summary system backend implementation

packages/orchestration-service/src/chat/index.js

@@ -4,6 +4,7 @@ const embedding = require("../services/embedding");
 const qdrant = require("../services/qdrant");
 const { ORCHESTRATION } = require("@nexusai/shared");
 const appSettings = require("../config/settings");
+const {triggerSummary} = require('../services/summarization')
 
 function buildPrompt(recentEpisodes, semanticEpisodes, entities, userMessage, systemPrompt) {
     const parts = [systemPrompt ?? ORCHESTRATION.SYSTEM_PROMPT];
@@ -193,12 +194,18 @@ async function chat(externalId, userMessage, options = {}) {
       console.error(`[orchestration] Failed to save episode`, err.message),
     );
 
-  // 7. Auto-name on first message
+  // 7. Trigger summarization check (fire-and-forget)
+  // Pass full episodes list so summarization can sum tokens accurately
+  const allEpisodes = await memory.getRecentEpisodes(session.id, 9999);
+  triggerSummary(session, allEpisodes);
+  
+  
+    // 8. Auto-name on first message
   if (isFirstMessage && !session.name) {
     autoNameSession(externalId, userMessage, result.text).catch(() => {}); // already logged inside autoNameSession
   }
 
-  // 8. Return response
+  // 9. Return response
   return {
     sessionId: externalId,
     response: result.text,
@@ -311,6 +318,8 @@ async function chatStream(externalId, userMessage, onChunk, options = {}) {
 
     if (fullText.trim()) {
       await memory.createEpisode(session.id, userMessage, fullText, tokenCount, session.project_id ?? null);
+      const allEpisodes = await memory.getRecentEpisodes(session.id, 9999);
+      triggerSummary(session, allEpisodes);
     } else {
       console.warn(
         "[orchestration] Stream finished with no assistant text; episode not saved",

packages/orchestration-service/src/services/memory.js

@@ -150,6 +150,32 @@ async function deleteEpisode(id) {
   if (!res.ok) throw new Error(`Failed to delete episode: ${res.status}`);
 }
 
+async function getSummariesBySession(sessionId) {
+    const res = await fetch(`${BASE_URL}/sessions/${sessionId}/summaries`);
+    if (!res.ok) throw new Error(`Failed to fetch summaries: ${res.status}`);
+    return res.json();
+}
+
+async function createSummary({ sessionId, projectId, content, tokenCount, episodeRange }) {
+    const res = await fetch(`${BASE_URL}/summaries`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ sessionId, projectId, content, tokenCount, episodeRange }),
+    });
+    if (!res.ok) throw new Error(`Failed to create summary: ${res.status}`);
+    return res.json();
+}
+
+async function updateSummary(id, { content, tokenCount, episodeRange }) {
+    const res = await fetch(`${BASE_URL}/summaries/${id}`, {
+        method: 'PATCH',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ content, tokenCount, episodeRange }),
+    });
+    if (!res.ok) throw new Error(`Failed to update summary: ${res.status}`);
+    return res.json();
+}
+
 module.exports = {
     getSessionByExternalId,
     createSession,
@@ -168,4 +194,7 @@ module.exports = {
     getProject,
     getEpisodes,
     deleteEpisode,
+    getSummariesBySession,
+    createSummary,
+    updateSummary,
 }

packages/orchestration-service/src/services/summarization.js

@@ -0,0 +1,129 @@
+const { getEnv, SERVICES, SUMMARIES } = require('@nexusai/shared');
+
+const EXTRACTION_URL  = getEnv('EXTRACTION_URL', 'http://localhost:11434');
+const EXTRACTION_MODEL = getEnv('EXTRACTION_MODEL', 'qwen2.5:3b');
+const MEMORY_URL      = getEnv('MEMORY_SERVICE_URL', SERVICES.MEMORY_URL);
+
+const THRESHOLD_TOKENS  = parseInt(getEnv('SUMMARY_THRESHOLD_TOKENS', SUMMARIES.THRESHOLD_TOKENS));
+const MAX_SUMMARY_TOKENS = parseInt(getEnv('SUMMARY_MAX_TOKENS', SUMMARIES.MAX_SUMMARY_TOKENS));
+const MIN_EPISODES_SINCE = parseInt(getEnv('SUMMARY_MIN_EPISODES', SUMMARIES.MIN_EPISODES_SINCE));
+
+function buildSummaryPrompt(episodes, existingSummary = null) {
+    const context = episodes
+        .map(ep => `User: ${ep.user_message}\nAssistant: ${ep.ai_response}`)
+        .join('\n\n');
+
+    const instruction = existingSummary
+        ? `You have a previous summary of this conversation. Update it to include the new exchanges below. Keep it concise — plain prose, no markdown, no headers, third person, max 200 words.
+
+Previous summary:
+${existingSummary}
+
+New exchanges to incorporate:`
+        : `Summarise this conversation. Be concise — plain prose, no markdown, no headers, third person, max 200 words. Preserve key decisions, facts, named entities, and unresolved questions.
+
+Conversation:`;
+
+    return [
+        '<|im_start|>system',
+        'You are a conversation summarisation assistant. You write concise, factual summaries for long-term memory storage. Output only the summary text — no preamble, no labels.<|im_end|>',
+        '<|im_start|>user',
+        instruction,
+        '',
+        context,
+        '<|im_end|>',
+        '<|im_start|>assistant',
+    ].join('\n');
+}
+
+async function generateSummary(episodes, existingSummary = null) {
+    const prompt = buildSummaryPrompt(episodes, existingSummary);
+
+    const res = await fetch(`${EXTRACTION_URL}/api/generate`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({
+            model: EXTRACTION_MODEL,
+            prompt,
+            stream: false,
+            options: {
+                temperature: 0.3,   // slightly higher than entities — summaries benefit from some fluency
+                num_predict: 300,   // generous but bounded — keeps summaries from running long
+            },
+        }),
+    });
+
+    if (!res.ok) throw new Error(`Ollama responded ${res.status}`);
+    const data = await res.json();
+    return data.response?.trim() ?? '';
+}
+
+async function maybeSummarize(session, allEpisodes) {
+    // 1. Sum total tokens for this session
+    const totalTokens = allEpisodes.reduce((sum, ep) => sum + (ep.token_count || 0), 0);
+    if (totalTokens < THRESHOLD_TOKENS) return; // under threshold — nothing to do
+
+    // 2. Fetch existing summaries for session
+    const summariesRes = await fetch(`${MEMORY_URL}/sessions/${session.id}/summaries`);
+    if (!summariesRes.ok) return;
+    const summaries = await summariesRes.json();
+
+    const latest = summaries.at(-1) ?? null;
+
+    // 3. Guard — don't re-summarize until MIN_EPISODES_SINCE new episodes have accumulated
+    if (latest) {
+        const lastEpisodeRange = latest.episode_range ?? '0';
+        const lastCoveredId = parseInt(lastEpisodeRange.split('-').at(-1)) || 0;
+        const newEpisodes = allEpisodes.filter(ep => ep.id > lastCoveredId);
+        if (newEpisodes.length < MIN_EPISODES_SINCE) return;
+    }
+
+    // 4. Determine episode range string  e.g. "1-42"
+    const ids = allEpisodes.map(ep => ep.id);
+    const episodeRange = `${ids.at(0)}-${ids.at(-1)}`;
+    const totalEpisodeTokens = allEpisodes.reduce((sum, ep) => sum + (ep.token_count || 0), 0);
+
+    // 5. Generate summary — pass existing content if updating
+    const content = await generateSummary(
+        allEpisodes,
+        latest && latest.content.length < MAX_SUMMARY_TOKENS ? latest.content : null
+        // if existing summary is already large, treat as fresh rather than appending to a huge blob
+    );
+
+    if (!content) return;
+
+    // 6. Create new row or update existing
+    if (!latest || latest.content.length >= MAX_SUMMARY_TOKENS) {
+        await fetch(`${MEMORY_URL}/summaries`, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({
+                sessionId: session.id,
+                content,
+                tokenCount: totalEpisodeTokens,
+                episodeRange,
+            }),
+        });
+        console.log(`[summarization] Created new summary for session ${session.id}`);
+    } else {
+        await fetch(`${MEMORY_URL}/summaries/${latest.id}`, {
+            method: 'PATCH',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({
+                content,
+                tokenCount: totalEpisodeTokens,
+                episodeRange,
+            }),
+        });
+        console.log(`[summarization] Updated summary ${latest.id} for session ${session.id}`);
+    }
+}
+
+async function triggerSummary(session, allEpisodes) {
+    // Intentionally fire-and-forget — caller doesn't await this
+    maybeSummarize(session, allEpisodes).catch(err =>
+        console.warn('[summarization] Summary failed (non-critical):', err.message)
+    );
+}
+
+module.exports = { triggerSummary };

packages/shared/src/config/constants.js

@@ -69,6 +69,11 @@ const SQLITE = {
     DEFAULT_PATH: './data/nexusai.db'
 }
 
+const SUMMARIES = {
+    THRESHOLD_TOKENS:   5000,   //trigger summary when session hits this many tokens
+    MAX_SUMMARY_TOKENS: 800,    //if existing summary exceeds this, create new instead of update
+    MIN_EPISODES_SINCE: 5,      // don't resummarize until N new episodes since last summary
+}
 module.exports = {
     QDRANT,
     COLLECTIONS,
@@ -79,5 +84,6 @@ module.exports = {
     LLAMACPP,
     INFERENCE_DEFAULTS,
     SQLITE,
-    ORCHESTRATION
+    ORCHESTRATION,
+    SUMMARIES
 };

packages/shared/src/index.js

@@ -1,5 +1,5 @@
 const {getEnv} = require('./config/env');
-const {QDRANT, COLLECTIONS, EPISODIC, SERVICES, OLLAMA, PORTS, LLAMACPP, INFERENCE_DEFAULTS, SQLITE, ORCHESTRATION } = require('./config/constants');
+const {QDRANT, COLLECTIONS, EPISODIC, SERVICES, OLLAMA, PORTS, LLAMACPP, INFERENCE_DEFAULTS, SQLITE, ORCHESTRATION, SUMMARIES } = require('./config/constants');
 const {parseRow, formatEpisodeText} = require('./utils')
 
 module.exports = {
@@ -16,4 +16,5 @@ module.exports = {
     ORCHESTRATION,
     parseRow,
     formatEpisodeText,
+    SUMMARIES,
 };