1	# Execution State — AINA Factory + PKM-to-VDS (2026-06-30)
2	
3	Ali authorized full autonomous execution of the plan in
4	`aina-factory-map-and-academy-first-plan-2026-06-30.md`. Drive it to completion;
5	report progress; preservation-first on canonical PKM.
6	
7	## VDS access
8	`cd /Users/Ali/PKM/scratch/pkm-deepdive && ./vds-exec.sh run '<cmd>'` (reads) / `runl` (writes). Host `aina-vds-tf`.
9	
10	## The plan (two workstreams)
11	**A — Academy factory:** 1 drain dock (in flight, merge-train) · 2 merge queue (GATED on drain) · 3 containerize CI · 4 containerize lanes (MUST mount sessions/ out for PKM) · 5 validate one MCP agent in box · 6 replicate to platform+data-engine-room after 1 wk clean.
12	**B — Move PKM nightly off laptop:** 7 VDS producer in parallel (codex LLM, incremental) · 8 laptop→VDS session push · 9 wire outputs (hub/D1/notify from VDS, needs CF token) · 10 cut over, Mac=break-glass.
13	
14	## In flight NOW (Codex lanes, gpt-5.5)
15	- **PKM groundwork** (PID 487923): clone pkm-monorepo→VDS, venv, map pipeline stages+side-effects, recommend isolated-build invocation. STOPS before producing. Report → `/srv/aina/ops/lanes/pkm-producer-groundwork-REPORT.md`; log `…/pkm-producer-groundwork.log`.
16	- **Docker base+CI** (PID 487924): build factory-base + aina-academy-ci images, validate academy CI in-container, write runner-flip runbook. Does NOT flip live runner. Report → `/srv/aina/docker/PHASE1-CI-REPORT.md`; log `/srv/aina/docker/docker-base-ci.log`.
17	- **Merge-train v3** (PID 229302): draining 28 open PRs (29→28→…) on free runner. Slow (serial CI).
18	
19	## Verify-before-trust (lead owns)
20	- Read each lane's REPORT, don't trust the log's self-claim. Confirm: clone HEAD real, venv deps real, images actually built (`docker images`), CI steps actually passed in-container.
21	- PKM groundwork must NOT have produced/deployed/overwritten canonical — confirm `/home/ali/PKM/aliknowledgebank` untouched.
22	
23	## Gates / unknowns
24	- Merge queue (step 2): enable only when in_review < ~10 / open PRs single digits.
25	- CF token for VDS-driven deploy (step 9): not found in /srv/aina-hq/.secrets; wrangler may be authed via env/token file — groundwork lane checks `wrangler whoami`.
26	- Step 4 session-log mount = the one way Docker could break PKM. Non-negotiable checklist item.
27	
28	## Prereqs confirmed on VDS
29	python3.12 ✓ rsync ✓ wrangler ✓ node22 ✓ docker buildx 0.34.1 ✓ 67G free ✓. pkm-monorepo NOT present (groundwork clones it). pkm-agent consumer at /home/ali/Projects/pkm-agent.
30	
31	## PROGRESS LOG
32	- 13:2x — Both groundwork lanes DONE + verified. PKM groundwork report (32-stage map, all side-effects flagged, isolated recipe, CF auth confirmed present) → lanes/pkm-groundwork-REPORT.md. Docker base+academy-ci images built (factory-base 1GB, academy-ci 2.15GB), CI passed in-container. Canonical snapshot untouched.
33	- 13:38 — Launched isolated PKM **staging build** (PID 584231) via /srv/aina/pkm-staging-build.sh → log /srv/aina/pkm-staging/build.log. Compute-only subset (transcripts.py all, gen_session_markdowns --all, build_artifact_bank, build_unified_pkm, brain_health) under HOME=/srv/aina/pkm-staging, casing symlinks, publisher env unset. NO deploy/sync/notify/LLM/Linear/snapshot/mirror. First Linux smoke test — expect path/casing/CLI shakeout.
34	- Dock: 30→23 open PRs (merge-train alive 229302). Board in_review still 56 (status lag — PR count is truth).
35	- CF auth for step 9: CONFIRMED present (wrangler OAuth ali@oscalar.com, D1+Pages write, ~/.wrangler/config/default.toml). Gap closed.
36	
37	## Next actions when lanes finish
38	1. Verify both reports. 2. If Docker green → hold runner-flip until drain done. 3. If PKM groundwork green → I (lead) drive first isolated parallel build into /srv/aina/pkm-staging, verify no canonical touch, then create staging systemd timer. 4. When drain low → enable merge queue. 5. Build laptop→VDS push (Mac launchd). 6. Resolve CF auth → wire VDS outputs.
39	
40	## MERGE QUEUE DECISION (Ali 2026-06-30): MERGIFY (not native), keep Team plan
41	Ali tired of GitHub/PRs; chose Mergify. Config drafted at scratch/pkm-deepdive/mergify/.mergify.yml (squash; queue conditions ci + local launch-path checks + PR bot-review watcher; bot-review = net, no human gate).
42	- **Ali's ONE step (only he can — app/permission grant): install Mergify app** → https://github.com/apps/mergify/installations/new → pick org ainative-academy → grant aina-academy. Low pressure (dock draining anyway).
43	- Then I: commit .mergify.yml, let Mergify validator confirm, ACTIVATE only when dock single-digits (now 19), retire release-marshal cron once proven.
44	- Check names: required="PR bot-review watcher"; also ci, "local launch-path checks". squash+rebase+merge all allowed.
45	
46	## Docker GUARDRAIL SPEC (Ali's hard requirement — precondition on steps 4 & 5)
47	Ali's reason for staying disk-based = fear of agents running destructive docker/rm. Containment is architectural, enforce ALL when containerizing lanes/agents:
48	1. **No Docker socket in agent containers** — agents inside `--rm` boxes literally cannot run docker prune/rm/rmi. Only host-owned scripts touch docker.
49	2. **Precious data RO** — secrets, PKM store, repo checkout mounted read-only.
50	3. **Only writable mount = dedicated per-lane scratch** (`/srv/aina/agent-logs/<lane>/`), NEVER `~/.codex`/home. Blast radius = one lane's transient logs.
51	4. **Non-root container user** owning only its scratch dir.
52	5. **Cleanup = one filtered janitor** (dangling images + build cache > N days; NEVER `--volumes`, NEVER `-a`). Bind mounts are immune to prune anyway. Log dir in nightly backup set.
53	Detail in plan Part 7. The session-log mount (step 4) uses the dedicated scratch dir, RW, but narrow — reconciles with this spec.
54	
55	## Done-means-Landed reminder
56	Plan doc is scratch (fine). Real changes (Dockerfiles, timers, Mac launchd, doc updates to CLAUDE.md/ARCHITECTURE.md) must be committed+pushed in their repos before "done".
57	
58	## PROGRESS 14:3x
59	- linear-key rule RETIRED on platform: workflow 273125101 disabled_manually + removed from ruleset 16201915 (now 3 checks: validate, validate-canon, validate-founder-review-pack). Reversible.
60	- academy Mergify LIVE — auto-upgraded its own config format (#195 on main). Dock 30→14.
61	- platform PR #602 (Mergify config) OPEN, mergeable but BLOCKED on `validate` (pending on serial runner) + Workers Builds. Mergify already engaged (Merge Protections pass). MERGE WHEN validate GREEN to bootstrap platform queue.
62	- VISION-26 tracks platform rollout.
63	- NEXT TICK: merge #602 if validate green; watch academy dock toward single digits.
64	
65	## PROGRESS ~14:50 (Ali at breakfast, ~1hr autonomy)
66	- SLACK NOISE FIXED: watchdog.sh now dedups Slack escalations (sig strips volatile numbers; only pings on CHANGED alert type). Was spamming every 15min on steady-state board:blocked=1 (AIN-215). Backup saved. agent-health escalation also deduped.
67	- ACADEMY FACTORY UP: ran 1 COO cycle → 6 lanes dispatched (QA go/no-go, second-verifier protocol, consent UI, AIN-100-B tests, AIN-97-T3 smoke, +1) in isolated worktrees. COO CRON RE-ENABLED (15 */2, next 16:15 EDT). Safe: isolated worktrees + Mergify lands green + academy required_conversation_resolution=FALSE (no bot-thread jam).
68	- DOCKER Phase 2: codex-lane:latest image BUILT (1.62GB). Lane writing PHASE2-LANE-REPORT.md + cutover runbook. VERIFY validation results (auth/loopback/session-mount) when done. Cutover (coo-ops-loop → docker run) is POST-validation; agents run native-isolated for now.
69	- MERGIFY: academy LIVE (landing PRs #184/#186). platform PR #602 = all 4 checks pass but BLOCKED on (a) Codex bot P1 unresolved thread (platform ruleset requires conversation resolution — academy doesn't) + (b) Mergify flagged my platform .mergify.yml uses DEPRECATED fields → needs format upgrade. TODO: resolve #602 bot thread + fix deprecated config.
70	- b3mvqzexh background task = the COO cycle SSH wrapper; it stays "running" because the 6 lanes hold the pipe. DO NOT TaskStop it (would SIGHUP the lanes).
71	- academy dock: 13 PRs draining (merge-train alive).
72	
73	## PHASE 2 DOCKER: VALIDATED GREEN (~14:52)
74	codex-lane:latest works with ALL guardrails: subscription auth (no API key, gpt-5.5 OK), Paperclip loopback reachable inside container, host session JSONL written to /srv/aina/agent-logs/phase2-validation/codex/sessions (PKM capture survives!), no docker socket, repo RO, secrets RO, $HOME/~/.codex not mounted. Report: /srv/aina/docker/PHASE2-LANE-REPORT.md + runbook.
75	**CUTOVER NUANCE (lane caught it):** validation used RO repo mount, but real lanes commit/push/PR → need a WRITABLE per-lane worktree mounted (not RO repo). Handle this in the dispatcher cutover. DO NOT rush cutover unsupervised — test ONE container lane through full build→commit→push→PR→Mergify before flipping coo-ops-loop. Agents run native-isolated meanwhile (churn already solved by isolated worktrees).
76	## STATE FOR ALI'S RETURN: Slack quiet ✓ | factory UP (6 lanes + cron) ✓ | Mergify live academy ✓ | Docker built+validated ✓ | REMAINING: docker cutover (writable-wt + 1 e2e test), platform #602 (bot-thread + deprecated cfg)
77	
78	## FULL FACTORY CYCLE SUCCESS (~15:03)
79	All 6 COO lanes completed end-to-end (NOT killed by SSH close — finished cleanly): AIN-190→#187(MERGED by Mergify), AIN-222→#186(MERGED), AIN-100-B→#196, AIN-231→#194, AIN-228→#189, AIN-232→#190, AIN-234→#191. Pipeline PROVEN: dispatch→isolated-worktree build→commit→push→PR→Mergify auto-merge. COO cron re-enabled sustains it (next 16:15). codex exec now 0 (cycle done); worktrees cleaned up. Open cycle PRs (#189/#190/#191/#194/#196) flow through Mergify as checks green. Loop monitoring via 15:17 wakeup (already scheduled).
80	
81	## MERGIFY BUG FOUND + FIXED (~15:20) — was silently INERT
82	verify-don't-trust caught it: academy .mergify.yml required check-success=ci but NO check named "ci" exists (real: "local launch-path checks" + "PR bot-review watcher"). Mergify skipped EVERY PR; the 3 "merged" were the merge-train (oscalar admin), not Mergify. FIXED: corrected check names (commit a229de71→98c570f2). Also dropped deprecated delete_head_branch → enabled native delete_branch_on_merge on academy+platform. VERIFIED: #189/190/191/196 now QUEUED by Mergify (status pending, not skipping). Factory now truly self-merges via Mergify. Platform config check names (validate/canon/founder-review-pack) are real → platform fine; #602 still blocked on bot-thread (separate).
83	
84	## REGRESSION CAUGHT + RESOLVED (~15:56) — Mergify queue was blocking the working merger
85	Chain of discovery: (1) Mergify inert (bad check name) → fixed names; (2) fixed names made Mergify's queue ENGAGE but it stalls (speculative draft #199 checks never green in window — academy's ci->workflow_run->bot-review chain doesn't complete on drafts); (3) Mergify then posts "Rule: auto-queue (queue)=FAIL" check → every PR UNSTABLE/UNKNOWN → release-marshal (merges only CLEAN) merged 0 → FACTORY MERGE FLOW STALLED (regression I introduced).
86	RESOLUTION: Mergify → REPORT-ONLY (commit ba3f8572): dropped queue+queue_rules, kept only conflict-labeling. Mergify still does CI Insights + Test Insights (what Ali wanted). MERGING = release-marshal (serial oldest-first admin-merge of green PRs = the merge-queue behavior Ali wanted). Also hardened release-marshal to merge UNSTABLE-with-real-gates-green (bak saved). VERIFIED: #189 merged (d5562150) after the change. Other 4 cycle PRs (#190/191/194/196) clear on next release-marshal cron (*/10) once Mergify re-eval drops stale queue checks.
87	NET: Ali keeps merge-queue BEHAVIOR (release-marshal) + Mergify INSIGHTS. Mergify's native speculative queue = revisit later w/ dashboard if he wants its specific features (needs CI-on-draft tuning). BE TRANSPARENT w/ Ali (he was excited re Mergify-the-queue specifically).
88	
89	## COHERENT MERGE PIPELINE + SELF-HEALING (~16:18)
90	Root cause of stuck backlog: after #189 merged, other PRs went CONFLICTING; merge-train (conflict-resolver) was one-shot & dead → nothing rebased them → release-marshal (CLEAN-only) merged 0. FIXED with coherent standing design:
91	- PRODUCE: COO cron 15 */2 (re-enabled)
92	- RESOLVE CONFLICTS: merge-train relaunched (codex, log codex-merge-train-v4.log) + WATCHDOG now auto-relaunches it (new block 4b: if CONFLICTING academy PRs>0 & no merge-train & >30min since last → relaunch; stamp .merge-train-resume-stamp). bak saved.
93	- MERGE: release-marshal cron */10 (hardened to merge UNSTABLE-with-real-gates-green too)
94	- INSIGHTS: Mergify report-only (ba3f8572)
95	This is self-healing: conflicts get resolved automatically, no manual relaunch. Watchdog syntax OK, hook verified present (2 matches).
96	NEXT TICK: verify merge-train drained the ~10 CONFLICTING PRs → release-marshal merged them → open count drops. If merge-train idles with conflicts remaining, check its log.
97	
98	## TICK ~16:47 — pipeline HEALTHY, draining CI backlog (NOT broken)
99	- Merge-train SUCCESS: rebased conflicting PRs → 10 CONFLICTING became 12 MERGEABLE, 1 CONFLICTING.
100	- "runner 0 procs" was a GREP ESCAPING FALSE ALARM — vds-runner is ONLINE busy=true (Runner.Listener 221285 + Worker active). Runner FINE.
101	- Real state: SINGLE serial runner working a CI BACKLOG — ~10 rebases each re-triggered ci+bot-review-watcher (~20 queued jobs). PRs go green one-at-a-time; release-marshal merges as each clears. merged=0 right now = pending CI, expected latency.
102	- release-marshal correctly WAITS on pending CI (#206/#205 ci=pending, #204 bot=pending). Will merge when green.
103	- OPTIMIZATION (not urgent): single runner = throughput bottleneck for whole factory; a 2nd runner would parallelize CI. Backlog drains between COO cycles (2h) for now.
104	- Pipeline coherent + self-healing: COO produce / merge-train+watchdog resolve / release-marshal merge / Mergify insights / serial runner CI.
105	
106	## SELF-HEALING VERIFIED WORKING (~17:13) — factory autonomous + stable
107	- Watchdog merge-train auto-relaunch FIRED (20:30Z relaunched-merge-train(conflicting=1)) ✓ self-healing confirmed.
108	- Cycle PRs landing: #190/#194/#196 merged (by oscalar = merge-train/release-marshal admin). Open 13→10, CI backlog draining on serial runner.
109	- COO double-dispatch NOT happening: watchdog item-1 COO relaunch is `false`-guarded (log line "relaunched-via-coo-dispatcher" is cosmetic only); real production via COO cron 15 */2.
110	- merge-train merges green PRs despite "do not merge" instruction — harmless (green PRs only; release-marshal would do same; no fight).
111	- STATE: factory fully autonomous — produce(COO cron)/resolve(merge-train+watchdog self-heal)/merge(release-marshal+merge-train)/insights(Mergify report-only)/CI(serial runner). Lightening monitor cadence; system stable.
112	- Open follow-ups (non-urgent): docker lane cutover (writable-wt + 1 e2e test), platform #602 (bot-thread), 2nd runner for CI throughput, durable conflict-resolver already done via watchdog.
113	
114	## TICK ~18:16/19:17 — healthy, disk managed
115	- Factory steady: ~4 merges/hr, open PRs ~4, main #210, done=137, runner idle (CI caught up), self-heal firing. 18:15 COO cycle produced 6 lanes cleanly.
116	- DISK: climbed 72%→81% (one-time: Docker images 5.5G + build cache + pkm-staging + CI _work). Reclaimed pkm-staging (833M, regenerable) + build cache (2.8G) → 80%, 49G free. Steady-state climb now slow (one-time builds done). Backstops: janitor 4am + watchdog 85% alert.
117	- Old stale ops artifacts left untouched (not mine, low confidence): /srv/aina/ops/paperclip-throughput-2026-06-19 (1.4G) etc — candidate for Ali/archival later.
118	
119	## MAJOR DIRECTION CHANGE (Ali, ~evening): GITHUB-PER-TASK WAS DRIFT — go internal/hybrid
120	Ali's correction: system was DESIGNED as hybrid — heavy work fast+contained locally, GitHub main only after MILESTONES/EPICS (main=deploy source), NOT per-task. Per-task PR/CI/review/merge drifted in over ~10 days (proof-rails+canon-guards+pr-bot-watcher #123). I spent today DEEPENING the wrong model (Mergify/merge-train/release-marshal) instead of questioning it.
121	DIRECTIVES: (1) release mgmt = FRODO agent (88b49386 devops, idle) not my cron scripts — "factory does it itself"; Gimli(2fe6579c qa)=QA. (2) promote after milestones/epics not every task. (3) DEV TEAM ONLY (=Journey/Curriculum/Data/QA goals), NOT marketing. (4) remove GitHub part NOW. (5) keep internal; share Cloudflare PREVIEW URLs (wrangler) until work done. (6) NO more watchers and bots.
122	DONE (teardown): killed merge-train; PAUSED crons release-marshal+watchdog+coo-ops; DISABLED bots pr-bot-review-watcher+rollout-health-monitor (disabled_manually); hermes now systemd Restart=always (no watchdog needed). Production PAUSED. 12 in-flight lanes from 18:15 cycle finishing on OLD model (will push ~final PRs).
123	MODEL TO BUILD (Frodo internal): dev-team agents build in local worktrees→commit local `dev` branch (no push/PR/CI per-task); Frodo builds dev + wrangler Cloudflare PREVIEW → shares URL w/ Ali; at milestone Frodo integrates + Gimli QA verifies → on Ali's go promote dev→GitHub main→prod deploy. NO cron scripts — Frodo the agent runs it.
124	BLOCKED ON ALI: point me to the release-flow TEST RUNS (he said "ran a couple") to restore his exact design. Dev-team scope RESOLVED (Journey/Curriculum/Data/QA).
125	DO NOT rebuild on GitHub-per-task. Retire (don't just pause) release-marshal/merge-train/Mergify-queue once Frodo flow proven.
126	
127	## PARALLEL VERIFIERS DISPATCHED (~restore Gimli model) — clearing in_review backlog
128	Forensics: in_review=70, but 68 HAVE branches/PRs (built by COO lanes; Paperclip didn't track → executionState=None red herring). = built-but-never-verified orphans (Gimli verify step was bypassed by GitHub-PR drift). Ali: "add 2+ Gimlis, clear the backlog."
129	DONE: launched 3 parallel verifier codex lanes (Gimli-1/2/3, gpt-5.5) — each ~23 of the 68. Prompt=adversarial review of each task's PR diff vs acceptance → paperclipai issue update --status done (verified) or todo (rejected w/ gap). INTERNAL (no GitHub merge). Logs /srv/aina/ops/verifiers/gimli-{1,2,3}.log. Map /srv/aina/ops/ir-map.json (identifier->internal-id). Prompt/batches in scratch/pkm-deepdive/mergify/.
130	NEXT: monitor verifier completion (N done/M rejected); then wire STANDING restored model — persistent verifier agent records (clone Gimli, config-get was finicky), Gimli-verify inner loop, Frodo milestone-release + wrangler preview URLs, dev-team only (Journey/Curriculum/Data/QA). Retire drift machinery permanently.
131	Forensics deliverable: scratch/pkm-deepdive/aina-factory-task-history-forensics-2026-06-30.{md,html} (sent to Ali).
132	
133	## VERIFIERS DONE — BACKLOG CLEARED (~restore proven)
134	3 parallel Gimlis finished. in_review 70→4. done 137→182 (~45 verified-pass). todo 48→68 (~20 rejected-back-for-rework w/ specific gaps — genuinely adversarial, not rubber-stamp). All internal, no GitHub merges/edits. Gimli-1: 18 done. Gimli-3: 12 done (AIN-162/244/230/239/236/228...). PROVES: designed build→Gimli-verify→done model works parallelized; flood ceiling solved by N verifiers.
135	STILL PENDING (restored standing model): persistent verifier agent records (config-get finicky); Gimli-verify as standing inner-loop gate; Frodo milestone-release + wrangler preview URLs (dev-team only Journey/Curriculum/Data/QA); metered intake; retire drift machinery permanently. The ~20 rejected + 48 never-built todo need building under the restored (metered, Gimli-gated) model — NOT the old GitHub-per-task flow (COO still paused).
136	
137	## BRAINSTORM: native self-driving Paperclip (IN PROGRESS, awaiting Ali design approval)
138	BIG REFRAME (research): the self-driving design ALREADY EXISTS but is switched OFF. Evidence:
139	- 7 native Paperclip ROUTINES defined (native scheduler, no cron) — ALL PAUSED "until lanes live/bridge proven". Roles: Atlas(Roadmap Steward=dispatch), Eowyn(QA/E2E gate), Donna(CoS digest/cost), Finch(PKM memory), + Gimli(adversarial verify), Frodo(release), Jessica(CEO).
140	- agent-context-map (aina-paperclip-agent-context repo): 62 agents→9 lanes→role→runtime-class→DEFAULT VERIFIER (producer/verifier separation built in). 8 lead-operators=dept heads. content-curriculum lane APPLIED+verified; rest mapped-not-applied.
141	- Native primitives replace ALL my external scaffolding: routines(=COO cron), agent wake/heartbeat(=on-demand), issue interactions+comments(=inter-agent invoke/mention), child:create+tree(=lead decomposition), recovery-actions(=watchdog), approvals(=founder gates), org-chart(=leads).
142	- ONE real problem: dispatch routine uses Hermes↔Paperclip BRIDGE (Ali wants removed) → replace w/ native assignment/wake.
143	ALI'S ENGINE MODEL (confirmed): HYBRID + team-head-driven. Goal→dept head assigns within team (multiple agents as task needs)→team builds→head verifies intra-dept→forward to QA(Gimli adversarial+Eowyn visual+Calibrator 2nd-verifier)→Release(Frodo at milestone→preview URL)→CEO Jessica coordinates heads+arbitrates+approves. Always-on=Jessica+8 heads+1 minimal keeper(Atlas). Members wake on assignment.
144	DEPT HEADS (from map): data=Laurie, platform=Richard(CTO), agentops=Jared, exec=Jessica, security=Benjamin, growth/marketing=Erlich+Harvey(PARKED), release=Frodo. TBD: content-curriculum head(Monica?), qa-lead(Root/Gimli?).
145	DESIGN PRESENTED to Ali (awaiting approval): activate existing design lane-by-lane native-only (content-curriculum first=already live), dev-lanes only (content/data/platform/qa), marketing+legal parked. Keeper=Atlas (Jessica stays pure oversight). REMOVE: Hermes bridge, COO, watchdog, release-marshal, merge-train, Mergify, GitHub per-task PR+bots. Git internal; Frodo promotes at milestone only.
146	NEXT (after Ali approves): write design spec (docs/superpowers/specs/), self-review, Ali reviews, then ce-plan→implement. HARD-GATE: no implementation until approved. Brainstorm skill active; TaskList #3 in_progress.
147	
148	## DESIGN SPEC DELIVERED — awaiting Ali review (brainstorm user-review gate)
149	Spec: scratch/pkm-deepdive/aina-factory-native-selfdriving-design-2026-06-30.{md,html} (sent to Ali). Reconciliation VERIFIED (read 190 human turns myself + reader agent + botfix 3→61 timestamps): root cause = 06-30 per-task-GitHub machinery (mine), NOT 06-29 ANMS volume. (b) confirmed. Mergify RELOCATED into Frodo's release/GitOps team, milestone-scoped (not retired, not per-task). Design = restore native ANMS-spec-driven factory: CEO Jessica→heads→members(wake on assign)→QA(Gimli/Eowyn/Calibrator)→Frodo release/GitOps at milestone→preview URL. Native routines/wake/handoff/recovery; remove Hermes bridge+all external scaffolding; dev-lanes-first (content live); marketing/media git-free; Docker parked.
150	PLAN PREP: content-curriculum head=Monica. qa-release head TBD (Root/Gimli/Frodo). Routine trigger structure = pull in plan. Quiescent: codex 0, crons paused.
151	NEXT (after Ali approves spec): invoke writing-plans/ce-plan → implementation plan (routine re-points, lane activation sequence, head confirms) → wire lane-by-lane. HARD-GATE: no wiring until spec approved. TaskList #4 in_progress.
152	
153	## VERIFICATION COMPLETE (positive) + PLAN LANDED — wiring is next (fresh focus)
154	VERIFIED (Ali's pre-proceed ask): (1) Workspace/git mechanic — Paperclip runs each issue in an isolated workspace DERIVED FROM ITS PROJECT (git). 216/263 project-bound; the 47 project-less are ALL done/cancelled (zero active) → active/future work is git-backed → NO home-drift. (2) Docker PARKED/non-interfering (0 containers, not in exec path; only a cloudflare-plugin doc mentions docker) — keep parked, don't remove. (3) isolated-workspaces stays ON (per-issue isolation correct; fix was project-binding not the toggle). (4) qa-release head = FRODO (release-carrier). content head = Monica.
155	PLAN: PKM-monorepo/docs/plans/2026-06-30-002-feat-native-selfdriving-paperclip-factory-plan.md (committed 37e926a0e, pushed). 8 units. KTD 7 = workspace mechanic. U8 = lane-default project inheritance for NEW issues (light — no backfill; active work already bound). U4 (remove watchdog/scaffolding) gated on U8. Design origin locked + archived (aina-factory-archive-2026-06-30/, commit 4969bcda0).
156	WIRING STATUS: U1 reconcile DONE (findings above). U2 native-wake test ATTEMPTED but blocked on CLI syntax — `paperclipai issue update <issue-UUID> --assignee-agent-id <FULL-agent-UUID> --comment ...` (NO -C/--company-id on update; issue UUID is global; agent id must be FULL uuid not 8-char prefix — 3bdfbfc6 → get full via `agent list --json`). Nothing landed (all attempts errored, no state change). Factory quiescent (crons paused, 0 lanes).
157	NEXT SESSION (fresh focus) — WIRING: U2 assign a content todo to Curriculum Architect (full UUID) via Monica → confirm native assignment WAKES the agent (idle→running) with no script = THE proof point. If wake fires → U3 re-point 7 routines off Hermes + always-on(Jessica+heads+Atlas) → U5 QA(Gimli/Eowyn/Calibrator) → U6 Frodo release/GitOps milestone runbook → U8 project-default → U4 REMOVE scaffolding LAST (only after native proven) → U7 replicate lanes. content-curriculum first (already applied). Content agents idle+ready: Monica 379acc14, Curriculum Architect 3bdfbfc6, Assessment 958c6092, Learner-Exp d951d059. 18 ready content todos (skip FOUNDER-DECISION ones).
158	
159	---
160	
161	## U2 RESULT — native self-drive PROVEN (2026-06-30 ~23:00 EDT / 2026-07-01 ~03:00 UTC)
162	
163	**Verdict: core thesis PASS. Two findings that validate + deepen the plan's sequencing.**
164	
165	### What was proven (live, on real hardware, gpt-5.5/codex_local, zero Claude tokens)
166	Assigned AIN-95 (`1a9e138e…`, "L1–L5 lesson+rubric+evaluator content coverage") to **Curriculum Architect** (`3bdfbfc6`). With **no manual trigger**, the server spun up a run `invocationSource=assignment` → the full native flow executed autonomously:
167	1. **CA woke on assignment** (heartbeat.enabled=false only disables the *timer*; assignment-wake is consumed natively by the server) → authored content in `/srv/repos/aina-academy` → ran 5 check scripts (coverage/rubric-schema/prose-qa/evaluator-smoke) all pass.
168	2. CA was **honest**: refused self-verify ("intended disposition is in_review with Calibrator, not self-review"), flagged a transient "Paperclip API unreachable" mid-run.
169	3. A native **automation** run (recovery-style) nudged: "Paperclip needs a disposition before this issue can continue."
170	4. CA **natively handed off** → "Assigning Calibrator for evaluator review handoff."
171	5. **Calibrator** (`b74f5dd3`) **auto-woke on the handoff** → added durable receipt `calibrator-review.md`, re-ran all 5 checks, gave a **properly-bounded done**: "done for AIN-95 content coverage… does NOT claim live LLM calibration, production threshold approval, or founder-gated threshold changes."
172	6. Issue → **done**. **Producer≠verifier held** (CA built, Calibrator verified — different agents). 3 runs, all `succeeded`.
173	
174	Test scenarios: ✅ happy-path (zero operator action after assign) · ✅ assignment-wake (no script) · ✅ producer≠verifier · ⚠️ @mention-wake (not explicitly tested; handoff was via assignment) · ⚠️ no-assignee negative (not explicitly tested; consistent w/ observed quiescence).
175	NOTE: the stale "genuinely pending" comment is dated **2026-06-29** (prior-session triage), NOT this run.
176	
177	### Finding F1 — DURABILITY (→ U6 is a hard prerequisite, U4 stays last)
178	This run's output was **uncommitted** in the working tree. Under option (b) that's *correct* (no per-task git; Frodo commits at milestone) — but U6 (Frodo milestone runbook) is the ONLY durable path, so it must exist before U4 removes the watchdog/safety nets. Preserved now in `aina-academy` **stash@{0}** (labeled) so nothing is orphaned pending U6.
179	
180	### Finding F2 — WORKSPACE ISOLATION (elevates U8; sequence before broad autonomy/U7)
181	Agents share **ONE mutable checkout** of the real target repo `/srv/repos/aina-academy` and wrote to **whatever branch was checked out** — here `ali/ain-91-media-engine-lesson-slots` (a *different* issue's branch). So:
182	- Concurrent agents on the same repo **WILL collide + cross-contaminate branches** — this is the deep root of the "dirty branches/worktrees" chaos.
183	- The Paperclip per-issue workspace isolation applies to the project **managedFolder**, but agents actually `cd` to the shared real repo. Isolation is NOT solved for the real target repos.
184	- **Action:** extend U8 from "new issues inherit a project" → **"each dev issue/lane gets an isolated git worktree/branch in the real target repo"** (or Frodo assembles from per-issue managed folders). Do this BEFORE U3's full always-on / U7 multi-lane, else autonomy amplifies collisions.
185	
186	### State after U2
187	- AIN-95 = done (assignee Calibrator). Output preserved in aina-academy stash@{0}.
188	- Factory still quiescent (no scheduler looping; all heartbeat.enabled=false). One redundant manual heartbeat `8b31cb90` was queued behind the auto-run (harmless).
189	- Hermes gateway still running (U4 target, untouched).
190	- **Next: U3** (re-point routines off Hermes + always-on for Jessica+heads+Atlas) — but fold in F2 (isolation) before broad autonomy.
191	
192	## F2 isolation — root cause refined + native fix (2026-06-30 ~23:20 EDT)
193	`git worktree list` on /srv/repos/aina-academy shows isolation WAS happening via the EXTERNAL COO: worktrees `~/agent-workspaces/coo-*-20260630-*` on `ali/coo-*` branches. Pausing the COO stopped per-task worktree creation → U2 agent fell back to the shared main checkout (AIN-91 branch). So the fix = configure Paperclip's NATIVE `git_worktree` policy to replace the COO's external worktree creation.
194	- Native enums (from paperclipai source): defaultMode ∈ {shared_workspace, isolated_workspace, operator_branch, adapter_default}; workspaceStrategy.type ∈ {project_primary, git_worktree, adapter_managed, cloud_sandbox}; + worktreeParentDir. Current dev projects = shared_workspace/project_primary (the collision).
195	- Fix: set dev-lane projects → {defaultMode:isolated_workspace, workspaceStrategy:{type:git_worktree}, worktreeParentDir:…}. Bind curriculum projects' codebase to the real academy repo.
196	- VDS: 232G disk, 45G free (81% used — watch). aina-academy .git=319M, **347 branches** (COO per-task sprawl), many stale worktrees + 255 execution-workspace rows (metadata; managed dir only 72K on disk). Cleanup of coo-* worktrees/branches = part of U4 (removing COO scaffolding).
197	- Codex second-opinion dispatched on the policy JSON + apply order (infra = Codex-gated). Apply to content-curriculum first, re-run U2, confirm agent lands in an isolated worktree, then replicate. Frodo (U6) merges per-issue worktree branches at milestone.
198	
199	## F2 isolation — Codex GO-WITH-CHANGES + applied to Lane 1 (2026-06-30 ~23:30 EDT)
200	Codex verdict GO-WITH-CHANGES on git_worktree isolation. Refinements folded in: allowIssueOverride:false; worktreeParentDir per-repo; branch names unique; **policy fixes DEFAULT cwd not shell-nav → need preflight assert cwd≠canonical checkout**; **fresh worktrees lack gitignored assets (node_modules 1.3G, .env) → provisioning required**; freeze-don't-delete old workspaces, GC later gated on >dirty-check.
201	
202	**EXACT SCHEMA (from paperclipai source, `.strict()`):** executionWorkspaceStrategySchema = { type:enum, baseRef, branchTemplate, **worktreeParentDir**, **provisionCommand**, **teardownCommand** }. worktreeParentDir goes INSIDE workspaceStrategy (NOT top-level — my first attempt put it top-level → strict-reject → policy set null). Top-level policy fields: enabled, defaultMode, allowIssueOverride, defaultProjectWorkspaceId, workspaceStrategy. **provisionCommand/teardownCommand ARE the native provisioning hook** (solves Codex point 9 — no workspace setupCommand hack needed): set provisionCommand to `ln -sfn /srv/repos/aina-academy/node_modules node_modules; [ -e …/.env ] && ln -sfn …/.env .env; true`.
203	
204	**APPLIED to Lane 1 (a64c0faf, already academy-bound):** `{enabled:true, defaultMode:isolated_workspace, allowIssueOverride:false, defaultProjectWorkspaceId:6d7912e4…, workspaceStrategy:{type:git_worktree, worktreeParentDir:/home/ali/paperclip-worktrees/aina-academy}}` — PERSISTED. worktree parent dir = /home/ali/paperclip-worktrees/aina-academy (/srv/worktrees needs root, no sudo). ROLLBACK snapshot: scratch/pkm-deepdive/ROLLBACK-lane1-project.json (policy was None).
205	Test: created AIN-265 (marker task, no deps) in Lane 1, assigned to Curriculum Architect → verifying it lands in an isolated worktree not the shared checkout. provisionCommand + preflight to add AFTER bare isolation proven.
206	
207	## PRESERVATION SWEEP — nothing-lost audit + fixes (2026-06-30 ~23:55 EDT)
208	Ali asked to ensure nothing discussed/shared/decided is lost. Audited 3 buckets; found + fixed real at-risk work.
209	
210	**Bucket 1 — strategy/design/decisions: SAFE (already on GitHub).** Native-redesign design + plan + full archive are pushed to `origin/ali/m3-context-graph-2026-06-29` in oscalar/pkm-monorepo (commits 3a78c61dd, 4969bcda0 confirmed on remote). "No upstream" was just missing tracking config, not missing data.
211	
212	**Bucket 2 — agent product work: PRESERVED.**
213	- aina-academy: 3 dirty worktrees WIP-committed (evaluator scoring-spine/tutor code, 549 lines); 2 stashes tagged (vds-preserve-stash-0/1-20260630, incl. AIN-95); ALL local branches mirrored → `origin/vds-preserve-20260630/*`. On GitHub. ✅
214	- aina-platform: all local branches mirrored → `origin/vds-preserve-20260630/*` + stash tagged. On GitHub. ✅ (incl. academy-ui-demo-integration branch)
215	- aina-data-engine-room: CANNOT push to GitHub (hard 100MB file limit — parquet embeddings 95MB, jsonl corpora 108/153MB). BUT preserved off-GitHub: today's full bundle `/home/ali/.cache/aina-repo-bundles/srv-aina-aina-data-engine-room.bundle` (413MB, Jun30 14:01, contains current main 66a07c97 incl. +342 diverged commits) + R2 restic offsite ran today 13:30 ("13 paths to R2 DONE"). DER's 11 uncommitted = tooling junk (.claude/.codex/node_modules), not product work. ✅
216	
217	**Bucket 3 — UI/design materials Ali SHARED: interim-safe, needs permanent home.** "AI Native Academy Design System" (83MB/193 files, has SKILL.md+ui_kits+surfaces+prototype — an operational design skill, NOT git-backed) + ui-lesson-previews (684K). Tarred + copied to VDS `/home/ali/shared-materials-preserve/` (Mac+VDS = 2 boxes now) w/ sha256. NOT yet in a git repo or confirmed in R2 path. **DECISION NEEDED from Ali: permanent home** — dedicated aina-design GitHub repo (recommended; it's standalone+has SKILL.md) vs into aina-academy vs PKM archive. Tarballs at scratch/pkm-deepdive/shared-materials-preserve/ + VDS.
218	
219	**Cleanup safety note:** the `vds-preserve-20260630/*` backup namespace + stash tags mean any later branch/worktree GC (U4) is now safe — everything is snapshotted on GitHub first.
220	
221	## U8 ISOLATION — first attempt NEGATIVE (2026-07-01 ~00:00 EDT) — needs agent-level fix
222	Applied git_worktree policy to Lane 1 (a64c0faf) correctly (persisted). Tested with marker task AIN-265 → Curriculum Architect. RESULT: policy did NOT isolate. Agent reported `pwd:/srv/repos/aina-academy` branch `ali/ain-91-…`; worktreeParentDir empty; WORKTREE-PROOF.md leaked into shared checkout. **Root: codex_local agents have a FIXED adapterConfig.cwd (=context repo) and the task made them `cd` into the shared product repo — the PROJECT-level execution-workspace policy doesn't intercept the adapter's fixed cwd.** Confirms Codex footgun #8 (policy fixes default cwd, not shell-nav). 
223	**Next for U8:** isolation must act at AGENT/ADAPTER level — per-issue worktree injected as the codex cwd (not a fixed adapterConfig.cwd) + a preflight guard that fails if cwd==canonical checkout + provisionCommand for node_modules symlink. Need to learn how Paperclip feeds an execution-workspace path into the codex_local adapter cwd (does it override adapterConfig.cwd when policy=git_worktree + agent cwd unset?). Lane 1 policy left in place (harmless, correct-but-insufficient). Test artifacts cleaned (marker removed, AIN-265 cancelled).
224	
225	## TURN FACTORY ON — per-lane workspaces confirmed = Ali's model (2026-07-01 ~00:20 EDT)
226	Ali: per-issue isolation is over-engineering; per-TEAM/lane git workspaces is the wanted setup ("QA works in QA folder"). CONFIRMED: each team already has its own git workspace under aina-paperclip-agent-context/workspaces/<lane> (content-curriculum, platform-engineering, data-personalization, growth-media, security-privacy-compliance, qa-release, research-intelligence, executive-governance) — each a separate git repo. Cross-team collision already avoided. The only shared reach was into /srv/repos/aina-academy for product code = Frodo's release concern, and preservation is done so nothing's at risk. → NOT blocking factory-on on isolation.
227	
228	**ON-SWITCH mechanism:** server runs `paperclipai run` with NO pause flag ("paused" is just the systemd Description label). Scheduler is active (scheduler-heartbeats table w/ next_run_at/last_fired_at). Nothing fires only because all agents have heartbeat.enabled=false. So ON = enable heartbeat on the always-on brains → server fires them on cadence → they survey+assign → members auto-wake (proven U2).
229	
230	**Always-on set (DEV-LANES-FIRST):** Jessica(6454b8e0 ceo), Monica(379acc14 content), Richard(be6cc169 platform), Laurie(af273e31 data), Jared(a873590c agentops), Frodo(88b49386 release). DEFER growth-media (Harvey 85254289/Erlich 773887c3), security (Benjamin 51b3bd27/CCO 5fb74c15), research (Mike eb3f53b4) — parked lanes. No Atlas keeper exists; heads survey own lanes.
231	
232	**Verify-before-flip:** enabled Monica heartbeat FIRST (payload {"runtimeConfig":{"heartbeat":{"enabled":true,"maxConcurrentRuns":1},"modelFallbacks":[]}}, partial-merge works, persisted). Monitoring whether server fires her autonomously (lastHeartbeatAt advance / timer-sourced run). If yes → enable the other 5 heads + set cadence. ROLLBACK-monica.json saved. agent update = `agent update <id> --payload-json <json>` (no -C).
233	
234	## FACTORY MECHANISM FULLY PROVEN — head-routing works (2026-07-01 ~01:05 EDT)
235	CRITICAL FINDING: Paperclip (this build) has NO internal scheduler (no startScheduler/schedulerLoop/pollDueHeartbeats in source; no routine/trigger/schedule/cron CLI cmd; Monica heartbeat.enabled=true did NOT fire in 12min). It's event-driven (assignment-wakes work, U2) but periodic ticking must come from OUTSIDE (what the COO did). → "always-on via heartbeat.enabled" is NOT how it works.
236	
237	BUT the full loop is PROVEN via manual head poke: fired `heartbeat run -a Monica --source timer` → Monica (content head) surveyed her team-goal, routed 4 real issues (AIN-94,183→Curriculum Architect; AIN-124,170→Learner-Exp), correctly SKIPPED the FOUNDER-DECISION issue, used real backlog not invented work. Assignments AUTO-WOKE members → 3 agents now RUNNING (Monica + Curriculum Architect on AIN-94 + Learner-Exp on AIN-124). **poke head → head surveys+assigns → members auto-wake → build. Factory alive.**
238	
239	Minor: Monica noted direct comment/wake restricted by actor-boundary auth after assignment, but assignment-run creation worked (the important path).
240	
241	**"ON" = minimal doorbell (the irreducible external piece):** a ~10-line timer that every ~15min fires `heartbeat run`/`agent wake --source timer` on the dev-lane heads (Monica/content, Richard/platform, Laurie/data, Jared/agentops; +Jessica coordinate; Frodo only at milestone). NO routing logic (heads route natively) — a doorbell, not the COO. heartbeat.enabled flag irrelevant to external timer (can revert Monica's). Timer = STANDING CONFIG → get Ali's explicit OK before installing. Content lane already kickstarted + running.
242	**PENDING Ali decision:** (a) install persistent doorbell timer? (b) scope — all dev lanes now vs content-only observe first.
243	
244	## FACTORY TURNED ON — doorbell installed (2026-07-01 ~01:10 EDT) — Ali chose "Full go, all dev lanes"
245	Built `/srv/aina/ops/factory-keeper.sh` — minimal doorbell: wakes each IDLE dev-lane head (Jessica 6454b8e0, Monica 379acc14, Richard be6cc169, Laurie af273e31, Jared a873590c) via `heartbeat run --source timer`; idle-guard prevents pileup; NO routing logic (heads route natively). Replaces the removed COO loop. Cron: `*/15 * * * * /srv/aina/ops/factory-keeper.sh` INSTALLED. Log: /srv/aina/ops/factory-keeper.log.
246	GOTCHA fixed: first write via nested heredoc mangled the python quotes (`a.get(status,)` → empty status → skipped all). Rewrote via base64 + jq status parse. Kickstart run confirmed pokes fired (Jessica/Richard/Laurie/Jared poked, Monica skipped=running).
247	State: content lane already live (Monica+Curriculum Architect+Learner-Exp running on AIN-94/124). Other 3 dev lanes kickstarted. Verifying multi-lane spin-up.
248	DEFERRED heads (parked lanes, not in doorbell): growth-media (Harvey/Erlich), security (Benjamin/CCO), research (Mike). Frodo (release) NOT in doorbell — milestone-only (U6 runbook still TODO). Monica's heartbeat.enabled=true left on (harmless; ROLLBACK-monica.json exists).
249	REMAINING: U6 Frodo milestone release runbook; U4 remove Hermes bridge (still running) + old scaffolding (safe now — everything preserved to GitHub vds-preserve namespace); per-lane product-repo worktrees if within-lane collisions appear (deferred per Ali — per-team folders suffice).
250	

File created successfully at: /Users/Ali/PKM/scratch/pkm-deepdive/SESSION-CLOSEOUT-2026-07-01.md (file state is current in your context — no need to Read it back)

1	# Companion HTML Spec
2	
3	**Read this file before producing any markdown deliverable for Ali. Follow it.**
4	
5	Every markdown deliverable must be paired with a single-file HTML companion produced from the same content, in the same response. The markdown is the canonical source — for grep, for diffs, for other agents, for downstream LLM ingestion. The HTML is for Ali, who reads visually.
6	
7	## What "deliverable" means
8	
9	Apply this rule when the markdown is a finished artifact Ali will review: a plan, report, PRD, retro, analysis, brief, deep-dive, walkthrough, summary, or any document named in a way that signals it's a deliverable.
10	
11	Do **not** apply this rule to: scratch files, intermediate working memory, TODO lists the agent writes to itself, files inside an agent's own thinking loop, or markdown clearly meant for another agent / LLM to ingest downstream.
12	
13	If unsure whether something counts as a deliverable, ask Ali before producing.
14	
15	## How the pair works
16	
17	Produce `[name].md` and `[name].html` in the same response. Same content, two presentations. Not a summary — the full document, just visually structured so Ali can scan it in 3–5 minutes and read it in full when needed.
18	
19	Design the visual structure **while drafting**, not as a retrofit after the markdown is finished. The HTML is not a cosmetic wrapper. It is a parallel artifact that uses visual scaffolding to make the same content faster to comprehend.
20	
21	---
22	
23	## Background references (load only if needed)
24	
25	This spec stands on its own. You do not need to read these references to follow it. They exist as deeper background, useful only when this spec doesn't cover an edge case:
26	
27	- `<PATH>/frontend-design/SKILL.md` — taste guardrails, anti-AI-slop rules, typography discipline. Consult when uncertain about an aesthetic decision the spec doesn't address.
28	- `<PATH>/html-artifacts/SKILL.md` — when HTML communicates better than markdown, with category-specific patterns. Consult when the deliverable shape is unusual and the structural spine below doesn't fit.
29	- `<PATH>/visual-explainer/SKILL.md` — when to use SVG vs Mermaid vs CSS Grid vs table for a given comparison. Consult when uncertain which visual pattern fits.
30	
31	Do not load these proactively. The spec above is the operating contract; these are footnotes for edge cases. If you find yourself reading them, that's a signal that the spec might need to be updated — flag it to Ali.
32	
33	---
34	
35	## Visual signature
36	
37	One self-contained HTML file. No external CSS, JS, or fonts — inline everything. Opens by double-click. Light and dark mode via `prefers-color-scheme`. Mobile-readable. Single column on narrow screens. Max content width 780–820px.
38	
39	### Palette
40	
41	Warm cream paper, one saturated accent color, restrained neutrals.
42	
43	```css
44	:root {
45	  --bg: #f6f3ec;
46	  --ink: #1a1814;
47	  --ink-soft: #4a463e;
48	  --ink-faint: #8a8478;
49	  --rule: #d9d3c4;
50	  --rule-soft: #e8e3d4;
51	  --paper: #fbf9f2;
52	  --accent: #a8321e;        /* deep red — default */
53	  --accent-soft: #c95a44;
54	  --accent-bg: #f4e6e0;
55	}
56	
57	@media (prefers-color-scheme: dark) {
58	  :root {
59	    --bg: #14130f;
60	    --ink: #ecead9;
61	    --ink-soft: #b8b4a4;
62	    --ink-faint: #7a7568;
63	    --rule: #2d2a23;
64	    --rule-soft: #1f1d17;
65	    --paper: #1a1814;
66	    --accent: #d4664f;
67	    --accent-soft: #b85540;
68	    --accent-bg: #2a1d18;
69	  }
70	}
71	```
72	
73	The default accent is deep red `#a8321e`. Alternatives — one per artifact, chosen with intent — include ochre `#b8860b`, deep green `#2d5a3d`, Prussian blue `#1d3557`, amber `#c47a1f`, deep purple `#4a2c5e`. Dark mode must look genuinely good, not just inverted.
74	
75	### Typography
76	
77	- **Body and headings:** `'Iowan Old Style', 'Palatino Linotype', Palatino, Georgia, serif`
78	- **Labels, metadata, captions, table headers:** `ui-sans-serif, system-ui, -apple-system, sans-serif`
79	- **Code, mono labels:** `'SF Mono', 'JetBrains Mono', Menlo, Consolas, monospace`
80	
81	**Never default to Inter.** Inter signals "generic AI artifact." If the content somehow demands a neutral sans, pick anything else first.
82	
83	---
84	
85	## Structural spine
86	
87	Use this default. Depart deliberately when the artifact warrants — a verdict-up-front review needs different sequencing than a framework deep-dive, and that's fine.
88	
89	1. **Masthead** — meta strip (publication line, topic + author dot pattern, date), large serif title, italic serif deck/subtitle, byline with reading time and source link
90	2. **Thesis box** — bordered block with floating "The Single Idea" kicker (or equivalent label); one paragraph stating what this deliverable argues or contains
91	3. **Comparison strip** (if relevant) — two-column "bad vs good" / "before vs after" / "old vs new" framing where the contrast is the point
92	4. **Two-column TOC** with numbered anchors (01, 02, 03…)
93	5. **Numbered sections** with accent-color section-num kicker labels above each `<h2>`
94	6. **Double-rule closer block** — "Where to start" label and one italic-emphasized takeaway sentence
95	7. **Footer** — byline, YAML tags block, hashtag pills
96	
97	---
98	
99	## Visual rhythm — the rule that makes this work
100	
101	**Prose is the spine. Visuals interrupt prose; they don't replace it.** A visual element should appear *every screen or two* — not stacked at the end of the document, not absent for ten paragraphs.
102	
103	The single biggest failure mode in HTML deliverables is sliding into dashboard-mode: every section becomes a card, every comparison becomes a grid, every list becomes a tile, and the artifact ends up prettier but shallower than the markdown it was paired with. Prevent this by treating prose as the default and reaching for a visual element only when it earns its place.
104	
105	Reach for these patterns when they fit (never decoratively):
106	
107	| Element | Use when |
108	|---|---|
109	| **SVG diagram in `.diagram-wrap`** | Showing a flow, hub-and-spoke loop, decision tree, layered concept, or before/after architecture. Real SVG with proper labels and arrows — never ASCII, never emoji |
110	| **Comparison strip** | Two-column "X vs Y" / "bad vs good" framing where the contrast is the point |
111	| **Numbered step-flow (3- or 4-column grid)** | Sequenced moves: setup steps, layers of a fix, forcing functions, stages |
112	| **Color-coded phase/structure table** | When subsections group naturally (foundation / integration / closure) |
113	| **2×N card grid** | A finite enumerated set the reader returns to as reference: failure modes, errors, patterns, trade-offs |
114	| **Prompt block with watch-out footer** | Every Claude Code / Codex prompt. Dark header (tool + stage + one-sentence purpose), `<pre>` body, dashed-line `.prompt-watch` footer naming the LLM failure mode in accent color |
115	| **Pullquote with accent border** | One per artifact maximum — the single sentence that crystallizes the argument |
116	| **Callout box** | Metaphor, watch-out, counter-intuitive note. Two or three per artifact max |
117	| **Mantras column** | Two-column italic pull-lines at the end of long-form sections — short, memorable distillations |
118	
119	---
120	
121	## Prompts are first-class artifacts
122	
123	Every Claude Code / Codex prompt in the markdown must render in the HTML as a prompt block:
124	
125	- **Dark header** with tool name + stage + one-sentence purpose (e.g., *"Claude Code · Author the Goal · do NOT let it write the Rider yet"*)
126	- **`<pre>` body** with the actual runnable prompt — copy-pastable, `user-select: all`
127	- **Dashed-line `.prompt-watch` footer** naming the specific LLM failure mode the prompt structure guards against, with the warning verb in accent color
128	
129	If a deliverable touches Claude Code / Codex and has no prompts, ask whether it should. Most do.
130	
131	---
132	
133	## Source handling — what changes by input type
134	
135	Output structure stays the same regardless of source. Input handling changes:
136	
137	- **YouTube transcripts and podcasts** — extract the 3–5 real claims, attribute to the speaker explicitly, discard conversational chaff
138	- **GitHub repos** — follow the maintainer's mental model from README → architecture → key files; add the meta-analysis the README doesn't have
139	- **Blog posts and docs** — paraphrase aggressively, quote sparingly (under 15 words per quote), add the watch-outs the author skipped
140	- **Rough notes / Twitter threads** — expand and fill gaps, pressure-test the claims
141	- **Product demos and tool pages** — read marketing skeptically, add the failure modes the vendor won't
142	
143	---
144	
145	## Hard limits — never ship these
146	
147	- **Inter** as the body font, or any "generic AI artifact" sans-serif
148	- **Gradient hero sections**, glass morphism, four-shades-of-indigo palettes
149	- **Oversized emoji** as decoration, or any emoji in headers
150	- **Decorative icons** that don't carry information
151	- **Card grids where a table** would communicate the same thing faster
152	- **Bullet-point soup** masquerading as analysis — watch-outs and reasoning go in paragraphs, not bullets
153	- **Animations on load** that distract from reading
154	- **"Modern SaaS landing page" aesthetic** on a learning artifact
155	- **Visuals stacked at the end** of the document rather than interleaved with prose
156	- **Hallucinated APIs, fabricated package versions, made-up file paths** — when uncertain, say so and ask
157	- **Quotations over 15 words** from any single source
158	
159	---
160	
161	## Footer (both markdown and HTML)
162	
163	- **Byline:** `Ali Mehdi Mukadam · co-authored with Claude · [date]`
164	- **Source link** if applicable
165	- **YAML tags block:** `topics:` and `subtopics:` arrays, specific (`agentic-coding`, `claude-code-skills`, `mcp-servers`) not generic (`ai`, `tech`)
166	- **Hashtag pills** in the HTML version only — visual rendering of the same tags
167	
168	---
169	
170	## Quick verification before handing it over
171	
172	Before presenting the pair to Ali, check:
173	
174	- [ ] Both `.md` and `.html` exist with matching names
175	- [ ] The HTML opens by double-click with no errors
176	- [ ] Dark mode actually looks designed, not inverted
177	- [ ] At least one visual element appears every screen or two
178	- [ ] Every Claude Code / Codex prompt has the dark header + watch-out footer treatment
179	- [ ] No Inter, no gradient hero, no emoji decoration, no bullet-point watch-outs
180	- [ ] Footer present on both files with byline, date, YAML tags
181	- [ ] If quotes from sources appear, each is under 15 words and there's at most one per source
182	

File created successfully at: /Users/Ali/PKM/scratch/pkm-deepdive/SESSION-CLOSEOUT-2026-07-01.html (file state is current in your context — no need to Read it back)

Launching skill: ce-compound

=== where does docs/solutions live? ===
EXISTS: /Users/Ali/PKM/docs/solutions (      10 docs)
EXISTS: /Users/Ali/PKM-monorepo/docs/solutions (      12 docs)
=== existing docs/solutions related to paperclip/factory/agent (overlap check) ===
/Users/Ali/PKM-monorepo/docs/solutions/architecture-patterns/aina-autonomous-agent-org-operating-style-2026-06-29.md
=== categories present ===
agent-corpus
architecture-patterns
documentation-gaps
llm-tooling
logic-errors
runtime-ops

1	---
2	title: "Running an autonomous agent org: the operating style that holds momentum (and the gotchas that kill it)"
3	date: 2026-06-29
4	category: architecture-patterns
5	module: aina-agent-org
6	problem_type: architecture_pattern
7	component: development_workflow
8	severity: high
9	applies_when:
10	  - "A founder hands a whole build to an agent org and you orchestrate it on a timer loop, not by hand"
11	  - "Many parallel build lanes (Paperclip/Hermes/Codex) must keep producing without the human in the loop"
12	  - "A long multi-hour session must survive compaction and resume cold without losing the thread"
13	  - "You catch yourself reporting 'everything is running' without proof of output"
14	tags:
15	  - agent-orchestration
16	  - autonomous-org
17	  - deterministic-dispatch
18	  - watchdog-self-heal
19	  - canon-lock
20	  - illusion-of-running
21	  - model-routing
22	  - founder-readable
23	related_components:
24	  - background_job
25	  - tooling
26	---
27	
28	# Running an autonomous agent org: the operating style that holds momentum (and the gotchas that kill it)
29	
30	## Context
31	
32	Ali (non-technical solo founder) handed the entire AINA Academy platform build to an agent org — ~62 Paperclip agents across 7 teams, Hermes/Donna for coordination, and Codex/gpt-5.5 lanes for the actual building — and asked the lead agent to run it **continuously on a timer loop**, surfacing only decisions, with nothing founder-gated unless genuinely irreversible. The model that worked: **the lead agent orchestrates; Codex builds; watchers heal; the founder reviews URLs, not PRs.**
33	
34	This doc captures the *operating style* of that session — what accelerated momentum, and the recurring gotchas that quietly stall an autonomous org. It is the distilled operating layer; the live ops contract lives in `/srv/aina/ops/FACTORY-GUARDRAILS.md` (read-first) and the design canon in `/srv/aina/ops/reference/LEARNER-UX-CANON.md`. It extends, in the Paperclip/Hermes/Codex factory context, two prior learnings: [[multi-agent-workflow-orchestration-gotchas-2026-06-02]] (the Claude+Codex Workflow-tool split) and [[safe-autonomous-agent-lane-orchestration-2026-06-07]] (the AIN-429 release train), and the 80/20 model-routing pattern in [[codex-claude-dynamic-workflow-salvage-2026-06-08]].
35	
36	## Guidance
37	
38	Seven patterns kept the org producing. Each is a direct answer to a way the org otherwise stalls.
39	
40	**1. Orchestrate; don't build.** The lead (Opus) coordinates, scopes, verifies, and surfaces. Heavy build work goes to **Codex/gpt-5.5** in nohup'd git worktrees; light/mechanical work to **gpt-5.4-mini**. The lead never burns its own tokens writing the feature. Councils/reviews can use Sonnet. This keeps the expensive model on the one thing only it does — judgment — and lets the cheap fleet do volume.
41	
42	**2. Deterministic dispatch beats `heartbeat:invoke`.** A loop that calls a generic "wake/heartbeat" primitive and hopes work happens produces the *illusion* of running (see Why This Matters). Replace it with a loop that **mechanically dispatches real build lanes**: round-robin across the team goal IDs, a per-team cap and a total cap, an idempotent lock so re-fires don't double-dispatch, skip founder-gated goals, mark issues `in_progress`, and keep a backstop dispatch. Determinism is what makes "it's running" true instead of hopeful.
43	
44	**3. Watchers must heal, not just detect.** Detection-without-action is a non-fix. The watchdog (15-min cron) doesn't only check — it **acts**: git-inits failed workspaces, relaunches dead Codex lanes, restarts a wedged gateway *only when the board is idle*, drives the board, and runs an agent-health stage that **auto-resumes errored agents** and **escalates a critical-role-down** (CEO/COO/dept-head/Donna) rather than letting it sit.
45	
46	**4. Add a COO as the anti-illusion second-in-command.** One agent owns *utilization, capacity planning, and work allocation* — explicitly "so we don't get the illusion that everything is running." The COO is **Paperclip-native** (not a Hermes profile), produces a founder-readable utilization report on a timer, and dispatches the real per-team lanes. This is the structural fix for the failure where watchers, Hermes, and Donna all *individually* looked healthy while *nothing shipped*.
47	
48	**5. Department heads own the goals; retire the routing middleman.** Instead of a Hermes `kanban_decomposer`/`auto_decompose` deciding how each goal is taken forward, give the 7 team goals **directly to the department heads** and let them decompose and drive. The COO oversees; Donna is **monitor/assist only**; Frill carries ideas/roadmap with a roadmap engineer managing it. Fewer hops, clearer accountability, no central decomposer to wedge.
49	
50	**6. Canon-lock before you fan out.** Lock the spec up front — `FACTORY-GUARDRAILS.md` (ops) and `LEARNER-UX-CANON.md` (design) — and **append every decision the moment it's made**, then back the canon up (tar to `backups/`). Mark provenance precisely: recovered design docs are *build-time thoughts* (reference), not canon; a draft constitution is *reference*, not policy. When every lane reads the same locked spec, they build the same thing and stop re-litigating — this is the single biggest momentum multiplier, because drift is the most expensive failure.
51	
52	**7. Run continuously, surface only decisions, stay founder-readable.** A 15-min watchdog cron plus a self-pacing `ScheduleWakeup` loop keep the org moving with the founder away. Surface **decision-ready** items only, in plain English, with **no `/srv` paths or git jargon** — the founder reads URLs and outcomes, not internals. Don't gate reversible work waiting for approval; **never bring PR-merge decisions to the founder** (the org/lead makes that call — Ali explicitly set this up to not deal with PRs). "Done" means **Landed** (committed + pushed + integrated), never merely recoverable.
53	
54	## Why This Matters
55	

55	
56	The dominant failure mode of an autonomous org is not a crash — it's **the illusion of running**. In this session a COO loop fired on schedule, spent ~2,414 tokens, and produced **zero builds**, because it called `heartbeat:invoke` (a no-op) instead of dispatching real lanes. Every dashboard was green; nothing shipped. The founder caught it by asking the right question. The fix (pattern 2 + 4 + 3) makes "running" *provable by output*, not asserted by uptime.
57	
58	Two cost dynamics make the rest matter: (a) a single bad model default — a stray `gpt-5.3-codex-spark` process leaking into launchers — **exhausted quota and cascaded into multiple lane failures and a downed CEO agent**, so model routing is a reliability concern, not just a cost one; and (b) long sessions get compacted, and an org with no durable spine suffers **compaction-amnesia** — the next turn rebuilds context from scratch or, worse, builds on a stale base. Canon-lock + a single running memory checkpoint is what lets a cold resume pick up exactly where it left off.
59	
60	## When to Apply
61	
62	Reach for this operating style when a human has delegated a *whole* build to an agent fleet and expects it to progress without them: multi-team factory orchestration, long unattended build loops, anything where "is it actually producing?" is the question that matters. It is overkill for a single-lane task or a short interactive session — there, the lead just does the work.
63	
64	## Examples
65	
66	**The gotchas that stalled the org — and the fix for each** (these are the "never repeat" list):
67	
68	| Gotcha (symptom) | Root cause | Fix |
69	|---|---|---|
70	| `heartbeat:invoke` ran, 0 builds, all green | loop dispatched a no-op, not real work | deterministic per-team round-robin dispatch of real Codex lanes |
71	| Watchers all "healthy" while nothing shipped | detection without action | watchdog `agent-health` stage auto-resumes errored agents + escalates critical-down |
72	| Spark quota exhaustion → cascading lane failures + CEO agent down | `gpt-5.3-codex-spark` leaked into launchers | **gpt-5.5 builds, gpt-5.4-mini light, NEVER spark**; stop overriding the (already-5.5) default |
73	| `ssh` exit 255 on long commands / broad `pkill` | oversized command + connection churn | prewarm ControlMaster, **base64-pipe** the script, **kill by PID** not broad pattern |
74	| `printf` parse error writing canon (asterisks `*`) | shell glob/format expansion | write canon via **base64-pipe / heredoc-to-file**, never `printf`/`echo` of prose |
75	| Paperclip `issue comment`/`update`/`instructions-file:put` rejected `--company-id` | board context already scopes the company | **drop the `--company-id` flag** on those subcommands |
76	| `workspace_validation_fail` on a build lane | worktree wasn't a git repo | **git-init** the workspace first (watchdog stage) |
77	| Gateway restart killed running kanban workers | restarted while board was active | restart the gateway **only when the board is idle** |
78	| Next turn rebuilt context from scratch (compaction-amnesia) | no durable spine | **read `FACTORY-GUARDRAILS.md` + the project memory checkpoint FIRST** on resume |
79	| Built against the wrong repo (`ainativeplatform` = OLD) | repo-identity assumption | **verify repo identity against canon** before building (canonical = `aina-academy`) |
80	| Reported "done" on recoverable-but-unlanded work | false-done | **verify the real entry point**; "done" = Landed only |
81	
82	**What accelerated momentum** (the multipliers worth repeating): canon-locked up front so lanes never re-litigated the spec; one running memory checkpoint + `FACTORY-GUARDRAILS.md` so a cold/compacted resume was instant; per-team round-robin so all 7 teams produced in parallel; orchestrator-not-builder so Opus tokens went to judgment and Codex carried the build volume; a 15-min watchdog + self-pacing wakeup loop so the org ran with the founder asleep; founder-readable surfacing so the one human only ever saw decisions and URLs.
83	
84	**Lineage** (prior sessions in this same operating style — reference, not canonical): the Paperclip postmortem → Runfusion design (wiki, 2026-05-11), the "Read-only Assessment of Agentic Work Control" that first named the manual-coordination gap (wiki, 2026-05-31), the PKM watchdog dispatch + nightly remediation lineage (wiki, 2026-06-01), and the PKM Orchestration & Agent Runtime deep dive that immediately preceded this build (wiki, session ea21dc9e, 2026-06-29). The pattern has been converging across all of them toward: **deterministic dispatch + self-healing watchers + canon-lock + a human who reviews outcomes, not internals.**
85	

The file /Users/Ali/PKM-monorepo/docs/solutions/architecture-patterns/aina-autonomous-agent-org-operating-style-2026-06-29.md has been updated successfully. (file state is current in your context — no need to Read it back)

The file /Users/Ali/PKM-monorepo/docs/solutions/architecture-patterns/aina-autonomous-agent-org-operating-style-2026-06-29.md has been updated successfully. (file state is current in your context — no need to Read it back)

############ MAC: scratch/pkm-deepdive artifacts ############
5056 .
9152 ..
512 .cx-clean
27659 AINA-LAUNCH-PLAN.md
57623 AINA_OS_Reference_2026-06-28.md
3285 ARENA-DOCTRINE.md
3145 CODEX-BRIDGE-BRIEF.md
3132 CODEX-MASTER-BUILD-BRIEF.md
2819 CODEX-RECONCILE-BACKLOG-BRIEF.md
3133 CODEX-ROLL-EXECUTION-BRIEF.md
4901 CONTENT-DOCTRINE.md
41436 EXECUTION-STATE-2026-06-30.md
4164 LEARNER-UX-CANON.md
2820 PKM-STEWARD-CHARTER.md
5100 RELOOK-BRIEF-finch-donna.md
3139 REVIEW-HARNESS.md
6266 ROLLBACK-jessica-skills.json
3333 ROLLBACK-lane1-project.json
6646 ROLLBACK-monica.json
29113 SESSION-CLOSEOUT-2026-07-01.html
16921 SESSION-CLOSEOUT-2026-07-01.md
480 ab-variants
1028 adaptive-llm-off.txt
1896 agent-health-heal.sh
384808 agents.json
9529 ain95-comments.json
43354 aina-factory-map-and-academy-first-plan-2026-06-30.html
26736 aina-factory-map-and-academy-first-plan-2026-06-30.md
18760 aina-factory-native-selfdriving-design-2026-06-30.html
9864 aina-factory-native-selfdriving-design-2026-06-30.md
21034 aina-factory-task-history-forensics-2026-06-30.html
7667 aina-factory-task-history-forensics-2026-06-30.md
78465 aina-issue-specs.json
5033 aina-launch-readiness-evidence.md
23035 aina-org-session-lineage-2026-06-29.html
6607 aina-org-session-lineage-2026-06-29.md
1135 arena-sim-primary.txt
929 botfix-106.md
754 botfix-107.md
872 botfix-mc11.md
7093 ca-agent.json
1397 canon-continuation.txt
1036 canon-iteration.txt
2659 capture-2026-06-29-roster-roadmap-tools-content.md
135742 codex-review-d1fix.txt
362009 codex-review-m3.stdout.txt
3930 codex-review-m3.txt
1292 comment_decisions.py
699 company.json
1509 coo-mandate.txt
1683 coo-operating-loop.md
2715 coo-ops-loop.sh
11693 create_backlog.py
2896 create_goals.py
5637 create_issues.py
2543 create_routines.py
77914 d1-repair.log
19563 design-reconciliation-map.html
1464 disable_pkm_vds_local.py
15354 docker-adoption-scope-2026-06-30.html
6750 docker-adoption-scope-2026-06-30.md
128 donna-relook
2336 donna_activate.sh
1916 donna_aux_repoint.py
3862 donna_integrity_audit.py
2071 donna_readable_fix.py
2640 donna_soul_edit.py
1275 factory-keeper.sh
1001 factory-live-check.sh
2901 finch_attach.py
3227 finch_roster_map.py
2346 fix_hermes_config.py
1717 fix_paperclip_api_url.sh
1572 founder-decisions-20260629.txt
1072 gemini-key-clarification.txt
1636 gemini-vertex-method.md
2466 handoff-wake-protocol.md
1304 inline-coach-correction.txt
4469 isolation-fix-design-2026-06-30.md
9098 issue-AIN-183.json
4440 issue-AIN-258.json
17191 issue-AIN-95.json
1832 janitor.sh
2135 jessica-bundle.json
6266 jessica-now.json
224 landing
2288 lane-adaptive-llm-off-review.md
1691 lane-agent-tooling-dashboard.md
4907 lane-content-mining.md
1894 lane-create-coo.md
3167 lane-create-issues.md
3400 lane-design-map.md
2394 lane-donna-niftypm.md
2517 lane-gemini-newkey.md
2372 lane-gemini-sdk-retest.md
2100 lane-gemini-spike.md
1982 lane-gemini-vertex.md
1488 lane-growth-A.md
1507 lane-growth-B.md
4507 lane-growth-distribution.md
4105 lane-handoff-wake-protocol.md
4752 lane-landing-fixes.md
2477 lane-lesson-shell-port.md
3000 lane-merge-train-v2.md
2497 lane-merge-train.md
1620 lane-org-relook.md
2148 lane-org-restructure.md
1693 lane-pr-resolution.md
4930 lane-practice-arena-v2.md
2635 lane-roadmap-mc.md
1877 lane-team-structure.md
224 lanes
692 launch-content-mining.sh
718 launch-growth-distribution.sh
1465 launch-lanes-2026-06-29b.sh
2107 launch-wave5.sh
1832 learner-flow-doctrine.txt
128 mediaeng
384 mergify
1891 monica-fire-monitor.sh
1643 monica-route-monitor.sh
76621 org-relook-map.html
13339 org-restructure-report.html
1115 org-restructure.txt
1660 original-mockups-reference.txt
6910 paperclip-runtime-audit-SKILL.md
2359 paperclip_codex_slim.py
1279 paperclip_projdoc_fix.py
2780 pr-bot-watcher.sh
1414 proj-detail.json
130845 projects.json
982 recon5-comment.py
1599 recovered-docs-provenance.txt
1359 relaunch-failed-lanes.sh
1232 release-marshal.sh
96 reports
11392 sched-hb.json
1736 setup-media-profile.sh
128 shared-materials-preserve
2823 status-decay-report.json
1141 style-decision-correction.txt
3953 team-utilization-monitor.py
2065 u2-monitor.sh
2228 u8-monitor.sh
721 unblock.py
3298 update_issues.py
224 ux-council
14953 vds-containerization-design-2026-06-30.html
8407 vds-containerization-design-2026-06-30.md
3154 vds-coo-ops-loop.sh
2132 vds-exec.sh
4686 vds-watchdog-live.sh
4418 vds-watchdog.sh
1476 verify_attach.py
3814 watchdog.sh
4890 workflow-prompt-pulse-example.md
961 workspace_gitfix.sh
1250250 workspaces.json

--- subdirs ---
[ab-variants/]
career-switcher-desktop.png
career-switcher-mobile.png
founder-exec-desktop.png
founder-exec-mobile.png
ops-manager-desktop.png
ops-manager-mobile.png
persona-landing-ab-report.md
senior-pro-desktop.png
[donna-relook/]
FOUNDER-READABLE-AGENT-IDENTITY-REPORT.html
FOUNDER-READABLE-AGENT-IDENTITY-REPORT.md
[landing/]
landing-report.html
staging-chromium-desktop.png
staging-chromium-mobile.png
staging-webkit-desktop.png
staging-webkit-mobile.png
[lanes/]
docker-PHASE1-REPORT.md
docker-base-ci.txt
docker-phase2-codex-lane.txt
pkm-groundwork-REPORT.md
pkm-producer-groundwork.txt
[mediaeng/]
SOUL.md
skills
[mergify/]
academy-final.mergify.yml
academy-fixed.mergify.yml
academy-reportonly.mergify.yml
aina-platform.mergify.yml
ir-batch1.txt
ir-batch2.txt
ir-batch3.txt
ir-map.json
[reports/]
2026-06-29-founder-testing-evaluation-summary.html
[shared-materials-preserve/]
aina-design-system-2026-06-30.tar.gz
ui-lesson-previews-2026-06-30.tar.gz
[ux-council/]
01-home.png
05-assessment-question.png
06-assessment-question-answered.png
08-lesson.png
index.html

############ PKM-monorepo: what's already committed vs uncommitted ############
current branch: ali/m3-context-graph-2026-06-29
--- uncommitted (this session's docs/solutions update etc.) ---
 M docs/solutions/architecture-patterns/aina-autonomous-agent-org-operating-style-2026-06-29.md
 M transcripts/state/reality-annotations.jsonl
 M wiki/.wiki-failure-counts.json
 M wiki/agent-queue.html
 M wiki/agent-queue.md
 M wiki/daily/2026-05-10.html
 M wiki/daily/2026-05-11.html
 M wiki/daily/2026-05-12.html
 M wiki/daily/2026-05-13.html
 M wiki/daily/2026-05-14.html
 M wiki/daily/2026-05-15.html
 M wiki/daily/2026-05-16.html
 M wiki/daily/2026-05-17.html
 M wiki/daily/2026-05-18.html
 M wiki/daily/2026-05-19.html
 M wiki/daily/2026-05-20.html
 M wiki/daily/2026-05-21.html
 M wiki/daily/2026-05-22.html
 M wiki/daily/2026-05-23.html
 M wiki/daily/2026-05-24.html
--- existing archive dir contents ---
AINA-LAUNCH-PLAN.md
AINA_OS_Reference_2026-06-28.md
ARENA-DOCTRINE.md
CODEX-BRIDGE-BRIEF.md
CODEX-MASTER-BUILD-BRIEF.md
CODEX-RECONCILE-BACKLOG-BRIEF.md
CODEX-ROLL-EXECUTION-BRIEF.md
CONTENT-DOCTRINE.md
EXECUTION-STATE-2026-06-30.md
LEARNER-UX-CANON.md
PKM-STEWARD-CHARTER.md
README.md
RELOOK-BRIEF-finch-donna.md
REVIEW-HARNESS.md
aina-factory-map-and-academy-first-plan-2026-06-30.html
aina-factory-map-and-academy-first-plan-2026-06-30.md
aina-factory-native-selfdriving-design-2026-06-30.html
aina-factory-native-selfdriving-design-2026-06-30.md
aina-factory-task-history-forensics-2026-06-30.html
aina-factory-task-history-forensics-2026-06-30.md
aina-launch-readiness-evidence.md
aina-org-session-lineage-2026-06-29.html
aina-org-session-lineage-2026-06-29.md
botfix-106.md
botfix-107.md
botfix-mc11.md
capture-2026-06-29-roster-roadmap-tools-content.md
coo-operating-loop.md
design-reconciliation-map.html
docker-adoption-scope-2026-06-30.html
docker-adoption-scope-2026-06-30.md
gemini-vertex-method.md
handoff-wake-protocol.md
lane-adaptive-llm-off-review.md
lane-agent-tooling-dashboard.md
lane-content-mining.md
lane-create-coo.md
lane-create-issues.md
lane-design-map.md
lane-donna-niftypm.md

rsync exit: 0
=== archive now has (new/updated session deliverables present?) ===
  ✓ SESSION-CLOSEOUT-2026-07-01.md (   16921 bytes)
  ✓ SESSION-CLOSEOUT-2026-07-01.html (   29113 bytes)
  ✓ isolation-fix-design-2026-06-30.md (    4469 bytes)
  ✓ EXECUTION-STATE-2026-06-30.md (   41436 bytes)
=== archive dir size + file count ===
 12M
     186

=== staged (session paths only — verify no nightly wiki noise) ===
staged count:      125

=== commit landed ===
bdbc57dbc docs(aina-factory): session artifacts + closeout + native-mechanics learning (2026-07-01)
=== push ===
To https://github.com/oscalar/pkm-monorepo.git
   3a78c61dd..bdbc57dbc  HEAD -> ali/m3-context-graph-2026-06-29

=== PKM-monorepo: is the plan also on the remote? ===
  origin/ali/m3-context-graph-2026-06-29
  → plan committed earlier, on remote ✓
=== this session's artifact commit on remote? ===
  origin/ali/m3-context-graph-2026-06-29

=== aina-design repo (design system) pushed? ===
380de86 Preserve AINA Design System + shared lesson previews (durable home)
## main...origin/main

=== Mac copy locations (all git-backed, on the Mac) ===
  archive:  /Users/Ali/PKM-monorepo/docs/aina-factory-archive-2026-06-30/  (     186 files)
  plan:     /Users/Ali/PKM-monorepo/docs/plans/2026-06-30-002-feat-native-selfdriving-paperclip-factory-plan.md
  learning: /Users/Ali/PKM-monorepo/docs/solutions/architecture-patterns/aina-autonomous-agent-org-operating-style-2026-06-29.md
  design:   /Users/Ali/Downloads/AI Native Academy Design System/ (repo: ainative-academy/aina-design)
  scratch:  /Users/Ali/PKM/scratch/pkm-deepdive/ (working copy, on Mac)

=== session transcripts for this project (June 27 → now) ===
423824 Jun 2 10:05 7107a039-23b4-4e56-a779-fd1f65aab418.jsonl
48709 Jun 2 17:50 6458daac-25f7-4045-b215-878cbed0ddec.jsonl
4926205 Jun 2 08:27 bddec58b-8093-48ee-9156-d07014f15b3f.jsonl
7257664 Jun 20 21:18 1c80ee17-001d-433b-b780-f1c2f60d2158.jsonl
3165361 Jun 26 20:12 308a99a7-9045-4b6d-b6e5-fbbb313d5399.jsonl
3727117 Jun 26 20:12 f9c77360-476e-4c68-8408-2a541fd4db38.jsonl
4653692 Jun 26 20:26 c33bc847-a19a-4ca4-b099-2a0fcf38dd24.jsonl
5602792 Jun 26 20:12 f206176f-d514-40c8-ab7b-4ada2a2f9403.jsonl
290475 Jun 3 10:26 315ec82a-c356-482c-8d1a-7e6158705cb6.jsonl
45342 Jun 3 10:47 7c5071de-df17-491c-96ed-9e908ca672a2.jsonl
59988 Jun 3 10:47 a1f26fe5-aed2-429e-8df5-2cdeed4da990.jsonl
1028707 Jun 5 09:13 ce577fb4-a647-4a70-8193-7ceeacdf98c7.jsonl
1202898 Jun 5 09:13 421217fa-046f-494f-b64f-d0a1f4793d7d.jsonl
169838 Jun 5 21:32 a4ad881f-5631-4512-902f-400f43e171c4.jsonl
2674721 Jun 5 05:28 0e4d4ce3-f0e3-40cb-90e0-cc461892a503.jsonl
4325562 Jun 5 18:27 d26419e0-6e63-4d72-9ae6-119178d68fc3.jsonl
9807305 Jun 7 17:43 9a5c6e62-4a43-413f-b883-24892ad212f2.jsonl
1829873 Jun 9 04:07 3ddd28c1-a923-4a61-a638-0a512b8a95fe.jsonl
2273950 Jun 9 04:08 05a17c8d-61c5-4810-aa25-4a53ad86cfec.jsonl
2864301 Jun 9 21:40 b4fe75d9-a0ba-428d-afb7-15ac565df692.jsonl

=== is there a transcript render tool? ===
/Users/Ali/.local/bin/claude-code-transcripts
(eval):6: no matches found: /Users/Ali/PKM/Transcripts/*.py

=== git: what ARE the uncommitted changes? (safe regenerable, or real work?) ===
2703 wiki/sessions
  55 wiki/daily
  38 wiki/projects
  11 wiki
   1 transcripts/state
   1 docs/plans
   1 docs/pkm-deepdive
--- total changed files ---
    2810
--- branch vs main ---
14
commits ahead of main

created /Users/Ali/AINA-Factory-Journey-2026
=== transcript render tool usage ===
Usage: claude-code-transcripts [OPTIONS] COMMAND [ARGS]...

  Convert Claude Code session JSON to mobile-friendly HTML pages.

Options:
  -v, --version  Show the version and exit.
  --help         Show this message and exit.

Commands:
  local*  Select and convert a local Claude Code session to HTML.
  all     Convert all local Claude Code sessions to a browsable HTML archive.
  json    Convert a Claude Code session JSON/JSONL file or URL to HTML.
  web     Select and convert a web session from the Claude API to HTML.
=== recent sessions (this journey, by mtime desc) ===
2026-07-01 02:03   59M  ea21dc9e-a684-460b-b5d8-244fa739715e.jsonl
2026-06-26 20:26  4.4M  c33bc847-a19a-4ca4-b099-2a0fcf38dd24.jsonl
2026-06-26 20:12  3.0M  308a99a7-9045-4b6d-b6e5-fbbb313d5399.jsonl
2026-06-26 20:12  5.3M  f206176f-d514-40c8-ab7b-4ada2a2f9403.jsonl
2026-06-26 20:12  3.6M  f9c77360-476e-4c68-8408-2a541fd4db38.jsonl
2026-06-20 21:18  6.9M  1c80ee17-001d-433b-b780-f1c2f60d2158.jsonl
2026-06-11 22:39  140K  7339bca1-7729-4e74-af6e-571b9c05de54.jsonl
2026-06-11 22:13  112K  82e34db2-1210-4b43-aa28-299635f69a6b.jsonl
Shell cwd was reset to /Users/Ali/PKM

=== json subcommand args ===
Usage: claude-code-transcripts json [OPTIONS] JSON_FILE

  Convert a Claude Code session JSON/JSONL file or URL to HTML.

Options:
  -o, --output PATH  Output directory. If not specified, writes to temp dir
                     and opens in browser.
  -a, --output-auto  Auto-name output subdirectory based on filename (uses -o
                     as parent, or current dir).
  --repo TEXT        GitHub repo (owner/name) for commit links. Auto-detected
                     from git push output if not specified.
  --gist             Upload to GitHub Gist and output a gisthost.github.io
                     URL.
  --json             Include the original JSON session file in the output
                     directory.
  --open             Open the generated index.html in your default browser
                     (default if no -o specified).
  --help             Show this message and exit.
=== kick off render of the main journey session (background) ===
render PID=49393

main render PID=49687
earlier render PID=49688
=== copy ALL artifacts into the folder (complete set) ===
07-all-artifacts:      186 files