The composer is the chat again: the old dashboard's chat, copied from
ui/src/chat and moved onto the chat module's API. It is the full /composer
page and a dock on every other page, with the session list, session menu,
left, right and floating positions and a full-screen sheet at phone width.
A message carries the page it was asked from and the page's suggested
prompts; a reply streams its thinking, tool calls and text, Stop cancels it,
and a message sent meanwhile is queued by the server. Workflow notifications
and approval requests show in the conversation as cards, and an approval is
answered only with its card's Approve or Deny.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- scaffold a React/Vite reference app under ui/astryx-reference with shell, composer, runs, and area pages
- wire @astryxdesign packages, a neutral-derived theme, and reference dev/build scripts
- document the astryx workflow in ui/AGENTS.md
Validate bearer tokens before header construction and return users to sign-in when a saved token contains unsupported characters.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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.
The run trail exposes the model request the journal recorded and its finish reason. Each model and tool step opens a Request and a Response, and each decision lists the connector calls behind it. The composer lists each delivery attempt with its outcome and response.
An action judgement holds at propose and wait is no longer a dead end. The
new approvals module owns the request: it binds to the decision and the
action's digest, so an answer covers the action the person was shown and
nothing else, and it settles once. The answer wakes the run, which judges the
action again and runs it only as the approval allows: a refusal still refuses,
an altered input runs nothing, and a judgement that came back worse runs
nothing on that approval.
The composer carries the request as a message with the request id and its
deadline, and its answer is a message too, so the trail shows what was asked
and what was answered. A request nobody answers inside its deadline is settled
as expired and nothing runs.
How long a request waits is an organisation setting, edited in the dashboard
and stored in milliseconds, because a Postgres interval scans as text. A run
pins the deadline it started with, like its model.
An agent that proposes the same action twice is asked about it once, and the
notification says when the investigation proposed nothing at all.
GET /api/runs/{id} assembles a run's trail from rows already kept: the event
and trigger that started it, each workflow step, and each model and tool call
from the agent's journal. Investigations end by notifying their findings on
the composer, whose messages are read from a cursor with a live stream that
only says when to read. The binary serves its own SPA entry, archie.html,
calling only the new API. The investigate prompt now treats the event as a
claim to check against what it measures.
The task session carries containers.egress_hosts and the profile's remote MCP
hosts, and the container gets ProxyEnv with the relay exempt from the proxy so
the State Store and NATS dials bypass it. A host the session lists exactly may
resolve to a private address; wildcard and any-host matches may not.
egress_hosts moves from openshell to containers, as it applies to both runtimes.
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.