Commit Graph

5 Commits

Author SHA1 Message Date
Jesse Vincent
e355795625 Hand reviewers the diff as a file, not a paste
Paste adoption stayed at 0/15 even as a Red Flag — and the controller's
reluctance is locally rational: pasting loads the diff into the (most
expensive) controller context permanently, while a reviewer self-fetch
costs a few cheap turns. The diff-file handoff is cheap for both sides:
the controller redirects git diff to /tmp without reading it, and the
reviewer gets the whole change in one Read call.
2026-06-10 03:44:19 -07:00
Jesse Vincent
29ee4e8e44 Reviewer skepticism covers the implementer's design rationales
Fourth planted-defect failure mode: the implementer's self-report said
'noted mild structural duplication; left unabstracted per YAGNI' and the
reviewer deferred to that framing, rating the duplication no finding at
all. The pre-judging keeps relocating — controller prompt, then reviewer
calibration, now the implementer's report. Rationales are claims; they
never downgrade severity.
2026-06-10 02:20:28 -07:00
Jesse Vincent
28498a5cde Make diff-pasting non-optional for task reviewer dispatch
Adoption was 6/11 reviews on fractals and 0/17 on svelte when phrased
as guidance; reviewers without the diff re-derive it by hand, which is
the single largest remaining reviewer cost. Now a Red Flags Never entry
and a REQUIRED marker on the template placeholder.
2026-06-10 02:10:34 -07:00
Jesse Vincent
5e2907fc4f Close the Minor-severity escape hatch
With merged review, a planted verbatim-duplication defect shipped: the
reviewer rated it Minor (YAGNI) under the strict cannot-be-trusted
definition of Important, and the Minor-rolls-up rule meant no fix was
ever dispatched and the final review never saw the finding. Calibration
now names merge-blocking maintainability damage (verbatim duplication,
swallowed errors, assertion-free tests) as Important, and controllers
must paste accumulated Minor findings into the final review dispatch.
2026-06-10 02:09:10 -07:00
Jesse Vincent
e3c74fc1c9 Merge per-task reviews into one task reviewer (iteration 2)
Iteration-1 profiling: implementers and per-dispatch overhead dominate
(429 of 686 subagent turns; controller coordination is half the dollars
and scales with dispatch count), reviewers are individually lean, and
the controller pasted the diff in only 2 of 22 review dispatches when
the guidance was phrased as optional.

Changes: spec-reviewer-prompt.md + code-quality-reviewer-prompt.md
replaced by task-reviewer-prompt.md (one reviewer, one reading of a
pasted diff, two verdicts: spec compliance //⚠️ and task quality);
one fix dispatch can address both kinds of findings; controller now
runs git diff itself and pastes it (imperative, not optional);
implementers run focused tests while iterating and the full suite once
before committing; flowchart, example, Red Flags, tool tables updated.
The broad final whole-branch review is unchanged.
2026-06-09 23:58:28 -07:00