mempalace-toolkit/docs/rfc-001-global-palace.md

RFC 001 — Global palace with local fallback (mempalace-edge)

Status	Phases 0–1 implemented and verified — 2026-08-10 / 08-12 / 08-14. Primary live + seeded, first client flipped. Phases 1.5, 2 and 4 outstanding; Phase 3 deferred by decision.
Created	2026-08-08
Applies to	mempalace 3.6.0, mempalace-toolkit @ 96699f2, pi-devbox ≥ v1.3.0
Decision	Phases 0–2 + 4 in scope. Phase 3 (full pull replication) explicitly deferred — "a laptop that can reach its own stuff plus whatever it can reach" is good enough. Centralization is strictly opt-in — solitary devbox operation remains the default and must not change (§1.1).
Recon update	2026-08-09 — §9 Q1 and Q6 are RESOLVED, both in the permissive direction (opencode supports remote MCP; opencode-devbox already templates the mempalace entry). Neither is a blocker. See those entries for evidence; §2, §4.1 and R5 were corrected accordingly.
Rollout update	2026-08-14 — Phase 1 is live. Primary serving at https://mempalace.jordbo.se/mcp since 2026-08-12 (synlig, mempalace-serve.service under systemctl --user, palace /home/ecsjper/.mempalace/palace); seeded 2026-08-14 15:07 from EMB-7KJ4VR4G's palace — which is itself a carry-over copy from the
operator's previous work computer EMB-X1JY06WJ (lineage and evidence in the §4.4 Deviation note) —
14,777 drawers / 9 wings / 16,337 embeddings / KG 46 entities, 34 triples (14,803 drawers by 17:00); first client flipped and verified end-to-end the same afternoon. ⚠️ Two things not to misread: the seed was a file-level copy of one palace, not the §4.4 MCP replay (see the Deviation note in §4.4), and it therefore sidestepped §7.6 rather than resolving it — §7.6 remains a hard blocker for the second joiner (§8 Phase 0). §2's and §4.1's predictions about the pi client were confirmed in production; §4.4's count-based verification advice was wrong and has been corrected.

Read this first if you are asked to "centralize MemPalace" / "sync palaces between machines". Most of the hard-won facts below are non-obvious and two of them are actively destructive if you guess wrong (§7.1, §7.2). The evidence index in §10 lets you re-verify any claim without re-reading 45k lines.

---

1. The problem

One palace per machine per harness. Today: a pi-devbox container on EMB-7KJ4VR4G, another on tor-ms22, opencode-devbox containers, MBP-M1-2020, plus native hosts — each with a private ~/.mempalace. Consequences:

1. Memory is sharded by accident of where you happened to be working. A decision recorded on the laptop is invisible to the agent on the desktop.
2. Container recreates are amnesia events unless the palace happens to be host-bind-mounted.
3. The KG is the worst hit — kg_query/kg_timeline answers depend on which machine you ask.

Target state: one primary palace holds the fleet's memory. Every client keeps working when the primary is unreachable (writes buffer locally, reads degrade to local), and reconciles when it returns. Access is authenticated per device, with a sane authorization policy.

1.1 Hard requirement: solitary-first, centralization strictly opt-in

This is a requirement, not a preference, and it constrains every choice below.

Centralization solves a problem specific to this usage pattern: several machines and containers (pi-devbox, opencode-devbox, native hosts) doing development and other work against a common set of artifacts. For most users of the published joakimp/pi-devbox and joakimp/opencode-devbox images it is useless — one machine, one palace, done. Evidence that this is already the norm: all three sampled opencode-devbox deployments (docker-compose-repo/{synlig,nyvaken,devbox-affection}/) contain zero mempalace references.

ID	Requirement
R1	Solitary operation stays the default and stays unchanged. With no MEMPALACE_* variables set, a devbox must behave exactly as it does today: harness → local mempalace-mcp over stdio, palace at ~/.mempalace. No extra process, no outbox, no network calls, no new failure mode, no measurable startup cost.
R2	Opt-in lives in docker-compose.yml + .env — the mechanism users already know. No opt-in via image rebuild, no baked-in defaults, no latest-central variant.
R3	Credentials only in .env (chmod 600, gitignored). Never in docker-compose.yml, never in the image, never on a command line (visible in ps), never logged. Compose passes them through with a ${VAR:-} empty default so solitary users never define them.
R4	No new required services. The primary stays in the separate standalone docker-compose.mempalace.yml project; it is never merged into the main compose file. A solitary docker compose up starts exactly what it starts today.
R5	Degrade, never fail, when mempalace is absent. The published opencode-devbox image does ship mempalace by default (Dockerfile.base:380,402 — ARG INSTALL_MEMPALACE=true, MEMPALACE_VERSION=3.6.0, installed via uv tool install), but it is a build arg precisely so it can be omitted to save ~300 MB — and a bind-mounted host config or a non-devbox client may have no mempalace either. So any wiring must stay additive and skip when the binary is missing — the probe-and-warn idiom install.sh already uses (warn + return 0, never halt).
R6	Reversible. Commenting the .env lines out returns the container to pure solitary operation, with the local palace intact and readable.

Acceptance test for R1 (must pass before Phase 2 ships): bring up a devbox with no MEMPALACE_* variables; assert the palace tool list, drawer counts and diary writes are identical to the previous image, and that no edge/outbox process exists (pgrep -f mempalace-edge → empty).

1.2 The opt-in surface

The existing convention is already the right one — extend it, do not invent a new one. pi-devbox's .env.example lines 12–23 already ship a commented MEMPALACE_REMOTE_URL / MEMPALACE_REMOTE_TOKEN pair under the heading "MemPalace memory (local by default)", and docker-compose.yml:79-83 already ships the devbox-palace volume commented out. So the opt-in ladder becomes three states derived from two variables — both existing behaviours are preserved, the third is new:

MEMPALACE_REMOTE_URL	MEMPALACE_EDGE	Behaviour	Status
unset	—	local stdio mempalace-mcp, palace at ~/.mempalace	default, today, unchanged (R1)
set	unset/0	direct remote HTTP; no local palace, no offline	today (96699f2), unchanged
set	1	mempalace-edge: local-first writes + outbox → primary + merged reads	new (Phase 2)

Volume coupling reverses under edge mode — document it prominently. Today .env.example correctly says that with MEMPALACE_REMOTE_URL set "the devbox-palace volume is then irrelevant", because the remote owns all state. Under edge mode that flips: the local palace holds the outbox and all local-first writes, so an un-persisted palace means losing un-flushed writes on container recreate. Opting into MEMPALACE_EDGE=1 therefore requires uncommenting devbox-palace:/home/developer/.mempalace.

Corollary for §4.1: mempalace-edge must not be in the path unless opted in. Registering it unconditionally (letting it decide by env at runtime) is tempting — one static config for every harness — but it violates R1 by inserting a process and a failure mode into every solitary user's setup. Selection must happen at registration time. See open question §9.6.

---

2. Verified starting point (as of 2026-08-08)

Two of the three pieces already exist. This is not greenfield.

Piece	State	Evidence
Primary server	✅ Exists. mempalace serve --host --port --token --tls-cert --tls-key --read-only --allow-insecure. Bearer token compared with hmac.compare_digest, mandatory on non-loopback binds (unless --allow-insecure), TLS 1.2+ resolved before bind, Host-header pinning + Origin allowlist (anti-DNS-rebinding), 16 MiB body cap, token-free /healthz.	cli.py:cmd_serve (~1448); mcp_server.py:5205-5215, 5284-5289
Remote client	⚠️ Exists for pi only, and it is either/or. createClient() picks stdio or HTTP once at process start. ✅ Confirmed in production 2026-08-14 on the first flipped client: the branch is a pure transport swap, and in remote mode no local mempalace-mcp child is spawned at all (zero mempalace processes in the flipped container). So writes go only to the primary — no dual-write, no local mirror.	extensions/pi/mempalace.ts:629-641
Fallback + resync	❌ Absent everywhere. On remote failure the pi bridge re-handshakes the same URL, then de-registers all palace tools and runs blind. ✅ Confirmed 2026-08-14 — and the precise word is fail-closed, not fail-local. After bounded retries it prints mempalace-mcp unavailable after retries; continuing without palace tools and registers nothing; it never silently falls back to the local palace, so a write cannot land in the wrong store. Operational corollary worth stating once: "the palace tools vanished" is the expected symptom of a server / token / DNS fault, not of a broken client.	extensions/pi/mempalace.ts:665-673
mempalace CLI	❌ No remote support whatsoever. Its only palace selector is --palace <path>; otherwise it resolves palace_path from the local config.json. Verified 2026-08-14: on a flipped client the CLI still reads and writes the now-dead local archive — and cheerfully reports ~14,777 drawers while doing so. It is a false-positive machine: never verify a flip with mempalace status/search, and never file memories with the CLI post-flip (they land in the archive, not the primary). Corollary: a transcript backfill must be mined on the primary host, where the CLI's local palace is the primary.	cli.py argument surface; verified on EMB-7KJ4VR4G
opencode client	✅ Remote is supported and already wired. opencode's published schema (https://opencode.ai/config.json, $defs.McpRemoteConfig) makes {"type":"remote","url","headers","oauth"} a first-class sibling of McpLocalConfig, headers being a free string→string map (so bearer is a convention, not a constraint). opencode-devbox already emits exactly that entry when MEMPALACE_REMOTE_URL is set. The all-type:local configs in myconfigs are a deployment fact, not a capability limit.	generate-config.py:107-118; hook at entrypoint-user.sh:117; schema $defs.McpRemoteConfig
Server compose	✅ Exists: pi-devbox/docker-compose.mempalace.yml (canonical) + a tor-ms22 derivative (docker-compose-repo/tor-ms22/pi-devbox/, df2c2ae, port 8766, uid 1000, binds the real ~/.mempalace). Not enabled.	pi-devbox CHANGELOG v1.3.0 (2026-07-02)

Stale docs warning. docker-compose.mempalace.yml, .env.example and CHANGELOG v1.3.0 all say the HTTP transport is unauthenticated and should be fronted by a reverse proxy. That was true for mempalace-mcp --transport http in the v1.3.0 era. mempalace 3.6.0's serve has token + TLS built in (upstream #1877). Fix those comments during Phase 1. Specifically: pi-devbox/.env.example:21 still advertises mempalace-mcp --transport http --host 0.0.0.0 --port 8765 as the way to serve a shared palace — replace with mempalace serve --token … --tls-cert …, and change the example URL from http://mempalace.lan:8765/mcp to https://.

✅ Done 2026-08-12 — pi-devbox/.env.example and mempalace-toolkit/extensions/pi/README.md both now recommend mempalace serve, bind docker0 rather than 0.0.0.0/loopback, and state that the transport is authenticated. docker-compose.mempalace.yml audited too, and it was worse than stale — it was broken on 3.6.0 in both directions: --host 0.0.0.0 with no token in the environment makes the server refuse to start (crash-looping under restart: unless-stopped), and once a token is supplied the healthcheck's unauthenticated tools/list POST 401s, marking a healthy server unhealthy forever. Fixed: token now required via ${MEMPALACE_REMOTE_TOKEN:?} (fails fast at up), healthcheck switched to the token-free /healthz.

⚠️ Corrected 2026-08-14 — one sub-claim above was wrong for two days. The https:// example URL landed in pi-devbox/.env.example only; extensions/pi/README.md still carried http://mempalace.lan:8765/mcp until it was fixed on 2026-08-14. Everything else in this block checked out. Worth naming as a pattern, because it is cheap to repeat: a doc's own ✅ is not evidence the work landed — verify it per sub-claim and per file.

Two things that sound like the feature and are not

• sync.py is not replication. It is gitignore-aware drawer deletion: "Removes drawers whose source files are now gitignored, deleted, or moved out of the project" (sync.py:1-12). See §7.2 — running it against a shared palace is a fleet-wide memory wipe.
• wal/write_log.jsonl is not a replayable WAL. _WAL_REDACT_KEYS strips content/content_preview/document/entry/entry_preview/query/text and replaces them with "[REDACTED N chars]"; all 12 references are writers, there is no reader and no replay function (wal.py:74). Reconstructing memory from it is information-theoretically impossible.

---

3. Why we sync operations, not databases

Row-level / file-level replication of a palace is a trap in this codebase. Four findings, each independently disqualifying:

1. Vectors are not portable. Embeddings are computed client-side — backends/pgvector.py:6-8: "Embeddings are still produced locally by MemPalace through the core embedding wrapper before vectors are written to Postgres." Cross-architecture ONNX determinism (arm64 macOS vs x86-64 Linux, different execution providers) is not guaranteed. → Ship text + metadata, always re-embed on receipt. Cheap and safe: the raw text is always stored as the chroma document.

   ⚠️ Not absolute — see the 2026-08-14 deviation in §4.4. A whole-palace file-level copy arm64 macOS → x86-64 Linux did preserve working search and an intact HNSW index. Re-embedding on receipt remains the rule for merging operations into an existing store; it is not a prohibition on cloning one palace wholesale, provided the embedder sidecar travels with it (§7.4).

2. KG rows cannot be copied. triples has no UNIQUE(subject,predicate,object,valid_from) — only id is unique, and make_triple_id embeds datetime.now(). A row copy therefore duplicates every fact. But add_triple() guards at the application level (SELECT id … WHERE subject=? AND predicate=? AND object=? AND valid_to IS NULL → returns the existing id), so replaying kg_add is idempotent for open facts (knowledge_graph.py:163-178, 305-313). ⚠️ Scoped to open facts only (verified 2026-08-09). The guard's WHERE … valid_to IS NULL means an already-closed historical fact — one written with valid_to, or closed later by kg_invalidate/kg_supersede — has no guard at all, so replaying it inserts a duplicate row every time. A bootstrap that replays full KG history rather than just currently-open facts must dedupe closed facts client-side on (s,p,o,valid_from,valid_to) (§4.4).

3. Only one write path has deterministic IDs.

   Write path	ID recipe	Same content on 2 hosts → same ID?
   add_drawer / checkpoint	drawer_{wing}_{room}_{sha256(wing|room|content)[:24]}	YES — content-addressed, merges for free
   project/format miner	…sha256(source_file|chunk_index)	NO — absolute path (/Users/joakim/x vs /workspace/x)
   convo miner	…sha256(source_file|extract_mode|chunk_index)	NO — same reason
   diary	diary_{wing}_{YYYYmmdd_HHMMSSffffff}_{sha256(entry)[:12]}	NO (µs timestamp) — and the write is a bare col.add with no pre-write probe at all (mcp_server.py:3546), unlike add_drawer. The 12-hex suffix is the only usable content dedup key, and it must be applied client-side (§7.6)
   KG triple	t_{s}_{p}_{o}_{sha256(valid_from|recorded_at)[:12]}	NO (recorded_at = now())

   (ids.py:56,71 — ID_RECIPE = "v3", length-prefixed delimited hashing.)

4. Batch dedup will not save a naive merge. dedup.py groups by source_file and only compares within a group (cosine < 0.15) → cross-host duplicates with differing paths are never compared. The mechanism that does work is write-time: tool_check_duplicate(content, threshold=0.9) queries the whole collection, and mempalace_checkpoint already runs it per item.

Conclusion: the MCP tool surface is already a small, coarse-grained, mostly-idempotent operation vocabulary. Log the intent, replay the intent. That sidesteps chroma internals, chunking, embedder drift and vector portability in one move.

One exception, and it is not cosmetic: diary_write has no idempotency guard whatsoever, so for diaries "replay the intent" duplicates rather than merges (§7.6). Every other write path either content-addresses or guards. §4.4 carries the per-record-type dedup keys a joining client must therefore bring with it.

---

4. Design: mempalace-edge, a local MCP proxy

4.1 Shape

Do not put fallback logic in extensions/pi/mempalace.ts — opencode would need it again — not because opencode lacks remote MCP (it has it, §9.1), but because offline-first writes are a client concern that every harness would otherwise reimplement. Instead: a sidecar that is an MCP server.

pi        (mempalace.ts, stdio) ─┐
opencode  (mcp: type=local)     ─┼──►  mempalace-edge  ──HTTPS MCP──►   PRIMARY
mempalace CLI (local palace)    ─┘        │   (stdio MCP server)       mempalace serve
                                          ├─ child: mempalace-mcp       --token --tls-cert
                                          │  (local palace, always writable)
                                          └─ outbox.sqlite (durable op queue)

mempalace-edge needs zero mempalace internals — it is an MCP-to-MCP proxy. It speaks stdio down to a child mempalace-mcp and HTTPS up to the primary, reusing the RemoteMcpClient already written in 96699f2 (extensions/pi/mempalace.ts:390, vendored from pi-extensions/mcp-loader.ts — mind the MCP-STREAMABLE-HTTP-CLIENT-SYNC: v1 drift token if you copy it again).

Why this shape wins:

• One implementation for every harness. opencode's change is one line: "command": ["mempalace-edge"]. pi's is one line. The CLI is untouched.
• Tools never vanish from the tool list, so wake-up context injection keeps working offline — unlike today's fail-soft de-registration.
• Survives mempalace upgrades: coupled to the tool schema, not to chroma/HNSW.
• The remote transport is sessionless JSON-RPC today (per 96699f2's own note), so reconnect after an outage is cheap — there is no session to re-establish.

But per R1, that one-line change is conditional, not baked in. The edge binary is present in the image (it costs nothing unused) and inserted into the path only when MEMPALACE_EDGE=1:

• pi: createClient() (extensions/pi/mempalace.ts:629) already branches on env at startup — add a third branch. Zero change to the default path.

• opencode: the MCP server entry is static JSON — but the templating step already exists and already implements the first two rungs of the §1.2 ladder. rootfs/usr/local/lib/opencode-devbox/generate-config.py (run unconditionally from entrypoint-user.sh:117) registers mempalace as {"type":"remote", url, headers:{Authorization: Bearer …}} when MEMPALACE_REMOTE_URL is set, else {"type":"local","command":["mempalace-mcp"]} when the binary is on PATH, else nothing — R5-compliant already. Its own comment states it uses the "same env contract as the mempalace.ts pi extension … so one shared MemPalace can serve pi + opencode + native", i.e. the two images are deliberately kept in step. Phase 2's opencode work is therefore a third branch in an existing script, not a new mechanism.

  ⚠️ But the opt-in does not propagate to an existing container. generate-config.py never overwrites an existing config, and ~/.config/opencode is the named volume devbox-opencode-config (docker-compose.yml:64,153) — so a config generated during solitary use survives recreate, and later setting MEMPALACE_REMOTE_URL/MEMPALACE_EDGE only produces a non-loaded opencode.jsonc.proposed sidecar for manual merge (generate-config.py:203-244). Flipping the .env alone is a no-op there. Phase 1/2 docs must say: merge the sidecar, or docker volume rm the config volume, to adopt the change — and the same applies in reverse for R6 (reversibility). This asymmetry with pi — whose createClient() re-reads env every start — is the single biggest behavioural difference between the two harnesses under this RFC.

  ✅ Fix shape (decided 2026-08-09): make the mcp.mempalace subtree env-authoritative. Four verified inputs:

  1. pi is immune for a structural reason worth naming: its MemPalace wiring is code, not config — createClient() reads env at every startup, with no generated file in the path. pi's own settings.json does sit on a preserved volume and does go stale, and pi-devbox already solved that properly at pi-devbox/entrypoint-user.sh:131-162: jq -s '.[0] * .[1]' deep-merge with template first, live second so the user's values always win and only missing keys are filled; arrays treated as leaves (a deliberately removed model is not re-added); rewrite only when the merge changes something; timestamped .bak first; PI_SETTINGS_MERGE=0 to disable; invalid JSON on either side → skip, never clobber. That is the pattern to port.
  2. The precedence must be inverted for this one subtree. pi's "live wins" is right for adding new keys and wrong for a changed env value — and a changed MEMPALACE_REMOTE_URL is the whole problem. So mcp.mempalace needs env-wins, which is only safe with a fingerprint: store a hash of what was last auto-generated and refresh only while the live value still matches it; otherwise fall back to the .proposed sidecar for that key. write_proposed (generate-config.py:203-244) already diffs rendered config against the live file, so this is an extension of existing logic at narrower granularity, not new machinery.
  3. No higher-precedence layer exists to hide in. There is no OPENCODE_CONFIG* env override in opencode's published schema (or anywhere in opencode-devbox/myconfigs), and MCP registration is global rather than project-scoped, so the real file must be written.
  4. The fingerprint is the one genuinely new mechanism — neither repo has a managed-marker convention for JSON; the only prior art is the markdown <!-- pi-devbox:managed-block --> idiom.

  This is a self-contained opencode-devbox change, independent of the rest of this RFC, and it is what turns Phase 1 into "flip .env, restart" for both harnesses — hence Phase 1.5 in §8.

4.2 Routing policy

service.py:29,54,72 already ships the exact three-way split we need — READ_TOOLS, WRITE_TOOLS, MAINTENANCE_TOOLS ({mine, sync, reconnect}) — plus classify_tool().

Class	Primary up	Primary down
read (search, kg_query, diary_read, list_*, traverse…)	query both, merge ranked lists, dedupe by drawer id	local only, response flagged degraded: true
write (add_drawer, checkpoint, diary_write, kg_add…)	apply local and enqueue → primary	apply local, enqueue, keep working
maintenance (mine, sync, reconnect)	never proxied — local only (§5, §7.2)	local only
destructive (delete_drawer, delete_by_source, delete_tunnel…)	admin-scoped only; tombstone, never hard-delete remotely	local only

⚠️ classify_tool() must be treated as fail-closed. mempalace_kg_supersede is a real MCP tool (3 references in mcp_server.py) but is absent from WRITE_TOOLS → classify_tool() returns "unknown" for it. An edge proxy that routed "unknown" as read would silently drop supersede operations. Maintain our own tool→class table, default unknown ⇒ write, and file the upstream fix.

The merged-read trick is what makes Phase 3 optional. Both palaces return ranked results with distances; if the embedder identity matches (§7.4) the distances are comparable, so a union + re-sort + dedupe-by-id gives a correct combined result set. You get fleet-wide recall without replicating anything. Offline you simply see less.

KG reads are the exception: unioning triples is unsafe because invalidate/supersede are order-dependent. Use primary-first, local-fallback (no union) for kg_* reads, and accept that an offline KG answer is incomplete.

4.3 Outbox

Model it on daemon.py, which already implements a durable local job queue and is the closest existing prior art (token auth via ensure_token, 0600, per-palace state dir, MAX_ATTEMPTS = 3, recover_running, JOB_RETENTION_DAYS = 7). Its key primitive is worth copying verbatim:

CREATE UNIQUE INDEX IF NOT EXISTS idx_jobs_dedupe_active
  ON jobs(dedupe_key) WHERE state IN ('queued', 'running');

A TOCTOU-safe, cross-process "at most one active job per key". Our outbox rows:

Column	Purpose
op_id	sha256(origin_device, local_seq, tool_name, canonical_payload) — stable across retries, the primary's idempotency key
local_seq	Per-device monotonic counter → causal order for kg_invalidate/supersede replay
origin_device, origin_label	Provenance, stamped by edge (interim) or the primary (authoritative) — never by the agent (§7.3)
tool_name, payload_json	The MCP call to replay
state, attempts, created_at, flushed_at, error_json	Retry/audit

Flush = drain in local_seq order, stop on first hard failure (preserve ordering), exponential backoff, resume on reconnect. The primary de-dupes on op_id; add_drawer's own pre-write probe and add_triple's open-fact guard make replay safe even if op_id tracking is lost.

write_routing.py is the upstream-shaped seam for this if we ever want it in core: its WriteRoutingPolicy{DIRECT,PREFER,REQUIRE} → WriteRoutingTarget{DIRECT,DAEMON,BLOCKED} enums would gain a REMOTE target. The module says it "changes no caller defaults by itself" — i.e. it exists precisely to be extended.

4.4 Joining an existing primary (bootstrap)

Framing correction (2026-08-09). This is not "seed the primary from one chosen palace". Every container joins the same way, at any time, repeatedly — so a join is idempotent replay of local history, and the only real question per record type is what dedupes it.

⚠️ Deviation (2026-08-14) — the first join did not follow this section. It was precisely the thing the framing correction says this is not: a file-level copy of one chosen palace, arm64 macOS → x86-64 Linux, bypassing MCP replay entirely. It worked — search verified live on the primary, HNSW index intact, KG intact (46 entities / 34 triples). Recorded here so the next operator neither repeats it blind nor believes it is forbidden. Four conditions made it safe, and all four must hold:

1. Same mempalace version (3.6.0) at both ends, so the on-disk chroma/HNSW layout matched.
2. mempalace_embedder.json travelled with the palace, so embedder identity matched. This is the load-bearing one: a mismatched embedding model does not raise — it silently returns garbage search results, and §7.4 explains why the guard cannot catch it (only the model name is compared, and dimension: 0 is skipped as unknown).
3. A single source palace, so no merge semantics were exercised at all. This is exactly what makes the method inapplicable to the second joiner.
4. Python's sqlite3 online-backup API (src.backup(dst)) for the two sqlite DBs — WAL-safe with a live writer, and the only option available because neither host has the sqlite3 CLI. The rest of palace/ was rsynced with --exclude 'chroma.sqlite3*'.

This sidesteps the merge problem; it does not solve it. The second machine to join still needs the replay path and the dedupe keys tabulated below, and still needs §7.6 settled. Three traps found while doing it: never rsync --delete into ~/.mempalace — the server's bearer token lives inside that tree at ~/.mempalace/server/<hash>/token (§10) and there is no second copy; palace paths cannot move, because the palace directory name is a sha256 prefix of its own path; and compare sizes with stat -c%s, not du (APFS and ext4 disagree on block accounting, so du shows a spurious delta). Quiesce the writer first — the source palace's own MCP server was live throughout, which is how a write landed on the far side of the snapshot boundary and produced the false alarm described below.

Lineage — this was the second file-level copy, not the first (established 2026-08-15). The "chosen palace" on EMB-7KJ4VR4G was itself carried over from EMB-X1JY06WJ, the operator's previous work computer, around 2026-07-06 when that machine was replaced. Evidence in the archive: 76 drawers tagged source_machine=EMB-X1JY06WJ, and they are the oldest in it — earliest filed_at 2026-05-04, two months before the EMB-7KJ4VR4G stack existed — with no other source_machine value present; the remaining ~16k were filed locally afterwards (15,189 in July, 1,073 in August). So the primary's full provenance is EMB-X1JY06WJ → EMB-7KJ4VR4G → synlig, by two successive whole-palace file copies and zero merges.

Two consequences worth stating, because this is easy to read as reassuring. First, it strengthens condition 3 rather than weakening it: the method now has two successes behind it, both of them single-source clones, and still not one exercise of merge semantics — so §7.6 is less tested than a "we've done this twice" reading would suggest. Second, the primary's history contains records from a machine that no longer exists, so source_machine is the only thing distinguishing them; do not treat it as noise when pruning or re-mining.

Record type	Dedupe on replay	Client work needed
add_drawer / checkpoint drawers	Server-side: content-addressed id + pre-write col.get probe → {"reason":"already_exists"}, no write (mcp_server.py:2593-2600)	None. Just replay
KG open facts	Server-side: add_triple guard on (s,p,o) WHERE valid_to IS NULL	None. Just replay
KG closed facts	None — the guard is scoped to open facts (§3.2)	Dedupe on (s,p,o,valid_from,valid_to) before sending
Diary entries	None whatsoever (§7.6)	Skip any local entry whose sha256(entry)[:12] suffix already exists remotely
Mined drawers	id is path-dependent → same content from two hosts = two rows	Out of scope: mined wings are local (§5)

Existence checks available today, with no new server code:

Tool	Kind	Fit
get_drawer(id)	exact id, clean not-found (mcp_server.py:3103-3114)	The right check wherever ids are deterministic
list_drawers(wing, room, since, before)	metadata page	Bulk "what does this wing already hold" — the cheap way to collect existing diary id suffixes. Note since/before filter in Python, not in the backend where (chroma 1.5.7 rejects string $gte/$lt)
check_duplicate(content, threshold)	semantic, whole collection, no wing/room scoping	One embed + one HNSW query per call → the cost driver at thousands-of-records scale. Reserve it for diaries, where nothing cheaper works
kg_query	fact lookup	Redundant for open facts (the guard covers them); useful for closed ones

Two containers on one host are the easy case, not the hard one. They share a bind-mounted palace, so it is one palace joining once, and content-addressing makes even a concurrent double-join harmless for everything except diaries. Belt and braces:

• Keep join state in the shared palace, not in the container — e.g. <palace>/edge/bootstrap.json holding {target_url: {joined_at, high_water_local_seq}}. Both containers then see "this palace has already joined", a recreate does not repeat the work, and it is the same durable-state-next-to-the-data pattern as the outbox (§4.3). It must not live in a container-only path: ~/.mempalace is not preserved by default for solitary users (§1.2), which is exactly why the file belongs to the palace directory.

• First join is a dry run. Bootstrap one palace, verify it, then let the rest join. Ordering matters only because of diaries and closed facts; everything else is order-free.

  ⚠️ Corrected 2026-08-14. This bullet used to say "verify counts (status, kg_stats, per-wing list_drawers) against expectations". Do not verify a join by counts. Two independent reasons, both learned on the first real seed:

  1. mempalace status counts chunk rows, not logical drawers. Three drawers plus one 2-chunk diary presented as +9. A count delta cannot even tell you how many records moved.
  2. Chunk counts and chunk-id sets legitimately differ between two palaces whenever a drawer was updated on either side: an update preserves drawer_id, re-chunks to the new length, and deletes the surplus chunk rows (§9.3). A …_chunk_000007 present on one side and absent on the other is therefore the ordinary signature of an edit, not of loss.

  On 2026-08-14 that second mechanism produced a confident "the seed lost a chunk" conclusion that was filed as a finding before being retracted. Counts hid the difference (14,777 vs 14,778 looked like one lost row); an id-set diff over-reported it. The two methods fail in opposite directions, so agreeing with either one alone proves nothing.

  Verify by content. For a sample of drawers, get_drawer(<parent id>) on both palaces and compare the reassembled content. An id-set diff is a fine first pass to find candidates, but it must be adjudicated by a content comparison before anyone concludes loss. Two cheap decisive checks once a difference is real: is one side a prefix of the other (that, and only that, is truncation), and does the final chunk's length equal len(content) - chunk_size * (n_chunks - 1) (800 in 3.6.0)? If both sides satisfy the arithmetic for their own content, both are complete and you are looking at two revisions, not damage.

The genuinely hard case is two different palaces holding overlapping mined content — the same repo mined on a laptop and a workstation under different absolute paths. §5 excludes it by keeping mined wings local; that exclusion is load-bearing, not tidiness.

---

5. Not everything should be global

Per-wing replication policy, declared in edge config:

Policy	Wings	Rationale
replicated	diaries, wing_pi, checkpoints, KG, hand-authored notes	Small, curated, content-addressed → already merge-safe
local	mined code/docs (e.g. the 13,597-drawer workspace wing on this host)	Derived data, re-mineable from git, and carries exactly the path-dependent IDs that break merging (§3.3)

This shrinks the hard problem to the layer that is already safe, and it is why mine must never be remote: the primary serializes every request behind one lock (§7.5), so a bulk remote mine would stall every other agent in the fleet.

Decided 2026-08-09: diaries are replicated. Cross-machine continuity is the entire point, and diaries are the highest-value content in the palace to share ("given their value, I say go with (a)"). Accepted consequence, stated plainly because it follows from the primary being synlig, a work VM (§8.1): personal diaries will live on employer infrastructure. They already quote internal hostnames, paths, moods and the occasional token prefix (§6.1 threat 2) — so "don't put secrets in memory" stops being advice and becomes a precondition.

The work/personal boundary is a property of the wing, not of the device. Rejected design (2026-08-09): splitting the fleet into a work primary and a personal primary along machine lines. The reasoning is decisive — pi-devbox/opencode-devbox are simultaneously work and home projects, and personal machines get used for work-adjacent work, so the device where the work happened cannot classify the project. That is precisely the axis this table already encodes, which is why replicated/local per wing is the right knob and a second primary is not needed to express it.

Shape the config so multiple stores stay possible without paying for them now. Phase 1 keeps MEMPALACE_REMOTE_URL a scalar (one primary). Per-wing targets — this same policy column, plus a destination — belong to the edge config in Phase 2+, so nothing in the .env contract has to be un-designed later.

---

6. Security model

The transport is largely solved; the gap is authorization, not cryptography.

6.1 Threats, in priority order

1. Memory poisoning / persistent cross-machine prompt injection — the underrated one. Palace content is injected into agent context at wake-up. A shared palace means one careless or compromised container can plant instructions that every other agent in the fleet reads as trusted memory. Mitigation: server-stamped provenance on every synced record (§7.3.2), don't auto-inject wake-up content authored by devices outside a trusted set, keep an admin-only wing for anything instruction-shaped.
2. Aggregation raises exfiltration impact. One primary holds every machine's diaries — which already quote internal hostnames, paths and token prefixes. Mitigation: per-wing ACL; don't put secrets in memory (the WAL redaction list exists for a reason); private-network-only exposure.
3. Accidental mass deletion by a client (sync, delete_by_source) — see §7.2.
4. Availability: the server is single-writer by design; one long operation blocks everyone.

6.2 Policy

Control	Decision
Network posture	Primary never internet-exposed. Publish only onto the private overlay / existing tunnel (Pangolin/newt). ⚠️ The reflexive "bind loopback in the container" is the failure mode here — see Transport.
Transport	Decided 2026-08-09: terminate TLS in the existing Pangolin/newt tunnel, not in serve (cheaper than patching Python's TLS surface; one DNS record per service on the web hotel is the whole setup cost). ✅ Host/Origin policy verified by experiment on synlig 2026-08-10, 11/11 as predicted (runbook §2.4) — the summary: do not bind loopback behind the tunnel. enforce_host_pin = _http_is_loopback(host) (mcp_server.py:5367), so a loopback bind + a proxy forwarding Host: palace.example.com → 403, while a non-loopback bind → 200 (pin deliberately relaxed, "may sit behind a proxy that rewrites Host", :5362-5365); tokenless non-loopback binds require --allow-insecure (cli.py:1450). Prefer binding the docker0 gateway (e.g. 172.17.0.1) over 0.0.0.0: non-loopback, so the pin relaxes, yet reachable only from the host and its containers — so a newt container on the box reaches it and the LAN cannot. The Origin check is never relaxed: absent Origin is fine (every non-browser MCP client, incl. pi and opencode), a present non-loopback Origin is 403 with no override — so keep browser-based clients and Origin-injecting proxies out of the path. /healthz is Host/Origin-gated but token-free, so it works as the tunnel's liveness probe.
Authentication	Target: per-device bearer tokens with a server-side token → {device_id, scopes} registry — revoke one laptop, rotate without a fleet outage. Decided 2026-08-09: Phase 1 ships the single shared token ("iterate more feature rich but more complex solutions over time"), so per-device lands with Phase 4. Store in the existing .env.age flow, 0600 on disk. Consequence: until then the primary cannot tell devices apart, so origin_device stays client-asserted and advisory — nothing load-bearing may depend on it (§7.3.2).
Authorization	Per-device read/write wing globs. Server-side refusal of mine/sync/delete_* except for an admin device. --read-only gives a free observer tier.
Provenance/audit	origin_device (+ optional origin_label) + op_id on every record, stamped server-side from the authenticated credential — a client-asserted origin is a hint, not a fact (§7.3.2); server-side append-only op log.
Recovery	Deletes as tombstones; server-side backups with backups.py retention (MEMPALACE_MAX_BACKUPS).
DoS	Keep the 16 MiB cap; add rate limiting; no remote mine.

---

7. Landmines — Phase 0 runbook

Do these before any cutover. 7.1 and 7.2 cause silent data loss; 7.6 causes silent duplication the first time a palace joins (§4.4).

7.1 MEMPALACE_PALACE_PATH ≠ --palace (silent empty KG)

# mcp_server.py:708-711  (_palace_flag_given = bool(_args.palace), line 325)
def _resolve_kg_path() -> str:
    if _palace_flag_given:
        return os.path.join(_config.palace_path, "knowledge_graph.sqlite3")
    return DEFAULT_KG_PATH        # knowledge_graph.py:49 → ~/.mempalace/knowledge_graph.sqlite3

cmd_serve always passes --palace. So the moment you start the server, the KG becomes <palace>/knowledge_graph.sqlite3 — a different file from the live ~/.mempalace/knowledge_graph.sqlite3. The vector store looks fine and the knowledge graph is silently empty.

Four stores, three location rules:

Store	Location rule
drawers	backend-abstracted (BaseCollection)
knowledge_graph.sqlite3	HOME-anchored unless --palace flag (knowledge_graph.py:49)
hallways.json	derived from palace_path, with legacy HOME fallback (hallways.py:73,83)
known_entities.json	HOME-anchored (miner.py:701)

Action: mv all three files into the palace directory before first serve, and verify kg_stats is non-empty afterwards. Corollary: a shared pgvector/qdrant backend shares drawers and nothing else — it would leave the KG as fragmented as it is today. That is why the shared-backend option is not the answer.

⚠️ Understated above, corrected 2026-08-10 while provisioning synlig: this is not a migration hazard, it is the stock-default behaviour, and it is permanent. DEFAULT_PALACE_PATH is ~/.mempalace/palace (config.py:221) while DEFAULT_KG_PATH is ~/.mempalace/knowledge_graph.sqlite3 (knowledge_graph.py:49) — those differ out of the box, with no custom path involved. So on every host, forever: serve (always passes --palace) uses the KG inside the palace, while any CLI command run without --palace uses the HOME one. A one-time mv does not fix that; it just relocates which of the two files is populated.

Better action — converge the two resolution rules onto one inode (and the only option on a greenfield primary, where there is nothing to move):

ln -sfn palace/knowledge_graph.sqlite3 ~/.mempalace/knowledge_graph.sqlite3
ln -sfn palace/known_entities.json     ~/.mempalace/known_entities.json
ln -sfn palace/hallways.json           ~/.mempalace/hallways.json   # added 2026-08-14, see note

Updated 2026-08-14 — hallways.json is symlinked too now. This block previously said it was deliberately not symlinked, on the narrow grounds that it is already palace-derived and its HOME path is a warning-only legacy probe that never auto-migrates (hallways.py:73-95). Both facts still hold — but the goal changed from "symlink only what the code demands" to "all real state lives under palace/, so one copy of palace/ is a complete copy", which is what let the 2026-08-14 file-level seed (§4.4) treat the palace as a single self-contained unit. With all three links in place every parent-level path resolves, and 3.6.0's three different resolution rules — palace-relative for the served KG, HOME for the CLI KG, dirname(palace_path) for hallways, hardcoded HOME for known_entities.json — converge on one set of files. Revert by deleting the symlink if it ever causes trouble.

Verified on synlig 2026-08-10, because the WAL behaviour was the load-bearing assumption: a dangling symlink is created on first sqlite3.connect; -wal/-shm land next to the target (inside the palace dir, so the palace stays a self-contained backup/bind-mount unit) and not beside the symlink; a write through one path reads back through the other; same inode. Full record in synlig-primary-runbook.md §2.3.

7.2 Never run mempalace sync against a shared palace

It classifies drawers whose source files are absent on the running host as orphans and deletes them; _auto_detect_project_roots guesses roots from drawer metadata, so the blast radius is data-dependent rather than obvious. From a laptop that lacks the repos, it is a fleet-wide wipe. Action: edge blocks mempalace_sync from ever reaching the primary; document it; consider an upstream --refuse-shared guard.

Measured on the live primary, 2026-08-15 — the threat model is not where this section puts it. An unscoped mempalace_sync dry-run against central (14,829 drawers) reports out_of_scope: 14391, no_source: 438, missing: 0, kept: 0 — so zero drawers are currently deletable. The mechanism matters: a source root that is entirely absent yields out_of_scope, not missing, and only missing/gitignored drawers are removed. A wipe therefore needs the root to exist while the files under it do not — not a host that simply lacks the repos.

Two corrections follow. (a) The "laptop" scenario is currently blocked twice over, and neither guard was designed for this: the CLI has no remote support at all, so mempalace sync on a client physically cannot reach central; and the MCP mempalace_sync tool executes server-side on synlig, where clients' /workspace/... roots do not exist — hence out_of_scope. Do not mistake this for safety by design; it is safety by coincidence of layout, and it decays. (b) The real hazard arrives with the transcript feeder's remote mode. That mode rsyncs staged transcripts into per-device inboxes on synlig, so those source files will exist on the palace host — making them in-scope for the first time. Any later stage rotation, cleanup, or per-device inbox removal then reclassifies that device's conversation drawers as missing, i.e. prunable, and prunable by a sync triggered from a different device. bin/mempalace-pi-session already documents the local form of this ("do NOT run mempalace sync while the stage is missing, or the drawers mined from it get pruned"); shared-palace multi-device turns it cross-device. Settle stage retention on synlig, and the sync guard, as part of enabling the feeder fleet-wide — not after.

7.3 Provenance belongs to the sync boundary — not to the agent, and not to a solitary container

Today every drawer carries exactly {wing, room, source_file, added_by, filed_at, id_recipe} (+chunk_index, parent_drawer_id); diaries add {hall, topic, type, agent, date}. added_by/agent is the agent name (pi, mcp, checkpoint) — never the machine. So in a merged store you cannot tell which host wrote a record, cannot audit, and cannot compute per-device high-water marks.

Verified 2026-08-09 (mcp_server.py:2578-2585 drawers, 3527-3536 diaries): those lists are exhaustive — there is no session, PID or conversation field either. Two consequences, because both are natural questions:

• Two concurrent pi sessions (the tmux pattern pi's own docs suggest) writing to one palace are indistinguishable. Nothing records which session produced which record.
• pi vs opencode is only accidentally distinguishable. added_by is a free-form optional string (default "mcp"; checkpoint resolves explicit arg → diary agent_name → "checkpoint"), and extensions/pi/mempalace.ts never sets it for add_drawer/checkpoint — it sets identity only for diaries (agent_name from $MEMPALACE_AGENT_NAME, default pi, :758). kg_add has no attribution field at all. So the only real harness attribution today is the diary wing, and for drawers the value is whatever string an LLM happened to pass. ✅ Fixed 2026-08-25: the bridge now defaults the writer field on every write path that has one, and marks diary entries in-text — §7.3.5.

Design consequence: device + agent, never session. Provenance has exactly three consumers — poisoning triage ("which box planted this?"), per-device high-water marks, and revocation — and none of them needs session granularity; adding it would put a field on every record with no reader. Under §6's per-device tokens, provenance granularity equals token granularity: one token per host makes two containers on that host a single origin, while a token per container separates them. §7.3.4's <agent>/<label>/<device> encoding keeps the two axes orthogonal, so pi-vs-opencode stays recoverable — but only if the edge populates the agent segment, never the LLM.

Earlier drafts of this section said "stamp it everywhere, now, because it cannot be backfilled." That was wrong on both counts. See §7.3.3.

7.3.1 What can actually be stamped (mechanics)

The metadata schema is fixed — there is no free-form field — and tools/call whitelists arguments to declared schema properties ("Prevents callers from spoofing internal params like added_by/source_file"), so an extra origin_host=… never reaches storage.

Corrected 2026-08-25 against 3.8.0: that whitelist is no longer a silent drop. mcp_server.py:6440 now returns a hard JSON-RPC error — -32602 Unknown parameter '<k>' for tool <name> — for any argument outside the tool's declared properties. Practical consequence for any stamper: injection must be allowlisted per tool, never blanket. Adding added_by to a diary_write or kg_add call no longer gets quietly ignored; it fails the whole call.

Surface	Provenance slot	Notes
add_drawer, checkpoint	added_by	The only one. Free-form (strip_lone_surrogates only, not sanitize_name, so / and @ are legal). checkpoint resolves explicit arg → diary.agent_name → literal "checkpoint", so omitting it yields a permanently unattributable drawer — no @, no source path, no rule can recover it later.
mine	agent	Reaches added_by on every filed drawer (miner.py:1432, convo_miner.py:129,248). Defaults to "mempalace".
event_append, artifact_put	from_agent / created_by, plus a free-form metadata dict stored verbatim	The best-provisioned surfaces in the whole API — and they also carry their own origin_replica column. If a future record type needs structured provenance, this is the shape to copy.
diary_write	none in metadata — the entry TEXT is the only channel	⚠️ Never put a device in agent_name: wing = f"wing_{agent_name}" → a separate wing per host, and diary_read filters {"agent": agent_name} → diary_read("pi") then misses those entries. sanitize_name does not block @, so this fails silently rather than loudly. Since 2026-08-25 the edge instead prefixes the entry with an AAAK field, `HOST:
kg_add	none	Only source_file/source_closet/source_drawer_id. Origin is inferable only via source_drawer_id → that drawer's added_by, so always pass source_drawer_id.

Metadata is write-only to readers, and that asymmetry decides where provenance must live. added_by and any stamped device are returned by get_drawer — _response_safe_meta/_safe_meta (mcp_server.py:1688-1707) is a None-coercion guard, not a key filter, so an earlier claim that the read path strips provenance was wrong. But search results are assembled from a fixed key list (searcher.py:1822-1839: drawer_id, text, wing, room, source_file, source_path, created_at, authored_at, similarity, distance, effective_distance, closet_boost, matched_via) and diary_read returns content — so no amount of correct metadata is visible to an agent doing a search or reading its own diary. That is not a cosmetic gap: it is exactly how the 2026-08-25 cross-host misattribution happened (drawer_pi-devbox_landmines_fa0002a4). Metadata serves the three consumers below; reader-visible attribution needs the record's own text. → Upstream asks: surface added_by/device in search results, give kg_add a provenance field, and give diary_write an added_by that does not feed the wing name.

Triples and coordination events live in different databases, which bounds any stamper's reach. knowledge_graph.sqlite3 (triples: id, subject, predicate, object, valid_from, valid_to, confidence, source_closet, source_file, source_drawer_id, adapter_name, extracted_at) and logstream.sqlite3 (events, artifacts) sit beside chroma.sqlite3 in the palace directory. A stamper written against Chroma's embedding_metadata — which is what bin/mempalace-device-stamp is — cannot reach them at all. As of 2026-08-25 that is 156 triples and 11 events/3 artifacts, i.e. small enough to leave, but it must be stated rather than assumed: the palace is three stores, and provenance coverage is per store.

7.3.2 Who should stamp it — a ladder of trust

Provenance answers "which device asserted this?" Only something that can verify the answer should write it. Ranked by trustworthiness:

Stamper	Knows the device?	Verifiable?	Uniform?	Verdict
Agent (via skill)	No — must shell out to read env	No	No — per-call boilerplate, forgettable, improvisable	❌ Worst possible place. Rejected.
Client / mempalace-edge	Yes, from host-supplied .env	No — self-asserted	Yes — one line in a proxy	⚠️ Acceptable interim — implemented 2026-08-25, §7.3.5
Primary, from the authenticated credential	Yes	Yes — bound to the token	Yes, for every synced record	✅ Correct home

The ❌ row was not hypothetical. Between 2026-08-23 and 08-25 the mempalace skill did instruct the agent to pass added_by="<harness>@<device>" by hand, and it behaved exactly as this table predicts: hand-filed drawers came out as checkpoint/mcp/pi whenever the instruction was not recalled, and the agent that wrote the instruction then filed its own provenance drawer without it. Measured on 2026-08-25: 199 rows the stamper had already seen and could not resolve, of which 10 were that drawer. Moving the same one-line convention into the bridge (§7.3.5) removed the failure mode without changing the values written — which is the point of the ladder: the value was never the problem, the writer was.

The decisive point: a client-asserted origin is a hint, not a fact. The primary is the only party that can bind a write to an identity it verified. And under the §4 design every write reaches the primary through an authenticated channel — including offline ones, at outbox-flush time — so the server can stamp the complete set without any client cooperation. Provenance is a property of the sync channel, not of the record's author.

Blocker for the ✅ row, verified in 3.6.0 and re-verified in 3.8.0 on 2026-08-25: serve takes a single shared bearer token — one scalar string, auth_token = os.environ.get("MEMPALACE_MCP_HTTP_TOKEN") compared with one hmac.compare_digest (mcp_server.py:7137-7140, :7685) — and the package still contains zero occurrences of any device/origin concept. Two consequences worth stating plainly, because "just issue per-device tokens now" sounds like a shortcut and is not:

• Per-device tokens are not a config change. There is no token → {device, scopes} registry to populate; the code holds one string. Multiple tokens require a code change.
• Tokens are the cheap half. Even with N tokens, nothing would stamp: an origin field would have to be added to six write paths (add_drawer, checkpoint, diary_write, kg_add, event_append, artifact_put) across three separate databases (§7.3.1). And mempalace is upstream MIT (PyPI mempalace, github.com/MemPalace/mempalace) consumed via uv tool install — so this is an upstream PR or a carried fork, on a package that moved 3.7.1→3.8.0 inside one week.
• The tunnel cannot substitute. Pangolin terminates TLS and nothing more (§6.2), and "a Pangolin user per container with credentials in each .env" was considered and rejected in the exposure runbook §1.2 — its HTTP auth is browser-shaped (SSO, resource PIN), not client-shaped.

So the realistic ✅ implementation is a small authenticating rewriter we own in front of the palace: it holds token → {device, label}, and rewrites the JSON-RPC params to set added_by from the verified token. That is mempalace-edge relocated from the client to the primary. It must track tool schemas to stay safe (§7.3.1: -32602 on undeclared args; diary_write has no slot), which is precisely why it is Phase 4 work and not a quick win. Hence the phasing:

• Phase 2 (edge): edge may stamp added_by from its configured env — self-asserted, advisory only, never load-bearing for authorization or destructive scoping. Implemented 2026-08-25 (§7.3.5).
• Phase 4 (authz): per-device tokens land; the primary stamps authoritatively and the client-supplied value becomes redundant (and must be treated as untrusted input, not merely ignored). The upgrade is lossless because every stamp carries a *_source key — an authoritative pass simply overwrites with device_source='token', so nothing done in Phase 2 has to be undone.

7.3.3 Solitary containers should stamp nothing — and lose nothing by it

A pi-devbox or opencode-devbox running solitarily is a single-origin store by definition. Origin is therefore a property of the whole palace, not of each record — so it can be assigned wholesale at the moment the store stops being solitary: one --origin-device flag on the import/first-sync path attributes every record from that palace to that device.

That dissolves the "impossible to backfill" argument. Per-record stamping is only necessary once records from multiple origins are interleaved in one store, which is exactly and only the primary. So:

• Solitary devboxes: no stamping, no config, no skill instruction, no behaviour change. This is strictly more compliant with R1 than the earlier draft, which quietly asked every solitary user to carry metadata for a feature they had opted out of.
• Migration is unaffected: bulk attribution at import is more reliable than per-record stamping, because it cannot be partially applied.
• Multi-harness on one host is solved in principle by added_by = agent name (pi vs opencode) — that is what the field is for, and it needs no device component. ⚠️ Corrected 2026-08-09: nothing actually sets it. The pi extension leaves added_by at its default for add_drawer/checkpoint, so in practice the value is whatever an LLM passed. The field is the right home; the client-side write that populates it is missing, and it belongs to the edge (the ⚠️ row of §7.3.2) — not to a skill instruction. ✅ Closed 2026-08-25: the edge write now exists (§7.3.5), and it carries the device as well as the harness — <harness>@<device> — because in a shared palace the harness axis alone cannot answer "which box planted this?".
• A palace on a shared host bind-mount (as tor-ms22's compose does) is still single-device under the "host owns the palace" model, so it too imports as one origin.

The one case bulk attribution cannot fix: a palace that was already merged from several devices without stamps. Preventing that is precisely why the primary must stamp from day one of Phase 4 — it is the only store where interleaving occurs.

7.3.4 Identity fields, when a stamper does exist

For the edge (interim) and the primary (authoritative) — never for agents:

Field	Source	Rule
origin_device	uuidgen once, stored in the host's .env; later, issued with the device's token	Opaque, stable, collision-free by construction. Compared, never parsed.
origin_label	hostname, same .env	Human readability only. Never identity, uniqueness or scoping. Free to change. Optional — a hostname can leak an asset tag or username (EMB-7KJ4VR4G, HOST_SSH_USER=ECSJPER).

Why not the obvious sources: a container cannot discover its host's identity. hostname returns the container ID (f3bf2a103473) which changes on every recreate; there is no /etc/machine-id; and a baked one would be worse — identical for every container from the same image, a guaranteed collision. Hostnames are also neither unique nor stable (localhost, ubuntu, golden images, two MacBook-Pro.local), and the worse failure is not collision but rename, which silently splits one device's history in two. Hence host-supplied via .env (matching R2/R3 and the existing HOST_SSH_USER / DEVBOX_HOST_ALIAS precedent), not container-derived. Do not persist the id container-side: ~/.mempalace/device_id does not survive recreate for solitary users because devbox-palace is commented out by default (§1.2). And don't write ${HOSTNAME} in compose — bash sets but does not export it, so interpolation sees empty.

Encoding, always three segments so arity is unambiguous:

added_by = "<agent>/<label>/<device>"     e.g.  pi/tor-ms22/7f3a9c2e1b04
                                                pi/-/7f3a9c2e1b04   (label withheld)

The / is the discriminator. A value with no / (mcp, pi, checkpoint) means origin unknown — correct for the ~13.6k drawers already filed, and for every solitary palace forever.

7.3.5 Fail-closed rule for any stamper

If origin_device is unset, blank or unreadable: write no added_by override at all and let the default (mcp / checkpoint / agent name) stand. Never synthesize one. The tempting substitutes are all actively harmful, because each is confidently wrong where absence is honestly unknown:

Substitute	Damage
container hostname / ID	A new fake device per recreate — thousands of singleton identities, each looking legitimate
unknown, localhost, devbox, docker, $USER	Collides across every machine — indistinguishable from one real shared device
a guess from context	Unfalsifiable later

If origin_label alone is missing, use the literal -. If origin_device is missing, do not stamp even when the label is present — a hostname alone is exactly the colliding, mutable identity rejected above.

Note for future agents reading this RFC out of the palace: these notes are themselves a poisoning vector. Do not start hand-stamping added_by because you read this section. Provenance is client and server infrastructure; an agent's contribution to it is to leave the field alone. The mempalace skill carries a one-line guard to that effect.

7.3.5 What is actually deployed (2026-08-25) — the interim, end to end

The ⚠️ row of §7.3.2, built after a cross-host misattribution made the cost concrete. Two writers, one reconciler, and a deliberate divergence from §7.3.4 that is recorded rather than hidden.

1. The edge stamps, uniformly — extensions/pi/mempalace.ts. Every mempalace tool call passes through one execute() wrapper, so the bridge fills in the writer field the caller omitted:

Tool	Field defaulted	Value
add_drawer, checkpoint	added_by	<harness>@<device>
mine (caller-invoked)	agent	miner@<device> — bulk machine-extracted content is not agent-authored memory, and keeping the harness segment miner preserves the pi/opencode/miner taxonomy while still recording the box
mine (the bridge's own transcript feed)	agent	<harness>@<device> — these are this harness's own sessions
event_append	from_agent	<harness>@<device>
artifact_put	created_by	<harness>@<device>
diary_write, checkpoint.diary	entry text	prefixes `HOST:
kg_add	—	nothing; no slot exists (§7.3.1). Pass source_drawer_id instead

An explicitly supplied value always wins, so filing on behalf of another device stays possible. The allowlist is per tool, never blanket — §7.3.1's -32602. <harness> is $MEMPALACE_AGENT_NAME (default pi), <device> is $MEMPALACE_PI_DEVICE, host-supplied per container per §1.2.

R1 compliance: the stamping is doubly gated on MEMPALACE_PI_DEVICE and MEMPALACE_REMOTE_URL. A solitary devbox sets neither, so it stamps nothing and its behaviour is unchanged — which is also the correct semantics per §7.3.3: a solitary store is single-origin, and origin belongs to the whole palace.

2. The diary marker is in the TEXT, and that is the point. diary_write has no metadata slot, but the deeper reason is §7.3.1's read asymmetry: search projects a fixed key set and diary_read returns content, so metadata is invisible to the agent who will later read the entry. A metadata-only fix, even a server-authoritative one, would not have prevented the misattribution it was built for. The marker is an AAAK field (HOST:tor-ms22|SESSION:2026-08-25|…), so it is machine-parseable and the first thing a reader sees. The wake-up block now also states the device and warns that diary_read interleaves every machine's diary.

3. The primary reconciles — bin/mempalace-device-stamp + contrib/systemd/mempalace-device-stamp.{service,timer}, hourly on synlig. It fills device and agent_kind where absent, each paired with a *_source key recording how it was determined, so an inference is never mistaken for a fact. It must stay on a timer, not run once: live re-mining replaces metadata rows and silently drops earlier stamps. Its remaining job after the edge exists is historic rows, re-mined rows, and diary entries. Coverage on 2026-08-25: agent_kind 28,817/30,661 (94%), device 14,157 (46%) — the deficit is dominated by ~16k /workspace project mines that are deliberately unattributed, because /workspace/myconfigs/<host>/… names the machine a config belongs to, not the machine that mined it, and /workspace looks identical on every devbox. Conflating subject with source would be worse than a blank.

Two traps found by dry-running the reconciler before deploying it (--dry-run exists for this reason; the palace is shared, so a wrong rule invents device names that then have to be un-invented across 30k rows, and scripts/test-device-stamp.sh pins both):

• HOST: was already in use, with a different grammar — older entries carry a composite fingerprint, HOST:emb-7kj4vr4g.f1d3c3f89e3e.v1.8.3.pi0.84.2 (device.container.image.pi), and some carry a bare container id, HOST:2efe2b06f480. Taking the match whole would have invented devices like f1d3c3f89e3e.pi0.84.2. The rule therefore validates against the known-device set (the feed inboxes) and falls back to the first dotted segment — which recovers the composite entries correctly and refuses container ids, exactly as §7.3.4 requires (containers are not devices).
• HOST: also carries a different SENSE — e.g. HOST:exec.via.ssh-controlmaster->alpserv-2(…), meaning "the box I was executing on", not "the box that wrote this". Validation rejects it, so the two senses cannot be conflated. A marker convention inherits every prior meaning of its own name.

One further mechanism: chunks. A drawer's chunks are one write call, hence one origin — but a text marker lands only in the chunk that contains it, so a 5-chunk diary entry would stamp 1 and leave 4 blank. The reconciler propagates a resolved value across parent_drawer_id siblings (device_source='sibling_chunk') when they agree, and never overrides a row that resolved on its own evidence.

Divergence from §7.3.4, stated openly. §7.3 refers to an <agent>/<label>/<device> encoding that §7.3.4 never actually defines — §7.3.4 specifies two fields (origin_device, an opaque uuid; and origin_label, a hostname for readability only, explicitly "never identity"). What is deployed is <harness>@<label>: two segments, hostname-derived, no opaque id. Why, and what it costs:

• There is nowhere to put a second field. added_by is one free-form string (§7.3.1), so a uuid could only be carried instead of the readable label, in the one slot that also has to carry the harness.
• A uuid would have to be provisioned and kept in each host's .env; the label already exists there as MEMPALACE_PI_DEVICE, is already the feed inbox name, and is therefore already the join key for the inbox_path rule that resolves 13,350 rows.
• The cost is real and already visible. §7.3.4 warns that the worse failure of hostname identity is not collision but rename, silently splitting one device's history. The palace holds tor-ms22 (4,680 rows) and tor-ms22-native (3,826) — one physical machine, two device values, because the label encoded an access mode. Under §7.3.4's design those would share an origin_device and differ only in origin_label, which is exactly the property we gave up.

So: <harness>@<label> is the honest Phase-2 shape given one string to write into, and the *_source keys are what make the Phase-4 upgrade to verified identity lossless. §7.3 should be read as promising orthogonality of the harness and device axes, which @ delivers — not the three-segment encoding it appears to cite. → Fix §7.3's forward reference, or define the three-segment form in §7.3.4, when Phase 4 settles which identity the primary issues.

7.4 Embedder identity is client-local and currently toothless

check_embedder_identity() raises DimensionMismatchError / EmbedderIdentityMismatchError, but the sidecar on this host reads {"mempalace_drawers": {"model_name": "minilm", "dimension": 0}} — and dimension: 0 means unknown and is skipped, so only the model name is compared. The sidecar lives in the client's palace dir (_sidecar.py), so with a remote backend the check is per-client and never centrally enforced. Action: the primary must reject writes from a client whose embedder identity does not match, and merged reads (§4.2) must be disabled on mismatch — comparing distances across models silently degrades recall.

7.5 Concurrency expectations

• _HTTP_REQUEST_LOCK = threading.Lock() wraps every dispatch (mcp_server.py:5115, held at 5346/5513), commented: "HTTP gives us a safer transport, not concurrent Chroma/HNSW mutation." The primary is a single-writer, one-request-at-a-time service. Size for a handful of agents.
• mine_palace_lock uses fcntl.flock(LOCK_EX|LOCK_NB) and exists because parallel HNSW inserts "can corrupt the HNSW graph" — but the lock file is HOME-derived (~/.mempalace/locks/ mine_palace_{sha256(realpath(palace))[:16]}.lock) while the key is palace-derived. Two containers with different ~/.mempalace mounts but the same palace path compute the same key on different files → no mutual exclusion.
• Therefore: reject "put the palace on a NAS/SMB share and point everyone at it." flock over NFS/SMB is unreliable, and the lock wouldn't be shared anyway. One process owning the files and serving HTTP is the supported model — which is exactly why serve exists.

7.6 diary_write has no idempotency guard — replay duplicates every entry

# mcp_server.py:3511-3513, then 3546
entry_id = f"diary_{wing}_{now:%Y%m%d_%H%M%S%f}_{hashlib.sha256(entry.encode()).hexdigest()[:12]}"
...
col.add(ids=[entry_id], ...)      # not upsert — and no col.get probe anywhere in tool_diary_write

Compare add_drawer 900 lines earlier, which probes col.get(ids=idempotency_probe_ids) and returns {"reason": "already_exists"} without writing (:2593-2600). The contrast is the finding: the µs timestamp makes every diary id unique by construction, and nothing checks the content. So §3's conclusion — log the intent, replay the intent — is false for diaries; for them, replay is duplication.

This matters more than it sounds, because diaries are replicated (§5) and are precisely the content a join replays (§4.4).

⚠️ Still open as of 2026-08-14 — and the first join did not test it. The seed was a file-level copy (§4.4 Deviation), which replays no diaries and therefore cannot duplicate them. §7.6 was sidestepped by method choice, not resolved. Neither action below has been built. The moment a second palace joins — by any replay-based route — this becomes live again, and it is the single most likely thing for a future operator to get wrong, because the first join appears to have proved the path safe. It did not: it avoided the path.

Actions:

1. Client-side, now: before replay, list the target's diary drawers for the wing, extract the 12-hex sha256(entry)[:12] suffix from each existing id, and skip any local entry whose suffix already appears. The suffix is already content-addressed — no new key needs inventing.
2. Upstream ask: make diary_write probe-and-skip on that suffix the way add_drawer does on its content hash. A small, self-contained patch in the sibling function's own idiom, and it closes the gap for every future writer instead of for one migration script.
3. Do not "fix" this by making the agent dedupe. An agent cannot know what the primary holds without a call, and per-call boilerplate is exactly the failure mode §7.3.2 rejects.

---

8. Phasing

Phase	Effort	Deliverable
0 — hygiene	hours	§7 runbook: converge the KG/entities store paths on synlig before first serve (§7.1 — done 2026-08-10, runbook §2.3), ban sync on shared palaces (§7.2), fix stale "unauthenticated" docs (incl. pi-devbox/.env.example:21) — done 2026-08-12, and docker-compose.mempalace.yml turned out to be outright broken on 3.6.0, now fixed. Added 2026-08-09: settle the diary dedup approach and file its upstream ask (§7.6), and dry-run the join from one palace only (§4.4). ✅ Both done 2026-08-14, with one asterisk that matters: the join was dry-run and executed from one palace only — but §7.6 was sidestepped, not settled (a file-level copy replays no diaries, so it cannot duplicate them). The §7.6 client-side dedupe and its upstream ask are still unbuilt and are hard blockers for the second joiner. No provenance work here — it is not backfill-critical (§7.3.3) and belongs to the stamper, not the agent
1 — primary up ✅ done 2026-08-14	hours, no code	mempalace serve --token --tls-cert on a private-net host (reuse docker-compose.mempalace.yml — keep it a separate standalone project, R4 — and mind port 8765 vs pi-studio; tor-ms22 already moved to 8766). Repoint pi clients via MEMPALACE_REMOTE_URL/MEMPALACE_REMOTE_TOKEN. opencode clients can be repointed in the same breath — remote MCP is supported and generate-config.py already emits it (§9.1, §9.6), subject to the sidecar caveat in §4.1. Shared memory today, no offline. Decided 2026-08-09: primary = synlig, TLS at Pangolin, single shared token (§8.1) — mind the loopback Host-pin trap in §6.2.
1.5 — opencode env propagation	hours	Make the mcp.mempalace subtree env-authoritative in generate-config.py, gated by a generated-value fingerprint (§4.1). Independent of the rest of this RFC. Without it, adopting or reverting the opt-in on an existing opencode container needs a manual sidecar merge or a docker volume rm — which also blocks R6 reversibility
2 — mempalace-edge	~1 week	The actual ask: local-first writes + outbox flush + merged reads + per-wing policy. Not "fixes opencode" — opencode's transport is already fine after Phase 1; what edge adds there is offline/local-first, since generate-config.py's switch is remote or local with no failover. Ships with the §1.2 opt-in wiring (compose + .env.example + a third branch in the existing generate-config.py) and must pass the R1 acceptance test.
3 — pull replication	~1 week	DEFERRED (2026-08-08). Server-side op-log with monotonic seq → each edge a full offline replica. Only needed if a laptop must hold everything offline. Accepted trade-off: offline recall = own writes + last-reachable state.
4 — authz	days–week	Per-wing ACL, per-device scopes, audit log, token rotation. Two things fold in here, decided 2026-08-25 (§7.3.2): (a) per-device bearer tokens, motivated first by revocation — today one shared token covers 4+ devices and every container on them, so a single compromised or decommissioned laptop cannot be cut off without rotating the whole fleet, and that is a standing risk independent of provenance; (b) authoritative server-side provenance rides along free once (a) exists — but only via a component we own, because upstream core holds one scalar auth_token and has zero device concept, so the shape is a small authenticating rewriter in front of the palace that maps token → {device, label} and sets added_by from the verified credential. Do not sequence (b) before (a): tokens are the cheap half, and stamping without a verified identity is what Phase 2 already does more simply. Prerequisite understanding: §7.3.1 (-32602 on undeclared args; three separate databases; diary_write has no slot) and §7.3.5 (what the interim already covers, and the *_source key that makes the upgrade lossless)

Phase 1 is worth doing on its own — it is pure configuration and immediately ends KG fragmentation for online clients.

8.1 Deployment decisions (2026-08-09)

Decision	Value	Note
Primary host	synlig — a VM in Xerces (work OpenStack cloud)	Chosen for always-on + good connectivity, not for work/personal reasons. Consequence: replicated content, diaries included, lives on employer infrastructure (§5, §6.1 threat 2)
TLS / ingress	Pangolin/newt, one DNS record per service on the web hotel	Not serve --tls-cert. See the bind-address/Host-pin coupling in §6.2
Authentication	Single shared token for now	Per-device deferred to Phase 4; origin_device stays advisory until then. Re-verified 2026-08-25 on 3.8.0: still one scalar auth_token (mcp_server.py:7685), so per-device is a code change, not configuration — and the shared token is a revocation gap, now recorded as the primary motivation for Phase 4 (§8) rather than a provenance detail
Diaries	replicated	Highest-value cross-machine content; accepted placement consequence (§5)
Work/personal split	per-wing, not per-device	Rejects two primaries split along machine lines — the device cannot classify the project (§5)
Multi-store	Possible later, not now	MEMPALACE_REMOTE_URL stays a scalar in Phase 1; per-wing targets are an edge-config concern (Phase 2+)

---

9. Open questions

1. Does opencode's MCP config support a remote/HTTP transport at all? RESOLVED 2026-08-09: YES. opencode's published JSON Schema (https://opencode.ai/config.json) defines $defs.McpRemoteConfig = {type:"remote" (enum), url (required), headers?: {string:string}, oauth?, enabled?, timeout?} as a sibling of McpLocalConfig inside Config.properties.mcp.additionalProperties.anyOf. So headers carries any bearer/API-key scheme, and set oauth: false to stop opencode probing the URL for OAuth. The earlier "every sampled entry is type:local" observation was deployment evidence being read as schema evidence — the schema settles it in one fetch. Consequence: the edge proxy is not the only option for opencode. A plain Phase 1 mempalace serve --token can be consumed directly, so nothing in the phasing depends on this question any more. What opencode still lacks is local-first writes and offline fallback — generate-config.py's switch is remote or local per container, with no failover — and that is the real Phase 2 justification for it.

2. Upstream or local? mempalace-edge needs no core changes, so it belongs in this repo (bin/ + extensions/). But origin_device stamping from the authenticated token, per-wing ACL, the kg_supersede classification fix, and a sync --refuse-shared guard all want to go upstream (github.com/MemPalace/mempalace).

3. Chunked drawers under merge. Oversized content splits into {drawer_id}_chunk_NNNNNN with parent_drawer_id, and the add-time idempotency probe checks only the last chunk id — a partially transferred chunk set may look "already present" and stay truncated. Largely resolved 2026-08-09: the last-chunk-only probe is deliberate, not an oversight. The code's own comment (mcp_server.py:2586-2592) states that the last chunk's presence implies every earlier one landed because the batched upsert is all-or-nothing, and it additionally probes drawer_id alongside so a re-call with identical oversized content cannot duplicate a legacy pre-#1539 single-row write. The normal path is therefore safe by construction. What remains untested is the abnormal one: a chunk set left partial by a crash or kill mid-upsert, which would then look present and stay truncated. Worth a single fault-injection test before trusting bulk replay of oversized drawers. Still untested as of 2026-08-14 — the first join did not exercise it.

   ⚠️ But 2026-08-14 surfaced a benign mechanism that mimics it, and it will generate false alarms during any join verification (§4.4). Updating a drawer preserves drawer_id, re-chunks the new content, and deletes the surplus chunk rows. So two palaces holding two revisions of one drawer legitimately differ in chunk count and chunk-id set, with zero data loss — and the shorter side returns a clean "not found" for the chunk ids it no longer needs, which looks exactly like the truncation this entry warns about. The absence of a derived chunk id is not evidence of loss. Distinguish them by prefix test and final-chunk arithmetic per §4.4, not by id-set membership.

4. migrate.py as a bootstrap tool. extract_drawers_from_sqlite() reads {id, document, metadata} straight out of chroma's SQLite (bypassing the chromadb API) and re-adds them with ids and metadata preserved and embeddings recomputed (migrate.py:326) — the right shape for a one-shot "seed the primary from an existing palace". Unverified: col.add behaviour on id collision into a non-empty target. Test before relying on it. (exporter.py is markdown-only, lossy, and has zero callers — not a transfer format. backups.py is retention pruning only.) Reframed 2026-08-09: §4.4 makes MCP-level replay the primary join path — it reuses the server's own idempotency guards instead of trusting chroma-level add semantics — so migrate.py is now a fallback for bulk transfer rather than the plan, and its untested collision behaviour only matters if we reach for it.

5. Does _HTTP_REQUEST_LOCK stay held for the duration of an MCP-triggered mine? Strongly suggested by the code shape; if yes, a remote mine makes the primary unusable for its duration (another argument for §5).

6. How does opencode-devbox learn the opt-in? RESOLVED 2026-08-09: it already does. The image ships rootfs/usr/local/lib/opencode-devbox/generate-config.py, invoked from entrypoint-user.sh:117 on every start, which auto-registers the mempalace MCP server — remote+bearer when MEMPALACE_REMOTE_URL/MEMPALACE_REMOTE_TOKEN are set, local stdio when mempalace-mcp is on PATH, nothing otherwise — documented in that repo's .env.example:38-49 and .env.shared.example:30-35. It also ships mempalace by default (see R5). So the config is templated at container start, not baked, and Phase 2 only adds a third branch. Two residual constraints replace the original unknown, and both are documented in §4.1: (a) the script never overwrites an existing config and ~/.config/opencode is a named volume, so an env flip yields only an opencode.jsonc.proposed sidecar — adopting or reverting the opt-in needs a manual merge or a volume removal; (b) it no-ops entirely unless OPENCODE_PROVIDER is set. Prefer extending this script over inventing a parallel mechanism — treat it as the reference implementation, and check it before designing any pi-devbox-side mechanism with an opencode counterpart.

7. Is a work VM the right long-term home for personal memory? Accepted with eyes open for Phase 1 (§8.1): synlig wins on availability and connectivity, and the alternative — splitting by machine — was rejected for sound reasons (§5). But the placement question survives the routing question: diaries are replicated (decided), diaries are personal, and synlig is employer infrastructure. Revisit when per-wing targets exist (Phase 2+), at which point a second personal primary becomes an additive config change rather than a re-architecture. Until then, treat §6.1 threat 2 as live.

---

10. Evidence index

Re-verify without re-reading the package. Paths relative to /opt/uv-tools/mempalace/lib/python3.13/site-packages/mempalace/ (mempalace 3.6.0) unless noted.

Claim	Where
Server auth/TLS/read-only	cli.py:1448-1503; mcp_server.py:282-320, 5205-5215, 5284-5289
Single global request lock	mcp_server.py:5115, 5346, 5513
KG path follows --palace flag only	mcp_server.py:325, 708-711; knowledge_graph.py:49
KG DDL, no (s,p,o) uniqueness, open-fact guard	knowledge_graph.py:163-178, 305-313
ID recipes	ids.py:25, 56, 71; diary at mcp_server.py:3511-3514
Diary write has no idempotency probe	mcp_server.py:3546 (col.add, no col.get) vs add_drawer's probe at 2593-2600
Chunk probe is deliberate (all-or-nothing upsert)	mcp_server.py:2586-2592
Metadata is exhaustive — no session/PID/conversation field	mcp_server.py:2578-2585 (drawers), 3527-3536 (diaries)
pi extension sets identity for diaries only	extensions/pi/mempalace.ts:758 (agent_name); no added_by set anywhere in the file
Anti-rebinding Host/Origin checks	mcp_server.py:5160-5194, 5276-5290, 5362-5367; cli.py:1450. Verified empirically — runbook §2.4
Stock defaults already split the KG	config.py:221 (~/.mempalace/palace) vs knowledge_graph.py:49 (~/.mempalace/knowledge_graph.sqlite3)
Server token path (stable across restarts)	cli.py:_server_token_path — ~/.mempalace/server/sha256(realpath(palace))[:24]/token
pi-devbox non-destructive settings merge (pattern to port)	pi-devbox/entrypoint-user.sh:131-162 (jq -s '.[0] * .[1]', .bak, PI_SETTINGS_MERGE=0)
No OPENCODE_CONFIG* env layer upstream	absent from https://opencode.ai/config.json; zero hits in opencode-devbox, myconfigs
Tool classification (+ kg_supersede gap)	service.py:29, 54, 72-84
Write-routing seam	write_routing.py:1-60
Outbox prior art (queue DDL, token, retries)	daemon.py (_init_db, ensure_token, MAX_ATTEMPTS)
sync is destructive pruning	sync.py:1-12
WAL redacts + has no reader	wal.py:74, _WAL_REDACT_KEYS
Client-side embeddings	backends/pgvector.py:6-8; embedding.py:6-11; _sidecar.py
Dedup scoped by source_file	dedup.py:get_source_groups
Store location rules	hallways.py:73,83; miner.py:701
Mine lock (HOME-derived file)	palace.py:1090, 1123-1128
Migrate as export primitive	migrate.py:extract_drawers_from_sqlite, :326
pi remote transport + fail-soft	mempalace-toolkit/extensions/pi/mempalace.ts:11-12, 87, 108, 390, 629-641, 665-673 (commit 96699f2)
Server compose + port history	pi-devbox/docker-compose.mempalace.yml; pi-devbox/CHANGELOG.md v1.3.0; docker-compose-repo/tor-ms22/pi-devbox/ (df2c2ae)
Existing opt-in convention (§1.2)	pi-devbox/.env.example:12-23 ("MemPalace memory (local by default)", commented MEMPALACE_REMOTE_URL/_TOKEN); pi-devbox/docker-compose.yml:79-83 (devbox-palace volume commented out)
opencode-devbox does not wire mempalace	docker-compose-repo/{synlig,nyvaken,devbox-affection}/opencode-devbox/docker-compose.yml — zero mempalace references in any

11. See also

• ARCHITECTURE.md — producer side (how the palace gets fed); §6 upstream roadmap
• extensions/pi/README.md — pi bridge internals
• SKILL.md — consumer-side protocol (search before answering, diary before exit)