Auto-merge upstream openclaw/openclaw

Author: friuns2

CHANGELOG.md

@@ -51,6 +51,7 @@ Docs: https://docs.openclaw.ai
 
 - Security: preserve restrictive plugin-only tool allowlists, require owner access for `/allowlist add` and `/allowlist remove`, fail closed when `before_tool_call` hooks crash, block browser SSRF redirect bypasses earlier, and keep non-interactive auth-choice inference scoped to bundled and already-trusted plugins. (#58476, #59836, #59822, #58771, #59120) Thanks @eleqtrizit and @pgondhi987.
 - Auto-reply: unify reply lifecycle ownership across preflight compaction, session rotation, CLI-backed runs, and gateway restart handling so `/stop` and same-session overlap checks target the right active turn and restart-interrupted turns return the restart notice instead of being silently dropped. (#61267) Thanks @dutifulbob.
+- Exec/remote skills: stop advertising `exec host=node` when the current exec policy cannot route to a node, and clarify blocked exec-host override errors with both the requested host and allowed config path.
 - Agents/Claude CLI/security: clear inherited Claude Code config-root and plugin-root env overrides like `CLAUDE_CONFIG_DIR` and `CLAUDE_CODE_PLUGIN_*`, so OpenClaw-launched Claude CLI runs cannot be silently pointed at an alternate Claude config/plugin tree with different hooks, plugins, or auth context. Thanks @vincentkoc.
 - Agents/Claude CLI/security: clear inherited Claude Code provider-routing and managed-auth env overrides, and mark OpenClaw-launched Claude CLI runs as host-managed, so Claude CLI backdoor sessions cannot be silently redirected to proxy, Bedrock, Vertex, Foundry, or parent-managed token contexts. Thanks @vincentkoc.
 - Agents/Claude CLI/security: force host-managed Claude CLI backdoor runs to `--setting-sources user`, even under custom backend arg overrides, so repo-local `.claude` project/local settings, hooks, and plugin discovery do not silently execute inside non-interactive OpenClaw sessions. Thanks @vincentkoc.
@@ -200,6 +201,7 @@ Docs: https://docs.openclaw.ai
 - Agents/video generation: accept `agents.defaults.videoGenerationModel` in strict config validation and `openclaw config set/get`, so gateways using `video_generate` no longer fail to boot after enabling a video model.
 - Discord/image generation: persist volatile workspace-generated media into durable outbound media before final reply delivery so generated image replies stop failing with missing local workspace paths.
 - Matrix: move legacy top-level `avatarUrl` into the default account during multi-account promotion and keep env-backed account setup avatar config persisted. (#61437) Thanks @gumadeiras.
+- Matrix/DM sessions: add `channels.matrix.dm.sessionScope`, shared-session collision notices, and aligned outbound session reuse so separate Matrix DM rooms can keep distinct context when configured. (#61373) Thanks @gumadeiras.
 
 ## 2026.4.2
 

docs/channels/matrix.md

@@ -152,6 +152,7 @@ This is a practical baseline config with DM pairing, room allowlist, and E2EE en
 
       dm: {
         policy: "pairing",
+        sessionScope: "per-room",
         threadReplies: "off",
       },
 
@@ -522,12 +523,17 @@ The repair flow does not delete old rooms automatically. It only picks the healt
 
 Matrix supports native Matrix threads for both automatic replies and message-tool sends.
 
+- `dm.sessionScope: "per-user"` (default) keeps Matrix DM routing sender-scoped, so multiple DM rooms can share one session when they resolve to the same peer.
+- `dm.sessionScope: "per-room"` isolates each Matrix DM room into its own session key while still using normal DM auth and allowlist checks.
+- Explicit Matrix conversation bindings still win over `dm.sessionScope`, so bound rooms and threads keep their chosen target session.
 - `threadReplies: "off"` keeps replies top-level and keeps inbound threaded messages on the parent session.
 - `threadReplies: "inbound"` replies inside a thread only when the inbound message was already in that thread.
 - `threadReplies: "always"` keeps room replies in a thread rooted at the triggering message and routes that conversation through the matching thread-scoped session from the first triggering message.
 - `dm.threadReplies` overrides the top-level setting for DMs only. For example, you can keep room threads isolated while keeping DMs flat.
 - Inbound threaded messages include the thread root message as extra agent context.
 - Message-tool sends now auto-inherit the current Matrix thread when the target is the same room, or the same DM user target, unless an explicit `threadId` is provided.
+- Same-session DM user-target reuse only kicks in when the current session metadata proves the same DM peer on the same Matrix account; otherwise OpenClaw falls back to normal user-scoped routing.
+- When OpenClaw sees a Matrix DM room collide with another DM room on the same shared Matrix DM session, it posts a one-time `m.notice` in that room with the `/focus` escape hatch when thread bindings are enabled and the `dm.sessionScope` hint.
 - Runtime thread bindings are supported for Matrix. `/focus`, `/unfocus`, `/agents`, `/session idle`, `/session max-age`, and thread-bound `/acp spawn` now work in Matrix rooms and DMs.
 - Top-level Matrix room/DM `/focus` creates a new Matrix thread and binds it to the target session when `threadBindings.spawnSubagentSessions=true`.
 - Running `/focus` or `/acp spawn --thread here` inside an existing Matrix thread binds that current thread instead.
@@ -842,8 +848,9 @@ Live directory lookup uses the logged-in Matrix account:
 - `mediaMaxMb`: media size cap in MB for Matrix media handling. It applies to outbound sends and inbound media processing.
 - `autoJoin`: invite auto-join policy (`always`, `allowlist`, `off`). Default: `off`.
 - `autoJoinAllowlist`: rooms/aliases allowed when `autoJoin` is `allowlist`. Alias entries are resolved to room IDs during invite handling; OpenClaw does not trust alias state claimed by the invited room.
-- `dm`: DM policy block (`enabled`, `policy`, `allowFrom`, `threadReplies`).
+- `dm`: DM policy block (`enabled`, `policy`, `allowFrom`, `sessionScope`, `threadReplies`).
 - `dm.allowFrom` entries should be full Matrix user IDs unless you already resolved them through live directory lookup.
+- `dm.sessionScope`: `per-user` (default) or `per-room`. Use `per-room` when you want each Matrix DM room to keep separate context even if the peer is the same.
 - `dm.threadReplies`: DM-only thread policy override (`off`, `inbound`, `always`). It overrides the top-level `threadReplies` setting for both reply placement and session isolation in DMs.
 - `execApprovals`: Matrix-native exec approval delivery (`enabled`, `approvers`, `target`, `agentFilter`, `sessionFilter`).
 - `execApprovals.approvers`: Matrix user IDs allowed to approve exec requests. Optional when `dm.allowFrom` already identifies the approvers.

docs/gateway/configuration-reference.md

@@ -655,6 +655,7 @@ Matrix is extension-backed and configured under `channels.matrix`.
   - `sessionFilter`: optional session key patterns (substring or regex).
   - `target`: where to send approval prompts. `"dm"` (default), `"channel"` (originating room), or `"both"`.
   - Per-account overrides: `channels.matrix.accounts.<id>.execApprovals`.
+- `channels.matrix.dm.sessionScope` controls how Matrix DMs group into sessions: `per-user` (default) shares by routed peer, while `per-room` isolates each DM room.
 - Matrix status probes and live directory lookups use the same proxy policy as runtime traffic.
 - Full Matrix configuration, targeting rules, and setup examples are documented in [Matrix](/channels/matrix).
 

docs/pi.md

@@ -503,7 +503,7 @@ if (sandboxRoot) {
 
 - Refusal magic string scrubbing
 - Turn validation for consecutive roles
-- Claude Code parameter compatibility
+- Strict upstream Pi tool parameter validation
 
 ### Google/Gemini
 

extensions/matrix/src/config-schema.test.ts

@@ -31,6 +31,18 @@ describe("MatrixConfigSchema SecretInput", () => {
     expect(result.success).toBe(true);
   });
 
+  it("accepts dm sessionScope overrides", () => {
+    const result = MatrixConfigSchema.safeParse({
+      homeserver: "https://matrix.example.org",
+      accessToken: "token",
+      dm: {
+        policy: "pairing",
+        sessionScope: "per-room",
+      },
+    });
+    expect(result.success).toBe(true);
+  });
+
   it("accepts room-level account assignments", () => {
     const result = MatrixConfigSchema.safeParse({
       homeserver: "https://matrix.example.org",

extensions/matrix/src/config-schema.ts

@@ -104,6 +104,7 @@ export const MatrixConfigSchema = z.object({
   autoJoinAllowlist: AllowFromListSchema,
   groupAllowFrom: AllowFromListSchema,
   dm: buildNestedDmConfigSchema({
+    sessionScope: z.enum(["per-user", "per-room"]).optional(),
     threadReplies: z.enum(["off", "inbound", "always"]).optional(),
   }),
   execApprovals: matrixExecApprovalsSchema,

extensions/matrix/src/matrix/monitor/handler.test-helpers.ts

@@ -31,6 +31,7 @@ type MatrixHandlerTestHarnessOptions = {
   replyToMode?: ReplyToMode;
   threadReplies?: "off" | "inbound" | "always";
   dmThreadReplies?: "off" | "inbound" | "always";
+  dmSessionScope?: "per-user" | "per-room";
   streaming?: "partial" | "off";
   blockStreamingEnabled?: boolean;
   dmEnabled?: boolean;
@@ -214,6 +215,7 @@ export function createMatrixHandlerTestHarness(
     replyToMode: options.replyToMode ?? "off",
     threadReplies: options.threadReplies ?? "inbound",
     dmThreadReplies: options.dmThreadReplies,
+    dmSessionScope: options.dmSessionScope,
     streaming: options.streaming ?? "off",
     blockStreamingEnabled: options.blockStreamingEnabled ?? false,
     dmEnabled: options.dmEnabled ?? true,