Every /api operation is registered with Huma behind one admin-token
middleware, served at /api/openapi.json with a docs page at /api/docs,
and committed as api/openapi.yaml, which task check keeps current.
Credentials are typed (machine, age), write-only through the API and sealed
to the age identity in the bootstrap config. A field holds a value or names a
secret engine key; connectors and engines are accepted with credential slots
that resolve into their Configure secrets. The secret engine contract gains
secrets so an engine can receive its own key.
The agent model is an organisation setting in the new governance module.
Every model and tool call is a journal step, so a killed run resumes without
repeating either. Agents are offered connector lookups and read-only actions
only, until judgement exists.
Task containers log in with their run credential on an external broker and
reach only their own subjects, decided by the embedded broker's authenticator.
The broker token is never put in a container environment.
Container runtime policies gain a runtime (docker or openshell) and the
OpenShell gateway's address, workspace and token, set on the container
runtime page and applied on restart. The OpenShell backend creates a
sandbox per task with the worktree and volumes bound in, reports when
the agent exits or outlives its maximum uptime, deletes the sandbox on
release, and sweeps this instance's leftovers at boot. Storage volumes
are created attachable to OpenShell sandboxes.
Deletes the hand-written internal/tools/mcp client and transports. The
provider talks to an SDK ClientSession over CommandTransport,
StreamableClientTransport or SSEClientTransport, and reconnects when the
server exits. The http transport now keeps a real streamable session
instead of stateless POSTs. Sampling goes through one adapter, since the
SDK marks it deprecated (SEP-2577). message_endpoint is removed: the
SSE transport takes the POST URL from the server's endpoint event.
Removes the Kit task-tool result shim (and with it the MCP go-sdk
dependency), the messaging enable/disable/restart helpers and channel
rebuild closures nothing calls since channels became extensions, the
unused messaging capability, ephemeral and text-fallback types, and
single stragglers in telemetry, releaseupdate, skill, storepkg and
webui. The egress sandbox relay stays for #1867.
Archie runs its own agent loop only. Removes Kit resolution and launch,
the harness runner and adapters, the setup terminal and sandbox view,
harness secrets and OAuth capture (table dropped in migration 0075), the
task-tools contract that only Kit containers reached, and the
sandbox-kit-spec dependency. Agent profiles carry image and tools only.
The egress proxy keeps the model-session path; the sandbox relay code
stays for #1867.
The deploy gate's govulncheck step failed on the first run that reached it, for
two real findings: crypto/x509 in the standard library, fixed in go1.27.3, and
golang.org/x/net v0.61.0, reached from webfetch.htmlToText calling html.Parse,
fixed in v0.62.0. govulncheck now reports none.
Gemini 3.x/4 chat now routes through the Interactions API transport, which
replays thought signatures on tool turns; long decode stays opt-in. Also
takes go get -u updates (x/*, genproto, goose, nats-server, modernc sqlite).
The dependency bump moved sandbox-kit-spec from v3.0.0-m.6 to m.8 without
adapting the code, so the tree no longer builds: CredentialCapability.Phase
is now spec.Phases, not a string (internal/infrastructure/egress), and
Client.Assemble became a package-level fetch.Assemble that takes a Loader
and a LayerValidator instead of spec.MergeOptions (internal/infrastructure/
kitrun).
Migrating to m.8 is not a version-string change: m.8 pushes kit integrity,
safe layer extraction and resource limits onto the caller, so it is
security-relevant work, not an unblock. Pin back to m.6, which the code is
written against, and leave the migration to a deliberate change.
Verified: go build ./..., go vet ./..., go test -short ./... all pass with
this pin. The gate's ui:check and lint steps fail for unrelated
toolchain reasons recorded separately.
Bump github.com/samcharles93/ai-sdk v0.1.40 -> v0.1.41. ai-sdk now sends
max_completion_tokens for reasoning models and omits temperature when the
model rejects it, so the max_tokens workarounds are no longer needed: the
chat-turn bound is set directly and MCP sampling loses its reasoning
branch. Classic models keep their existing bounds.
A secret engine is now a subprocess serving secretengine.v1, installed through
the package store's new extensions family and enabled by extension-settings.
bws leaves the binary, as do the Yaegi engine loader and its examples.