diff options
Diffstat (limited to 'todo.org')
| -rw-r--r-- | todo.org | 190 |
1 files changed, 105 insertions, 85 deletions
@@ -34,12 +34,6 @@ Tags are assigned and refreshed by =task-audit=; =task-review= keeps them honest * Rulesets Open Work -** TODO [#D] Fully-unattended scheduled inbox check (/schedule cron pass) :feature: -:PROPERTIES: -:CREATED: [2026-06-23 Tue] -:END: -vNext from the inbox-consolidation spec. =auto inbox zero= (v1) is the interactive =/loop= recurring check that waits for Craig's yes before executing. A fully-unattended =/schedule= cron pass that fires while Craig is away needs its own contract before it can ship: read-only vs may-mutate =todo.org= / =~/org/roam/inbox.org=, how a find surfaces asynchronously when Craig isn't at the session, how dedup state persists across runs that don't share a session, and what session/auth context a cron run carries. Design it after v1 consolidation lands. From the inbox-consolidation spec-review (Codex finding 1). See [[file:docs/inbox-workflow-consolidation-spec.org][spec]]. - ** DOING [#B] wrap-it-up teardown + "wrap it up and shutdown" :feature: :PROPERTIES: :CREATED: [2026-06-23 Tue] @@ -84,58 +78,26 @@ What we're verifying: no sentinel is dropped before commit + push succeeds. - Trigger a teardown wrap in a state where the push would fail (e.g. temporarily point the remote somewhere unreachable). Expected: the wrap surfaces the push failure and stops; no =/tmp/ai-wrap-*-<proj>= sentinel is created, so no teardown fires. -** TODO [#C] Multiple agent-source improvements :spec: +** TODO [#C] Surface cross-project dependencies first in what's-next :feature:spec: :PROPERTIES: -:CREATED: [2026-06-23 Tue] -:LAST_REVIEWED: 2026-06-24 +:CREATED: [2026-06-24 Wed] :END: -Make the tooling agent-agnostic instead of Claude-specific. Three threads from Craig (roam 2026-06-23): (1) give the agent a name so workflows don't say "Claude" everywhere — a non-Claude agent (Codex) reading "you are Claude" gets confused; evaluate whether naming resolves the confusion or whether other spots also leak Claude-specificity. (2) Pull agent-neutral content out of Anthropic-specific files (=CLAUDE.md=) into a shared source that each agent's own entry file points to, so Codex (which runs more literal) reads the same rules; or link =CLAUDE.md= and the Codex equivalent to one source. Have Codex review the workflows for literal-reading wording gaps. (3) Send =.emacs.d= a note (inbox-send) to let =ai-term= launch Claude / Codex / a local ollama LLM, switchable seamlessly at session start. Spec-shaped — needs design before build. From the roam inbox 2026-06-23 (deferred from the 2026-06-21 session). - -*** 2026-06-24 Wed @ 00:21:20 -0400 Partial — agent-neutral wording sweep + thread-3 note landed -Thread 2's wording half shipped in 6ad0442 (=refactor(rules): use agent-neutral language in shared rules=): agent-as-actor phrasing replaced with "the agent" across interaction.md, cross-project.md, triggers.md, working-files.md. Thread 3's note reached =.emacs.d=, whose 2026-06-23 inbox FYI confirms it received and filed the "multi-LLM support" ai-term handoff. Remaining and still TODO: thread 1 (give the agent a name), and thread 2's structural half (extract agent-neutral content into a shared source with a Codex entry-file pointer, then have Codex review the workflows for literal-reading gaps). +Tasks that depend on another project can sit for ages when the dependency is low-priority or needs its own spec process — e.g. wrap-teardown depends on =.emacs.d= for the =ai-term= companion. Craig's proposal (roam 2026-06-24): (1) an org-tag marking a task as blocked-by / depends-on another project (pick a short tag name); (2) several ways to bind dependencies into the what's-next (=open-tasks.org=) decision tree so blocked-by-dependency tasks surface first; (3) review the what's-next workflow as a whole, since many projects use it. Spec-shaped — design the tag + the surfacing approaches before building. -** TODO [#B] Anki deck name from #+TITLE :bug:quick:solo: +** TODO [#C] Task-audit: consolidate adjacent / related tasks :feature: :PROPERTIES: -:CREATED: [2026-06-22 Mon] -:LAST_REVIEWED: 2026-06-24 +:CREATED: [2026-06-24 Wed] :END: -flashcard-to-anki.py's =default_deck_name= returns =input_path.stem= (the filename), so every deck built through =flashcard-sync= (which passes no =--deck=) is named after the file, not the curated =#+TITLE=. =flashcard-review.org= already documents the intended behavior ("the #+TITLE line drives the Anki deck name"); the script never matched it. Fix: =default_deck_name(input_path, org_text)= scans for a =#+TITLE:= line (case-insensitive, trimmed) and returns it, basename fallback when absent; =main()= passes the already-read =org_text=. Edited script + test ready (validated, 29 pass): [[file:docs/design/2026-06-21-anki-titlefix-flashcard-to-anki.py][script]], [[file:docs/design/2026-06-21-anki-titlefix-test.py][test]], rationale [[file:docs/design/2026-06-21-anki-titlefix-proposal.org][proposal]]. Apply to both =.ai/scripts/= and =claude-templates/.ai/scripts/=, sync-check + make test. Migration caveat: deck ID derives from the name, so decks previously built without =--deck= land as new decks on next import (old basename-named decks keep history, delete by hand). Coordinate with "Reconcile flashcard multi-tag tooling into canonical" below — both edit =flashcard-to-anki.py=, build together to avoid conflicting edits. Shared-asset, review-gated. From home 2026-06-21. +The task-audit workflow should also consider combining related tasks when they're adjacent, so a spread-out effort reads as one whole. Craig's example (roam 2026-06-24): the agent-agnostic / agent-source work could collapse into one item, or at least a parent task with the related ones as children. Add a "consolidate related tasks" consideration to =task-audit.org= (a Phase C step or a new phase): detect adjacency, propose a merge or a parent-with-children grouping, apply on Craig's confirm. -** TODO [#C] apkg → org-drill converter :feature: -:PROPERTIES: -:CREATED: [2026-06-22 Mon] -:LAST_REVIEWED: 2026-06-24 -:END: -Inverse of =flashcard-to-anki.py=: read an Anki =.apkg= (zip → =collection.anki2=/=.anki21= sqlite) and emit an org-drill =.org= in the house canonical shape. Recovers orphaned decks (=deepsat-fundamentals.apkg= has no saved =.org= source) and enables phone→org round-trip. Mapping: deck name → =#+TITLE=; each note → =** <Front> :drill:= with Back as body; card tag → =* Section= grouping (best-effort); Back HTML → org (=<br>= → newlines, unescape entities, strip =<hr id="answer">=); fresh =:ID:= UUID per card. Edge cases for tests: multiple decks per apkg, non-basic note types (skip/warn), HTML entities, empty back, media refs, =.anki2= vs =.anki21= schema. Lives beside the flashcard-* family in =claude-templates/.ai/scripts/= (a new file must be built in canonical — downstream =.ai/scripts/= is wiped by startup =--delete=). PEP 723 uv-run, stdlib =zipfile= + =sqlite3= (no genanki for reading). Acceptance: round-trip a known org-drill source through =flashcard-to-anki.py= then back, assert cards match. Build request: [[file:docs/design/2026-06-21-apkg-to-orgdrill-buildreq.org][buildreq]]. Backlog, not urgent. From home 2026-06-21. - -** TODO [#C] flashcard-stats refutation / claim-prompt mode :feature: -:PROPERTIES: -:CREATED: [2026-06-22 Mon] -:LAST_REVIEWED: 2026-06-24 -:END: -A refutation card (heading is a bare false claim, body is the rebuttal) is valid org-drill but trips two BLOCKING =flashcard-stats.py= checks as false positives: non-prompt-heading (a declarative claim has no =?= or imperative verb) and answer-leakage (claim words reappear in the rebuttal). =flashcard-sync='s gate then blocks the whole deck. Fix (pick one): a file-level =#+DECK_KIND: refutation= keyword that skips those two checks for the file, or a per-card =:claim:= tag exempting individual cards. Option 1 is simpler and matches how the deck works (the whole file is one family). Also document the family in =flashcard-review.org= and add tests (refutation-marked file passes despite declarative headings + claim/answer overlap). Edits =flashcard-stats.py= — coordinate with the multi-tag reconcile, same file. Proposal: [[file:docs/design/2026-06-21-flashcard-stats-refutation-proposal.org][proposal]]. Backlog. From home 2026-06-21. - -** TODO [#C] Guard against hardcoded host identity in synced files :feature: -:PROPERTIES: -:CREATED: [2026-06-22 Mon] -:LAST_REVIEWED: 2026-06-24 -:END: -A =CLAUDE.md= / notes file that asserts mutable environment identity as a fixed fact ("This machine is ratio", a current OS, an IP, "the laptop") is false on every machine the synced/tracked file lands on but one. It bit a real archsetup session: a stale "this machine is ratio" line made the agent reason backwards all session while on velox. Proposal: a claude-rule — don't assert mutable host/env identity as a fixed fact in a tracked/synced project file; derive it at runtime and name the command (=uname -n= for host; the =hostname= binary is often absent). Optionally a codify- or startup-time lint flagging "this machine is <name>" / "the current host is" style claims. Decide rule-only vs rule+lint. Proposal: [[file:docs/design/2026-06-21-host-identity-guard-proposal.org][proposal]]. From archsetup 2026-06-21. - -** TODO [#C] coverage-summary.el install location vs CI reachability :bug: +** TODO [#B] Anki deck name from #+TITLE :bug:quick:solo: :PROPERTIES: :CREATED: [2026-06-22 Mon] :LAST_REVIEWED: 2026-06-24 :END: -The elisp bundle installs =coverage-summary.el= into =.claude/scripts/=, which is gitignored in code projects, so CI can't run =make coverage-summary= against it. emacs-wttrin flagged this (its copy's header was rewritten to claim a tracked =scripts/= home). Decide: ship =coverage-summary.el= to a tracked =scripts/= dir so CI reaches it, or keep =.claude/scripts/= and document it as a local-only helper. If moved, reconcile the bundle install path + the =make coverage-summary= fragment + the script's header comment. Surfaced 2026-06-21 during the coverage-summary autoloads bugfix (commit fb86736). - -** TODO [#D] Warn-only pre-commit hook for tooling-path enumeration :feature: -:PROPERTIES: -:CREATED: [2026-06-22 Mon] -:END: -Optional enforcement teeth for the no-attribution / no-tooling-artifacts tightening landed 2026-06-22 (commit 91217d9), which is documentation-only. A warn-only (not blocking) pre-commit hook could scan the commit subject + body for tooling-path enumeration (=CLAUDE.md=, =.claude/=, =.ai/=, =todo.org=, =notes.org=, =session-context=) and AI-attribution language, with the two exemptions baked in: a commit whose change IS one of those files, and private single-user repos. Must warn, not block — a rigid grep false-positives on legit subject mentions. Deferred: Craig chose docs-only for now. +flashcard-to-anki.py's =default_deck_name= returns =input_path.stem= (the filename), so every deck built through =flashcard-sync= (which passes no =--deck=) is named after the file, not the curated =#+TITLE=. =flashcard-review.org= already documents the intended behavior ("the #+TITLE line drives the Anki deck name"); the script never matched it. Fix: =default_deck_name(input_path, org_text)= scans for a =#+TITLE:= line (case-insensitive, trimmed) and returns it, basename fallback when absent; =main()= passes the already-read =org_text=. Edited script + test ready (validated, 29 pass): [[file:docs/design/2026-06-21-anki-titlefix-flashcard-to-anki.py][script]], [[file:docs/design/2026-06-21-anki-titlefix-test.py][test]], rationale [[file:docs/design/2026-06-21-anki-titlefix-proposal.org][proposal]]. Apply to both =.ai/scripts/= and =claude-templates/.ai/scripts/=, sync-check + make test. Migration caveat: deck ID derives from the name, so decks previously built without =--deck= land as new decks on next import (old basename-named decks keep history, delete by hand). Coordinate with "Reconcile flashcard multi-tag tooling into canonical" below — both edit =flashcard-to-anki.py=, build together to avoid conflicting edits. Shared-asset, review-gated. From home 2026-06-21. -** TODO [#B] Helper-instance support — concurrent same-project Claude :feature:spec: +** TODO [#B] Helper-agent instance support — concurrent same-project Claude :feature:spec: :PROPERTIES: :CREATED: [2026-06-11 Thu] :LAST_REVIEWED: 2026-06-24 @@ -179,6 +141,87 @@ DEPENDENCY QUESTION (Craig, 2026-06-15, resolved 2026-06-24 — see below): does *** 2026-06-24 Wed @ 00:30:32 -0400 RESOLVED — independent, unblocked (keyword VERIFY → TODO) Craig's call (2026-06-24): helper-instance is independent of the generic-runtime refactor and builds on its own. The shipped pieces and the remaining wiring are all shared-file concurrency-safety (two Edit writers, one file), orthogonal to which LLM runtime launches — none of it assumes the runtime-manifest / multi-runtime machinery of phases 2-6. One caveat: =ai --helper= overlaps the launcher refactor the generic-runtime arc plans, so keep that launcher change small and contained so the later refactor doesn't fight it. Now a buildable [#B] task behind its own three-ring gate (bats → sandbox drills → live pilot). +** DOING [#B] Wrap-up inbox/transcript routing to destination projects :feature:spec: +:PROPERTIES: +:CREATED: [2026-06-13 Sat] +:LAST_REVIEWED: 2026-06-24 +:END: +Optional wrap-up step that surfaces filed keepers belonging to another project, recommends a destination, and routes each to that project's =inbox/= via =inbox-send= (the destination's own =process-inbox= files it; transcript filing deferred to vNext). Spec: [[file:docs/design/wrapup-routing-spec.org]] — Ready, [9/9] decisions. Source proposal: [[file:docs/design/2026-06-13-wrapup-inbox-transcript-routing-proposal.org]]. + +*** 2026-06-21 Sun @ 02:06:37 -0400 Spec-review + spec-response complete — Ready +Craig's review challenge reshaped the design from a direct cross-repo =todo.org= move to =inbox-send= delivery into the destination's inbox (safer: reuses the sanctioned cross-project path, gets provenance + per-project filing for free, degrades gracefully where a destination has an =inbox/= but no =todo.org=). D2/D3 superseded; D7 (inbox-send delivery), D8 (=:ROUTE_CANDIDATE:= marker at file time), D9 (local source removal + reject-flow recovery) added. Spec-review file consumed and deleted. Implementation-task breakdown filed below (spec-response Phase 6). + +*** 2026-06-24 Wed @ 00:21:20 -0400 Reconcile — marker sub-task repointed at inbox.org +The 2026-06-23 inbox consolidation (24ca58d) merged =process-inbox= + =monitor-inbox= + =inbox-zero= into one =inbox.org= engine (process/monitor/roam modes) and deleted the three old files. The =:ROUTE_CANDIDATE:= marker sub-task targeted =process-inbox.org='s Phase D — repointed it to =inbox.org= process mode (core §3 "File as TODO"). No build has started, so this is a target-rename only; the spec design is unaffected. + +*** TODO [#B] Recommendation engine + destination discovery :feature:solo: +Pure function =(item, project-list) → (destination, confidence)= reusing =inbox-send.py='s =discover_projects= for the project list. Confidence tiers: strong (destination name/path literal in the item), weak (topic-word overlap only — still routed, visibly labeled), none (stays put, never surfaced). Unit-tested directly: strong/weak/none, two-project tie, empty project list. Covers spec Phases 1 + 3. Spec: [[file:docs/design/wrapup-routing-spec.org]]. + +*** TODO [#B] =:ROUTE_CANDIDATE:= marker in inbox process mode :feature:solo: +Extend =inbox.org= process mode's "File as TODO" disposition (core §3 / Phase D) to stamp =:ROUTE_CANDIDATE: <inferred-project>= on any keeper whose inferred home differs from the current project (uses the engine above). Edit the canonical, sync the =.ai/= mirror, verify sync-check clean. Spec Phase 2 / D8. Spec: [[file:docs/design/wrapup-routing-spec.org]]. (Originally targeted =process-inbox.org=, merged into =inbox.org= by the 2026-06-23 consolidation.) + +*** TODO [#B] Wrap-up router sub-step in wrap-it-up.org :feature:solo: +Add the optional router to =wrap-it-up.org= Step 3 after the inbox sanity check: surface the =:ROUTE_CANDIDATE:= batch (task / destination / delivery mode / confidence), go/skip; on go, per candidate =inbox-send= a one-task handoff to the destination's =inbox/= and remove the keeper from the local =todo.org=; empty set = silent. Name the gate-vs-optional split in the prose. Edit canonical + sync mirror. Spec Phase 4 / D7 / D9. Spec: [[file:docs/design/wrapup-routing-spec.org]]. + +*** TODO [#B] Wrap-up routing — test surface :test:solo: +Unit: recommendation engine (strong/weak/none, two-project tie, empty list); marker stamping (cross-project keeper tagged, local keeper not, standing backlog never). Integration (bats, fixture projects + temp =todo.org=): go issues N =inbox-send= calls to the right inboxes with sources removed; skip leaves all in place; empty set = zero interaction; a candidate whose destination has =inbox/= but no =todo.org= still delivers. Spec: [[file:docs/design/wrapup-routing-spec.org]] (Acceptance criteria). + +*** TODO [#B] Wrap-up routing — manual end-to-end validation :test: +What we're verifying: a real keeper routes through a live wrap and the destination actually files it. +- In a project session, let process-inbox file a handoff whose home is a different project; confirm the local task carries =:ROUTE_CANDIDATE: <dest>=. +- Run wrap-it-up; at the router sub-step, confirm the candidate is surfaced with the right destination + confidence, then choose "go". +- Confirm a =from-<thisproject>= handoff landed in the destination's =inbox/= and the keeper was removed from the local =todo.org=. +- Open the destination project; confirm its startup/process-inbox files the handoff into its =todo.org= per its own conventions. +Expected: the task ends up in the destination's =todo.org=, gone from the source, with no foreign =todo.org= written directly. Not =:solo:= — needs a real cross-project wrap and the destination's next session. + +*** TODO [#D] Wrap-up routing — transcript filing (vNext) :feature:no-sync: +File a meeting recording into the destination =assets/= per =working-files.md=, batch go/skip mirroring the task router. Gated on the source-location decision (spec D4). Spec: [[file:docs/design/wrapup-routing-spec.org]] (Phase 5). + +** TODO [#C] Multiple agent-source improvements :spec: +:PROPERTIES: +:CREATED: [2026-06-23 Tue] +:LAST_REVIEWED: 2026-06-24 +:END: +Make the tooling agent-agnostic instead of Claude-specific. Three threads from Craig (roam 2026-06-23): (1) give the agent a name so workflows don't say "Claude" everywhere — a non-Claude agent (Codex) reading "you are Claude" gets confused; evaluate whether naming resolves the confusion or whether other spots also leak Claude-specificity. (2) Pull agent-neutral content out of Anthropic-specific files (=CLAUDE.md=) into a shared source that each agent's own entry file points to, so Codex (which runs more literal) reads the same rules; or link =CLAUDE.md= and the Codex equivalent to one source. Have Codex review the workflows for literal-reading wording gaps. (3) Send =.emacs.d= a note (inbox-send) to let =ai-term= launch Claude / Codex / a local ollama LLM, switchable seamlessly at session start. Spec-shaped — needs design before build. From the roam inbox 2026-06-23 (deferred from the 2026-06-21 session). + +*** 2026-06-24 Wed @ 00:21:20 -0400 Partial — agent-neutral wording sweep + thread-3 note landed +Thread 2's wording half shipped in 6ad0442 (=refactor(rules): use agent-neutral language in shared rules=): agent-as-actor phrasing replaced with "the agent" across interaction.md, cross-project.md, triggers.md, working-files.md. Thread 3's note reached =.emacs.d=, whose 2026-06-23 inbox FYI confirms it received and filed the "multi-LLM support" ai-term handoff. Remaining and still TODO: thread 1 (give the agent a name), and thread 2's structural half (extract agent-neutral content into a shared source with a Codex entry-file pointer, then have Codex review the workflows for literal-reading gaps). + +** TODO [#C] apkg → org-drill converter :feature:solo: +:PROPERTIES: +:CREATED: [2026-06-22 Mon] +:LAST_REVIEWED: 2026-06-24 +:END: +Inverse of =flashcard-to-anki.py=: read an Anki =.apkg= (zip → =collection.anki2=/=.anki21= sqlite) and emit an org-drill =.org= in the house canonical shape. Recovers orphaned decks (=deepsat-fundamentals.apkg= has no saved =.org= source) and enables phone→org round-trip. Mapping: deck name → =#+TITLE=; each note → =** <Front> :drill:= with Back as body; card tag → =* Section= grouping (best-effort); Back HTML → org (=<br>= → newlines, unescape entities, strip =<hr id="answer">=); fresh =:ID:= UUID per card. Edge cases for tests: multiple decks per apkg, non-basic note types (skip/warn), HTML entities, empty back, media refs, =.anki2= vs =.anki21= schema. Lives beside the flashcard-* family in =claude-templates/.ai/scripts/= (a new file must be built in canonical — downstream =.ai/scripts/= is wiped by startup =--delete=). PEP 723 uv-run, stdlib =zipfile= + =sqlite3= (no genanki for reading). Acceptance: round-trip a known org-drill source through =flashcard-to-anki.py= then back, assert cards match. Build request: [[file:docs/design/2026-06-21-apkg-to-orgdrill-buildreq.org][buildreq]]. Backlog, not urgent. From home 2026-06-21. + +** TODO [#C] flashcard-stats refutation / claim-prompt mode :feature: +:PROPERTIES: +:CREATED: [2026-06-22 Mon] +:LAST_REVIEWED: 2026-06-24 +:END: +A refutation card (heading is a bare false claim, body is the rebuttal) is valid org-drill but trips two BLOCKING =flashcard-stats.py= checks as false positives: non-prompt-heading (a declarative claim has no =?= or imperative verb) and answer-leakage (claim words reappear in the rebuttal). =flashcard-sync='s gate then blocks the whole deck. Fix (pick one): a file-level =#+DECK_KIND: refutation= keyword that skips those two checks for the file, or a per-card =:claim:= tag exempting individual cards. Option 1 is simpler and matches how the deck works (the whole file is one family). Also document the family in =flashcard-review.org= and add tests (refutation-marked file passes despite declarative headings + claim/answer overlap). Edits =flashcard-stats.py= — coordinate with the multi-tag reconcile, same file. Proposal: [[file:docs/design/2026-06-21-flashcard-stats-refutation-proposal.org][proposal]]. Backlog. From home 2026-06-21. +#+begin_src cj: comment + we need to make it more generic than this. there will be other cards like this in the future. let's not block against the information when it exists in the org header. +#+end_src + +** TODO [#C] Guard against hardcoded host identity in synced files :feature:solo: +:PROPERTIES: +:CREATED: [2026-06-22 Mon] +:LAST_REVIEWED: 2026-06-24 +:END: +A =CLAUDE.md= / notes file that asserts mutable environment identity as a fixed fact ("This machine is ratio", a current OS, an IP, "the laptop") is false on every machine the synced/tracked file lands on but one. It bit a real archsetup session: a stale "this machine is ratio" line made the agent reason backwards all session while on velox. Proposal: a claude-rule — don't assert mutable host/env identity as a fixed fact in a tracked/synced project file; derive it at runtime and name the command (=uname -n= for host; the =hostname= binary is often absent). Optionally a codify- or startup-time lint flagging "this machine is <name>" / "the current host is" style claims. Decide rule-only vs rule+lint. Proposal: [[file:docs/design/2026-06-21-host-identity-guard-proposal.org][proposal]]. From archsetup 2026-06-21. + +** TODO [#C] coverage-summary.el install location vs CI reachability :bug: +:PROPERTIES: +:CREATED: [2026-06-22 Mon] +:LAST_REVIEWED: 2026-06-24 +:END: +The elisp bundle installs =coverage-summary.el= into =.claude/scripts/=, which is gitignored in code projects, so CI can't run =make coverage-summary= against it. emacs-wttrin flagged this (its copy's header was rewritten to claim a tracked =scripts/= home). Decide: ship =coverage-summary.el= to a tracked =scripts/= dir so CI reaches it, or keep =.claude/scripts/= and document it as a local-only helper. If moved, reconcile the bundle install path + the =make coverage-summary= fragment + the script's header comment. Surfaced 2026-06-21 during the coverage-summary autoloads bugfix (commit fb86736). + +#+begin_src cj: comment +we can document it as a local-only helper. +#+end_src + ** VERIFY [#C] Check that memories are sync'd across machines via git :spec: :PROPERTIES: :LAST_REVIEWED: 2026-06-15 @@ -274,43 +317,8 @@ Expected: all four behave per the spec; any miss promotes to a bug task. (Agent- *** 2026-06-10 Wed @ 18:21:33 -0500 Phase 4 done — monthly hygiene automation live =scripts/kb-hygiene.sh= (6 bats green, shellcheck clean, read-only by design) inventories =:agent:= nodes, flags orphans / duplicate titles / conflict files, and writes an org report into the rulesets inbox; =roam-hygiene.timer= (monthly, Persistent) installed + enabled. Live run against the real KB verified (4 agent nodes, 428 files, 0 conflicts). Conditional vNext stays in the spec's scope tiers: a =/promote= command if the wrap-up prompt proves insufficient, an =:agent:inbox:= staging tag if free writes prove too noisy. Commit b014095. -** DOING [#B] Wrap-up inbox/transcript routing to destination projects :feature:spec: -:PROPERTIES: -:CREATED: [2026-06-13 Sat] -:LAST_REVIEWED: 2026-06-24 -:END: -Optional wrap-up step that surfaces filed keepers belonging to another project, recommends a destination, and routes each to that project's =inbox/= via =inbox-send= (the destination's own =process-inbox= files it; transcript filing deferred to vNext). Spec: [[file:docs/design/wrapup-routing-spec.org]] — Ready, [9/9] decisions. Source proposal: [[file:docs/design/2026-06-13-wrapup-inbox-transcript-routing-proposal.org]]. - -*** 2026-06-21 Sun @ 02:06:37 -0400 Spec-review + spec-response complete — Ready -Craig's review challenge reshaped the design from a direct cross-repo =todo.org= move to =inbox-send= delivery into the destination's inbox (safer: reuses the sanctioned cross-project path, gets provenance + per-project filing for free, degrades gracefully where a destination has an =inbox/= but no =todo.org=). D2/D3 superseded; D7 (inbox-send delivery), D8 (=:ROUTE_CANDIDATE:= marker at file time), D9 (local source removal + reject-flow recovery) added. Spec-review file consumed and deleted. Implementation-task breakdown filed below (spec-response Phase 6). - -*** 2026-06-24 Wed @ 00:21:20 -0400 Reconcile — marker sub-task repointed at inbox.org -The 2026-06-23 inbox consolidation (24ca58d) merged =process-inbox= + =monitor-inbox= + =inbox-zero= into one =inbox.org= engine (process/monitor/roam modes) and deleted the three old files. The =:ROUTE_CANDIDATE:= marker sub-task targeted =process-inbox.org='s Phase D — repointed it to =inbox.org= process mode (core §3 "File as TODO"). No build has started, so this is a target-rename only; the spec design is unaffected. - -*** TODO [#B] Recommendation engine + destination discovery :feature:solo: -Pure function =(item, project-list) → (destination, confidence)= reusing =inbox-send.py='s =discover_projects= for the project list. Confidence tiers: strong (destination name/path literal in the item), weak (topic-word overlap only — still routed, visibly labeled), none (stays put, never surfaced). Unit-tested directly: strong/weak/none, two-project tie, empty project list. Covers spec Phases 1 + 3. Spec: [[file:docs/design/wrapup-routing-spec.org]]. - -*** TODO [#B] =:ROUTE_CANDIDATE:= marker in inbox process mode :feature:solo: -Extend =inbox.org= process mode's "File as TODO" disposition (core §3 / Phase D) to stamp =:ROUTE_CANDIDATE: <inferred-project>= on any keeper whose inferred home differs from the current project (uses the engine above). Edit the canonical, sync the =.ai/= mirror, verify sync-check clean. Spec Phase 2 / D8. Spec: [[file:docs/design/wrapup-routing-spec.org]]. (Originally targeted =process-inbox.org=, merged into =inbox.org= by the 2026-06-23 consolidation.) - -*** TODO [#B] Wrap-up router sub-step in wrap-it-up.org :feature:solo: -Add the optional router to =wrap-it-up.org= Step 3 after the inbox sanity check: surface the =:ROUTE_CANDIDATE:= batch (task / destination / delivery mode / confidence), go/skip; on go, per candidate =inbox-send= a one-task handoff to the destination's =inbox/= and remove the keeper from the local =todo.org=; empty set = silent. Name the gate-vs-optional split in the prose. Edit canonical + sync mirror. Spec Phase 4 / D7 / D9. Spec: [[file:docs/design/wrapup-routing-spec.org]]. - -*** TODO [#B] Wrap-up routing — test surface :test:solo: -Unit: recommendation engine (strong/weak/none, two-project tie, empty list); marker stamping (cross-project keeper tagged, local keeper not, standing backlog never). Integration (bats, fixture projects + temp =todo.org=): go issues N =inbox-send= calls to the right inboxes with sources removed; skip leaves all in place; empty set = zero interaction; a candidate whose destination has =inbox/= but no =todo.org= still delivers. Spec: [[file:docs/design/wrapup-routing-spec.org]] (Acceptance criteria). - -*** TODO [#B] Wrap-up routing — manual end-to-end validation :test: -What we're verifying: a real keeper routes through a live wrap and the destination actually files it. -- In a project session, let process-inbox file a handoff whose home is a different project; confirm the local task carries =:ROUTE_CANDIDATE: <dest>=. -- Run wrap-it-up; at the router sub-step, confirm the candidate is surfaced with the right destination + confidence, then choose "go". -- Confirm a =from-<thisproject>= handoff landed in the destination's =inbox/= and the keeper was removed from the local =todo.org=. -- Open the destination project; confirm its startup/process-inbox files the handoff into its =todo.org= per its own conventions. -Expected: the task ends up in the destination's =todo.org=, gone from the source, with no foreign =todo.org= written directly. Not =:solo:= — needs a real cross-project wrap and the destination's next session. - -*** TODO [#D] Wrap-up routing — transcript filing (vNext) :feature:no-sync: -File a meeting recording into the destination =assets/= per =working-files.md=, batch go/skip mirroring the task router. Gated on the source-location decision (spec D4). Spec: [[file:docs/design/wrapup-routing-spec.org]] (Phase 5). - -** TODO [#C] Morning ops orchestrator pilot — read-only :feature: +** CANCELLED [#C] Morning ops orchestrator pilot — read-only :feature: +CLOSED: [2026-06-24 Wed 05:46] :PROPERTIES: :CREATED: [2026-06-11 Thu] :LAST_REVIEWED: 2026-06-15 @@ -429,13 +437,25 @@ Proposal from the home project (2026-06-17): promote the self-hosted ntfy-over-T :END: The work project edited two synced scripts locally as a stopgap (2026-06-17) and asked rulesets to fold them into the canonical so the next sync doesn't revert them. Preserved bundle: [[file:docs/design/2026-06-17-flashcard-multitag-note.md][note]], [[file:docs/design/2026-06-17-flashcard-multitag-to-anki.py][to-anki.py]], [[file:docs/design/2026-06-17-flashcard-multitag-stats.py][stats.py]]. Change: support a second org tag on drill headings (=:fundamental:drill:=) for curated subset decks. =flashcard-to-anki.py= — broaden =CARD_RE= to match a trailing tag block (a heading is a card when =drill= is among its tags), bound the card body by any L1/L2 heading, add =--tag-filter <tag>= (emit only cards carrying that tag) and =--guid-salt <s>= (separate GUID space so a subset deck imports non-empty without disturbing the full deck's SRS state). =flashcard-stats.py= — same =CARD_RE=/=HEADING_RE= broadening plus a drill-membership guard. Use the preserved to-anki.py (the 0953 version: dropped an unused =heading_tags()= helper, tightened =CARD_RE= =(.*?)=→=(.+?)= for parity with stats). Apply to both =.ai/scripts/= and =claude-templates/.ai/scripts/=, add a multi-tag bats case to =flashcard-sync.bats= (a =:foo:drill:= heading parses; =--tag-filter foo= returns only those), verify the full deck still parses to 465 and =--tag-filter fundamental= returns 100, then sync-check + make test. Shared-asset change, so review-gated. -** TODO [#C] triage-intake.org auto mode — push each sweep to phone (ntfy) :feature: +** TODO [#C] triage-intake.org auto mode — push each sweep to phone (ntfy) :feature:solo: :PROPERTIES: :CREATED: [2026-06-20 Sat] :LAST_REVIEWED: 2026-06-24 :END: The work project (2026-06-18) added a "Push each sweep to Craig's phone (ntfy) — the primary delivery" subsection under "Trigger and delivery" in triage-intake.org auto mode, and asks to fold it into the canonical engine plus re-sync. Preserved bundle: [[file:docs/design/2026-06-18-triage-intake-phone-push-note.org][note]] + [[file:docs/design/2026-06-18-triage-intake-phone-push-workflow.org][edited workflow]]. Auto mode is the away-from-desk / vacation mode, so phone-notify becomes the primary delivery each sweep (fuller end-of-sweep output: per-source deltas, open-PR/Linear state, awaiting-ack list, one-line verdict, timestamp; SCAN FAILED banner on any source failure), plus phone-recv polling each sweep for Craig's replies. Falls back to inline when phone-notify is absent. Depends on the ntfy agent-comms task above (phone-notify/phone-recv must be canonicalized first). Shared template-workflow change, so review-gated. +** TODO [#D] Fully-unattended scheduled inbox check (/schedule cron pass) :feature: +:PROPERTIES: +:CREATED: [2026-06-23 Tue] +:END: +vNext from the inbox-consolidation spec. =auto inbox zero= (v1) is the interactive =/loop= recurring check that waits for Craig's yes before executing. A fully-unattended =/schedule= cron pass that fires while Craig is away needs its own contract before it can ship: read-only vs may-mutate =todo.org= / =~/org/roam/inbox.org=, how a find surfaces asynchronously when Craig isn't at the session, how dedup state persists across runs that don't share a session, and what session/auth context a cron run carries. Design it after v1 consolidation lands. From the inbox-consolidation spec-review (Codex finding 1). See [[file:docs/inbox-workflow-consolidation-spec.org][spec]]. + +** TODO [#D] Warn-only pre-commit hook for tooling-path enumeration :feature: +:PROPERTIES: +:CREATED: [2026-06-22 Mon] +:END: +Optional enforcement teeth for the no-attribution / no-tooling-artifacts tightening landed 2026-06-22 (commit 91217d9), which is documentation-only. A warn-only (not blocking) pre-commit hook could scan the commit subject + body for tooling-path enumeration (=CLAUDE.md=, =.claude/=, =.ai/=, =todo.org=, =notes.org=, =session-context=) and AI-attribution language, with the two exemptions baked in: a commit whose change IS one of those files, and private single-user repos. Must warn, not block — a rigid grep false-positives on legit subject mentions. Deferred: Craig chose docs-only for now. + ** TODO [#D] Build =create-documentation= skill for high-quality project/product docs :feature: :PROPERTIES: :LAST_REVIEWED: 2026-06-15 |