| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| | |
|
| |
|
|
| |
The SessionStart hook joined host and project with a space ("ratio rulesets"), which reads as two words in the claude.ai/code and mobile session lists. I changed the join to "$host-$project" ("ratio-rulesets") so the title is one token, and updated the three session-title-hook.bats expectations test-first.
|
| | |
|
| |
|
|
|
|
|
|
| |
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 <project>: 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.
|
| |
|
|
|
|
| |
The validate-el hook only put the current project's roots on the load path, so editing an .el file from another project failed Phase 1 byte-compile on free-variable warnings: the file's own sibling modules weren't reachable. I added the edited file's directory and its parent to the load path. For in-project edits both are redundant (already covered by PROJECT_ROOT and its modules dir). They only do work when the file sits outside the current project root.
I left Phase 2's test runner alone. It discovers tests by stem under PROJECT_ROOT/tests, so a cross-project file's tests aren't found regardless of load path.
|
| |
|
|
| |
routing spec
|
| |
|
|
|
|
|
|
| |
All six decisions resolved. The router's input is filed keepers that belong to another project, not raw inbox files (Reading B). That keeps it a separate sub-step from the inbox gate (D1) and distinct from the defer-and-stage router (D5). Transcript routing is deferred to vNext (D4).
I reworked the design to match: the input definition, a candidate-set note bounding the router to session-filed keepers rather than the standing backlog, and Phase 3. The cookie reads [6/6] and the Status moved to ready for review.
The A-vs-B input ambiguity was the root under D1 and D5. Reading B keeps the inbox gate, the router, and defer-and-stage each simple instead of entangling all three.
|
| |
|
|
|
|
|
|
| |
A spec for the optional wrap-up step that routes inbox items (and, vNext, transcripts) to the project they belong to. Three decisions settled from grounding (reuse todo-cleanup's Open Work matcher as the destination anchor, move atomically through one helper, keep cross-project writes visible with a provenance note); three left open for Craig (separate router step vs merged into the inbox sanity check, transcript scope and trigger, reconciling with the defer-and-stage router). Five implementation phases, acceptance criteria, readiness dimensions.
Status stays draft while decisions are open. The todo task moves to DOING and links the spec.
From the archsetup handoff 2026-06-13.
|
| |
|
|
|
|
| |
A wrap-up router that surfaces outstanding inbox items, recommends a destination project for each, and batch-moves task items into that project's todo.org, with a parallel transcript-filing step. I captured it as a design source and filed a spec-bound feature task rather than building it now: the work clears the spec bar, with design uncertainty (merge or stay separate from the inbox sanity check, recommendation-engine confidence, an unresolved transcript source-location dependency) and overlap with this session's defer-and-stage router to reconcile.
From the archsetup handoff 2026-06-13.
|
| |
|
|
|
|
|
|
| |
A checklist step that is code the user runs (verification setup, bug repro, walkthrough wiring) now goes in an org src block instead of a list bullet, so the user executes it in place with C-c C-c and reads the result in the buffer rather than copy-pasting. Manual actions, prose context, and Expected lines stay as bullets between the blocks.
I scoped the Steps bullet in the same edit: it had said "one action per item" with the command as a bullet, which the new rule would contradict. It now names manual actions as the bullet case and points code steps at the src block.
From the smoke handoff 2026-06-12, worked out on its manual-verification walkthroughs.
|
| |
|
|
|
|
|
|
| |
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.
|
| |
|
|
| |
A literal reading of cross-project.md could see its new propagation section (send synced-file edits to rulesets without being told) as conflicting with the file's stop-and-ask rule. One sentence reconciles them: ask-first governs work inside another project's scope, and an inbox drop is the sanctioned alternative to that, so it needs no confirmation.
|
| |
|
|
|
|
| |
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.
|
| |
|
|
|
|
| |
A downstream edit to a rulesets-owned synced file (workflows, scripts, rules, protocols.org) is a stopgap the next template sync reverts. cross-project.md now documents the three-step propagation (edit locally, inbox-send the file to rulesets, include an intro note with the why and any companions to reconcile) so agents propagate a synced-file edit without being told.
From the .emacs.d handoff 2026-06-12.
|
| |
|
|
|
|
| |
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.
|
| | |
|
| |
|
|
| |
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.
|
| |
|
|
| |
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.
|
| |
|
|
| |
The wrap runs --archive-done twice (wrap-it-up, then open-tasks.org Phase A). The first pass archives and reports. The second finds nothing and used to print "0 subtree(s) moved", which reads as alarming next to the first pass's diff. Now a real-mode run that moves nothing and skips nothing says nothing. Check mode still previews "0 would move", and a missing-section skip still reports, since those are conditions the caller needs.
|
| |
|
|
|
|
| |
The reported "0 subtree(s) moved while moving" is a second-run artifact, not a defect. open-tasks.org runs --archive-done after wrap-it-up already archived, so the second pass correctly reports 0 next to the first pass's diff. The counter increments inline with every move. The exact pre-archive state reports the right count.
Also drops the page-signal pager VERIFY.
|
| |
|
|
| |
Rename the "Priority and Tag Scheme" section to "Rulesets Priority Scheme" so the repo follows the convention it just documented. Refresh the review dates on the open tasks and drop a processed inbox note.
|
| |
|
|
|
|
| |
Every project's task list now opens with a "[Projectname] Priority Scheme" section declaring both the [#A]-[#D] semantics and the tag vocabulary. The concept already lived in the tooling (task-audit enforces a declared tag set, process-inbox checks for the scheme before filing), but nothing required the section or fixed its name, so a list could leave [#A] and its tags undefined.
The set is declared, not fixed. A project adapts the priorities and tags to its own work. The floor is that both are spelled out.
|
| |
|
|
| |
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.
|
| |
|
|
| |
The archive pass moved four closed subtrees to Resolved while reporting zero moves; the relocation was correct and the reporting defect is filed as a [#D] bug.
|
| | |
|
| |
|
|
| |
The re-review confirmed every disposition with no new high or medium findings: Phase 1.5 stands at Ready with caveats, phases 2-5 stay parked behind the decisions fence. The response is correspondingly small — the accepted editorial rename of the Emacs subsection (its "open issue / blocks readiness" heading outlived the body, which is now an integration contract) and the second-pass note in the dispositions section. The updated review file and its history and task-tracking edits ride along.
|
| | |
|
| | |
|
| |
|
|
| |
mu4e registers its link type in a live Emacs, so batch org-lint parsed [[mu4e:msgid:...]] links as fuzzy heading refs and flagged "Unknown fuzzy location" on links that work interactively. lint-org now registers each type in lo-runtime-link-types as a no-op before linting. org-link-set-parameters merges rather than replaces, so a genuinely loaded mu4e keeps its real parameters.
|
| |
|
|
|
|
| |
The review's top finding was that one Not-ready label hid an implementable slice. Status now splits by arc: Phase 1.5 helper instances are READY WITH CAVEATS (the three-ring gate and the manual drills are binding, and the ai-term.el work is a coordinated .emacs.d handoff with an exact artifact), while phases 2-5 stay NOT READY behind a decisions-required section and a Phase 5 reverification prerequisite that demotes the model table to a recommendation.
The remaining findings hardened the slice: per-ring rollback actions including the half-propagated-sync case, the review's test inventory adopted as normative, a message contract for stale helper files, and explicit roster-unavailable behavior on unsupported platforms. All recommendations accepted except the document split, modified to a dual rubric in one document. The review file and dispositions table ride along.
|
| | |
|
| |
|
|
|
|
| |
The detection and identity subsections were authored under one design and patched under two others. They're now three pieces: the roster as the single detection primitive, two spawn paths (deterministic launcher, startup safety net) sharing the same three steps, and identity plus the role contract, with helper-mode.org named the single home of the helper rules.
Verified ai-term.el's launch mechanics in code: the startup instruction is embedded in the tmux new-session command string, so env injection is a prefix on that string, and the -A flag means one session per project, so the helper path needs its own session and buffer names. Added ai-term recommendations to ride the same handoff (roster-derived badges, agent-exit visibility, one source for opener strings) and reconciled the v0 session-context symlink question with the Phase 1.5 answer.
|
| |
|
|
|
|
| |
The first draft of the Emacs open issue assumed eat/vterm and invented an ai --no-tmux mode for a tmux-less path that doesn't exist. Verified against the actual config: the terminal is ghostel (native emulator over libghostty-vt), and ai-term.el is already the Emacs AI launch surface, creating project-named aiv- tmux sessions with liveness badges and crash recovery.
Emacs-born agents are therefore tmux-parented like shell launches, so detection is uniform across surfaces. The remaining design is integration, not a new surface: ai-term.el's session-create learns the roster, export, and opener steps, the picker gains a [helper] badge, and the launchers share only the agent-roster script since ai-term owns its own session naming and window placement.
|
| |
|
|
|
|
|
|
| |
gating
Two gaps block implementation. Sessions are also born from Emacs terminal buffers, where roster detection works (the scan matches process cwd, and eat/vterm shells are children of emacs) but the deterministic spawn path doesn't exist; the open issue weighs an elisp command against shelling out to ai with a no-tmux mode, leaning to the latter so the logic lives once.
Second, template sync makes "live everywhere" the default failure mode for startup.org changes, so the test strategy gains three-ring gating: bats with sleeper processes and a byte-identical no-op guarantee, a disposable sandbox project for the corruption, orphaned-helper, and raw-launch drills, then a dormant-by-construction pilot through project-scripts before the template-wide release. The Status section carries the readiness checklist and the implementation task is blocked on it.
|
| |
|
|
|
|
| |
The launcher becomes the spawn mechanism: a shell script runs the roster check, assigns the id, and launches with the helper instructions in order, where a model-followed startup instruction can skip a step. The in-session roster check stays as the safety net for raw launches and still splits a live anchor into crashed versus concurrent.
Session-end ordering was unhandled: a helper outliving the primary stranded a dirty worktree, since the helper may not commit and the agent allowed to is gone. The git ban on helpers is concurrency-scoped, so it lifts when the helper finds itself alone at wrap-up and the last agent out closes the door with the full wrap-up. The mirror case pauses too: a primary wrapping with live helpers stops at the commit and asks whether to sweep the helper's in-flight work, wait, or leave closing to the helper.
|
| |
|
|
|
|
| |
A second agent now discovers concurrency itself instead of being told: a stateless process scan (running agent processes, /proc cwd matched within the project root, own ancestry excluded) runs as the first action of every session, before any pull. Alone with no anchor is a fresh session, alone with an anchor is today's crash recovery, and not-alone skips startup and routes to helper-mode.org, the role-contract workflow. The scan also splits the previously ambiguous live-anchor signal into crashed versus concurrent primary.
Verified the signal live with four concurrent agents on this machine. The ai --helper launcher flag drops from mechanism to convenience. Known v1 limits recorded: sessions not running as local processes are invisible to the scan, and the match is process-cwd based.
|
| |
|
|
|
|
| |
Four loss windows the scoped-edit discipline doesn't cover: a primary file-wide hygiene pass silently clobbering a helper's concurrent edit (gate on live session-context.d/ files before any such pass), a new primary misreading helper dirt as leftover mess (surface live helper files at startup), crash recovery for shared-file edits (helpers journal each edit before applying it), and MEMORY.md's anchor-less read-modify-write index (memory writes stay primary-only).
Backstop: every file-wide pass snapshots to /tmp before modifying. lint-org and wrap-org-table already conform; todo-cleanup — the pass that moves whole subtrees — does not, and Phase 1.5 brings it up to the invariant.
|
| |
|
|
| |
The v0 draft covered identity and message targeting for concurrent agents but not spawn mechanics or write-safety for the shared files the session-context split doesn't isolate. I added a section for the motivating case (a second Claude in one project doing lookups and safe task updates): ai --helper spawn with automatic AI_AGENT_ID, a tiered read/write contract where helpers make scoped single-heading org edits and file-wide passes plus all git mutation stay primary-only, light helper startup, and helper wrap-up. Phase 1.5 sequences the slice independently of the runtime-neutral phases 2-6.
|
| | |
|
| | |
|
| | |
|
| |
|
|
|
|
| |
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.
|
| | |
|
| | |
|
| | |
|
| |
|
|
|
|
|
|
| |
Upstream releases fixes worth pulling into the forks (arch-decide, playwright-js, playwright-py) without losing our local modifications. Each fork now has a manifest at upstreams/<name>/ plus a committed baseline snapshot that is the 3-way merge base. scripts/update-skills.py classifies each file's drift and merges to stdout. The command owns per-file confirmation, per-hunk conflict prompts, and every target write.
I centralized manifests under upstreams/ instead of per-skill dotfile dirs because arch-decide is now two flat files in commands/ and can't carry one. A "files" map in its manifest handles the upstream rename of SKILL.md to arch-decide.md.
I seeded baselines from today's upstream HEADs, so pre-existing local modifications classify as local-only from here on. git merge-file signals hard errors as exit 255, which subprocess reports as positive. The guard treats anything 128 and up as an error so a binary-file failure isn't misread as a conflict.
|
| |
|
|
|
|
| |
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.
|
| |
|
|
| |
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.
|
| |
|
|
| |
The wide voice-pass table in todo.org reflows to the 120-column standard (the new lint check's first real catch), and the two tasks closed today move to Resolved.
|
| |
|
|
| |
Consumers load lint-org with a bare -l and no load-path flag, so the new require of wrap-org-table failed everywhere outside make test's -L. lint-org now adds its own directory to load-path first. lint-org-cli.bats locks the bare-load contract for both scripts.
|
