Replace Outline with an Obsidian-format knowledge vault on the agent host

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE

docs/Architecture.md

@@ -297,7 +297,7 @@ does not stop at gates for their own sake.
 **Approval sources.** Matrix (L5), Gitea comments (D2) and Vikunja comments (O5)
 are approval sources; each authenticates the approver against its own operator
 allowlist. The first valid approval wins and is echoed to the other channels. The
-knowledge store (L10) is **never** an approval source or an instruction channel.
+knowledge vault (L10) is **never** an approval source or an instruction channel.
 
 **The trust dial.** How much the operator reviews after the fact is **data the
 operator sets**, per project and per milestone: for example, whether PR review is
@@ -408,16 +408,16 @@ the caller treats it as a failure (L9).
 - **For a repo:** the project's own documents (`ARCHITECTURE.md`, build plans,
   conventions), versioned in the repo and changed by PR (D2). Read at work-item
   start; the repo is the authority.
-- **For infrastructure:** the world model in the knowledge store (L10): what
+- **For infrastructure:** the world model in the knowledge vault (L10): what
   exists and how it is arranged.
 
 **4. Agent memory** — the agent's own notes, outliving work items and scopes.
 - **What it holds:** the operator's preferences, lessons learned, recurring
   decisions and their reasons. Much like a good collaborator's notebook.
-- **Where:** the agent's private space in the knowledge store (L10), one note per
+- **Where:** the agent's own folder under `memory/` in the knowledge vault (L10),
-  fact, with an index.
+  one note per fact, with an index. Private between agents.
-- **Written by the agent** at defined moments (below); **visible to the operator**,
+- **Written by the agent** at defined moments (below); **visible to the operator**
-  who corrects it through conversation, not by editing.
+  (read-only, L10), who corrects it through conversation, not by editing.
 - **Read at work-item start** (the index, plus notes relevant to the task) and when
   the agent is about to make a decision the notes cover.
 
@@ -589,38 +589,55 @@ are recorded as input/output pairs from the start, with outcomes marked. Changin
 a model is then a configuration change and a re-run, not a matter of benchmark
 chatter.
 
-### L10. Knowledge store (Outline)
+### L10. Knowledge vault
 
 Durable knowledge that outlives work items: world models, agent memory (L6), and
-later operator-written procedures.
+operator-written material such as procedures. It is a folder of Markdown files on
+the agent host (X1), in the format Obsidian reads (frontmatter, `[[links]]`,
+tags), so the operator browses it in Obsidian with links, backlinks and the graph.
 
-**Layout: one writer per document.**
+**One vault, one writer per folder.**
-- **One collection per writing principal:** `nisse-ops-world`, `nisse-dev-world`,
+- **Agent memory lives under `memory/`,** one folder per agent. Other folders hold
-  each agent's memory, and `procedures` (the operator's). Sharing grants read
+  shared material (world models, the operator's notes); their names and layout are
-  access only; concurrent writers never exist.
+  left to grow with need.
-- **`nisse-dev` gets private space only.** Shared infrastructure documents are a
+- **Every folder has exactly one writer,** an agent or the operator, so concurrent
-  map of exactly what its sealed network keeps its builds from (D7).
+  writes never happen.
-- **Each agent authenticates as its own Outline user,** with its own API token. A
+- **Mounts enforce it** (a hard wall, P4): each agent's container gets the folders it
-  token from the operator's account would silently void every permission here.
+  writes read-write, the shared folders it may read read-only, and nothing else. No
-- **Collections and documents are identified by ID** from configuration and state,
+  agent can read another's memory. `nisse-dev` gets no infrastructure material,
-  never discovered, and document IDs recorded when created make writes idempotent.
+  which would be a map of exactly what its builds are kept from (D7).
+- **Links point from memory to shared notes, never the other way,** so the shared
+  part reads cleanly on its own.
+- **Writes are atomic** (write, then rename), so a reader never sees half a note.
+- **Access is through control tools** (L13): the harness reads and writes the mounted
+  folders. No tool VM ever sees the vault.
+- **History:** the vault is a git repository on the agent host, and the harness
+  commits each write with the agent and work item that made it. A note's revision is
+  its commit (L6).
+
+**The operator's copy.** Syncthing keeps a copy on the operator's devices, with the
+direction set per folder:
+- **folders an agent writes,** memory included, are send-only from the host: the
+  operator reads them, and a local edit never flows back;
+- **folders the operator writes** are receive-only on the host.
+
+So conflicts can't arise. Obsidian's own settings folder and `.git` are not synced.
 
 **Never an instruction channel, never an approval channel.** Work is never read
-out of the knowledge store, and an agent never writes there to make another agent
+out of the vault, and an agent never writes there to make another agent act.
-act. Coordination between agents goes through the operator, Matrix, or a ticket (L1).
+Coordination between agents goes through the operator, Matrix, or a ticket (L1).
 
 **Corrections go through conversation.** The operator tells the agent, which
-records the correction verbatim (L6). The operator keeps write permission as a
+records the correction verbatim (L6). As a break-glass, the operator can stop the
-break-glass: stop the agent, edit, restart. An agent re-reads a document's
+agent and edit its folder on the host, then restart.
-revision before writing and merges rather than overwrites if it moved.
 
 **Retrieval is structural first.** Procedures are bound to entries in ops policy
-(O2) and fetched whenever a plan uses that entry; search exists in addition, never
+(O2) by path and read whenever a plan uses that entry; search (over plain files)
-instead.
+exists in addition, never instead.
 
-**Outages.** A failed write never blocks work (retry, or record locally and
+**Failures.** A failed write never blocks work (retry, or record and reconcile). A
-reconcile). A failed read of a bound procedure stops planning that action; other
+missing bound procedure stops planning that action; other failed reads proceed and
-failed reads proceed and log the gap.
+log the gap.
 
 ### L11. Prompt injection
 
@@ -1062,8 +1079,8 @@ identity, so every upstream action traces to one agent.
 ### X5. Supporting services
 
 All self-hosted: Matrix (Synapse), Gitea, LiteLLM, the local inference host
-(llama-swap on an RTX 4090 host), Vikunja, Outline, Vaultwarden, LLDAP with
+(llama-swap on an RTX 4090 host), Vikunja, Vaultwarden, LLDAP with Authelia, and
-Authelia. Each agent gets its own account, scoped token and room in each service
+Syncthing for the operator's copy of the knowledge vault (L10). Each agent gets its own account, scoped token and room in each service
 it uses; nothing is shared between agents.
 
 ---
@@ -1123,11 +1140,13 @@ history):
 - **Documents as the dev workflow (D2),** a fresh workspace per task and toolchain
   preflight (D3), and git hygiene learned from the live runs (D4).
 - **Conversation (L5)** is a first-class requirement, not a command interpreter.
+- **The knowledge vault (L10)** replaces Outline: Markdown on the agent host, shared
+  between agents by mounts, synced to the operator by Syncthing. Revised in PR #90.
 - **Deployment (X1, L13),** revised in PR #90: one agent host with each agent as a
   container, and disposable tool VMs (a build VM per project for `nisse-dev`) where
   every model-chosen command runs over SSH, replacing a VM per agent.
 - **Kept, largely as they were:** the work model, durability and reconciliation,
-  LiteLLM and the canonical log, delegation, the knowledge store, prompt injection,
+  LiteLLM and the canonical log, delegation, prompt injection,
   identity, and `nisse-ops`' approved step sequences.
 - **Moved to the Development Plan (to be written):** build order, supporting-service
   status, and interim arrangements.