@opengsd/gsd-path 1.4.0 → 1.6.0

package/skills/gsd-path-migrate/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-migrate/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-migrate/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:
@@ -65,6 +66,49 @@ VERIFY_RESULTS = ("pass", "fail")
 VERIFY_LEDGER_SCHEMA = "gsd-path/verify-ledger/v2"
 VERIFY_BLOCK_PATTERN = re.compile(r"```bash[ \t]*\n(?P<block>.*?)```", re.DOTALL)
 
+REVIEW_BULLET_HEADING_PATTERN = re.compile(r"^#{2,3} ")
+REVIEW_BULLET_FIELD_LABEL_PATTERN = re.compile(r"^- \*\*[^*]+\*\*:")
+
+
+def review_bullet_field_label_pattern(field: str) -> re.Pattern[str]:
+    return re.compile(rf"^- \*\*{re.escape(field)}\*\*:[ \t]*(.*)$")
+
+
+def _review_bullet_field_value(lines: Sequence[str], index: int, inline: str) -> str:
+    if inline:
+        return inline
+    collected: list[str] = []
+    for line in lines[index + 1 :]:
+        if REVIEW_BULLET_FIELD_LABEL_PATTERN.match(line) or REVIEW_BULLET_HEADING_PATTERN.match(
+            line
+        ):
+            break
+        if line and not line[0].isspace():
+            break
+        stripped = line.strip()
+        if stripped:
+            collected.append(stripped)
+    return "\n".join(collected)
+
+
+def find_review_bullet_field_values(lines: Sequence[str], field: str) -> list[str]:
+    pattern = review_bullet_field_label_pattern(field)
+    values: list[str] = []
+    for index, line in enumerate(lines):
+        match = pattern.fullmatch(line)
+        if match is None:
+            continue
+        values.append(_review_bullet_field_value(lines, index, match.group(1)))
+    return values
+
+
+def parse_review_bullet_field(lines: Sequence[str], field: str) -> str:
+    """Parse one `- **Field**:` review bullet, including indented continuations."""
+    values = find_review_bullet_field_values(lines, field)
+    if len(values) != 1:
+        raise ValueError(field)
+    return values[0]
+
 
 # Sample paths the pipeline must commit. A product rule such as an unanchored
 # `build/` would otherwise drop them silently from every commit.
@@ -118,6 +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(
@@ -126,6 +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")
@@ -133,6 +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."""
@@ -150,6 +299,11 @@ def verify_ledger_entries(path: Path) -> list:
     return parse_verify_ledger(path.read_text(encoding="utf-8"))
 
 
+def read_user_text(path: Path) -> str:
+    """Read a user-edited text file with CRLF normalized to LF."""
+    return path.read_text(encoding="utf-8").replace("\r\n", "\n").replace("\r", "\n")
+
+
 def parse_verify_ledger(text: str) -> list:
     entries = []
     for number, line in enumerate(text.splitlines(), start=1):
@@ -204,7 +358,43 @@ def run_command(
 def run_git(
     repo: Path, *arguments: str, input: Optional[str] = None
 ) -> subprocess.CompletedProcess[str]:
-    return _run_exact(("git", "-C", str(repo), *arguments), input=input)
+    return _run_exact(git_command(repo, *arguments), input=input)
+
+
+def git_command(repo: Path, *arguments: str) -> tuple[str, ...]:
+    """Git argv for repo, including WSL drvfs workarounds when needed."""
+    return ("git", "-C", str(repo), *git_drvfs_config_flags(repo), *arguments)
+
+
+def git_drvfs_config_flags(repo: Path) -> tuple[str, ...]:
+    """Disable index preload on 9p/drvfs mounts where git commit races on index.lock (#207)."""
+    if os.name != "posix":
+        return ()
+    try:
+        root = repo.resolve()
+        mounts = Path("/proc/mounts").read_text(encoding="utf-8", errors="replace").splitlines()
+    except OSError:
+        return ()
+    best = ""
+    fstype = ""
+    for line in mounts:
+        parts = line.split()
+        if len(parts) < 3:
+            continue
+        mount_point, mount_type = parts[1], parts[2]
+        if mount_type not in {"9p", "drvfs"}:
+            continue
+        if root == Path(mount_point) or root.is_relative_to(mount_point):
+            if len(mount_point) >= len(best):
+                best, fstype = mount_point, mount_type
+    if not fstype:
+        return ()
+    return ("-c", "core.preloadindex=false", "-c", "index.threads=1")
+
+
+def git_index_lock_retryable(stderr: str) -> bool:
+    text = stderr.casefold()
+    return "index.lock" in text and "file exists" in text
 
 
 # OS files that are never pipeline artifacts when git ignores them.
@@ -227,6 +417,70 @@ def git_visible_entries(directory: Path) -> set:
     return {path.split("/", 1)[0] for path in result.stdout.split("\0") if path}
 
 
+RUNTIME_PIN_PATH = ".gsd-path/runtime.json"
+RUNTIME_PIN_ALLOWANCE = (
+    "only runtime-pin commits (.gsd-path/runtime.json) may follow the reviewed HEAD"
+)
+
+
+def reviewed_head_covers(repo: Path, reviewed: str, head: str) -> bool:
+    """True when a review of `reviewed` still covers `head`.
+
+    That is the same commit, or `reviewed` is an ancestor of `head` and every
+    commit on the first-parent path in ``reviewed..head`` is a non-merge commit
+    whose only change is ``.gsd-path/runtime.json``. An empty commit does not
+    qualify. Any other path, any merge commit, an unresolvable SHA, or a
+    non-ancestor returns False.
+    """
+    if not reviewed or not head:
+        return False
+    resolved_repo = Path(repo)
+    resolved: List[str] = []
+    for value in (reviewed, head):
+        result = run_git(
+            resolved_repo, "rev-parse", "--verify", "--quiet", f"{value}^{{commit}}"
+        )
+        if result.returncode != 0 or not result.stdout.strip():
+            return False
+        resolved.append(result.stdout.strip())
+    reviewed_sha, head_sha = resolved
+    if reviewed_sha == head_sha:
+        return True
+    if (
+        run_git(resolved_repo, "merge-base", "--is-ancestor", reviewed_sha, head_sha).returncode
+        != 0
+    ):
+        return False
+    listing = run_git(
+        resolved_repo,
+        "rev-list",
+        "--first-parent",
+        "--parents",
+        f"{reviewed_sha}..{head_sha}",
+    )
+    if listing.returncode != 0:
+        return False
+    for line in listing.stdout.splitlines():
+        fields = line.split()
+        if len(fields) != 2:
+            return False
+        commit_sha, parent_sha = fields[0], fields[1]
+        changed = run_git(
+            resolved_repo,
+            "diff",
+            "--name-only",
+            "--no-renames",
+            "--no-ext-diff",
+            parent_sha,
+            commit_sha,
+        )
+        if changed.returncode != 0:
+            return False
+        if {path for path in changed.stdout.splitlines() if path} != {RUNTIME_PIN_PATH}:
+            return False
+    return True
+
+
 def atomic_replace(path: Path, temporary_path: Path, content: str) -> None:
     temporary_path.parent.mkdir(parents=True, exist_ok=True)
     descriptor = None

package/skills/gsd-path-migrate/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-migrate/scripts/loop_run.py

@@ -514,16 +514,28 @@ def run_shell(command: str, timeout: float) -> tuple[Optional[int], str]:
     """Run one spec command; a hung command counts as failed (exit None).
 
     POSIX runs /bin/sh as shell=True did; Windows runs Git for Windows bash, not
-    cmd.exe. A timeout kills the whole process group, so a grandchild cannot
-    keep the output pipes open.
+    cmd.exe. A timeout kills the whole process group when possible; if output
+    pipes stay open, drain them with a short grace timeout and then close them.
     """
     argv = _common.bash_argv(command) if os.name == "nt" else ["/bin/sh", "-c", command]
     process = _common.popen_group(argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    stdout = b""
+    stderr = b""
     try:
         stdout, stderr = process.communicate(timeout=timeout)
-    except subprocess.TimeoutExpired:
+    except subprocess.TimeoutExpired as expired:
         _common.kill_tree(process)
-        stdout, stderr = process.communicate()
+        try:
+            stdout, stderr = process.communicate(timeout=5)
+        except subprocess.TimeoutExpired as drained:
+            stdout = drained.stdout or expired.stdout or b""
+            stderr = drained.stderr or expired.stderr or b""
+            if process.stdout:
+                process.stdout.close()
+            if process.stderr:
+                process.stderr.close()
+            process.kill()
+            process.wait(timeout=5)
         output = stdout.decode("utf-8", errors="replace") + stderr.decode("utf-8", errors="replace")
         return None, f"{output}\ntimed out at the admitted wall-clock deadline"
     return process.returncode, (stdout + stderr).decode("utf-8", errors="replace")

package/skills/gsd-path-migrate/scripts/migrate_core.py

@@ -10,6 +10,8 @@ import shutil
 import stat
 import sys
 
+import _common
+
 
 def hook_inventory(settings):
     if settings.is_symlink() or not settings.is_file():

package/skills/gsd-path-migrate/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-migrate/scripts/path_config.py

@@ -13,7 +13,7 @@ sys.dont_write_bytecode = True
 ROLES = ('coder', 'reviewer', 'review_panel', 'skeptic', 'inspect_codebase',
          'inspect_docs', 'docs_audit', 'research', 'decide', 'roadmap', 'plan', 'plan_patch')
 HOSTS = ('codex', 'claude', 'grok', 'opencode', 'copilot', 'qwen', 'antigravity',
-         'cursor', 'zed', 'kiro', 'kimi')
+         'cursor', 'zed', 'kiro', 'kimi', 'muse')
 
 
 def sibling(name):
@@ -73,8 +73,8 @@ def validate_value(key, value):
     if not isinstance(value, str) or not value or value != value.strip():
         raise ValueError(f'{key} requires a nonempty string')
     if key == 'integration':
-        if value not in ('direct', 'pull-request'):
-            raise ValueError('integration must be direct or pull-request')
+        if value not in ('direct', 'pull-request', 'external-landing'):
+            raise ValueError('integration must be direct, pull-request, or external-landing')
     elif key == 'review_panel':
         if any(char.isspace() for char in value):
             raise ValueError('use off, detected, or comma-separated families without spaces')

package/skills/gsd-path-plan/SKILL.md

@@ -115,9 +115,13 @@ as stated in Lookahead mode.
      In patch mode, tasks already `done` keep their landed metadata; only
      the appended patch tasks must start clean.
    - Require every dependency id to exist, forbid later-wave dependencies,
-     detect cycles, and forbid file overlap between planned tasks in the same
-     wave. Same-wave dependency chains are allowed only when their files do
-     not overlap; the build executes them in dependency layers.
+     detect cycles, and forbid unordered file overlap between planned tasks
+     in the same wave. Same-wave tasks may share files only when one
+     transitively depends on the other through `deps`; the build executes
+     them in dependency layers.
+   - Require an optional `supersedes` field to be a list of different task
+     ids; each one names an existing task of an earlier wave, in the same
+     repo, that shares a declared file with the task.
    - Reject a declared dependency that carries neither data nor a prerequisite
      effect. A `deps` edge is valid only when the dependent consumes a symbol,
      signature, schema, endpoint, file format, or path named in that
@@ -157,6 +161,13 @@ as stated in Lookahead mode.
      command's output — not an internal unit test.
      Require the surface to land in the same wave as the capability behind
      it, never in a later polish wave.
+   - When INTENT.md has `## Edge coverage`, require a PLAN.md
+     `## Held-out checks` row for every `held-out` edge and for no other
+     edge. The named test is in that task's `files`, the task's Verify runs
+     it, and the task's Acceptance criteria state the edge id and its ruling
+     (see [spec-reach probes](references/spec-probes.md)). An edge or
+     prohibition ruled `criterion SCn` needs no extra row; it is covered as
+     SCn. Put each `judgment` prohibition in its owning task's Approach.
    - Prove every intent constraint and synthesis decision is covered, that no
      scope-out veto appears in a task, and that `Project verify` is a real,
      non-placeholder command in PLAN.md. Every Verify — task and project —

package/skills/gsd-path-plan/references/build-recovery.md

@@ -69,6 +69,19 @@ checks landed-task preservation and restored intent ownership, restores review
 evidence only for unchanged contracts, and creates the normal journaled plan
 checkpoint. A failed approval leaves recovery open.
 
+A wave keeps its review evidence when INTENT.md, its own `## Wave N` section,
+its task files, and every other non-wave PLAN.md section are byte-identical to
+the recovery base. Two edits are exempt: the value of the `max_review_cycles`
+and `wave_budget` lines in `## Config`, and all of `## Dependency notes`. In
+`## Config` only those two values may change; any other edit there, a comment
+edit included, drops the evidence of every wave, as does any other non-wave
+edit. A `- review_panel:` line that is added, removed, or changed anywhere in
+PLAN.md also drops the evidence of every wave. The approval result reports
+this in `recovery_reviews`: `restored` lists the waves that kept their evidence, and
+`review_again` lists each wave that lost it, with the reason. Review every
+`review_again` wave again after build resumes; completion refuses a wave
+without a passing review.
+
 Return through `plan/done → build/active` with event `build started`. The dispatch
 driver uses a separate record directory for this recovery base, while retaining
 the milestone budget ledger. Resume only from the new approved task inventory.

package/skills/gsd-path-plan/references/dispatch.md

@@ -44,6 +44,19 @@ use exactly one matching branch:
   create another worktree. Encode task dependencies explicitly; launch
   independent children concurrently up to the host's advertised
   concurrent-subagent capacity.
+- A `muse.subagent_spawn` tool (with `muse.subagent_wait`,
+  `muse.subagent_read_result`, and `muse.subagent_send_message` siblings) is
+  Muse Code. Omit `subagent_type` (general-purpose, full capability), pass the
+  logical task name as `task_name` and `role`, and the complete brief as
+  `objective`. Never set `worktree_isolation`. Keep the returned
+  `subagent_id`; send a correction to a still-live child with
+  `muse.subagent_send_message` mode `followup` and the complete new prompt,
+  otherwise start a fresh child. Collect with `muse.subagent_wait`
+  (`wait_for: task_terminal`) then `muse.subagent_read_result`; on
+  `root_capacity_exhausted`, wait for a child to finish and retry. Spawn has no
+  model or effort argument, so record no such capability. If only
+  `muse.workflow` is exposed (untrusted workspace), do not script or inline
+  the work; stop and report that the workspace must be trusted.
 
 For every branch:
 

package/skills/gsd-path-plan/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-plan/references/planner.md

@@ -38,8 +38,9 @@ the how.
    security-critical; `verify-only` suits polish and low-risk feature waves
    whose Verify commands meaningfully cover the criteria.
 
-Every dependency must be in an earlier wave or in the same wave with no file
-overlap. Produce an acyclic graph; same-wave chains execute in layers.
+Every dependency must be in an earlier wave or in the same wave. Same-wave
+tasks may share files only when one transitively depends on the other. Produce
+an acyclic graph; same-wave chains execute in layers.
 
 Declare a dependency only when something real crosses it: data — the dependent
 consumes a symbol, signature, schema, endpoint, file format, or path named in
@@ -72,8 +73,17 @@ plan order above, which still keeps plan-invalidating risk in wave 1.
   criterion may appear in only one surface block. Put the surface in the same
   wave as the capability behind it. A milestone with a surface is not done
   when only its internals run.
+- When INTENT.md carries `## Edge coverage` or `## Prohibitions` (read the
+  supplied [spec-reach probes](spec-probes.md)), treat every ruling as a hard
+  limit on its criterion. For each `held-out` edge, write one PLAN.md
+  `## Held-out checks` row: a test file in the owning task's `files`, a
+  Verify that runs it, and an Acceptance criterion that names the edge id
+  and states its ruling from Detail. Omit the section when no edge is
+  held-out. Put each `judgment` prohibition's Must not and Detail in the
+  owning task's Approach.
 - Make `files` exhaustive, including imports, routes, generated artifacts,
-  tests, and wiring. Require disjoint files for same-wave tasks.
+  tests, and wiring. Require disjoint files for same-wave tasks that are not
+  dependency-ordered. A declared directory overlaps every path below it.
 - Write an Interface contract in every task: `None` for independent tasks;
   for any tasks that exchange a symbol, signature, schema, endpoint, file
   format, or path, the exact shapes both sides code against — identical text
@@ -86,6 +96,18 @@ plan order above, which still keeps plan-invalidating risk in wave 1.
   this task's work is skipped. That command must name a path from `files`,
   and must not be PLAN.md's project Verify unless an SC this task owns names
   that command. Criteria and Verify are the contract; Approach is guidance.
+  A task that lists a file of an earlier-wave task must also pass that
+  task's Verify to land. When it changes that behavior on purpose, list the
+  tests that Verify runs in its `files`.
+- Add `supersedes: [<task id>]` only when INTENT.md requires this task to
+  remove or replace behavior of an earlier-wave task, and that task's Verify
+  cannot pass after the change. The named task must be in an earlier wave,
+  in the same repo, and share a file with this task. Its Verify is then
+  retired: it does not run at this landing or at a later landing. State the
+  replacement in this task's acceptance criteria. This task's Verify then
+  runs in its place for each later task that shares a file with the named
+  task, so it must check the replacement behavior for all files of that
+  task.
 - In a multi-repo milestone (`.project/MEMBERS.md` lists members), each task
   changes exactly one repo. Give a member task `repo: <member>`; its `files`
   and Verify are relative to that member's root, and its Verify runs there.
@@ -105,7 +127,7 @@ family list. Copy `Finding skeptics:` from INTENT.md into PLAN.md Config as
 invent `on`. Quick-lane plans always write both values as `off`.
 
 Before returning, check veto exclusion, decision coverage, Intent coverage,
-the Surface contract, dependencies, file overlap, task size, criteria, and
+the Surface contract, Held-out checks, dependencies, file overlap, task size, criteria, and
 Verify commands.
 
 Return a brief structured summary: wave count, task count, and the wave-1

package/skills/gsd-path-plan/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.