@opengsd/gsd-path 1.5.0 → 1.6.0

package/skills/gsd-path-discuss/scripts/_common.py

@@ -25,7 +25,8 @@ import signal
 import subprocess
 import time
 from pathlib import Path
-from typing import BinaryIO, Iterator, List, Optional, Sequence
+from typing import BinaryIO, Iterable, Iterator, List, Optional, Sequence, Tuple
+
 
 # Chosen by what imports, not os.name, so tests can emulate Windows on POSIX.
 try:
@@ -161,6 +162,33 @@ def project_ignore_error(repo: Path) -> Optional[str]:
             + ". Anchor the product rule (for example `/build/`) in a task that owns it.")
 
 
+_DEFAULT_BRANCH_RE = re.compile(
+    r"[^\s#\"'\\~^:?*\[\x00-\x1f\x7f-][^\s#\"'\\~^:?*\[\x00-\x1f\x7f]*"
+)
+_RESERVED_BRANCH_PREFIXES = ("gsd-path/", "gsd-path-integrate/", "gsd-path-task/")
+
+
+def valid_default_branch(name: str) -> bool:
+    """A git branch name that STATE frontmatter can hold and Path does not reserve."""
+    return (
+        bool(_DEFAULT_BRANCH_RE.fullmatch(name))
+        and name != "null"
+        and not name.startswith(_RESERVED_BRANCH_PREFIXES)
+        and not name.endswith(("/", ".", ".lock"))
+        and not any(part in name for part in ("..", "//", "/.", "@{"))
+    )
+
+
+def origin_default_branch(repo: Path) -> str:
+    """The origin default branch that initialization records; an unset origin/HEAD means main."""
+    result = run_git(repo, "symbolic-ref", "--quiet", "refs/remotes/origin/HEAD")
+    prefix = "refs/remotes/origin/"
+    remote_ref = result.stdout.strip()
+    if result.returncode != 0 or not remote_ref.startswith(prefix):
+        return "main"
+    return remote_ref.removeprefix(prefix)
+
+
 def section_body(text: str, heading: str) -> Optional[str]:
     """The text under `## <heading>` up to the next `## `, or None when absent."""
     match = re.search(
@@ -169,6 +197,79 @@ def section_body(text: str, heading: str) -> Optional[str]:
     return match.group("body") if match else None
 
 
+def overlapping_paths(left: Sequence[str], right: Sequence[str]) -> List[str]:
+    """Return the sorted paths that two task `files` lists both cover.
+
+    An entry covers itself and the paths below it. For a declared directory
+    and a path below it, the result names the lower path. The callers have no
+    task base, so this does not ask if an entry is a file: the task-brief
+    lint rejects a path below a file at the base.
+    """
+    return sorted(
+        {
+            max(one, other, key=len)
+            for one in left
+            for other in right
+            if one == other or one.startswith(other + "/") or other.startswith(one + "/")
+        }
+    )
+
+
+# The `- ` of an indented sub-bullet line. A line that would then read as a
+# numbered item (`- 2. text`) keeps its marker, so both readings of a source
+# have the same criteria.
+SUB_BULLET_MARKER = re.compile(r"(?m)^([ \t]+)-[ \t]+(?![ \t]*\d+\.\s)")
+
+
+def without_sub_bullet_markers(source: str) -> str:
+    """`source` with the `- ` marker of each indented sub-bullet line removed."""
+    return SUB_BULLET_MARKER.sub(r"\1", source)
+
+
+class Criterion(str):
+    """A criterion as its parser joins it, with the `- ` markers of its sub-bullet lines.
+
+    `bare` is the same criterion parsed from `without_sub_bullet_markers(source)`.
+    The joined text cannot tell a marker from a minus sign; the source lines can.
+    """
+
+    bare: str
+
+    def __new__(cls, text: str, bare: str) -> "Criterion":
+        criterion = super().__new__(cls, text)
+        criterion.bare = bare
+        return criterion
+
+
+def quotes_criterion(quote: str, criterion: str) -> bool:
+    """Whether a review quote is `criterion`, for every reader.
+
+    Only whitespace is collapsed. The quote must equal the criterion with all
+    the markers of its sub-bullet lines or with none of them; every other
+    character, a hyphen inside a line too, is compared.
+    """
+    forms = (criterion, getattr(criterion, "bare", criterion))
+    return " ".join(quote.split()) in {" ".join(form.split()) for form in forms}
+
+
+def quoted_criterion(item: str, criteria: Sequence[str]) -> Optional[Tuple[int, int]]:
+    """Index of the criterion quoted at the start of `item`, and where the quote ends.
+
+    A criterion can contain ` — ` itself, so each separator and the end of
+    `item` is a candidate, the longest quote first. A criterion as written
+    wins over any criterion read without its sub-bullet markers.
+    """
+    ends = [match.start() for match in re.finditer("(?= —(?: |$))|$", item)][::-1]
+    for bare in (False, True):
+        for end in ends:
+            quote = " ".join(item[:end].split())
+            for index, criterion in enumerate(criteria):
+                form = getattr(criterion, "bare", criterion) if bare else criterion
+                if quote == " ".join(form.split()):
+                    return index, end
+    return None
+
+
 def task_verify_command(task_text: str) -> str:
     """The Verify shell text, excluding the closing fence's separator newline."""
     body = section_body(task_text, "Verify")
@@ -176,6 +277,11 @@ def task_verify_command(task_text: str) -> str:
     return block.group("block").removesuffix("\n") if block else ""
 
 
+def fix_verify(commands: Iterable[str]) -> str:
+    """The Verify of a fix task: each distinct source Verify in its own subshell, under `set -e`."""
+    return "set -e\n" + "\n".join(f"(\n{command}\n)" for command in dict.fromkeys(commands))
+
+
 def latest_verify_entry(entries: list, command: str, commit: str,
                         repo: Optional[str] = None) -> Optional[dict]:
     """Rows are keyed by (command, repo, commit); a row without `repo` is a coordinator row."""

package/skills/gsd-path-discuss/scripts/discussion_records.py

@@ -7,6 +7,7 @@ import json
 import os
 import shutil
 import sys
+import traceback
 
 # Runtime helpers must not modify their immutable installation.
 sys.dont_write_bytecode = True
@@ -33,7 +34,7 @@ def _load_pipeline_modules():
     try:
         from scripts import archive_milestone, pipeline_state, _common
         return _common, archive_milestone, pipeline_state
-    except ModuleNotFoundError as error:
+    except ImportError as error:  # a foreign `scripts` package
         if error.name not in {
             "scripts",
             "scripts.archive_milestone",
@@ -41,6 +42,13 @@ def _load_pipeline_modules():
             "scripts._common",
         }:
             raise
+        # A plain ImportError raised while a `scripts` module loaded is not a
+        # foreign package. A missing module falls back, as before.
+        if not isinstance(error, ModuleNotFoundError) and any(
+            frame.f_globals.get("__name__", "").startswith("scripts.")
+            for frame, _ in traceback.walk_tb(error.__traceback__)
+        ):
+            raise
         shared_scripts = Path(__file__).resolve().parents[2] / "gsd-path" / "scripts"
         sys.path.insert(0, str(shared_scripts))
         import archive_milestone

package/skills/gsd-path-discuss/scripts/model_policy.py

@@ -202,7 +202,11 @@ def native_record(args):
         identity = {'repo': str(args.repo.resolve()), 'project_dir': args.project_dir,
                     'scope': args.scope, 'assignment': args.assignment, 'role': args.role}
         if data is not None and data.get('identity') != identity:
-            raise PolicyError('record belongs to another assignment or milestone/track/cycle')
+            recorded = data.get('identity')
+            recorded = recorded if isinstance(recorded, dict) else {}
+            differing = ', '.join(f'{field}: {value}, record has {recorded.get(field)}'
+                                  for field, value in identity.items() if recorded.get(field) != value)
+            raise PolicyError(f'record belongs to another assignment or milestone/track/cycle ({differing})')
         if args.action == 'release':
             if data is None or not args.terminal_result:
                 raise PolicyError('release requires an existing record and terminal-result evidence')

package/skills/gsd-path-docs-audit/references/operating-rules.md

@@ -38,8 +38,8 @@ bundles this file; spawned agents follow their role brief instead.
   the lookahead planning track for the next milestone; it follows the same
   marker rule, owns no task frontmatter, and never binds a branch.
 - STATE.integration_default is the project closeout choice and
-  STATE.integration is the current milestone choice. Both are `direct` or
-  `pull-request`; STATE.integration_source is `default` or `milestone` and
+  STATE.integration is the current milestone choice. Both are `direct`,
+  `pull-request`, or `external-landing`; STATE.integration_source is `default` or `milestone` and
   preserves explicit override provenance. Older v2 state defaults to `direct`,
   and modes may be changed only through `pipeline_state.py
   configure-integration` before build. A next milestone resets its current
@@ -82,7 +82,9 @@ bundles this file; spawned agents follow their role brief instead.
   `isolation.py attest` may stand in for it: one `.project/`-only commit that
   names the base, the attested HEAD, the declared files that changed, the
   task Verify recorded as passing at that HEAD, and the ruling verbatim.
-  `recover` reports it as `attested`, never as a proven landing.
+  `recover` reports it as `attested`, never as a proven landing. Attestation
+  matches the declared files literally: work that is only below a declared
+  directory can land but cannot be attested.
 - All pipeline work for a milestone lives on `gsd-path/M00N` (M001, M002,
   …) bound in STATE.branch. The next milestone binds a new unused
   `gsd-path/M00N` at the remote default after the previous ship integrates.
@@ -90,6 +92,12 @@ bundles this file; spawned agents follow their role brief instead.
   branch — either Path's direct merge or a Path-owned PR merged by the user.
   The bound branch never receives merges or back-merges and is never the
   GitHub default.
+- The default branch is the one that STATE `default_branch` records at
+  initialization; a STATE file without the field means `main`. `main` and
+  `origin/main` in these rules mean that branch. Never change the record and
+  never take the name from a later `origin/HEAD` lookup. For a member
+  repository, the branch is the one that its `.project/MEMBERS.md` section
+  records as `Default branch`; a section without the field means `main`.
 - After initialization writes STATE.md, and before entering the first pipeline
   phase in an existing Git repository, the router calls
   `scripts/pipeline_git.py bind-initial` with the selected M00N and exact

package/skills/gsd-path-docs-audit/references/runtime-selection.md

@@ -20,6 +20,15 @@ references to bundled copies of those helpers. Other skill helpers, templates,
 and role briefs remain in the installed skill bundle. Pass `-B` to Python helper
 invocations so execution does not create bytecode in the runtime store.
 
+The selected runtime is authoritative for each helper in its `manifest.json`;
+this includes `review_findings.py` and `task_context.py`. A selected runtime
+that was published before a helper became a runtime file does not list that
+helper: run the bundled copy until the project runtime is upgraded.
+`dispatch_driver.py` and `workflow_run.py` always run from the installed skill
+bundle, because they read role briefs and templates from it; a skill update
+replaces them, a runtime upgrade does not. The driver reloads the helper modules
+that it imports from the selected runtime.
+
 With no declaration, retain the legacy helper lookup. An existing
 `.gsd-path/runtime/` requires the explicit `--runtime-migrate --project PATH`
 operation before adopting external storage; review the resulting Git diff.

package/skills/gsd-path-docs-audit/scripts/_common.py

@@ -25,7 +25,8 @@ import signal
 import subprocess
 import time
 from pathlib import Path
-from typing import BinaryIO, Iterator, List, Optional, Sequence
+from typing import BinaryIO, Iterable, Iterator, List, Optional, Sequence, Tuple
+
 
 # Chosen by what imports, not os.name, so tests can emulate Windows on POSIX.
 try:
@@ -161,6 +162,33 @@ def project_ignore_error(repo: Path) -> Optional[str]:
             + ". Anchor the product rule (for example `/build/`) in a task that owns it.")
 
 
+_DEFAULT_BRANCH_RE = re.compile(
+    r"[^\s#\"'\\~^:?*\[\x00-\x1f\x7f-][^\s#\"'\\~^:?*\[\x00-\x1f\x7f]*"
+)
+_RESERVED_BRANCH_PREFIXES = ("gsd-path/", "gsd-path-integrate/", "gsd-path-task/")
+
+
+def valid_default_branch(name: str) -> bool:
+    """A git branch name that STATE frontmatter can hold and Path does not reserve."""
+    return (
+        bool(_DEFAULT_BRANCH_RE.fullmatch(name))
+        and name != "null"
+        and not name.startswith(_RESERVED_BRANCH_PREFIXES)
+        and not name.endswith(("/", ".", ".lock"))
+        and not any(part in name for part in ("..", "//", "/.", "@{"))
+    )
+
+
+def origin_default_branch(repo: Path) -> str:
+    """The origin default branch that initialization records; an unset origin/HEAD means main."""
+    result = run_git(repo, "symbolic-ref", "--quiet", "refs/remotes/origin/HEAD")
+    prefix = "refs/remotes/origin/"
+    remote_ref = result.stdout.strip()
+    if result.returncode != 0 or not remote_ref.startswith(prefix):
+        return "main"
+    return remote_ref.removeprefix(prefix)
+
+
 def section_body(text: str, heading: str) -> Optional[str]:
     """The text under `## <heading>` up to the next `## `, or None when absent."""
     match = re.search(
@@ -169,6 +197,79 @@ def section_body(text: str, heading: str) -> Optional[str]:
     return match.group("body") if match else None
 
 
+def overlapping_paths(left: Sequence[str], right: Sequence[str]) -> List[str]:
+    """Return the sorted paths that two task `files` lists both cover.
+
+    An entry covers itself and the paths below it. For a declared directory
+    and a path below it, the result names the lower path. The callers have no
+    task base, so this does not ask if an entry is a file: the task-brief
+    lint rejects a path below a file at the base.
+    """
+    return sorted(
+        {
+            max(one, other, key=len)
+            for one in left
+            for other in right
+            if one == other or one.startswith(other + "/") or other.startswith(one + "/")
+        }
+    )
+
+
+# The `- ` of an indented sub-bullet line. A line that would then read as a
+# numbered item (`- 2. text`) keeps its marker, so both readings of a source
+# have the same criteria.
+SUB_BULLET_MARKER = re.compile(r"(?m)^([ \t]+)-[ \t]+(?![ \t]*\d+\.\s)")
+
+
+def without_sub_bullet_markers(source: str) -> str:
+    """`source` with the `- ` marker of each indented sub-bullet line removed."""
+    return SUB_BULLET_MARKER.sub(r"\1", source)
+
+
+class Criterion(str):
+    """A criterion as its parser joins it, with the `- ` markers of its sub-bullet lines.
+
+    `bare` is the same criterion parsed from `without_sub_bullet_markers(source)`.
+    The joined text cannot tell a marker from a minus sign; the source lines can.
+    """
+
+    bare: str
+
+    def __new__(cls, text: str, bare: str) -> "Criterion":
+        criterion = super().__new__(cls, text)
+        criterion.bare = bare
+        return criterion
+
+
+def quotes_criterion(quote: str, criterion: str) -> bool:
+    """Whether a review quote is `criterion`, for every reader.
+
+    Only whitespace is collapsed. The quote must equal the criterion with all
+    the markers of its sub-bullet lines or with none of them; every other
+    character, a hyphen inside a line too, is compared.
+    """
+    forms = (criterion, getattr(criterion, "bare", criterion))
+    return " ".join(quote.split()) in {" ".join(form.split()) for form in forms}
+
+
+def quoted_criterion(item: str, criteria: Sequence[str]) -> Optional[Tuple[int, int]]:
+    """Index of the criterion quoted at the start of `item`, and where the quote ends.
+
+    A criterion can contain ` — ` itself, so each separator and the end of
+    `item` is a candidate, the longest quote first. A criterion as written
+    wins over any criterion read without its sub-bullet markers.
+    """
+    ends = [match.start() for match in re.finditer("(?= —(?: |$))|$", item)][::-1]
+    for bare in (False, True):
+        for end in ends:
+            quote = " ".join(item[:end].split())
+            for index, criterion in enumerate(criteria):
+                form = getattr(criterion, "bare", criterion) if bare else criterion
+                if quote == " ".join(form.split()):
+                    return index, end
+    return None
+
+
 def task_verify_command(task_text: str) -> str:
     """The Verify shell text, excluding the closing fence's separator newline."""
     body = section_body(task_text, "Verify")
@@ -176,6 +277,11 @@ def task_verify_command(task_text: str) -> str:
     return block.group("block").removesuffix("\n") if block else ""
 
 
+def fix_verify(commands: Iterable[str]) -> str:
+    """The Verify of a fix task: each distinct source Verify in its own subshell, under `set -e`."""
+    return "set -e\n" + "\n".join(f"(\n{command}\n)" for command in dict.fromkeys(commands))
+
+
 def latest_verify_entry(entries: list, command: str, commit: str,
                         repo: Optional[str] = None) -> Optional[dict]:
     """Rows are keyed by (command, repo, commit); a row without `repo` is a coordinator row."""

package/skills/gsd-path-docs-audit/scripts/build_recovery.py

@@ -22,6 +22,10 @@ MARKER = "build recovery: "
 RECOVERY_KEYS = frozenset({"base", "branch", "kind", "source"})
 
 
+# Only the value of a cap line is exempt; a comment or a line separator after it stays in the compared text.
+CAP_VALUE = re.compile(r"(?m)^(-[ \t]*(?:max_review_cycles|wave_budget):)[ \t\w.,$/:]*")
+
+
 def runtime():
     if __package__:
         from scripts import pipeline_state
@@ -58,8 +62,17 @@ def _parse_recovery_record(value: object) -> dict:
     return {**value, "source": source}
 
 
-def _recovery_base_proves_milestone(before, current, source: str) -> bool:
-    if before.branch != current.branch or before.milestone != current.milestone:
+def _recovery_base_proves_milestone(before, current, source: str, active: bool = True) -> bool:
+    if before.branch != current.branch:
+        return False
+    if before.milestone != current.milestone and (
+        # Issue #374: a legacy base records milestone null when define never
+        # named it. The owner names it at ship, after the build resumed, so
+        # only a closed build recovery accepts an unset base milestone; the
+        # bound branch already encodes M00N. A milestone named by the base
+        # must still equal the current one.
+        active or source != "build" or before.milestone is not None
+    ):
         return False
     if source == "plan":
         return (before.phase, before.status) in {("plan", "active"), ("plan", "blocked")}
@@ -99,7 +112,9 @@ def context(repo: Path, text: str | None = None) -> dict | None:
         if base_text is None:
             raise state.PipelineStateError("build recovery base has no STATE.md")
         before = state._state_from_text(base_text)
-        if not _recovery_base_proves_milestone(before, current, recovery.get("source", "build")):
+        if not _recovery_base_proves_milestone(
+            before, current, recovery.get("source", "build"), recovery["active"]
+        ):
             raise state.PipelineStateError("build recovery base does not prove this blocked milestone")
     return recovery
 
@@ -289,61 +304,78 @@ def validate_plan(repo: Path) -> None:
         intent = checkpoint_runtime()._git_text_at(repo, recovery["base"], ".project/intent/INTENT.md")
         if state._read_real_file(repo / ".project/intent/INTENT.md", "INTENT.md") != intent:
             raise state.PipelineStateError("plan repair cannot change approved intent")
-    unchanged = unchanged_waves(repo, recovery)
-    for path in (repo / ".project/review").iterdir():
-        match = re.match(r"wave-([1-9]\d*)[.]", path.name)
-        if match and int(match[1]) not in unchanged:
-            raise state.PipelineStateError("changed wave must be reviewed after build resumes")
+    if stale_review_reasons(repo, recovery, _review_waves(repo / ".project/review")):
+        raise state.PipelineStateError("changed wave must be reviewed after build resumes")
 
 
-def unchanged_waves(repo: Path, recovery: dict) -> set[int]:
-    """Reuse evidence only when its intent, wave contract, and task bytes match."""
+def _review_waves(directory: Path) -> set[int]:
+    return {int(match[1]) for path in directory.iterdir()
+            if (match := re.match(r"wave-([1-9]\d*)[.]", path.name))}
+
+
+def stale_review_reasons(repo: Path, recovery: dict, waves: set[int]) -> dict[int, str]:
+    """Say why a wave's preserved review is stale; a wave not returned has matching intent, plan, and task bytes."""
     state = runtime()
     project = repo / ".project"
     old_intent = checkpoint_runtime()._git_text_at(repo, recovery["base"], ".project/intent/INTENT.md")
     if state._read_real_file(project / "intent/INTENT.md", "INTENT.md") != old_intent:
-        return set()
+        return dict.fromkeys(waves, "INTENT.md changed")
     old_plan = checkpoint_runtime()._git_text_at(repo, recovery["base"], ".project/plan/PLAN.md") or ""
     new_plan = state._read_real_file(project / "plan/PLAN.md", "PLAN.md")
+    panel_lines = r"(?m)^-[ \t]*review_panel:.*$"
+    if re.findall(panel_lines, old_plan) != re.findall(panel_lines, new_plan):
+        return dict.fromkeys(waves, "PLAN.md `review_panel` setting changed")
 
     def sections(text):
         return {match[1]: match[2] for match in re.finditer(
             r"(?ms)^## ([^\n]+)\n(.*?)(?=^## |\Z)", text,
         )}
 
+    def governing(plan):
+        # Non-wave settings govern every wave, including coverage and surfaces. Caps only bound
+        # later work and Dependency notes are prose, so neither changes what a passed review judged.
+        return {title: CAP_VALUE.sub(r"\1", body) if title == "Config" else body
+                for title, body in plan.items()
+                if not title.startswith("Wave ") and title != "Dependency notes"}
+
     old_sections, new_sections = sections(old_plan), sections(new_plan)
-    # Non-wave settings govern every wave, including coverage and surfaces.
-    if ({k: v for k, v in old_sections.items() if not k.startswith("Wave ")}
-            != {k: v for k, v in new_sections.items() if not k.startswith("Wave ")}):
-        return set()
+    old_governing, new_governing = governing(old_sections), governing(new_sections)
+    for title in sorted(old_governing.keys() | new_governing.keys()):
+        if old_governing.get(title) != new_governing.get(title):
+            return dict.fromkeys(waves, f"PLAN.md section `{title}` changed")
     old_tasks = checkpoint_runtime()._task_contracts_at(repo, recovery["base"], ".project/tasks")
     current = settled_tasks(repo)
-    unchanged = set()
-    for title, body in new_sections.items():
-        match = re.match(r"Wave ([1-9]\d*)\b", title)
-        if not match or old_sections.get(title) != body:
+    reasons = {}
+    for wave in waves:
+        section = {title: body for title, body in new_sections.items() if re.match(rf"Wave {wave}\b", title)}
+        if not section or any(old_sections.get(title) != body for title, body in section.items()):
+            reasons[wave] = f"PLAN.md section `Wave {wave}` changed"
             continue
-        wave = match[1]
         before = {Path(path).name: text for path, text in old_tasks.values()
-                  if task_fields(text, path).get("wave") == wave}
-        after = {name: text for name, (text, fields) in current.items() if fields.get("wave") == wave}
-        if before and before == after:
-            unchanged.add(int(wave))
-    return unchanged
+                  if task_fields(text, path).get("wave") == str(wave)}
+        after = {name: text for name, (text, fields) in current.items() if fields.get("wave") == str(wave)}
+        if not before or before != after:
+            reasons[wave] = f"wave {wave} task contracts changed"
+    return reasons
 
 
-def restore_unchanged_reviews(repo: Path) -> None:
+def restore_unchanged_reviews(repo: Path) -> dict | None:
+    """Restore reusable wave reviews and report every preserved wave, so a dropped review is visible at approval."""
     recovery = context(repo)
     if not recovery or not recovery["active"]:
-        return
-    unchanged = unchanged_waves(repo, recovery)
-    for path in review_backup(repo, recovery).iterdir():
+        return None
+    backup = review_backup(repo, recovery)
+    waves = _review_waves(backup)
+    reasons = stale_review_reasons(repo, recovery, waves)
+    for path in backup.iterdir():
         match = re.match(r"wave-([1-9]\d*)[.]", path.name)
-        if match and int(match[1]) in unchanged:
+        if match and int(match[1]) not in reasons:
             destination = repo / ".project/review" / path.name
             content = path.read_text(encoding="utf-8")
             if not destination.exists() or runtime()._read_real_file(destination, destination.name) != content:
                 runtime()._atomic_write(destination, content)
+    return {"restored": sorted(waves - reasons.keys()),
+            "review_again": [{"wave": wave, "reason": reasons[wave]} for wave in sorted(reasons)]}
 
 
 def inventory_checkpoint(repo: Path, head: str) -> bool: