people_named_to decides whom the edit page and the share dialog name:
the reader, the holder's owner, anyone sharing a team with the reader and,
for the owner, whoever sponsored something on the holder. A resource's
owner, named as whom to ask or whose credentials a tool uses, also needs
the reader to see that resource. Sponsors, runs_as, contact and account
in resource_states and sponsors in sponsor_details all follow it; anyone
else is left unnamed and the pages say someone else.
A tool's run details (note, credential_mode, account, writes) come from
one function and only for a tool that runs. The share dialog keys each
person's own account on the per_user_account note, as the notice does,
and the unused noteKey helper and its string are gone.
Only removing a connection notes it on a kept tool. A config save through
update_tool or update_tool_config carries the stored note and ignores the
client's copy, so it can neither fake nor clear it; creating a tool, an
MCP server save and an agent import start without one. The note is now
written even for a connection with no catalog key, and a kept tool its
owner gave credentials of its own since runs again.
A member-mode tool runs on each caller's own account, so the owner's
account no longer marks it stopped: it is active with the note
per_user_account, and only an admin turning its service off stops it.
connection_removed now needs the note remove_connection leaves on a kept
tool, so a tool that never had a connection (a tokenless ntfy) runs.
Whom to ask is contact_role resource_owner; contact names them only when
the reader can see the resource or they own the holder. connection carries
its id only with can_reconnect and the account's own name only for its
owner. Run state and audience are best effort (a failure logs and leaves
them out of the read), resolve answers are cached for the rest of a read,
and a workflow read names node resources by the run state's own names.
resource_states gains runs_as, the live sponsor a running item runs as
(None once the owner can use it, even with a sponsor on record), and
writes_allowed, False when an admin turned off changes through the
tool's connector (its writes are then not listed for the allowlist).
account now also names the owner of an API tool's saved key, a signed-in
MCP server or stored secrets, not only of an owner-mode connection, and
only to a reader who shares a team with that person. A running tool's
connection id is no longer sent.
resource_states now carries, for a running tool, its credential mode when
it has a connection (after any mode an admin forces), whose account an
owner-mode connection acts as, and the write actions it takes on
credentials its owner stored, which API, widget and public-link users can
run only from the agent's API write allowlist. The service of a connected
tool is named whether it runs or not. Still only for people who may edit
the agent or workflow.
The agent and workflow reads now return resource_states to people who may
edit them: every attached tool, source and prompt (and workflow node tool
and source) with active or stopped and the reason: deleted,
owner_lost_access, the sponsor reasons, connection_needs_reconnect,
connection_removed or connector_disabled. Each entry names the sponsor,
someone other than the reader who can fix it, the service for a connection
reason, and whether the reader may take it over or reconnect it. When
something can be taken over, sponsor_audience says who it would reach.
The state comes from the checks the run itself uses (ref_access,
resolve_holder_tool and the tool's connection as the run resolves it), so
the page and the run can't disagree. A run that leaves a resource out logs
resource_stopped with the holder, type, id and reason.
The workflow read gives sponsor details, run state and node resource names
only to people who may edit it, and names only resources the workflow runs,
someone sponsored, or the reader can see. Owner saves and new workflows
now refuse node tools and sources the owner can't use, like editor saves.
A resource attached in a save now ignores any sponsor recorded for it
before it was removed: the caller must be able to sponsor it and confirm.
YAML import prunes the sponsors of resources it drops, for agents and
workflow graphs. Sponsor details, with the resources' names, go only to
people who may edit the agent. The workflow read returns the names of
every node tool and source, so editors can remove the owner's private
ones. An agent image is stored only once the save is known to go ahead.
A paused turn is found by the agent owner's id, so anyone holding one of
the owner's agent keys could resume the owner's own chat with its saved
wiki edit rights. A resume now counts as an API or widget caller when
either the saved state or the resuming request is one, cuts the wiki tool
to wiki_view unless the wiki allows outside edits, and gives the tool
executor the same flags. A request that names an agent, by key or id, may
only resume that agent's turn; otherwise the claim is released and the
request refused.
Public-link visitors run as themselves and reach only wikis they may edit,
so the wiki switch no longer applies to them. Instead every wiki write in
a public-link run waits for the visitor's approval, so the agent owner's
prompt or sources can't steer an edit to the visitor's wiki unasked.
Sponsoring a tool, source or prompt the agent's owner can't use now takes
owning it or having edit access to it; use access alone no longer extends it
to the agent's audience. A save that would make the caller a new sponsor is
refused with 409 sponsor_confirmation_required (the resources and the
agent's audience) until it is retried with confirm_sponsor listing them.
When a sponsor loses access, the resource stops instead of passing to
whoever saves next; another editor takes it over only by confirming.
Workflows follow the same rules. sponsor_details now reports each
sponsorship's state, the reason it stopped, and whether the reader can
take it over.
A run from an agent's API key or widget acts as the agent's owner, so it
could rewrite any wiki the owner can edit. A new per-wiki setting,
wiki_outside_edits (off by default), decides whether such runs, and runs
from the agent's public link, get the wiki's edit actions. While it is off
they are offered only wiki_view, and the tool refuses writes itself after
reading the live setting. The owner changes it through the owner-only
/api/sources/<id>/wiki/settings route; tokens can read it but not change it.
The answer routes refuse such a request with 401, but only after building
the agent, so a public agent's prompt tools were pre-fetched, and their
actions run, for nobody. Anonymous chat without an agent key is not
supported, so the processor now stops before any setup and the route
answers 401 as before.
A scheduled or webhook run acts as the agent's owner with no one to
approve, so a public-link user or API-key caller could have the agent
schedule a write and have it run on the owner's accounts. Runs now keep
the caller's rules: a schedule set by someone who reaches the agent only
by its public link runs as a public-link caller, one set through the API
(recorded as created_via 'api', migration 0042) and every webhook run as
an external caller, each with the agent's API write allowlist.
Pre-fetch judged someone else's tool by its stored approval flags, which
a remote device or the code executor decides per call, and it took a
widget or API run for the owner because the run carries the owner's id.
Those tools no longer pre-fetch for anyone but their owner, an API-key or
public-link run treats every tool as someone else's, and writes with the
owner's credentials are never pre-fetched for them.
API-key, widget and public-link callers were held to the write allowlist
only on connected accounts, so they could still write through an API
tool or a signed-in MCP server that carries the owner's credentials. Any
write on credentials the caller doesn't hold is now refused unless the
owner allowlisted it, and a scheduled run for such a caller counts as not
holding any. The tool list names these writes per tool, so the allowlist
can offer them, and its copy now names every route it covers.
The /v1 route runs with the agent owner's token, so the processor took a
key holder for the owner: writes on the owner's connected accounts ran or
waited for an approval the client could send. The route now marks the
processor as an external caller server-side, which keeps the allowlist
in force for the run and any resume, including state saved before.
Callers that build a StreamProcessor without __init__ and stub the agent
key lookup never set the flag, and configuring the agent then failed.
It now reads as not a public-link caller.
Headless runs searched only the agent's primary source, so an agent whose
knowledge sat in its extra sources answered a schedule or webhook without
it. They now take the primary and every extra source through the same
owner-or-sponsor check a chat uses, shared as one helper, and retrieve
through the per-source dispatcher so each source keeps its own settings.
Tool pre-fetch ran the caller's own active tools, so a teammate chatting
with a shared agent had the owner's prompt fill in from their tools, and
even the owner got every active tool rather than the agent's. It now uses
the toolset the run gets: the agent's tools as its owner or sponsor, or
the caller's tools and defaults outside an agent. Pre-fetch asks nobody,
so on someone else's tool it skips approval-gated actions and anything on
a connected account.
Someone who reaches an agent only through its public link was offered the
approval card for writes on the owner's connected accounts, so a stranger
could approve for the owner. Those writes are now refused with a tool
result, like an API-key caller's, unless the owner allowed the action in
the agent's Access details. Team members keep the card, and a tool on the
caller's own account (member mode) is unaffected. The flag survives a
resume, and workflow nodes now follow the run's caller rules (scheduled,
API-key and public-link) instead of starting from none.
/api/update_tool now checks submitted actions against the stored ones the
same way /api/update_tool_actions does: nothing can be added, and only the
tool's owner can change a fixed value. The tool type (name) can no longer
be changed after creation by anyone.
For API tools, changing who fills an existing header, query or body
parameter, its value, or clearing a stored value is now owner-only on both
/api/update_tool and /api/update_tool_config. Before, an editor could hand
a stored secret query value to the model and read it back in the chat.
The chat now masks every value that came from the stored action rather
than from the model.
A connection-backed MCP tool can no longer be moved to another server or
sign-in method through /api/update_tool or /api/update_tool_config (400,
pointing to /api/mcp_server/save), and a new key saved through
/api/update_tool_config goes to its connection, owner only.
Main's access model (team editors and viewers, edit_credentials, owner-only
OAuth servers, per-user tool preferences, resource sponsors) now applies to
connection-backed tools and sources. Our migrations are renumbered to
0040_connections and 0041_connection_account_name, after main's
0038_resource_access_settings and 0039_resource_sponsors.
Where the two sides met: MCP tools save and load their connections as the
tool owner, editors may add a key (a new connection on the owner's account)
but never rewrite an existing connection's secret, fixed values stay
owner-only, and a member's own connection is used in member mode.
After removing a Linear connection, connecting again could skip signing in
and save Linear as an unconnected custom tool: a client cached before the
removal still held the old tokens, and a late token write re-created a
connection for them. A token write for a named connection no longer creates
one, removing or disconnecting a connection drops its cached clients, and a
sign-in server is never saved without its connection.
The connection setup endpoint takes sync.config, validated like an
upload's config, and passes it to the ingest task so the synced source
gets the chosen chunking and retrieval settings. An invalid config is
refused before the idempotency key is claimed.
The Linear connector now syncs as well as giving agents its tools, from
one connection. Linear's MCP server is its own OAuth issuer, so its
tokens are read through the same MCP tools the agents use (list_issues,
get_issue, list_comments, list_documents) rather than Linear's GraphQL
API, and no OAuth app has to be registered.
A source picks teams and projects, with comments (on by default) and the
projects' documents. Each issue becomes one document with its state,
assignee, priority, labels, description and comments, filed under its
team and citing its Linear URL. Each sync reads up to 500 issues and 100
documents again. /api/connections/<id>/linear lists the teams and
projects to pick from. Sources sync on their schedule with the owner's
connection, and pause when the sign-in needs reconnecting.
A GitHub connection's MCP tool can now point at GitHub's full endpoint
(/mcp/) instead of the read-only one when its owner opts in, at setup
(allow_writes) or later (PUT /api/connections/<id>/writes), which re-reads
the actions and keeps the choices for those on both endpoints. Actions from
the write endpoint are writes unless GitHub marks them read-only, so they
default to asking first.
Admins can forbid it per connector (allow_writes in Admin > Connectors,
kept in app_metadata). Then the option is refused, a refresh goes back to
read-only, and at run time the tool only ever calls the read-only endpoint
and write calls are denied with a reason.
Connections get an account_name (migration 0039) that the owner sets with
PATCH /api/connections/<id>; the account label stays the account's
identity, so signing in again still finds it. When someone has more than
one account of a service, its tools are listed as "Telegram · <account>"
and the model sees each account's actions under the account's name
(telegram_send_message_alerts_bot) with the account in the description,
instead of _1 and _2. Actions shared by different services are named
after the service. Tools a user renamed keep their name.
A Telegram connection can now hold an optional default chat ID. When it
is set, both Telegram actions send there, the model is no longer asked
for a chat, and a chat it names anyway is ignored. In member mode each
member's own connection supplies their own chat. The same bot with a
different chat is a separate connection.
PUT /api/connections/<id>/tools/<tool_id>/parameters takes an action and
a map of parameter to value (always use it) or null (let the model
decide), checked against the action's schema; only the tool's owner can
call it. Connection tools now list each action's parameters and whether
they are fixed.
update_tool_actions now checks the submitted actions against the tool's
stored ones: no new actions or parameters, fixed values must fit their
parameter's type. A team editor can still switch actions on and off but
gets 403 for changing a fixed value.
The admin connectors API lists the settings that add Sign in with GitHub
and whether they are complete, next to the required settings (none for
GitHub, which works with tokens alone).
One GitHub connection feeds both a Knowledge source and an agent tool.
Users connect with a personal access token, checked against GitHub and
named after the account, or, when an admin registers a GitHub App
(GITHUB_CLIENT_ID, GITHUB_CLIENT_SECRET, GITHUB_APP_SLUG), with Sign in
with GitHub. App tokens expire after eight hours and are refreshed before
each sync or tool call; tokens with no expiry are never treated as expired.
The catalog gains an optional second sign-in method (oauth_settings,
exposed as sign_in_methods) without changing any other connector.
Sync lists the repositories the connection can read (the token's own, or
the App installations') and ingests one with the connection's token. The
tool is GitHub's read-only MCP server (api.githubcopilot.com/mcp/readonly):
setup discovers its actions and creates it bound to the connection, and
the executor sends the connection's token only to that server.
GITHUB_ACCESS_TOKEN belongs to the server, but any user could ingest any
repository it can see, private ones included. It is now used only for
public repositories; the loader checks the repository's visibility first
and asks for a GitHub connection otherwise.
The loader also takes a token from the connection a source syncs from.
Merging a connection's keys into a plain repository URL no longer fails
on json.loads, manual Sync now passes the source's connection, and a
token GitHub rejects pauses the connection's sources for reconnect.
mcp 2.x reads code, state and the RFC 9207 iss off the callback handler's
result; the handler still returned a (code, state) tuple, so every MCP
sign-in failed after the user approved it. The callback route now keeps the
issuer too, since servers that advertise it (Linear) refuse a sign-in
without it.
The client follows an MCP sign-in by its task's events, but the test route
kept only success, requires_oauth and auth_url, so the wizard and the custom
MCP modal reported a failed sign-in before the popup could load.
- One control for members' own MCP servers: the custom MCP server row's
switch (it sets both the policy and the instance switch); the separate
top-level switch is gone.
- Connectors that only sync content show "No tools" instead of a
sharing policy, and the policies read "The sharer decides per share",
"Always the sharer's account", "Always each person's own account".
- A connector that needs server settings can't be switched on until they
exist; a tooltip says why.
- On phones the table becomes a list ("On · 2 connections · …") and each
connector's controls open in a sheet.
- Add Source hands a connection tile to the connect wizard: an existing
account goes straight to choosing what to sync, otherwise it connects
one. The legacy per-service forms stay only for installs without
connectors, so S3 no longer has two different forms.
- Add Tool lists services from the connector catalog first, MCP presets
included, each with its connection state; a connected one opens its
drawer, the rest start the wizard. Built-in tools follow.
- Service tools carry the connector's name everywhere ("Telegram", not
"Telegram Bot"), and the composer groups custom tools (API tool, MCP
servers) as Custom, like the agent builder.
- OpenAPI opens the API tool editor as an unsaved draft; the tool is
created on its first save, so exploring the menu leaves nothing behind.
Notion, Linear, Atlassian, Sentry, Asana and Stripe no longer open the
MCP server form. The wizard shows one "Sign in to Notion" button: the
pop-up opens inside the click (so browsers allow it), follows the
worker's mcp.oauth events to the provider, and the tool is saved on
success with its actions on the done step. Reconnecting a preset uses
the same flow, as do the chat bar and the health toast.
Saving an OAuth MCP server without a new handshake now uses the stored
sign-in instead of failing, and the custom MCP form keeps scopes and
timeout under Show advanced.
An agent called with its API key (widget, API) runs as its owner, and
nobody can approve an action there, so a write set to Always allow ran
on the owner's account for anyone holding the key. A caller is external
when the request carries the key and is not signed in as the owner (an
owner previewing their agent keeps full access).
For external callers, write actions on connection-backed tools are
refused unless listed in the agent config's new api_write_allowlist
(tool_id:action), and a missing connection is refused instead of pausing
on a Connect card the widget cannot show. The flag and list survive a
paused-and-resumed stream. Owners pick the allowed actions under Access
details; a team editor's update keeps the stored list.
A connector's enabled switch is now optional: unset means on when the
connector has the server settings it needs, so Google Drive, SharePoint
and Confluence start off until their OAuth settings are present, and an
admin's explicit switch always wins. Changing only the sharing mode no
longer switches a connector on.
Members only see connectors they can use. The catalog, Add Source tiles
and Add Tool leave out anything turned off or still needing setup, except
a connector a member already has a connection to, which stays listed as
turned off so it can be managed or removed.
- Creating a tool from an existing connection validates its config too;
the connection supplies the secrets the request leaves out.
- When the connector policies cannot be read, the MCP test and save
routes answer 503 instead of contacting the server.
- Editing a connection-backed tool validates the config before writing
new credentials, so a rejected edit no longer rotates the connection's
key and resumes its sources.
- An MCP edit keeps its previous connection only when the caller owns it
and it signs in the way the tool now does.
arc53-machine