riskrails 4.1.0 → 4.3.0

package/skills/rr-build/SKILL.md

@@ -157,10 +157,13 @@ The batch is `[{"question": "…", "options": [{"key": "A", "text": "…"}, …]
 `"A: text"` becomes `{"key": "A", "text": "text"}`.
 
 Option keys are single letters, A first, at least two; `--recommend` marks the
-one you would pick. Then **stop** and show the questions: while one is pending,
+one you would pick. If `ask` printed `DIALOG_PENDING`, send that dialog. With no
+decision pending (a free question-tool call is denied while one is), put the
+question through the question tool and record the pick with
+`$STATE answer Q1=B --via picker`. Otherwise **stop** and show the questions: while one is pending,
 `step-done` and `close` exit 4. The human answers in the conversation — record
 it with `$STATE answer Q1=B Q2=X:"free text"` or `--prose "1B 2A"` — or fills the
-`[Answer]:` line in `.ai/reports/<task-id>/task.md` §Questions, which is then the
+`[Answer]:` line in `.ai/reports/<task-id>/task.md` §Questions; that file stays the
 record. Never edit that file, and never answer on the human's behalf.
 
 ## 6. Hand over by mode

package/skills/rr-setup/SKILL.md

@@ -164,7 +164,9 @@ formatting fix. Problems you find are written down, never fixed. Never read
    line as printed (the `enabledPlugins` line is the human's to add — never
    write it), and the suggested first task:
    `/rr-plan <it>`. Claim nothing was validated that was not run. Suggest
-   `git add .ai .gitignore docs/sdlc` plus the instruction files created.
+   `git add .ai .gitignore docs/sdlc` plus the instruction files created
+   (`.ai/memory/` and `.ai/reports/` are git-ignored; memory stays local unless the human runs
+   `memory enable --share git`).
 
 ## --options
 
@@ -243,7 +245,7 @@ riskrails is installed: until then the project's old shapes are not read.
    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
+   and what is the human's. Suggest `git add -A .ai docs/sdlc .gitignore` (the record and task logs are git-ignored) plus
    the runtime directories and instruction files.
 
 ## --audit

package/skills/rr-setup/setup.py

@@ -440,7 +440,7 @@ def write(path, text):
 
 def sibling(directory, name):
     """A module of this skill or of another, imported once its directory leads sys.path: `python3 -I` puts none
-    there, and the module's own imports are by name (memory_sync reaches memory_compact that way). Skills are
+    there, and the module's own imports are by name (memory_export reaches memory_compact that way). Skills are
     installed independently, so a missing module is an ImportError for the caller to answer."""
     if directory not in sys.path:
         sys.path.insert(0, directory)
@@ -477,7 +477,7 @@ def dialog_on(root):
 
 
 def author_source(cfg):
-    """Where `cfg.author` comes from, in the order memory_sync.MemoryConfig.author tries them."""
+    """Where `cfg.author` comes from, in the order memory_config.MemoryConfig.author tries them."""
     if cfg.local.get("author"):
         return "local config"
     return next(("$" + name for name in ("USER", "USERNAME") if os.environ.get(name)), "default")
@@ -494,22 +494,23 @@ def fts5():
 
 def memory_option(root, git):
     """Packages-mode project memory: set once memory.json exists, its mode being `current`. `author` is what
-    `memory enable` writes without --author (the local config, else $USER): memory_sync's own answer, never git's."""
+    `memory enable` writes without --author (the local config, else $USER): memory_config's own answer, never git's."""
     def unavailable(why):
         return {"key": "memory", "state": "unavailable", "why": why}
     if not git:
         return unavailable("not a git work tree")
     try:
-        sync = sibling(AI_TASK, "memory_sync")
+        memory_config = sibling(AI_TASK, "memory_config")
+        memory_io = sibling(AI_TASK, "memory_io")
     except ImportError as exc:
         return unavailable("the memory modules are not installed beside state.py (%s)" % exc)
     try:
-        cfg = sync.load_config(root)
-    except sync.MemoryError_ as exc:
+        cfg = memory_config.load_config(root)
+    except memory_io.MemoryError_ as exc:
         return unavailable(str(exc))
     return {"key": "memory", "state": "set" if cfg.present else "unset", "current": cfg.mode if cfg.present else None,
             "author": cfg.author, "author_from": author_source(cfg),
-            "period": None if cfg.present else sync.DEFAULTS["period"], "fts5": fts5()}
+            "period": None if cfg.present else memory_config.DEFAULTS["period"], "fts5": fts5()}
 
 
 def runtime_option(root):
@@ -602,17 +603,17 @@ def memory_decision(option, root, name):
     if option["state"] == "set":
         first = choice_option("Keep — %s mode" % option["current"], "keep")
         question = ("Project memory for %s is in %s mode: off keeps closed tasks only in .ai/reports/. packages also writes "
-                    "one compact committed file per developer per period under .ai/memory/, checked by a pre-push hook. "
-                    "%s. Keep it, or run memory enable?" % (name, option["current"], who))
+                    "one compact file per developer per period under .ai/memory/; both stay local (git-ignored) unless you "
+                    "run 'state.py memory enable --share git' in your own terminal. %s. Keep it, or run memory enable?" % (name, option["current"], who))
     else:
         first = choice_option("Off — keep files mode", "off")
         question = ("Project memory for %s: off keeps closed tasks only in .ai/reports/. packages also writes one compact "
-                    "committed file per developer per %s under .ai/memory/, checked by a pre-push hook. %s, period %s. "
-                    "Turn it on?" % (name, option["period"], who, option["period"]))
+                    "file per developer per %s under .ai/memory/; both stay local (git-ignored) unless you run "
+                    "'state.py memory enable --share git' in your own terminal. %s, period %s. Turn it on?" % (name, option["period"], who, option["period"]))
     return decision("memory", question, [
         first,
         command_option(state_label(root, "memory", "enable", *period),
-                       "packages; installs .git/hooks/pre-push unless one exists or core.hooksPath is set"),
+                       "packages; local, git-ignored record under .ai/memory/"),
         command_option(state_label(root, "memory", "enable", *period, "--index", "sqlite"),
                        "plus a local, git-ignored SQLite index; FTS5 %s — without it search scans: same results, slower"
                        % ("yes" if option["fts5"] else "no"))])

package/skills/rr-ship/SKILL.md

@@ -51,8 +51,8 @@ approve in your own terminal, then run close again:
   python3 /home/…/skills/ai-task/state.py --root /path/to/project approve --by "<name>"
 ```
 
-Show the human the summary (§3), the open findings, the rollback, and that
-command **verbatim** — paths absolute and quoted, because they paste it into
+Show the human the summary (§3), the review's `READ FIRST` lines, the open
+findings, the rollback, and that command **verbatim** — paths absolute and quoted, because they paste it into
 their own shell, where `$AI_HOME` is not set. Then **stop**.
 
 - **You approve only through the dialog.** With `.ai/policies/dialog.json`

package/skills/rr-spec/SKILL.md

@@ -39,6 +39,12 @@ $STATE ask --topic <slug> "<one line>" --option "A: <text>" --option "B: <text>"
 $STATE answer --topic <slug> Q1=B              # or --prose "1B", or Q1=X:"free text"
 ```
 
+If `ask` printed `DIALOG_PENDING`, send that dialog. With no decision pending (a
+free question-tool call is denied while one is), put the question through the
+question tool and relay the pick with `$STATE answer --topic <slug> Q1=B --via
+picker`; the questions file stays the record, and the human may still answer in
+the chat or fill `[Answer]:`.
+
 If `superpowers:brainstorming` is available, let it drive the conversation; the
 questions and answers still go through `ask` and `answer`. Otherwise:
 

package/skills/rr-status/SKILL.md

@@ -16,6 +16,8 @@ done
 python3 -I "$AI_HOME/skills/rr-status/status.py" --root "$PWD"
 ```
 
+With a task in flight or a decision open, the first line says who it waits on (`waiting on you` or `waiting on the agent`).
+
 After the output, at most one line, and only when a line asks for it:
 
 - `root:` is an ancestor of this repository, or `$HOME`: that `.ai/` arms the

package/skills/rr-status/status.py

@@ -174,9 +174,11 @@ def main(argv=None):
         return 1
     lines, task_id = None, None
     state = read_json(state_file(root))
-    if state.get("schema") == 7:
-        # A schema-7 task is state.py's to describe; this file's own read stays for
-        # an older task, and for an install whose state.py cannot answer.
+    decisions = read_json(os.path.join(root, ".ai", "state", "decision.json")).get("open")
+    if state.get("schema") == 7 or (not state.get("task_id") and decisions):
+        # A schema-7 task, or an open decision with no task, is state.py's to describe
+        # (its first line says who waits); this file's own read stays for an older
+        # task, and for an install whose state.py cannot answer.
         done = subprocess.run([sys.executable, "-I", os.path.join(SKILLS, "ai-task", "state.py"),
                                "--root", root, "status"], capture_output=True, text=True, check=False)
         if done.returncode == 0 and done.stdout.strip():