cli-agent-runner 0.1.40__tar.gz → 0.1.42__tar.gz

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/CHANGELOG.md

@@ -5,6 +5,27 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.1.42] - 2026-06-25
+
+### Added
+- `crash_loop` defense — serve stops after 5 consecutive *unknown* short crashes (non-zero exit, <60s, no classified transient), escalating the restart delay and recording the failure reason. Ends the respawn-forever crash loop; recoverable-slow failures (rate-limit / quota / 5xx / timeout) still ride the transient-error backoff unchanged.
+- `config_broken` defense — a permanent startup-battery failure now halts serve (distinct no-retry exit code `78`) instead of respawning a broken config every round.
+
+### Fixed
+- `vcs.dirty_action` no longer sweeps the runner's own `log_dir` bookkeeping when `log_dir` is inside `work_dir`: `auto_commit` excludes it from the commit (no more phantom `git_head` advance on a zero-work round) and `stash` excludes it from `git stash push -u` (logs no longer vanish). `.evolving/` and agent work are unaffected.
+
+### Removed
+- The inert `smoke_fail_rate` monitor alert (could never fire — superseded by the always-on `config_broken` stop). Monitor now ships 11 detectors.
+
+### Docs
+- `thesis.md`: the stuck-loop defense is described honestly as a notify-level, opt-in-to-auto-stop monitor detector (`anomaly_repetitive_active`), not a default hard-stop; fixed the `stuck_loop_detected` naming drift.
+
+## [0.1.41] - 2026-06-07
+
+### Added
+- New `codewhale` preset — supervise Hmbown/CodeWhale (DeepSeek terminal agent) via `codewhale exec --auto --output-format stream-json`. `agent-runner init --preset codewhale`.
+- New built-in `codewhale_error_detector` plugin — emits `agent_usage_recorded` (model + token counts) from codewhale's stream-json output. Transient-error classification is best-effort (mappable buckets only); auth failures surface via the existing monitor `oauth_fail` detector.
+
 ## [0.1.40] - 2026-05-31
 
 ### Security

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cli-agent-runner
-Version: 0.1.40
+Version: 0.1.42
 Summary: Restart-on-exit supervisor for autonomous CLI agents
 Project-URL: Homepage, https://github.com/wan9yu/cli-agent-runner
 Project-URL: Documentation, https://github.com/wan9yu/cli-agent-runner#readme
@@ -49,7 +49,7 @@ full disks, runaway memory.
 
 ```
 ┌──────────────────────────────────────────┐
-│ Layer 3: The Witness (monitor)           │  12 detectors + auto-stop
+│ Layer 3: The Witness (monitor)           │  11 detectors + auto-stop
 ├──────────────────────────────────────────┤
 │ Layer 2: The Loop (serve, ~120 LOC)      │  signal-trapping restart loop
 ├──────────────────────────────────────────┤
@@ -86,14 +86,14 @@ Full walkthrough: [`docs/quickstart.md`](docs/quickstart.md).
 |---|---|
 | `init` / `install` / `uninstall` | `peek` — state snapshot |
 | `start` / `stop` / `kill` / `cancel` | `watch` — peek in a refresh loop |
-| `restart` / `status` | `monitor` — 12 detectors, alerts, auto-stop |
+| `restart` / `status` | `monitor` — 11 detectors, alerts, auto-stop |
 | `round` / `serve` / `upgrade` | `events` — query / stream events.jsonl |
 
 Verb reference: [`docs/commands.md`](docs/commands.md).
 
 ## Defenses (built in)
 
-11 named defenses, structured as data — see `agent-runner peek --select defenses`.
+12 named defenses, structured as data — see `agent-runner peek --select defenses`.
 Each carries the historical incident it codifies and the invariant test that
 guards it. Highlights:
 
@@ -106,7 +106,7 @@ guards it. Highlights:
 
 Full list and rationale: [`docs/architecture.md`](docs/architecture.md).
 
-## Monitor: 12 detectors
+## Monitor: 11 detectors
 
 Notify only: `timeout_rate`, `hung`, `orphan_chain`, `disk_warning`,
 `mem_pressure`, `smoke_fail_rate`, `network_fail`, `rate_limit_active`,

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/README.md

@@ -12,7 +12,7 @@ full disks, runaway memory.
 
 ```
 ┌──────────────────────────────────────────┐
-│ Layer 3: The Witness (monitor)           │  12 detectors + auto-stop
+│ Layer 3: The Witness (monitor)           │  11 detectors + auto-stop
 ├──────────────────────────────────────────┤
 │ Layer 2: The Loop (serve, ~120 LOC)      │  signal-trapping restart loop
 ├──────────────────────────────────────────┤
@@ -49,14 +49,14 @@ Full walkthrough: [`docs/quickstart.md`](docs/quickstart.md).
 |---|---|
 | `init` / `install` / `uninstall` | `peek` — state snapshot |
 | `start` / `stop` / `kill` / `cancel` | `watch` — peek in a refresh loop |
-| `restart` / `status` | `monitor` — 12 detectors, alerts, auto-stop |
+| `restart` / `status` | `monitor` — 11 detectors, alerts, auto-stop |
 | `round` / `serve` / `upgrade` | `events` — query / stream events.jsonl |
 
 Verb reference: [`docs/commands.md`](docs/commands.md).
 
 ## Defenses (built in)
 
-11 named defenses, structured as data — see `agent-runner peek --select defenses`.
+12 named defenses, structured as data — see `agent-runner peek --select defenses`.
 Each carries the historical incident it codifies and the invariant test that
 guards it. Highlights:
 
@@ -69,7 +69,7 @@ guards it. Highlights:
 
 Full list and rationale: [`docs/architecture.md`](docs/architecture.md).
 
-## Monitor: 12 detectors
+## Monitor: 11 detectors
 
 Notify only: `timeout_rate`, `hung`, `orphan_chain`, `disk_warning`,
 `mem_pressure`, `smoke_fail_rate`, `network_fail`, `rate_limit_active`,

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/README.zh.md

@@ -6,7 +6,7 @@
 
 把任意 CLI agent（Claude Code、自研 agent、任何长跑命令）包装成可被
 systemd / launchd 拉起、能被远程观测的服务。**每轮跑完进程退出**，外层
-supervisor 重启 —— 这是核心模式。中间穿插 11 条防御，避开 production 上
+supervisor 重启 —— 这是核心模式。中间穿插 12 条防御，避开 production 上
 最容易翻车的几条路：
 
 - 轮卡死、Tool 调用空转 → 硬墙 timeout
@@ -20,7 +20,7 @@ supervisor 重启 —— 这是核心模式。中间穿插 11 条防御，避开
 
 ```
 ┌──────────────────────────────────────────┐
-│ Layer 3：Witness（monitor）              │  12 个检测器 + 自动停服
+│ Layer 3：Witness（monitor）              │  11 个检测器 + 自动停服
 ├──────────────────────────────────────────┤
 │ Layer 2：Loop（serve，~120 LOC 薄壳）    │  捕获信号，循环拉起 round
 ├──────────────────────────────────────────┤
@@ -63,7 +63,7 @@ agent-runner monitor              # 实时异常检测，OAuth/磁盘 critical
 |---|---|
 | `init` / `install` / `uninstall` | `peek` —— 项目状态快照 |
 | `start` / `stop` / `kill` / `cancel` | `watch` —— peek 在刷新循环里 |
-| `restart` / `status` | `monitor` —— 12 个检测器 + 告警 + 自动停服 |
+| `restart` / `status` | `monitor` —— 11 个检测器 + 告警 + 自动停服 |
 | `round` / `serve` / `upgrade` | `events` —— 查询 / 流式订阅 events.jsonl |
 
 **停服三动词**有清晰的语义分层：
@@ -73,7 +73,7 @@ agent-runner monitor              # 实时异常检测，OAuth/磁盘 critical
 
 动词参考：[`docs/commands.md`](docs/commands.md)。
 
-## 内置防御（11 条）
+## 内置防御（12 条）
 
 防御以数据形式定义在 `agent_runner/defenses.py`，可通过
 `agent-runner peek --select defenses` 直接拿到。每条防御自带：
@@ -95,7 +95,7 @@ agent-runner monitor              # 实时异常检测，OAuth/磁盘 critical
 
 完整列表 + 历史出处：[`docs/architecture.md`](docs/architecture.md)。
 
-## Monitor：12 个检测器
+## Monitor：11 个检测器
 
 **只告警**（warning 级，服务继续跑）：
 `timeout_rate` / `hung` / `orphan_chain` / `disk_warning` /

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/_emit.py

@@ -45,6 +45,29 @@ def emit_max_rounds_reached(log_dir: Path, *, rounds_completed: int, max_rounds:
     emit(log_dir, MAX_ROUNDS_REACHED, rounds_completed=rounds_completed, max_rounds=max_rounds)
 
 
+def emit_config_broken(log_dir: Path, *, reason: str) -> None:
+    """Emit config_broken (serve stopped on a permanent startup-battery failure)."""
+    from agent_runner.events import CONFIG_BROKEN, emit
+
+    emit(log_dir, CONFIG_BROKEN, reason=reason)
+
+
+def emit_crash_loop(log_dir: Path, *, consecutive: int, exit_code: int, log_path: Path) -> None:
+    """Emit crash_loop (serve stopped after consecutive unknown short crashes).
+
+    Captures the failure reason — a redacted tail of the round log — so a
+    recurring unknown crash can later be classified into a transient bucket.
+    """
+    from agent_runner._redact import redact_secrets
+    from agent_runner.events import CRASH_LOOP, emit
+
+    try:
+        reason = redact_secrets(log_path.read_text(errors="replace")[-2000:])
+    except OSError:
+        reason = ""
+    emit(log_dir, CRASH_LOOP, consecutive=consecutive, exit_code=exit_code, reason=reason)
+
+
 def emit_stop_file_detected(
     log_dir: Path, *, stop_file: Path, content: str, rounds_completed: int
 ) -> None:

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.1.40'
-__version_tuple__ = version_tuple = (0, 1, 40)
+__version__ = version = '0.1.42'
+__version_tuple__ = version_tuple = (0, 1, 42)
 
 __commit_id__ = commit_id = None

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/api.py

@@ -18,7 +18,7 @@ import sysconfig
 import time
 from collections.abc import Iterator
 from pathlib import Path
-from typing import Any
+from typing import Any, Literal
 
 from agent_runner import events, lifecycle
 from agent_runner.api_types import (
@@ -45,6 +45,59 @@ from agent_runner.service_unit import (
     serve_unit_filename,
 )
 
+# Exit code for a permanent (no-retry) startup-battery failure. A broken config
+# does not self-heal between rounds, so serve STOPS rather than respawning it
+# forever. 78 = EX_CONFIG (sysexits) — avoids argparse's 2 and the generic 1.
+# Lives here (not runner.py) so serve_cmd can import it from the sanctioned api
+# facade without coupling to runner (runner imports api, not the reverse).
+PERMANENT_CONFIG_EXIT = 78
+
+# Crash-loop circuit breaker (b12). The serve loop escalates the restart delay
+# on consecutive UNKNOWN short crashes (non-zero exit, short duration, no
+# classified transient) and STOPS after CRASH_LOOP_THRESHOLD of them — the Run 6
+# ~100-empty-rounds scar. Recoverable-slow failures (rate limit / 5h quota / 5xx
+# / timeout) are already handled by the transient-error throttle and never reach
+# this path. A clean (exit 0), long, or classified-transient round resets the run.
+CRASH_LOOP_THRESHOLD = 5
+CRASH_LOOP_SHORT_EXIT_S = 60  # mirrors monitor.SHORT_EXIT_THRESHOLD_S
+CRASH_LOOP_MAX_DELAY_S = 1800  # cap the escalating restart delay (30 min)
+
+
+def post_round_decision(
+    *,
+    returncode: int,
+    duration_s: float,
+    throttle_active: bool,
+    consecutive: int,
+    restart_delay_s: int,
+) -> tuple[Literal["config_broken", "crash_loop", "continue"], int, int]:
+    """Restart policy after one round — keeps the serve loop a thin dispatcher.
+
+    Returns ``(action, delay_s, consecutive)`` where action is:
+    - ``"config_broken"`` — permanent startup failure (b18): stop.
+    - ``"crash_loop"`` — CRASH_LOOP_THRESHOLD consecutive unknown short crashes
+      (b12): stop. An unknown short crash is a non-zero, fast exit with no
+      classified transient (rate-limit/5xx/timeout are handled by the throttle).
+    - ``"continue"`` — sleep ``delay_s`` then run the next round.
+
+    A clean (exit 0), long, or transient round resets ``consecutive`` to 0; an
+    unknown short crash escalates the delay (restart × 2ⁿ, capped) until the stop.
+    """
+    if returncode == PERMANENT_CONFIG_EXIT:
+        return ("config_broken", 0, consecutive)
+    unknown_short_crash = (
+        returncode != 0 and duration_s < CRASH_LOOP_SHORT_EXIT_S and not throttle_active
+    )
+    if unknown_short_crash:
+        consecutive += 1
+        if consecutive >= CRASH_LOOP_THRESHOLD:
+            return ("crash_loop", 0, consecutive)
+        delay = min(restart_delay_s * 2**consecutive, CRASH_LOOP_MAX_DELAY_S)
+        return ("continue", delay, consecutive)
+    delay = restart_delay_s if returncode == 0 else restart_delay_s * 2
+    return ("continue", delay, 0)
+
+
 _PROJECT_NAME_RE = re.compile(r"^[A-Za-z0-9._-]+$")
 
 _LINGER_HINT = (
@@ -730,6 +783,8 @@ def check_self_terminated_sentinel(log_dir: Path) -> bool:
 from agent_runner._emit import (  # noqa: E402,F401 — intentional bottom re-export
     emit_agent_usage_recorded,
     emit_anomaly_repetitive_tool,
+    emit_config_broken,
+    emit_crash_loop,
     emit_fresh_eyes_round_triggered,
     emit_max_rounds_reached,
     emit_rate_limit_stop,

cli_agent_runner-0.1.42/agent_runner/builtin_plugins/codewhale.py

@@ -0,0 +1,133 @@
+"""Built-in post_round_hook for codewhale CLI: usage events + transient classifier.
+
+Third built-in plugin (after claude, gemini). Parses codewhale's `exec
+--output-format stream-json` NDJSON stdout tail; emits agent_usage_recorded
+from the terminal metadata record. Transient-error classification is
+best-effort and emits ONLY when an error maps to an existing bucket (like
+gemini): codewhale's exec stdout surfaces a {"type":"error"} record, but the
+only observed case so far is auth failure (oauth_fail territory, not a
+transient bucket), so nothing maps yet -- usage-only today. 429/5xx mapping
+is added when a real rate-limit sample is captured.
+"""
+
+from __future__ import annotations
+
+import json
+import time
+from collections import deque
+from pathlib import Path
+from typing import Any
+
+from agent_runner.api import (
+    emit_agent_usage_recorded,
+    emit_transient_error_detected,
+)
+from agent_runner.builtin_plugins._constants import (
+    _5XX_STATUSES,
+    _BACK_OFF_DEFAULTS,
+    _RAW_CAP,
+    _TAIL_LINES,
+)
+from agent_runner.hooks import HookContext, register_post_round_hook
+
+
+class CodewhaleErrorDetector:
+    """Parse codewhale round log tail; emit usage + transient_error_detected events."""
+
+    name = "codewhale_error_detector"
+
+    def after_round(self, ctx: HookContext, result: Any) -> None:
+        if ctx.agent_binary != "codewhale":
+            return
+        log_path = ctx.agent_log_path
+        if log_path is None or not log_path.exists():
+            return
+        parsed = _parse_codewhale_log(log_path)
+        if parsed.get("transient_error"):
+            emit_transient_error_detected(
+                ctx.log_dir, round_num=ctx.round_num, **parsed["transient_error"]
+            )
+        if parsed.get("usage"):
+            emit_agent_usage_recorded(
+                ctx.log_dir,
+                round_num=ctx.round_num,
+                phase=ctx.phase or "",
+                success=(result.exit_code == 0 and not result.timed_out),
+                **parsed["usage"],
+            )
+
+
+def _parse_codewhale_log(log_path: Path) -> dict[str, Any]:
+    """Scan last _TAIL_LINES of codewhale NDJSON; extract usage from the metadata
+    record; classify any {"type":"error"} that maps to a transient bucket.
+
+    Tolerates non-JSON lines (codewhale prefixes some stdout with terminal
+    escapes) via per-line try/except.
+    """
+    with log_path.open("r", encoding="utf-8", errors="replace") as f:
+        tail = deque(f, maxlen=_TAIL_LINES)
+    metadata: dict | None = None
+    error_event: dict | None = None
+    for line in tail:
+        line = line.strip()
+        if not line:
+            continue
+        try:
+            event = json.loads(line)
+        except json.JSONDecodeError:
+            continue
+        if not isinstance(event, dict):
+            continue
+        etype = event.get("type")
+        if etype == "metadata":
+            metadata = event.get("meta") or {}
+        elif etype == "error":
+            error_event = event
+
+    out: dict[str, Any] = {}
+
+    if metadata:
+        out["usage"] = {
+            "agent": "codewhale",
+            "model": str(metadata.get("model", "unknown")),
+            "input_tokens": int(metadata.get("input_tokens", 0)),
+            "output_tokens": int(metadata.get("output_tokens", 0)),
+            "cached_tokens": 0,  # codewhale exec stdout exposes no cache counts
+            "cost_usd": None,  # codewhale exec stdout exposes no USD
+            "duration_ms": 0,  # not in exec metadata
+        }
+
+    if error_event is not None:
+        classification = _classify_codewhale_error(error_event)
+        if classification:
+            duration = _BACK_OFF_DEFAULTS[classification]
+            out["transient_error"] = {
+                "classification": classification,
+                "agent": "codewhale",
+                "reset_at_epoch": int(time.time() + duration),
+                "raw": str(error_event.get("error", "error"))[:_RAW_CAP],
+            }
+    return out
+
+
+def _classify_codewhale_error(error_event: dict[str, Any]) -> str | None:
+    """Map a codewhale {"type":"error"} record to a transient bucket, or None.
+
+    None means 'not a transient error' (e.g. auth failure -> handled by the
+    monitor's oauth_fail log-scan, not the transient classifier). codewhale's
+    error record currently carries only a free-text 'error' string with no
+    status code; until a real rate-limit/5xx sample is captured we cannot map
+    to rate_limit_model / api_transient_5xx / api_timeout, so we return None.
+    A future revision keys on a numeric status field once observed.
+    """
+    code = error_event.get("code") or error_event.get("status_code")
+    if code == 429:
+        return "rate_limit_model"
+    if code in _5XX_STATUSES:
+        return "api_transient_5xx"
+    if code == 408:
+        return "api_timeout"
+    return None
+
+
+register_post_round_hook(CodewhaleErrorDetector())

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/cli/init_cmd.py

@@ -2,15 +2,27 @@
 
 from __future__ import annotations
 
+import importlib.resources
+
 from agent_runner import api
 from agent_runner.cli.common import emit, fail, work_dir_from_args
 
 
+def _preset_names() -> list[str]:
+    """Discover scaffold presets from the shipped ``agent_runner/presets/*.toml``.
+
+    Derived (not hardcoded) so adding a preset is a single new .toml file — the
+    ``--preset`` choices and validation track the filesystem automatically.
+    """
+    presets = importlib.resources.files("agent_runner.presets")
+    return sorted(p.name[:-5] for p in presets.iterdir() if p.name.endswith(".toml"))
+
+
 def add_parser(sub, parent) -> None:
     p = sub.add_parser("init", parents=[parent], help="Scaffold agent-runner project files")
     p.add_argument(
         "--preset",
-        choices=["claude", "aider", "gemini"],
+        choices=_preset_names(),
         default="claude",
         help="Which agent CLI preset to scaffold (default: claude)",
     )

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/cli/serve_cmd.py

@@ -23,12 +23,15 @@ from agent_runner._throttle import _check_throttle_state
 from agent_runner._throttle import reset_counters as _reset_counters
 from agent_runner.api import (
     check_self_terminated_sentinel,
+    emit_config_broken,
+    emit_crash_loop,
     emit_fresh_eyes_round_triggered,
     emit_max_rounds_reached,
     emit_rate_limit_stop,
     emit_round_substrate_after,
     emit_round_substrate_before,
     emit_stop_file_detected,
+    post_round_decision,
 )
 from agent_runner.cli.common import cfg_from_args
 from agent_runner.hooks import run_serve_startup_hooks
@@ -135,6 +138,7 @@ def cmd(args) -> int:
     stop_file = cfg.runtime.stop_file  # cache: same pattern as effective_max_rounds
     work_dir = cfg.runtime.work_dir
     rounds_completed = 0
+    consecutive_crashes = 0  # b12: consecutive UNKNOWN short crashes (crash-loop breaker)
 
     try:
         pid_file.write(os.getpid())
@@ -197,6 +201,7 @@ def cmd(args) -> int:
                     every_n=cfg.runtime.fresh_eyes_every_n,
                 )
             round_log_path = log_dir / f"round-{round_num}.log"
+            round_started = time.monotonic()
             with round_log_path.open("w") as f:
                 r = subprocess.run(
                     [
@@ -211,6 +216,7 @@ def cmd(args) -> int:
                     stdout=f,
                     stderr=subprocess.STDOUT,
                 )
+            round_duration_s = time.monotonic() - round_started
             atomic_relink(log_dir / ROUND_CURRENT_LINK, round_log_path)
             git_head_after = compute_git_head(work_dir)
             paths_hash_after = compute_paths_hash(work_dir, cfg.runtime.substrate_fingerprint_paths)
@@ -221,13 +227,28 @@ def cmd(args) -> int:
                 paths_hash=paths_hash_after,
             )
             rounds_completed += 1
+            # Restart policy (config_broken / crash_loop / continue) lives in the
+            # tested api.post_round_decision helper so this loop stays thin.
+            action, delay, consecutive_crashes = post_round_decision(
+                returncode=r.returncode,
+                duration_s=round_duration_s,
+                throttle_active=_check_throttle_state(log_dir) is not None,
+                consecutive=consecutive_crashes,
+                restart_delay_s=cfg.runtime.restart_delay_s,
+            )
+            if action == "config_broken":
+                emit_config_broken(log_dir, reason="startup battery permanent failure")
+                break
+            if action == "crash_loop":
+                emit_crash_loop(
+                    log_dir,
+                    consecutive=consecutive_crashes,
+                    exit_code=r.returncode,
+                    log_path=round_log_path,
+                )
+                break
             if args.once or stop["requested"]:
                 break
-            delay = (
-                cfg.runtime.restart_delay_s
-                if r.returncode == 0
-                else cfg.runtime.restart_delay_s * 2
-            )
             time.sleep(delay)
     finally:
         pid_file.unlink()

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/defenses.py

@@ -83,8 +83,18 @@ def catalog(cfg: Config) -> list[Defense]:
         Defense(
             name="startup_smoke_check",
             value="6 checks (config / log_dir / agent_cli / git / prompt_file / prompt_smoke)",
-            codifies="R721 + #446 — _common.md frontmatter caused 4h/123-round silent burn",
-            guarded_by=None,
+            codifies=(
+                "R721 + #446 — _common.md frontmatter caused 4h/123-round silent burn; "
+                "now halts serve (config_broken) instead of respawning a broken config"
+            ),
+            guarded_by=Path("tests/unit/test_serve_config_broken.py"),
+            current_state="active",
+        ),
+        Defense(
+            name="crash_loop_breaker",
+            value="stop after 5 consecutive short crashes; exp-escalating delay",
+            codifies="Run 6 — crashing agent respawned ~100 empty rounds at a fixed 2x delay",
+            guarded_by=Path("tests/unit/test_serve_crash_loop.py"),
             current_state="active",
         ),
         Defense(

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/events.py

@@ -32,6 +32,8 @@ ANOMALY_REPETITIVE_TOOL = "anomaly_repetitive_tool"
 AGENT_NETWORK_BLIP = "agent_network_blip"
 AGENT_SPAWN = "agent_spawn"
 AGENT_USAGE_RECORDED = "agent_usage_recorded"
+CONFIG_BROKEN = "config_broken"
+CRASH_LOOP = "crash_loop"
 DIRTY_COMMIT_FAILED = "dirty_commit_failed"
 DIRTY_DETECTED = "dirty_detected"
 FRESH_EYES_ROUND_TRIGGERED = "fresh_eyes_round_triggered"

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/monitor.py

@@ -49,7 +49,6 @@ KNOWN_ALERT_KINDS: frozenset[str] = frozenset(
         "disk_warning",
         "disk_critical",
         "mem_pressure",
-        "smoke_fail_rate",
         "oauth_fail",
         "network_fail",
         "rate_limit_active",
@@ -265,29 +264,6 @@ def detect_mem_pressure(metrics: list[dict[str, Any]], *, threshold_mb: int = 20
     )
 
 
-def detect_smoke_fail_rate(
-    events: list[dict[str, Any]], *, window: int = 10, threshold: float = 0.1
-) -> Alert | None:
-    ends = [e for e in events if e.get("event") == "round_end"]
-    if len(ends) < window:
-        return None
-    recent_round_nums = [e.get("round_num") for e in ends[-window:]]
-    fails = sum(
-        1
-        for e in events
-        if e.get("event") == "smoke_check_failed" and e.get("round_num") in recent_round_nums
-    )
-    rate = fails / window
-    if rate < threshold:
-        return None
-    return _alert(
-        "smoke_fail_rate",
-        "warning",
-        f"{fails}/{window} recent rounds had smoke_check_failed",
-        {"rate": rate, "threshold": threshold, "hint": "Inspect events.jsonl for failure reasons"},
-    )
-
-
 def detect_oauth_fail(
     events: list[dict[str, Any]],
     log_tails: dict[int, str],
@@ -603,7 +579,6 @@ def run_all_detectors(
         ),
         detect_disk_critical(metrics, threshold_pct=disk_critical_pct),
         detect_mem_pressure(metrics, threshold_mb=mem_avail_min_mb),
-        detect_smoke_fail_rate(events),
         detect_oauth_fail(events, log_tails, patterns=compiled_auth_pats, hint=auth_fail_hint),
         detect_network_fail(events, log_tails),
         detect_rate_limit_active(events, now=now.timestamp()),

cli_agent_runner-0.1.42/agent_runner/presets/codewhale.toml

@@ -0,0 +1,30 @@
+# agent-runner.toml — generated by `agent-runner init --preset codewhale`.
+#
+# Prereqs:
+#   - codewhale installed (ships `codewhale` + `codewhale-tui`; both on PATH):
+#       npm i -g codewhale     (or cargo/brew per CodeWhale docs)
+#   - DEEPSEEK_API_KEY set on the supervisor host (or a key saved via
+#     `codewhale auth set`; resolution order is config > keyring > env)
+#   - work_dir is a git repo
+
+[agent]
+command = ["codewhale", "exec", "--auto", "--output-format", "stream-json"]
+prompt_arg_template = ["{prompt}"]
+name = "codewhale"
+
+[runtime]
+work_dir = "."
+log_dir = "~/.agent-runner/{project}/logs"
+round_timeout_s = 1800
+restart_delay_s = 3
+
+[prompt]
+file = "./prompts/main.md"
+inject_context = true
+
+[vcs]
+dirty_action = "stash"
+stash_idempotency_s = 5
+
+[monitor]
+auth_fail_hint = "Run `codewhale auth status` to inspect provider/credentials, or set DEEPSEEK_API_KEY on the supervisor host."

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/runner.py

@@ -369,7 +369,7 @@ def run_one_round(cfg: Config, *, phase_override: str | None = None) -> RoundRes
                 file=sys.stderr,
             )
             events.emit(log_dir, "smoke_check_failed", reason=f"{r.name}: {r.reason}")
-        sys.exit(1)
+        sys.exit(api.PERMANENT_CONFIG_EXIT)
 
     # Concurrency lock (per-project)
     lock_path = log_dir / "agent-runner.lock"
@@ -521,6 +521,7 @@ def _run_one_round_inner(cfg: Config, *, phase_override: str | None = None) -> R
                 round_num=round_num,
                 phase=phase,
                 idempotency_s=cfg.vcs.stash_idempotency_s,
+                log_dir=cfg.runtime.log_dir,
             )
             if ref is not None:
                 context_store.write_orphan_state(
@@ -546,7 +547,9 @@ def _run_one_round_inner(cfg: Config, *, phase_override: str | None = None) -> R
             # Leave tree dirty for next round; dirty_detected already emitted
             pass
         elif action == "auto_commit":
-            err = vcs_state.try_auto_commit(cfg.runtime.work_dir, round_num, phase)
+            err = vcs_state.try_auto_commit(
+                cfg.runtime.work_dir, round_num, phase, log_dir=cfg.runtime.log_dir
+            )
             if err is not None:
                 events.emit(
                     log_dir,

{cli_agent_runner-0.1.40 → cli_agent_runner-0.1.42}/agent_runner/scaffold.py

@@ -5,8 +5,8 @@ Writes three files into a git repo:
   prompts/main.md        — neutral 8-line placeholder
   .gitignore             — append "logs/" if missing
 
-Available presets ship as package data in `agent_runner/presets/*.toml`.
-Currently: `claude`, `aider`, `gemini`.
+Available presets ship as package data in `agent_runner/presets/*.toml`;
+`agent-runner init --preset <name>` discovers them from that directory.
 
 Optionally commits in one step (default true via the CLI).
 """