diff options
Diffstat (limited to '.ai')
| -rw-r--r-- | .ai/metrics/work-the-backlog.jsonl | 6 | ||||
| -rwxr-xr-x | .ai/scripts/cj-remove-block.py | 81 | ||||
| -rw-r--r-- | .ai/scripts/route_recommend.py | 9 | ||||
| -rw-r--r-- | .ai/scripts/tests/test-todo-cleanup.el | 103 | ||||
| -rw-r--r-- | .ai/scripts/tests/test_cj_remove_block.py | 167 | ||||
| -rw-r--r-- | .ai/scripts/tests/test_route_recommend.py | 28 | ||||
| -rw-r--r-- | .ai/scripts/todo-cleanup.el | 34 | ||||
| -rw-r--r-- | .ai/session-context.org | 153 |
8 files changed, 577 insertions, 4 deletions
diff --git a/.ai/metrics/work-the-backlog.jsonl b/.ai/metrics/work-the-backlog.jsonl index f7bb44b..88c6764 100644 --- a/.ai/metrics/work-the-backlog.jsonl +++ b/.ai/metrics/work-the-backlog.jsonl @@ -7,3 +7,9 @@ {"ts":"2026-07-23T23:57:59-05:00","run_id":"711400a5-c6bc-4684-b928-6b818d0d33f2","project":"rulesets","caller":"speedrun","task":"inbox-send two smaller defects","outcome":"implemented-committed","upfront_decision":false,"commit_sha":"a053e9d","review_findings":0} {"ts":"2026-07-24T00:02:14-05:00","run_id":"711400a5-c6bc-4684-b928-6b818d0d33f2","project":"rulesets","caller":"speedrun","task":"lint-org todo-format checkers fire on specs","outcome":"implemented-committed","upfront_decision":true,"commit_sha":"c38bab9","review_findings":0} {"ts":"2026-07-24T00:02:49-05:00","run_id":"711400a5-c6bc-4684-b928-6b818d0d33f2","project":"rulesets","caller":"speedrun","task":"notes.org template four lint flags","outcome":"already-satisfied","defer_reason":"already-satisfied","upfront_decision":false,"commit_sha":"","review_findings":0} +{"ts":"2026-07-24T01:41:14-05:00","run_id":"sentry-fire2-1784875274","project":"rulesets","caller":"loop","task":"cj-remove-block over-deletion + unsafe write","outcome":"implemented-committed","upfront_decision":false,"commit_sha":"17f5d48","review_findings":0} +{"ts":"2026-07-24T01:43:52-05:00","run_id":"sentry-fire2","project":"rulesets","caller":"loop","task":"route_recommend duplicate-name tier downgrade","outcome":"implemented-committed","upfront_decision":false,"commit_sha":"1b0f284","review_findings":0} +{"ts":"2026-07-24T02:38:48-05:00","run_id":"sentry-fire3","project":"rulesets","caller":"loop","task":"audit.bats flaky teardown","outcome":"implemented-committed","upfront_decision":false,"commit_sha":"7f45d4b","review_findings":0} +{"ts":"2026-07-24T03:39:16-05:00","run_id":"sentry-fire4","project":"rulesets","caller":"loop","task":"todo-cleanup missing backup","outcome":"implemented-committed","upfront_decision":false,"commit_sha":"0686784","review_findings":0} +{"ts":"2026-07-24T04:36:09-05:00","run_id":"sentry-fire5","project":"rulesets","caller":"loop","task":"attachment filename sanitization","outcome":"deferred-verify","defer_reason":"needs-deliberation","upfront_decision":false,"commit_sha":"","review_findings":0} +{"ts":"2026-07-24T07:38:47-05:00","run_id":"sentry-fire8","project":"rulesets","caller":"loop","task":"bin/ lint coverage gap","outcome":"implemented-committed","upfront_decision":false,"commit_sha":"f91feef","review_findings":1} diff --git a/.ai/scripts/cj-remove-block.py b/.ai/scripts/cj-remove-block.py index 71c7b3d..d5137a3 100755 --- a/.ai/scripts/cj-remove-block.py +++ b/.ai/scripts/cj-remove-block.py @@ -16,8 +16,12 @@ Companion to the /respond-to-cj-comments skill and to cj-scan.py. from __future__ import annotations import argparse +import os import re +import shutil import sys +import tempfile +from datetime import datetime from pathlib import Path SRC_OPEN_RE = re.compile(r"^\s*#\+begin_src\s+cj:", re.IGNORECASE) @@ -57,12 +61,83 @@ def looks_like_cj_range(lines: list[str], start: int, end: int) -> tuple[bool, s f"Line {end} does not look like a #+end_src closing fence " f"(got: {last[:60]!r})" ) + + # The range must hold exactly ONE block. Checking only the first and last + # lines let a drifted range run from one block's opener to a *later* block's + # closer: validation passed and the removal silently deleted everything + # between, prose and headings included. Drift is the case this check exists + # for, so it has to look inside the range, not just at its ends. + for offset, line in enumerate(lines[start:end - 1], start=start + 1): + if SRC_CLOSE_RE.match(line): + return False, ( + f"Range {start}..{end} covers more than one cj block — " + f"a #+end_src appears at line {offset}, before the range ends. " + f"Re-scan for current line numbers; removing this range would " + f"delete everything between the two blocks." + ) + if SRC_OPEN_RE.match(line): + return False, ( + f"Range {start}..{end} covers more than one cj block — " + f"a second #+begin_src cj: appears at line {offset}. " + f"Re-scan for current line numbers." + ) return True, "" +def _backup(path: Path) -> Path: + """Copy path to /tmp before mutating it, mirroring lint-org.el's convention. + + These are Craig's org files. lint-org.el, the other tool that rewrites them, + leaves a /tmp copy before touching anything; this matches it so a bad edit is + always recoverable without reaching for git (which only reaches the last + commit, losing intra-session work). + """ + stamp = datetime.now().strftime("%Y%m%d-%H%M%S") + base = Path(tempfile.gettempdir()) / f"{path.name}.before-cj-remove.{stamp}" + # Never overwrite an earlier backup. The skill removes several annotations + # in quick succession, so a second-resolution stamp collides and the later + # copy would replace the earlier one with already-mutated content — losing + # the pre-session original the backup exists to preserve. + dest = base + n = 2 + while dest.exists(): + dest = base.with_name(f"{base.name}-{n}") + n += 1 + shutil.copy2(path, dest) + return dest + + +def _atomic_write(path: Path, text: str) -> None: + """Write text to path via a temp sibling and os.replace. + + A bare write_text truncates the target on open, so a mid-write failure left + the org file truncated with no complete copy on disk. Writing a temp sibling + and renaming means the file is either its old content or its new content, + never a partial. + """ + # Follow a symlink to the file it names. os.replace would otherwise swap the + # symlink itself for a regular file, leaving the real target holding the old + # content — the edit silently goes nowhere. Resolving also puts the temp + # sibling on the same filesystem as the real file, which os.replace needs. + path = path.resolve() + fd, tmp = tempfile.mkstemp(dir=path.parent, prefix=f".{path.name}.", suffix=".tmp") + os.close(fd) + tmp_path = Path(tmp) + # Carry the original's permissions across. mkstemp creates 0600, and + # defaulting to the umask instead widened a deliberately-restricted file + # (a 0600 org file came back 0644). + shutil.copymode(path, tmp_path) + try: + tmp_path.write_text(text, encoding="utf-8") + os.replace(tmp_path, path) + except BaseException: + tmp_path.unlink(missing_ok=True) + raise + + def remove_range(path: Path, start: int, end: int) -> None: """Read path, validate range looks like cj content, remove the range, write back.""" - text = path.read_text() + text = path.read_text(encoding="utf-8") had_trailing_newline = text.endswith("\n") lines = text.splitlines(keepends=False) @@ -77,7 +152,9 @@ def remove_range(path: Path, start: int, end: int) -> None: new_text += "\n" elif not new_lines and had_trailing_newline: new_text = "" - path.write_text(new_text) + + _backup(path) + _atomic_write(path, new_text) def main() -> int: diff --git a/.ai/scripts/route_recommend.py b/.ai/scripts/route_recommend.py index 7b36405..12ab132 100644 --- a/.ai/scripts/route_recommend.py +++ b/.ai/scripts/route_recommend.py @@ -71,6 +71,15 @@ def recommend(item: str, projects: list[str]) -> tuple[str | None, str]: if not projects: return (None, "none") + # Collapse identical names first. Projects are addressed by bare basename, so + # two projects sharing one across roots (~/code/notes, ~/projects/notes) arrive + # twice; both literal-match, and the tie test below then read that as ambiguity + # and downgraded a correct strong match to weak. Deduping here rather than in + # discover_destination_names protects every caller of the pure core, not just + # the CLI path. Order-preserving, and it collapses only identical names — two + # *different* projects matching is real ambiguity and still downgrades. + projects = list(dict.fromkeys(projects)) + item_lower = item.lower() item_tokens = _tokens(item) diff --git a/.ai/scripts/tests/test-todo-cleanup.el b/.ai/scripts/tests/test-todo-cleanup.el index 838913f..a92d238 100644 --- a/.ai/scripts/tests/test-todo-cleanup.el +++ b/.ai/scripts/tests/test-todo-cleanup.el @@ -516,6 +516,12 @@ gitignore todo.org, then run `--archive-done' aging with the DEFAULT archive pat .gitignore contents or nil), :archive-ignored (whether git ignores the archive), :archive-exists." (let* ((root (make-temp-file "tc-git-" t)) + ;; Private backup dir: this helper writes a file literally named + ;; todo.org and runs a real (non-check) pass, so without this its + ;; backup lands in the shared temp dir under the exact production + ;; name and is indistinguishable from a real one. + (temporary-file-directory + (file-name-as-directory (make-temp-file "tc-git-bk-" t))) (todo (expand-file-name "todo.org" root)) (archive (expand-file-name "archive/task-archive.org" root)) (gi (expand-file-name ".gitignore" root))) @@ -536,7 +542,8 @@ gitignore todo.org, then run `--archive-done' aging with the DEFAULT archive pat :archive-ignored (eq 0 (call-process "git" nil nil nil "check-ignore" "-q" archive)) :archive-exists (file-readable-p archive))) - (delete-directory root t)))) + (delete-directory root t) + (delete-directory temporary-file-directory t)))) (ert-deftest tc-age-self-protect-gitignores-archive-when-todo-ignored () "When the todo file is gitignored, the aged-out archive is added to .gitignore @@ -1073,3 +1080,97 @@ line) is left untouched — the strip stops at the first non-planning line." (provide 'test-todo-cleanup) ;;; test-todo-cleanup.el ends here + +;;; --------------------------------------------------------------------------- +;;; Backup before mutating (parity with lint-org.el / wrap-org-table.el) +;; +;; todo-cleanup rewrites todo.org in place and left no copy behind, while both +;; sibling org-mutators back up to /tmp first. It is also the one that runs most +;; often (every wrap, every sentry fire). Emacs's own backup does not fire under +;; --batch -q, so there was genuinely no undo short of git. + +(ert-deftest tc-backup-written-before-a-real-mutation () + "A real (non-check) run leaves a copy holding the pre-edit content. + +`temporary-file-directory' is rebound to a private dir for the duration: the +backup name derives from the *file's* basename, and the real todo.org shares +that basename, so a live sentry run writing /tmp/todo.org.before-todo-cleanup.* +would otherwise be indistinguishable from this test's own artifact. The first +version of this test globbed the shared /tmp and passed only until a real run +created one (2026-07-24)." + (let* ((dir (make-temp-file "tc-backup-" t)) + (bdir (file-name-as-directory (make-temp-file "tc-bk-" t))) + (file (expand-file-name "todo.org" dir)) + (before "* P Open Work\n** TODO [#B] parent\n*** DONE a subtask\nCLOSED: [2026-07-01 Tue]\n")) + (unwind-protect + (progn + (with-temp-file file (insert before)) + (let ((tc-check-only nil) + (tc-convert-subtasks t) + (temporary-file-directory bdir)) + (tc-process-file file)) + (let ((backups (file-expand-wildcards + (concat bdir "todo.org.before-todo-cleanup.*")))) + (should backups) + (should (string-match-p + "a subtask" + (with-temp-buffer (insert-file-contents (car backups)) + (buffer-string)))))) + (delete-directory dir t) + (delete-directory bdir t)))) + +(ert-deftest tc-no-backup-in-check-mode () + "--check writes nothing, so it must not leave a backup either. +Uses a private `temporary-file-directory' for the same isolation reason." + (let* ((dir (make-temp-file "tc-backup-" t)) + (bdir (file-name-as-directory (make-temp-file "tc-bk-" t))) + (file (expand-file-name "todo.org" dir))) + (unwind-protect + (progn + (with-temp-file file + (insert "* P Open Work\n** TODO [#B] parent\n*** DONE sub\nCLOSED: [2026-07-01 Tue]\n")) + (let ((tc-check-only t) + (tc-convert-subtasks t) + (temporary-file-directory bdir)) + (tc-process-file file)) + (should-not (file-expand-wildcards + (concat bdir "todo.org.before-todo-cleanup.*")))) + (delete-directory dir t) + (delete-directory bdir t)))) + +(ert-deftest tc-backup-never-overwrites-an-earlier-one () + "Two invocations in the same second must not collapse to one backup. + +open-tasks.org runs --convert-subtasks then --archive-done back to back, each +a sub-second batch run. With a second-resolution stamp and copy-file's +OK-IF-ALREADY-EXISTS, the second invocation overwrote the first's backup with +already-mutated content, so the true pre-session original was unrecoverable — +the exact state the backup exists to preserve (found 2026-07-24 in review)." + (let* ((dir (make-temp-file "tc-collide-" t)) + (bdir (file-name-as-directory (make-temp-file "tc-cbk-" t))) + (file (expand-file-name "todo.org" dir)) + (original (concat "* P Open Work\n** TODO [#B] parent\n*** DONE sub\n" + "CLOSED: [2026-07-01 Tue]\n" + "* P Resolved\n** DONE [#C] old\nCLOSED: [2025-01-01 Wed]\n"))) + (unwind-protect + (progn + (with-temp-file file (insert original)) + ;; Two back-to-back invocations, as the shipped workflow does. + (let ((temporary-file-directory bdir)) + (let ((tc-check-only nil) (tc-convert-subtasks t)) + (tc-process-file file)) + (let ((tc-check-only nil) (tc-convert-subtasks nil) (tc-archive-done t) + (tc-archive-retain-days nil)) + (tc-process-file file))) + (let ((backups (file-expand-wildcards + (concat bdir "todo.org.before-todo-cleanup.*")))) + ;; Both invocations kept their own backup. + (should (= (length backups) 2)) + ;; And one of them still holds the true original. + (should (cl-some (lambda (b) + (string= original + (with-temp-buffer (insert-file-contents b) + (buffer-string)))) + backups)))) + (delete-directory dir t) + (delete-directory bdir t)))) diff --git a/.ai/scripts/tests/test_cj_remove_block.py b/.ai/scripts/tests/test_cj_remove_block.py index 2c8dade..3cdee46 100644 --- a/.ai/scripts/tests/test_cj_remove_block.py +++ b/.ai/scripts/tests/test_cj_remove_block.py @@ -14,6 +14,34 @@ import pytest SCRIPT = Path(__file__).parent.parent / "cj-remove-block.py" +@pytest.fixture(autouse=True) +def isolated_tmpdir(tmp_path, monkeypatch): + """Give every test in this module a private TMPDIR. + + The script backs up to the system temp dir under a name derived from the + edited file's BASENAME. The real todo.org shares that basename, so any test + operating on a fixture named todo.org writes something indistinguishable + from a production backup — and an earlier version of this file globbed the + shared /tmp and unlinked every match, so a routine `make test` destroyed + Craig's real backups (found in review, 2026-07-24). + + Isolating at module scope rather than per-test is deliberate: the same bug + was fixed once in the elisp sibling and left here, so relying on each new + test to remember is exactly how it recurred. Autouse makes it structural. + """ + d = tmp_path / "_tmpdir" + d.mkdir() + # TMPDIR covers subprocess invocations of the script. + monkeypatch.setenv("TMPDIR", str(d)) + # tempfile.gettempdir() caches its answer on first call, so a test that + # loads the module in-process would keep writing to the real /tmp no matter + # what TMPDIR says. Override the cache too — this is the gap that made the + # env-var-only version still leak one backup per suite run. + import tempfile as _tempfile + monkeypatch.setattr(_tempfile, "tempdir", str(d)) + return d + + @pytest.fixture def run_remove(tmp_path): """Write content to a temp org file, run cj-remove-block, return new contents.""" @@ -155,3 +183,142 @@ class TestCjRemoveBlockSafety: err, post_content = run_remove_expecting_failure(original, start=4, end=2) assert err.returncode != 0 assert post_content == original + + +class TestMultiBlockRangeRefused: + """The validation exists to catch a drifted range, but it only checked the + first and last lines of that range. A span from one block's opening fence to + a LATER block's closing fence passed, and the removal silently deleted every + line between — real prose, headings, whole tasks — with a zero exit. Drift is + the skill's normal operating mode (respond-to-cj-comments edits the file as it + processes, and a file under cj review usually holds several blocks), so this + is the exact scenario the check was written for. Reproduced 2026-07-24.""" + + TWO_BLOCKS = ( + "* Alpha\n" + "#+begin_src cj:\n" + "note A\n" + "#+end_src\n" + "KEEP THIS LINE\n" + "* Beta\n" + "#+begin_src cj:\n" + "note B\n" + "#+end_src\n" + ) + + def test_range_spanning_two_blocks_is_refused(self, run_remove_expecting_failure): + # Lines 2..9: block one's opener through block two's closer. + err, content = run_remove_expecting_failure(self.TWO_BLOCKS, 2, 9) + assert err.returncode == 1 + assert "KEEP THIS LINE" in content, "content between the blocks was destroyed" + assert "* Beta" in content, "a heading between the blocks was destroyed" + + def test_refusal_names_the_reason(self, run_remove_expecting_failure): + err, _ = run_remove_expecting_failure(self.TWO_BLOCKS, 2, 9) + assert "more than one" in err.stderr.decode().lower() + + def test_a_correct_single_block_range_still_removes(self, run_remove): + # The fix must not over-tighten: the legitimate range still works. + out = run_remove(self.TWO_BLOCKS, 2, 4) + assert "note A" not in out + assert "KEEP THIS LINE" in out + assert "note B" in out, "the second block must be untouched" + + def test_a_nested_end_src_inside_the_range_is_refused(self, run_remove_expecting_failure): + # Any #+end_src before the final line means the range covers >1 block. + content = ( + "#+begin_src cj:\n" + "a\n" + "#+end_src\n" + "middle\n" + "#+begin_src cj:\n" + "b\n" + "#+end_src\n" + ) + err, after = run_remove_expecting_failure(content, 1, 7) + assert err.returncode == 1 + assert "middle" in after + + +class TestSafeMutation: + """The script rewrites Craig's org files (todo.org, notes.org). It wrote with + a bare write_text, which truncates the target on open, and took no backup — + so a mid-write failure left the file truncated with no copy to recover from. + lint-org.el, the other tool that mutates these files, backs up to a temp dir + first. Match that, and make the write atomic. + + Every test here redirects TMPDIR to a private directory. The backup name + derives from the file's basename, and the real todo.org shares it, so a test + globbing the shared temp dir cannot tell its own artifact from a genuine + backup — and an earlier version of this class globbed /tmp and unlinked every + match, so a routine `make test` destroyed real backups (found in review, + 2026-07-24). Never glob or delete across the shared temp dir.""" + + ONE_BLOCK = "* T\n#+begin_src cj:\nnote\n#+end_src\nkeep\n" + + def test_a_backup_is_written_before_mutating(self, tmp_path): + import subprocess, glob, os + bdir = tmp_path / "bk" + bdir.mkdir() + f = tmp_path / "todo.org" + f.write_text(self.ONE_BLOCK) + subprocess.run( + ["python3", str(SCRIPT), "--file", str(f), "--start", "2", "--end", "4"], + check=True, capture_output=True, + env={**os.environ, "TMPDIR": str(bdir)}, + ) + backups = glob.glob(str(bdir / "todo.org.before-cj-remove.*")) + assert backups, "no backup was written before mutating the org file" + assert "note" in Path(max(backups)).read_text() + + def test_no_partial_file_when_the_write_fails(self, tmp_path, monkeypatch): + import importlib.util + spec = importlib.util.spec_from_file_location("crb", SCRIPT) + mod = importlib.util.module_from_spec(spec) + spec.loader.exec_module(mod) + bdir = tmp_path / "bk" + bdir.mkdir() + monkeypatch.setenv("TMPDIR", str(bdir)) + f = tmp_path / "todo.org" + f.write_text(self.ONE_BLOCK) + def boom(*a, **k): + raise OSError("disk full") + monkeypatch.setattr(mod.os, "replace", boom) + with pytest.raises(OSError): + mod.remove_range(f, 2, 4) + # The original survives intact — no truncation, no partial. + assert f.read_text() == self.ONE_BLOCK + + +class TestBackupNeverOverwrites: + """Same defect class as todo-cleanup's, and more reachable here: the + respond-to-cj-comments skill removes several annotations in quick + succession, so a second-resolution stamp collides and the later backup + overwrote the earlier one with already-mutated content.""" + + TWO_BLOCKS = ( + "* A\n#+begin_src cj:\nfirst\n#+end_src\n" + "* B\n#+begin_src cj:\nsecond\n#+end_src\n" + ) + + def test_consecutive_removals_each_keep_a_backup(self, tmp_path, monkeypatch): + import subprocess, glob + bdir = tmp_path / "bk" + bdir.mkdir() + monkeypatch.setenv("TMPDIR", str(bdir)) + f = tmp_path / "todo.org" + f.write_text(self.TWO_BLOCKS) + original = f.read_text() + # Remove the second block, then the first — back to back, same second. + subprocess.run(["python3", str(SCRIPT), "--file", str(f), + "--start", "6", "--end", "8"], + check=True, capture_output=True, + env={**__import__("os").environ, "TMPDIR": str(bdir)}) + subprocess.run(["python3", str(SCRIPT), "--file", str(f), + "--start", "2", "--end", "4"], + check=True, capture_output=True, + env={**__import__("os").environ, "TMPDIR": str(bdir)}) + backups = glob.glob(str(bdir / "todo.org.before-cj-remove.*")) + assert len(backups) == 2, f"expected 2 backups, got {len(backups)}" + contents = [Path(b).read_text() for b in backups] + assert original in contents, "no backup holds the true original" diff --git a/.ai/scripts/tests/test_route_recommend.py b/.ai/scripts/tests/test_route_recommend.py index acc4755..2ec900a 100644 --- a/.ai/scripts/tests/test_route_recommend.py +++ b/.ai/scripts/tests/test_route_recommend.py @@ -122,3 +122,31 @@ def test_cli_exclude_drops_current_project(tmp_path): r = _run(["--exclude", "foo"], roots=[tmp_path / "projects"], item="fix the foo widget") assert r.returncode == 0 assert r.stdout.strip() == "none" + + +# ---------------------------------------------------------------------- +# Duplicate candidate names +# +# Projects are collapsed to bare basenames, so two projects sharing a basename +# across roots (~/code/notes and ~/projects/notes) appear twice in the candidate +# list. Both literal-match, recommend read len(strong) > 1 as an ambiguous tie, +# and a correct strong match was downgraded to weak. Latent when discovered +# 2026-07-24 (27 projects, 27 distinct basenames) but real. +# ---------------------------------------------------------------------- + +def test_duplicate_candidate_name_keeps_strong_confidence(): + assert rr.recommend("fix the notes thing", ["notes", "other"]) == ("notes", "strong") + # The same name twice must not read as a tie. + assert rr.recommend("fix the notes thing", ["notes", "notes", "other"]) == ("notes", "strong") + + +def test_genuine_ambiguity_still_downgrades(): + # Two DIFFERENT projects both matching is a real tie and stays weak — the + # dedupe must collapse identical names only, never real ambiguity. + dest, conf = rr.recommend("notes and other both", ["notes", "other"]) + assert conf == "weak" + + +def test_duplicates_do_not_change_the_chosen_destination(): + dest, _ = rr.recommend("fix the notes thing", ["notes", "notes"]) + assert dest == "notes" diff --git a/.ai/scripts/todo-cleanup.el b/.ai/scripts/todo-cleanup.el index c4a87de..cb333e2 100644 --- a/.ai/scripts/todo-cleanup.el +++ b/.ai/scripts/todo-cleanup.el @@ -100,6 +100,12 @@ ;; --check-child-priority is the report-only alias for --sync-child-priority ;; --check. +;; Before any modification a backup is copied to +;; /tmp/<basename>.before-todo-cleanup.<YYYYMMDD-HHMMSS> +;; matching lint-org.el and wrap-org-table.el. Skipped under --check, which +;; writes nothing. +;; + (require 'org) (require 'cl-lib) (require 'calendar) @@ -832,9 +838,37 @@ event-log entry, pulling the timestamp from its CLOSED cookie. Honors ;;; --------------------------------------------------------------------------- ;;; Driver + reporting +(defun tc--backup (file) + "Copy FILE to /tmp before any modification. Skipped in --check mode. + +Matches `lint-org.el' and `wrap-org-table.el', the other tools that rewrite +these org files. todo-cleanup runs the most often of the three (every wrap, +every sentry fire), and Emacs's own backup does not fire under --batch -q, so +without this a mechanical rewrite has no undo short of git — which recovers +only to the last commit and loses intra-session work." + (let* ((base (format "%s%s.before-todo-cleanup.%s" + temporary-file-directory + (file-name-nondirectory file) + (format-time-string "%Y%m%d-%H%M%S"))) + (backup base) + (n 2)) + ;; Never overwrite an earlier backup. A second-resolution stamp collides + ;; when two invocations run back to back, which the shipped workflow does + ;; (open-tasks.org runs --convert-subtasks then --archive-done, each a + ;; sub-second batch run). Overwriting there replaces the true pre-session + ;; original with already-mutated content — losing exactly what the backup + ;; exists to preserve. Suffix instead, so every invocation keeps its own. + (while (file-exists-p backup) + (setq backup (format "%s-%d" base n)) + (setq n (1+ n))) + (copy-file file backup nil) + backup)) + (defun tc-process-file (file) (setq tc-current-file (file-name-nondirectory file)) (setq tc-current-dir (file-name-directory (expand-file-name file))) + (unless tc-check-only + (tc--backup file)) (with-current-buffer (find-file-noselect file) (org-mode) (cond diff --git a/.ai/session-context.org b/.ai/session-context.org index e3f539c..d095f80 100644 --- a/.ai/session-context.org +++ b/.ai/session-context.org @@ -6,7 +6,7 @@ ** Active Goal -Sentry armed for the night on =sentry/2026-07-23-ratio=, hourly. Morning teardown is Craig's. +Sentry re-armed for the night 2026-07-24 on =sentry/2026-07-24-ratio=, hourly, with the implement pass ON (=:SENTRY_MAY_IMPLEMENT: yes=). This run implements solo, decision-free tasks and arriving solo work on the branch, never pushing; shared-asset/convention proposals still park. Bug+refactor finding files graded tasks. Every review runs the premise check first (reproduce before judging). Morning teardown + merge is Craig's. Earlier-tonight run (2026-07-24 00:xx) shipped the sentry workflow addition itself (pass 11 refactor finding, pass 12 opt-in implement, the =:SENTRY_MAY_IMPLEMENT:= marker) to main, plus the speedrun (4 solo tasks) and eight parked VERIFYs. ** Decisions @@ -173,6 +173,157 @@ Filed [#A], SCHEDULED today — the only [#A] of the night. The fix is find-not- Two fires' worth of evidence now says bundle-to-bundle propagation is where this repo leaks changes. +** 00:51 — Fire 1 of the 2026-07-24 run (working) — first fire with pass 12 live + +Lock acquired, branch =sentry/2026-07-24-ratio= verified, tree clean outside the spine. Digest: + +- P1 roam pull — ran, already up to date. +- P2 inbox zero — ran, no-op. Inbox at zero (the question-capture proposal was parked during entry). +- P3 triage intake — skipped: no active source surviving the mail/messenger exclusion. +- P4 todo cleanup — ran with real work. =--archive-done= moved three completed speedrun tasks out of Open Work into Resolved; =--convert-subtasks= normalized the tree. Committed. +- P5 task audit — mechanical subset. Staleness 13, back to the pre-speedrun baseline now that the four solo tasks closed. +- P6 working-files hygiene — ran. All =working/= dirs still have open backing VERIFY tasks (the parked proposals). No orphans. +- P7 spec status board — ran. Two READY specs, nothing stuck. +- P8 link integrity — ran. The docs-lifecycle spec still shows its two known prose false positives (=file:→id:= and =keep-file:-links-through-pilot=, bare =file:= tokens org parses as bracketless links). Correctly unaffected by tonight's spec-scoping, since =link-to-local-file= is org-lint's own checker, not a todo-format one. No new findings. +- P9 git health — main level with origin, sentry branch correctly has no upstream, no stale branches. +- P10 prep freshness — skipped: no =daily-prep/=. +- P11 bug and refactor finding — ran, first fire under the widened pass. Rotating area: the cross-project routing scripts (=route_recommend.py=, =broadcast.py=), untouched by the previous six areas. One verified latent bug filed [#D] (below). Refactor note not worth a task: =recommend='s two weak-tier branches collapse to a single =_tiebreak= call, since =_tiebreak= on a one-element list returns that element. Two lines, no behavior change, so it's a digest line rather than backlog noise. +- P12 solo-task implementation — *active this run* (=:SENTRY_MAY_IMPLEMENT: yes=) but a correct no-op: zero eligible tasks. All four open =:solo:= TODOs were completed in tonight's speedrun, so the ready bucket is empty. Nothing to implement, nothing deferred. + +*** The finding + +=route_recommend='s =discover_destination_names= collapses projects to bare basenames, so two projects sharing a basename across roots would both literal-match and read as an ambiguous tie, downgrading a correct strong match to weak. Reproduced by direct probe. Latent rather than live: 27 projects, 27 distinct basenames today. The destination stays right, only the tier is wrong, so the cost is an extra routing prompt. Filed [#D] with the order-preserving dedupe as the fix. + +** 01:33 — Fire 2 (working) — pass 12's first real implementations + +Digest: + +- P1 roam pull — ran, already up to date. +- P2 inbox zero — ran. Project inbox at zero. The roam inbox dropped 9 → 5 (another session filed some); all 5 remaining belong to archsetup or work, none rulesets-claimed, so roam mode is correctly a no-op here. +- P3 triage intake — skipped: no active source. +- P4 todo cleanup — ran, all three checks clean (fire 1 did the archiving). +- P5 task audit — mechanical subset. Staleness 13, flat. +- P6 working-files hygiene — ran. All =working/= dirs still backed by open VERIFYs. +- P7 spec status board — ran. Two READY specs, nothing stuck. +- P8 link integrity — ran. Only the docs-lifecycle spec's two known prose false positives. +- P9 git health — main level with origin, sentry branch correctly upstream-less. +- P10 prep freshness — skipped: no =daily-prep/=. +- P11 bug and refactor finding — rotating area: the cj-comment tooling (=cj-scan.py=, =cj-remove-block.py=). Two findings filed, one of them serious. +- P12 solo-task implementation — *two tasks implemented and committed to the branch* (17f5d48, 1b0f284). Both premise-checked before a line was written. + +*** The serious find: cj-remove-block destroys content + +=looks_like_cj_range= validated only the first and last lines of a range. A span from one cj block's opener to a *later* block's closer passed, and the removal then deleted everything between — prose, headings, whole tasks — silently, exit 0. That is exactly the failure the check exists to prevent, and drift is its normal case, since =respond-to-cj-comments= edits the file while processing and a file under cj review usually holds several blocks. Reproduced on a two-block fixture that lost a heading and two content lines. Filed [#B], then implemented in pass 12 after an independent re-verification on a different fixture shape. + +Same file, second defect fixed alongside: =remove_range= rewrote the org file with a bare =write_text= (truncates on open) and took no backup, so a mid-write failure would leave =todo.org= truncated with nothing to recover from. =lint-org.el= already backs these files up to =/tmp= before mutating; cj-remove-block now matches that and writes atomically. + +*** The measurement lesson, third time tonight + +A full-suite run went red on =audit.bats= test 4. I stashed my changes, saw it pass clean, and had a one-sample A/B pointing straight at my own diff. Re-ran three times with the changes restored and it passed every time. The failure is an intermittent teardown flake (=rm -rf= racing something still writing into a fixture =.git/objects=), not my change, and I nearly filed the wrong cause off a single sample. Filed [#C] with the git-background-gc theory explicitly labelled a lead rather than a verified cause. + +Committed only on a genuinely green re-run, not on the red with a hand-wave. + +** 02:33 — Fire 3 (working) — the flake's cause traced, and my own lead disproved + +Digest: + +- P1 roam pull — ran, already up to date. +- P2 inbox zero — ran, no-op. Project inbox at zero; roam holds 5, none rulesets-claimed. +- P3 triage intake — skipped: no active source. +- P4 todo cleanup — ran. =--archive-done= moved fire 2's two completed tasks to Resolved. Committed. +- P5 task audit — mechanical subset. Staleness 13, flat. +- P6 working-files hygiene — ran, all dirs backed. +- P7 spec status board — ran, two READY, nothing stuck. +- P8 link integrity — ran, only the known docs-lifecycle prose false positives. +- P9 git health — main level with origin, branch upstream-less, nothing stale. +- P10 prep freshness — skipped. +- P11 bug and refactor finding — no new findings. The fire's whole investigative budget went to confirming fire 2's filed flake, which is the honest place for it; a hunt that finds nothing new is a result. +- P12 solo-task implementation — one task implemented and committed (7f45d4b). + +*** Confirming the cause before fixing, and disproving my own lead + +Fire 2 filed the =audit.bats= flaky teardown with a stated theory: =gc.auto='s loose-object threshold. Pass 12's premise check went after that theory rather than the fix, and killed it — a fixture holds five objects against a default threshold of 6700, so that mechanism cannot fire. + +The real cause came from a =GIT_TRACE= run: =git commit= spawns =git maintenance run --auto --quiet --detach= on git 2.55. The commit returns while the detached process is still writing a pack, and teardown's =rm -rf= races it. Every failed run had left a =tmp_pack_*= behind, which is the thread that led there. + +Fix: =maintenance.auto false= plus =gc.auto 0= in the fixture, killing the background writer rather than retrying the delete (a retry loop hides a live process instead of removing it). Validated over 20 consecutive clean runs against a ~1-in-8 baseline, and recorded honestly in the task that 20 clean runs alone would be ~7% likely by luck — the trace is the evidence, the runs confirm. + +This is the second night running where the premise check changed the outcome. Fire 2 it stopped a wrong causation call; here it stopped me implementing a fix for a mechanism that was never operating. Both times the cost of checking was minutes and the cost of not checking would have been a plausible, wrong, committed change. + +** 03:33 — Fire 4 (working) — two hypotheses killed, one real gap closed + +Digest: + +- P1 roam pull — ran, up to date. P2 inbox zero — no-op, both surfaces clean. P3 triage — skipped, no active source. +- P4 todo cleanup — ran. Archived fire 3's completed task to Resolved. Committed. +- P5 task audit — mechanical subset. Staleness 13, flat all night. +- P6 working-files — all dirs backed. P7 spec board — two READY, nothing stuck. P8 link integrity — only the known prose false positives. P9 git health — clean. P10 — skipped, no prep dir. +- P11 bug and refactor finding — rotating area: the org-file mutators, chosen because =cj-remove-block= yielded a serious find in that same class last fire. One gap filed. +- P12 solo-task implementation — one task implemented and committed (0686784). + +*** What the area review actually found, and what it disproved + +The lead was that =todo-cleanup.el= might lose data. It rewrites =todo.org=, creates archive files, and moves subtrees *between* files, which is the shape that bit =cj-remove-block=. Two specific hypotheses, both tested, both wrong: + +- *"A mid-move failure loses a subtree from both files."* No. The order is delete-from-buffer, write-archive, save-todo.org-last, so an archive-write failure aborts before the save. Verified by making the archive directory unwritable: exit 255, =todo.org= byte-identical, content intact. +- *"Errors are swallowed on the mutation path."* No. The only =ignore-errors= in the file wrap =call-process "git"=, never a write. + +What survived was narrower and real: todo-cleanup mutates with *no backup*, while both sibling mutators (=lint-org.el=, =wrap-org-table.el=) copy to =/tmp= first, and =cj-remove-block= joined them last fire. It is also the one that runs most often. Confirmed empirically that Emacs's own backup does not fire under =--batch -q=, so there was genuinely no undo short of git. Filed [#C], then implemented in P12. + +Also checked my own change for regression rather than assuming: a missing input file exits 255 and creates nothing, identical to the pre-change version tested from git. + +*** Running tally on the premise habit + +Three fires, three times it changed the outcome. Fire 2 it stopped a wrong causation call. Fire 3 it disproved my own filed =gc.auto= theory before I could implement against it. Here it killed two data-loss hypotheses before they became tasks, leaving only the gap that was actually there. The pattern is consistent: the cheap check keeps a plausible story from becoming a committed change. + +** 04:33 — Fire 5 (working) — the first real defer, and last fire's fix proving itself + +Digest: + +- P1 roam pull — ran, up to date. P2 inbox zero — no-op, both surfaces clean. P3 triage — skipped, no active source. +- P4 todo cleanup — ran, archived fire 4's completed task. *Confirmed last fire's backup fix working live*: the real =--archive-done= run left =/tmp/todo.org.before-todo-cleanup.20260724-043331=. Dogfooded within an hour of shipping. +- P5 task audit — staleness 13, flat all night. P6 working-files — all backed. P7 spec board — two READY. P8 link integrity — only the known prose false positives. P9 git health — clean. P10 — skipped. +- P11 bug and refactor finding — rotating area: the attachment/email handlers, chosen because they parse genuinely untrusted input, unlike every internal-tooling area covered so far. One finding filed. +- P12 solo-task implementation — *deferred*, and correctly. First defer of the run. + +*** The find: attachment filenames are partly sanitized, in two different ways + +Both writers derive on-disk names from the =filename= an email declares, and both sanitize incompletely, covering *different* gaps. =eml-view= cleans the name but interpolates the extension raw. =gmail-fetch='s =safe_filename= handles path separators and leading =..= and nothing else. Probed both with the same adversarial set: a =; rm -rf ~= extension survives in both, a literal newline survives in both, a 300-character extension produces a 314-character filename in both. + +Two things I checked so this doesn't get over-graded later. Not RCE — files are written through Python =open=, never a shell. Not path traversal — =splitext= only returns an extension when the last dot follows the last separator, so =ext= can never hold a slash, and the traversal case is neutralized in both scripts. The genuine harms are narrower: a newline in a filename breaks downstream tooling that reads the directory as a line-delimited list, and an unbounded extension blows the 255-byte limit so a crafted attachment aborts extraction. Graded [#C] on that honest read rather than the scarier one. + +I also corrected my own framing mid-investigation. I first read this as the familiar "one sibling hardened, the other not" pattern from the last two fires. It isn't — =safe_filename= is narrower than it looks, and the two scripts are *differently* incomplete. Neither handles newlines or length. + +*** Why pass 12 deferred instead of implementing + +The fix itself is clear, but where the shared sanitizer lives is a design call: a shared helper module (clean, but a new synced template file plus =importlib= gymnastics for kebab-named scripts), duplicate it in both (self-contained, but drift — the exact defect class that produced three separate findings tonight), or patch each in place (smallest diff, permanent divergence). That is deliberation, not a quick factual question, so checklist item 4 fires and the unattended loop defers. Filed the VERIFY with the three options and my lean, and left the task *un-=:solo:=-tagged* so a later run doesn't pick it up and guess. + +This is the checklist discriminating rather than rubber-stamping. Four fires implemented; this one correctly didn't. + +sentry at 05:33: nothing (bug hunt swept =scripts/*.py=; two candidate gaps both disproved — =workflow-integrity.py= *is* gated, its bats runs the real checker against the real canonical tree under =make test=, and =update-skills.py= is an on-demand maintenance command rather than a gate. Recorded so neither gets re-investigated.) + +sentry at 06:33: nothing (bug hunt swept =wrap-org-table.el=, the third org-file mutator and the one with prior history — its load-time dispatch caused the 2026-07-09 corruption. Clean on every probe: the entry-script guard correctly refuses to dispatch when lint-org merely =require='s it, it backs up before writing like its siblings, and it is block-aware — a table inside =#+begin_example= stayed verbatim while a real over-budget table wrapped onto continuation rows with rules. Second consecutive quiet hunt.) + +** 07:33 — Fire 8 (working) — a time bomb I planted four fires ago went off + +Digest: P1-P10 all no-op (roam current, both inboxes clean, todo cleanup clean, staleness 13, working dirs backed, two READY specs, only the known prose link false positives, git clean). P11 found a real coverage gap. P12 implemented it, and the suite caught a regression of my own making. + +*** The find: the only ungated shell in the repo + +=scripts/lint.sh= sweeps =scripts/*.sh=, the language hooks, and the language githooks. It never touched =claude-templates/bin/= — zero references. Those four scripts (=ai=, =agent-text=, =agent-page=, =install-ai=) are the ones =make install= symlinks onto PATH, which makes them the *most* exposed shell in the repo and left them the only shell with no gate over it. All four are clean today, so the guard is a no-op by design; it exists so a future regression can't pass silently. The =ai= launcher was hardened to 42 tests recently and nothing enforced that going forward. + +The test pins *coverage*, not cleanliness: it plants a broken file in each swept location and asserts lint complains, so a location that stops being swept fails the suite rather than passing quietly. + +Surfaced a bigger question I did *not* answer overnight: rulesets ships shellcheck enforcement to consuming projects (the bash bundle's pre-commit, =validate-bash.sh=) and runs none on itself. Filed as a VERIFY, because turning it on would surface the false positives dispositioned earlier this session and choosing between fixing them or adding disable-directives is a preference, not a fact. + +*** The regression: my own test, detonating on schedule + +The full suite went red on the two backup tests I added in fire 4. Not a flake — a time bomb. They globbed =/tmp/todo.org.before-todo-cleanup.*=, but the backup name derives from the file's *basename*, and the real =todo.org= shares it. So a live sentry run's genuine backup was indistinguishable from the test's own artifact, and the check-mode test (which asserts *no* backup exists) failed the moment fire 5's real archive pass created one. + +They passed when written only because no real backup existed yet. Three now sit in =/tmp=. Both tests rebind =temporary-file-directory= to a private dir, and I verified they pass with the real backups present rather than by clearing them. + +Worth naming plainly: I shipped a test whose correctness depended on the state of a shared directory that the code under test writes to in production. That is the "no shared mutable state" rule in =testing.md=, and I broke it while fixing a different durability bug. The suite caught it two fires later, which is the argument for running the full suite every fire rather than only the touched file. + * Sentry approval queue (2026-07-23) Five items. Each names what, why, and the exact edit. Items 2 through 5 are also filed as =VERIFY [#B]= tasks in =todo.org= with prepared diffs under =working/=, so they survive this anchor being archived — say "approve the parked <topic>" for any of them. |