Round 93: cross-category eval_harness contract heading library registry

- DRY PROMPT_CONTRACT_HEADINGS, PROMPT_EVAL_MIN_SCORE, assert_prompt_contract_headings in prompt_eval_helpers.py
- Add test_prompt_contract_library_registry.py for library-wide contract parity
- Refactor all test_*_prompts_eval_harness.py to use shared contract constants
- Governance sync: GLOSSARY step 25, panel record, QUALITY_GATES 615+ 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 1–92)
+- **Panel record:** [multi-agent-panel-consensus](reflective-prompt-library/plans/multi-agent-panel-consensus-2026-06-25.md) — six-lens Socratic consensus (Rounds 1–93)
 - **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 1–92). Not agent instructions — operator checklist.
+Ongoing upkeep after panel close (Rounds 1–93). 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.
 
@@ -365,3 +365,4 @@ Ongoing upkeep after panel close (Rounds 1–92). Not agent instructions — ope
 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.
 23. When adding composable prompts or new categories, keep `PROMPT_LIBRARY_CATEGORIES` and `test_human_review_library_registry.py` aligned so frozen HR sets cover every `00-core`–`06-repo` prompt exactly once.
 24. When adding composable prompts or editing `*_SKILL_LINKS` / `*_THINKING_LINKS`, keep per-category dict keys aligned with prompt globs and run `test_prompt_skill_links_library_registry.py` plus `test_all_*_prompts_have_skill_link` in `test_prompt_cross_links.py`.
+25. When adding composable prompts or editing eval_harness contract preambles, keep `PROMPT_CONTRACT_HEADINGS` / `PROMPT_EVAL_MIN_SCORE` in `prompt_eval_helpers.py` and run `test_prompt_contract_library_registry.py` plus per-category `test_*_prompts_eval_harness.py` guards.

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 93 panel — cross-category eval_harness contract heading library registry (`test_prompt_contract_library_registry.py`, DRY `PROMPT_CONTRACT_HEADINGS`) → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 - 2026-06-25 Round 92 panel — cross-category skill/thinking cross-link library registry (`test_prompt_skill_links_library_registry.py`) + missing `test_all_*_prompts_have_skill_link` guards → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 - 2026-06-25 Round 91 panel — cross-category Human Review library registry (`test_human_review_library_registry.py`, `PROMPT_LIBRARY_CATEGORIES`) → [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)

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 1–92, options A–GL) 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 1–93, options A–GQ) 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_human_review_library_registry.py`, `test_prompt_skill_links_library_registry.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; 600+ 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)
+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_human_review_library_registry.py`, `test_prompt_skill_links_library_registry.py`, `test_prompt_contract_library_registry.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; 615+ 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); library-wide contract heading registry (`PROMPT_CONTRACT_HEADINGS`, Round 93)
 
 ### 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 1–92; 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 1–93; 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

@@ -2677,3 +2677,55 @@ User directive (repeat): review prompts, plans, skills, and Socratic/critical-th
 
 **Resealed 2026-06-25** after **Round 92** (options GH–GL). Primary workflow surface cross-links are now library-registry checked (`00-core`, `02-engineering`–`06-repo`) with thinking-lens consumer map parity for `01-thinking`. Holdout expansion remains recurrence-gated maintenance.
 
+## Round 93 — cross-category eval_harness contract heading library registry (2026-06-25)
+
+**Options GM–GQ** | Six-lens panel (Opus, Codex, Gemini, Composer, Sakana, GLM)
+
+### Round 93 options
+
+| ID | Proposal | Verdict |
+| --- | --- | --- |
+| GM | DRY `PROMPT_CONTRACT_HEADINGS` / `PROMPT_EVAL_MIN_SCORE` / `assert_prompt_contract_headings` in `prompt_eval_helpers.py`; refactor `test_*_prompts_eval_harness.py` | **Agree** |
+| GN | `test_prompt_contract_library_registry.py` cross-category contract registry + library glob parity | **Agree** |
+| GO | GLOSSARY playbook step 25 + governance sync | **Agree** |
+| GP | ROUTE holdout expansion | **Defer** |
+| GQ | Router / tenth skill / benchmark CI | **Reject** |
+
+### Round 93 verdict table
+
+| ID | Option | Verdict | Action |
+| --- | --- | --- | --- |
+| GM | Shared contract constants | **Agree** | `prompt_eval_helpers.py` + harness refactor |
+| GN | Contract library registry | **Agree** | `test_prompt_contract_library_registry.py` |
+| GO | Playbook + docs | **Agree** | step 25; panel round 93 sync |
+| GP | Holdout expansion | **Defer** | maintenance |
+| GQ | Router/tenth skill/benchmark CI | **Reject** | no change |
+
+### Socratic rationale (Round 93)
+
+- **Opus:** Rounds 91–92 closed HR and cross-link library registries; contract headings remain duplicated across seven harness files with no library-wide falsifiability.
+- **Codex:** Centralizing `PROMPT_CONTRACT_HEADINGS` prevents per-category drift; registry test mirrors HR/cross-link pattern.
+- **Gemini:** Low-risk maintenance; no router or skill-count changes.
+- **Composer:** `assert_prompt_contract_headings` DRYs seven identical test bodies.
+- **Sakana:** `01-thinking` included in contract registry (unlike cross-link composable-only registry) because all categories share the same preamble contract.
+- **GLM:** Unanimous — implement GM–GO only.
+
+## Implemented Changes (Round 93)
+
+- `plans/tests/prompt_eval_helpers.py`: `PROMPT_CONTRACT_HEADINGS`, `PROMPT_EVAL_MIN_SCORE`, `assert_prompt_contract_headings`
+- `plans/tests/test_*_prompts_eval_harness.py`: import shared contract constants; DRY contract heading guards
+- `plans/tests/test_prompt_contract_library_registry.py`: cross-category contract registry + library glob parity
+- `GLOSSARY.md`: playbook Rounds 1–93; step 25 for contract library registry
+- `QUALITY_GATES_SUMMARY.md`: contract registry note; panel Rounds 1–93; 615+ pytest floor
+- `PROJECT_KNOWLEDGE.md`: Decision Index Round 93 entry
+- `README.md`, `reflective-prompt-library/README.md`, `test_readme_governance.py`: panel round 93 sync
+
+## Verification (Round 93)
+
+- `make all`: pytest + ROUTE-001/002/003 100%
+
+---
+
+**Resealed 2026-06-25** after **Round 93** (options GM–GQ). Eval_harness contract headings are now library-registry checked across all `00-core`–`06-repo` prompts with shared `PROMPT_CONTRACT_HEADINGS`. Holdout expansion remains recurrence-gated maintenance.
+
+

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

@@ -15,6 +15,24 @@
     "06-repo",
 )
 
+PROMPT_CONTRACT_HEADINGS = (
+    "## Purpose",
+    "## Scope",
+    "## Acceptance Criteria",
+    "## Falsifiability",
+)
+
+PROMPT_EVAL_MIN_SCORE = 80.0
+
+
+def assert_prompt_contract_headings(prompt_path: Path) -> None:
+    """Contract headings must appear in preamble outside fenced template blocks."""
+    preamble = prompt_preamble(prompt_path)
+    for heading in PROMPT_CONTRACT_HEADINGS:
+        assert heading in preamble, (
+            f"{prompt_path.name} missing {heading} outside template block"
+        )
+
 
 def prompt_preamble(prompt_path: Path) -> str:
     return prompt_path.read_text(encoding="utf-8").split("```", 1)[0]

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

@@ -9,18 +9,13 @@
 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, assert_human_review_required_matches_detection, assert_human_review_exempt_have_no_preamble_section, assert_human_review_sets_partition  # 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, PROMPT_CONTRACT_HEADINGS, PROMPT_EVAL_MIN_SCORE, assert_prompt_contract_headings  # noqa: E402
+
+REQUIRED_HEADINGS = PROMPT_CONTRACT_HEADINGS
+MIN_SCORE = PROMPT_EVAL_MIN_SCORE
 
 AGENT_DIR = Path(__file__).parent.parent.parent / "04-agent"
 REPO_ROOT = str(Path(__file__).parent.parent.parent.parent)
-MIN_SCORE = 80.0
-
-REQUIRED_HEADINGS = (
-    "## Purpose",
-    "## Scope",
-    "## Acceptance Criteria",
-    "## Falsifiability",
-)
 
 AGENT_PROMPTS = tuple(sorted(AGENT_DIR.glob("*.md")))
 AGENT_PROMPTS_WITH_HUMAN_REVIEW = prompts_with_human_review(AGENT_PROMPTS)
@@ -49,10 +44,7 @@ def harness() -> EvalHarness:
 
 @pytest.mark.parametrize("prompt_path", AGENT_PROMPTS, ids=lambda p: p.name)
 def test_agent_prompt_has_contract_headings(prompt_path: Path):
-    text = prompt_path.read_text(encoding="utf-8")
-    preamble = text.split("```", 1)[0]
-    for heading in REQUIRED_HEADINGS:
-        assert heading in preamble, f"{prompt_path.name} missing {heading} outside template block"
+    assert_prompt_contract_headings(prompt_path)
 
 
 @pytest.mark.parametrize("prompt_path", AGENT_PROMPTS, ids=lambda p: p.name)

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

@@ -9,18 +9,13 @@
 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, assert_human_review_required_matches_detection, assert_human_review_exempt_have_no_preamble_section, assert_human_review_sets_partition  # 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, PROMPT_CONTRACT_HEADINGS, PROMPT_EVAL_MIN_SCORE, assert_prompt_contract_headings  # noqa: E402
+
+REQUIRED_HEADINGS = PROMPT_CONTRACT_HEADINGS
+MIN_SCORE = PROMPT_EVAL_MIN_SCORE
 
 CONTEXT_DIR = Path(__file__).parent.parent.parent / "03-context"
 REPO_ROOT = str(Path(__file__).parent.parent.parent.parent)
-MIN_SCORE = 80.0
-
-REQUIRED_HEADINGS = (
-    "## Purpose",
-    "## Scope",
-    "## Acceptance Criteria",
-    "## Falsifiability",
-)
 
 CONTEXT_PROMPTS = tuple(sorted(CONTEXT_DIR.glob("*.md")))
 CONTEXT_PROMPTS_WITH_HUMAN_REVIEW = prompts_with_human_review(CONTEXT_PROMPTS)
@@ -46,10 +41,7 @@ def harness() -> EvalHarness:
 
 @pytest.mark.parametrize("prompt_path", CONTEXT_PROMPTS, ids=lambda p: p.name)
 def test_context_prompt_has_contract_headings(prompt_path: Path):
-    text = prompt_path.read_text(encoding="utf-8")
-    preamble = text.split("```", 1)[0]
-    for heading in REQUIRED_HEADINGS:
-        assert heading in preamble, f"{prompt_path.name} missing {heading} outside template block"
+    assert_prompt_contract_headings(prompt_path)
 
 
 @pytest.mark.parametrize("prompt_path", CONTEXT_PROMPTS, ids=lambda p: p.name)

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

@@ -9,24 +9,22 @@
 sys.path.insert(0, str(Path(__file__).parent))
 
 from eval_harness import EvalHarness  # noqa: E402
-from prompt_eval_helpers import (  # noqa: E402
+from prompt_eval_helpers import (
+    PROMPT_CONTRACT_HEADINGS,
+    PROMPT_EVAL_MIN_SCORE,
+    assert_prompt_contract_headings,  # noqa: E402
     assert_human_review_exempt_have_no_preamble_section,
     assert_human_review_preamble,
     assert_human_review_required_matches_detection,
     assert_human_review_sets_partition,
     prompts_with_human_review,
 )
 
+REQUIRED_HEADINGS = PROMPT_CONTRACT_HEADINGS
+MIN_SCORE = PROMPT_EVAL_MIN_SCORE
+
 CORE_DIR = Path(__file__).parent.parent.parent / "00-core"
 REPO_ROOT = str(Path(__file__).parent.parent.parent.parent)
-MIN_SCORE = 80.0
-
-REQUIRED_HEADINGS = (
-    "## Purpose",
-    "## Scope",
-    "## Acceptance Criteria",
-    "## Falsifiability",
-)
 
 CORE_PROMPTS = tuple(sorted(CORE_DIR.glob("*.md")))
 CORE_HUMAN_REVIEW_REQUIRED = frozenset({
@@ -53,10 +51,7 @@ def harness() -> EvalHarness:
 
 @pytest.mark.parametrize("prompt_path", CORE_PROMPTS, ids=lambda p: p.name)
 def test_core_prompt_has_contract_headings(prompt_path: Path):
-    text = prompt_path.read_text(encoding="utf-8")
-    preamble = text.split("```", 1)[0]
-    for heading in REQUIRED_HEADINGS:
-        assert heading in preamble, f"{prompt_path.name} missing {heading} outside template block"
+    assert_prompt_contract_headings(prompt_path)
 
 
 @pytest.mark.parametrize("prompt_path", CORE_PROMPTS, ids=lambda p: p.name)