sam/paperclip-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Project>project overview from the dashboard endpoint; tools chooser drawn in Board>board; docs for Shell and t

Browse Source
This commit is contained in:
Sam
2026-11-10 21:48:03 +11:00
parent 3d31243317
commit 3e90ca82ab
14 changed files with 1225 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
.pi/memory-vault/packs/paperclip-harness/20-context/home.md
View File

@@ -309,3 +309,133 @@ Committed as `7f18c54`. Say which item you want first and I will build only that
- session: [[packs/paperclip-harness/80-sessions/paperclip-harness-reverted-pane-split-interface-gap-discover|Paperclip-harness — reverted pane split, interface gap discovery, and PLAN-INTERFACE roadmap]]
- session: [[packs/paperclip-harness/80-sessions/rich-discovery-home-2026-11-10-05-41-48|Rich discovery: home 2026-11-10 05:41:48]]
- context: [[packs/paperclip-harness/20-context/home|home]]
---
## Update (2026-11-10 10:01:16)
## Rich discovery update (2026-11-10 10:01:16)
Explored all of it. Recorded in `docs/PLAN-INTERFACE.md`; the short version:
## Skills per agent — Paperclip already models it
`GET /api/agents/{id}/skills` returns a desired set, a managed set and a state per skill. On `Builder` today:
```
desired: ["paperclipai/paperclip/paperclip"]
company/<id>/obsidian-cli desired: false managed: true state: "stale"
```
`POST /api/agents/{id}/skills/sync` takes `add`, `remove` or **`replace`** — `replace` is exactly "this agent gets these and nothing else", which is how a sub-agent's context stays small. There is also a company skill catalog, versions, audit, and `GET/PUT /api/companies/{id}/skill-policy` with an `evaluate` call.
Proposal: two rows in `Agents>agents` settings — **skills** (the desired set, read-only first, add/remove later) and **skill source**. A full browser is a later screen, not a panel. Also: `obsidian-cli` sitting `stale` on Builder is worth fixing.
## Memory — three different things
| | state here | what it is |
|---|---|---|
| **engram** | installed, v1.16.1, MCP mode, **not** registered in `~/.pi/agent/mcp.json` (only `codebase-memory`, `graphify-vault`) | persistent memory |
| **headroom** | running, v0.24.0, healthy at `192.168.20.13:8787`, memory backend **disabled**, compression on | a prompt-compression proxy, not a store |
| **pi memctx** | in use now | injects notes into a prompt |
They are complementary. Paperclip's only per-agent lever is `adapterConfig` and `runtimeConfig`, so memory is set per agent by pointing that agent at the proxy or store it should use. Proposal: a **memory** row in `Agents>agents` settings showing which of the three that agent uses, and nothing more until one agent has run both ways and been measured.
## MOUSE-1
`MOUSE_API_KEY` is set (checked the name only, never the value). `JEV_API_KEY` too. No `mouse`, `mouse1`, `jev` or `switch` binary is installed.
There **are** notes, and they are good ones — in the old project's plan documents:
> MOUSE-1 is *"triage only: label, score, route, escalate. Never a gate, never a permit"* — explicitly ruled out for deciding a merge or allowing a tool call, because a cheap classifier that fails open on a network error makes a green run a lie.
I would adopt that policy unchanged. Its place, if added: ordering `Board>board`'s needs-you list, or pre-sorting findings in `Work>review`. Never the merge, never an approval.
## Lazygit
Already wired: `t` in `Board>board` or `Work>work`, choose Lazygit. Verified opening in the right workspace and closing with `q`.
## The old `office` — and what ours lacks
The previous `office` did four things: remember the host; run `new-project` to write the scaffold (`settings.toml`, a file per role, `verify.sh`, the per-screen notes) writing **only what is missing**; refuse if the session does not exist and print the exact `tuios new` line; then build the pages.
Ours does the host, the refusal and the pages — but **no scaffold**. No per-role files, no `verify.sh`, no page notes. That is the cheapest real gap in the whole plan.
## Dashboard — the API answers it in one call
`GET /api/companies/{id}/dashboard`, 1.8 KB:
```
agents {active 6, running 0, paused 0, error 0}
tasks {open 8, inProgress 0, blocked 4, done 147}
costs {monthSpendCents 11, monthBudgetCents 0, utilization 0}
runActivity [14 entries]
```
Proposal: a `Project>overview` panel with those blocks and a sparkline drawn in Go with `tuios.dev/plot`, rather than embedding the web dashboard in a pane.
## Not doing
Artifacts — dropped as instructed.
I am ready for the task you are about to deliver; nothing in the tree is half-changed, the eight workspaces are running, and the last commit is `3d31243`.
## Source paths observed
- `home/sam/.local/bin/engram`
- `home/sam/.config/environment.d/10-secrets.conf`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/80-sessions/paperclip-harness-reverted-pane-split-interface-gap-discover.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/80-sessions/rich-discovery-tmp-2026-11-10-07-35-38.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/80-sessions/rich-discovery-home-2026-11-10-05-41-48.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/20-context/home.md`
- `github.com/Gentleman-Programming/engram/cmd/engram`
- `api/skills/available`
- `api/skills/catalog`
- `api/skills/index`
- `paperclipai/paperclip/paperclip`
- `company/d4921013-e5da-4d88-8016-57d5746e2d03/obsidian-cli`
- `home/sam/.paperclip/instances/default/skills/d4921013-e5da-4d88-8016-57d5746e2d03/obsidian-cli`
- `home/sam/.pi/agent/skills/obsidian-`
- `dir/.harness/host`
- `home/sam/paseo/projects/tuios_coding_harness/plan/82-control-room.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/83-interface.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/80-forked-plan.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/91-paperclip-or-oma.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/50-open-work.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/skills/graphify/SKILL.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/skills/system-architect/SKILL.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/extensions/pi-graphify/skills/graphify/SKILL.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/node_modules`
- `google/genai/dist/node/index.cjs`
- `google/genai/dist/node/node.d.ts`
- `home/sam/.config/systemd/user/lan-mouse.service`
- `home/sam/.config/lan-mouse`
- `home/sam/.config/lan-mouse/lan-mouse.pem`
- `home/sam/.cache/lan-mouse`
- `home/sam/.local/bin/lan-mouse-011`
- `home/sam/.pi/agent/auth.json`
- `home/sam/.pi/agent/mcp-cache.json`
- `home/sam/.pi/agent/mcp.json`
- `home/sam/.pi/agent/models.json`
- `home/sam/.pi/agent/models-store.json`
- `home/sam/.pi/agent/settings.json`
- `home/sam/.pi/agent/trust.json`
- `home/sam/.local/bin/codebase-memory-mcp`
## Evidence
- Confidence: 84%
- Reason: Update component/repository context with detailed discovered structure and configuration
## Related learned memories <!-- same-turn-2026-11-10 10:01:16 -->
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|Paperclip per-agent skills state and sync semantics]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|Adopt an existing folder into the harness with `office` (and its known scaffold gap)]]
- decision: [[packs/paperclip-harness/50-decisions/mouse-1-restricted-to-triage-never-a-gate-or-permit|MOUSE-1 restricted to triage; never a gate or permit]]
- action: [[packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups|Recorded interface plan for Paperclip + TUIOS harness in docs/PLAN-INTERFACE.md]]
- session: [[packs/paperclip-harness/80-sessions/paperclip-tuios-interface-discovery-skills-api-memory-stack-|Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold]]
- context: [[packs/paperclip-harness/20-context/paperclip-tuios-harness-sam-s-coding-harness-office-board-wo|Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)]]
- session: [[packs/paperclip-harness/80-sessions/rich-discovery-paperclipai-2026-11-10-10-01-16|Rich discovery: paperclipai 2026-11-10 10:01:16]]
- context: [[packs/paperclip-harness/20-context/home|paperclipai]]

51
.pi/memory-vault/packs/paperclip-harness/20-context/paperclip-tuios-harness-sam-s-coding-harness-office-board-wo.md Normal file
View File

@@ -0,0 +1,51 @@
---
type: context
id: context.paperclip-harness.paperclip-tuios-harness-sam-s-coding-harness-office-board-wo
title: Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)
status: active
source_of_truth: false
freshness: current
last_reviewed: 2026-11-10
tags:
- pack/paperclip-harness
- agent-memory/context
- paperclip
- tuios
- harness
- architecture
- paths
---
# Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)
The user's coding harness is a TUIOS-based multi-screen workspace over the Paperclip API, with old source in /home/sam/paseo/projects/tuios_coding_harness (scripts `office`, `new-project`, `board`; plan/ docs 50-open-work, 80-forked-plan, 82-control-room, 83-interface, 91-paperclip-or-oma).
Screens/proposals: Agents>agents (skills rows + skill source, memory row), Project>overview (dashboard summary + Go sparkline via tuios.dev/plot), Board>board (needs-you list, `t` → Lazygit), Work>work (review/findings, `t` → Lazygit).
`office <dir> --session <name>`: detects/remembers host in .harness/host, dry-run flag, refuses when the TUIOS session does not exist (non-interactive session creation impossible) and prints `tuios new <session>`; then invokes board to build pages. Old version additionally ran new-project to write scaffold only-what-is-missing; current version lacks this scaffold step (known gap). Attach: `tuios-gpui attach <session>` (graphical) or `tuios attach <session>`, remote via `tuios-gpui attach --host <host> <session>`.
Paperclip company id in this instance: d4921013-e5da-4d88-8016-57d5746e2d03; agent adapterType pi_local, mode persistent, skills materialized under /home/sam/.paperclip/instances/default/skills/<companyId>/ and targeted at /home/sam/.pi/agent/skills/. Per-agent config levers: adapterConfig, runtimeConfig. Paperclip state at discovery: 6 active agents, 8 open / 4 blocked / 147 done tasks, 0 pending approvals, month spend 11 cents.
Local MCP: codebase-memory and graphify-vault. Pi config repo: /home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config (skills graphify, system-architect; extension pi-graphify). Also present: ~/.config/systemd/user/lan-mouse.service, /home/sam/.local/bin/codebase-memory-mcp, relay-graphify-mcp; ~/.pi/agent/{auth,mcp,models,settings,trust}.json.
Artifacts feature: dropped per instruction. Last commit at time of planning: 3d31243.
## Evidence
- Confidence: 85%
- Reason: Durable component overview with paths, environment split, screens, and integration points for the existing harness.
## Related
- [[packs/paperclip-harness/00-system/pi-agent/memory-manifest|Memory Manifest]]
## Related learned memories <!-- same-turn-2026-11-10 10:01:16 -->
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|Paperclip per-agent skills state and sync semantics]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|Adopt an existing folder into the harness with `office` (and its known scaffold gap)]]
- decision: [[packs/paperclip-harness/50-decisions/mouse-1-restricted-to-triage-never-a-gate-or-permit|MOUSE-1 restricted to triage; never a gate or permit]]
- action: [[packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups|Recorded interface plan for Paperclip + TUIOS harness in docs/PLAN-INTERFACE.md]]
- session: [[packs/paperclip-harness/80-sessions/paperclip-tuios-interface-discovery-skills-api-memory-stack-|Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold]]
- context: [[packs/paperclip-harness/20-context/paperclip-tuios-harness-sam-s-coding-harness-office-board-wo|Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)]]
- session: [[packs/paperclip-harness/80-sessions/rich-discovery-paperclipai-2026-11-10-10-01-16|Rich discovery: paperclipai 2026-11-10 10:01:16]]
- context: [[packs/paperclip-harness/20-context/home|paperclipai]]

89
.pi/memory-vault/packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups.md
View File

@@ -371,3 +371,92 @@ Also field-verified that per-agent settings PATCH merges into existing config (c
- context: [[packs/paperclip-harness/20-context/tmp|tmp]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|tmp deployment operations]]
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|tmp repository structure and configuration patterns]]
---
## Update (2026-11-10 10:01:16)
Deliverable: `docs/PLAN-INTERFACE.md` (commit `3d31243`) capturing the full interface plan: skills rows in Agents>agents (desired set + skill source, backed by existing /api/agents/{id}/skills + sync), memory row (engram/headroom/memctx), MOUSE-1 limited to triage, Project>overview panel built from /api/companies/{id}/dashboard with tuios.dev/plot sparkline, and adopting the old office scaffold (settings.toml, per-role file, verify.sh, per-screen notes) as the cheapest real gap. Lazygit confirmed already wired (`t` in Board>board / Work>work). Artifacts dropped. Validation: tree clean, eight workspaces running, no half-changes. Follow-ups: fix stale obsidian-cli on Builder; implement scaffold step in office; optionally register engram in mcp.json.
## Detailed deliverable from completed turn
Explored all of it. Recorded in `docs/PLAN-INTERFACE.md`; the short version:
## Skills per agent — Paperclip already models it
`GET /api/agents/{id}/skills` returns a desired set, a managed set and a state per skill. On `Builder` today:
```
desired: ["paperclipai/paperclip/paperclip"]
company/<id>/obsidian-cli desired: false managed: true state: "stale"
```
`POST /api/agents/{id}/skills/sync` takes `add`, `remove` or **`replace`** — `replace` is exactly "this agent gets these and nothing else", which is how a sub-agent's context stays small. There is also a company skill catalog, versions, audit, and `GET/PUT /api/companies/{id}/skill-policy` with an `evaluate` call.
Proposal: two rows in `Agents>agents` settings — **skills** (the desired set, read-only first, add/remove later) and **skill source**. A full browser is a later screen, not a panel. Also: `obsidian-cli` sitting `stale` on Builder is worth fixing.
## Memory — three different things
| | state here | what it is |
|---|---|---|
| **engram** | installed, v1.16.1, MCP mode, **not** registered in `~/.pi/agent/mcp.json` (only `codebase-memory`, `graphify-vault`) | persistent memory |
| **headroom** | running, v0.24.0, healthy at `192.168.20.13:8787`, memory backend **disabled**, compression on | a prompt-compression proxy, not a store |
| **pi memctx** | in use now | injects notes into a prompt |
They are complementary. Paperclip's only per-agent lever is `adapterConfig` and `runtimeConfig`, so memory is set per agent by pointing that agent at the proxy or store it should use. Proposal: a **memory** row in `Agents>agents` settings showing which of the three that agent uses, and nothing more until one agent has run both ways and been measured.
## MOUSE-1
`MOUSE_API_KEY` is set (checked the name only, never the value). `JEV_API_KEY` too. No `mouse`, `mouse1`, `jev` or `switch` binary is installed.
There **are** notes, and they are good ones — in the old project's plan documents:
> MOUSE-1 is *"triage only: label, score, route, escalate. Never a gate, never a permit"* — explicitly ruled out for deciding a merge or allowing a tool call, because a cheap classifier that fails open on a network error makes a green run a lie.
I would adopt that policy unchanged. Its place, if added: ordering `Board>board`'s needs-you list, or pre-sorting findings in `Work>review`. Never the merge, never an approval.
## Lazygit
Already wired: `t` in `Board>board` or `Work>work`, choose Lazygit. Verified opening in the right workspace and closing with `q`.
## The old `office` — and what ours lacks
The previous `office` did four things: remember the host; run `new-project` to write the scaffold (`settings.toml`, a file per role, `verify.sh`, the per-screen notes) writing **only what is missing**; refuse if the session does not exist and print the exact `tuios new` line; then build the pages.
Ours does the host, the refusal and the pages — but **no scaffold**. No per-role files, no `verify.sh`, no page notes. That is the cheapest real gap in the whole plan.
## Dashboard — the API answers it in one call
`GET /api/companies/{id}/dashboard`, 1.8 KB:
```
agents {active 6, running 0, paused 0, error 0}
tasks {open 8, inProgress 0, blocked 4, done 147}
costs {monthSpendCents 11, monthBudgetCents 0, utilization 0}
runActivity [14 entries]
```
Proposal: a `Project>overview` panel with those blocks and a sparkline drawn in Go with `tuios.dev/plot`, rather than embedding the web dashboard in a pane.
## Not doing
Artifacts — dropped as instructed.
I am ready for the task you are about to deliver; nothing in the tree is half-changed, the eight workspaces are running, and the last commit is `3d31243`.
## Evidence
- Confidence: 90%
- Reason: Completed deliverable with artifact path, commit, validation, and follow-ups.; enriched with final-answer detail because persistence should be reusable
## Related learned memories <!-- same-turn-2026-11-10 10:01:16 -->
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|Paperclip per-agent skills state and sync semantics]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|Adopt an existing folder into the harness with `office` (and its known scaffold gap)]]
- decision: [[packs/paperclip-harness/50-decisions/mouse-1-restricted-to-triage-never-a-gate-or-permit|MOUSE-1 restricted to triage; never a gate or permit]]
- action: [[packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups|Recorded interface plan for Paperclip + TUIOS harness in docs/PLAN-INTERFACE.md]]
- session: [[packs/paperclip-harness/80-sessions/paperclip-tuios-interface-discovery-skills-api-memory-stack-|Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold]]
- context: [[packs/paperclip-harness/20-context/paperclip-tuios-harness-sam-s-coding-harness-office-board-wo|Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)]]
- session: [[packs/paperclip-harness/80-sessions/rich-discovery-paperclipai-2026-11-10-10-01-16|Rich discovery: paperclipai 2026-11-10 10:01:16]]
- context: [[packs/paperclip-harness/20-context/home|paperclipai]]

107
.pi/memory-vault/packs/paperclip-harness/50-decisions/mouse-1-restricted-to-triage-never-a-gate-or-permit.md Normal file
View File

@@ -0,0 +1,107 @@
---
type: decision
id: decision.paperclip-harness.mouse-1-restricted-to-triage-never-a-gate-or-permit
title: MOUSE-1 restricted to triage; never a gate or permit
status: active
source_of_truth: false
freshness: current
last_reviewed: 2026-11-10
tags:
- pack/paperclip-harness
- agent-memory/decision
- mouse-1
- policy
- triage
- board
- review
---
# MOUSE-1 restricted to triage; never a gate or permit
Adopted the existing note policy unchanged: MOUSE-1 is triage only — label, score, route, escalate; never a gate, never a permit. Rationale: it is an external service (key + network hop, unproven product) and fails open on network errors, so a green run would be misleading if it gated merges or approvals. Permitted future uses: ordering Board>board's needs-you list, pre-sorting findings in Work>review. Consequences: no MOUSE-1 calls in merge/approval/tool-permission paths; MOUSE_API_KEY/JEV_API_KEY env names exist but no mouse/jev/switch binaries installed. Review caveat: revisit only after measured reliability evidence.
## Detailed decision context from completed turn
Explored all of it. Recorded in `docs/PLAN-INTERFACE.md`; the short version:
## Skills per agent — Paperclip already models it
`GET /api/agents/{id}/skills` returns a desired set, a managed set and a state per skill. On `Builder` today:
```
desired: ["paperclipai/paperclip/paperclip"]
company/<id>/obsidian-cli desired: false managed: true state: "stale"
```
`POST /api/agents/{id}/skills/sync` takes `add`, `remove` or **`replace`** — `replace` is exactly "this agent gets these and nothing else", which is how a sub-agent's context stays small. There is also a company skill catalog, versions, audit, and `GET/PUT /api/companies/{id}/skill-policy` with an `evaluate` call.
Proposal: two rows in `Agents>agents` settings — **skills** (the desired set, read-only first, add/remove later) and **skill source**. A full browser is a later screen, not a panel. Also: `obsidian-cli` sitting `stale` on Builder is worth fixing.
## Memory — three different things
| | state here | what it is |
|---|---|---|
| **engram** | installed, v1.16.1, MCP mode, **not** registered in `~/.pi/agent/mcp.json` (only `codebase-memory`, `graphify-vault`) | persistent memory |
| **headroom** | running, v0.24.0, healthy at `192.168.20.13:8787`, memory backend **disabled**, compression on | a prompt-compression proxy, not a store |
| **pi memctx** | in use now | injects notes into a prompt |
They are complementary. Paperclip's only per-agent lever is `adapterConfig` and `runtimeConfig`, so memory is set per agent by pointing that agent at the proxy or store it should use. Proposal: a **memory** row in `Agents>agents` settings showing which of the three that agent uses, and nothing more until one agent has run both ways and been measured.
## MOUSE-1
`MOUSE_API_KEY` is set (checked the name only, never the value). `JEV_API_KEY` too. No `mouse`, `mouse1`, `jev` or `switch` binary is installed.
There **are** notes, and they are good ones — in the old project's plan documents:
> MOUSE-1 is *"triage only: label, score, route, escalate. Never a gate, never a permit"* — explicitly ruled out for deciding a merge or allowing a tool call, because a cheap classifier that fails open on a network error makes a green run a lie.
I would adopt that policy unchanged. Its place, if added: ordering `Board>board`'s needs-you list, or pre-sorting findings in `Work>review`. Never the merge, never an approval.
## Lazygit
Already wired: `t` in `Board>board` or `Work>work`, choose Lazygit. Verified opening in the right workspace and closing with `q`.
## The old `office` — and what ours lacks
The previous `office` did four things: remember the host; run `new-project` to write the scaffold (`settings.toml`, a file per role, `verify.sh`, the per-screen notes) writing **only what is missing**; refuse if the session does not exist and print the exact `tuios new` line; then build the pages.
Ours does the host, the refusal and the pages — but **no scaffold**. No per-role files, no `verify.sh`, no page notes. That is the cheapest real gap in the whole plan.
## Dashboard — the API answers it in one call
`GET /api/companies/{id}/dashboard`, 1.8 KB:
```
agents {active 6, running 0, paused 0, error 0}
tasks {open 8, inProgress 0, blocked 4, done 147}
costs {monthSpendCents 11, monthBudgetCents 0, utilization 0}
runActivity [14 entries]
```
Proposal: a `Project>overview` panel with those blocks and a sparkline drawn in Go with `tuios.dev/plot`, rather than embedding the web dashboard in a pane.
## Not doing
Artifacts — dropped as instructed.
I am ready for the task you are about to deliver; nothing in the tree is half-changed, the eight workspaces are running, and the last commit is `3d31243`.
## Evidence
- Confidence: 90%
- Reason: Architectural/policy convention with rationale and explicit boundaries.; enriched with final-answer detail because persistence should be reusable
## Related
- [[packs/paperclip-harness/00-system/pi-agent/memory-manifest|Memory Manifest]]
## Related learned memories <!-- same-turn-2026-11-10 10:01:16 -->
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|Paperclip per-agent skills state and sync semantics]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|Adopt an existing folder into the harness with `office` (and its known scaffold gap)]]
- decision: [[packs/paperclip-harness/50-decisions/mouse-1-restricted-to-triage-never-a-gate-or-permit|MOUSE-1 restricted to triage; never a gate or permit]]
- action: [[packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups|Recorded interface plan for Paperclip + TUIOS harness in docs/PLAN-INTERFACE.md]]
- session: [[packs/paperclip-harness/80-sessions/paperclip-tuios-interface-discovery-skills-api-memory-stack-|Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold]]
- context: [[packs/paperclip-harness/20-context/paperclip-tuios-harness-sam-s-coding-harness-office-board-wo|Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)]]
- session: [[packs/paperclip-harness/80-sessions/rich-discovery-paperclipai-2026-11-10-10-01-16|Rich discovery: paperclipai 2026-11-10 10:01:16]]
- context: [[packs/paperclip-harness/20-context/home|paperclipai]]

185
.pi/memory-vault/packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns.md
View File

@@ -1304,3 +1304,188 @@ Committed as `7b12b45`. Say go and I run that list end to end and report each re
- context: [[packs/paperclip-harness/20-context/tmp|tmp]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|tmp deployment operations]]
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|tmp repository structure and configuration patterns]]
---
## Update (2026-11-10 10:01:16)
`GET /api/agents/{id}/skills` returns supported/mode, desiredSkills + desiredSkillEntries (key/versionId), and entries[] with key, runtimeName, versionId, currentVersionId, desired, managed, state, sourcePath, targetPath.
Observed on agent Builder (adapterType pi_local, mode persistent): desired=[`paperclipai/paperclip/paperclip`]; entry `company/d4921013-e5da-4d88-8016-57d5746e2d03/obsidian-cli` has desired=false, managed=true, state=`stale`, runtimeName `obsidian-cli--b74ae42966`, sourcePath under /home/sam/.paperclip/instances/default/skills/<companyId>/obsidian-cli, targetPath under /home/sam/.pi/agent/skills/.
`POST /api/agents/{id}/skills/sync` supports add / remove / replace; `replace` gives an exclusive skill set (keeps sub-agent context small).
Company-level skill management surface: /api/companies/{companyId}/skills (GET,POST, /{skillId} GET/PATCH/DELETE), versions (GET,POST, /{versionId}), files, audit, comments, fork + fork-precheck, rename, reset, star, install-update, update-status, test-inputs, test-runs (+cancel), categories, import, install-catalog, scan-projects, browse-project; skill-policy GET/PUT/DELETE + /evaluate; skill-test-run-templates. Public: /api/skills/{index,available,catalog,catalogId,skillName}; invite-scoped /api/invites/{token}/skills/...
## Evidence
- Confidence: 90%
- Reason: Factual API/state discovery likely to be reused when implementing skills UI or fixing stale skills.
---
## Update (2026-11-10 10:01:16)
`GET /api/companies/{id}/dashboard` returns (observed 1.8 KB): agents {active, running, paused, error} = 6/0/0/0; tasks {open, inProgress, blocked, done} = 8/0/4/147; costs {monthSpendCents, monthBudgetCents, monthUtilizationPercent} = 11/0/0; pendingApprovals 0; budgets {activeIncidents, pendingApprovals, pausedAgents, pausedProjects} all 0; runActivity list of 14. Proposed UI: a Project>overview panel rendering these blocks with a Go sparkline (tuios.dev/plot) instead of embedding the web dashboard.
## Detailed observations from completed turn
Explored all of it. Recorded in `docs/PLAN-INTERFACE.md`; the short version:
## Skills per agent — Paperclip already models it
`GET /api/agents/{id}/skills` returns a desired set, a managed set and a state per skill. On `Builder` today:
```
desired: ["paperclipai/paperclip/paperclip"]
company/<id>/obsidian-cli desired: false managed: true state: "stale"
```
`POST /api/agents/{id}/skills/sync` takes `add`, `remove` or **`replace`** — `replace` is exactly "this agent gets these and nothing else", which is how a sub-agent's context stays small. There is also a company skill catalog, versions, audit, and `GET/PUT /api/companies/{id}/skill-policy` with an `evaluate` call.
Proposal: two rows in `Agents>agents` settings — **skills** (the desired set, read-only first, add/remove later) and **skill source**. A full browser is a later screen, not a panel. Also: `obsidian-cli` sitting `stale` on Builder is worth fixing.
## Memory — three different things
| | state here | what it is |
|---|---|---|
| **engram** | installed, v1.16.1, MCP mode, **not** registered in `~/.pi/agent/mcp.json` (only `codebase-memory`, `graphify-vault`) | persistent memory |
| **headroom** | running, v0.24.0, healthy at `192.168.20.13:8787`, memory backend **disabled**, compression on | a prompt-compression proxy, not a store |
| **pi memctx** | in use now | injects notes into a prompt |
They are complementary. Paperclip's only per-agent lever is `adapterConfig` and `runtimeConfig`, so memory is set per agent by pointing that agent at the proxy or store it should use. Proposal: a **memory** row in `Agents>agents` settings showing which of the three that agent uses, and nothing more until one agent has run both ways and been measured.
## MOUSE-1
`MOUSE_API_KEY` is set (checked the name only, never the value). `JEV_API_KEY` too. No `mouse`, `mouse1`, `jev` or `switch` binary is installed.
There **are** notes, and they are good ones — in the old project's plan documents:
> MOUSE-1 is *"triage only: label, score, route, escalate. Never a gate, never a permit"* — explicitly ruled out for deciding a merge or allowing a tool call, because a cheap classifier that fails open on a network error makes a green run a lie.
I would adopt that policy unchanged. Its place, if added: ordering `Board>board`'s needs-you list, or pre-sorting findings in `Work>review`. Never the merge, never an approval.
## Lazygit
Already wired: `t` in `Board>board` or `Work>work`, choose Lazygit. Verified opening in the right workspace and closing with `q`.
## The old `office` — and what ours lacks
The previous `office` did four things: remember the host; run `new-project` to write the scaffold (`settings.toml`, a file per role, `verify.sh`, the per-screen notes) writing **only what is missing**; refuse if the session does not exist and print the exact `tuios new` line; then build the pages.
Ours does the host, the refusal and the pages — but **no scaffold**. No per-role files, no `verify.sh`, no page notes. That is the cheapest real gap in the whole plan.
## Dashboard — the API answers it in one call
`GET /api/companies/{id}/dashboard`, 1.8 KB:
```
agents {active 6, running 0, paused 0, error 0}
tasks {open 8, inProgress 0, blocked 4, done 147}
costs {monthSpendCents 11, monthBudgetCents 0, utilization 0}
runActivity [14 entries]
```
Proposal: a `Project>overview` panel with those blocks and a sparkline drawn in Go with `tuios.dev/plot`, rather than embedding the web dashboard in a pane.
## Not doing
Artifacts — dropped as instructed.
I am ready for the task you are about to deliver; nothing in the tree is half-changed, the eight workspaces are running, and the last commit is `3d31243`.
## Evidence
- Confidence: 90%
- Reason: Concrete endpoint shape and counts support future Project>overview implementation.; enriched with final-answer detail because persistence should be reusable
---
## Update (2026-11-10 10:01:16)
Three complementary memory mechanisms: (a) engram v1.16.1 installed in MCP mode but NOT registered in ~/.pi/agent/mcp.json; (b) headroom prompt-compression proxy v0.24.0 healthy at 192.168.20.13:8787 with memory backend disabled (memory check enabled=false, backend null) and compression on; (c) pi memctx, which injects notes into a prompt. Registered MCP servers at discovery: only codebase-memory and graphify-vault (both lifecycle lazy). Paperclip exposes only adapterConfig and runtimeConfig per agent, so memory choice is expressed by pointing an agent at the desired proxy/store. Proposal: a memory row in Agents>agents showing which mechanism an agent uses, pending measurement.
## Detailed observations from completed turn
Explored all of it. Recorded in `docs/PLAN-INTERFACE.md`; the short version:
## Skills per agent — Paperclip already models it
`GET /api/agents/{id}/skills` returns a desired set, a managed set and a state per skill. On `Builder` today:
```
desired: ["paperclipai/paperclip/paperclip"]
company/<id>/obsidian-cli desired: false managed: true state: "stale"
```
`POST /api/agents/{id}/skills/sync` takes `add`, `remove` or **`replace`** — `replace` is exactly "this agent gets these and nothing else", which is how a sub-agent's context stays small. There is also a company skill catalog, versions, audit, and `GET/PUT /api/companies/{id}/skill-policy` with an `evaluate` call.
Proposal: two rows in `Agents>agents` settings — **skills** (the desired set, read-only first, add/remove later) and **skill source**. A full browser is a later screen, not a panel. Also: `obsidian-cli` sitting `stale` on Builder is worth fixing.
## Memory — three different things
| | state here | what it is |
|---|---|---|
| **engram** | installed, v1.16.1, MCP mode, **not** registered in `~/.pi/agent/mcp.json` (only `codebase-memory`, `graphify-vault`) | persistent memory |
| **headroom** | running, v0.24.0, healthy at `192.168.20.13:8787`, memory backend **disabled**, compression on | a prompt-compression proxy, not a store |
| **pi memctx** | in use now | injects notes into a prompt |
They are complementary. Paperclip's only per-agent lever is `adapterConfig` and `runtimeConfig`, so memory is set per agent by pointing that agent at the proxy or store it should use. Proposal: a **memory** row in `Agents>agents` settings showing which of the three that agent uses, and nothing more until one agent has run both ways and been measured.
## MOUSE-1
`MOUSE_API_KEY` is set (checked the name only, never the value). `JEV_API_KEY` too. No `mouse`, `mouse1`, `jev` or `switch` binary is installed.
There **are** notes, and they are good ones — in the old project's plan documents:
> MOUSE-1 is *"triage only: label, score, route, escalate. Never a gate, never a permit"* — explicitly ruled out for deciding a merge or allowing a tool call, because a cheap classifier that fails open on a network error makes a green run a lie.
I would adopt that policy unchanged. Its place, if added: ordering `Board>board`'s needs-you list, or pre-sorting findings in `Work>review`. Never the merge, never an approval.
## Lazygit
Already wired: `t` in `Board>board` or `Work>work`, choose Lazygit. Verified opening in the right workspace and closing with `q`.
## The old `office` — and what ours lacks
The previous `office` did four things: remember the host; run `new-project` to write the scaffold (`settings.toml`, a file per role, `verify.sh`, the per-screen notes) writing **only what is missing**; refuse if the session does not exist and print the exact `tuios new` line; then build the pages.
Ours does the host, the refusal and the pages — but **no scaffold**. No per-role files, no `verify.sh`, no page notes. That is the cheapest real gap in the whole plan.
## Dashboard — the API answers it in one call
`GET /api/companies/{id}/dashboard`, 1.8 KB:
```
agents {active 6, running 0, paused 0, error 0}
tasks {open 8, inProgress 0, blocked 4, done 147}
costs {monthSpendCents 11, monthBudgetCents 0, utilization 0}
runActivity [14 entries]
```
Proposal: a `Project>overview` panel with those blocks and a sparkline drawn in Go with `tuios.dev/plot`, rather than embedding the web dashboard in a pane.
## Not doing
Artifacts — dropped as instructed.
I am ready for the task you are about to deliver; nothing in the tree is half-changed, the eight workspaces are running, and the last commit is `3d31243`.
## Evidence
- Confidence: 85%
- Reason: Durable operational facts about memory components and configuration gaps.; enriched with final-answer detail because persistence should be reusable
## Related learned memories <!-- same-turn-2026-11-10 10:01:16 -->
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|Paperclip per-agent skills state and sync semantics]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|Adopt an existing folder into the harness with `office` (and its known scaffold gap)]]
- decision: [[packs/paperclip-harness/50-decisions/mouse-1-restricted-to-triage-never-a-gate-or-permit|MOUSE-1 restricted to triage; never a gate or permit]]
- action: [[packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups|Recorded interface plan for Paperclip + TUIOS harness in docs/PLAN-INTERFACE.md]]
- session: [[packs/paperclip-harness/80-sessions/paperclip-tuios-interface-discovery-skills-api-memory-stack-|Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold]]
- context: [[packs/paperclip-harness/20-context/paperclip-tuios-harness-sam-s-coding-harness-office-board-wo|Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)]]
- session: [[packs/paperclip-harness/80-sessions/rich-discovery-paperclipai-2026-11-10-10-01-16|Rich discovery: paperclipai 2026-11-10 10:01:16]]
- context: [[packs/paperclip-harness/20-context/home|paperclipai]]

302
.pi/memory-vault/packs/paperclip-harness/70-runbooks/tmp-deployment-operations.md
View File

@@ -101,3 +101,305 @@ Committed as `7b12b45`. Say go and I run that list end to end and report each re
- context: [[packs/paperclip-harness/20-context/tmp|tmp]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|tmp deployment operations]]
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|tmp repository structure and configuration patterns]]
---
## Update (2026-11-10 10:01:16)
Trigger: bringing an existing git repo or folder into the TUIOS harness.
Procedure (`office <dir> [--session <name>] [--dry]`):
1. Resolve host: read/write `<dir>/.harness/host`; mkdir `<dir>/.harness` if missing (dry-run prints planned actions and exits).
2. Detect whether project is 'adopting (writing what is missing)' vs 'already a harness project'.
3. Ensure TUIOS session exists: `timeout 20 tuios list-sessions` (strip ANSI, parse column 2) must contain the session. If absent, office prints `tuios new <session>` and exits 2 — TUIOS cannot create sessions non-interactively in this build ('Standard output is not a terminal').
4. Run `board` with HARNESS_REPO and HARNESS_SESSION set to build/repair pages.
5. Print attach commands: `tuios-gpui attach <session>`, `tuios attach <session>`, remote `tuios-gpui attach --host <hostname> <session>`.
Known gap: old office also ran `new-project` to write scaffold (settings.toml, one file per role, verify.sh, per-screen notes) only when missing; current office skips this. Safe: office/new-project never overwrite existing files. Troubleshooting: 'office: new-project failed' or 'office: board failed' indicate the respective step; re-run is idempotent.
## Detailed procedure from completed turn
Explored all of it. Recorded in `docs/PLAN-INTERFACE.md`; the short version:
## Skills per agent — Paperclip already models it
`GET /api/agents/{id}/skills` returns a desired set, a managed set and a state per skill. On `Builder` today:
```
desired: ["paperclipai/paperclip/paperclip"]
company/<id>/obsidian-cli desired: false managed: true state: "stale"
```
`POST /api/agents/{id}/skills/sync` takes `add`, `remove` or **`replace`** — `replace` is exactly "this agent gets these and nothing else", which is how a sub-agent's context stays small. There is also a company skill catalog, versions, audit, and `GET/PUT /api/companies/{id}/skill-policy` with an `evaluate` call.
Proposal: two rows in `Agents>agents` settings — **skills** (the desired set, read-only first, add/remove later) and **skill source**. A full browser is a later screen, not a panel. Also: `obsidian-cli` sitting `stale` on Builder is worth fixing.
## Memory — three different things
| | state here | what it is |
|---|---|---|
| **engram** | installed, v1.16.1, MCP mode, **not** registered in `~/.pi/agent/mcp.json` (only `codebase-memory`, `graphify-vault`) | persistent memory |
| **headroom** | running, v0.24.0, healthy at `192.168.20.13:8787`, memory backend **disabled**, compression on | a prompt-compression proxy, not a store |
| **pi memctx** | in use now | injects notes into a prompt |
They are complementary. Paperclip's only per-agent lever is `adapterConfig` and `runtimeConfig`, so memory is set per agent by pointing that agent at the proxy or store it should use. Proposal: a **memory** row in `Agents>agents` settings showing which of the three that agent uses, and nothing more until one agent has run both ways and been measured.
## MOUSE-1
`MOUSE_API_KEY` is set (checked the name only, never the value). `JEV_API_KEY` too. No `mouse`, `mouse1`, `jev` or `switch` binary is installed.
There **are** notes, and they are good ones — in the old project's plan documents:
> MOUSE-1 is *"triage only: label, score, route, escalate. Never a gate, never a permit"* — explicitly ruled out for deciding a merge or allowing a tool call, because a cheap classifier that fails open on a network error makes a green run a lie.
I would adopt that policy unchanged. Its place, if added: ordering `Board>board`'s needs-you list, or pre-sorting findings in `Work>review`. Never the merge, never an approval.
## Lazygit
Already wired: `t` in `Board>board` or `Work>work`, choose Lazygit. Verified opening in the right workspace and closing with `q`.
## The old `office` — and what ours lacks
The previous `office` did four things: remember the host; run `new-project` to write the scaffold (`settings.toml`, a file per role, `verify.sh`, the per-screen notes) writing **only what is missing**; refuse if the session does not exist and print the exact `tuios new` line; then build the pages.
Ours does the host, the refusal and the pages — but **no scaffold**. No per-role files, no `verify.sh`, no page notes. That is the cheapest real gap in the whole plan.
## Dashboard — the API answers it in one call
`GET /api/companies/{id}/dashboard`, 1.8 KB:
```
agents {active 6, running 0, paused 0, error 0}
tasks {open 8, inProgress 0, blocked 4, done 147}
costs {monthSpendCents 11, monthBudgetCents 0, utilization 0}
runActivity [14 entries]
```
Proposal: a `Project>overview` panel with those blocks and a sparkline drawn in Go with `tuios.dev/plot`, rather than embedding the web dashboard in a pane.
## Not doing
Artifacts — dropped as instructed.
I am ready for the task you are about to deliver; nothing in the tree is half-changed, the eight workspaces are running, and the last commit is `3d31243`.
## Evidence
- Confidence: 85%
- Reason: Repeatable procedure with prerequisites, exit codes, safe behavior, and the known-scaffold caveat.; enriched with final-answer detail because persistence should be reusable
---
## Update (2026-11-10 10:01:16)
Trigger: desired skill set for an agent changed, or a skill shows `stale`.
1. Inspect: `GET /api/agents/{id}/skills` — read desiredSkills, desiredSkillEntries, and entries[] (desired, managed, state, runtimeName, sourcePath, targetPath).
2. Decide mode: `POST /api/agents/{id}/skills/sync` with add / remove, or `replace` for an exclusive set (recommended for sub-agents to keep context small).
3. For company-level operations use `/api/companies/{companyId}/skills/...` (import, install-catalog, scan-projects, versions, audit, fork, install-update). Policy checks: `GET/PUT /api/companies/{companyId}/skill-policy` and `POST .../skill-policy/evaluate`.
4. Verify after sync that entries show desired=true and state not `stale`.
Caveats: managed skills materialize from /home/sam/.paperclip/instances/default/skills/<companyId>/ into /home/sam/.pi/agent/skills/; a `stale` managed skill (e.g. obsidian-cli on Builder) needs reset/install-update, not just add. Avoid `replace` on the top-level orchestrator agent, which intentionally carries the `paperclipai/paperclip/paperclip` skill.
## Detailed procedure from completed turn
Explored all of it. Recorded in `docs/PLAN-INTERFACE.md`; the short version:
## Skills per agent — Paperclip already models it
`GET /api/agents/{id}/skills` returns a desired set, a managed set and a state per skill. On `Builder` today:
```
desired: ["paperclipai/paperclip/paperclip"]
company/<id>/obsidian-cli desired: false managed: true state: "stale"
```
`POST /api/agents/{id}/skills/sync` takes `add`, `remove` or **`replace`** — `replace` is exactly "this agent gets these and nothing else", which is how a sub-agent's context stays small. There is also a company skill catalog, versions, audit, and `GET/PUT /api/companies/{id}/skill-policy` with an `evaluate` call.
Proposal: two rows in `Agents>agents` settings — **skills** (the desired set, read-only first, add/remove later) and **skill source**. A full browser is a later screen, not a panel. Also: `obsidian-cli` sitting `stale` on Builder is worth fixing.
## Memory — three different things
| | state here | what it is |
|---|---|---|
| **engram** | installed, v1.16.1, MCP mode, **not** registered in `~/.pi/agent/mcp.json` (only `codebase-memory`, `graphify-vault`) | persistent memory |
| **headroom** | running, v0.24.0, healthy at `192.168.20.13:8787`, memory backend **disabled**, compression on | a prompt-compression proxy, not a store |
| **pi memctx** | in use now | injects notes into a prompt |
They are complementary. Paperclip's only per-agent lever is `adapterConfig` and `runtimeConfig`, so memory is set per agent by pointing that agent at the proxy or store it should use. Proposal: a **memory** row in `Agents>agents` settings showing which of the three that agent uses, and nothing more until one agent has run both ways and been measured.
## MOUSE-1
`MOUSE_API_KEY` is set (checked the name only, never the value). `JEV_API_KEY` too. No `mouse`, `mouse1`, `jev` or `switch` binary is installed.
There **are** notes, and they are good ones — in the old project's plan documents:
> MOUSE-1 is *"triage only: label, score, route, escalate. Never a gate, never a permit"* — explicitly ruled out for deciding a merge or allowing a tool call, because a cheap classifier that fails open on a network error makes a green run a lie.
I would adopt that policy unchanged. Its place, if added: ordering `Board>board`'s needs-you list, or pre-sorting findings in `Work>review`. Never the merge, never an approval.
## Lazygit
Already wired: `t` in `Board>board` or `Work>work`, choose Lazygit. Verified opening in the right workspace and closing with `q`.
## The old `office` — and what ours lacks
The previous `office` did four things: remember the host; run `new-project` to write the scaffold (`settings.toml`, a file per role, `verify.sh`, the per-screen notes) writing **only what is missing**; refuse if the session does not exist and print the exact `tuios new` line; then build the pages.
Ours does the host, the refusal and the pages — but **no scaffold**. No per-role files, no `verify.sh`, no page notes. That is the cheapest real gap in the whole plan.
## Dashboard — the API answers it in one call
`GET /api/companies/{id}/dashboard`, 1.8 KB:
```
agents {active 6, running 0, paused 0, error 0}
tasks {open 8, inProgress 0, blocked 4, done 147}
costs {monthSpendCents 11, monthBudgetCents 0, utilization 0}
runActivity [14 entries]
```
Proposal: a `Project>overview` panel with those blocks and a sparkline drawn in Go with `tuios.dev/plot`, rather than embedding the web dashboard in a pane.
## Not doing
Artifacts — dropped as instructed.
I am ready for the task you are about to deliver; nothing in the tree is half-changed, the eight workspaces are running, and the last commit is `3d31243`.
## Evidence
- Confidence: 80%
- Reason: Actionable procedure derived from concrete API behavior and observed stale state.; enriched with final-answer detail because persistence should be reusable
---
## Update (2026-11-10 10:01:16)
## Deployment/runbook details discovered (2026-11-10 10:01:16)
Explored all of it. Recorded in `docs/PLAN-INTERFACE.md`; the short version:
## Skills per agent — Paperclip already models it
`GET /api/agents/{id}/skills` returns a desired set, a managed set and a state per skill. On `Builder` today:
```
desired: ["paperclipai/paperclip/paperclip"]
company/<id>/obsidian-cli desired: false managed: true state: "stale"
```
`POST /api/agents/{id}/skills/sync` takes `add`, `remove` or **`replace`** — `replace` is exactly "this agent gets these and nothing else", which is how a sub-agent's context stays small. There is also a company skill catalog, versions, audit, and `GET/PUT /api/companies/{id}/skill-policy` with an `evaluate` call.
Proposal: two rows in `Agents>agents` settings — **skills** (the desired set, read-only first, add/remove later) and **skill source**. A full browser is a later screen, not a panel. Also: `obsidian-cli` sitting `stale` on Builder is worth fixing.
## Memory — three different things
| | state here | what it is |
|---|---|---|
| **engram** | installed, v1.16.1, MCP mode, **not** registered in `~/.pi/agent/mcp.json` (only `codebase-memory`, `graphify-vault`) | persistent memory |
| **headroom** | running, v0.24.0, healthy at `192.168.20.13:8787`, memory backend **disabled**, compression on | a prompt-compression proxy, not a store |
| **pi memctx** | in use now | injects notes into a prompt |
They are complementary. Paperclip's only per-agent lever is `adapterConfig` and `runtimeConfig`, so memory is set per agent by pointing that agent at the proxy or store it should use. Proposal: a **memory** row in `Agents>agents` settings showing which of the three that agent uses, and nothing more until one agent has run both ways and been measured.
## MOUSE-1
`MOUSE_API_KEY` is set (checked the name only, never the value). `JEV_API_KEY` too. No `mouse`, `mouse1`, `jev` or `switch` binary is installed.
There **are** notes, and they are good ones — in the old project's plan documents:
> MOUSE-1 is *"triage only: label, score, route, escalate. Never a gate, never a permit"* — explicitly ruled out for deciding a merge or allowing a tool call, because a cheap classifier that fails open on a network error makes a green run a lie.
I would adopt that policy unchanged. Its place, if added: ordering `Board>board`'s needs-you list, or pre-sorting findings in `Work>review`. Never the merge, never an approval.
## Lazygit
Already wired: `t` in `Board>board` or `Work>work`, choose Lazygit. Verified opening in the right workspace and closing with `q`.
## The old `office` — and what ours lacks
The previous `office` did four things: remember the host; run `new-project` to write the scaffold (`settings.toml`, a file per role, `verify.sh`, the per-screen notes) writing **only what is missing**; refuse if the session does not exist and print the exact `tuios new` line; then build the pages.
Ours does the host, the refusal and the pages — but **no scaffold**. No per-role files, no `verify.sh`, no page notes. That is the cheapest real gap in the whole plan.
## Dashboard — the API answers it in one call
`GET /api/companies/{id}/dashboard`, 1.8 KB:
```
agents {active 6, running 0, paused 0, error 0}
tasks {open 8, inProgress 0, blocked 4, done 147}
costs {monthSpendCents 11, monthBudgetCents 0, utilization 0}
runActivity [14 entries]
```
Proposal: a `Project>overview` panel with those blocks and a sparkline drawn in Go with `tuios.dev/plot`, rather than embedding the web dashboard in a pane.
## Not doing
Artifacts — dropped as instructed.
I am ready for the task you are about to deliver; nothing in the tree is half-changed, the eight workspaces are running, and the last commit is `3d31243`.
## Source paths observed
- `home/sam/.local/bin/engram`
- `home/sam/.config/environment.d/10-secrets.conf`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/80-sessions/paperclip-harness-reverted-pane-split-interface-gap-discover.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/80-sessions/rich-discovery-tmp-2026-11-10-07-35-38.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/80-sessions/rich-discovery-home-2026-11-10-05-41-48.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/20-context/home.md`
- `github.com/Gentleman-Programming/engram/cmd/engram`
- `api/skills/available`
- `api/skills/catalog`
- `api/skills/index`
- `paperclipai/paperclip/paperclip`
- `company/d4921013-e5da-4d88-8016-57d5746e2d03/obsidian-cli`
- `home/sam/.paperclip/instances/default/skills/d4921013-e5da-4d88-8016-57d5746e2d03/obsidian-cli`
- `home/sam/.pi/agent/skills/obsidian-`
- `dir/.harness/host`
- `home/sam/paseo/projects/tuios_coding_harness/plan/82-control-room.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/83-interface.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/80-forked-plan.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/91-paperclip-or-oma.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/50-open-work.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/skills/graphify/SKILL.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/skills/system-architect/SKILL.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/extensions/pi-graphify/skills/graphify/SKILL.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/node_modules`
- `google/genai/dist/node/index.cjs`
- `google/genai/dist/node/node.d.ts`
- `home/sam/.config/systemd/user/lan-mouse.service`
- `home/sam/.config/lan-mouse`
- `home/sam/.config/lan-mouse/lan-mouse.pem`
- `home/sam/.cache/lan-mouse`
- `home/sam/.local/bin/lan-mouse-011`
- `home/sam/.pi/agent/auth.json`
- `home/sam/.pi/agent/mcp-cache.json`
- `home/sam/.pi/agent/mcp.json`
- `home/sam/.pi/agent/models.json`
- `home/sam/.pi/agent/models-store.json`
- `home/sam/.pi/agent/settings.json`
- `home/sam/.pi/agent/trust.json`
- `home/sam/.local/bin/codebase-memory-mcp`
## Evidence
- Confidence: 83%
- Reason: Extracted repeatable deploy/configuration procedure from rich discovery
## Related learned memories <!-- same-turn-2026-11-10 10:01:16 -->
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|Paperclip per-agent skills state and sync semantics]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|Adopt an existing folder into the harness with `office` (and its known scaffold gap)]]
- decision: [[packs/paperclip-harness/50-decisions/mouse-1-restricted-to-triage-never-a-gate-or-permit|MOUSE-1 restricted to triage; never a gate or permit]]
- action: [[packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups|Recorded interface plan for Paperclip + TUIOS harness in docs/PLAN-INTERFACE.md]]
- session: [[packs/paperclip-harness/80-sessions/paperclip-tuios-interface-discovery-skills-api-memory-stack-|Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold]]
- context: [[packs/paperclip-harness/20-context/paperclip-tuios-harness-sam-s-coding-harness-office-board-wo|Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)]]
- session: [[packs/paperclip-harness/80-sessions/rich-discovery-paperclipai-2026-11-10-10-01-16|Rich discovery: paperclipai 2026-11-10 10:01:16]]
- context: [[packs/paperclip-harness/20-context/home|paperclipai]]

55
.pi/memory-vault/packs/paperclip-harness/80-sessions/paperclip-tuios-interface-discovery-skills-api-memory-stack-.md Normal file
View File

@@ -0,0 +1,55 @@
---
type: session
id: session.paperclip-harness.paperclip-tuios-interface-discovery-skills-api-memory-stack-
title: Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold
status: active
source_of_truth: false
freshness: current
last_reviewed: 2026-11-10
tags:
- pack/paperclip-harness
- agent-memory/session
- paperclip
- tuios
- skills-api
- memory
- mouse-1
- dashboard
- office-scaffold
---
# Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold
Discovery pass recorded in `docs/PLAN-INTERFACE.md`, last commit `3d31243`.
1) Skills per agent: `GET /api/agents/{id}/skills` returns desired/managed sets + per-skill state. Builder currently: desired=[paperclipai/paperclip/paperclip]; company/<id>/obsidian-cli desired=false, managed=true, state="stale" (runtimeName obsidian-cli--b74ae42966, currentVersionId cf41ba39-..., sourcePath /home/sam/.paperclip/instances/default/skills/<companyId>/obsidian-cli). `POST /api/agents/{id}/skills/sync` accepts add/remove/replace (`replace` = exclusive set, keeps sub-agent context small). Full skills API surface: company skills CRUD/import/install-catalog/scan-projects/browse-project, versions, audit, comments, files, fork + fork-precheck, rename, reset, star, test-inputs, test-runs(+cancel), install-update, update-status, `GET/PUT/DELETE /api/companies/{id}/skill-policy` + `/evaluate`, skill-test-run-templates, `/api/skills/{index,available,catalog,...}`, invite-scoped skill index. Proposal: two rows in Agents>agents settings — skills (desired set, read-only first) and skill source; full browser later; fix stale obsidian-cli.
2) Memory is three distinct things: engram (v1.16.1 installed, MCP mode, NOT registered in ~/.pi/agent/mcp.json), headroom (v0.24.0 proxy at 192.168.20.13:8787, healthy, memory backend disabled, compression on — not a store), and pi memctx (injects notes into prompt). Only mcp servers registered: codebase-memory (/home/sam/.local/bin/codebase-memory-mcp), graphify-vault (/home/sam/.local/bin/relay-graphify-mcp), both lazy. Paperclip per-agent levers are adapterConfig/runtimeConfig. Proposal: a memory row in Agents>agents showing which of the three an agent uses, nothing more until measured.
3) MOUSE-1: MOUSE_API_KEY and JEV_API_KEY env names present (values not inspected); no mouse/mouse1/jev/switch binary installed. Existing notes state policy: "triage only: label, score, route, escalate. Never a gate, never a permit" — ruled out for merges/tool-call gating because it fails open on network errors. Adopted unchanged; if added, may only order Board>board needs-you list or pre-sort findings in Work>review.
4) Lazygit: already wired — `t` in Board>board or Work>work, opens in correct workspace, quits with `q`.
5) Old `office` (~/paseo/projects/tuios_coding_harness, scripts office/new-project/board): remembers host in .harness/host; runs new-project to write scaffold (settings.toml, per-role file, verify.sh, per-screen notes) only what is missing; refuses if session absent and prints exact `tuios new <session>` line (TUIOS cannot create sessions non-interactively — "Standard output is not a terminal"); then builds pages. Current office does host/refusal/pages but NO scaffold — cheapest real gap.
6) Dashboard: `GET /api/companies/{id}/dashboard` returns ~1.8KB: agents{active 6, running 0, paused 0, error 0}, tasks{open 8, inProgress 0, blocked 4, done 147}, costs{monthSpendCents 11, monthBudgetCents 0, utilization 0}, runActivity[14]. Proposal: Project>overview panel with those blocks + sparkline via tuios.dev/plot instead of embedding web dashboard. Artifacts explicitly dropped.
## Evidence
- Confidence: 90%
- Reason: Rich evidence-backed discovery snapshot with concrete endpoints, component versions, paths, and proposals useful to future agents.
## Related
- [[packs/paperclip-harness/00-system/pi-agent/memory-manifest|Memory Manifest]]
## Related learned memories <!-- same-turn-2026-11-10 10:01:16 -->
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|Paperclip per-agent skills state and sync semantics]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|Adopt an existing folder into the harness with `office` (and its known scaffold gap)]]
- decision: [[packs/paperclip-harness/50-decisions/mouse-1-restricted-to-triage-never-a-gate-or-permit|MOUSE-1 restricted to triage; never a gate or permit]]
- action: [[packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups|Recorded interface plan for Paperclip + TUIOS harness in docs/PLAN-INTERFACE.md]]
- session: [[packs/paperclip-harness/80-sessions/paperclip-tuios-interface-discovery-skills-api-memory-stack-|Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold]]
- context: [[packs/paperclip-harness/20-context/paperclip-tuios-harness-sam-s-coding-harness-office-board-wo|Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)]]
- session: [[packs/paperclip-harness/80-sessions/rich-discovery-paperclipai-2026-11-10-10-01-16|Rich discovery: paperclipai 2026-11-10 10:01:16]]
- context: [[packs/paperclip-harness/20-context/home|paperclipai]]

149
.pi/memory-vault/packs/paperclip-harness/80-sessions/rich-discovery-paperclipai-2026-11-10-10-01-16.md Normal file
View File

@@ -0,0 +1,149 @@
---
type: session
id: session.paperclip-harness.rich-discovery-paperclipai-2026-11-10-10-01-16
title: Rich discovery: paperclipai 2026-11-10 10:01:16
status: active
source_of_truth: false
freshness: current
last_reviewed: 2026-11-10
tags:
- pack/paperclip-harness
- agent-memory/session
- autolearn
- rich-discovery
- repo/paperclipai
---
# Rich discovery: paperclipai 2026-11-10 10:01:16
Sanitized rich discovery snapshot captured automatically from the completed turn.
## Source paths observed
- `home/sam/.local/bin/engram`
- `home/sam/.config/environment.d/10-secrets.conf`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/80-sessions/paperclip-harness-reverted-pane-split-interface-gap-discover.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/80-sessions/rich-discovery-tmp-2026-11-10-07-35-38.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/80-sessions/rich-discovery-home-2026-11-10-05-41-48.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups.md`
- `home/sam/paseo/projects/paperclip-harness/.pi/memory-vault/packs/paperclip-harness/20-context/home.md`
- `github.com/Gentleman-Programming/engram/cmd/engram`
- `api/skills/available`
- `api/skills/catalog`
- `api/skills/index`
- `paperclipai/paperclip/paperclip`
- `company/d4921013-e5da-4d88-8016-57d5746e2d03/obsidian-cli`
- `home/sam/.paperclip/instances/default/skills/d4921013-e5da-4d88-8016-57d5746e2d03/obsidian-cli`
- `home/sam/.pi/agent/skills/obsidian-`
- `dir/.harness/host`
- `home/sam/paseo/projects/tuios_coding_harness/plan/82-control-room.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/83-interface.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/80-forked-plan.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/91-paperclip-or-oma.md`
- `home/sam/paseo/projects/tuios_coding_harness/plan/50-open-work.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/skills/graphify/SKILL.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/skills/system-architect/SKILL.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/extensions/pi-graphify/skills/graphify/SKILL.md`
- `home/sam/.pi/agent/git/gitea.lab.audasmedia.com.au/sam/pi-config/node_modules`
- `google/genai/dist/node/index.cjs`
- `google/genai/dist/node/node.d.ts`
- `home/sam/.config/systemd/user/lan-mouse.service`
- `home/sam/.config/lan-mouse`
- `home/sam/.config/lan-mouse/lan-mouse.pem`
- `home/sam/.cache/lan-mouse`
- `home/sam/.local/bin/lan-mouse-011`
- `home/sam/.pi/agent/auth.json`
- `home/sam/.pi/agent/mcp-cache.json`
- `home/sam/.pi/agent/mcp.json`
- `home/sam/.pi/agent/models.json`
- `home/sam/.pi/agent/models-store.json`
- `home/sam/.pi/agent/settings.json`
- `home/sam/.pi/agent/trust.json`
- `home/sam/.local/bin/codebase-memory-mcp`
## Final answer snapshot
Explored all of it. Recorded in `docs/PLAN-INTERFACE.md`; the short version:
## Skills per agent — Paperclip already models it
`GET /api/agents/{id}/skills` returns a desired set, a managed set and a state per skill. On `Builder` today:
```
desired: ["paperclipai/paperclip/paperclip"]
company/<id>/obsidian-cli desired: false managed: true state: "stale"
```
`POST /api/agents/{id}/skills/sync` takes `add`, `remove` or **`replace`** — `replace` is exactly "this agent gets these and nothing else", which is how a sub-agent's context stays small. There is also a company skill catalog, versions, audit, and `GET/PUT /api/companies/{id}/skill-policy` with an `evaluate` call.
Proposal: two rows in `Agents>agents` settings — **skills** (the desired set, read-only first, add/remove later) and **skill source**. A full browser is a later screen, not a panel. Also: `obsidian-cli` sitting `stale` on Builder is worth fixing.
## Memory — three different things
| | state here | what it is |
|---|---|---|
| **engram** | installed, v1.16.1, MCP mode, **not** registered in `~/.pi/agent/mcp.json` (only `codebase-memory`, `graphify-vault`) | persistent memory |
| **headroom** | running, v0.24.0, healthy at `192.168.20.13:8787`, memory backend **disabled**, compression on | a prompt-compression proxy, not a store |
| **pi memctx** | in use now | injects notes into a prompt |
They are complementary. Paperclip's only per-agent lever is `adapterConfig` and `runtimeConfig`, so memory is set per agent by pointing that agent at the proxy or store it should use. Proposal: a **memory** row in `Agents>agents` settings showing which of the three that agent uses, and nothing more until one agent has run both ways and been measured.
## MOUSE-1
`MOUSE_API_KEY` is set (checked the name only, never the value). `JEV_API_KEY` too. No `mouse`, `mouse1`, `jev` or `switch` binary is installed.
There **are** notes, and they are good ones — in the old project's plan documents:
> MOUSE-1 is *"triage only: label, score, route, escalate. Never a gate, never a permit"* — explicitly ruled out for deciding a merge or allowing a tool call, because a cheap classifier that fails open on a network error makes a green run a lie.
I would adopt that policy unchanged. Its place, if added: ordering `Board>board`'s needs-you list, or pre-sorting findings in `Work>review`. Never the merge, never an approval.
## Lazygit
Already wired: `t` in `Board>board` or `Work>work`, choose Lazygit. Verified opening in the right workspace and closing with `q`.
## The old `office` — and what ours lacks
The previous `office` did four things: remember the host; run `new-project` to write the scaffold (`settings.toml`, a file per role, `verify.sh`, the per-screen notes) writing **only what is missing**; refuse if the session does not exist and print the exact `tuios new` line; then build the pages.
Ours does the host, the refusal and the pages — but **no scaffold**. No per-role files, no `verify.sh`, no page notes. That is the cheapest real gap in the whole plan.
## Dashboard — the API answers it in one call
`GET /api/companies/{id}/dashboard`, 1.8 KB:
```
agents {active 6, running 0, paused 0, error 0}
tasks {open 8, inProgress 0, blocked 4, done 147}
costs {monthSpendCents 11, monthBudgetCents 0, utilization 0}
runActivity [14 entries]
```
Proposal: a `Project>overview` panel with those blocks and a sparkline drawn in Go with `tuios.dev/plot`, rather than embedding the web dashboard in a pane.
## Not doing
Artifacts — dropped as instructed.
I am ready for the task you are about to deliver; nothing in the tree is half-changed, the eight workspaces are running, and the last commit is `3d31243`.
## Evidence
- Confidence: 86%
- Reason: Preserve full sanitized discovery detail from a rich investigation turn
## Related
- [[packs/paperclip-harness/00-system/pi-agent/memory-manifest|Memory Manifest]]
## Related learned memories <!-- same-turn-2026-11-10 10:01:16 -->
- observation: [[packs/paperclip-harness/60-observations/tmp-repository-structure-and-configuration-patterns|Paperclip per-agent skills state and sync semantics]]
- runbook: [[packs/paperclip-harness/70-runbooks/tmp-deployment-operations|Adopt an existing folder into the harness with `office` (and its known scaffold gap)]]
- decision: [[packs/paperclip-harness/50-decisions/mouse-1-restricted-to-triage-never-a-gate-or-permit|MOUSE-1 restricted to triage; never a gate or permit]]
- action: [[packs/paperclip-harness/40-actions/2026-11-10-wrote-docs-ui-layout-md-and-three-live-layout-mockups|Recorded interface plan for Paperclip + TUIOS harness in docs/PLAN-INTERFACE.md]]
- session: [[packs/paperclip-harness/80-sessions/paperclip-tuios-interface-discovery-skills-api-memory-stack-|Paperclip-TUIOS interface discovery: skills API, memory stack, MOUSE-1, dashboard, old office scaffold]]
- context: [[packs/paperclip-harness/20-context/paperclip-tuios-harness-sam-s-coding-harness-office-board-wo|Paperclip-TUIOS harness (sam's coding harness: office/board/work screens)]]
- session: [[packs/paperclip-harness/80-sessions/rich-discovery-paperclipai-2026-11-10-10-01-16|Rich discovery: paperclipai 2026-11-10 10:01:16]]
- context: [[packs/paperclip-harness/20-context/home|paperclipai]]