Three defects the first sweep left behind, each caught by a rule the guard did not yet have. Statuses. RULES.md gives three; the tree had 25 values, and the free-text ones were carrying progress. "Implemented (wiring landed)" and "Ratified (rev. 2e). Rev. 2e adds the OpenTaskByPR lookup. Rev. 2d revised section 10..." were both changelogs living in the one field the other rules exempt. Every PRD now declares Draft, Approved or Finalised and nothing else; five that declared nothing now declare one. A revision number moves to **Revision:**, a pointer to the authoritative document to **Authority:**, and what a past revision changed to git. CLAUDE.md's citation of state-store-contract rev. 2e still resolves. Stale cross-references. "Supersedes the 2026-09-03 open question", "this bullet previously said", "an earlier draft of this document claimed" all point at text the reader cannot see, because it was replaced. A supersede marker survives only when it names a file, a section or a symbol that can be found. Temporal hedges. 100 uses of today, currently and right now across 31 files. Each dates its sentence to the day it was written: "[notify] today is one webhook URL, read in one place" stops being true the moment this design lands, while still reading as the premise it rests on. The header-field exemption was also too wide. "**Date:** 2026-09-03, Channel resolved 2026-09-22" smuggled a dated status into the one line the rules did not read; the exemption is now a Date holding only a date and a Status holding only one of the three.
4.1 KiB
Operator-triggered PR review
Status: Draft
Beads issue: archie-core-h019.8
This PRD reuses the adversarial-self-review contract
(docs/prds/adversarial-self-review.md) and the workflow.Reviewer /
workflow.ReviewReport types from internal/domain/workflow. It decides
only what is new: how an operator asks for a review of an existing PR, and
how that PR's content reaches the reviewer.
Problem
The adversarial reviewer (StageReview) runs automatically before StageOpenPR
and reviews the task's own worktree HEAD. There is no way to review a PR that
already exists: one archie opened, a human opened, or one whose findings the
operator wants re-checked after a push.
Shape
One channel-neutral command — review_pr — accepts a repository and PR number
and returns the structured ReviewReport. The Web UI chat and Telegram invoke
the same command; neither duplicates review behaviour. The reviewer model is
models.reviewer (falling back to models.builder), already the rule the
workflow stage uses, so an operator configures it independently of
planner/builder.
Decisions
-
Forge read.
GetPullRequest(owner, repo, number)returns a forge-neutralPullRequest{Number, Title, Body, HeadRef, BaseRef, HeadSHA, BaseSHA, State}. Declared as a narrowPullRequestReaderinterface, implemented by GitHub and Gitea; the noop forge does not implement it, so the daemon type-asserts and refuses review with "forge does not support PR review". Adding to the fatForgeinterface would churn every test fake for a capability the noop forge cannot honestly provide. -
Materialisation.
worktree.Manager.CheckoutPR(owner, repo, headRef, baseRef)clones the repository fully and checks outorigin/<headRef>.Diff(dir, baseRef)andSnapshot(dir, destDir)then work unchanged:Diffresolvesorigin/<baseRef>via the existingresolveBase, andSnapshotstrips.gitexactly as the workflow stage does. The head must already be pushed to the same repository — archie's own PRs always are; a cross-repo or deleted head is refused with that reason, not half-reviewed. -
Reviewer reuse.
agentworker.NewOperatorReviewer(models, providers)builds the samesubagentReviewerthe stage uses, from daemon-level config rather than ataskrun.Request. It drops only theRepo.ReviewEnabledgate (the operator asked explicitly) and the task-run scaffolding. -
Command. A gateway tool
review_pr(toolsettasks) bound to the channel's identity at construction — the model never names an identity, matchingtask_spawn/task_action. The daemon suppliesChatPRReviewer, a narrow gateway interface; the daemon adapter mapsworkflow.ReviewReportinto a gateway-owned result shape (gateway states what it needs, the daemon adapts — theChatTaskActorpattern). -
Authorization. Identity-scoped repository allow-list, the
task_spawnrule: a chat identity may only review a repo in itsTaskProfile.Repos.identity == nildenotes an authenticated dashboard operator who may review any configured repository. -
Determinism. One review per (owner, repo, number) at a time: the daemon holds an in-flight set; a concurrent request for the same PR returns "review already in progress" rather than launching a second reviewer and racing on the snapshot.
Files
internal/forge/forge.go,github.go,gitea.go—PullRequest,PullRequestReader,GetPullRequest.internal/worktree/worktree.go—CheckoutPR.internal/app/agentworker/review.go—NewOperatorReviewer.internal/gateway/review_tools.go—ChatPRReviewer, result shape,review_pr.internal/gateway/turn.go,gateway.go— tool wiring into the turn.internal/app/archied/pr_review.go— theChatPRRevieweradapter.internal/app/archied/{bootstrap.go,main.go,telegram_setup.go}— composition.
Not in scope
- Surfacing findings on the PR body or the dashboard (h019.6).
- Reviewer model per-invocation override: configuration via
models.revieweris the selection surface; a per-call override is a later knob.