Snapshot WIP: solver HP epic progress, BPHX/HX physics, BMAD skill refresh.

Capture uncommitted solver robustness work (regularization, domain errors, linear solver lifecycle, tube DP/MSH), web workbench updates, and synced BMAD skills across IDE agent folders before starting BPHX pressure-drop.

Co-authored-by: Cursor <cursoragent@cursor.com>

.agent/skills/bmad-architecture/scripts/lint_spine.py

@@ -0,0 +1,257 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.10"
+# ///
+"""lint-spine — the mechanical half of spine decision-integrity, done deterministically.
+
+LLMs miscount IDs and miss literal placeholders; a grep does not. This linter owns the
+checks a script does better than a prompt, and leaves the semantic half (is each Rule
+actually enforceable? does the boundary make sense?) to the rubric walker.
+
+It reads ARCHITECTURE-SPINE.md from a workspace and reports, as compact JSON on stdout:
+
+  - placeholder    literal TBD / TODO / "similar to AD-n" / unfilled {template-token}
+  - ad_id          duplicate or non-monotonic AD-n identifiers
+  - ad_fields      an AD-n block missing Binds / Prevents / Rule
+  - version_pin    a ## Stack table row with no version
+
+Fenced code blocks are blanked (replaced with equal-count blank lines) before scanning, so
+mermaid and source trees don't trip false positives AND reported line numbers still line up
+with the real file. Reported lines are absolute file lines (frontmatter offset added). Exit
+code is always 0 — findings travel in the JSON; the caller (Reviewer Gate / rubric walker)
+decides what to do with them.
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import re
+import sys
+from pathlib import Path
+
+SPINE = "ARCHITECTURE-SPINE.md"
+
+AD_HEADING = re.compile(r"^#{2,4}\s*AD-(\d+)\b(.*)$", re.MULTILINE)
+HEADING = re.compile(r"^#{1,6}\s", re.MULTILINE)
+FENCE = re.compile(r"```.*?```", re.DOTALL)
+PLACEHOLDER_WORD = re.compile(r"\b(TBD|TODO|FIXME|XXX)\b")
+SIMILAR_TO = re.compile(r"similar to AD-\d+", re.IGNORECASE)
+TEMPLATE_TOKEN = re.compile(r"\{[a-z_][a-z0-9_ /.-]*\}")
+
+
+def split_frontmatter(text: str) -> tuple[str, str, int]:
+    """Return (frontmatter, body, body_line_offset).
+
+    Frontmatter is the content between the first two lines that are *exactly* `---`
+    (line-exact, like memlog.split — a `---` inside a value or a body thematic break never
+    truncates it). body_line_offset is the number of file lines before the body begins, so a
+    body-relative line number plus the offset gives the absolute file line. Absent frontmatter
+    → ('', text, 0)."""
+    lines = text.split("\n")
+    if lines and lines[0] == "---":
+        for i in range(1, len(lines)):
+            if lines[i] == "---":
+                fm = "\n".join(lines[1:i])
+                body = "\n".join(lines[i + 1:])
+                return fm, body, i + 1
+    return "", text, 0
+
+
+def blank_fences(text: str) -> str:
+    """Replace each fenced block with the same number of newlines, so scanning skips fenced
+    content while every line number outside the fence stays put."""
+    return FENCE.sub(lambda m: "\n" * m.group(0).count("\n"), text)
+
+
+def line_of(text: str, idx: int) -> int:
+    return text.count("\n", 0, idx) + 1
+
+
+def find_placeholders(body: str, offset: int) -> list[dict]:
+    findings: list[dict] = []
+    scan = blank_fences(body)
+    # (regex, label, severity) — TBD/TODO and dangling cross-refs are unambiguous; a bare
+    # {template-token} can be legitimate brace prose, so it is flagged low ("possible") to keep
+    # the mechanical pass near-zero false-positive rather than train reviewers to ignore it.
+    for rx, label, severity in (
+        (PLACEHOLDER_WORD, "placeholder marker", "high"),
+        (SIMILAR_TO, "unresolved cross-reference", "high"),
+        (TEMPLATE_TOKEN, "possible unfilled template token (verify)", "low"),
+    ):
+        for m in rx.finditer(scan):
+            findings.append({
+                "category": "placeholder",
+                "severity": severity,
+                "detail": f"{label}: {m.group(0)!r}",
+                "location": f"{SPINE} (line {offset + line_of(scan, m.start())})",
+            })
+    return findings
+
+
+def find_frontmatter_placeholders(frontmatter: str) -> list[dict]:
+    """Catch unfilled tokens left in frontmatter (e.g. paradigm/scope/date) — part of the
+    spine contract, but outside the body that find_placeholders scans."""
+    findings: list[dict] = []
+    for rx, label, severity in (
+        (PLACEHOLDER_WORD, "placeholder marker", "high"),
+        (TEMPLATE_TOKEN, "possible unfilled template token (verify)", "low"),
+    ):
+        for m in rx.finditer(frontmatter):
+            findings.append({
+                "category": "placeholder",
+                "severity": severity,
+                "detail": f"frontmatter {label}: {m.group(0)!r}",
+                "location": f"{SPINE} frontmatter (line {1 + line_of(frontmatter, m.start())})",
+            })
+    return findings
+
+
+def find_ad_issues(body: str, offset: int) -> list[dict]:
+    findings: list[dict] = []
+    scan = blank_fences(body)  # AD headings shown inside a code fence are not live ADs
+    matches = list(AD_HEADING.finditer(scan))
+    seen: dict[int, int] = {}
+    prev: int | None = None
+    for m in matches:
+        num = int(m.group(1))
+        file_line = offset + line_of(scan, m.start())
+        loc = f"{SPINE} AD-{num} (line {file_line})"
+        if num in seen:
+            findings.append({
+                "category": "ad_id",
+                "severity": "high",
+                "detail": f"AD-{num} id reused (also at line {seen[num]})",
+                "location": loc,
+            })
+        else:
+            seen[num] = file_line
+        if prev is not None and num <= prev:
+            findings.append({
+                "category": "ad_id",
+                "severity": "high",
+                "detail": f"AD-{num} is non-monotonic (follows AD-{prev}); ids must ascend and never renumber",
+                "location": loc,
+            })
+        prev = num if prev is None else max(prev, num)
+
+        # block text = from this heading to the next heading of any level
+        start = m.end()
+        nxt = HEADING.search(scan, start)
+        block = scan[start:nxt.start()] if nxt else scan[start:]
+        low = block.lower()
+        missing = [f for f in ("binds", "prevents", "rule") if f not in low]
+        if missing:
+            findings.append({
+                "category": "ad_fields",
+                "severity": "high",
+                "detail": f"AD-{num} missing required field(s): {', '.join(missing)}",
+                "location": loc,
+            })
+    return findings
+
+
+def find_unpinned_stack(body: str, offset: int) -> list[dict]:
+    """Flag a `## Stack` table row that names something but leaves its version blank or a
+    placeholder. Pinning lives in the body table now, not frontmatter. A row whose name is
+    still a `{token}` skeleton is left to the placeholder pass, not double-reported here.
+
+    Fences are blanked first (like find_placeholders / find_ad_issues), so a pipe-row or
+    heading inside a code block is never read as live Stack content. The heading match is
+    `## Stack` with a word boundary, so a renamed heading (`## Stack & Versions`) still
+    counts. Name and Version columns are located from the header row, so a reordered table
+    pairs name to version correctly; both default to the canonical positions (0, 1)."""
+    findings: list[dict] = []
+    in_stack = False
+    header_seen = False
+    name_idx, ver_idx = 0, 1
+    scan = blank_fences(body)
+    for i, raw in enumerate(scan.splitlines()):
+        if HEADING.match(raw):
+            in_stack = re.match(r"^##\s+Stack\b", raw) is not None
+            header_seen = False
+            name_idx, ver_idx = 0, 1
+            continue
+        if not in_stack or not raw.lstrip().startswith("|"):
+            continue
+        if set(raw.strip()) <= set("|-: "):
+            continue  # separator row
+        cells = _table_cells(raw)
+        if not header_seen:
+            header_seen = True
+            for j, c in enumerate(cells):
+                if c.lower() == "name":
+                    name_idx = j
+                elif c.lower() == "version":
+                    ver_idx = j
+            continue
+        name = cells[name_idx] if len(cells) > name_idx else ""
+        version = cells[ver_idx] if len(cells) > ver_idx else ""
+        if not name or TEMPLATE_TOKEN.search(name):
+            continue
+        if not version or TEMPLATE_TOKEN.search(version):
+            findings.append({
+                "category": "version_pin",
+                "severity": "medium",
+                "detail": f"Stack entry {name!r} has no version",
+                "location": f"{SPINE} (line {offset + i + 1})",
+            })
+    return findings
+
+
+def _table_cells(row: str) -> list[str]:
+    """Split a markdown table row into trimmed cells, dropping the leading/trailing pipe."""
+    s = row.strip()
+    if s.startswith("|"):
+        s = s[1:]
+    if s.endswith("|"):
+        s = s[:-1]
+    return [c.strip() for c in s.split("|")]
+
+
+def lint(text: str) -> dict:
+    frontmatter, body, offset = split_frontmatter(text)
+    findings: list[dict] = []
+    findings += find_frontmatter_placeholders(frontmatter)
+    findings += find_placeholders(body, offset)
+    findings += find_ad_issues(body, offset)
+    findings += find_unpinned_stack(body, offset)
+    counts: dict[str, int] = {}
+    for f in findings:
+        counts[f["severity"]] = counts.get(f["severity"], 0) + 1
+    return {
+        "ok": len(findings) == 0,
+        "spine": SPINE,
+        "total_findings": len(findings),
+        "by_severity": counts,
+        "findings": findings,
+    }
+
+
+def main(argv: list[str] | None = None) -> int:
+    ap = argparse.ArgumentParser(description="Lint an architecture spine for mechanical integrity.")
+    ap.add_argument("--workspace", required=True, help="run folder containing ARCHITECTURE-SPINE.md")
+    ap.add_argument("-o", "--output", help="write JSON here instead of stdout")
+    args = ap.parse_args(argv)
+
+    spine_path = Path(args.workspace) / SPINE
+    if not spine_path.exists():
+        result = {"ok": False, "error": f"{spine_path} not found", "findings": [], "total_findings": 0}
+    else:
+        try:
+            text = spine_path.read_text(encoding="utf-8")
+        except (OSError, UnicodeDecodeError) as e:
+            # honor the "exit code is always 0" contract: a read/decode failure travels in JSON
+            result = {"ok": False, "error": f"could not read {spine_path}: {e}", "findings": [], "total_findings": 0}
+        else:
+            result = lint(text)
+
+    out = json.dumps(result, indent=2)
+    if args.output:
+        Path(args.output).write_text(out + "\n", encoding="utf-8")
+    else:
+        print(out)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.agent/skills/bmad-architecture/scripts/tests/test_lint_spine.py

@@ -0,0 +1,270 @@
+# /// script
+# requires-python = ">=3.10"
+# dependencies = ["pytest>=8.0"]
+# ///
+"""Tests for lint_spine.py. Run: uv run --with pytest pytest scripts/tests/test_lint_spine.py
+
+The spine under test: a clean spine lints empty; the linter catches exactly the
+mechanical defects a prompt is unreliable at — literal placeholders, AD-n id breakage,
+AD-n blocks missing required fields, and unpinned Stack versions.
+"""
+import importlib.util
+import json
+import re
+import sys
+from pathlib import Path
+
+import pytest
+
+_SPEC = importlib.util.spec_from_file_location(
+    "lint_spine", Path(__file__).resolve().parent.parent / "lint_spine.py"
+)
+lint_spine = importlib.util.module_from_spec(_SPEC)
+sys.modules["lint_spine"] = lint_spine
+_SPEC.loader.exec_module(lint_spine)
+
+
+CLEAN = """---
+name: 'Demo'
+---
+
+## Invariants & Rules
+
+### AD-1 — single write path
+
+- **Binds:** all
+- **Prevents:** divergent mutation
+- **Rule:** state changes only through the command bus
+
+### AD-2 — layered deps `[ADOPTED]`
+
+- **Binds:** all
+- **Prevents:** import cycles
+- **Rule:** ui -> app -> domain, never backward
+
+```mermaid
+flowchart LR
+  A --> B{decision}
+```
+
+## Stack
+
+| Name | Version |
+| --- | --- |
+| fastapi | 0.115 |
+| pydantic | 2.9 |
+"""
+
+
+def cats(result):
+    return sorted(f["category"] for f in result["findings"])
+
+
+def test_clean_spine_passes():
+    result = lint_spine.lint(CLEAN)
+    assert result["ok"] is True
+    assert result["total_findings"] == 0
+
+
+def test_mermaid_braces_not_flagged():
+    # the {decision} node lives in a fenced block and must not read as a template token
+    result = lint_spine.lint(CLEAN)
+    assert "placeholder" not in cats(result)
+
+
+def test_placeholder_markers_caught():
+    text = CLEAN.replace("the command bus", "TBD")
+    result = lint_spine.lint(text)
+    assert "placeholder" in cats(result)
+
+
+def test_similar_to_caught():
+    text = CLEAN.replace("import cycles", "similar to AD-1")
+    result = lint_spine.lint(text)
+    assert any("cross-reference" in f["detail"] for f in result["findings"])
+
+
+def test_unfilled_template_token_caught():
+    text = CLEAN.replace("single write path", "{decision}")
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "placeholder" for f in result["findings"])
+
+
+def test_duplicate_ad_id_caught():
+    text = CLEAN.replace("### AD-2 — layered deps `[ADOPTED]`", "### AD-1 — layered deps")
+    result = lint_spine.lint(text)
+    assert "ad_id" in cats(result)
+
+
+def test_non_monotonic_ad_id_caught():
+    text = CLEAN.replace("### AD-2 — layered deps `[ADOPTED]`", "### AD-5 — layered deps").replace(
+        "### AD-1 — single write path", "### AD-9 — single write path"
+    )
+    result = lint_spine.lint(text)
+    assert any("non-monotonic" in f["detail"] for f in result["findings"])
+
+
+def test_missing_field_caught():
+    text = CLEAN.replace("- **Rule:** state changes only through the command bus\n", "")
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "ad_fields" and "rule" in f["detail"] for f in result["findings"])
+
+
+def test_unpinned_dep_caught():
+    text = CLEAN.replace("| fastapi | 0.115 |", "| fastapi |  |")
+    result = lint_spine.lint(text)
+    assert "version_pin" in cats(result)
+
+
+def test_placeholder_version_caught():
+    text = CLEAN.replace("| fastapi | 0.115 |", "| fastapi | {pin} |")
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "version_pin" and "fastapi" in f["detail"] for f in result["findings"])
+
+
+def test_no_stack_section_ok():
+    text = CLEAN.split("## Stack")[0]
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_stack_skeleton_row_not_version_pinned():
+    # a leftover {token} name is the placeholder pass's job, not a double-reported version_pin
+    text = CLEAN.replace("| fastapi | 0.115 |", "| {language / framework} | {pinned version} |")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_stack_html_comment_not_parsed_as_row():
+    text = CLEAN.replace("## Stack\n", "## Stack\n\n<!-- SEED — verified current 2026-06 -->\n")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_template_token_is_low_severity():
+    # a bare {token} can be legitimate brace prose; it is flagged, but low (not high) so the
+    # mechanical pass stays near-zero false-positive
+    text = CLEAN.replace("single write path", "{decision}")
+    result = lint_spine.lint(text)
+    toks = [f for f in result["findings"] if f["category"] == "placeholder" and "template token" in f["detail"]]
+    assert toks and all(f["severity"] == "low" for f in toks)
+
+
+def test_no_frontmatter_body_still_scanned():
+    text = "## Invariants\n\n### AD-1 — x\n\n- **Binds:** all\n- **Prevents:** drift\n- **Rule:** TBD\n"
+    result = lint_spine.lint(text)
+    assert "placeholder" in cats(result)  # TBD caught even with no frontmatter
+
+
+def test_frontmatter_value_with_dashes_not_truncated():
+    # a value containing '---' must not be read as the closing fence (line-exact close)
+    text = ("---\nname: 'x'\nscope: 'phase 1 --- phase 2'\n---\n\n"
+            "## Stack\n\n| Name | Version |\n| --- | --- |\n| fastapi |  |\n")
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "version_pin" for f in result["findings"])  # read past the inline ---
+
+
+def test_ad_heading_in_fence_not_counted():
+    text = (
+        "---\nname: 'x'\n---\n\n"
+        "### AD-1 — real\n\n- **Binds:** all\n- **Prevents:** drift\n- **Rule:** do x\n\n"
+        "## Docs\n\n```text\n### AD-2 — illustrative only, no fields\n```\n"
+    )
+    result = lint_spine.lint(text)
+    assert result["ok"] is True  # the fenced AD-2 is not a live AD → no ad_fields/ad_id finding
+
+
+def test_stack_table_flags_only_the_unpinned_row():
+    text = ("---\nname: 'x'\n---\n\n## Stack\n\n| Name | Version |\n| --- | --- |\n"
+            "| fastapi | 0.115 |\n| redis |  |\n")
+    result = lint_spine.lint(text)
+    pins = [f for f in result["findings"] if f["category"] == "version_pin"]
+    assert len(pins) == 1 and "redis" in pins[0]["detail"]
+
+
+def test_stack_table_all_pinned_ok():
+    text = ("---\nname: 'x'\n---\n\n## Stack\n\n| Name | Version |\n| --- | --- |\n"
+            "| fastapi | 0.115 |\n")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_fenced_stack_rows_not_parsed():
+    # an illustrative fenced table under ## Stack must not be read as live rows (fences are
+    # blanked first, like every other pass) — a blank-version row inside a fence is not a finding
+    text = ("---\nname: 'x'\n---\n\n## Stack\n\n| Name | Version |\n| --- | --- |\n"
+            "| fastapi | 0.115 |\n\n```text\n| example |  |\n```\n")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_fenced_stack_heading_not_live():
+    # a `## Stack` heading shown inside a code fence is not the live Stack section
+    text = ("---\nname: 'x'\n---\n\n## Docs\n\n```md\n## Stack\n\n| foo |  |\n```\n")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_renamed_stack_heading_still_scanned():
+    # the heading match is word-boundary, so a varied `## Stack` heading still counts
+    text = ("---\nname: 'x'\n---\n\n## Stack & Versions\n\n| Name | Version |\n| --- | --- |\n"
+            "| redis |  |\n")
+    result = lint_spine.lint(text)
+    pins = [f for f in result["findings"] if f["category"] == "version_pin"]
+    assert len(pins) == 1 and "redis" in pins[0]["detail"]
+
+
+def test_reordered_columns_pair_name_to_version():
+    # Version-then-Name header: the unpinned row must still be flagged by its real name
+    text = ("---\nname: 'x'\n---\n\n## Stack\n\n| Version | Name |\n| --- | --- |\n"
+            "| 0.115 | fastapi |\n|  | redis |\n")
+    result = lint_spine.lint(text)
+    pins = [f for f in result["findings"] if f["category"] == "version_pin"]
+    assert len(pins) == 1 and "redis" in pins[0]["detail"]
+
+
+def test_placeholder_line_number_is_absolute():
+    # a TBD after a multi-line fence reports its real file line (fence blanked, not collapsed)
+    text = (
+        "---\nname: 'x'\n---\n\n"
+        "## A\n\n"
+        "```text\nf1\nf2\nf3\n```\n\n"
+        "TBD here\n"
+    )
+    result = lint_spine.lint(text)
+    ph = next(f for f in result["findings"] if "TBD" in f["detail"])
+    n = int(re.search(r"line (\d+)", ph["location"]).group(1))
+    assert n == 13
+
+
+def test_missing_spine_file_reports_error(tmp_path, capsys):
+    rc = lint_spine.main(["--workspace", str(tmp_path)])
+    out = json.loads(capsys.readouterr().out)
+    assert rc == 0 and out["ok"] is False and "not found" in out["error"]
+
+
+def test_frontmatter_unfilled_token_caught():
+    # an unfilled {scope}/{paradigm}/{date} in frontmatter is part of the contract and must lint
+    text = "---\nname: 'x'\nscope: '{what this spine governs}'\n---\n\n## Invariants\n"
+    result = lint_spine.lint(text)
+    fm = [f for f in result["findings"] if f["category"] == "placeholder" and "frontmatter" in f["detail"]]
+    assert fm and any("template token" in f["detail"] for f in fm)
+
+
+def test_frontmatter_tbd_caught():
+    text = "---\nname: 'x'\nstatus: TBD\n---\n\n## Invariants\n"
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "placeholder" and "frontmatter" in f["detail"] and "TBD" in f["detail"]
+               for f in result["findings"])
+
+
+def test_unreadable_spine_returns_error_not_crash(tmp_path, capsys):
+    # a spine that exists but can't be UTF-8 decoded must yield error JSON + exit 0, not a traceback
+    (tmp_path / lint_spine.SPINE).write_bytes(b"\xff\xfe bad bytes not utf-8")
+    rc = lint_spine.main(["--workspace", str(tmp_path)])
+    out = json.loads(capsys.readouterr().out)
+    assert rc == 0 and out["ok"] is False and "could not read" in out["error"]
+
+
+if __name__ == "__main__":
+    sys.exit(pytest.main([__file__, "-q"]))