| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
| |
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.
|
| | |
|
| |
|
|
|
|
| |
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 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.
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| |
|
|
| |
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.
|
| |
|
|
|
|
|
|
|
|
| |
Wide org tables overflow the page in exported PDF/docx, and hand-wrapping a cell into continuation rows is tedious and error-prone. The standard existed only as a work-project convention with nothing enforcing it.
claude-rules/org-tables.md carries the generalized standard: 120-column budget measured at render width (a link counts as its visible label and is never split), over-budget cells wrap onto continuation rows, and a rule sits under the header and every logical row.
wrap-org-table.el reflows a table to that shape mechanically. Columns shrink from natural width toward a floor of their widest atomic token, cells wrap link-safe, and rule-delimited continuation groups merge back into their logical row before re-wrapping, which makes the reflow idempotent. A table whose floors still exceed the budget reflows best-effort and stays flagged for restructuring.
lint-org.el gains an org-table-standard judgment check: width overruns and missing rules surface during the sweep with a pointer to the helper. Conformant wrapped tables don't false-flag, since the check reuses the helper's continuation-group reading. The check is judgment-only by design: reflowing is a visible layout change the sweep shouldn't make silently.
|
| |
|
|
|
|
| |
session-clear-resume.sh shipped 2026-06-02 with its settings.json entry, but make install didn't cover hooks and nothing re-ran install-hooks, so the symlink only existed on machines that had linked it by hand. Everywhere else the hook errored silently on every /clear.
make install now links DEFAULT_HOOKS alongside skills, rules, config, and bin scripts, so the startup workflow's install step propagates new hooks machine-wide. Opt-in hooks stay manual. scripts/tests/install-hooks-link.bats covers the new section. The SessionStart-on-clear todo task closes with this: the hook feature already existed, and the gap was distribution.
|
| | |
|
| |
|
|
|
|
|
|
| |
invariants
From the 2026-06-11 usage report. The debug skill gains a hypothesis-discipline contract (rank candidate causes by cheapest empirical test, run probes in parallel, report only confirmed findings) targeting the serial theory-cycling the report flagged. commits.md's pre-commit checklist gains a staged-files guard covering the untracked-set and canonical-vs-mirror conventions. A small tracked CLAUDE.md carries the rulesets mirror invariant at turn zero. Two [#C] pilots filed: a read-only morning ops orchestrator and a monthly session-harvest workflow.
The report's 500-token-cap finding was a mislabel: the underlying transcripts show 529 Overloaded and stream-idle-timeout errors with no token cap configured anywhere, so nothing to change there.
|
| |
|
|
| |
All five phases shipped today. The spec status flips to implemented with a history entry carrying the commit trail; the phase tasks become dated completion entries under the parent, which moves to DOING until the manual-testing checklist and the other machines' clone + timer setup land.
|
| |
|
|
| |
Phase 0 of the agent KB spec: the org-roam KB now lives at ~/org/roam as a git repo on cjennings.net. roam-sync.sh (bats-tested: commit, rebase, push, conflict-abort) runs from a 15-minute systemd user timer; canonical unit files live in scripts/systemd/. Live references to the old ~/sync/org/roam path (the task-list pointer, the journal workflow, the notes template) repoint to ~/org/roam, and a transition symlink at the old location covers stragglers.
|
| |
|
|
|
|
| |
The KB leaves the ~/sync/org Syncthing share for its own git repo on cjennings.net (new decision D8). A systemd timer auto-syncs Craig's edits, agents pull before query and commit+push after write, machines replicate by clone (the work machine doesn't), and agent writes land under an agents/ subdirectory. Syncthing's no-history, no-gate, conflict-fork costs were the design's weakest accepted risks, and the phone constraint dissolved: mobile stays on on-demand doc drops to the ~/sync/phone share.
The amendment also folds in inclusion criteria plus a guided per-project memory sweep (Phase 1.5), a Success metrics section with a 30-day checkpoint, the seed node redefined as the KB's own documentation, and monthly hygiene automation (Phase 4). Phases renumbered 0-4. Implementation stays held pending the go-ahead.
|
| |
|
|
| |
Craig confirmed the denylist is complete at ~/projects/work alone (archangel is not work-scoped), which clears the spec's one remaining caveat. Phase 1 is unblocked, and implementation still awaits the explicit go.
|
| |
|
|
|
|
| |
I ratified all seven decisions: the org-roam KB is the shared agent substrate, the write boundary is read-shared write-scoped (work never writes), nodes are per-fact, agent writes land freely in the KB only, and harness memory stays as the ephemeral capture layer. The spec moves to docs/agent-knowledge-base-spec.org in spec-create format, superseding the 2026-06-05 draft.
A work-root denylist classifier routes writes: personal projects write, work and unknown projects refuse and report the redacted fact. Implementation is broken into three phases and waits on confirming the denylist contents.
|
| |
|
|
| |
Meeting-prep promotion session. The completed task moved from Open Work to Resolved in the todo cleanup.
|
| | |
|
| |
|
|
| |
tag meeting-prep solo
|
| |
|
|
| |
Promoting meeting-prep to a template needs its project-specific references generalized first, so it's a follow-up rather than part of the daily-prep additions.
|
| |
|
|
| |
Two work-project handoffs filed as backlog tasks: a SessionStart-on-clear auto-resume hook (after /flush), and wide org-table handling via an auto-wrap helper, a width lint, or a tightened standard. Inbox-process marker updated.
|
| |
|
|
| |
The spec adopts the existing ~/sync/org/roam/ KB (Syncthing-synced, 484 files) as the shared store agents read from and write to, so cross-machine memory sync comes for free instead of needing new infrastructure. It recommends the mechanics (queried as files, capture in harness memory then promote durable facts to the KB, a claude-rules pointer, an :agent: write schema) and leaves the work/personal write boundary for ratification. Supersedes the dedicated-repo and two-tier approaches for the storage-and-sync half.
|
| |
|
|
| |
Promoted the flush workflow into rulesets as a /flush skill plus a canonicalized SessionStart(clear) hook, then ran the four open :solo: tasks: start-work Justify and Approach gate additions, a task-review chain on task-audit, and lint-org follow-ups reconcile-on-write.
|
| |
|
|
|
|
|
|
|
|
| |
Every run appended a fresh dated "lint-org follow-ups" section with line-number-keyed entries, so the follow-ups file grew an unbounded pile of near-duplicate sections, kept entries whose finding had since resolved, and broke whenever the target file's line numbers shifted. Running an audit against a large todo.org surfaced exactly that drift: dead-link flags pointing at docs that now exist, and three stacked dated runs for one file.
Now lint-org rewrites the current file's section from the current run. Findings that no longer reproduce simply are not re-emitted, re-runs dedupe to one section, and entries key on checker plus message with the line as a trailing annotation, so a finding survives line shifts as the same entry. Other files' sections are left intact, and the strip step tolerates the old dated-header shape so existing follow-ups files migrate on first run. This changes the follow-ups file from an append-only log to the current outstanding findings per file.
task-audit's Phase C link-hygiene step now also reaps a matching dead-link entry when it fixes or verifies the link, scoped strictly to dead-link entries, so the audit and the follow-ups file stop drifting between lint runs.
Five follow-ups tests cover record-by-content, dedupe across runs, drop-on-resolve, and preserve-other-files. Mirrors synced.
|
| |
|
|
| |
A task audit verified the surviving tasks are factually honest but left their relevance and priority untouched, so keeping the list lean still needed a separate task-review run. Added Phase F: after the audit stamps :LAST_AUDIT:, run task-review on the oldest-unreviewed batch in the same pass. The two stay distinct (audit owns facts and :LAST_AUDIT:, review owns relevance and the per-task :LAST_REVIEWED:); chaining just refreshes both markers in one invocation. open-tasks does not invoke task-review, so nothing there needed to change. Mirror synced.
|
| |
|
|
| |
The Approach gate planned tests, migration, and commits but never asked whether the work needs a design spec it does not yet have. Added item 5: a spec is warranted for large or wide-surface work, unresolved design questions, or a new interface others build on. For a big task it is never a silent skip — the approach summary must state why no spec is needed, so the call is visible and challengeable at the gate. Small contained tasks pass without comment.
|
| |
|
|
| |
The Justify gate covered Downsides and Alternatives but had no forced verdict on whether the work should happen at all. Added item 9: surface the top three objections when real ones exist, or say so in one line when none rise to a genuine objection, rather than manufacturing three. Building the case against the work is cheapest at this gate.
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| |
|
|
|
|
|
|
| |
Phase A's startup rsync copies template updates from rulesets into each project's .ai/, but nothing committed that churn, so it accumulated across sessions and eventually blocked Phase A.0's auto-fast-forward (git won't ff a dirty tree). Two projects hit it the same day.
I added a Step 4.0 to wrap-it-up.org that commits the churn as its own chore commit before the session-work commit, guarded so it only auto-commits synced .ai paths matching rulesets canonical byte-for-byte and surfaces anything that doesn't. startup.org Phase C now surfaces leftover churn at session start as the crashed-session safety net. Both skip the rulesets repo, where .ai/ is a committed mirror.
I also moved four misplaced PROPERTIES drawers in todo.org (DONE tasks) from after the resolution prose to immediately under the CLOSED line, so org parses them as real drawers.
|
| |
|
|
| |
Move the completed solo-batch, rename-tool, and coverage-fan-out tasks into Resolved, and file the lint-org judgment items for the next daily-prep.
|
| |
|
|
|
|
|
|
|
|
| |
Last language in the coverage-summary fan-out, after Elisp, Python, and Go. Same kernel: count every source file on disk that's absent from the coverage report as 0% and weight the project number by file, so an untested file stays visible instead of being averaged away.
The script at languages/typescript/claude/scripts/coverage-summary.js parses an Istanbul json-summary report (the coverage-summary.json that c8, Vitest, and Jest all emit), takes per-file statements covered over total, and reports a file-weighted number plus the missing files. It walks the source dir for .ts/.js, skipping test files, declarations, and node_modules. Node built-ins only, so it runs via node with no install, and it doesn't reimplement the per-file table nyc already prints.
Tests are black-box, run with node's own test runner: a temp tree plus a json-summary report, the script invoked via node, output asserted. They cover missing-file detection, all-tracked, test-file and node_modules exclusion, and the missing-report error. make test gained a node --test discovery path for languages/*/tests, guarded so environments without Node skip it cleanly. As with Python, the TypeScript bundle had no gitignore-add.txt, which would have left the script un-gitignored on install, so I added one.
This finishes the fan-out: coverage-summary now ships in all four bundles, each parsing its own tool's report behind the same file-weighted, missing-as-0% kernel. I proved the Go and TypeScript scripts by running them (Go against a live profile, TS against a synthetic report and the CLI). Python and TypeScript weren't run against a live coverage tool, since neither coverage.py nor nyc is installed here, so the first adopter of each should check against a real report.
|
| |
|
|
|
|
|
|
|
|
| |
Third language in the coverage-summary fan-out, after Elisp and Python. Same kernel: count every source file on disk that's absent from the coverage profile as 0% and weight the project number by file, so an untested file stays visible instead of being averaged away.
The script at languages/go/claude/scripts/coverage-summary.go parses a cover.out profile, maps each import-path-qualified entry back to an on-disk relative path using the module path from go.mod, and reports a file-weighted number plus the missing files. It's standard library only, so it runs anywhere via go run, and it doesn't reimplement the per-function table that go tool cover -func already prints. I proved it against a real go test -coverprofile run, not just a synthetic fixture, since the Go toolchain is installed here.
Two findings to flag. Modern go test ./... already lists every module package in the profile at 0% even when untested, so for in-module code the missing-file list is usually empty. The detection earns its keep on build-tagged files and dirs outside ./.... And this is a coverage-only slice of a Go bundle that doesn't otherwise exist yet: there's no go.md rule file, so sync-language-bundle.sh can't fingerprint it (detection keys on a bundle's own .claude/rules). The script installs via make install-lang LANG=go but won't be sync-maintained until the Go bundle gets real rules and a CLAUDE.md. Building that out is the natural companion task.
Tests are black-box: a Go test in its own throwaway module runs the script via go run against temp fixtures and checks output, so the shipped script dir stays test-free. They cover missing-file detection, all-tracked, _test.go exclusion, and the missing-report error. make test gained a go test discovery path for languages/*/tests, guarded so environments without Go skip it cleanly.
|
| |
|
|
|
|
|
|
|
|
| |
Second language in the coverage-summary fan-out, after the Elisp pilot. Same kernel: a module no test imports never appears in coverage.py's report, so a line-weighted total skips it silently and the suite looks healthier than it is. This counts every source file on disk that's absent from the report as 0% and weights the project number by file, so untested modules stay visible.
The script at languages/python/claude/scripts/coverage-summary.py parses coverage.py's JSON (files[path].summary.covered_lines / num_statements), resolves report paths against the report's directory since coverage records them relative to where it ran, and recurses the source dir for *.py. Unlike the Elisp version it doesn't print a per-file table, because coverage.py's own coverage report already does. The script adds the missing-file accounting that report lacks. It uses only the standard library, parsing the report rather than importing coverage.
The Python run confirmed the plumbing from the pilot is genuinely generic. install-lang and sync deliver the script and the project-owned coverage-makefile.txt with no Python-specific code. The one gap I had to close: the Python bundle shipped without a gitignore-add.txt, so the .claude/ footprint wasn't ignored and the script would have been committable. Added one mirroring the Elisp footprint plus Python artifacts (__pycache__, .coverage, coverage.json). make test gained a languages/*/tests/test_*.py discovery path alongside the existing Elisp ERT one.
Tests: 12 pytest covering the parser, the file-weighted number, and the missing-file detection including subpackage recursion, plus an install-lang check that the script lands in the gitignored footprint. I proved it against a report matching coverage.py's documented schema and the CLI end to end, but not against a live coverage json run, because coverage.py isn't installed in this repo's env. The first project to adopt it should sanity-check against a real report.
|
