| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
|
|
|
| |
convention
Home proposed two linked cross-project norms and Craig approved rolling them out. Both now ship in the template so every project inherits them.
A new "Colloquialisms and Expansions" section in protocols.org maps Craig's shorthand to a defined action the agent applies without asking. Two seed entries: "put X on the list" appends to a session-scoped Before-Close Queue, and "tell <project> <message>" drops the message in that project's inbox via inbox-send. The set is extensible.
The queue lives under a "* Before-Close Queue" heading in the session anchor, so it resets when the anchor is archived at wrap. Anything that must outlive the session stays a todo.org task. wrap-it-up Step 1 gets a sub-step that works the queue oldest-first before the Summary, so any resulting edits ride the wrap commit, with unfinished items surfaced in the valediction rather than dropped.
I settled three design calls. The reference lives in protocols.org rather than a per-project notes.org (home's local reference), since a synced section is what makes it a shared norm. The queue lives in the session anchor, as home did. The wrap step sits at the front of Step 1 rather than a new half-step, which keeps the "Steps 1 through 5" framing intact. A documentation-integrity bats guards the wiring and the before-the-Summary ordering against a future edit or sync dropping it.
|
| |
|
|
|
|
|
|
| |
The "check inbox/ at every task boundary" rule was prose-only in protocols.org, so it held only as well as the agent remembered it and a handoff could pass a turn unseen. inbox-boundary-check.sh is a Stop hook that backs the rule: when inbox-status -q reports pending items it blocks the yield once and injects the count, so the agent processes them before returning.
It soft-nudges rather than hard-blocks. On the harness re-entry (stop_hook_active: true) the hook steps aside and lets the turn end, so a mid-task pause to ask a question, or an item the agent genuinely can't process, never wedges the session. A hard block would instead push inbox processing ahead of that clarifying question.
The hook self-skips where it doesn't apply: no inbox/ dir, no inbox-status, or a clean inbox each exit 0 silently, so one global hook covers every project with no config. It prefers the project-local .ai/scripts/inbox-status and falls back to one on PATH. It's wired into the Stop array ahead of ai-wrap-teardown in both the tracked settings.json (which the live ~/.claude/settings.json symlinks to) and the documented snippet. bats covers pending, clean, the re-entry step-aside, no-inbox, and the absent-status degrade.
|
| |
|
|
|
|
|
|
| |
I moved the decision logic out of the launcher's I/O-coupled functions so it's unit-testable on plain inputs, the hardening the audit called for. Three pure cores now carry logic that was buried in git and tmux calls: _git_prep_action classifies a repo's state into none/pull/report, _order_windows sorts the window listing, and _match_window_id resolves a name to a window id. _git_is_dirty replaces the staged/unstaged/untracked check that was copy-pasted across three functions.
prep_git_single and auto_pull_if_clean both route their pull-or-report choice through _git_prep_action, so the "never auto-pull a dirty repo" rule lives in one place with its own test instead of two parallel branches. sort_windows keeps its two-pass move (park high, then reassign) but hands the ordering to _order_windows, and find_window_id is now a thin tmux wrapper over _match_window_id.
Each core gets a Normal/Boundary/Error set: the git-prep truth table including diverged and behind-while-dirty, the window ordering including whole-line-not-substring matching. The 42 launcher tests stay green and a live black-box run still prints the right launch command for claude and codex, so the extraction is behavior-neutral. I also ran shfmt (-i 2 -ci) to match the house style the other bin/ scripts follow.
|
| |
|
|
|
|
|
|
| |
Brings the session launcher under characterization tests ahead of the hardening refactor, so the pure-core extractions and footgun fixes land against a green net. The tmux/git-coupled functions can't be reached by running the launcher black-box, so I wrapped dispatch in main() behind a run-vs-sourced guard: run directly it dispatches as before, sourced it exposes the functions to the tests.
The net pins current behavior (record-not-spec) with a Normal/Boundary/Error set per unit: git_status_indicator across no-upstream/ahead/behind/dirty/clean, candidate discovery and filtering, selection parsing, and functional tests over create_window, find_window_id, and sort_windows ordering against a throwaway tmux server. Every tmux call runs on a private socket so nothing touches the live ai session, and the throwaway repos disable git auto-maintenance to dodge the teardown race that flaked rename-ai.
Also cleared the two pre-existing shellcheck warnings on the touched paths: quoted the "@{u}" revspecs (SC1083) and marked the intentionally-literal display tilde (SC2088). Both are behavior-neutral, and the existing runtime tests confirm the launch path is unchanged.
|
| |
|
|
|
|
|
|
|
|
| |
A task phrased as an absence ("find bugs until none remain," "refactor until nothing worthwhile is left," "clean it up") can't be :solo:, because it fails the verifiable-by-the-agent gate. Absence isn't falsifiable, so "done" is a judgment call, which is what :solo: forbids. This kept surfacing (the ai-launcher-hardening task is the live case) with no written recipe for fixing it.
todo-format.md gains a subsection, right after the :solo:/:quick: definitions, on converting a fuzzy goal into a measurable one: bound the surface (enumerate the units, that's the done-set), net the behavior with characterization tests, disposition every finding (fixed / filed / declined-with-reason, never "looked and it's fine"), and gate on an objective floor (static-analysis clean, suite green, coverage of the enumerated surface). The qualifying answer becomes a dispositioned report, not a claim of perfection, and the honest limit stays honest: "no visible bugs" means "every enumerated path passes its characterization set and clears the audit." Once a task carries those criteria it can carry :solo:.
work-the-backlog's keystone defer item now names open-ended goals as a specific, recognizable failure of test-writability, so a mistagged :solo: task with no writable acceptance test is deferred and routed to get criteria rather than guessed at.
start-work has the same Justify/Approach gate and wants the same pointer, but its skill lives outside rulesets, so that edit is a follow-up in its home.
|
| |
|
|
|
|
|
|
|
|
|
|
| |
quality sweep
The rule already said "write a characterization test before refactoring" but not what one is or how many to write per unit. Two additions close that.
testing.md's "Adding Tests to Existing Untested Code" now defines a characterization test as recording what the code actually does, not what it should (Feathers' assert-wrong-read-the-real-value recipe), and requires the same Normal/Boundary/Error set as any unit rather than one happy-path capture. The reason is the useful part: on a characterization test the negative and boundary cases are the bug-finders, because untested legacy code is weakest at the empty input and the missing upstream, and pinning what it currently does there writes the wrong behavior down where it becomes a visible bug. A pinned case that turns out to be a bug graduates from recording current behavior to asserting correct behavior. In-unit bugs fall to this set. Composition bugs need a functional test.
The refactor-for-testability section gains the framing that when the untestable code is legacy you're hardening, extracting the pure core is the hardening, not a detour around it. A function you can't characterize without mocking tmux or git can't be refactored safely, so "needs too much mocking" is the signal to reshape it, never a license to skip the boundary and error cases.
code-quality.org's passes claim to preserve behavior, so it now states the precondition that makes that true: on untested scope, a characterization net comes first, or "behavior-preserving" is an assertion the green suite can't actually verify.
|
| |
|
|
|
|
|
|
|
|
| |
Craig wanted a curated "DeepSat Fundamentals" deck: the ~100 most fundamental cards out of the 465-card deepsat.org deck, marked with a second org tag (:fundamental:) so they stay grep-able in the source. Both flashcard-to-anki.py and flashcard-stats.py keyed a card on a heading ending in exactly :drill:, so adding any second tag turned the heading into :fundamental:drill:, which that anchor didn't match. The 100 tagged cards would have silently dropped from the full-deck apkg and been undercounted by stats. That's the passing-gate-skips-your-file failure.
CARD_RE now matches a trailing org tag block, and a heading is a card when drill is among its tags. The other tags ride along as Anki tags next to the section tag. Card bodies are bounded by any L1/L2 heading (HEADING_RE) rather than only a section or a drill heading. flashcard-to-anki.py gains --tag-filter <tag> (emit only cards carrying that org tag, the subset deck) and --guid-salt <s> (a distinct GUID space so the subset imports non-empty instead of colliding with the full deck on GUID and importing empty). No salt is unchanged, so the existing deck's GUIDs and SRS state are untouched. flashcard-stats.py gets the same CARD_RE/HEADING_RE broadening plus a drill-membership guard.
This is the rulesets-canonical reconcile of a stopgap the work project ran locally. I re-derived it against the current canonical rather than copying the preserved files, which predate the #+TITLE deck-name fix (060a938) and would have reverted it.
parse()'s third element is now the Anki-tag list rather than a single tag string. Only build() and the tests consumed it. The existing parse tests move to the list contract, and new tests cover multi-tag parsing, --tag-filter, the guid salt, and the stats count. A bats case guards that a :fundamental:drill: card still counts. The full deck's real 465/100 check needs the work deck and isn't runnable here. Verified end to end instead on a synthetic multi-tag deck (2 cards, --tag-filter fundamental returns 1) through the real genanki path.
|
| |
|
|
|
|
|
|
|
|
| |
The flashcard pipeline was one-directional (org-drill to apkg). A deck curated on the phone, or an orphaned apkg whose org source was never saved, had no way back into the org source of truth. apkg-to-orgdrill.py closes the loop.
An apkg is a zip holding an Anki sqlite collection, so reading it needs no third-party library: stdlib zipfile + sqlite3. genanki is only needed to write apkgs, not read them, so the converter has no runtime deps. It mirrors flashcard-to-anki.py inverted: deck name to #+TITLE, note Front to the ** heading, note Back HTML to the body (<br> to newlines, entities unescaped, the answer <hr> stripped), the note tag to a * section, and a fresh :ID: UUID per card so the output is org-drill-valid.
The entity unescape runs in the order that inverts escape_html, which escaped & first, so & is unescaped last here. Otherwise a literally-escaped < in the source would wrongly collapse to <. Only Front/Back note types convert; a cloze or other model is skipped with a warning rather than silently dropped, and a note referencing media is flagged since the org side has no media path.
17 tests cover the HTML-to-org conversion, the apkg read (single and multiple decks, Default-deck exclusion, non-basic skip, .anki2 vs .anki21, media flag), the org emission, and errors. The round-trip test closes the loop through flashcard-to-anki.py's own parse(): a known org source becomes an apkg fixture, converts back, and the recovered (front, back, tag) tuples match the original. Verified end to end against a real genanki-produced apkg too.
|
| |
|
|
|
|
|
|
| |
The sentry live trial surfaced this. A sentry inbox-zero pass running from the work project parked the whole 19-item roam inbox as a cross-project boundary crossing and refused to tidy it unattended, reading knowledge-base.md's work-denylist as "don't touch roam from work."
That over-reads the rule. The denylist is a confidentiality guard on one thing: promoting a durable fact into a new agents/ node, so work-confidential material stays out of the personal cross-machine store. Roam is a shared resource, not another project's product scope. Reading it and tidying the shared roam inbox are housekeeping any project may do, work included.
knowledge-base.md gains a "Scope of the denylist" paragraph stating that and naming the mis-park as the error it closes. sentry.org's inbox-zero pass and inbox.org's roam mode each get a one-line note pointing at the rule, so a future agent doesn't re-derive the refusal. Only durable-node promotion stays work-denylisted.
|
| |
|
|
|
|
|
|
|
|
| |
Phase 3 of the sentry supervisor: reconcile the existing roam writers and wrap-up so sentry's locks actually guard something, and its shutdown has one enforced entry point.
The roam-write lock only helps if every roam writer takes it, so both writers now do. knowledge-base.md's write recipe and inbox.org core §5 acquire the roam-write lock around their edit and trigger roam-sync instead of committing themselves. That closes a gap the one-git-owner rule already implied but the KB recipe still violated: the recipe told agents to run git add -A && commit && push against a tree that's chronically dirty from live captures, which could sweep an in-flight capture into a stray commit. roam-sync stays the roam repo's only committer. Agents edit-plus-trigger under the lock, and roam-sync.sh's header now states that contract instead of the old "agents commit inline" note.
Both writers degrade as the spec settled: an absent agent-lock proceeds unlocked (today's behavior), and only a present helper reporting the lock busy after its bounded wait defers or surfaces.
wrap-it-up.org gains a Step 0 that refuses while sentry is live. It checks the single-runner lock and points at "stop sentry" rather than archiving the anchor and tearing down the buffer under a still-firing loop. Both files derive the lock name the same way (sentry-<repo-basename>), so the guard and the engine agree. triage-intake.org notes that it also runs as sentry's triage pass under the no-approvals contract, with its trigger phrases unchanged.
|
| |
|
|
|
|
|
|
|
|
| |
Phase 2 of the sentry supervisor. sentry.org is the engine: an interval loop (default hourly) that walks a fixed pass list (roam pull, inbox zero, triage, todo cleanup, task audit, working-files hygiene, spec board, link integrity, git health, prep freshness) and commits each writing pass to a throwaway sentry/<date>-<host> branch. Nothing pushes. The morning teardown (review, squash-merge, delete) stays Craig's.
The file owns the whole engine: the :COMMIT_AUTONOMY: entry ticket, the interactive entry gates (clean tree, green suite, prior-branch check, ff-only reconcile) that run with Craig present, the single-runner and roam-write locks via agent-lock, the probe-work-session-context-commit pass contract, the digest and morning-approval queue, the skip-not-degrade safety model, the conditional fire-end suite, the multi-day stall notification, and the stop-sentry shutdown.
Every one of the spec's ten decisions and twelve review findings is reflected: host-suffixed branch so the two daily drivers don't collide, tmpfs lock homes so a lock never rides roam-sync to the other machine, roam-sync kept as the roam repo's only committer, spine-excluded dirty checks so sentry's own bookkeeping can't trip its safety skip, and the queue-don't-execute rule for every judgment or destructive action.
Phase 3 wires the roam writers (inbox.org, knowledge-base.md) to acquire the roam-write lock and adds the wrap-it-up guard. Until then the engine is documented but the companions don't yet cooperate. INDEX.org lists it under Tasks and planning.
|
| |
|
|
|
|
|
|
|
|
| |
Phase 1 of the sentry supervisor workflow. sentry needs two locks: a single-runner lock so overlapping /loop fires don't stack, and a roam-write lock so agent edits to the shared roam tree serialize. flock can't serve either, because every Bash call an agent makes is its own short-lived shell, so an flock dies with the call that took it.
agent-lock persists the lock on disk between calls. An atomic mkdir is the acquire. A metadata file inside records pid, host, ISO timestamp, and TTL. Staleness is age-based on the meta mtime, so a crashed holder's lock expires instead of wedging every later acquire, and every reclaim surfaces a note rather than clearing silently. refresh re-touches the mtime as a heartbeat, release is idempotent, status reports free/held/stale, path prints the resolved dir. Locks live under XDG_RUNTIME_DIR/agent-locks (tmpfs: host-local, out of every repo, cleared on reboot), with a ~/.cache fallback where no runtime dir exists.
Reclaim claims the stale dir with an atomic rename before removing it, so two acquirers that both see a lock stale can't both win. A plain remove-then-mkdir would let the loser delete the winner's fresh lock and double-acquire, defeating the roam-write lock's purpose.
Nothing calls it yet. 18 bats tests cover fresh win, contention, release, stale reclaim, heartbeat, path resolution, and usage errors.
|
| |
|
|
|
|
|
|
| |
Two batched changes to the todo hygiene tooling.
Dated-seal archiving: --archive-done aging now keeps one month in-file (retain default 7 → 31, named as tc-archive-retain-days-default) and a new --seal renames the working task-archive.org to resolved-YYYY-MM-DD.org beside it, letting the next aging start a fresh working file. Dating the sealed file by the seal run rather than the calendar quarter is what avoids mislabeling a task closed late in a quarter and archived after the boundary. The unparseable-CLOSED case is now explicit in the contract: a keyword-complete task with no readable close date ages out too. The sealed file inherits the todo file's gitignore status.
Planning-line strip: --convert-subtasks now drops the whole planning line when it rewrites a done sub-task to a dated event-log entry, not just the CLOSED cookie. A dated-log heading carries its date in the heading, so an active SCHEDULED/DEADLINE left on it pins the finished entry to the agenda as weeks-overdue forever (org renders any active planning timestamp, keyword or not). New lint-org checker dated-log-heading-active-timestamp backstops any that predate this. todo-format.md's sub-task and VERIFY completion rules gain the strip step.
|
| |
|
|
| |
Added claude-templates/bin/install-ai, a thin launcher that resolves its own path through the symlink chain and execs scripts/install-ai.sh. make install's bin loop symlinks it into ~/.local/bin/install-ai, the same mechanism that links ai and agent-page, so the fresh-project bootstrapper now runs as install-ai from anywhere. The symlink always points at the canonical, so no separate dotfiles copy is needed. Three launcher bats cover the wrapper, including invocation through a symlink from another directory (the case a naive dirname "$0"/.. would break).
|
| |
|
|
|
|
|
|
| |
New stdlib-only upcoming_birthdays.py reads ~/sync/org/contacts.org for :BIRTHDAY: properties and prints a daily-prep block: name, date, days-away, and the age turned when the birth year is known (1900 is the org-contacts unknown-year placeholder, rendered date-only). Birthdays inside 7 days come back flagged so a gift or plan gets prompted. 19 pytest cases cover the window boundaries, leap-day fallback to Feb 28, the placeholder year, and the CLI.
daily-prep gains a Phase A source that runs the script and a Heads-Up line that folds in the block, so contact birthdays the calendar doesn't carry still surface.
Built and tested in the home project. Promoted here because the daily-prep hook lives in this synced workflow and the contacts file is present on every machine.
|
| |
|
|
|
|
| |
Phase C now renders a TASKS / FYI / MISC digest with a two-option close offer. The per-source breakdown and the itemized action menu move to on-request. Phase D becomes the close and runs by default after the digest: file the TASKS items, run mail hygiene on every scanned account without itemized confirmation, advance the sentinel, tear down anything the sweep started. Prose sends under my name and destructive non-mail actions stay gated. The reroute modifier delivers outside-project items to their owners via inbox-send. The stay-open-until-confirmed exit loop is retired. I updated daily-prep's Sub-step 3b to match.
I ratified this in the work project on 2026-07-18 and applied it here as sent from that handoff (inbox 2026-07-18-1730-from-work).
|
| |
|
|
|
|
|
|
| |
The residue probe cut off at before:<anchor-YYYY/MM/DD> while the scan started at after:<anchor-epoch>. Gmail's before:<date> excludes the named day, so the anchor day fell between the two queries. Each sweep then advanced the anchor past that window and never looked back, so an evening anchor hid most of a day for good. That's the exact failure the probe was added on 2026-07-08 to prevent.
The probe now cuts off at the epoch, matching the scan. I hoisted the epoch rule to cover both anchored queries once rather than twice. I scoped it to the anchor windows so the date-slice walk's deliberate day resolution doesn't read as a bug.
home caught it: after acting on 38 messages the probe reported zero while a plain is:unread in:inbox still returned two messages from the anchor day. personal-gmail is the only source pairing an anchored scan with a residue probe, so nothing else needed the fix.
|
| | |
|
| |
|
|
|
|
| |
The meeting recorder switched to lossless FLAC on 2026-07-01, and the transcript workflow's scan globbed only .mkv and .m4a, so a .flac recording was silently never found. FLAC now threads through the audio-only path: found by the scan, transcribed natively by AssemblyAI with no ffmpeg extraction, kept on cleanup, and archived with its own gitignore pattern.
Adopted verbatim from work's handoff (2026-07-14-0105), diff-verified against the canonical.
|
| |
|
|
|
|
| |
Both helpers treated any pipe-led line as a table row, so ASCII art in an example block got mangled into a bordered table (a work file took a 1949-line reformat on 2026-07-09). The scanners now track the open block's type and skip its content. Only the matching end marker closes a block, so a literal end_src quoted inside an example block can't re-expose it.
The deeper cause was wrap-org-table's load-time dispatch: it fired when lint-org merely required the library, running the reformatter over files lint-org was only asked to report on. It now dispatches only when named as the entry script. lint-org's CLI is also report-only by default now. Writes require --fix, and the wrap-up workflow and lint command pass it.
|
| |
|
|
| |
The interactive flow now opens with a runtime picker: claude first (Enter-Enter preserves the old two-keystroke habit), codex labeled as ChatGPT, and one local:<model> line per ollama model, queried live with a short timeout so a dead server just drops those lines. The pick feeds the existing runtime map, then the annotated project multi-select runs as before. --runtime and AI_RUNTIME skip the question, single-directory mode is unchanged, and --print-runtimes exposes the choice list for the two new bats tests.
|
| |
|
|
| |
ai --runtime local now launches codex against the machine's ollama (explicit --local-provider=ollama, model from AI_LOCAL_MODEL, default gpt-oss:120b). Verified end to end with a codex exec completion through the local model. The dependency check probes AGENT_BIN now that AGENT_CMD carries flags. This makes codex-over-ollama the de-facto answer to the runtime spec's first-supported-local-CLI blocker.
|
| |
|
|
| |
The Signal pager reconcile found one pager identity, registered in velox's signal-cli, reachable from other machines only by hand-rolled ssh. agent-page wraps that: direct signal-cli on velox, ssh relay over the tailnet from everywhere else, a desktop-fallback hint when the relay fails, and the UUID target baked in so nobody pages the unregistered phone number again. Four bats tests stub ssh/uname/signal-cli to verify command construction; the real path was verified with a live phone push today. protocols.org's Paging Craig section now teaches both channels (notify for the desk, agent-page for the phone) and demotes signal-mcp to a velox-local nicety; page-me.org, work-the-backlog, and the INDEX carry the same two-channel story. Every project inherits on its next startup sync and make install.
|
| |
|
|
| |
The ai launcher can now start codex sessions: --runtime claude|codex (or AI_RUNTIME), a runtime-to-CLI map with local reserved behind a clear error until the local-model evaluation picks a CLI, and a runtime-aware dependency check. A new --print-launch mode prints the pane launch command without touching tmux or fzf, and is the seam the six new bats tests drive. Both current CLIs take the opening line as a positional prompt, so only the command name varies.
|
| |
|
|
| |
claude-templates/AGENTS.md points any harness at protocols.org, the rules locations, and the /name-to-file resolution rule, and tells it to degrade per each rule's documented fallback instead of skipping gates. make install links it to ~/.codex/AGENTS.md (new CODEX_DIR stanza) and install-ai.sh seeds a project-owned copy at bootstrap, never overwriting an existing one. The rulesets root carries a tracked symlink as dogfood. Five new bats tests cover the link idiom and the seeding. This resolves the generic-instruction-file blocker from the runtime spec, and velox picks up the global link on its next session's make install.
|
| |
|
|
| |
interaction.md gains a Showing Craig Visuals section: EAT renders SendUserFile and inline images as a text line, so visuals open in the browser or imv (per desktop-capture.md), with inline sixel as the quick-glance lane behind a capability gate (patched EAT answering CSI 14 t plus tmux terminal-features sixel, diagnosed 2026-07-13). protocols.org gains the zsh no-word-split gotcha next to the exa alias note. takuzu sent the proposal as inbox handoff 2026-07-11-2137; the sixel findings correct its capability claim.
|
| |
|
|
|
|
| |
task-review-staleness.sh expected a bare 2026-07-09 and treated an org inactive timestamp ([2026-07-09 Thu], the form matching the CREATED:/CLOSED: cookies in the same drawer) as unparseable. The count branch folded that into the stale count, so a freshly-reviewed task reported as never-reviewed, and a full review pass never dropped the startup nudge. Both the bare and bracketed forms now normalize to the ISO date. A value that is neither warns loudly to stderr (file:line:value) and stays out of the count, since a data error shouldn't hide as "never reviewed." task-review.org documents the accepted format.
Tested red/green: 5 new bats cases (bracketed fresh and stale, list-mode sort by real date, malformed warns and is excluded). Full suite 273 ok.
|
| |
|
|
|
|
| |
For a spec whose deliverable is a real UI, a design argued on paper is a guess. New claude-rules/ui-prototyping.md: research the category first, brainstorm the UX in the spec, build ~5 distinct working prototypes over one engine, iterate one to a final, and record a UI decision only once it's been seen working in a prototype. spec-create gains the step for non-trivial-UI specs. spec-review gates on it: research cited, final prototype linked, iterations in history, decisions backed by a prototype. Prototypes live at docs/prototypes/<spec-name>-prototype-<N>.html.
Worked example: archsetup's timer-panel spec and its three prototypes.
|
| |
|
|
|
|
| |
The google-docs MCP listMessages tool caps at maxResults=100 and exposes no pageToken, so an unread pile over 100 truncates silently and every later anchored sweep skips the tail below the cap. That's how a 300+ backlog built up unseen by 2026-07-08. Two Scan-section rules close it: when a scan returns exactly 100, walk the tail in date slices and dedupe by id, and never report resultSizeEstimate as a count. A cheap backlog-residue probe each sweep (before:<anchor>, maxResults=5) surfaces pre-anchor unread loudly, so an anchored "no changes" can't mask a window the scan never saw.
personal-gmail is the only gmail-family plugin here, so it's the only file that changed.
|
| |
|
|
|
|
|
|
|
|
| |
Every org document an agent writes carried `#+AUTHOR: Craig Jennings & Claude`. No template stamps that line. Agents copy it from a neighboring file, so one stray header propagates through everything generated afterward.
My own repos tolerate the co-author line. Employers whose policy is that work product carries employee names alone do not. An `#+AUTHOR:` line survives conversion into docx, a wiki page, or a PDF that reaches a customer.
I rewrote the header to `Craig Jennings` across the workflows, templates, specs, and design docs. The rule now lives in commits.md, so the next generated document starts correct rather than inheriting the mistake.
Archived session logs keep their original headers as a record of what happened. The two Codex-authored design docs keep their byline, because Codex wrote them and relabeling would be a false attribution rather than the removal of one.
|
| |
|
|
|
|
|
|
|
|
| |
Phase A step 3 guarded its template rsync only on whether rulesets' own source was clean, never on whether the project branch was current. When a branch is diverged or behind-and-dirty, Phase A.0 correctly declines to fast-forward, but the rsync then landed templates on the stale committed .ai/ baseline. The diff came out huge (measured against old content) and conflicted once the branch reconciled to upstream's newer templates. home hit it today: a 3-ahead/46-behind divergence produced ~25 files of phantom drift nobody authored.
I added a second guard: after Phase A.0's reconcile, it re-checks git rev-list @{u}...HEAD and skips the rsync when behind>0. It composes with the rulesets-clean guard, so both a stable source and a current branch are required before the sync runs. No-upstream and ahead-only both fall through and sync, which is correct.
It's deliberately not an auto-discard: a legitimate local stopgap in a synced file can't be told from accidental drift by content alone, so prevention is safe where blind cleanup isn't. Phase C's churn safety net still surfaces pre-existing dirt.
home proposed this via inbox handoff.
|
| |
|
|
|
|
| |
Craig's verdict on the all-red page styling: it reads like the system is about to crash. page-me and the work-the-backlog end-of-set page now use notify info --persist, still persistent and audible, never crash-scary. status-check's success and fail notifications keep their types, since a job outcome isn't a page.
The commit also carries the two loop-filed task records and the archive sweep counterpart from earlier tonight.
|
| |
|
|
| |
Two sends in the same minute whose text starts with the same phrase derived identical filenames, and the second silently replaced the first. A message was lost this way in the wild. An existing target now gets a -2/-3 stem suffix, extension preserved, on both the text and file paths. Four red-first tests reproduce the loss with a fixed timestamp so the same-minute case is deterministic.
|
| |
|
|
|
|
| |
Projects were falling behind on templates because somebody sent them a task: an untracked inbox drop read as a dirty tree to the stricter gates. The policy is now stated where the gates live: dirty means tracked modifications only, and untracked or gitignored files never block a template pull, a fast-forward, or a monitoring gate.
The audit found one offender. The inbox monitor's precondition used bare porcelain, counting the very drops it exists to process. It now checks tracked changes only, which is safe because the per-item commit already stages explicitly. The rsync WIP-guard keeps counting untracked files inside the synced source paths on purpose, since a half-written template is exactly the WIP it holds back.
|
| |
|
|
|
|
| |
A tracked or synced doc asserting "this machine is X" is false on every machine but its origin, and an agent trusting it reasons backwards all session. It happened live: a stale "ratio" claim steered a session running on velox. The new rule bans fixed identity claims in tracked/synced docs and requires the runtime derivation instead (uname -n, since the hostname binary is often absent). Describing the fleet stays legal. Claiming the current member doesn't.
startup gained a read-only probe that greps CLAUDE.md and notes.org for the pattern and surfaces hits as a judgment flag, never a block. Fixture-verified under bash and zsh.
|
| |
|
|
|
|
| |
Long autonomous sessions bloat or hit auto-compaction because /clear is a prompt keystroke no tool call can execute. Auto mode closes that gap: after the write-verified checkpoint, the agent derives its own tmux pane, arms self-inject.sh through tmux run-shell -b, and ends the turn so /clear and a resume line land at an idle prompt. The server-owned arm is load-bearing: a detached child of a tool call dies at the turn boundary. The pane must be derived before arming because ancestry detection can't work under the tmux server.
self-inject.sh joins the synced scripts with a six-test bats suite, tmux stubbed at the boundary. work-the-backlog now auto-flushes between tasks when context grows heavy, and its speedrun preset gained the per-item disposition rule: feature-level work gets a spec, unguessable decisions get a VERIFY, well-defined tasks get implemented. The mechanism was proven live in another project's session and its design note is preserved under docs/design/.
|
| |
|
|
|
|
| |
"synthesize backlog metrics" reads the JSONL union across personal projects and computes the per-run rollups, the trends, and the corrections signal (a later revert or fix touching an autonomous commit's files within ~14 days, a flag for review rather than a conviction). It writes one :agent:metrics: KB node linking back to prior synthesis nodes. Work and unknown projects are excluded by the denylist classification and reported per the refusal contract.
The step is read-only over the logs plus the single KB write. It never mutates the JSONL, todo.org, or any project tree.
|
| |
|
|
|
|
| |
One record per task at outcome time, appended to the project's .ai/metrics/work-the-backlog.jsonl. The field table follows the spec, with commit_sha called out as the corrections-signal key and comma-separated when a task decomposes into several commits. A failed append warns in the run summary but never blocks or aborts the run.
I added the "failed" outcome the spec's error-handling section required but its enum missed: a mid-implementation failure leaves the tree working, gets surfaced, and the run continues.
|
| |
|
|
|
|
|
|
| |
The defer checklist gained its filing mechanics. A deferral VERIFY now dedups against an existing sibling before filing, since the deferred task stays TODO and every later run would otherwise re-file. Placement, heading, and body follow the todo conventions.
A quick-question gap routes to the pre-flight Q&A only under the speedrun preset, and only for one-line factual or preference picks. Three or more questions means the task is underspecified and files instead. The data-loss item never routes to the Q&A.
The batch-ask is one message with recommendation-first numbered options, and answers land as dated lines in the task bodies before the run starts. The page fires exactly once, on set-done or cap-hit, via notify --persist.
|
| |
|
|
|
|
| |
The waiver is now a machine-read marker: ":COMMIT_AUTONOMY: yes" in notes.org's Workflow State, with ":LOOP_MAY_COMMIT: yes" as the separate grant for the unattended loop. An absent or non-yes marker reads as no, and the read is a fresh grep each run, never memory. A caller requesting autonomous-commit without the marker degrades to file-only, surfaced in both the run intro and the summary.
I stamped rulesets' own :COMMIT_AUTONOMY: and left :LOOP_MAY_COMMIT: ungranted. Letting the recurring loop commit unattended is a separate trust decision.
|
| |
|
|
|
|
|
|
| |
inbox.org's auto mode regains its "run this batch next?" ask, now chaining into work-the-backlog as an explicit second step after routing: the eligibility query over the queued batch, file-only, paging off, cap 1. Startup and wrap-up still never execute.
The no-approvals speedrun lands as the named preset: an explicit ordered list run under autonomous-commit + always-push + paging-on, every approval front-loaded into the seven-step pre-flight. Any phrase containing "speedrun" routes to the preset, with disambiguation notes in no-approvals.org and the index. The finer Q&A mechanics land with Phase 4.
I scoped the chain's task set to the queued batch rather than all of todo.org. The ask is "run this batch next?", and a batch-yes running an unrelated higher-priority task would be surprising.
|
| |
|
|
|
|
| |
work-the-backlog.org now owns the autonomous execution loop: the mechanical eligibility gate, the four-item defer checklist, the per-task quality bar, and the run-cap kill switch, fed a task set, session mode, and cap by its callers. I stubbed the pre-flight Q&A, waiver read, end-of-set page, and metrics record with pointers to their phases.
inbox.org's auto mode drops its execute step. Per-cycle item 3 routes and queues only, so the loop has one home. This is Phase 1 of the autonomous-batch execution spec.
|
| |
|
|
|
|
|
|
|
|
| |
This closes the build half of the wrap-up routing spec: Phases 2 and 4 here, with the engine and discovery already shipped.
inbox.org's "File as TODO" disposition now runs route_recommend on each keeper and stamps :ROUTE_CANDIDATE: <destination> on strong and weak matches, so the wrap-up router has a candidate set without ever scanning the standing backlog. wrap-it-up.org Step 3 gains the optional router after the inbox sanity check, with the gate-vs-optional split named in the prose: surface the batch with destinations and confidence labels, then go or skip. An empty set stays silent.
The go path is mechanical rather than prose-driven: the new route-batch helper lists candidates read-only, and on go extracts each subtree (children ride along, markers stripped, headings promoted), delivers it via inbox-send for provenance, and removes the local copy only after a successful send, rewriting todo.org per send so a crash never strands an already-sent task locally. Overlapping candidate spans (a tagged child inside a tagged parent) are a loud conflict, left in place with a non-zero exit, because routing either span would silently take the other along.
A 13-test bats suite covers list/backlog exclusion, empty-set silence, delivery with provenance and children, promotion, drawer pruning, the no-todo.org destination, failed-send recovery with the marker intact, the nested-candidate conflict, and duplicate-marker dedupe. cross-project.md notes the router as a sanctioned cross-project write path.
|
| |
|
|
|
|
|
|
| |
The Phase A batch gains a read-only probe that prints one line when a project has an unsorted docs pile (a docs/design/ or stray docs/*-spec.org files) and no :LAST_SPEC_SORT: marker. Phase C surfaces the "run spec-sort" offer when the probe fired and stays silent otherwise.
The stray-root check uses find instead of the spec's compgen sketch: compgen is bash-only and zsh aborts on an unmatched glob, so the original snippet false-negatived on stray root specs under zsh. The spec's snippet is updated with a note, and the probe is fixture-verified in both shells across the four project shapes.
I also fixed startup.org's reference to the encourage-kb-contribution spec's pre-pilot path and sent .emacs.d the convention-live note with the id-index ask.
|
| |
|
|
|
|
|
|
| |
spec-sort is Phase 2 of the docs-lifecycle build. It proposes the sort (spine-predicate classification, an evidence panel per candidate, a conservative keyword proposal) and a human confirms every move with --confirm/--skip. Terminal states need an explicit --reason, recorded in the status history.
--apply is fail-safe. It refuses a dirty worktree, validates then writes from a recorded plan file, names applied and not-applied work with a git restore recovery recipe on mid-apply failure, and exits non-zero on post-apply residue. Moves land in docs/specs/ with the -spec.org suffix, a status heading carrying :ID: and a dated history line, and the two-sequence keyword header. file: links across the project-owned roots are recomputed, including a moved doc's own outbound links. Session archives and synced template paths are reported, never rewritten, with the canonical claude-templates file named. A successful run stamps :LAST_SPEC_SORT: in .ai/notes.org.
The 33-test bats suite is glob-discovered by make test. A dry run against rulesets' own pile matches the expected five candidates.
|
| |
|
|
|
|
| |
Phase 1 of the docs-lifecycle build. claude-rules/docs-lifecycle.md captures the shape: formal-vs-notes location split (docs/specs/ vs docs/design/), an authoritative org-keyword status heading with dated history and an :ID: UUID, the two-sequence keyword header that keeps decision cookies computing, named owners for every transition, and the one-grep status board.
The four workflows each take their piece: spec-create emits into docs/specs/ and stamps DRAFT in the template; spec-review checks location (legacy spots stay reviewable until :LAST_SPEC_SORT: is stamped) and owns the DRAFT-to-READY flip plus the demote path; spec-response owns READY-to-DOING at decomposition, stamps :SPEC_ID: on the build parent, and always emits the flip-to-IMPLEMENTED task; task-audit reconciles DOING specs against their bound parent's keyword.
|
| |
|
|
|
|
| |
Phase 0 of the autonomous-batch (speedrun) build. todo-format.md now carries fixed cross-project definitions: :solo: is the autonomy/eligibility tag (buildable, agent-verifiable, no design deliberation — at most one or two quick upfront-answerable decisions, which the speedrun pre-flight Q&A batches), and :quick: is a ≤30-minute effort hint that never gates eligibility. task-review and task-audit now treat the tag assessment as mandatory — a pass that skips it is incomplete.
task-review's :solo: gate 3 also moves from "no upfront decision" to the no-deliberation form: the stricter wording predated the pre-flight Q&A decision and would have wrongly excluded tasks with a quick answerable question.
|
| |
|
|
|
|
| |
Six checks for specs covering a user-facing panel or control surface: name each list item's source, don't gate immediately-showable data behind a scan, don't ask users to retype discovered values, tense-correct destructive confirmations, review diagnostics/repair affordances as one flow, and make popups visually belong to their launcher. Conditional — non-UI specs skip it.
Promoted from archsetup's Waybar network-panel review (2026-06-30 handoff).
|
| |
|
|
|
|
|
|
| |
sweep-gitignore-tooling.sh decided gitignore-mode with an exact unanchored match on `.ai/`, so a project using the anchored `/.ai/` form was misclassified as track-mode and silently skipped — which left .emacs.d's tracked tooling on a public GitHub mirror until its 2026-06-30 scrub. Both forms now count for mode detection and per-pattern presence, and appended lines follow whichever style the file already uses.
Track-mode projects also get a new check: tracked tooling paths combined with a non-cjennings.net remote draw a loud WARN, since a track-mode repo on a public host is the exposure the convention exists to prevent. The convention itself is now written down in protocols.org: a non-cjennings.net remote means the tooling set is gitignored, a deliberate team-shared config being the only explicit exception, and a private remote is not proof of privacy because a server-side mirror hook republishes invisibly.
From the .emacs.d handoff (2026-06-30 tooling-exposure broadcast).
|
| |
|
|
|
|
| |
A parent whose child tasks are all resolved closes (DONE/CANCELLED + CLOSED) and archives on the next --archive-done; a parent with one or two open children gets those promoted to standalone level-2 tasks first. Carries the leaf-with-notes carve-out (a task whose only descendant is a dated design note is unstarted work, not a finished container — flag NEEDS-USER, never close) and a warning to verify open-child counts against a real subtree scan, not a fragile regex. Depends on --convert-subtasks running first so the counts are accurate.
From the .emacs.d handoff (2026-07-01 task-audit note).
|
