blitz-cli 0.9.0__tar.gz → 0.10.0__tar.gz

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/.gitignore

@@ -8,4 +8,4 @@ dist/
 
 # stray test artifacts from running the CLI in-repo
 /.claude/
-/.playbooks/
+/.blitz/

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: blitz-cli
-Version: 0.9.0
+Version: 0.10.0
 Summary: Developer CLI for Blitz locker-room: spec-driven playbooks, a codebase/huddle ontology graph with an MCP tool, and the composable watcher/trainer/graph containers.
 License: MIT
 License-File: LICENSE
@@ -31,18 +31,18 @@ The core CLI is stdlib plus `rich`. Two optional extras carry heavier deps only
 when you need them: `blitz-cli[locker-room]` (the MCP server) and
 `blitz-cli[train]` (the QLoRA trainer).
 
-Top-level commands: `playbooks`, `implement`, `locker-room`, `activity`.
+Top-level commands: `init`, `implement`, `locker-room`.
 
 ## Playbooks: spec-driven development commands
 
-`blitz playbooks init` installs a set of spec-driven-development slash-commands
+`blitz init` installs a set of spec-driven-development slash-commands
 into a repo, rendered for whichever agent you use (Claude Code, Cursor, GitHub
-Copilot, Gemini CLI, OpenCode), plus a shared `.playbooks/` working area.
+Copilot, Gemini CLI, OpenCode), plus a shared `.blitz/` working area.
 
 ```bash
-blitz playbooks init                 # auto-detect the agent(s) in this repo
-blitz playbooks init --agent claude  # or target one explicitly
-blitz playbooks init --all           # install for every supported agent
+blitz init                 # auto-detect the agent(s) in this repo
+blitz init --agent claude  # or target one explicitly
+blitz init --all           # install for every supported agent
 ```
 
 The commands are `specify`, `plan`, `tasks`, `implement`, `playbook`, `clarify`,
@@ -61,7 +61,7 @@ each phase's machine-runnable verification, retries with the failure fed back
 `- [x]` in the tasks.md. A task that keeps failing stops the run so the state
 stays inspectable. Per-attempt model replies, snapshots, and exact token
 accounting (`usage.json`, per task and total) land under
-`.playbooks/implement/runs/<timestamp>/`.
+`.blitz/implement/runs/<timestamp>/`.
 
 ```bash
 blitz implement                                   # auto-detect the open specs/*/tasks.md
@@ -120,17 +120,17 @@ the base model with `BASE_MODEL_HF` or `blitz locker-room init --base-model`.
 
 ## Activity: replay a coding-agent session
 
-`blitz activity` reads your coding agent's own local session transcripts
+`blitz locker-room activity` reads your coding agent's own local session transcripts
 (currently Claude Code's, at `~/.claude/projects`) for the current repo and
 replays each prompt alongside the actions taken to resolve it (tool calls,
 sub-agents) and the final response:
 
 ```bash
-blitz activity --list               # sessions for this repo, most recent first
-blitz activity                      # the most recent session's timeline
-blitz activity <session-id-prefix>  # a specific session
-blitz activity --full               # untruncated prompts/responses/tool I/O
-blitz activity --html report.html   # also write a self-contained HTML report
+blitz locker-room activity --list               # sessions for this repo, most recent first
+blitz locker-room activity                      # the most recent session's timeline
+blitz locker-room activity <session-id-prefix>  # a specific session
+blitz locker-room activity --full               # untruncated prompts/responses/tool I/O
+blitz locker-room activity --html report.html   # also write a self-contained HTML report
 ```
 
 The terminal view is compact by default; `--full` shows untruncated text. The

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/README.md

@@ -12,18 +12,18 @@ The core CLI is stdlib plus `rich`. Two optional extras carry heavier deps only
 when you need them: `blitz-cli[locker-room]` (the MCP server) and
 `blitz-cli[train]` (the QLoRA trainer).
 
-Top-level commands: `playbooks`, `implement`, `locker-room`, `activity`.
+Top-level commands: `init`, `implement`, `locker-room`.
 
 ## Playbooks: spec-driven development commands
 
-`blitz playbooks init` installs a set of spec-driven-development slash-commands
+`blitz init` installs a set of spec-driven-development slash-commands
 into a repo, rendered for whichever agent you use (Claude Code, Cursor, GitHub
-Copilot, Gemini CLI, OpenCode), plus a shared `.playbooks/` working area.
+Copilot, Gemini CLI, OpenCode), plus a shared `.blitz/` working area.
 
 ```bash
-blitz playbooks init                 # auto-detect the agent(s) in this repo
-blitz playbooks init --agent claude  # or target one explicitly
-blitz playbooks init --all           # install for every supported agent
+blitz init                 # auto-detect the agent(s) in this repo
+blitz init --agent claude  # or target one explicitly
+blitz init --all           # install for every supported agent
 ```
 
 The commands are `specify`, `plan`, `tasks`, `implement`, `playbook`, `clarify`,
@@ -42,7 +42,7 @@ each phase's machine-runnable verification, retries with the failure fed back
 `- [x]` in the tasks.md. A task that keeps failing stops the run so the state
 stays inspectable. Per-attempt model replies, snapshots, and exact token
 accounting (`usage.json`, per task and total) land under
-`.playbooks/implement/runs/<timestamp>/`.
+`.blitz/implement/runs/<timestamp>/`.
 
 ```bash
 blitz implement                                   # auto-detect the open specs/*/tasks.md
@@ -101,17 +101,17 @@ the base model with `BASE_MODEL_HF` or `blitz locker-room init --base-model`.
 
 ## Activity: replay a coding-agent session
 
-`blitz activity` reads your coding agent's own local session transcripts
+`blitz locker-room activity` reads your coding agent's own local session transcripts
 (currently Claude Code's, at `~/.claude/projects`) for the current repo and
 replays each prompt alongside the actions taken to resolve it (tool calls,
 sub-agents) and the final response:
 
 ```bash
-blitz activity --list               # sessions for this repo, most recent first
-blitz activity                      # the most recent session's timeline
-blitz activity <session-id-prefix>  # a specific session
-blitz activity --full               # untruncated prompts/responses/tool I/O
-blitz activity --html report.html   # also write a self-contained HTML report
+blitz locker-room activity --list               # sessions for this repo, most recent first
+blitz locker-room activity                      # the most recent session's timeline
+blitz locker-room activity <session-id-prefix>  # a specific session
+blitz locker-room activity --full               # untruncated prompts/responses/tool I/O
+blitz locker-room activity --html report.html   # also write a self-contained HTML report
 ```
 
 The terminal view is compact by default; `--full` shows untruncated text. The

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/blitz_cli/__init__.py

@@ -13,7 +13,7 @@ Commands:
 - ``blitz traces list`` / ``blitz traces show <trace_id>`` — inspect captured
   traces from the local SQLite store.
 
-- ``blitz activity [session] [--list] [--html report.html]`` — replay a
+- ``blitz locker-room activity [session] [--list] [--html report.html]`` — replay a
   Claude Code session for this repo: each prompt you sent, the actions taken
   to resolve it (tool calls, sub-agents), and the final response. Reads
   ``~/.claude/projects`` directly; unrelated to Blitz's own captured traces.
@@ -30,4 +30,4 @@ Commands:
 
 __all__ = ["__version__"]
 
-__version__ = "0.9.0"
+__version__ = "0.10.0"

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/blitz_cli/_activity.py

@@ -1,4 +1,4 @@
-"""`blitz activity` — replay a coding-agent session: what you asked, and how it
+"""`blitz locker-room activity` — replay a coding-agent session: what you asked, and how it
 was resolved.
 
 The currently-supported transcript format is Claude Code's, at
@@ -734,7 +734,7 @@ def render_html(session: Session, limit: int) -> str:
         '<html lang="en">',
         "<head>",
         '<meta charset="utf-8">',
-        f"<title>blitz activity — {html.escape(session.title)}</title>",
+        f"<title>blitz locker-room activity — {html.escape(session.title)}</title>",
         f"<style>{_HTML_STYLE}</style>",
         "</head>",
         "<body>",

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/blitz_cli/_implement.py

@@ -220,12 +220,12 @@ def spec_name(repo: Path, tasks_file: Path) -> str:
 
 
 def local_model_config(repo: Path) -> dict:
-    """The `local_model` block from the nearest `.playbooks/config.json`,
+    """The `local_model` block from the nearest `.blitz/config.json`,
     checking the repo first and then walking up to the workspace root. This is
     the same config the `tasks` playbook reads to decide which tasks get the
     [L] (local-model eligible) marker. Returns {} when unconfigured."""
     for d in [repo.resolve(), *repo.resolve().parents]:
-        cfg = d / ".playbooks" / "config.json"
+        cfg = d / ".blitz" / "config.json"
         if cfg.is_file():
             try:
                 block = json.loads(cfg.read_text()).get("local_model")
@@ -238,11 +238,11 @@ def local_model_config(repo: Path) -> dict:
 
 def usage_by_spec(repo: Path) -> dict:
     """Aggregate every implement run's usage.json under
-    .playbooks/implement/runs/, keyed by spec: total input/output tokens, model
+    .blitz/implement/runs/, keyed by spec: total input/output tokens, model
     calls, run count, and the models used. This is what the locker-room
     ontologizer attaches to Feature nodes so the UI can show per-spec cost."""
     totals: dict = {}
-    for f in sorted(repo.glob(".playbooks/implement/runs/*/usage.json")):
+    for f in sorted(repo.glob(".blitz/implement/runs/*/usage.json")):
         try:
             record = json.loads(f.read_text())
         except (OSError, ValueError):
@@ -289,7 +289,7 @@ def run(
     """Execute every unchecked task in tasks_file. Returns 0 on success, 1 when a
     task fails after all retries (the run stops there so state stays inspectable)."""
     call_model = call_model or (lambda messages: call_ollama(ollama_url, model, messages))
-    run_root = run_root or (repo / ".playbooks" / "implement" / "runs")
+    run_root = run_root or (repo / ".blitz" / "implement" / "runs")
     rundir = run_root / datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
     snapdir = rundir / "snapshots"
     snapdir.mkdir(parents=True, exist_ok=True)
@@ -333,7 +333,7 @@ def run(
     if local_only and not any(t["local"] for t in tasks):
         print_fn("warning: no [L] markers in this tasks.md — with --local-only "
                  "there is nothing to execute (regenerate tasks with a "
-                 "local_model configured in .playbooks/config.json).")
+                 "local_model configured in .blitz/config.json).")
     last_in_phase = {t["phase"]: t["id"] for t in tasks}
     started = start_at is None
 

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/blitz_cli/_ontology.py

@@ -338,8 +338,8 @@ class OntologyStore:
 
 
 def _read_active_feature(repo: Path) -> str | None:
-    """Basename of the repo's active feature dir, from .playbooks/feature.json."""
-    fj = repo / ".playbooks" / "feature.json"
+    """Basename of the repo's active feature dir, from .blitz/feature.json."""
+    fj = repo / ".blitz" / "feature.json"
     try:
         val = json.loads(fj.read_text(encoding="utf-8")).get("feature_directory", "")
     except (OSError, ValueError):
@@ -422,7 +422,7 @@ def _parse_huddle(text: str) -> dict:
 
 
 def _ingest_huddles(ws_root: Path, ws_id: str, store: OntologyStore, repo_ids: dict) -> None:
-    huddles_dir = ws_root / ".playbooks" / "huddles"
+    huddles_dir = ws_root / ".blitz" / "huddles"
     if not huddles_dir.is_dir():
         return
     for hd in sorted(huddles_dir.iterdir()):
@@ -491,19 +491,19 @@ def ontologize(workspace_root, db_path, ignore=None, code=True,
     ws_id = f"workspace:{ws_root}"
     store.add_node(ws_id, "Workspace", {"name": ws_root.name, "path": str(ws_root)})
     _ingest_doc_file(store, ws_id, "playbook",
-                     ws_root / ".playbooks" / "memory" / "playbook.md", max_file_bytes)
+                     ws_root / ".blitz" / "memory" / "playbook.md", max_file_bytes)
 
     repo_ids: dict[str, str] = {}  # name -> node id, for huddle cross-referencing
     ignore_paths = [Path(p) for p in (ignore or [])]
     for repo in _playbooks.find_git_repos(ws_root, ignore=ignore_paths):
-        if not (repo / ".playbooks").is_dir():
+        if not (repo / ".blitz").is_dir():
             continue  # only playbook-enabled repos are ontologized
         rid = f"repo:{repo.resolve()}"
         repo_ids[repo.name] = rid
         store.add_node(rid, "Repo", {"name": repo.name, "path": str(repo)})
         store.add_edge(ws_id, rid, "CONTAINS")
         _ingest_doc_file(store, rid, "playbook",
-                         repo / ".playbooks" / "memory" / "playbook.md", max_file_bytes)
+                         repo / ".blitz" / "memory" / "playbook.md", max_file_bytes)
 
         for agent in _playbooks.detect_agents(repo):
             aid = f"agent:{agent}"

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/blitz_cli/_playbooks.py

@@ -1,10 +1,10 @@
-"""`blitz playbooks init` — install spec-driven-development slash-commands into a repo.
+"""`blitz init` — install spec-driven-development slash-commands into a repo.
 
 The command bodies under ``blitz_cli/playbooks/commands`` are spec-driven-development
 slash-commands adapted from GitHub's spec-kit (https://github.com/github/spec-kit).
 At install time we render each agent-agnostic body into the conventional command
 file for whichever agentic coding tool the user runs (Claude Code, Cursor, GitHub Copilot, Gemini
-CLI, OpenCode), and drop a shared ``.playbooks/`` working area (scripts +
+CLI, OpenCode), and drop a shared ``.blitz/`` working area (scripts +
 templates) that those commands drive.
 """
 
@@ -41,11 +41,11 @@ AGENTS: dict[str, AgentSpec] = {
     "opencode": AgentSpec(".opencode/command", ".md", "md", "$ARGUMENTS", (".opencode",)),
 }
 
-WORKDIR = ".playbooks"
+WORKDIR = ".blitz"
 
 _COMMANDS_PKG = "blitz_cli.playbooks.commands"
 # Workspace-only commands (e.g. /huddle) install into a *folder of repos*, never
-# into an individual repo — they orchestrate across the repos' .playbooks/ dirs.
+# into an individual repo — they orchestrate across the repos' .blitz/ dirs.
 _WORKSPACE_PKG = "blitz_cli.playbooks.workspace"
 
 # spec-kit cross-references commands as ``__SPECKIT_COMMAND_<NAME>__``; we drop
@@ -136,7 +136,7 @@ def render(command: str, agent: str, package: str = _COMMANDS_PKG) -> str:
     return _wrap(spec.fmt, description, body)
 
 
-# --- scaffold (shared .playbooks working area) -------------------------------
+# --- scaffold (shared .blitz working area) -------------------------------
 
 
 def _walk(node, prefix: str = ""):
@@ -231,7 +231,7 @@ def workspace_command_names() -> list[str]:
 
 
 def install_workspace_scaffold(dest_dir: Path) -> Path | None:
-    """Seed the workspace-level ``.playbooks/memory/playbook.md`` from the
+    """Seed the workspace-level ``.blitz/memory/playbook.md`` from the
     default template. Unlike command installs this NEVER overwrites — the
     file holds user-authored operating knowledge, so even ``--force`` must
     not reset it. Returns the written path, or None when it already exists."""
@@ -254,8 +254,8 @@ def install_workspace_commands(
     """Install workspace-only commands (/huddle) into ``dest_dir``'s command dirs.
 
     ``dest_dir`` is a workspace root — a folder of repos, not a repo itself.
-    No ``.playbooks/`` scaffold is installed here; the huddle command creates
-    what it needs (``.playbooks/huddles/``) on first use.
+    No ``.blitz/`` scaffold is installed here; the huddle command creates
+    what it needs (``.blitz/huddles/``) on first use.
     """
     commands = workspace_command_names()
     results: list[InstallResult] = []
@@ -271,9 +271,9 @@ def install_workspace_commands(
 
 
 def install_scaffold(dest_dir: Path, force: bool) -> InstallResult:
-    """Copy the shared ``.playbooks/`` working area, rewriting stale paths.
+    """Copy the shared ``.blitz/`` working area, rewriting stale paths.
 
-    Files under ``.playbooks/memory/`` are seeded once and NEVER overwritten,
+    Files under ``.blitz/memory/`` are seeded once and NEVER overwritten,
     even with ``force`` — they hold user-authored knowledge (a repo's
     constitution/playbook), and ``--force`` is for refreshing rendered
     commands and scaffold templates, not resetting memory."""

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/blitz_cli/_redact.py

@@ -12,7 +12,7 @@ is exactly the class of thing this module exists to catch, and exactly why
 "best-effort" is not "guaranteed."
 
 That same real key also surfaced a concrete failure mode worth documenting:
-once displayed via `blitz activity --full`, rich's Tree rendering wrapped the
+once displayed via `blitz locker-room activity --full`, rich's Tree rendering wrapped the
 long token across terminal lines, inserting a real newline plus a
 box-drawing tree-branch prefix (e.g. "\\n│   │   ") *in the middle of the
 token*. If that wrapped output is later captured as another tool's output

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/blitz_cli/cli.py

@@ -81,7 +81,7 @@ def _cmd_implement(args: argparse.Namespace) -> int:
         return 2
 
     # Model resolution: --model flag > BLITZ_IMPLEMENT_MODEL env >
-    # .playbooks/config.json local_model.model (repo, then workspace) > default.
+    # .blitz/config.json local_model.model (repo, then workspace) > default.
     model = (
         args.model
         or os.environ.get("BLITZ_IMPLEMENT_MODEL")
@@ -152,7 +152,7 @@ def _cmd_activity(args: argparse.Namespace) -> int:
         if len(matches) > 1:
             _eprint(
                 f"error: {args.session!r} matches {len(matches)} sessions; use more "
-                "characters or `blitz activity --list`."
+                "characters or `blitz locker-room activity --list`."
             )
             return 2
         summary = matches[0]
@@ -196,16 +196,9 @@ def _playbooks_install_one(_playbooks, dest: Path, agents: list, force: bool) ->
         )
 
 
-def _cmd_playbooks(args: argparse.Namespace) -> int:
+def _cmd_init(args: argparse.Namespace) -> int:
     from blitz_cli import _playbooks
 
-    if getattr(args, "playbooks_cmd", None) != "init":
-        _eprint(
-            "usage: blitz playbooks init [--dir .] [--agent NAME]... [--all] "
-            "[--each | --root] [--force]"
-        )
-        return 2
-
     dest = Path(args.dir)
 
     # Decide per-repo vs. single install. Default to per-repo when --dir is a
@@ -252,7 +245,7 @@ def _cmd_playbooks(args: argparse.Namespace) -> int:
             _playbooks_install_one(_playbooks, repo, agents, args.force)
             workspace_agents.extend(a for a in agents if a not in workspace_agents)
         # A folder of repos also gets the workspace-only /huddle command, which
-        # orchestrates cross-repo work over each repo's .playbooks/ area, plus a
+        # orchestrates cross-repo work over each repo's .blitz/ area, plus a
         # seed workspace playbook (topology + cross-repo conventions; never
         # overwritten, even with --force). Only when dest isn't itself a repo —
         # huddle has no meaning inside one.
@@ -301,7 +294,7 @@ def build_parser() -> argparse.ArgumentParser:
         "implement",
         help="Execute a playbook-generated tasks.md with a local model served by "
         "Ollama: one task per call, driver-side verification, bounded retries, "
-        "snapshots under .playbooks/implement/runs/.",
+        "snapshots under .blitz/implement/runs/.",
     )
     impl.add_argument(
         "tasks", nargs="?", default=None,
@@ -315,7 +308,7 @@ def build_parser() -> argparse.ArgumentParser:
         "--model",
         default=None,
         help="Ollama model to drive. Default resolution: this flag, then "
-        "BLITZ_IMPLEMENT_MODEL, then local_model.model in .playbooks/config.json "
+        "BLITZ_IMPLEMENT_MODEL, then local_model.model in .blitz/config.json "
         "(repo, then workspace), then qwen2.5-14b-28k.",
     )
     impl.add_argument(
@@ -340,56 +333,9 @@ def build_parser() -> argparse.ArgumentParser:
     )
     impl.set_defaults(func=_cmd_implement)
 
-    act = sub.add_parser(
-        "activity",
-        help="Replay a coding-agent session: your prompts and how each was "
-        "resolved (currently reads Claude Code's local transcripts).",
-    )
-    act.add_argument(
-        "session", nargs="?", default=None,
-        help="Session id (or unique prefix) to show; default: the most "
-        "recently modified session for the resolved project",
-    )
-    act.add_argument(
-        "--project", default=None,
-        help="Repo path whose agent sessions to inspect (default: cwd)",
-    )
-    act.add_argument(
-        "--sessions-dir", "--claude-dir",
-        dest="sessions_dir",
-        default=os.environ.get("BLITZ_SESSIONS_DIR", os.environ.get("BLITZ_CLAUDE_DIR")),
-        help="Override the agent transcript root (default: ~/.claude/projects; "
-        "env BLITZ_SESSIONS_DIR)",
-    )
-    act.add_argument(
-        "--list", action="store_true",
-        help="List sessions for the resolved project instead of showing one",
-    )
-    act.add_argument(
-        "--limit", type=int, default=30,
-        help="Max turns to show, most recent first (default 30)",
-    )
-    act.add_argument(
-        "--full", action="store_true",
-        help="Terminal output: show untruncated prompts/responses/tool "
-        "input+output instead of the compact single-line labels (the HTML "
-        "report always includes full detail, expandable per action, "
-        "regardless of this flag)",
-    )
-    act.add_argument(
-        "--html", default=None,
-        help="Also write a self-contained HTML report to this path",
-    )
-    act.set_defaults(func=_cmd_activity)
-
-    pb = sub.add_parser(
-        "playbooks",
-        help="Spec-driven development playbooks (slash-commands for your agent tool).",
-    )
-    pb_sub = pb.add_subparsers(dest="playbooks_cmd", required=True)
-    sp_init = pb_sub.add_parser(
+    sp_init = sub.add_parser(
         "init",
-        help="Install the playbook slash-commands + .playbooks/ working area into this repo.",
+        help="Install the playbook slash-commands + .blitz/ working area into this repo.",
     )
     sp_init.add_argument(
         "--dir", default=".", help="Repo root to install into (default: current dir)."
@@ -427,8 +373,7 @@ def build_parser() -> argparse.ArgumentParser:
     sp_init.add_argument(
         "--force", action="store_true", help="Overwrite existing command/scaffold files."
     )
-    sp_init.set_defaults(func=_cmd_playbooks)
-    pb.set_defaults(func=_cmd_playbooks)
+    sp_init.set_defaults(func=_cmd_init)
 
     lr = sub.add_parser(
         "locker-room",
@@ -464,6 +409,48 @@ def build_parser() -> argparse.ArgumentParser:
         )
         leaf.set_defaults(func=_cmd_locker_room_make, target=target)
 
+    act = lr_sub.add_parser(
+        "activity",
+        help="Replay a coding-agent session: your prompts and how each was "
+        "resolved (currently reads Claude Code's local transcripts).",
+    )
+    act.add_argument(
+        "session", nargs="?", default=None,
+        help="Session id (or unique prefix) to show; default: the most "
+        "recently modified session for the resolved project",
+    )
+    act.add_argument(
+        "--project", default=None,
+        help="Repo path whose agent sessions to inspect (default: cwd)",
+    )
+    act.add_argument(
+        "--sessions-dir", "--claude-dir",
+        dest="sessions_dir",
+        default=os.environ.get("BLITZ_SESSIONS_DIR", os.environ.get("BLITZ_CLAUDE_DIR")),
+        help="Override the agent transcript root (default: ~/.claude/projects; "
+        "env BLITZ_SESSIONS_DIR)",
+    )
+    act.add_argument(
+        "--list", action="store_true",
+        help="List sessions for the resolved project instead of showing one",
+    )
+    act.add_argument(
+        "--limit", type=int, default=30,
+        help="Max turns to show, most recent first (default 30)",
+    )
+    act.add_argument(
+        "--full", action="store_true",
+        help="Terminal output: show untruncated prompts/responses/tool "
+        "input+output instead of the compact single-line labels (the HTML "
+        "report always includes full detail, expandable per action, "
+        "regardless of this flag)",
+    )
+    act.add_argument(
+        "--html", default=None,
+        help="Also write a self-contained HTML report to this path",
+    )
+    act.set_defaults(func=_cmd_activity)
+
     return parser
 
 

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/blitz_cli/playbooks/commands/analyze.md

@@ -17,7 +17,7 @@ You **MUST** consider the user input before proceeding (if not empty).
 ## Pre-Execution Checks
 
 **Check for extension hooks (before analysis)**:
-- Check if `.playbooks/extensions.yml` exists in the project root.
+- Check if `.blitz/extensions.yml` exists in the project root.
 - If it exists, read it and look for entries under the `hooks.before_analyze` key
 - If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
 - Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.
@@ -47,7 +47,7 @@ You **MUST** consider the user input before proceeding (if not empty).
     Wait for the result of the hook command before proceeding to the Goal.
     ```
     After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `/skill:playbook-...` or `$playbook-...`). Emitting the block alone does not run the hook.
-- If no hooks are registered or `.playbooks/extensions.yml` does not exist, skip silently
+- If no hooks are registered or `.blitz/extensions.yml` does not exist, skip silently
 
 ## Goal
 
@@ -57,7 +57,7 @@ Identify inconsistencies, duplications, ambiguities, and underspecified items ac
 
 **STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).
 
-**Constitution Authority**: The project constitution (`/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `__SPECKIT_COMMAND_ANALYZE__`.
+**Playbook Authority**: The project playbook (`/memory/playbook.md`) is **non-negotiable** within this analysis scope. Playbook conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit playbook update outside `__SPECKIT_COMMAND_ANALYZE__`.
 
 ## Execution Steps
 
@@ -99,9 +99,9 @@ Load only the minimal necessary context from each artifact:
 - Parallel markers [P]
 - Referenced file paths
 
-**From constitution:**
+**From playbook:**
 
-- Load `/memory/constitution.md` for principle validation
+- Load `/memory/playbook.md` for principle validation
 
 ### 3. Build Semantic Models
 
@@ -110,7 +110,7 @@ Create internal representations (do not include raw artifacts in output):
 - **Requirements inventory**: For each Functional Requirement (FR-###) and Success Criterion (SC-###), record a stable key. Use the explicit FR-/SC- identifier as the primary key when present, and optionally also derive an imperative-phrase slug for readability (e.g., "User can upload file" → `user-can-upload-file`). Include only Success Criteria items that require buildable work (e.g., load-testing infrastructure, security audit tooling), and exclude post-launch outcome metrics and business KPIs (e.g., "Reduce support tickets by 50%").
 - **User story/action inventory**: Discrete user actions with acceptance criteria
 - **Task coverage mapping**: Map each task to one or more requirements or stories (inference by keyword / explicit reference patterns like IDs or key phrases)
-- **Constitution rule set**: Extract principle names and MUST/SHOULD normative statements
+- **Playbook rule set**: Extract principle names and MUST/SHOULD normative statements
 
 ### 4. Detection Passes (Token-Efficient Analysis)
 
@@ -132,10 +132,10 @@ Focus on high-signal findings. Limit to 50 findings total; aggregate remainder i
 - User stories missing acceptance criteria alignment
 - Tasks referencing files or components not defined in spec/plan
 
-#### D. Constitution Alignment
+#### D. Playbook Alignment
 
 - Any requirement or plan element conflicting with a MUST principle
-- Missing mandated sections or quality gates from constitution
+- Missing mandated sections or quality gates from playbook
 
 #### E. Coverage Gaps
 
@@ -154,7 +154,7 @@ Focus on high-signal findings. Limit to 50 findings total; aggregate remainder i
 
 Use this heuristic to prioritize findings:
 
-- **CRITICAL**: Violates constitution MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality
+- **CRITICAL**: Violates playbook MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality
 - **HIGH**: Duplicate or conflicting requirement, ambiguous security/performance attribute, untestable acceptance criterion
 - **MEDIUM**: Terminology drift, missing non-functional task coverage, underspecified edge case
 - **LOW**: Style/wording improvements, minor redundancy not affecting execution order
@@ -176,7 +176,7 @@ Output a Markdown report (no file writes) with the following structure:
 | Requirement Key | Has Task? | Task IDs | Notes |
 |-----------------|-----------|----------|-------|
 
-**Constitution Alignment Issues:** (if any)
+**Playbook Alignment Issues:** (if any)
 
 **Unmapped Tasks:** (if any)
 
@@ -203,7 +203,7 @@ Ask the user: "Would you like me to suggest concrete remediation edits for the t
 
 ### 9. Check for extension hooks
 
-After reporting, check if `.playbooks/extensions.yml` exists in the project root.
+After reporting, check if `.blitz/extensions.yml` exists in the project root.
 - If it exists, read it and look for entries under the `hooks.after_analyze` key
 - If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
 - Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.
@@ -231,7 +231,7 @@ After reporting, check if `.playbooks/extensions.yml` exists in the project root
     EXECUTE_COMMAND: {command}
     ```
     After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `/skill:playbook-...` or `$playbook-...`). Emitting the block alone does not run the hook.
-- If no hooks are registered or `.playbooks/extensions.yml` does not exist, skip silently
+- If no hooks are registered or `.blitz/extensions.yml` does not exist, skip silently
 
 ## Operating Principles
 
@@ -246,7 +246,7 @@ After reporting, check if `.playbooks/extensions.yml` exists in the project root
 
 - **NEVER modify files** (this is read-only analysis)
 - **NEVER hallucinate missing sections** (if absent, report them accurately)
-- **Prioritize constitution violations** (these are always CRITICAL)
+- **Prioritize playbook violations** (these are always CRITICAL)
 - **Use examples over exhaustive rules** (cite specific instances, not generic patterns)
 - **Report zero issues gracefully** (emit success report with coverage statistics)
 

{blitz_cli-0.9.0 → blitz_cli-0.10.0}/blitz_cli/playbooks/commands/clarify.md

@@ -21,7 +21,7 @@ You **MUST** consider the user input before proceeding (if not empty).
 ## Pre-Execution Checks
 
 **Check for extension hooks (before clarification)**:
-- Check if `.playbooks/extensions.yml` exists in the project root.
+- Check if `.blitz/extensions.yml` exists in the project root.
 - If it exists, read it and look for entries under the `hooks.before_clarify` key
 - If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
 - Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.
@@ -51,7 +51,7 @@ You **MUST** consider the user input before proceeding (if not empty).
     Wait for the result of the hook command before proceeding to the Outline.
     ```
     After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `/skill:playbook-...` or `$playbook-...`). Emitting the block alone does not run the hook.
-- If no hooks are registered or `.playbooks/extensions.yml` does not exist, skip silently
+- If no hooks are registered or `.blitz/extensions.yml` does not exist, skip silently
 
 ## Outline
 
@@ -68,7 +68,7 @@ Execution steps:
    - If JSON parsing fails, abort and instruct user to re-run `__SPECKIT_COMMAND_SPECIFY__` or verify feature branch environment.
    - For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
 
-2. **IF EXISTS**: Load `/memory/constitution.md` for project principles and governance constraints.
+2. **IF EXISTS**: Load `/memory/playbook.md` for project principles and governance constraints.
 
 3. Load the current spec file. Perform a structured ambiguity & coverage scan using this taxonomy. For each category, mark status: Clear / Partial / Missing. Produce an internal coverage map used for prioritization (do not output raw map unless no questions will be asked).
 
@@ -236,7 +236,7 @@ Context for prioritization: {ARGS}
 
 **You MUST complete this section before reporting completion to the user.**
 
-Check if `.playbooks/extensions.yml` exists in the project root.
+Check if `.blitz/extensions.yml` exists in the project root.
 - If it does not exist, or no hooks are registered under `hooks.after_clarify`, skip to the Completion Report.
 - If it exists, read it and look for entries under the `hooks.after_clarify` key.
 - If the YAML cannot be parsed or is invalid, skip hook checking silently and continue to the Completion Report.