fix(#4097): evidence preservation no longer sweeps the run's own input copies into .review-diagnostics/ (#4329)

* test(#4097): failing-first regression — run input copies swept into .review-diagnostics

The present_results preserve+cleanup glob `_DIAG_MD=( "$RUN_DIR"/gsd-review-*.md )`
matches both lane outputs and the run's own assembled input copies (prompt,
instructions, roadmap, per-plan copies, project/context/research/requirements,
per-lane trimmed prompts) because both share the gsd-review- prefix.

Seed the full input-copy set into the existing runWriteReviewsFlow fixture and
assert (a) the diagnostics dir holds exactly the lane report + .err sidecar and
no input basenames, and (b) an inputs-only run creates no diagnostics dir at all
and still cleans up. Both RED against the shipped block.

* fix(#4097): preserve lane output only — exclude the run's input copies from evidence

The preserve+cleanup glob treated every gsd-review-*.md in RUN_DIR as lane
evidence, but the workflow itself writes the run's assembled INPUTS there under
the same prefix (prompt, instructions, roadmap, per-plan copies, project/
context/research/requirements, per-lane trimmed prompts). Filter _DIAG_MD by
basename against that closed input set instead.

Direct glob iteration + case filter — identical under bash and zsh (#4099/
#4109), nullglob-safe (#2962), and the exclusion list is closed and owned in
this step: a future input basename cannot silently rejoin the evidence set.
Lane reports, diagnostic stubs and non-empty .err sidecars are unchanged.

Emitted-Drift-Ack-Growth: review.md — #4097 narrows the present_results evidence-preservation glob: the closed input-basename exclusion list (case filter) plus its rationale note are deliberate additions so a future input basename cannot silently rejoin the evidence set.

* changeset(#4097): fixed — review diagnostics no longer sweep run input copies

* changeset(#4097): backfill PR number 4329

---------

Co-authored-by: sim <sim@local>

.changeset/clever-cats-wake.md

@@ -0,0 +1,5 @@
+---
+type: Fixed
+pr: 4329
+---
+**`/gsd-review` no longer sweeps the run's own prompt/plan copies into `.review-diagnostics/`** — after a review, the preserved diagnostics folder is now dominated by actual evidence (reviewer reports and stderr sidecars) instead of byte-identical duplicates of the prompt, instructions, roadmap, and every plan under review. (#4097)

gsd-core/workflows/review.md

@@ -845,6 +845,19 @@ NOT a preservation failure. This copy is deliberately NOT part of the commit abo
 step names only `{padded_phase}-REVIEWS.md` explicitly, never a directory glob, so
 `.review-diagnostics/` is never swept into it.
 
+**#4097: preserve lane OUTPUT, never the run's own input copies.** `RUN_DIR` holds not only
+lane outputs — prompt assembly (the `gather_context`/section-copy step above) also writes the
+run's assembled INPUTS there under the same `gsd-review-` prefix: the combined prompt, the
+instructions/roadmap sections, a copy of every plan under review, the project/context/research/
+requirements sections, and the per-lane trimmed prompts. Those are byte-identical duplicates of
+files already committed under `.planning/`; sweeping them into `.review-diagnostics/` buries
+the actual evidence under plan duplicates and grows the phase directory on every run. The
+exclusion list below is CLOSED and owned here: this workflow itself writes every input
+basename at prompt-assembly time, so a future input file CANNOT silently join the evidence
+set — adding one means adding its stem to this list consciously. Lane slugs never begin with
+any excluded stem (`prompt`, `instructions`, `plan-`, `project`, `roadmap`, `context`,
+`research`, `requirements`), so a lane report can never be excluded by accident.
+
 Preservation and cleanup MUST run in the same fenced block below (a shell variable cannot
 survive across separate fences — each is its own process). `mkdir -p` and every `cp` are
 exit-status checked; `rm -rf "$RUN_DIR"` runs ONLY if nothing was preserved (nothing to
@@ -858,7 +871,20 @@ shopt -s nullglob 2>/dev/null; setopt NULL_GLOB 2>/dev/null
 RUN_DIR="{run_dir}"
 DIAG_DIR="{phase_dir}/.review-diagnostics"
 
-_DIAG_MD=( "$RUN_DIR"/gsd-review-*.md )
+# #4097: `gsd-review-*.md` matches BOTH lane outputs (reports, diagnostic stubs) and the
+# run's own assembled input copies (see the #4097 note above). Filter by basename against
+# the closed input set this workflow itself writes — direct glob iteration with a `case`
+# filter, no string accumulator, identical under bash and zsh (#4099/#4109), and the
+# `nullglob` set at the top of this fence keeps an empty RUN_DIR an empty array (#2962).
+# `gsd-review-prompt*` deliberately covers BOTH the combined prompt (`gsd-review-prompt.md`)
+# and the per-lane trimmed prompts (`gsd-review-prompt-<slug>.md`).
+_DIAG_MD=()
+for f in "$RUN_DIR"/gsd-review-*.md; do
+  case "$(basename "$f")" in
+    gsd-review-prompt*|gsd-review-instructions*|gsd-review-plan-*|gsd-review-project*|gsd-review-roadmap*|gsd-review-context*|gsd-review-research*|gsd-review-requirements*) ;;
+    *) _DIAG_MD+=("$f") ;;
+  esac
+done
 _DIAG_ERR=()
 for f in "$RUN_DIR"/gsd-review-*.err; do
   [ -s "$f" ] && _DIAG_ERR+=("$f")

tests/review-parallel-lanes.test.cjs

@@ -708,6 +708,14 @@ function runWriteReviewsFlow(t, opts) {
     fs.writeFileSync(path.join(phaseDir, '.review-diagnostics'), 'blocking file, not a directory\n');
   }
 
+  // #4097: stage the run's OWN input copies exactly as prompt assembly
+  // (review.md's section-copy fence) writes them, so the preserve+cleanup
+  // block can be observed deciding input vs. evidence. `name` is a bare
+  // basename written into the fixture run dir.
+  for (const [name, content] of Object.entries(opts.seedFiles || {})) {
+    fs.writeFileSync(path.join(runDir, name), content);
+  }
+
   if (opts.jsonlLines && opts.jsonlLines.length > 0) {
     fs.writeFileSync(
       path.join(runDir, 'gsd-review-lane-results.jsonl'),
@@ -997,6 +1005,85 @@ describe('#3885 failed preservation leaves run_dir intact (no silent swallow)',
   });
 });
 
+describe('#4097 the run\'s own input copies are not preserved as diagnostics', () => {
+  // The preserve+cleanup glob assumes every `gsd-review-*.md` in RUN_DIR is
+  // lane OUTPUT. But the workflow itself writes the run's assembled INPUTS
+  // into RUN_DIR under the same prefix at prompt-assembly time (review.md's
+  // section-copy fence): the combined prompt, instructions, roadmap, one copy
+  // of every plan under review, project/context/research/requirements
+  // sections, and the per-lane trimmed prompts. On a multi-plan phase those
+  // byte-identical `.planning/` duplicates bury the actual evidence (a
+  // handful of reviewer reports and `.err` sidecars) and grow the phase
+  // directory on every review run (#4097).
+  const INPUT_COPIES_4097 = {
+    'gsd-review-prompt.md': 'combined reviewer prompt\n',
+    'gsd-review-instructions.md': 'instructions section\n',
+    'gsd-review-roadmap.md': 'roadmap section\n',
+    'gsd-review-project.md': 'PROJECT.md copy\n',
+    'gsd-review-context.md': 'CONTEXT.md concatenation\n',
+    'gsd-review-research.md': 'RESEARCH.md concatenation\n',
+    'gsd-review-requirements.md': 'REQUIREMENTS.md copy\n',
+    'gsd-review-plan-12.6-01.md': 'plan 12.6-01 duplicate\n',
+    'gsd-review-plan-12.6-02.md': 'plan 12.6-02 duplicate\n',
+    // Per-lane trimmed prompt written by prepare_trimmed_prompt_for_reviewer
+    // — also a run input, also matched by the issue's `gsd-review-prompt*`
+    // exclusion prefix.
+    'gsd-review-prompt-claude.md': 'budget-trimmed prompt for lane claude\n',
+  };
+
+  test('inputCopiesAreNotSweptIntoDiagnostics_4097', (t) => {
+    const result = runWriteReviewsFlow(t, {
+      selected: 'claude',
+      jsonlLines: [{ slug: 'claude' }],
+      seedFiles: INPUT_COPIES_4097,
+      lanes: {
+        claude: { md: '# Claude review\nok\n', err: 'mild stderr warning\n' },
+      },
+    });
+
+    assert.equal(result.outcome, 'exited');
+    assert.equal(result.runDirExists, false, 'successful preservation must still clean up the run dir');
+    assert.equal(result.diagDirExists, true, 'real lane evidence must still be preserved');
+
+    const preserved = fs.existsSync(result.diagDir)
+      ? fs.readdirSync(result.diagDir).sort()
+      : [];
+    // Only the lane's own output belongs in the diagnostics folder.
+    assert.deepEqual(
+      preserved,
+      ['gsd-review-claude.err', 'gsd-review-claude.md'],
+      `diagnostics must hold exactly the lane report and stderr sidecar, not the run's input copies; got: ${preserved.join(', ')}`,
+    );
+    assert.equal(
+      fs.readFileSync(path.join(result.diagDir, 'gsd-review-claude.md'), 'utf-8'),
+      '# Claude review\nok\n',
+      'the lane report must be preserved byte-identically',
+    );
+    for (const inputName of Object.keys(INPUT_COPIES_4097)) {
+      assert.equal(
+        fs.existsSync(path.join(result.diagDir, inputName)),
+        false,
+        `input copy ${inputName} must NOT be swept into .review-diagnostics/ (#4097)`,
+      );
+    }
+  });
+
+  test('inputsOnlyRunLeavesNoDiagnosticsDir_4097', (t) => {
+    // Inputs only, no lane artifacts at all: inputs are not evidence, so
+    // this is the "nothing to preserve" branch — no diagnostics directory is
+    // created and cleanup proceeds (#4097 narrowing of #3352's glob).
+    const result = runWriteReviewsFlow(t, {
+      selected: 'claude',
+      jsonlLines: [],
+      seedFiles: INPUT_COPIES_4097,
+      lanes: {},
+    });
+
+    assert.equal(result.runDirExists, false, 'nothing to preserve is not a failure — run dir must still be removed');
+    assert.equal(result.diagDirExists, false, 'a run that produced only input copies has no evidence to preserve');
+  });
+});
+
 describe('#3352 preserved evidence is never swept into the commit (N6)', () => {
   test('preservedEvidenceIsNotSweptIntoTheCommit', (t) => {
     const result = runWriteReviewsFlow(t, {