Round 90: library-wide Human Review required/exempt set parity

Add DRY HR set parity helpers in prompt_eval_helpers and frozen
*_HUMAN_REVIEW_REQUIRED / *_HUMAN_REVIEW_EXEMPT sets with partition
tests for 01-thinking through 06-repo harness files. Refactor 00-core
tests to shared helpers. Sync governance (GLOSSARY step 22, panel
record, READMEs, QUALITY_GATES 580+ pytest floor).

Author: johnteee

README.md

@@ -21,7 +21,7 @@ Full library docs: [reflective-prompt-library/README.md](reflective-prompt-libra
 ## Governance
 
 - **Contributing:** [CONTRIBUTING.md](CONTRIBUTING.md) — quality gates, routing maintenance (R8–R12), `make all`
-- **Panel record:** [multi-agent-panel-consensus](reflective-prompt-library/plans/multi-agent-panel-consensus-2026-06-25.md) — six-lens Socratic consensus (Rounds 1–89)
+- **Panel record:** [multi-agent-panel-consensus](reflective-prompt-library/plans/multi-agent-panel-consensus-2026-06-25.md) — six-lens Socratic consensus (Rounds 1–90)
 - **Operator playbook:** [GLOSSARY.md](reflective-prompt-library/GLOSSARY.md) — Governance Maintenance Playbook
 
 The repository contains:

reflective-prompt-library/GLOSSARY.md

@@ -337,7 +337,7 @@ Curated top-of-cheatsheet summary of high-confusion routing traps (ROUTE-002 hol
 
 ## Governance Maintenance Playbook / 治理維護手冊
 
-Ongoing upkeep after panel close (Rounds 1–89). Not agent instructions — operator checklist.
+Ongoing upkeep after panel close (Rounds 1–90). Not agent instructions — operator checklist.
 
 **Operational test:** Before router tuning, add fresh ROUTE-002/003 holdout phrases; run `make all`; record decisions in `PROJECT_KNOWLEDGE.md` Decision Index when governance surface changes.
 
@@ -362,3 +362,4 @@ Ongoing upkeep after panel close (Rounds 1–89). Not agent instructions — ope
 19. When editing Human Review guards, use `prompt_eval_helpers.assert_human_review_preamble` in all `test_*_prompts_eval_harness.py` files (thinking lenses + composable categories).
 20. When adding or editing risk-bearing `00-core/` prompts with `## Human Review`, keep preamble escalation routed to `reflective-risk` and run `test_core_prompts_eval_harness.py` Human Review guards via `prompt_eval_helpers.py`.
 21. When editing `00-core/` Human Review coverage, keep `CORE_HUMAN_REVIEW_REQUIRED` and `CORE_HUMAN_REVIEW_EXEMPT` in `test_core_prompts_eval_harness.py` aligned with preamble `## Human Review` sections; run core HR parity tests.
+22. When editing Human Review coverage on thinking lenses or composable prompts (`01-thinking`–`06-repo`), keep frozen `*_HUMAN_REVIEW_REQUIRED` / `*_HUMAN_REVIEW_EXEMPT` sets in `test_*_prompts_eval_harness.py` aligned with preamble `## Human Review` sections; use `prompt_eval_helpers.assert_human_review_*` parity helpers and run HR set partition tests.

reflective-prompt-library/PROJECT_KNOWLEDGE.md

@@ -73,6 +73,7 @@ deferred promotions are recurrence-gated — see [panel backlog](plans/multi-age
 ## Decision Index
 
 - 2026-06-25 Round 85 panel — composable prompt Primary workflow surface preamble guards (`test_*_prompts_eval_harness.py`) + Supporting-lens exemption → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
+- 2026-06-25 Round 90 panel — library-wide Human Review required/exempt set parity (`01-thinking`–`06-repo`) + DRY `prompt_eval_helpers` HR set guards → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 - 2026-06-25 Round 89 panel — `00-core` Human Review required/exempt set parity (`CORE_HUMAN_REVIEW_REQUIRED` / `CORE_HUMAN_REVIEW_EXEMPT`) → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 - 2026-06-25 Round 88 panel — `00-core` Human Review preamble guards on risk-bearing prompts + `test_core_prompts_eval_harness.py` → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 - 2026-06-25 Round 87 panel — Human Review helper DRY + GLOSSARY playbook step repair → [record](plans/multi-agent-panel-consensus-2026-06-25.md)

reflective-prompt-library/README.md

@@ -30,7 +30,7 @@ Pick **Strictness L1–L6** first (`skills/reflective-dispatch/SKILL.md`, [GLOSS
 
 ## Governance Panel Record
 
-Multi-agent Socratic consensus on project goals and the nine skills (Rounds 1–89, options A–FW) is recorded in [plans/multi-agent-panel-consensus-2026-06-25.md](plans/multi-agent-panel-consensus-2026-06-25.md). Run `make all` before claiming routing or governance changes are verified.
+Multi-agent Socratic consensus on project goals and the nine skills (Rounds 1–90, options A–GB) is recorded in [plans/multi-agent-panel-consensus-2026-06-25.md](plans/multi-agent-panel-consensus-2026-06-25.md). Run `make all` before claiming routing or governance changes are verified.
 
 ## Directory Map
 

reflective-prompt-library/plans/QUALITY_GATES_SUMMARY.md

@@ -314,7 +314,7 @@ ROUTE-002 measures unseen phrasing separately from ROUTE-001. Round 7 (2026-06-2
 2. **ROUTE-001/002/003 in CI** — 128 + 102 + 53 paraphrases at 100% consistency (seeded fixtures); `validate_route_fixture.py` gates minimum coverage
 3. **Governance validators** — links, lint, governance metadata, PROJECT_KNOWLEDGE, benchmark fixture, skill examples
 4. **Harness policy docs** — CONTRIBUTING, AGENTS, SKILL_INSTALLATION, maintenance playbook
-5. **Doc anti-drift** — `test_routing_contract.py`, cheatsheet parity tests, `test_readme_governance.py`, `test_thinking_prompts_eval_harness.py`, `test_engineering_prompts_eval_harness.py`, `test_prompt_cross_links.py`, `test_core_prompts_eval_harness.py`, `test_agent_prompts_eval_harness.py`, `test_context_prompts_eval_harness.py`, `test_domain_prompts_eval_harness.py`, `test_repo_prompts_eval_harness.py`, `test_validate_governance.py`, `test_validate_links.py`, `test_lint_skills.py`, `test_skill_module_contract.py` (Escalation subsection + Trigger/Methods/Output/Never; 560+ pytest anti-drift suite in CI); reciprocal thinking-lens ↔ skill checks and `00-core` + composable `Primary workflow surface(s)` ↔ `*_SKILL_LINKS` parity in `test_prompt_cross_links.py` (including strict Primary workflow surfaces parity via `test_thinking_lens_primary_surfaces_match_consumer_graph`); Human Review + Escalation route-target guards in thinking/skill contract tests; composable `Primary workflow surface(s)` / Supporting-lens preamble guards and composable `## Human Review` preamble guards (route to `reflective-risk`) via `prompt_eval_helpers.assert_human_review_preamble` in `test_*_prompts_eval_harness.py`
+5. **Doc anti-drift** — `test_routing_contract.py`, cheatsheet parity tests, `test_readme_governance.py`, `test_thinking_prompts_eval_harness.py`, `test_engineering_prompts_eval_harness.py`, `test_prompt_cross_links.py`, `test_core_prompts_eval_harness.py`, `test_agent_prompts_eval_harness.py`, `test_context_prompts_eval_harness.py`, `test_domain_prompts_eval_harness.py`, `test_repo_prompts_eval_harness.py`, `test_validate_governance.py`, `test_validate_links.py`, `test_lint_skills.py`, `test_skill_module_contract.py` (Escalation subsection + Trigger/Methods/Output/Never; 580+ pytest anti-drift suite in CI); reciprocal thinking-lens ↔ skill checks and `00-core` + composable `Primary workflow surface(s)` ↔ `*_SKILL_LINKS` parity in `test_prompt_cross_links.py` (including strict Primary workflow surfaces parity via `test_thinking_lens_primary_surfaces_match_consumer_graph`); Human Review + Escalation route-target guards in thinking/skill contract tests; composable `Primary workflow surface(s)` / Supporting-lens preamble guards and composable `## Human Review` preamble guards (route to `reflective-risk`) via `prompt_eval_helpers.assert_human_review_preamble` in `test_*_prompts_eval_harness.py`; frozen `*_HUMAN_REVIEW_REQUIRED` / `*_HUMAN_REVIEW_EXEMPT` set parity across all prompt categories (Round 90)
 
 ### Ongoing maintenance (not blockers)
 
@@ -384,4 +384,4 @@ Phase 1 quality-gate tooling and documentation are **complete**. Routing consist
 - ✅ Benchmark fixture gate plus optional manual benchmark runs
 - ✅ Research-backed design decisions
 
-The project is positioned to grow sustainably with quality discipline built in from the start. **No open implementation blockers** remain from panel Rounds 1–89; work is recurrence-gated maintenance per playbook. The next measurable quality target is **holdout expansion before router tuning** and optional manual baseline-vs-skill benchmark runs — not shipping new core skills without promotion evidence.
+The project is positioned to grow sustainably with quality discipline built in from the start. **No open implementation blockers** remain from panel Rounds 1–90; work is recurrence-gated maintenance per playbook. The next measurable quality target is **holdout expansion before router tuning** and optional manual baseline-vs-skill benchmark runs — not shipping new core skills without promotion evidence.

reflective-prompt-library/plans/multi-agent-panel-consensus-2026-06-25.md

@@ -2539,3 +2539,50 @@ User directive (repeat): review prompts, plans, skills, and Socratic/critical-th
 ## Panel status (updated)
 
 **Resealed 2026-06-25** after **Round 89** (options FT–FW). `00-core` Human Review coverage is now explicit via frozen required/exempt sets; full library HR contract parity closed (thinking R81, composable R86, core R88–R89). Holdout expansion remains recurrence-gated maintenance.
+
+---
+
+## Round 90 — library-wide Human Review required/exempt set parity (2026-06-25)
+
+**Options FX–GB** | Six-lens panel (Opus, Codex, Gemini, Composer, Sakana, GLM)
+
+### Round 90 options
+
+| ID | Proposal | Verdict |
+| --- | --- | --- |
+| FX | DRY Human Review set parity helpers in `prompt_eval_helpers.py` + refactor `test_core_prompts_eval_harness.py` | **Agree** |
+| FY | Frozen `*_HUMAN_REVIEW_REQUIRED` / `*_HUMAN_REVIEW_EXEMPT` sets + pytest parity for `01-thinking`–`06-repo` | **Agree** |
+| FZ | GLOSSARY playbook step 22 + governance sync | **Agree** |
+| GA | ROUTE holdout expansion | **Defer** |
+| GB | Router / tenth skill / benchmark CI | **Reject** |
+
+### Round 90 verdict table
+
+| ID | Option | Verdict | Action |
+| --- | --- | --- | --- |
+| FX | HR set parity helpers | **Agree** | `assert_human_review_required_matches_detection`, `assert_human_review_exempt_have_no_preamble_section`, `assert_human_review_sets_partition` |
+| FY | Library HR frozen sets | **Agree** | codify required/exempt per category in all `test_*_prompts_eval_harness.py` files |
+| FZ | Playbook + docs | **Agree** | step 22; panel round 90 sync |
+| GA | Holdout expansion | **Defer** | maintenance |
+| GB | Router/tenth skill/benchmark CI | **Reject** | no change |
+
+**All roles agree.**
+
+## Implemented Changes (Round 90)
+
+- `plans/tests/prompt_eval_helpers.py`: shared Human Review set parity helpers
+- `plans/tests/test_core_prompts_eval_harness.py`: refactor to shared helpers
+- `plans/tests/test_{thinking,engineering,context,agent,domain,repo}_prompts_eval_harness.py`: frozen HR required/exempt sets + partition parity tests
+- `GLOSSARY.md`: playbook Rounds 1–90; step 22 for library-wide HR set parity
+- `QUALITY_GATES_SUMMARY.md`: HR set parity note; panel Rounds 1–90; 580+ pytest floor
+- `PROJECT_KNOWLEDGE.md`: Decision Index Round 90 entry
+- `README.md`, `reflective-prompt-library/README.md`, `test_readme_governance.py`: panel round 90 sync
+
+## Verification (Round 90)
+
+- `make all`: pytest + ROUTE-001/002/003 100%
+
+## Panel status (updated)
+
+**Resealed 2026-06-25** after **Round 90** (options FX–GB). Human Review coverage is now explicit via frozen required/exempt sets across all prompt categories (`00-core`–`06-repo`). Holdout expansion remains recurrence-gated maintenance.
+

reflective-prompt-library/plans/tests/prompt_eval_helpers.py

@@ -27,3 +27,39 @@ def assert_human_review_preamble(prompt_path: Path) -> None:
     assert "reflective-risk" in preamble, (
         f"{prompt_path.name} Human Review should route to reflective-risk"
     )
+
+
+def assert_human_review_required_matches_detection(
+    required: frozenset[str],
+    prompts: tuple[Path, ...],
+) -> None:
+    """Frozen required set must match prompts that declare ## Human Review in preambles."""
+    detected = {p.name for p in prompts_with_human_review(prompts)}
+    assert detected == required, (
+        f"detected Human Review preambles {sorted(detected)} "
+        f"!= frozen required {sorted(required)}"
+    )
+
+
+def assert_human_review_exempt_have_no_preamble_section(
+    exempt: frozenset[str],
+    prompts: tuple[Path, ...],
+) -> None:
+    """Exempt prompts keep Human Review cues in fenced templates only."""
+    by_name = {p.name: p for p in prompts}
+    for name in sorted(exempt):
+        assert not has_human_review_preamble(by_name[name]), (
+            f"{name} should not declare ## Human Review in preamble"
+        )
+
+
+def assert_human_review_sets_partition(
+    all_names: frozenset[str],
+    required: frozenset[str],
+    exempt: frozenset[str],
+) -> None:
+    """Required + exempt sets must cover all prompts without overlap."""
+    assert required | exempt == all_names, (
+        f"required ∪ exempt {sorted(required | exempt)} != all prompts {sorted(all_names)}"
+    )
+    assert not required & exempt, "required and exempt Human Review sets must not overlap"

reflective-prompt-library/plans/tests/test_agent_prompts_eval_harness.py

@@ -9,7 +9,7 @@
 sys.path.insert(0, str(Path(__file__).parent))
 
 from eval_harness import EvalHarness  # noqa: E402
-from prompt_eval_helpers import assert_human_review_preamble, prompts_with_human_review  # noqa: E402
+from prompt_eval_helpers import assert_human_review_preamble, prompts_with_human_review, assert_human_review_required_matches_detection, assert_human_review_exempt_have_no_preamble_section, assert_human_review_sets_partition  # noqa: E402
 
 AGENT_DIR = Path(__file__).parent.parent.parent / "04-agent"
 REPO_ROOT = str(Path(__file__).parent.parent.parent.parent)
@@ -25,6 +25,22 @@
 AGENT_PROMPTS = tuple(sorted(AGENT_DIR.glob("*.md")))
 AGENT_PROMPTS_WITH_HUMAN_REVIEW = prompts_with_human_review(AGENT_PROMPTS)
 SUPPORTING_LENS_AGENT_PROMPTS = frozenset({"runtime-trust-boundary.md"})
+AGENT_HUMAN_REVIEW_REQUIRED = frozenset({
+    "agent-scaffold-provenance.md",
+    "agent-selection.md",
+    "memory-consolidation.md",
+    "retro.md",
+    "review-rating-fix.md",
+    "runtime-trust-boundary.md",
+    "sop-compiler.md",
+})
+AGENT_HUMAN_REVIEW_EXEMPT = frozenset({
+    "workflow-engine.md",
+    "workflow-recipes.md",
+})
+
+AGENT_PROMPTS_WITH_HUMAN_REVIEW = prompts_with_human_review(AGENT_PROMPTS)
+
 
 
 @pytest.fixture(scope="module")
@@ -87,3 +103,27 @@ def test_agent_prompts_have_workflow_surface_preamble_line():
 def test_agent_prompt_has_human_review_section(prompt_path: Path):
     """Prompts with Human Review declare escalation outside zh-TW templates."""
     assert_human_review_preamble(prompt_path)
+
+def test_agent_human_review_required_set_matches_detection():
+    """Frozen required set must match prompts that declare ## Human Review in preambles."""
+    assert_human_review_required_matches_detection(
+        AGENT_HUMAN_REVIEW_REQUIRED, AGENT_PROMPTS
+    )
+
+
+def test_agent_human_review_exempt_prompts_have_no_preamble_section():
+    """Exempt prompts keep Human Review cues in fenced templates only."""
+    assert_human_review_exempt_have_no_preamble_section(
+        AGENT_HUMAN_REVIEW_EXEMPT, AGENT_PROMPTS
+    )
+
+
+def test_agent_human_review_sets_partition_prompts():
+    """Required + exempt sets must cover all prompts without overlap."""
+    all_names = frozenset(p.name for p in AGENT_PROMPTS)
+    assert_human_review_sets_partition(
+        all_names,
+        AGENT_HUMAN_REVIEW_REQUIRED,
+        AGENT_HUMAN_REVIEW_EXEMPT,
+    )
+

reflective-prompt-library/plans/tests/test_context_prompts_eval_harness.py

@@ -9,7 +9,7 @@
 sys.path.insert(0, str(Path(__file__).parent))
 
 from eval_harness import EvalHarness  # noqa: E402
-from prompt_eval_helpers import assert_human_review_preamble, prompts_with_human_review  # noqa: E402
+from prompt_eval_helpers import assert_human_review_preamble, prompts_with_human_review, assert_human_review_required_matches_detection, assert_human_review_exempt_have_no_preamble_section, assert_human_review_sets_partition  # noqa: E402
 
 CONTEXT_DIR = Path(__file__).parent.parent.parent / "03-context"
 REPO_ROOT = str(Path(__file__).parent.parent.parent.parent)
@@ -24,6 +24,20 @@
 
 CONTEXT_PROMPTS = tuple(sorted(CONTEXT_DIR.glob("*.md")))
 CONTEXT_PROMPTS_WITH_HUMAN_REVIEW = prompts_with_human_review(CONTEXT_PROMPTS)
+CONTEXT_HUMAN_REVIEW_REQUIRED = frozenset({
+    "context-handoff.md",
+    "low-token.md",
+    "small-context.md",
+})
+CONTEXT_HUMAN_REVIEW_EXEMPT = frozenset({
+    "context-engineering.md",
+    "gemini-long-document.md",
+    "large-context.md",
+    "medium-context.md",
+})
+
+CONTEXT_PROMPTS_WITH_HUMAN_REVIEW = prompts_with_human_review(CONTEXT_PROMPTS)
+
 
 
 @pytest.fixture(scope="module")
@@ -80,3 +94,27 @@ def test_context_prompts_have_primary_workflow_surfaces_line():
 def test_context_prompt_has_human_review_section(prompt_path: Path):
     """Prompts with Human Review declare escalation outside zh-TW templates."""
     assert_human_review_preamble(prompt_path)
+
+def test_context_human_review_required_set_matches_detection():
+    """Frozen required set must match prompts that declare ## Human Review in preambles."""
+    assert_human_review_required_matches_detection(
+        CONTEXT_HUMAN_REVIEW_REQUIRED, CONTEXT_PROMPTS
+    )
+
+
+def test_context_human_review_exempt_prompts_have_no_preamble_section():
+    """Exempt prompts keep Human Review cues in fenced templates only."""
+    assert_human_review_exempt_have_no_preamble_section(
+        CONTEXT_HUMAN_REVIEW_EXEMPT, CONTEXT_PROMPTS
+    )
+
+
+def test_context_human_review_sets_partition_prompts():
+    """Required + exempt sets must cover all prompts without overlap."""
+    all_names = frozenset(p.name for p in CONTEXT_PROMPTS)
+    assert_human_review_sets_partition(
+        all_names,
+        CONTEXT_HUMAN_REVIEW_REQUIRED,
+        CONTEXT_HUMAN_REVIEW_EXEMPT,
+    )
+

reflective-prompt-library/plans/tests/test_core_prompts_eval_harness.py

@@ -10,8 +10,10 @@
 
 from eval_harness import EvalHarness  # noqa: E402
 from prompt_eval_helpers import (  # noqa: E402
+    assert_human_review_exempt_have_no_preamble_section,
     assert_human_review_preamble,
-    has_human_review_preamble,
+    assert_human_review_required_matches_detection,
+    assert_human_review_sets_partition,
     prompts_with_human_review,
 )
 
@@ -98,20 +100,23 @@ def test_core_prompt_has_human_review_section(prompt_path: Path):
 
 def test_core_human_review_required_set_matches_detection():
     """Frozen required set must match prompts that declare ## Human Review in preambles."""
-    detected = {p.name for p in CORE_PROMPTS_WITH_HUMAN_REVIEW}
-    assert detected == CORE_HUMAN_REVIEW_REQUIRED
+    assert_human_review_required_matches_detection(
+        CORE_HUMAN_REVIEW_REQUIRED, CORE_PROMPTS
+    )
 
 
 def test_core_human_review_exempt_prompts_have_no_preamble_section():
     """L1 opener prompts keep Human Review cues in fenced templates only."""
-    for name in CORE_HUMAN_REVIEW_EXEMPT:
-        assert not has_human_review_preamble(CORE_DIR / name), (
-            f"{name} should not declare ## Human Review in preamble (exempt opener)"
-        )
+    assert_human_review_exempt_have_no_preamble_section(
+        CORE_HUMAN_REVIEW_EXEMPT, CORE_PROMPTS
+    )
 
 
 def test_core_human_review_sets_partition_core_prompts():
     """Required + exempt sets must cover all 00-core prompts without overlap."""
-    all_names = {p.name for p in CORE_PROMPTS}
-    assert CORE_HUMAN_REVIEW_REQUIRED | CORE_HUMAN_REVIEW_EXEMPT == all_names
-    assert not CORE_HUMAN_REVIEW_REQUIRED & CORE_HUMAN_REVIEW_EXEMPT
+    all_names = frozenset(p.name for p in CORE_PROMPTS)
+    assert_human_review_sets_partition(
+        all_names,
+        CORE_HUMAN_REVIEW_REQUIRED,
+        CORE_HUMAN_REVIEW_EXEMPT,
+    )