Commit Graph
587 Commits
Author SHA1 Message Date
sam bb0d7fa8d0 feat(archied): raise an alert when container max uptime is under the task limit 2026-10-26 19:48:09 +11:00
sam 8bcd89e050 fix(gateway): name a plan wait's workflow from its run, not the next one
workflow.approve pre-writes the task's workflow column with the workflow
that runs once approved, so task_list named a workflow that had not
started while the task's own log named the one that produced the plan.
Chat now names the compiled workflow through the pinned definition for a
plan wait, matching the log.
2026-10-26 18:32:25 +11:00
sam b6b13ea97c fix(archied): bound task titles in chat notifications 2026-10-26 18:32:25 +11:00
sam 660e97f87e fix(taskactions): let the operator chat act on every task, like the dashboard
A chat profile bound to the operator identity passed a strict scope to the
action gate, so it refused root-owned tasks whose identity is the daemon's
empty sentinel (task 22: belongs to "", not "d898c8c8-..."). The dashboard
acts with a nil scope and the chat read paths already treat the operator as
acting across identities, so the write gate was the only surface that disagreed.

Exempt the operator identity from the scope comparison and share that rule with
the chat adapters that had their own copy.
2026-10-26 18:24:47 +11:00
sam 877d45f275 fix(container): report a crashed container's panic line and log its stderr 2026-10-26 18:24:46 +11:00
sam 0f75475b91 feat(ui): schedules table, runs page and Schedule trigger
Schedules list as a table with enable, run now, edit, duplicate, delete and
view runs; built-ins only enable, retime and run. The runs page links each
run's tasks through its capture's dispatches. The Start node gains a Schedule
trigger that picks or creates a schedule and binds the schedule source to the
workflow. Times show in a per-browser display zone set under Appearance; the
cron time zone and run retention are edited on the Schedules page.
2026-10-26 00:57:52 +11:00
sam 8026c07319 feat(workflow): message.send step delivers text through archied's messaging client 2026-10-26 00:56:07 +11:00
sam 87ac7b693c feat(archied): run daemon maintenance as built-in schedules 2026-10-26 00:51:53 +11:00
sam cc5789eb5f feat(scheduling): schedules and runs in the State Store with grid timing and run history
Schedules leave the schedules control-plane resource for State Store tables
behind a ScheduleService contract. A run is claimed per schedule slot, missed
slots fire once, the next run stays on the schedule's grid, cron is read in the
schedule-settings time zone, and failed runs are recorded and advance. Three
failures in a row raise a schedule.failing alert. A fired run records a
schedule-fired capture. Run history is pruned by age and count.

Removes the chat and spawn-task runners, the dangerous-payload guard and the
old schedules settings page.
2026-10-26 00:49:24 +11:00
sam e951dbd6cd fix(extension): log go-plugin output through the service slog logger 2026-10-26 00:25:37 +11:00
sam 220302b41e fix(logging): route ui, messaging and playbook logs through the service log 2026-10-26 00:18:39 +11:00
sam 97655323b9 refactor(logging): log with the caller's context so records carry trace ids 2026-10-25 23:30:01 +11:00
sam b1ef0be333 feat(llm): trace model and tool calls via ai-sdk v0.5.0 2026-10-25 23:19:40 +11:00
sam 812f1bdd9e feat(agent): export container spans over NATS through archied 2026-10-25 23:17:34 +11:00
sam 4b7e843ead feat(servicekit): OpenTelemetry tracer provider and RPC propagation 2026-10-25 23:11:03 +11:00
sam 74b11b331d feat(natsrpc): propagate trace context across NATS and into task runs 2026-10-25 23:03:55 +11:00
sam 72f833db09 feat(logging): stamp trace and span ids on log records 2026-10-25 22:55:57 +11:00
sam 29a2a782c9 refactor(controlplane): move the store-backed server out of internal/app 2026-10-25 22:49:27 +11:00
sam 81f379346e fix(channelext): bound the extension broker server with service limits 2026-10-25 22:46:47 +11:00
sam 3912d7e3e0 fix(audit): harden export, scope history and derive feed targets 2026-10-25 22:39:22 +11:00
sam c95ff24f23 feat(webui): audit feed API, export and read_audit grant 2026-10-25 22:01:02 +11:00
sam 763053e698 feat(state): audit retention resource and observability sweep 2026-10-25 21:53:29 +11:00
sam 7cdd1d11b0 fix(state): retain product-read events and normalise audit retention 2026-10-25 21:53:19 +11:00
sam 3c0f0fc2d3 fix(archied): drop a cached extension binary when its start fails 2026-10-25 21:47:31 +11:00
sam c07ccc22ff perf(archied): reuse running forge extension instances and materialized binaries 2026-10-25 21:46:51 +11:00
sam 5705833c0b feat(state): apply audit retention to observability events 2026-10-25 21:42:38 +11:00
sam dd9b378431 feat(state): org-scoped audit feed contract and read model 2026-10-25 21:23:52 +11:00
sam 9bedaaefb4 feat(state): org-scoped audit trail and complete policy write audit 2026-10-25 20:49:20 +11:00
sam a971947c39 refactor(state)!: split StateStoreService into per-domain services
One gRPC service per domain in state.v1 (tasks, executions, accounts, identities, packages, captures, bindings, access, orgs, alerts and so on), each with its own server type in staterpc. RPC and message names and numbers are unchanged.
2026-10-25 19:54:27 +11:00
sam c265b07ec7 refactor(workflow): stop assuming a human decides
An approval, ask or park can be resolved by an operator, a rule, a
classifier or automatically, so the vocabulary stops naming a person:

- step type human.approve -> workflow.approve
- park class needs_human -> needs_decision (ParkNeedsDecision)
- event kinds human_* -> operator_*
- alert kind task.needs_human -> task.needs_decision
- status grouping "needs you" -> "needs attention"

0061 rewrites the stored values, including the approval step type in the
workflow-definitions resource and each task's pinned definition, with the
digest recomputed so resumed tasks still match.
2026-10-25 17:31:16 +11:00
sam 5f3cceb940 feat(modelloop): run a step's tool calls in parallel as each tool's classification allows 2026-10-25 16:45:34 +11:00
sam 5c922038f9 fix(access): check the policy version before each decision
archied, archie-ui and the tool gateway re-read the stored policies on a 30s
ticker, so a forbid written seconds earlier did not stop a run. One
instance-wide revision now moves inside the transaction of every policy write,
and a decision reads it first and rebuilds the engine only when it moved.

A version read that fails, or a policy list that fails after a bump, refuses
with ErrChainUnavailable instead of standing on the last chain, so three call
sites now treat unavailable as availability rather than denial: dispatch leaves
the capture for the next cycle, a task start parks transient, and the tool
gateway reports the tool as unavailable.
2026-10-25 16:21:01 +11:00
sam 64ab228658 feat(egress): record a test run's deliveries instead of sending them
A test run used to suppress only forge and push writes, which named one
destination among many. Deliveries now have one seam: TaskContext.Deliveries
records each as "would ..." and performs none, and a recording egress
session does the same for a Kit run's HTTP writes and central tool calls,
answering them synthetically. Provider hosts stay live, since model traffic
is how a test run reads. Native containers have no proxy (archie-core-n8d3).
2026-10-25 16:01:06 +11:00
sam d2cbe25814 fix(daemon): archied --once drains until callees of a waiting call finish 2026-10-25 02:46:16 +11:00
sam 6f0ea530aa fix(archied): post each reportable status a chat task reaches, recorded by status not by flag 2026-10-25 02:42:31 +11:00
sam 55e68f536b feat(archied): tell the chat when its task opens a pull request 2026-10-25 02:39:34 +11:00
sam 6a412a3b24 feat(archied): post approval requests to the chat that started the task 2026-10-24 23:59:25 +11:00
sam c7c1861ee7 refactor!: waiting_human becomes waiting_approval, with the approval kind on each task 2026-10-24 23:45:20 +11:00
sam 751081cb46 fix(archied): post dashboard chat task outcomes into the conversation through the gateway 2026-10-24 23:22:11 +11:00
sam 83e1e1cfb1 feat(archied): update agent-image sets the image new tasks run 2026-10-24 23:16:13 +11:00
sam 7abc816735 refactor!: remove the diff-size cap and its gate.diff-size step 2026-10-24 22:19:23 +11:00
sam 4719b9cf00 feat(chat): show each tool call where it happened in the reply 2026-10-24 20:48:43 +11:00
sam c6c4f36a09 feat(gateway): record how long each chat tool call took and show it per row 2026-10-24 20:44:40 +11:00
sam e65855ce26 fix(archied): stop retrying task outcomes for a channel messaging does not have 2026-10-24 17:02:50 +11:00
sam b2e1810bd6 fix(archieui): reach the sandbox and setup terminal on the daemon's listener 2026-10-24 11:24:49 +11:00
sam dc8ddce89a fix(configuration): keep named instances under the archie- namespace 2026-10-22 17:38:40 +11:00
sam 1528b8d739 fix(daemon): relay a loopback State Store with external NATS, and only for the task's container 2026-10-22 17:35:24 +11:00
sam 7140af08d8 fix(archiegateway): confine non-operator chat identities to their own tasks 2026-10-22 17:32:55 +11:00
sam 12cc06271d fix(controlplane): keep an org's own provider credential reference 2026-10-22 17:31:54 +11:00
sam b4d8bb702e fix(egress): bind a task's model providers from their api_key_ref
A container task parked when a provider carried an api_key_env but no
credential binding named after it, even though the task's models never
reached that provider. Egress pre-bound every provider the instance
configures and ignored api_key_ref, so the credentials an operator stores in
provider-settings were never used.

A task's config now carries only the providers its model aliases resolve to,
each with the variable its credential is read from: the operator's
api_key_env, or a name derived from the provider when its credential is a
secret reference. modelEgress resolves that reference once for the session
and the proxy substitutes the session's key for the sentinel, so the
container still holds no key. A provider that only declares an env var keeps
resolving through its org credential binding.
2026-10-20 06:56:38 +11:00