forge-openclaw-plugin 0.2.40 → 0.2.43

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "forge-openclaw-plugin",
-  "version": "0.2.40",
+  "version": "0.2.43",
   "description": "Curated OpenClaw adapter for the Forge collaboration API, UI entrypoint, and localhost auto-start runtime.",
   "type": "module",
   "license": "MIT",
@@ -44,17 +44,58 @@
     "openclaw": "2026.4.15"
   },
   "dependencies": {
+    "@dnd-kit/core": "^6.3.1",
+    "@dnd-kit/sortable": "^10.0.0",
+    "@dnd-kit/utilities": "^3.2.2",
     "@azure/msal-node": "^5.1.2",
     "@fastify/cors": "^10.0.1",
     "@fastify/multipart": "^9.4.0",
+    "@fontsource-variable/plus-jakarta-sans": "^5.2.8",
+    "@fontsource-variable/sora": "^5.2.8",
+    "@fontsource/space-grotesk": "^5.2.10",
+    "@hookform/resolvers": "^5.1.1",
+    "@mariozechner/pi-ai": "^0.66.1",
+    "@radix-ui/react-dialog": "^1.1.14",
+    "@reduxjs/toolkit": "^2.11.2",
     "@sinclair/typebox": "^0.34.48",
+    "@tanstack/react-query": "^5.80.10",
+    "@tanstack/react-table": "^8.21.3",
+    "@tanstack/react-virtual": "^3.13.12",
+    "@tauri-apps/api": "^2.8.0",
+    "@tiptap/react": "^2.15.0",
+    "@tiptap/starter-kit": "^2.15.0",
+    "@types/react-grid-layout": "^1.3.6",
+    "@xyflow/react": "^12.10.2",
     "adm-zip": "^0.5.17",
+    "bonjour-service": "^1.3.0",
+    "class-variance-authority": "^0.7.1",
+    "clsx": "^2.1.1",
+    "cron-parser": "^5.5.0",
     "fastify": "^5.8.5",
+    "framer-motion": "^12.16.0",
+    "graphology": "^0.26.0",
+    "graphology-layout": "^0.6.1",
+    "graphology-layout-forceatlas2": "^0.10.1",
+    "lucide-react": "^0.525.0",
     "node-ical": "^0.20.1",
+    "qrcode": "^1.5.4",
+    "react": "^19.1.0",
+    "react-arborist": "^3.4.3",
+    "react-dom": "^19.1.0",
+    "react-grid-layout": "^2.2.3",
+    "react-hook-form": "^7.57.0",
+    "react-is": "^19.2.5",
+    "react-redux": "^9.2.0",
+    "react-router-dom": "^7.13.1",
+    "recharts": "^3.1.0",
+    "sigma": "^3.0.2",
+    "tailwind-merge": "^3.3.1",
     "tsdav": "^2.1.8",
-    "zod": "^3.25.67"
+    "zod": "^3.25.67",
+    "zustand": "^5.0.5"
   },
   "overrides": {
+    "basic-ftp": "^5.3.0",
     "axios": "^1.15.0",
     "follow-redirects": "^1.16.0",
     "hono": "4.12.14"

package/skills/forge-openclaw/SKILL.md

@@ -141,6 +141,7 @@ Psyche interview rule:
 - Sound professionally warm and therapist-like: grounded, accurate, reflective, and intentional, not clinical, vague, or lecture-like.
 - After the first real answer, choose one follow-up lane at a time: situation, sequence, meaning, protection, cost, longing/value, or tentative name.
 - For Psyche updates, start with what feels newly true, newly visible, or newly inaccurate, then ask what should stay true before changing the formulation.
+- If a fresh episode is what made a Psyche update visible, anchor in that episode before renaming the durable belief, pattern, mode, or value.
 - If the user says they want help understanding a Psyche issue before saving it, ask one orienting question first instead of jumping straight into a full interpretation, diagnosis-like label, save suggestion, replacement belief, or suggested title.
 - In that first exploratory turn, keep the reflection to one or two short sentences, avoid numbered lists or schema dumps, and wait for the user's answer before offering a fuller formulation.
 - In that first exploratory turn, stay in plain prose, end with one question, and do not mention Forge fields or save formatting yet unless the user interrupts to save immediately.
@@ -386,6 +387,7 @@ Use the dedicated domain routes for specialized surfaces that are not simple bat
   `/api/v1/workbench/flows/:id/output` for published outputs, and the run/node routes
   under `/api/v1/workbench/flows/:id` for run history and node-level inspection.
 - If you are unsure which specialized route family applies, check `forge_get_agent_onboarding` and use its `entityRouteModel.specializedDomainSurfaces` section before guessing.
+- After a concrete Movement, Life Force, or Workbench correction, read the relevant specialized view back when the user is trying to understand the result rather than only store it.
 
 Use live work tools for `task_run`:
 `forge_log_work`, `forge_start_task_run`, `forge_heartbeat_task_run`, `forge_focus_task_run`, `forge_complete_task_run`, `forge_release_task_run`

package/skills/forge-openclaw/entity_conversation_playbooks.md

@@ -416,6 +416,15 @@ Use this when the user is updating an existing record rather than creating a new
 If the current title or shape may no longer fit, offer one revised formulation yourself
 before asking the user to rewrite it from scratch.
 
+## Update-first openers
+
+Use these when the user is correcting or revising something that already exists.
+
+- "What feels different enough now that this record needs to change?"
+- "What still feels right and should stay intact while we update it?"
+- "If this is really one correction rather than a full rethink, what is the exact part you want changed?"
+- "I can stay narrow here. What is the one thing that no longer fits?"
+
 ## Goal
 
 Aim: clarify the direction and why it matters, not just produce a title.
@@ -1016,6 +1025,11 @@ Direct action rules:
   traveled.
 - Use raw `PATCH /api/v1/movement/stays/:id` or `/api/v1/movement/trips/:id` only for
   editing an already-recorded stay or trip, not for filling a missing span.
+- If the user wants to undo or remove one manual overlay, delete the saved
+  user-defined box instead of patching a recorded stay or trip.
+- If the user wants to inspect one already-saved movement correction before editing
+  it, read the box detail first so the follow-up write stays grounded in the saved
+  object.
 - When the user has already given the real answer, for example "I stayed home during
   that missing block", do not ask a broad review question again. Confirm only the
   interval or place if that is still ambiguous, then act.
@@ -1045,14 +1059,20 @@ Lane-to-route map:
   `/api/v1/movement/places` or `/api/v1/movement/places/:id`
 - inspect one trip:
   `/api/v1/movement/trips/:id`
+- inspect one saved movement box before repairing it:
+  `/api/v1/movement/boxes/:id`
 - fill a missing span:
   `/api/v1/movement/user-boxes/preflight` then `/api/v1/movement/user-boxes`
 - repair or revise one saved overlay:
   `/api/v1/movement/user-boxes/:id`
+- delete one saved overlay:
+  `DELETE /api/v1/movement/user-boxes/:id`
 - repair one recorded automatic box:
   `/api/v1/movement/automatic-boxes/:id/invalidate`
 - edit an already-recorded stay, trip, or trip point:
   `/api/v1/movement/stays/:id`, `/api/v1/movement/trips/:id`, or `/api/v1/movement/trips/:id/points/:pointId`
+- delete an already-recorded stay, trip, or trip point:
+  `DELETE /api/v1/movement/stays/:id`, `DELETE /api/v1/movement/trips/:id`, or `DELETE /api/v1/movement/trips/:id/points/:pointId`
 
 Ready to act when:
 
@@ -1063,7 +1083,7 @@ Ready to act when:
 
 Preferred opening question:
 
-- "What are you trying to make clearer or correct about where you stayed and traveled?"
+- "What are you trying to understand, correct, or preserve about where you stayed and traveled?"
 
 ## Life Force
 
@@ -1109,6 +1129,8 @@ Direct action rules:
   template instead of editing the profile.
 - If the user is describing right-now depletion or recovery, post a fatigue signal and
   then read the overview back if they want to see the updated picture.
+- After a profile or weekday-template change, read the overview back when the user is
+  trying to understand the practical impact of the change, not just store it silently.
 
 Ready to act when:
 
@@ -1118,7 +1140,7 @@ Ready to act when:
 
 Preferred opening question:
 
-- "What feels most off, important, or worth tracking in your energy picture right now?"
+- "What feels most off, important, or worth understanding in your energy picture right now?"
 
 ## Workbench
 
@@ -1153,6 +1175,8 @@ Lane-to-route map:
   `/api/v1/workbench/flows/:id/run`
 - run from a payload-first contract:
   `/api/v1/workbench/run`
+- send one follow-up message into a saved flow chat:
+  `/api/v1/workbench/flows/:id/chat`
 - inspect published output or run history:
   `/api/v1/workbench/flows/:id/output` or `/api/v1/workbench/flows/:id/runs`
 - inspect one run or node result:
@@ -1173,6 +1197,8 @@ Direct action rules:
   `/api/v1/workbench/run`.
 - If the user wants one node's latest successful output, do not browse old runs first
   unless they explicitly want historical debugging.
+- If the user wants to understand what inputs a flow can accept before editing or
+  running it, read the box catalog or flow detail before asking for a payload.
 
 Ready to act when:
 
@@ -1182,7 +1208,7 @@ Ready to act when:
 
 Preferred opening question:
 
-- "What are you trying to inspect a flow, change it, run it, or publish from Workbench?"
+- "What are you trying to inspect, change, run, or publish through Workbench?"
 
 ## Preference Catalog
 

package/skills/forge-openclaw/psyche_entity_playbooks.md

@@ -350,6 +350,9 @@ If the entity is already clear:
 
 - reflect briefly
 - name the core meaning in the user's language
+- if the user already gave a serviceable belief sentence, mode name, value phrase, or
+  pattern title, stay inside that wording long enough to reflect the live stake before
+  you ask for the one missing structural detail
 - keep the user's own wording when it is already serviceable and only refine one
   phrase if needed
 - ask only for the one missing structural detail
@@ -376,6 +379,10 @@ If the entity is not yet clear:
   replacing it with a more polished label unless they ask for help wording it.
 - When the user says the current wording misses, say what seems newly true before you
   ask whether the old name still fits.
+- Before you revise a durable formulation, say what the old wording was trying to
+  hold and what the new episode or evidence changes.
+- If a recent charged episode is what made the update visible, anchor in that episode
+  before you rename the durable belief, pattern, mode, or value.
 - If another belief, value, pattern, mode, or note becomes visible, name it gently but
   do not switch containers unless the user wants to.
 
@@ -386,9 +393,11 @@ from scratch.
 
 1. Ask what feels newly true, newly visible, or newly inaccurate.
 2. Ask what still feels essentially right and should not be lost.
-3. Re-check the name only if the old wording no longer fits the lived experience.
-4. Ask for one concrete recent example if the update is abstract or sweeping.
-5. Then change only the parts the new understanding actually affects.
+3. If the update was triggered by one recent charged episode, anchor in that episode
+   before you re-check the durable formulation.
+4. Re-check the name only if the old wording no longer fits the lived experience.
+5. Ask for one concrete recent example if the update is abstract or sweeping.
+6. Then change only the parts the new understanding actually affects.
 
 If the update is mostly about wording, offer one revised sentence yourself and ask
 whether it lands more accurately before you reopen the whole exploration.
@@ -397,6 +406,12 @@ Good update opener:
 
 - "Before we change it, what feels newly true about this now, and what still feels basically right?"
 
+Other strong update openers:
+
+- "What about the old wording no longer lands, and what still feels true inside it?"
+- "If this update comes from one fresh moment, what happened there that changed how this record feels?"
+- "Do you want to revise the whole formulation, or only the part that now feels inaccurate?"
+
 ## Safety rule
 
 If the user shows imminent risk of self-harm, suicide, violence, inability to stay