rulesets/.ai/workflows, branch main

feat(workflows): add inbox-zero for routing the roam inbox by project

2026-06-13T18:23:18+00:00

The global roam inbox (~/org/roam/inbox.org) is one shared capture file every project can see, and nothing routed its items to the project that owns them. inbox-zero claims the items prefixed for the current project, files them into that project's todo.org per the process-inbox discipline, and removes them from the shared inbox. Foreign-prefixed and unowned items stay. Every scan reports the total item count plus how many appear related to this project. This v1 is single-destination: it routes by explicit : prefix only. The domain-aware mode that would guess every item's owner and empty the whole inbox in one run is deferred until the multi-project need is concrete. Wired into both session ends so each project touches the inbox twice a session: startup surfaces a read-only count and offer, wrap-up Step 3 sweeps the claimed set before the cleanup scripts so imported tasks ride the wrap commit. INDEX carries the trigger phrases.

feat(workflows): skeptical review gate for inbox change proposals

2026-06-13T01:04:05+00:00

The value gate asks whether to take an inbox item, never whether the proposed change is right. process-inbox gains a Skeptical Review for proposals that change shared assets: a written question battery (fit for all consumers, conflicts elsewhere, effect on common activities, enhancement, simplification, plus at least three change-specific questions), ending in a summary and recommendation Craig approves before the change lands. In a no-approvals session, behavior-changing proposals park instead of self-applying: prepared diff in working/, a [#B] VERIFY carrying the decision package, a reply to the sender. Wording-only fixes proceed, logged. monitor-inbox's act-vs-file rule and protocols.org's act-now line gain the matching exception so all three statements of the rule agree. protocols.org's tables picked up the org-table-standard reflow in the same pass. The motivating case is today's spec-decisions handoff. I applied it as-is, and the after-the-fact review surfaced a lost state and a vacuous gate pass the battery would have caught up front.

feat(workflows): SUPERSEDED/CANCELLED decision states + old-model gate

2026-06-13T00:33:12+00:00

A superseded decision now flips to SUPERSEDED (linking its replacement) and a moot one to CANCELLED. Both are done-class via a #+TODO: header the spec template auto-adds, so the [/] cookie counts them resolved and neither blocks implementation-ready. The TODO/DONE pair alone had lost the old State: field's superseded value. spec-review's gate and Ready rubric now read "no decision is still TODO", and a spec still on the retired State: field model fails the gate item until converted. The gate as first written would have vacuously passed old specs, which have no decision tasks at all.

feat(workflows): spec decisions become org TODO/DONE tasks

2026-06-13T00:15:15+00:00

Each spec decision is now an org TODO task that flips to DONE when the decision-maker agrees, with a [/] cookie on the Decisions heading and a Discussion child for disputes. This replaces the inline State: proposed | accepted | superseded field. spec-response folds settled decisions by flipping them to DONE. spec-review's readiness gate and Ready rubric require the cookie to read complete. A spec can't move past draft to implementation-ready while any decision is still TODO. From the .emacs.d handoff 2026-06-12.

chore: drop the Signal triage-intake plugin

2026-06-12T20:49:56+00:00

Remove the triage-intake Signal source plugin and de-list Signal from the engine's plugin enumeration. I'm rebuilding the Signal client (signel + signal-cli) from scratch, so the plugin would scan against an unstable client. The signal MCP server and its README setup stay. Re-add the plugin when the client is stable.

chore: delete the page-signal pager wrapper

2026-06-12T20:26:22+00:00

Remove the page-signal CLI wrapper, its workflow, and the references in INDEX.org, broadcast.org, and mcp/README.org. The signal MCP server stays. It's the two-way path and a separate capability. The pager number had deregistered and the send-only wrapper isn't worth re-registering.

docs(task-audit): add tag-vocabulary enforcement and verify-then-close

2026-06-12T12:30:57+00:00

Two Phase C behaviors, both surfaced auditing an Emacs-config todo.org. Enforce a project's declared closed tag set (strip tags outside it) where the legend marks the set exhaustive, leaving open-vocabulary projects untouched. For a task whose code shipped but awaits a manual or visual check, file that check under the project's manual-testing parent (dedup first) and close the implementation task, rather than letting "done but unverified" linger half-open.

feat(triage): deltas-only sweep summaries and silent telegram dev groups

2026-06-11T23:22:12+00:00

A sweep now reports only what changed: a new invite, a moved or cancelled event, a message needing attention. Unchanged sources get no block. An all-quiet sweep renders as one line. Scan failures keep their loud banner and the suggested-actions line stays when actions are queued. Telegram dev-community group traffic (zed, GNU Emacs, Kitty) is dropped from sweep reports entirely unless Craig asks. Real DMs from known contacts still surface as Action.

feat(workflows): session-harvest monthly promotion-mining pass

2026-06-11T21:53:21+00:00

session-harvest runs a monthly pass over recent session summaries across every AI project and proposes promotion candidates in four lanes: patterns catalog, KB facts, rule refinements, workflow learnings. Capture already happens continuously. This adds the batched review cadence that turns it into curated promotion. The window filter reads each session filename's date prefix instead of mtime. Clones and syncs reset mtime, which let 2025 sessions pass a recency filter. The run also aggregates the KB receipt lines from session summaries, so it doubles as the 30-day KB metrics readout.

fix(triage): correct telegram mark-read verbs and crash guidance

2026-06-11T20:01:53+00:00

The documented mark-read verb telega-chat--mark-read never existed in telega. I replaced it with the verified telega--viewMessages form (plus mentions and reactions), noted that telega-chat-toggle-read toggles and needs an unread guard, and added the delete-join-notice sweep Craig approved (first run deleted 41 chats). The SEGFAULT gotcha now reflects reality: the dockerized server crashes spontaneously (memory corruption, 11 coredumps since 2026-06-09), the verbs were never the trigger, so action batches check the server first and treat a death as retryable.