Commit Graph
1972 Commits
Author SHA1 Message Date
sam b9dd744f8c fix(pg): number the action classes migration after the schedules one, so it applies in order (archie #2003) 2026-11-16 04:37:11 +11:00
sam a91df7ec1f feat(judgement,approvals,ui): action classes are records with a level, history and reset; the precedent guard reads the class level (#2003) 2026-11-16 04:35:12 +11:00
sam 5712c9c4e6 feat(events,approvals): triggers fire on an interval, and an expired approval is escalated on every channel (archie #1992) 2026-11-16 04:33:28 +11:00
sam 1f5163092b feat(runs,approvals,ui): a run's trail joins each action's verdicts, approval and effect, and the run view shows them in order (archie #1996) 2026-11-16 04:33:27 +11:00
sam 1b8eb362d2 fix(prompts): the agent calls a lookup it would recommend instead of ending on it (archie #1999) 2026-11-16 04:24:38 +11:00
sam 7903a0e225 feat(connectors,deliveries,events): channels are connectors that deliver and listen; messages retry from their rows, and answers arrive as events (archie #1984, #1985) 2026-11-16 04:22:52 +11:00
sam 0238f247e5 feat(approvals): a held action is asked of a person, and the run waits for the answer (archie #1985, #1999)
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.
2026-11-16 02:21:06 +11:00
sam 200c6d0928 fix(prompts): the investigate prompt tells the agent to call the action it recommends (archie #1999)
It also said its tools only read, which stopped being true when actions became tools. Judgement decides whether an action runs, so calling one is the proposal.
2026-11-16 01:39:32 +11:00
sam 0dbf241106 feat(judgement): the weakest-link decision, and executing only what was judged (#1986, #1989, #1990, #1988)
A new judgement module assesses one concrete action: hard rules refuse before
any guard runs; every guard sets a ceiling and the action runs at the lowest;
a guard that fails, panics or gives no ceiling holds it at propose and wait;
an advisory verdict is recorded and sets no ceiling. Reversibility and
Precedent (the fresh-install class default) are the first guards. Every
decision is recorded with its verdicts and class, and the run's trail lists
them. Agent tools now offer connector actions too: each call is assessed and
executed only as decided and only with the judged input, and a held action
comes back to the agent as a failed call naming its level and findings.
Tools gain Resolve, so an MCP server's declared effect reaches judgement.
2026-11-16 01:05:29 +11:00
sam 4877362223 fix(runs): a step hands back its value as recorded, so a resumed agent doesn't diverge from its journal (#1977)
Killing the binary mid-investigation and restarting it failed the run: the
first model request after the resume didn't match the recorded one. The tool
schemas pinned in a step reached the live attempt as written but the resume
as stored, and both the v2 encoder (compacting raw JSON) and jsonb (reordering
keys) rewrite them. Step now returns the decoded recorded value on the live
path too, and runs.steps.output is json, which keeps the text as written.
2026-11-16 00:36:19 +11:00
sam eb9d470ba8 fix(runs): the forecast figure is in hours, so the model doesn't convert it (archie #2005) 2026-11-16 00:16:14 +11:00
sam a3d32e92e5 feat(runs): the investigate prompt names the labels and the figure (archie #2005)
An alert about a filesystem carries instance and mountpoint, and those are the
labels the forecast query needs, so the prompt names both and gives the query
that answers what an operator asks: the seconds until the disk is full, from
predict_linear and deriv over the same window. A negative figure is the
filesystem not filling, which the prompt says to report as that rather than as
a time.
2026-11-16 00:13:13 +11:00
sam 6d97f62929 fix(runs,pg): grant the runtime role on sequences, and read a missing result as null (archie #2005)
Two faults stopped an investigation from finishing on staging.

The runtime role was granted DML on every table but nothing on sequences, so
the first table keyed by a serial (deliveries.messages) failed its insert with
"permission denied for sequence messages_seq_seq", failing the run at its
notification step.

A run that failed has no result, and a step with no output is recorded as NULL;
the rows were read straight into jsontext.Value, which can't hold NULL, so the
trail API answered 500 for exactly the runs and steps that needed reading. The
reads coalesce to JSON null instead.

Verified on staging after deploying: the same run's trail reads back.
2026-11-16 00:09:46 +11:00
sam cf249d7643 feat(connectors): MCP servers as a fourth accepted package, with their declared tools offered to agents (archie #2005)
An investigation needs Prometheus's own metrics, and Prometheus publishes an
MCP server, so the connectors module now runs MCP servers as published instead
of wrapping them: a stdio binary in its own user and network namespace with an
egress allow-list, or an HTTP endpoint dialled through declared egress.

Acceptance names the transport, the tools it permits, and the credential slots
that resolve into the server's environment (stdio) or Authorization header
(HTTP). Each permitted tool is declared as a lookup, or as an action with its
effect; a tool the server lists but the acceptance doesn't name is never
offered, and a declared tool the server doesn't list fails the start rather
than going silently missing. Declared tools reach agents beside connector
lookups through the same declaration and the same call path, with the server's
own input schema, under a name no connector can take: an accepted name runs one
package.

A server that fails to start, exits or stops answering is reported by readiness
and reconnected with backoff. Tool calls carry a deadline, results are capped,
and an error result fails its call with the server's own text rather than the
run.

The investigate prompt now asks for a time-until-full figure from
`predict_linear` through the metrics server instead of an estimate from raw
points.

The old core MCP path stays for now: the legacy gateway and task containers
still read config.Tools.MCPServers, so it goes with them.
2026-11-15 23:43:39 +11:00
sam 66220e1752 feat(runs,deliveries): the decision trail, the composer channel, and the dashboard that shows them (#1996, #1984)
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.
2026-11-15 23:36:42 +11:00
sam e787a79af4 feat(connectors): credentials sealed with age, and secret engines that resolve them (#1977, #1982)
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.
2026-11-15 22:14:26 +11:00
sam 02df83ccb7 feat(runs): the in-process agent loop, checkpointed as run steps, and the investigate workflow (#1977, #1889)
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.
2026-11-15 21:49:53 +11:00
sam 68d81fbbd0 refactor: the single binary uses encoding/json/v2 and jsontext (#1977) 2026-11-15 18:11:37 +11:00
sam b89d9e0f05 feat(events): hear Alertmanager through its connector: verified intake, dedupe, links, triggers that start runs (#1980, #1978) 2026-11-15 18:05:38 +11:00
sam 58858f0d92 feat(connectors): the connector contract and its confined extension host (#1979) 2026-11-15 17:24:31 +11:00
sam 8b64ab0afe refactor(runs): Step, Sleep and Wait are generic methods on the run context (#1977) 2026-11-15 17:17:09 +11:00
sam e8366683a9 feat(runs): durable run engine with step checkpoints and lease-fenced writes (#1977) 2026-11-15 17:14:05 +11:00
sam a69a0ea942 feat(archie): the single binary's skeleton: bootstrap config, migrations under an advisory lock, health (#1977) 2026-11-15 16:59:21 +11:00
sam 9cd31e48ca fix(openshell): sandboxes install scoped npm packages; egress endpoints allow encoded slashes (#1864) 2026-11-15 00:12:07 +11:00
sam 998c72f8d3 fix(agentworker): the agent works from its worktree, so a resumed stage in an OpenShell sandbox finds the repository 2026-11-15 00:07:29 +11:00
sam 7a311a3c74 fix(taskactions): a person's own action no longer reads 'no authorising principal'; delegated ones say on whose behalf 2026-11-15 00:04:06 +11:00
sam e78cb1e63e fix(webhookguard): token counts in task logs keep their value; secrets under token keys stay redacted (#1720) 2026-11-14 23:42:46 +11:00
sam 14e2474a49 feat(ui): workflow list shows triggers, steps, last run and delivery with an inline enabled switch; the workflow page header carries them too 2026-11-14 23:11:38 +11:00
sam 990cd9408c chore(gatewayrpc): remove the session-store RPCs no client called 2026-11-14 23:09:57 +11:00
sam 5d620461fe fix(openshell): sandboxes reach the embedded broker by the services host, and may open /dev/null and /proc (#1864) 2026-11-14 22:06:09 +11:00
sam 411632548c fix(openshell): a sandbox that fails to start reports its last log lines (#1864) 2026-11-14 21:59:42 +11:00
sam a262151cb9 fix(daemon): park pr_open tasks on permanent forge resolution failures (#1975) 2026-11-14 20:09:19 +11:00
sam a8d1de8b5e fix(prompts): mark forge-authored text as untrusted data (#1976) 2026-11-14 20:09:19 +11:00
sam 9f830db510 fix(daemon): publish polled issues only from authors with write access (#1830)
The issue poller published title and body of every labelled or assigned
issue to the agent. It now keeps only write-access authors, failing closed
when the forge cannot answer. The filter moves to forge.WriterIssues,
shared with the issue_list tool.
2026-11-14 18:31:54 +11:00
sam 80129b7dd6 fix(webui): capture list narrows to the requested workspace in the store query (#1335) 2026-11-14 15:29:36 +11:00
sam 48c28b36ba fix(gateway): bound task titles in the /tasks and /agents listings (#1076) 2026-11-14 15:29:36 +11:00
sam c5382a8476 fix(webui): a personal token create that fails is revoked and bounded under the dashboard timeout (#1717) 2026-11-14 15:08:37 +11:00
sam 1d329bad35 fix(daemon): reclaim idle task clones hourly, not only on a full volume (#1814) 2026-11-14 15:05:53 +11:00
sam f5c566bcab fix(logging): redact secrets from shipped task log entries (#1720) 2026-11-14 15:05:53 +11:00
sam 90090922e1 fix(archied): the Docker egress proxy and relay do not start under the OpenShell runtime (#1973) 2026-11-14 14:22:29 +11:00
sam a8f1fc9ea3 fix(openshell): keyless model providers get an egress rule on their base URL's host and port (#1972) 2026-11-14 14:22:29 +11:00
sam a9621b91cd fix(archiemessaging): enabling or disabling a channel extension applies without a restart (#1586) 2026-11-14 14:20:37 +11:00
sam c7fabbee25 fix(archiegateway): curators resolve the default chat model per pass, not at boot (#1818) 2026-11-14 14:20:37 +11:00
sam 5f45cdebb5 fix(daemon): reconcile PR state through the repository's org connection (#1872) 2026-11-14 12:03:40 +11:00
sam bfe28f6750 fix(taskactions): a refused merge tells the operator why, not the forge's error chain (#1872) 2026-11-14 12:03:40 +11:00
sam 44a7d59acf fix(daemon): log why a task's forge could not be resolved (#1872) 2026-11-14 11:56:53 +11:00
sam 7148579544 fix(controlplanestore): the container runtime document stores egress_hosts (#1967) 2026-11-14 11:37:16 +11:00
sam 3225396cf1 fix(agent): pass the State Store CA base64-encoded; the OpenShell gateway rejects newlines in the environment (#1864) 2026-11-14 04:04:16 +11:00
sam 811cab57ac fix(openshell): short random sandbox names the gateway accepts (#1864) 2026-11-14 04:04:15 +11:00
sam 3a965e2a4f feat(nats): an external broker defers logins to archie through auth callout (#1866)
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.
2026-11-14 04:04:15 +11:00