hermes/automaton
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Restore archived tasks, fix dashboard scroll-reset, bind ornith, add Playwright smoke test

Browse Source 
- **Restore 82 completed tasks** from tasks/complete/ back to tasks/ top
  level (all <7 days old per the cleanup policy; premature bulk archive
  was fixed).
- **Dashboard: fix scroll-reset on auto-refresh** — renderBoard rebuilds
  the board via innerHTML every 2s, destroying each column-body's
  scrollTop. Now snapshots column-body scrollTop + board.scrollLeft +
  view.scrollTop before rebuild and restores after (matched by
  PHASE_GROUPS index).
- **Dashboard UI additions** (pre-existing unstaged work): approval
  section cards, transition buttons, inline artifact editor (textarea for
  writing missing SPEC/VERDICT/etc from the detail modal).
- **Bind ornith as Implement model** — config.md: Model explicit to
  omlx/Ornith-1.0-35B-4bit-mlx, context window 32768. Interactive
  autopilot already used ornith via opencode default; now explicit.
- **Fix cleanup stub** — automaton-cleanup.sh had a stale --project arg
  pointing at a pytest temp dir (test isolation leak). Rewired to point
  at ~/.automaton.
- **Fix plist-isolation test** — test asserted host plist doesn't exist,
  but a real install creates it. Now snapshots mtime before run, asserts
  unchanged after (only a write during the test counts as bleed).
- **New Playwright smoke test** (tests/test_dashboard_ui.py) — 2 tests:
  board renders tasks, column scroll survives auto-refresh tick.
  Verified the test fails without the scroll fix (scrollTop resets to 0).
  Skipped via importorskip when playwright is absent (main CI stays
  green).
- **Clarify SI loop scope in README** — new-project onboarding section
  documents the framework-scoped self-improvement loop and options
  (leave/pause/create project loop).
- **CHANGELOG** documents all changes including the known model-divergence
  gap (mde tasks marked complete but per-role model binding was never
  implemented).
This commit is contained in:
Lap Tran
2026-06-26 10:05:18 -04:00
parent fe43b9e1fc
commit bc7daf8590
666 changed files with 15994 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_task.py
+24 -24
View File
@@ -26,14 +26,14 @@ def _make_task(tmp_path: Path, name: str, artifacts: dict[str, str]) -> Path:
def test_backlog_state(tmp_path: Path) -> None:
task_dir = _make_task(tmp_path, "backlog-task", {})
state, artifacts = determine_task_state(task_dir)
state, phase_raw, artifacts = determine_task_state(task_dir)
assert state == TaskState.BACKLOG
assert not artifacts
def test_research_state(tmp_path: Path) -> None:
task_dir = _make_task(tmp_path, "research-task", {"SPEC.md": "# Spec"})
state, artifacts = determine_task_state(task_dir)
state, phase_raw, artifacts = determine_task_state(task_dir)
assert state == TaskState.RESEARCH
assert "SPEC.md" in artifacts
@@ -44,7 +44,7 @@ def test_implementation_state(tmp_path: Path) -> None:
"impl-task",
{"SPEC.md": "# Spec", "TEST_PLAN.md": "# Tests", "IMPLEMENTATION.md": "# Impl"},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.IMPLEMENT
@@ -54,7 +54,7 @@ def test_implementation_from_test_plan(tmp_path: Path) -> None:
"impl-test-plan",
{"SPEC.md": "# Spec", "TEST_PLAN.md": "# Tests"},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.TEST_DESIGN
@@ -64,7 +64,7 @@ def test_bug_find_state(tmp_path: Path) -> None:
"bug-task",
{"SPEC.md": "# Spec", "IMPLEMENTATION.md": "# Impl", "BUG_REPORT.md": "# Bugs"},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.BUG_FIND
@@ -79,7 +79,7 @@ def test_adv_bug_find_state(tmp_path: Path) -> None:
"ADVERSARIAL_BUG_REPORT.md": "# Adv",
},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.ADV_BUG_FIND
@@ -89,7 +89,7 @@ def test_done_state(tmp_path: Path) -> None:
"done-task",
{"SPEC.md": "# Spec", "VERDICT.md": "## Status: PASS"},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.DONE
@@ -99,13 +99,13 @@ def test_blocked_state(tmp_path: Path) -> None:
"blocked-task",
{"SPEC.md": "# Spec", "VERDICT.md": "## Status: FAIL"},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.BLOCKED
def test_empty_verdict_is_blocked(tmp_path: Path) -> None:
task_dir = _make_task(tmp_path, "empty-verdict", {"VERDICT.md": ""})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.BLOCKED
@@ -166,43 +166,43 @@ class TestVerdictParsing:
def test_pass_verdict_with_fail_in_findings(self, tmp_path: Path) -> None:
ver = "## Status: PASS\n\nThe previous FAIL finding was resolved."
task_dir = _make_task(tmp_path, "pass-with-fail", {"SPEC.md": "# Spec", "VERDICT.md": ver})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.DONE
def test_pass_verdict_with_needs_review_in_body(self, tmp_path: Path) -> None:
ver = "## Status: PASS\n\nNote: NEEDS_REVIEW was discussed but resolved."
task_dir = _make_task(tmp_path, "pass-with-nr", {"SPEC.md": "# Spec", "VERDICT.md": ver})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.DONE
def test_fail_verdict_structured(self, tmp_path: Path) -> None:
ver = "## Status: FAIL\n\n2 tests PASS, 1 test FAIL."
task_dir = _make_task(tmp_path, "fail-mentions-pass", {"SPEC.md": "# Spec", "VERDICT.md": ver})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.BLOCKED
def test_needs_review_verdict_structured(self, tmp_path: Path) -> None:
ver = "## Status: NEEDS_REVIEW\n\nSome items PASS but need review."
task_dir = _make_task(tmp_path, "nr-mentions-pass", {"SPEC.md": "# Spec", "VERDICT.md": ver})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.BLOCKED
def test_verdict_with_bold_status(self, tmp_path: Path) -> None:
ver = "# Verdict\n\n- **Status**: PASS\n- **Timestamp**: 2025-01-01"
task_dir = _make_task(tmp_path, "bold-status", {"SPEC.md": "# Spec", "VERDICT.md": ver})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.DONE
def test_verdict_no_status_line(self, tmp_path: Path) -> None:
ver = "# Verdict\nEverything looks good, PASS!"
task_dir = _make_task(tmp_path, "no-status-line", {"SPEC.md": "# Spec", "VERDICT.md": ver})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.REFEREE # no structured ## Status: header → ambiguous
def test_verdict_no_status_no_keywords(self, tmp_path: Path) -> None:
ver = "# Verdict\n\nNeeds further discussion."
task_dir = _make_task(tmp_path, "no-status-no-keywords", {"SPEC.md": "# Spec", "VERDICT.md": ver})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.REFEREE
@@ -211,7 +211,7 @@ class TestStateMachineAlignment:
def test_implementation_alone_shows_implement(self, tmp_path: Path) -> None:
task_dir = _make_task(tmp_path, "impl-only", {"IMPLEMENTATION.md": "# Impl"})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.IMPLEMENT
def test_bug_report_without_adversarial(self, tmp_path: Path) -> None:
@@ -219,7 +219,7 @@ class TestStateMachineAlignment:
tmp_path, "bug-only",
{"SPEC.md": "# Spec", "IMPLEMENTATION.md": "# Impl", "BUG_REPORT.md": "# Bugs"},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.BUG_FIND
def test_both_bug_reports_shows_adv_bug_find(self, tmp_path: Path) -> None:
@@ -228,7 +228,7 @@ class TestStateMachineAlignment:
{"SPEC.md": "# Spec", "IMPLEMENTATION.md": "# Impl",
"BUG_REPORT.md": "# Bugs", "ADVERSARIAL_BUG_REPORT.md": "# Adv"},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.ADV_BUG_FIND
def test_adv_bug_report_alone_shows_bug_find(self, tmp_path: Path) -> None:
@@ -237,22 +237,22 @@ class TestStateMachineAlignment:
{"SPEC.md": "# Spec", "IMPLEMENTATION.md": "# Impl",
"ADVERSARIAL_BUG_REPORT.md": "# Adv bugs only"},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.BUG_FIND
def test_spec_alone_shows_research(self, tmp_path: Path) -> None:
task_dir = _make_task(tmp_path, "spec-only", {"SPEC.md": "# Spec"})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.RESEARCH
def test_test_plan_shows_test_design(self, tmp_path: Path) -> None:
task_dir = _make_task(tmp_path, "testplan", {"SPEC.md": "# Spec", "TEST_PLAN.md": "# Tests"})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.TEST_DESIGN
def test_design_with_spec_shows_design(self, tmp_path: Path) -> None:
task_dir = _make_task(tmp_path, "design-spec", {"SPEC.md": "# Spec", "DESIGN.md": "# Design"})
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.DESIGN
def test_doc_review_shows_doc_review(self, tmp_path: Path) -> None:
@@ -262,7 +262,7 @@ class TestStateMachineAlignment:
"BUG_REPORT.md": "# Bugs", "ADVERSARIAL_BUG_REPORT.md": "# Adv",
"DOC_REVIEW.md": "# Docs"},
)
state, _ = determine_task_state(task_dir)
state, phase_raw, _ = determine_task_state(task_dir)
assert state == TaskState.DOC_REVIEW