The dashboard's setup terminal was a 503: it had a WebSocket route, an authorizer and an xterm.js surface, but nothing owned a container. The daemon owns containers, so the session contract lands there and the dashboard consumes it over a new gRPC contract. One session concept, two targets. A setup session is addressed by Kit profile and is ephemeral; a run session (archie-core-qi91) is addressed by task and attempt and is bounded by the task. This slice serves setup and answers Unimplemented for run. The contract, the authorisation, the lifetime and the egress phase are settled in docs/prds/external-agent-harness.md, "Session contract". The short version: the daemon serves harness.v1.HarnessService; the dashboard authorizes the operator as an update on the secret and then dials the daemon with the harness service token, required even on loopback because a session is a shell holding an org's credential; the setup container runs no worker, mounts no worktree, holds a keepalive, and carries an empty container environment. Install hooks run at the install phase and the session enters runtime before the shell, so a runtime-phase credential's token endpoint is the one the proxy intercepts. Capture is gated by the egress proxy on a granted service, and a setup session has no task, so the daemon registers a session grant: the session's proxy token resolves to the org's bindings for the Kit's declared services. The real token never enters the container: the token endpoint response is sentinelized and stored as the org's harness secret. Every teardown path releases the pool slot, revokes the egress session and the grant, removes the sandbox network, and removes the session's volumes. The listener requires HARNESS_TOKEN and stops with a 10s grace before Stop, so an open session cannot hold shutdown to the watchdog leash.
20 KiB
External agent harnesses
Status: Approved
Scope: the harness model and, in "Session contract", the duplex session
that the setup terminal and the run-scoped live view both use. Code cites
this file for both (ui/src/harness/SetupTerminal.vue,
internal/infrastructure/postgres/queries/harness_secrets.sql).
Decision
A workflow stage can run on an external coding-agent CLI instead of the built-in agent loop: Claude Code, Codex, Pi, OMP, GitHub Copilot CLI, or any other CLI packaged as a Docker Sandbox Kit v3. Each authenticates with an API key or the operator's subscription login, and can carry the operator's own skills, plugins, subagents and instructions.
Two boundaries hold regardless of what the harness does:
- The real credential never enters the container. The container sees sentinel values; archie's egress proxy substitutes the real credential on outbound requests and performs OAuth refresh on the host.
- Archie's workflow guarantees are enforced outside the harness. Git, protected paths, read-only stages, gates and budgets are checked by archie around the process and against the worktree afterwards.
Kits
A harness is packaged as a Kit v3 image: an OCI image whose
vnd.docker.sandbox.kit.descriptor manifest annotation declares what the
harness needs. Archie reads descriptors with the published
github.com/docker/sandbox-kit-spec/v3/spec package and does not maintain
its own descriptor format. Published Kits run unmodified.
Archie is a partial Kit runtime. It implements these capability types:
| Type | Archie behaviour |
|---|---|
credential@1 |
Proxy-managed only, described below. |
network-policy@1 |
Enforced by the egress proxy. |
volume@1 |
A Docker volume keyed by WorkflowExecution, deleted with it. |
lifecycle@1 |
Install and startup hooks run on container create. |
agent-sessions@1 |
The headless prompt and resume invocations for the stage. |
agent-skills@1 |
The operator's skills store (skills_dir), mounted read-only whatever the Kit asks. |
agent-context@1 |
The workload's profile file beside the workspace, indexing each Kit's guidance. |
resources@1 |
Container CPU and memory limits. |
Every other type fails closed: a required entry refuses the launch, an
optional one is skipped and recorded on the step. credential@1 with
passthrough: true and any credential for a forge service are refused.
The operator's own setup (plugins, subagents, instructions, settings) is a mixin Kit, published with the harness Kit as a Kit set: the set merges their layers into one image. It is versioned image content, rewritten on every create, never state a run can modify.
Contract
A harness run is a second implementation of agentexec.Runner. It takes the
same Request and returns the same Result, so workflows, the daemon and
the State Store do not know which runner ran a stage.
agent-sessions@1 supplies the invocation. Archie supplies, per CLI, an
output adapter that translates the CLI's JSON output stream into
ToolCallReporter calls, Usage and a session ID. A CLI with no adapter can
run stages with no capture tools, reporting no usage; its token budget falls
back to wall clock.
Workflow definition validation rejects, at load time, a stage whose needs the
selected harness cannot meet: capture tools without an adapter, or a gate
retry without a resume verb.
Selection
A harness is an agent profile. docs/prds/event-automation.md defines a
profile as the execution environment a workflow selects; a harness profile
names one Kit pinned by digest, a workload Kit or a published Kit set, in
place of a container image. Archie runs that Kit's image and composes no Kits
itself; a bare mixin is refused. Everything else about profiles
holds: a workflow names its profile, a stage may name a different one, and a
profile holds no secrets.
archie-agent builds the stage's runner from the stage's profile: the
ai-sdk agent loop for an image profile, the harness runner for a Kit
profile. Image profiles, and every workflow already written against them,
are unchanged. A Kit profile named by no workflow is a validation error.
A stage naming a different profile than its workflow's is a separate run,
not a mid-container runner switch: a Kit task runs in one container
provisioned for one profile (Container layout), so a stage that needs a
different one is its own callee, started the way workflow.call already
starts one (docs/prds/event-automation.md "Workflows call workflows"),
with its own agent profile resolved off its own task row. This needs no
mechanism beyond workflow.call plus per-task profile resolution
(daemon.pinTaskProfile), both of which already treat every task's
profile independently of any caller's -- see
TestWorkflowCallerConformance (staterpc) for the callee's independent
Workflow field and TestWorkflowCallGivesACalleeItsOwnProfile (daemon)
for the Kit-vs-image runner selection that independence produces.
Profiles are org resources in the State Store, so a Kit profile belongs to one org, is granted to its workspaces like any profile, and applies without a restart.
Organisations
docs/prds/orgs-and-access.md is the boundary; a harness adds nothing that
crosses it.
- A Kit profile, its credential bindings and its OAuth tokens belong to one org. No record is shared between orgs.
- A harness run is a run like any other: it acts as the workflow's identity, under the run credential issued at dispatch.
- The egress proxy injects a credential only when the run credential carries the secret the binding names. A Kit that declares a service the identity is not granted gets no credential: a required one refuses the launch, an optional one is skipped.
- A Kit's network policy is what the Kit asks for; the identity's network grants are what the org allows. The proxy enforces the intersection.
- Concurrency slots are counted per binding within its org.
Credentials
A credential binding maps a Kit's credential@1 service name to an org
secret, which the org grants to identities like any secret. The secret holds
one of:
- API key: a value in the org's secret store.
- OAuth: tokens captured by the setup terminal, stored in the State Store
under the at-rest envelope of
binding-secret-encryption.mdwith its own domain separator.
The egress proxy resolves the binding for each request against the run
credential. The container gets the Kit's sentinel in the named variable or
credential file. OAuth refresh happens at the proxy, which intercepts the
Kit's tokenEndpoint, so a refreshed token is written to the State Store and
never returned to the container.
Runs sharing an OAuth binding share its subscription's rate limit.
max_concurrent on the binding (default 1) caps its simultaneous runs. A
stage waiting for a slot is pending, not running.
Session contract
A session is a duplex PTY into a Kit container the daemon owns. One concept covers both targets; only the address, the lifetime and the established egress phase differ.
| Setup session | Run session (deferred) | |
|---|---|---|
| Address | {org, profile} |
{org, task, attempt} |
| Container | ephemeral, from the profile's Kit | the task's running container |
| Purpose | run the CLI's own login so the proxy captures the tokens | watch and optionally take over |
| Lifetime | bounded by the session TTL; the container is removed on close | bounded by the task |
- Transport. The daemon serves
harness.v1.HarnessService, a bidi gRPC stream, and the dashboard implements itsHarnessTerminalinterface (internal/webui) over that client; the browser's WebSocket route is unchanged. The contract lives on the daemon because the daemon owns containers: the dashboard process must not linkinternal/container,internal/app/archiedorinternal/agentexec. - Authorisation. Opening a session is the
updateaction on the secret, decided by the dashboard's authorizer before the route runs (internal/webui/authorize.go). The dashboard then dials the daemon with the harness service token. The daemon does not re-authorise a human; it trusts the asserted{org, profile}exactly as the task-action RPC trusts an asserted actor. Because that authority is a shell in a container holding an org's credential, the harness listener requiresHARNESS_TOKENeven on loopback, unlike the State Store's loopback convention. - Egress phase. Token interception is filtered by phase
(
oauth.go'srule.runtime == atRun), andEnterRuntimeis one-way. A setup session therefore follows a run's lifecycle exactly: install hooks at the install phase,EnterRuntimebefore the shell. A credential whose token endpoint must be captured declaresphase: runtime; a credential capturing at install phase is captured by the install hooks that run before the switch. - Credentials. Capture is gated: the proxy intercepts a token endpoint
only for a service the session is granted (
Proxy.granted). A setup session has no task, so the daemon registers a session grant: its proxy token resolves to{org, the Kit's declared credential services the org binds}. That is the intersection theupdate-on-secret authorisation covers. The real token never enters the container: the response is sentinelized and stored as the org's harness secret. - Container discipline. The setup container runs a keepalive entrypoint
with an empty
Config.Env; the PTY is an exec as the Kit's harness user with the harness env and nothing inherited from any worker. No worktree is mounted. It is acquired through the container pool, so it carries thearchie-daemonlabel, the concurrency cap and the max-uptime reaper; the session TTL is the smaller bound. Closing revokes the egress session, removes the sandbox network and the Kit volumes, then releases the container. - Kit unavailable. The daemon serves the contract only when it has a
container pool and a Kit launcher; otherwise there is no listener, and a
client's refused connection is gRPC's
Unavailable. The dashboard's existing failure surface is the honest degrade;/api/harness'sterminalfield means "a client is configured", not "the daemon can run a Kit". - Run target. Deferred (
archie-core-qi91).OpenanswersUnimplementedfor it in the setup slice. A finished or absent attempt will beNotFound, notUnavailable. - Audit. Opening and closing a session and a successful capture are recorded with the asserted org and profile.
Each session is the only interactive path into a harness container.
Egress
Only Kit profiles run on the egress path. An image profile keeps the network access its identity is granted, because workflows such as a network investigator need raw DNS, ICMP and arbitrary TCP that no HTTP proxy carries.
- Sandbox network. Each Kit run gets its own internal Docker bridge on which the host holds no address. Host services, including those listening on every interface, are unreachable from it by any address.
- Relay. One relay container,
archie-agent relay, sits on the sandbox networks under a fixed alias and on the host-reachable network. It forwards three fixed ports, to the proxy, NATS and the State Store, and can reach nothing else. It holds no secrets. - Proxy. The proxy runs inside
archied, listening on the host gateway of the host-reachable network. It terminates TLS with a per-daemon CA installed into the container at create, identifies the container by a per-run proxy token, and applies that run's network policy and credential inject rules. Upstream dials refuse loopback, and refuse internal addresses unless the policy names the exact IP, so an allowed name cannot resolve back into the host.
Container layout
A Kit task runs in one container, from the Kit composition's image, on the task's sandbox network. The worker and every harness invocation share it; they are separated by user, not by container, so a run's cost scales with the run and not with how many agents it fans out to.
- Worker. Archie mounts its own
archie-agentbinary read-only and runs it as the container's entrypoint, as root. It holds the task's NATS and State Store credentials in its own environment and in root-only files, runs the workflow, and servesarchie-agent mcp. The Kit image's entrypoint is not PID 1. - Harness. Every invocation runs as the Kit's user (the image's
User, default uid 1000) with an explicit environment: the Kit's variables, the proxy environment and the credential sentinels, and nothing inherited from the worker. That user cannot read the worker's environment or files, or trace it. Sibling invocations in one run share the user and the worktree. - Hooks.
lifecycle@1install and startup hooks run as the user each declares, before the worker accepts work. - Mounts. The task worktree at the Kit's workspace directory, owned by the Kit's user, and the read-only skills store. Nothing else from the host.
- Network. The relay forwards three fixed ports on the sandbox network: the egress proxy, NATS and the State Store. The worker reaches NATS and the State Store with its credentials; a harness can open those ports but holds no credential either accepts.
- Volumes.
volume@1paths persist for the life of the WorkflowExecution, which covers session resume across gate iterations and retries. They are not shared between executions.
Archie tools inside the harness
Capture tools, which are how a stage returns structured results, are served
by archie-agent mcp, a stdio MCP server registered through the Kit's MCP
configuration or the adapter's flags. It serves the stage's CaptureTools
and the central tools the agent profile's AllowTools permits, never the
workspace toolset. The runner's ToolLimits bound its results; the
harness's own built-in tools are outside archie's limits.
Enforcement around the harness
| Property | Enforcement |
|---|---|
| Model never runs git | No forge credential can be bound. Archie records HEAD and every ref before the run; any change fails the step (failed, policy class). The workflow commits the stage's changes. |
| Protected paths | A diff touching a Protection path fails the step. |
| Read-only stage | Any worktree diff fails the step. |
| Gate | Archie runs the stage's gate after the harness exits. On failure it resumes the session with the gate output, up to the stage's iteration budget. |
| Budget | Archie kills the process on wall-clock timeout, or when streamed usage passes the token budget. |
| Cancellation | Cancelling the step kills the process group, then the container. |
| Egress | Only the proxy is reachable; the Kit's network policy decides the rest. |
Harness settings that deny git or protected paths are added where the CLI supports them, to save wasted turns. They are never the enforcement.
Execution tree
A harness run is one agent StepExecution. Subagents the harness spawns
internally are not recorded as children. Their usage is included in the
step's tokens_used when the adapter reports it.
Agents never hold a harness
An Agent reaches a harness only by invoking a Workflow whose stage names it. No Agent tool, chat tool or capability exposes a harness, its setup terminal or its credential. The stage boundary is what carries the container, the git and path checks, the gate and the budget; a harness outside a stage has none of them.
Out of scope
- Chat through a harness. The gateway chat loop stays on the built-in runtime.
network-policy@2HTTP method and path rules; a Kit requiring it is refused.- Recording the harness's internal subagents as StepExecutions.
- Cost in currency.
- Choosing a harness automatically per task.
Plan
- Descriptor resolution with the Kit spec package; capability support table and fail-closed refusal.
- Egress proxy: internal network, per-daemon CA, per-container token,
network-policy@1. credential@1: API-key bindings, sentinel rendering, inject rules.- Harness
Runner: container create with worktree, volumes, lifecycle hooks and the mountedarchie-agent;agent-sessions@1invocation; worktree checks for git, protected paths and read-only; budget and cancellation. - Claude Code output adapter;
archie-agent mcp; gate-and-resume loop. - Kit profiles, runner selection from the stage's profile, and definition validation.
- OAuth bindings as org secrets: token-endpoint interception, encrypted storage, per-binding concurrency; dashboard setup terminal.
- Output adapters for Codex, Pi, OMP and GitHub Copilot CLI.
Verification
- The same workflow definition completes on
builtinand on the Claude Code Kit with the sameResultshape and captures. - After
/loginin the setup terminal, the container's credential file holds only sentinels, the State Store holds the encrypted token, and a task run authenticates. - A real API key or OAuth token never appears in the container environment, filesystem, worktree, task log or event stream.
- A request to a host outside the Kit's runtime allow list fails, including a direct connection that bypasses the proxy settings.
- A harness instructed to
git commitfails its step, and the task branch is unchanged. - A harness edit to a protected test file fails the step in a TDD fix stage.
- A read-only feasibility stage that writes a file fails.
- A file a run writes into a Kit-managed path such as the CLI's settings file is gone on the next execution.
- A Kit requiring an unsupported capability is refused at launch with the capability named.
- A stage with a failing gate resumes the same session with the gate output, then succeeds or exhausts its iterations.
- Two tasks sharing an OAuth binding with
max_concurrent = 1run one at a time; the second waits aspending. - Stopping a run kills the harness process and removes the container.
- A harness invocation cannot read the worker's NATS or State Store
credential from its environment, its files or
/proc. - A run fanning out to many agent invocations uses one container.
- A Kit profile in org A cannot be selected, and its binding cannot be resolved, by a workflow in org B.
- A harness run whose identity is not granted a Kit's required credential is refused at launch; the proxy never injects a secret outside the run credential.
- The firewall investigation example runs unchanged on an image profile with direct network access.