memorix 1.2.2 → 1.2.3

package/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 All notable changes to this project will be documented in this file.
 
+## [1.2.3] - 2026-07-25
+
+### Fixed
+- **Session context now respects observation visibility** -- Automatic session handoff and manual session-context reads in the CLI, MCP server, and Workbench apply the caller's project, team, and personal-memory reader. A new identity cannot receive another agent's personal observations through session startup.
+- **Identity before handoff** -- CLI and MCP coordination sessions establish their explicit identity before assembling prior context, so an owner's own personal records remain available while a newly joined agent fails closed.
+- **Graph-side disclosure guard** -- Agent-facing session handoff no longer derives graph-neighbor hints from graph relations that do not yet carry observation visibility metadata.
+
 ## [1.2.2] - 2026-07-25
 
 ### Added

package/TEAM.md

@@ -1,18 +1,18 @@
-# Memorix Team Protocol
-
+# Memorix Team Protocol
+
 Rules for project-scoped autonomous-agent coordination via Memorix team tools. The Team page is an **Agent Team status surface** — it shows explicitly joined autonomous agents, open tasks, locks, messages, handoffs, and what needs attention. It is NOT an organization backend, staffing admin tool, or automatic chat room between separate IDE windows.
 
 Only agents that are intentionally participating in team/task/message/lock workflows need this protocol. Memory-only sessions should stay lightweight and do not need a team identity.
 
 For real autonomous multi-agent development, prefer `memorix orchestrate`: it launches and supervises CLI agent workers through Memorix tasks, context, verification, and fix loops. The team tools support that workflow; they should not be interpreted as proof that unrelated IDE conversation windows can autonomously contact each other.
-
-There are 4 team tools, each with an `action` parameter:
-
-- `team_manage` — action: join / leave / status
-- `team_file_lock` — action: lock / unlock / status
-- `team_task` — action: create / claim / complete / list
-- `team_message` — action: send / broadcast / inbox
-
+
+There are 4 team tools, each with an `action` parameter:
+
+- `team_manage` — action: join / leave / status
+- `team_file_lock` — action: lock / unlock / status
+- `team_task` — action: create / claim / complete / list
+- `team_message` — action: send / broadcast / inbox
+
 ## RULE 1: Start Lightweight, Join Team Explicitly
 
 At the **beginning of every memory session**, before project-scoped memory work:
@@ -25,82 +25,82 @@ At the **beginning of every memory session**, before project-scoped memory work:
 4. Store the returned **agent ID** only after an explicit join — you will need it for subsequent team operations.
 5. Call `memorix_poll` with your agent ID to see current autonomous agents, check available tasks, and read unread messages.
 6. If you need a custom role or capabilities, use explicit `team_manage(join)` so the role overrides the default mapping cleanly.
-
-## RULE 2: Lock Before Edit
-
-Before modifying any file that another agent might also be working on:
-
-1. Call `team_file_lock` with `action: "status"` and the file path to check if it is already locked.
-2. If unlocked, call `team_file_lock` with `action: "lock"`, the file path, and your agent ID.
-3. If locked by another agent, **do not edit that file**. Either:
-   - Work on a different file.
-   - Send a `request` message to the lock owner asking them to release it.
-   - Wait and re-check later.
-4. When you are done editing, call `team_file_lock` with `action: "unlock"` to release the lock.
-
-**Never edit a file locked by another agent.** Lock violations cause merge conflicts and data loss.
-
-Locks auto-expire after 10 minutes. If you hold a lock for extended work, re-lock periodically to refresh the TTL.
-
-## RULE 3: Use Tasks for Work Coordination
-
-When the user assigns work that involves multiple agents or multiple steps:
-
-1. Call `team_task` with `action: "create"` to break the work into discrete tasks with clear descriptions.
-2. Use `deps` to declare dependencies between tasks (a task cannot be claimed until its dependencies are completed).
-3. Call `team_task` with `action: "claim"` to assign a task to yourself before starting work on it.
-4. Call `team_task` with `action: "complete"` and a `result` summary when the task is done.
-5. Call `team_task` with `action: "list"` to see overall progress and find available work.
-
-Rules:
-- Only claim tasks whose dependencies are all completed.
-- Only one agent may claim a given task.
-- If you cannot complete a claimed task, leave the team so the task returns to pending and another agent can pick it up.
-
-## RULE 4: Communication Protocol
-
-Use `team_message` with `action: "send"` for direct messages and `action: "broadcast"` for announcements. Message types and their intended use:
-
-| Type | Use |
-|------|-----|
-| `request` | Ask another agent to do something, release a lock, or provide information. |
-| `response` | Reply to a prior request. |
-| `info` | Share context: discoveries, status updates, warnings about tricky code. |
-| `announcement` | Broadcast to all agents: major state changes, deployment events, breaking changes. |
-| `contract` | Propose or agree on a division of work. Both agents should acknowledge. |
-| `error` | Report a blocking issue that requires another agent's attention. |
-
-Rules:
-- `action: "send"` requires the full UUID of the target agent. Get it from `team_manage` with `action: "status"`.
-- Check your inbox (`action: "inbox"`) at least once before starting new work and once before ending a session.
-- Keep message content under 10KB. Be concise and actionable.
-
-## RULE 5: Leave on Session End
-
-When the session is ending:
-
-1. Call `team_file_lock` with `action: "unlock"` for every file you have locked, or they will remain locked until TTL expiry (10 min).
-2. If you have in-progress tasks you cannot finish, leave them — leaving releases your tasks back to pending.
-3. Call `team_manage` with `action: "leave"` and your agent ID. This marks you inactive, releases all your locks, and clears your inbox.
-
-## RULE 6: Conflict Prevention
-
-- **Check before acting.** Always check team status and file lock status before starting work to understand the current state.
-- **Communicate before diverging.** If you plan to refactor shared code, broadcast an `announcement` first so other agents can save their work.
-- **Respect lock ownership.** The lock holder has exclusive write access. No exceptions.
-- **Prefer small, scoped changes.** Large cross-cutting changes increase conflict risk. Coordinate via tasks and messages if a change touches files other agents are working on.
-- **Do not duplicate work.** Check the task list before creating new tasks. If a similar task exists, claim it instead of creating a duplicate.
-
-## Summary of Required Calls
-
-| When | Tool Call |
-|------|-----------|
+
+## RULE 2: Lock Before Edit
+
+Before modifying any file that another agent might also be working on:
+
+1. Call `team_file_lock` with `action: "status"` and the file path to check if it is already locked.
+2. If unlocked, call `team_file_lock` with `action: "lock"`, the file path, and your agent ID.
+3. If locked by another agent, **do not edit that file**. Either:
+   - Work on a different file.
+   - Send a `request` message to the lock owner asking them to release it.
+   - Wait and re-check later.
+4. When you are done editing, call `team_file_lock` with `action: "unlock"` to release the lock.
+
+**Never edit a file locked by another agent.** Lock violations cause merge conflicts and data loss.
+
+Locks auto-expire after 10 minutes. If you hold a lock for extended work, re-lock periodically to refresh the TTL.
+
+## RULE 3: Use Tasks for Work Coordination
+
+When the user assigns work that involves multiple agents or multiple steps:
+
+1. Call `team_task` with `action: "create"` to break the work into discrete tasks with clear descriptions.
+2. Use `deps` to declare dependencies between tasks (a task cannot be claimed until its dependencies are completed).
+3. Call `team_task` with `action: "claim"` to assign a task to yourself before starting work on it.
+4. Call `team_task` with `action: "complete"` and a `result` summary when the task is done.
+5. Call `team_task` with `action: "list"` to see overall progress and find available work.
+
+Rules:
+- Only claim tasks whose dependencies are all completed.
+- Only one agent may claim a given task.
+- If you cannot complete a claimed task, leave the team so the task returns to pending and another agent can pick it up.
+
+## RULE 4: Communication Protocol
+
+Use `team_message` with `action: "send"` for direct messages and `action: "broadcast"` for announcements. Message types and their intended use:
+
+| Type | Use |
+|------|-----|
+| `request` | Ask another agent to do something, release a lock, or provide information. |
+| `response` | Reply to a prior request. |
+| `info` | Share context: discoveries, status updates, warnings about tricky code. |
+| `announcement` | Broadcast to all agents: major state changes, deployment events, breaking changes. |
+| `contract` | Propose or agree on a division of work. Both agents should acknowledge. |
+| `error` | Report a blocking issue that requires another agent's attention. |
+
+Rules:
+- `action: "send"` requires the full UUID of the target agent. Get it from `team_manage` with `action: "status"`.
+- Check your inbox (`action: "inbox"`) at least once before starting new work and once before ending a session.
+- Keep message content under 10KB. Be concise and actionable.
+
+## RULE 5: Leave on Session End
+
+When the session is ending:
+
+1. Call `team_file_lock` with `action: "unlock"` for every file you have locked, or they will remain locked until TTL expiry (10 min).
+2. If you have in-progress tasks you cannot finish, leave them — leaving releases your tasks back to pending.
+3. Call `team_manage` with `action: "leave"` and your agent ID. This marks you inactive, releases all your locks, and clears your inbox.
+
+## RULE 6: Conflict Prevention
+
+- **Check before acting.** Always check team status and file lock status before starting work to understand the current state.
+- **Communicate before diverging.** If you plan to refactor shared code, broadcast an `announcement` first so other agents can save their work.
+- **Respect lock ownership.** The lock holder has exclusive write access. No exceptions.
+- **Prefer small, scoped changes.** Large cross-cutting changes increase conflict risk. Coordinate via tasks and messages if a change touches files other agents are working on.
+- **Do not duplicate work.** Check the task list before creating new tasks. If a similar task exists, claim it instead of creating a duplicate.
+
+## Summary of Required Calls
+
+| When | Tool Call |
+|------|-----------|
 | Session start | `memorix_session_start` (lightweight) |
 | Join Agent Team | `memorix_session_start(joinTeam=true)` or `team_manage(join)` |
 | After joining | `memorix_poll` (check status + inbox) |
-| Before editing a shared file | `team_file_lock(status)`, `team_file_lock(lock)` |
-| After editing | `team_file_lock(unlock)` |
-| Starting a unit of work | `team_task(claim)` or `team_task(create)` + `team_task(claim)` |
-| Finishing a unit of work | `team_task(complete)` |
-| Need to coordinate | `team_message(send)` or `team_message(broadcast)` |
-| Session end | `team_file_lock(unlock)` (all), `team_manage(leave)` |
+| Before editing a shared file | `team_file_lock(status)`, `team_file_lock(lock)` |
+| After editing | `team_file_lock(unlock)` |
+| Starting a unit of work | `team_task(claim)` or `team_task(create)` + `team_task(claim)` |
+| Finishing a unit of work | `team_task(complete)` |
+| Need to coordinate | `team_message(send)` or `team_message(broadcast)` |
+| Session end | `team_file_lock(unlock)` (all), `team_manage(leave)` |

package/dist/cli/index.js

@@ -3212,7 +3212,7 @@ ${import_picocolors.default.gray(m3)}  ${s2}
 
 // src/cli/version.ts
 function getCliVersion() {
-  return true ? "1.2.2" : pkg.version;
+  return true ? "1.2.3" : pkg.version;
 }
 var init_version = __esm({
   "src/cli/version.ts"() {
@@ -41147,7 +41147,7 @@ async function startSession(projectDir2, projectId, opts) {
     status: "active",
     agent: opts?.agent
   };
-  const previousContext = await getSessionContext(projectDir2, projectId);
+  const previousContext = await getSessionContext(projectDir2, projectId, 3, opts?.reader);
   const sessionStore = getSessionStore();
   const aliasSet = await resolveProjectIds(projectId);
   await sessionStore.atomicRolloverInsert(session, [...aliasSet], now3);
@@ -41165,23 +41165,27 @@ async function endSession(projectDir2, sessionId, summary) {
   await sessionStore.update(session);
   return session;
 }
-async function getSessionContext(projectDir2, projectId, limit = 3) {
+async function getSessionContext(projectDir2, projectId, limit = 3, reader) {
   const aliasSet = await resolveProjectIds(projectId);
   const [sessions, allObs] = await Promise.all([
     loadAliasSessions(aliasSet),
     loadAliasActiveObservations(aliasSet)
   ]);
+  const readableObs = reader ? allObs.filter((observation) => {
+    const observationReader = reader.projectId && aliasSet.has(observation.projectId) ? { ...reader, projectId: observation.projectId } : reader;
+    return canReadObservation(observation, observationReader);
+  }) : allObs;
   const isNoisySummary = (summary) => {
     if (!summary) return false;
     return NOISE_PATTERNS2.some((p2) => p2.test(summary)) || SYSTEM_SELF_PATTERNS.some((p2) => p2.test(summary));
   };
   const projectSessions = sessions.filter((session) => session.status === "completed").filter((session) => !isNoisySummary(session.summary)).sort((a3, b3) => new Date(b3.endedAt || b3.startedAt).getTime() - new Date(a3.endedAt || a3.startedAt).getTime()).slice(0, limit);
-  if (projectSessions.length === 0 && allObs.length === 0) {
+  if (projectSessions.length === 0 && readableObs.length === 0) {
     return "";
   }
   const lines = [];
   const projectTokens = tokenizeProjectId(projectId);
-  const projectObs = allObs.filter((obs) => !isNoiseObservation(obs) && !isSystemSelfObservation(obs));
+  const projectObs = readableObs.filter((obs) => !isNoiseObservation(obs) && !isSystemSelfObservation(obs));
   const l2Scored = projectObs.filter((obs) => PRIORITY_TYPES.has(obs.type) && classifyLayer(obs) === "L2").map((obs) => ({ obs, score: scoreObservationForSessionContext(obs, projectTokens) })).sort((a3, b3) => {
     if (b3.score !== a3.score) return b3.score - a3.score;
     return new Date(b3.obs.createdAt).getTime() - new Date(a3.obs.createdAt).getTime();
@@ -41207,7 +41211,7 @@ async function getSessionContext(projectDir2, projectId, limit = 3) {
   const hasL1Content = l1HookObs.length > 0 || l3GitCount > 0;
   if (hasL1Content) {
     let graphNeighbors = [];
-    if (activeEntities.length > 0) {
+    if (!reader && activeEntities.length > 0) {
       try {
         const graphMgr = new KnowledgeGraphManager(projectDir2);
         await graphMgr.init();
@@ -41333,6 +41337,7 @@ var init_session = __esm({
     init_session_store();
     init_graph();
     init_secret_filter();
+    init_visibility();
     PRIORITY_TYPES = /* @__PURE__ */ new Set(["gotcha", "decision", "problem-solution", "trade-off", "discovery"]);
     TYPE_EMOJI = {
       "gotcha": "[DISCOVERY]",
@@ -41492,7 +41497,7 @@ var init_session2 = __esm({
         const action = args._?.[0] || "";
         const asJson = !!args.json;
         try {
-          const { project, dataDir, teamStore } = await getCliProjectContext({
+          const { project, dataDir, teamStore, reader } = await getCliProjectContext({
             projectRoot: args.projectRoot
           });
           switch (action) {
@@ -41505,10 +41510,6 @@ var init_session2 = __esm({
                 emitError("use requires --agent or --agentType so Memorix can activate a coordination identity.", asJson);
                 return;
               }
-              const result = await startSession(dataDir, project.id, {
-                sessionId: args.sessionId,
-                agent: args.agent
-              });
               const shouldJoinTeam = !!args.joinTeam;
               let agentRecord = null;
               let teamJoinNotice = null;
@@ -41526,6 +41527,16 @@ var init_session2 = __esm({
               } else if (shouldJoinTeam) {
                 teamJoinNotice = "Coordination join skipped: provide --agent or --agentType to create a coordination identity.";
               }
+              const contextReader = agentRecord ? {
+                projectId: project.id,
+                agentId: agentRecord.agent_id,
+                isTeamMember: agentRecord.status === "active"
+              } : reader;
+              const result = await startSession(dataDir, project.id, {
+                sessionId: args.sessionId,
+                agent: args.agent,
+                reader: contextReader
+              });
               let identityActivated = false;
               if (args.use && agentRecord) {
                 await saveCliIdentity(dataDir, {
@@ -41615,7 +41626,7 @@ var init_session2 = __esm({
             case "context": {
               const limit = parsePositiveInt(args.limit, 3);
               const [context, sessions] = await Promise.all([
-                getSessionContext(dataDir, project.id, limit),
+                getSessionContext(dataDir, project.id, limit, reader),
                 listSessions(dataDir, project.id)
               ]);
               const active = sessions.filter((session) => session.status === "active").length;
@@ -69995,7 +70006,7 @@ The path should point to a directory containing a .git folder.`
   };
   const server = existingServer ?? new McpServer({
     name: "memorix",
-    version: true ? "1.2.2" : "1.0.1"
+    version: true ? "1.2.3" : "1.0.1"
   });
   const originalRegisterTool = server.registerTool.bind(server);
   server.registerTool = ((name, ...args) => {
@@ -72496,7 +72507,6 @@ Ensure the path points to a directory containing a .git folder (or a subdirector
       const unresolved = requireResolvedProject("start a project session");
       if (unresolved) return unresolved;
       const { startSession: startSession2 } = await Promise.resolve().then(() => (init_session(), session_exports));
-      const result = await startSession2(projectDir2, project.id, { sessionId, agent });
       const llmStatus = isLLMEnabled() ? `LLM enhanced mode: ${getLLMConfig()?.provider}/${getLLMConfig()?.model} (fact extraction + auto-dedup active)` : "LLM mode: off (set MEMORIX_LLM_API_KEY to enable enhanced memory quality)";
       const shouldJoinTeam = !!joinTeam;
       let registeredAgent = null;
@@ -72553,6 +72563,11 @@ Ensure the path points to a directory containing a .git folder (or a subdirector
         }
       } catch {
       }
+      const result = await startSession2(projectDir2, project.id, {
+        sessionId,
+        agent,
+        reader: getObservationReader()
+      });
       const lines = [
         `[OK] Session started: ${result.session.id}`,
         `Project: ${project.name} (${project.id})`,
@@ -72675,7 +72690,7 @@ ${summary ? "Summary saved for next session context injection." : "No summary pr
     async ({ limit }) => {
       const safeLimit = limit != null ? coerceNumber(limit, 3) : 3;
       const { getSessionContext: getSessionContext2, listSessions: listSessions2 } = await Promise.resolve().then(() => (init_session(), session_exports));
-      const context = await getSessionContext2(projectDir2, project.id, safeLimit);
+      const context = await getSessionContext2(projectDir2, project.id, safeLimit, getObservationReader());
       const sessions = await listSessions2(projectDir2, project.id);
       const activeSessions = sessions.filter((s2) => s2.status === "active");
       const completedSessions = sessions.filter((s2) => s2.status === "completed");
@@ -87870,11 +87885,12 @@ async function getSessionState(projectId) {
 }
 async function bindSession() {
   try {
-    const proj = await resolveProject();
-    if (!proj) return { status: "error", error: "No project detected" };
+    const { getTuiOperatorContext: getTuiOperatorContext2 } = await Promise.resolve().then(() => (init_operator_context(), operator_context_exports));
+    const { project: proj, reader } = await getTuiOperatorContext2();
     const { startSession: startSession2 } = await Promise.resolve().then(() => (init_session(), session_exports));
     const { session, previousContext } = await startSession2(proj.rootPath, proj.id, {
-      agent: "memorix-tui"
+      agent: "memorix-tui",
+      reader
     });
     return {
       status: "bound",