@caddis/cli 0.4.64 → 0.4.65

package/bundles/antigravity-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "caddis",
-  "version": "1.3.150",
+  "version": "1.3.151",
   "description": "caddis — agent-agnostic dev harness as an Antigravity (agy) plugin: TDD skills + commands, single-sourced with the Claude Code plugin."
 }

package/bundles/antigravity-plugin/scripts/caddis_fleet.py

@@ -295,8 +295,8 @@ def check_sheet(sheet_text: str, roster_text: str) -> list[str]:
 
 # ---- session presence -------------------------------------------------------------------------
 
-def whoami(session_id: str, name: str, root: Path) -> Path:
-    """Write `<artifacts>/session-state/<sid>.name`: one tab-separated line `name  repo root  branch`."""
+def _name_file(session_id: str, root: Path) -> Path:
+    """`<artifacts>/session-state/<sid>.name`, the file `whoami` writes."""
     slug = "".join(c for c in session_id if c.isalnum() or c in "-_")[:64]
     if not slug:
         raise ValueError("empty session id")
@@ -305,6 +305,21 @@ def whoami(session_id: str, name: str, root: Path) -> Path:
         art = Path(artifact_root(str(root)))
     except Exception:
         art = root / ".caddis"
+    return art / "session-state" / f"{slug}.name"
+
+
+def session_name(session_id: str, root: Path) -> tuple[str, bool]:
+    """The session's display name and whether `whoami` recorded it; else the first 8 characters of the id."""
+    try:
+        line = _name_file(session_id, root).read_text(encoding="utf-8").split("\n", 1)[0].split("\t")[0].strip()
+    except (OSError, UnicodeDecodeError, ValueError):
+        line = ""
+    return (line, True) if line else (session_id[:8], False)
+
+
+def whoami(session_id: str, name: str, root: Path) -> Path:
+    """Write `<artifacts>/session-state/<sid>.name`: one tab-separated line `name  repo root  branch`."""
+    out = _name_file(session_id, root)
     branch = "-"
     for cmd in (["symbolic-ref", "--short", "-q", "HEAD"], ["rev-parse", "--short", "HEAD"]):  # branch, else detached
         proc = subprocess.run(["git", "-C", str(root), *cmd], capture_output=True, text=True,
@@ -312,12 +327,64 @@ def whoami(session_id: str, name: str, root: Path) -> Path:
         if proc.returncode == 0 and proc.stdout.strip():
             branch = proc.stdout.strip()
             break
-    out = art / "session-state" / f"{slug}.name"
     out.parent.mkdir(parents=True, exist_ok=True)
     out.write_text(f"{name}\t{root}\t{branch}\n", encoding="utf-8")
     return out
 
 
+# ---- resume block -----------------------------------------------------------------------------
+
+class ResumeError(ValueError):
+    """The relay has no usable `## Resume prompt`."""
+
+
+_RESUME_SECTION = re.compile(r"^## Resume prompt[^\n]*\n(.*?)(?=^## |\Z)", re.MULTILINE | re.DOTALL)
+_FENCE_OPEN = re.compile(r"^(`{3,}|~{3,})[^\n`]*$")
+
+
+def resume_prompt(relay_text: str) -> str:
+    """The text inside the first fenced block of the relay's `## Resume prompt` section, verbatim."""
+    m = _RESUME_SECTION.search(relay_text)
+    if not m:
+        raise ResumeError("relay has no ## Resume prompt section")
+    body: list[str] = []
+    fence: str | None = None
+    for line in m.group(1).splitlines():
+        if fence is None:
+            opened = _FENCE_OPEN.match(line.strip())
+            if opened:
+                fence = opened.group(1)
+            continue
+        if line.strip().startswith(fence) and not line.strip().strip(fence[0]):
+            break  # the closing fence
+        body.append(line)
+    else:
+        if fence is None:
+            raise ResumeError("## Resume prompt section has no fenced block")
+        raise ResumeError("## Resume prompt fenced block is not closed")
+    prompt = "\n".join(body).strip("\n")
+    if not prompt.strip():
+        raise ResumeError("## Resume prompt fenced block is empty")
+    return prompt
+
+
+def shell_arg(text: str) -> str:
+    """One word that PowerShell and bash read the same: one line, inside single quotes (no expansion in either).
+    A `'` would end the word in bash and a `"` is dropped by Windows PowerShell 5.1, so both become typographic."""
+    one_line = " ".join(text.split())
+    return "'" + one_line.replace("'", "’").replace('"', "”") + "'"
+
+
+def render_resume(session: str, session_id: str, workstream: str, prompt: str, role: str, stamp: datetime,
+                  fleet_mode: bool = False) -> str:
+    """The last output of `/caddis:handoff`. In a fleet close the restart sheet holds the only start line."""
+    if fleet_mode:
+        start = "Start line: from the restart sheet"
+    else:
+        start = f"Start line:\nclaude --name {new_name(role, stamp)} {shell_arg(prompt)}"
+    return (f"=== RESUME ===\nSession: {session} ({session_id})\nWorkstream: {workstream}\n"
+            f"{_fenced(prompt)}\n{start}\n")
+
 # ---- CLI --------------------------------------------------------------------------------------
 
 def _load_acks(fleet_dir: Path) -> list[Ack]:
@@ -327,6 +394,32 @@ def _load_acks(fleet_dir: Path) -> list[Ack]:
     return [parse_ack(p.read_text(encoding="utf-8")) for p in sorted(acks_dir.glob("*.md"))]
 
 
+def _resume_block_cli(args: argparse.Namespace) -> int:
+    try:
+        import caddis_workstreams
+    except ModuleNotFoundError as exc:
+        if exc.name != "caddis_workstreams":
+            raise
+        sys.path.insert(0, str(Path(__file__).resolve().parent))
+        import caddis_workstreams
+    root = args.root.resolve()
+    try:
+        text, digest = caddis_workstreams.read_relay(root, args.name)
+        if digest is None:
+            raise ResumeError(f"relay {args.name!r} not found")
+        prompt = resume_prompt(text)
+    except (ValueError, OSError) as exc:  # ResumeError is a ValueError; a bad relay name is one too
+        sys.stderr.write(f"resume-block failed: {exc}\n")
+        return caddis_exit.BLOCKED
+    session, known = session_name(args.session_id, root)
+    role = args.role or (role_of(session) if known else args.name)
+    if not _SAFE_NAME.match(role):  # the role goes unquoted into the start line
+        sys.stderr.write(f"resume-block failed: bad role {role!r}\n")
+        return caddis_exit.BLOCKED
+    print(render_resume(session, args.session_id, args.name, prompt, role, datetime.now(), args.fleet), end="")
+    return caddis_exit.CLEAN
+
+
 def main(argv: list[str] | None = None) -> int:
     parser = argparse.ArgumentParser(prog="caddis_fleet.py", description=__doc__.splitlines()[0])
     sub = parser.add_subparsers(dest="cmd", required=True)
@@ -353,6 +446,12 @@ def main(argv: list[str] | None = None) -> int:
     p.add_argument("--session-id", required=True)
     p.add_argument("--name", required=True)
     p.add_argument("--root", default=".", type=Path)
+    p = sub.add_parser("resume-block", help="print the session name and the relay's resume prompt (last step of handoff)")
+    p.add_argument("--name", required=True, help="the relay's workstream name")
+    p.add_argument("--session-id", required=True)
+    p.add_argument("--root", default=".", type=Path)
+    p.add_argument("--role", help="role for the new session's name (default: the session name's role, else the relay name)")
+    p.add_argument("--fleet", action="store_true", help="fleet close: print no start line (the restart sheet has it)")
     args = parser.parse_args(argv)
 
     if args.cmd == "role-of":
@@ -419,6 +518,8 @@ def main(argv: list[str] | None = None) -> int:
             return caddis_exit.BLOCKED
         print("[FLEET] sheet ok")
         return caddis_exit.CLEAN
+    if args.cmd == "resume-block":
+        return _resume_block_cli(args)
     # whoami
     try:
         out = whoami(args.session_id, args.name, args.root.resolve())

package/bundles/antigravity-plugin/scripts/oss_review.py

@@ -3,14 +3,15 @@
 
 A different vendor's model has different blind spots, so a second model reviewing your diff
 catches bugs a same-vendor reviewer misses. This tool is provider-agnostic: point it at
-DeepSeek (default — cheapest + most architecturally distinct from Claude), GLM, OpenRouter,
-or any OpenAI-compatible `/chat/completions` endpoint via three env vars.
+agy Argon (default since 2026-10-21; needs no key), DeepSeek (cheap, architecturally distinct from
+Claude), GLM, OpenRouter, or any OpenAI-compatible `/chat/completions` endpoint via three env vars.
 
 Config precedence (highest wins): explicit CLI flag  >  env var  >  provider preset.
-  REVIEW_PROVIDER   preset name: deepseek | glm | openrouter   (default deepseek)
+  REVIEW_PROVIDER   preset name: agy-argon | deepseek | glm | openrouter   (default agy-argon)
+                    precedence: --provider flag, process env, then REVIEW_PROVIDER in ~/.caddis/keys.env
   REVIEW_BASE_URL   base URL, no trailing /chat/completions    (overrides the preset's URL)
   REVIEW_MODEL      model id                                   (overrides the preset's model)
-  REVIEW_API_KEY    bearer token                               (REQUIRED — no key ⇒ exit 3)
+  REVIEW_API_KEY    bearer token                               (REQUIRED for an HTTP provider; agy-argon needs none)
 
 Future-proofing: model ids and endpoints churn. Two layers protect against that — (1) the PROVIDERS
 table below is the ONE place a renamed model/URL is edited; (2) REVIEW_MODEL / REVIEW_BASE_URL env
@@ -37,8 +38,9 @@ Exit codes (fail-closed):
   4  error              — no diff verdict parsed, git failure, other endpoint/parse failure, or the diff
                           exceeds REVIEW_MAX_DIFF_CHARS (see below — never silently downgraded to CLEAN)
 
-Provider chain (owner policy, 2026-10-16): deepseek -> agy-argon -> glm. A named --provider goes first,
-then the rest in policy order; a provider with no key (or no agy on PATH) is skipped. A provider failure
+Provider chain (owner policy, 2026-10-21; was deepseek first from 2026-10-16): agy-argon -> deepseek -> glm.
+A named --provider goes first, then the rest in policy order; a provider with no key (or no agy on PATH)
+is skipped. With no provider named, the chain starts at the first provider that is available. A provider failure
 moves to the next provider and never splits the diff. On HTTP 429 a `Retry-After` is honoured ONCE per
 provider (capped at 60 s), then the next provider is tried. A provider that failed gets no more calls in
 the same run. agy runs through `caddis_spend.py run` (the EUR spend cap), in plan mode, with the diff in
@@ -99,9 +101,12 @@ PROVIDERS: dict[str, dict[str, str]] = {
     "glm":        {"base_url": "https://api.z.ai/api/coding/paas/v4", "model": "glm-5.3"},
     "openrouter": {"base_url": "https://openrouter.ai/api/v1",        "model": "deepseek/deepseek-v4-flash"},
 }
-DEFAULT_PROVIDER = "deepseek"
+# The HTTP preset used when nobody names a provider but an HTTP endpoint is still needed: a custom
+# endpoint (REVIEW_BASE_URL / REVIEW_MODEL) with no --provider, and resolve_config's own default. It is
+# a key-lookup and label default only; it is NOT the review order (see REVIEW_ORDER).
+HTTP_DEFAULT_PROVIDER = "deepseek"
 
-# The review chain, in owner-policy order (2026-10-16): DeepSeek, then agy Argon, then GLM. A named
+# The review chain, in owner-policy order (2026-10-21): agy Argon, then DeepSeek, then GLM. A named
 # provider goes first and the rest follow in this order; a custom endpoint (REVIEW_BASE_URL /
 # REVIEW_MODEL) never falls back, because its owner named exactly who reviews.
 #
@@ -112,12 +117,14 @@ DEFAULT_PROVIDER = "deepseek"
 # sessions recorded "cross-review inconclusive" and moved on. A review that silently does not
 # happen is the same failure class as a diff that silently is not read.
 #
-# Order matters: DeepSeek leads because it has actually found real bugs (a date-boundary bug
-# two same-vendor passes missed, an anchor bug, an orphaned-permission-rows bug). GLM is the
-# spare tyre, not a co-equal — an alternation policy that sends half the phases to a provider
-# that times out buys variety it never actually collects.
+# Order matters: agy Argon leads since 2026-10-21 (owner decision) because DeepSeek ran out of credit,
+# so every unnamed review tried DeepSeek first and failed before it reached Argon. DeepSeek stays
+# second: it has actually found real bugs (a date-boundary bug two same-vendor passes missed, an
+# anchor bug, an orphaned-permission-rows bug). GLM is the spare tyre, not a co-equal — an alternation
+# policy that sends half the phases to a provider that times out buys variety it never actually collects.
 AGY_PROVIDER = "agy-argon"
-REVIEW_ORDER: tuple[str, ...] = ("deepseek", AGY_PROVIDER, "glm")
+DEFAULT_PROVIDER = AGY_PROVIDER
+REVIEW_ORDER: tuple[str, ...] = (AGY_PROVIDER, "deepseek", "glm")
 
 # agy runs headless through the spend cap: plan mode (it needs no tools, the diff is in the prompt).
 AGY_MODEL = "gemini-4-argon-high"
@@ -239,8 +246,14 @@ def _parse_keys_file(path: str) -> dict[str, str]:
     p = Path(path).expanduser()
     if not p.is_file():
         return {}
+    try:
+        text = p.read_text(encoding="utf-8")
+    except (OSError, UnicodeDecodeError):
+        # Unreadable or not UTF-8 (PowerShell writes UTF-16). agy needs no key, so this file must not
+        # stop a review; a provider that needs a key then reports "no API key" as usual.
+        return {}
     out: dict[str, str] = {}
-    for raw in p.read_text(encoding="utf-8").splitlines():
+    for raw in text.splitlines():
         line = raw.strip()
         if not line or line.startswith("#") or "=" not in line:
             continue
@@ -249,6 +262,15 @@ def _parse_keys_file(path: str) -> dict[str, str]:
     return out
 
 
+def named_provider(args: argparse.Namespace, env: dict[str, str]) -> str:
+    """The provider the caller chose, or "". Order: --provider flag, process env REVIEW_PROVIDER,
+    REVIEW_PROVIDER in the keys file (~/.caddis/keys.env), so a default is switched with one line there."""
+    chosen = args.provider or env.get("REVIEW_PROVIDER")
+    if not chosen:
+        chosen = _parse_keys_file(env.get("CADDIS_KEYS_FILE") or DEFAULT_KEYS_FILE).get("REVIEW_PROVIDER")
+    return (chosen or "").strip().lower()
+
+
 def resolve_config(
     args: argparse.Namespace,
     env: dict[str, str],
@@ -265,9 +287,7 @@ def resolve_config(
     provider: pointing DeepSeek's model id at GLM's endpoint would turn a clean fallback into
     a confusing 404.
     """
-    provider = (
-        provider or args.provider or env.get("REVIEW_PROVIDER") or DEFAULT_PROVIDER
-    ).strip().lower()
+    provider = (provider or named_provider(args, env) or HTTP_DEFAULT_PROVIDER).strip().lower()
     preset = PROVIDERS.get(provider, {})
     if use_overrides:
         base_url = (args.base_url or env.get("REVIEW_BASE_URL") or preset.get("base_url") or "").rstrip("/")
@@ -735,15 +755,16 @@ def main(argv: list[str] | None = None, env: dict[str, str] | None = None) -> in
     parser.add_argument("--cwd", default=".", help="repo directory (default: cwd)")
     parser.add_argument("--provider", default=None,
                         help=f"preset: {', '.join(sorted(PROVIDERS))} or {AGY_PROVIDER} (default "
-                             f"{DEFAULT_PROVIDER}); env REVIEW_PROVIDER. A provider failure falls back in "
-                             f"the order {' -> '.join(REVIEW_ORDER)}")
+                             f"{DEFAULT_PROVIDER}, then the next available provider); env REVIEW_PROVIDER "
+                             f"or REVIEW_PROVIDER in the keys file. "
+                             f"A provider failure falls back in the order {' -> '.join(REVIEW_ORDER)}")
     parser.add_argument("--base-url", dest="base_url", default=None, help="override REVIEW_BASE_URL / the preset")
     parser.add_argument("--model", default=None, help="override REVIEW_MODEL / the preset")
     parser.add_argument("--max-diff-chars", type=int, default=None,
                         help=f"override REVIEW_MAX_DIFF_CHARS (default {DEFAULT_MAX_DIFF_CHARS})")
     parser.add_argument("--check-config", action="store_true",
-                        help="report whether a usable key exists and exit — no diff, no LLM call. "
-                             "Exit 0 = ready, 3 = nothing configured.")
+                        help="report whether a usable reviewer exists (agy on PATH, or an API key) and "
+                             "exit — no diff, no LLM call. Exit 0 = ready, 3 = nothing configured.")
     parser.add_argument("--allow-path", dest="allow_path", action="append", default=[],
                         metavar="GLOB",
                         help="re-admit a file the secret-filter deny list would otherwise drop "
@@ -756,16 +777,18 @@ def main(argv: list[str] | None = None, env: dict[str, str] | None = None) -> in
     # that can actually talk to a human. This half just answers "is it configured?" cheaply enough
     # to call before you need it, instead of finding out mid-commit.
     if args.check_config:
-        available = configured_providers(env)
+        # agy Argon is the default reviewer and needs no key: agy on PATH plus caddis_spend.py is enough.
+        available = ([AGY_PROVIDER] if agy_launcher() is not None else []) + configured_providers(env)
         if not available:
             sys.stderr.write(
-                "no second-vendor API key is configured anywhere.\n"
+                "no second-vendor reviewer is configured: no API key anywhere, and no agy on PATH\n"
+                "  (with caddis_spend.py) for the default agy-argon reviewer.\n"
                 "  Cross-review needs one — the whole point is a reviewer that does not share this\n"
                 "  model's blind spots, so a same-vendor fallback would be no review at all.\n"
                 f"  Add a key to {env.get('CADDIS_KEYS_FILE') or DEFAULT_KEYS_FILE}, e.g.\n"
-                "    DEEPSEEK_API_KEY=<your-key>\n")
+                "    GLM_API_KEY=<your-key>\n")
             return EXIT_CONFIG
-        print(f"cross-review is ready. Providers with a key: {', '.join(available)}")
+        print(f"cross-review is ready. Providers available: {', '.join(available)}")
         return EXIT_CLEAN
 
     try:
@@ -804,13 +827,14 @@ def main(argv: list[str] | None = None, env: dict[str, str] | None = None) -> in
         return EXIT_CONFIG
     diff_text = filter_result.kept_diff
 
-    primary_provider = (
-        args.provider or env.get("REVIEW_PROVIDER") or DEFAULT_PROVIDER
-    ).strip().lower()
+    named = named_provider(args, env)
     # A custom ENDPOINT names exactly who reviews (REVIEW_BASE_URL/REVIEW_MODEL, the documented
     # future-proofing path): it never falls back. A named preset falls back on a provider failure,
     # and the switch is printed, so the reviewer is never misreported.
     custom = bool(args.base_url or env.get("REVIEW_BASE_URL") or args.model or env.get("REVIEW_MODEL"))
+    # With nothing named, the default is agy Argon. A custom endpoint with no provider named is an HTTP
+    # call (never agy), keyed and labelled as before.
+    primary_provider = named or (HTTP_DEFAULT_PROVIDER if custom else DEFAULT_PROVIDER)
     agy_cmd = agy_launcher()
 
     def _http_entry(name: str, url: str, key: str, mdl: str):
@@ -821,12 +845,35 @@ def main(argv: list[str] | None = None, env: dict[str, str] | None = None) -> in
 
     try:
         if primary_provider == AGY_PROVIDER and not custom:
-            if agy_cmd is None:
+            if agy_cmd is not None:
+                chain = [_agy_entry(agy_cmd)]
+            elif named:
                 raise ConfigError(f"provider {AGY_PROVIDER!r} needs agy on PATH and caddis_spend.py "
                                   "(beside this script or in the repo's scripts/ folder).")
-            chain = [_agy_entry(agy_cmd)]
+            else:
+                # The default degrades: no agy here, so the chain starts at the next provider with a key.
+                chain = []
         else:
             chain = [_http_entry(primary_provider, *resolve_config(args, env))]
+        # The rest of the chain in policy order (agy Argon -> DeepSeek -> GLM). A provider with no key, or
+        # agy with no agy on PATH, is skipped: not an error, just nothing to fall back to.
+        if not custom:
+            for name in REVIEW_ORDER:
+                if chain and name == chain[0][0]:
+                    continue
+                if name == AGY_PROVIDER:
+                    if agy_cmd is not None:
+                        chain.append(_agy_entry(agy_cmd))
+                    continue
+                try:
+                    chain.append(_http_entry(name, *resolve_config(args, env, provider=name, use_overrides=False)))
+                except ConfigError:
+                    continue
+        if not chain:
+            raise ConfigError(
+                "no reviewer is available: agy is not on PATH (with caddis_spend.py) and no provider has an "
+                "API key. Set $REVIEW_API_KEY, or add a key such as DEEPSEEK_API_KEY or GLM_API_KEY to "
+                f"{env.get('CADDIS_KEYS_FILE') or DEFAULT_KEYS_FILE}, or install agy.")
     except ConfigError as exc:
         sys.stderr.write(f"{exc}\n")
         return EXIT_CONFIG
@@ -897,21 +944,6 @@ def main(argv: list[str] | None = None, env: dict[str, str] | None = None) -> in
 
     branch = current_branch(args.cwd)
 
-    # The rest of the chain in policy order (DeepSeek -> agy Argon -> GLM). A provider with no key, or
-    # agy with no agy on PATH, is skipped: not an error, just nothing to fall back to.
-    if not custom:
-        for name in REVIEW_ORDER:
-            if name == chain[0][0]:
-                continue
-            if name == AGY_PROVIDER:
-                if agy_cmd is not None:
-                    chain.append(_agy_entry(agy_cmd))
-                continue
-            try:
-                chain.append(_http_entry(name, *resolve_config(args, env, provider=name, use_overrides=False)))
-            except ConfigError:
-                continue
-
     # Per run: a provider that failed (429, 5xx, timeout, empty reply, cap refusal) gets no more calls,
     # and each provider waits for a 429 Retry-After at most once. Hammering a throttled provider with
     # more, smaller calls is the 18-19 Oct 2026 failure.

package/bundles/antigravity-plugin/skills/_registry.md

@@ -15,7 +15,7 @@
 | Backend Development | `backend-development/` | Backend API design, database schemas, microservices and TDD. Use for backend system architecture. |
 | Code Review | `code-review/` | Automated code review for quality, security, performance and best practices. Use when reviewing code changes, PRs, or doing code audits. |
 | Codebase Audit | `codebase-audit/` | Audit an unfamiliar codebase before architecture or implementation work. Use for a new codebase, pre-implementation audit, codebase review, technical due diligence or onboarding. Produces AUDIT-FINDINGS.md and QUESTIONS.md. |
-| Cross Review | `cross-review/` | Cross-vendor code review of the current diff — a second-vendor model (DeepSeek/GLM/any OpenAI-compatible endpoint) reviews your changes to catch bugs a same-vendor reviewer misses |
+| Cross Review | `cross-review/` | Cross-vendor code review of the current diff — a second-vendor model (agy Argon by default; DeepSeek, GLM or any OpenAI-compatible endpoint) reviews your changes to catch bugs a same-vendor reviewer misses |
 | Dashboard Perf Sweep | `dashboard-perf-sweep/` | Re-measure dashboard/API endpoints for load-time regressions and decide by checklist if a slow one needs the rs-kit refresher, an index, keyset paging, gzip, or nothing. Use when the user says "sweep dashboard performance", "check if this app needs rs-kit", "re-measure the perf tracker", "is this endpoint a refresher candidate", or dashboard-performance-tracker.md is stale. Read-only. |
 | Error Handling | `error-handling/` | Error handling for Python and TypeScript: error hierarchies, custom exceptions, result types, retries, circuit breakers, error boundaries, logging, user-facing messages. |
 | Fastapi Dev | `fastapi-dev/` | Build FastAPI backends with standard patterns, error handling, and testing |

package/bundles/antigravity-plugin/skills/cross-review/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: cross-review
-description: Cross-vendor code review of the current diff — a second-vendor model (DeepSeek/GLM/any OpenAI-compatible endpoint) reviews your changes to catch bugs a same-vendor reviewer misses
+description: Cross-vendor code review of the current diff — a second-vendor model (agy Argon by default; DeepSeek, GLM or any OpenAI-compatible endpoint) reviews your changes to catch bugs a same-vendor reviewer misses
 ---
 
 # /caddis:cross-review — a second-vendor set of eyes on your diff
 
 Run a cross-vendor review of the current changes with a DIFFERENT model family than the one that wrote them
-(default **DeepSeek** — the cheapest + most architecturally distinct-from-Claude option). Use after a phase
+(default **agy Argon** since 2026-10-21 — it needs no key; DeepSeek and GLM are fallbacks). Use after a phase
 is green and before you commit, or for a second opinion on a risky diff. This is the *cross-vendor*
 complement to `/caddis:code-review`, not a replacement.
 
@@ -16,7 +16,7 @@ complement to `/caddis:code-review`, not a replacement.
 python "$TOOL" --check-config      # resolve $TOOL first, see "Run it" below
 ```
 
-Exit 0 means ready; it prints which providers have a key. **Exit 3 means nothing is configured —
+Exit 0 means ready; it prints which providers are available (agy-argon needs no key, only agy on PATH and caddis_spend.py). **Exit 3 means nothing is configured —
 STOP and ask the user now.** Do not proceed to the review, and do not silently skip it.
 
 Ask with `AskUserQuestion`: which provider to set up (DeepSeek, GLM, or another OpenAI-compatible
@@ -65,7 +65,7 @@ fi
 > copied weeks earlier silently won. `caddis_gate.py vendor-drift` now fails on the same condition.
 ```
 python "$TOOL" $ARGUMENTS                                # pass the user's flags THROUGH, raw
-python "$TOOL"                                           # no arguments: DeepSeek eyes on the working tree
+python "$TOOL"                                           # no arguments: agy Argon eyes on the working tree
 ```
 
 **`$ARGUMENTS` goes through raw, and must not be re-prefixed.** Callers are told to type the flag
@@ -74,7 +74,7 @@ writes. This line used to prefix the flag itself, which turned that into a doubl
 `--range --range main..HEAD` and made every plan-emitted call fail. Whatever the user typed is already a complete flag list:
 
 ```
-/caddis:cross-review                          -> the working tree, DeepSeek
+/caddis:cross-review                          -> the working tree, agy Argon
 /caddis:cross-review --range main..HEAD       -> that range
 /caddis:cross-review --provider glm           -> GLM eyes
 ```
@@ -86,8 +86,8 @@ now means the narrower case — a **single file** too big to split, or more batc
 see it, the fix is usually to review that one file separately, not to narrow `--range`; don't raise
 `--max-diff-chars` blind.
 
-**Do not alternate providers on a schedule.** The order is the owner policy: **DeepSeek, then agy Argon,
-then GLM** (`REVIEW_ORDER` in `oss_review.py`). A named `--provider` goes first; on a provider failure
+**Do not alternate providers on a schedule.** The order is the owner policy (21 Oct 2026): **agy Argon,
+then DeepSeek, then GLM** (`REVIEW_ORDER` in `oss_review.py`). A named `--provider` goes first; on a provider failure
 (HTTP 429, any 5xx, a timeout, a connection error, an empty reply) the tool moves to the next one in
 that order and prints which provider gave the verdict. A provider with no key is skipped. agy runs
 through `caddis_spend.py run` (the spend cap); if the cap refuses, agy is skipped. On a 429 the tool
@@ -95,6 +95,9 @@ waits for `Retry-After` once (at most 60 s); it never splits the diff because of
 reply. A custom endpoint (`--base-url`/`--model`) never falls back. Name a provider only when you have
 a reason.
 
+**Change the default.** The first provider comes from `--provider`, then the process env `REVIEW_PROVIDER`, then
+`REVIEW_PROVIDER` in `~/.caddis/keys.env`, then agy Argon. The others follow in `REVIEW_ORDER`. To make DeepSeek the default again, add `REVIEW_PROVIDER=deepseek` to ~/.caddis/keys.env.
+
 ## Interpret the exit code
 - **0 — REVIEW: CLEAN** → no blocking issues. Proceed.
 - **1 — REVIEW: BLOCKING** → read the printed findings, then **FIX each blocking item** (or explicitly

package/bundles/antigravity-plugin/skills/fleet-close/SKILL.md

@@ -72,7 +72,10 @@ FLEET CLOSE from <coordinator>: write your handoff and ack.
 Then these close rules, in the message:
 1. Run `/caddis:handoff` for **your own** relay only. Never touch another session's files. Skip its
    Step 7 (the `Push this note for another machine?` question): the restart sheet carries your prompt,
-   and a question nobody answers would stop you before you ack.
+   and a question nobody answers would stop you before you ack. Run the handoff's Step 9 as
+   `resume-block ... --fleet`: it prints your Session, Workstream and prompt, and
+   `Start line: from the restart sheet`. The restart sheet holds the only start line. The ack stays a
+   separate reply (rule 5).
 2. In a shared checkout (its `AGENTS.md` says `Shared checkout: yes`, or `git status` shows changes you
    did not make), skip the steps the handoff checklist skips there.
 3. If you run watchers: copy each watcher script to `.caddis/relay/<your name>-files/watchers/`, and fill
@@ -132,7 +135,7 @@ remove that session from the `--no-ack` list before the next `write`.
 
 ## Step 6 — your own handoff and ack
 
-Run `/caddis:handoff` for this session (the coordinator's own relay). Then write your own ack (the
+Run `/caddis:handoff` for this session (the coordinator's own relay), with Step 9 as `resume-block ... --fleet`. Then write your own ack (the
 `FLEET-ACK` block with your fields and your resume prompt) to a temp file and save it with
 `ack add`, as in Step 4. The coordinator's ack is never skipped. Then record this session's presence
 (your session id is printed at session start as `[caddis] this session's id: <id>`; never guess one):

package/bundles/antigravity-plugin/skills/handoff/SKILL.md

@@ -162,6 +162,10 @@ history, and the relay has a 4,000-character budget (`caddis_budget.py`).
 >    finished, by id and column name, never by hand:
 >    `python "${CLAUDE_PLUGIN_ROOT}/scripts/caddis_rows.py" set --file .caddis/open-work.md --id <row id> --col Status=done --col Evidence=<evidence>`.
 >    In a shared checkout (Step 0), use `--file <worktree>/.caddis/open-work.md` instead.
+>    When the file is missing or has no `type: open-work` frontmatter, report row 3 exactly as
+>    `skipped: no open-work.md with type: open-work (session tasks are saved by row 5)`, or, for a
+>    file without the frontmatter, `skipped: open-work.md has no type: open-work frontmatter (session
+>    tasks are saved by row 5)`. open-work.md is a repo backlog; this session's own tasks go to row 5.
 >    **Order of work:** when the repo has a roadmap (`caddis_roadmap.py list` prints a slug), the
 >    roadmap on origin is the order of work. Write the relay's "Next step (exact)" as
 >    `next: top open item of roadmap <slug> (caddis_roadmap.py status --roadmap <slug>)`. Never copy a
@@ -350,7 +354,7 @@ index or staged files — after the secret filter passes. Report its one-line re
 On the other machine, `/catchup <name>` fetches it.
 
 ## Step 8 — the checklist report
-End the handoff with this block, every row filled with `done`, `skipped: <reason>` or `failed: <error>`:
+Print this block, every row filled with `done`, `skipped: <reason>` or `failed: <error>`:
 
 ```
 === HANDOFF CHECKLIST ===
@@ -372,6 +376,32 @@ Shared checkout: yes|no <reason>
 
 Then, in a shared checkout, `Docs PR needed:` with the `PR:` line and the file list from Step 0.
 
+Step 9 prints after this report. It is the last output of the handoff.
+
+## Step 9 — print the resume prompt (always the last output)
+The owner should never have to ask for the resume prompt. After the checklist report, run:
+```
+python "${CLAUDE_PLUGIN_ROOT}/scripts/caddis_fleet.py" resume-block --name <name> --session-id <session-id> --root .
+```
+`<name>` is the workstream name from Step 3. It reads the relay's `## Resume prompt` block verbatim, and
+the session name (`session-state/<session-id>.name` when `whoami` wrote it, else the first 8 characters of
+the id). It prints, and you print its output as it is, with nothing after it:
+```
+=== RESUME ===
+Session: <session name> (<session id>)
+Workstream: <name>
+<the resume prompt, in a fenced block>
+Start line:
+claude --name <role>-<MMDD>-<HH> '<the resume prompt on one line>'
+```
+- **Fleet close.** When this handoff runs because a peer sent `FLEET CLOSE from <coordinator>`, add
+  `--fleet`. The Start line is then `Start line: from the restart sheet`: the restart sheet is the only
+  start line in a fleet close. The `FLEET-ACK` reply is a separate message and does not change.
+- **Exit 1** (no `## Resume prompt` block, or no relay) prints nothing on stdout. The handoff is not
+  complete: fix the relay (Step 3, point 5) and run the command again. Never write the block by hand.
+- Workstream with no `whoami` record: the new name uses the workstream name as its role. Pass
+  `--role <role>` to set another.
+
 ## Rules
 - **One next action, by priority ladder.** `## Next step` names exactly ONE action — not a menu. Pick it in
   order: (1) interrupted mid-phase work → finish + commit it; else (2) the active plan's next not-started

package/bundles/antigravity-plugin/skills/use-model/SKILL.md

@@ -17,7 +17,9 @@ command is the quick-reference + do-it-now version.
 | **Primary** | `claude` | your Anthropic plan |
 | **OSS lane** | `claude-oss <provider> [claude args…]` | the provider's plan/pay-per-token |
 | **Convenience alias** | `claude-glm [claude args…]` | same as `claude-oss glm` |
-| **Cross-vendor review** | `/caddis:cross-review` (`oss_review.py`) | the reviewer's plan |
+| **Cross-vendor review** | `/caddis:cross-review` (`oss_review.py`; default reviewer agy Argon, then DeepSeek, then GLM) | the reviewer's plan |
+
+To make DeepSeek the default again, add `REVIEW_PROVIDER=deepseek` to ~/.caddis/keys.env.
 
 `claude-oss` / `claude-glm` are launchers at `claude-harness/scripts/claude-oss.{sh,ps1}`. Each
 resolves the endpoint/model/key, sets `ANTHROPIC_BASE_URL` / `ANTHROPIC_MODEL` / `ANTHROPIC_AUTH_TOKEN`

package/bundles/antigravity-plugin-extras/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "caddis-extras",
-  "version": "1.3.45",
+  "version": "1.3.46",
   "description": "caddis-extras — the long-tail skills for the Antigravity (agy) caddis plugin; install alongside caddis for the full set."
 }

package/bundles/antigravity-plugin-extras/skills/_registry.md

@@ -30,7 +30,7 @@
 | Caching Patterns | `caching-patterns/` | Caching strategies for Streamlit and FastAPI applications |
 | Case Management | `case-management/` | >- |
 | Code Explainer | `code-explainer/` | Explain code with diagrams, analogies and step-by-step walkthroughs. Use when teaching a codebase or answering "how does this work?" |
-| Cross Review | `cross-review/` | Have a different vendor's model (DeepSeek, GLM, any OpenAI-compatible endpoint) review the current diff. Use after a phase is green and before commit/merge, or for a second opinion on a risky diff. |
+| Cross Review | `cross-review/` | Have a different vendor's model (agy Argon by default; DeepSeek, GLM, any OpenAI-compatible endpoint) review the current diff. Use after a phase is green and before commit/merge, or for a second opinion on a risky diff. |
 | Llm Application Dev | `llm-application-dev/` | LLM applications: prompt engineering, RAG and LLM integration. Use for AI-powered features, chatbots or LLM automation. |
 | Mcp Builder | `mcp-builder/` | Build high-quality MCP (Model Context Protocol) servers that let LLMs use external APIs and services, in Python (FastMCP) or Node/TypeScript (MCP SDK). |
 | Observability | `observability/` | Structured logging, correlation IDs, PII redaction, OpenTelemetry tracing, metrics (RED), SLO alerting, health probes and Sentry, in Python and TypeScript. Use when adding logs, traces, metrics or error tracking. |

package/bundles/antigravity-plugin-extras/skills/agent-orchestration/SKILL.md

@@ -458,7 +458,7 @@ LiteLLM cutover. **This table is the single place the intent→model mapping liv
 | **deepest** | Subtle correctness, security invariants, novel architecture, judgment-heavy seams | `opus` | `/model opus`; `Agent(model: "opus")` | **High** — Anthropic plan quota |
 | **broad** | Wide parallel coverage of a large but not-subtle surface; the workhorse | `sonnet` | `/model sonnet`; `Agent(model: "sonnet")` | Medium — the default; budget for several |
 | **mechanical** | Fully-specced, repeat-of-a-known-pattern, no judgment required | `haiku` | `/model haiku`; `Agent(model: "haiku")` | Low |
-| **cross-vendor-reviewer** | A *different vendor's* blind spots on a diff — **code review only** | `deepseek` (default), `glm` | `/caddis:cross-review`, `/glm`, `/deepseek` | **Scarce** — separate starter-tier subscription, NOT Anthropic quota. Ration it. |
+| **cross-vendor-reviewer** | A *different vendor's* blind spots on a diff — **code review only** | `agy-argon` (default), `deepseek`, `glm` | `/caddis:cross-review`, `/glm`, `/deepseek` | **Scarce** — separate starter-tier subscription, NOT Anthropic quota. Ration it. |
 | **synthesis / long-horizon** | Orchestrating many lanes, or work that can't self-verify across a large codebase | `fable` | `/model fable` | **Very high** — ~2× opus's rate-limit burn. RARE. |
 
 **Update this table, not the callers**, when a model is added, retired, or re-tiered. A plan that says
@@ -512,7 +512,7 @@ Invent no new machinery. Everything needed already ships:
 | Per-phase model + lane assignment in a plan | `/caddis:feature-plan` — every phase already carries **Model**, **Lane**, and a cross-review provider |
 
 **Reviewer rule (standing):** the reviewer is always a different vendor than whoever wrote the code.
-Claude or GLM implemented → DeepSeek reviews (or swap). Never same-vendor.
+Claude or GLM implemented → agy Argon reviews by default (DeepSeek, then GLM, as fallbacks). Never same-vendor.
 
 Full command/billing decision table: `docs/guide/multi-model-workflow.md`.
 

package/bundles/antigravity-plugin-extras/skills/cross-review/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: cross-review
-description: Have a different vendor's model (DeepSeek, GLM, any OpenAI-compatible endpoint) review the current diff. Use after a phase is green and before commit/merge, or for a second opinion on a risky diff.
+description: Have a different vendor's model (agy Argon by default; DeepSeek, GLM, any OpenAI-compatible endpoint) review the current diff. Use after a phase is green and before commit/merge, or for a second opinion on a risky diff.
 ---
 
 # Cross-Review — a second-vendor set of eyes on your diff
 
 A different vendor's model has different blind spots. Claude reviewing Claude's diff shares those
-blind spots; a **DeepSeek** (or GLM, or any OpenAI-compatible) reviewer catches a different class of
+blind spots; an **agy Argon** (default), DeepSeek, GLM or other OpenAI-compatible reviewer catches a different class of
 issue. This skill runs that second reviewer over the current changes and acts on its verdict.
 
 ## When to use
@@ -20,7 +20,7 @@ issue. This skill runs that second reviewer over the current changes and acts on
 python "$TOOL" --check-config
 ```
 
-Exit 0 prints which providers have a key. **Exit 3 means nothing is configured — stop and ask the
+Exit 0 prints which providers are available (agy-argon needs no key, only agy on PATH and caddis_spend.py). **Exit 3 means nothing is configured — stop and ask the
 user before reading any diff.** Do not proceed, and do not silently skip the review.
 
 Ask with `AskUserQuestion` which provider to set up, then write the key to `~/.caddis/keys.env` as
@@ -36,15 +36,16 @@ If a key exists for a *different* provider than the one requested, the error nam
 exact flag (`--provider glm`). Read the message before concluding anything is missing.
 
 ## Prerequisites (one-time)
-Only the key is mandatory — the tool ships **provider presets** (default `deepseek`, the cheapest + most
-architecturally distinct-from-Claude option; a review costs well under a cent):
+The default reviewer is **agy Argon** (since 2026-10-21; no key, but agy and `caddis_spend.py` must be present). For an HTTP
+provider only the key is mandatory — the tool ships **provider presets** (`deepseek`, `glm`, `openrouter`):
 ```
 REVIEW_API_KEY   = <your provider key>     # REQUIRED (exit 3 without it)
-REVIEW_PROVIDER  = deepseek                 # optional: deepseek | glm | openrouter (default deepseek)
+REVIEW_PROVIDER  = deepseek                 # optional: agy-argon | deepseek | glm | openrouter (default agy-argon)
 REVIEW_BASE_URL  = ...                      # optional: overrides the preset's URL
 REVIEW_MODEL     = ...                      # optional: overrides the preset's model id
 ```
-Switch provider with one flag: `--provider glm` (or `REVIEW_PROVIDER=glm`). **Future-proofing:** model ids
+Switch provider with one flag: `--provider glm` (or `REVIEW_PROVIDER=glm`, in the env or in `~/.caddis/keys.env`; flag, then env,
+then keys file, then agy Argon). To make DeepSeek the default again, add `REVIEW_PROVIDER=deepseek` to ~/.caddis/keys.env. **Future-proofing:** model ids
 churn — the preset table in `oss_review.py` is the one place to edit a rename, and `REVIEW_MODEL` /
 `REVIEW_BASE_URL` always win, so you can point at any new id without touching code.
 
@@ -91,7 +92,7 @@ smaller chunks; don't just raise `--max-diff-chars` without knowing the endpoint
   Fix it, then re-review only the fix diff. After 3 rounds, ask the owner (rule 3).
 - **4 — error** → no verdict parsed, a git failure, or an endpoint/parse failure. Read stderr; do not
   treat this as CLEAN — investigate.
-- **3 — misconfigured** → `REVIEW_API_KEY` is unset. Set it (see Prerequisites) and re-run.
+- **3 — could not run** → no reviewer is available (no agy on PATH and no API key), or every provider failed. Fix it (see Prerequisites) and re-run.
 
 ## Three rules: one attempt, one review
 1. **Think before you send.** Before a task goes to any coder, write its edge cases and check the facts it depends on (one query or one file read).

package/bundles/manifest.json

@@ -1,8 +1,8 @@
 {
-  "poolVersion": "1.3.150",
+  "poolVersion": "1.3.151",
   "bundles": {
-    "antigravity-plugin": "1.3.150",
-    "antigravity-plugin-extras": "1.3.45",
+    "antigravity-plugin": "1.3.151",
+    "antigravity-plugin-extras": "1.3.46",
     "codex": "unknown"
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@caddis/cli",
-  "version": "0.4.64",
+  "version": "0.4.65",
   "description": "Install, update and diagnose the caddis dev harness across every coding agent you use (Claude Code, agy/Antigravity, and more).",
   "keywords": [
     "caddis",