forge-openclaw-plugin 0.3.0 → 0.3.1

package/dist/server/server/src/app.js

@@ -3114,6 +3114,7 @@ const AGENT_ONBOARDING_CONVERSATION_RULES = [
     "For direct update or review requests, the next question should usually narrow the saved object, timeframe, or route family instead of reopening the whole meaning-making arc.",
     "For updates, start with the smallest thing that now feels wrong, newly true, or newly visible rather than restarting the whole story.",
     "For review requests, ask what practical question the user wants the read to answer before you ask for more scope.",
+    "For review-first requests, use the correct read posture before asking write-shaped questions: shared batch search or read hints for normal entities, wiki/calendar dedicated reads for specialized CRUD, read-model routes for overviews, and Movement, Life Force, or Workbench dedicated reads for those domain surfaces. After the read, answer the practical question before asking for any save, correction, link, run, enrichment, or publish detail.",
     "After a review, overview, navigation, or specialized read returns data, first answer the user's practical question in plain language, then name one implication or uncertainty that matters for the next decision. Ask a follow-up only if it changes the next action: save, update, correct, link, schedule, run, publish, enrich, or open the UI.",
     "Treat userId, owner, and human/bot assignees as accountability and scope, not as opening form fields. Ask whose record or owner scope matters only when it changes visibility, review results, collaboration, automation behavior, or later filtering.",
     "For read and overview requests, ask for human or bot user scope only when the answer would meaningfully differ across owners; otherwise keep the next question focused on the user's practical question.",
@@ -5455,10 +5456,10 @@ function buildAgentOnboardingPayload(request) {
             maxQuestionsPerTurn: 1,
             psycheExplorationRule: "When a Psyche entity needs understanding first, begin with one exploratory question before any working formulation, replacement belief, suggested title, or save pitch. Keep the opening reflection to one or two short sentences, stay in plain prose instead of bullets or numbered lists, keep that first reply short, do not mention Forge search or save structure yet, avoid colons or list-shaped phrasing, prefer what/when/how over why until the experience is grounded, wait for the user's answer before offering a fuller formulation, ask permission before moving from charged exploration into naming or challenge when needed, make the next question help the user feel more able to name the experience rather than more examined, do not widen into adjacent entities until the current one has a working sentence the user recognizes, and once the lived experience is coherent stop deepening and help the user name it cleanly. After one concrete example is clear and a hypothesis lands or is corrected, translate it into a saveable record shape such as a belief sentence, functional loop, behavior, mode, trigger report, value, event type, or emotion definition; ask one accuracy question instead of reopening broad exploration, then use the shared batch entity routes after the user accepts the wording or explicitly asks to save. When the user is updating a Psyche record because of one fresh episode, anchor in that episode before renaming the durable formulation, begin with the smallest part of the old wording that no longer fits, and do not reopen the full origin story unless the new understanding is truly structural. If the user accepts the wording, move toward the save instead of reopening deeper exploration.",
             specializedSurfaceRule: "For Movement, Life Force, and Workbench, clarify the job first, then choose the dedicated route family internally and do not guess at a generic CRUD path. Use specializedDomainSurfaces.routeSelectionQuestions when they are present so the next follow-up selects the right route instead of asking generic questions. When available, use forge_call_movement_route, forge_call_life_force_route, or forge_call_workbench_route after the lane is clear. In user-facing language, talk about timeline, overlay, weekday template, published output, run detail, or node result rather than surfaces, payloads, read paths, mutation paths, or CRUD. If the truth of the current state is still uncertain, read the relevant dedicated view before you mutate it. When the user already named a precise correction or review target, confirm only the route-selecting detail that is still missing. After a concrete Movement, Life Force, or Workbench correction, read the relevant view back when the user is trying to understand the result rather than just store it. The canonical runtime routes stay under /api/v1/*, and the OpenClaw HTTP mirror exposes the same families under /forge/v1/movement, /forge/v1/life-force, and /forge/v1/workbench.",
-            reviewShortcutRule: "When the user is reviewing or correcting an existing record, ask what practical question they want the read or correction to answer, then narrow the saved object, timeframe, or route family first. Do not reopen the whole intake unless the user is actually redefining the record.",
+            reviewShortcutRule: "When the user is reviewing or correcting an existing record, ask what practical question they want the read or correction to answer, then narrow the saved object, timeframe, or route family first. Use the correct read posture before asking write-shaped questions: shared batch search or read hints for normal entities, wiki/calendar dedicated reads for specialized CRUD, read-model routes for overviews, and Movement, Life Force, or Workbench dedicated reads for those domain surfaces. After the read, answer the practical question before asking for any save, correction, link, run, enrichment, or publish detail. Do not reopen the whole intake unless the user is actually redefining the record.",
             readModelWriteRule: "Self-observation is note-backed and should be written through observed notes with frontmatter.observedAt only when a lightweight episode observation is the right container. Do not use it as the default bucket for Psyche material: prefer trigger_report for one emotionally meaningful episode, behavior_pattern for functional analysis of a recurring loop, behavior for one repeated move, belief_entry for a core sentence, mode_guide_session or mode_profile for a central part-state, and wiki_page for durable memory such as books, articles, concepts, sources, or personal manuals. Sleep and workout sessions stay on batch CRUD by default; use the reflective review helpers only when enriching one already-known record after review.",
             psycheOpeningQuestionRule: "Prefer a concrete opening question tied to the entity: ask when the value mattered, what happened the last time the pattern appeared, what cue or body signal came first before the behavior, what the belief starts saying about self or outcome, what feels most at risk inside the mode, what the part is trying to get the user to do or stop doing, or where the shift began in the incident. Reflect briefly before the question, choose one follow-up lane at a time, say what is becoming clearer before the next deeper question, and if several Psyche entities are visible hold the adjacent ones lightly until the main container is clear.",
-            psycheHypothesisRule: "When one concrete Psyche example is visible, a helpful hypothesis should start from evidence in the user's own example, offer one testable interpretation, name the function without blame such as protection, prediction, relief, or cost, and ask whether the danger, need, or wording fits. Do not present schema, mode, belief, or pattern language as a verdict. If the user corrects the hypothesis, revise it once and move toward the saveable record shape instead of asking for another broad story.",
+            psycheHypothesisRule: "When one concrete Psyche example is visible, a helpful hypothesis should start from evidence in the user's own example, offer one testable interpretation, name the function without blame such as protection, prediction, relief, or cost, and ask whether the danger, need, or wording fits. Use the hypothesis timing checkpoint before asking a second or third deepening question: offer a hypothesis when one concrete episode, body cue, belief sentence, behavior, or mode voice is visible and the hypothesis would change the record shape, wording, links, or next action. Do not hypothesize yet when no concrete moment is visible, the user only wants a direct mechanical save, the user is flooded or unsafe, or the only available interpretation would be diagnosis-like, an origin story, or a certainty claim. Do not present schema, mode, belief, or pattern language as a verdict. If the user corrects the hypothesis, revise it once and move toward the saveable record shape instead of asking for another broad story.",
             mixedIntentSequencingRule: "When one user message combines several Forge jobs, identify the primary job and the order of operations before asking a follow-up. If a read changes the truth of a later write, read first: Movement timeline or box detail before correction, Workbench run or node detail before editing or publishing, and Life Force overview before changing durable assumptions when the current energy picture is uncertain. If the user asks to understand and save Psyche material plus create a support record, formulate the primary Psyche record first, then derive the flashcard, note, link, task, or habit from the accepted wording. If the user already gave the concrete action, do not ask a broad lane question; say the product sequence briefly and ask only for the missing span, wording, flow, run, node, weekday, or link that changes the next action.",
             duplicateDisambiguationRule: "Before creating or updating a normal stored entity when duplicate risk is plausible, search the shared batch entity route by entity type, distinctive title or wording, owner scope, and linked content. If a likely existing record appears, ask whether the user wants to update that record, link to it, or save a separate new record; do not reopen the whole create flow. For Psyche records, a similar belief, pattern, mode, trigger report, value, or flashcard is a formulation choice, not a duplicate error: compare the sentence, cue/payoff/cost, protective job, episode, urge sentence, or message and let the user choose update, link, or new version. For wiki_page and calendar_connection, use dedicated search/list/read routes before creating another page or connection. For Movement, Life Force, and Workbench, use the dedicated read lanes instead of batch duplicate search.",
             destructiveActionRule: "Before deleting, archiving, invalidating, overwriting, disconnecting, or substantially replacing a Forge record or specialized object, confirm the exact target and what should remain understandable. Prefer normal soft-delete for stored entities unless the user explicitly asks for permanent removal. For Psyche records, preserve therapeutic history by asking whether the old belief, pattern, mode, trigger report, value, or flashcard should be updated, linked as history, archived, or kept distinct; do not delete it just because a cleaner formulation exists. For Movement, distinguish user-defined overlay deletion from automatic-box invalidation and stay/trip/point deletion, and read the specific span first when the target is uncertain. For calendar connections, Workbench flows, wiki pages, and questionnaire instruments, ask what downstream sync, published output, backlinks, run history, or completed runs should remain understandable before deleting or replacing the saved object.",

package/dist/server/server/src/openapi.js

@@ -4766,6 +4766,9 @@ export function buildOpenApiDocument() {
             "latestDateKey",
             "rawSwearCount",
             "swearingMessagePercent",
+            "averageMaxCumulativeRage",
+            "maxCumulativeRage",
+            "maxSwearingStreak",
             "conversationsScanned",
             "messagesScanned",
             "messagesWithSwears",
@@ -4780,25 +4783,42 @@ export function buildOpenApiDocument() {
             latestDateKey: nullable({ type: "string" }),
             rawSwearCount: { type: "number" },
             swearingMessagePercent: { type: "number" },
+            averageMaxCumulativeRage: { type: "number" },
+            maxCumulativeRage: { type: "number" },
+            maxSwearingStreak: { type: "integer" },
             conversationsScanned: { type: "integer" },
             messagesScanned: { type: "integer" },
             messagesWithSwears: { type: "integer" },
             dailyAverage: {
                 type: "object",
                 additionalProperties: false,
-                required: ["rawSwearCount", "swearingMessagePercent"],
+                required: [
+                    "rawSwearCount",
+                    "swearingMessagePercent",
+                    "averageMaxCumulativeRage",
+                    "maxCumulativeRage"
+                ],
                 properties: {
                     rawSwearCount: { type: "number" },
-                    swearingMessagePercent: { type: "number" }
+                    swearingMessagePercent: { type: "number" },
+                    averageMaxCumulativeRage: { type: "number" },
+                    maxCumulativeRage: { type: "number" }
                 }
             },
             weeklyAverage: {
                 type: "object",
                 additionalProperties: false,
-                required: ["rawSwearCount", "swearingMessagePercent"],
+                required: [
+                    "rawSwearCount",
+                    "swearingMessagePercent",
+                    "averageMaxCumulativeRage",
+                    "maxCumulativeRage"
+                ],
                 properties: {
                     rawSwearCount: { type: "number" },
-                    swearingMessagePercent: { type: "number" }
+                    swearingMessagePercent: { type: "number" },
+                    averageMaxCumulativeRage: { type: "number" },
+                    maxCumulativeRage: { type: "number" }
                 }
             },
             history: arrayOf({
@@ -4808,6 +4828,9 @@ export function buildOpenApiDocument() {
                     "dateKey",
                     "rawSwearCount",
                     "swearingMessagePercent",
+                    "averageMaxCumulativeRage",
+                    "maxCumulativeRage",
+                    "maxSwearingStreak",
                     "conversationsScanned",
                     "messagesScanned",
                     "messagesWithSwears"
@@ -4816,6 +4839,9 @@ export function buildOpenApiDocument() {
                     dateKey: { type: "string" },
                     rawSwearCount: { type: "number" },
                     swearingMessagePercent: { type: "number" },
+                    averageMaxCumulativeRage: { type: "number" },
+                    maxCumulativeRage: { type: "number" },
+                    maxSwearingStreak: { type: "integer" },
                     conversationsScanned: { type: "integer" },
                     messagesScanned: { type: "integer" },
                     messagesWithSwears: { type: "integer" }
@@ -4952,19 +4978,33 @@ export function buildOpenApiDocument() {
                     dailyAverage: {
                         type: "object",
                         additionalProperties: false,
-                        required: ["rawSwearCount", "swearingMessagePercent"],
+                        required: [
+                            "rawSwearCount",
+                            "swearingMessagePercent",
+                            "averageMaxCumulativeRage",
+                            "maxCumulativeRage"
+                        ],
                         properties: {
                             rawSwearCount: { type: "number" },
-                            swearingMessagePercent: { type: "number" }
+                            swearingMessagePercent: { type: "number" },
+                            averageMaxCumulativeRage: { type: "number" },
+                            maxCumulativeRage: { type: "number" }
                         }
                     },
                     weeklyAverage: {
                         type: "object",
                         additionalProperties: false,
-                        required: ["rawSwearCount", "swearingMessagePercent"],
+                        required: [
+                            "rawSwearCount",
+                            "swearingMessagePercent",
+                            "averageMaxCumulativeRage",
+                            "maxCumulativeRage"
+                        ],
                         properties: {
                             rawSwearCount: { type: "number" },
-                            swearingMessagePercent: { type: "number" }
+                            swearingMessagePercent: { type: "number" },
+                            averageMaxCumulativeRage: { type: "number" },
+                            maxCumulativeRage: { type: "number" }
                         }
                     },
                     sync: {

package/dist/server/server/src/psyche-types.js

@@ -280,21 +280,31 @@ export const devrageMetricPayloadSchema = z.object({
     latestDateKey: z.string().nullable(),
     rawSwearCount: z.number().nonnegative(),
     swearingMessagePercent: z.number().nonnegative(),
+    averageMaxCumulativeRage: z.number().nonnegative(),
+    maxCumulativeRage: z.number().nonnegative(),
+    maxSwearingStreak: z.number().int().nonnegative(),
     conversationsScanned: z.number().int().nonnegative(),
     messagesScanned: z.number().int().nonnegative(),
     messagesWithSwears: z.number().int().nonnegative(),
     dailyAverage: z.object({
         rawSwearCount: z.number().nonnegative(),
-        swearingMessagePercent: z.number().nonnegative()
+        swearingMessagePercent: z.number().nonnegative(),
+        averageMaxCumulativeRage: z.number().nonnegative(),
+        maxCumulativeRage: z.number().nonnegative()
     }),
     weeklyAverage: z.object({
         rawSwearCount: z.number().nonnegative(),
-        swearingMessagePercent: z.number().nonnegative()
+        swearingMessagePercent: z.number().nonnegative(),
+        averageMaxCumulativeRage: z.number().nonnegative(),
+        maxCumulativeRage: z.number().nonnegative()
     }),
     history: z.array(z.object({
         dateKey: z.string(),
         rawSwearCount: z.number().nonnegative(),
         swearingMessagePercent: z.number().nonnegative(),
+        averageMaxCumulativeRage: z.number().nonnegative(),
+        maxCumulativeRage: z.number().nonnegative(),
+        maxSwearingStreak: z.number().int().nonnegative(),
         conversationsScanned: z.number().int().nonnegative(),
         messagesScanned: z.number().int().nonnegative(),
         messagesWithSwears: z.number().int().nonnegative()
@@ -337,11 +347,15 @@ export const psycheMetricsViewDataSchema = z.object({
         totalSwears: z.number().nonnegative(),
         dailyAverage: z.object({
             rawSwearCount: z.number().nonnegative(),
-            swearingMessagePercent: z.number().nonnegative()
+            swearingMessagePercent: z.number().nonnegative(),
+            averageMaxCumulativeRage: z.number().nonnegative(),
+            maxCumulativeRage: z.number().nonnegative()
         }),
         weeklyAverage: z.object({
             rawSwearCount: z.number().nonnegative(),
-            swearingMessagePercent: z.number().nonnegative()
+            swearingMessagePercent: z.number().nonnegative(),
+            averageMaxCumulativeRage: z.number().nonnegative(),
+            maxCumulativeRage: z.number().nonnegative()
         }),
         sync: z.object({
             fullSyncCompletedAt: z.string().nullable(),

package/dist/server/server/src/services/devrage-scanner.js

@@ -7,7 +7,8 @@ import { createInterface } from "node:readline/promises";
 const require = createRequire(import.meta.url);
 const tokenPattern = /[a-z][a-z0-9'*_-]*/gi;
 const defaultSwearLexicon = [
-    { root: "fuck", variants: ["fuck", "fucked", "fucker", "fuckers", "fuckin", "fucking", "fucks", "motherfuck", "motherfucked", "motherfucker", "motherfuckers", "motherfucking"] },
+    { root: "fuck", variants: ["fuck", "f*ck", "f**k", "fck", "fuk", "fucked", "fucker", "fuckers", "fuckin", "fucking", "fucks", "motherfuck", "motherfucked", "motherfucker", "motherfuckers", "motherfucking"] },
+    { root: "ffs", variants: ["ffs", "for fucks sake", "for fuck's sake", "for-fucks-sake", "for-fuck's-sake"] },
     { root: "wtf", variants: ["wtf"] },
     { root: "shit", variants: ["shit", "shitshow", "shits", "shitty", "bullshit", "bullshitting", "dipshit", "dipshits"] },
     { root: "dick", variants: ["dick", "dicks", "dickhead", "dickheads"] },
@@ -33,10 +34,7 @@ const ADAPTER_FACTORIES = {
         join(homedir(), ".hermes", "**/*.{json,jsonl}"),
         join(homedir(), ".config", "hermes", "**/*.{json,jsonl}")
     ]),
-    openclaw: () => genericLocalLogAdapter("openclaw", [
-        join(homedir(), ".openclaw", "**/*.{json,jsonl}"),
-        join(homedir(), "Library", "Application Support", "OpenClaw", "**/*.{json,jsonl}")
-    ]),
+    openclaw: openclawAdapter,
     opencode: opencodeAdapter,
     zed: zedAdapter
 };
@@ -69,7 +67,7 @@ function createAdapter(source) {
 function allAdapters() {
     return availableSources().map((source) => createAdapter(source));
 }
-function analyzeConversations(conversations, options, generatedAt = new Date().toISOString()) {
+export function analyzeConversations(conversations, options, generatedAt = new Date().toISOString()) {
     const { tokenIndex, phraseVariants } = buildLexiconIndexes();
     const agentStats = new Map();
     const sourceStats = new Map();
@@ -89,6 +87,10 @@ function analyzeConversations(conversations, options, generatedAt = new Date().t
         let conversationMessages = 0;
         let conversationMessagesWithSwears = 0;
         let conversationSwears = 0;
+        let cumulativeRage = 0;
+        let maxCumulativeRage = 0;
+        let swearingStreak = 0;
+        let maxSwearingStreak = 0;
         const currentSource = sourceStats.get(conversation.source) ?? {
             source: conversation.source,
             conversations: 0,
@@ -125,7 +127,15 @@ function analyzeConversations(conversations, options, generatedAt = new Date().t
                 currentSource.messagesWithSwears += 1;
                 currentAgent.messagesWithSwears += 1;
                 currentAgent.swears += swearsInMessage;
+                cumulativeRage += swearsInMessage;
+                swearingStreak += 1;
+            }
+            else {
+                cumulativeRage = Math.max(0, cumulativeRage - 1);
+                swearingStreak = 0;
             }
+            maxCumulativeRage = Math.max(maxCumulativeRage, cumulativeRage);
+            maxSwearingStreak = Math.max(maxSwearingStreak, swearingStreak);
             agentStats.set(agent, currentAgent);
         }
         sourceStats.set(conversation.source, currentSource);
@@ -138,9 +148,17 @@ function analyzeConversations(conversations, options, generatedAt = new Date().t
             dateKey,
             messages: conversationMessages,
             messagesWithSwears: conversationMessagesWithSwears,
-            swears: conversationSwears
+            swears: conversationSwears,
+            maxCumulativeRage,
+            maxSwearingStreak
         });
     }
+    const maxCumulativeRage = Math.max(0, ...conversationStats.map((conversation) => conversation.maxCumulativeRage));
+    const maxSwearingStreak = Math.max(0, ...conversationStats.map((conversation) => conversation.maxSwearingStreak));
+    const averageMaxCumulativeRage = conversationStats.length === 0
+        ? 0
+        : conversationStats.reduce((sum, conversation) => sum + conversation.maxCumulativeRage, 0) /
+            conversationStats.length;
     return {
         generatedAt,
         filesScanned: [...filesScanned].sort(),
@@ -148,6 +166,9 @@ function analyzeConversations(conversations, options, generatedAt = new Date().t
         messagesScanned,
         messagesWithSwears,
         totalSwears,
+        averageMaxCumulativeRage,
+        maxCumulativeRage,
+        maxSwearingStreak,
         byAgent: [...agentStats.entries()]
             .map(([agent, stats]) => ({ agent, ...stats }))
             .sort((left, right) => right.swears - left.swears ||
@@ -399,6 +420,28 @@ function genericLocalLogAdapter(source, patterns) {
         }
     };
 }
+function openclawAdapter() {
+    return {
+        source: "openclaw",
+        async read() {
+            const trajectoryResult = await readJsonlTree("openclaw", [
+                join(homedir(), ".openclaw", "agents"),
+                join(homedir(), "Library", "Application Support", "OpenClaw", "agents")
+            ], parseOpenClawTrajectoryLine);
+            const genericResult = await genericLocalLogAdapter("openclaw", [
+                join(homedir(), ".openclaw", "**/*.{json,jsonl}"),
+                join(homedir(), "Library", "Application Support", "OpenClaw", "**/*.{json,jsonl}")
+            ]).read();
+            return {
+                conversations: [
+                    ...trajectoryResult.conversations,
+                    ...genericResult.conversations.filter((conversation) => !conversation.sourceFile.endsWith(".trajectory.jsonl"))
+                ],
+                warnings: [...trajectoryResult.warnings, ...genericResult.warnings]
+            };
+        }
+    };
+}
 async function readJsonlTree(source, roots, parser) {
     const files = (await Promise.all(roots.map((root) => globFiles(`${root.replace(/\/+$/, "")}/**/*.jsonl`))))
         .flat()
@@ -515,6 +558,47 @@ function parseGenericJsonLine(record, context) {
         index: context.line
     });
 }
+export function parseOpenClawTrajectoryLine(record, context) {
+    if (!isObject(record) || record.type !== "prompt.submitted" || !isObject(record.data)) {
+        return null;
+    }
+    const data = record.data;
+    const text = typeof data.prompt === "string" && data.prompt.trim().length > 0
+        ? data.prompt.trim()
+        : latestOpenClawUserMessageText(data.messages);
+    if (!text || isContextInjection("user", text)) {
+        return null;
+    }
+    return {
+        agent: "openclaw",
+        source: "openclaw",
+        conversationId: context.conversationId.replace(/\.trajectory$/, ""),
+        role: "user",
+        text,
+        timestamp: stringTimestamp(record.ts) ??
+            stringTimestamp(record.timestamp) ??
+            stringTimestamp(data.timestamp) ??
+            numberTimestamp(record.ts) ??
+            context.fallbackTimestamp,
+        sourceFile: context.sourceFile
+    };
+}
+function latestOpenClawUserMessageText(messages) {
+    if (!Array.isArray(messages)) {
+        return "";
+    }
+    for (let index = messages.length - 1; index >= 0; index -= 1) {
+        const message = messages[index];
+        if (!isObject(message) || normalizeRole(message.role ?? message.type) !== "user") {
+            continue;
+        }
+        const text = extractText(message.content ?? message.text).join("\n").trim();
+        if (text) {
+            return text;
+        }
+    }
+    return "";
+}
 function parseGenericMessage(entry, context) {
     if (!isObject(entry)) {
         return null;
@@ -590,7 +674,7 @@ function buildLexiconIndexes(lexicon = defaultSwearLexicon) {
                 });
                 continue;
             }
-            tokenIndex.set(normalizedVariant, entry.root);
+            tokenIndex.set(normalizeToken(normalizedVariant), entry.root);
         }
     }
     phraseVariants.sort((left, right) => right.variant.length - left.variant.length || left.variant.localeCompare(right.variant));
@@ -676,17 +760,38 @@ function buildDailyStats(conversations) {
                 messages: 0,
                 messagesWithSwears: 0,
                 swears: 0,
-                swearingMessagePercent: 0
+                swearingMessagePercent: 0,
+                averageMaxCumulativeRage: 0,
+                maxCumulativeRage: 0,
+                maxSwearingStreak: 0,
+                maxCumulativeRageSum: 0
             };
         current.conversations += 1;
         current.messages += conversation.messages;
         current.messagesWithSwears += conversation.messagesWithSwears;
         current.swears += conversation.swears;
+        current.maxCumulativeRageSum += conversation.maxCumulativeRage;
+        current.maxCumulativeRage = Math.max(current.maxCumulativeRage, conversation.maxCumulativeRage);
+        current.maxSwearingStreak = Math.max(current.maxSwearingStreak, conversation.maxSwearingStreak);
         current.swearingMessagePercent =
             current.messages === 0 ? 0 : (current.messagesWithSwears / current.messages) * 100;
+        current.averageMaxCumulativeRage =
+            current.conversations === 0 ? 0 : current.maxCumulativeRageSum / current.conversations;
         byDay.set(conversation.dateKey, current);
     }
-    return [...byDay.values()].sort((left, right) => right.dateKey.localeCompare(left.dateKey));
+    return [...byDay.values()]
+        .map((stats) => ({
+        dateKey: stats.dateKey,
+        conversations: stats.conversations,
+        messages: stats.messages,
+        messagesWithSwears: stats.messagesWithSwears,
+        swears: stats.swears,
+        swearingMessagePercent: stats.swearingMessagePercent,
+        averageMaxCumulativeRage: stats.averageMaxCumulativeRage,
+        maxCumulativeRage: stats.maxCumulativeRage,
+        maxSwearingStreak: stats.maxSwearingStreak
+    }))
+        .sort((left, right) => right.dateKey.localeCompare(left.dateKey));
 }
 function compactMessage(message) {
     return message ? [message] : [];

package/dist/server/server/src/services/devrage.js

@@ -4,6 +4,8 @@ import { getDatabase, runInTransaction } from "../db.js";
 import { psycheMetricsViewDataSchema } from "../psyche-types.js";
 const SWEAR_COUNT_KEY = "swear_count";
 const SWEARING_MESSAGE_PERCENT_KEY = "swearing_message_percent";
+const AVERAGE_MAX_CUMULATIVE_RAGE_KEY = "average_max_cumulative_rage";
+const MAX_CUMULATIVE_RAGE_KEY = "max_cumulative_rage";
 const DEFAULT_ROLE_FILTER = new Set(["user"]);
 const DAILY_RESYNC_INTERVAL_MS = 60 * 60 * 1000;
 const PSYCHE_METRIC_DEFINITIONS = {
@@ -20,6 +22,20 @@ const PSYCHE_METRIC_DEFINITIONS = {
         category: "conversationTone",
         unit: "%",
         aggregation: "discrete"
+    },
+    [AVERAGE_MAX_CUMULATIVE_RAGE_KEY]: {
+        metric: "devrageAverageMaxCumulativeRage",
+        label: "Average max cumulative rage",
+        category: "conversationTone",
+        unit: "score",
+        aggregation: "discrete"
+    },
+    [MAX_CUMULATIVE_RAGE_KEY]: {
+        metric: "devrageMaxCumulativeRage",
+        label: "Max cumulative rage",
+        category: "conversationTone",
+        unit: "score",
+        aggregation: "discrete"
     }
 };
 let syncInFlight = null;
@@ -69,16 +85,23 @@ export function getDevrageMetricPayload() {
         latestDateKey: latest?.dateKey ?? null,
         rawSwearCount: latest?.rawSwearCount ?? 0,
         swearingMessagePercent: latest?.swearingMessagePercent ?? 0,
+        averageMaxCumulativeRage: latest?.averageMaxCumulativeRage ?? 0,
+        maxCumulativeRage: latest?.maxCumulativeRage ?? 0,
+        maxSwearingStreak: latest?.maxSwearingStreak ?? 0,
         conversationsScanned: latest?.conversationsScanned ?? 0,
         messagesScanned: latest?.messagesScanned ?? 0,
         messagesWithSwears: latest?.messagesWithSwears ?? 0,
         dailyAverage: {
             rawSwearCount: dailyAverages.rawSwearCount,
-            swearingMessagePercent: dailyAverages.swearingMessagePercent
+            swearingMessagePercent: dailyAverages.swearingMessagePercent,
+            averageMaxCumulativeRage: dailyAverages.averageMaxCumulativeRage,
+            maxCumulativeRage: dailyAverages.maxCumulativeRage
         },
         weeklyAverage: {
             rawSwearCount: weeklyAverages.rawSwearCount,
-            swearingMessagePercent: weeklyAverages.swearingMessagePercent
+            swearingMessagePercent: weeklyAverages.swearingMessagePercent,
+            averageMaxCumulativeRage: weeklyAverages.averageMaxCumulativeRage,
+            maxCumulativeRage: weeklyAverages.maxCumulativeRage
         },
         history,
         sync: {
@@ -220,11 +243,15 @@ export function getPsycheMetricsViewData() {
             totalSwears: Number(context.swear_count) || 0,
             dailyAverage: {
                 rawSwearCount: dailyAverages.rawSwearCount,
-                swearingMessagePercent: dailyAverages.swearingMessagePercent
+                swearingMessagePercent: dailyAverages.swearingMessagePercent,
+                averageMaxCumulativeRage: dailyAverages.averageMaxCumulativeRage,
+                maxCumulativeRage: dailyAverages.maxCumulativeRage
             },
             weeklyAverage: {
                 rawSwearCount: weeklyAverages.rawSwearCount,
-                swearingMessagePercent: weeklyAverages.swearingMessagePercent
+                swearingMessagePercent: weeklyAverages.swearingMessagePercent,
+                averageMaxCumulativeRage: weeklyAverages.averageMaxCumulativeRage,
+                maxCumulativeRage: weeklyAverages.maxCumulativeRage
             },
             sync: {
                 fullSyncCompletedAt: state?.full_sync_completed_at ?? null,
@@ -255,20 +282,23 @@ export function storeDevrageReport(report, options) {
         const deleteDate = database.prepare(`DELETE FROM psyche_devrage_conversation_measures WHERE date_key = ?`);
         const insertConversation = database.prepare(`INSERT INTO psyche_devrage_conversation_measures (
          id, source, conversation_id, date_key, updated_at, messages,
-         messages_with_swears, swear_count, scanned_at
+         messages_with_swears, swear_count, max_cumulative_rage,
+         max_swearing_streak, scanned_at
        )
-       VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
+       VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
        ON CONFLICT(source, conversation_id, date_key) DO UPDATE SET
          updated_at = excluded.updated_at,
          messages = excluded.messages,
          messages_with_swears = excluded.messages_with_swears,
          swear_count = excluded.swear_count,
+         max_cumulative_rage = excluded.max_cumulative_rage,
+         max_swearing_streak = excluded.max_swearing_streak,
          scanned_at = excluded.scanned_at`);
         for (const dateKey of affectedDateKeys) {
             deleteDate.run(dateKey);
         }
         for (const conversation of report.conversations) {
-            insertConversation.run(stableId("devrage_conversation", conversation.source, conversation.conversationId, conversation.dateKey), conversation.source, conversation.conversationId, conversation.dateKey, conversation.updatedAt, conversation.messages, conversation.messagesWithSwears, conversation.swears, scannedAt);
+            insertConversation.run(stableId("devrage_conversation", conversation.source, conversation.conversationId, conversation.dateKey), conversation.source, conversation.conversationId, conversation.dateKey, conversation.updatedAt, conversation.messages, conversation.messagesWithSwears, conversation.swears, conversation.maxCumulativeRage, conversation.maxSwearingStreak, scannedAt);
         }
         for (const dateKey of affectedDateKeys) {
             recomputeMetricMeasuresForDate(dateKey, scannedAt);
@@ -287,16 +317,23 @@ function recomputeMetricMeasuresForDate(dateKey, computedAt) {
          COUNT(*) AS conversations,
          COALESCE(SUM(messages), 0) AS messages,
          COALESCE(SUM(messages_with_swears), 0) AS messages_with_swears,
-         COALESCE(SUM(swear_count), 0) AS swear_count
+         COALESCE(SUM(swear_count), 0) AS swear_count,
+         COALESCE(AVG(max_cumulative_rage), 0) AS average_max_cumulative_rage,
+         COALESCE(MAX(max_cumulative_rage), 0) AS max_cumulative_rage,
+         COALESCE(MAX(max_swearing_streak), 0) AS max_swearing_streak
        FROM psyche_devrage_conversation_measures
        WHERE date_key = ?`)
         .get(dateKey);
     const messages = Number(aggregate.messages) || 0;
     const messagesWithSwears = Number(aggregate.messages_with_swears) || 0;
     const swearCount = Number(aggregate.swear_count) || 0;
+    const averageMaxCumulativeRage = Number(aggregate.average_max_cumulative_rage) || 0;
+    const maxCumulativeRage = Number(aggregate.max_cumulative_rage) || 0;
     const percent = messages > 0 ? (messagesWithSwears / messages) * 100 : 0;
     upsertMetricMeasure(dateKey, SWEAR_COUNT_KEY, swearCount, "count", Number(aggregate.conversations) || 0, computedAt);
     upsertMetricMeasure(dateKey, SWEARING_MESSAGE_PERCENT_KEY, percent, "percent", messages, computedAt);
+    upsertMetricMeasure(dateKey, AVERAGE_MAX_CUMULATIVE_RAGE_KEY, averageMaxCumulativeRage, "score", Number(aggregate.conversations) || 0, computedAt);
+    upsertMetricMeasure(dateKey, MAX_CUMULATIVE_RAGE_KEY, maxCumulativeRage, "score", Number(aggregate.conversations) || 0, computedAt);
 }
 function upsertMetricMeasure(dateKey, metricKey, value, unit, sampleCount, computedAt) {
     getDatabase()
@@ -339,7 +376,10 @@ function getDevrageDailyHistory(limit) {
          COUNT(*) AS conversations,
          COALESCE(SUM(messages), 0) AS messages,
          COALESCE(SUM(messages_with_swears), 0) AS messages_with_swears,
-         COALESCE(SUM(swear_count), 0) AS swear_count
+         COALESCE(SUM(swear_count), 0) AS swear_count,
+         COALESCE(AVG(max_cumulative_rage), 0) AS average_max_cumulative_rage,
+         COALESCE(MAX(max_cumulative_rage), 0) AS max_cumulative_rage,
+         COALESCE(MAX(max_swearing_streak), 0) AS max_swearing_streak
        FROM psyche_devrage_conversation_measures
        GROUP BY date_key
        ORDER BY date_key DESC
@@ -352,6 +392,9 @@ function getDevrageDailyHistory(limit) {
             dateKey: row.date_key,
             rawSwearCount: Number(row.swear_count) || 0,
             swearingMessagePercent: messages > 0 ? (messagesWithSwears / messages) * 100 : 0,
+            averageMaxCumulativeRage: Number(row.average_max_cumulative_rage) || 0,
+            maxCumulativeRage: Number(row.max_cumulative_rage) || 0,
+            maxSwearingStreak: Number(row.max_swearing_streak) || 0,
             conversationsScanned: Number(row.conversations) || 0,
             messagesScanned: messages,
             messagesWithSwears
@@ -375,9 +418,13 @@ function getMetricAverages(days) {
         .all(...(days ? [days] : []));
     const swearAverage = rows.find((row) => row.metric_key === SWEAR_COUNT_KEY)?.value ?? 0;
     const percentAverage = rows.find((row) => row.metric_key === SWEARING_MESSAGE_PERCENT_KEY)?.value ?? 0;
+    const averageMaxCumulativeRage = rows.find((row) => row.metric_key === AVERAGE_MAX_CUMULATIVE_RAGE_KEY)?.value ?? 0;
+    const maxCumulativeRage = rows.find((row) => row.metric_key === MAX_CUMULATIVE_RAGE_KEY)?.value ?? 0;
     return {
         rawSwearCount: round(Number(swearAverage) || 0, 1),
-        swearingMessagePercent: round(Number(percentAverage) || 0, 1)
+        swearingMessagePercent: round(Number(percentAverage) || 0, 1),
+        averageMaxCumulativeRage: round(Number(averageMaxCumulativeRage) || 0, 1),
+        maxCumulativeRage: round(Number(maxCumulativeRage) || 0, 1)
     };
 }
 function getDevrageConversationTotals() {
@@ -387,7 +434,10 @@ function getDevrageConversationTotals() {
          COUNT(DISTINCT source) AS sources,
          COALESCE(SUM(messages), 0) AS messages,
          COALESCE(SUM(messages_with_swears), 0) AS messages_with_swears,
-         COALESCE(SUM(swear_count), 0) AS swear_count
+         COALESCE(SUM(swear_count), 0) AS swear_count,
+         COALESCE(AVG(max_cumulative_rage), 0) AS average_max_cumulative_rage,
+         COALESCE(MAX(max_cumulative_rage), 0) AS max_cumulative_rage,
+         COALESCE(MAX(max_swearing_streak), 0) AS max_swearing_streak
        FROM psyche_devrage_conversation_measures`)
         .get();
 }

package/openclaw.plugin.json

@@ -2,7 +2,7 @@
   "id": "forge-openclaw-plugin",
   "name": "Forge",
   "description": "Curated OpenClaw adapter for the Forge collaboration API, UI entrypoint, and localhost auto-start runtime.",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "activation": {
     "onStartup": true,
     "onCapabilities": [

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "forge-openclaw-plugin",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "Curated OpenClaw adapter for the Forge collaboration API, UI entrypoint, and localhost auto-start runtime.",
   "type": "module",
   "license": "Apache-2.0",

package/server/migrations/069_psyche_devrage_cumulative_rage.sql

@@ -0,0 +1,5 @@
+ALTER TABLE psyche_devrage_conversation_measures
+  ADD COLUMN max_cumulative_rage REAL NOT NULL DEFAULT 0;
+
+ALTER TABLE psyche_devrage_conversation_measures
+  ADD COLUMN max_swearing_streak INTEGER NOT NULL DEFAULT 0;

package/skills/forge-openclaw/SKILL.md

@@ -265,6 +265,12 @@ Entity conversation rule:
 - When the user wants to review, compare, inspect, or navigate an existing Forge
   record, ask what they are trying to understand first and look up the existing record
   before you reopen create or update intake.
+- For review-first requests, use the correct read posture before asking write-shaped
+  questions: shared batch search or read hints for normal entities, wiki/calendar
+  dedicated reads for specialized CRUD, read-model routes for overviews, and
+  Movement, Life Force, or Workbench dedicated reads for those domain surfaces. After
+  the read, answer the practical question before asking for any save, correction,
+  link, run, enrichment, or publish detail.
 - When updating an entity, start with what is changing, what should stay true, and what prompted the update now.
 - When enough is clear, briefly summarize what you heard in the user's own language before asking for the last missing structural detail.
 - Treat `userId` and human/bot assignees as accountability and scope, not as opening form fields. Ask whose human or bot record it is only when ownership changes visibility, review scope, collaboration, automation behavior, or later filtering; for read requests, ask user scope only when the answer would differ across owners.
@@ -294,6 +300,7 @@ Psyche interview rule:
 - After the first real answer, choose one follow-up lane at a time: situation, sequence, meaning, protection, cost, longing/value, or tentative name.
 - Do not minimize functional analysis, trigger chains, behavior patterns, modes, beliefs, or schema themes. Once at least one concrete example is clear, offer one careful interpretive hypothesis when it would help the user understand the function, protection, cost, belief, mode, or schema theme.
 - Phrase interpretive hypotheses as collaborative and testable, not as verdicts. A good hypothesis says what the reaction may be protecting, predicting, relieving, or costing, then asks whether that lands or needs correction.
+- Use the hypothesis timing checkpoint before asking a second or third deepening question: offer a hypothesis when one concrete episode, body cue, belief sentence, behavior, or mode voice is visible and the hypothesis would change the record shape, wording, links, or next action. Do not hypothesize yet when no concrete moment is visible, the user only wants a direct mechanical save, the user is flooded or unsafe, or the only available interpretation would be diagnosis-like, an origin story, or a certainty claim.
 - If several Psyche containers are plausible, do not ask the user to choose from a taxonomy menu first. Reflect the lived difference, offer one careful hypothesis when a concrete example is visible, then distinguish the options in plain language: one episode as a `trigger_report`, a recurring loop as a `behavior_pattern`, one repeated move as `behavior`, one sentence as `belief_entry`, a part-state as `mode_profile` or `mode_guide_session`, or reusable future-labeling as `event_type` or `emotion_definition`.
 - 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.