riskrails 3.0.1 → 3.2.1

package/skills/rr-build-all/SKILL.md

@@ -146,8 +146,8 @@ EOF
 - **pass** → §6.
 - **pass_with_findings** → the in-scope HIGHs, grouped by file, one fixer per group in
   parallel; `$STATE verify --scope all --after-fix "H1,H2: …"`; `$STATE review --closes "H1,H2"`
-  → §6. Each MEDIUM and LOW is one `$STATE memory risk add`, not a fix; only a BLOCKER, a HIGH
-  or a regression buys an `--after-fix` run.
+  → §6. MEDIUM and LOW: `memory risk add` as `/rr-review` §4 says, for every verdict; only a
+  BLOCKER, a HIGH or a regression buys an `--after-fix` run.
 - **blockers_open** → every in-scope BLOCKER and HIGH, grouped by file, one fixer per group in
   parallel; `$STATE verify --scope all --after-fix "B1,H1: …"` (red: §4's batch); then
   **§5 again, a full pass** — a fix batch across many files is a new change, not a scoped one.

package/skills/rr-plan/SKILL.md

@@ -24,7 +24,9 @@ first: a task already in flight is finished or abandoned before another starts.
 
 When `$ARGUMENTS` is a spec (default: the newest `docs/sdlc/specs/*.md`):
 
-1. `docs/sdlc/plans/TEMPLATE.md` exists, else `/rr-setup`. If the spec's
+1. `docs/sdlc/constitution.md` exists, else `/rr-setup`. The template is
+   `docs/sdlc/plans/TEMPLATE.md` when the project overrides it, else
+   `$AI_HOME/skills/project-init/templates/plan.md`. If the spec's
    **Flagged concerns** holds unresolved items, list them and have the human
    resolve or explicitly accept each one before planning.
 2. If `superpowers:writing-plans` is available, use it for the step

package/skills/rr-review/SKILL.md

@@ -60,7 +60,10 @@ guarded, about 80 in full, then FINDINGS and VERDICT.
 
 Before you delegate, probe the change yourself for a minute: the few inputs its
 own threat model makes interesting, through the real code, and hand the
-reviewer what you saw — it starts where you stopped.
+reviewer what you saw — it starts where you stopped. When the change touches a
+guard regex's running time, run the timed probe yourself (`/usr/bin/grep -E`,
+or Python `timeit` on inputs of at most 4096 chars) and hand over the
+measurement: the bounded reviewer may not run timing loops.
 
 ## 3. Record the verdict
 
@@ -81,16 +84,18 @@ task's record (`task.md`), so there is no separate report to write.
 
 ## 4. After the verdict
 
-- **pass:** `/rr-ship`; the record and the close are one call,
-  `$STATE review --verdict pass … <<'EOF' && $STATE close`. `review` exits 0 for every
-  verdict, so the chain is for `pass` only.
+Continue from the verdict §3 recorded; do not record it again. Whatever the
+verdict, each MEDIUM and LOW is one `$STATE memory risk add`
+(`.ai/project/known-risks.md` amended into the task if missing), not a fix.
+
+- **pass:** `/rr-ship`, i.e. `$STATE close` directly: the verdict is already
+  recorded. (To record and close in one call, §3's `review --verdict pass … <<'EOF' && $STATE close`;
+  `review` exits 0 for every verdict, so that chain is for `pass` only.)
 - **pass_with_findings:** fix every in-scope HIGH in one batch, then
   `$STATE verify --scope all --after-fix "H1,H2: <one line>"` and
   `$STATE review --closes "H1,H2"`. The findings close on that green run, on a
-  tree the fix changed — no second review. Each MEDIUM and LOW is one
-  `$STATE memory risk add` (`.ai/project/known-risks.md` amended into the task
-  if missing), not a fix; only a BLOCKER, a HIGH or a regression buys an
-  `--after-fix` run.
+  tree the fix changed — no second review. MEDIUM and LOW: `memory risk add`
+  as above; only a BLOCKER, a HIGH or a regression buys an `--after-fix` run.
 - **blockers_open:** fix every BLOCKER and HIGH together, `verify --scope all
   --after-fix "…"`, then **one scoped re-review** (`/rr-review B1,H1`): brief a fresh `ai-reviewer`
   with the named findings and the fix's diff only — do they close, and what did

package/skills/rr-setup/SKILL.md

@@ -133,12 +133,25 @@ it cannot.
    each in one plain sentence and ask, unless `$ARGUMENTS` holds `--apply`.
 4. `$UPDATE --apply`. Exit 3 stopped on a changed, non-regular or unwritable
    file and names it; nothing after it was written — run the dry run again.
-   **A `delete?` is the human's.** Never pass `--confirm-delete`, not even with
+   **A `delete?` is the human's.** Never pass `--confirm-delete` or `--confirm-cleanup`, not even with
    `--apply`. Give them, with `$AI_HOME` and `$PWD` substituted, for their own
    terminal (the `!` prefix is refused):
    `python3 "<home>/skills/project-update/update.py" "<project>" --apply --confirm-delete "<your name>"`.
    The schema stays put until it is settled — that command, or deleting the
-   file by hand; there is no third way. For 0006 (shared files) the order is:
+   file by hand; there is no third way. Two kinds are housekeeping, not
+   migrations: `[sdlc]` — an unedited `docs/sdlc/*/TEMPLATE.md`, which the plugin
+   now supplies (an edited one stays as the project's override); `[cleanup]` —
+   the `*.log` files of closed tasks, and the report and log files of an
+   abandoned task (its `state.json` stays) or of one unclosed for more than seven
+   days (never the task in flight; and none when `.ai/state/state.json` is unreadable).
+   `--confirm-delete` does not settle `[cleanup]` rows, and the rows differ by kind:
+   files under `.ai/state/logs/` are git-ignored and git cannot restore them; files
+   under `.ai/reports/` are usually tracked, and the row says "tracked: git can restore
+   a committed copy" or, when git holds no committed copy, "uncommitted" — then
+   commit `.ai/` first (the hint says so), and an `original/` copy is kept as for any
+   other deletion. They have their own command, the human's too, never passed by the agent:
+   `python3 "<home>/skills/project-update/update.py" "<project>" --apply --confirm-cleanup "<your name>"`.
+   Show both groups as printed. For 0006 (shared files) the order is:
    `install.sh` for every runtime used, commit `.ai/`, read the `delete?` list,
    then the command with no task in flight. Rollback is git:
    `git restore --source=<commit before> --staged --worktree -- .ai`, before
@@ -157,7 +170,12 @@ it cannot.
    `that rule is not rendered`: name the `.ai/rules/` file and what it lacks
    (`paths:` and a body). `overrides the plugin's shared copy`: offer to diff
    each and delete those that add nothing. `foreign structure detected`: offer
-   **--adopt**.
+   **--adopt**. `tracked by git but ignored`: show the line as printed and give
+   the human the command it prints, exactly as printed, plus a commit, for their
+   own terminal (never rebuilt from the path; only the xargs form untracks every
+   such file under `.ai/state`, a printed `rm --cached -- <path>` one file; a
+   second machine runs the same before its next pull, else a modify/delete
+   conflict); never run it yourself.
 7. `$UPDATE --check` and `git diff --stat`; say what changed, what you merged
    and what is the human's. Suggest `git add -A .ai docs/sdlc .gitignore` plus
    the runtime directories and instruction files.
@@ -177,7 +195,9 @@ overwrite. A foreign tool's structure, below, can be present as well.
 
 Every command is `$UPDATE --adopt …`, with `--mode coexist` on each when the team
 still uses the other tool (router rows only, nothing moves). Exit 5
-`ADOPT_REFUSED`: show the first line and stop. Exit 4 `ADOPT_INCOMPLETE`:
+`ADOPT_REFUSED`: show the first line and stop. Exit 2: the routing table or a
+migration could not be read (reason on stderr, prefixed `project-update:`),
+nothing written. Exit 4 `ADOPT_INCOMPLETE`:
 `unmapped` files and a `split?` are yours to settle, then dry-run again; a
 `conflict` or a check `FAIL` left after that is the human's — never edit a
 destination or a source to make it pass.

package/skills/rr-setup/setup.py

@@ -182,7 +182,11 @@ def comment_purpose(lines):
 
 
 def purpose_of(root, rel):
-    text = read_text(os.path.join(root, rel))
+    full = os.path.join(root, rel)
+    real, base = os.path.realpath(full), os.path.realpath(root)
+    if os.path.commonpath([real, base]) != base:
+        return None  # a link out of the project: listed UNKNOWN, never read into toolbox.md
+    text = read_text(full)
     if text is None:
         return None
     lines = text.splitlines()
@@ -225,6 +229,8 @@ def inventory(root, table):
         for rel in paths:
             if rel in seen or not pattern.match(rel):
                 continue
+            if "/hooks/" in rel and os.path.basename(rel).startswith("."):
+                continue
             seen.add(rel)
             if row["kind"] == "make":
                 for n, target, purpose in make_targets(root, rel):

package/skills/rr-spec/SKILL.md

@@ -19,7 +19,9 @@ STATE="python3 $AI_HOME/skills/ai-task/state.py"
 
 ## 1. Prerequisites
 
-`docs/sdlc/specs/TEMPLATE.md` exists, else run `/rr-setup` first. Derive
+`docs/sdlc/constitution.md` exists, else run `/rr-setup` first. The template is
+`docs/sdlc/specs/TEMPLATE.md` when the project overrides it, else
+`$AI_HOME/skills/project-init/templates/spec.md`. Derive
 `<slug>` from the topic (kebab-case, at most five words). If
 `docs/sdlc/specs/<slug>.md` exists, offer to refine it instead of starting over.
 When `$ARGUMENTS` is a path to an intent file, read it fully — it is small by
@@ -75,7 +77,7 @@ decision — moves this to the top tier.
 
 ## 5. Write
 
-Copy `docs/sdlc/specs/TEMPLATE.md` to `docs/sdlc/specs/<slug>.md`, replace
+Copy the template (§1) to `docs/sdlc/specs/<slug>.md`, creating the folder, replace
 `{{TITLE}}` and `{{SLUG}}`. Replace the template's `Intent:` line with:
 
 ```markdown

package/skills/rr-status/status.py

@@ -5,7 +5,7 @@
 
 Read-only and model-free. A schema-7 task is described by `state.py status`;
 for any other task, and whenever that call fails, it reads the files directly —
-.ai/state/state.json (or the legacy current.json), the task's events.jsonl, .ai/policies/risk-tiers.json
+.ai/state/state.json (or the legacy current.json), the task's events.jsonl, .ai/policies/weight.json (else the shipped table)
 and .ai/VERSION — so it answers in a project whose state.py is older, newer or
 broken. The root is found the way the guards find it (find_ai_root in
 hooks/lib/ai-hook-common.sh): the nearest ancestor holding .ai/, not stopping at
@@ -81,7 +81,7 @@ def schema_line(root):
     numbers = [int(name[:4]) for name in names if re.match(r"\d{4}_", name)]
     plugin = str(max(numbers)) if numbers else "?"
     behind = project.isdigit() and plugin.isdigit() and int(project) < int(plugin)
-    return "schema: project %s · plugin %s%s" % (project, plugin, " — behind: run /project-update" if behind else "")
+    return "schema: project %s · plugin %s%s" % (project, plugin, " — behind: run /rr-setup --update" if behind else "")
 
 
 def one_line(value, limit=160):
@@ -97,13 +97,40 @@ def short(items, limit=4):
     return ", ".join(items[:limit]) + more if items else "none"
 
 
+def budgets(root, state):
+    """(max_suite_runs, review_rounds_max) as state.py's budget() enforces them:
+    weight.json's batch section while the batch loop is on, else tests.max_suite_runs
+    and review_rounds_max. A project without weight.json runs the shipped table."""
+    policy = read_json(os.path.join(root, ".ai", "policies", "weight.json")) \
+        or read_json(os.path.join(SKILLS, "ai-init", "templates", ".ai", "policies", "weight.json"))
+
+    def whole(value, default):
+        return value if isinstance(value, int) and not isinstance(value, bool) and value >= 1 else default
+
+    if (state.get("batch") or {}).get("on"):
+        section = policy.get("batch") if isinstance(policy.get("batch"), dict) else {}
+        return whole(section.get("max_suite_runs"), 8), whole(section.get("review_rounds_max"), 3)
+    tests = policy.get("tests") if isinstance(policy.get("tests"), dict) else {}
+    return tests.get("max_suite_runs", 2), policy.get("review_rounds_max", 2)
+
+
+def counter(state, section, key, legacy):
+    """A schema-7 counter (verify.suite_runs, review.passes), else the legacy one
+    (tests.suite_runs, reviews); 0 when neither is a number."""
+    new = state.get(section)
+    if isinstance(new, dict) and isinstance(new.get(key), int):
+        return new[key]
+    old = state.get(legacy)
+    old = old.get(key) if isinstance(old, dict) else old
+    return old if isinstance(old, int) else 0
+
+
 def report(root):
     lines = ["root: %s" % root]
     state = read_json(state_file(root))
     if not state.get("task_id"):
         return lines + ["task: none — no task in flight", schema_line(root)], None
-    policy = read_json(os.path.join(root, ".ai", "policies", "risk-tiers.json"))
-    tests_cfg = ((policy.get("sensors") or {}).get("tests") or {})
+    max_runs, max_rounds = budgets(root, state)
     plan = state.get("approved_plan") or {}
     steps = plan.get("steps") or []
     current = plan.get("current_step_id")
@@ -122,11 +149,11 @@ def report(root):
          else "step: none current (%d of %d done)" % (done, len(steps))),
         "verify: tests %s · suite runs %s/%s · e2e %s"
         % (state.get("test_status") or "?",
-           (state.get("tests") if isinstance(state.get("tests"), dict) else {}).get("suite_runs", 0),
-           tests_cfg.get("max_suite_runs", 5), state.get("e2e_status") or "?"),
+           counter(state, "verify", "suite_runs", "tests"),
+           max_runs, state.get("e2e_status") or "?"),
         "review: %s (%s of %s) · security %s"
-        % (state.get("review_status") or "?", state.get("reviews") or 0,
-           policy.get("review_rounds_max", 2), state.get("security_status") or "?"),
+        % (state.get("review_status") or "?", counter(state, "review", "passes", "reviews"),
+           max_rounds, state.get("security_status") or "?"),
         "approval: %s" % ("granted by %s" % approval.get("granted_by") if approval.get("granted")
                           else "requested, waiting for the human" if approval.get("requested_at")
                           else "not requested"),
@@ -146,7 +173,7 @@ def main(argv=None):
     args = parser.parse_args(argv)
     root = find_ai_root(args.root)
     if not root:
-        print("root: none — no .ai/ in %s or above it; /ai-init sets one up" % os.path.abspath(args.root))
+        print("root: none — no .ai/ in %s or above it; run /rr-setup first" % os.path.abspath(args.root))
         return 1
     lines, task_id = None, None
     state = read_json(state_file(root))

package/skills/usage-report/usage-report.py

@@ -690,7 +690,8 @@ def task_report(args) -> int:
         return 1
     start = min(stamps)
     closed = [parse_ts(e.get("ts")) for e in events if e.get("event") == "task_closed"]
-    end = max(c for c in closed if c) if any(closed) else dt.datetime.now(dt.timezone.utc)
+    unclosed = not any(closed)
+    end = max(stamps) if unclosed else max(c for c in closed if c)   # unclosed: the last event, not now
     tier, mode = "untiered", None
     involved = []
     for e in events:
@@ -729,7 +730,8 @@ def task_report(args) -> int:
 
     label = f"mode {mode} (tier {tier})" if mode else f"tier {tier}"
     print(f"task {args.task} {label} window {start.isoformat(timespec='seconds')}"
-          f"..{end.isoformat(timespec='seconds')}")
+          f"..{end.isoformat(timespec='seconds')}"
+          + (" (unclosed: window ends at the last event)" if unclosed else ""))
     print("  (by time window: any other session in this project inside it is counted too)")
     for rt in involved or sorted(used):
         inp, cache, out = used.get(rt, [0, 0, 0])