sam df3d86acc4 docs(prds): decide reviewer isolation via agent.Subagent, fail-closed
Section 1 of the adversarial self-review decision was superseded on
2026-08-24: it assumed daemon-owned in-process execution and a daemon-side
second Pool.Acquire, both removed by archie-core-q15y. It is now re-decided
rather than merely marked dead, so the document is Active again.

The reviewer is an agent.Subagent run from inside the task-scoped worker.
ai-sdk v0.1.22 is already pinned, so this needs no SDK bump, and it adds no
host executor, no second container acquire and no nested container lifecycle
-- the open question the supersession left.

Subagent.Run passes Prompt and never populates Messages, so conversation
isolation is a construction fact rather than prompt text. It does NOT give
filesystem isolation: the sub-agent shares the parent's process, working
directory and credentials, so the .git-stripped snapshot survives from the
original design and is load-bearing, and the reviewer's toolset must be
read-only, rooted at the snapshot, and must exclude the worktreerpc
publication grant -- otherwise a reviewer could push the branch it exists to
block. Run() not Tool(), so the implementer cannot elect to review itself.
Findings return through a closure-captured tool because Run yields only text,
and are read even when Run errors, since captured findings survive.

Also decides fail-closed: a review that fails to RUN parks the task rather
than opening an unreviewed PR. ReviewEnabled is opt-in, so an operator who
turned the gate on wants the gate. This is why h019.2 models "ran and found
nothing" separately from "did not run" -- collapsing them would make an
outage indistinguishable from a clean review.

h019.3 is unblocked and rewritten with the construction rules. h019.4's
description said the task parks as waiting_human, contradicting section 4's
decision of StatusParked; corrected, and the fail-closed rule added.
2026-08-25 00:56:10 +10:00
S
Description
Archie connects events from your systems to agents that can investigate, reason, and act. Define what an event means, map its data into a workflow, and give that workflow an agent equipped for the job: its own execution environment, tools, and identity.
https://archie.catlow.cloud
Apache-2.0
132 MiB
0 Stars 1 Watchers 0 Forks
2026-11-10 10:01:23 +00:00
Languages
Go 76.7%
Vue 13.1%
TypeScript 7.8%
JavaScript 1.2%
Shell 0.6%
Other 0.4%