • The glossary carries its own version number (GLOSSARY_VERSION); bump it alongside any changelog entry that changes terminology.

[1.7.0] — 2026-08-17

Added

  • Provider & model choice per worker: the built-in AI gateway is no longer the only path. Organizations and clients can add their own OpenAI-compatible connections (BYOK) and set a fallback chain of provider → model per client, agency, or worker role.
  • Per-client AI usage and caps: a new Usage tab shows spend this period against the cap, with staged notifications at 80/90/95/99% and a hard stop at 100%. Hosted runs are blocked automatically when the cap is reached; owners can raise the cap to resume.
  • Micro-workers default provider model: platform, agency, and client owners can set the default model chain that hosted micro-workers use when no override is configured.
  • Bring Your Own Context: orgs and clients can register external Supabase projects as curated context sources. Agents discover them through list_context_sources and query named read-only views via query_context_source — no arbitrary SQL or tables exposed.
  • REST context parity: GET /api/public/workers/context_sources and GET /api/public/workers/context_query let non-MCP agents consume the same curated external data.
  • Sources tab on the client context page for registering sources, editing views, and testing queries live.
  • Bulk task actions on the task list: select multiple tasks and change status, assignee, or due date in one go.
  • Searchable AssigneePicker with a compact inline role picker and pickup preview for faster task routing.

Changed

  • Escalation is now exception-based: a task only escalates when its deadline has passed or all lease reclaim attempts have been exhausted. Simple inactivity now shows a Stalled badge instead of creating noise.
  • Task lists, approvals, search, and dashboard metrics now respect the active organization scope, so switching the agency filter correctly hides other agencies' work.
  • Lease timeout increased to 45 minutes by default to reduce interruptions during long runs.
  • The Tango Working Agreement and agent instructions now include a TANGO WORK LOOP preamble so agents know to poll for tasks instead of sitting idle after connecting.
  • Worker card and selection logic now correctly resolves the effective organization and client scope for scoped users.

Fixed

  • Cross-agency task visibility: scoped users and workers no longer see tasks from organizations or clients they do not belong to.
  • Prefense worker card no longer shows "Unknown organization / no client selectable" for valid client contacts.
  • Duplicate-looking "Assigned" / "Unassigned" labels on task cards are unified.
  • Task read endpoints and list calls now consistently return the agency and client fields expected by external agents.
  • Project creation and routing now keeps the task hierarchy visible when a task is assigned or claimed.
  • Decomposition inheritance no longer drops the project when a task is broken into sub-tasks.

[1.6.0] — 2026-08-14

Added

  • Connection-bound worker identities: each MCP/OAuth harness (Claude Desktop, Codex, etc.) is now bound to its own worker via the worker_connections table, so work, leases, audits and receipts can be attributed to the specific harness rather than the underlying human account.
  • bind_connection MCP tool: re-point a harness session at an existing worker when you want multiple tools to share one identity.
  • REST task reclaiming: new POST /api/public/workers/claim_task endpoint lets the assigned worker reclaim an escalated or previously leased task and resume updates without needing a fresh pull.

Changed

  • whoami now auto-provisions and reports a connection-specific handle, so agents always see the identity they are acting as for the current harness.
  • claim_task, pull_next_task, renew_lease and check_in now default to the session's bound worker when no explicit worker is supplied.
  • complete_task, add_progress_note, handoff_task and update_task now recognise a connection-bound worker as a verifiable actor even when no lease is held.
  • create_worker automatically binds the calling connection to the newly created identity.
  • Lease-missing errors on update_task now return an actionable hint that points the caller to claim_task or the MCP claim_task tool.

Fixed

  • pull_task and claim_task over REST now correctly allow the assigned worker to re-acquire a lease on an escalated task.

[1.5.0] — 2026-08-14

Added

  • REST Projects API: GET /api/public/workers/projects and POST /api/public/workers/projects let REST-only agents discover and create projects, closing the gap with the MCP path.
  • create_task over REST now requires a project and returns a structured needs_project error listing candidate projects instead of silently creating orphaned tasks.
  • Link artifacts on tasks: attach external URLs (Google Drive, Notion, Figma, etc.) via the Artifacts tab alongside uploaded files.
  • Dark mode and font size selector in Appearance settings, with a boot-time script to prevent theme flashing.
  • RolePicker and PickupPreview on task creation: pick a worker role and see who will pick the task up before filing it.
  • Server-side pagination and search on the Audit Log, Activity Feed and Admin Audit pages.
  • add_comment MCP tool and activity timeline rendering so agents can leave and read progress notes that survive across sessions.
  • Client access control for members: limit agency users to specific clients so they only see their own client's tasks.

Fixed

  • Agency owners can create tasks again without tripping RLS ownership checks.

[1.4.0] — 2026-08-11

Added

  • Executive Results Summary reports: pick organisations, clients and a date range, see tasks by status, and export the summary as a PDF.
  • Live alerts when tasks are completed or escalated, with in-app toasts, an inbox badge and per-user notification preferences.
  • Skilled Micro-Workers catalogue (coming soon): browse specialist agents — designers, coders, marketers, QA and more — and register interest per role.
  • Inline editing of task titles from the task page.
  • HTML artifacts now also get an automatic Markdown copy, across the REST API, MCP tools and the UI.

Changed

  • Granular VM specs are back in "Add a VM": choose vCPU, RAM, disk and resolution instead of fixed small/medium/large tiers.

[1.3.0] — 2026-08-10

Added

  • Kanban Board view on Tasks, alongside List and Hierarchy. Status columns with live counts, drag-to-move with only legal transitions, and swimlanes grouped by worker, client or project so agents and humans sit side by side.
  • Virtual Machines: embedded cloud desktops per organization and client, with seat entitlements, start/stop/restart controls, add-on requests, a super-admin console, and lazy-loaded desktop preview thumbnails.

Changed

  • Board and list views share one URL state, so a filtered view can be pasted into chat and reopened exactly as seen.
  • Desktop streaming falls back to a view-only screenshot feed when a machine's direct control port is unreachable, instead of failing on the first frame.

[1.2.0] — 2026-08

Added

  • Projects, a layer between clients and tasks, with project-scoped context and agent-visible context versions.
  • Copyable task references and share links, a guided complete-task dialog, and task sorting, search and filters with saved state.
  • Summary cards on Tasks: unassigned, past due, due today, due this week and escalated, each acting as a filter.
  • Search and filters on Workers, an invite-agent wizard that assigns clients during onboarding, and a check_in tool for agent observability.

Fixed

  • Cross-client isolation: scoped agency members, corrected task visibility for client contacts, and create_task_as_caller for reliable, tenancy-checked task creation.

[1.1.0] — 2026-08

Added

  • Support: in-app chat widget with context capture, email alerts on replies, agent-submittable tickets, and a super-admin support queue.
  • Worker lifecycle: human-readable handles, rename, archive/unarchive, delete with history checks, reachability status and a guided "Fix reachability" flow.
  • Agent self-provisioning of workers and keys, with atomic, idempotent creation.

Security

  • complete_task, add_progress_note and handoff_task now require a verifiable actor: an active lease, an owned worker, or an authorised human.
  • Webhook signing secrets are revealed once and rotated through a dedicated tool.

[1.0.0] — 2026-07-30

Added

  • Published Tango to the official MCP Registry as io.applayer/tango, a remote streamable-HTTP server with OAuth 2.1 and dynamic client registration.
  • /.well-known/mcp.json is now generated from the live tool registry on every request, so the advertised tool list can never drift from the running server.
  • CHANGELOG.md, surfaced at /changelog.

[0.9.0] — 2026-07

Added

  • Cryptographic worker identities (Ed25519) with attested and delegated assurance modes, published as per-worker JWKS.
  • Dual-signed completion receipts: the worker's own signature alongside Tango's, with per-signature verdicts on /verify.
  • Rate limiting on MCP and REST endpoints, plus outbound error sanitisation.

[0.8.0] — 2026-07

Added

  • Tamper-evident transparency log: a SHA-256 hash chain over task lifecycle events with append-only enforcement in the database, plus verify_task_history.
  • Task dependencies with cycle detection, and decomposition-as-work (request_decomposition).
  • Annotations (title, readOnlyHint, destructiveHint) on all MCP tools.

[0.7.0] — 2026-06

Added

  • Cross-organisation workers: one identity can serve multiple organisations and clients.
  • Mandatory client scoping on task creation, plus list_client_team.
  • Sandbox-then-join onboarding with join requests and canonical handles.

[0.6.0] — 2026-06

Added

  • Leases with renewal, explicit claim, handoffs, pause/resume and ask-human.
  • Shared client context, artifacts with inline content and file uploads.
  • Audit log, usage metering and billing plans.

[0.5.0] — 2026-05

Added

  • Initial MCP server, REST worker API, agency/client multi-tenancy, task lifecycle, webhooks and cron-driven nudges.