v1.89.0.0 feat: add shared-code extraction audit (#2925)

* feat: bind shared-code review advice to source and branch

* feat: add shared-code extraction audit and scoped review checks

* test: recognize complete source reads and explicit coverage legends

* chore: bump version and changelog (v1.88.0.0)

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: capture native review questions and retain public evidence

Capture the actual first public native question with strict ownership and display matching. Preserve terminal failures and raw evidence, and retain SDK completion checks.

* test: recognize verified review evidence and complete fixtures

Recognize complete source and diagram evidence, concrete design and developer-experience decisions, and the complete planted scenario contracts. Preserve negative controls and grading thresholds.

* fix: preserve decision brief structure in native questions

Keep the required pros-and-cons heading and final Net field in native question text. Regenerate host outputs and document the release and evaluation repairs.

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* docs: update project documentation for v1.88.0.0

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* fix: correct eval retry accounting and ship workflow gates

* fix: capture native eval evidence and stabilize CI fixtures

* fix: keep shared-code eval skips read-only

Choose explicit no-change answers instead of mixed fix/preservation options.
Reuse the bounded revalidation prompt for path fixtures so required review
metadata is available without repeated discovery. Preserve source checks,
retry limits, and failed native terminal outcomes.

Add captured-question and callback regressions, plus evaluation selection
coverage for the affected fixtures.

---------

Co-authored-by: OpenAI Codex <noreply@openai.com>

review/sections/adversarial.md

@@ -252,7 +252,12 @@ High-confidence findings (agreed on by multiple sources) should be prioritized f
 
 If this pass applied any fixes (including adversarial fixes), repeat Steps 3–5.7 against the updated diff with a new REVIEW_START. A pass converges only when it completes without edits. Allow at most 3 fix cycles; if the third still applies fixes, persist `converged:false` and stop with the remaining findings. Do not capture a new token just to log the fixed tree.
 
+Keep the invocation action list across those cycles. The final zero-edit pass verifies the resulting code; it does not replace earlier completed actions with an empty list. Merge final-pass decisions with accumulated actions once per structural identity and advisory/defect kind. An approved extraction that removed the original duplication retains its `fixed` record with the original `evidence_paths` and `helper_target`; recompute its fingerprint from that preserved metadata, not from an invented replacement candidate. Verify the resulting helper/caller behavior and tests without requiring the removed blocks to still exist. Carry a skipped advisory into the final saved findings only after re-reading all its evidence against the final snapshot and confirming the same supported proposal and decision still apply. If that cannot be established, report the earlier choice as history in the response without binding it as a reusable skipped finding. A prior fixed action never clears a recurring defect: final unresolved counts and completion still come from the current pass.
+
+For each saved skipped shared-code advisory, record `snapshot_covered_paths` from the final snapshot eligibility checks in Step 5.0, including raw-byte equality with that snapshot's blobs. Recompute this list from actual reads; never copy coverage from earlier cycles, supplied findings, or prior records. Ineligible evidence can still support fresh advice, but omit it from the coverage list so the decision cannot be reused without revalidation. Persist an empty list when no path qualifies. Fixed advisories do not need reusable skip coverage.
+
 For the Step 5.8 record, REVIEW_START is the token captured before this pass's Step 3 diff read. COMPLETED is true only if the checklist and dispatched specialists completed; missing coverage is false, never clean. CONVERGED is true only for a completed pass with zero edits. CYCLES counts fix cycles (0 for a first-pass completion). Preserve unavailable specialist/provider coverage in the summary; completion of one source does not imply completion of another.
 
 - `specialists` = the per-specialist stats object compiled in Step 4.6. Each specialist that was considered gets an entry: `{"dispatched":true/false,"findings":N,"critical":N,"informational":N}` if dispatched, or `{"dispatched":false,"reason":"scope|gated"}` if skipped. Include Design specialist. Example: `{"testing":{"dispatched":true,"findings":2,"critical":0,"informational":2},"security":{"dispatched":false,"reason":"scope"}}`
-- `findings` = array of per-finding records from Step 5. For each finding (from critical pass and specialists), include: `{"fingerprint":"path:line:category","severity":"CRITICAL|INFORMATIONAL","action":"ACTION"}`. ACTION is `"auto-fixed"` (Step 5b), `"fixed"` (user approved in Step 5d), or `"skipped"` (user chose Skip in Step 5c). Suppressed findings from Step 5.0 are NOT included (they were already recorded in a prior review entry).
+- `findings` = array of per-finding records from Step 5 and the invocation action list, merged as above. For each finding (from core pass and specialists), include: `{"fingerprint":"path:line:category","severity":"CRITICAL|INFORMATIONAL","action":"ACTION"}` and preserve `advisory`, `evidence_paths`, and `helper_target` whenever present. For shared-code advisories, recompute the fingerprint with the same installed `sharedLibsFingerprint` helper from the core pass immediately before persistence; do not trust supplied or model-generated hashes. Recheck the supporting source after fixes, applying the fixed-versus-skipped rules above. ACTION is `"auto-fixed"` (Step 5b), `"fixed"` (user approved in Step 5d), or `"skipped"` (user explicitly chose Skip in Step 5c). Advisories may be `"fixed"` or `"skipped"`, never `"auto-fixed"`; silence is not a skip. If a user defers answering, preserve the pending advice in the response without inventing a saved decision. Findings suppressed from a persistent prior review in Step 5.0 are NOT included (they were already recorded); revalidated decisions from this invocation ARE included.
+- The review logger discards caller-supplied binding fields and constructs trusted `review_binding`, including a digest of the validated captured branch. Do not manufacture a binding or capture a fresh start token solely to obtain a matching fingerprint. Excluding advisory counts does not relax start-token, completion, convergence, or missing-reviewer rules.

review/sections/adversarial.md.tmpl

@@ -4,7 +4,12 @@
 
 If this pass applied any fixes (including adversarial fixes), repeat Steps 3–5.7 against the updated diff with a new REVIEW_START. A pass converges only when it completes without edits. Allow at most 3 fix cycles; if the third still applies fixes, persist `converged:false` and stop with the remaining findings. Do not capture a new token just to log the fixed tree.
 
+Keep the invocation action list across those cycles. The final zero-edit pass verifies the resulting code; it does not replace earlier completed actions with an empty list. Merge final-pass decisions with accumulated actions once per structural identity and advisory/defect kind. An approved extraction that removed the original duplication retains its `fixed` record with the original `evidence_paths` and `helper_target`; recompute its fingerprint from that preserved metadata, not from an invented replacement candidate. Verify the resulting helper/caller behavior and tests without requiring the removed blocks to still exist. Carry a skipped advisory into the final saved findings only after re-reading all its evidence against the final snapshot and confirming the same supported proposal and decision still apply. If that cannot be established, report the earlier choice as history in the response without binding it as a reusable skipped finding. A prior fixed action never clears a recurring defect: final unresolved counts and completion still come from the current pass.
+
+For each saved skipped shared-code advisory, record `snapshot_covered_paths` from the final snapshot eligibility checks in Step 5.0, including raw-byte equality with that snapshot's blobs. Recompute this list from actual reads; never copy coverage from earlier cycles, supplied findings, or prior records. Ineligible evidence can still support fresh advice, but omit it from the coverage list so the decision cannot be reused without revalidation. Persist an empty list when no path qualifies. Fixed advisories do not need reusable skip coverage.
+
 For the Step 5.8 record, REVIEW_START is the token captured before this pass's Step 3 diff read. COMPLETED is true only if the checklist and dispatched specialists completed; missing coverage is false, never clean. CONVERGED is true only for a completed pass with zero edits. CYCLES counts fix cycles (0 for a first-pass completion). Preserve unavailable specialist/provider coverage in the summary; completion of one source does not imply completion of another.
 
 - `specialists` = the per-specialist stats object compiled in Step 4.6. Each specialist that was considered gets an entry: `{"dispatched":true/false,"findings":N,"critical":N,"informational":N}` if dispatched, or `{"dispatched":false,"reason":"scope|gated"}` if skipped. Include Design specialist. Example: `{"testing":{"dispatched":true,"findings":2,"critical":0,"informational":2},"security":{"dispatched":false,"reason":"scope"}}`
-- `findings` = array of per-finding records from Step 5. For each finding (from critical pass and specialists), include: `{"fingerprint":"path:line:category","severity":"CRITICAL|INFORMATIONAL","action":"ACTION"}`. ACTION is `"auto-fixed"` (Step 5b), `"fixed"` (user approved in Step 5d), or `"skipped"` (user chose Skip in Step 5c). Suppressed findings from Step 5.0 are NOT included (they were already recorded in a prior review entry).
+- `findings` = array of per-finding records from Step 5 and the invocation action list, merged as above. For each finding (from core pass and specialists), include: `{"fingerprint":"path:line:category","severity":"CRITICAL|INFORMATIONAL","action":"ACTION"}` and preserve `advisory`, `evidence_paths`, and `helper_target` whenever present. For shared-code advisories, recompute the fingerprint with the same installed `sharedLibsFingerprint` helper from the core pass immediately before persistence; do not trust supplied or model-generated hashes. Recheck the supporting source after fixes, applying the fixed-versus-skipped rules above. ACTION is `"auto-fixed"` (Step 5b), `"fixed"` (user approved in Step 5d), or `"skipped"` (user explicitly chose Skip in Step 5c). Advisories may be `"fixed"` or `"skipped"`, never `"auto-fixed"`; silence is not a skip. If a user defers answering, preserve the pending advice in the response without inventing a saved decision. Findings suppressed from a persistent prior review in Step 5.0 are NOT included (they were already recorded); revalidated decisions from this invocation ARE included.
+- The review logger discards caller-supplied binding fields and constructs trusted `review_binding`, including a digest of the validated captured branch. Do not manufacture a binding or capture a fresh start token solely to obtain a matching fingerprint. Excluding advisory counts does not relax start-token, completion, convergence, or missing-reviewer rules.

review/sections/review-army.md

@@ -43,7 +43,7 @@ Based on the scope signals above, select which specialists to dispatch.
 1. **Testing** — read `~/.claude/skills/gstack/review/specialists/testing.md`
 2. **Maintainability** — read `~/.claude/skills/gstack/review/specialists/maintainability.md`
 
-**If DIFF_LINES < 50:** Skip all specialists. Print: "Small diff ($DIFF_LINES lines) — specialists skipped." Continue to Step 5.
+**If DIFF_LINES < 50:** Skip all specialists. Print: "Small diff ($DIFF_LINES lines) — specialists skipped." Continue to Step 5. This threshold only gates specialist dispatch; any core shared-code check still runs.
 
 **Conditional (dispatch if the matching scope signal is true):**
 3. **Security** — if SCOPE_AUTH=true, OR if SCOPE_BACKEND=true AND DIFF_LINES > 100. Read `~/.claude/skills/gstack/review/specialists/security.md`
@@ -97,7 +97,9 @@ For each finding, output a JSON object on its own line:
 {\"severity\":\"CRITICAL|INFORMATIONAL\",\"confidence\":N,\"path\":\"file\",\"line\":N,\"category\":\"category\",\"summary\":\"description\",\"fix\":\"recommended fix\",\"fingerprint\":\"path:line:category\",\"specialist\":\"name\"}
 
 Required fields: severity, confidence, path, category, summary, specialist.
-Optional: line, fix, fingerprint, evidence, test_stub.
+Optional: line, fix, fingerprint, evidence, test_stub, advisory, evidence_paths, helper_target.
+
+Optional extraction advice belongs to the core shared-code check; do not duplicate its proposals. Report real defects in duplicated code independently. Preserve advisory metadata when returning structural advice, and never label a demonstrated defect advisory merely because sharing a helper could fix it.
 
 If you can write a test that would catch this issue, include it in the `test_stub` field.
 Use the detected test framework ({TEST_FW}). Write a minimal skeleton — describe/it/test
@@ -129,12 +131,17 @@ For each specialist's output:
 2. Otherwise, parse each line as a JSON object. Skip lines that are not valid JSON.
 3. Collect all parsed findings into a single list, tagged with their specialist name.
 
+**Validate advisory severity first.** If a current finding has `"severity":"CRITICAL"` and `"advisory":true`, remove `advisory` and retain its `CRITICAL` severity. Handle it as a normal defect before fingerprinting, partitioning, deduplication, counting, scoring, and Fix-First. Never downgrade severity to make advisory metadata consistent. Valid INFORMATIONAL advisories remain advisory in every category, including simplification. Apply this validation to core and specialist findings alike before combining them.
+
 **Fingerprint and deduplicate:**
 For each finding, compute its fingerprint:
+- For a shared-code advisory (category `shared-libs` or a `shared-libs:` fingerprint), call the installed `sharedLibsFingerprint` helper from `~/.claude/skills/gstack/lib/review-evidence.ts` with literal JSON on stdin, as in the core pass. Recompute from `evidence_paths` and `helper_target`; never trust a supplied hash or generate hash text yourself. Missing/malformed metadata cannot deduplicate or reuse a saved decision.
 - If `fingerprint` field is present, use it
 - Otherwise: `{path}:{line}:{category}` (if line is present) or `{path}:{category}`
 
-Group findings by fingerprint. For findings sharing the same fingerprint:
+The last two rules apply only to other findings. Preserve `advisory`, `evidence_paths`, and `helper_target` through merging. Core review owns shared-code proposals: consolidate equivalent specialist advice with the core proposal and count overlapping savings once. Keep the actual specialist activity in its stats; core-only advice must not create a specialist dispatch or finding.
+
+Partition defects and advisories BEFORE grouping by fingerprint. A defect and an advisory must never merge with each other, even if a supplied fingerprint collides. A higher-confidence advisory or prior skipped extraction cannot replace, downgrade, or suppress a demonstrated defect. For findings sharing the same fingerprint within the same partition:
 - Keep the finding with the highest confidence score
 - Tag it: "MULTI-SPECIALIST CONFIRMED ({specialist1} + {specialist2})"
 - Boost confidence by +1 (cap at 10)
@@ -146,11 +153,13 @@ Group findings by fingerprint. For findings sharing the same fingerprint:
 - Confidence 3-4: move to appendix (suppress from main findings)
 - Confidence 1-2: suppress entirely
 
-**Advisory carve-out (simplification specialist):**
-Findings with `"advisory": true` are excluded from BOTH the quality_score
+**Advisory carve-out (all sources, including core shared-code and simplification):**
+After severity validation, remaining findings with `"advisory": true` are excluded from BOTH the quality_score
 summation and the findings-count header below — they are structure suggestions,
 not defects, and must not make "5 findings … 10/10" look contradictory. In
-Fix-First they are ASK-only: NEVER auto-applied, even when mechanical.
+Fix-First they are ASK-only: NEVER auto-applied, even when mechanical. Also exclude
+them from unresolved-defect totals and clean-status blockers. Preserve normal
+Fix-First handling for any real defect affecting the same code.
 
 **Compute PR Quality Score:**
 After merging, compute the quality score over NON-advisory findings only:
@@ -180,6 +189,8 @@ PR Quality Score: X/10
   `Simplification: lean already — nothing to cut.`
 - If it was not dispatched, print neither line.
 
+Do not add core shared-code savings to this specialist footer. Explain any overlap once in the core proposal instead of presenting duplicate savings.
+
 These findings flow into Step 5 Fix-First alongside the CRITICAL pass findings from Step 4.
 The Fix-First heuristic applies identically — specialist findings follow the same AUTO-FIX vs ASK classification (except advisory findings, which are ASK-only per the carve-out above).
 
@@ -192,7 +203,8 @@ For each specialist (testing, maintainability, security, performance, data-migra
 - If not applicable (e.g., red-team not activated): omit from the object
 
 Advisory findings COUNT in the stats `findings` field — the advisory
-carve-out governs the quality score and the findings-count header only.
+carve-out governs defect counts, score penalties, and clean-status blockers,
+not specialist activity. Count only findings that specialist actually returned.
 Logging simplification's advisories as `findings: 0` would auto-gate the
 lens into permanent silence after 10 dispatches.