Restore websocket follow-up for embed stack

* refactor(sandbox): remove socat proxy and fix chromium keyring deadlock

* fix(sandbox): address review feedback by reinstating cdp isolation and stability flags

* fix(sandbox): increase entrypoint cdp timeout to 20s to honor autoStartTimeoutMs

* fix(sandbox): align implementation with PR description (keyring bypass, fail-fast, watchdog)

* fix

* fix(sandbox): remove bash CDP watchdog to eliminate dual-timeout race

* fix(sandbox): apply final fail-fast and lifecycle bindings

* fix(sandbox): restore noVNC and CDP port offset

* fix(sandbox): add max-time to curl to prevent HTTP hang

* fix(sandbox): align timeout with host and restore env flags

* fix(sandbox): pass auto-start timeout to container and restore wait -n

* fix(sandbox): update hash input type to include autoStartTimeoutMs

* fix(sandbox): implement production-grade lifecycle and timeout management

- Add strict integer validation for port and timeout environment variables
- Implement robust two-stage trap cleanup (SIGTERM with SIGKILL fallback) to prevent zombie processes
- Refactor CDP readiness probe to use absolute millisecond-precision deadlines
- Add early fail-fast detection if Chromium crashes during the startup phase
- Track all daemon PIDs explicitly for reliable teardown via wait -n

* fix(sandbox): allow renderer process limit to be 0 for chromium default

* fix(sandbox): add autoStartTimeoutMs to SandboxBrowserHashInput type

* test(sandbox): cover browser timeout cleanup

---------

Co-authored-by: Ayaan Zaidi <hi@obviy.us>

.agents/skills/openclaw-parallels-smoke/SKILL.md

@@ -30,9 +30,12 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 
 - Preferred entrypoint: `pnpm test:parallels:npm-update`
 - Flow: fresh snapshot -> install npm package baseline -> smoke -> install current main tgz on the same guest -> smoke again.
+- For beta/stable verification, resolve the tag immediately before the run (`npm view openclaw@beta version dist.tarball` or `npm view openclaw@latest ...`). Tags can move while a long VM matrix is already running; restart the matrix when the intended prerelease appears after an earlier registry 404/tag-lag check.
+- Source Peter's profile in the host shell (`set -a; source "$HOME/.profile"; set +a`) before OpenAI/Anthropic lanes. Do not print profile contents or env dumps; pass provider secrets through the guest exec environment.
 - Same-guest update verification should set the default model explicitly to `openai/gpt-5.4` before the agent turn and use a fresh explicit `--session-id` so old session model state does not leak into the check.
 - The aggregate npm-update wrapper must resolve the Linux VM with the same Ubuntu fallback policy as `parallels-linux-smoke.sh` before both fresh and update lanes. Treat any Ubuntu guest with major version `>= 24` as acceptable when the exact default VM is missing, preferring the closest version match. On Peter's current host today, missing `Ubuntu 24.04.3 ARM64` should fall back to `Ubuntu 25.10`.
 - On macOS same-guest update checks, restart the gateway after the npm upgrade before `gateway status` / `agent`; launchd can otherwise report a loaded service while the old process has exited and the fresh process is not RPC-ready yet.
+- The npm-update aggregate's macOS update leg writes the guest update script as root, then runs it as the desktop user. If `prlctl exec "$MACOS_VM" --current-user ...` cannot authenticate, retry through plain root `prlctl exec` plus `sudo -u <desktop-user> /usr/bin/env HOME=/Users/<desktop-user> USER=<desktop-user> LOGNAME=<desktop-user> PATH=/opt/homebrew/bin:/opt/homebrew/opt/node/bin:/usr/bin:/bin:/usr/sbin:/sbin ...`. That is a Parallels transport fallback; still verify `openclaw --version`, gateway RPC, and an agent turn after the update.
 - On Windows same-guest update checks, restart the gateway after the npm upgrade before `gateway status` / `agent`; in-place global npm updates can otherwise leave stale hashed `dist/*` module imports alive in the running service.
 - In those Windows same-guest update checks, do not treat one nonzero `openclaw gateway restart` as definitive failure. Current login-item restarts can report failure before the background service becomes observable again; follow with a longer RPC-ready wait and use `gateway start` only as a recovery step if readiness still never returns.
 - After that Windows restart, do not trust one `gateway status --deep --require-rpc` call after a fixed sleep. Retry the RPC-ready probe for roughly 30 seconds and log each attempt; current guests can keep port `18789` bound while the fresh RPC endpoint is still coming up.
@@ -41,6 +44,7 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - Linux same-guest update verification should also export `HOME=/root`, pass `OPENAI_API_KEY` via `prlctl exec ... /usr/bin/env`, and use `openclaw agent --local`; the fresh Linux baseline does not rely on persisted gateway credentials.
 - The npm-update wrapper now prints per-lane progress from the nested log files. If a lane still looks stuck, inspect the nested logs in `runDir` first (`macos-fresh.log`, `windows-fresh.log`, `linux-fresh.log`, `macos-update.log`, `windows-update.log`, `linux-update.log`) instead of assuming the outer wrapper hung.
 - If the wrapper fails a lane, read the auto-dumped tail first, then the full nested lane log under `/tmp/openclaw-parallels-npm-update.*`.
+- Current known macOS update-lane transport signature when the fallback is missing or bypassed: `Unable to authenticate the user. Make sure that the specified credentials are correct and try again.` Treat that as Parallels current-user authentication before blaming npm or OpenClaw.
 
 ## CLI invocation footgun
 
@@ -64,6 +68,7 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - If a packaged install regresses with `500` on `/`, `/healthz`, or `__openclaw/control-ui-config.json` after `fresh.install-main` or `upgrade.install-main`, suspect bundled plugin runtime deps resolving from the package root `node_modules` rather than `dist/extensions/*/node_modules`. Repro quickly with a real `npm pack`/global install lane before blaming dashboard auth or Safari.
 - `prlctl exec` is fine for deterministic repo commands, but use the guest Terminal or `prlctl enter` when installer parity or shell-sensitive behavior matters.
 - Multi-word `openclaw agent --message ...` checks should go through a guest shell wrapper (`guest_current_user_sh` / `guest_current_user_cli` or `/bin/sh -lc ...`), not raw `prlctl exec ... node openclaw.mjs ...`, or the message can be split into extra argv tokens and Commander reports `too many arguments for 'agent'`.
+- The same wrapper rule applies when bypassing `--current-user`: write a tiny `/tmp/*.sh` on the guest and execute `/bin/bash /tmp/*.sh` through the sudo desktop-user environment. Do not pass `openclaw agent --message '...'` directly as one raw `prlctl exec` command.
 - When ref-mode onboarding stores `OPENAI_API_KEY` as an env secret ref, the post-onboard agent verification should also export `OPENAI_API_KEY` for the guest command. The gateway can still reject with pairing-required and fall back to embedded execution, and that fallback needs the env-backed credential available in the shell.
 - On the fresh Tahoe snapshot, `brew` exists but `node` may be missing from PATH in noninteractive exec. Use `/opt/homebrew/bin/node` when needed.
 - Fresh host-served tgz installs should install as guest root with `HOME=/var/root`, then run onboarding as the desktop user via `prlctl exec --current-user`.

.agents/skills/openclaw-qa-testing/SKILL.md

@@ -57,31 +57,28 @@ Use `qa character-eval` for style/persona/vibe checks across multiple live model
 pnpm openclaw qa character-eval \
   --model openai/gpt-5.4,thinking=xhigh \
   --model openai/gpt-5.2,thinking=xhigh \
+  --model openai/gpt-5,thinking=xhigh \
   --model anthropic/claude-opus-4-6,thinking=high \
   --model anthropic/claude-sonnet-4-6,thinking=high \
-  --model minimax/MiniMax-M2.7,thinking=high \
   --model zai/glm-5.1,thinking=high \
   --model moonshot/kimi-k2.5,thinking=high \
-  --model qwen/qwen3.6-plus,thinking=high \
-  --model xiaomi/mimo-v2-pro,thinking=high \
   --model google/gemini-3.1-pro-preview,thinking=high \
-  --model codex-cli/<codex-model>,thinking=high \
   --judge-model openai/gpt-5.4,thinking=xhigh,fast \
   --judge-model anthropic/claude-opus-4-6,thinking=high \
-  --concurrency 8 \
-  --judge-concurrency 8 \
+  --concurrency 16 \
+  --judge-concurrency 16 \
   --output-dir .artifacts/qa-e2e/character-eval-<tag>
 ```
 
 - Runs local QA gateway child processes, not Docker.
 - Preferred model spec syntax is `provider/model,thinking=<level>[,fast|,no-fast|,fast=<bool>]` for both `--model` and `--judge-model`.
 - Do not add new examples with separate `--model-thinking`; keep that flag as legacy compatibility only.
-- Defaults to candidate models `openai/gpt-5.4`, `openai/gpt-5.2`, `anthropic/claude-opus-4-6`, `anthropic/claude-sonnet-4-6`, `minimax/MiniMax-M2.7`, `zai/glm-5.1`, `moonshot/kimi-k2.5`, `qwen/qwen3.6-plus`, `xiaomi/mimo-v2-pro`, and `google/gemini-3.1-pro-preview` when no `--model` is passed.
+- Defaults to candidate models `openai/gpt-5.4`, `openai/gpt-5.2`, `openai/gpt-5`, `anthropic/claude-opus-4-6`, `anthropic/claude-sonnet-4-6`, `zai/glm-5.1`, `moonshot/kimi-k2.5`, and `google/gemini-3.1-pro-preview` when no `--model` is passed.
 - Candidate thinking defaults to `high`, with `xhigh` for OpenAI models that support it. Prefer inline `--model provider/model,thinking=<level>`; `--thinking <level>` and `--model-thinking <provider/model=level>` remain compatibility shims.
 - OpenAI candidate refs default to fast mode so priority processing is used where supported. Use inline `,fast`, `,no-fast`, or `,fast=false` for one model; use `--fast` only to force fast mode for every candidate.
 - Judges default to `openai/gpt-5.4,thinking=xhigh,fast` and `anthropic/claude-opus-4-6,thinking=high`.
 - Report includes judge ranking, run stats, durations, and full transcripts; do not include raw judge replies. Duration is benchmark context, not a grading signal.
-- Candidate and judge concurrency default to 8. Use `--concurrency <n>` and `--judge-concurrency <n>` to override when local gateways or provider limits need a gentler lane.
+- Candidate and judge concurrency default to 16. Use `--concurrency <n>` and `--judge-concurrency <n>` to override when local gateways or provider limits need a gentler lane.
 - Scenario source should stay markdown-driven under `qa/scenarios/`.
 - For isolated character/persona evals, write the persona into `SOUL.md` and blank `IDENTITY.md` in the scenario flow. Use `SOUL.md + IDENTITY.md` only when intentionally testing how the normal OpenClaw identity combines with the character.
 - Keep prompts natural and task-shaped. The candidate model should receive character setup through `SOUL.md`, then normal user turns such as chat, workspace help, and small file tasks; do not ask "how would you react?" or tell the model it is in an eval.

.github/workflows/ci.yml

@@ -779,6 +779,11 @@ jobs:
         continue-on-error: true
         run: pnpm test:gateway:watch-regression
 
+      - name: Run import cycle guard
+        id: import_cycles
+        continue-on-error: true
+        run: pnpm check:import-cycles
+
       - name: Upload gateway watch regression artifacts
         if: always()
         uses: actions/upload-artifact@v7
@@ -811,6 +816,7 @@ jobs:
           NO_RAW_WINDOW_OPEN_OUTCOME: ${{ steps.no_raw_window_open.outcome }}
           CONTROL_UI_I18N_OUTCOME: ${{ steps.control_ui_i18n.outcome == 'skipped' && 'success' || steps.control_ui_i18n.outcome }}
           GATEWAY_WATCH_REGRESSION_OUTCOME: ${{ steps.gateway_watch_regression.outcome }}
+          IMPORT_CYCLES_OUTCOME: ${{ steps.import_cycles.outcome }}
         run: |
           failures=0
           for result in \
@@ -834,7 +840,8 @@ jobs:
             "test:extensions:package-boundary|$EXTENSION_PACKAGE_BOUNDARY_TSC_OUTCOME" \
             "lint:ui:no-raw-window-open|$NO_RAW_WINDOW_OPEN_OUTCOME" \
             "ui:i18n:check|$CONTROL_UI_I18N_OUTCOME" \
-            "gateway-watch-regression|$GATEWAY_WATCH_REGRESSION_OUTCOME"; do
+            "gateway-watch-regression|$GATEWAY_WATCH_REGRESSION_OUTCOME" \
+            "check:import-cycles|$IMPORT_CYCLES_OUTCOME"; do
             name="${result%%|*}"
             outcome="${result#*|}"
             if [ "$outcome" != "success" ]; then
@@ -1042,7 +1049,9 @@ jobs:
           set -euo pipefail
           case "$TASK" in
             test)
-              pnpm test
+              # Linux owns the full repo test suite. Keep the Windows runner focused on
+              # Windows-native process/path wrappers so platform regressions fail fast.
+              pnpm test:windows:ci
               ;;
             *)
               echo "Unsupported Windows checks task: $TASK" >&2
@@ -1093,7 +1102,9 @@ jobs:
           set -euo pipefail
           case "$TASK" in
             test)
-              pnpm test
+              # Linux owns the full repo test suite. Keep macOS CI focused on
+              # launchd/Homebrew/runtime path coverage and the process-group wrapper.
+              pnpm test:macos:ci
               ;;
             *)
               echo "Unsupported macOS node task: $TASK" >&2

.github/workflows/openclaw-npm-release.yml

@@ -162,9 +162,63 @@ jobs:
           RELEASE_NPM_DIST_TAG: ${{ inputs.npm_dist_tag }}
         run: |
           set -euo pipefail
-          PACK_JSON="$(npm pack --json)"
-          echo "$PACK_JSON"
-          PACK_PATH="$(printf '%s\n' "$PACK_JSON" | node -e 'const chunks=[]; process.stdin.on("data", (chunk) => chunks.push(chunk)); process.stdin.on("end", () => { const parsed = JSON.parse(Buffer.concat(chunks).toString("utf8")); const first = Array.isArray(parsed) ? parsed[0] : null; if (!first || typeof first.filename !== "string" || !first.filename) { process.exit(1); } process.stdout.write(first.filename); });')"
+          PACK_OUTPUT="$RUNNER_TEMP/npm-pack-output.txt"
+          npm pack --json 2>&1 | tee "$PACK_OUTPUT"
+          PACK_PATH="$(node - "$PACK_OUTPUT" <<'NODE'
+          const fs = require("node:fs");
+          const input = fs.readFileSync(process.argv[2], "utf8");
+
+          function arrayEndFrom(start) {
+            let depth = 0;
+            let inString = false;
+            let escape = false;
+            for (let i = start; i < input.length; i += 1) {
+              const char = input[i];
+              if (inString) {
+                if (escape) {
+                  escape = false;
+                } else if (char === "\\") {
+                  escape = true;
+                } else if (char === "\"") {
+                  inString = false;
+                }
+                continue;
+              }
+              if (char === "\"") {
+                inString = true;
+              } else if (char === "[") {
+                depth += 1;
+              } else if (char === "]") {
+                depth -= 1;
+                if (depth === 0) {
+                  return i + 1;
+                }
+              }
+            }
+            return -1;
+          }
+
+          for (let start = input.indexOf("["); start !== -1; start = input.indexOf("[", start + 1)) {
+            const end = arrayEndFrom(start);
+            if (end === -1) {
+              continue;
+            }
+            try {
+              const parsed = JSON.parse(input.slice(start, end));
+              const first = Array.isArray(parsed) ? parsed[0] : null;
+              if (first && typeof first.filename === "string" && first.filename) {
+                process.stdout.write(first.filename);
+                process.exit(0);
+              }
+            } catch {
+              // Keep scanning; npm lifecycle output can legally precede the JSON.
+            }
+          }
+
+          console.error("Could not find npm pack --json output with a filename.");
+          process.exit(1);
+          NODE
+          )"
           if [[ -z "$PACK_PATH" || ! -f "$PACK_PATH" ]]; then
             echo "npm pack did not produce a tarball file." >&2
             exit 1

CHANGELOG.md

@@ -6,31 +6,114 @@ Docs: https://docs.openclaw.ai
 
 ### Changes
 
-- iOS: pin release versioning to an explicit CalVer in `apps/ios/version.json`, keep TestFlight iteration on the same short version until maintainers intentionally promote the next gateway version, and add the documented `pnpm ios:version:pin -- --from-gateway` workflow for release trains. (#63001) Thanks @ngutman.
-- Plugins/provider-auth: let provider manifests declare `providerAuthAliases` so provider variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices without core-specific wiring.
-- Memory/dreaming: add a grounded REM backfill lane with historical `rem-harness --path`, diary commit, and reset flows so old daily notes can be replayed safely into `DREAMS.md`. Thanks @mbelinky.
-- Memory/dreaming: harden grounded diary extraction so `What Happened`, `Reflections`, and durable candidates suppress operational noise and preserve more atomic lasting facts. Thanks @mbelinky.
-- Control UI/dreaming: add a structured diary view with timeline navigation, backfill/reset controls, and traceable dreaming summaries. Thanks @mbelinky.
+- Memory/Active Memory: add a new optional Active Memory plugin that gives OpenClaw a dedicated memory sub-agent right before the main reply, so ongoing chats can automatically pull in relevant preferences, context, and past details without making users remember to manually say "remember this" or "search memory" first. Includes configurable message/recent/full context modes, live `/verbose` inspection, advanced prompt/thinking overrides for tuning, and opt-in transcript persistence for debugging.
+- macOS/Talk: add an experimental local MLX speech provider for Talk Mode, with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback. (#63539) Thanks @ImLukeF.
+- Docs i18n: chunk raw doc translation, reject truncated tagged outputs, avoid ambiguous body-only wrapper unwrapping, and recover from terminated Pi translation sessions without changing the default `openai/gpt-5.4` path. (#62969, #63808) Thanks @hxy91819.
+- QA/testing: add a `--runner multipass` lane for `openclaw qa suite` so repo-backed QA scenarios can run inside a disposable Linux VM and write back the usual report, summary, and VM logs. (#63426) Thanks @shakkernerd.
+- Gateway: split startup and runtime seams so gateway lifecycle sequencing, reload state, and shutdown behavior stay easier to maintain without changing observed behavior. (#63975) Thanks @gumadeiras.
+- Control UI/webchat: normalize assistant `MEDIA:`/reply/voice directives into structured bubble rendering, rename the unreleased rich web shortcode to `[embed ...]`, and surface session runtime roots so hosted web content is written to the correct document path instead of guessed local files.
+
+### Fixes
+
+- fix(agents): guard nodes tool outPath against workspace boundary [AI-assisted]. (#63551) Thanks @pgondhi987.
+- fix(qqbot): enforce media storage boundary for all outbound local file paths [AI]. (#63271) Thanks @pgondhi987.
+- iMessage/self-chat: distinguish normal DM outbound rows from true self-chat using `destination_caller_id` plus chat participants, while preserving multi-handle self-chat aliases so outbound DM replies stop looping back as inbound messages. (#61619) Thanks @neeravmakwana.
+- fix(browser): auto-generate browser control auth token for none/trusted-proxy modes [AI]. (#63280) Thanks @pgondhi987.
+- fix(exec): replace TOCTOU check-then-read with atomic pinned-fd open in script preflight [AI]. (#62333) Thanks @pgondhi987.
+- WhatsApp/auto-reply: keep inbound reply, media, and composing sends on the current socket across reconnects, wait through reconnect gaps, and retry timeout-only send failures without dropping the active socket ref. (#62892) Thanks @mcaxtr.
+- Config/plugins: let config writes keep disabled plugin entries without forcing required plugin config schemas or crashing raw plugin validation, so slot switches and similar plugin-state updates persist cleanly. (#63296) Thanks @fuller-stack-dev.
+- WhatsApp/outbound queue: drain queued WhatsApp deliveries when the listener reconnects without dropping reconnect-delayed sends after a special TTL or rewriting retry history, so disconnect-window outbound messages can recover once the channel is ready again. (#46299) Thanks @manuel-claw.
+- Tools/web_fetch: add an opt-in `tools.web.fetch.ssrfPolicy.allowRfc2544BenchmarkRange` config so fake-IP proxy environments that resolve public sites into `198.18.0.0/15` can use `web_fetch` without weakening the default SSRF block. (#61830) Thanks @xing-xing-coder.
+- Daemon/gateway install: preserve safe custom service env vars on forced reinstall, merge prior custom PATH segments behind the managed service PATH, and stop removed managed env keys from persisting as custom carryover. (#63136) Thanks @WarrenJones.
+- Config validation: surface the actual offending field for strict-schema union failures in bindings, including top-level unexpected keys on the matching ACP branch. (#40841) Thanks @Hollychou924.
+- QQBot/security: replace raw `fetch()` in the image-size probe with SSRF-guarded `fetchRemoteMedia`, fix `resolveRepoRoot()` to walk up to `.git` instead of hardcoding two parent levels, and refresh the raw-fetch allowlist to match the corrected scan. (#63495) Thanks @dims.
+- Cron/scheduling: treat `nextRunAtMs <= 0` as invalid across cron update, maintenance, timer, and stale-delivery paths so corrupted zero timestamps self-heal instead of causing immediate runs or skipped deliveries. (#63507) Thanks @WarrenJones.
+- Status: show configured fallback models in `/status` and shared session status cards so per-agent fallback configuration is visible before a live failover happens. (#33111) Thanks @AnCoSONG.
+- Fireworks/FirePass: disable Kimi K2.5 Turbo reasoning output by forcing thinking off on the FirePass path and hardening the provider wrapper so hidden reasoning no longer leaks into visible replies. (#63607) Thanks @frankekn.
+- Sessions/model selection: preserve catalog-backed session model labels and keep already-qualified session model refs stable when catalog metadata is unavailable, so Control UI model selection survives reloads without bogus provider-prefixed values. (#61382) Thanks @Mule-ME.
+- Gateway/startup: keep WebSocket RPC available while channels and plugin sidecars start, hold `chat.history` unavailable until startup sidecars finish so synchronous history reads cannot stall startup (reported in #63450), refresh advertised gateway methods after deferred plugin reloads, and enforce the pre-auth WebSocket upgrade budget before the no-handler 503 path so upgrade floods cannot bypass connection limits during that window. (#63480) Thanks @neeravmakwana.
+- Dreaming/cron: reconcile managed dreaming cron from the resolved gateway startup config so boot-time schedule recovery respects the configured cadence and timezone. (#63873) Thanks @mbelinky.
+- Dreaming/cron: keep managed dreaming cron reconciled after startup by rechecking lifecycle state during runtime config/plugin changes, recovering missing managed jobs, and applying cadence/timezone updates idempotently. (#63929) Thanks @mbelinky.
+- Gateway/tailscale: start Tailscale exposure and the gateway update check before awaiting channel and plugin sidecar startup so remote operators are not locked out when startup sidecars stall.
+- QQBot/streaming: make block streaming configurable per QQ bot account via `streaming.mode` (`"partial"` | `"off"`, default `"partial"`) instead of hardcoding it off, so responses can be delivered incrementally. (#63746)
+- Dreaming/gateway: require `operator.admin` for persistent `/dreaming on|off` changes and treat missing gateway client scopes as unprivileged instead of silently allowing config writes. (#63872) Thanks @mbelinky.
+- Matrix/multi-account: keep room-level `account` scoping, inherited room overrides, and implicit account selection consistent across top-level default auth, named accounts, and cached-credential env setups. (#58449) thanks @Daanvdplas and @gumadeiras.
+- Gateway/pairing: prefer explicit QR bootstrap auth over earlier Tailscale auth classification so iOS `/pair qr` silent bootstrap pairing does not fall through to `pairing required`. (#59232) Thanks @ngutman.
+- WhatsApp/outbound queue: drain same-account pending WhatsApp deliveries when the listener reconnects, including fresh queued sends that are already retry-eligible, so reconnects recover deliverable outbound messages without waiting for another gateway restart. (#63916) Thanks @mcaxtr.
+- Config/Discord: coerce safe integer numeric Discord IDs to strings during config validation, keep unsafe or precision-losing numeric snowflakes rejected, and align `openclaw doctor` repair guidance with the same fail-closed behavior. (#45125) Thanks @moliendocode.
+- Gateway/sessions: scope bare `sessions.create` aliases like `main` to the requested agent while preserving the canonical `global` and `unknown` sentinel keys. (#58207) thanks @jalehman.
+- `/context detail` now compares the tracked prompt estimate with cached context usage and surfaces untracked provider/runtime overhead when present. (#28391) thanks @ImLukeF.
+- Gateway/session reset: emit the typed `before_reset` hook for gateway `/new` and `/reset`, preserving reset-hook behavior even when the previous transcript has already been archived. (#53872) thanks @VACInc
+- Plugins/commands: pass the active host `sessionKey` into plugin command contexts, and include `sessionId` when it is already available from the active session entry, so bundled and third-party commands can resolve the current conversation reliably. (#59044) Thanks @jalehman.
+- Agents/auth: honor `models.providers.*.authHeader` for pi embedded runner model requests by injecting `Authorization: Bearer <apiKey>` when requested. (#54390) Thanks @lndyzwdxhs.
+- Dreaming/cron: stop runtime cron reconciliation on ordinary user turns and only recover managed dreaming cron state during heartbeat-triggered dreaming checks, so unrelated chat traffic does not silently recreate removed jobs. (#63938) Thanks @mbelinky.
+- UI/compaction: keep the compaction indicator in a retry-pending state until the run actually finishes, so the UI does not show `Context compacted` before compaction actually finishes. (#55132) Thanks @mpz4life.
+- Cron/tool schemas: keep cron tool schemas strict-model-friendly while still preserving `failureAlert=false`, nullable `agentId`/`sessionKey`, and flattened add/update recovery for the newly exposed cron job fields. (#55043) Thanks @brunolorente.
+- BlueBubbles/config: accept `enrichGroupParticipantsFromContacts` in the core strict config schema so gateways no longer fail validation or startup when the BlueBubbles plugin writes that field. (#56889) Thanks @zqchris.
+- Agents/failover: classify AbortError and stream-abort messages as timeout so Ollama NDJSON stream aborts stop showing `reason=unknown` in model fallback logs. (#58324) Thanks @yelog
+- Exec approvals: route Slack, Discord, and Telegram approvals through the shared channel approval-capability path so native approval auth, delivery, and `/approve` handling stay aligned across channels while preserving Telegram session-key agent filtering. (#58634) thanks @gumadeiras
+- Matrix/runtime: resolve the verification/bootstrap runtime from a distinct packaged Matrix entry so global npm installs stop failing on crypto bootstrap with missing-module or recursive runtime alias errors. (#59249) Thanks @gumadeiras.
+- Matrix/streaming: preserve ordered block flushes before tool, message, and agent boundaries, add explicit `channels.matrix.blockStreaming` opt-in so Matrix `streaming: "off"` stays final-only by default, and move MiniMax plain-text final handling into the MiniMax provider runtime instead of the shared core heuristic. (#59266) thanks @gumadeiras
+- Gateway/agents: fix stale run-context TTL cleanup so the new maintenance sweep compiles and resets orphaned run sequence state correctly. (#52731) thanks @artwalker
+- Memory/lancedb: accept `dreaming` config when `memory-lancedb` owns the memory slot so Dreaming surfaces can read slot-owner settings without schema rejection. (#63874) Thanks @mbelinky.
+- Control UI/dreaming: keep the Dreaming trace area contained and scrollable so overlays no longer cover tabs or blow out the page layout. (#63875) Thanks @mbelinky.
+- Dreaming/diary: add idempotent narrative subagent runs, preserve restrictive `DREAMS.md` permissions during atomic writes, and surface temp cleanup failures so repeated sweeps do not double-run the same narrative request or silently weaken diary safety. (#63876) Thanks @mbelinky.
+- Heartbeats/sessions: remove stale accumulated isolated heartbeat session keys when the next tick converges them back to the canonical sibling, so repaired sessions stop showing orphaned `:heartbeat:heartbeat` variants in session listings. (#59606) Thanks @rogerdigital.
+- Cron/Telegram: collapse isolated announce delivery to the final assistant-visible text only for Telegram targets, while preserving existing multi-message direct delivery semantics for other channels. (#63228) Thanks @welfo-beo.
+- Gateway/thread routing: preserve Slack, Telegram, and Mattermost thread-child delivery targets so bound subagent completion messages land in the originating thread instead of top-level channels. (#54840) Thanks @yzzymt.
+- ACP/stream relay: pass parent delivery context to ACP stream relay system events so `streamTo="parent"` updates route to the correct thread or topic instead of falling back to the main DM. (#57056) Thanks @pingren.
+- Agents/sessions: preserve announce `threadId` when `sessions.list` fallback rehydrates agent-to-agent announce targets so final announce messages stay in the originating thread/topic. (#63506) Thanks @SnowSky1.
+- Browser/plugin SDK: route browser auth, profile, host-inspection, and doctor readiness helpers through browser plugin public facades so core compatibility helpers stop carrying duplicate runtime implementations. (#63957) Thanks @joshavant.
+- Browser/act: centralize `/act` request normalization and execution dispatch while adding stable machine-readable route-level error codes for invalid requests, selector misuse, evaluate-disabled gating, target mismatch, and existing-session unsupported actions. (#63977) Thanks @joshavant.
+- Windows/exec: settle supervisor waits from child exit state after stdout and stderr drain even when `close` never arrives, so CLI commands stop hanging or dying with forced `SIGKILL` on Windows. (#64072) Thanks @obviyus.
+
+## 2026.4.9
+
+### Changes
+
+- Memory/dreaming: add a grounded REM backfill lane with historical `rem-harness --path`, diary commit/reset flows, cleaner durable-fact extraction, and live short-term promotion integration so old daily notes can replay into Dreams and durable memory without a second memory stack. Thanks @mbelinky.
+- Control UI/dreaming: add a structured diary view with timeline navigation, backfill/reset controls, traceable dreaming summaries, and a grounded Scene lane with promotion hints plus a safe clear-grounded action for staged backfill signals. (#63395) Thanks @mbelinky.
+- QA/lab: add character-vibes evaluation reports with model selection and parallel runs so live QA can compare candidate behavior faster.
+- Plugins/provider-auth: let provider manifests declare `providerAuthAliases` so provider variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices without core-specific wiring.
+- iOS: pin release versioning to an explicit CalVer in `apps/ios/version.json`, keep TestFlight iteration on the same short version until maintainers intentionally promote the next gateway version, and add the documented `pnpm ios:version:pin -- --from-gateway` workflow for release trains. (#63001) Thanks @ngutman.
 
 ### Fixes
 
-- Control UI: guard stale session-history reloads during fast session switches so the selected session and rendered transcript stay in sync. (#62975) Thanks @scoootscooob.
-- Slack/media: preserve bearer auth across same-origin `files.slack.com` redirects while still stripping it on cross-origin Slack CDN hops, so `url_private_download` image attachments load again. (#62960) Thanks @vincentkoc.
-- Gateway/node exec events: mark remote node `exec.started`, `exec.finished`, and `exec.denied` summaries as untrusted system events and sanitize node-provided command/output/reason text before enqueueing them, so remote node output cannot inject trusted `System:` content into later turns. (#62659) Thanks @eleqtrizit.
-- Agents/timeouts: make the LLM idle timeout inherit `agents.defaults.timeoutSeconds` when configured, disable the unconfigured idle watchdog for cron runs, and point idle-timeout errors at `agents.defaults.llm.idleTimeoutSeconds`. Thanks @drvoss.
-- Security/dotenv: expand workspace `.env` filtering to block runtime-control variables like gateway routing, ClawHub endpoints/tokens, browser executable overrides, and skip/disable control families, so untrusted repositories cannot steer OpenClaw runtime behavior through repo-local dotenv files. (#62660) Thanks @eleqtrizit.
-- Agents/failover: classify Z.ai vendor code `1311` as billing and `1113` as auth, including long wrapped `1311` payloads, so these errors stop falling through to generic failover handling. (#49552) Thanks @1bcMax.
-- Browser/security: block browser-control module override and skip-server env vars from untrusted workspace `.env` files, and reject unsafe URL-style browser control override specifiers before lazy loading, so repo-local dotenv state cannot steer browser control module loading. (#62663) Thanks @eleqtrizit.
-- QQBot/media-tags: support HTML entity-encoded angle brackets (`&lt;`/`&gt;`) in media-tag regexes so entity-escaped `<qqimg>` tags from upstream are correctly parsed and normalized. (#60493) Thanks @ylc0919.
-- npm packaging: mirror bundled Slack, Telegram, Discord, and Feishu channel runtime deps at the root and harden published-install verification so fresh installs fail fast on manifest drift instead of missing-module crashes. (#63065) Thanks @scoootscooob.
-- npm packaging: derive required root runtime mirrors from bundled plugin manifests and built root chunks, then install packed release tarballs without the repo `node_modules` so release checks catch missing plugin deps before publish.
-- Reply/doctor: resolve reply-run SecretRefs before preflight helpers touch config, surface gateway OAuth reauth failures to users, and make `openclaw doctor` call out exact reauth commands.
-- Android/pairing: clear stale setup-code auth on new QR scans, bootstrap operator and node sessions from fresh pairing, prefer stored device tokens after bootstrap handoff, and pause pairing auto-retry while the app is backgrounded so scan-once Android pairing recovers reliably again. (#63199) Thanks @obviyus.
-- Auto-reply/NO_REPLY: strip glued leading `NO_REPLY` tokens before reply normalization and ACP-visible streaming so silent sentinel text no longer leaks into user-visible replies while preserving substantive `NO_REPLY ...` text. Thanks @frankekn.
-- Gateway/sessions: clear auto-fallback-pinned model overrides on `/reset` and `/new` while still preserving explicit user model selections, including legacy sessions created before override-source tracking existed. (#63155) Thanks @frankekn.
-- Codex CLI: pass OpenClaw's system prompt through Codex's `model_instructions_file` config override so fresh Codex CLI sessions receive the same prompt guidance as Claude CLI sessions.
-- Matrix/gateway: wait for Matrix sync readiness before marking startup successful, keep Matrix background handler failures contained, and route fatal Matrix sync stops through channel-level restart handling instead of crashing the whole gateway. (#62779) Thanks @gumadeiras.
 - Browser/security: re-run blocked-destination safety checks after interaction-driven main-frame navigations from click, evaluate, hook-triggered click, and batched action flows, so browser interactions cannot bypass the SSRF quarantine when they land on forbidden URLs. (#63226) Thanks @eleqtrizit.
+- Security/dotenv: block runtime-control env vars plus browser-control override and skip-server env vars from untrusted workspace `.env` files, and reject unsafe URL-style browser control override specifiers before lazy loading. (#62660, #62663) Thanks @eleqtrizit.
+- Gateway/node exec events: mark remote node `exec.started`, `exec.finished`, and `exec.denied` summaries as untrusted system events and sanitize node-provided command/output/reason text before enqueueing them, so remote node output cannot inject trusted `System:` content into later turns. (#62659) Thanks @eleqtrizit.
+- Plugins/onboarding auth choices: prevent untrusted workspace plugins from colliding with bundled provider auth-choice ids during non-interactive onboarding, so bundled provider setup keeps operator secrets out of untrusted workspace plugin handlers unless those plugins are explicitly trusted. (#62368) Thanks @pgondhi987.
+- Security/dependency audit: force `basic-ftp` to `5.2.1` for the CRLF command-injection fix and bump Hono plus `@hono/node-server` in production resolution paths.
+- Android/pairing: clear stale setup-code auth on new QR scans, bootstrap operator and node sessions from fresh pairing, prefer stored device tokens after bootstrap handoff, and pause pairing auto-retry while the app is backgrounded so scan-once Android pairing recovers reliably again. (#63199) Thanks @obviyus.
+- Matrix/gateway: wait for Matrix sync readiness before marking startup successful, keep Matrix background handler failures contained, and route fatal Matrix sync stops through channel-level restart handling instead of crashing the whole gateway. (#62779) Thanks @gumadeiras.
+- Slack/media: preserve bearer auth across same-origin `files.slack.com` redirects while still stripping it on cross-origin Slack CDN hops, so `url_private_download` image attachments load again. (#62960) Thanks @vincentkoc.
+- Reply/doctor: use the active runtime snapshot for queued reply runs, resolve reply-run SecretRefs before preflight helpers touch config, surface gateway OAuth reauth failures to users, and make `openclaw doctor` call out exact reauth commands. (#62693, #63217) Thanks @mbelinky.
+- Control UI: guard stale session-history reloads during fast session switches so the selected session and rendered transcript stay in sync. (#62975) Thanks @scoootscooob.
+- Gateway/chat: suppress exact and streamed `ANNOUNCE_SKIP` / `REPLY_SKIP` control replies across live chat updates and history sanitization so internal agent-to-agent control tokens no longer leak into user-facing gateway chat surfaces. (#51739) Thanks @Pinghuachiu.
+- Auto-reply/NO_REPLY: strip glued leading `NO_REPLY` tokens before reply normalization and ACP-visible streaming so silent sentinel text no longer leaks into user-visible replies while preserving substantive `NO_REPLY ...` text. Thanks @frankekn.
+- Sessions/routing: preserve established external routes on inter-session announce traffic so `sessions_send` follow-ups do not steal delivery from Telegram, Discord, or other external channels. (#58013) Thanks @duqaXxX.
+- Gateway/sessions: clear auto-fallback-pinned model overrides on `/reset` and `/new` while still preserving explicit user model selections, including legacy sessions created before override-source tracking existed. (#63155) Thanks @frankekn.
+- Slack/ACP: treat Slack ACP block replies as visible delivered output so OpenClaw stops re-sending the final fallback text after Slack already rendered the reply. (#62858) Thanks @gumadeiras.
+- Slack/partial streaming: key turn-local dedupe by dispatch kind and keep the final fallback reply path active when preview finalization fails so stale preview text cannot suppress the actual final answer. (#62859) Thanks @gumadeiras.
+- Matrix/doctor: migrate legacy `channels.matrix.dm.policy: "trusted"` configs back to compatible DM policies during `openclaw doctor --fix`, preserving explicit `allowFrom` boundaries as `allowlist` and defaulting empty legacy configs to `pairing`. (#62942) Thanks @lukeboyett.
+- npm packaging: mirror bundled channel runtime deps, stage Nostr runtime deps, derive required root mirrors from manifests and built chunks, and test packed release tarballs without repo `node_modules` so fresh installs fail fast on missing plugin deps instead of crashing at runtime. (#63065) Thanks @scoootscooob.
+- QA/live auth: fail fast when live QA scenarios hit classified auth or runtime failure replies, including raw scenario wait paths, and sanitize missing-key guidance so gateway auth problems surface as actionable errors instead of timeouts. (#63333) Thanks @shakkernerd.
+- Providers/OpenAI: default missing reasoning effort to `high` on OpenAI Responses, WebSocket, and compatible completions transports, while still honoring explicit per-run reasoning levels.
+- Providers/Ollama: allow Ollama models using the native `api: "ollama"` path to optionally display thinking output when `/think` is set to a non-off level. (#62712) Thanks @hoyyeva.
+- Codex CLI: pass OpenClaw's system prompt through Codex's `model_instructions_file` config override so fresh Codex CLI sessions receive the same prompt guidance as Claude CLI sessions.
+- Auth/profiles: persist explicit auth-profile upserts directly and skip external CLI sync for local writes so profile changes are saved without stale external credential state.
+- Agents/timeouts: make the LLM idle timeout inherit `agents.defaults.timeoutSeconds` when configured, disable the unconfigured idle watchdog for cron runs, and point idle-timeout errors at `agents.defaults.llm.idleTimeoutSeconds`. Thanks @drvoss.
+- Agents/failover: classify Z.ai vendor code `1311` as billing and `1113` as auth, including long wrapped `1311` payloads, so these errors stop falling through to generic failover handling. (#49552) Thanks @1bcMax.
+- QQBot/media-tags: support HTML entity-encoded angle brackets (`&lt;`/`&gt;`), URL slashes in attributes, and self-closing media tags so upstream `<qqimg>` payloads are correctly parsed and normalized. (#60493) Thanks @ylc0919.
+- Memory/dreaming: harden grounded backfill inputs, diary writes, status payloads, and diary action classification by preserving source-day labels, rejecting missing or symlinked targets cleanly, normalizing diary headings in gateway backfills, and tightening claim splitting plus diary source metadata. Thanks @mbelinky.
+- Memory/dreaming: accept embedded heartbeat trigger tokens so light and REM dreaming still run when runtime wrappers include extra heartbeat text.
+- Android/manual connect: allow blank port input only for TLS manual gateway endpoints so standard HTTPS Tailscale hosts default to `443` without silently changing cleartext manual connects. (#63134) Thanks @Tyler-RNG.
+- Windows/update: add heap headroom to Windows `pnpm build` steps during dev updates so update preflight builds stop failing on low default Node memory.
+- Plugin SDK: export the channel plugin base and web-search config contract through the public package so plugins can use them without private imports.
+- Plugins/contracts: keep test-only helpers out of production contract barrels, load shared contract harnesses through bundled test surfaces, and harden guardrails so indirect re-exports and canonical `*.test.ts` files stay blocked. (#63311) Thanks @altaywtf.
+- Control UI/models: preserve provider-qualified refs for OpenRouter catalog models whose ids already contain slashes so picker selections submit allowlist-compatible model refs instead of dropping the `openrouter/` prefix. (#63416) Thanks @sallyom.
+- Plugin SDK/command auth: split command status builders onto the lightweight `openclaw/plugin-sdk/command-status` subpath while preserving deprecated `command-auth` compatibility exports, so auth-only plugin imports no longer pull status/context warmup into CLI onboarding paths. (#63174) Thanks @hxy91819.
+- Wizard/plugin config: coerce integer-typed plugin config fields from interactive text input so integer schema values persist as numbers instead of failing validation. (#63346) Thanks @jalehman.
 
 ## 2026.4.8
 
@@ -81,7 +164,6 @@ Docs: https://docs.openclaw.ai
 - TUI: route `/status` through the shared session-status command, keep commentary hidden in history, strip raw envelope metadata from async command notices, preserve fallback streaming before per-attempt failures finalize, and restore Kitty keyboard state on exit or fatal crashes. (#49130, #59985, #60043, #61463) Thanks @biefan and contributors.
 - iOS/Watch exec approvals: keep Apple Watch review and approval recovery working while the iPhone is locked or backgrounded, including reconnect recovery, pending approval persistence, notification cleanup, and APNs-backed watch refresh recovery. (#61757) Thanks @ngutman.
 - Agents/context overflow: combine oversized and aggregate tool-result recovery in one pass and restore a total-context overflow backstop so recoverable sessions retry instead of failing early. (#61651) Thanks @Takhoffman.
-- Agents/OpenAI: default missing reasoning effort to `high` on OpenAI Responses, WebSocket, and compatible completions transports, while still honoring explicit per-run reasoning levels.
 - Auth/OpenAI Codex OAuth: reload fresh on-disk credentials inside the locked refresh path and retry once after `refresh_token_reused` rotates only the stored refresh token, so relogin/restart recovery stops getting stuck on stale cached auth state. Thanks @owen-ever.
 - Auth/OpenAI Codex OAuth: keep native `/model ...@profile` selections on the target session and honor explicit user-locked auth profiles even when per-agent auth order excludes them. (#62744) Thanks @jalehman.
 - Providers/Anthropic: preserve thinking blocks for Claude Opus 4.5+, Sonnet 4.5+, and newer Claude 4-family models so prompt-cache prefixes keep matching, and skip `service_tier` injection on OAuth-authenticated stream wrapper requests so Claude OAuth streaming stops failing with HTTP 401. (#60356, #61793)
@@ -92,7 +174,6 @@ Docs: https://docs.openclaw.ai
 - Gateway tool/exec config: block model-facing `gateway config.apply` and `config.patch` writes from changing exec approval paths such as `safeBins`, `safeBinProfiles`, `safeBinTrustedDirs`, and `strictInlineEval`, while still allowing unchanged structured values through. (#62001) Thanks @eleqtrizit.
 - Host exec/env sanitization: block dangerous Java, Rust, Cargo, Git, Kubernetes, cloud credential, config-path, and Helm env overrides so host-run tools cannot be redirected to attacker-chosen code, config, credentials, or repository state. (#59119, #62002, #62291) Thanks @eleqtrizit and contributors.
 - Commands/allowlist: require owner authorization for `/allowlist add` and `/allowlist remove` before channel resolution, so non-owner but command-authorized senders can no longer persistently rewrite allowlist policy state. (#62383) Thanks @pgondhi987.
-- Plugins/onboarding auth choices: prevent untrusted workspace plugins from colliding with bundled provider auth-choice ids during non-interactive onboarding, so bundled provider setup keeps operator secrets out of untrusted workspace plugin handlers unless those plugins are explicitly trusted. (#62368) Thanks @pgondhi987.
 - Feishu/docx uploads: honor `tools.fs.workspaceOnly` for local `upload_file` and `upload_image` paths by forwarding workspace-constrained `localRoots` into the media loader, so docx uploads can no longer read host-local files outside the workspace when workspace-only mode is active. (#62369) Thanks @pgondhi987.
 - Network/fetch guard: drop request bodies and body-describing headers on cross-origin `307` and `308` redirects by default, so attacker-controlled redirect hops cannot receive secret-bearing POST payloads from SSRF-guarded fetch flows unless a caller explicitly opts in. (#62357) Thanks @pgondhi987.
 - Browser/SSRF: treat main-frame `document` redirect hops as navigations even when Playwright does not flag them as `isNavigationRequest()`, so strict private-network blocking still stops forbidden redirect pivots before the browser reaches the internal target. (#62355) Thanks @pgondhi987.
@@ -149,9 +230,10 @@ Docs: https://docs.openclaw.ai
 - Agents/model resolution: let explicit `openai-codex/gpt-5.4` selection prefer provider runtime metadata when it reports a larger context window, keeping configured Codex runs aligned with the live provider limits. (#62694) Thanks @ruclaw7.
 - Agents/model resolution: keep explicit-model runtime comparisons on the configured workspace plugin registry, so workspace-installed providers do not silently fall back to stale explicit metadata during runtime model lookup.
 - Providers/Z.AI: default onboarding and endpoint detection to GLM-5.1 instead of GLM-5. (#61998) Thanks @serg0x.
-- Reply execution: prefer the active runtime snapshot over stale queued reply config during embedded reply and follow-up execution so SecretRef-backed reply turns stop crashing after secrets have already resolved. (#62693) Thanks @mbelinky.
-- Android/manual connect: allow blank port input only for TLS manual gateway endpoints so standard HTTPS Tailscale hosts default to `443` without silently changing cleartext manual connects. (#63134) Thanks @Tyler-RNG.
-- Matrix/agents: hide owner-only `set-profile` from embedded agent channel-action discovery so non-owner runs stop advertising profile updates they cannot execute. (#62662) Thanks @eleqtrizit.
+- Cron/isolated: resolve auth profiles without treating every isolated run as a brand-new auth session, so profile-based providers (for example OpenRouter) keep a stable credential choice instead of rotating or ignoring stored keys. (#62783) Thanks @neeravmakwana.
+- CLI/tasks: `openclaw tasks cancel` now records operator cancellation for CLI runtime tasks instead of returning "Task runtime does not support cancellation yet", so stuck `running` CLI tasks can be cleared. (#62419) Thanks @neeravmakwana.
+- Sessions/context: resolve context window limits using the active provider plus model (not bare model id alone) when persisting session usage, applying inline directives, and sizing memory-flush / preflight compaction thresholds, so duplicate model ids across providers no longer leak the wrong `contextTokens` into the session store or `/status`. (#62472) Thanks @neeravmakwana.
+- Channels/setup: exclude workspace shadow entries from channel setup catalog lookups and align trust checks with auto-enable so workspace-scoped overrides no longer bypass the trusted catalog. (`GHSA-82qx-6vj7-p8m2`) Thanks @zsxsoft.
 
 ## 2026.4.5
 

appcast.xml

@@ -2,6 +2,63 @@
 <rss xmlns:sparkle="http://www.andymatuschak.org/xml-namespaces/sparkle" version="2.0">
     <channel>
         <title>OpenClaw</title>
+        <item>
+            <title>2026.4.9</title>
+            <pubDate>Thu, 09 Apr 2026 02:38:08 +0000</pubDate>
+            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
+            <sparkle:version>2026040990</sparkle:version>
+            <sparkle:shortVersionString>2026.4.9</sparkle:shortVersionString>
+            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
+            <description><![CDATA[<h2>OpenClaw 2026.4.9</h2>
+<h3>Changes</h3>
+<ul>
+<li>Memory/dreaming: add a grounded REM backfill lane with historical <code>rem-harness --path</code>, diary commit/reset flows, cleaner durable-fact extraction, and live short-term promotion integration so old daily notes can replay into Dreams and durable memory without a second memory stack. Thanks @mbelinky.</li>
+<li>Control UI/dreaming: add a structured diary view with timeline navigation, backfill/reset controls, traceable dreaming summaries, and a grounded Scene lane with promotion hints plus a safe clear-grounded action for staged backfill signals. (#63395) Thanks @mbelinky.</li>
+<li>QA/lab: add character-vibes evaluation reports with model selection and parallel runs so live QA can compare candidate behavior faster.</li>
+<li>Plugins/provider-auth: let provider manifests declare <code>providerAuthAliases</code> so provider variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices without core-specific wiring.</li>
+<li>iOS: pin release versioning to an explicit CalVer in <code>apps/ios/version.json</code>, keep TestFlight iteration on the same short version until maintainers intentionally promote the next gateway version, and add the documented <code>pnpm ios:version:pin -- --from-gateway</code> workflow for release trains. (#63001) Thanks @ngutman.</li>
+</ul>
+<h3>Fixes</h3>
+<ul>
+<li>Browser/security: re-run blocked-destination safety checks after interaction-driven main-frame navigations from click, evaluate, hook-triggered click, and batched action flows, so browser interactions cannot bypass the SSRF quarantine when they land on forbidden URLs. (#63226) Thanks @eleqtrizit.</li>
+<li>Security/dotenv: block runtime-control env vars plus browser-control override and skip-server env vars from untrusted workspace <code>.env</code> files, and reject unsafe URL-style browser control override specifiers before lazy loading. (#62660, #62663) Thanks @eleqtrizit.</li>
+<li>Gateway/node exec events: mark remote node <code>exec.started</code>, <code>exec.finished</code>, and <code>exec.denied</code> summaries as untrusted system events and sanitize node-provided command/output/reason text before enqueueing them, so remote node output cannot inject trusted <code>System:</code> content into later turns. (#62659) Thanks @eleqtrizit.</li>
+<li>Plugins/onboarding auth choices: prevent untrusted workspace plugins from colliding with bundled provider auth-choice ids during non-interactive onboarding, so bundled provider setup keeps operator secrets out of untrusted workspace plugin handlers unless those plugins are explicitly trusted. (#62368) Thanks @pgondhi987.</li>
+<li>Security/dependency audit: force <code>basic-ftp</code> to <code>5.2.1</code> for the CRLF command-injection fix and bump Hono plus <code>@hono/node-server</code> in production resolution paths.</li>
+<li>Android/pairing: clear stale setup-code auth on new QR scans, bootstrap operator and node sessions from fresh pairing, prefer stored device tokens after bootstrap handoff, and pause pairing auto-retry while the app is backgrounded so scan-once Android pairing recovers reliably again. (#63199) Thanks @obviyus.</li>
+<li>Matrix/gateway: wait for Matrix sync readiness before marking startup successful, keep Matrix background handler failures contained, and route fatal Matrix sync stops through channel-level restart handling instead of crashing the whole gateway. (#62779) Thanks @gumadeiras.</li>
+<li>Slack/media: preserve bearer auth across same-origin <code>files.slack.com</code> redirects while still stripping it on cross-origin Slack CDN hops, so <code>url_private_download</code> image attachments load again. (#62960) Thanks @vincentkoc.</li>
+<li>Reply/doctor: use the active runtime snapshot for queued reply runs, resolve reply-run SecretRefs before preflight helpers touch config, surface gateway OAuth reauth failures to users, and make <code>openclaw doctor</code> call out exact reauth commands. (#62693, #63217) Thanks @mbelinky.</li>
+<li>Control UI: guard stale session-history reloads during fast session switches so the selected session and rendered transcript stay in sync. (#62975) Thanks @scoootscooob.</li>
+<li>Gateway/chat: suppress exact and streamed <code>ANNOUNCE_SKIP</code> / <code>REPLY_SKIP</code> control replies across live chat updates and history sanitization so internal agent-to-agent control tokens no longer leak into user-facing gateway chat surfaces. (#51739) Thanks @Pinghuachiu.</li>
+<li>Auto-reply/NO_REPLY: strip glued leading <code>NO_REPLY</code> tokens before reply normalization and ACP-visible streaming so silent sentinel text no longer leaks into user-visible replies while preserving substantive <code>NO_REPLY ...</code> text. Thanks @frankekn.</li>
+<li>Sessions/routing: preserve established external routes on inter-session announce traffic so <code>sessions_send</code> follow-ups do not steal delivery from Telegram, Discord, or other external channels. (#58013) Thanks @duqaXxX.</li>
+<li>Gateway/sessions: clear auto-fallback-pinned model overrides on <code>/reset</code> and <code>/new</code> while still preserving explicit user model selections, including legacy sessions created before override-source tracking existed. (#63155) Thanks @frankekn.</li>
+<li>Slack/ACP: treat Slack ACP block replies as visible delivered output so OpenClaw stops re-sending the final fallback text after Slack already rendered the reply. (#62858) Thanks @gumadeiras.</li>
+<li>Slack/partial streaming: key turn-local dedupe by dispatch kind and keep the final fallback reply path active when preview finalization fails so stale preview text cannot suppress the actual final answer. (#62859) Thanks @gumadeiras.</li>
+<li>Matrix/doctor: migrate legacy <code>channels.matrix.dm.policy: "trusted"</code> configs back to compatible DM policies during <code>openclaw doctor --fix</code>, preserving explicit <code>allowFrom</code> boundaries as <code>allowlist</code> and defaulting empty legacy configs to <code>pairing</code>. (#62942) Thanks @lukeboyett.</li>
+<li>npm packaging: mirror bundled channel runtime deps, stage Nostr runtime deps, derive required root mirrors from manifests and built chunks, and test packed release tarballs without repo <code>node_modules</code> so fresh installs fail fast on missing plugin deps instead of crashing at runtime. (#63065) Thanks @scoootscooob.</li>
+<li>QA/live auth: fail fast when live QA scenarios hit classified auth or runtime failure replies, including raw scenario wait paths, and sanitize missing-key guidance so gateway auth problems surface as actionable errors instead of timeouts. (#63333) Thanks @shakkernerd.</li>
+<li>Providers/OpenAI: default missing reasoning effort to <code>high</code> on OpenAI Responses, WebSocket, and compatible completions transports, while still honoring explicit per-run reasoning levels.</li>
+<li>Providers/Ollama: allow Ollama models using the native <code>api: "ollama"</code> path to optionally display thinking output when <code>/think</code> is set to a non-off level. (#62712) Thanks @hoyyeva.</li>
+<li>Codex CLI: pass OpenClaw's system prompt through Codex's <code>model_instructions_file</code> config override so fresh Codex CLI sessions receive the same prompt guidance as Claude CLI sessions.</li>
+<li>Auth/profiles: persist explicit auth-profile upserts directly and skip external CLI sync for local writes so profile changes are saved without stale external credential state.</li>
+<li>Agents/timeouts: make the LLM idle timeout inherit <code>agents.defaults.timeoutSeconds</code> when configured, disable the unconfigured idle watchdog for cron runs, and point idle-timeout errors at <code>agents.defaults.llm.idleTimeoutSeconds</code>. Thanks @drvoss.</li>
+<li>Agents/failover: classify Z.ai vendor code <code>1311</code> as billing and <code>1113</code> as auth, including long wrapped <code>1311</code> payloads, so these errors stop falling through to generic failover handling. (#49552) Thanks @1bcMax.</li>
+<li>QQBot/media-tags: support HTML entity-encoded angle brackets (<code>&lt;</code>/<code>&gt;</code>), URL slashes in attributes, and self-closing media tags so upstream <code><qqimg></code> payloads are correctly parsed and normalized. (#60493) Thanks @ylc0919.</li>
+<li>Memory/dreaming: harden grounded backfill inputs, diary writes, status payloads, and diary action classification by preserving source-day labels, rejecting missing or symlinked targets cleanly, normalizing diary headings in gateway backfills, and tightening claim splitting plus diary source metadata. Thanks @mbelinky.</li>
+<li>Memory/dreaming: accept embedded heartbeat trigger tokens so light and REM dreaming still run when runtime wrappers include extra heartbeat text.</li>
+<li>Android/manual connect: allow blank port input only for TLS manual gateway endpoints so standard HTTPS Tailscale hosts default to <code>443</code> without silently changing cleartext manual connects. (#63134) Thanks @Tyler-RNG.</li>
+<li>Windows/update: add heap headroom to Windows <code>pnpm build</code> steps during dev updates so update preflight builds stop failing on low default Node memory.</li>
+<li>Plugin SDK: export the channel plugin base and web-search config contract through the public package so plugins can use them without private imports.</li>
+<li>Plugins/contracts: keep test-only helpers out of production contract barrels, load shared contract harnesses through bundled test surfaces, and harden guardrails so indirect re-exports and canonical <code>*.test.ts</code> files stay blocked. (#63311) Thanks @altaywtf.</li>
+<li>Control UI/models: preserve provider-qualified refs for OpenRouter catalog models whose ids already contain slashes so picker selections submit allowlist-compatible model refs instead of dropping the <code>openrouter/</code> prefix. (#63416) Thanks @sallyom.</li>
+<li>Plugin SDK/command auth: split command status builders onto the lightweight <code>openclaw/plugin-sdk/command-status</code> subpath while preserving deprecated <code>command-auth</code> compatibility exports, so auth-only plugin imports no longer pull status/context warmup into CLI onboarding paths. (#63174) Thanks @hxy91819.</li>
+</ul>
+<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
+]]></description>
+            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.9/OpenClaw-2026.4.9.zip" length="25336730" type="application/octet-stream" sparkle:edSignature="zFKTcKpejPyGEHj6Bdop3EBDfRrHyQMtJzrpVKsIkBq3I/jbTNvsxQveKEy9r7dqkZVsldFYv7eSunP3SUmaAw=="/>
+        </item>
         <item>
             <title>2026.4.8</title>
             <pubDate>Wed, 08 Apr 2026 06:12:50 +0000</pubDate>
@@ -132,253 +189,5 @@
 ]]></description>
             <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.7/OpenClaw-2026.4.7.zip" length="25324827" type="application/octet-stream" sparkle:edSignature="RyFWRz1trE/qvOiInD4vR6je9wx7fUTtHpZ94W8rMlZDByux9CyXOm/Anai96b9KyjTeQyC7YnJp5SRnYY3iCg=="/>
         </item>
-        <item>
-            <title>2026.4.5</title>
-            <pubDate>Mon, 06 Apr 2026 04:55:17 +0100</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>2026040590</sparkle:version>
-            <sparkle:shortVersionString>2026.4.5</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.4.5</h2>
-<h3>Breaking</h3>
-<ul>
-<li>Config: remove legacy public config aliases such as <code>talk.voiceId</code> / <code>talk.apiKey</code>, <code>agents.*.sandbox.perSession</code>, <code>browser.ssrfPolicy.allowPrivateNetwork</code>, <code>hooks.internal.handlers</code>, and channel/group/room <code>allow</code> toggles in favor of the canonical public paths and <code>enabled</code>, while keeping load-time compatibility and <code>openclaw doctor --fix</code> migration support for existing configs. (#60726) Thanks @vincentkoc.</li>
-</ul>
-<h3>Changes</h3>
-<ul>
-<li>Agents/video generation: add the built-in <code>video_generate</code> tool so agents can create videos through configured providers and return the generated media directly in the reply.</li>
-<li>Agents/music generation: ignore unsupported optional hints such as <code>durationSeconds</code> with a warning instead of hard-failing requests on providers like Google Lyria.</li>
-<li>Providers/ComfyUI: add a bundled <code>comfy</code> workflow media plugin for local ComfyUI and Comfy Cloud workflows, including shared <code>image_generate</code>, <code>video_generate</code>, and workflow-backed <code>music_generate</code> support, with prompt injection, optional reference-image upload, live tests, and output download.</li>
-<li>Tools/music generation: add the built-in <code>music_generate</code> tool with bundled Google (Lyria) and MiniMax providers plus workflow-backed Comfy support, including async task tracking and follow-up delivery of finished audio.</li>
-<li>Providers: add bundled Qwen, Fireworks AI, and StepFun providers, plus MiniMax TTS, Ollama Web Search, and MiniMax Search integrations for chat, speech, and search workflows. (#60032, #55921, #59318, #54648)</li>
-<li>Providers/Amazon Bedrock: add bundled Mantle support plus inference-profile discovery and automatic request-region injection so Bedrock-hosted Claude, GPT-OSS, Qwen, Kimi, GLM, and similar routes work with less manual setup. (#61296, #61299) Thanks @wirjo.</li>
-<li>Control UI/multilingual: add localized control UI support for Simplified Chinese, Traditional Chinese, Brazilian Portuguese, German, Spanish, Japanese, Korean, French, Turkish, Indonesian, Polish, and Ukrainian. Thanks @vincentkoc.</li>
-<li>Plugins: add plugin-config TUI prompts to guided onboarding/setup flows, and add <code>openclaw plugins install --force</code> so existing plugin and hook-pack targets can be replaced without using the dangerous-code override flag. (#60590, #60544)</li>
-<li>Control UI/skills: add ClawHub search, detail, and install flows directly in the Skills panel. (#60134) Thanks @samzong.</li>
-<li>iOS/exec approvals: add generic APNs approval notifications that open an in-app exec approval modal, fetch command details only after authenticated operator reconnect, and clear stale notification state when the approval resolves. (#60239) Thanks @ngutman.</li>
-<li>Matrix/exec approvals: add Matrix-native exec approval prompts with account-scoped approvers, channel-or-DM delivery, and room-thread aware resolution handling. (#58635) Thanks @gumadeiras.</li>
-<li>Channels/context visibility: add configurable <code>contextVisibility</code> per channel (<code>all</code>, <code>allowlist</code>, <code>allowlist_quote</code>) so supplemental quote, thread, and fetched history context can be filtered by sender allowlists instead of always passing through as received.</li>
-<li>Providers/request overrides: add shared model and media request transport overrides across OpenAI-, Anthropic-, Google-, and compatible provider paths, including headers, auth, proxy, and TLS controls. (#60200)</li>
-<li>Providers/OpenAI: add forward-compat <code>openai-codex/gpt-5.4-mini</code>, an opt-in GPT personality, and provider-owned GPT-5 prompt contributions so Codex/GPT runs stay cache-stable and compatible with bundled catalog lag.</li>
-<li>Agents/Claude CLI: expose OpenClaw tools to background Claude CLI runs through a loopback MCP bridge and switch bundled runs to stdin + <code>stream-json</code> partial-message streaming so prompts stop riding argv, long replies show live progress, and final session/usage metadata still land cleanly. (#35676) Thanks @mylukin.</li>
-<li>ACPX/runtime: embed the ACP runtime directly in the bundled <code>acpx</code> plugin, remove the extra external ACP CLI hop, harden live ACP session binding and reuse, and add a generic <code>reply_dispatch</code> hook so bundled plugins like ACPX can own reply interception without hardcoded ACP paths in core auto-reply routing. (#61319)</li>
-<li>Agents/progress: add experimental structured plan updates and structured execution item events so compatible UIs can show clearer step-by-step progress during long-running runs.</li>
-<li>Providers/Anthropic: remove the Claude CLI backend and setup-token from new onboarding, keep existing configured legacy profiles runnable, and have <code>openclaw doctor</code> repair or remove stale <code>anthropic:claude-cli</code> state during migration.</li>
-<li>Tools/video generation: add bundled xAI (<code>grok-imagine-video</code>), Alibaba Model Studio Wan, and Runway video providers, plus live-test/default model wiring for all three.</li>
-<li>Memory/search: add Amazon Bedrock embeddings for Titan, Cohere, Nova, and TwelveLabs models, with AWS credential-chain auto-detection for <code>provider: "auto"</code> and provider-specific dimension controls. Thanks @wirjo.</li>
-<li>Providers/Amazon Bedrock Mantle: generate bearer tokens from the AWS credential chain so Mantle auto-discovery can use IAM auth without manually exporting <code>AWS_BEARER_TOKEN_BEDROCK</code>. Thanks @wirjo.</li>
-<li>Memory/dreaming (experimental): add weighted short-term recall promotion, a <code>/dreaming</code> command, Dreams UI, multilingual conceptual tagging, and doctor/status repair support, while refactoring dreaming from competing modes into three cooperative phases (light, deep, REM) with independent schedules and recovery behavior so durable memory promotion can run in the background with less manual setup. (#60569, #60697) Thanks @vignesh07.</li>
-<li>Memory/dreaming: add configurable aging controls (<code>recencyHalfLifeDays</code>, <code>maxAgeDays</code>) plus optional verbose logging so operators can tune recall decay and inspect promotion decisions more easily.</li>
-<li>Memory/dreaming: add REM preview tooling (<code>openclaw memory rem-harness</code>, <code>promote-explain</code>), surface possible lasting truths during REM staging, and make deep promotion replay-safe so reruns reconcile instead of duplicating <code>MEMORY.md</code> entries.</li>
-<li>Memory/dreaming: write dreaming trail content to top-level <code>dreams.md</code> instead of daily memory notes, update <code>/dreaming</code> help text to point there, and keep <code>dreams.md</code> available for explicit reads without pulling it into default recall. Thanks @davemorin.</li>
-<li>Memory/dreaming: add the Dream Diary surface in Dreams, simplify user-facing dreaming config to <code>enabled</code> plus optional <code>frequency</code>, treat phases as implementation detail in docs/UI, and keep the lobster animation visible above diary content. Thanks @vignesh07.</li>
-<li>Prompt caching: keep prompt prefixes more reusable across transport fallback, deterministic MCP tool ordering, compaction, embedded image history, normalized system-prompt fingerprints, <code>openclaw status --verbose</code> cache diagnostics, and the removal of duplicate in-band tool inventories from agent system prompts so follow-up turns hit cache more reliably. (#58036, #58037, #58038, #59054, #60603, #60691) Thanks @bcherny and @vincentkoc.</li>
-<li>Agents/cache: diagnostics: add prompt-cache break diagnostics, trace live cache scenarios through embedded runner paths, and show cache reuse explicitly in <code>openclaw status --verbose</code>. Thanks @vincentkoc.</li>
-<li>Agents/cache: stabilize cache-relevant system prompt fingerprints by normalizing equivalent structured prompt whitespace, line endings, hook-added system context, and runtime capability ordering so semantically unchanged prompts reuse KV/cache more reliably. Thanks @vincentkoc.</li>
-<li>Agents/tool prompts: remove the duplicate in-band tool inventory from agent system prompts so tool-calling models rely on the structured tool definitions as the single source of truth, improving prompt stability and reducing stale tool guidance.</li>
-<li>Config/schema: enrich the exported <code>openclaw config schema</code> JSON Schema with field titles and descriptions so editors, agents, and other schema consumers receive the same config help metadata. (#60067) Thanks @solavrc.</li>
-<li>Providers/CLI: remove bundled CLI text-provider backends and the <code>agents.defaults.cliBackends</code> surface, while keeping ACP harness sessions and Gemini media understanding on the native bundled providers.</li>
-<li>Matrix/exec approvals: clarify unavailable-approval replies so Matrix no longer claims chat approvals are unsupported when native exec approvals are merely unconfigured. (#61424) Thanks @gumadeiras.</li>
-<li>Docs/IRC: replace public IRC hostname examples with <code>irc.example.com</code> and recommend private servers for bot coordination while listing common public networks for intentional use.</li>
-<li>Memory/dreaming: group nearby daily-note lines into short coherent chunks before staging them for dreaming, so one-off context from recent notes reaches REM/deep with better evidence and less line-level noise.</li>
-<li>Memory/dreaming: drop generic date/day headings from daily-note chunk prefixes while keeping meaningful section labels, so staged snippets stay cleaner and more reusable. (#61597) Thanks @mbelinky.</li>
-<li>Plugins/Lobster: run bundled Lobster workflows in process instead of spawning the external CLI, reducing transport overhead and unblocking native runtime integration. (#61523) Thanks @mbelinky.</li>
-<li>Plugins/Lobster: harden managed resume validation so invalid TaskFlow resume calls fail earlier, and memoize embedded runtime loading per runner while keeping failed loads retryable. (#61566) Thanks @mbelinky.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>Security: preserve restrictive plugin-only tool allowlists, require owner access for <code>/allowlist add</code> and <code>/allowlist remove</code>, fail closed when <code>before_tool_call</code> 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.</li>
-<li>Providers/OpenAI: make GPT-5 and Codex runs act sooner with lower-verbosity defaults, visible progress during tool work, and a one-shot retry when a turn only narrates the plan instead of taking action.</li>
-<li>Providers/OpenAI and reply delivery: preserve native <code>reasoning.effort: "none"</code> and strict schemas where supported, add GPT-5.4 assistant <code>phase</code> metadata across replay and the Gateway <code>/v1/responses</code> layer, and keep commentary buffered until <code>final_answer</code> so web chat, session previews, embedded replies, and Telegram partials stop leaking planning text. Fixes #59150, #59643, #61282.</li>
-<li>Telegram: fix current-model checks in the model picker, HTML-format non-default <code>/model</code> confirmations, explicit topic replies, persisted reaction ownership across restarts, caption-media placeholder and <code>file_id</code> preservation on download failure, and upgraded-install inbound image reads. (#60384, #60042, #59634, #59207, #59948, #59971) Thanks @sfuminya, @GitZhangChi, @dashhuang, @samzong, @v1p0r, and @neeravmakwana.</li>
-<li>Telegram: restore DM voice-note preflight transcription so direct-message audio stops arriving as raw <code><media:audio></code> placeholders. (#61008) Thanks @manueltarouca.</li>
-<li>Telegram/reasoning: only create a Telegram reasoning preview lane when the session is explicitly <code>reasoning:stream</code>, so hidden <code><think></code> traces from streamed replies stop surfacing as chat previews on normal sessions. Thanks @vincentkoc.</li>
-<li>Telegram/native command menu: trim long menu descriptions before dropping commands so sub-100 command sets can still fit Telegram's payload budget and keep more <code>/</code> entries visible. (#61129) Thanks @neeravmakwana.</li>
-<li>Discord: keep REST, webhook, and monitor traffic on the configured proxy, preserve component-only media sends, honor <code>@everyone</code> and <code>@here</code> mention gates, keep ACK reactions on the active account, and split voice connect/playback timeouts so auto-join is more reliable. (#57465, #60361, #60345) Thanks @geekhuashan.</li>
-<li>Discord/reply tags: strip leaked <code>[[reply_to_current]]</code> control tags from preview text and honor explicit reply-tag threading during final delivery, so Discord replies stay attached to the triggering message instead of printing reply metadata into chat.</li>
-<li>Discord/replies: replace the unshipped <code>replyToOnlyWhenBatched</code> flag with <code>replyToMode: "batched"</code> so native reply references only attach on debounced multi-message turns while explicit reply tags still work.</li>
-<li>Discord/image generation: include the real generated <code>MEDIA:</code> paths in tool output, avoid duplicate plain-output media requeueing, and persist volatile workspace-generated media into durable outbound media before final reply delivery so generated image replies stop pointing at missing local files.</li>
-<li>Slack: route live DM replies back to the concrete inbound DM channel while keeping persisted routing metadata user-scoped, so normal assistant replies stop disappearing when pairing and system messages still arrive. (#59030) Thanks @afurm.</li>
-<li>WhatsApp: restore <code>channels.whatsapp.blockStreaming</code> and reset watchdog timeouts after reconnect so quiet chats stop falling into reconnect loops. (#60007, #60069) Thanks @MonkeyLeeT and @mcaxtr.</li>
-<li>Android/Talk Mode: cancel in-flight <code>talk.speak</code> playback when speech is explicitly stopped, and restore spoken replies on both node-scoped and gateway-backed sessions by keeping reply routing and embedded transport overrides aligned with the current playback path. (#60306, #61164, #61214)</li>
-<li>Voice-call/OpenAI: pass full plugin config into realtime transcription provider resolution so streaming calls can discover the bundled OpenAI realtime transcription provider again. Fixes #60936. Thanks @sliekens and @vincentkoc.</li>
-<li>Matrix/exec approvals: anchor seeded approval reactions to the primary Matrix prompt event, resolve them from event metadata instead of prompt text, and clean up chunked approval prompts correctly. (#60931) Thanks @gumadeiras.</li>
-<li>Matrix: recover more reliably when secret storage or recovery keys are missing by recreating secret storage during repair and backup reset, hold crypto snapshot locks during persistence, and surface explicit too-large attachment markers. (#59846, #59851, #60599, #60289) Thanks @al3mart, @emonty, and @efe-arv.</li>
-<li>Matrix/DM sessions: add <code>channels.matrix.dm.sessionScope</code>, shared-session collision notices, and aligned outbound session reuse so separate Matrix DM rooms can keep distinct context when configured. (#61373) Thanks @gumadeiras.</li>
-<li>Matrix: move legacy top-level <code>avatarUrl</code> into the default account during multi-account promotion and keep env-backed account setup avatar config persisted. (#61437) Thanks @gumadeiras.</li>
-<li>MS Teams: download inline DM images via Graph API and preserve channel reply threading in proactive fallback. (#52212, #55198) Thanks @Ted-developer and @hyojin.</li>
-<li>MS Teams: replace the deprecated Teams SDK HttpPlugin stub with <code>httpServerAdapter</code> so recurring gateway deprecation warnings stop firing and the Express 5 compatibility workaround stays on the supported SDK path. (#60939) Thanks @coolramukaka-sys.</li>
-<li>Control UI/chat: add a per-session thinking-level picker in the chat header and mobile chat settings, and keep the browser bundle on UI-local thinking/session-key helpers so Safari no longer crashes on Node-only imports before rendering chat controls.</li>
-<li>Sandbox/SSH: reject hardlinked files during cross-device rename fallback so EXDEV file copies preserve the same pinned file-boundary checks as direct reads.</li>
-<li>Control UI: keep Stop visible during tool-only execution, preserve pending-send busy state, and clear stale ClawHub search results as soon as the query changes. (#54528, #59800, #60267) Thanks @chziyue and @frankekn.</li>
-<li>Control UI/avatar: honor <code>ui.assistant.avatar</code> when serving <code>/avatar/:agentId</code> so Appearance UI avatar paths stop falling back to initials placeholders. (#60778) Thanks @hannasdev.</li>
-<li>Control UI/cron: highlight the Cron refresh button while refresh is in flight so the page's loading state stays visible even when prior data remains on screen. (#60394) Thanks @coder-zhuzm.</li>
-<li>Control UI/Overview: prevent gateway access token/password visibility toggle buttons from overlapping their inputs at narrow widths. (#56924) Thanks @bbddbb1.</li>
-<li>Auto-reply: unify reply lifecycle ownership across preflight compaction, session rotation, CLI-backed runs, and gateway restart handling so <code>/stop</code> 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.</li>
-<li>Reply delivery: prevent duplicate block replies on <code>text_end</code> channels so providers that emit explicit text-end boundaries no longer double-send the same final message. (#61530)</li>
-<li>Gateway/startup: default <code>gateway.mode</code> to <code>local</code> when unset, detect PID recycling in gateway lock files on Windows and macOS, and show startup progress so healthy restarts stop getting blocked by stale locks. (#54801, #60085, #59843) Thanks @BradGroux and @TonyDerek-dot.</li>
-<li>Gateway/macOS: let launchd <code>KeepAlive</code> own in-process gateway restarts again, adding a short supervised-exit delay so rapid restarts avoid launchd crash-loop unloads while <code>openclaw gateway restart</code> still reports real LaunchAgent errors synchronously.</li>
-<li>Gateway/macOS: re-bootstrap the LaunchAgent if <code>launchctl kickstart -k</code> unloads it during restart so failed restarts do not leave the gateway unmanaged until manual repair.</li>
-<li>Gateway/macOS: recover installed-but-unloaded LaunchAgents during <code>openclaw gateway start</code> and <code>restart</code>, while still preferring live unmanaged gateways during restart recovery. (#43766) Thanks @HenryC-3.</li>
-<li>Gateway/Windows scheduled tasks: preserve Task Scheduler settings on reinstall, fail loudly when <code>/Run</code> does not start, and report fast failed restarts accurately instead of pretending they timed out after 60 seconds. (#59335) Thanks @tmimmanuel.</li>
-<li>Windows/restart: fall back to the installed Startup-entry launcher when the scheduled task was never registered, so <code>/restart</code> can relaunch the gateway on Windows setups where <code>schtasks</code> install fell back during onboarding. (#58943) Thanks @imechZhangLY.</li>
-<li>Windows/restart: clean up stale gateway listeners before Windows self-restart and treat listener and argv probe failures as inconclusive, so scheduled-task relaunch no longer falls into an <code>EADDRINUSE</code> retry loop. (#60480) Thanks @arifahmedjoy.</li>
-<li>Update/npm: prefer the npm binary that owns the installed global OpenClaw prefix so mixed Homebrew-plus-nvm setups update the right install. (#60153) Thanks @jayeshp19.</li>
-<li>Agents/music and video generation: add <code>tools.media.asyncCompletion.directSend</code> as an opt-in direct-delivery path for finished async media tasks, while keeping the legacy requester-session wake/model-delivery flow as the default.</li>
-<li>CLI/skills JSON: route <code>skills list --json</code>, <code>skills info --json</code>, and <code>skills check --json</code> output to stdout instead of stderr so machine-readable consumers receive JSON on the expected stream again. (#60914; fixes #57599; landed from contributor PR #57611 by @Aftabbs) Thanks @Aftabbs.</li>
-<li>CLI/Commander: preserve Commander-computed exit codes for argument and help-error paths, and cover the user-argv parse mode in the regression tests so invalid CLI invocations no longer report success when exits are intercepted. (#60923) Thanks @Linux2010.</li>
-<li>Cron: replay interrupted recurring jobs on the first gateway restart instead of waiting for a second restart. (#60583) Thanks @joelnishanth.</li>
-<li>Cron: send failure notifications through the job's primary delivery channel using the same session context as successful delivery when no explicit <code>failureDestination</code> is configured. (#60622) Thanks @artwalker.</li>
-<li>Exec/remote skills: stop advertising <code>exec host=node</code> 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.</li>
-<li>Agents/Claude CLI/security: clear inherited Claude Code config-root and plugin-root env overrides like <code>CLAUDE_CONFIG_DIR</code> and <code>CLAUDE_CODE_PLUGIN_*</code>, 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.</li>
-<li>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.</li>
-<li>Agents/Claude CLI/security: force host-managed Claude CLI backdoor runs to <code>--setting-sources user</code>, even under custom backend arg overrides, so repo-local <code>.claude</code> project/local settings, hooks, and plugin discovery do not silently execute inside non-interactive OpenClaw sessions. Thanks @vincentkoc.</li>
-<li>Agents/Claude CLI: treat malformed bare <code>--permission-mode</code> backend overrides as missing and fail safe back to <code>bypassPermissions</code>, so custom <code>cliBackends.claude-cli.args</code> security config cannot accidentally consume the next flag as a bogus permission mode. Thanks @vincentkoc.</li>
-<li>Gateway/device pairing: require non-admin paired-device sessions to manage only their own device for token rotate/revoke and paired-device removal, blocking cross-device token theft inside pairing-scoped sessions. (#50627) Thanks @coygeek.</li>
-<li>Gateway/plugin routes: keep gateway-auth plugin runtime routes on write-only fallback scopes unless a trusted-proxy caller explicitly declares narrower <code>x-openclaw-scopes</code>, so plugin HTTP handlers no longer mint admin-level runtime scopes on missing or untrusted HTTP scope headers. (#59815) Thanks @pgondhi987.</li>
-<li>Build/types: fix the Node <code>createRequire(...)</code> helper typing so provider-runtime lazy loads compile cleanly again and <code>pnpm build</code> no longer fails in the Pi embedded provider error-pattern path.</li>
-<li>Gateway/security: scope loopback browser-origin auth throttling by normalized origin so one localhost Control UI tab cannot lock out a different localhost browser origin after repeated auth failures.</li>
-<li>Gateway/auth: serialize async shared-secret auth attempts per client so concurrent Tailscale-capable failures cannot overrun the intended auth rate-limit budget. Thanks @Telecaster2147.</li>
-<li>Device pairing/security: keep non-operator device scope checks bound to the requested role prefix so bootstrap verification cannot redeem <code>operator.*</code> scopes through <code>node</code> auth. (#57258) Thanks @jlapenna.</li>
-<li>Device pairing: reject rotating device tokens into roles that were never approved during pairing, and keep reconnect role checks bounded to the paired device's approved role set. (#60462) Thanks @eleqtrizit.</li>
-<li>Gateway/device auth: reuse cached device-token scopes only for cached-token reconnects, while keeping explicit <code>deviceToken</code> scope requests and empty-cache fallbacks intact so reconnects preserve <code>operator.read</code> without breaking explicit auth flows. (#46032) Thanks @caicongyang.</li>
-<li>Mobile pairing/security: fail closed for internal <code>/pair</code> setup-code issuance, cleanup, and approval paths when gateway pairing scopes are missing, and keep approval-time requested-scope enforcement on the internal command path. (#55996) Thanks @coygeek.</li>
-<li>Mobile pairing/bootstrap: keep QR bootstrap handoff tokens bounded to the mobile-safe contract so node handoff stays unscoped and operator handoff drops mixed <code>node.*</code>, <code>operator.admin</code>, and <code>operator.pairing</code> scopes.</li>
-<li>Mobile pairing/Android: tighten secure endpoint handling so Tailscale and public remote setup reject cleartext endpoints, private LAN pairing still works, merged-role approvals mint both node and operator device tokens, and bootstrap tokens survive node auto-pair until operator approval finishes. (#60128, #60208, #60221) Thanks @obviyus.</li>
-<li>Android/canvas security: require exact normalized A2UI URL matches before forwarding canvas bridge actions, rejecting query mismatches and descendant paths while still allowing fragment-only A2UI navigation.</li>
-<li>Synology Chat/security: default low-level HTTPS helper TLS verification to on so helper/API defaults match the shipped safe account default, and only explicit <code>allowInsecureSsl: true</code> opts out.</li>
-<li>Synology Chat/security: route webhook token comparison through the shared constant-time secret helper for consistency with other bundled plugins.</li>
-<li>Plugins/marketplace: block remote marketplace symlink escapes without breaking ordinary local marketplace install paths. (#60556) Thanks @eleqtrizit.</li>
-<li>Telegram/local Bot API: honor <code>channels.telegram.apiRoot</code> for buffered media downloads, add <code>channels.telegram.network.dangerouslyAllowPrivateNetwork</code> for trusted fake-IP setups, and require <code>channels.telegram.trustedLocalFileRoots</code> before reading absolute Bot API <code>file_path</code> values. (#59544, #60705) Thanks @SARAMALI15792 and @obviyus.</li>
-<li>Outbound/sanitizer: strip leaked <code><tool_call></code>, <code><function_calls></code>, and model special tokens from shared user-visible assistant text, including truncated tool-call streams, so internal scaffolding no longer bleeds into replies across surfaces. (#60619) Thanks @oliviareid-svg.</li>
-<li>Agents/errors: surface an explicit disk-full message when local session or transcript writes fail with <code>ENOSPC</code>/<code>disk full</code>, so those runs stop degrading into opaque <code>NO_REPLY</code>-style failures. Thanks @vincentkoc.</li>
-<li>Exec approvals: remove heuristic command-obfuscation gating from host exec so gateway and node runs rely on explicit policy, allowlist, and strict inline-eval rules only.</li>
-<li>Agents/tool results: cap live tool-result persistence and overflow-recovery truncation at 40k characters so oversized tool output stays bounded without discarding recent context entirely.</li>
-<li>Discord/video replies: split text-plus-video deliveries into a text reply followed by a media-only send, and let live provider auth checks honor manifest-declared API key env vars like <code>MODELSTUDIO_API_KEY</code>.</li>
-<li>Config/All Settings: keep the raw config view intact when sensitive fields are blank instead of corrupting or dropping the rendered snapshot. (#28214) Thanks @solodmd.</li>
-<li>Plugin SDK/facades: back-fill bundled plugin facade sentinels before plugin-id tracking re-enters config loading, so CLI/provider startup no longer crashes with <code>shouldNormalizeGoogleProviderConfig is not a function</code> or other empty-facade reads during bundled plugin re-entry. Thanks @adam91holt.</li>
-<li>Plugins/facades: back-fill facade sentinels before tracked-plugin resolution re-enters config loading, so facade exports stay defined during circular provider normalization. (#61180) Thanks @adam91holt.</li>
-<li>QA lab: restore typed mock OpenAI gateway config wiring so QA-lab config helpers compile cleanly again and <code>pnpm check</code> / <code>pnpm build</code> stay green.</li>
-<li>Discord/image generation: include the real generated <code>MEDIA:</code> paths in tool output and avoid duplicate plain-output media requeueing so Discord image replies stop pointing at missing local files.</li>
-<li>Slack: route live DM replies back to the concrete inbound DM channel while keeping persisted routing metadata user-scoped, so normal assistant replies stop disappearing when pairing and system messages still arrive. (#59030) Thanks @afurm.</li>
-<li>Discord/reply tags: strip leaked <code>[[reply_to_current]]</code> control tags from preview text and honor explicit reply-tag threading during final delivery, so Discord replies stay attached to the triggering message instead of printing reply metadata into chat.</li>
-<li>Telegram: fix current-model checks in the model picker, HTML-format non-default <code>/model</code> confirmations, explicit topic replies, persisted reaction ownership across restarts, caption-media placeholder and <code>file_id</code> preservation on download failure, and upgraded-install inbound image reads. (#60384, #60042, #59634, #59207, #59948, #59971) Thanks @sfuminya, @GitZhangChi, @dashhuang, @samzong, @v1p0r, and @neeravmakwana.</li>
-<li>Telegram: restore DM voice-note preflight transcription so direct-message audio stops arriving as raw <code><media:audio></code> placeholders. (#61008) Thanks @manueltarouca.</li>
-<li>Telegram/reasoning: only create a Telegram reasoning preview lane when the session is explicitly <code>reasoning:stream</code>, so hidden <code><think></code> traces from streamed replies stop surfacing as chat previews on normal sessions. Thanks @vincentkoc.</li>
-<li>Telegram/native command menu: trim long menu descriptions before dropping commands so sub-100 command sets can still fit Telegram's payload budget and keep more <code>/</code> entries visible. (#61129) Thanks @neeravmakwana.</li>
-<li>Feishu/reasoning: only expose streamed reasoning previews when the session is explicitly <code>reasoning:stream</code>, so hidden reasoning traces do not surface on normal streaming sessions. Thanks @vincentkoc.</li>
-<li>Discord: keep REST, webhook, and monitor traffic on the configured proxy, preserve component-only media sends, honor <code>@everyone</code> and <code>@here</code> mention gates, keep ACK reactions on the active account, and split voice connect/playback timeouts so auto-join is more reliable. (#57465, #60361, #60345) Thanks @geekhuashan.</li>
-<li>WhatsApp: restore <code>channels.whatsapp.blockStreaming</code> and reset watchdog timeouts after reconnect so quiet chats stop falling into reconnect loops. (#60007, #60069) Thanks @MonkeyLeeT and @mcaxtr.</li>
-<li>Memory: keep <code>memory-core</code> builtin embedding registration on the already-registered path so selecting <code>memory-core</code> no longer recurses through plugin discovery and crashes during startup. (#61402) Thanks @ngutman.</li>
-<li>Agents/tool results: keep large <code>read</code> outputs visible longer, preserve the latest <code>read</code> output when older tool output can absorb the overflow budget, and fall back to Pi's normal overflow compaction/retry path before replacing a fresh <code>read</code> with a compacted stub. Thanks @vincentkoc.</li>
-<li>Memory/QMD: prefer modern <code>qmd collection add --glob</code>, accept newer single-line JSON hit metadata while keeping legacy line fields, refresh QMD docs/doctor install guidance and model-override guidance, and keep older QMD releases working. Thanks @vincentkoc.</li>
-<li>MS Teams: download inline DM images via Graph API and preserve channel reply threading in proactive fallback. (#52212, #55198) Thanks @Ted-developer and @hyojin.</li>
-<li>MS Teams: replace the deprecated Teams SDK HttpPlugin stub with <code>httpServerAdapter</code> so recurring gateway deprecation warnings stop firing and the Express 5 compatibility workaround stays on the supported SDK path. (#60939) Thanks @coolramukaka-sys.</li>
-<li>Matrix/exec approvals: anchor seeded approval reactions to the primary Matrix prompt event, resolve them from event metadata instead of prompt text, and clean up chunked approval prompts correctly. (#60931) Thanks @gumadeiras.</li>
-<li>Matrix: recover more reliably when secret storage or recovery keys are missing by recreating secret storage during repair and backup reset, hold crypto snapshot locks during persistence, and surface explicit too-large attachment markers. (#59846, #59851, #60599, #60289) Thanks @al3mart, @emonty, and @efe-arv.</li>
-<li>Android/Talk Mode: cancel in-flight <code>talk.speak</code> playback when speech is explicitly stopped, so stale replies stop starting after barge-in or manual stop. (#61164) Thanks @obviyus.</li>
-<li>Android/Talk Mode: restore spoken assistant replies on node-scoped sessions by keeping reply routing synced to the resolved node session key and pausing mic capture during reply playback. (#60306) Thanks @MKV21.</li>
-<li>Android/Talk Mode: restore voice replies on gateway-backed talk mode sessions by updating embedded runner transport overrides to the current agent transport API. (#61214) Thanks @obviyus.</li>
-<li>Voice-call/OpenAI: pass full plugin config into realtime transcription provider resolution so streaming calls can discover the bundled OpenAI realtime transcription provider again. Fixes #60936. Thanks @sliekens and @vincentkoc.</li>
-<li>Control UI/chat: add a per-session thinking-level picker in the chat header and mobile chat settings, and keep the browser bundle on UI-local thinking/session-key helpers so Safari no longer crashes on Node-only imports before rendering chat controls.</li>
-<li>Control UI: keep Stop visible during tool-only execution, preserve pending-send busy state, and clear stale ClawHub search results as soon as the query changes. (#54528, #59800, #60267) Thanks @chziyue and @frankekn.</li>
-<li>Control UI/avatar: honor <code>ui.assistant.avatar</code> when serving <code>/avatar/:agentId</code> so Appearance UI avatar paths stop falling back to initials placeholders. (#60778) Thanks @hannasdev.</li>
-<li>Control UI/cron: highlight the Cron refresh button while refresh is in flight so the page's loading state stays visible even when prior data remains on screen. (#60394) Thanks @coder-zhuzm.</li>
-<li>Control UI/Overview: prevent gateway access token/password visibility toggle buttons from overlapping their inputs at narrow widths. (#56924) Thanks @bbddbb1.</li>
-<li>CLI/skills JSON: route <code>skills list --json</code>, <code>skills info --json</code>, and <code>skills check --json</code> output to stdout instead of stderr so machine-readable consumers receive JSON on the expected stream again. (#60914; fixes #57599; landed from contributor PR #57611 by @Aftabbs) Thanks @Aftabbs.</li>
-<li>CLI/Commander: preserve Commander-computed exit codes for argument and help-error paths, and cover the user-argv parse mode in the regression tests so invalid CLI invocations no longer report success when exits are intercepted. (#60923) Thanks @Linux2010.</li>
-<li>Cron: replay interrupted recurring jobs on the first gateway restart instead of waiting for a second restart. (#60583) Thanks @joelnishanth.</li>
-<li>Cron: send failure notifications through the job's primary delivery channel using the same session context as successful delivery when no explicit <code>failureDestination</code> is configured. (#60622) Thanks @artwalker.</li>
-<li>Live model switching: only treat explicit user-driven model changes as pending live switches, so fallback rotation, heartbeat overrides, and compaction no longer trip <code>LiveSessionModelSwitchError</code> before making an API call. (#60266) Thanks @kiranvk-2011.</li>
-<li>Exec approvals: reuse durable exact-command <code>allow-always</code> approvals in allowlist mode so identical reruns stop prompting, and tighten Windows interpreter/path approval handling so wrapper and malformed-path cases fail closed more consistently. (#59880, #59780, #58040, #59182) Thanks @luoyanglang, @SnowSky1, and @pgondhi987.</li>
-<li>Node exec approvals: keep node-host <code>system.run</code> approvals bound to the prepared execution plan across async forwarding, so mutable script operands still get approval-time binding and drift revalidation instead of dropping back to unbound execution.</li>
-<li>Agents/exec approvals: let <code>exec-approvals.json</code> agent security override stricter gateway tool defaults so approved subagents can use <code>security: “full”</code> without falling back to allowlist enforcement again. (#60310) Thanks @lml2468.</li>
-<li>Agents/exec: restore <code>host=node</code> routing for node-pinned and <code>host=auto</code> sessions, while still blocking sandboxed <code>auto</code> sessions from jumping to gateway. (#60788) Thanks @openperf.</li>
-<li>Exec/heartbeat: use the canonical <code>exec-event</code> wake reason for <code>notifyOnExit</code> so background exec completions still trigger follow-up turns when <code>HEARTBEAT.md</code> is empty or comments-only. (#41479) Thanks @rstar327.</li>
-<li>Heartbeat: skip wake delivery when the target session lane is already busy so the pending event is retried instead of getting drained too early. (#40526) Thanks @lucky7323.</li>
-<li>Group chats/agent prompts: tell models to minimize empty lines and use normal chat-style spacing so group replies avoid document-style blank-line formatting.</li>
-<li>Providers/OpenAI GPT: treat short approval turns like <code>ok do it</code> and <code>go ahead</code> as immediate action turns, and trim overly memo-like GPT-5 chat confirmations so OpenAI replies stay shorter and more conversational by default.</li>
-<li>Providers/OpenAI Codex: split native <code>contextWindow</code> from runtime <code>contextTokens</code>, keep the default effective cap at <code>272000</code>, and expose a per-model <code>contextTokens</code> override on <code>models.providers.*.models[]</code>.</li>
-<li>Providers/OpenAI-compatible WS: compute fallback token totals from normalized usage when providers omit or zero <code>total_tokens</code>, so DashScope-compatible sessions stop storing zero totals after alias normalization. (#54940) Thanks @lyfuci.</li>
-<li>Agents/OpenAI: mark Claude-compatible file tool schemas as <code>additionalProperties: false</code> so direct OpenAI GPT-5 routes stop rejecting the <code>read</code> tool with invalid strict-schema errors.</li>
-<li>Agents/OpenAI: fall back to <code>strict: false</code> for native OpenAI tool calls when a tool schema is not strict-compatible, and normalize empty-object tool schemas to include <code>required: []</code>, so direct GPT-5 routes stop failing with invalid strict-schema errors like missing <code>path</code> in <code>required</code>.</li>
-<li>Agents/GPT: add explicit work-item lifecycle events for embedded runs, use them to surface real progress more reliably, and stop counting tool-started turns as planning-only retries.</li>
-<li>Plugins/OpenAI: enable <code>gpt-image-1</code> reference-image edits through <code>/images/edits</code> multipart uploads, and stop inferring unsupported resolution overrides when no explicit <code>size</code> or <code>resolution</code> is provided.</li>
-<li>Agents/replay: remove the malformed assistant-content canonicalization repair from replay history sanitization instead of extending that legacy repair path into replay validation.</li>
-<li>Plugins/OpenAI: tune the OpenAI prompt overlay for live-chat cadence so GPT replies stay shorter, more human, and less wall-of-text by default.</li>
-<li>Providers/compat: stop forcing OpenAI-only defaults on proxy and custom OpenAI-compatible routes, preserve native vendor-specific reasoning/tool/streaming behavior across Anthropic-compatible, Moonshot, Mistral, ModelStudio, OpenRouter, xAI, and Z.ai endpoints, and route GitHub Copilot Claude models through Anthropic Messages instead of OpenAI Responses.</li>
-<li>Providers/GitHub Copilot: send IDE identity headers on runtime model requests and GitHub token exchange so IDE-authenticated Copilot runs stop failing with missing <code>Editor-Version</code>. (#60641) Thanks @VACInc and @vincentkoc.</li>
-<li>Providers/OpenRouter failover: classify <code>403 “Key limit exceeded”</code> spending-limit responses as billing so model fallback continues instead of stopping on generic auth. (#59892) Thanks @rockcent.</li>
-<li>Providers/Anthropic: keep <code>claude-cli/*</code> auth on live Claude CLI credentials at runtime, avoid persisting stale bearer-token profiles, and suppress macOS Keychain prompts during non-interactive Claude CLI setup. (#61234) Thanks @darkamenosa.</li>
-<li>Providers/Anthropic: when Claude CLI auth becomes the default, write a real <code>claude-cli</code> auth profile so local and gateway agent runs can use Claude CLI immediately without missing-API-key failures. Thanks @vincentkoc.</li>
-<li>Providers/Anthropic Vertex: honor <code>cacheRetention: “long”</code> with the real 1-hour prompt-cache TTL on Vertex AI endpoints, and default <code>anthropic-vertex</code> cache retention like direct Anthropic. (#60888) Thanks @affsantos.</li>
-<li>Agents/Anthropic: preserve native <code>toolu_*</code> replay ids on direct Anthropic and Anthropic Vertex paths so cache-sensitive history stops rewriting known-valid Anthropic tool-use ids. (#52612)</li>
-<li>Providers/Google: add model-level <code>cacheRetention</code> support for direct Gemini system prompts by creating, reusing, and refreshing <code>cachedContents</code> automatically on Google AI Studio runs. (#51372) Thanks @rafaelmariano-glitch.</li>
-<li>Google Gemini CLI auth: detect bundled npm installs by scanning packaged bundle files for the Gemini OAuth client config, so <code>npm install -g @google/gemini-cli</code> layouts work again. (#60486) Thanks @wzfmini01.</li>
-<li>Google Gemini CLI auth: detect personal OAuth mode from local Gemini settings and skip Code Assist project discovery for those logins, so personal Google accounts stop failing with <code>loadCodeAssist 400 Bad Request</code>. (#49226) Thanks @bobworrall.</li>
-<li>Google Gemini CLI auth: improve OAuth credential discovery across Windows nvm and Homebrew libexec installs, and align Code Assist metadata so Gemini login stops failing on packaged CLI layouts. (#40729) Thanks @hughcube.</li>
-<li>Google Gemini CLI models: add forward-compat support for stable <code>gemini-2.5-*</code> model ids by letting the bundled CLI provider clone them from Google templates, so <code>gemini-2.5-flash-lite</code> and related configured models stop showing up as missing. (#35274) Thanks @mySebbe.</li>
-<li>Google image generation: disable pinned DNS for Gemini image requests and honor explicit <code>pinDns</code> overrides in shared provider HTTP helpers so proxy-backed image generation works again. (#59873) Thanks @luoyanglang.</li>
-<li>Providers/Microsoft Foundry: preserve explicit image capability on normalized Foundry deployments, repair stale GPT/o-series text-only model metadata across gateway and runtime paths, and keep unknown fallback models from borrowing unrelated image support.</li>
-<li>Providers/Model Studio: preserve native streaming usage reporting for DashScope-compatible endpoints even when they are configured under a generic provider key, so streamed token totals stop sticking at zero. (#52395) Thanks @IVY-AI-gif.</li>
-<li>Providers/Z.AI: preserve explicitly registered <code>glm-5-*</code> variants like <code>glm-5-turbo</code> instead of intercepting them with the generic GLM-5 forward-compat shim. (#48185) Thanks @haoyu-haoyu.</li>
-<li>Amazon Bedrock/aws-sdk auth: stop injecting the fake <code>AWS_PROFILE</code> apiKey marker when no AWS auth env vars exist, so instance-role and other default-chain setups keep working without poisoning provider config. (#61194) Thanks @wirjo.</li>
-<li>Agents/Kimi tool-call repair: preserve tool arguments that were already present on streamed tool calls when later malformed deltas fail reevaluation, while still dropping stale repair-only state before <code>toolcall_end</code>.</li>
-<li>Plugins/Kimi Coding: parse tagged tool calls and keep Anthropic-native tool payloads so Kimi coding endpoints execute tools instead of echoing raw markup. (#60051, #60391) Thanks @obviyus and @Eric-Guo.</li>
-<li>Media understanding: auto-register image-capable config providers for vision routing, so custom GLM-style provider ids with image models stop failing with “no media-understanding provider registered”. (#51418) Thanks @xydt-610.</li>
-<li>Plugins/media understanding: enable bundled Groq and Deepgram providers by default so configured transcription models work without extra plugin activation config. (#59982) Thanks @yxjsxy.</li>
-<li>MiniMax/pricing: keep bundled MiniMax highspeed pricing distinct in provider catalogs and preserve the lower M2.5 cache-read pricing when onboarding older MiniMax models. (#54214) Thanks @octo-patch.</li>
-<li>MiniMax: advertise image input on bundled <code>MiniMax-M2.7</code> and <code>MiniMax-M2.7-highspeed</code> model definitions so image-capable flows can route through the M2.7 family correctly. (#54843) Thanks @MerlinMiao88888888.</li>
-<li>Models/MiniMax: honor <code>MINIMAX_API_HOST</code> for implicit bundled MiniMax provider catalogs so China-hosted API-key setups pick <code>api.minimaxi.com/anthropic</code> without manual provider config. (#34524) Thanks @caiqinghua.</li>
-<li>Usage/MiniMax: invert remaining-style <code>usage_percent</code> fields when MiniMax reports only remaining percentage data, so usage bars stop showing nearly-full remaining quota as nearly-exhausted usage. (#60254) Thanks @jwchmodx.</li>
-<li>Usage/MiniMax: let usage snapshots treat <code>minimax-portal</code> and MiniMax CN aliases as the same MiniMax quota surface, and prefer stored MiniMax OAuth before falling back to Coding Plan keys.</li>
-<li>Usage/MiniMax: prefer the chat-model <code>model_remains</code> entry and derive Coding Plan window labels from MiniMax interval timestamps so MiniMax usage snapshots stop picking zero-budget media rows and misreporting 4h windows as <code>5h</code>. (#52349) Thanks @IVY-AI-gif.</li>
-<li>Model picker/providers: treat bundled BytePlus and Volcengine plan aliases as their native providers during setup, and expose their bundled standard/coding catalogs before auth so setup can suggest the right models. (#58819) Thanks @Luckymingxuan.</li>
-<li>Tools/web_search (Kimi): when <code>tools.web.search.kimi.baseUrl</code> is unset, inherit native Moonshot chat <code>baseUrl</code> (<code>.ai</code> / <code>.cn</code>) so China console keys authenticate on the same host as chat. Fixes #44851. (#56769) Thanks @tonga54.</li>
-<li>Agents/Claude CLI: keep non-interactive <code>--permission-mode bypassPermissions</code> when custom <code>cliBackends.claude-cli.args</code> override defaults, including fallback resolution before the runtime plugin registry is active, so cron and heartbeat Claude CLI runs do not regress to interactive approval mode. (#61114) Thanks @cathrynlavery and @thewilloftheshadow.</li>
-<li>Agents/Claude CLI: persist explicit <code>openclaw agent --session-id</code> runs under a stable session key so follow-ups can reuse the stored CLI binding and resume the same underlying Claude session.</li>
-<li>Agents/Claude CLI: persist routed Claude session bindings, rotate them on <code>/new</code> and <code>/reset</code>, and keep live Claude CLI model switches moving across the configured Claude family so resumed sessions follow the real active thread and model. Thanks @vincentkoc.</li>
-<li>Agents/CLI backends: invalidate stored CLI session reuse when local CLI login state or the selected auth profile credential changes, so relogin and token rotation stop resuming stale sessions.</li>
-<li>Agents/Claude CLI/images: reuse stable hydrated image file paths and preserve shared media extensions like HEIC when passing image refs to local CLI runs, so Claude CLI image prompts stop thrashing KV cache prefixes and oddball image formats do not fall back to <code>.bin</code>. Thanks @vincentkoc.</li>
-<li>Agents/compaction: keep assistant tool calls and displaced tool results in the same compaction chunk so strict summarization providers stop rejecting orphaned tool pairs. (#58849) Thanks @openperf.</li>
-<li>Agents/failover: scope Anthropic <code>An unknown error occurred</code> failover matching by provider so generic internal unknown-error text no longer triggers retryable timeout fallback. (#59325) Thanks @aaron-he-zhu.</li>
-<li>Agents/subagents: honor allowlist validation, auth-profile handoff, and session override state when a subagent retries after <code>LiveSessionModelSwitchError</code>. (#58178) Thanks @openperf.</li>
-<li>Agents/runtime: make default subagent allowlists, inherited skills/workspaces, and duplicate session-id resolution behave more predictably, and include value-shape hints in missing-parameter tool errors. (#59944, #59992, #59858, #55317) Thanks @hclsys, @gumadeiras, @joelnishanth, and @priyansh19.</li>
-<li>Agents/pairing: merge completion announce delivery context with the requester session fallback so missing <code>to</code> still reaches the original channel, and include <code>operator.talk.secrets</code> in CLI default operator scopes for node-role device pairing approvals. (#56481) Thanks @maxpetrusenko.</li>
-<li>Agents/scheduling: steer background-now work toward automatic completion wake and treat <code>process</code> polling as on-demand inspection or intervention instead of default completion handling. (#60877) Thanks @vincentkoc.</li>
-<li>Agents/skills: skip <code>.git</code> and <code>node_modules</code> when mirroring skills into sandbox workspaces so read-only sandboxes do not copy repo history or dependency trees. (#61090) Thanks @joelnishanth.</li>
-<li>ACP/agents: inherit the target agent workspace for cross-agent ACP spawns and fall back safely when the inherited workspace no longer exists. (#58438) Thanks @zssggle-rgb.</li>
-<li>ACPX/Windows: preserve backslashes and absolute <code>.exe</code> paths in Claude CLI parsing, and fail fast on wrapper-script targets with guidance to use <code>cmd.exe /c</code>, <code>powershell.exe -File</code>, or <code>node <script></code>. (#60689) Thanks @steipete.</li>
-<li>Auth/failover: persist selected fallback overrides before retrying, shorten <code>auth_permanent</code> lockouts, and refresh websocket/shared-auth sessions only when real auth changes occur so retries and secret rotations behave predictably. (#60404, #60323, #60387) Thanks @extrasmall0 and @mappel-nv.</li>
-<li>Gateway/channels: pin the initial startup channel registry before later plugin-registry churn so configured channels stay visible and <code>channels.status</code> stops falling back to empty <code>channelOrder</code> / <code>channels</code> payloads after runtime plugin loads.</li>
-<li>Prompt caching: order stable workspace project-context files before <code>HEARTBEAT.md</code> and keep <code>HEARTBEAT.md</code> below the system-prompt cache boundary so heartbeat churn does not invalidate the stable project-context prefix. (#58979) Thanks @yozu and @vincentkoc.</li>
-<li>Prompt caching: route Codex Responses and Anthropic Vertex through boundary-aware cache shaping, and report the actual outbound system prompt in cache traces so cache reuse and misses line up with what providers really receive. Thanks @vincentkoc.</li>
-<li>Agents/cache: preserve the full 3-turn prompt-cache image window across tool loops, keep colliding bundled MCP tool definitions deterministic, and reapply Anthropic Vertex cache shaping after payload hook replacements so KV/cache reuse stays stable. Thanks @vincentkoc.</li>
-<li>Status/cache: restore <code>cacheRead</code> and <code>cacheWrite</code> in transcript fallback so <code>/status</code> keeps showing cache hit percentages when session logs are the only complete usage source. (#59247) Thanks @stuartsy.</li>
-<li>Status/usage: let <code>/status</code> and <code>session_status</code> fall back to transcript token totals when the session meta store stayed at zero, so LM Studio, Ollama, DashScope, and similar OpenAI-compatible providers stop showing <code>Context: 0/...</code>. (#55041) Thanks @jjjojoj.</li>
-<li>Mattermost/config schema: accept <code>groups.*.requireMention</code> again so existing Mattermost configs no longer fail strict validation after upgrade. (#58271) Thanks @MoerAI.</li>
-<li>Doctor/config: compare normalized <code>talk</code> configs by deep structural equality instead of key-order-sensitive serialization so <code>openclaw doctor --fix</code> stops repeatedly reporting/applying no-op <code>talk.provider/providers</code> normalization. (#59911) Thanks @ejames-dev.</li>
-<li>Anthropic CLI onboarding: rewrite migrated fallback model refs during non-interactive Claude CLI setup too, so onboarding and scripted setup no longer keep stale <code>anthropic/*</code> fallbacks after switching the primary model to <code>claude-cli/*</code>. Thanks @vincentkoc.</li>
-<li>Models/Anthropic CLI auth: replace migrated <code>agents.defaults.models</code> allowlists when <code>openclaw models auth login --provider anthropic --method cli --set-default</code> switches to <code>claude-cli/*</code>, so stale <code>anthropic/*</code> entries do not linger beside the migrated Claude CLI defaults. Thanks @vincentkoc.</li>
-<li>Doctor/Claude CLI: add dedicated Claude CLI health checks so <code>openclaw doctor</code> can spot missing local installs or broken auth before agent runs fail. Thanks @vincentkoc.</li>
-<li>Plugins/auth-choice: apply provider-owned auth config patches without recursively preserving replaced default-model maps, so Anthropic Claude CLI and similar migrations can intentionally swap model allowlists during onboarding and setup instead of accumulating stale entries. Thanks @vincentkoc.</li>
-<li>Plugins/onboarding: write dotted plugin uiHint paths like Brave <code>webSearch.mode</code> as nested plugin config so <code>llm-context</code> setup stops failing validation. (#61159) Thanks @obviyus.</li>
-<li>Plugins/install: preserve unsafe override flags across linked plugin and hook-pack probes so local <code>--link</code> installs honor the documented override behavior. (#60624) Thanks @JerrettDavis.</li>
-<li>Plugins/cache: inherit the active gateway workspace for provider, web-search, and web-fetch snapshot loads when callers omit <code>workspaceDir</code>, so compatible plugin registries and snapshot caches stop missing on gateway-owned runtime paths. (#61138) Thanks @jzakirov.</li>
-<li>Plugin SDK/context engines: export the missing context-engine result and subagent lifecycle types from <code>openclaw/plugin-sdk</code> so context engine plugins can type <code>ContextEngine</code> implementations without local workarounds. (#61251) Thanks @DaevMithran.</li>
-<li>Tasks/maintenance: reconcile stale cron and chat-backed CLI task rows against live cron-job and agent-run ownership instead of treating any persisted session key as proof that the task is still running. (#60310) Thanks @lml2468.</li>
-<li>Plugins: suppress trust-warning noise during non-activating snapshot and CLI metadata loads. (#61427) Thanks @gumadeiras.</li>
-<li>Agents/video generation: accept <code>agents.defaults.videoGenerationModel</code> in strict config validation and <code>openclaw config set/get</code>, so gateways using <code>video_generate</code> no longer fail to boot after enabling a video model.</li>
-<li>Matrix/streaming: add a quiet preview mode for streamed Matrix replies, keep legacy <code>partial</code> preview-first behavior, and finalize quiet media captions correctly so previews stop notifying early without dropping final text semantics. (#61450) Thanks @gumadeiras.</li>
-<li>Gateway/shutdown: bound websocket-server shutdown even when no tracked clients remain, so gateway restarts stop hanging until the watchdog kills the process. (#61565) Thanks @mbelinky.</li>
-<li>Control UI/multilingual: localize the remaining shared channel, instances, nodes, and gateway-confirmation strings so the dashboard stops mixing translated UI with hardcoded English labels. Thanks @vincentkoc.</li>
-<li>Discord/media: raise the default inbound and outbound media cap to <code>100MB</code> so Discord matches Telegram more closely and larger attachments stop failing on the old low default.</li>
-<li>Matrix: keep direct transport requests on the pinned dispatcher by routing them through undici runtime fetch, so Matrix clients resume syncing on newer runtimes without dropping the validated address binding. (#61595) Thanks @gumadeiras.</li>
-<li>Plugins/facades: resolve globally installed bundled-plugin runtime facades from registry roots so bundled channels like LINE still boot when the winning plugin install lives under the global extensions directory with an encoded scoped folder name. (#61297) Thanks @openperf.</li>
-</ul>
-<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
-]]></description>
-            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.5/OpenClaw-2026.4.5.zip" length="25050620" type="application/octet-stream" sparkle:edSignature="gVbB/73byllY0utwGIi3P5t0FyvLldeR0Uq2pAa6LTBr8VyZlwNCZ2xPlt2zDFshSUBFKxicYzohOmfJ28ACBg=="/>
-        </item>
     </channel>
 </rss>

apps/android/app/build.gradle.kts

@@ -65,8 +65,8 @@ android {
         applicationId = "ai.openclaw.app"
         minSdk = 31
         targetSdk = 36
-        versionCode = 2026040901
-        versionName = "2026.4.9"
+        versionCode = 2026041001
+        versionName = "2026.4.10"
         ndk {
             // Support all major ABIs — native libs are tiny (~47 KB per ABI)
             abiFilters += listOf("armeabi-v7a", "arm64-v8a", "x86", "x86_64")

apps/macos/Package.resolved

@@ -1,5 +1,5 @@
 {
-  "originHash" : "fb90e7b1977f43661ac91681d16da11f9ddd85630407ef170eaada0a6ee39972",
+  "originHash" : "31972864afdac74537794e1a3b7bd22484c09ec1be8e3624fb9ea582e9222ad9",
   "pins" : [
     {
       "identity" : "axorcist",
@@ -28,6 +28,15 @@
         "version" : "0.1.0"
       }
     },
+    {
+      "identity" : "eventsource",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/mattt/EventSource.git",
+      "state" : {
+        "revision" : "a3a85a85214caf642abaa96ae664e4c772a59f6e",
+        "version" : "1.4.1"
+      }
+    },
     {
       "identity" : "menubarextraaccess",
       "kind" : "remoteSourceControl",
@@ -37,6 +46,33 @@
         "version" : "1.2.2"
       }
     },
+    {
+      "identity" : "mlx-audio-swift",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/Blaizzy/mlx-audio-swift",
+      "state" : {
+        "revision" : "fcbd04daa1bfebe881932f630af2ba6ce9af3274",
+        "version" : "0.1.2"
+      }
+    },
+    {
+      "identity" : "mlx-swift",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/ml-explore/mlx-swift.git",
+      "state" : {
+        "revision" : "61b9e011e09a62b489f6bd647958f1555bdf2896",
+        "version" : "0.31.3"
+      }
+    },
+    {
+      "identity" : "mlx-swift-lm",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/ml-explore/mlx-swift-lm.git",
+      "state" : {
+        "revision" : "25b00d4e22e61ec9c41efda47990cd2084ec87ff",
+        "version" : "2.31.3"
+      }
+    },
     {
       "identity" : "peekaboo",
       "kind" : "remoteSourceControl",
@@ -64,6 +100,33 @@
         "version" : "1.2.1"
       }
     },
+    {
+      "identity" : "swift-asn1",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/apple/swift-asn1.git",
+      "state" : {
+        "revision" : "9f542610331815e29cc3821d3b6f488db8715517",
+        "version" : "1.6.0"
+      }
+    },
+    {
+      "identity" : "swift-atomics",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/apple/swift-atomics.git",
+      "state" : {
+        "revision" : "b601256eab081c0f92f059e12818ac1d4f178ff7",
+        "version" : "1.3.0"
+      }
+    },
+    {
+      "identity" : "swift-collections",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/apple/swift-collections.git",
+      "state" : {
+        "revision" : "6675bc0ff86e61436e615df6fc5174e043e57924",
+        "version" : "1.4.1"
+      }
+    },
     {
       "identity" : "swift-concurrency-extras",
       "kind" : "remoteSourceControl",
@@ -73,6 +136,33 @@
         "version" : "1.3.2"
       }
     },
+    {
+      "identity" : "swift-crypto",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/apple/swift-crypto.git",
+      "state" : {
+        "revision" : "bb4ba815dab96d4edc1e0b86d7b9acf9ff973a84",
+        "version" : "4.3.1"
+      }
+    },
+    {
+      "identity" : "swift-huggingface",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/huggingface/swift-huggingface.git",
+      "state" : {
+        "revision" : "b721959445b617d0bf03910b2b4aced345fd93bf",
+        "version" : "0.9.0"
+      }
+    },
+    {
+      "identity" : "swift-jinja",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/huggingface/swift-jinja.git",
+      "state" : {
+        "revision" : "0aeefadec459ce8e11a333769950fb86183aca43",
+        "version" : "2.3.5"
+      }
+    },
     {
       "identity" : "swift-log",
       "kind" : "remoteSourceControl",
@@ -82,6 +172,15 @@
         "version" : "1.10.1"
       }
     },
+    {
+      "identity" : "swift-nio",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/apple/swift-nio.git",
+      "state" : {
+        "revision" : "558f24a4647193b5a0e2104031b71c55d31ff83a",
+        "version" : "2.97.1"
+      }
+    },
     {
       "identity" : "swift-numerics",
       "kind" : "remoteSourceControl",
@@ -109,6 +208,15 @@
         "version" : "1.6.4"
       }
     },
+    {
+      "identity" : "swift-transformers",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/huggingface/swift-transformers.git",
+      "state" : {
+        "revision" : "58c4bc11963a140358d791f678a60a2745a23146",
+        "version" : "1.2.1"
+      }
+    },
     {
       "identity" : "swiftui-math",
       "kind" : "remoteSourceControl",
@@ -126,6 +234,15 @@
         "revision" : "5b06b811c0f5313b6b84bbef98c635a630638c38",
         "version" : "0.3.1"
       }
+    },
+    {
+      "identity" : "yyjson",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/ibireme/yyjson.git",
+      "state" : {
+        "revision" : "8b4a38dc994a110abaec8a400615567bd996105f",
+        "version" : "0.12.0"
+      }
     }
   ],
   "version" : 3

apps/macos/Package.swift

@@ -20,6 +20,7 @@ let package = Package(
         .package(url: "https://github.com/apple/swift-log.git", from: "1.10.1"),
         .package(url: "https://github.com/sparkle-project/Sparkle", from: "2.9.0"),
         .package(url: "https://github.com/steipete/Peekaboo.git", branch: "main"),
+        .package(url: "https://github.com/Blaizzy/mlx-audio-swift", exact: "0.1.2"),
         .package(path: "../shared/OpenClawKit"),
         .package(path: "../../Swabble"),
     ],
@@ -54,6 +55,7 @@ let package = Package(
                 .product(name: "Sparkle", package: "Sparkle"),
                 .product(name: "PeekabooBridge", package: "Peekaboo"),
                 .product(name: "PeekabooAutomationKit", package: "Peekaboo"),
+                .product(name: "MLXAudioTTS", package: "mlx-audio-swift"),
             ],
             exclude: [
                 "Resources/Info.plist",

apps/macos/Sources/OpenClaw/CommandResolver.swift

@@ -235,7 +235,8 @@ enum CommandResolver {
         extraArgs: [String] = [],
         defaults: UserDefaults = .standard,
         configRoot: [String: Any]? = nil,
-        searchPaths: [String]? = nil) -> [String]
+        searchPaths: [String]? = nil,
+        projectRoot: URL? = nil) -> [String]
     {
         let settings = self.connectionSettings(defaults: defaults, configRoot: configRoot)
         if settings.mode == .remote, let ssh = self.sshNodeCommand(
@@ -246,7 +247,7 @@ enum CommandResolver {
             return ssh
         }
 
-        let root = self.projectRoot()
+        let root = projectRoot ?? self.projectRoot()
         if let openclawPath = self.projectOpenClawExecutable(projectRoot: root) {
             return [openclawPath, subcommand] + extraArgs
         }
@@ -289,14 +290,16 @@ enum CommandResolver {
         extraArgs: [String] = [],
         defaults: UserDefaults = .standard,
         configRoot: [String: Any]? = nil,
-        searchPaths: [String]? = nil) -> [String]
+        searchPaths: [String]? = nil,
+        projectRoot: URL? = nil) -> [String]
     {
         self.openclawNodeCommand(
             subcommand: subcommand,
             extraArgs: extraArgs,
             defaults: defaults,
             configRoot: configRoot,
-            searchPaths: searchPaths)
+            searchPaths: searchPaths,
+            projectRoot: projectRoot)
     }
 
     // MARK: - SSH helpers

apps/macos/Sources/OpenClaw/Resources/Info.plist

@@ -15,9 +15,9 @@
     <key>CFBundlePackageType</key>
     <string>APPL</string>
     <key>CFBundleShortVersionString</key>
-    <string>2026.4.9</string>
+    <string>2026.4.10</string>
     <key>CFBundleVersion</key>
-    <string>2026040901</string>
+    <string>2026041001</string>
     <key>CFBundleIconFile</key>
     <string>OpenClaw</string>
     <key>CFBundleURLTypes</key>

apps/macos/Sources/OpenClaw/ShellExecutor.swift

@@ -73,8 +73,10 @@ enum ShellExecutor {
                 group.addTask { await waitTask.value }
                 group.addTask {
                     try? await Task.sleep(nanoseconds: nanos)
-                    if process.isRunning { process.terminate() }
-                    _ = await waitTask.value // drain pipes after termination
+                    guard process.isRunning else {
+                        return await waitTask.value
+                    }
+                    process.terminate()
                     return ShellResult(
                         stdout: "",
                         stderr: "",

apps/macos/Sources/OpenClaw/TalkMLXSpeechSynthesizer.swift

@@ -0,0 +1,178 @@
+import Foundation
+import MLXAudioTTS
+import OSLog
+
+// swiftformat:disable wrap wrapMultilineStatementBraces trailingCommas redundantSelf extensionAccessControl
+/// Runtime access stays serialized through `TalkModeRuntime` actor helper methods.
+final class TalkMLXSpeechSynthesizer {
+    enum SynthesizeError: Error {
+        case canceled
+        case modelLoadFailed(String)
+        case audioGenerationFailed
+        case audioPlaybackFailed
+        case timedOut
+    }
+
+    static let shared = TalkMLXSpeechSynthesizer()
+    static let defaultModelRepo = "mlx-community/Soprano-80M-bf16"
+
+    private let logger = Logger(subsystem: "ai.openclaw", category: "talk.mlx")
+    private var currentToken = UUID()
+    private var modelRepo: String?
+    private var model: (any SpeechGenerationModel)?
+
+    private init() {}
+
+    func stop() {
+        self.currentToken = UUID()
+    }
+
+    func synthesize(
+        text: String,
+        modelRepo: String?,
+        language: String?,
+        voicePreset: String?) async throws -> Data {
+        let trimmed = text.trimmingCharacters(in: .whitespacesAndNewlines)
+        guard !trimmed.isEmpty else { return Data() }
+
+        self.stop()
+        let token = UUID()
+        self.currentToken = token
+
+        let resolvedRepo = Self.resolvedModelRepo(modelRepo)
+        let rawModel = try await self.loadModel(
+            modelRepo: resolvedRepo,
+            token: token)
+        let model = UncheckedSpeechModel(raw: rawModel)
+        guard self.currentToken == token else {
+            throw SynthesizeError.canceled
+        }
+
+        let audioData: Data
+        do {
+            let audio = try await model.generateAudio(
+                text: trimmed,
+                voice: voicePreset,
+                language: language)
+            audioData = Self.makeWavData(
+                samples: audio,
+                sampleRate: Double(model.sampleRateValue()))
+        } catch {
+            self.logger.error(
+                "talk mlx generation failed: \(error.localizedDescription, privacy: .public)")
+            throw SynthesizeError.audioGenerationFailed
+        }
+
+        guard self.currentToken == token else {
+            throw SynthesizeError.canceled
+        }
+        return audioData
+    }
+
+    private func loadModel(
+        modelRepo: String,
+        token: UUID) async throws -> any SpeechGenerationModel {
+        if let model = self.model, self.modelRepo == modelRepo {
+            return model
+        }
+
+        self.logger.info("talk mlx loading modelRepo=\(modelRepo, privacy: .public)")
+        do {
+            let model = try await TTS.loadModel(modelRepo: modelRepo)
+            guard self.currentToken == token else {
+                throw SynthesizeError.canceled
+            }
+            self.model = model
+            self.modelRepo = modelRepo
+            return model
+        } catch is CancellationError {
+            throw SynthesizeError.canceled
+        } catch {
+            self.logger.error(
+                "talk mlx load failed: \(error.localizedDescription, privacy: .public)")
+            throw SynthesizeError.modelLoadFailed(modelRepo)
+        }
+    }
+
+    private static func resolvedModelRepo(_ modelRepo: String?) -> String {
+        let trimmed = modelRepo?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
+        return trimmed.isEmpty ? Self.defaultModelRepo : trimmed
+    }
+
+    private static func makeWavData(samples: [Float], sampleRate: Double) -> Data {
+        let channels: UInt16 = 1
+        let bitsPerSample: UInt16 = 16
+        let blockAlign = channels * (bitsPerSample / 8)
+        let sampleRateInt = UInt32(sampleRate.rounded())
+        let byteRate = sampleRateInt * UInt32(blockAlign)
+        let dataSize = UInt32(samples.count) * UInt32(blockAlign)
+
+        var data = Data(capacity: Int(44 + dataSize))
+        data.append(contentsOf: [0x52, 0x49, 0x46, 0x46]) // RIFF
+        data.appendLEUInt32(36 + dataSize)
+        data.append(contentsOf: [0x57, 0x41, 0x56, 0x45]) // WAVE
+
+        data.append(contentsOf: [0x66, 0x6D, 0x74, 0x20]) // fmt
+        data.appendLEUInt32(16)
+        data.appendLEUInt16(1)
+        data.appendLEUInt16(channels)
+        data.appendLEUInt32(sampleRateInt)
+        data.appendLEUInt32(byteRate)
+        data.appendLEUInt16(blockAlign)
+        data.appendLEUInt16(bitsPerSample)
+
+        data.append(contentsOf: [0x64, 0x61, 0x74, 0x61]) // data
+        data.appendLEUInt32(dataSize)
+
+        for sample in samples {
+            let clamped = max(-1.0, min(1.0, sample))
+            let scaled = Int16((clamped * Float(Int16.max)).rounded())
+            data.appendLEInt16(scaled)
+        }
+        return data
+    }
+}
+
+extension TalkMLXSpeechSynthesizer: @unchecked Sendable {}
+
+private struct UncheckedSpeechModel {
+    let raw: any SpeechGenerationModel
+
+    func sampleRateValue() -> Int {
+        raw.sampleRate
+    }
+
+    func generateAudio(
+        text: String,
+        voice: String?,
+        language: String?) async throws -> [Float] {
+        let generatedAudio = try await raw.generate(
+            text: text,
+            voice: voice,
+            refAudio: nil,
+            refText: nil,
+            language: language)
+        return generatedAudio.asArray(Float.self)
+    }
+}
+
+extension UncheckedSpeechModel: @unchecked Sendable {}
+
+extension Data {
+    fileprivate mutating func appendLEUInt16(_ value: UInt16) {
+        var littleEndian = value.littleEndian
+        Swift.withUnsafeBytes(of: &littleEndian) { append(contentsOf: $0) }
+    }
+
+    fileprivate mutating func appendLEUInt32(_ value: UInt32) {
+        var littleEndian = value.littleEndian
+        Swift.withUnsafeBytes(of: &littleEndian) { append(contentsOf: $0) }
+    }
+
+    fileprivate mutating func appendLEInt16(_ value: Int16) {
+        var littleEndian = value.littleEndian
+        Swift.withUnsafeBytes(of: &littleEndian) { append(contentsOf: $0) }
+    }
+}
+
+// swiftformat:enable wrap wrapMultilineStatementBraces trailingCommas redundantSelf extensionAccessControl

apps/macos/Sources/OpenClaw/TalkModeGatewayConfig.swift

@@ -44,7 +44,13 @@ enum TalkModeGatewayConfigParser {
                 acc[key] = value
             } ?? [:]
         let model = activeConfig?["modelId"]?.stringValue?.trimmingCharacters(in: .whitespacesAndNewlines)
-        let resolvedModel = (model?.isEmpty == false) ? model! : defaultModelIdFallback
+        let resolvedModel: String? = if model?.isEmpty == false {
+            model!
+        } else if activeProvider == defaultProvider {
+            defaultModelIdFallback
+        } else {
+            nil
+        }
         let outputFormat = activeConfig?["outputFormat"]?.stringValue
         let interrupt = talk?["interruptOnSpeech"]?.boolValue
         let apiKey = activeConfig?["apiKey"]?.stringValue

apps/macos/Sources/OpenClaw/TalkModeRuntime.swift

@@ -10,6 +10,7 @@ actor TalkModeRuntime {
 
     enum PlaybackPlan: Equatable {
         case elevenLabsThenSystemVoice(apiKey: String, voiceId: String)
+        case mlxThenSystemVoice
         case systemVoiceOnly
     }
 
@@ -17,6 +18,8 @@ actor TalkModeRuntime {
     private let ttsLogger = Logger(subsystem: "ai.openclaw", category: "talk.tts")
     private static let defaultModelIdFallback = "eleven_v3"
     private static let defaultTalkProvider = "elevenlabs"
+    private static let mlxTalkProvider = "mlx"
+    private static let systemTalkProvider = "system"
     private static let defaultSilenceTimeoutMs = TalkDefaults.silenceTimeoutMs
 
     private final class RMSMeter: @unchecked Sendable {
@@ -65,6 +68,7 @@ actor TalkModeRuntime {
     private var modelOverrideActive = false
     private var defaultOutputFormat: String?
     private var interruptOnSpeech: Bool = true
+    private var activeTalkProvider = TalkModeRuntime.defaultTalkProvider
     private var lastInterruptedAtSeconds: Double?
     private var voiceAliases: [String: String] = [:]
     private var lastSpokenText: String?
@@ -462,7 +466,7 @@ actor TalkModeRuntime {
     private func playAssistant(text: String) async {
         guard let input = await self.preparePlaybackInput(text: text) else { return }
 
-        switch Self.playbackPlan(apiKey: input.apiKey, voiceId: input.voiceId) {
+        switch Self.playbackPlan(provider: input.provider, apiKey: input.apiKey, voiceId: input.voiceId) {
         case let .elevenLabsThenSystemVoice(apiKey, voiceId):
             do {
                 try await self.playElevenLabs(input: input, apiKey: apiKey, voiceId: voiceId)
@@ -477,6 +481,23 @@ actor TalkModeRuntime {
                     self.ttsLogger.error("talk system voice failed: \(error.localizedDescription, privacy: .public)")
                 }
             }
+        case .mlxThenSystemVoice:
+            do {
+                try await self.playMLX(input: input)
+            } catch TalkMLXSpeechSynthesizer.SynthesizeError.canceled {
+                self.ttsLogger.info("talk mlx canceled")
+                return
+            } catch {
+                self.ttsLogger
+                    .error(
+                        "talk MLX failed: \(error.localizedDescription, privacy: .public); " +
+                            "falling back to system voice")
+                do {
+                    try await self.playSystemVoice(input: input)
+                } catch {
+                    self.ttsLogger.error("talk system voice failed: \(error.localizedDescription, privacy: .public)")
+                }
+            }
         case .systemVoiceOnly:
             do {
                 try await self.playSystemVoice(input: input)
@@ -491,19 +512,30 @@ actor TalkModeRuntime {
         }
     }
 
-    static func playbackPlan(apiKey: String?, voiceId: String?) -> PlaybackPlan {
-        guard let apiKey, !apiKey.isEmpty, let voiceId else {
+    static func playbackPlan(provider: String, apiKey: String?, voiceId: String?) -> PlaybackPlan {
+        switch provider {
+        case self.defaultTalkProvider:
+            guard let apiKey, !apiKey.isEmpty, let voiceId else {
+                return .systemVoiceOnly
+            }
+            return .elevenLabsThenSystemVoice(apiKey: apiKey, voiceId: voiceId)
+        case self.mlxTalkProvider:
+            return .mlxThenSystemVoice
+        case self.systemTalkProvider:
+            return .systemVoiceOnly
+        default:
             return .systemVoiceOnly
         }
-        return .elevenLabsThenSystemVoice(apiKey: apiKey, voiceId: voiceId)
     }
 
     private struct TalkPlaybackInput {
         let generation: Int
+        let provider: String
         let cleanedText: String
         let directive: TalkDirective?
         let apiKey: String?
         let voiceId: String?
+        let voicePreset: String?
         let language: String?
         let synthTimeoutSeconds: Double
     }
@@ -552,18 +584,20 @@ actor TalkModeRuntime {
             resolvedVoice ??
             self.currentVoiceId ??
             self.defaultVoiceId
+        let voicePreset = preferredVoice
+        let provider = self.activeTalkProvider
 
         let language = ElevenLabsTTSClient.validatedLanguage(directive?.language)
 
-        let voiceId: String? = if let apiKey, !apiKey.isEmpty {
+        let voiceId: String? = if provider == Self.defaultTalkProvider, let apiKey, !apiKey.isEmpty {
             await self.resolveVoiceId(preferred: preferredVoice, apiKey: apiKey)
         } else {
             nil
         }
 
-        if apiKey?.isEmpty != false {
+        if provider == Self.defaultTalkProvider, apiKey?.isEmpty != false {
             self.ttsLogger.warning("talk missing ELEVENLABS_API_KEY; falling back to system voice")
-        } else if voiceId == nil {
+        } else if provider == Self.defaultTalkProvider, voiceId == nil {
             self.ttsLogger.warning("talk missing voiceId; falling back to system voice")
         } else if let voiceId {
             self.ttsLogger
@@ -579,15 +613,21 @@ actor TalkModeRuntime {
 
         return TalkPlaybackInput(
             generation: gen,
+            provider: provider,
             cleanedText: cleaned,
             directive: directive,
             apiKey: apiKey,
             voiceId: voiceId,
+            voicePreset: voicePreset,
             language: language,
             synthTimeoutSeconds: synthTimeoutSeconds)
     }
 
-    private func playElevenLabs(input: TalkPlaybackInput, apiKey: String, voiceId: String) async throws {
+    private func playElevenLabs(
+        input: TalkPlaybackInput,
+        apiKey: String,
+        voiceId: String) async throws
+    {
         let desiredOutputFormat = input.directive?.outputFormat ?? self.defaultOutputFormat ?? "pcm_44100"
         let outputFormat = ElevenLabsTTSClient.validatedOutputFormat(desiredOutputFormat)
         if outputFormat == nil, !desiredOutputFormat.isEmpty {
@@ -696,6 +736,39 @@ actor TalkModeRuntime {
         self.ttsLogger.info("talk system voice done")
     }
 
+    private func playMLX(input: TalkPlaybackInput) async throws {
+        self.ttsLogger.info("talk mlx start chars=\(input.cleanedText.count, privacy: .public)")
+        if self.interruptOnSpeech {
+            guard await self.prepareForPlayback(generation: input.generation) else { return }
+        }
+        await MainActor.run { TalkModeController.shared.updatePhase(.speaking) }
+        self.phase = .speaking
+        let modelRepo = input.directive?.modelId ?? self.currentModelId
+        let audioData: Data
+        do {
+            audioData = try await AsyncTimeout.withTimeout(
+                seconds: input.synthTimeoutSeconds,
+                onTimeout: {
+                    TalkMLXSpeechSynthesizer.SynthesizeError.timedOut
+                },
+                operation: { [self] in
+                    try await self.synthesizeMLXVoice(
+                        text: input.cleanedText,
+                        modelRepo: modelRepo,
+                        language: input.language,
+                        voicePreset: input.voicePreset)
+                })
+        } catch TalkMLXSpeechSynthesizer.SynthesizeError.timedOut {
+            self.stopMLXVoice()
+            throw TalkMLXSpeechSynthesizer.SynthesizeError.timedOut
+        }
+        let result = await self.playTalkAudio(data: audioData)
+        if !result.finished, result.interruptedAt == nil {
+            throw TalkMLXSpeechSynthesizer.SynthesizeError.audioPlaybackFailed
+        }
+        self.ttsLogger.info("talk mlx done")
+    }
+
     private func prepareForPlayback(generation: Int) async -> Bool {
         await self.startRecognition()
         return self.isCurrent(generation)
@@ -750,10 +823,13 @@ actor TalkModeRuntime {
 
     func stopSpeaking(reason: TalkStopReason) async {
         let usePCM = self.lastPlaybackWasPCM
-        let interruptedAt = usePCM ? await self.stopPCM() : await self.stopMP3()
+        let remoteInterruptedAt = usePCM ? await self.stopPCM() : await self.stopMP3()
         _ = usePCM ? await self.stopMP3() : await self.stopPCM()
+        let localInterruptedAt = await self.stopTalkAudio()
         await TalkSystemSpeechSynthesizer.shared.stop()
+        self.stopMLXVoice()
         guard self.phase == .speaking else { return }
+        let interruptedAt = remoteInterruptedAt ?? localInterruptedAt
         if reason == .speech, let interruptedAt {
             self.lastInterruptedAtSeconds = interruptedAt
         }
@@ -795,6 +871,33 @@ extension TalkModeRuntime {
         StreamingAudioPlayer.shared.stop()
     }
 
+    @MainActor
+    private func playTalkAudio(data: Data) async -> TalkPlaybackResult {
+        await TalkAudioPlayer.shared.play(data: data)
+    }
+
+    @MainActor
+    private func stopTalkAudio() -> Double? {
+        TalkAudioPlayer.shared.stop()
+    }
+
+    private func synthesizeMLXVoice(
+        text: String,
+        modelRepo: String?,
+        language: String?,
+        voicePreset: String?) async throws -> Data
+    {
+        try await TalkMLXSpeechSynthesizer.shared.synthesize(
+            text: text,
+            modelRepo: modelRepo,
+            language: language,
+            voicePreset: voicePreset)
+    }
+
+    private func stopMLXVoice() {
+        TalkMLXSpeechSynthesizer.shared.stop()
+    }
+
     // MARK: - Config
 
     private func reloadConfig() async {
@@ -810,6 +913,7 @@ extension TalkModeRuntime {
         }
         self.defaultOutputFormat = cfg.outputFormat
         self.interruptOnSpeech = cfg.interruptOnSpeech
+        self.activeTalkProvider = cfg.activeProvider
         self.silenceWindow = TimeInterval(cfg.silenceTimeoutMs) / 1000
         self.apiKey = cfg.apiKey
         let hasApiKey = (cfg.apiKey?.isEmpty == false)
@@ -817,7 +921,8 @@ extension TalkModeRuntime {
         let modelLabel = (cfg.modelId?.isEmpty == false) ? cfg.modelId! : "none"
         self.logger
             .info(
-                "talk config voiceId=\(voiceLabel, privacy: .public) " +
+                "talk config provider=\(cfg.activeProvider, privacy: .public) " +
+                    "talk config voiceId=\(voiceLabel, privacy: .public) " +
                     "modelId=\(modelLabel, privacy: .public) " +
                     "apiKey=\(hasApiKey, privacy: .public) " +
                     "interrupt=\(cfg.interruptOnSpeech, privacy: .public) " +
@@ -859,11 +964,17 @@ extension TalkModeRuntime {
             await MainActor.run {
                 AppStateStore.shared.seamColorHex = parsed.seamColorHex
             }
-            if parsed.activeProvider != Self.defaultTalkProvider {
-                self.ttsLogger
-                    .info("talk provider \(parsed.activeProvider, privacy: .public) unsupported; using system voice")
-            } else if parsed.normalizedPayload {
+            if parsed.activeProvider == Self.defaultTalkProvider {
                 self.ttsLogger.info("talk config provider from talk.resolved")
+            } else if parsed.activeProvider == Self.mlxTalkProvider ||
+                parsed.activeProvider == Self.systemTalkProvider
+            {
+                self.ttsLogger.info(
+                    "talk provider \(parsed.activeProvider, privacy: .public) active")
+            } else {
+                self.ttsLogger
+                    .info(
+                        "talk provider \(parsed.activeProvider, privacy: .public) unsupported; using system voice")
             }
             return parsed
         } catch {

apps/macos/Sources/OpenClawProtocol/GatewayModels.swift

@@ -2837,6 +2837,7 @@ public struct ModelChoice: Codable, Sendable {
     public let id: String
     public let name: String
     public let provider: String
+    public let alias: String?
     public let contextwindow: Int?
     public let reasoning: Bool?
 
@@ -2844,12 +2845,14 @@ public struct ModelChoice: Codable, Sendable {
         id: String,
         name: String,
         provider: String,
+        alias: String?,
         contextwindow: Int?,
         reasoning: Bool?)
     {
         self.id = id
         self.name = name
         self.provider = provider
+        self.alias = alias
         self.contextwindow = contextwindow
         self.reasoning = reasoning
     }
@@ -2858,6 +2861,7 @@ public struct ModelChoice: Codable, Sendable {
         case id
         case name
         case provider
+        case alias
         case contextwindow = "contextWindow"
         case reasoning
     }

apps/macos/Tests/OpenClawIPCTests/CommandResolverTests.swift

@@ -17,7 +17,6 @@ import Testing
 
     private func makeProjectRootWithPnpm() throws -> (tmp: URL, pnpmPath: URL) {
         let tmp = try makeTempDirForTests()
-        CommandResolver.setProjectRoot(tmp.path)
         let pnpmPath = tmp.appendingPathComponent("node_modules/.bin/pnpm")
         try makeExecutableForTests(at: pnpmPath)
         return (tmp, pnpmPath)
@@ -27,12 +26,17 @@ import Testing
         let defaults = self.makeLocalDefaults()
 
         let tmp = try makeTempDirForTests()
-        CommandResolver.setProjectRoot(tmp.path)
 
         let openclawPath = tmp.appendingPathComponent("node_modules/.bin/openclaw")
         try makeExecutableForTests(at: openclawPath)
 
-        let cmd = CommandResolver.openclawCommand(subcommand: "gateway", defaults: defaults, configRoot: [:])
+        let searchPaths = [tmp.appendingPathComponent("node_modules/.bin").path]
+        let cmd = CommandResolver.openclawCommand(
+            subcommand: "gateway",
+            defaults: defaults,
+            configRoot: [:],
+            searchPaths: searchPaths,
+            projectRoot: tmp)
         #expect(cmd.prefix(2).elementsEqual([openclawPath.path, "gateway"]))
     }
 
@@ -40,7 +44,6 @@ import Testing
         let defaults = self.makeLocalDefaults()
 
         let tmp = try makeTempDirForTests()
-        CommandResolver.setProjectRoot(tmp.path)
 
         let nodePath = tmp.appendingPathComponent("node_modules/.bin/node")
         let scriptPath = tmp.appendingPathComponent("bin/openclaw.js")
@@ -53,7 +56,8 @@ import Testing
             subcommand: "rpc",
             defaults: defaults,
             configRoot: [:],
-            searchPaths: [tmp.appendingPathComponent("node_modules/.bin").path])
+            searchPaths: [tmp.appendingPathComponent("node_modules/.bin").path],
+            projectRoot: tmp)
 
         #expect(cmd.count >= 3)
         if cmd.count >= 3 {
@@ -67,7 +71,6 @@ import Testing
         let defaults = self.makeLocalDefaults()
 
         let tmp = try makeTempDirForTests()
-        CommandResolver.setProjectRoot(tmp.path)
 
         let binDir = tmp.appendingPathComponent("bin")
         let openclawPath = binDir.appendingPathComponent("openclaw")
@@ -79,7 +82,8 @@ import Testing
             subcommand: "rpc",
             defaults: defaults,
             configRoot: [:],
-            searchPaths: [binDir.path])
+            searchPaths: [binDir.path],
+            projectRoot: tmp)
 
         #expect(cmd.prefix(2).elementsEqual([openclawPath.path, "rpc"]))
     }
@@ -88,7 +92,6 @@ import Testing
         let defaults = self.makeLocalDefaults()
 
         let tmp = try makeTempDirForTests()
-        CommandResolver.setProjectRoot(tmp.path)
 
         let binDir = tmp.appendingPathComponent("bin")
         let openclawPath = binDir.appendingPathComponent("openclaw")
@@ -98,7 +101,8 @@ import Testing
             subcommand: "gateway",
             defaults: defaults,
             configRoot: [:],
-            searchPaths: [binDir.path])
+            searchPaths: [binDir.path],
+            projectRoot: tmp)
 
         #expect(cmd.prefix(2).elementsEqual([openclawPath.path, "gateway"]))
     }
@@ -133,9 +137,11 @@ import Testing
 
     @Test func `preferred paths start with project node bins`() throws {
         let tmp = try makeTempDirForTests()
-        CommandResolver.setProjectRoot(tmp.path)
 
-        let first = CommandResolver.preferredPaths().first
+        let first = CommandResolver.preferredPaths(
+            home: FileManager().homeDirectoryForCurrentUser,
+            current: [],
+            projectRoot: tmp).first
         #expect(first == tmp.appendingPathComponent("node_modules/.bin").path)
     }
 
@@ -182,7 +188,6 @@ import Testing
         defaults.set("openclaw@example.com:2222", forKey: remoteTargetKey)
 
         let tmp = try makeTempDirForTests()
-        CommandResolver.setProjectRoot(tmp.path)
 
         let openclawPath = tmp.appendingPathComponent("node_modules/.bin/openclaw")
         try makeExecutableForTests(at: openclawPath)
@@ -190,7 +195,9 @@ import Testing
         let cmd = CommandResolver.openclawCommand(
             subcommand: "daemon",
             defaults: defaults,
-            configRoot: ["gateway": ["mode": "local"]])
+            configRoot: ["gateway": ["mode": "local"]],
+            searchPaths: [tmp.appendingPathComponent("node_modules/.bin").path],
+            projectRoot: tmp)
 
         #expect(cmd.first == openclawPath.path)
         #expect(cmd.count >= 2)

apps/macos/Tests/OpenClawIPCTests/TalkModeGatewayConfigTests.swift

@@ -0,0 +1,48 @@
+import OpenClawProtocol
+import Testing
+@testable import OpenClaw
+
+struct TalkModeGatewayConfigTests {
+    @Test func `mlx provider does not inherit elevenlabs defaults`() {
+        let snapshot = ConfigSnapshot(
+            path: nil,
+            exists: true,
+            raw: nil,
+            hash: nil,
+            parsed: nil,
+            valid: true,
+            config: [
+                "talk": AnyCodable([
+                    "provider": "mlx",
+                    "providers": [
+                        "mlx": [
+                            "voiceId": "unused-voice",
+                        ],
+                    ],
+                    "resolved": [
+                        "provider": "mlx",
+                        "config": [
+                            "voiceId": "unused-voice",
+                        ],
+                    ],
+                ]),
+            ],
+            issues: nil
+        )
+
+        let parsed = TalkModeGatewayConfigParser.parse(
+            snapshot: snapshot,
+            defaultProvider: "elevenlabs",
+            defaultModelIdFallback: "eleven_v3",
+            defaultSilenceTimeoutMs: TalkDefaults.silenceTimeoutMs,
+            envVoice: "env-voice",
+            sagVoice: "sag-voice",
+            envApiKey: "env-key"
+        )
+
+        #expect(parsed.activeProvider == "mlx")
+        #expect(parsed.modelId == nil)
+        #expect(parsed.apiKey == nil)
+        #expect(parsed.voiceId == "unused-voice")
+    }
+}

apps/macos/Tests/OpenClawIPCTests/TalkModeRuntimeSpeechTests.swift

@@ -13,11 +13,34 @@ struct TalkModeRuntimeSpeechTests {
     }
 
     @Test func `playback plan falls back only from elevenlabs`() {
-        #expect(
-            TalkModeRuntime.playbackPlan(apiKey: "key", voiceId: "voice")
-                == .elevenLabsThenSystemVoice(apiKey: "key", voiceId: "voice"))
-        #expect(TalkModeRuntime.playbackPlan(apiKey: nil, voiceId: "voice") == .systemVoiceOnly)
-        #expect(TalkModeRuntime.playbackPlan(apiKey: "key", voiceId: nil) == .systemVoiceOnly)
-        #expect(TalkModeRuntime.playbackPlan(apiKey: "", voiceId: "voice") == .systemVoiceOnly)
+        let elevenLabsPlan = TalkModeRuntime.playbackPlan(
+            provider: "elevenlabs",
+            apiKey: "key",
+            voiceId: "voice"
+        )
+        let missingKeyPlan = TalkModeRuntime.playbackPlan(
+            provider: "elevenlabs",
+            apiKey: nil,
+            voiceId: "voice"
+        )
+        let missingVoicePlan = TalkModeRuntime.playbackPlan(
+            provider: "elevenlabs",
+            apiKey: "key",
+            voiceId: nil
+        )
+        let blankKeyPlan = TalkModeRuntime.playbackPlan(
+            provider: "elevenlabs",
+            apiKey: "",
+            voiceId: "voice"
+        )
+        let mlxPlan = TalkModeRuntime.playbackPlan(provider: "mlx", apiKey: nil, voiceId: nil)
+        let systemPlan = TalkModeRuntime.playbackPlan(provider: "system", apiKey: nil, voiceId: nil)
+
+        #expect(elevenLabsPlan == .elevenLabsThenSystemVoice(apiKey: "key", voiceId: "voice"))
+        #expect(missingKeyPlan == .systemVoiceOnly)
+        #expect(missingVoicePlan == .systemVoiceOnly)
+        #expect(blankKeyPlan == .systemVoiceOnly)
+        #expect(mlxPlan == .mlxThenSystemVoice)
+        #expect(systemPlan == .systemVoiceOnly)
     }
 }

apps/shared/OpenClawKit/Sources/OpenClawProtocol/GatewayModels.swift

@@ -2837,6 +2837,7 @@ public struct ModelChoice: Codable, Sendable {
     public let id: String
     public let name: String
     public let provider: String
+    public let alias: String?
     public let contextwindow: Int?
     public let reasoning: Bool?
 
@@ -2844,12 +2845,14 @@ public struct ModelChoice: Codable, Sendable {
         id: String,
         name: String,
         provider: String,
+        alias: String?,
         contextwindow: Int?,
         reasoning: Bool?)
     {
         self.id = id
         self.name = name
         self.provider = provider
+        self.alias = alias
         self.contextwindow = contextwindow
         self.reasoning = reasoning
     }
@@ -2858,6 +2861,7 @@ public struct ModelChoice: Codable, Sendable {
         case id
         case name
         case provider
+        case alias
         case contextwindow = "contextWindow"
         case reasoning
     }

docs/.generated/plugin-sdk-api-baseline.sha256

@@ -1,2 +1,2 @@
-763d2709dd26f4ec7d5807b2f1781b7f58cb115d2b0a9c9235a6c2c7b3788c1f  plugin-sdk-api-baseline.json
-87ab9ec219f037b13a8f42378d1fed02701d4035da0e5eca8a091626e8426523  plugin-sdk-api-baseline.jsonl
+087dc7fe9759330c953a00130ea20242b3d7f460eaa530d631cfb2a9f96e0370  plugin-sdk-api-baseline.json
+a84765a726e0493dc87d2799020fd454407b1fe2c4d3ad69e8c3cc3a0cde834b  plugin-sdk-api-baseline.jsonl

docs/automation/tasks.md

@@ -180,7 +180,7 @@ The lookup token accepts a task ID, run ID, or session key. Shows the full recor
 openclaw tasks cancel <lookup>
 ```
 
-For ACP and subagent tasks, this kills the child session. Status transitions to `cancelled` and a delivery notification is sent.
+For ACP and subagent tasks, this kills the child session. For CLI-tracked tasks, cancellation is recorded in the task registry (there is no separate child runtime handle). Status transitions to `cancelled` and a delivery notification is sent when applicable.
 
 ### `tasks notify`
 

docs/ci.md

@@ -21,7 +21,7 @@ The CI runs on every push to `main` and every pull request. It uses smart scopin
 | `checks-fast-extensions` | Aggregate the extension shard lanes after `checks-fast-extensions-shard` completes       | Node-relevant changes               |
 | `extension-fast`         | Focused tests for only the changed bundled plugins                                       | When extension changes are detected |
 | `check`                  | Main local gate in CI: `pnpm check` plus `pnpm build:strict-smoke`                       | Node-relevant changes               |
-| `check-additional`       | Architecture and boundary guards plus the gateway watch regression harness               | Node-relevant changes               |
+| `check-additional`       | Architecture, boundary, import-cycle guards plus the gateway watch regression harness    | Node-relevant changes               |
 | `build-smoke`            | Built-CLI smoke tests and startup-memory smoke                                           | Node-relevant changes               |
 | `checks`                 | Heavier Linux Node lanes: full tests, channel tests, and push-only Node 22 compatibility | Node-relevant changes               |
 | `check-docs`             | Docs formatting, lint, and broken-link checks                                            | Docs changed                        |
@@ -58,6 +58,7 @@ On pushes, the `checks` matrix adds the push-only `compat-node22` lane. On pull
 ```bash
 pnpm check          # types + lint + format
 pnpm build:strict-smoke
+pnpm check:import-cycles
 pnpm test:gateway:watch-regression
 pnpm test           # vitest tests
 pnpm test:channels

docs/cli/memory.md

@@ -167,4 +167,8 @@ Notes:
 - If effectively active memory remote API key fields are configured as SecretRefs, the command resolves those values from the active gateway snapshot. If gateway is unavailable, the command fails fast.
 - Gateway version skew note: this command path requires a gateway that supports `secrets.resolve`; older gateways return an unknown-method error.
 - Tune scheduled sweep cadence with `dreaming.frequency`. Deep promotion policy is otherwise internal; use CLI flags on `memory promote` when you need one-off manual overrides.
+- `memory rem-harness --path <file-or-dir> --grounded` previews grounded `What Happened`, `Reflections`, and `Possible Lasting Updates` from historical daily notes without writing anything.
+- `memory rem-backfill --path <file-or-dir>` writes reversible grounded diary entries into `DREAMS.md` for UI review.
+- `memory rem-backfill --path <file-or-dir> --stage-short-term` also seeds grounded durable candidates into the live short-term promotion store so the normal deep phase can rank them.
+- `memory rem-backfill --rollback` removes previously written grounded diary entries, and `memory rem-backfill --rollback-short-term` removes previously staged grounded short-term candidates.
 - See [Dreaming](/concepts/dreaming) for full phase descriptions and configuration reference.

docs/concepts/active-memory.md

@@ -0,0 +1,608 @@
+---
+title: "Active Memory"
+summary: "A plugin-owned blocking memory sub-agent that injects relevant memory into interactive chat sessions"
+read_when:
+  - You want to understand what active memory is for
+  - You want to turn active memory on for a conversational agent
+  - You want to tune active memory behavior without enabling it everywhere
+---
+
+# Active Memory
+
+Active memory is an optional plugin-owned blocking memory sub-agent that runs
+before the main reply for eligible conversational sessions.
+
+It exists because most memory systems are capable but reactive. They rely on
+the main agent to decide when to search memory, or on the user to say things
+like "remember this" or "search memory." By then, the moment where memory would
+have made the reply feel natural has already passed.
+
+Active memory gives the system one bounded chance to surface relevant memory
+before the main reply is generated.
+
+## Paste This Into Your Agent
+
+Paste this into your agent if you want it to enable Active Memory with a
+self-contained, safe-default setup:
+
+```json5
+{
+  plugins: {
+    entries: {
+      "active-memory": {
+        enabled: true,
+        config: {
+          enabled: true,
+          agents: ["main"],
+          allowedChatTypes: ["direct"],
+          modelFallbackPolicy: "default-remote",
+          queryMode: "recent",
+          promptStyle: "balanced",
+          timeoutMs: 15000,
+          maxSummaryChars: 220,
+          persistTranscripts: false,
+          logging: true,
+        },
+      },
+    },
+  },
+}
+```
+
+This turns the plugin on for the `main` agent, keeps it limited to direct-message
+style sessions by default, lets it inherit the current session model first, and
+still allows the built-in remote fallback if no explicit or inherited model is
+available.
+
+After that, restart the gateway:
+
+```bash
+node scripts/run-node.mjs gateway --profile dev
+```
+
+To inspect it live in a conversation:
+
+```text
+/verbose on
+```
+
+## Turn active memory on
+
+The safest setup is:
+
+1. enable the plugin
+2. target one conversational agent
+3. keep logging on only while tuning
+
+Start with this in `openclaw.json`:
+
+```json5
+{
+  plugins: {
+    entries: {
+      "active-memory": {
+        enabled: true,
+        config: {
+          agents: ["main"],
+          allowedChatTypes: ["direct"],
+          modelFallbackPolicy: "default-remote",
+          queryMode: "recent",
+          promptStyle: "balanced",
+          timeoutMs: 15000,
+          maxSummaryChars: 220,
+          persistTranscripts: false,
+          logging: true,
+        },
+      },
+    },
+  },
+}
+```
+
+Then restart the gateway:
+
+```bash
+node scripts/run-node.mjs gateway --profile dev
+```
+
+What this means:
+
+- `plugins.entries.active-memory.enabled: true` turns the plugin on
+- `config.agents: ["main"]` opts only the `main` agent into active memory
+- `config.allowedChatTypes: ["direct"]` keeps active memory on for direct-message style sessions only by default
+- if `config.model` is unset, active memory inherits the current session model first
+- `config.modelFallbackPolicy: "default-remote"` keeps the built-in remote fallback as the default when no explicit or inherited model is available
+- `config.promptStyle: "balanced"` uses the default general-purpose prompt style for `recent` mode
+- active memory still runs only on eligible interactive persistent chat sessions
+
+## How to see it
+
+Active memory injects hidden system context for the model. It does not expose
+raw `<active_memory_plugin>...</active_memory_plugin>` tags to the client.
+
+## Session toggle
+
+Use the plugin command when you want to pause or resume active memory for the
+current chat session without editing config:
+
+```text
+/active-memory status
+/active-memory off
+/active-memory on
+```
+
+This is session-scoped. It does not change
+`plugins.entries.active-memory.enabled`, agent targeting, or other global
+configuration.
+
+If you want the command to write config and pause or resume active memory for
+all sessions, use the explicit global form:
+
+```text
+/active-memory status --global
+/active-memory off --global
+/active-memory on --global
+```
+
+The global form writes `plugins.entries.active-memory.config.enabled`. It leaves
+`plugins.entries.active-memory.enabled` on so the command remains available to
+turn active memory back on later.
+
+If you want to see what active memory is doing in a live session, turn verbose
+mode on for that session:
+
+```text
+/verbose on
+```
+
+With verbose enabled, OpenClaw can show:
+
+- an active memory status line such as `Active Memory: ok 842ms recent 34 chars`
+- a readable debug summary such as `Active Memory Debug: Lemon pepper wings with blue cheese.`
+
+Those lines are derived from the same active memory pass that feeds the hidden
+system context, but they are formatted for humans instead of exposing raw prompt
+markup.
+
+By default, the blocking memory sub-agent transcript is temporary and deleted
+after the run completes.
+
+Example flow:
+
+```text
+/verbose on
+what wings should i order?
+```
+
+Expected visible reply shape:
+
+```text
+...normal assistant reply...
+
+🧩 Active Memory: ok 842ms recent 34 chars
+🔎 Active Memory Debug: Lemon pepper wings with blue cheese.
+```
+
+## When it runs
+
+Active memory uses two gates:
+
+1. **Config opt-in**
+   The plugin must be enabled, and the current agent id must appear in
+   `plugins.entries.active-memory.config.agents`.
+2. **Strict runtime eligibility**
+   Even when enabled and targeted, active memory only runs for eligible
+   interactive persistent chat sessions.
+
+The actual rule is:
+
+```text
+plugin enabled
++
+agent id targeted
++
+allowed chat type
++
+eligible interactive persistent chat session
+=
+active memory runs
+```
+
+If any of those fail, active memory does not run.
+
+## Session types
+
+`config.allowedChatTypes` controls which kinds of conversations may run Active
+Memory at all.
+
+The default is:
+
+```json5
+allowedChatTypes: ["direct"]
+```
+
+That means Active Memory runs by default in direct-message style sessions, but
+not in group or channel sessions unless you opt them in explicitly.
+
+Examples:
+
+```json5
+allowedChatTypes: ["direct"]
+```
+
+```json5
+allowedChatTypes: ["direct", "group"]
+```
+
+```json5
+allowedChatTypes: ["direct", "group", "channel"]
+```
+
+## Where it runs
+
+Active memory is a conversational enrichment feature, not a platform-wide
+inference feature.
+
+| Surface                                                             | Runs active memory?                                     |
+| ------------------------------------------------------------------- | ------------------------------------------------------- |
+| Control UI / web chat persistent sessions                           | Yes, if the plugin is enabled and the agent is targeted |
+| Other interactive channel sessions on the same persistent chat path | Yes, if the plugin is enabled and the agent is targeted |
+| Headless one-shot runs                                              | No                                                      |
+| Heartbeat/background runs                                           | No                                                      |
+| Generic internal `agent-command` paths                              | No                                                      |
+| Sub-agent/internal helper execution                                 | No                                                      |
+
+## Why use it
+
+Use active memory when:
+
+- the session is persistent and user-facing
+- the agent has meaningful long-term memory to search
+- continuity and personalization matter more than raw prompt determinism
+
+It works especially well for:
+
+- stable preferences
+- recurring habits
+- long-term user context that should surface naturally
+
+It is a poor fit for:
+
+- automation
+- internal workers
+- one-shot API tasks
+- places where hidden personalization would be surprising
+
+## How it works
+
+The runtime shape is:
+
+```mermaid
+flowchart LR
+  U["User Message"] --> Q["Build Memory Query"]
+  Q --> R["Active Memory Blocking Memory Sub-Agent"]
+  R -->|NONE or empty| M["Main Reply"]
+  R -->|relevant summary| I["Append Hidden active_memory_plugin System Context"]
+  I --> M["Main Reply"]
+```
+
+The blocking memory sub-agent can use only:
+
+- `memory_search`
+- `memory_get`
+
+If the connection is weak, it should return `NONE`.
+
+## Query modes
+
+`config.queryMode` controls how much conversation the blocking memory sub-agent sees.
+
+## Prompt styles
+
+`config.promptStyle` controls how eager or strict the blocking memory sub-agent is
+when deciding whether to return memory.
+
+Available styles:
+
+- `balanced`: general-purpose default for `recent` mode
+- `strict`: least eager; best when you want very little bleed from nearby context
+- `contextual`: most continuity-friendly; best when conversation history should matter more
+- `recall-heavy`: more willing to surface memory on softer but still plausible matches
+- `precision-heavy`: aggressively prefers `NONE` unless the match is obvious
+- `preference-only`: optimized for favorites, habits, routines, taste, and recurring personal facts
+
+Default mapping when `config.promptStyle` is unset:
+
+```text
+message -> strict
+recent -> balanced
+full -> contextual
+```
+
+If you set `config.promptStyle` explicitly, that override wins.
+
+Example:
+
+```json5
+promptStyle: "preference-only"
+```
+
+## Model fallback policy
+
+If `config.model` is unset, Active Memory tries to resolve a model in this order:
+
+```text
+explicit plugin model
+-> current session model
+-> agent primary model
+-> optional built-in remote fallback
+```
+
+`config.modelFallbackPolicy` controls the last step.
+
+Default:
+
+```json5
+modelFallbackPolicy: "default-remote"
+```
+
+Other option:
+
+```json5
+modelFallbackPolicy: "resolved-only"
+```
+
+Use `resolved-only` if you want Active Memory to skip recall instead of falling
+back to the built-in remote default when no explicit or inherited model is
+available.
+
+## Advanced escape hatches
+
+These options are intentionally not part of the recommended setup.
+
+`config.thinking` can override the blocking memory sub-agent thinking level:
+
+```json5
+thinking: "medium"
+```
+
+Default:
+
+```json5
+thinking: "off"
+```
+
+Do not enable this by default. Active Memory runs in the reply path, so extra
+thinking time directly increases user-visible latency.
+
+`config.promptAppend` adds extra operator instructions after the default Active
+Memory prompt and before the conversation context:
+
+```json5
+promptAppend: "Prefer stable long-term preferences over one-off events."
+```
+
+`config.promptOverride` replaces the default Active Memory prompt. OpenClaw
+still appends the conversation context afterward:
+
+```json5
+promptOverride: "You are a memory search agent. Return NONE or one compact user fact."
+```
+
+Prompt customization is not recommended unless you are deliberately testing a
+different recall contract. The default prompt is tuned to return either `NONE`
+or compact user-fact context for the main model.
+
+### `message`
+
+Only the latest user message is sent.
+
+```text
+Latest user message only
+```
+
+Use this when:
+
+- you want the fastest behavior
+- you want the strongest bias toward stable preference recall
+- follow-up turns do not need conversational context
+
+Recommended timeout:
+
+- start around `3000` to `5000` ms
+
+### `recent`
+
+The latest user message plus a small recent conversational tail is sent.
+
+```text
+Recent conversation tail:
+user: ...
+assistant: ...
+user: ...
+
+Latest user message:
+...
+```
+
+Use this when:
+
+- you want a better balance of speed and conversational grounding
+- follow-up questions often depend on the last few turns
+
+Recommended timeout:
+
+- start around `15000` ms
+
+### `full`
+
+The full conversation is sent to the blocking memory sub-agent.
+
+```text
+Full conversation context:
+user: ...
+assistant: ...
+user: ...
+...
+```
+
+Use this when:
+
+- the strongest recall quality matters more than latency
+- the conversation contains important setup far back in the thread
+
+Recommended timeout:
+
+- increase it substantially compared with `message` or `recent`
+- start around `15000` ms or higher depending on thread size
+
+In general, timeout should increase with context size:
+
+```text
+message < recent < full
+```
+
+## Transcript persistence
+
+Active memory blocking memory sub-agent runs create a real `session.jsonl`
+transcript during the blocking memory sub-agent call.
+
+By default, that transcript is temporary:
+
+- it is written to a temp directory
+- it is used only for the blocking memory sub-agent run
+- it is deleted immediately after the run finishes
+
+If you want to keep those blocking memory sub-agent transcripts on disk for debugging or
+inspection, turn persistence on explicitly:
+
+```json5
+{
+  plugins: {
+    entries: {
+      "active-memory": {
+        enabled: true,
+        config: {
+          agents: ["main"],
+          persistTranscripts: true,
+          transcriptDir: "active-memory",
+        },
+      },
+    },
+  },
+}
+```
+
+When enabled, active memory stores transcripts in a separate directory under the
+target agent's sessions folder, not in the main user conversation transcript
+path.
+
+The default layout is conceptually:
+
+```text
+agents/<agent>/sessions/active-memory/<blocking-memory-sub-agent-session-id>.jsonl
+```
+
+You can change the relative subdirectory with `config.transcriptDir`.
+
+Use this carefully:
+
+- blocking memory sub-agent transcripts can accumulate quickly on busy sessions
+- `full` query mode can duplicate a lot of conversation context
+- these transcripts contain hidden prompt context and recalled memories
+
+## Configuration
+
+All active memory configuration lives under:
+
+```text
+plugins.entries.active-memory
+```
+
+The most important fields are:
+
+| Key                         | Type                                                                                                 | Meaning                                                                                                |
+| --------------------------- | ---------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |
+| `enabled`                   | `boolean`                                                                                            | Enables the plugin itself                                                                              |
+| `config.agents`             | `string[]`                                                                                           | Agent ids that may use active memory                                                                   |
+| `config.model`              | `string`                                                                                             | Optional blocking memory sub-agent model ref; when unset, active memory uses the current session model |
+| `config.queryMode`          | `"message" \| "recent" \| "full"`                                                                    | Controls how much conversation the blocking memory sub-agent sees                                      |
+| `config.promptStyle`        | `"balanced" \| "strict" \| "contextual" \| "recall-heavy" \| "precision-heavy" \| "preference-only"` | Controls how eager or strict the blocking memory sub-agent is when deciding whether to return memory   |
+| `config.thinking`           | `"off" \| "minimal" \| "low" \| "medium" \| "high" \| "xhigh" \| "adaptive"`                         | Advanced thinking override for the blocking memory sub-agent; default `off` for speed                  |
+| `config.promptOverride`     | `string`                                                                                             | Advanced full prompt replacement; not recommended for normal use                                       |
+| `config.promptAppend`       | `string`                                                                                             | Advanced extra instructions appended to the default or overridden prompt                               |
+| `config.timeoutMs`          | `number`                                                                                             | Hard timeout for the blocking memory sub-agent                                                         |
+| `config.maxSummaryChars`    | `number`                                                                                             | Maximum total characters allowed in the active-memory summary                                          |
+| `config.logging`            | `boolean`                                                                                            | Emits active memory logs while tuning                                                                  |
+| `config.persistTranscripts` | `boolean`                                                                                            | Keeps blocking memory sub-agent transcripts on disk instead of deleting temp files                     |
+| `config.transcriptDir`      | `string`                                                                                             | Relative blocking memory sub-agent transcript directory under the agent sessions folder                |
+
+Useful tuning fields:
+
+| Key                           | Type     | Meaning                                                       |
+| ----------------------------- | -------- | ------------------------------------------------------------- |
+| `config.maxSummaryChars`      | `number` | Maximum total characters allowed in the active-memory summary |
+| `config.recentUserTurns`      | `number` | Prior user turns to include when `queryMode` is `recent`      |
+| `config.recentAssistantTurns` | `number` | Prior assistant turns to include when `queryMode` is `recent` |
+| `config.recentUserChars`      | `number` | Max chars per recent user turn                                |
+| `config.recentAssistantChars` | `number` | Max chars per recent assistant turn                           |
+| `config.cacheTtlMs`           | `number` | Cache reuse for repeated identical queries                    |
+
+## Recommended setup
+
+Start with `recent`.
+
+```json5
+{
+  plugins: {
+    entries: {
+      "active-memory": {
+        enabled: true,
+        config: {
+          agents: ["main"],
+          queryMode: "recent",
+          promptStyle: "balanced",
+          timeoutMs: 15000,
+          maxSummaryChars: 220,
+          logging: true,
+        },
+      },
+    },
+  },
+}
+```
+
+If you want to inspect live behavior while tuning, use `/verbose on` in the
+session instead of looking for a separate active-memory debug command.
+
+Then move to:
+
+- `message` if you want lower latency
+- `full` if you decide extra context is worth the slower blocking memory sub-agent
+
+## Debugging
+
+If active memory is not showing up where you expect:
+
+1. Confirm the plugin is enabled under `plugins.entries.active-memory.enabled`.
+2. Confirm the current agent id is listed in `config.agents`.
+3. Confirm you are testing through an interactive persistent chat session.
+4. Turn on `config.logging: true` and watch the gateway logs.
+5. Verify memory search itself works with `openclaw memory status --deep`.
+
+If memory hits are noisy, tighten:
+
+- `maxSummaryChars`
+
+If active memory is too slow:
+
+- lower `queryMode`
+- lower `timeoutMs`
+- reduce recent turn counts
+- reduce per-turn char caps
+
+## Related pages
+
+- [Memory Search](/concepts/memory-search)
+- [Memory configuration reference](/reference/memory-config)
+- [Plugin SDK setup](/plugins/sdk-setup)

docs/concepts/dreaming.md

@@ -81,6 +81,20 @@ subagent turn (using the default runtime model) and appends a short diary entry.
 
 This diary is for human reading in the Dreams UI, not a promotion source.
 
+There is also a grounded historical backfill lane for review and recovery work:
+
+- `memory rem-harness --path ... --grounded` previews grounded diary output from historical `YYYY-MM-DD.md` notes.
+- `memory rem-backfill --path ...` writes reversible grounded diary entries into `DREAMS.md`.
+- `memory rem-backfill --path ... --stage-short-term` stages grounded durable candidates into the same short-term evidence store the normal deep phase already uses.
+- `memory rem-backfill --rollback` and `--rollback-short-term` remove those staged backfill artifacts without touching ordinary diary entries or live short-term recall.
+
+The Control UI exposes the same diary backfill/reset flow so you can inspect
+results in the Dreams scene before deciding whether the grounded candidates
+deserve promotion. The Scene also shows a distinct grounded lane so you can see
+which staged short-term entries came from historical replay, which promoted
+items were grounded-led, and clear only grounded-only staged entries without
+touching ordinary live short-term state.
+
 ## Deep ranking signals
 
 Deep ranking uses six weighted base signals plus phase reinforcement:
@@ -207,8 +221,9 @@ When enabled, the Gateway **Dreams** tab shows:
 
 - current dreaming enabled state
 - phase-level status and managed-sweep presence
-- short-term, long-term, and promoted-today counts
+- short-term, grounded, signal, and promoted-today counts
 - next scheduled run timing
+- a distinct grounded Scene lane for staged historical replay entries
 - an expandable Dream Diary reader backed by `doctor.memory.dreamDiary`
 
 ## Related

docs/concepts/memory-search.md

@@ -138,5 +138,6 @@ earlier conversations. This is opt-in via
 
 ## Further reading
 
+- [Active Memory](/concepts/active-memory) -- sub-agent memory for interactive chat sessions
 - [Memory](/concepts/memory) -- file layout, backends, tools
 - [Memory configuration reference](/reference/memory-config) -- all config knobs

docs/concepts/memory.md

@@ -21,7 +21,7 @@ Your agent has three memory-related files:
 - **`memory/YYYY-MM-DD.md`** -- daily notes. Running context and observations.
   Today and yesterday's notes are loaded automatically.
 - **`DREAMS.md`** (experimental, optional) -- Dream Diary and dreaming sweep
-  summaries for human review.
+  summaries for human review, including grounded historical backfill entries.
 
 These files live in the agent workspace (default `~/.openclaw/workspace`).
 
@@ -133,6 +133,41 @@ It is designed to keep long-term memory high signal:
 For phase behavior, scoring signals, and Dream Diary details, see
 [Dreaming (experimental)](/concepts/dreaming).
 
+## Grounded backfill and live promotion
+
+The dreaming system now has two closely related review lanes:
+
+- **Live dreaming** works from the short-term dreaming store under
+  `memory/.dreams/` and is what the normal deep phase uses when deciding what
+  can graduate into `MEMORY.md`.
+- **Grounded backfill** reads historical `memory/YYYY-MM-DD.md` notes as
+  standalone day files and writes structured review output into `DREAMS.md`.
+
+Grounded backfill is useful when you want to replay older notes and inspect what
+the system thinks is durable without manually editing `MEMORY.md`.
+
+When you use:
+
+```bash
+openclaw memory rem-backfill --path ./memory --stage-short-term
+```
+
+the grounded durable candidates are not promoted directly. They are staged into
+the same short-term dreaming store the normal deep phase already uses. That
+means:
+
+- `DREAMS.md` stays the human review surface.
+- the short-term store stays the machine-facing ranking surface.
+- `MEMORY.md` is still only written by deep promotion.
+
+If you decide the replay was not useful, you can remove the staged artifacts
+without touching ordinary diary entries or normal recall state:
+
+```bash
+openclaw memory rem-backfill --rollback
+openclaw memory rem-backfill --rollback-short-term
+```
+
 ## CLI
 
 ```bash

docs/concepts/qa-e2e-automation.md

@@ -52,6 +52,21 @@ pnpm qa:lab:watch
 rebuilds that bundle on change, and the browser auto-reloads when the QA Lab
 asset hash changes.
 
+For a disposable Linux VM lane without bringing Docker into the QA path, run:
+
+```bash
+pnpm openclaw qa suite --runner multipass --scenario channel-chat-baseline
+```
+
+This boots a fresh Multipass guest, installs dependencies, builds OpenClaw
+inside the guest, runs `qa suite`, then copies the normal QA report and
+summary back into `.artifacts/qa-e2e/...` on the host.
+It reuses the same scenario-selection behavior as `qa suite` on the host.
+Live runs forward the supported QA auth inputs that are practical for the
+guest: env-based provider keys, the QA live provider config path, and
+`CODEX_HOME` when present. Keep `--output-dir` under the repo root so the guest
+can write back through the mounted workspace.
+
 ## Repo-backed seeds
 
 Seed assets live in `qa/`:
@@ -89,18 +104,17 @@ refs and write a judged Markdown report:
 pnpm openclaw qa character-eval \
   --model openai/gpt-5.4,thinking=xhigh \
   --model openai/gpt-5.2,thinking=xhigh \
+  --model openai/gpt-5,thinking=xhigh \
   --model anthropic/claude-opus-4-6,thinking=high \
   --model anthropic/claude-sonnet-4-6,thinking=high \
-  --model minimax/MiniMax-M2.7,thinking=high \
   --model zai/glm-5.1,thinking=high \
   --model moonshot/kimi-k2.5,thinking=high \
-  --model qwen/qwen3.6-plus,thinking=high \
-  --model xiaomi/mimo-v2-pro,thinking=high \
   --model google/gemini-3.1-pro-preview,thinking=high \
   --judge-model openai/gpt-5.4,thinking=xhigh,fast \
   --judge-model anthropic/claude-opus-4-6,thinking=high \
-  --concurrency 8 \
-  --judge-concurrency 8
+  --blind-judge-models \
+  --concurrency 16 \
+  --judge-concurrency 16
 ```
 
 The command runs local QA gateway child processes, not Docker. Character eval
@@ -109,6 +123,10 @@ such as chat, workspace help, and small file tasks. The candidate model should
 not be told that it is being evaluated. The command preserves each full
 transcript, records basic run stats, then asks the judge models in fast mode with
 `xhigh` reasoning to rank the runs by naturalness, vibe, and humor.
+Use `--blind-judge-models` when comparing providers: the judge prompt still gets
+every transcript and run status, but candidate refs are replaced with neutral
+labels such as `candidate-01`; the report maps rankings back to real refs after
+parsing.
 Candidate runs default to `high` thinking, with `xhigh` for OpenAI models that
 support it. Override a specific candidate inline with
 `--model provider/model,thinking=<level>`. `--thinking <level>` still sets a
@@ -120,14 +138,14 @@ single candidate or judge needs an override. Pass `--fast` only when you want to
 force fast mode on for every candidate model. Candidate and judge durations are
 recorded in the report for benchmark analysis, but judge prompts explicitly say
 not to rank by speed.
-Candidate and judge model runs both default to concurrency 8. Lower
+Candidate and judge model runs both default to concurrency 16. Lower
 `--concurrency` or `--judge-concurrency` when provider limits or local gateway
 pressure make a run too noisy.
 When no candidate `--model` is passed, the character eval defaults to
-`openai/gpt-5.4`, `openai/gpt-5.2`, `anthropic/claude-opus-4-6`,
-`anthropic/claude-sonnet-4-6`, `minimax/MiniMax-M2.7`, `zai/glm-5.1`,
-`moonshot/kimi-k2.5`, `qwen/qwen3.6-plus`, `xiaomi/mimo-v2-pro`, and
-`google/gemini-3.1-pro-preview`.
+`openai/gpt-5.4`, `openai/gpt-5.2`, `openai/gpt-5`, `anthropic/claude-opus-4-6`,
+`anthropic/claude-sonnet-4-6`, `zai/glm-5.1`,
+`moonshot/kimi-k2.5`, and
+`google/gemini-3.1-pro-preview` when no `--model` is passed.
 When no `--judge-model` is passed, the judges default to
 `openai/gpt-5.4,thinking=xhigh,fast` and
 `anthropic/claude-opus-4-6,thinking=high`.

docs/gateway/configuration-reference.md

@@ -2402,6 +2402,7 @@ OpenClaw uses the built-in model catalog. Add custom providers via `models.provi
   - `request.auth`: auth strategy override. Modes: `"provider-default"` (use provider's built-in auth), `"authorization-bearer"` (with `token`), `"header"` (with `headerName`, `value`, optional `prefix`).
   - `request.proxy`: HTTP proxy override. Modes: `"env-proxy"` (use `HTTP_PROXY`/`HTTPS_PROXY` env vars), `"explicit-proxy"` (with `url`). Both modes accept an optional `tls` sub-object.
   - `request.tls`: TLS override for direct connections. Fields: `ca`, `cert`, `key`, `passphrase` (all accept SecretRef), `serverName`, `insecureSkipVerify`.
+  - `request.allowPrivateNetwork`: when `true`, allow HTTPS to `baseUrl` when DNS resolves to private, CGNAT, or similar ranges, via the provider HTTP fetch guard (operator opt-in for trusted self-hosted OpenAI-compatible endpoints). WebSocket uses the same `request` for headers/TLS but not that fetch SSRF gate. Default `false`.
 - `models.providers.*.models`: explicit provider model catalog entries.
 - `models.providers.*.models.*.contextWindow`: native model context window metadata.
 - `models.providers.*.models.*.contextTokens`: optional runtime context cap. Use this when you want a smaller effective context budget than the model's native `contextWindow`.
@@ -2858,6 +2859,7 @@ See [Plugins](/tools/plugin).
       enabled: true,
       basePath: "/openclaw",
       // root: "dist/control-ui",
+      // embedSandbox: "powerful", // powerful | isolated
       // allowedOrigins: ["https://control.example.com"], // required for non-loopback Control UI
       // dangerouslyAllowHostHeaderOriginFallback: false, // dangerous Host-header origin fallback mode
       // allowInsecureAuth: false,

docs/gateway/doctor.md

@@ -93,6 +93,40 @@ cat ~/.openclaw/openclaw.json
 - Source install checks (pnpm workspace mismatch, missing UI assets, missing tsx binary).
 - Writes updated config + wizard metadata.
 
+## Dreams UI backfill and reset
+
+The Control UI Dreams scene includes **Backfill**, **Reset**, and **Clear Grounded**
+actions for the grounded dreaming workflow. These actions use gateway
+doctor-style RPC methods, but they are **not** part of `openclaw doctor` CLI
+repair/migration.
+
+What they do:
+
+- **Backfill** scans historical `memory/YYYY-MM-DD.md` files in the active
+  workspace, runs the grounded REM diary pass, and writes reversible backfill
+  entries into `DREAMS.md`.
+- **Reset** removes only those marked backfill diary entries from `DREAMS.md`.
+- **Clear Grounded** removes only staged grounded-only short-term entries that
+  came from historical replay and have not accumulated live recall or daily
+  support yet.
+
+What they do **not** do by themselves:
+
+- they do not edit `MEMORY.md`
+- they do not run full doctor migrations
+- they do not automatically stage grounded candidates into the live short-term
+  promotion store unless you explicitly run the staged CLI path first
+
+If you want grounded historical replay to influence the normal deep promotion
+lane, use the CLI flow instead:
+
+```bash
+openclaw memory rem-backfill --path ./memory --stage-short-term
+```
+
+That stages grounded durable candidates into the short-term dreaming store while
+keeping `DREAMS.md` as the review surface.
+
 ## Detailed behavior and rationale
 
 ### 0) Optional update (git installs)

docs/help/testing.md

@@ -26,7 +26,9 @@ Most days:
 - Faster local full-suite run on a roomy machine: `pnpm test:max`
 - Direct Vitest watch loop: `pnpm test:watch`
 - Direct file targeting now routes extension/channel paths too: `pnpm test extensions/discord/src/monitor/message-handler.preflight.test.ts`
+- Prefer targeted runs first when you are iterating on a single failure.
 - Docker-backed QA site: `pnpm qa:lab:up`
+- Linux VM-backed QA lane: `pnpm openclaw qa suite --runner multipass --scenario channel-chat-baseline`
 
 When you touch tests or want extra confidence:
 
@@ -40,6 +42,26 @@ When debugging real providers/models (requires real creds):
 
 Tip: when you only need one failing case, prefer narrowing live tests via the allowlist env vars described below.
 
+## QA-specific runners
+
+These commands sit beside the main test suites when you need QA-lab realism:
+
+- `pnpm openclaw qa suite`
+  - Runs repo-backed QA scenarios directly on the host.
+- `pnpm openclaw qa suite --runner multipass`
+  - Runs the same QA suite inside a disposable Multipass Linux VM.
+  - Keeps the same scenario-selection behavior as `qa suite` on the host.
+  - Reuses the same provider/model selection flags as `qa suite`.
+  - Live runs forward the supported QA auth inputs that are practical for the guest:
+    env-based provider keys, the QA live provider config path, and `CODEX_HOME`
+    when present.
+  - Output dirs must stay under the repo root so the guest can write back through
+    the mounted workspace.
+  - Writes the normal QA report + summary plus Multipass logs under
+    `.artifacts/qa-e2e/...`.
+- `pnpm qa:lab:up`
+  - Starts the Docker-backed QA site for operator-style QA work.
+
 ## Test suites (what runs where)
 
 Think of the suites as “increasing realism” (and increasing flakiness/cost):
@@ -203,6 +225,7 @@ Live tests are split into two layers so we can isolate failures:
   - `OPENCLAW_LIVE_MODELS=modern` to run the modern allowlist (Opus/Sonnet 4.6+, GPT-5.x + Codex, Gemini 3, GLM 4.7, MiniMax M2.7, Grok 4)
   - `OPENCLAW_LIVE_MODELS=all` is an alias for the modern allowlist
   - or `OPENCLAW_LIVE_MODELS="openai/gpt-5.4,anthropic/claude-opus-4-6,..."` (comma allowlist)
+  - Modern/all sweeps default to a curated high-signal cap; set `OPENCLAW_LIVE_MAX_MODELS=0` for an exhaustive modern sweep or a positive number for a smaller cap.
 - How to select providers:
   - `OPENCLAW_LIVE_PROVIDERS="google,google-antigravity,google-gemini-cli"` (comma allowlist)
 - Where keys come from:
@@ -234,6 +257,7 @@ Live tests are split into two layers so we can isolate failures:
   - Default: modern allowlist (Opus/Sonnet 4.6+, GPT-5.x + Codex, Gemini 3, GLM 4.7, MiniMax M2.7, Grok 4)
   - `OPENCLAW_LIVE_GATEWAY_MODELS=all` is an alias for the modern allowlist
   - Or set `OPENCLAW_LIVE_GATEWAY_MODELS="provider/model"` (or comma list) to narrow
+  - Modern/all gateway sweeps default to a curated high-signal cap; set `OPENCLAW_LIVE_GATEWAY_MAX_MODELS=0` for an exhaustive modern sweep or a positive number for a smaller cap.
 - How to select providers (avoid “OpenRouter everything”):
   - `OPENCLAW_LIVE_GATEWAY_PROVIDERS="google,google-antigravity,google-gemini-cli,openai,anthropic,zai,minimax"` (comma allowlist)
 - Tool + image probes are always on in this live test:

docs/plans/2026-04-05-002-refactor-real-plugin-sdk-workspace-plan.md

@@ -1,580 +0,0 @@
----
-title: "refactor: Make plugin-sdk a real workspace package incrementally"
-type: refactor
-status: active
-date: 2026-04-05
----
-
-# refactor: Make plugin-sdk a real workspace package incrementally
-
-## Overview
-
-This plan introduces a real workspace package for the plugin SDK at
-`packages/plugin-sdk` and uses it to opt in a small first wave of extensions to
-compiler-enforced package boundaries. The goal is to make illegal relative
-imports fail under normal `tsc` for a selected set of bundled provider
-extensions, without forcing a repo-wide migration or a giant merge-conflict
-surface.
-
-The key incremental move is to run two modes in parallel for a while:
-
-| Mode        | Import shape             | Who uses it                          | Enforcement                                  |
-| ----------- | ------------------------ | ------------------------------------ | -------------------------------------------- |
-| Legacy mode | `openclaw/plugin-sdk/*`  | all existing non-opted-in extensions | current permissive behavior remains          |
-| Opt-in mode | `@openclaw/plugin-sdk/*` | first-wave extensions only           | package-local `rootDir` + project references |
-
-## Problem Frame
-
-The current repo exports a large public plugin SDK surface, but it is not a real
-workspace package. Instead:
-
-- root `tsconfig.json` maps `openclaw/plugin-sdk/*` directly to
-  `src/plugin-sdk/*.ts`
-- extensions that were not opted into the previous experiment still share that
-  global source-alias behavior
-- adding `rootDir` only works when allowed SDK imports stop resolving into raw
-  repo source
-
-That means the repo can describe the desired boundary policy, but TypeScript
-does not enforce it cleanly for most extensions.
-
-You want an incremental path that:
-
-- makes `plugin-sdk` real
-- moves the SDK toward a workspace package named `@openclaw/plugin-sdk`
-- changes only about 10 extensions in the first PR
-- leaves the rest of the extension tree on the old scheme until later cleanup
-- avoids the `tsconfig.plugin-sdk.dts.json` + postinstall-generated declaration
-  workflow as the primary mechanism for the first-wave rollout
-
-## Requirements Trace
-
-- R1. Create a real workspace package for the plugin SDK under `packages/`.
-- R2. Name the new package `@openclaw/plugin-sdk`.
-- R3. Give the new SDK package its own `package.json` and `tsconfig.json`.
-- R4. Keep legacy `openclaw/plugin-sdk/*` imports working for non-opted-in
-  extensions during the migration window.
-- R5. Opt in only a small first wave of extensions in the first PR.
-- R6. The first-wave extensions must fail closed for relative imports that leave
-  their package root.
-- R7. The first-wave extensions must consume the SDK through a package
-  dependency and a TS project reference, not through root `paths` aliases.
-- R8. The plan must avoid a repo-wide mandatory postinstall generation step for
-  editor correctness.
-- R9. The first-wave rollout must be reviewable and mergeable as a moderate PR,
-  not a repo-wide 300+ file refactor.
-
-## Scope Boundaries
-
-- No full migration of all bundled extensions in the first PR.
-- No requirement to delete `src/plugin-sdk` in the first PR.
-- No requirement to rewire every root build or test path to use the new package
-  immediately.
-- No attempt to force VS Code squiggles for every non-opted-in extension.
-- No broad lint cleanup for the rest of the extension tree.
-- No large runtime behavior changes beyond import resolution, package ownership,
-  and boundary enforcement for the opted-in extensions.
-
-## Context & Research
-
-### Relevant Code and Patterns
-
-- `pnpm-workspace.yaml` already includes `packages/*` and `extensions/*`, so a
-  new workspace package under `packages/plugin-sdk` fits the existing repo
-  layout.
-- Existing workspace packages such as `packages/memory-host-sdk/package.json`
-  and `packages/plugin-package-contract/package.json` already use package-local
-  `exports` maps rooted in `src/*.ts`.
-- Root `package.json` currently publishes the SDK surface through `./plugin-sdk`
-  and `./plugin-sdk/*` exports backed by `dist/plugin-sdk/*.js` and
-  `dist/plugin-sdk/*.d.ts`.
-- `src/plugin-sdk/entrypoints.ts` and `scripts/lib/plugin-sdk-entrypoints.json`
-  already act as the canonical entrypoint inventory for the SDK surface.
-- Root `tsconfig.json` currently maps:
-  - `openclaw/plugin-sdk` -> `src/plugin-sdk/index.ts`
-  - `openclaw/plugin-sdk/*` -> `src/plugin-sdk/*.ts`
-- The previous boundary experiment showed that package-local `rootDir` works for
-  illegal relative imports only after allowed SDK imports stop resolving to raw
-  source outside the extension package.
-
-### First-Wave Extension Set
-
-This plan assumes the first wave is the provider-heavy set that is least likely
-to drag in complex channel-runtime edge cases:
-
-- `extensions/anthropic`
-- `extensions/exa`
-- `extensions/firecrawl`
-- `extensions/groq`
-- `extensions/mistral`
-- `extensions/openai`
-- `extensions/perplexity`
-- `extensions/tavily`
-- `extensions/together`
-- `extensions/xai`
-
-### First-Wave SDK Surface Inventory
-
-The first-wave extensions currently import a manageable subset of SDK subpaths.
-The initial `@openclaw/plugin-sdk` package only needs to cover these:
-
-- `agent-runtime`
-- `cli-runtime`
-- `config-runtime`
-- `core`
-- `image-generation`
-- `media-runtime`
-- `media-understanding`
-- `plugin-entry`
-- `plugin-runtime`
-- `provider-auth`
-- `provider-auth-api-key`
-- `provider-auth-login`
-- `provider-auth-runtime`
-- `provider-catalog-shared`
-- `provider-entry`
-- `provider-http`
-- `provider-model-shared`
-- `provider-onboard`
-- `provider-stream-family`
-- `provider-stream-shared`
-- `provider-tools`
-- `provider-usage`
-- `provider-web-fetch`
-- `provider-web-search`
-- `realtime-transcription`
-- `realtime-voice`
-- `runtime-env`
-- `secret-input`
-- `security-runtime`
-- `speech`
-- `testing`
-
-### Institutional Learnings
-
-- No relevant `docs/solutions/` entries were present in this worktree.
-
-### External References
-
-- No external research was needed for this plan. The repo already contains the
-  relevant workspace-package and SDK-export patterns.
-
-## Key Technical Decisions
-
-- Introduce `@openclaw/plugin-sdk` as a new workspace package while keeping the
-  legacy root `openclaw/plugin-sdk/*` surface alive during migration.
-  Rationale: this lets a first-wave extension set move onto real package
-  resolution without forcing every extension and every root build path to change
-  at once.
-
-- Use a dedicated opt-in boundary base config such as
-  `extensions/tsconfig.package-boundary.base.json` instead of replacing the
-  existing extension base for everyone.
-  Rationale: the repo needs to support both legacy and opt-in extension modes
-  simultaneously during migration.
-
-- Use TS project references from first-wave extensions to
-  `packages/plugin-sdk/tsconfig.json` and set
-  `disableSourceOfProjectReferenceRedirect` for the opt-in boundary mode.
-  Rationale: this gives `tsc` a real package graph while discouraging editor and
-  compiler fallback to raw source traversal.
-
-- Keep `@openclaw/plugin-sdk` private in the first wave.
-  Rationale: the immediate goal is internal boundary enforcement and migration
-  safety, not publishing a second external SDK contract before the surface is
-  stable.
-
-- Move only the first-wave SDK subpaths in the first implementation slice, and
-  keep compatibility bridges for the rest.
-  Rationale: physically moving all 315 `src/plugin-sdk/*.ts` files in one PR is
-  exactly the merge-conflict surface this plan is trying to avoid.
-
-- Do not rely on `scripts/postinstall-bundled-plugins.mjs` to build SDK
-  declarations for the first wave.
-  Rationale: explicit build/reference flows are easier to reason about and keep
-  repo behavior more predictable.
-
-## Open Questions
-
-### Resolved During Planning
-
-- Which extensions should be in the first wave?
-  Use the 10 provider/web-search extensions listed above because they are more
-  structurally isolated than the heavier channel packages.
-
-- Should the first PR replace the entire extension tree?
-  No. The first PR should support two modes in parallel and only opt in the
-  first wave.
-
-- Should the first wave require a postinstall declaration build?
-  No. The package/reference graph should be explicit, and CI should run the
-  relevant package-local typecheck intentionally.
-
-### Deferred to Implementation
-
-- Whether the first-wave package can point directly at package-local `src/*.ts`
-  via project references alone, or whether a small declaration-emission step is
-  still required for the `@openclaw/plugin-sdk` package.
-  This is an implementation-owned TS graph validation question.
-
-- Whether the root `openclaw` package should proxy first-wave SDK subpaths to
-  `packages/plugin-sdk` outputs immediately or continue using generated
-  compatibility shims under `src/plugin-sdk`.
-  This is a compatibility and build-shape detail that depends on the minimal
-  implementation path that keeps CI green.
-
-## High-Level Technical Design
-
-> This illustrates the intended approach and is directional guidance for review, not implementation specification. The implementing agent should treat it as context, not code to reproduce.
-
-```mermaid
-flowchart TB
-  subgraph Legacy["Legacy extensions (unchanged)"]
-    L1["extensions/*\nopenclaw/plugin-sdk/*"]
-    L2["root tsconfig paths"]
-    L1 --> L2
-    L2 --> L3["src/plugin-sdk/*"]
-  end
-
-  subgraph OptIn["First-wave extensions"]
-    O1["10 opted-in extensions"]
-    O2["extensions/tsconfig.package-boundary.base.json"]
-    O3["rootDir = '.'\nproject reference"]
-    O4["@openclaw/plugin-sdk"]
-    O1 --> O2
-    O2 --> O3
-    O3 --> O4
-  end
-
-  subgraph SDK["New workspace package"]
-    P1["packages/plugin-sdk/package.json"]
-    P2["packages/plugin-sdk/tsconfig.json"]
-    P3["packages/plugin-sdk/src/<first-wave-subpaths>.ts"]
-    P1 --> P2
-    P2 --> P3
-  end
-
-  O4 --> SDK
-```
-
-## Implementation Units
-
-- [ ] **Unit 1: Introduce the real `@openclaw/plugin-sdk` workspace package**
-
-**Goal:** Create a real workspace package for the SDK that can own the
-first-wave subpath surface without forcing a repo-wide migration.
-
-**Requirements:** R1, R2, R3, R8, R9
-
-**Dependencies:** None
-
-**Files:**
-
-- Create: `packages/plugin-sdk/package.json`
-- Create: `packages/plugin-sdk/tsconfig.json`
-- Create: `packages/plugin-sdk/src/index.ts`
-- Create: `packages/plugin-sdk/src/*.ts` for the first-wave SDK subpaths
-- Modify: `pnpm-workspace.yaml` only if package-glob adjustments are needed
-- Modify: `package.json`
-- Modify: `src/plugin-sdk/entrypoints.ts`
-- Modify: `scripts/lib/plugin-sdk-entrypoints.json`
-- Test: `src/plugins/contracts/plugin-sdk-workspace-package.contract.test.ts`
-
-**Approach:**
-
-- Add a new workspace package named `@openclaw/plugin-sdk`.
-- Start with the first-wave SDK subpaths only, not the entire 315-file tree.
-- If directly moving a first-wave entrypoint would create an oversized diff, the
-  first PR may introduce that subpath in `packages/plugin-sdk/src` as a thin
-  package wrapper first and then flip the source of truth to the package in a
-  follow-up PR for that subpath cluster.
-- Reuse the existing entrypoint inventory machinery so the first-wave package
-  surface is declared in one canonical place.
-- Keep the root package exports alive for legacy users while the workspace
-  package becomes the new opt-in contract.
-
-**Patterns to follow:**
-
-- `packages/memory-host-sdk/package.json`
-- `packages/plugin-package-contract/package.json`
-- `src/plugin-sdk/entrypoints.ts`
-
-**Test scenarios:**
-
-- Happy path: the workspace package exports every first-wave subpath listed in
-  the plan and no required first-wave export is missing.
-- Edge case: package export metadata remains stable when the first-wave entry
-  list is re-generated or compared against the canonical inventory.
-- Integration: root package legacy SDK exports remain present after introducing
-  the new workspace package.
-
-**Verification:**
-
-- The repo contains a valid `@openclaw/plugin-sdk` workspace package with a
-  stable first-wave export map and no legacy export regression in root
-  `package.json`.
-
-- [ ] **Unit 2: Add an opt-in TS boundary mode for package-enforced extensions**
-
-**Goal:** Define the TS configuration mode that opted-in extensions will use,
-while leaving the existing extension TS behavior unchanged for everyone else.
-
-**Requirements:** R4, R6, R7, R8, R9
-
-**Dependencies:** Unit 1
-
-**Files:**
-
-- Create: `extensions/tsconfig.package-boundary.base.json`
-- Create: `tsconfig.boundary-optin.json`
-- Modify: `extensions/xai/tsconfig.json`
-- Modify: `extensions/openai/tsconfig.json`
-- Modify: `extensions/anthropic/tsconfig.json`
-- Modify: `extensions/mistral/tsconfig.json`
-- Modify: `extensions/groq/tsconfig.json`
-- Modify: `extensions/together/tsconfig.json`
-- Modify: `extensions/perplexity/tsconfig.json`
-- Modify: `extensions/tavily/tsconfig.json`
-- Modify: `extensions/exa/tsconfig.json`
-- Modify: `extensions/firecrawl/tsconfig.json`
-- Test: `src/plugins/contracts/extension-package-project-boundaries.test.ts`
-- Test: `test/extension-package-tsc-boundary.test.ts`
-
-**Approach:**
-
-- Leave `extensions/tsconfig.base.json` in place for legacy extensions.
-- Add a new opt-in base config that:
-  - sets `rootDir: "."`
-  - references `packages/plugin-sdk`
-  - enables `composite`
-  - disables project-reference source redirect when needed
-- Add a dedicated solution config for the first-wave typecheck graph instead of
-  reshaping the root repo TS project in the same PR.
-
-**Execution note:** Start with a failing package-local canary typecheck for one
-opted-in extension before applying the pattern to all 10.
-
-**Patterns to follow:**
-
-- Existing package-local extension `tsconfig.json` pattern from the prior
-  boundary work
-- Workspace package pattern from `packages/memory-host-sdk`
-
-**Test scenarios:**
-
-- Happy path: each opted-in extension typechecks successfully through the
-  package-boundary TS config.
-- Error path: a canary relative import from `../../src/cli/acp-cli.ts` fails
-  with `TS6059` for an opted-in extension.
-- Integration: non-opted-in extensions remain untouched and do not need to
-  participate in the new solution config.
-
-**Verification:**
-
-- There is a dedicated typecheck graph for the 10 opted-in extensions, and bad
-  relative imports from one of them fail through normal `tsc`.
-
-- [ ] **Unit 3: Migrate the first-wave extensions onto `@openclaw/plugin-sdk`**
-
-**Goal:** Change the first-wave extensions to consume the real SDK package
-through dependency metadata, project references, and package-name imports.
-
-**Requirements:** R5, R6, R7, R9
-
-**Dependencies:** Unit 2
-
-**Files:**
-
-- Modify: `extensions/anthropic/package.json`
-- Modify: `extensions/exa/package.json`
-- Modify: `extensions/firecrawl/package.json`
-- Modify: `extensions/groq/package.json`
-- Modify: `extensions/mistral/package.json`
-- Modify: `extensions/openai/package.json`
-- Modify: `extensions/perplexity/package.json`
-- Modify: `extensions/tavily/package.json`
-- Modify: `extensions/together/package.json`
-- Modify: `extensions/xai/package.json`
-- Modify: production and test imports under each of the 10 extension roots that
-  currently reference `openclaw/plugin-sdk/*`
-
-**Approach:**
-
-- Add `@openclaw/plugin-sdk: workspace:*` to the first-wave extension
-  `devDependencies`.
-- Replace `openclaw/plugin-sdk/*` imports in those packages with
-  `@openclaw/plugin-sdk/*`.
-- Keep local extension-internal imports on local barrels such as `./api.ts` and
-  `./runtime-api.ts`.
-- Do not change non-opted-in extensions in this PR.
-
-**Patterns to follow:**
-
-- Existing extension-local import barrels (`api.ts`, `runtime-api.ts`)
-- Package dependency shape used by other `@openclaw/*` workspace packages
-
-**Test scenarios:**
-
-- Happy path: each migrated extension still registers/loads through its existing
-  plugin tests after the import rewrite.
-- Edge case: test-only SDK imports in the opted-in extension set still resolve
-  correctly through the new package.
-- Integration: migrated extensions do not require root `openclaw/plugin-sdk/*`
-  aliases for typechecking.
-
-**Verification:**
-
-- The first-wave extensions build and test against `@openclaw/plugin-sdk`
-  without needing the legacy root SDK alias path.
-
-- [ ] **Unit 4: Preserve legacy compatibility while the migration is partial**
-
-**Goal:** Keep the rest of the repo working while the SDK exists in both legacy
-and new-package forms during migration.
-
-**Requirements:** R4, R8, R9
-
-**Dependencies:** Units 1-3
-
-**Files:**
-
-- Modify: `src/plugin-sdk/*.ts` for first-wave compatibility shims as needed
-- Modify: `package.json`
-- Modify: build or export plumbing that assembles SDK artifacts
-- Test: `src/plugins/contracts/plugin-sdk-runtime-api-guardrails.test.ts`
-- Test: `src/plugins/contracts/plugin-sdk-index.bundle.test.ts`
-
-**Approach:**
-
-- Keep root `openclaw/plugin-sdk/*` as the compatibility surface for legacy
-  extensions and for external consumers that are not moving yet.
-- Use either generated shims or root-export proxy wiring for the first-wave
-  subpaths that have moved into `packages/plugin-sdk`.
-- Do not attempt to retire the root SDK surface in this phase.
-
-**Patterns to follow:**
-
-- Existing root SDK export generation via `src/plugin-sdk/entrypoints.ts`
-- Existing package export compatibility in root `package.json`
-
-**Test scenarios:**
-
-- Happy path: a legacy root SDK import still resolves for a non-opted-in
-  extension after the new package exists.
-- Edge case: a first-wave subpath works through both the legacy root surface and
-  the new package surface during the migration window.
-- Integration: plugin-sdk index/bundle contract tests continue to see a coherent
-  public surface.
-
-**Verification:**
-
-- The repo supports both legacy and opt-in SDK consumption modes without
-  breaking unchanged extensions.
-
-- [ ] **Unit 5: Add scoped enforcement and document the migration contract**
-
-**Goal:** Land CI and contributor guidance that enforce the new behavior for the
-first wave without pretending the entire extension tree is migrated.
-
-**Requirements:** R5, R6, R8, R9
-
-**Dependencies:** Units 1-4
-
-**Files:**
-
-- Modify: `package.json`
-- Modify: CI workflow files that should run the opt-in boundary typecheck
-- Modify: `AGENTS.md`
-- Modify: `docs/plugins/sdk-overview.md`
-- Modify: `docs/plugins/sdk-entrypoints.md`
-- Modify: `docs/plans/2026-04-05-001-refactor-extension-package-resolution-boundary-plan.md`
-
-**Approach:**
-
-- Add an explicit first-wave gate, such as a dedicated `tsc -b` solution run for
-  `packages/plugin-sdk` plus the 10 opted-in extensions.
-- Document that the repo now supports both legacy and opt-in extension modes,
-  and that new extension boundary work should prefer the new package route.
-- Record the next-wave migration rule so later PRs can add more extensions
-  without re-litigating the architecture.
-
-**Patterns to follow:**
-
-- Existing contract tests under `src/plugins/contracts/`
-- Existing docs updates that explain staged migrations
-
-**Test scenarios:**
-
-- Happy path: the new first-wave typecheck gate passes for the workspace package
-  and the opted-in extensions.
-- Error path: introducing a new illegal relative import in an opted-in
-  extension fails the scoped typecheck gate.
-- Integration: CI does not require non-opted-in extensions to satisfy the new
-  package-boundary mode yet.
-
-**Verification:**
-
-- The first-wave enforcement path is documented, tested, and runnable without
-  forcing the entire extension tree to migrate.
-
-## System-Wide Impact
-
-- **Interaction graph:** this work touches the SDK source-of-truth, root package
-  exports, extension package metadata, TS graph layout, and CI verification.
-- **Error propagation:** the main intended failure mode becomes compile-time TS
-  errors (`TS6059`) in opted-in extensions instead of custom script-only
-  failures.
-- **State lifecycle risks:** dual-surface migration introduces drift risk between
-  root compatibility exports and the new workspace package.
-- **API surface parity:** first-wave subpaths must remain semantically identical
-  through both `openclaw/plugin-sdk/*` and `@openclaw/plugin-sdk/*` during the
-  transition.
-- **Integration coverage:** unit tests are not enough; scoped package-graph
-  typechecks are required to prove the boundary.
-- **Unchanged invariants:** non-opted-in extensions keep their current behavior
-  in PR 1. This plan does not claim repo-wide import-boundary enforcement.
-
-## Risks & Dependencies
-
-| Risk                                                                                                   | Mitigation                                                                                                              |
-| ------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------- |
-| The first-wave package still resolves back into raw source and `rootDir` does not actually fail closed | Make the first implementation step a package-reference canary on one opted-in extension before widening to the full set |
-| Moving too much SDK source at once recreates the original merge-conflict problem                       | Move only the first-wave subpaths in the first PR and keep root compatibility bridges                                   |
-| Legacy and new SDK surfaces drift semantically                                                         | Keep a single entrypoint inventory, add compatibility contract tests, and make dual-surface parity explicit             |
-| Root repo build/test paths accidentally start depending on the new package in uncontrolled ways        | Use a dedicated opt-in solution config and keep root-wide TS topology changes out of the first PR                       |
-
-## Phased Delivery
-
-### Phase 1
-
-- Introduce `@openclaw/plugin-sdk`
-- Define the first-wave subpath surface
-- Prove one opted-in extension can fail closed through `rootDir`
-
-### Phase 2
-
-- Opt in the 10 first-wave extensions
-- Keep root compatibility alive for everyone else
-
-### Phase 3
-
-- Add more extensions in later PRs
-- Move more SDK subpaths into the workspace package
-- Retire root compatibility only after the legacy extension set is gone
-
-## Documentation / Operational Notes
-
-- The first PR should explicitly describe itself as a dual-mode migration, not a
-  repo-wide enforcement completion.
-- The migration guide should make it easy for later PRs to add more extensions
-  by following the same package/dependency/reference pattern.
-
-## Sources & References
-
-- Prior plan: `docs/plans/2026-04-05-001-refactor-extension-package-resolution-boundary-plan.md`
-- Workspace config: `pnpm-workspace.yaml`
-- Existing SDK entrypoint inventory: `src/plugin-sdk/entrypoints.ts`
-- Existing root SDK exports: `package.json`
-- Existing workspace package patterns:
-  - `packages/memory-host-sdk/package.json`
-  - `packages/plugin-package-contract/package.json`

docs/plugins/sdk-migration.md

@@ -245,6 +245,7 @@ Current bundled provider examples:
   | `plugin-sdk/allow-from` | Allowlist formatting | `formatAllowFromLowercase` |
   | `plugin-sdk/allowlist-resolution` | Allowlist input mapping | `mapAllowlistResolutionInputs` |
   | `plugin-sdk/command-auth` | Command gating and command-surface helpers | `resolveControlCommandGate`, sender-authorization helpers, command registry helpers |
+  | `plugin-sdk/command-status` | Command status/help renderers | `buildCommandsMessage`, `buildCommandsMessagePaginated`, `buildHelpMessage` |
   | `plugin-sdk/secret-input` | Secret input parsing | Secret input helpers |
   | `plugin-sdk/webhook-ingress` | Webhook request helpers | Webhook target utilities |
   | `plugin-sdk/webhook-request-guards` | Webhook body guard helpers | Request body read/limit helpers |

docs/plugins/sdk-overview.md

@@ -149,6 +149,7 @@ explicitly promotes one as public.
     | Subpath | Key exports |
     | --- | --- |
     | `plugin-sdk/command-auth` | `resolveControlCommandGate`, command registry helpers, sender-authorization helpers |
+    | `plugin-sdk/command-status` | Command/help message builders such as `buildCommandsMessagePaginated` and `buildHelpMessage` |
     | `plugin-sdk/approval-auth-runtime` | Approver resolution and same-chat action-auth helpers |
     | `plugin-sdk/approval-client-runtime` | Native exec approval profile/filter helpers |
     | `plugin-sdk/approval-delivery-runtime` | Native approval capability/delivery adapters |

docs/providers/qwen.md

@@ -88,7 +88,9 @@ requiring the built-in `qwen` provider id specifically.
 
 ## Built-in catalog
 
-OpenClaw currently ships this bundled Qwen catalog:
+OpenClaw currently ships this bundled Qwen catalog. The configured catalog is
+endpoint-aware: Coding Plan configs omit models that are only known to work on
+the Standard endpoint.
 
 | Model ref                   | Input       | Context   | Notes                                              |
 | --------------------------- | ----------- | --------- | -------------------------------------------------- |

docs/reference/memory-config.md

@@ -17,10 +17,22 @@ conceptual overviews, see:
 - [Builtin Engine](/concepts/memory-builtin) -- default SQLite backend
 - [QMD Engine](/concepts/memory-qmd) -- local-first sidecar
 - [Memory Search](/concepts/memory-search) -- search pipeline and tuning
+- [Active Memory](/concepts/active-memory) -- enabling the memory sub-agent for interactive sessions
 
 All memory search settings live under `agents.defaults.memorySearch` in
 `openclaw.json` unless noted otherwise.
 
+If you are looking for the **active memory** feature toggle and sub-agent config,
+that lives under `plugins.entries.active-memory` instead of `memorySearch`.
+
+Active memory uses a two-gate model:
+
+1. the plugin must be enabled and target the current agent id
+2. the request must be an eligible interactive persistent chat session
+
+See [Active Memory](/concepts/active-memory) for the activation model,
+plugin-owned config, transcript persistence, and safe rollout pattern.
+
 ---
 
 ## Provider selection

docs/reference/rich-output-protocol.md

@@ -0,0 +1,50 @@
+# Rich Output Protocol
+
+Assistant output can carry a small set of delivery/render directives:
+
+- `MEDIA:` for attachment delivery
+- `[[audio_as_voice]]` for audio presentation hints
+- `[[reply_to_current]]` / `[[reply_to:<id>]]` for reply metadata
+- `[canvas ...]` for Control UI rich rendering
+
+These directives are separate. `MEDIA:` and reply/voice tags remain delivery metadata; `[canvas ...]` is the web-only rich render path.
+
+## `[canvas ...]`
+
+`[canvas ...]` is the only agent-facing rich render syntax for the Control UI.
+
+Self-closing example:
+
+```text
+[canvas ref="cv_123" title="Status" /]
+```
+
+Rules:
+
+- `[view ...]` is no longer valid for new output.
+- Canvas shortcodes render in the assistant message surface only.
+- Only URL-backed canvases are rendered. Use `ref="..."` or `url="..."`.
+- Block-form inline HTML canvas shortcodes are not rendered.
+- The web UI strips the shortcode from visible text and renders the canvas inline.
+- `MEDIA:` is not a canvas alias and should not be used for rich canvas rendering.
+
+## Stored Rendering Shape
+
+The normalized/stored assistant content block is a structured `canvas` item:
+
+```json
+{
+  "type": "canvas",
+  "preview": {
+    "kind": "canvas",
+    "surface": "assistant_message",
+    "render": "url",
+    "viewId": "cv_123",
+    "url": "/__openclaw__/canvas/documents/cv_123/index.html",
+    "title": "Status",
+    "preferredHeight": 320
+  }
+}
+```
+
+Stored/rendered rich blocks use this `canvas` shape directly. `present_view` is not recognized.

docs/tools/browser.md

@@ -576,6 +576,27 @@ Notes:
 - If `gateway.auth.mode` is `none` or `trusted-proxy`, these loopback browser
   routes do not inherit those identity-bearing modes; keep them loopback-only.
 
+### `/act` error contract
+
+`POST /act` uses a structured error response for route-level validation and
+policy failures:
+
+```json
+{ "error": "<message>", "code": "ACT_*" }
+```
+
+Current `code` values:
+
+- `ACT_KIND_REQUIRED` (HTTP 400): `kind` is missing or unrecognized.
+- `ACT_INVALID_REQUEST` (HTTP 400): action payload failed normalization or validation.
+- `ACT_SELECTOR_UNSUPPORTED` (HTTP 400): `selector` was used with an unsupported action kind.
+- `ACT_EVALUATE_DISABLED` (HTTP 403): `evaluate` (or `wait --fn`) is disabled by config.
+- `ACT_TARGET_ID_MISMATCH` (HTTP 403): top-level or batched `targetId` conflicts with request target.
+- `ACT_EXISTING_SESSION_UNSUPPORTED` (HTTP 501): action is not supported for existing-session profiles.
+
+Other runtime failures may still return `{ "error": "<message>" }` without a
+`code` field.
+
 ### Playwright requirement
 
 Some features (navigate/act/AI snapshot/role snapshot, element screenshots,

extensions/acpx/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/acpx",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "description": "OpenClaw ACP runtime backend",
   "type": "module",
   "dependencies": {

extensions/active-memory/openclaw.plugin.json

@@ -0,0 +1,120 @@
+{
+  "id": "active-memory",
+  "name": "Active Memory",
+  "description": "Runs a bounded blocking memory sub-agent before eligible conversational replies and injects relevant memory into prompt context.",
+  "configSchema": {
+    "type": "object",
+    "additionalProperties": false,
+    "properties": {
+      "enabled": { "type": "boolean" },
+      "agents": {
+        "type": "array",
+        "items": { "type": "string" }
+      },
+      "model": { "type": "string" },
+      "modelFallbackPolicy": {
+        "type": "string",
+        "enum": ["default-remote", "resolved-only"]
+      },
+      "allowedChatTypes": {
+        "type": "array",
+        "items": {
+          "type": "string",
+          "enum": ["direct", "group", "channel"]
+        }
+      },
+      "thinking": {
+        "type": "string",
+        "enum": ["off", "minimal", "low", "medium", "high", "xhigh", "adaptive"]
+      },
+      "timeoutMs": { "type": "integer", "minimum": 250 },
+      "queryMode": {
+        "type": "string",
+        "enum": ["message", "recent", "full"]
+      },
+      "promptStyle": {
+        "type": "string",
+        "enum": [
+          "balanced",
+          "strict",
+          "contextual",
+          "recall-heavy",
+          "precision-heavy",
+          "preference-only"
+        ]
+      },
+      "promptOverride": { "type": "string" },
+      "promptAppend": { "type": "string" },
+      "maxSummaryChars": { "type": "integer", "minimum": 40, "maximum": 1000 },
+      "recentUserTurns": { "type": "integer", "minimum": 0, "maximum": 4 },
+      "recentAssistantTurns": { "type": "integer", "minimum": 0, "maximum": 3 },
+      "recentUserChars": { "type": "integer", "minimum": 40, "maximum": 1000 },
+      "recentAssistantChars": { "type": "integer", "minimum": 40, "maximum": 1000 },
+      "logging": { "type": "boolean" },
+      "persistTranscripts": { "type": "boolean" },
+      "transcriptDir": { "type": "string" },
+      "cacheTtlMs": { "type": "integer", "minimum": 1000, "maximum": 120000 }
+    }
+  },
+  "uiHints": {
+    "enabled": {
+      "label": "Active Memory Recall",
+      "help": "Globally enable or pause Active Memory recall while keeping the plugin command available."
+    },
+    "agents": {
+      "label": "Target Agents",
+      "help": "Explicit agent ids that may use active memory."
+    },
+    "model": {
+      "label": "Memory Model",
+      "help": "Provider/model used for the blocking memory sub-agent."
+    },
+    "modelFallbackPolicy": {
+      "label": "Model Fallback Policy",
+      "help": "Choose whether Active Memory falls back to the built-in remote default model when no explicit or inherited model is available."
+    },
+    "allowedChatTypes": {
+      "label": "Allowed Chat Types",
+      "help": "Choose which session types may run Active Memory. Defaults to direct-message style sessions only."
+    },
+    "timeoutMs": {
+      "label": "Timeout (ms)"
+    },
+    "queryMode": {
+      "label": "Query Mode",
+      "help": "Choose whether the blocking memory sub-agent sees only the latest user message, a small recent tail, or the full conversation."
+    },
+    "promptStyle": {
+      "label": "Prompt Style",
+      "help": "Choose how eager or strict the blocking memory sub-agent should be when deciding whether to return memory."
+    },
+    "thinking": {
+      "label": "Thinking Override",
+      "help": "Advanced: optional thinking level for the blocking memory sub-agent. Defaults to off for speed."
+    },
+    "promptOverride": {
+      "label": "Prompt Override",
+      "help": "Advanced: replace the default Active Memory sub-agent instructions. Conversation context is still appended."
+    },
+    "promptAppend": {
+      "label": "Prompt Append",
+      "help": "Advanced: append extra operator instructions after the default Active Memory sub-agent instructions."
+    },
+    "maxSummaryChars": {
+      "label": "Max Summary Characters",
+      "help": "Maximum total characters allowed in the active-memory summary."
+    },
+    "logging": {
+      "label": "Enable Logging",
+      "help": "Emit active memory timing and result logs."
+    },
+    "persistTranscripts": {
+      "label": "Persist Transcripts",
+      "help": "Keep blocking memory sub-agent session transcripts on disk in a separate plugin-owned directory."
+    },
+    "transcriptDir": {
+      "label": "Transcript Directory",
+      "help": "Relative directory under the agent sessions folder used when transcript persistence is enabled."
+    }
+  }
+}

extensions/alibaba/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/alibaba-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Alibaba Model Studio video provider plugin",
   "type": "module",

extensions/amazon-bedrock-mantle/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/amazon-bedrock-mantle-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Amazon Bedrock Mantle (OpenAI-compatible) provider plugin",
   "type": "module",

extensions/amazon-bedrock/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/amazon-bedrock-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Amazon Bedrock provider plugin",
   "type": "module",

extensions/anthropic-vertex/openclaw.plugin.json

@@ -2,6 +2,7 @@
   "id": "anthropic-vertex",
   "enabledByDefault": true,
   "providers": ["anthropic-vertex"],
+  "providerDiscoveryEntry": "./provider-discovery.ts",
   "configSchema": {
     "type": "object",
     "additionalProperties": false,

extensions/anthropic-vertex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/anthropic-vertex-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Anthropic Vertex provider plugin",
   "type": "module",

extensions/anthropic-vertex/provider-discovery.import-guard.test.ts

@@ -0,0 +1,10 @@
+import { describe, expect, it } from "vitest";
+
+describe("anthropic-vertex provider discovery entry", () => {
+  it("imports without loading the full plugin entry", async () => {
+    const module = await import("./provider-discovery.js");
+
+    expect(module.default.id).toBe("anthropic-vertex");
+    expect(module.default.catalog.order).toBe("simple");
+  });
+});

extensions/anthropic-vertex/provider-discovery.ts

@@ -0,0 +1,215 @@
+import { readFileSync } from "node:fs";
+import { homedir, platform } from "node:os";
+import { join } from "node:path";
+import type { ProviderCatalogContext } from "openclaw/plugin-sdk/provider-catalog-shared";
+import type {
+  ModelDefinitionConfig,
+  ModelProviderConfig,
+} from "openclaw/plugin-sdk/provider-model-shared";
+
+const PROVIDER_ID = "anthropic-vertex";
+const ANTHROPIC_VERTEX_DEFAULT_REGION = "global";
+const ANTHROPIC_VERTEX_REGION_RE = /^[a-z0-9-]+$/;
+const ANTHROPIC_VERTEX_DEFAULT_CONTEXT_WINDOW = 1_000_000;
+const GCP_VERTEX_CREDENTIALS_MARKER = "gcp-vertex-credentials";
+const GCLOUD_DEFAULT_ADC_PATH = join(
+  homedir(),
+  ".config",
+  "gcloud",
+  "application_default_credentials.json",
+);
+
+type AnthropicVertexProviderPlugin = {
+  id: string;
+  label: string;
+  docsPath: string;
+  auth: [];
+  catalog: {
+    order: "simple";
+    run: (ctx: ProviderCatalogContext) => ReturnType<typeof runAnthropicVertexCatalog>;
+  };
+  resolveConfigApiKey: (params: { env: NodeJS.ProcessEnv }) => string | undefined;
+};
+
+type AdcProjectFile = {
+  project_id?: unknown;
+  quota_project_id?: unknown;
+};
+
+function normalizeOptionalString(value: unknown): string | undefined {
+  return typeof value === "string" && value.trim() ? value.trim() : undefined;
+}
+
+function normalizeLowercaseStringOrEmpty(value: unknown): string {
+  return normalizeOptionalString(value)?.toLowerCase() ?? "";
+}
+
+function resolveAnthropicVertexRegion(env: NodeJS.ProcessEnv = process.env): string {
+  const region =
+    normalizeOptionalString(env.GOOGLE_CLOUD_LOCATION) ||
+    normalizeOptionalString(env.CLOUD_ML_REGION);
+
+  return region && ANTHROPIC_VERTEX_REGION_RE.test(region)
+    ? region
+    : ANTHROPIC_VERTEX_DEFAULT_REGION;
+}
+
+function hasAnthropicVertexMetadataServerAdc(env: NodeJS.ProcessEnv = process.env): boolean {
+  const explicitMetadataOptIn = normalizeOptionalString(env.ANTHROPIC_VERTEX_USE_GCP_METADATA);
+  return (
+    explicitMetadataOptIn === "1" ||
+    normalizeLowercaseStringOrEmpty(explicitMetadataOptIn) === "true"
+  );
+}
+
+function resolveAnthropicVertexDefaultAdcPath(env: NodeJS.ProcessEnv = process.env): string {
+  return platform() === "win32"
+    ? join(
+        env.APPDATA ?? join(homedir(), "AppData", "Roaming"),
+        "gcloud",
+        "application_default_credentials.json",
+      )
+    : GCLOUD_DEFAULT_ADC_PATH;
+}
+
+function resolveAnthropicVertexAdcCredentialsPathCandidate(
+  env: NodeJS.ProcessEnv = process.env,
+): string | undefined {
+  const explicit = normalizeOptionalString(env.GOOGLE_APPLICATION_CREDENTIALS);
+  if (explicit) {
+    return explicit;
+  }
+  if (env !== process.env) {
+    return undefined;
+  }
+  return resolveAnthropicVertexDefaultAdcPath(env);
+}
+
+function readAnthropicVertexAdc(env: NodeJS.ProcessEnv = process.env): AdcProjectFile | null {
+  const credentialsPath = resolveAnthropicVertexAdcCredentialsPathCandidate(env);
+  if (!credentialsPath) {
+    return null;
+  }
+  try {
+    return JSON.parse(readFileSync(credentialsPath, "utf8")) as AdcProjectFile;
+  } catch {
+    return null;
+  }
+}
+
+function hasAnthropicVertexAvailableAuth(env: NodeJS.ProcessEnv = process.env): boolean {
+  return hasAnthropicVertexMetadataServerAdc(env) || readAnthropicVertexAdc(env) !== null;
+}
+
+function resolveAnthropicVertexConfigApiKey(
+  env: NodeJS.ProcessEnv = process.env,
+): string | undefined {
+  return hasAnthropicVertexAvailableAuth(env) ? GCP_VERTEX_CREDENTIALS_MARKER : undefined;
+}
+
+function buildAnthropicVertexModel(params: {
+  id: string;
+  name: string;
+  reasoning: boolean;
+  input: ModelDefinitionConfig["input"];
+  cost: ModelDefinitionConfig["cost"];
+  maxTokens: number;
+}): ModelDefinitionConfig {
+  return {
+    id: params.id,
+    name: params.name,
+    reasoning: params.reasoning,
+    input: params.input,
+    cost: params.cost,
+    contextWindow: ANTHROPIC_VERTEX_DEFAULT_CONTEXT_WINDOW,
+    maxTokens: params.maxTokens,
+  };
+}
+
+function buildAnthropicVertexProvider(params?: { env?: NodeJS.ProcessEnv }): ModelProviderConfig {
+  const region = resolveAnthropicVertexRegion(params?.env);
+  const baseUrl =
+    normalizeLowercaseStringOrEmpty(region) === "global"
+      ? "https://aiplatform.googleapis.com"
+      : `https://${region}-aiplatform.googleapis.com`;
+
+  return {
+    baseUrl,
+    api: "anthropic-messages",
+    apiKey: GCP_VERTEX_CREDENTIALS_MARKER,
+    models: [
+      buildAnthropicVertexModel({
+        id: "claude-opus-4-6",
+        name: "Claude Opus 4.6",
+        reasoning: true,
+        input: ["text", "image"],
+        cost: { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
+        maxTokens: 128000,
+      }),
+      buildAnthropicVertexModel({
+        id: "claude-sonnet-4-6",
+        name: "Claude Sonnet 4.6",
+        reasoning: true,
+        input: ["text", "image"],
+        cost: { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 },
+        maxTokens: 128000,
+      }),
+    ],
+  };
+}
+
+function mergeImplicitAnthropicVertexProvider(params: {
+  existing?: ModelProviderConfig;
+  implicit: ModelProviderConfig;
+}) {
+  const { existing, implicit } = params;
+  if (!existing) {
+    return implicit;
+  }
+  return {
+    ...implicit,
+    ...existing,
+    models:
+      Array.isArray(existing.models) && existing.models.length > 0
+        ? existing.models
+        : implicit.models,
+  };
+}
+
+function resolveImplicitAnthropicVertexProvider(params?: { env?: NodeJS.ProcessEnv }) {
+  const env = params?.env ?? process.env;
+  if (!hasAnthropicVertexAvailableAuth(env)) {
+    return null;
+  }
+
+  return buildAnthropicVertexProvider({ env });
+}
+
+async function runAnthropicVertexCatalog(ctx: ProviderCatalogContext) {
+  const implicit = resolveImplicitAnthropicVertexProvider({
+    env: ctx.env,
+  });
+  if (!implicit) {
+    return null;
+  }
+  return {
+    provider: mergeImplicitAnthropicVertexProvider({
+      existing: ctx.config.models?.providers?.[PROVIDER_ID],
+      implicit,
+    }),
+  };
+}
+
+export const anthropicVertexProviderDiscovery: AnthropicVertexProviderPlugin = {
+  id: PROVIDER_ID,
+  label: "Anthropic Vertex",
+  docsPath: "/providers/models",
+  auth: [],
+  catalog: {
+    order: "simple",
+    run: runAnthropicVertexCatalog,
+  },
+  resolveConfigApiKey: ({ env }) => resolveAnthropicVertexConfigApiKey(env),
+};
+
+export default anthropicVertexProviderDiscovery;

extensions/anthropic/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/anthropic-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Anthropic provider plugin",
   "type": "module",

extensions/arcee/onboard.ts

@@ -2,7 +2,7 @@ import {
   createModelCatalogPresetAppliers,
   type OpenClawConfig,
 } from "openclaw/plugin-sdk/provider-onboard";
-import { ARCEE_BASE_URL } from "./api.js";
+import { ARCEE_BASE_URL } from "./models.js";
 import {
   buildArceeCatalogModels,
   buildArceeOpenRouterCatalogModels,

extensions/arcee/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/arcee-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Arcee provider plugin",
   "type": "module",

extensions/arcee/provider-catalog.ts

@@ -1,5 +1,5 @@
 import type { ModelProviderConfig } from "openclaw/plugin-sdk/provider-model-shared";
-import { buildArceeModelDefinition, ARCEE_BASE_URL, ARCEE_MODEL_CATALOG } from "./api.js";
+import { buildArceeModelDefinition, ARCEE_BASE_URL, ARCEE_MODEL_CATALOG } from "./models.js";
 
 export const OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1";
 

extensions/bluebubbles/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/bluebubbles",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "description": "OpenClaw BlueBubbles channel plugin",
   "type": "module",
   "devDependencies": {
@@ -8,7 +8,7 @@
     "openclaw": "workspace:*"
   },
   "peerDependencies": {
-    "openclaw": ">=2026.4.9"
+    "openclaw": ">=2026.4.10"
   },
   "peerDependenciesMeta": {
     "openclaw": {
@@ -40,13 +40,13 @@
     "install": {
       "npmSpec": "@openclaw/bluebubbles",
       "defaultChoice": "npm",
-      "minHostVersion": ">=2026.4.9"
+      "minHostVersion": ">=2026.4.10"
     },
     "compat": {
-      "pluginApi": ">=2026.4.9"
+      "pluginApi": ">=2026.4.10"
     },
     "build": {
-      "openclawVersion": "2026.4.9"
+      "openclawVersion": "2026.4.10"
     },
     "release": {
       "publishToClawHub": true,

extensions/bluebubbles/src/secret-contract.ts

@@ -33,7 +33,7 @@ export const secretTargetRegistryEntries = [
 
 export function collectRuntimeConfigAssignments(params: {
   config: { channels?: Record<string, unknown> };
-  defaults: SecretDefaults | undefined;
+  defaults?: SecretDefaults;
   context: ResolverContext;
 }): void {
   const resolved = getChannelSurface(params.config, "bluebubbles");

extensions/bluebubbles/src/status-issues.ts

@@ -1,6 +1,6 @@
+import type { ChannelAccountSnapshot } from "openclaw/plugin-sdk/channel-contract";
 import { collectIssuesForEnabledAccounts } from "openclaw/plugin-sdk/status-helpers";
 import { asRecord } from "./monitor-normalize.js";
-import type { ChannelAccountSnapshot } from "./runtime-api.js";
 
 type BlueBubblesAccountStatus = {
   accountId?: unknown;

extensions/brave/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/brave-plugin",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Brave plugin",
   "type": "module",

extensions/browser/browser-config.ts

@@ -5,13 +5,11 @@ export {
   DEFAULT_OPENCLAW_BROWSER_COLOR,
   DEFAULT_OPENCLAW_BROWSER_ENABLED,
   DEFAULT_OPENCLAW_BROWSER_PROFILE_NAME,
-  parseBrowserHttpUrl,
-  redactCdpUrl,
+  DEFAULT_UPLOAD_DIR,
   resolveBrowserConfig,
-  resolveBrowserControlAuth,
   resolveProfile,
-  type BrowserControlAuth,
   type ResolvedBrowserConfig,
   type ResolvedBrowserProfile,
-} from "./src/browser/config.js";
-export { DEFAULT_UPLOAD_DIR } from "./src/browser/paths.js";
+} from "./browser-profiles.js";
+export { resolveBrowserControlAuth, type BrowserControlAuth } from "./browser-control-auth.js";
+export { parseBrowserHttpUrl, redactCdpUrl } from "./src/browser/config.js";

extensions/browser/browser-control-auth.ts

@@ -1,2 +1,6 @@
 export type { BrowserControlAuth } from "./src/browser/control-auth.js";
-export { ensureBrowserControlAuth, resolveBrowserControlAuth } from "./src/browser/control-auth.js";
+export {
+  ensureBrowserControlAuth,
+  resolveBrowserControlAuth,
+  shouldAutoGenerateBrowserAuth,
+} from "./src/browser/control-auth.js";

extensions/browser/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/browser-plugin",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw browser tool plugin",
   "type": "module",

extensions/browser/src/browser/act-policy.ts

@@ -0,0 +1,44 @@
+export const ACT_MAX_BATCH_ACTIONS = 100;
+export const ACT_MAX_BATCH_DEPTH = 5;
+export const ACT_MAX_CLICK_DELAY_MS = 5_000;
+export const ACT_MAX_WAIT_TIME_MS = 30_000;
+
+const ACT_MIN_TIMEOUT_MS = 500;
+const ACT_MAX_INTERACTION_TIMEOUT_MS = 60_000;
+const ACT_MAX_WAIT_TIMEOUT_MS = 120_000;
+const ACT_DEFAULT_INTERACTION_TIMEOUT_MS = 8_000;
+const ACT_DEFAULT_WAIT_TIMEOUT_MS = 20_000;
+
+export function normalizeActBoundedNonNegativeMs(
+  value: number | undefined,
+  fieldName: string,
+  maxMs: number,
+): number | undefined {
+  if (value === undefined) {
+    return undefined;
+  }
+  if (!Number.isFinite(value) || value < 0) {
+    throw new Error(`${fieldName} must be >= 0`);
+  }
+  const normalized = Math.floor(value);
+  if (normalized > maxMs) {
+    throw new Error(`${fieldName} exceeds maximum of ${maxMs}ms`);
+  }
+  return normalized;
+}
+
+export function resolveActInteractionTimeoutMs(timeoutMs?: number): number {
+  const normalized =
+    typeof timeoutMs === "number" && Number.isFinite(timeoutMs)
+      ? Math.floor(timeoutMs)
+      : ACT_DEFAULT_INTERACTION_TIMEOUT_MS;
+  return Math.max(ACT_MIN_TIMEOUT_MS, Math.min(ACT_MAX_INTERACTION_TIMEOUT_MS, normalized));
+}
+
+export function resolveActWaitTimeoutMs(timeoutMs?: number): number {
+  const normalized =
+    typeof timeoutMs === "number" && Number.isFinite(timeoutMs)
+      ? Math.floor(timeoutMs)
+      : ACT_DEFAULT_WAIT_TIMEOUT_MS;
+  return Math.max(ACT_MIN_TIMEOUT_MS, Math.min(ACT_MAX_WAIT_TIMEOUT_MS, normalized));
+}

extensions/browser/src/browser/cdp.helpers.ts

@@ -6,7 +6,7 @@ import { rawDataToString } from "../infra/ws.js";
 import { redactSensitiveText } from "../logging/redact.js";
 import { getDirectAgentForCdp, withNoProxyForCdpUrl } from "./cdp-proxy-bypass.js";
 import { CDP_HTTP_REQUEST_TIMEOUT_MS, CDP_WS_HANDSHAKE_TIMEOUT_MS } from "./cdp-timeouts.js";
-import { resolveBrowserRateLimitMessage } from "./client-fetch.js";
+import { resolveBrowserRateLimitMessage } from "./rate-limit-message.js";
 
 export { isLoopbackHost };
 

extensions/browser/src/browser/chrome-mcp.ts

@@ -1,10 +1,10 @@
 import { randomUUID } from "node:crypto";
 import fs from "node:fs/promises";
-import os from "node:os";
 import path from "node:path";
 import { Client } from "@modelcontextprotocol/sdk/client/index.js";
 import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
 import { normalizeOptionalString, readStringValue } from "openclaw/plugin-sdk/text-runtime";
+import { resolvePreferredOpenClawTmpDir } from "../infra/tmp-openclaw-dir.js";
 import { asRecord } from "../record-shared.js";
 import type { ChromeMcpSnapshotNode } from "./chrome-mcp.snapshot.js";
 import type { BrowserTab } from "./client.js";
@@ -332,7 +332,7 @@ async function callTool(
 }
 
 async function withTempFile<T>(fn: (filePath: string) => Promise<T>): Promise<T> {
-  const dir = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-chrome-mcp-"));
+  const dir = await fs.mkdtemp(path.join(resolvePreferredOpenClawTmpDir(), "openclaw-chrome-mcp-"));
   const filePath = path.join(dir, randomUUID());
   try {
     return await fn(filePath);

extensions/browser/src/browser/chrome.executables.test.ts

@@ -0,0 +1,42 @@
+import fs from "node:fs";
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import {
+  parseBrowserMajorVersion,
+  resolveGoogleChromeExecutableForPlatform,
+} from "./chrome.executables.js";
+
+describe("chrome executables", () => {
+  beforeEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  it("parses odd dotted browser version tokens using the last match", () => {
+    expect(parseBrowserMajorVersion("Chromium 3.0/1.2.3")).toBe(1);
+  });
+
+  it("returns null when no dotted version token exists", () => {
+    expect(parseBrowserMajorVersion("no version here")).toBeNull();
+  });
+
+  it("classifies beta Linux Google Chrome builds as canary", () => {
+    vi.spyOn(fs, "existsSync").mockImplementation((candidate) => {
+      return String(candidate) === "/usr/bin/google-chrome-beta";
+    });
+
+    expect(resolveGoogleChromeExecutableForPlatform("linux")).toEqual({
+      kind: "canary",
+      path: "/usr/bin/google-chrome-beta",
+    });
+  });
+
+  it("classifies unstable Linux Google Chrome builds as canary", () => {
+    vi.spyOn(fs, "existsSync").mockImplementation((candidate) => {
+      return String(candidate) === "/usr/bin/google-chrome-unstable";
+    });
+
+    expect(resolveGoogleChromeExecutableForPlatform("linux")).toEqual({
+      kind: "canary",
+      path: "/usr/bin/google-chrome-unstable",
+    });
+  });
+});

extensions/browser/src/browser/client-fetch.ts

@@ -9,6 +9,7 @@ import {
   createBrowserControlContext,
   startBrowserControlServiceFromConfig,
 } from "./control-service.js";
+import { resolveBrowserRateLimitMessage } from "./rate-limit-message.js";
 import { createBrowserRouteDispatcher } from "./routes/dispatcher.js";
 
 // Application-level error from the browser control service (service is reachable
@@ -104,36 +105,10 @@ const BROWSER_TOOL_MODEL_HINT =
   "Do NOT retry the browser tool — it will keep failing. " +
   "Use an alternative approach or inform the user that the browser is currently unavailable.";
 
-const BROWSER_SERVICE_RATE_LIMIT_MESSAGE =
-  "Browser service rate limit reached. " +
-  "Wait for the current session to complete, or retry later.";
-
-const BROWSERBASE_RATE_LIMIT_MESSAGE =
-  "Browserbase rate limit reached (max concurrent sessions). " +
-  "Wait for the current session to complete, or upgrade your plan.";
-
 function isRateLimitStatus(status: number): boolean {
   return status === 429;
 }
 
-function isBrowserbaseUrl(url: string): boolean {
-  if (!isAbsoluteHttp(url)) {
-    return false;
-  }
-  try {
-    const host = normalizeLowercaseStringOrEmpty(new URL(url).hostname);
-    return host === "browserbase.com" || host.endsWith(".browserbase.com");
-  } catch {
-    return false;
-  }
-}
-
-export function resolveBrowserRateLimitMessage(url: string): string {
-  return isBrowserbaseUrl(url)
-    ? BROWSERBASE_RATE_LIMIT_MESSAGE
-    : BROWSER_SERVICE_RATE_LIMIT_MESSAGE;
-}
-
 function resolveBrowserFetchOperatorHint(url: string): string {
   const isLocal = !isAbsoluteHttp(url);
   return isLocal

extensions/browser/src/browser/control-auth.auto-token.test.ts

@@ -4,6 +4,7 @@ import type { OpenClawConfig } from "../config/config.js";
 
 const mocks = vi.hoisted(() => ({
   loadConfig: vi.fn<() => OpenClawConfig>(),
+  writeConfigFile: vi.fn<(cfg: OpenClawConfig) => Promise<void>>(async (_cfg) => {}),
   resolveGatewayAuth: vi.fn(
     ({
       authConfig,
@@ -46,6 +47,7 @@ const mocks = vi.hoisted(() => ({
 
 vi.mock("../config/config.js", () => ({
   loadConfig: mocks.loadConfig,
+  writeConfigFile: mocks.writeConfigFile,
 }));
 
 vi.mock("../gateway/startup-auth.js", () => ({
@@ -59,7 +61,7 @@ vi.mock("../gateway/auth.js", () => ({
 let ensureBrowserControlAuth: typeof import("./control-auth.js").ensureBrowserControlAuth;
 
 describe("ensureBrowserControlAuth", () => {
-  const expectExplicitModeSkipsAutoAuth = async (mode: "password" | "none") => {
+  const expectExplicitModeSkipsAutoAuth = async (mode: "password") => {
     const cfg: OpenClawConfig = {
       gateway: {
         auth: { mode },
@@ -72,6 +74,7 @@ describe("ensureBrowserControlAuth", () => {
     const result = await ensureBrowserControlAuth({ cfg, env: {} as NodeJS.ProcessEnv });
     expect(result).toEqual({ auth: {} });
     expect(mocks.loadConfig).not.toHaveBeenCalled();
+    expect(mocks.writeConfigFile).not.toHaveBeenCalled();
     expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
   };
 
@@ -95,6 +98,7 @@ describe("ensureBrowserControlAuth", () => {
   beforeEach(() => {
     vi.restoreAllMocks();
     mocks.loadConfig.mockClear();
+    mocks.writeConfigFile.mockClear();
     mocks.resolveGatewayAuth.mockClear();
     mocks.ensureGatewayStartupAuth.mockClear();
   });
@@ -112,6 +116,7 @@ describe("ensureBrowserControlAuth", () => {
 
     expect(result).toEqual({ auth: { token: "already-set" } });
     expect(mocks.loadConfig).not.toHaveBeenCalled();
+    expect(mocks.writeConfigFile).not.toHaveBeenCalled();
     expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
   });
 
@@ -129,6 +134,7 @@ describe("ensureBrowserControlAuth", () => {
 
     const result = await ensureBrowserControlAuth({ cfg, env: {} as NodeJS.ProcessEnv });
     await expectGeneratedTokenPersisted(result);
+    expect(mocks.writeConfigFile).not.toHaveBeenCalled();
   });
 
   it("skips auto-generation in test env", async () => {
@@ -145,6 +151,7 @@ describe("ensureBrowserControlAuth", () => {
 
     expect(result).toEqual({ auth: {} });
     expect(mocks.loadConfig).not.toHaveBeenCalled();
+    expect(mocks.writeConfigFile).not.toHaveBeenCalled();
     expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
   });
 
@@ -152,8 +159,146 @@ describe("ensureBrowserControlAuth", () => {
     await expectExplicitModeSkipsAutoAuth("password");
   });
 
-  it("respects explicit none mode", async () => {
-    await expectExplicitModeSkipsAutoAuth("none");
+  it("auto-generates and persists browser auth token in none mode", async () => {
+    const cfg: OpenClawConfig = {
+      gateway: {
+        auth: { mode: "none" },
+      },
+      browser: {
+        enabled: true,
+      },
+    };
+    mocks.loadConfig.mockReturnValue(cfg);
+
+    const result = await ensureBrowserControlAuth({ cfg, env: {} as NodeJS.ProcessEnv });
+
+    expect(result.generatedToken).toMatch(/^[a-f0-9]{48}$/);
+    expect(result.auth.token).toBe(result.generatedToken);
+    expect(result.auth.password).toBeUndefined();
+    expect(mocks.writeConfigFile).toHaveBeenCalledTimes(1);
+    const persistedCfg = mocks.writeConfigFile.mock.calls[0]?.[0] as OpenClawConfig | undefined;
+    expect(persistedCfg?.gateway?.auth?.mode).toBe("none");
+    expect(persistedCfg?.gateway?.auth?.token).toBe(result.generatedToken);
+    expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
+  });
+
+  it("does not persist over unresolved token SecretRef in none mode", async () => {
+    const cfg: OpenClawConfig = {
+      gateway: {
+        auth: {
+          mode: "none",
+          token: { source: "env", provider: "default", id: "BROWSER_TOKEN" },
+        },
+      },
+      browser: {
+        enabled: true,
+      },
+    };
+    mocks.loadConfig.mockReturnValue(cfg);
+
+    const result = await ensureBrowserControlAuth({ cfg, env: {} as NodeJS.ProcessEnv });
+
+    expect(result).toEqual({ auth: {} });
+    expect(mocks.writeConfigFile).not.toHaveBeenCalled();
+    expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
+  });
+
+  it("still auto-generates in none mode when only password SecretRef is set", async () => {
+    const cfg: OpenClawConfig = {
+      gateway: {
+        auth: {
+          mode: "none",
+          password: { source: "env", provider: "default", id: "INACTIVE_PASSWORD" },
+        },
+      },
+      browser: {
+        enabled: true,
+      },
+    };
+    mocks.loadConfig.mockReturnValue(cfg);
+
+    const result = await ensureBrowserControlAuth({ cfg, env: {} as NodeJS.ProcessEnv });
+
+    expect(result.generatedToken).toMatch(/^[a-f0-9]{48}$/);
+    expect(result.auth.token).toBe(result.generatedToken);
+    expect(result.auth.password).toBeUndefined();
+    expect(mocks.writeConfigFile).toHaveBeenCalledTimes(1);
+    const persistedCfg = mocks.writeConfigFile.mock.calls[0]?.[0] as OpenClawConfig | undefined;
+    expect(persistedCfg?.gateway?.auth?.mode).toBe("none");
+    expect(persistedCfg?.gateway?.auth?.token).toBe(result.generatedToken);
+    expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
+  });
+
+  it("auto-generates in trusted-proxy mode and persists browser auth password", async () => {
+    const cfg: OpenClawConfig = {
+      gateway: {
+        auth: { mode: "trusted-proxy", trustedProxy: { userHeader: "x-forwarded-user" } },
+      },
+      browser: {
+        enabled: true,
+      },
+    };
+    mocks.loadConfig.mockReturnValue(cfg);
+
+    const result = await ensureBrowserControlAuth({ cfg, env: {} as NodeJS.ProcessEnv });
+
+    expect(result.generatedToken).toMatch(/^[a-f0-9]{48}$/);
+    expect(result.auth.password).toBe(result.generatedToken);
+    expect(result.auth.token).toBeUndefined();
+    expect(mocks.writeConfigFile).toHaveBeenCalledTimes(1);
+    const persistedCfg = mocks.writeConfigFile.mock.calls[0]?.[0] as OpenClawConfig | undefined;
+    expect(persistedCfg?.gateway?.auth?.mode).toBe("trusted-proxy");
+    expect(persistedCfg?.gateway?.auth?.password).toBe(result.generatedToken);
+    expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
+  });
+
+  it("still auto-generates in trusted-proxy mode when only token SecretRef is set", async () => {
+    const cfg: OpenClawConfig = {
+      gateway: {
+        auth: {
+          mode: "trusted-proxy",
+          token: { source: "env", provider: "default", id: "INACTIVE_TOKEN" },
+          trustedProxy: { userHeader: "x-forwarded-user" },
+        },
+      },
+      browser: {
+        enabled: true,
+      },
+    };
+    mocks.loadConfig.mockReturnValue(cfg);
+
+    const result = await ensureBrowserControlAuth({ cfg, env: {} as NodeJS.ProcessEnv });
+
+    expect(result.generatedToken).toMatch(/^[a-f0-9]{48}$/);
+    expect(result.auth.password).toBe(result.generatedToken);
+    expect(result.auth.token).toBeUndefined();
+    expect(mocks.writeConfigFile).toHaveBeenCalledTimes(1);
+    const persistedCfg = mocks.writeConfigFile.mock.calls[0]?.[0] as OpenClawConfig | undefined;
+    expect(persistedCfg?.gateway?.auth?.mode).toBe("trusted-proxy");
+    expect(persistedCfg?.gateway?.auth?.password).toBe(result.generatedToken);
+    expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
+  });
+
+  it("does not persist over unresolved password SecretRef in trusted-proxy mode", async () => {
+    const cfg: OpenClawConfig = {
+      gateway: {
+        auth: {
+          mode: "trusted-proxy",
+          password: { source: "env", provider: "default", id: "BROWSER_PASSWORD" },
+          trustedProxy: { userHeader: "x-forwarded-user" },
+        },
+      },
+      browser: {
+        enabled: true,
+      },
+    };
+    mocks.loadConfig.mockReturnValue(cfg);
+
+    const result = await ensureBrowserControlAuth({ cfg, env: {} as NodeJS.ProcessEnv });
+
+    expect(result).toEqual({ auth: {} });
+    expect(mocks.writeConfigFile).not.toHaveBeenCalled();
+    expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
   });
 
   it("reuses auth from latest config snapshot", async () => {
@@ -176,6 +321,7 @@ describe("ensureBrowserControlAuth", () => {
     const result = await ensureBrowserControlAuth({ cfg, env: {} as NodeJS.ProcessEnv });
 
     expect(result).toEqual({ auth: { token: "latest-token" } });
+    expect(mocks.writeConfigFile).not.toHaveBeenCalled();
     expect(mocks.ensureGatewayStartupAuth).not.toHaveBeenCalled();
   });
 

extensions/browser/src/browser/control-auth.test.ts

@@ -6,7 +6,7 @@ describe("ensureBrowserControlAuth", () => {
   async function expectNoAutoGeneratedAuth(cfg: OpenClawConfig): Promise<void> {
     const result = await ensureBrowserControlAuth({
       cfg,
-      env: { OPENCLAW_BROWSER_AUTO_AUTH: "1" },
+      env: { NODE_ENV: "test" },
     });
     expect(result.generatedToken).toBeUndefined();
     expect(result.auth.token).toBeUndefined();
@@ -14,7 +14,7 @@ describe("ensureBrowserControlAuth", () => {
   }
 
   describe("trusted-proxy mode", () => {
-    it("should not auto-generate token when auth mode is trusted-proxy", async () => {
+    it("should skip auto-generation in test mode", async () => {
       const cfg: OpenClawConfig = {
         gateway: {
           auth: {
@@ -31,7 +31,7 @@ describe("ensureBrowserControlAuth", () => {
   });
 
   describe("password mode", () => {
-    it("should not auto-generate token when auth mode is password (even if password not set)", async () => {
+    it("should skip auto-generation in test mode", async () => {
       const cfg: OpenClawConfig = {
         gateway: {
           auth: {
@@ -44,7 +44,7 @@ describe("ensureBrowserControlAuth", () => {
   });
 
   describe("none mode", () => {
-    it("should not auto-generate token when auth mode is none", async () => {
+    it("should skip auto-generation in test mode", async () => {
       const cfg: OpenClawConfig = {
         gateway: {
           auth: {
@@ -69,7 +69,7 @@ describe("ensureBrowserControlAuth", () => {
 
       const result = await ensureBrowserControlAuth({
         cfg,
-        env: { OPENCLAW_BROWSER_AUTO_AUTH: "1" },
+        env: {} as NodeJS.ProcessEnv,
       });
 
       expect(result.generatedToken).toBeUndefined();

extensions/browser/src/browser/control-auth.ts

@@ -1,9 +1,10 @@
+import crypto from "node:crypto";
 import {
   normalizeLowercaseStringOrEmpty,
   normalizeOptionalString,
 } from "openclaw/plugin-sdk/text-runtime";
 import type { OpenClawConfig } from "../config/config.js";
-import { loadConfig } from "../config/config.js";
+import { loadConfig, writeConfigFile } from "../config/config.js";
 import { resolveGatewayAuth } from "../gateway/auth.js";
 import { ensureGatewayStartupAuth } from "../gateway/startup-auth.js";
 
@@ -13,7 +14,7 @@ export type BrowserControlAuth = {
 };
 
 export function resolveBrowserControlAuth(
-  cfg: OpenClawConfig | undefined,
+  cfg?: OpenClawConfig,
   env: NodeJS.ProcessEnv = process.env,
 ): BrowserControlAuth {
   const auth = resolveGatewayAuth({
@@ -29,7 +30,7 @@ export function resolveBrowserControlAuth(
   };
 }
 
-function shouldAutoGenerateBrowserAuth(env: NodeJS.ProcessEnv): boolean {
+export function shouldAutoGenerateBrowserAuth(env: NodeJS.ProcessEnv): boolean {
   const nodeEnv = normalizeLowercaseStringOrEmpty(env.NODE_ENV);
   if (nodeEnv === "test") {
     return false;
@@ -41,6 +42,89 @@ function shouldAutoGenerateBrowserAuth(env: NodeJS.ProcessEnv): boolean {
   return true;
 }
 
+function hasExplicitNonStringGatewayCredentialForMode(params: {
+  cfg?: OpenClawConfig;
+  mode: "none" | "trusted-proxy";
+}): boolean {
+  const { cfg, mode } = params;
+  const auth = cfg?.gateway?.auth;
+  if (!auth) {
+    return false;
+  }
+  if (mode === "none") {
+    return auth.token != null && typeof auth.token !== "string";
+  }
+  return auth.password != null && typeof auth.password !== "string";
+}
+
+function generateBrowserControlToken(): string {
+  return crypto.randomBytes(24).toString("hex");
+}
+
+async function generateAndPersistBrowserControlToken(params: {
+  cfg: OpenClawConfig;
+  env: NodeJS.ProcessEnv;
+}): Promise<{
+  auth: BrowserControlAuth;
+  generatedToken?: string;
+}> {
+  const token = generateBrowserControlToken();
+  const nextCfg: OpenClawConfig = {
+    ...params.cfg,
+    gateway: {
+      ...params.cfg.gateway,
+      auth: {
+        ...params.cfg.gateway?.auth,
+        token,
+      },
+    },
+  };
+  await writeConfigFile(nextCfg);
+
+  // Re-read to stay consistent with any concurrent config writer.
+  const persistedAuth = resolveBrowserControlAuth(loadConfig(), params.env);
+  if (persistedAuth.token || persistedAuth.password) {
+    return {
+      auth: persistedAuth,
+      generatedToken: persistedAuth.token === token ? token : undefined,
+    };
+  }
+
+  return { auth: { token }, generatedToken: token };
+}
+
+async function generateAndPersistBrowserControlPassword(params: {
+  cfg: OpenClawConfig;
+  env: NodeJS.ProcessEnv;
+}): Promise<{
+  auth: BrowserControlAuth;
+  generatedToken?: string;
+}> {
+  const password = generateBrowserControlToken();
+  const nextCfg: OpenClawConfig = {
+    ...params.cfg,
+    gateway: {
+      ...params.cfg.gateway,
+      auth: {
+        ...params.cfg.gateway?.auth,
+        password,
+      },
+    },
+  };
+  await writeConfigFile(nextCfg);
+
+  // Re-read to stay consistent with any concurrent config writer.
+  const persistedAuth = resolveBrowserControlAuth(loadConfig(), params.env);
+  if (persistedAuth.token || persistedAuth.password) {
+    return {
+      auth: persistedAuth,
+      generatedToken: persistedAuth.password === password ? password : undefined,
+    };
+  }
+
+  return { auth: { password }, generatedToken: password };
+}
+
 export async function ensureBrowserControlAuth(params: {
   cfg: OpenClawConfig;
   env?: NodeJS.ProcessEnv;
@@ -62,14 +146,6 @@ export async function ensureBrowserControlAuth(params: {
     return { auth };
   }
 
-  if (params.cfg.gateway?.auth?.mode === "none") {
-    return { auth };
-  }
-
-  if (params.cfg.gateway?.auth?.mode === "trusted-proxy") {
-    return { auth };
-  }
-
   // Re-read latest config to avoid racing with concurrent config writers.
   const latestCfg = loadConfig();
   const latestAuth = resolveBrowserControlAuth(latestCfg, env);
@@ -79,11 +155,25 @@ export async function ensureBrowserControlAuth(params: {
   if (latestCfg.gateway?.auth?.mode === "password") {
     return { auth: latestAuth };
   }
-  if (latestCfg.gateway?.auth?.mode === "none") {
-    return { auth: latestAuth };
-  }
-  if (latestCfg.gateway?.auth?.mode === "trusted-proxy") {
-    return { auth: latestAuth };
+  const latestMode = latestCfg.gateway?.auth?.mode;
+  if (latestMode === "none" || latestMode === "trusted-proxy") {
+    if (
+      hasExplicitNonStringGatewayCredentialForMode({
+        cfg: latestCfg,
+        mode: latestMode,
+      })
+    ) {
+      // Avoid silently overwriting SecretRef-style gateway auth inputs with generated plaintext.
+      // Startup will fail closed if no resolved browser auth is available.
+      return { auth: latestAuth };
+    }
+    if (latestMode === "trusted-proxy") {
+      // gateway.auth.mode=trusted-proxy must never be persisted with gateway.auth.token.
+      // Persist a browser-only shared secret through gateway.auth.password instead so
+      // out-of-process loopback clients can resolve it from config/env.
+      return await generateAndPersistBrowserControlPassword({ cfg: latestCfg, env });
+    }
+    return await generateAndPersistBrowserControlToken({ cfg: latestCfg, env });
   }
 
   const ensured = await ensureGatewayStartupAuth({

extensions/browser/src/browser/pw-ai.ts

@@ -29,6 +29,7 @@ export {
   dragViaPlaywright,
   emulateMediaViaPlaywright,
   evaluateViaPlaywright,
+  executeActViaPlaywright,
   fillFormViaPlaywright,
   getConsoleMessagesViaPlaywright,
   getNetworkRequestsViaPlaywright,

extensions/browser/src/browser/pw-tools-core.browser-ssrf-guard.test.ts

@@ -52,8 +52,13 @@ describe("pw-tools-core browser SSRF guards", () => {
   });
 
   it("re-checks click-triggered navigations with the session safety helper", async () => {
-    pageState.page = { url: vi.fn(() => "https://example.com") };
-    pageState.locator = { click: vi.fn(async () => {}) };
+    let currentUrl = "https://example.com";
+    pageState.page = { url: vi.fn(() => currentUrl) };
+    pageState.locator = {
+      click: vi.fn(async () => {
+        currentUrl = "https://target.example";
+      }),
+    };
 
     await interactions.clickViaPlaywright({
       cdpUrl: "http://127.0.0.1:18792",
@@ -86,8 +91,13 @@ describe("pw-tools-core browser SSRF guards", () => {
   });
 
   it("re-checks batched click-triggered navigations with the session safety helper", async () => {
-    pageState.page = { url: vi.fn(() => "https://example.com") };
-    pageState.locator = { click: vi.fn(async () => {}) };
+    let currentUrl = "https://example.com";
+    pageState.page = { url: vi.fn(() => currentUrl) };
+    pageState.locator = {
+      click: vi.fn(async () => {
+        currentUrl = "https://target.example";
+      }),
+    };
 
     await interactions.batchViaPlaywright({
       cdpUrl: "http://127.0.0.1:18792",

extensions/browser/src/browser/pw-tools-core.clamps-timeoutms-scrollintoview.test.ts

@@ -65,7 +65,7 @@ describe("pw-tools-core", () => {
       throw new Error(errorMessage);
     });
     setPwToolsCoreCurrentRefLocator({ click });
-    setPwToolsCoreCurrentPage({});
+    setPwToolsCoreCurrentPage({ url: vi.fn(() => "https://example.com") });
 
     await expect(
       mod.clickViaPlaywright({
@@ -82,7 +82,7 @@ describe("pw-tools-core", () => {
       );
     });
     setPwToolsCoreCurrentRefLocator({ click });
-    setPwToolsCoreCurrentPage({});
+    setPwToolsCoreCurrentPage({ url: vi.fn(() => "https://example.com") });
 
     await expect(
       mod.clickViaPlaywright({

extensions/browser/src/browser/pw-tools-core.interactions.navigation-guard.test.ts

@@ -10,7 +10,7 @@ installPwToolsCoreTestHooks();
 const mod = await import("./pw-tools-core.js");
 
 describe("pw-tools-core interaction navigation guard", () => {
-  it("does not wait for the grace window after a successful non-navigating click", async () => {
+  it("waits for the grace window before completing a successful non-navigating click", async () => {
     vi.useFakeTimers();
     try {
       const listeners = new Set<() => void>();
@@ -42,15 +42,16 @@ describe("pw-tools-core interaction navigation guard", () => {
         .then(completion);
 
       await vi.advanceTimersByTimeAsync(0);
-      expect(completion).toHaveBeenCalledTimes(1);
+      expect(completion).not.toHaveBeenCalled();
       expect(listeners.size).toBe(1);
       expect(
         getPwToolsCoreSessionMocks().assertPageNavigationCompletedSafely,
       ).not.toHaveBeenCalled();
 
       await vi.advanceTimersByTimeAsync(250);
-      expect(listeners.size).toBe(0);
       await task;
+      expect(completion).toHaveBeenCalledTimes(1);
+      expect(listeners.size).toBe(0);
     } finally {
       vi.useRealTimers();
     }
@@ -96,13 +97,14 @@ describe("pw-tools-core interaction navigation guard", () => {
         .then(completion);
 
       await vi.advanceTimersByTimeAsync(0);
-      expect(completion).toHaveBeenCalledTimes(1);
+      expect(completion).not.toHaveBeenCalled();
       expect(
         getPwToolsCoreSessionMocks().assertPageNavigationCompletedSafely,
       ).not.toHaveBeenCalled();
 
       await vi.advanceTimersByTimeAsync(10);
       await task;
+      expect(completion).toHaveBeenCalledTimes(1);
 
       expect(getPwToolsCoreSessionMocks().assertPageNavigationCompletedSafely).toHaveBeenCalledWith(
         {
@@ -207,20 +209,22 @@ describe("pw-tools-core interaction navigation guard", () => {
       setPwToolsCoreCurrentRefLocator({ click });
       setPwToolsCoreCurrentPage(page);
 
-      await mod.clickViaPlaywright({
+      const first = mod.clickViaPlaywright({
         cdpUrl: "http://127.0.0.1:18792",
         targetId: "T1",
         ref: "1",
         ssrfPolicy: { allowPrivateNetwork: false },
       });
+      await vi.advanceTimersByTimeAsync(0);
       expect(listeners.size).toBe(1);
 
-      await mod.clickViaPlaywright({
+      const second = mod.clickViaPlaywright({
         cdpUrl: "http://127.0.0.1:18792",
         targetId: "T1",
         ref: "1",
         ssrfPolicy: { allowPrivateNetwork: false },
       });
+      await vi.advanceTimersByTimeAsync(0);
       expect(listeners.size).toBe(1);
 
       currentUrl = "http://127.0.0.1:9222/json/list";
@@ -228,6 +232,7 @@ describe("pw-tools-core interaction navigation guard", () => {
         listener();
       }
       await vi.advanceTimersByTimeAsync(0);
+      await Promise.all([first, second]);
 
       expect(
         getPwToolsCoreSessionMocks().assertPageNavigationCompletedSafely,
@@ -238,6 +243,56 @@ describe("pw-tools-core interaction navigation guard", () => {
     }
   });
 
+  it("propagates blocked delayed navigation instead of reporting click success", async () => {
+    vi.useFakeTimers();
+    try {
+      const listeners = new Set<() => void>();
+      let currentUrl = "http://127.0.0.1:9222/json/version";
+      const click = vi.fn(async () => {
+        setTimeout(() => {
+          currentUrl = "http://127.0.0.1:9222/private-target";
+          for (const listener of listeners) {
+            listener();
+          }
+        }, 10);
+      });
+      const page = {
+        on: vi.fn((event: string, listener: () => void) => {
+          if (event === "framenavigated") {
+            listeners.add(listener);
+          }
+        }),
+        off: vi.fn((event: string, listener: () => void) => {
+          if (event === "framenavigated") {
+            listeners.delete(listener);
+          }
+        }),
+        url: vi.fn(() => currentUrl),
+      };
+      setPwToolsCoreCurrentRefLocator({ click });
+      setPwToolsCoreCurrentPage(page);
+
+      const blocked = new Error("blocked delayed interaction navigation");
+      getPwToolsCoreSessionMocks().assertPageNavigationCompletedSafely.mockRejectedValueOnce(
+        blocked,
+      );
+
+      const task = mod.clickViaPlaywright({
+        cdpUrl: "http://127.0.0.1:18792",
+        targetId: "T1",
+        ref: "1",
+        ssrfPolicy: { allowPrivateNetwork: false },
+      });
+      const rejection = expect(task).rejects.toThrow("blocked delayed interaction navigation");
+
+      await vi.advanceTimersByTimeAsync(10);
+      await rejection;
+      expect(listeners.size).toBe(0);
+    } finally {
+      vi.useRealTimers();
+    }
+  });
+
   it("runs the post-click navigation guard with the resolved SSRF policy", async () => {
     const click = vi.fn(async () => {});
     const page = {

extensions/browser/src/browser/pw-tools-core.interactions.ts

@@ -1,7 +1,15 @@
 import { normalizeOptionalString } from "openclaw/plugin-sdk/text-runtime";
-import { formatErrorMessage } from "../infra/errors.js";
 import type { Frame, Page } from "playwright-core";
+import { formatErrorMessage } from "../infra/errors.js";
 import type { SsrFPolicy } from "../infra/net/ssrf.js";
+import {
+  ACT_MAX_BATCH_ACTIONS,
+  ACT_MAX_BATCH_DEPTH,
+  ACT_MAX_CLICK_DELAY_MS,
+  ACT_MAX_WAIT_TIME_MS,
+  resolveActInteractionTimeoutMs,
+  resolveActWaitTimeoutMs,
+} from "./act-policy.js";
 import type { BrowserActRequest, BrowserFormField } from "./client-actions-core.js";
 import { DEFAULT_FILL_FIELD_TYPE } from "./form-fields.js";
 import { DEFAULT_UPLOAD_DIR, resolveStrictExistingPathsWithinRoot } from "./paths.js";
@@ -26,9 +34,6 @@ type TargetOpts = {
   targetId?: string;
 };
 
-const MAX_CLICK_DELAY_MS = 5_000;
-const MAX_WAIT_TIME_MS = 30_000;
-const MAX_BATCH_ACTIONS = 100;
 const INTERACTION_NAVIGATION_GRACE_MS = 250;
 
 type NavigationObservablePage = Pick<Page, "url"> & {
@@ -57,9 +62,7 @@ async function getRestoredPageForTarget(opts: TargetOpts) {
   return page;
 }
 
-function resolveInteractionTimeoutMs(timeoutMs?: number): number {
-  return Math.max(500, Math.min(60_000, Math.floor(timeoutMs ?? 8000)));
-}
+const resolveInteractionTimeoutMs = resolveActInteractionTimeoutMs;
 
 // Returns true only when the URL change indicates a cross-document navigation
 // (i.e., a real network fetch occurred). Same-document hash-only mutations —
@@ -164,59 +167,68 @@ function scheduleDelayedInteractionNavigationGuard(opts: {
   previousUrl: string;
   ssrfPolicy?: SsrFPolicy;
   targetId?: string;
-}): void {
+}): Promise<void> {
   if (!opts.ssrfPolicy) {
-    return;
+    return Promise.resolve();
   }
   const page = opts.page as unknown as NavigationObservablePage;
   if (didCrossDocumentUrlChange(page, opts.previousUrl)) {
-    void assertPageNavigationCompletedSafely({
+    return assertPageNavigationCompletedSafely({
       cdpUrl: opts.cdpUrl,
       page: opts.page,
       response: null,
       ssrfPolicy: opts.ssrfPolicy,
       targetId: opts.targetId,
-    }).catch(() => {});
-    return;
+    });
   }
   if (typeof page.on !== "function" || typeof page.off !== "function") {
-    return;
+    return Promise.resolve();
   }
 
   pendingInteractionNavigationGuardCleanup.get(opts.page)?.();
 
-  const onFrameNavigated = (frame: Frame) => {
-    if (!isMainFrameNavigation(page, frame)) {
-      return;
-    }
-    // Use isHashOnlyNavigation rather than !didCrossDocumentUrlChange: the
-    // event firing is itself the navigation signal, so a same-URL reload must
-    // not be treated as "no navigation" the way URL polling would.
-    if (isHashOnlyNavigation(page.url(), opts.previousUrl)) {
-      return;
-    }
-    cleanup();
-    void assertPageNavigationCompletedSafely({
-      cdpUrl: opts.cdpUrl,
-      page: opts.page,
-      response: null,
-      ssrfPolicy: opts.ssrfPolicy,
-      targetId: opts.targetId,
-    }).catch(() => {});
-  };
-  const timeout = setTimeout(() => {
-    cleanup();
-  }, INTERACTION_NAVIGATION_GRACE_MS);
-  const cleanup = () => {
-    clearTimeout(timeout);
-    page.off!("framenavigated", onFrameNavigated);
-    if (pendingInteractionNavigationGuardCleanup.get(opts.page) === cleanup) {
-      pendingInteractionNavigationGuardCleanup.delete(opts.page);
-    }
-  };
+  return new Promise<void>((resolve, reject) => {
+    const settle = (err?: unknown) => {
+      cleanup();
+      if (err) {
+        reject(err);
+        return;
+      }
+      resolve();
+    };
+    const onFrameNavigated = (frame: Frame) => {
+      if (!isMainFrameNavigation(page, frame)) {
+        return;
+      }
+      // Use isHashOnlyNavigation rather than !didCrossDocumentUrlChange: the
+      // event firing is itself the navigation signal, so a same-URL reload must
+      // not be treated as "no navigation" the way URL polling would.
+      if (isHashOnlyNavigation(page.url(), opts.previousUrl)) {
+        return;
+      }
+      cleanup();
+      void assertPageNavigationCompletedSafely({
+        cdpUrl: opts.cdpUrl,
+        page: opts.page,
+        response: null,
+        ssrfPolicy: opts.ssrfPolicy,
+        targetId: opts.targetId,
+      }).then(() => settle(), settle);
+    };
+    const timeout = setTimeout(() => {
+      settle();
+    }, INTERACTION_NAVIGATION_GRACE_MS);
+    const cleanup = () => {
+      clearTimeout(timeout);
+      page.off!("framenavigated", onFrameNavigated);
+      if (pendingInteractionNavigationGuardCleanup.get(opts.page) === settle) {
+        pendingInteractionNavigationGuardCleanup.delete(opts.page);
+      }
+    };
 
-  pendingInteractionNavigationGuardCleanup.set(opts.page, cleanup);
-  page.on("framenavigated", onFrameNavigated);
+    pendingInteractionNavigationGuardCleanup.set(opts.page, settle);
+    page.on!("framenavigated", onFrameNavigated);
+  });
 }
 
 async function assertInteractionNavigationCompletedSafely<T>(opts: {
@@ -292,9 +304,10 @@ async function assertInteractionNavigationCompletedSafely<T>(opts: {
       });
     }
   } else {
-    // Successful non-navigating interactions should not wait out the grace window,
-    // but we still keep a short-lived listener alive to quarantine late SSRF hops.
-    scheduleDelayedInteractionNavigationGuard({
+    // Successful interactions still need a short grace window: a click can resolve
+    // before the navigation event fires, and a blocked late hop must be observable
+    // to the current caller instead of only quarantining the page in the background.
+    await scheduleDelayedInteractionNavigationGuard({
       cdpUrl: opts.cdpUrl,
       page: opts.page,
       previousUrl: opts.previousUrl,
@@ -309,22 +322,64 @@ async function assertInteractionNavigationCompletedSafely<T>(opts: {
   return result as T;
 }
 
-async function awaitEvalWithAbort<T>(
-  evalPromise: Promise<T>,
+async function awaitActionWithAbort<T>(
+  actionPromise: Promise<T>,
   abortPromise?: Promise<never>,
 ): Promise<T> {
   if (!abortPromise) {
-    return await evalPromise;
+    return await actionPromise;
   }
   try {
-    return await Promise.race([evalPromise, abortPromise]);
+    return await Promise.race([actionPromise, abortPromise]);
   } catch (err) {
-    // If abort wins the race, evaluate may reject later; avoid unhandled rejections.
-    void evalPromise.catch(() => {});
+    // If abort wins the race, the action may reject later; avoid unhandled rejections.
+    void actionPromise.catch(() => {});
     throw err;
   }
 }
 
+function createAbortPromise(signal?: AbortSignal): {
+  abortPromise?: Promise<never>;
+  cleanup: () => void;
+} {
+  return createAbortPromiseWithListener(signal);
+}
+
+function createAbortPromiseWithListener(
+  signal?: AbortSignal,
+  onAbort?: () => void,
+): {
+  abortPromise?: Promise<never>;
+  cleanup: () => void;
+} {
+  if (!signal) {
+    return { cleanup: () => {} };
+  }
+  let abortListener: (() => void) | undefined;
+  const abortPromise: Promise<never> = signal.aborted
+    ? (() => {
+        onAbort?.();
+        return Promise.reject(signal.reason ?? new Error("aborted"));
+      })()
+    : new Promise((_, reject) => {
+        abortListener = () => {
+          onAbort?.();
+          reject(signal.reason ?? new Error("aborted"));
+        };
+        signal.addEventListener("abort", abortListener, { once: true });
+      });
+  // Avoid unhandled rejections on early returns.
+  void abortPromise.catch(() => {});
+  return {
+    abortPromise,
+    cleanup: () => {
+      if (abortListener) {
+        signal.removeEventListener("abort", abortListener);
+      }
+    },
+  };
+}
+
 async function assertPostInteractionNavigationSafe(opts: {
   cdpUrl: string;
   page: Awaited<ReturnType<typeof getPageForTargetId>>;
@@ -380,7 +435,11 @@ export async function clickViaPlaywright(opts: {
   try {
     await assertInteractionNavigationCompletedSafely({
       action: async () => {
-        const delayMs = resolveBoundedDelayMs(opts.delayMs, "click delayMs", MAX_CLICK_DELAY_MS);
+        const delayMs = resolveBoundedDelayMs(
+          opts.delayMs,
+          "click delayMs",
+          ACT_MAX_CLICK_DELAY_MS,
+        );
         if (delayMs > 0) {
           await locator.hover({ timeout });
           await new Promise((resolve) => setTimeout(resolve, delayMs));
@@ -619,38 +678,15 @@ export async function evaluateViaPlaywright(opts: {
   evaluateTimeout = Math.min(evaluateTimeout, outerTimeout);
 
   const signal = opts.signal;
-  let abortListener: (() => void) | undefined;
-  let abortReject: ((reason: unknown) => void) | undefined;
-  let abortPromise: Promise<never> | undefined;
-  if (signal) {
-    abortPromise = new Promise((_, reject) => {
-      abortReject = reject;
-    });
-    // Ensure the abort promise never becomes an unhandled rejection if we throw early.
-    void abortPromise.catch(() => {});
-  }
-  if (signal) {
-    const disconnect = () => {
-      void forceDisconnectPlaywrightForTarget({
-        cdpUrl: opts.cdpUrl,
-        targetId: opts.targetId,
-        reason: "evaluate aborted",
-      }).catch(() => {});
-    };
-    if (signal.aborted) {
-      disconnect();
-      throw signal.reason ?? new Error("aborted");
-    }
-    abortListener = () => {
-      disconnect();
-      abortReject?.(signal.reason ?? new Error("aborted"));
-    };
-    signal.addEventListener("abort", abortListener, { once: true });
-    // If the signal aborted between the initial check and listener registration, handle it.
-    if (signal.aborted) {
-      abortListener();
-      throw signal.reason ?? new Error("aborted");
-    }
+  const { abortPromise, cleanup } = createAbortPromiseWithListener(signal, () => {
+    void forceDisconnectPlaywrightForTarget({
+      cdpUrl: opts.cdpUrl,
+      targetId: opts.targetId,
+      reason: "evaluate aborted",
+    }).catch(() => {});
+  });
+  if (signal?.aborted) {
+    throw signal.reason ?? new Error("aborted");
   }
 
   try {
@@ -686,7 +722,7 @@ export async function evaluateViaPlaywright(opts: {
         timeoutMs: evaluateTimeout,
       });
       const result = await assertInteractionNavigationCompletedSafely({
-        action: () => awaitEvalWithAbort(evalPromise, abortPromise),
+        action: () => awaitActionWithAbort(evalPromise, abortPromise),
         cdpUrl: opts.cdpUrl,
         page,
         previousUrl,
@@ -725,7 +761,7 @@ export async function evaluateViaPlaywright(opts: {
       timeoutMs: evaluateTimeout,
     });
     const result = await assertInteractionNavigationCompletedSafely({
-      action: () => awaitEvalWithAbort(evalPromise, abortPromise),
+      action: () => awaitActionWithAbort(evalPromise, abortPromise),
       cdpUrl: opts.cdpUrl,
       page,
       previousUrl,
@@ -734,9 +770,7 @@ export async function evaluateViaPlaywright(opts: {
     });
     return result;
   } finally {
-    if (signal && abortListener) {
-      signal.removeEventListener("abort", abortListener);
-    }
+    cleanup();
   }
 }
 
@@ -773,46 +807,63 @@ export async function waitForViaPlaywright(opts: {
   loadState?: "load" | "domcontentloaded" | "networkidle";
   fn?: string;
   timeoutMs?: number;
+  signal?: AbortSignal;
 }): Promise<void> {
   const page = await getPageForTargetId(opts);
   ensurePageState(page);
-  const timeout = normalizeTimeoutMs(opts.timeoutMs, 20_000);
+  const timeout = resolveActWaitTimeoutMs(opts.timeoutMs);
+  const { abortPromise, cleanup } = createAbortPromise(opts.signal);
+  const waitForStep = async <T>(stepPromise: Promise<T>) => {
+    await awaitActionWithAbort(stepPromise, abortPromise);
+  };
 
-  if (typeof opts.timeMs === "number" && Number.isFinite(opts.timeMs)) {
-    await page.waitForTimeout(resolveBoundedDelayMs(opts.timeMs, "wait timeMs", MAX_WAIT_TIME_MS));
-  }
-  if (opts.text) {
-    await page.getByText(opts.text).first().waitFor({
-      state: "visible",
-      timeout,
-    });
-  }
-  if (opts.textGone) {
-    await page.getByText(opts.textGone).first().waitFor({
-      state: "hidden",
-      timeout,
-    });
-  }
-  if (opts.selector) {
-    const selector = normalizeOptionalString(opts.selector) ?? "";
-    if (selector) {
-      await page.locator(selector).first().waitFor({ state: "visible", timeout });
+  try {
+    if (typeof opts.timeMs === "number" && Number.isFinite(opts.timeMs)) {
+      await waitForStep(
+        page.waitForTimeout(
+          resolveBoundedDelayMs(opts.timeMs, "wait timeMs", ACT_MAX_WAIT_TIME_MS),
+        ),
+      );
     }
-  }
-  if (opts.url) {
-    const url = normalizeOptionalString(opts.url) ?? "";
-    if (url) {
-      await page.waitForURL(url, { timeout });
+    if (opts.text) {
+      await waitForStep(
+        page.getByText(opts.text).first().waitFor({
+          state: "visible",
+          timeout,
+        }),
+      );
     }
-  }
-  if (opts.loadState) {
-    await page.waitForLoadState(opts.loadState, { timeout });
-  }
-  if (opts.fn) {
-    const fn = normalizeOptionalString(opts.fn) ?? "";
-    if (fn) {
-      await page.waitForFunction(fn, { timeout });
+    if (opts.textGone) {
+      await waitForStep(
+        page.getByText(opts.textGone).first().waitFor({
+          state: "hidden",
+          timeout,
+        }),
+      );
     }
+    if (opts.selector) {
+      const selector = normalizeOptionalString(opts.selector) ?? "";
+      if (selector) {
+        await waitForStep(page.locator(selector).first().waitFor({ state: "visible", timeout }));
+      }
+    }
+    if (opts.url) {
+      const url = normalizeOptionalString(opts.url) ?? "";
+      if (url) {
+        await waitForStep(page.waitForURL(url, { timeout }));
+      }
+    }
+    if (opts.loadState) {
+      await waitForStep(page.waitForLoadState(opts.loadState, { timeout }));
+    }
+    if (opts.fn) {
+      const fn = normalizeOptionalString(opts.fn) ?? "";
+      if (fn) {
+        await waitForStep(page.waitForFunction(fn, { timeout }));
+      }
+    }
+  } finally {
+    cleanup();
   }
 }
 
@@ -1029,8 +1080,6 @@ export async function setInputFilesViaPlaywright(opts: {
   }
 }
 
-const MAX_BATCH_DEPTH = 5;
-
 async function executeSingleAction(
   action: BrowserActRequest,
   cdpUrl: string,
@@ -1038,9 +1087,10 @@ async function executeSingleAction(
   evaluateEnabled?: boolean,
   ssrfPolicy?: SsrFPolicy,
   depth = 0,
-): Promise<void> {
-  if (depth > MAX_BATCH_DEPTH) {
-    throw new Error(`Batch nesting depth exceeds maximum of ${MAX_BATCH_DEPTH}`);
+  signal?: AbortSignal,
+): Promise<unknown> {
+  if (depth > ACT_MAX_BATCH_DEPTH) {
+    throw new Error(`Batch nesting depth exceeds maximum of ${ACT_MAX_BATCH_DEPTH}`);
   }
   const effectiveTargetId = action.targetId ?? targetId;
   switch (action.kind) {
@@ -1152,21 +1202,22 @@ async function executeSingleAction(
         loadState: action.loadState,
         fn: action.fn,
         timeoutMs: action.timeoutMs,
+        signal,
       });
       break;
     case "evaluate":
       if (!evaluateEnabled) {
         throw new Error("act:evaluate is disabled by config (browser.evaluateEnabled=false)");
       }
-      await evaluateViaPlaywright({
+      return await evaluateViaPlaywright({
         cdpUrl,
         targetId: effectiveTargetId,
         ssrfPolicy,
         fn: action.fn,
         ref: action.ref,
         timeoutMs: action.timeoutMs,
+        signal,
       });
-      break;
     case "close":
       await closePageViaPlaywright({
         cdpUrl,
@@ -1182,11 +1233,51 @@ async function executeSingleAction(
         stopOnError: action.stopOnError,
         evaluateEnabled,
         depth: depth + 1,
+        signal,
       });
       break;
     default:
       throw new Error(`Unsupported batch action kind: ${(action as { kind: string }).kind}`);
   }
+  return undefined;
+}
+
+export async function executeActViaPlaywright(opts: {
+  cdpUrl: string;
+  action: BrowserActRequest;
+  targetId?: string;
+  evaluateEnabled?: boolean;
+  ssrfPolicy?: SsrFPolicy;
+  signal?: AbortSignal;
+}): Promise<{
+  result?: unknown;
+  results?: Array<{ ok: boolean; error?: string }>;
+}> {
+  if (opts.action.kind === "batch") {
+    const batch = await batchViaPlaywright({
+      cdpUrl: opts.cdpUrl,
+      targetId: opts.targetId,
+      ssrfPolicy: opts.ssrfPolicy,
+      actions: opts.action.actions,
+      stopOnError: opts.action.stopOnError,
+      evaluateEnabled: opts.evaluateEnabled,
+      signal: opts.signal,
+    });
+    return { results: batch.results };
+  }
+  const result = await executeSingleAction(
+    opts.action,
+    opts.cdpUrl,
+    opts.targetId,
+    opts.evaluateEnabled,
+    opts.ssrfPolicy,
+    0,
+    opts.signal,
+  );
+  if (opts.action.kind === "evaluate") {
+    return { result };
+  }
+  return {};
 }
 
 export async function batchViaPlaywright(opts: {
@@ -1197,16 +1288,20 @@ export async function batchViaPlaywright(opts: {
   evaluateEnabled?: boolean;
   ssrfPolicy?: SsrFPolicy;
   depth?: number;
+  signal?: AbortSignal;
 }): Promise<{ results: Array<{ ok: boolean; error?: string }> }> {
   const depth = opts.depth ?? 0;
-  if (depth > MAX_BATCH_DEPTH) {
-    throw new Error(`Batch nesting depth exceeds maximum of ${MAX_BATCH_DEPTH}`);
+  if (depth > ACT_MAX_BATCH_DEPTH) {
+    throw new Error(`Batch nesting depth exceeds maximum of ${ACT_MAX_BATCH_DEPTH}`);
   }
-  if (opts.actions.length > MAX_BATCH_ACTIONS) {
-    throw new Error(`Batch exceeds maximum of ${MAX_BATCH_ACTIONS} actions`);
+  if (opts.actions.length > ACT_MAX_BATCH_ACTIONS) {
+    throw new Error(`Batch exceeds maximum of ${ACT_MAX_BATCH_ACTIONS} actions`);
   }
   const results: Array<{ ok: boolean; error?: string }> = [];
   for (const action of opts.actions) {
+    if (opts.signal?.aborted) {
+      throw opts.signal.reason ?? new Error("aborted");
+    }
     try {
       await executeSingleAction(
         action,
@@ -1215,6 +1310,7 @@ export async function batchViaPlaywright(opts: {
         opts.evaluateEnabled,
         opts.ssrfPolicy,
         depth,
+        opts.signal,
       );
       results.push({ ok: true });
     } catch (err) {

extensions/browser/src/browser/pw-tools-core.last-file-chooser-arm-wins.test.ts

@@ -150,4 +150,51 @@ describe("pw-tools-core", () => {
       timeout: 1234,
     });
   });
+
+  it("clamps wait timeoutMs to 120000 for wait steps", async () => {
+    const waitForSelector = vi.fn(async () => {});
+    const page = {
+      locator: vi.fn(() => ({
+        first: () => ({ waitFor: waitForSelector }),
+      })),
+      waitForURL: vi.fn(async () => {}),
+      waitForLoadState: vi.fn(async () => {}),
+      waitForFunction: vi.fn(async () => {}),
+      waitForTimeout: vi.fn(async () => {}),
+      getByText: vi.fn(() => ({ first: () => ({ waitFor: vi.fn() }) })),
+    };
+    setPwToolsCoreCurrentPage(page);
+
+    await mod.waitForViaPlaywright({
+      cdpUrl: "http://127.0.0.1:18792",
+      selector: "#main",
+      timeoutMs: 999_999,
+    });
+
+    expect(waitForSelector).toHaveBeenCalledWith({
+      state: "visible",
+      timeout: 120_000,
+    });
+  });
+
+  it("clamps interaction timeoutMs to 60000 for click steps", async () => {
+    const click = vi.fn(async () => {});
+    const page = {
+      url: vi.fn(() => "https://example.com"),
+      locator: vi.fn(() => ({ click })),
+    };
+    setPwToolsCoreCurrentPage(page);
+
+    await mod.clickViaPlaywright({
+      cdpUrl: "http://127.0.0.1:18792",
+      selector: "#main",
+      timeoutMs: 999_999,
+    });
+
+    expect(click).toHaveBeenCalledWith(
+      expect.objectContaining({
+        timeout: 60_000,
+      }),
+    );
+  });
 });

extensions/browser/src/browser/rate-limit-message.ts

@@ -0,0 +1,31 @@
+import { normalizeLowercaseStringOrEmpty } from "openclaw/plugin-sdk/text-runtime";
+
+const BROWSER_SERVICE_RATE_LIMIT_MESSAGE =
+  "Browser service rate limit reached. " +
+  "Wait for the current session to complete, or retry later.";
+
+const BROWSERBASE_RATE_LIMIT_MESSAGE =
+  "Browserbase rate limit reached (max concurrent sessions). " +
+  "Wait for the current session to complete, or upgrade your plan.";
+
+function isAbsoluteHttp(url: string): boolean {
+  return /^https?:\/\//i.test(url.trim());
+}
+
+function isBrowserbaseUrl(url: string): boolean {
+  if (!isAbsoluteHttp(url)) {
+    return false;
+  }
+  try {
+    const host = normalizeLowercaseStringOrEmpty(new URL(url).hostname);
+    return host === "browserbase.com" || host.endsWith(".browserbase.com");
+  } catch {
+    return false;
+  }
+}
+
+export function resolveBrowserRateLimitMessage(url: string): string {
+  return isBrowserbaseUrl(url)
+    ? BROWSERBASE_RATE_LIMIT_MESSAGE
+    : BROWSER_SERVICE_RATE_LIMIT_MESSAGE;
+}

extensions/browser/src/browser/routes/agent.act.download.ts

@@ -6,6 +6,7 @@ import {
   resolveTargetIdFromBody,
   withRouteTabContext,
 } from "./agent.shared.js";
+import { EXISTING_SESSION_LIMITS } from "./existing-session-limits.js";
 import { ensureOutputRootDir, resolveWritableOutputPathOrRespond } from "./output-paths.js";
 import { DEFAULT_DOWNLOAD_DIR } from "./path-output.js";
 import type { BrowserRouteRegistrar } from "./types.js";
@@ -36,11 +37,7 @@ export function registerBrowserAgentActDownloadRoutes(
       targetId,
       run: async ({ profileCtx, cdpUrl, tab }) => {
         if (getBrowserProfileCapabilities(profileCtx.profile).usesChromeMcp) {
-          return jsonError(
-            res,
-            501,
-            "download waiting is not supported for existing-session profiles yet.",
-          );
+          return jsonError(res, 501, EXISTING_SESSION_LIMITS.download.waitUnsupported);
         }
         const pw = await requirePwAi(res, "wait for download");
         if (!pw) {
@@ -90,11 +87,7 @@ export function registerBrowserAgentActDownloadRoutes(
       targetId,
       run: async ({ profileCtx, cdpUrl, tab }) => {
         if (getBrowserProfileCapabilities(profileCtx.profile).usesChromeMcp) {
-          return jsonError(
-            res,
-            501,
-            "downloads are not supported for existing-session profiles yet.",
-          );
+          return jsonError(res, 501, EXISTING_SESSION_LIMITS.download.downloadUnsupported);
         }
         const pw = await requirePwAi(res, "download");
         if (!pw) {

extensions/browser/src/browser/routes/agent.act.errors.ts

@@ -0,0 +1,30 @@
+import type { BrowserResponse } from "./types.js";
+
+export const ACT_ERROR_CODES = {
+  kindRequired: "ACT_KIND_REQUIRED",
+  invalidRequest: "ACT_INVALID_REQUEST",
+  selectorUnsupported: "ACT_SELECTOR_UNSUPPORTED",
+  evaluateDisabled: "ACT_EVALUATE_DISABLED",
+  unsupportedForExistingSession: "ACT_EXISTING_SESSION_UNSUPPORTED",
+  targetIdMismatch: "ACT_TARGET_ID_MISMATCH",
+} as const;
+
+export type ActErrorCode = (typeof ACT_ERROR_CODES)[keyof typeof ACT_ERROR_CODES];
+
+export function jsonActError(
+  res: BrowserResponse,
+  status: number,
+  code: ActErrorCode,
+  message: string,
+) {
+  res.status(status).json({ error: message, code });
+}
+
+export function browserEvaluateDisabledMessage(action: "wait" | "evaluate"): string {
+  return [
+    action === "wait"
+      ? "wait --fn is disabled by config (browser.evaluateEnabled=false)."
+      : "act:evaluate is disabled by config (browser.evaluateEnabled=false).",
+    "Docs: /gateway/configuration#browser-openclaw-managed-browser",
+  ].join("\n");
+}

extensions/browser/src/browser/routes/agent.act.hooks.ts

@@ -7,6 +7,7 @@ import {
   resolveTargetIdFromBody,
   withRouteTabContext,
 } from "./agent.shared.js";
+import { EXISTING_SESSION_LIMITS } from "./existing-session-limits.js";
 import { DEFAULT_UPLOAD_DIR, resolveExistingPathsWithinRoot } from "./path-output.js";
 import type { BrowserRouteRegistrar } from "./types.js";
 import { jsonError, toBoolean, toNumber, toStringArray, toStringOrEmpty } from "./utils.js";
@@ -46,22 +47,14 @@ export function registerBrowserAgentActHookRoutes(
 
         if (getBrowserProfileCapabilities(profileCtx.profile).usesChromeMcp) {
           if (element) {
-            return jsonError(
-              res,
-              501,
-              "existing-session file uploads do not support element selectors; use ref/inputRef.",
-            );
+            return jsonError(res, 501, EXISTING_SESSION_LIMITS.hooks.uploadElement);
           }
           if (resolvedPaths.length !== 1) {
-            return jsonError(
-              res,
-              501,
-              "existing-session file uploads currently support one file at a time.",
-            );
+            return jsonError(res, 501, EXISTING_SESSION_LIMITS.hooks.uploadSingleFile);
           }
           const uid = inputRef || ref;
           if (!uid) {
-            return jsonError(res, 501, "existing-session file uploads require ref or inputRef.");
+            return jsonError(res, 501, EXISTING_SESSION_LIMITS.hooks.uploadRefRequired);
           }
           await uploadChromeMcpFile({
             profileName: profileCtx.profile.name,
@@ -128,11 +121,7 @@ export function registerBrowserAgentActHookRoutes(
       run: async ({ profileCtx, cdpUrl, tab }) => {
         if (getBrowserProfileCapabilities(profileCtx.profile).usesChromeMcp) {
           if (timeoutMs) {
-            return jsonError(
-              res,
-              501,
-              "existing-session dialog handling does not support timeoutMs.",
-            );
+            return jsonError(res, 501, EXISTING_SESSION_LIMITS.hooks.dialogTimeout);
           }
           await evaluateChromeMcpScript({
             profileName: profileCtx.profile.name,

extensions/browser/src/browser/routes/agent.act.normalize.ts

@@ -0,0 +1,321 @@
+import {
+  ACT_MAX_BATCH_ACTIONS,
+  ACT_MAX_CLICK_DELAY_MS,
+  ACT_MAX_WAIT_TIME_MS,
+  normalizeActBoundedNonNegativeMs,
+} from "../act-policy.js";
+import type { BrowserActRequest, BrowserFormField } from "../client-actions-core.js";
+import { normalizeBrowserFormField } from "../form-fields.js";
+import {
+  type ActKind,
+  isActKind,
+  parseClickButton,
+  parseClickModifiers,
+} from "./agent.act.shared.js";
+import { toBoolean, toNumber, toStringArray, toStringOrEmpty } from "./utils.js";
+
+function normalizeActKind(raw: unknown): ActKind {
+  const kind = toStringOrEmpty(raw);
+  if (!isActKind(kind)) {
+    throw new Error("kind is required");
+  }
+  return kind;
+}
+
+export function countBatchActions(actions: BrowserActRequest[]): number {
+  let count = 0;
+  for (const action of actions) {
+    count += 1;
+    if (action.kind === "batch") {
+      count += countBatchActions(action.actions);
+    }
+  }
+  return count;
+}
+
+export function validateBatchTargetIds(
+  actions: BrowserActRequest[],
+  targetId: string,
+): string | null {
+  for (const action of actions) {
+    if (action.targetId && action.targetId !== targetId) {
+      return "batched action targetId must match request targetId";
+    }
+    if (action.kind === "batch") {
+      const nestedError = validateBatchTargetIds(action.actions, targetId);
+      if (nestedError) {
+        return nestedError;
+      }
+    }
+  }
+  return null;
+}
+
+function normalizeFields(rawFields: unknown): BrowserFormField[] {
+  const entries = Array.isArray(rawFields) ? rawFields : [];
+  return entries
+    .map((field) => {
+      if (!field || typeof field !== "object") {
+        return null;
+      }
+      return normalizeBrowserFormField(field as Record<string, unknown>);
+    })
+    .filter((field): field is BrowserFormField => field !== null);
+}
+
+function normalizeBatchAction(value: unknown): BrowserActRequest {
+  if (!value || typeof value !== "object" || Array.isArray(value)) {
+    throw new Error("batch actions must be objects");
+  }
+  return normalizeActRequest(value as Record<string, unknown>, { source: "batch" });
+}
+
+export function normalizeActRequest(
+  body: Record<string, unknown>,
+  options?: { source?: "request" | "batch" },
+): BrowserActRequest {
+  const source = options?.source ?? "request";
+  const kind = normalizeActKind(body.kind);
+
+  switch (kind) {
+    case "click": {
+      const ref = toStringOrEmpty(body.ref) || undefined;
+      const selector = toStringOrEmpty(body.selector) || undefined;
+      if (!ref && !selector) {
+        throw new Error("click requires ref or selector");
+      }
+      const buttonRaw = toStringOrEmpty(body.button);
+      const button = buttonRaw ? parseClickButton(buttonRaw) : undefined;
+      if (buttonRaw && !button) {
+        throw new Error("click button must be left|right|middle");
+      }
+      const modifiersRaw = toStringArray(body.modifiers) ?? [];
+      const parsedModifiers = parseClickModifiers(modifiersRaw);
+      if (parsedModifiers.error) {
+        throw new Error(parsedModifiers.error);
+      }
+      const doubleClick = toBoolean(body.doubleClick);
+      const delayMs = normalizeActBoundedNonNegativeMs(
+        toNumber(body.delayMs),
+        "click delayMs",
+        ACT_MAX_CLICK_DELAY_MS,
+      );
+      const timeoutMs = toNumber(body.timeoutMs);
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      return {
+        kind,
+        ...(ref ? { ref } : {}),
+        ...(selector ? { selector } : {}),
+        ...(targetId ? { targetId } : {}),
+        ...(doubleClick !== undefined ? { doubleClick } : {}),
+        ...(button ? { button } : {}),
+        ...(parsedModifiers.modifiers ? { modifiers: parsedModifiers.modifiers } : {}),
+        ...(delayMs !== undefined ? { delayMs } : {}),
+        ...(timeoutMs !== undefined ? { timeoutMs } : {}),
+      };
+    }
+    case "type": {
+      const ref = toStringOrEmpty(body.ref) || undefined;
+      const selector = toStringOrEmpty(body.selector) || undefined;
+      const text = body.text;
+      if (!ref && !selector) {
+        throw new Error("type requires ref or selector");
+      }
+      if (typeof text !== "string") {
+        throw new Error("type requires text");
+      }
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      const submit = toBoolean(body.submit);
+      const slowly = toBoolean(body.slowly);
+      const timeoutMs = toNumber(body.timeoutMs);
+      return {
+        kind,
+        ...(ref ? { ref } : {}),
+        ...(selector ? { selector } : {}),
+        text,
+        ...(targetId ? { targetId } : {}),
+        ...(submit !== undefined ? { submit } : {}),
+        ...(slowly !== undefined ? { slowly } : {}),
+        ...(timeoutMs !== undefined ? { timeoutMs } : {}),
+      };
+    }
+    case "press": {
+      const key = toStringOrEmpty(body.key);
+      if (!key) {
+        throw new Error("press requires key");
+      }
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      const delayMs = toNumber(body.delayMs);
+      return {
+        kind,
+        key,
+        ...(targetId ? { targetId } : {}),
+        ...(delayMs !== undefined ? { delayMs } : {}),
+      };
+    }
+    case "hover":
+    case "scrollIntoView": {
+      const ref = toStringOrEmpty(body.ref) || undefined;
+      const selector = toStringOrEmpty(body.selector) || undefined;
+      if (!ref && !selector) {
+        throw new Error(`${kind} requires ref or selector`);
+      }
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      const timeoutMs = toNumber(body.timeoutMs);
+      return {
+        kind,
+        ...(ref ? { ref } : {}),
+        ...(selector ? { selector } : {}),
+        ...(targetId ? { targetId } : {}),
+        ...(timeoutMs !== undefined ? { timeoutMs } : {}),
+      };
+    }
+    case "drag": {
+      const startRef = toStringOrEmpty(body.startRef) || undefined;
+      const startSelector = toStringOrEmpty(body.startSelector) || undefined;
+      const endRef = toStringOrEmpty(body.endRef) || undefined;
+      const endSelector = toStringOrEmpty(body.endSelector) || undefined;
+      if (!startRef && !startSelector) {
+        throw new Error("drag requires startRef or startSelector");
+      }
+      if (!endRef && !endSelector) {
+        throw new Error("drag requires endRef or endSelector");
+      }
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      const timeoutMs = toNumber(body.timeoutMs);
+      return {
+        kind,
+        ...(startRef ? { startRef } : {}),
+        ...(startSelector ? { startSelector } : {}),
+        ...(endRef ? { endRef } : {}),
+        ...(endSelector ? { endSelector } : {}),
+        ...(targetId ? { targetId } : {}),
+        ...(timeoutMs !== undefined ? { timeoutMs } : {}),
+      };
+    }
+    case "select": {
+      const ref = toStringOrEmpty(body.ref) || undefined;
+      const selector = toStringOrEmpty(body.selector) || undefined;
+      const values = toStringArray(body.values);
+      if ((!ref && !selector) || !values?.length) {
+        throw new Error("select requires ref/selector and values");
+      }
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      const timeoutMs = toNumber(body.timeoutMs);
+      return {
+        kind,
+        ...(ref ? { ref } : {}),
+        ...(selector ? { selector } : {}),
+        values,
+        ...(targetId ? { targetId } : {}),
+        ...(timeoutMs !== undefined ? { timeoutMs } : {}),
+      };
+    }
+    case "fill": {
+      const fields = normalizeFields(body.fields);
+      if (!fields.length) {
+        throw new Error("fill requires fields");
+      }
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      const timeoutMs = toNumber(body.timeoutMs);
+      return {
+        kind,
+        fields,
+        ...(targetId ? { targetId } : {}),
+        ...(timeoutMs !== undefined ? { timeoutMs } : {}),
+      };
+    }
+    case "resize": {
+      const width = toNumber(body.width);
+      const height = toNumber(body.height);
+      if (width === undefined || height === undefined || width <= 0 || height <= 0) {
+        throw new Error("resize requires positive width and height");
+      }
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      return {
+        kind,
+        width,
+        height,
+        ...(targetId ? { targetId } : {}),
+      };
+    }
+    case "wait": {
+      const loadStateRaw = toStringOrEmpty(body.loadState);
+      const loadState =
+        loadStateRaw === "load" ||
+        loadStateRaw === "domcontentloaded" ||
+        loadStateRaw === "networkidle"
+          ? loadStateRaw
+          : undefined;
+      const timeMs = normalizeActBoundedNonNegativeMs(
+        toNumber(body.timeMs),
+        "wait timeMs",
+        ACT_MAX_WAIT_TIME_MS,
+      );
+      const text = toStringOrEmpty(body.text) || undefined;
+      const textGone = toStringOrEmpty(body.textGone) || undefined;
+      const selector = toStringOrEmpty(body.selector) || undefined;
+      const url = toStringOrEmpty(body.url) || undefined;
+      const fn = toStringOrEmpty(body.fn) || undefined;
+      if (timeMs === undefined && !text && !textGone && !selector && !url && !loadState && !fn) {
+        throw new Error(
+          "wait requires at least one of: timeMs, text, textGone, selector, url, loadState, fn",
+        );
+      }
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      const timeoutMs = toNumber(body.timeoutMs);
+      return {
+        kind,
+        ...(timeMs !== undefined ? { timeMs } : {}),
+        ...(text ? { text } : {}),
+        ...(textGone ? { textGone } : {}),
+        ...(selector ? { selector } : {}),
+        ...(url ? { url } : {}),
+        ...(loadState ? { loadState } : {}),
+        ...(fn ? { fn } : {}),
+        ...(targetId ? { targetId } : {}),
+        ...(timeoutMs !== undefined ? { timeoutMs } : {}),
+      };
+    }
+    case "evaluate": {
+      const fn = toStringOrEmpty(body.fn);
+      if (!fn) {
+        throw new Error("evaluate requires fn");
+      }
+      const ref = toStringOrEmpty(body.ref) || undefined;
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      const timeoutMs = toNumber(body.timeoutMs);
+      return {
+        kind,
+        fn,
+        ...(ref ? { ref } : {}),
+        ...(targetId ? { targetId } : {}),
+        ...(timeoutMs !== undefined ? { timeoutMs } : {}),
+      };
+    }
+    case "close": {
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      return {
+        kind,
+        ...(targetId ? { targetId } : {}),
+      };
+    }
+    case "batch": {
+      const actions = Array.isArray(body.actions) ? body.actions.map(normalizeBatchAction) : [];
+      if (!actions.length) {
+        throw new Error(source === "batch" ? "batch requires actions" : "actions are required");
+      }
+      if (countBatchActions(actions) > ACT_MAX_BATCH_ACTIONS) {
+        throw new Error(`batch exceeds maximum of ${ACT_MAX_BATCH_ACTIONS} actions`);
+      }
+      const targetId = toStringOrEmpty(body.targetId) || undefined;
+      const stopOnError = toBoolean(body.stopOnError);
+      return {
+        kind,
+        actions,
+        ...(targetId ? { targetId } : {}),
+        ...(stopOnError !== undefined ? { stopOnError } : {}),
+      };
+    }
+  }
+}

extensions/browser/src/browser/routes/agent.snapshot.ts

@@ -37,6 +37,7 @@ import {
   shouldUsePlaywrightForAriaSnapshot,
   shouldUsePlaywrightForScreenshot,
 } from "./agent.snapshot.plan.js";
+import { EXISTING_SESSION_LIMITS } from "./existing-session-limits.js";
 import type { BrowserResponse, BrowserRouteRegistrar } from "./types.js";
 import { jsonError, toBoolean, toStringOrEmpty } from "./utils.js";
 
@@ -270,11 +271,7 @@ export function registerBrowserAgentSnapshotRoutes(
       return;
     }
     if (getBrowserProfileCapabilities(profileCtx.profile).usesChromeMcp) {
-      return jsonError(
-        res,
-        501,
-        "pdf is not supported for existing-session profiles yet; use screenshot/snapshot instead.",
-      );
+      return jsonError(res, 501, EXISTING_SESSION_LIMITS.snapshot.pdfUnsupported);
     }
     await withPlaywrightRouteContext({
       req,
@@ -319,11 +316,7 @@ export function registerBrowserAgentSnapshotRoutes(
       run: async ({ profileCtx, tab, cdpUrl }) => {
         if (getBrowserProfileCapabilities(profileCtx.profile).usesChromeMcp) {
           if (element) {
-            return jsonError(
-              res,
-              400,
-              "element screenshots are not supported for existing-session profiles; use ref from snapshot.",
-            );
+            return jsonError(res, 400, EXISTING_SESSION_LIMITS.snapshot.screenshotElement);
           }
           const buffer = await takeChromeMcpScreenshot({
             profileName: profileCtx.profile.name,
@@ -404,11 +397,7 @@ export function registerBrowserAgentSnapshotRoutes(
       }
       if (getBrowserProfileCapabilities(profileCtx.profile).usesChromeMcp) {
         if (plan.selectorValue || plan.frameSelectorValue) {
-          return jsonError(
-            res,
-            400,
-            "selector/frame snapshots are not supported for existing-session profiles; snapshot the whole page and use refs.",
-          );
+          return jsonError(res, 400, EXISTING_SESSION_LIMITS.snapshot.snapshotSelector);
         }
         const snapshot = await takeChromeMcpSnapshot({
           profileName: profileCtx.profile.name,

extensions/browser/src/browser/routes/existing-session-limits.ts

@@ -0,0 +1,45 @@
+export const EXISTING_SESSION_LIMITS = {
+  act: {
+    clickSelector: "existing-session click does not support selector targeting yet; use ref.",
+    clickButtonOrModifiers:
+      "existing-session click currently supports left-click only (no button overrides/modifiers).",
+    typeSelector: "existing-session type does not support selector targeting yet; use ref.",
+    typeSlowly: "existing-session type does not support slowly=true; use fill/press instead.",
+    pressDelay: "existing-session press does not support delayMs.",
+    hoverSelector: "existing-session hover does not support selector targeting yet; use ref.",
+    hoverTimeout: "existing-session hover does not support timeoutMs overrides.",
+    scrollSelector:
+      "existing-session scrollIntoView does not support selector targeting yet; use ref.",
+    scrollTimeout: "existing-session scrollIntoView does not support timeoutMs overrides.",
+    dragSelector:
+      "existing-session drag does not support selector targeting yet; use startRef/endRef.",
+    dragTimeout: "existing-session drag does not support timeoutMs overrides.",
+    selectSelector: "existing-session select does not support selector targeting yet; use ref.",
+    selectSingleValue: "existing-session select currently supports a single value only.",
+    selectTimeout: "existing-session select does not support timeoutMs overrides.",
+    fillTimeout: "existing-session fill does not support timeoutMs overrides.",
+    waitNetworkIdle: "existing-session wait does not support loadState=networkidle yet.",
+    evaluateTimeout: "existing-session evaluate does not support timeoutMs overrides.",
+    batch: "existing-session batch is not supported yet; send actions individually.",
+  },
+  hooks: {
+    uploadElement:
+      "existing-session file uploads do not support element selectors; use ref/inputRef.",
+    uploadSingleFile: "existing-session file uploads currently support one file at a time.",
+    uploadRefRequired: "existing-session file uploads require ref or inputRef.",
+    dialogTimeout: "existing-session dialog handling does not support timeoutMs.",
+  },
+  download: {
+    waitUnsupported: "download waiting is not supported for existing-session profiles yet.",
+    downloadUnsupported: "downloads are not supported for existing-session profiles yet.",
+  },
+  snapshot: {
+    pdfUnsupported:
+      "pdf is not supported for existing-session profiles yet; use screenshot/snapshot instead.",
+    screenshotElement:
+      "element screenshots are not supported for existing-session profiles; use ref from snapshot.",
+    snapshotSelector:
+      "selector/frame snapshots are not supported for existing-session profiles; snapshot the whole page and use refs.",
+  },
+  responseBody: "response body is not supported for existing-session profiles yet.",
+} as const;

extensions/browser/src/browser/server.agent-contract-act-error-codes.test.ts

@@ -0,0 +1,176 @@
+import { describe, expect, it } from "vitest";
+import {
+  installAgentContractHooks,
+  startServerAndBase,
+} from "./server.agent-contract.test-harness.js";
+import {
+  setBrowserControlServerEvaluateEnabled,
+  setBrowserControlServerProfiles,
+} from "./server.control-server.test-harness.js";
+import { getBrowserTestFetch } from "./test-fetch.js";
+
+type ActErrorResponse = {
+  error?: string;
+  code?: string;
+};
+
+type ActErrorHttpResponse = {
+  status: number;
+  body: ActErrorResponse;
+};
+
+async function postActAndReadError(base: string, body?: unknown): Promise<ActErrorHttpResponse> {
+  const realFetch = getBrowserTestFetch();
+  const response = await realFetch(`${base}/act`, {
+    method: "POST",
+    headers: { "Content-Type": "application/json" },
+    body: body === undefined ? undefined : JSON.stringify(body),
+  });
+  return {
+    status: response.status,
+    body: (await response.json()) as ActErrorResponse,
+  };
+}
+
+describe("browser control server", () => {
+  installAgentContractHooks();
+
+  const slowTimeoutMs = process.platform === "win32" ? 40_000 : 20_000;
+
+  it(
+    "returns ACT_KIND_REQUIRED when kind is missing",
+    async () => {
+      const base = await startServerAndBase();
+      const response = await postActAndReadError(base, {});
+
+      expect(response.status).toBe(400);
+      expect(response.body.code).toBe("ACT_KIND_REQUIRED");
+      expect(response.body.error).toContain("kind is required");
+    },
+    slowTimeoutMs,
+  );
+
+  it(
+    "returns ACT_INVALID_REQUEST for malformed action payloads",
+    async () => {
+      const base = await startServerAndBase();
+      const response = await postActAndReadError(base, {
+        kind: "click",
+        ref: {},
+      });
+
+      expect(response.status).toBe(400);
+      expect(response.body.code).toBe("ACT_INVALID_REQUEST");
+      expect(response.body.error).toContain("click requires ref or selector");
+    },
+    slowTimeoutMs,
+  );
+
+  it(
+    "returns ACT_EXISTING_SESSION_UNSUPPORTED for unsupported existing-session actions",
+    async () => {
+      setBrowserControlServerProfiles({
+        openclaw: {
+          color: "#FF4500",
+          driver: "existing-session",
+        },
+      });
+
+      const base = await startServerAndBase();
+      const response = await postActAndReadError(base, {
+        kind: "batch",
+        actions: [{ kind: "press", key: "Enter" }],
+      });
+
+      expect(response.status).toBe(501);
+      expect(response.body.code).toBe("ACT_EXISTING_SESSION_UNSUPPORTED");
+      expect(response.body.error).toContain("batch");
+    },
+    slowTimeoutMs,
+  );
+
+  it(
+    "returns ACT_TARGET_ID_MISMATCH for batched action targetId overrides",
+    async () => {
+      const base = await startServerAndBase();
+      const response = await postActAndReadError(base, {
+        kind: "batch",
+        actions: [{ kind: "click", ref: "5", targetId: "other-tab" }],
+      });
+
+      expect(response.status).toBe(403);
+      expect(response.body.code).toBe("ACT_TARGET_ID_MISMATCH");
+      expect(response.body.error).toContain("batched action targetId must match request targetId");
+    },
+    slowTimeoutMs,
+  );
+
+  it(
+    "returns ACT_TARGET_ID_MISMATCH for top-level action targetId overrides",
+    async () => {
+      const base = await startServerAndBase();
+      const response = await postActAndReadError(base, {
+        kind: "click",
+        ref: "5",
+        // Intentionally non-string: route-level target selection ignores this,
+        // while action normalization stringifies it.
+        targetId: 12345,
+      });
+
+      expect(response.status).toBe(403);
+      expect(response.body.code).toBe("ACT_TARGET_ID_MISMATCH");
+      expect(response.body.error).toContain("action targetId must match request targetId");
+    },
+    slowTimeoutMs,
+  );
+
+  it(
+    "returns ACT_SELECTOR_UNSUPPORTED for selector on unsupported action kinds",
+    async () => {
+      const base = await startServerAndBase();
+      const response = await postActAndReadError(base, {
+        kind: "evaluate",
+        fn: "() => 1",
+        selector: "#submit",
+      });
+
+      expect(response.status).toBe(400);
+      expect(response.body.code).toBe("ACT_SELECTOR_UNSUPPORTED");
+      expect(response.body.error).toContain("'selector' is not supported");
+    },
+    slowTimeoutMs,
+  );
+
+  it(
+    "returns ACT_INVALID_REQUEST for malformed unsupported selector actions before selector gating",
+    async () => {
+      const base = await startServerAndBase();
+      const response = await postActAndReadError(base, {
+        kind: "press",
+        selector: "#submit",
+      });
+
+      expect(response.status).toBe(400);
+      expect(response.body.code).toBe("ACT_INVALID_REQUEST");
+      expect(response.body.error).toContain("press requires key");
+    },
+    slowTimeoutMs,
+  );
+
+  it(
+    "returns ACT_EVALUATE_DISABLED when evaluate is blocked by config",
+    async () => {
+      setBrowserControlServerEvaluateEnabled(false);
+      const base = await startServerAndBase();
+      const response = await postActAndReadError(base, {
+        kind: "evaluate",
+        fn: "() => 1",
+      });
+
+      expect(response.status).toBe(403);
+      expect(response.body.code).toBe("ACT_EVALUATE_DISABLED");
+      expect(response.body.error).toContain("browser.evaluateEnabled=false");
+    },
+    slowTimeoutMs,
+  );
+});

extensions/browser/src/browser/server.agent-contract-form-layout-act-commands.test.ts

@@ -107,18 +107,36 @@ describe("browser control server", () => {
         }),
       );
 
+      const resizeZero = await postJson<{ error?: string; code?: string }>(`${base}/act`, {
+        kind: "resize",
+        width: 0,
+        height: 600,
+      });
+      expect(resizeZero.code).toBe("ACT_INVALID_REQUEST");
+      expect(resizeZero.error).toContain("resize requires positive width and height");
+      expect(pwMocks.resizeViewportViaPlaywright).toHaveBeenCalledTimes(1);
+
+      const resizeNegative = await postJson<{ error?: string; code?: string }>(`${base}/act`, {
+        kind: "resize",
+        width: -800,
+        height: 600,
+      });
+      expect(resizeNegative.code).toBe("ACT_INVALID_REQUEST");
+      expect(resizeNegative.error).toContain("resize requires positive width and height");
+      expect(pwMocks.resizeViewportViaPlaywright).toHaveBeenCalledTimes(1);
+
       const wait = await postJson<{ ok: boolean }>(`${base}/act`, {
         kind: "wait",
         timeMs: 5,
       });
       expect(wait.ok).toBe(true);
-      expect(pwMocks.waitForViaPlaywright).toHaveBeenCalledWith({
-        cdpUrl: state.cdpBaseUrl,
-        targetId: "abcd1234",
-        timeMs: 5,
-        text: undefined,
-        textGone: undefined,
-      });
+      expect(pwMocks.waitForViaPlaywright).toHaveBeenCalledWith(
+        expect.objectContaining({
+          cdpUrl: state.cdpBaseUrl,
+          targetId: "abcd1234",
+          timeMs: 5,
+        }),
+      );
 
       const evalRes = await postJson<{ ok: boolean; result?: string }>(`${base}/act`, {
         kind: "evaluate",
@@ -220,12 +238,13 @@ describe("browser control server", () => {
     async () => {
       const base = await startServerAndBase();
 
-      const batchRes = await postJson<{ error?: string }>(`${base}/act`, {
+      const batchRes = await postJson<{ error?: string; code?: string }>(`${base}/act`, {
         kind: "batch",
         actions: [{ kind: "click", ref: {} }],
       });
 
       expect(batchRes.error).toContain("click requires ref or selector");
+      expect(batchRes.code).toBe("ACT_INVALID_REQUEST");
       expect(pwMocks.batchViaPlaywright).not.toHaveBeenCalled();
     },
     slowTimeoutMs,
@@ -236,12 +255,13 @@ describe("browser control server", () => {
     async () => {
       const base = await startServerAndBase();
 
-      const batchRes = await postJson<{ error?: string }>(`${base}/act`, {
+      const batchRes = await postJson<{ error?: string; code?: string }>(`${base}/act`, {
         kind: "batch",
         actions: [{ kind: "click", ref: "5", targetId: "other-tab" }],
       });
 
       expect(batchRes.error).toContain("batched action targetId must match request targetId");
+      expect(batchRes.code).toBe("ACT_TARGET_ID_MISMATCH");
       expect(pwMocks.batchViaPlaywright).not.toHaveBeenCalled();
     },
     slowTimeoutMs,

extensions/browser/src/browser/server.agent-contract-snapshot-endpoints.test.ts

@@ -90,17 +90,21 @@ describe("browser control server", () => {
       modifiers: ["Shift"],
     });
     expect(click.ok).toBe(true);
-    expect(pwMocks.clickViaPlaywright).toHaveBeenNthCalledWith(1, {
-      cdpUrl: state.cdpBaseUrl,
-      targetId: "abcd1234",
-      ref: "1",
-      doubleClick: false,
-      button: "left",
-      modifiers: ["Shift"],
-      ssrfPolicy: {
-        dangerouslyAllowPrivateNetwork: true,
-      },
-    });
+    expect(pwMocks.clickViaPlaywright).toHaveBeenNthCalledWith(
+      1,
+      expect.objectContaining({
+        cdpUrl: state.cdpBaseUrl,
+        targetId: "abcd1234",
+        ref: "1",
+        button: "left",
+        modifiers: ["Shift"],
+        ssrfPolicy: {
+          dangerouslyAllowPrivateNetwork: true,
+        },
+      }),
+    );
+    const [clickArgs] = pwMocks.clickViaPlaywright.mock.calls[0] ?? [];
+    expect((clickArgs as { doubleClick?: boolean }).doubleClick).toBeUndefined();
 
     const clickSelector = await realFetch(`${base}/act`, {
       method: "POST",
@@ -109,15 +113,19 @@ describe("browser control server", () => {
     });
     expect(clickSelector.status).toBe(200);
     expect(((await clickSelector.json()) as { ok?: boolean }).ok).toBe(true);
-    expect(pwMocks.clickViaPlaywright).toHaveBeenNthCalledWith(2, {
-      cdpUrl: state.cdpBaseUrl,
-      targetId: "abcd1234",
-      selector: "button.save",
-      doubleClick: false,
-      ssrfPolicy: {
-        dangerouslyAllowPrivateNetwork: true,
-      },
-    });
+    expect(pwMocks.clickViaPlaywright).toHaveBeenNthCalledWith(
+      2,
+      expect.objectContaining({
+        cdpUrl: state.cdpBaseUrl,
+        targetId: "abcd1234",
+        selector: "button.save",
+        ssrfPolicy: {
+          dangerouslyAllowPrivateNetwork: true,
+        },
+      }),
+    );
+    const [clickSelectorArgs] = pwMocks.clickViaPlaywright.mock.calls[1] ?? [];
+    expect((clickSelectorArgs as { doubleClick?: boolean }).doubleClick).toBeUndefined();
 
     const type = await postJson<{ ok: boolean }>(`${base}/act`, {
       kind: "type",
@@ -125,53 +133,69 @@ describe("browser control server", () => {
       text: "",
     });
     expect(type.ok).toBe(true);
-    expect(pwMocks.typeViaPlaywright).toHaveBeenNthCalledWith(1, {
-      cdpUrl: state.cdpBaseUrl,
-      targetId: "abcd1234",
-      ref: "1",
-      text: "",
-      submit: false,
-      slowly: false,
-      ssrfPolicy: {
-        dangerouslyAllowPrivateNetwork: true,
-      },
-    });
+    expect(pwMocks.typeViaPlaywright).toHaveBeenNthCalledWith(
+      1,
+      expect.objectContaining({
+        cdpUrl: state.cdpBaseUrl,
+        targetId: "abcd1234",
+        ref: "1",
+        text: "",
+        ssrfPolicy: {
+          dangerouslyAllowPrivateNetwork: true,
+        },
+      }),
+    );
+    const [typeArgs] = pwMocks.typeViaPlaywright.mock.calls[0] ?? [];
+    expect((typeArgs as { submit?: boolean }).submit).toBeUndefined();
+    expect((typeArgs as { slowly?: boolean }).slowly).toBeUndefined();
 
     const press = await postJson<{ ok: boolean }>(`${base}/act`, {
       kind: "press",
       key: "Enter",
     });
     expect(press.ok).toBe(true);
-    expect(pwMocks.pressKeyViaPlaywright).toHaveBeenCalledWith({
-      cdpUrl: state.cdpBaseUrl,
-      targetId: "abcd1234",
-      key: "Enter",
-      ssrfPolicy: {
-        dangerouslyAllowPrivateNetwork: true,
-      },
-    });
+    expect(pwMocks.pressKeyViaPlaywright).toHaveBeenCalledWith(
+      expect.objectContaining({
+        cdpUrl: state.cdpBaseUrl,
+        targetId: "abcd1234",
+        key: "Enter",
+        ssrfPolicy: {
+          dangerouslyAllowPrivateNetwork: true,
+        },
+      }),
+    );
+    const [pressArgs] = pwMocks.pressKeyViaPlaywright.mock.calls[0] ?? [];
+    expect((pressArgs as { delayMs?: number }).delayMs).toBeUndefined();
 
     const hover = await postJson<{ ok: boolean }>(`${base}/act`, {
       kind: "hover",
       ref: "2",
     });
     expect(hover.ok).toBe(true);
-    expect(pwMocks.hoverViaPlaywright).toHaveBeenCalledWith({
-      cdpUrl: state.cdpBaseUrl,
-      targetId: "abcd1234",
-      ref: "2",
-    });
+    expect(pwMocks.hoverViaPlaywright).toHaveBeenCalledWith(
+      expect.objectContaining({
+        cdpUrl: state.cdpBaseUrl,
+        targetId: "abcd1234",
+        ref: "2",
+      }),
+    );
+    const [hoverArgs] = pwMocks.hoverViaPlaywright.mock.calls[0] ?? [];
+    expect((hoverArgs as { timeoutMs?: number }).timeoutMs).toBeUndefined();
 
     const scroll = await postJson<{ ok: boolean }>(`${base}/act`, {
       kind: "scrollIntoView",
       ref: "2",
     });
     expect(scroll.ok).toBe(true);
-    expect(pwMocks.scrollIntoViewViaPlaywright).toHaveBeenCalledWith({
-      cdpUrl: state.cdpBaseUrl,
-      targetId: "abcd1234",
-      ref: "2",
-    });
+    expect(pwMocks.scrollIntoViewViaPlaywright).toHaveBeenCalledWith(
+      expect.objectContaining({
+        cdpUrl: state.cdpBaseUrl,
+        targetId: "abcd1234",
+        ref: "2",
+      }),
+    );
+    const [scrollArgs] = pwMocks.scrollIntoViewViaPlaywright.mock.calls[0] ?? [];
+    expect((scrollArgs as { timeoutMs?: number }).timeoutMs).toBeUndefined();
 
     const drag = await postJson<{ ok: boolean }>(`${base}/act`, {
       kind: "drag",
@@ -179,11 +203,15 @@ describe("browser control server", () => {
       endRef: "4",
     });
     expect(drag.ok).toBe(true);
-    expect(pwMocks.dragViaPlaywright).toHaveBeenCalledWith({
-      cdpUrl: state.cdpBaseUrl,
-      targetId: "abcd1234",
-      startRef: "3",
-      endRef: "4",
-    });
+    expect(pwMocks.dragViaPlaywright).toHaveBeenCalledWith(
+      expect.objectContaining({
+        cdpUrl: state.cdpBaseUrl,
+        targetId: "abcd1234",
+        startRef: "3",
+        endRef: "4",
+      }),
+    );
+    const [dragArgs] = pwMocks.dragViaPlaywright.mock.calls[0] ?? [];
+    expect((dragArgs as { timeoutMs?: number }).timeoutMs).toBeUndefined();
   });
 });

extensions/browser/src/browser/server.auth-fail-closed.test.ts

@@ -2,12 +2,22 @@ import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
 import { startBrowserControlServerFromConfig, stopBrowserControlServer } from "../server.js";
 import { getFreePort } from "./test-port.js";
 
+type EnsureBrowserControlAuthResult = {
+  auth: {
+    token?: string;
+    password?: string;
+  };
+  generatedToken?: string;
+};
+
 const mocks = vi.hoisted(() => ({
   controlPort: 0,
-  ensureBrowserControlAuth: vi.fn(async () => {
+  gatewayAuthMode: undefined as "password" | undefined,
+  ensureBrowserControlAuth: vi.fn<() => Promise<EnsureBrowserControlAuthResult>>(async () => {
     throw new Error("read-only config");
   }),
   resolveBrowserControlAuth: vi.fn(() => ({})),
+  shouldAutoGenerateBrowserAuth: vi.fn(() => true),
   ensureExtensionRelayForProfiles: vi.fn(async () => {}),
 }));
 
@@ -18,9 +28,12 @@ vi.mock("../config/config.js", async () => {
   };
   return {
     ...actual,
-    loadConfig: () => ({
-      browser: browserConfig,
-    }),
+    loadConfig: () => {
+      return {
+        browser: browserConfig,
+        ...(mocks.gatewayAuthMode ? { gateway: { auth: { mode: mocks.gatewayAuthMode } } } : {}),
+      };
+    },
   };
 });
 
@@ -38,6 +51,7 @@ vi.mock("./config.js", async () => {
 vi.mock("./control-auth.js", () => ({
   ensureBrowserControlAuth: mocks.ensureBrowserControlAuth,
   resolveBrowserControlAuth: mocks.resolveBrowserControlAuth,
+  shouldAutoGenerateBrowserAuth: mocks.shouldAutoGenerateBrowserAuth,
 }));
 
 vi.mock("./routes/index.js", () => ({
@@ -60,8 +74,10 @@ vi.mock("./pw-ai-state.js", () => ({
 describe("browser control auth bootstrap failures", () => {
   beforeEach(async () => {
     mocks.controlPort = await getFreePort();
+    mocks.gatewayAuthMode = undefined;
     mocks.ensureBrowserControlAuth.mockClear();
     mocks.resolveBrowserControlAuth.mockClear();
+    mocks.shouldAutoGenerateBrowserAuth.mockClear();
     mocks.ensureExtensionRelayForProfiles.mockClear();
   });
 
@@ -77,4 +93,28 @@ describe("browser control auth bootstrap failures", () => {
     expect(mocks.resolveBrowserControlAuth).toHaveBeenCalledTimes(1);
     expect(mocks.ensureExtensionRelayForProfiles).not.toHaveBeenCalled();
   });
+
+  it("fails closed when auth bootstrap resolves empty auth in production-like mode", async () => {
+    mocks.ensureBrowserControlAuth.mockResolvedValueOnce({ auth: {} });
+    mocks.resolveBrowserControlAuth.mockReturnValueOnce({});
+    mocks.shouldAutoGenerateBrowserAuth.mockReturnValueOnce(true);
+
+    const started = await startBrowserControlServerFromConfig();
+
+    expect(started).toBeNull();
+    expect(mocks.ensureBrowserControlAuth).toHaveBeenCalledTimes(1);
+    expect(mocks.resolveBrowserControlAuth).toHaveBeenCalledTimes(1);
+    expect(mocks.ensureExtensionRelayForProfiles).not.toHaveBeenCalled();
+  });
+
+  it("keeps legacy password-mode startup when password is not configured", async () => {
+    mocks.gatewayAuthMode = "password";
+    mocks.ensureBrowserControlAuth.mockResolvedValueOnce({ auth: {} });
+    mocks.resolveBrowserControlAuth.mockReturnValueOnce({});
+    mocks.shouldAutoGenerateBrowserAuth.mockReturnValueOnce(true);
+
+    const started = await startBrowserControlServerFromConfig();
+
+    expect(started).not.toBeNull();
+  });
 });

extensions/browser/src/browser/server.control-server.test-harness.ts

@@ -95,50 +95,206 @@ export function getCdpMocks(): { createTargetViaCdp: MockFn; snapshotAria: MockF
   return cdpMocks as unknown as { createTargetViaCdp: MockFn; snapshotAria: MockFn };
 }
 
+type ExecuteActMockAction = { kind: string } & Record<string, unknown>;
+type ExecuteActMockOptions = {
+  cdpUrl: string;
+  action: ExecuteActMockAction;
+  targetId?: string;
+  ssrfPolicy?: unknown;
+  evaluateEnabled?: boolean;
+  signal?: AbortSignal;
+};
+
+type PassThroughActDispatch = {
+  mock: (opts?: unknown) => Promise<unknown>;
+  fields: readonly string[];
+  includeSsrf?: boolean;
+  includeSignal?: boolean;
+};
+
+function pickActionFields(
+  action: ExecuteActMockAction,
+  fields: readonly string[],
+): Record<string, unknown> {
+  const picked: Record<string, unknown> = {};
+  for (const field of fields) {
+    picked[field] = action[field];
+  }
+  return picked;
+}
+
+function buildActPayload(params: {
+  cdpUrl: string;
+  targetId?: string;
+  action: ExecuteActMockAction;
+  fields: readonly string[];
+  ssrfPolicy?: unknown;
+  signal?: AbortSignal;
+  includeSsrf?: boolean;
+  includeSignal?: boolean;
+}): Record<string, unknown> {
+  return {
+    cdpUrl: params.cdpUrl,
+    targetId: params.targetId,
+    ...pickActionFields(params.action, params.fields),
+    ...(params.includeSsrf ? { ssrfPolicy: params.ssrfPolicy } : {}),
+    ...(params.includeSignal ? { signal: params.signal } : {}),
+  };
+}
+
 const pwMocks = vi.hoisted(() => ({
   armDialogViaPlaywright: vi.fn(async () => {}),
   armFileUploadViaPlaywright: vi.fn(async () => {}),
-  batchViaPlaywright: vi.fn(async () => ({ results: [] })),
-  clickViaPlaywright: vi.fn(async () => {}),
-  closePageViaPlaywright: vi.fn(async () => {}),
+  batchViaPlaywright: vi.fn(async (_opts?: unknown) => ({ results: [] })),
+  clickViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
+  closePageViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
   closePlaywrightBrowserConnection: vi.fn(async () => {}),
   downloadViaPlaywright: vi.fn(async () => ({
     url: "https://example.com/report.pdf",
     suggestedFilename: "report.pdf",
     path: "/tmp/report.pdf",
   })),
-  dragViaPlaywright: vi.fn(async () => {}),
-  evaluateViaPlaywright: vi.fn(async () => "ok"),
-  fillFormViaPlaywright: vi.fn(async () => {}),
+  dragViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
+  evaluateViaPlaywright: vi.fn(async (_opts?: unknown) => "ok"),
+  fillFormViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
   getConsoleMessagesViaPlaywright: vi.fn(async () => []),
-  hoverViaPlaywright: vi.fn(async () => {}),
-  scrollIntoViewViaPlaywright: vi.fn(async () => {}),
+  hoverViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
+  scrollIntoViewViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
   navigateViaPlaywright: vi.fn(async () => ({ url: "https://example.com" })),
   pdfViaPlaywright: vi.fn(async () => ({ buffer: Buffer.from("pdf") })),
-  pressKeyViaPlaywright: vi.fn(async () => {}),
+  pressKeyViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
   responseBodyViaPlaywright: vi.fn(async () => ({
     url: "https://example.com/api/data",
     status: 200,
     headers: { "content-type": "application/json" },
     body: '{"ok":true}',
   })),
-  resizeViewportViaPlaywright: vi.fn(async () => {}),
-  selectOptionViaPlaywright: vi.fn(async () => {}),
+  resizeViewportViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
+  selectOptionViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
   setInputFilesViaPlaywright: vi.fn(async () => {}),
   snapshotAiViaPlaywright: vi.fn(async () => ({ snapshot: "ok" })),
   traceStopViaPlaywright: vi.fn(async () => {}),
   takeScreenshotViaPlaywright: vi.fn(async () => ({
     buffer: Buffer.from("png"),
   })),
-  typeViaPlaywright: vi.fn(async () => {}),
+  typeViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
   waitForDownloadViaPlaywright: vi.fn(async () => ({
     url: "https://example.com/report.pdf",
     suggestedFilename: "report.pdf",
     path: "/tmp/report.pdf",
   })),
-  waitForViaPlaywright: vi.fn(async () => {}),
+  waitForViaPlaywright: vi.fn(async (_opts?: unknown) => {}),
+  executeActViaPlaywright: vi.fn(async (_opts?: ExecuteActMockOptions) => ({})),
 }));
 
+const passThroughActDispatch: Record<string, PassThroughActDispatch> = {
+  click: {
+    mock: pwMocks.clickViaPlaywright,
+    fields: ["ref", "selector", "doubleClick", "button", "modifiers", "delayMs", "timeoutMs"],
+    includeSsrf: true,
+  },
+  type: {
+    mock: pwMocks.typeViaPlaywright,
+    fields: ["ref", "selector", "text", "submit", "slowly", "timeoutMs"],
+    includeSsrf: true,
+  },
+  press: {
+    mock: pwMocks.pressKeyViaPlaywright,
+    fields: ["key", "delayMs"],
+    includeSsrf: true,
+  },
+  hover: {
+    mock: pwMocks.hoverViaPlaywright,
+    fields: ["ref", "selector", "timeoutMs"],
+  },
+  scrollIntoView: {
+    mock: pwMocks.scrollIntoViewViaPlaywright,
+    fields: ["ref", "selector", "timeoutMs"],
+  },
+  drag: {
+    mock: pwMocks.dragViaPlaywright,
+    fields: ["startRef", "startSelector", "endRef", "endSelector", "timeoutMs"],
+  },
+  select: {
+    mock: pwMocks.selectOptionViaPlaywright,
+    fields: ["ref", "selector", "values", "timeoutMs"],
+  },
+  fill: {
+    mock: pwMocks.fillFormViaPlaywright,
+    fields: ["fields", "timeoutMs"],
+  },
+  resize: {
+    mock: pwMocks.resizeViewportViaPlaywright,
+    fields: ["width", "height"],
+  },
+  wait: {
+    mock: pwMocks.waitForViaPlaywright,
+    fields: ["timeMs", "text", "textGone", "selector", "url", "loadState", "fn", "timeoutMs"],
+    includeSignal: true,
+  },
+  close: {
+    mock: pwMocks.closePageViaPlaywright,
+    fields: [],
+  },
+};
+
+pwMocks.executeActViaPlaywright.mockImplementation(
+  async (opts: ExecuteActMockOptions | undefined) => {
+    if (!opts) {
+      return {};
+    }
+    const { cdpUrl, action, targetId, ssrfPolicy, evaluateEnabled, signal } = opts;
+    const spec = passThroughActDispatch[action.kind];
+    if (spec) {
+      await spec.mock(
+        buildActPayload({
+          cdpUrl,
+          targetId,
+          action,
+          fields: spec.fields,
+          ssrfPolicy,
+          signal,
+          includeSsrf: spec.includeSsrf,
+          includeSignal: spec.includeSignal,
+        }),
+      );
+      return {};
+    }
+
+    switch (action.kind) {
+      case "evaluate": {
+        if (!evaluateEnabled) {
+          throw new Error("act:evaluate is disabled by config (browser.evaluateEnabled=false)");
+        }
+        const result = await pwMocks.evaluateViaPlaywright({
+          cdpUrl,
+          targetId,
+          ssrfPolicy,
+          fn: action.fn,
+          ref: action.ref,
+          timeoutMs: action.timeoutMs,
+          signal,
+        });
+        return { result };
+      }
+      case "batch": {
+        const result = await pwMocks.batchViaPlaywright({
+          cdpUrl,
+          targetId,
+          actions: action.actions,
+          stopOnError: action.stopOnError,
+          evaluateEnabled,
+          ssrfPolicy,
+          signal,
+        });
+        return { results: result.results };
+      }
+      default:
+        return {};
+    }
+  },
+);
+
 export function getPwMocks(): Record<string, MockFn> {
   return pwMocks as unknown as Record<string, MockFn>;
 }

extensions/browser/src/node-host/invoke-browser.test.ts

@@ -26,56 +26,11 @@ const browserConfigMocks = vi.hoisted(() => ({
   })),
 }));
 
-vi.mock("../core-api.js", () => ({
-  createBrowserControlContext: controlServiceMocks.createBrowserControlContext,
-  createBrowserRouteDispatcher: dispatcherMocks.createBrowserRouteDispatcher,
-  detectMime: vi.fn(async () => "image/png"),
-  isPersistentBrowserProfileMutation: vi.fn((method: string, path: string) => {
-    if (method === "POST" && (path === "/profiles/create" || path === "/reset-profile")) {
-      return true;
-    }
-    return method === "DELETE" && /^\/profiles\/[^/]+$/.test(path);
-  }),
+vi.mock("openclaw/plugin-sdk/browser-config-runtime", () => ({
   loadConfig: configMocks.loadConfig,
-  normalizeBrowserRequestPath: vi.fn((path: string) => path),
-  redactCdpUrl: vi.fn((url: string) => {
-    try {
-      const parsed = new URL(url);
-      parsed.username = "";
-      parsed.password = "";
-      const normalized = parsed.toString().replace(/\/$/, "");
-      const token = parsed.searchParams.get("token");
-      if (!token || token.length <= 8) {
-        return normalized;
-      }
-      return normalized.replace(token, `${token.slice(0, 6)}…${token.slice(-4)}`);
-    } catch {
-      return url;
-    }
-  }),
-  resolveBrowserConfig: browserConfigMocks.resolveBrowserConfig,
-  resolveRequestedBrowserProfile: vi.fn(
-    ({
-      query,
-      body,
-      profile,
-    }: {
-      query?: Record<string, unknown>;
-      body?: unknown;
-      profile?: string;
-    }) => {
-      if (query && typeof query.profile === "string" && query.profile.trim()) {
-        return query.profile.trim();
-      }
-      const bodyProfile =
-        body && typeof body === "object" ? (body as { profile?: unknown }).profile : undefined;
-      if (typeof bodyProfile === "string" && bodyProfile.trim()) {
-        return bodyProfile.trim();
-      }
-      return typeof profile === "string" && profile.trim() ? profile.trim() : undefined;
-    },
-  ),
-  startBrowserControlServiceFromConfig: controlServiceMocks.startBrowserControlServiceFromConfig,
+}));
+
+vi.mock("openclaw/plugin-sdk/browser-node-runtime", () => ({
   withTimeout: vi.fn(
     async (
       run: (signal: AbortSignal | undefined) => Promise<unknown>,
@@ -110,6 +65,72 @@ vi.mock("../core-api.js", () => ({
   ),
 }));
 
+vi.mock("openclaw/plugin-sdk/browser-setup-tools", () => ({
+  detectMime: vi.fn(async () => "image/png"),
+}));
+
+vi.mock("../browser/cdp.helpers.js", () => ({
+  redactCdpUrl: vi.fn((url: string) => {
+    try {
+      const parsed = new URL(url);
+      parsed.username = "";
+      parsed.password = "";
+      const normalized = parsed.toString().replace(/\/$/, "");
+      const token = parsed.searchParams.get("token");
+      if (!token || token.length <= 8) {
+        return normalized;
+      }
+      return normalized.replace(token, `${token.slice(0, 6)}…${token.slice(-4)}`);
+    } catch {
+      return url;
+    }
+  }),
+}));
+
+vi.mock("../browser/config.js", () => ({
+  resolveBrowserConfig: browserConfigMocks.resolveBrowserConfig,
+}));
+
+vi.mock("../browser/request-policy.js", () => ({
+  isPersistentBrowserProfileMutation: vi.fn((method: string, path: string) => {
+    if (method === "POST" && (path === "/profiles/create" || path === "/reset-profile")) {
+      return true;
+    }
+    return method === "DELETE" && /^\/profiles\/[^/]+$/.test(path);
+  }),
+  normalizeBrowserRequestPath: vi.fn((path: string) => path),
+  resolveRequestedBrowserProfile: vi.fn(
+    ({
+      query,
+      body,
+      profile,
+    }: {
+      query?: Record<string, unknown>;
+      body?: unknown;
+      profile?: string;
+    }) => {
+      if (query && typeof query.profile === "string" && query.profile.trim()) {
+        return query.profile.trim();
+      }
+      const bodyProfile =
+        body && typeof body === "object" ? (body as { profile?: unknown }).profile : undefined;
+      if (typeof bodyProfile === "string" && bodyProfile.trim()) {
+        return bodyProfile.trim();
+      }
+      return typeof profile === "string" && profile.trim() ? profile.trim() : undefined;
+    },
+  ),
+}));
+
+vi.mock("../browser/routes/dispatcher.js", () => ({
+  createBrowserRouteDispatcher: dispatcherMocks.createBrowserRouteDispatcher,
+}));
+
+vi.mock("../control-service.js", () => ({
+  createBrowserControlContext: controlServiceMocks.createBrowserControlContext,
+  startBrowserControlServiceFromConfig: controlServiceMocks.startBrowserControlServiceFromConfig,
+}));
+
 let resetBrowserProxyCommandStateForTests: typeof import("./invoke-browser.js").resetBrowserProxyCommandStateForTests;
 let runBrowserProxyCommand: typeof import("./invoke-browser.js").runBrowserProxyCommand;
 

extensions/browser/src/node-host/invoke-browser.ts

@@ -1,17 +1,19 @@
 import fsPromises from "node:fs/promises";
+import { loadConfig } from "openclaw/plugin-sdk/browser-config-runtime";
+import { withTimeout } from "openclaw/plugin-sdk/browser-node-runtime";
+import { detectMime } from "openclaw/plugin-sdk/browser-setup-tools";
+import { redactCdpUrl } from "../browser/cdp.helpers.js";
+import { resolveBrowserConfig } from "../browser/config.js";
+import {
+  isPersistentBrowserProfileMutation,
+  normalizeBrowserRequestPath,
+  resolveRequestedBrowserProfile,
+} from "../browser/request-policy.js";
+import { createBrowserRouteDispatcher } from "../browser/routes/dispatcher.js";
 import {
   createBrowserControlContext,
-  createBrowserRouteDispatcher,
-  detectMime,
-  isPersistentBrowserProfileMutation,
-  loadConfig,
-  normalizeBrowserRequestPath,
-  redactCdpUrl,
-  resolveBrowserConfig,
-  resolveRequestedBrowserProfile,
   startBrowserControlServiceFromConfig,
-  withTimeout,
-} from "../core-api.js";
+} from "../control-service.js";
 
 type BrowserProxyParams = {
   method?: string;

extensions/browser/src/server.ts

@@ -1,7 +1,12 @@
 import type { Server } from "node:http";
 import express from "express";
+import { deleteBridgeAuthForPort, setBridgeAuthForPort } from "./browser/bridge-auth-registry.js";
 import { resolveBrowserConfig } from "./browser/config.js";
-import { ensureBrowserControlAuth, resolveBrowserControlAuth } from "./browser/control-auth.js";
+import {
+  ensureBrowserControlAuth,
+  resolveBrowserControlAuth,
+  shouldAutoGenerateBrowserAuth,
+} from "./browser/control-auth.js";
 import { registerBrowserRoutes } from "./browser/routes/index.js";
 import type { BrowserRouteRegistrar } from "./browser/routes/types.js";
 import { createBrowserRuntimeState, stopBrowserRuntime } from "./browser/runtime-lifecycle.js";
@@ -38,19 +43,36 @@ export async function startBrowserControlServerFromConfig(): Promise<BrowserServ
     const ensured = await ensureBrowserControlAuth({ cfg });
     browserAuth = ensured.auth;
     if (ensured.generatedToken) {
-      logServer.info("No browser auth configured; generated gateway.auth.token automatically.");
+      logServer.info(
+        "No browser auth configured; generated browser control auth credential automatically.",
+      );
     }
   } catch (err) {
     logServer.warn(`failed to auto-configure browser auth: ${String(err)}`);
     browserAuthBootstrapFailed = true;
   }
 
-  // Fail closed: if auth bootstrap failed and no explicit auth is available,
-  // do not start the browser control HTTP server.
-  if (browserAuthBootstrapFailed && !browserAuth.token && !browserAuth.password) {
-    logServer.error(
-      "browser control startup aborted: authentication bootstrap failed and no fallback auth is configured.",
-    );
+  const browserAuthRequired =
+    browserAuthBootstrapFailed || shouldAutoGenerateBrowserAuth(process.env);
+  const allowLegacyPasswordModeWithoutSecret =
+    !browserAuthBootstrapFailed &&
+    cfg.gateway?.auth?.mode === "password" &&
+    !browserAuth.token &&
+    !browserAuth.password;
+  if (
+    browserAuthRequired &&
+    !allowLegacyPasswordModeWithoutSecret &&
+    !browserAuth.token &&
+    !browserAuth.password
+  ) {
+    if (browserAuthBootstrapFailed) {
+      logServer.error(
+        "browser control startup aborted: authentication bootstrap failed " +
+          "and no fallback auth is configured.",
+      );
+    } else {
+      logServer.error("browser control startup aborted: no authentication configured.");
+    }
     return null;
   }
 
@@ -83,6 +105,7 @@ export async function startBrowserControlServerFromConfig(): Promise<BrowserServ
     resolved,
     onWarn: (message) => logServer.warn(message),
   });
+  setBridgeAuthForPort(port, browserAuth);
 
   const authMode = browserAuth.token ? "token" : browserAuth.password ? "password" : "off";
   logServer.info(`Browser control listening on http://127.0.0.1:${port}/ (auth=${authMode})`);
@@ -91,6 +114,9 @@ export async function startBrowserControlServerFromConfig(): Promise<BrowserServ
 
 export async function stopBrowserControlServer(): Promise<void> {
   const current = state;
+  if (current?.port) {
+    deleteBridgeAuthForPort(current.port);
+  }
   await stopBrowserRuntime({
     current,
     getState: () => state,

extensions/byteplus/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/byteplus-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw BytePlus provider plugin",
   "type": "module",

extensions/byteplus/provider-catalog.ts

@@ -5,7 +5,7 @@ import {
   BYTEPLUS_CODING_BASE_URL,
   BYTEPLUS_CODING_MODEL_CATALOG,
   BYTEPLUS_MODEL_CATALOG,
-} from "./api.js";
+} from "./models.js";
 
 export function buildBytePlusProvider(): ModelProviderConfig {
   return {

extensions/chutes/onboard.ts

@@ -8,7 +8,7 @@ import {
   CHUTES_DEFAULT_MODEL_REF,
   CHUTES_MODEL_CATALOG,
   buildChutesModelDefinition,
-} from "./api.js";
+} from "./models.js";
 
 export { CHUTES_DEFAULT_MODEL_REF };
 

extensions/chutes/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/chutes-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Chutes.ai provider plugin",
   "type": "module",

extensions/chutes/provider-catalog.ts

@@ -4,7 +4,7 @@ import {
   CHUTES_MODEL_CATALOG,
   buildChutesModelDefinition,
   discoverChutesModels,
-} from "./api.js";
+} from "./models.js";
 
 /**
  * Build the Chutes provider with dynamic model discovery.

extensions/cloudflare-ai-gateway/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/cloudflare-ai-gateway-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Cloudflare AI Gateway provider plugin",
   "type": "module",

extensions/comfy/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/comfy-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw ComfyUI provider plugin",
   "type": "module",

extensions/copilot-proxy/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/copilot-proxy",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Copilot Proxy provider plugin",
   "type": "module",

extensions/deepgram/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openclaw/deepgram-provider",
-  "version": "2026.4.9",
+  "version": "2026.4.10",
   "private": true,
   "description": "OpenClaw Deepgram media-understanding provider",
   "type": "module",