Files
archie/docs/prds/inline-review.md
T
sam e0b6aa6105 feat(workflow): post line-anchored review comments with suggested fixes (#891)
* feat(workflow): post line-anchored review comments with suggested fixes

Bead archie-core-q9au (docs/prds/inline-review.md). A review's findings reached
the operator only as a flat list in the PR body, so the author had to map every
finding back to its line by hand and apply mechanical fixes by hand. Now the
line-anchored findings are also posted as inline review comments, carrying a
one-click suggestion when the reviewer could state the fix.

Domain (internal/domain/workflow):
- ReviewFinding gains Suggestion; Validate rejects one on anything but a
  confirmed finding, so the agent's record_finding call is refused with
  something it can act on. Validate splits into validateAnchor /
  validateClassification / validateDisposition, which also brings it back under
  the cyclop limit the gate enforces.
- StagePostReviewComments runs after StageOpenPR in the implement workflow. It
  posts only line-anchored findings (Line > 0); a whole-file finding has no line
  to attach to and stays in the body list, which remains the complete record.
  It is best-effort: the PR is open and the body already lists every finding, so
  a failed comment is logged, never a park -- the same reasoning as OpenPR's
  existing best-effort LinkBranch call.
- The suggestion fence is gated on Verdict == confirmed where the fence is
  written, because it is a one-click apply: a wrong suggestion breaks the code
  and the author has to notice.

Forge (internal/forge): ReviewCommentWriter + GitHub/Gitea implementations,
type-asserted like PullRequestReader so a forge that cannot is skipped rather
than faked (NoopForge is pinned as not satisfying it). GitHub loops one
CreateComment per comment and joins the failures, so one refused anchor cannot
drop the rest; Gitea carries them on a single COMMENT-state review.

Two deliberate departures from the PRD's sketch, both recorded in it:
- The interface is batch (CreateReviewComments), not one call per comment:
  Gitea's only inline shape is one submitted review, and the set then crosses
  NATS once instead of once per finding.
- The head SHA is resolved inside each forge implementation rather than by the
  caller. The stage runs in archie-agent, which holds no forge credentials and
  has no PullRequestReader; the daemon-side forgerpc handler is the only place
  that does.

Transport (internal/forgerpc): workflow.Forger gains the method, so the agent
reaches the daemon over the new create_review_comments subject; the server
type-asserts the writer and answers an incapable forge with an error the stage
logs. This is the one proxied method whose absence on an image skew does not
park a task.

The reviewer prompt and record_finding schema ask for a suggestion on a
confirmed, mechanically fixable defect only.

Regenerating the wfextract symbol table -- the documented way a new exported
workflow symbol reaches interpreted stage plugins -- also picked up symbols that
were missing from the committed table (the Status* and Source* constants,
ReviewCheck, Store, Task, and the _Store wrapper). Nil-guards were re-applied to
every wrapper afterwards, as that file's header requires.

Evidence: task check exit 0 (incl. 229 UI tests). Three mutations of the new
stage logic each fail a test that names the behaviour -- dropping the
confirmed-only gate, dropping the Line > 0 filter, and letting a posting failure
escape -- so the tests discriminate rather than passing vacuously.

* fix(build): drop the Dockerfile pin assertion

The guard fetched golangci-lint's go.mod at image build time to fail the build
when GOLANGCI_LINT_VERSION and GOFUMPT_VERSION disagreed. It only ever tripped
on self-inflicted pin drift, but it added a network fetch and a new failure
mode to the release build, which is not where that belongs.

The pins stay correct (golangci-lint 2.13.2, whose vendored gofumpt v0.11.0
equals GOFUMPT_VERSION) and the comment above them still states the invariant,
so the reasoning survives without the build-time machinery. The pin change
itself reaches the agent image through the normal release path: CI rebuilds
and pushes archie-agent on an archie/vX.Y.Z release, and a gateway-only
release deliberately does not.

* feat(workflow): add the remediate workflow for PR review remediation

Implements step 5 of docs/prds/pr-review-remediation.md: a remediate
workflow that resumes the task's existing worktree onto its PR branch
(worktree.Manager.Resume, not Prepare's refresh), runs a builder agent
against the review's actionable comments, commits and pushes to the
same branch, and replies via the forge's ReplyToReview. Task.RetryCount
doubles as the remediation round counter, capped by the repo's
max_retries; the round-cap stage parks the task and posts one comment
when it's hit.

Task gains a ReviewPayload field (JSON-encoded review unit) with full
store/proto/staterpc plumbing. workflow.Forger gains Comment and
ReplyToReview, proxied to archie-agent via a new forgerpc RPC. Resume
and its Dir lookup are added as an unexported optional Trees capability
rather than widening the exported interface, which is already at
golangci-lint's interfacebloat cap and is projected into wfextract's
Yaegi symbol table for repository-authored stage plugins.

The daemon-side reaction consumer that dispatches into this workflow
(subscribing ARCHIE_REACTIONS, grouping comments by review, enforcing
per-task serialization) is tracked separately in archie-core-8li9.4.

* feat(messaging): extract standalone messaging service binary and process composition

* feat(messaging): adapt channel frontends to consume Gateway ChatContract

* feat(messaging): remove in-process channels and Router from daemon bootstrap

Telegram, email and webhook now run only in the Messaging Service, which
reaches this process through the Gateway's ChatContract. The daemon builds
no channel and no gateway.Router, so the wiring that existed only to serve
them goes with it: setupGateways, setupEmailGateway, setupWebhookGateway,
setupTelegramGateway, buildTelegramRouter, makeTelegramReload and the
release-announcement path helper.

The seams those paths owned move to where they can still be honoured:

- Channel ValidateConfig runs in archiemessaging.compose, which now returns
  an error, so a configured-but-invalid front-end fails the service rather
  than being dropped silently.
- The inbound rate limiter moves to the Gateway process, which owns the only
  Router and therefore the only place a per-sender budget applies to every
  channel's turns.
- The daemon's gateway readiness probe becomes a ContractProbe against the
  Gateway. It cannot observe a channel lifecycle it no longer runs, and a
  channel-count probe would have reported every daemon degraded.
- telegramSetup is now chatSetup (in chat_setup.go), trimmed to the fields a
  chat turn runner actually reads.

Telegram operator features that were wired only in the daemon (/update,
release announcements, version reporting, SIGHUP reload) are not yet wired
in the Messaging Service: archie-core-8cda.6.6. Channel lifecycle reporting:
archie-core-8cda.6.8. The Gateway process builds no worktree manager, so
review_pr is unadvertised on every channel: archie-core-8cda.6.7.

* feat(messaging): re-wire the Telegram operator surface in the Messaging Service

setupTelegramGateway satisfied eight telegram.Gateway seams from the daemon's
own process. Each is resolved by where the fact it needs is owned, not by
where it used to be built; the decision table is in
docs/architecture/migration-decisions.md.

Wired here: /update (built from this service's own [chat.telegram] check and
install commands), the update-report relay (same sha256(bot_user)[:8] path the
daemon wrote, so a pending report is found rather than written afresh),
show_tool_calls, and /restart's config reload, which re-resolves the token and
allowlist from this service's own file and refuses a reload that resolves to
an empty token.

/version is sourced from the Gateway: ChatSnapshot gains a Version field
carrying the Gateway's rendered build block, read per call and bounded by the
dependency timeout. cmd/archie-messaging deliberately takes no version
ldflags, so it cannot report a partial upgrade as a matched one.

RunningVersions and ReleaseAnnouncements stay nil. Both need a component's
real running version, and the only versions this process can obtain are a
different binary's stamps -- reporting them would manufacture exactly the
false success the update check exists to catch, and the announcer without
parseable versions is a no-op that reads as configured. archie-core-8cda.6.9
carries the contract that unblocks them. Dangerous stays nil: no composition
has ever supplied a command authority.

Enrich is dropped from the update service: componentInstallTypeEnricher read
[nats], which this service must not decode, so the check command's own
reported install type stands.

* fix(workflow): guard inline review comments against head drift

Two findings from the review of q9au.

A comment's line numbers describe exactly one revision of the branch, but the
forge resolved the pull request's head at posting time -- after the review had
already read the worktree. A push in that window (a collaborator, a retry) meant
the findings were anchored to whatever now occupied those lines, mislabelling
instead of failing. The revision the review measured now travels with the
comment set: OpenPR records it from the same worktree read it already performs
(TaskContext.ReviewedHeadSHA), StagePostReviewComments threads it through
Forger to forgerpc, and the forge refuses the whole set once the head it reads
has moved off it -- which the best-effort stage logs, the PR body remaining the
record. An unmeasured revision posts unverified rather than dropping every
finding, so a worktree that cannot report one degrades instead of regressing.

Suggestion was documented single-line only, because GitHub applies a suggestion
fence up to its first line and a multi-line replacement would silently corrupt
the file. Only the verdict was validated, so a multi-line suggestion reached the
renderer and posted as that truncated fence. Validate now rejects an embedded
newline, which makes record_finding refuse it with feedback the model can act on
instead of the reviewer discovering the corruption later.
2026-09-19 23:37:23 +10:00

7.2 KiB

Inline review -- decision

Status: Implemented Beads issue: archie-core-q9au Builds on: archie-core-h019 (adversarial self-review), docs/architecture/adversarial-review.md

Problem

Findings reach the operator only as a flat list in the PR body (renderPRReviewSection, h019.6): - `file.go:12` (confirmed, error): <defect> — <scenario>. That is a report about the code, not a review of it. A real reviewer anchors each finding to the line it is about, so the author sees it in context — and, when the fix is mechanical, attaches the replacement so it can be applied in one click.

Both halves are missing today:

  • No line-anchored comment. forge.Forge.Comment posts to the PR conversation (Issues.CreateComment); nothing creates a review comment at path + line.
  • No suggested fix. ReviewFinding carries File/Line/Defect/ FailureScenario/Verdict/Level/Category — no replacement code, so even an anchored comment could only describe the fix, not offer it.

Decisions

1. A narrow, type-asserted write surface

The set of comments travels in one call, so a forge that can only carry them on a submitted review needs one request rather than one per finding:

type ReviewCommentWriter interface {
    CreateReviewComments(ctx context.Context, owner, repo string, number int,
        comments []InlineReviewComment) error
}

Type-asserted like PullRequestReader/PullRequestReviewReader, so a forge that cannot do it is skipped rather than faked. The stage reaches it through workflow.Forger, whose production implementation is forgerpc.Client — the worker holds no forge credentials, so the daemon's forgerpc server type-asserts forge.ReviewCommentWriter and answers an incapable forge with an error the best-effort stage logs.

The comment's line is anchored to the pull request's current head revision, resolved inside each implementation rather than passed in by the caller: it is the revision the comments are attached to, and the caller that produced the line numbers holds no forge credentials to read it. The caller does pass the revision those line numbers were measured on (TaskContext.ReviewedHeadSHA, recorded when StageOpenPR opens the pull request), and the implementation posts only while the head it read still matches it — see §4.

Per-forge reality (verified against the SDKs, 2026-09-11):

  • GitHub — direct: PullRequests.CreateComment with {Body, Path, Line, Side: "RIGHT", CommitID}.
  • Gitea — no direct inline-comment call. Inline comments ride on a submitted review (CreatePullReview with Comments and a COMMENT state). The Gitea implementation therefore submits a single COMMENT-state review carrying the findings, or the capability is simply absent (the type assertion skips it). Decided: implement Gitea as a COMMENT-state review; do not block the feature on it.

2. Suggestion, and only on confirmed findings

ReviewFinding gains an optional Suggestion string — the replacement text for the anchored line, rendered as a fenced suggestion block (GitHub's one-click "Commit suggestion").

Only confirmed findings may carry one. A wrong suggestion is a one-click path to breaking code a reviewer then has to notice; confirmed is by definition the verdict the reviewer traced and can state the failure for. A plausible finding is a worry, and a worry gets a sentence, not a patch. This is the h019.5 calibration rule reused, not a new one.

Suggestion replaces the anchored line exactly, and is only rendered when Verdict == confirmed. Single-line only in this cut; multi-line (GitHub's StartLine/StartSide) is a follow-up, because a multi-line suggestion that is off by one line silently corrupts the file. The rule is enforced in ReviewFinding.Validate — an embedded newline is rejected there, so the record_finding tool refuses it with feedback the model can act on, rather than the renderer silently posting a fence that applies only its first line.

3. Which findings are posted inline

Only findings that are line-anchored (Line > 0). A whole-file finding (Line == 0, e.g. "README.md is stale") has no line to attach to and stays in the PR-body list. The body section keeps listing everything, so it remains the complete record and the fallback.

Findings that block never reach this path: a surviving blocking finding parks the task before StageOpenPR, so there is no PR to comment on. Inline comments are the non-blocking, line-anchored subset — which is exactly the set that would otherwise be a body-only list the author has to map back to lines by hand.

4. A best-effort stage after StageOpenPR

New StagePostReviewComments, after StageOpenPR:

  1. Read the report stashed by StageReview (tc.ReviewReport, h019.6).
  2. Post each line-anchored finding as an inline comment, with a suggestion block when Verdict == confirmed && Suggestion != "". The head SHA the comments are anchored to is resolved by the forge implementation, not here; there is no PullRequestReader on this side of the agent boundary. The stage passes tc.ReviewedHeadSHA alongside them.

Nothing in the run pushes between StageReview and this stage, so at that moment the pull request's head is the revision the review read. That was an assumption, and a collaborator can falsify it by pushing to the branch between the review and the posting. A line number is not validated against a revision: both forges anchor it to whatever now occupies that line, so a stale anchor mislabels rather than failing. The revision is therefore carried with the comments and the set is refused when the head has moved off it (reviewHeadDrift) — a refusal lands in the failure path below, leaving the PR body as the record. With no measured revision (a Trees that cannot report one) the comments post unverified rather than being dropped.

Failures log and never fail the task. The PR is already open; a comment that failed to post must not park a task whose actual work succeeded, and the body section already carries every finding. This mirrors OpenPR's existing best-effort LinkBranch call.

5. No separate opt-in flag (for now)

Inline comments are posted whenever a review ran and produced line-anchored findings — the same repo.review_enabled gate already covers it. A second flag is a knob to add if it proves noisy in practice; adding it speculatively is the smallest-change principle's opposite.

Out of scope

  • Commenting on the blocking/parked case (no PR exists).
  • Resolving/dismissing threads, or reacting to replies (that is the archie-core-8li9 remediation direction).
  • Multi-line suggestions.
  • Gitea's "suggested change" rendering: Gitea has no one-click apply, so the Suggestion there is informational text in the comment body.

Packages this touches

  • internal/domain/workflow — ReviewFinding.Suggestion; StagePostReviewComments; the Forger subset gains the writer (or TaskContext gains the writer seam).
  • internal/forge — ReviewCommentWriter, GitHub + Gitea implementations.
  • internal/app/agentworker — the reviewer prompt asks for a Suggestion on confirmed, mechanically-fixable findings; record_finding accepts it.