Files
archie/docs/prds/operator-pr-review.md
T
sam 207b071917 fix(archied): build the Gateway's worktree manager so it serves review_pr
boot.prReviewer returns nil without a worktree manager, and a nil reviewer
omits review_pr from every channel's tool set. RunGateway never called
buildTreesAndIdentities, so the Gateway resolved a nil reviewer and no
channel could review a PR.

Extract the manager's construction into boot.buildWorktreeManager, called
by buildTreesAndIdentities (daemon, unchanged field-for-field) and by
startGatewayRuntime before setupGatewayChat. The Gateway does not call
buildTreesAndIdentities: that also registers daemon identity runners the
Gateway must not own, and PR review only needs a clone of the PR head,
which worktree.Manager.CheckoutPR does from the forge.

Pin the ordering by source position in composition_order_test.go, alongside
the memory-engine ordering the same function already carries, and pin both
compositions behaviourally in worktree_manager_composition_test.go: the
Gateway's step must yield a reviewer that advertises review_pr, and the
daemon must still build its root manager plus one runner per identity with
a distinct WorkDir.

Correct docs/prds/operator-pr-review.md, which still asserted the daemon
supplies ChatPRReviewer and holds the review in-flight set.
2026-09-22 03:44:45 +10:00

4.2 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

  1. Forge read. GetPullRequest(owner, repo, number) returns a forge-neutral PullRequest{Number, Title, Body, HeadRef, BaseRef, HeadSHA, BaseSHA, State}. Declared as a narrow PullRequestReader interface, implemented by GitHub and Gitea; the noop forge does not implement it, so the composition root type-asserts and refuses review with "forge does not support PR review". Adding to the fat Forge interface would churn every test fake for a capability the noop forge cannot honestly provide.

  2. Materialisation. worktree.Manager.CheckoutPR(owner, repo, headRef, baseRef) clones the repository fully and checks out origin/<headRef>. Diff(dir, baseRef) and Snapshot(dir, destDir) then work unchanged: Diff resolves origin/<baseRef> via the existing resolveBase, and Snapshot strips .git exactly 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.

  3. Reviewer reuse. agentworker.NewOperatorReviewer(models, providers) builds the same subagentReviewer the stage uses, from daemon-level config rather than a taskrun.Request. It drops only the Repo.ReviewEnabled gate (the operator asked explicitly) and the task-run scaffolding.

  4. Command. A gateway tool review_pr (toolset tasks) bound to the channel's identity at construction — the model never names an identity, matching task_spawn/task_action. The Gateway process serves it: it composes the worktree manager it needs to materialise the PR head, and the composition root supplies ChatPRReviewer, a narrow gateway interface whose adapter maps workflow.ReviewReport into a gateway-owned result shape (gateway states what it needs, the composition root adapts — the ChatTaskActor pattern).

  5. Authorization. Identity-scoped repository allow-list, the task_spawn rule: a chat identity may only review a repo in its TaskProfile.Repos. identity == nil denotes an authenticated dashboard operator who may review any configured repository.

  6. Determinism. One review per (owner, repo, number) at a time: the Gateway 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 — the ChatPRReviewer adapter.
  • internal/app/archied/{bootstrap.go,gateway.go,main.go} — composition.

Not in scope

  • Surfacing findings on the PR body or the dashboard (h019.6).
  • Reviewer model per-invocation override: configuration via models.reviewer is the selection surface; a per-call override is a later knob.