node-red-contrib-knx-ultimate 6.3.26 → 6.3.28

package/CHANGELOG.md

@@ -6,6 +6,18 @@
 
 # CHANGELOG
 
+**Version 6.3.28** - August 2026<br/>
+
+- **KNX AI — patient provider-neutral model requests**: every LLM chat request now receives the same 30-minute minimum deadline, regardless of provider, model or model manager, while longer legacy configured values remain honored. The model transport carries that deadline through both streaming and non-streaming responses instead of inheriting a shorter HTTP-library header timeout; fast responses are returned immediately, model-response timeouts remain distinct from unreachable-server errors, and Telegram audio operations retain their separate two-minute safeguard.<br/>
+- **KNX AI — provider-neutral reasoning control and responsive chat**: added a localized **Reasoning effort** selector with provider/model default, `none`, `minimal`, `low`, `medium`, `high`, `xhigh` and `max` choices. The default sends no preference; explicit supported values are mapped by request protocol to Chat Completions `reasoning_effort`, Anthropic `output_config.effort` or Ollama `think`, without model-name allowlists, and a rejected preference is removed while preserving the rest of the request. OpenAI-compatible and Ollama chats now stream responses for every configured endpoint, keep reasoning traces separate from the structured user reply and retry without streaming when an endpoint rejects it. Abort and HTTP transport timeouts are reported as model-response timeouts instead of as false connection failures; genuine unreachable-server errors retain their provider-specific setup guidance. Context-error compaction remains in force. Editor help and wiki documentation were aligned in EN, IT, DE, FR, ES and zh-CN.<br/>
+- **KNX AI — optional model-sized local context**: added a localized **No KNX AI limit** choice to the local-model chat-context selector. The existing 4K, 8K and 16K budgets are unchanged and 16K remains the backward-compatible default; when the new choice is explicit, KNX AI uses the active/reported Ollama or Bionic LM Studio context window instead of imposing its own token cap, while the model's physical limit and the existing context-error fallback remain authoritative.<br/>
+- **KNX AI editor — quieter Setup Doctor placement**: moved Setup Doctor to the bottom of the **Chat and home** page, below the available-chat-context overview, and made it an accessible collapsed-by-default section so routine configuration stays compact while every diagnostic and refresh action remains available on demand.<br/>
+- **KNX AI — semantic persistent chat scheduling and fixed AI Education**: added model-selected `scheduleActions` for creating, listing and cancelling one-time or recurring reminders, monitors and future home commands from normal human-language chat, without keywords, trigger phrases or rigid intent classifiers. Each node persists authoritative schedule state in JSON and a generated readable Markdown view across restarts; due tasks reuse both the model's execution instruction and the exact original user request while retaining Web budgets, detected-camera limits, explicit TTS Ultimate wiring, ETS/DPT validation and configured KNX confirmation. Empty structured replies from smaller local models receive one general semantic recovery pass instead of surfacing the old “No response text” placeholder. Scheduled camera results are delivered back to sidebar chat, and cancelling a plan also invalidates any pending camera work or KNX confirmation belonging to it. `reset` clears all schedules for the node, while `clear_chat` cancels only the current session's schedules. AI Education remains a fixed, user-edited node property stored in the Node-RED flow: the model reads it as authoritative guidance but never writes it; learned chat memory stores facts and preferences requested in chat, while scheduler storage holds plans and reminders. The previously introduced legacy `knxai-education-<node-id>.md` file is no longer read or written; existing copies are left untouched and ignored. Localized editor strings, help and wiki pages were aligned in EN, IT, DE, FR, ES and zh-CN.<br/>
+
+**Version 6.3.27** - August 2026<br/>
+
+- KNX AI: enabled some things by default.
+
 **Version 6.3.26** - August 2026<br/>
 
 - **KNX AI — opt-in Web Intelligence with verified sources**: added a provider-independent general Web tool that the conversational model selects semantically from the current request, without topic-specific logic, keywords or intent classifiers. Web access is off by default; proactive Web checks require a separate opt-in, explicit user-authored AI Education, a destination learned from at least one normal chat request and a configurable 5, 10, 15, 30, 60 or 180-minute minimum interval. Setup Doctor reports Web/proactive readiness, missing Education or recipient and the live hourly budget. Interactive and proactive requests share a rolling hourly call budget, with at most three Web operations in total per user turn or proactive cycle. Web-backed answers carry runtime-validated numbered citations (`[S1]`, …) with sanitized URLs and available publication/retrieval times; external content remains untrusted data and cannot override assistant rules or permissions. Only bounded public HTTPS resources are accepted, with private/local/link-local/cloud-metadata targets, unsafe redirects, authenticated browsing and cookies blocked. Queries and the server's public IP are disclosed to external sites or the search service, while KNX/ETS data, camera content, chat identifiers, learned memory and credentials are never added automatically. Once verified Web results are available, the model can compose other enabled tools when authorized by the current chat or AI Education; existing tool availability, KNX permissions, ETS/DPT validation and configured write confirmation remain unchanged. Editor help and wiki documentation were aligned in EN, IT, DE, FR, ES and zh-CN.<br/>

package/examples/KNX AI - Summary Anomalies and Ask.json

@@ -144,7 +144,7 @@
     "llmSystemPrompt": "You are a KNX building automation assistant. Analyze KNX bus traffic and provide actionable insights.",
     "llmTemperature": "0.2",
     "llmMaxTokens": "600",
-    "llmTimeoutMs": "30000",
+    "llmTimeoutMs": "1800000",
     "llmMaxEventsInPrompt": "600",
     "llmIncludeRaw": false,
     "x": 560,

package/nodes/knxUltimateAI.html

@@ -187,7 +187,6 @@
         margin: 18px 0 0;
     }
 
-    #knx-ai-setup-doctor-panel>h4,
     #knx-ai-detected-adapters-panel>h4,
     #knx-ai-chat-context-panel>h4,
     #knx-ai-chat-learning-link-panel>h4 {
@@ -197,11 +196,53 @@
     }
 
     #knx-ai-setup-doctor-panel {
-        margin: 16px 0 18px;
+        margin: 24px 0 0;
         border-color: rgba(255, 152, 0, 0.55);
         background: linear-gradient(135deg, rgba(255, 152, 0, 0.10), var(--red-ui-secondary-background, #f7f7f7));
     }
 
+    .knx-ai-setup-doctor-toggle {
+        display: flex;
+        align-items: center;
+        justify-content: space-between;
+        gap: 12px;
+        margin: 0;
+        color: var(--red-ui-primary-text-color, #555);
+        font-size: 14px;
+        font-weight: 600;
+        cursor: pointer;
+        list-style: none;
+        user-select: none;
+    }
+
+    .knx-ai-setup-doctor-toggle::-webkit-details-marker {
+        display: none;
+    }
+
+    .knx-ai-setup-doctor-toggle>span>i {
+        width: 18px;
+        text-align: center;
+    }
+
+    .knx-ai-setup-doctor-toggle:focus-visible {
+        outline: 2px solid var(--red-ui-primary-color, #377e00);
+        outline-offset: 3px;
+        border-radius: 2px;
+    }
+
+    .knx-ai-setup-doctor-chevron {
+        flex: 0 0 auto;
+        transition: transform 0.16s ease;
+    }
+
+    #knx-ai-setup-doctor-panel[open] .knx-ai-setup-doctor-chevron {
+        transform: rotate(90deg);
+    }
+
+    .knx-ai-setup-doctor-body {
+        margin-top: 11px;
+    }
+
     #knx-ai-setup-doctor-panel.status-ready {
         border-color: rgba(46, 125, 50, 0.55);
         background: linear-gradient(135deg, rgba(46, 125, 50, 0.10), var(--red-ui-secondary-background, #f7f7f7));
@@ -437,14 +478,15 @@
             llmProvider: { value: "openai_compat" },
             llmBaseUrl: { value: "https://api.openai.com/v1/chat/completions" },
             llmModel: { value: "gpt-5.4" },
+            llmReasoningEffort: { value: "default" },
             llmContextLength: { value: 0 },
             llmPromptContextTokens: { value: 16384 },
             llmAllowKnxCommands: { value: false },
             llmRequireCommandConfirmation: { value: true },
-            webAccessEnabled: { value: false },
-            webProactiveEnabled: { value: false },
-            webProactiveIntervalMinutes: { value: 30 },
-            webMaxCallsPerHour: { value: 12 },
+            webAccessEnabled: { value: true },
+            webProactiveEnabled: { value: true },
+            webProactiveIntervalMinutes: { value: 5 },
+            webMaxCallsPerHour: { value: 40 },
             chatAdapterPreset: { value: "none" },
             chatInputCode: { value: "" },
             chatOutputCode: { value: "" },
@@ -813,12 +855,16 @@
                 const contextLimit = overview.contextLimit && typeof overview.contextLimit === "object" ? overview.contextLimit : {};
                 const currentProvider = String(contextLimit.provider || $("#node-input-llmProvider").val() || "").toLowerCase();
                 let contextLimitTokens = Math.max(0, Number(contextLimit.tokens) || 0);
-                if (!contextLimitTokens && (currentProvider === "lmstudio" || currentProvider === "ollama")) {
-                    contextLimitTokens = Math.min(
-                        Math.max(0, Number($("#node-input-llmContextLength").val()) || 16384),
-                        Math.max(0, Number($("#node-input-llmPromptContextTokens").val()) || 16384),
-                        16384
-                    );
+                const contextIsProviderManaged = String(contextLimit.mode || "") === "provider-managed";
+                if (!contextLimitTokens && !contextIsProviderManaged && (currentProvider === "lmstudio" || currentProvider === "ollama")) {
+                    const modelContextTokens = Math.max(0, Number($("#node-input-llmContextLength").val()) || 16384);
+                    const selectedContextValue = String($("#node-input-llmPromptContextTokens").val() || "16384");
+                    const selectedContextTokens = selectedContextValue === "0"
+                        ? 0
+                        : Math.min(16384, Math.max(4096, Number(selectedContextValue) || 16384));
+                    contextLimitTokens = selectedContextTokens === 0
+                        ? modelContextTokens
+                        : Math.min(modelContextTokens, selectedContextTokens);
                 }
                 const contextLimitValue = contextLimitTokens
                     ? formatCompactTokens(contextLimitTokens) + " " + t("knxUltimateAI.messages.chatContextTokens", "tokens")
@@ -852,7 +898,7 @@
                     knxTraffic: t("knxUltimateAI.messages.chatContextSourceKnxTraffic", "Live KNX summary, anomalies, topology and selected telegrams."),
                     adapterHistory: t("knxUltimateAI.messages.chatContextSourceAdapterHistory", "Persistent history of automatically detected adapter events."),
                     etsProject: t("knxUltimateAI.messages.chatContextSourceEtsProject", "ETS semantics and the full Node-RED project inventory."),
-                    memoryEducation: t("knxUltimateAI.messages.chatContextSourceMemoryEducation", "Session context, AI Education and bounded home memory."),
+                    memoryEducation: t("knxUltimateAI.messages.chatContextSourceMemoryEducation", "Session context, AI Education, bounded home memory and active plans."),
                     cameras: t("knxUltimateAI.messages.chatContextSourceCameras", "Detected cameras and their available capabilities.")
                 };
                 (Array.isArray(overview.sources) ? overview.sources : []).forEach(function (sourceId) {
@@ -867,7 +913,9 @@
 
                 const fileDescriptions = {
                     chatContext: t("knxUltimateAI.messages.chatContextFileChatContext", "Persistent conversation turns, instructions and camera notification rules."),
-                    homeMemory: t("knxUltimateAI.messages.chatContextFileHomeMemory", "AI Education and bounded learned home memory."),
+                    homeMemory: t("knxUltimateAI.messages.chatContextFileHomeMemory", "Bounded learned home memory only; AI Education remains in the node property."),
+                    schedules: t("knxUltimateAI.messages.chatContextFileSchedules", "Authoritative structured plans and reminders for this node."),
+                    schedulesReadable: t("knxUltimateAI.messages.chatContextFileSchedulesReadable", "Human-readable plans and reminders generated from the scheduler state."),
                     assistantConfig: t("knxUltimateAI.messages.chatContextFileAssistantConfig", "Persistent web Assistant configuration and semantic areas for this node.")
                 };
                 (Array.isArray(overview.files) ? overview.files : []).forEach(function (item) {
@@ -1017,8 +1065,11 @@
                     text += " · " + t("knxUltimateAI.messages.lmStudioContextCurrentlyLoaded", "currently loaded") + ": " + loadedTokens + " token";
                 }
                 if (provider === "lmstudio" || provider === "ollama") {
-                    const selectedBudget = Math.max(4096, Number($("#node-input-llmPromptContextTokens").val()) || 16384);
-                    text += " · " + t("knxUltimateAI.messages.localContextBudget", "KNX AI context budget") + ": " + (selectedBudget / 1024) + "K";
+                    const selectedContextValue = String($("#node-input-llmPromptContextTokens").val() || "16384");
+                    const selectedBudget = selectedContextValue === "0"
+                        ? t("knxUltimateAI.selectlists.promptContext.unlimited", "No KNX AI limit (model context)")
+                        : (Math.max(4096, Number(selectedContextValue) || 16384) / 1024) + "K";
+                    text += " · " + t("knxUltimateAI.messages.localContextBudget", "KNX AI context budget") + ": " + selectedBudget;
                 }
                 $status.text(text).css("color", color).show();
             };
@@ -1119,9 +1170,13 @@
                     : Number(detail.maxContextLength);
                 $("#node-input-llmContextLength").val(activeContextLength);
                 if (provider === "ollama") {
-                    detail.configuredContextLength = Math.min(Number(detail.maxContextLength), 16384);
+                    const selectedContextValue = String($("#node-input-llmPromptContextTokens").val() || "16384");
+                    const selectedContextTokens = selectedContextValue === "0"
+                        ? Number(detail.maxContextLength)
+                        : Math.min(16384, Math.max(4096, Number(selectedContextValue) || 16384));
+                    detail.configuredContextLength = Math.min(Number(detail.maxContextLength), selectedContextTokens);
                     $("#node-input-llmContextLength").val(detail.configuredContextLength);
-                    setLocalModelContextStatus(detail, "configured");
+                    setLocalModelContextStatus(detail);
                     return;
                 }
 
@@ -1142,7 +1197,7 @@
                     type: "POST",
                     contentType: "application/json",
                     data: JSON.stringify(payload)
-                    })
+                })
                     .done(function (data) {
                         if (requestVersion !== localContextRequestVersion) return;
                         const resolvedContextLength = Math.max(0, Number(data && data.contextLength) || 0);
@@ -1312,7 +1367,12 @@
             });
             $("#node-input-llmPromptContextTokens").on("change", function () {
                 const detail = localModelDetailsById.get(String($("#node-input-llmModel").val() || "").trim());
-                if (detail) setLocalModelContextStatus(detail, detail.loadedContextLength > 0 ? "configured" : "inactive");
+                if (!detail) return;
+                if ($("#node-input-llmProvider").val() === "ollama") {
+                    configureSelectedLocalModel();
+                    return;
+                }
+                setLocalModelContextStatus(detail, detail.loadedContextLength > 0 ? "configured" : "inactive");
             });
             $("#knx-ai-downloadOllamaModel").on("click", function (evt) {
                 evt.preventDefault();
@@ -1389,34 +1449,6 @@
         </div>
     </div>
 
-    <div id="knx-ai-setup-doctor-panel">
-        <h4><i class="fa fa-magic"></i> <span data-i18n="knxUltimateAI.sections.setupDoctor"></span></h4>
-        <div id="knx-ai-setup-doctor-status" data-i18n="knxUltimateAI.messages.setupDoctorLoading"></div>
-        <div id="knx-ai-setup-doctor-content" style="display:none;">
-            <div class="knx-ai-setup-doctor-hero">
-                <div class="knx-ai-setup-doctor-summary">
-                    <strong id="knx-ai-setup-doctor-state"></strong>
-                    <div id="knx-ai-setup-doctor-summary"></div>
-                </div>
-                <div id="knx-ai-setup-doctor-score" class="knx-ai-setup-doctor-score"></div>
-            </div>
-            <div id="knx-ai-setup-doctor-checks"></div>
-            <div class="knx-ai-setup-doctor-prompts">
-                <strong data-i18n="knxUltimateAI.messages.setupDoctorPromptsTitle"></strong>
-                <div class="knx-ai-setup-doctor-prompts-hint" data-i18n="knxUltimateAI.messages.setupDoctorPromptsHint"></div>
-                <div id="knx-ai-setup-doctor-prompt-list" class="knx-ai-setup-doctor-prompt-list"></div>
-            </div>
-            <div class="knx-ai-setup-doctor-footer">
-                <div class="knx-ai-setup-doctor-deploy-hint">
-                    <i class="fa fa-info-circle"></i> <span data-i18n="knxUltimateAI.messages.setupDoctorDeployHint"></span>
-                </div>
-                <button type="button" class="red-ui-button" id="knx-ai-setup-doctor-refresh">
-                    <i class="fa fa-refresh"></i> <span data-i18n="knxUltimateAI.buttons.refreshSetupDoctor"></span>
-                </button>
-            </div>
-        </div>
-    </div>
-
     <div id="knx-ai-tabs">
         <ul>
             <li><a href="#knx-ai-tabs-assistant"><i class="fa fa-magic"></i> <span data-i18n="knxUltimateAI.sections.groupAssistant"></span></a></li>
@@ -1470,6 +1502,38 @@
                     <div id="knx-ai-chat-context-pattern" class="knx-ai-chat-context-pattern"></div>
                 </div>
             </div>
+            <details id="knx-ai-setup-doctor-panel">
+                <summary class="knx-ai-setup-doctor-toggle">
+                    <span><i class="fa fa-magic"></i> <span data-i18n="knxUltimateAI.sections.setupDoctor"></span></span>
+                    <i class="fa fa-chevron-right knx-ai-setup-doctor-chevron" aria-hidden="true"></i>
+                </summary>
+                <div class="knx-ai-setup-doctor-body">
+                    <div id="knx-ai-setup-doctor-status" data-i18n="knxUltimateAI.messages.setupDoctorLoading"></div>
+                    <div id="knx-ai-setup-doctor-content" style="display:none;">
+                        <div class="knx-ai-setup-doctor-hero">
+                            <div class="knx-ai-setup-doctor-summary">
+                                <strong id="knx-ai-setup-doctor-state"></strong>
+                                <div id="knx-ai-setup-doctor-summary"></div>
+                            </div>
+                            <div id="knx-ai-setup-doctor-score" class="knx-ai-setup-doctor-score"></div>
+                        </div>
+                        <div id="knx-ai-setup-doctor-checks"></div>
+                        <div class="knx-ai-setup-doctor-prompts">
+                            <strong data-i18n="knxUltimateAI.messages.setupDoctorPromptsTitle"></strong>
+                            <div class="knx-ai-setup-doctor-prompts-hint" data-i18n="knxUltimateAI.messages.setupDoctorPromptsHint"></div>
+                            <div id="knx-ai-setup-doctor-prompt-list" class="knx-ai-setup-doctor-prompt-list"></div>
+                        </div>
+                        <div class="knx-ai-setup-doctor-footer">
+                            <div class="knx-ai-setup-doctor-deploy-hint">
+                                <i class="fa fa-info-circle"></i> <span data-i18n="knxUltimateAI.messages.setupDoctorDeployHint"></span>
+                            </div>
+                            <button type="button" class="red-ui-button" id="knx-ai-setup-doctor-refresh">
+                                <i class="fa fa-refresh"></i> <span data-i18n="knxUltimateAI.buttons.refreshSetupDoctor"></span>
+                            </button>
+                        </div>
+                    </div>
+                </div>
+            </details>
         </div>
 
     </div>
@@ -1504,6 +1568,20 @@
                         <i class="fa fa-refresh"></i> <span data-i18n="knxUltimateAI.buttons.refreshModels"></span>
                     </button>
                 </div>
+                <div class="form-row">
+                    <label style="width:290px" for="node-input-llmReasoningEffort"><i class="fa fa-tachometer"></i> <span data-i18n="knxUltimateAI.properties.llmReasoningEffort"></span></label>
+                    <select style="width:100%" id="node-input-llmReasoningEffort">
+                        <option value="default" data-i18n="knxUltimateAI.selectlists.reasoningEffort.default"></option>
+                        <option value="none" data-i18n="knxUltimateAI.selectlists.reasoningEffort.none"></option>
+                        <option value="minimal" data-i18n="knxUltimateAI.selectlists.reasoningEffort.minimal"></option>
+                        <option value="low" data-i18n="knxUltimateAI.selectlists.reasoningEffort.low"></option>
+                        <option value="medium" data-i18n="knxUltimateAI.selectlists.reasoningEffort.medium"></option>
+                        <option value="high" data-i18n="knxUltimateAI.selectlists.reasoningEffort.high"></option>
+                        <option value="xhigh" data-i18n="knxUltimateAI.selectlists.reasoningEffort.xhigh"></option>
+                        <option value="max" data-i18n="knxUltimateAI.selectlists.reasoningEffort.max"></option>
+                    </select>
+                    <div class="knx-ai-prompt-context-hint" data-i18n="knxUltimateAI.messages.reasoningEffortHint"></div>
+                </div>
                 <input type="hidden" id="node-input-llmContextLength">
                 <div id="knx-ai-local-context-status" style="display:none;"></div>
                 <div class="form-row" id="knx-ai-prompt-context-row" style="display:none;">
@@ -1512,6 +1590,7 @@
                         <option value="4096" data-i18n="knxUltimateAI.selectlists.promptContext.small"></option>
                         <option value="8192" data-i18n="knxUltimateAI.selectlists.promptContext.medium"></option>
                         <option value="16384" data-i18n="knxUltimateAI.selectlists.promptContext.full"></option>
+                        <option value="0" data-i18n="knxUltimateAI.selectlists.promptContext.unlimited"></option>
                     </select>
                     <div class="knx-ai-prompt-context-hint" data-i18n="knxUltimateAI.messages.promptContextHint"></div>
                 </div>
@@ -1554,13 +1633,13 @@
             <div class="form-row">
                 <input type="checkbox" id="node-input-webAccessEnabled" style="display:inline-block; width:auto; vertical-align:top;">
                 <label style="width:auto" for="node-input-webAccessEnabled">&nbsp;&nbsp;<span data-i18n="knxUltimateAI.properties.webAccessEnabled"></span></label>
-                <div class="knx-ai-prompt-context-hint" data-i18n="knxUltimateAI.messages.webAccessHint"></div>
+                <!-- <div class="knx-ai-prompt-context-hint" data-i18n="knxUltimateAI.messages.webAccessHint"></div> -->
             </div>
             <div id="knx-ai-web-access-settings">
                 <div class="form-row">
                     <label style="width:290px" for="node-input-webMaxCallsPerHour"><i class="fa fa-tachometer"></i> <span data-i18n="knxUltimateAI.properties.webMaxCallsPerHour"></span></label>
                     <input type="number" id="node-input-webMaxCallsPerHour" min="1" max="60" step="1" style="width:100%;">
-                    <div class="knx-ai-prompt-context-hint" data-i18n="knxUltimateAI.messages.webBudgetHint"></div>
+                    <!-- <div class="knx-ai-prompt-context-hint" data-i18n="knxUltimateAI.messages.webBudgetHint"></div> -->
                 </div>
                 <div class="form-row">
                     <input type="checkbox" id="node-input-webProactiveEnabled" style="display:inline-block; width:auto; vertical-align:top;">