Claude Code transcript - page 110/114

1	---
2	title: "feat: Activate native self-driving AINA Paperclip factory"
3	type: feat
4	status: active
5	created: 2026-06-30
6	origin: docs/aina-factory-archive-2026-06-30/aina-factory-native-selfdriving-design-2026-06-30.md
7	target_repo: aina-paperclip-agent-context (+ Paperclip control plane, company 7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9)
8	depth: deep
9	---
10	
11	# feat: Activate native self-driving AINA Paperclip factory
12	
13	**Target systems:** the Paperclip control plane (via `paperclipai` CLI) + the `aina-paperclip-agent-context` repo on the VDS (`aina-vds-tf`). This is infrastructure/configuration work, not application code — "tests" are **self-drive verification** (does a lane run end-to-end with no external nudge?), not unit test files.
14	
15	---
16	
17	## Problem frame
18	
19	The native, ANMS-spec-driven, handoff-wake factory **worked on 06-29** (agents coordinating through Paperclip handoffs + wake, gated by canon-locked Gherkin specs). It broke on **06-30** when a per-task GitHub apparatus (commit+push+PR per task → CI → bot-review-watcher → a jam then stacked with Mergify/merge-train/release-marshal) replaced the native model — verified via the botfix churn metric (3 → 61) and Ali's own words. The external scaffolding is already **torn down and paused**; the 70-item in-review backlog is already **cleared** by parallel verifiers.
20	
21	This plan **activates the native design** (origin doc) so the factory self-drives on Paperclip's own primitives with zero external scaffolding — **restore, don't rebuild**.
22	
23	## Scope boundaries
24	
25	**In scope:** activate the `agent-context-map` per **dev lane** (content-curriculum, data-personalization, product-platform, agentops-tools, qa-release); un-pause + re-point the 7 native routines off the Hermes bridge to native assignment/wake; wire the flow (CEO → heads → members → QA → Frodo release at milestone); always-on for Jessica + heads + one keeper (Atlas); remove the Hermes bridge + all remaining external scaffolding; GitOps (incl. Mergify) relocated into Frodo's milestone runbook.
26	
27	### Deferred to Follow-Up Work
28	- **growth-media (marketing) + security/legal lanes** — remain draft/parked until Ali approves public/legal lanes; they need **no git/PR/CI**.
29	- **Docker** containerization of lanes — validated capability, parked; not part of this activation.
30	- **PKM-nightly-to-VDS** — separate adjacent decision.
31	- **Canon reconciliation** of the scratch-flagged doctrines into CANON-INDEX — a canon-steward (Finch) task, not this plan.
32	
33	### Outside this plan's identity
34	- Any per-task GitHub PR/CI, any external cron/watchdog/bridge, any script-based orchestration. If a job needs doing, a Paperclip **agent** does it on a native **routine**.
35	
36	---
37	
38	## Key technical decisions
39	
40	1. **Native primitives replace every external script** — `routines`/`triggers` (was COO cron), `agent wake`/heartbeat (on assignment/@mention), `issue comment`+`interaction:create`+`successfulRunHandoff` (inter-agent handoff), `child:create`+issue-tree (decomposition), `recovery-actions` (was watchdog), `approval` (founder gates), `org` chart (leads).
41	2. **Hybrid, team-head-driven** — a minimal keeper routine (Atlas) only surfaces ready/stalled work + fires recovery; **heads route** (assign N members per task, first-verify in-team).
42	3. **Always-on ≈ 9** — Jessica + department heads + Atlas keeper. Everyone else wakes on assignment/@mention (not heartbeat).
43	4. **Option (b) release** — dev inner loop internal (no per-task git); branches/PRs only as *evidence* where a lane needs them; **Frodo's team owns all GitOps (incl. Mergify) at milestone granularity**; `dev→main` batch promotion via release runbook; preview URLs via wrangler; marketing/media git-free.
44	5. **Producer ≠ verifier**, enforced by the map's default-verifier pairing + `aina-runsafe-gate` before every wake/assign/handoff.
45	6. **Lane-by-lane, reversible** — each activation is a config apply with Paperclip receipts; content-curriculum is already applied+verified and is the reference lane.
46	7. **Workspace/git mechanic (verified 06-30) — the drift cause + the gate on U4.** Paperclip runs each issue in an isolated per-issue workspace **derived from the issue's assigned PROJECT (a git repo; 57 projects exist)**. If an issue has **no `projectId`**, its workspace defaults to **home/codex-home → plugin re-discovery → bloat/drift** (this is the "fall back to codex-home" failure). Current state: 216/263 issues project-bound; **47 have no project**. The watchdog's `git-init` self-heal was a band-aid for the project-less ones. **Therefore every active dev-lane issue must be project-bound (native git-backing) BEFORE the watchdog is removed (U4).** Keep isolated-workspaces **on** (per-issue isolation is correct); the fix is project-binding, not toggling it off. Docker is verified **parked/non-interfering** (0 containers, not in the execution path) — keep parked.
47	
48	---
49	
50	## High-level design (directional, not implementation spec)
51	
52	```
53	Native routine (keeper: Atlas) surfaces ready work ─┐
54	                                                    ▼
55	CEO Jessica ── org-chart ── Dept Head ── issue:update --assignee (+ child:create) ── Member
56	                              │  first-verify (comment/interaction)                    │ wakes, builds
57	                              └──────────────── handoff (successfulRunHandoff) ─────────┘
58	                                                    ▼
59	QA gate: Gimli (adversarial) → Éowyn (visual/E2E) → Calibrator (2nd-verifier vs canon+PKM)
60	                                                    ▼
61	Frodo Release/GitOps team ── AT MILESTONE ── branches/PR/CI/Mergify · runbook · dev→main · deploy · preview URL
62	                                                    ▼
63	recovery-actions self-heal any stalled issue (no watchdog)
64	```
65	*This illustrates the intended approach and is directional guidance for review, not implementation specification.*
66	
67	---
68	
69	## Implementation units
70	
71	### U1. Reconcile activation prerequisites (read-only)
72	
73	**Goal:** pin the exact facts the activation needs, so no unit guesses at runtime.
74	**Requirements:** advances all downstream units.
75	**Dependencies:** none.
76	**Files:** (control-plane reads only) `paperclipai routine get <id>` for all 7 routines; `paperclipai org get`; `aina-paperclip-agent-context/mappings/agent-context-map.md`.
77	**Approach:** capture (a) each routine's current **trigger** structure + `assigneeAgentId` (to know what "re-point off Hermes" changes), (b) the **qa-release head** name (Root/Gimli/Frodo split — confirm from the map/org), (c) which lanes are `applied-live-verified` vs `mapped-not-applied`, (d) the exact `aina-runsafe-gate` + scope-precheck invocation from `AGENTS.md`, (e) **the 47 project-less issues — which lanes they belong to** (dev = must-fix before U4; marketing/parked = out of scope), and the project→lane binding map (57 projects).
78	**Verification:** a short reconciliation note listing each routine's trigger, the confirmed heads per dev lane (content=Monica), the runsafe-gate command, and **the list of project-less dev issues needing binding** — no unknowns remain for U2–U7.
79	**Test scenarios:** `Test expectation: none — read-only reconciliation.`
80	
81	### U2. Content-curriculum lane — prove native self-drive end-to-end
82	
83	**Goal:** make the *already-applied* content-curriculum lane run a real task fully self-driven, as the reference implementation every other lane copies.
84	**Requirements:** KTD 1,2,5; the "restore what worked" thesis.
85	**Dependencies:** U1.
86	**Files:** Paperclip control plane (issue assign/comment/interaction on a content-curriculum goal); `aina-paperclip-agent-context/lanes/content-curriculum/`.
87	**Approach:** place/pick one ready content-curriculum issue → **head Monica** assigns a member (`issue update --assignee`) → member **wakes** (native), builds in scoped workspace → Monica **first-verifies** in-team (comment/interaction) → **handoff** to QA → mark done. No external nudge, no git. Confirm each hop fires natively.
88	**Patterns to follow:** the map's content-curriculum default-verifiers (Monica); the assignment-envelope template.
89	**Test scenarios (self-drive verification):**
90	- Happy path: a ready issue flows assign → wake → build → verify → handoff → done with **zero** operator action after the head assigns.
91	- Wake: the assigned member's heartbeat/inbox fires from the assignment alone (no `agent wake` script).
92	- @mention: a comment tagging a second agent wakes it and it responds.
93	- Producer≠verifier: the member and Monica are different agents; runsafe-gate passes.
94	- Negative: an issue with no assignee does **not** auto-run (heads route, not the keeper).
95	**Verification:** one content-curriculum issue reaches `done` via native handoff-wake only, with Paperclip activity-log evidence for each hop.
96	
97	### U3. Re-point the 7 routines off Hermes + set always-on
98	
99	**Goal:** the native scheduler runs without the Hermes bridge; the right agents are always-on.
100	**Requirements:** KTD 1,2,3.
101	**Dependencies:** U1, U2.
102	**Files:** Paperclip routines (7) via `paperclipai routine update` / `trigger:update`; agent heartbeat config for Jessica + heads + Atlas.
103	**Approach:** for each routine, replace the **Hermes-bridge dispatch** with a native action (assignment/wake/`child:create`) and **un-pause** only those that serve dev lanes now (Atlas keeper, Gimli verify, Éowyn E2E, Frodo release; Donna digest/cost = monitor-only; Finch canon; hold marketing-adjacent). Set **always-on heartbeat** for Jessica + department heads + the Atlas keeper; keep everyone else on-demand.
104	**Patterns to follow:** the existing routine descriptions (owner/cadence intent) — preserve intent, swap the dispatch mechanism.
105	**Test scenarios (self-drive verification):**
106	- Keeper (Atlas) surfaces a ready/stalled item to the correct head **without** touching the Hermes bridge.
107	- A stalled issue triggers native `recovery-actions` (no watchdog).
108	- Always-on set = Jessica + heads + Atlas only; a non-lead member is **not** heartbeating.
109	- No routine references or calls the Hermes bridge after update.
110	**Verification:** `routine list` shows the dev routines `active` with native triggers; Hermes bridge receives zero calls over one keeper cycle; always-on roster is exactly the intended ~9.
111	
112	### U4. Remove the Hermes bridge + all remaining external scaffolding
113	
114	**Goal:** delete every external orchestration surface so nothing outside Paperclip can nudge the factory.
115	**Requirements:** "zero external scaffolding" scope.
116	**Dependencies:** U3 (native path proven first) **AND U8 (project-binding done — the watchdog's git-init safety net can only be removed once workspaces are natively git-backed).**
117	**Files (VDS):** `/srv/aina/ops/` (coo-ops-loop.sh, watchdog.sh, release-marshal.sh, pr-bot-watcher.sh, merge-train lanes), crontab, the Hermes↔Paperclip bridge / kanban_decomposer, hermes dispatch loop.
118	**Approach:** confirm crons already paused → **retire** (archive + remove) the external scripts; disable the Hermes bridge dispatch path (kanban_decomposer); ensure hermes stays only as Donna's monitor/assist surface (systemd, no dispatch). Leave the GitHub bots disabled (already `disabled_manually`).
119	**Test scenarios (verification):**
120	- After removal, a placed issue still flows end-to-end (native path carries it) — proves nothing depended on the scaffolding.
121	- No cron, no watchdog, no bridge process participates in dispatch.
122	- hermes gateway still up (monitor-only) via systemd `Restart=always`.
123	**Verification:** crontab has no factory dispatch/merge/watch entries; no external process appears in a dispatch trace; a full lane cycle completes with scaffolding gone.
124	
125	### U5. QA gate wiring (Gimli · Éowyn · Calibrator)
126	
127	**Goal:** the cross-lane QA gate runs as native verifier assignments after a head's first-verify.
128	**Requirements:** KTD 5; producer≠verifier.
129	**Dependencies:** U2.
130	**Files:** Paperclip control plane (verifier assignment/interaction); the qa-release lane bundle.
131	**Approach:** on head handoff, the issue routes to **Gimli** (adversarial) → **Éowyn** (visual/E2E, may run staging preview per milestone) → **Calibrator** (2nd-verifier vs canon+PKM) before `done`/promotion-eligible. Each is a **separate** agent from the producer; `aina-runsafe-gate` blocks producer=verifier.
132	**Test scenarios (self-drive verification):**
133	- A handed-off issue is picked up by Gimli via native assignment/wake (no script).
134	- A verifier rejection sends the issue **back** to the lane (native), not to a merge.
135	- Producer=verifier is blocked by the runsafe-gate.
136	- Éowyn's E2E can target a wrangler staging preview when the issue is release-bound.
137	**Verification:** an issue traverses head-verify → Gimli → Éowyn → Calibrator → eligible, with a rejection round-trip demonstrated once.
138	
139	### U6. Frodo Release/GitOps team + milestone runbook
140	
141	**Goal:** all git operations (incl. Mergify) live in Frodo's team and fire **per milestone**, promoting `dev→main` in batches with a preview URL.
142	**Requirements:** KTD 4; option (b).
143	**Dependencies:** U5.
144	**Files:** the qa-release/Frodo lane bundle; a release runbook doc in `aina-paperclip-agent-context/lanes/qa-release/`; the (relocated) `.mergify.yml` scoped to release branches; wrangler preview/deploy invocation.
145	**Approach:** define Frodo's runbook: at milestone/epic close, gather the verified work → run CI/Mergify **once** on the release branch → promote `dev→main` (deploy source) → post the Cloudflare **preview URL** to Ali along the way. Mergify is a **release** tool here, not a per-task gate. Marketing/media never enter this path.
146	**Technical design (directional):** milestone-gate = all lane issues for the milestone `done` + QA-passed → Frodo assembles release branch → CI/Mergify → promote → deploy → notify Ali (preview + prod). *Directional only.*
147	**Test scenarios (verification):**
148	- No git operation fires at the task level; the first git action is Frodo's milestone assembly.
149	- A milestone with all issues verified triggers exactly one release cycle → preview URL delivered.
150	- Mergify runs only on the release branch, not per-task PRs.
151	- A marketing issue completes with **no** branch/PR/CI.
152	**Verification:** one simulated milestone promotes `dev→main` via Frodo's runbook with a single CI/Mergify pass + preview URL; zero per-task git in the trace.
153	
154	### U7. Replicate lane-by-lane to remaining dev lanes
155	
156	**Goal:** apply the proven pattern to data-personalization, product-platform, agentops-tools.
157	**Requirements:** full dev-lane coverage.
158	**Dependencies:** U2–U6 proven on content-curriculum.
159	**Files:** `agent-context-map` apply per lane; per-lane heads (Laurie/data, Richard/platform, Jared/agentops).
160	**Approach:** for each lane in order, apply the map (role/verifier/scoped context), confirm the head, and run the U2 self-drive verification. Prove each lane self-drives before the next. Preserve the ~20 rejected + never-built tasks — they re-enter the restored native flow, not the old GitHub path.
161	**Test scenarios (self-drive verification):** per lane, repeat U2's happy-path + producer≠verifier + no-per-task-git checks.
162	**Verification:** each dev lane completes one real issue end-to-end natively; growth-media/legal remain parked.
163	
164	---
165	
166	### U8. Guarantee new dev issues inherit a project (git-backed workspaces)
167	
168	**Goal:** every *new* dev-lane issue inherits its lane **project** so its isolated workspace is git-derived — closing the home/codex-home fallback (the drift) natively, so the watchdog's git-init band-aid can be removed.
169	**Requirements:** KTD 7; safe removal of U4.
170	**Dependencies:** U1.
171	**Note (U1 finding):** the 47 project-less issues are **all done/cancelled — zero active**. All active/future work is already project-bound. So this unit is *lighter than first scoped*: no backfill needed; the job is **default inheritance for new issues** only.
172	**Files:** Paperclip control plane (lane/goal → default project binding); the 57 projects ↔ lane map.
173	**Approach:** for each dev lane, set the goal/lane default so a newly-created issue inherits the correct lane project (Curriculum→content, Data Engine Room→data, Platform Engineering→platform, AgentOps→agentops, qa-release→Frodo). Verify a fresh test issue lands git-backed with no git-init. (Historical project-less issues are done — left as-is.)
174	**Test scenarios (verification):**
175	- A newly-created dev issue in an activated lane inherits a project → its workspace is git-backed with no git-init step.
176	- A previously project-less dev issue, once bound, passes `codex_local` workspace validation.
177	- With the watchdog OFF (simulated), a project-bound issue's agent does **not** fall back to home/codex-home.
178	**Verification:** zero project-less **dev** issues remain; a sample agent run produces a git-backed workspace and no codex-home fallback, with the watchdog inactive.
179	
180	---
181	
182	## System-wide impact
183	
184	- **Agents/heads:** Jessica + heads become always-on; members become wake-on-assignment — a behavioral shift from the 06-30 push model.
185	- **Cost:** always-on ≈ 9 (not 62); GitHub minutes → ~0 between milestones; no per-task CI churn.
186	- **Founder surface:** Jessica/Donna produce founder-readable digests (no `/srv` paths); preview URLs at milestones.
187	- **Reversibility:** every lane activation is a receipted config apply; the removed scripts are archived, not destroyed.
188	
189	## Risks & mitigations
190	
191	- **Native wake doesn't fire as expected** → U2 proves one lane end-to-end *before* removing scaffolding (U4 depends on U3/U2). If wake is unreliable, stop at U2 and diagnose — do not remove the safety nets.
192	- **Re-pointing a routine breaks its intent** → U1 captures each routine's current trigger; changes preserve owner/cadence intent, swap only the dispatch mechanism; reversible via `routine revision:restore`.
193	- **A lane self-approves** → runsafe-gate + producer≠verifier enforced; U5 demonstrates a rejection round-trip.
194	- **Removing scaffolding strands in-flight work** → U4 verifies a full cycle completes *after* removal; backlog already cleared.
195	
196	## Deferred to implementation
197	
198	- Exact `routine update` payloads / trigger JSON (captured in U1, applied in U3).
199	- The qa-release head name (confirmed in U1).
200	- Whether Éowyn's E2E routine deploys its own wrangler preview or reuses Frodo's (decide when wiring U5/U6).
201	- Keeper (Atlas) cadence — start conservative, tune after U2.
202	
203	## Verification (overall)
204	
205	Success = a goal placed in a dev lane flows head → member → QA → (at milestone) Frodo release + preview URL, **with no external nudge, no cron, and no per-task GitHub roundtrip**; stalls self-heal via `recovery-actions`; an @mentioned agent wakes; zero `.botfix` churn; zero GitHub-minutes burn between milestones.
206	
207	---
208	
209	**Origin:** `docs/aina-factory-archive-2026-06-30/aina-factory-native-selfdriving-design-2026-06-30.md` (LOCKED design) · reconciled + verified across the full session + prior-session history.
210	

#!/usr/bin/env bash
# vds-exec.sh — single multiplexed SSH channel to the VDS (PKM lane).
#
# WHY: when many workflow lanes hit the VDS in parallel, each would otherwise open
# its own SSH connection → duplicate sessions / "dedup" churn / rate-limit / host-key
# noise. This routes ALL lanes through ONE ControlMaster connection (pre-warmed once);
# every parallel session multiplexes over that single channel. Writes can be serialized
# with run-locked. Portable to macOS (no flock dependency).
#
# Usage:
#   vds-exec.sh prewarm                 # open the master once (do this before fan-out)
#   vds-exec.sh status                  # is the master alive?
#   vds-exec.sh run   '<remote cmd>'    # concurrent-safe remote command (reads)
#   vds-exec.sh runl  '<remote cmd>'    # serialized remote command (writes)
#   vds-exec.sh stop                    # close the master
set -uo pipefail

VDS_HOST="${VDS_HOST:-aina-vds-tf}"
CM_DIR="${CM_DIR:-$HOME/.ssh/cm}"
CP="${CP:-$CM_DIR/pkm-vds.sock}"
LOCKDIR="${LOCKDIR:-$HOME/PKM/scratch/pkm-deepdive/.vds-write.lock.d}"
SSH_OPTS=(
  -o BatchMode=yes
  -o ConnectTimeout=12
  -o ServerAliveInterval=30
  -o ServerAliveCountMax=4
  -o ControlMaster=auto
  -o "ControlPath=$CP"
  -o ControlPersist=15m
)

mkdir -p "$CM_DIR" 2>/dev/null || true
chmod 700 "$CM_DIR" 2>/dev/null || true

cmd="${1:-help}"; shift 2>/dev/null || true

case "$cmd" in
  prewarm)
    ssh "${SSH_OPTS[@]}" "$VDS_HOST" 'echo prewarm_ok; hostname; date "+%Y-%m-%dT%H:%M:%S%z"'
    ;;
---EXIT 0---

prewarm_ok
vmi3344880
2026-06-30T22:43:06-0400
===STATUS===
Master running (pid=88128)

Task #6 created successfully: U2: Prove content-curriculum self-drives via native wake

/usr/bin/paperclipai
---PATH---
---WHICH---
/usr/bin/paperclipai

Usage: paperclipai [options] [command]

Paperclip CLI — setup, diagnose, and configure your instance

Options:
  -V, --version                                             output the version number
  -h, --help                                                display help for command

Commands:
  onboard [options]                                         Interactive first-run setup wizard
  doctor|--fix [options]                                    Run diagnostic checks on your Paperclip setup
  env [options]                                             Print environment variables for deployment
  configure [options]                                       Update configuration sections
  db:backup [options]                                       Create a one-off database backup using current config
  allowed-hostname [options] <host>                         Allow a hostname for authenticated/private mode access
  run [options]                                             Bootstrap local setup (onboard + doctor) and run Paperclip
  heartbeat                                                 Heartbeat utilities
  context                                                   Manage CLI client context profiles
  connect [options]                                         Interactively connect the CLI as a board operator or agent
  company                                                   Company operations
  issue                                                     Issue operations
  agent                                                     Agent operations
  project                                                   Project operations
  goal                                                      Goal operations
  token                                                     Manage Paperclip API tokens
  agent-prompt [options] <agent> <agentApiKey> <prompt...>  Create/update Paperclip work for an agent using an agent API key
  board                                                     Board operator operations
  approval                                                  Approval operations
  activity                                                  Activity log operations
  dashboard                                                 Dashboard summary operations
  cost                                                      Cost and finance operations
  finance                                                   Finance event and summary operations
  budget                                                    Budget policy and incident operations
  org                                                       Organization chart operations
  agent-config                                              Agent configuration summaries
  workspace                                                 Execution workspace operations
  environment                                               Environment operations
  project-workspace                                         Project workspace operations
  whoami [options]                                          Show current CLI auth identity
  health [options]                                          Check API health

=== AGENT ===
Usage: paperclipai agent [options] [command]

Agent operations

Options:
  -h, --help                                                 display help for command

Commands:
  me [options]                                               Show the current agent identity
  inbox [options]                                            List current agent assigned inbox items
  inbox-mine [options]                                       List current agent inbox items touched or archived by a board user
  list [options]                                             List agents for a company
  get [options] <agentId>                                    Get one agent
  create [options]                                           Create an agent from a JSON payload
  hire [options]                                             Create an agent hire request
  update [options] <agentId>                                 Update an agent from a JSON payload
  delete [options] <agentId>                                 Delete an agent
  pause [options] <agentId>                                  Pause an agent
  resume [options] <agentId>                                 Resume an agent
  approve [options] <agentId>                                Approve a pending agent
  terminate [options] <agentId>                              Terminate an agent
  heartbeat:invoke [options] <agentId>                       Invoke an agent heartbeat
  claude-login [options] <agentId>                           Trigger Claude login for an agent
  permissions:update [options] <agentId>                     Update agent permissions
  configuration [options] <agentId>                          Get redacted agent configuration
  config-revisions [options] <agentId>                       List agent config revisions
  config-revision:get [options] <agentId> <revisionId>       Get one agent config revision
  config-revision:rollback [options] <agentId> <revisionId>  Roll an agent back to a config revision
  runtime-state [options] <agentId>                          Get agent runtime state
  runtime-state:reset-session [options] <agentId>            Reset an agent runtime session
  task-sessions [options] <agentId>                          List agent task sessions
  skills [options] <agentId>                                 List agent skills
  skills:sync [options] <agentId>                            Sync desired skills onto an agent
  instructions-path:update [options] <agentId>               Update an agent instructions path. Process adapters require adapterConfigKey and relative paths require adapterConfig.cwd.
  instructions-bundle [options] <agentId>                    Get an agent instructions bundle
  instructions-bundle:update [options] <agentId>             Update an agent instructions bundle
  instructions-file:get [options] <agentId>                  Get an agent instructions file
  instructions-file:put [options] <agentId>                  Create or update an agent instructions file
  instructions-file:delete [options] <agentId>               Delete an agent instructions file
  wake [options] <agentRef>                                  Request a heartbeat wakeup for an agent
  local-cli [options] <agentRef>                             Create an agent API key, install local Paperclip skills for Codex/Claude, and print shell exports
  prompt [options] <prompt...>                               Create/update Paperclip work using an agent persona
  help [command]                                             display help for command

=== HEARTBEAT ===
Usage: paperclipai heartbeat [options] [command]

Heartbeat utilities

Options:
  -h, --help      display help for command

Commands:
  run [options]   Run one agent heartbeat and stream live logs
  help [command]  display help for command

=== ISSUE ===
Usage: paperclipai issue [options] [command]

Issue operations

Options:
  -h, --help                                               display help for command

Commands:
  list [options]                                           List issues for a company
  get [options] <idOrIdentifier>                           Get an issue by UUID or identifier (e.g. PC-12)
  delete [options] <issueId>                               Delete an issue
  heartbeat-context [options] <issueId>                    Get heartbeat context for an issue
  create [options]                                         Create an issue
  update [options] <issueId>                               Update an issue
  comment [options] <issueId>                              Add comment to issue
  comments [options] <issueId>                             List issue comments
  comment:get [options] <issueId> <commentId>              Get one issue comment
  comment:delete [options] <issueId> <commentId>           Delete or cancel one issue comment
  approvals [options] <issueId>                            List approvals linked to an issue
  approval:link [options] <issueId> <approvalId>           Link an approval to an issue
  approval:unlink [options] <issueId> <approvalId>         Unlink an approval from an issue
  read [options] <issueId>                                 Mark an issue as read
  unread [options] <issueId>                               Mark an issue as unread
  archive [options] <issueId>                              Archive an issue from the inbox
  unarchive [options] <issueId>                            Unarchive an issue from the inbox
  recovery-actions [options] <issueId>                     List active recovery actions for an issue
  recovery:resolve [options] <issueId>                     Resolve an issue recovery action
  child:create [options] <issueId>                         Create a child issue from a JSON payload
  force-release [options] <issueId>                        Force-release an issue from an agent checkout
  work-products [options] <issueId>                        List issue work products
  work-product:create [options] <issueId>                  Create an issue work product from JSON
  work-product:update [options] <workProductId>            Update a work product from JSON
  work-product:delete [options] <workProductId>            Delete a work product
  documents [options] <issueId>                            List issue documents
  document:get [options] <issueId> <key>                   Get an issue document
  document:put [options] <issueId> <key>                   Create or update an issue document
  interactions [options] <issueId>                         List issue thread interactions
  interaction:create [options] <issueId>                   Create an issue thread interaction from JSON
  interaction:accept [options] <issueId> <interactionId>   Accept an issue thread interaction
  interaction:reject [options] <issueId> <interactionId>   Reject an issue thread interaction
  interaction:cancel [options] <issueId> <interactionId>   Cancel an issue thread interaction
  interaction:respond [options] <issueId> <interactionId>  Respond to an issue question interaction
  tree-state [options] <issueId>                           Get issue tree control state
  tree-preview [options] <issueId>                         Preview issue tree control changes
  tree-holds [options] <issueId>                           List issue tree holds
  tree-hold:create [options] <issueId>                     Create an issue tree hold from JSON
  tree-hold:get [options] <issueId> <holdId>               Get an issue tree hold
  tree-hold:release [options] <issueId> <holdId>           Release an issue tree hold
  attachments [options] <issueId>                          List issue attachments
  attachment:upload [options] <issueId>                    Upload an issue attachment
  attachment:download [options] <attachmentId>             Download an attachment
  attachment:delete [options] <attachmentId>               Delete an attachment
  label:list [options]                                     List issue labels in a company
  label:create [options]                                   Create an issue label
  label:delete [options] <labelId>                         Delete an issue label
  feedback:votes [options] <issueId>                       List feedback votes for an issue
  feedback:vote [options] <issueId>                        Create or update a feedback vote
  document:delete [options] <issueId> <key>                Delete an issue document
  document:lock [options] <issueId> <key>                  Lock an issue document
  document:unlock [options] <issueId> <key>                Unlock an issue document
  document:revisions [options] <issueId> <key>             List issue document revisions
  document:restore [options] <issueId> <key> <revisionId>  Restore an issue document revision
  feedback:list [options] <issueId>                        List feedback traces for an issue
  runs [options] <issueId>                                 List heartbeat runs associated with an issue
  live-runs [options] <issueId>                            List queued and running heartbeat runs associated with an issue
  active-run [options] <issueId>                           Show the active heartbeat run associated with an issue
  feedback:export [options] <issueId>                      Export feedback traces for an issue
  checkout [options] <issueId>                             Checkout issue for an agent
  release [options] <issueId>                              Release issue back to todo and clear assignee
  help [command]                                           display help for command

=== WHOAMI ===
{
  "user": {
    "id": "local-board",
    "name": "Ali",
    "email": "local@paperclip.local"
  },
  "userId": "local-board",
  "isInstanceAdmin": true,
  "companyIds": [
    "7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9"
  ],
  "memberships": [
    {
      "companyId": "7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9",
      "membershipRole": "owner",
      "status": "active"
    }
  ],
  "source": "local_implicit",
  "keyId": null
}

=== ISSUE UPDATE HELP ===
Usage: paperclipai issue update [options] <issueId>

Update an issue

Arguments:
  issueId                     Issue ID

Options:
  --title <title>             Issue title
  --description <text>        Issue description
  --status <status>           Issue status
  --priority <priority>       Issue priority
  --assignee-agent-id <id>    Assignee agent ID
  --project-id <id>           Project ID
  --goal-id <id>              Goal ID
  --parent-id <id>            Parent issue ID
  --request-depth <n>         Request depth integer
  --billing-code <code>       Billing code
  --comment <text>            Optional comment to add with update
  --hidden-at <iso8601|null>  Set hiddenAt timestamp or literal 'null'
  -c, --config <path>         Path to Paperclip config file
  -d, --data-dir <path>       Paperclip data directory root (isolates state from
                              ~/.paperclip)
  --context <path>            Path to CLI context file
  --profile <name>            CLI context profile name
  --api-base <url>            Base URL for the Paperclip API
  --api-key <token>           Bearer token for agent-authenticated calls
  --run-id <id>               Heartbeat run id for agent-authenticated mutations
                              (checkout/release/interactions/in-progress
                              update); falls back to $PAPERCLIP_RUN_ID
  --json                      Output raw JSON
  -h, --help                  display help for command

=== AGENT WAKE HELP ===
Usage: paperclipai agent wake [options] <agentRef>

Request a heartbeat wakeup for an agent

Arguments:
  agentRef                 Agent ID or shortname/url-key

Options:
  -C, --company-id <id>    Company ID for shortname/url-key lookup
  --source <source>        Invocation source (timer, assignment, on_demand,
                           automation) (default: "on_demand")
  --trigger <trigger>      Trigger detail (manual, ping, callback, system)
                           (default: "manual")
  --reason <text>          Wakeup reason
  --payload <json>         JSON object payload
  --idempotency-key <key>  Wakeup idempotency key
  --force-fresh-session    Request a fresh adapter session
  -c, --config <path>      Path to Paperclip config file
  -d, --data-dir <path>    Paperclip data directory root (isolates state from
                           ~/.paperclip)
  --context <path>         Path to CLI context file
  --profile <name>         CLI context profile name
  --api-base <url>         Base URL for the Paperclip API
  --api-key <token>        Bearer token for agent-authenticated calls
  --run-id <id>            Heartbeat run id for agent-authenticated mutations
                           (checkout/release/interactions/in-progress update);
                           falls back to $PAPERCLIP_RUN_ID
  --json                   Output raw JSON
  -h, --help               display help for command

=== ISSUE LIST HELP ===
Usage: paperclipai issue list [options]

List issues for a company

Options:
  -C, --company-id <id>     Company ID
  --status <csv>            Comma-separated statuses
  --assignee-agent-id <id>  Filter by assignee agent ID
  --project-id <id>         Filter by project ID
  --match <text>            Local text match on identifier/title/description
  -c, --config <path>       Path to Paperclip config file
  -d, --data-dir <path>     Paperclip data directory root (isolates state from
                            ~/.paperclip)
  --context <path>          Path to CLI context file
  --profile <name>          CLI context profile name
  --api-base <url>          Base URL for the Paperclip API
  --api-key <token>         Bearer token for agent-authenticated calls
  --run-id <id>             Heartbeat run id for agent-authenticated mutations
                            (checkout/release/interactions/in-progress update);
                            falls back to $PAPERCLIP_RUN_ID
  --json                    Output raw JSON
  -h, --help                display help for command

bytes:       61
=== content/curriculum/monica/assessment/learner agents ===
PARSE FAIL: Expecting value: line 1 column 1 (char 0)

=== raw agents.json ===
error: required option '-C, --company-id <id>' not specified

=== retry with -C ===
[
  {
    "id": "a873590c-2166-4054-9dad-329e17d2c889",
    "companyId": "7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9",
    "name": "Jared",
    "role": "pm",
    "title": "AgentOps Director",
    "icon": null,
    "status": "idle",
    "reportsTo": "6454b8e0-0522-467b-9c5a-64e2700393c2",
    "capabilities

bytes:   384808
total agents: 64

=== key agents (heads, content lane, QA, release, keeper) ===
8674f22f-ff06-4deb-b7b2-9a78c055ba7e | idle     | Éowyn            | qa     | QA — Automation Engineer               | reports→ Richard
d951d059-bd54-44e7-8774-3e48f43ddf32 | idle     | Learner Experience Architect | general | Learner Experience Architect           | reports→ Monica
596f5873-16e0-41dc-8c6b-73089a59ba81 | idle     | Hermes Paperclip Bridge | devops | Donna↔Paperclip Bridge Agent           | reports→ —
958c6092-0b43-433c-8b2b-9d0d957ae150 | idle     | Assessment & Rubric Designer | general | Assessment & Rubric Designer           | reports→ Monica
3bdfbfc6-8498-4fc1-931c-eb3ebecec910 | idle     | Curriculum Architect | general | Curriculum Architect                   | reports→ Monica
b74f5dd3-403d-43c3-ab4c-fd2117723060 | idle     | Calibrator       | qa     | Evaluation Judge                       | reports→ Laurie
6454b8e0-0522-467b-9c5a-64e2700393c2 | idle     | Jessica          | ceo    | CEO / Mission Control                  | reports→ —
ccdea777-861b-4847-92e8-10946702f191 | paused   | Social Content Strategist | general | Social Content Strategist              | reports→ Harvey
2eaf9ae5-eaa7-4e0a-81d1-4fed6d069411 | idle     | Finch            | general | Knowledge & Canon Steward              | reports→ Gandalf
379acc14-2207-432d-92a7-25ab0a85c1fa | idle     | Monica           | pm     | Chief Product & Learning Officer       | reports→ Jessica
2fe6579c-21d5-4af3-b475-f0efe8e35e10 | idle     | Gimli            | qa     | Adversary — Code Reviewer              | reports→ Richard
88b49386-ac86-4b3f-876f-4a0af410fdfe | idle     | Frodo            | devops | Release Manager                        | reports→ Jessica

total projects: 57
9f03824c-126f-436b-8729-a2562974da27 | Curriculum — Tier-1 Launch | repo=— | status=backlog
865bd51f-1a35-4b75-a2f5-104ced0ea523 | Product & Learning — Curriculum Context | repo=— | status=in_progress
727c003c-3b01-45be-b1bd-496a475d70fe | Curriculum - L1-L5 Authoring | repo=— | status=in_progress
5847f0bf-0803-4557-8263-70536d5ded4f | Curriculum - Universal Track Composer | repo=— | status=in_progress
5bcf03f8-20d0-4254-9676-ecf143173e83 | Curriculum - Rubrics & Evaluators | repo=— | status=in_progress
53333693-c9ab-44f9-9dc6-81cae3cce66b | Curriculum - Coverage & Cleanup | repo=— | status=in_progress
07e439a9-0a3b-49d6-aa55-9c927d9d4cd3 | Data - LearnerDO Backbone | repo=— | status=in_progress
00355821-b0e3-4b3d-bd25-48f59360ddf0 | Growth - Content Engine | repo=— | status=in_progress
--- all project names ---
 - Curriculum — Tier-1 Launch | 9f03824c-126f-436b-8729-a2562974da27
 - Lane 1 — Auth + Planner Foundation | a64c0faf-a346-4478-b08a-98b744bbec07
 - Lane 3 — Parallel | 4842d061-f67b-46a4-9508-15c531db08fe
 - Marketing — Public Surface | d076f2cd-8589-408c-bd77-d7e80db6bddc
 - Phase 0 — Foundation | e1cb6778-80d6-41ae-8bf1-b4eb02fbaa21
 - Data Engine Room | 04e7918b-7726-4b4d-a42e-b2a034792e80
 - Security, Privacy & Compliance Context | 7e1f3827-8fd4-4519-823e-728350b59bf0
 - Executive Governance — Mission Control | 0a0f325b-ed1b-49c8-8471-d73040542a4f
 - AgentOps — Paperclip Runtime Context | 4c66639c-0fb3-4481-a77f-f77e62ef7f1a
 - Platform Engineering — Scoped Runtime | 606ba79f-3306-4cd2-b7ed-41287a96dbdf
 - Product & Learning — Curriculum Context | 865bd51f-1a35-4b75-a2f5-104ced0ea523
 - Data & Personalization — Data Engine Context | a16d1ecb-5978-479f-a9cf-43b24bc1c338
 - Research & Intelligence — Evidence Context | 9d2c82e1-24eb-44a5-a53a-b4f8fab199c6
 - Growth & Media — Public Surface Context | d3ba7ac0-cf16-4a73-83fa-f9323cdb8e8f
 - Finch & Living Knowledge Context | 8aaa0913-83db-48f4-a807-ad329de9723c
 - QA & Release Readiness Context | 6a2a8c02-b419-444a-aaf8-71c304d184aa
 - Journey - Lesson Shell & RECON | 3791f838-6740-4e4d-815d-55c7c69a532d
 - Journey - Pricing & Entitlement | 6b5d9c55-c8cc-43ba-a8fa-bca949d47f49
 - Journey - Practice Arena | 6a456b32-7b10-4c96-9159-19ded81174ec
 - Journey - Onboarding & Placement | 8c5ffeea-bfa3-4fac-ac35-93cdca93519a
 - Journey - Chat Tutor | e3e7c559-31ad-43ac-bf55-f9cdf1ca6212
 - Journey - Media Slot Integration | 57ec479a-ff78-423f-a30b-b02b369d329e
 - Curriculum - L1-L5 Authoring | 727c003c-3b01-45be-b1bd-496a475d70fe
 - Curriculum - Universal Track Composer | 5847f0bf-0803-4557-8263-70536d5ded4f
 - Curriculum - Rubrics & Evaluators | 5bcf03f8-20d0-4254-9676-ecf143173e83
 - Curriculum - Coverage & Cleanup | 53333693-c9ab-44f9-9dc6-81cae3cce66b
 - Release - Skill Packaging | cb784947-f599-43d8-b64a-dfac2f69e4dc
 - Growth - Campaign AI-Fluenting | 2b56feb4-571d-4a12-87c4-a5d54794fe9a
 - Growth - Domain Portfolio & Assessment | c6ea2ff5-9cf9-45d4-97d3-2a74417b3c8d
 - AgentOps - Roadmap Integrations | b4518dbf-8ebe-4431-978a-66babf767a4b
 - Data - Personalization | 077fa1cc-cca8-4348-9edb-9a5caaa632c6
 - Data - Vertex Embeddings | 46ca246a-6e93-432c-aa07-0d47a714811e
 - QA - Verification Receipts | 3ca0cb4b-c222-4049-a221-9885bb78d36a
 - QA - Launch Bar | 53770c34-0ba2-4b46-9bda-d5d69501bd2b
 - Data - Telemetry & Privacy | fa576e2c-96f8-43f9-95de-19c6ca3e32b2
 - QA - Visual & Adversarial | dc11c25c-5ed5-4b93-b406-10c8a2f8165c
 - Release - PR Bot Watcher | 8e684f74-7f0a-457b-88c9-1f68bd26c685
 - Growth - MCP/Skills Release | 1b237785-9933-42a1-aa92-b4ebc5d2550b
 - AgentOps - Receipt Enforcement | 17496657-6ac4-4f44-82f0-d868532c15f3
 - Data - DER & Consent Ops | 668f7978-2e8b-4a33-bf99-409b7cd4d06d
 - Data - LearnerDO Backbone | 07e439a9-0a3b-49d6-aa55-9c927d9d4cd3
 - QA - Persona E2E | fa6b0c2e-c71a-4c56-b5f3-9fc1e3ae89c2
 - QA - Coverage & Acceptance | 85a3585e-9792-496e-9aeb-7f6e423e79a9
 - Release - Runbooks | 30152bc7-53a8-465d-9929-5e074a8eb147
 - AgentOps - Governance | 416b6b28-a41a-48e1-9c67-cf6fc0dfae95
 - QA - Evaluator Verification | b589a0cb-61e5-4ef2-b008-038b0ed61213
 - Growth - Media Pipeline | 5532e7c5-d242-4558-b211-0731b5177c98
 - Release - CF Control | 900c9991-b613-4406-84a4-f37a469ed7a7
 - Release - Preview & Health | 6f0bc71a-779f-4df1-82dc-acfd49e58eff
 - Growth - Landing A/B | b816f527-0016-40cc-9f74-255301e773bd
 - Growth - Content Engine | 00355821-b0e3-4b3d-bd25-48f59360ddf0
 - Growth - Referral | 5a0a572b-936e-4ece-90b3-3ea53dfa530f
 - AgentOps - Canon Mining | 8656754f-a3c6-4057-9157-f36a51965b80
 - AgentOps - Memory | 8c8907f4-efbc-49d9-849c-eea9bb56f282
 - AgentOps - MCP Server | ba660998-8ef5-4c01-951f-ba38508bc6cd
 - AgentOps - Factory Health | 29d829bc-50db-4dfb-8607-14f71982a581
 - AgentOps - Mobile/EAS Pipeline | 6c0c89a1-2eaa-4d08-a557-da4b7b4e3812

KEYS: ['archivedAt', 'codebase', 'color', 'companyId', 'createdAt', 'description', 'env', 'executionWorkspacePolicy', 'goalId', 'goalIds', 'goals', 'icon', 'id', 'leadAgentId', 'managedByPlugin', 'name', 'pauseReason', 'pausedAt', 'primaryWorkspace', 'status', 'targetDate', 'updatedAt', 'urlKey', 'workspaces']

id: 727c003c-3b01-45be-b1bd-496a475d70fe
companyId: 7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9
goalId: 0f13f625-7aae-467c-a9b9-c6a55019f670
name: Curriculum - L1-L5 Authoring
description: Lesson corpus, coverage matrix, prose QA, and launch-scope authoring.
status: in_progress
leadAgentId: None
targetDate: None
color: None
icon: None
env: None
pauseReason: None
pausedAt: None
executionWorkspacePolicy: None
archivedAt: None
createdAt: 2026-06-30T01:42:54.770Z
updatedAt: 2026-06-30T01:42:54.770Z
urlKey: curriculum-l1-l5-authoring
goalIds: ["0f13f625-7aae-467c-a9b9-c6a55019f670"]
goals: [{"id": "0f13f625-7aae-467c-a9b9-c6a55019f670", "title": "Curriculum & Learning Design"}]
codebase: {"workspaceId": null, "repoUrl": null, "repoRef": null, "defaultRef": null, "repoName": null, "localFolder": null, "managedFolder": "/home/ali/.paperclip/instances/default/projects/7d58fc13-7c9a-4c87-
workspaces: []
primaryWorkspace: None
managedByPlugin: None

codebase: {
  "workspaceId": null,
  "repoUrl": null,
  "repoRef": null,
  "defaultRef": null,
  "repoName": null,
  "localFolder": null,
  "managedFolder": "/home/ali/.paperclip/instances/default/projects/7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9/727c003c-3b01-45be-b1bd-496a475d70fe/_default",
  "effectiveLocalFolder": "/home/ali/.paperclip/instances/default/projects/7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9/727c003c-3b01-45be-b1bd-496a475d70fe/_default",
  "origin": "managed_checkout"
}
executionWorkspacePolicy: None
=== TODO/BACKLOG issues in content-curriculum projects ===
  AIN-183 | todo     | asg=None | AIN-94-C: Integration test composer with Journey platform (l  [5847f0bf-0803-4557-8263-70536d5ded4f]
  AIN-94 | todo     | asg=None | [curriculum] Universal Track / 500-module composer wiring  [5847f0bf-0803-4557-8263-70536d5ded4f]
  AIN-95 | todo     | asg=None | [curriculum] L1–L5 lesson + rubric + evaluator content cover  [5bcf03f8-20d0-4254-9676-ecf143173e83]
  AIN-159 | todo     | asg=None | [FOUNDER-DECISION] AIN-NEW-PROD-2: 500-module vs. minimum vi  [53333693-c9ab-44f9-9dc6-81cae3cce66b]
  AIN-258 | todo     | asg=None | RECON-9: Clean up stale recovered-era framing  [53333693-c9ab-44f9-9dc6-81cae3cce66b]

=== paperclip/heartbeat systemd services ===
  aina-tailscale-password-sshd.service           loaded    active   running AINA Tailscale-only password SSH bridge
● mission-collector.service                      loaded    failed   failed  AINA Mission Control near-live collector (VDS)
  paperclip.service                              loaded    active   running Paperclip (AINA control plane, loopback-only, paused)

=== running paperclip-related processes ===
ali       112643  0.0  0.7 1114356 245872 ?      Ssl  10:20   0:40 /home/ali/.hermes/hermes-agent/venv/bin/python -m hermes_cli.main --profile aina-chief-of-staff gateway run
ali       898536  0.9  1.5 23276776 523136 ?     Ssl  Jun28  26:10 node /usr/bin/paperclipai run --bind loopback --no-repair
ali       898619  0.0  0.0 225152 26524 ?        S    Jun28   0:07 /usr/lib/node_modules/paperclipai/node_modules/@embedded-postgres/linux-x64/native/bin/postgres -D /home/ali/.paperclip/instances/default/db -p 54329
ali      1477297  0.0  0.0 227752 20224 ?        Ss   18:03   0:00 postgres: paperclip paperclip 127.0.0.1(44550) idle
ali      1931659  0.0  0.1 230848 45112 ?        Ss   21:56   0:00 postgres: paperclip paperclip 127.0.0.1(42978) idle
ali      1932345  0.0  0.0 230324 31512 ?        Ss   21:57   0:00 postgres: paperclip paperclip 127.0.0.1(58720) idle
ali      1938717  0.0  0.1 230856 44840 ?        Ss   22:05   0:00 postgres: paperclip paperclip 127.0.0.1(43482) idle
ali      1940997  0.0  0.1 230400 41904 ?        Ss   22:09   0:00 postgres: paperclip paperclip 127.0.0.1(46798) idle
ali      1948518  0.0  0.1 230336 41356 ?        Ss   22:19   0:00 postgres: paperclip paperclip 127.0.0.1(37016) idle
ali      1951046  0.0  0.1 230488 42960 ?        Ss   22:22   0:00 postgres: paperclip paperclip 127.0.0.1(42768) idle
ali      1959428  0.0  0.0 230136 30612 ?        Ss   22:33   0:00 postgres: paperclip paperclip 127.0.0.1(44518) idle
ali      1959429  0.0  0.0 230272 30152 ?        Ss   22:33   0:00 postgres: paperclip paperclip 127.0.0.1(44524) idle
ali      1960115  0.0  0.0 230320 29584 ?        Ss   22:34   0:00 postgres: paperclip paperclip 127.0.0.1(46032) idle

=== any timers ===

=== company subcommands ===
Usage: paperclipai company [options] [command]

Company operations

Options:
  -h, --help                             display help for command

Commands:
  list [options]                         List companies
  get [options] <companyId>              Get one company
  current [options]                      Get the current scoped company from --company-id, context, env, or agent authentication
  stats [options]                        Get company stats
  create [options]                       Create a company
  update [options] <companyId>           Update a company
  branding:update [options] <companyId>  Update company branding
  archive [options] <companyId>          Archive a company
  export:preview [options] <companyId>   Preview a portable company export
  export:api [options] <companyId>       Export a company through the raw API route
  import:preview [options] <companyId>   Preview a safe company import through the raw API route
  import:apply [options] <companyId>     Apply a safe company import through the raw API route
  feedback:list [options]                List feedback traces for a company
  feedback:export [options]              Export feedback traces for a company
  export [options] <companyId>           Export a company into a portable markdown package
  import [options] <fromPathOrUrl>       Import a portable markdown company package from local path, URL, or GitHub
  delete [options] <selector>            Delete a company by ID or shortname/prefix (destructive)
  help [command]                         display help for command

=== heartbeat run help ===
Usage: paperclipai heartbeat run [options]

Run one agent heartbeat and stream live logs

Options:
  -a, --agent-id <agentId>  Agent ID to invoke
  -c, --config <path>       Path to config file
  -d, --data-dir <path>     Paperclip data directory root (isolates state from
                            ~/.paperclip)
  --context <path>          Path to CLI context file
  --profile <name>          CLI context profile name
  --api-base <url>          Base URL for the Paperclip server API
  --api-key <token>         Bearer token for agent-authenticated calls
  --source <source>         Invocation source (timer | assignment | on_demand |
                            automation) (default: "on_demand")
  --trigger <trigger>       Trigger detail (manual | ping | callback | system)
                            (default: "manual")
  --timeout-ms <ms>         Max time to wait before giving up (default: "0")
  --json                    Output raw JSON where applicable
  --debug                   Show raw adapter stdout/stderr JSON chunks
  -h, --help                display help for command

=== agent heartbeat:invoke help ===
Usage: paperclipai agent heartbeat:invoke [options] <agentId>

Invoke an agent heartbeat

Arguments:
  agentId                Agent ID

Options:
  -c, --config <path>    Path to Paperclip config file
  -d, --data-dir <path>  Paperclip data directory root (isolates state from
                         ~/.paperclip)
  --context <path>       Path to CLI context file
  --profile <name>       CLI context profile name
  --api-base <url>       Base URL for the Paperclip API
  --api-key <token>      Bearer token for agent-authenticated calls
  --run-id <id>          Heartbeat run id for agent-authenticated mutations
                         (checkout/release/interactions/in-progress update);
                         falls back to $PAPERCLIP_RUN_ID
  --json                 Output raw JSON
  -h, --help             display help for command

=== AIN-258: PARSE FAIL — first 200 chars ===
error: unknown option '-C'


=== AIN-183: PARSE FAIL — first 200 chars ===
error: unknown option '-C'


=== AIN-95: PARSE FAIL — first 200 chars ===
error: unknown option '-C'

=== AIN-258 :: RECON-9: Clean up stale recovered-era framing
id: 5ebaae41-bb4a-461d-b215-e5303be3d131
status: todo | projectId: 53333693-c9ab-44f9-9dc6-81cae3cce66b | assignee: None
desc: Replace 30 Track 1, 50/500, Lesson 4 of 16 where they leak into UI/docs; keep the recovered shell design, not its stale commercial frame.
Source: design-reconciliation-map 2026-06-29. council-2026-06-29 design-reconciliation. Builder: Forge/Bridge; Verifier: Eowyn.

=== AIN-183 :: AIN-94-C: Integration test composer with Journey platform (lesson cards resolve from composer output)
id: 317b9bbd-6102-44f3-ab95-9c7785411a78
status: todo | projectId: 5847f0bf-0803-4557-8263-70536d5ded4f | assignee: None
desc: Department: Curriculum & Learning Design
Lane: journey
Skills: curriculum_architect, platform-engineering, Monica
Builder: Jared
Verifier: curriculum_architect
Acceptance: A learner logging into the staging Academy sees a lesson list populated from the composer output, not a hardcoded fixture. Clicking a lesson card resolves to the correct lesson body. Tested for at least one profile at each of L1-L5. No 404s or empty cards.
Depends-on: AIN-94-B, AIN-123
Milestone: M5 — Lesson Wiring + Tutor Integration
Source: council-2026-06-29

=== AIN-95 :: [curriculum] L1–L5 lesson + rubric + evaluator content coverage
id: 1a9e138e-ba80-4714-ab1f-f5e83ac7cd55
status: todo | projectId: 5bcf03f8-20d0-4254-9676-ecf143173e83 | assignee: None
desc: **Lane:** curriculum  ·  **Owner (charter):** curriculum_architect+evaluation_judge  ·  **Canon:** curriculum council ruling 2026-06-18

**ANMS spec (stable-top → flexible-bottom):**
- Intent (stable): Each of L1–L5 has lesson content, rubrics, and evaluator criteria sufficient to teach + assess.
- Approach (flexible): Author/port lesson+rubric+evaluator content per level; evaluator firewall respected.

**Gherkin acceptance:**
```gherkin
Given level Lx
When a learner completes its lessons
Then rubric-based evaluation produces a valid score against the evaluator criteria
```

**Tests:** unit on rubric scoring; integration on lesson→evaluation

_Unassigned (no auto-wake). Assigned to the lane agent once skills are attached. Authored by Ali via Claude, 2026-06-29._

PARSE FAIL: error: unknown option '-C'

=== skills attached ===
  raw: error: unknown option '-C'

KEYS: ['access', 'adapterConfig', 'adapterType', 'budgetMonthlyCents', 'capabilities', 'chainOfCommand', 'companyId', 'createdAt', 'defaultEnvironmentId', 'icon', 'id', 'lastHeartbeatAt', 'metadata', 'name', 'orgChainHealth', 'pauseReason', 'pausedAt', 'permissions', 'reportsTo', 'role', 'runtimeConfig', 'spentMonthlyCents', 'status', 'title', 'updatedAt', 'urlKey']
  access: {"canAssignTasks": true, "taskAssignSource": "explicit_grant", "membership": {"id": "121435bb-c22a-45c8-a58f-e6089ceaeccd", "companyId": "7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9", "principalType": "agent", "principalId": "3bdfbfc6-8498-4fc1-931c-eb3ebecec910", "status": "active", "m
  adapterConfig: {"cwd": "/srv/repos/aina-paperclip-agent-context/workspaces/content-curriculum", "env": {}, "model": "gpt-5.5", "extraArgs": ["--skip-git-repo-check"], "paperclipSkillSync": {"desiredSkills": ["paperclipai/paperclip/paperclip", "paperclipai/paperclip/paperclip-converting-plans-to
  adapterType: codex_local
  budgetMonthlyCents: 20000
  capabilities: None
  chainOfCommand: [{"id": "379acc14-2207-432d-92a7-25ab0a85c1fa", "name": "Monica", "role": "pm", "title": "Chief Product & Learning Officer"}, {"id": "6454b8e0-0522-467b-9c5a-64e2700393c2", "name": "Jessica", "role": "ceo", "title": "CEO / Mission Control"}]
  companyId: 7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9
  createdAt: 2026-06-22T14:22:23.658Z
  defaultEnvironmentId: None
  icon: None
  id: 3bdfbfc6-8498-4fc1-931c-eb3ebecec910
  lastHeartbeatAt: 2026-06-30T12:33:06.158Z
  metadata: {"modelRouting": {"note": "All agents routed to GPT-5.5 via codex_local; leads use high effort, non-leads use medium effort.", "model": "gpt-5.5", "leadClass": "subagent", "updatedAt": "2026-06-25T20:31:00Z", "adapterType": "codex_local", "requestedBy": "Ali", "modelReasoningEffo
  name: Curriculum Architect
  orgChainHealth: {"status": "healthy", "reason": "healthy", "fullChain": [{"id": "3bdfbfc6-8498-4fc1-931c-eb3ebecec910", "companyId": "7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9", "name": "Curriculum Architect", "status": "idle", "reportsTo": "379acc14-2207-432d-92a7-25ab0a85c1fa", "depth": 0, "relatio
  pauseReason: None
  pausedAt: None
  permissions: {"canCreateAgents": false}
  reportsTo: 379acc14-2207-432d-92a7-25ab0a85c1fa
  role: general
  runtimeConfig: {"heartbeat": {"enabled": false, "maxConcurrentRuns": 1}, "modelFallbacks": []}
  spentMonthlyCents: 0
  status: idle
  title: Curriculum Architect
  updatedAt: 2026-06-30T12:33:06.158Z
  urlKey: curriculum-architect
=== skills ===
  count: 0

cwd: /srv/repos/aina-paperclip-agent-context/workspaces/content-curriculum
model: gpt-5.5 | extraArgs: ['--skip-git-repo-check']
paperclipSkillSync keys: ['desiredSkills']
desiredSkills: [
"paperclipai/paperclip/paperclip",
"paperclipai/paperclip/paperclip-converting-plans-to-tasks",
"paperclipai/paperclip/paperclip-create-agent",
"paperclipai/paperclip/paperclip-dev",
"paperclipai/paperclip/para-memory-files",
"local/0a7b309eb2/agent-goal-charter",
"local/55f00a981c/aina-agentops-core",
"local/d4d4032f24/ci-evals-release-gate",
"local/7a44c7c687/companion-html-reviewer",
"local/3c21880423/decide-dont-defer",
"local/9b6e7cc244/humanizer",
"local/d2f6a40d74/idea-to-prd",
"local/54af4280ff/implementation-pr-flow",
"local/97e8eebc5c/landed",
"local/c748495e79/paperclip-cli",
"local/56d2f43498/prd-to-issues",
"local/0ef6b3c008/repo-truth-evidence-table",
"local/1cb56f781c/research-source-intelligence",
"local/feae861d8f/safety-guard",
"local/4c6d23f49b/semantic-data-qa",
"local/45db5a24fe/session-closeout",
"local/31349ba31a/verification-before-completion"
]
instructionsPath: None
=== scoped cwd is a git repo? + Monica heartbeat ===
--- CA cwd ---
total 24
drwxrwxr-x  3 ali ali 4096 Jun 29 09:32 .
drwxrwxr-x 10 ali ali 4096 Jun 29 05:12 ..
drwxrwxr-x  8 ali ali 4096 Jun 29 09:32 .git
-rw-rw-r--  1 ali ali  344 Jun 27 11:02 AGENTS.md
-rw-rw-r--  1 ali ali  105 Jun 29 09:32 README.md
-rw-rw-r--  1 ali ali   86 Jun 27 11:02 SOURCE-MAP.md
--- is git? ---
true
=== Monica heartbeat config ===
name: Monica | status: idle | adapterType: codex_local
heartbeat: {'enabled': False, 'maxConcurrentRuns': 1}
cwd: /srv/repos/aina-paperclip-agent-context/workspaces/content-curriculum
lastHeartbeatAt: 2026-06-29T18:51:27.304Z

=== BASELINE (before assign) ===
null

--- assign AIN-95 -> Curriculum Architect (head envelope) ---
OK assigned -> assignee: 3bdfbfc6-8498-4fc1-931c-eb3ebecec910 | status: todo

Command running in background with ID: b311789y0. Output is being written to: /private/tmp/claude-502/-Users-Ali-PKM/ea21dc9e-a684-460b-b5d8-244fa739715e/tasks/b311789y0.output. You will be notified when it completes. To check interim output, use Read on that file path.

1	=== auto-run check (expect no run: quiescent, heartbeat.enabled=false) ===
2	{
3	  "id": "2907c266-dec5-4be7-9b77-aad3ddf8dc7d",
4	  "status": "running",
5	  "invocationSource": "assignment",
6	  "triggerD <-active-run
7	CA status: running
8	=== launch ONE native heartbeat for CA (detached, logged, 15m cap) ===
9	LAUNCHED_PID=1972844
10	

=== manual heartbeat log (did it no-op due to maxConcurrentRuns=1?) ===
Invoked heartbeat run 8b31cb90-bd34-4bf1-bba5-327556a606de for agent Curriculum Architect (3bdfbfc6-8498-4fc1-931c-eb3ebecec910)
Status: queued

=== live runs on AIN-95 (expect 1) ===
live run count: 1
   2907c266-dec5-4be7-9b77-aad3ddf8dc7d | running |src= assignment |started= 2026-07-01T02:50:22.831Z

=== git workspace activity ===
--- recent commits ---
1991b55 init lane workspace (content-curriculum) — codex_local requires a git worktree

Command running in background with ID: bx3gvhku0. Output is being written to: /private/tmp/claude-502/-Users-Ali-PKM/ea21dc9e-a684-460b-b5d8-244fa739715e/tasks/bx3gvhku0.output. You will be notified when it completes. To check interim output, use Read on that file path.

1	[poll 1] live-runs=1  (22:53:49)
2	[poll 2] live-runs=1  (22:54:20)
3	[poll 3] live-runs=1  (22:54:51)
4	[poll 4] live-runs=1  (22:55:22)
5	[poll 5] live-runs=1  (22:55:53)
6	[poll 6] live-runs=1  (22:56:24)
7	[poll 7] live-runs=1  (22:56:55)
8	

1	[poll 1] live-runs=1  (22:53:49)
2	[poll 2] live-runs=1  (22:54:20)
3	[poll 3] live-runs=1  (22:54:51)
4	[poll 4] live-runs=1  (22:55:22)
5	[poll 5] live-runs=1  (22:55:53)
6	[poll 6] live-runs=1  (22:56:24)
7	[poll 7] live-runs=1  (22:56:55)
8	[poll 8] live-runs=1  (22:57:26)
9	[poll 9] live-runs=1  (22:57:57)
10	[poll 10] live-runs=1  (22:58:28)
11	[poll 11] live-runs=0  (22:58:59)
12	=== RUN(S) TERMINAL ===
13	
14	################ EVIDENCE BUNDLE ################
15	=== AIN-95 final state ===
16	status: done | assignee: b74f5dd3-403d-43c3-ab4c-fd2117723060
17	=== AIN-95 comments (last 6) ===
18	 - b74f5dd3 | Calibrator evaluator review complete for AIN-95. I acknowledged the Curriculum Architect handoff and verified the evaluator lane rather than authoring more curriculum.
19	
20	Durable rep
21	 - 3bdfbfc6 | Assigning Calibrator for evaluator review handoff on AIN-95.
22	 - ? | Paperclip needs a disposition before this issue can continue.
23	 - 3bdfbfc6 | Completed the AIN-95 content pass in `/srv/repos/aina-academy`.
24	
25	I added the wake-specific canon and evaluator-firewall metadata to:
26	
27	- [l1-l2 coverage](/srv/repos/aina-academy/con
28	 - ? | U2 self-drive proof — assigning to Curriculum Architect (lane member). Envelope: author L1 lesson+rubric+evaluator content per the ANMS stable-top intent; respect evaluator firewal
29	 - ? | ## Codex verification verdict
30	
31	**Genuinely pending, but should be merged conceptually with the 500-module Phase-C lane.** L1-L3 have meaningful seed/Universal content and evaluator
32	=== work products ===
33	[]
34	
35	=== git diff/status in lane workspace ===
36	--- log ---
37	1991b55 init lane workspace (content-curriculum) — codex_local requires a git worktree
38	=== CA runtime + heartbeat runs on issue ===
39	 run  | succeeded |src= assignment | 
40	 run  | succeeded |src= automation | 
41	 run  | succeeded |src= assignment | 
42	################ END ################
43	

--- raw comments file head ---
(eval):2: no such file or directory: ./vds-exec.sh

--- comments help ---
Usage: paperclipai issue comments [options] <issueId>

List issue comments

Arguments:
  issueId                  Issue ID

Options:
  --after-comment-id <id>  Only return comments after this comment ID
  --order <order>          asc or desc
  --limit <n>              Maximum comments to return
  -c, --config <path>      Path to Paperclip config file
  -d, --data-dir <path>    Paperclip data directory root (isolates state from
                           ~/.paperclip)

total comments: 6

----- ? @ 2026-06-29T13:26:38 -----
## Codex verification verdict

**Genuinely pending, but should be merged conceptually with the 500-module Phase-C lane.** L1-L3 have meaningful seed/Universal content and evaluator rubrics; L4/L5 and full capability-bound coverage are still real gaps.

- Evidence: `docs/AINA-MASTER-CONTROL.md` says L4/L5 are nearly unseeded and 500-slot/tool-variant scale does not exist; FD #52 defines post-activation promote-map-QA.
- Lane tag: Curriculum + Evaluation is correct.
- Dedupe: overlaps [AIN-94](/AIN/issues/AIN-94) unless scoped as coverage QA/rubric gate for the authored library.
- ANMS/Gherkin/test: sound, but needs a coverage ledger test by `level x capability x module row x rubric`, not just a learner completes Lx.

----- ? @ 2026-07-01T02:50:22 -----
U2 self-drive proof — assigning to Curriculum Architect (lane member). Envelope: author L1 lesson+rubric+evaluator content per the ANMS stable-top intent; respect evaluator firewall; cite curriculum council canon 2026-06-18. Verifier: Calibrator (evaluation_judge), NOT self. This is the reference native-flow task.

----- CurriculumArchitect @ 2026-07-01T02:53:35 -----
Completed the AIN-95 content pass in `/srv/repos/aina-academy`.

I added the wake-specific canon and evaluator-firewall metadata to:

- [l1-l2 coverage](/srv/repos/aina-academy/content/launch-readiness/ain-95/l1-l2/coverage.json)
- [l3-l5 coverage](/srv/repos/aina-academy/content/launch-readiness/ain-95/l3-l5/coverage.json)
- [evaluator coverage](/srv/repos/aina-academy/content/launch-readiness/ain-95/evaluators/coverage.json)
- [evaluator prompt](/srv/repos/aina-academy/content/launch-readiness/ain-95/evaluators/evaluator-agent-system-prompt.md)

Verification passed:

- `ain-95-l1-l2-coverage.mjs --check`
- `ain-95-l3-l5-coverage.mjs --check`
- `ain-95-rubric-schema.mjs --check`
- `ain-95-lesson-prose-qa.mjs --check`
- `ain-95-evaluator-smoke.mjs --check`

I could not update AIN-95 to `in_review` or wake/route Calibrator because the Paperclip API is unreachable; the scope precheck and final `paperclipai issue update` both failed with “Could not reach the Paperclip API,” and `/api/health` timed out. The intended disposition is `in_review` with Calibrator (`evaluation_judge`) as verifier, not self-review.

----- ? @ 2026-07-01T02:53:35 -----
Paperclip needs a disposition before this issue can continue.

----- CurriculumArchitect @ 2026-07-01T02:55:45 -----
Assigning Calibrator for evaluator review handoff on AIN-95.

----- Calibrator @ 2026-07-01T02:58:24 -----
Calibrator evaluator review complete for AIN-95. I acknowledged the Curriculum Architect handoff and verified the evaluator lane rather than authoring more curriculum.

Durable repo evidence added:
- content/launch-readiness/ain-95/evaluators/calibrator-review.md records Calibrator pass disposition, evidence checked, commands run, and explicit limitations.
- content/launch-readiness/ain-95/evaluators/coverage.json now links verifier_review_path to that receipt.

Focused verification rerun from /srv/repos/aina-academy:
- node scripts/checks/ain-95-l1-l2-coverage.mjs --check: pass
- node scripts/checks/ain-95-l3-l5-coverage.mjs --check: pass
- node scripts/checks/ain-95-rubric-schema.mjs --check: pass
- node scripts/checks/ain-95-lesson-prose-qa.mjs --check: pass
- node scripts/checks/ain-95-evaluator-smoke.mjs --check: pass; 15 configs, L1-L5 covered, no failures

Disposition: done for AIN-95 content coverage. Each L1-L5 slot has lesson, rubric, and evaluator config coverage sufficient for deterministic rubric-based evaluation against supplied evaluator criteria. Boundary: this does not claim live LLM calibration, production threshold approval, or founder-gated threshold changes.

=== files authored for AIN-95 ===
total 28
drwxrwxr-x 5 ali ali 4096 Jun 30 20:17 .
drwxrwxr-x 4 ali ali 4096 Jun 30 20:17 ..
drwxrwxr-x 2 ali ali 4096 Jun 30 22:57 evaluators
drwxrwxr-x 4 ali ali 4096 Jun 30 20:17 l1-l2
drwxrwxr-x 4 ali ali 4096 Jun 30 20:17 l3-l5
-rw-rw-r-- 1 ali ali 2165 Jun 30 20:17 prose-qa.json
-rw-rw-r-- 1 ali ali 1702 Jun 30 20:17 rubric.schema.json
content/launch-readiness/ain-95/l3-l5/rubrics/l4-integrated-rubric.json
content/launch-readiness/ain-95/l3-l5/rubrics/l3-applied-rubric.json
content/launch-readiness/ain-95/l3-l5/rubrics/l4-foundation-rubric.json
content/launch-readiness/ain-95/l3-l5/rubrics/l5-integrated-rubric.json
content/launch-readiness/ain-95/l3-l5/rubrics/l3-foundation-rubric.json
content/launch-readiness/ain-95/l3-l5/rubrics/l5-foundation-rubric.json
content/launch-readiness/ain-95/l3-l5/rubrics/l5-applied-rubric.json
content/launch-readiness/ain-95/l3-l5/rubrics/l4-applied-rubric.json
content/launch-readiness/ain-95/l3-l5/rubrics/l3-integrated-rubric.json
content/launch-readiness/ain-95/l3-l5/coverage.json
content/launch-readiness/ain-95/l3-l5/lessons/l5-applied.json
content/launch-readiness/ain-95/l3-l5/lessons/l3-integrated.json
content/launch-readiness/ain-95/l3-l5/lessons/l4-applied.json
content/launch-readiness/ain-95/l3-l5/lessons/l5-integrated.json
content/launch-readiness/ain-95/l3-l5/lessons/l3-foundation.json
content/launch-readiness/ain-95/l3-l5/lessons/l5-foundation.json
content/launch-readiness/ain-95/l3-l5/lessons/l3-applied.json
content/launch-readiness/ain-95/l3-l5/lessons/l4-integrated.json
content/launch-readiness/ain-95/l3-l5/lessons/l4-foundation.json
content/launch-readiness/ain-95/prose-qa.json
content/launch-readiness/ain-95/rubric.schema.json
content/launch-readiness/ain-95/l1-l2/rubrics/l2-integrated-rubric.json
content/launch-readiness/ain-95/l1-l2/rubrics/l2-applied-rubric.json
content/launch-readiness/ain-95/l1-l2/rubrics/l1-integrated-rubric.json
content/launch-readiness/ain-95/l1-l2/rubrics/l2-foundation-rubric.json
content/launch-readiness/ain-95/l1-l2/rubrics/l1-foundation-rubric.json
content/launch-readiness/ain-95/l1-l2/rubrics/l1-applied-rubric.json
content/launch-readiness/ain-95/l1-l2/coverage.json
content/launch-readiness/ain-95/l1-l2/lessons/l2-applied.json
content/launch-readiness/ain-95/l1-l2/lessons/l2-integrated.json

=== git status (committed vs dangling?) ===
 M content/launch-readiness/ain-95/evaluators/coverage.json
 M content/launch-readiness/ain-95/evaluators/evaluator-agent-system-prompt.md
 M content/launch-readiness/ain-95/l1-l2/coverage.json
 M content/launch-readiness/ain-95/l3-l5/coverage.json
?? content/launch-readiness/ain-95/evaluators/calibrator-review.md
--- recent commits mentioning ain-95 or curriculum ---
3441bdf6 fix(AIN-91): bind lesson media to manifest matches
b684af65 fix(personalization): add cold-start fallback (#210)
2f401de1 docs(AIN-238): add learner outage incident runbook (#209)
099f1960 test(AIN-237): add Cloudflare env parity guard (#208)
b7855867 fix(AIN-239): add brand QA receipt gate (#207)
ea81d7d3 docs(AIN-226): select personalization storage substrate (#206)
06a2239f test(AIN-100-C): cover evaluator and tutor lanes (#205)
9f7f84fd feat(AIN-236): add rollout health monitor (#204)
--- is ain-95 content tracked/committed? ---
b311bf57 docs(AIN-223): add lesson prose QA gate (#188)
b038d558 feat(AIN-222): define canonical rubric schema (#186)
85b6daf3 AIN-178: add L3-L5 launch lesson rubrics (#162)
--- current branch ---
ali/ain-91-media-engine-lesson-slots

=== before: changed files ===
 M content/launch-readiness/ain-95/evaluators/coverage.json
 M content/launch-readiness/ain-95/evaluators/evaluator-agent-system-prompt.md
 M content/launch-readiness/ain-95/l1-l2/coverage.json
 M content/launch-readiness/ain-95/l3-l5/coverage.json
?? content/launch-readiness/ain-95/evaluators/calibrator-review.md
=== stash AIN-95 run output (preserve, un-pollute AIN-91 branch, fully recoverable) ===
Saved working directory and index state On ali/ain-91-media-engine-lesson-slots: AIN-95 U2 self-drive proof output — content+evaluator-firewall metadata + calibrator receipt; awaiting Frodo milestone commit (U6)
=== after: working tree clean on AIN-91 branch? ===
=== stash list ===
stash@{0}: On ali/ain-91-media-engine-lesson-slots: AIN-95 U2 self-drive proof output — content+evaluator-firewall metadata + calibrator receipt; awaiting Frodo milestone commit (U6)
stash@{1}: WIP on ali/watchdog-staging-proof-2026-06-30: 669a3be docs: refresh watchdog staging proof
=== confirm files preserved in stash ===
+  "canon_sources": [
+    "docs/AINA-INDEX.md: reconciled to Founder Decisions #34-40 on 2026-06-18; governs the single L1-L5 product, governed 51-capability spine, and runtime/build distinction.",
+    "docs/FOUNDER-DECISIONS.md: binding founder decisions for curriculum structure, adaptive evidence loop, tool-neutrality, and proof-of-work progression.",
+    "docs/canon/EVALUATOR-FIREWALL.md: evaluator firewall means commercial neutrality; rubric/gate review remains with Calibrator/evaluation_judge and founder-gated threshold changes."
+  ],
   "slots": [
     {
       "slot_id": "l3-foundation",

handoff updated (     190 lines)

Updated task #6 status

The file /Users/Ali/.claude/projects/-Users-Ali-PKM/memory/project_aina_factory_native_redesign_2026_06_30.md has been updated successfully. (file state is current in your context — no need to Read it back)

=== crontab (the paused external scheduler) ===
15 9 * * * cd ~/home-agent-dotfiles && ./autosync.sh >> ~/home-agent-dotfiles/.autosync.log 2>&1
*/15 * * * * cd /home/ali/aina-mission-control && /usr/bin/python3 collector/paperclip_snapshot.py >> /home/ali/aina-mission-control/logs/paperclip-poll.log 2>&1
0 */2 * * * cd /srv/aina/ops && PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/usr/local/bin python3 /srv/aina/ops/team-utilization-monitor.py >> /srv/aina/ops/team-status/monitor.log 2>&1
0 4 * * * bash /srv/aina/ops/janitor.sh >/dev/null 2>&1

=== systemd timers (any) ===
NEXT                            LEFT LAST                           PASSED UNIT                           ACTIVATES
Wed 2026-07-01 00:00:00 EDT    55min Tue 2026-06-30 00:00:44 EDT   23h ago archive-retention-report.timer archive-retention-report.service
Wed 2026-07-01 00:28:25 EDT 1h 24min Tue 2026-06-30 22:28:25 EDT 35min ago vds-local-index.timer          vds-local-index.service
Wed 2026-07-01 08:37:25 EDT       9h Tue 2026-06-30 08:37:25 EDT   14h ago launchpadlib-cache-clean.timer launchpadlib-cache-clean.service
Wed 2026-07-01 13:00:00 EDT      13h Tue 2026-06-30 13:00:44 EDT   10h ago aina-backup.timer              aina-backup.service
Wed 2026-07-01 13:30:00 EDT      14h Tue 2026-06-30 13:30:44 EDT    9h ago aina-r2-backup.timer           aina-r2-backup.service
Wed 2026-07-01 14:00:00 EDT      14h Tue 2026-06-30 14:00:44 EDT    9h ago aina-repos-backup.timer        aina-repos-backup.service

6 timers listed.

=== the 7 routines: search agent-context repo + ops for definitions ===
/srv/repos/aina-paperclip-agent-context/skills/paperclip-runtime-audit/SKILL.md
/srv/repos/aina-paperclip-agent-context/skills/maintainer-orchestrator/SKILL.md
/srv/repos/aina-paperclip-agent-context/docs/reports/roster-qa-sdlc-gap-reconciliation-2026-06-29.html
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-122-factory-media-asset-safety-check.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-202-pr-bot-review-watcher-deploy.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-147-platform-cto-launch-architecture-assessment.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-146-product-learning-launch-readiness.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-108-factory-pilot-verifier.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-154-qa-release-readiness-assessment.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-153-growth-gtm-launch-plan-input.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-148-data-personalization-launch-assessment.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-135-canon-mining-routing-pass.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-110-frontend-slice-verifier.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-120-factory-curriculum-verifier.md
/srv/repos/aina-paperclip-agent-context/docs/reports/paperclip-agent-runs/2026-06-29-ain-136-memory-reconciliation-pass.md
--- ops dir ---
total 498784
drwxrwxr-x 72 ali ali    36864 Jun 30 20:44 .
drwxr-xr-x 26 ali ali     4096 Jun 30 19:19 ..
-rw-rw-r--  1 ali ali        0 Jun 29 17:33 .botfix-ainative-academy-aina-academy-108.lock
-rw-rw-r--  1 ali ali        0 Jun 30 01:30 .botfix-ainative-academy-aina-academy-112.lock
-rw-rw-r--  1 ali ali        0 Jun 30 06:00 .botfix-ainative-academy-aina-academy-113.lock
-rw-rw-r--  1 ali ali        0 Jun 30 01:22 .botfix-ainative-academy-aina-academy-117.lock
-rw-rw-r--  1 ali ali        0 Jun 29 20:15 .botfix-ainative-academy-aina-academy-118.lock
-rw-rw-r--  1 ali ali        0 Jun 30 06:00 .botfix-ainative-academy-aina-academy-119.lock
-rw-rw-r--  1 ali ali        0 Jun 30 01:22 .botfix-ainative-academy-aina-academy-120.lock
-rw-rw-r--  1 ali ali        0 Jun 30 06:00 .botfix-ainative-academy-aina-academy-121.lock
-rw-rw-r--  1 ali ali        0 Jun 30 01:00 .botfix-ainative-academy-aina-academy-123.lock
-rw-rw-r--  1 ali ali        0 Jun 30 01:00 .botfix-ainative-academy-aina-academy-124.lock
-rw-rw-r--  1 ali ali        0 Jun 30 01:00 .botfix-ainative-academy-aina-academy-125.lock
-rw-rw-r--  1 ali ali        0 Jun 30 05:45 .botfix-ainative-academy-aina-academy-127.lock
-rw-rw-r--  1 ali ali        0 Jun 30 02:15 .botfix-ainative-academy-aina-academy-129.lock
-rw-rw-r--  1 ali ali        0 Jun 30 02:15 .botfix-ainative-academy-aina-academy-130.lock
-rw-rw-r--  1 ali ali        0 Jun 30 02:00 .botfix-ainative-academy-aina-academy-133.lock
-rw-rw-r--  1 ali ali        0 Jun 30 01:45 .botfix-ainative-academy-aina-academy-134.lock
-rw-rw-r--  1 ali ali        0 Jun 30 02:00 .botfix-ainative-academy-aina-academy-135.lock
-rw-rw-r--  1 ali ali        0 Jun 30 03:00 .botfix-ainative-academy-aina-academy-136.lock
-rw-rw-r--  1 ali ali        0 Jun 30 03:00 .botfix-ainative-academy-aina-academy-137.lock
-rw-rw-r--  1 ali ali        0 Jun 30 02:30 .botfix-ainative-academy-aina-academy-138.lock
-rw-rw-r--  1 ali ali        0 Jun 30 02:30 .botfix-ainative-academy-aina-academy-139.lock
-rw-rw-r--  1 ali ali        0 Jun 30 02:30 .botfix-ainative-academy-aina-academy-140.lock

=== how does the agent get pointed to the real repo? (lane workspace anchor files) ===
--- AGENTS.md ---
# content-curriculum Paperclip Workspace

This is a scoped Paperclip context workspace for `content-curriculum`.

Read `/srv/repos/aina-paperclip-agent-context/AGENTS.md` first, then this lane's README/source map.
Do not treat this workspace as product source truth. Product repos are read/written only when an assignment explicitly allows it.
--- SOURCE-MAP.md ---
See `/srv/repos/aina-paperclip-agent-context/lanes/content-curriculum/SOURCE-MAP.md`.
--- README.md ---
# AINA lane workspace: content-curriculum

Scoped codex_local workspace for the content-curriculum lane.

=== native workspace/isolation primitives ===
### workspace ###
Usage: paperclipai workspace [options] [command]

Execution workspace operations

Options:
  -h, --help                               display help for command

Commands:
  list [options]                           List execution workspaces
  get [options] <id>                       Get an execution workspace
  close-readiness [options] <id>           Check execution workspace close readiness
  operations [options] <id>                List execution workspace operations
  update [options] <id>                    Update an execution workspace
  runtime-service [options] <id> <action>  Control an execution workspace runtime service
  runtime-command [options] <id> <action>  Run an execution workspace runtime command
  help [command]                           display help for command
### project-workspace ###
Usage: paperclipai project-workspace [options] [command]

Project workspace operations

Options:
  -h, --help                                                    display help for command

Commands:
  list [options] <projectId>                                    List project workspaces
  create [options] <projectId> [workspaceId]                    Create a project workspace
  update [options] <projectId> [workspaceId]                    Update a project workspace
  delete [options] <projectId> <workspaceId>                    Delete a project workspace
  runtime-service [options] <projectId> <workspaceId> <action>  Control a project workspace runtime service
  runtime-command [options] <projectId> <workspaceId> <action>  Run a project workspace runtime command
  help [command]                                                display help for command

=== existing execution workspaces (how many, structure) ===
execution workspace count: 255
  ccacf6cb | issue=None | proj=5bcf03f8 | status=active | path=None
  41b60902 | issue=None | proj=5bcf03f8 | status=active | path=None
  6fba5853 | issue=None | proj=5bcf03f8 | status=active | path=None
  44a795c0 | issue=None | proj=5532e7c5 | status=active | path=None
  49261c6f | issue=None | proj=8e684f74 | status=active | path=None
  f4777fc5 | issue=None | proj=5532e7c5 | status=active | path=None
  be765d9d | issue=None | proj=5532e7c5 | status=active | path=None
  819765b7 | issue=None | proj=29d829bc | status=active | path=None
  c77e946c | issue=None | proj=3791f838 | status=active | path=None
  0114053b | issue=None | proj=cb784947 | status=active | path=None
  f3bba529 | issue=None | proj=cb784947 | status=active | path=None
  aecbf3bf | issue=None | proj=cb784947 | status=active | path=None

=== does ANY project have a real repoUrl bound? (template) ===
will probe platform/data/journey projects for repoUrl binding
  Platform Engineering — Scoped Runtime    | repoUrl=None | policy={'enabled': True, 'defaultMode': 'shared_workspace', 'allowIssueOverride': True, 'defaultProjectWorkspaceId': 'ac19b9b8-9814-4a1f-8db2-02b012ef9c2c', 'workspaceStrategy': {'type': 'project_primary'}} | localFolder=/srv/repos/aina-paperclip-agent-context
  Data Engine Room                         | repoUrl=None | policy=None | localFolder=/srv/aina/aina-data-engine-room
  Journey - Lesson Shell & RECON           | repoUrl=None | policy=None | localFolder=/home/ali/.paperclip/instances/default/projects/7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9/3791f838-6740-4e4d-815d-55c7c69a532d/_default
  Lane 1 — Auth + Planner Foundation       | repoUrl=None | policy=None | localFolder=/srv/repos/aina-academy

=== project update help (policy flags?) ===
Usage: paperclipai project update [options] <project>

Update a project

Arguments:
  project                                        Project ID or shortname

Options:
  -C, --company-id <id>                          Company ID for shortname lookup
  --name <name>                                  Project name
  --description <text|null>                      Project description
  --status <status>                              Project status
  --goal-id <id|null>                            Deprecated single goal ID
  --goal-ids <csv>                               Comma-separated goal IDs
  --lead-agent-id <id|null>                      Lead agent ID
  --target-date <date|null>                      Target date
  --color <value|null>                           Project color
  --env-json <json|null>                         Project env binding JSON
  --execution-workspace-policy-json <json|null>  Execution workspace policy JSON
  --archived-at <iso8601|null>                   Archive timestamp or null
  -c, --config <path>                            Path to Paperclip config file
  -d, --data-dir <path>                          Paperclip data directory root (isolates state from ~/.paperclip)
  --context <path>                               Path to CLI context file
  --profile <name>                               CLI context profile name
  --api-base <url>                               Base URL for the Paperclip API
  --api-key <token>                              Bearer token for agent-authenticated calls
  --run-id <id>                                  Heartbeat run id for agent-authenticated mutations (checkout/release/interactions/in-progress update); falls back to $PAPERCLIP_RUN_ID
  --json                                         Output raw JSON
  -h, --help                                     display help for command

=== project-workspace create help (worktree/isolation?) ===
Usage: paperclipai project-workspace create [options] <projectId> [workspaceId]

Create a project workspace

Arguments:
  projectId              Project ID
  workspaceId            Workspace ID for update

Options:
  --payload-json <json>  JSON payload
  -c, --config <path>    Path to Paperclip config file
  -d, --data-dir <path>  Paperclip data directory root (isolates state from
                         ~/.paperclip)
  --context <path>       Path to CLI context file
  --profile <name>       CLI context profile name
  --api-base <url>       Base URL for the Paperclip API
  --api-key <token>      Bearer token for agent-authenticated calls
  --run-id <id>          Heartbeat run id for agent-authenticated mutations
                         (checkout/release/interactions/in-progress update);
                         falls back to $PAPERCLIP_RUN_ID
  --json                 Output raw JSON
  -h, --help             display help for command

=== enum values near shared_workspace / workspaceStrategy / defaultMode ===
    366 worktree
     22 isolated
     12 ephemeral
      6 shared_workspace
      6 project_primary
      5 isolated_workspace

=== lines defining workspaceStrategy types ===
workspaceStrategy: executionWorkspaceStrategySchema.optional().nullable(),\n    workspaceRuntime: z.record(z.string(), z.unknown()).optio
workspaceStrategy: executionWorkspaceStrategySchema.optional().nullable(),\n    workspaceRuntime: z.record(z.string(), z.unknown()).optio
workspaceStrategy?: string | null
workspaceStrategy],\n    [\"PAPERCLIP_WORKSPACE_ID\", input.workspaceId],\n    [\"PAPERCLIP_WORKSPACE_REPO_URL\", input.workspaceRepoUrl]
workspaceStrategy?: string | null
workspaceStrategy: input.workspaceStrategy,\n    workspaceId: input.workspaceId,\n    workspaceRepoUrl: input.workspaceRepoUrl,\n    work
workspaceStrategy: executionWorkspaceStrategySchema.optional().nullable(),
workspaceStrategy: executionWorkspaceStrategySchema2.optional().nullable(),

=== defaultMode allowed values ===
defaultMode: z.enum([\"shared_workspace\"
defaultMode: z20.enum(["shared_workspace"

=== full defaultMode enum ===
defaultMode: z.enum([\"shared_workspace\", \"isolated_workspace\", \"operator_branch\", \"adapter_default\"]
defaultMode: z20.enum(["shared_workspace", "isolated_workspace", "operator_branch", "adapter_default"]
=== executionWorkspaceStrategySchema / mode enums ===
z12.enum(["issue", "comment", "document", "work_product"]
z13.enum(["project_primary", "git_worktree", "adapter_managed", "cloud_sandbox"]
z20.enum(["project_primary", "git_worktree", "adapter_managed", "cloud_sandbox"]
=== any strategy type literal set ===
      2 "project_primary"
=== how worktree path is derived (per issue?) ===
worktreeParentDir: z.string().optional().nullable()
worktreeParentDir: z.string().optional().nullable()
worktreePath = path.resolve(entry.worktree)
worktreePath
worktreePath
worktreePath === currentCwd
worktreePathHasUncommittedChanges(worktreePath: string): boolean {\n  try {\n    const outpu
worktreePath

File created successfully at: /Users/Ali/PKM/scratch/pkm-deepdive/isolation-fix-design-2026-06-30.md (file state is current in your context — no need to Read it back)

Command running in background with ID: bq9hwso6c. Output is being written to: /private/tmp/claude-502/-Users-Ali-PKM/ea21dc9e-a684-460b-b5d8-244fa739715e/tasks/bq9hwso6c.output. You will be notified when it completes. To check interim output, use Read on that file path.

=== VDS disk ===
Filesystem      Size  Used Avail Use% Mounted on
/dev/sda1       232G  188G   45G  81% /
/dev/sda1       232G  188G   45G  81% /

=== /srv/repos/aina-academy: git worktrees today ===
/srv/repos/aina-academy                                       3441bdf6 [ali/ain-91-media-engine-lesson-slots]
/home/ali/agent-workspaces/aina-academy-calibration-20260622  72cbf51b [ali/acad-calibration-integrity-2026-06-22]
/home/ali/agent-workspaces/aina-academy-runtime-20260622      72cbf51b [ali/acad-runtime-memory-2026-06-22]
/home/ali/agent-workspaces/aina-academy-scaffold-20260622     72cbf51b [ali/acad-84-scaffold-2026-06-22]
/home/ali/agent-workspaces/coo-13018752-efb-20260630-144451   5e2f08c6 [ali/coo-13018752-efb-20260630]
/home/ali/agent-workspaces/coo-16fd768e-54d-20260630-201506   38263a43 [ali/coo-16fd768e-54d-20260630]
/home/ali/agent-workspaces/coo-214ceb6a-eab-20260630-144452   03379c31 [ali/coo-214ceb6a-eab-20260630]
/home/ali/agent-workspaces/coo-236171fc-32c-20260630-181506   54becb5a [ali/coo-236171fc-32c-20260630]
/home/ali/agent-workspaces/coo-3a7e9408-5d0-20260630-144453   66d339bd [ali/coo-3a7e9408-5d0-20260630]
/home/ali/agent-workspaces/coo-426bf94f-b13-20260630-201508   59217bd9 [ali/coo-426bf94f-b13-20260630]
repo .git size:
319M	.git
branch count:
347

=== does /srv/worktrees exist? ===
ls: cannot access '/srv/worktrees': No such file or directory

=== paperclip instance projects dir size (managed workspaces) ===
72K	/home/ali/.paperclip/instances/default/projects
n project dirs:
8

recorded
=== Codex progress ===

1	1. Pause/confirm quiescent: no active runs, no agents with live cwd/processes in shared checkout.
2	2. Snapshot current Paperclip project/workspace config.
3	3. For the target repo: confirm `/srv/repos/aina-academy` is a clean git checkout, on expected base, with remote/ref sane. Set `repoUrl`/`repoRef` if Paperclip’s git-worktree path requires it; localFolder is git-sufficient, but Paperclip may still use `repoUrl` for metadata/branch setup.
4	4. Create `/srv/worktrees/aina-academy` with correct owner/permissions.
5	5. Apply policy to one curriculum project only, with `allowIssueOverride:false`.
6	6. Run one synthetic U2/self-drive issue.
7	7. Verify: agent cwd is under `/srv/worktrees/aina-academy/...`, branch is unique to the issue, `/srv/repos/aina-academy` remains untouched, `git worktree list` shows the new worktree, and close-readiness detects dirty state.
8	8. Apply to the rest of the academy-bound dev projects.
9	9. Repeat per real repo/lane.
10	10. Only after successful runs, separately GC stale Paperclip execution workspaces/worktrees.
11	
12	**Direct Answers / Footguns**
13	
14	Several projects pointing at the same real repo is sound with git worktrees, provided branch names are globally unique across projects. Use project/issue ids in branch names. Git worktrees share objects/refs, not indexes; index isolation is fine, but concurrent `fetch`, `gc`, `prune`, branch deletion, and same-branch checkout are the risks.
15	
16	`worktreePathHasUncommittedChanges` is necessary but not enough for cleanup. Also require: Paperclip issue closed/done/canceled, no active process cwd inside the worktree, branch already merged or intentionally preserved, no locks, and disk usage below threshold. GC policy: TTL closed worktrees, cap open worktrees per repo/project, alert on disk, prune only after manifesting what will be removed.
17	
18	Mid-flight policy changes can orphan or strand existing shared workspaces. Since the factory is quiescent, this is the right moment. Do not delete old shared workspaces during the policy change; freeze them, prove new issue creation uses worktrees, then clean old records separately.
19	
20	The biggest non-git footgun: agents can still `cd /srv/repos/aina-academy` manually if prompts/tools allow it. The policy fixes default cwd, not malicious or sloppy shell navigation. Add a runtime/preflight assertion that fails if cwd is the canonical shared checkout.
21	
22	Prior memory also flags a related isolated-worktree failure mode: gitignored/local runtime assets missing from new worktrees. Make provisioning explicit before declaring this fixed.
23	
24	**Bottom line:** GO-WITH-CHANGES. Flip to git worktrees, set `allowIssueOverride:false`, prove one lane, then expand. No broad cleanup until after the new isolation path is verified. Not landed yet — analysis only, no files changed, as requested.
25	
26	
27	hook: Stop
28	hook: Stop
29	hook: Stop Completed
30	hook: Stop Completed
31	tokens used
32	124,753
33	**Verdict: GO-WITH-CHANGES**
34	
35	The core fix is correct: `isolated_workspace` + `git_worktree` is the right direction for per-issue parallel execution. Do not use `operator_branch` for this; that sounds like branch switching inside one checkout, which preserves the collision class. I would not prefer `adapter_managed` unless Paperclip’s adapter is explicitly providing stronger sandbox lifecycle guarantees than native git worktrees.
36	
37	**Minimal policy JSON**
38	
39	```json
40	{
41	  "enabled": true,
42	  "defaultMode": "isolated_workspace",
43	  "allowIssueOverride": false,
44	  "workspaceStrategy": {
45	    "type": "git_worktree"
46	  },
47	  "worktreeParentDir": "/srv/worktrees/aina-academy"
48	}
49	```
50	
51	Use a unique `worktreeParentDir` per real repo, not per project. If the CLI schema requires `defaultProjectWorkspaceId`, include the project’s primary workspace id explicitly, but do not guess it.
52	
53	**Safest Apply Order**
54	
55	1. Pause/confirm quiescent: no active runs, no agents with live cwd/processes in shared checkout.
56	2. Snapshot current Paperclip project/workspace config.
57	3. For the target repo: confirm `/srv/repos/aina-academy` is a clean git checkout, on expected base, with remote/ref sane. Set `repoUrl`/`repoRef` if Paperclip’s git-worktree path requires it; localFolder is git-sufficient, but Paperclip may still use `repoUrl` for metadata/branch setup.
58	4. Create `/srv/worktrees/aina-academy` with correct owner/permissions.
59	5. Apply policy to one curriculum project only, with `allowIssueOverride:false`.
60	6. Run one synthetic U2/self-drive issue.
61	7. Verify: agent cwd is under `/srv/worktrees/aina-academy/...`, branch is unique to the issue, `/srv/repos/aina-academy` remains untouched, `git worktree list` shows the new worktree, and close-readiness detects dirty state.
62	8. Apply to the rest of the academy-bound dev projects.
63	9. Repeat per real repo/lane.
64	10. Only after successful runs, separately GC stale Paperclip execution workspaces/worktrees.
65	
66	**Direct Answers / Footguns**
67	
68	Several projects pointing at the same real repo is sound with git worktrees, provided branch names are globally unique across projects. Use project/issue ids in branch names. Git worktrees share objects/refs, not indexes; index isolation is fine, but concurrent `fetch`, `gc`, `prune`, branch deletion, and same-branch checkout are the risks.
69	
70	`worktreePathHasUncommittedChanges` is necessary but not enough for cleanup. Also require: Paperclip issue closed/done/canceled, no active process cwd inside the worktree, branch already merged or intentionally preserved, no locks, and disk usage below threshold. GC policy: TTL closed worktrees, cap open worktrees per repo/project, alert on disk, prune only after manifesting what will be removed.
71	
72	Mid-flight policy changes can orphan or strand existing shared workspaces. Since the factory is quiescent, this is the right moment. Do not delete old shared workspaces during the policy change; freeze them, prove new issue creation uses worktrees, then clean old records separately.
73	
74	The biggest non-git footgun: agents can still `cd /srv/repos/aina-academy` manually if prompts/tools allow it. The policy fixes default cwd, not malicious or sloppy shell navigation. Add a runtime/preflight assertion that fails if cwd is the canonical shared checkout.
75	
76	Prior memory also flags a related isolated-worktree failure mode: gitignored/local runtime assets missing from new worktrees. Make provisioning explicit before declaring this fixed.
77	
78	**Bottom line:** GO-WITH-CHANGES. Flip to git worktrees, set `allowIssueOverride:false`, prove one lane, then expand. No broad cleanup until after the new isolation path is verified. Not landed yet — analysis only, no files changed, as requested.
79	
80	
81	

=== how is Lane 1 bound to /srv/repos/aina-academy? (template) ===
codebase: {
 "workspaceId": "6d7912e4-fc49-4161-9593-1335fba067b6",
 "repoUrl": null,
 "repoRef": null,
 "defaultRef": null,
 "repoName": null,
 "localFolder": "/srv/repos/aina-academy",
 "managedFolder": "/home/ali/.paperclip/instances/default/projects/7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9/a64c0faf-a346-4478-b08a-98b744bbec07/_default",
 "effectiveLocalFolder": "/srv/repos/aina-academy",
 "origin": "local_folder"
}
primaryWorkspace: {
 "id": "6d7912e4-fc49-4161-9593-1335fba067b6",
 "companyId": "7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9",
 "projectId": "a64c0faf-a346-4478-b08a-98b744bbec07",
 "name": "AINA Academy canonical workspace",
 "sourceType": "local_path",
 "cwd": "/srv/repos/aina-academy",
 "repoUrl": null,
 "repoRef": null,
 "defaultRef": null,
 "visibility": "default",
 "setupCommand": null,
 "cleanupCommand": null,
 "remoteProvider": null,
 "remoteWorkspaceRef": null,
 "sharedWorkspaceKey": null,
 "metadata": {
  "purpose": "paused-readiness repo/workspace binding",
  "createdBy": "aina-chief-of-staff",
  "nonWakin
workspaces: [
 {
  "id": "6d7912e4-fc49-4161-9593-1335fba067b6",
  "companyId": "7d58fc13-7c9a-4c87-b9f8-a7cfae8564a9",
  "projectId": "a64c0faf-a346-4478-b08a-98b744bbec07",
  "name": "AINA Academy canonical workspace",
  "sourceType": "local_path",
  "cwd": "/srv/repos/aina-academy",
  "repoUrl": null,
  "repoRef": null,
  "defaultRef": null,
  "visibility": "default",
  "setupCommand": null,
  "cleanupComm
policy: None

=== project-workspace payload schema (source) ===
projectWorkspaceRuntimeConfigSchema = z.object({\n  workspaceRuntime: z.record(z.string(), z.unknown()).optional().nullable(),\n  desiredState: z.enum([\"running\", \"stopped\", \"manual\"]).optional().nullable(),\n  serviceStates: z.record(z.enum([\"running\", \"stopped\", \"manual\"])).optional().nullable(),\n
projectWorkspaceRuntimeConfigSchema = z20.object({

=== provisioning: is node_modules gitignored in academy + do checks need it? ===
1:node_modules/
10:.env
11:.env.*
--- node_modules present in main checkout? ---
node_modules
1.3G	node_modules
--- check scripts need node deps? ---
#!/usr/bin/env node
import { existsSync, readFileSync } from "node:fs";
import { join } from "node:path";

const repoRoot = process.cwd();

<persisted-output>
Output too large (1.5MB). Full output saved to: /Users/Ali/.claude/projects/-Users-Ali-PKM/ea21dc9e-a684-460b-b5d8-244fa739715e/tool-results/b9yc3e1ej.txt

Preview (first 2KB):
=== git_worktree creation flow: setupCommand + worktree add ===
git worktree at ${linkedWorktree.worktree}...`)
git worktree at ${linkedWorktree.worktree}.`)
git worktree at ${targetPath}...`)
git worktree at ${targetPath}.`)
git worktree for ${bra
git worktree, then initialize an isolated Paperclip instance inside it").argument("<name>", "Worktree name \u2014 auto-prefixed with paperclip- if needed (created at ~/paperclip-NAME)").option("--start-point <ref>", "Remote ref to base the new branch on (env: PAPERCLIP_WORKTREE_START_POINT)").option("--instance <id>", "Explicit isolated instance id").option("--home <path>", `Home root for worktree instances (env: PAPERCLIP_WORKTREES_DIR, default: ${DEFAULT_WORKTREE_HOME})`).option("--from-config <path>", "Source config.json to seed from").option("--from-data-dir <path>", "Source PAPERCLIP_HOME used when deriving the source config").option("--from-instance <id>", "Source instance id when deriving the source config", "default").option("--server-port <port>", "Preferred server port", (value) => Number(value)).option("--db-port <port>", "Preferred embedded Postgres port", (value) => Number(value)).option("--seed-mode <mode>", "Seed profile: minimal or full (default: minimal)", "minimal").option("--preserve-live-work", "Do not quarantine copied agent timers or assigned open issues in the seeded worktree", false).option("--no-seed", "Skip database seeding from the source instance").option("--force", "Replace existing repo-local config and isolated instance data", false).action(worktreeMakeComma
git worktree."))
git worktree: ${targetPath}`)
git worktrees visible from this repo and whether they look like Paperclip worktrees").option("--json", "Print JSON instead of text output").action(worktreeListComma
git", ["worktree", "list", "--porcelai
git", ["worktree", "pru
git", worktreeArgs, {
...
</persisted-output>

drwxrwxr-x 2 ali ali 4096 Jun 30 23:15 /home/ali/paperclip-worktrees/aina-academy
--- writable? ---
OK writable
/dev/sda1       232G  188G   45G  81% /

policy file:
{"enabled":true,"defaultMode":"isolated_workspace","allowIssueOverride":false,"workspaceStrategy":{"type":"git_worktree"},"worktreeParentDir":"/home/ali/paperclip-worktrees/aina-academy"}
--- apply to Lane 1 ---
APPLIED policy: null

persisted policy: null

=== executionWorkspacePolicySchema object def ===

=== executionWorkspaceStrategySchema object def ===
executionWorkspaceStrategySchema = z13.object({
executionWorkspaceStrategySchema2 = z20.object({

file: /usr/lib/node_modules/paperclipai/dist/index.js.map
======== POLICY ========

===== executionWorkspaceStrategySchema =====
executionWorkspaceStrategySchema = z13.object({
      type: z13.enum(["project_primary", "git_worktree", "adapter_managed", "cloud_sandbox"]).optional(),
      baseRef: z13.string().optional().nullable(),
      branchTemplate: z13.string().optional().nullable(),
      worktreeParentDir: z13.string().optional().nullable(),
      provisionCommand: z13.string().optional().nullable(),
      teardownCommand: z13.string().optional().nullable()
    }).strict();
    issueExecutionWorkspaceSettingsSchema = z13.object({
      mode: z13.enum(ISSUE_EXECUTION_WORKSPACE_PREFERENCES).optional(),
      enviro

===== executionWorkspacePolicySchema =====
NOT FOUND

PERSISTED: {
 "enabled": true,
 "defaultMode": "isolated_workspace",
 "allowIssueOverride": false,
 "defaultProjectWorkspaceId": "6d7912e4-fc49-4161-9593-1335fba067b6",
 "workspaceStrategy": {
  "type": "git_worktree",
  "worktreeParentDir": "/home/ali/paperclip-worktrees/aina-academy"
 }
}

=== issue create flags ===
Usage: paperclipai issue create [options]

Create an issue

Options:
  -C, --company-id <id>     Company ID
  --title <title>           Issue title
  --description <text>      Issue description
  --status <status>         Issue status
  --priority <priority>     Issue priority
  --assignee-agent-id <id>  Assignee agent ID
  --project-id <id>         Project ID
  --goal-id <id>            Goal ID
  --parent-id <id>          Parent issue ID
  --request-depth <n>       Request depth integer
  --billing-code <code>     Billing code
  -c, --config <path>       Path to Paperclip config file
  -d, --data-dir <path>     Paperclip data directory root (isolates state from
                            ~/.paperclip)
  --context <path>          Path to CLI context file
  --profile <name>          CLI context profile name
  --api-base <url>          Base URL for the Paperclip API
  --api-key <token>         Bearer token for agent-authenticated calls
  --run-id <id>             Heartbeat run id for agent-authenticated mutations
                            (checkout/release/interactions/in-progress update);
                            falls back to $PAPERCLIP_RUN_ID
  --json                    Output raw JSON
  -h, --help                display help for command

CREATED: AIN-265 | id: 8c592c69-296c-4794-8e07-804f5f981ae4 | proj: a64c0faf-a346-4478-b08a-98b744bbec07

=== baseline: worktrees before ===
canonical checkout branch/status:
ali/ain-91-media-engine-lesson-slots
=== assign AIN-265 -> Curriculum Architect ===
assigned -> 3bdfbfc6-8498-4fc1-931c-eb3ebecec910 | status todo

Command running in background with ID: b8inj9d8d. Output is being written to: /private/tmp/claude-502/-Users-Ali-PKM/ea21dc9e-a684-460b-b5d8-244fa739715e/tasks/b8inj9d8d.output. You will be notified when it completes. To check interim output, use Read on that file path.

recorded (     205 lines)