chore(release): 0.8.1

.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "bmad-loop",
       "source": "./src/bmad_loop/data/skills",
       "description": "Automation-mode skills driven by the bmad-loop orchestrator: interactive escalation resolution (bmad-loop-resolve) and deferred-work sweep triage (bmad-loop-sweep) — the inner dev primitive (which self-reviews and commits) is the upstream bmad-dev-auto skill",
-      "version": "0.8.0",
+      "version": "0.8.1",
       "author": {
         "name": "pinkyd"
       },

CHANGELOG.md

@@ -5,6 +5,50 @@ All notable changes to `bmad-loop` are documented here. The format is based on
 [Semantic Versioning](https://semver.org/spec/v2.0.0.html). While the project is pre-1.0,
 breaking changes may land in a minor release.
 
+## [0.8.1] — 2026-07-05
+
+### Fixed
+
+- **A session that finished its work but crashed before the run recorded it no longer loses that work
+  to a restart-and-rollback.** The engine now records a completed dev/review session behind a
+  durability barrier _before_ running post-session hooks (usage is folded in afterward as best-effort
+  metadata); on resume it consumes that durably-recorded result straight into verify/decide instead of
+  restarting the attempt from baseline. A raw `KeyboardInterrupt` now records a controlled stop, and
+  replay preserves the attempt/cycle/baseline. (#62, closes #57)
+- **Several narrower resume-replay edges opened by that durability work are closed.** A host death in
+  the post-session window of the _last_ allowed review cycle no longer drops a recorded clean review to
+  a defer; a reconcile early-return no longer persists a pre-reconcile dict that could silently skip a
+  recommended follow-up review; and triage/sweep and labeled plugin-workflow sessions no longer persist
+  large, never-consumed result payloads into `state.json`. (#63)
+- **A dev session is now completed only on a real Stop or window death, never on a terminal artifact
+  glimpsed while the agent window is still alive.** The idle-tick and grace-expiry shortcuts could
+  return "completed" mid-turn and let the run's cleanup kill a working agent, handing the engine
+  half-written state. Both shortcuts are removed, liveness is re-probed immediately before the
+  grace-expiry stall verdict, and a re-driven spec has its stale `## Auto Run Result` section stripped
+  on both re-arm paths so a resolved re-drive can't be misread as its own terminal result. Result scans
+  are now fence-aware, so an `## Auto Run Result` heading quoted inside a fenced code block is never
+  mistaken for a real section (nor destructively stripped). (#53, closes #48 #52)
+- **Long journal fields in the TUI now wrap with a hanging indent instead of spilling back under the
+  timestamp and kind columns.** Each row renders as a fixed-width grid whose fields cell folds within
+  its own column.
+
+### Added
+
+- **Attempt-preserve recovery refs are now bounded.** With `scm.rollback_on_failure` on, auto-rollback
+  parks a failed attempt's committed work under `attempt-preserve/*` and its dirty worktree snapshot
+  under `attempt-preserve-dirty/*`; nothing pruned them, so they grew unbounded. Run start now keeps
+  only the newest `scm.preserve_keep` (default 20, `0` = never prune) per family by committer date and
+  best-effort-deletes the tail — a stuck ref never wedges the ones behind it, and prune failures are
+  journaled but never block the run. (#50 #54, closes #32 #49)
+
+### Changed
+
+- **The adapter shell-dialect seam is now an explicit, documented contract.** `new_window` /
+  `new_parked_window` factor their shell-dialect fragments into overridable hooks (POSIX output stays
+  byte-identical), and the `command` parameter's semantics are pinned in the ABC docstring
+  (shlex-joined argv; operator handling is backend-defined). Relevant only to authors porting the
+  adapter to a non-POSIX backend. (#47 #60)
+
 ## [0.8.0] — 2026-07-03
 
 ### Changed
@@ -945,6 +989,7 @@ enforced in CI.
   implementation phase, driven by a Python control loop with hook-based session transport and
   resumable on-disk run state.
 
+[0.8.1]: https://github.com/bmad-code-org/bmad-loop/releases/tag/v0.8.1
 [0.8.0]: https://github.com/bmad-code-org/bmad-loop/releases/tag/v0.8.0
 [0.7.12]: https://github.com/bmad-code-org/bmad-auto/releases/tag/v0.7.12
 [0.7.11]: https://github.com/bmad-code-org/bmad-auto/releases/tag/v0.7.11

module.yaml

@@ -1,7 +1,7 @@
 code: bmad-loop
 name: BMAD Loop Skills
 description: "Automation-mode skills driven by the bmad-loop orchestrator: interactive escalation resolution (bmad-loop-resolve) and deferred-work sweep triage (bmad-loop-sweep) — the inner dev primitive (which self-reviews and commits) is the upstream bmad-dev-auto skill"
-module_version: 0.8.0
+module_version: 0.8.1
 default_selected: false
 module_greeting: >
   BMAD Loop installed — both the automation skills and the

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "bmad-loop"
-version = "0.8.0"
+version = "0.8.1"
 description = "Deterministic ralph-loop orchestrator for the BMAD implementation phase"
 readme = "README.md"
 license = "MIT"

src/bmad_loop/__init__.py

@@ -6,4 +6,4 @@
 spec files, and the per-run directory under .bmad-loop/runs/.
 """
 
-__version__ = "0.8.0"
+__version__ = "0.8.1"

src/bmad_loop/data/skills/bmad-loop-setup/assets/module.yaml

@@ -1,7 +1,7 @@
 code: bmad-loop
 name: BMAD Loop Skills
 description: "Automation-mode skills driven by the bmad-loop orchestrator: interactive escalation resolution (bmad-loop-resolve) and deferred-work sweep triage (bmad-loop-sweep) — the inner dev primitive (which self-reviews and commits) is the upstream bmad-dev-auto skill"
-module_version: 0.8.0
+module_version: 0.8.1
 default_selected: false
 module_greeting: >
   BMAD Loop installed — both the automation skills and the

src/bmad_loop/tui/widgets.py

@@ -11,6 +11,7 @@
 from pathlib import Path
 from typing import Any
 
+from rich.table import Table
 from rich.text import Text
 from textual.selection import Selection
 from textual.widgets import RichLog, Static, Tree
@@ -166,23 +167,34 @@ def show_run(
 # the journal -> log jump, not the human
 _JOURNAL_HIDDEN_FIELDS = ("ts", "kind", "log_task", "log_pos")
 
+# Row-grid geometry. The fields column's left edge sits at
+# _JOURNAL_CLOCK_WIDTH + _JOURNAL_COL_PAD + _JOURNAL_KIND_WIDTH + _JOURNAL_COL_PAD;
+# the hanging-indent test derives its indent from the same constants so the two
+# can't silently drift apart.
+_JOURNAL_CLOCK_WIDTH = 8
+_JOURNAL_KIND_WIDTH = 24
+_JOURNAL_COL_PAD = 1  # per-column right pad in the row grid
 
-def journal_line(entry: dict[str, Any]) -> Text:
+
+def journal_line(entry: dict[str, Any]) -> Table:
     kind = str(entry.get("kind", "?"))
     style = next((s for sub, s in _JOURNAL_STYLES if sub in kind), "dim")
     ts = entry.get("ts")
     clock = ""
     if isinstance(ts, (int, float)):
         clock = time.strftime("%H:%M:%S", time.localtime(ts))
-    text = Text()
-    text.append(f"{clock:8s} ", style="dim")
-    text.append(f"{kind:24s}", style=style)
     fields = "  ".join(
         f"{k}={_short(v)}" for k, v in entry.items() if k not in _JOURNAL_HIDDEN_FIELDS
     )
-    if fields:
-        text.append(" " + fields)
-    return text
+    # A grid per row so the fields cell folds within its own column (hanging
+    # indent) instead of wrapping back under the clock/kind columns. A long kind
+    # likewise folds within its own column rather than spilling into the fields.
+    grid = Table.grid(padding=(0, _JOURNAL_COL_PAD, 0, 0))
+    grid.add_column(width=_JOURNAL_CLOCK_WIDTH)
+    grid.add_column(width=_JOURNAL_KIND_WIDTH, overflow="fold")
+    grid.add_column(overflow="fold")
+    grid.add_row(Text(clock, style="dim"), Text(kind, style=style), Text(fields))
+    return grid
 
 
 class JournalEntryOption(Option):

tests/test_tui_app.py

@@ -12,6 +12,7 @@
 
 import pytest
 from conftest import install_bmad_config, write_sprint
+from rich.console import Console
 from rich.text import Text
 from textual.geometry import Offset
 from textual.selection import Selection
@@ -39,7 +40,15 @@
     StartSweepModal,
     TextOutputModal,
 )
-from bmad_loop.tui.widgets import RunHeader, SelectableRichLog, SprintTree
+from bmad_loop.tui.widgets import (
+    _JOURNAL_CLOCK_WIDTH,
+    _JOURNAL_COL_PAD,
+    _JOURNAL_KIND_WIDTH,
+    RunHeader,
+    SelectableRichLog,
+    SprintTree,
+    journal_line,
+)
 
 
 def make_run(
@@ -270,7 +279,14 @@ async def test_token_weight_falls_back_to_default(project):
 
 
 def journal_rows(journal: OptionList) -> list[str]:
-    return [str(journal.get_option_at_index(i).prompt) for i in range(journal.option_count)]
+    # Journal prompts are Rich Table grids, so render them to plain text.
+    console = Console(width=400)
+    rows = []
+    for i in range(journal.option_count):
+        with console.capture() as capture:
+            console.print(journal.get_option_at_index(i).prompt)
+        rows.append(capture.get())
+    return rows
 
 
 def log_text(screen: DashboardScreen) -> str:
@@ -296,6 +312,30 @@ def has_entry() -> bool:
         assert any("1-2-search" in row for row in journal_rows(journal))
 
 
+def test_journal_line_wraps_fields_with_hanging_indent():
+    entry = {
+        "ts": 1_750_000_000,
+        "kind": "session-start",
+        "task_id": "6-1-sound-as-information-audio-layer-dev-1",
+        "role": "dev",
+        "prompt": "/bmad-dev-auto 6-1-sound-as-information-audio-layer",
+    }
+    console = Console(width=60)
+    with console.capture() as capture:
+        console.print(journal_line(entry))
+    lines = capture.get().splitlines()
+    assert len(lines) > 1  # fields are long enough to wrap at width 60
+    assert "session-start" in lines[0]
+    # continuation lines stay in the fields column, never spilling back under
+    # the clock/kind columns. The fields column's left edge is derived from the
+    # same width constants journal_line lays the grid out with.
+    indent = _JOURNAL_CLOCK_WIDTH + _JOURNAL_COL_PAD + _JOURNAL_KIND_WIDTH + _JOURNAL_COL_PAD
+    for line in lines[1:]:
+        assert line[:indent] == " " * indent
+    # and the wrapped fields carry real content past the indent
+    assert any(line[indent:].strip() for line in lines[1:])
+
+
 async def test_log_pane_shows_emulated_content(project):
     from test_tui_data import ink_stream