release: LORE 0.62.28 README reference update

.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
       "name": "lore",
       "source": "./",
       "description": "Shared memory for Claude Code, Codex, and DOXA: capped curated facts, evidence-backed beliefs, FTS5 session search, staged review, learned skills, and signed sync.",
-      "version": "0.62.27"
+      "version": "0.62.28"
     }
   ]
 }

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "lore",
   "description": "Memory for Claude Code that reasons about you and improves itself: Honcho-pattern belief store with deriver, dreamer and dialectic (/lore:ask), automatic skillification with a closed judge/update/retire loop, on a Hermes-pattern core \u2014 hard-capped curated memory, FTS5 session search, staged review.",
-  "version": "0.62.27",
+  "version": "0.62.28",
   "author": {
     "name": "Fabian Wilde",
     "email": "docwilde@proton.me"

CHANGELOG.md

@@ -1,5 +1,15 @@
 # Changelog
 
+## 0.62.28 — 2026-11-12
+
+**README reference**
+
+- Document startup memory availability when pending enumeration fails, carrier
+  setup after plugin updates, and empty replacement and match-error behavior.
+- Clarify interactive CLI writes, staged model proposals, Codex hook trust and
+  MCP registration, and the graph-context defaults and Codex prompt-hook setup.
+- Describe learned skill outcomes, sync conflicts, and memory refresh behavior.
+
 ## 0.62.27 — 2026-11-12
 
 **Startup memory**

README.md

@@ -4,7 +4,7 @@
   <img src="https://img.shields.io/badge/status-beta-f59f00" alt="beta: the store migrates itself; command surfaces can still change">
   <a href="https://github.com/docwilde/LORE/releases"><img src="https://img.shields.io/github/v/release/docwilde/LORE?label=release&color=ff7f50" alt="latest release"></a>
   <img src="https://img.shields.io/badge/Claude%20Code%20%7C%20Codex%20%7C%20DOXA-shared%20memory-d97757" alt="shared memory for Claude Code, Codex, and DOXA">
-  <img src="https://img.shields.io/badge/curated%20writes-human--approved-2f9e44" alt="curated memory requires approval">
+  <img src="https://img.shields.io/badge/curated%20proposals-reviewed-2f9e44" alt="curated memory proposals require review">
   <img src="https://img.shields.io/badge/search-SQLite%20FTS5-044a64" alt="SQLite FTS5 search">
   <img src="https://img.shields.io/badge/search-no%20embeddings%20or%20API%20calls-555" alt="search uses no embeddings or API calls">
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-8a8073" alt="license"></a>
@@ -13,15 +13,15 @@
 # LORE — Lots Of Reconciled Engrams
 
 **Persistent memory shared by Claude Code, Codex, and DOXA.** Curated facts
-are capped and reviewed. Derived beliefs retain their evidence and appear
-on request or through explicitly enabled context.
+are hard-capped; curated proposals wait for review. Derived beliefs retain their
+evidence and appear on request or through explicitly enabled context.
 
 > [!WARNING]
 > **Beta.** Commands, caps, and configuration may change between releases.
 > LORE indexes local transcripts; Claude review sends a scrubbed digest to
 > the session's Anthropic endpoint. `/lore:setup` edits Claude settings.
-> Curated memory requires approval, but the deriver writes beliefs without
-> it. Sync is off until configured. Read [Data & safety](#data--safety).
+> Hooks and model tools stage curated changes for review; the deriver writes
+> beliefs directly. Sync is off until configured. Read [Data & safety](#data--safety).
 
 LORE keeps recall separate from authority: a belief carries citations,
 and relations between beliefs do not turn them into approved facts.
@@ -35,11 +35,11 @@ and relations between beliefs do not turn them into approved facts.
 - **Beliefs with evidence.** Query conclusions, citations, and their graph on demand.
 - **Session search.** Local FTS5 index of Claude Code, DOXA, and Codex transcripts.
 - **File maps.** A short `path — purpose` guide to important project files.
-- **Learned skills.** Verified recipes are proposed, evaluated, and updated or retired.
+- **Learned skills.** Recipes carry outcome history and staged updates or retirement.
 - **Local skill experiments.** [Capture diagnostic traces and compare pending coding skills](docs/skill-evaluation.md) against frozen tests before human approval.
 - **Cross-machine sync.** Signed hub, peer, or offline transfer; off by default.
 - **Agent integration.** Claude Code and Codex plugins inject startup context;
-  Claude review and explicit Codex writes retain the proposal and approval gates.
+  interactive CLI writes apply directly, while review and model tools stage proposals.
 
 Engine-origin labels add context, not authority. The [manual](docs/manual.md)
 explains the write gates, hooks, and belief model.
@@ -60,6 +60,9 @@ in a private disk cache. Hooks use the installed carrier and never build during
 startup. From a checkout, use `./task build` or `./task install`.
 The carrier may use a newer patch release within the plugin’s major/minor
 version; preview versions require an exact match.
+`./task install` places `lore-rs` and `lore` in `~/.local/bin` by default;
+keep that directory on `PATH`. Run setup after a plugin update so hooks have
+a compatible carrier before the next session starts.
 
 Native CLI, hooks, MCP and DOXA share saved caps, stage switches, review
 model preferences, context refresh and sync transport settings from
@@ -68,6 +71,12 @@ overrides saved values, including explicit empty values. A custom store
 uses only process overrides unless it belongs to the chosen settings
 directory. Store paths and identity remain process configuration. Saved credentials require a private, owned settings file.
 
+In [v0.62.27](https://github.com/docwilde/LORE/releases/tag/v0.62.27), startup
+and refresh snapshots load curated memory even when the pending-review scan
+fails. The snapshot reports the pending count as unknown with a diagnostic
+code. The pending directory scan is bounded at 4,096 entries; pending listings
+and review commands retain their bounds and approval checks.
+
 `/lore:setup` walks each `/lore:doctor` finding behind its own confirmation: disabling Claude Code's built-in auto-memory, adding the permission allowlist, porting existing entries, priming the session index.
 
 **First run:** review only looks forward, so run `/lore:backfill project` once to derive existing sessions into the belief store.
@@ -89,23 +98,36 @@ This WSL 2 setup has not been verified in LORE CI; see the
 ### Codex
 
 LORE supports Codex through the portable [`plugin.json`](plugin.json) and
-its [SessionStart hook](codex/hooks/hooks.json). Installing the full Codex
-plugin automatically injects the shared user and current project snapshot
-at startup, resume, clear, and compaction. Claude Code, Codex, and DOXA read
-the same store; set `LORE_ROOT` when using a store other than `~/.claude/lore`.
+its [SessionStart hook](codex/hooks/hooks.json). Enable the full plugin, then
+review and trust its hook with `/hooks` in Codex. Once trusted, the hook injects
+the shared user and current project snapshot at startup, resume, clear, and
+compaction. Codex requires a new review when a hook changes; see its
+[hook trust documentation](https://learn.chatgpt.com/docs/hooks#review-and-trust-hooks).
+Claude Code, Codex, and DOXA read the same store; set `LORE_ROOT` when using a
+store other than `~/.claude/lore`.
 
 The [Codex skill](codex/skills/lore/SKILL.md) supports explicit recall and
 memory writes. Index local Codex, Claude Code, and DOXA transcripts with
 `lore index`, search them with `lore search "terms" --all`, and read a match
 with `lore session <id>`. Indexing and search stay local and use SQLite FTS5.
 The Codex startup hook does not index transcripts or run the Claude reviewer.
 
-Use `lore memory add --scope user|project "one concise fact"` for an explicit
-write. Detached Codex writes become proposals under the normal write gate;
-inspect them with `lore pending` and resolve the exact reviewed proposal in
-the native terminal or DOXA. A proposal or search result is not an approved
-fact. The plugin manifest declares hooks and interface metadata; the native
-`lore mcp` server is available separately and is not registered automatically.
+Interactive Codex sessions can apply CLI memory writes directly. Calls
+classified as hooks or detached/model writers stage proposals; inspect them
+with `lore pending` and resolve the exact reviewed
+proposal in the native terminal or DOXA. The MCP tool `lore_remember` always
+stages a proposal. A proposal or search result is not an approved fact.
+
+The plugin declares its startup hook and skills. Register the native MCP server
+separately to give Codex tools for curated memory, beliefs and evidence,
+graph traversal, session search, and staged memory proposals. From this checkout:
+
+```sh
+./task install
+codex mcp add lore --env LORE_ENGINE=codex -- "$HOME/.local/bin/lore-rs" mcp --engine codex
+```
+
+Restart Codex to load the registered server.
 
 For a skill-only local setup from this checkout:
 
@@ -118,12 +140,41 @@ The skill calls LORE's CLI against the shared store when a task needs recall.
 This skill-only setup does not install the automatic SessionStart hook;
 install the full Codex plugin for startup context injection.
 
+## Memory and graph context
+
+Claude Code refreshes curated memory on prompt submission when its content
+changes by default (`LORE_REFRESH_ON_CHANGE=0` opts out). The bundled Codex
+hook supplies startup snapshots; read back changes during a session with
+`lore memory show` or the MCP tool `lore_memory_list`.
+
+Replacements and removals require a unique `--match`. Empty or whitespace-only
+replacement text is refused; use `memory remove` to delete an entry:
+
+```sh
+lore memory replace --scope project --match "old wording" "replacement fact"
+lore memory remove --scope project --match "obsolete fact"
+```
+
+An absent entry reports `match_not_found`; multiple matches report
+`match_ambiguous`.
+
+Graph context is experimental and off by default. Enable it in the shared
+settings with `lore config set LORE_GRAPH_CONTEXT 1`. Its defaults are a
+1,200-character budget (`LORE_GRAPH_CONTEXT_CAP`) and one relation hop
+(`LORE_GRAPH_CONTEXT_HOPS`). The Claude prompt hook injects the bounded block;
+automatic graph context in Codex requires a separate `UserPromptSubmit` hook.
+With graph context enabled, `lore graph context --prompt "topic terms"` reads
+the block explicitly. `lore graph stats`, `lore graph neighbours <id>`, and the
+MCP tool `lore_belief_neighbours` support on-demand inspection and traversal.
+Graph-retrieved beliefs retain their own evidence and citation status.
+
 ## Sync — one memory on every machine
 
 Sync is **off until configured**. LORE records portable changes in a local
 operation log; a configured transport moves signed operations between
-machines. Failed verification and conflicting writes go to pending review.
-Machine memory stays on its own host.
+machines. Unverified operations go to pending review; class-specific merge
+rules preserve alternatives or stage conflicting content. Machine memory
+stays on its own host.
 
 - **Hub:** push and pull through the private `lore-hub` service, which stores operations without interpreting them.
 - **Direct peer:** exchange operations between two machines without a hub.
@@ -153,7 +204,7 @@ an older hub copy cannot be replaced.
 - **Search stays local.** Indexing needs no embeddings or API calls.
 - **Claude review uses the session's Anthropic endpoint.** LORE scrubs likely secrets before sending a digest.
 - **Derived beliefs are written without approval.** The [read gate](docs/manual.md#the-belief-gate-sits-on-read-not-on-write) limits when they can influence an agent.
-- **The write gate is advisory.** `LORE_WRITE_GATE` classifies callers; it is not a security boundary.
+- **The write gate is advisory.** Interactive CLI calls can write curated memory directly; hook/model callers stage proposals. `LORE_WRITE_GATE=off` bypasses CLI staging and is not a security boundary.
 - **Sync is opt-in.** Configured transports can carry memory, beliefs, proposals, skills, and selected scrubbed session text; treat the destination as private storage.
 - **Setup changes Claude settings with confirmation.** `lore teardown` reverses those changes.
 
@@ -177,7 +228,11 @@ and interoperability test oracle.
 
 ## Lineage
 
-Curated memory follows the [Hermes Agent](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory) pattern: hard caps, a reviewer that proposes but never applies, a snapshot that stays frozen rather than thrashing the prompt cache. The belief layer is [Honcho](https://github.com/plastic-labs/honcho)'s deriver/dreamer/dialectic split, run here on one SQLite file with no standing service.
+Curated memory follows the [Hermes Agent](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory)
+pattern: hard caps, a reviewer that proposes but never applies, and stable
+context with change-detected refresh in Claude Code and startup snapshots in
+Codex. The belief layer uses [Honcho](https://github.com/plastic-labs/honcho)'s
+deriver/dreamer/dialectic split, stored locally in SQLite.
 
 The name means the accumulated knowledge of a craft — and, coincidentally, Data's brother in TNG. The logo's amber is a positronic wink at that.
 

plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "lore",
-  "version": "0.62.27",
+  "version": "0.62.28",
   "description": "Unified user, repo, and session memory for Claude Code, Codex, and DOXA",
   "author": {
     "name": "Dr. Fabian Wilde",

rust/lore-core/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lore-core"
-version = "0.62.27"
+version = "0.62.28"
 edition = "2021"
 license = "AGPL-3.0-only"
 description = "Native LORE memory, beliefs, review and session index"