Remove PRD/doc paths, bead IDs, phase notes and deleted-test references
from comments; drop test-only hooks left by the test deletion. Includes
in-progress archied bootstrap, gateway and query changes.
The gate now writes its offer to the task's review_gate document before it
waits -- the scored findings, the head SHA, the pull request's identity
and the resuming workflow -- because the engine cannot resume a run
partway, so a resumed pipeline recomputes its findings and only the
recorded document is the review the operator saw
(docs/prds/pr-review-operator-response.md, "The review the operator
answers").
The document lives with the task column it encodes (internal/domain/
workflow/task), the way EncodeInputs does, and carries each finding as
opaque JSON beside the key an operator's selection names. That is what
lets the dashboard render and answer a gate without linking the workflow
engine -- cmd/archie-ui/architecture_test.go measures the linked binary,
and an operator-domain service importing the finding's own type linked
prreview into archie-ui. prreview owns the key derivation and the
finding's encoding, and the MaxRereviewRounds constant lives in the task
vocabulary beside the action names it answers with.
Intake restores the document into the run: a re-review's instructions
ride one labelled block in runLens's and runReviewer's missions only, and
an approve's recorded review is posted by phase 9 filtered by the
operator's selection, with the recomputed findings kept out of the output.
The gate does not wait again on an answered approve.
taskstate gains the rereview action the vocabulary needs -- offered for
waiting_human beside approve and reject, routed to queued -- whose
surfaces follow in the response channel.
docs/prds/pr-review-agent.md's own header already declared this
superseded (docs/architecture/adversarial-review.md, docs/prds/
operator-pr-review.md, docs/prds/review-calibration.md); this executes
that removal per the maintainer's explicit decision, so no reference
to the old path remains:
- internal/domain/workflow/review.go, review_findings.go,
review_report_md.go and their tests: Reviewer, ReviewRequest,
StageReview, StagePostReviewComments, ReviewReport/ReviewFinding and
friends. ReviewComment relocated into workflow.go (still used by
Forger.CreateReviewComments and the new pr-review pipeline).
- internal/app/agentworker/review.go: the ai-sdk-backed subagentReviewer.
- internal/app/archied/pr_review.go: the synchronous operator-review
path (prReviewer, gateway.ChatPRReviewer wiring). The review_pr chat
tool now self-omits (nil reviewer) until the operator trigger is
rebuilt to enqueue an async pr-review task instead of reviewing
synchronously in the chat turn.
- config.Repo.ReviewEnabled and its dashboard exposure.
- Two composition-order tests and one dashboard test that existed only
to pin the deleted path.
Also splits PRReview()'s Stage list into prReviewDecisionStages()
(phases 1-8) and stagePROutput() (phase 9), so a future caller can
splice the decision phases before a PR exists and defer posting until
after -- needed for the "archie's own PRs" trigger, not wired here: it
needs the same stage-loop-around-StageOpenPR semantics this pass
couldn't fully verify in the time available (does an Outcome-setting
stage like StageOpenPR end the compiled-workflow-definition engine the
same way it ends workflow.Run's literal loop?). Carries ScoredFinding.
Adversary through synthesis so that trigger's blocking-finding check
doesn't need to cross-reference back into the pre-synthesis slice.
Not built in this pass, left as a precise continuation (see the bead
comment): the watched-repositories and operator triggers, both blocked
on the same real question -- how a forge-reading credential reaches
PRSource's real implementation when the pr-review pipeline's Stage.Run
bodies execute inside the sandboxed archie-agent process, which holds
none today.
Phase 8 (merge gate) runs one classification call per finding, deciding
blocking vs advisory per the PRD's narrow criteria; a failed or malformed
call leaves the finding advisory. Added between synthesis and output.
A run-level token/wall-clock budget, split into cumulative per-phase
shares (prreview.Budget.PhaseExhausted), gates the expensive agent-call
work in lenses, review, verification, coverage-consistency, merge-gate,
and the anatomy narrative / output polish sub-calls -- deterministic
bookkeeping (snapshot, blast radius, clustering, scoring) always runs
regardless. A skipped phase is recorded and named in the posted review's
outcome, alongside the REQUEST_CHANGES/COMMENT event ReviewEventFor
already decided.
Known gaps left for a follow-up: workflow.Forger.CreateReviewComments
always posts a COMMENT-state review (GitHub's implementation submits
per-comment calls, not a review object, so REQUEST_CHANGES needs a
Forger/forge change), and there is no PR-body fallback list for
whole-file findings (docs/prds/inline-review.md).
Extends the afbk.1 deterministic core for afbk.4's coverage gate and
compound-defect check: exposure fan-in counts and high-exposure filtering
(blast.go), cluster/finding coverage matching and grouping (coverage.go),
and a high-priority severity predicate the evidence verifier gates on
(scoring.go).
First slice of archie-core-afbk.3's pr-review pipeline (phases 1 and 3's
deterministic logic): depth classification from changed-line count with the
operator-override rule, the depth-to-dimension-cap table, cross-lens
dimension merge/dedup/cap, and the hallucination-check dimension added for a
likely-machine-written PR.
Table-driven tests cover the classification boundaries, the override rule,
duplicate-name merging, priority-ordered capping and the AI-generated
threshold. Stage wiring (agent calls, StepExecution recording, the fan-out
concurrency phases 3/4/9 need, and a PR diff/snapshot source) is still open;
see the bead for what remains.
Scores a reviewer's findings on the 38 runnable Martian Code-Review-Bench
PRs: the deterministic core turns findings into posted comments, an
independent judge model matches them to the goldens, and the run reports
golden micro-recall and golden-only precision. The reviewer is a findings
fixture directory until the pr-review workflow lands.
Run with: task bench:prreview -- -findings DIR
The duplicate merge compared each finding against the ones already kept, so
overlap was transitive only through the survivors: a chain of findings 1-2,
2-3, 3-4 collapsed to one finding or to two depending on the order they were
handed in, and the two readings tied on score. It is a clustering now -- a
canonical sort, then a union of each run of overlapping ranges -- so the
surviving set is a property of the findings and not of the permutation they
arrived in, and a cluster's member is chosen by score and then by the
finding itself rather than by arrival order.
Two things the merge got wrong besides order. The PRD keys duplicates on
(file, overlapping lines, category), not on severity, so Finding carries a
Category and the merge reads it, while the severity now only decides which
duplicate speaks for the cluster. And a cluster is blocking when any member
is, so an advisory duplicate can no longer swallow the merge gate's verdict
and turn REQUEST_CHANGES into COMMENT.
diff.go read only the shape git writes. A plain unified diff -- sections
opened by a --- / +++ header pair with no "diff --git" line -- belonged to no
file and contributed no added lines, a silent narrowing of the diff-rules
gate's input; a file section opens from either now. git's C-quoted paths are
decoded from the diff --git line, the --- / +++ headers and the rename pair,
octal escapes to bytes, because a quoted path is not a path the snapshot has.
FileStatus is derived from every statement the section makes -- new file
mode, deleted file mode, old mode / new mode, rename from / rename to, and
the /dev/null side -- so a binary or empty file, whose patch has no headers
and no hunks, is reported as what it was rather than as a modification, and a
change of object type is the typechange the change capture already persists.
Score recorded a finding's duplicate identity before dropping it under its
severity's confidence floor, so a below-floor finding shadowed a later
above-floor duplicate of the same defect. The floor now runs first, and the
merge keeps the higher-scoring of two duplicates, so the result depends on
which findings were given and not on the order they were given in.
The duplicate rule was byte-identical line ranges. The PRD's rule is
overlapping lines: two same-file, same-severity findings whose ranges share a
line are now one finding.
FileStatus said "removed" for a deleted file, a second vocabulary for the
status the repository persists as "deleted". The value says "deleted" now.
Every phase of docs/prds/pr-review-agent.md that can be computed is computed
here, in a package that imports the standard library only: diff parsing with
renames, deletions, multi-hunk files and no-newline markers; directory
clustering; per-language blast radius; evidence packages; scoring,
deduplication, line mapping to diff coordinates and the review event.
The review event is REQUEST_CHANGES when a finding is blocking and COMMENT
otherwise; there is no approving value, because archie does not own the merge
decision.
internal/domain/workflow/prreview is now the one diff parser in this
repository: the diff-rules step's addedDiffLines delegates to it and the
private hunk-header and path helpers it used to carry are deleted, so a
repository rule and a review comment cannot disagree about which line a change
introduced. diff_rules_test.go is unchanged.
Blast radius resolves Go imports through the module path in go.mod, Python
module names, and JavaScript/TypeScript relative specifiers, all against files
inside the snapshot; an import that resolves to nothing there contributes no
edge. Evidence extraction reads through an fs.FS rooted at the snapshot, so
both are tested against fstest.MapFS fixtures.
NOTICE records the derivation from PR-AF (Apache-2.0).