feat(kb/ask): live SSE streaming of Shira's progress (v0.2.0)

User wanted to see what Shira is doing while she thinks — like Claude
does — instead of staring at an incrementing seconds counter. Now the
ask UI shows one line per agent step as it happens:

  3s  🧠  קוראת את השאלה
  4s  🔍  מחפשת בבסיס הידע: "תקנה 36"
  9s  ✓   נמצאו 5 קטעים רלוונטיים
 10s  🔍  מחפשת בבסיס הידע: "תקנה 36 ביטוח לאומי"
 14s  ✓   נמצאו 5 קטעים רלוונטיים
 15s  🧠  ממשיכה לחקור
 22s  ✍️  מנסחת תשובה
 → תשובה

Client wiring:
- runAsk now opens an EventSource at ?entryPoint=KnowledgeBaseAskStream
  instead of POSTing JSON. Each SSE event of type thinking/tool_start/
  tool_done/tool_error/writing appends a row to a stacked progress log.
  The final {type:answer,text,sources} event triggers renderAskAnswer
  with the existing split view. {type:error} surfaces via showError.
- Module-level state from v0.1.9 unchanged in spirit but now stores the
  EventSource + accumulated events. afterRender on view re-mount replays
  the entire event list and re-binds onmessage/onerror — the SSE
  connection itself doesn't drop because it lives at module scope.
- Elapsed-time pill stays for cadence but is decoration; the real
  signal is the per-event log.

EspoCRM proxy:
- New EntryPoint KnowledgeBaseAskStream — required because EventSource
  is GET-only and ?message= must come via the URL. PHP buffering is
  disabled (zlib + ob + apache_setenv no-gzip), Apache headers are set
  for SSE (no-cache, X-Accel-Buffering: no), and we cURL into
  shira-hermes /kb/ask/stream with CURLOPT_WRITEFUNCTION echoing each
  byte and flushing immediately. The handler ends with exit; to bypass
  EspoCRM's Response wrapper which would otherwise emit headers/body
  on top of our raw stream.
- KnowledgeBaseService gained two public accessors (getStreamingUrl,
  getStreamingApiKey) so the EntryPoint can build the cURL without
  going through request() (which buffers the whole body).
- entryPoints.json registers the new class.

Server (shira-hermes 76fd77f):
- AgentRunner.run accepts an on_event sync callback fired before each
  LLM call (thinking) and around each tool call (tool_start, tool_done,
  tool_error). Hebrew labels in agent_runner._tool_label / _tool_done_label
  ship over the wire ready-to-display — keeps the client free of
  translation concerns.
- POST /kb/ask/stream wraps the existing agent runner in an asyncio
  task feeding an asyncio.Queue, returns StreamingResponse with proper
  SSE headers (X-Accel-Buffering, Cache-Control). 15s comment-line
  heartbeats keep the connection open through proxy idle-timeouts.
- Original POST /kb/ask still works — additive change.

Refs Task Master #8

.taskmaster/tasks/tasks.json

@@ -5,7 +5,7 @@
         "id": 1,
         "title": "feat: search-mode split-view with PDF + page jump",
         "description": "Render /kb/search results as a two-column split view: left column is the stack of ranked hit cards (kind, title, section, page label), right column is an iframe viewing the selected hit's PDF scrolled to page_number. Clicking any hit swaps the iframe. Text-only sources (law from Wikisource) fall back to a chunk/text panel with a Wikisource link so the right column never 404s.",
-        "status": "in-progress",
+        "status": "done",
         "priority": "high",
         "details": "Before this change renderSearchResults produced plain vertical text cards — users got the chunk body and had to open the Wikisource link (or track down the PDF manually) to verify context. With 5 of 5 PDFs now carrying accurate page_number (shira-hermes e534709 + 1ca1cc0), the search UI can finally deep-link to the right page. Mirrors the ask-mode split view (v0.1.7 uncommitted).",
         "testStrategy": "Search 'תקנה 37' → first hit should be a regulation/circular → right pane loads the PDF at page ~N where the section appears. Click a lower-ranked law hit → right pane swaps to a Wikisource link view. Search 'הגדרות' → hits span multiple sources → each click swaps iframe source.",
@@ -24,11 +24,83 @@
         "subtasks": [],
         "dependencies": [],
         "createdAt": "2026-04-24T15:47:00Z"
+      },
+      {
+        "id": 3,
+        "title": "feat(kb/search): LLM query expansion so ranked-by-title docs don't crowd everything else out (shira-hermes)",
+        "description": "User reports searching 'מהי תקנה 37' returns only the תקנה 37 circular and the law — never ספר הליקויים, even though that's where the underlying medical content lives. Root cause is a single-shot retrieval where any document whose title contains the query terms wins by a huge margin. Fix: ask the LLM (via ai-gateway) for up to 3 alternative phrasings, retrieve candidates for the original + each variant in parallel, merge by chunk_id keeping best RRF score, then rerank the union against the ORIGINAL query. After fix: src 29 (ספר הליקויים) shows up with 2 hits in the same query.",
+        "status": "done",
+        "priority": "high",
+        "details": "Lives in espocrm-extensions/shira-hermes commit 1441a41. /kb/search now has expand=true by default, agent path (search_insurance_kb tool) keeps expand=false because the agent already does multi-query via tool calls.",
+        "testStrategy": "POST /kb/search {query:'מהי תקנה 37', top_k:8} should return hits from at least 2 distinct source_ids, including src 29 (ספר הליקויים) and src 26 (תקנה 37 חוזר).",
+        "subtasks": [],
+        "dependencies": [],
+        "createdAt": "2026-04-25T10:00:00Z"
+      },
+      {
+        "id": 8,
+        "title": "feat(kb/ask): SSE streaming with live agent progress",
+        "description": "User wanted Shira's progress to be visible while she thinks — like Claude does — instead of just an incrementing seconds counter. Implementation: AgentRunner.run accepts an optional sync on_event callback that emits {type, label, ...} dicts at each agent step. New POST /kb/ask/stream returns text/event-stream, with the runner running in an asyncio task whose events feed an asyncio.Queue that the response generator drains as SSE. Client opens EventSource against a new EspoCRM EntryPoint KnowledgeBaseAskStream that proxies the SSE bytes through cURL with output buffering disabled (echo + flush + exit, bypassing the framework Response). The progress UI now stacks one line per event (thinking, tool_start with the query Shira chose, tool_done with the chunk count, writing) instead of just a seconds counter. v0.1.9 _activeAsk persistence pattern preserved — events accumulate at module scope so a view switch + return replays the live log.",
+        "status": "done",
+        "priority": "high",
+        "details": "shira-hermes 76fd77f. EspoCRM EntryPoint registered in metadata/app/entryPoints.json. Hebrew labels live in agent_runner._tool_label / _tool_done_label so the wire format already carries display-ready strings (no client-side mapping). 15s heartbeats keep the connection open through proxy idle-timeouts.",
+        "testStrategy": "curl -N POST /kb/ask/stream {message:'מהי תקנה 36'} should produce data: lines with thinking → tool_start (with query) → tool_done (with chunk count) → ... → writing → answer. Browser EventSource should drive the same flow into the UI.",
+        "subtasks": [],
+        "dependencies": [],
+        "createdAt": "2026-04-25T13:00:00Z"
+      },
+      {
+        "id": 7,
+        "title": "fix: search preview duplicates left card for text sources",
+        "description": "User report: searching the law (Wikisource source 5) shows the same chunk content in both the left list-card and the right preview pane. The preview adds zero value when the matched source has no PDF — both panes are visually identical (modulo the left's 14em truncation), which reads as a bug. Fixed by fetching the matched chunk plus K=2 surrounding sections from /kb/source/{id}/chunks?around=N&ctx=2 and rendering them stacked: matched section is highlighted with a yellow header (#fff3cd), neighbors render as muted context blocks above and below. Adds a prominent 'פתח ב-Wikisource' button in the panel header, scrolls the matched section into view on render. Race-safe via _previewToken so a quick second click doesn't render stale results.",
+        "status": "done",
+        "priority": "high",
+        "details": "shira-hermes b127caf added chunk_index to /kb/search hits + an `around`/`ctx` query param to /source/{id}/chunks. Espo controller passes them through. Client uses the new fields in showSearchPreview when the hit is a text source.",
+        "testStrategy": "Search 'מהי תקנה 36'; click the law-kind hit. Right pane: yellow-highlighted ס' 36 in the middle, ס' 35 above (muted), ס' 37 below (muted), Wikisource button in header. Click the תקנה 37 חוזר hit: right pane swaps to PDF iframe at the cited page (PDF path unchanged).",
+        "subtasks": [],
+        "dependencies": [],
+        "createdAt": "2026-04-25T12:30:00Z"
+      },
+      {
+        "id": 5,
+        "title": "feat(kb): drag-to-resize splitter (both ask + search)",
+        "description": "Replace the fixed Bootstrap col-md-5/7 split with a flex layout containing a 6px drag handle. mousedown on the handle starts the drag; while dragging an invisible full-screen overlay covers any iframe so the PDF.js viewer doesn't swallow mouse events. The chosen ratio (15-85%) persists to localStorage as kb-split-pct so the layout sticks across sessions. Both modes share the same _buildSplitShell helper so the look stays consistent.",
+        "status": "done",
+        "priority": "normal",
+        "details": "Default ratio = 42% left (matches the previous col-md-5 ≈ 41.66%). Applied to renderSearchResults, renderAskAnswer, and showSearchPreview (which now uses 100%-height containers via flex column).",
+        "testStrategy": "Open ask mode, drag the divider; verify PDF iframe doesn't lose mouse focus mid-drag; reload — divider stays at last position. Repeat in search mode.",
+        "subtasks": [],
+        "dependencies": [],
+        "createdAt": "2026-04-25T11:00:00Z"
+      },
+      {
+        "id": 6,
+        "title": "fix: search survives view switch (parity with ask in v0.1.9)",
+        "description": "Search mode had the same view-bound promise problem as ask did before v0.1.9: navigating to another EspoCRM screen and back blanked the results. Hoisted {query, kind, promise} to a module-level _activeSearch with the same {query, kind, hits, selectedIdx} sessionStorage replay we already built for ask. Selected hit index also persists so the right pane comes back to the same source/page the user had open.",
+        "status": "done",
+        "priority": "high",
+        "details": "Mirrors the v0.1.9 ask fix in _attachSearchHandlers + afterRender. Click handler updates _lastSearch.selectedIdx so a return-trip lands on the user's last-clicked hit, not always the top-ranked one.",
+        "testStrategy": "Search 'מהי תקנה 37'; click a result other than the first; navigate to Contacts; navigate back — same hit selected, same PDF page on the right.",
+        "subtasks": [],
+        "dependencies": [],
+        "createdAt": "2026-04-25T11:00:00Z"
+      },
+      {
+        "id": 4,
+        "title": "fix: ask survives view switch via module-level promise + sessionStorage",
+        "description": "User reports asking Shira a question and switching to a different EspoCRM view loses the in-flight request — coming back shows a blank screen as if nothing was asked. Cause: the Espo.Ajax promise was view-bound, so handlers fired against a detached DOM after re-mount. Fix: hoist {question, promise, startedAt} to a module-level _activeAsk; afterRender re-attaches handlers and resumes the progress UI with the original startedAt; completed answers persist to sessionStorage and replay on remount or a hard reload.",
+        "status": "done",
+        "priority": "high",
+        "details": "All client-side, files/client/custom/modules/knowledge-base/src/views/kb/index.js. State is intentionally session-scoped — kept in sessionStorage so the next browser session starts clean.",
+        "testStrategy": "Ask a question; while the spinner shows, click Contacts (or any other navbar item); wait until the request would have finished; click back to בסיס ידע — the answer (or active spinner with correct elapsed-time) should be there.",
+        "subtasks": [],
+        "dependencies": [],
+        "createdAt": "2026-04-25T10:00:00Z"
       }
     ],
     "metadata": {
       "created": "2026-04-24T15:47:00Z",
-      "updated": "2026-04-24T15:47:00Z",
+      "updated": "2026-04-25T10:30:00Z",
       "description": "KnowledgeBase extension tasks"
     }
   }

files/client/custom/modules/knowledge-base/src/views/kb/index.js

@@ -1,5 +1,42 @@
 define('modules/knowledge-base/views/kb/index', ['view'], function (Dep) {
 
+    // Module-level state survives view unmount/remount within a single
+    // SPA session so a user can fire an ask, navigate elsewhere, and come
+    // back to the answer (or to the still-spinning request) without losing
+    // it. sessionStorage backs the last completed answer so a hard reload
+    // also recovers it. None of this leaks to the next browser session —
+    // ask history is intentionally ephemeral.
+    let _activeAsk = null;     // {question, promise, startedAt} while in flight
+    let _lastAsk = null;       // {question, text, sources, completedAt} after success
+    let _activeSearch = null;  // {query, kind, promise} while in flight
+    let _lastSearch = null;    // {query, kind, hits, selectedIdx, completedAt}
+
+    const SS_ASK = 'kb-last-ask';
+    const SS_SEARCH = 'kb-last-search';
+    const LS_SPLIT = 'kb-split-pct';   // long-lived UI preference (not session)
+
+    function _loadJson(storage, key, validator) {
+        try {
+            const raw = storage.getItem(key);
+            if (!raw) return null;
+            const parsed = JSON.parse(raw);
+            return validator(parsed) ? parsed : null;
+        } catch (e) { return null; }
+    }
+    function _saveJson(storage, key, value) {
+        try { storage.setItem(key, JSON.stringify(value)); }
+        catch (e) { /* quota or disabled, fine */ }
+    }
+    function _clear(storage, key) {
+        try { storage.removeItem(key); } catch (e) { /* ignore */ }
+    }
+    if (!_lastAsk) {
+        _lastAsk = _loadJson(sessionStorage, SS_ASK, x => x && typeof x.question === 'string');
+    }
+    if (!_lastSearch) {
+        _lastSearch = _loadJson(sessionStorage, SS_SEARCH, x => x && typeof x.query === 'string' && Array.isArray(x.hits));
+    }
+
     return Dep.extend({
 
         template: 'knowledge-base:kb/index',
@@ -68,6 +105,40 @@ define('modules/knowledge-base/views/kb/index', ['view'], function (Dep) {
             } else if (this._sources) {
                 this.renderSourcesList();
             }
+
+            // Recover prior state across view remounts (user navigated away and
+            // back). Active in-flight wins; otherwise replay the last result
+            // from sessionStorage so the work the user already did doesn't
+            // disappear behind a tab switch.
+            if (this.mode === 'ask') {
+                if (_activeAsk) {
+                    const $input = this.$el.find('input[data-name="query"]');
+                    if ($input.length) $input.val(_activeAsk.question);
+                    this.setLoading(true);
+                    // Pass the whole ask so startAskProgress can replay the
+                    // accumulated event log into the freshly-rendered DOM.
+                    this.startAskProgress(_activeAsk);
+                    this._attachAskHandlers(_activeAsk);
+                } else if (_lastAsk) {
+                    const $input = this.$el.find('input[data-name="query"]');
+                    if ($input.length) $input.val(_lastAsk.question);
+                    this.renderAskAnswer(_lastAsk.text, _lastAsk.sources);
+                }
+            } else if (this.mode === 'search') {
+                if (_activeSearch) {
+                    const $input = this.$el.find('input[data-name="query"]');
+                    if ($input.length) $input.val(_activeSearch.query);
+                    this.setLoading(true);
+                    this._attachSearchHandlers(_activeSearch);
+                } else if (_lastSearch && _lastSearch.hits.length) {
+                    const $input = this.$el.find('input[data-name="query"]');
+                    if ($input.length) $input.val(_lastSearch.query);
+                    const $kind = this.$el.find('select[data-name="kind"]');
+                    if ($kind.length && _lastSearch.kind) $kind.val(_lastSearch.kind);
+                    this.renderSearchResults(_lastSearch.hits, _lastSearch.selectedIdx || 0);
+                }
+            }
+
             // Focus the input on every render so users can start typing right away.
             const $input = this.$el.find('input[data-name="query"]');
             if ($input.length) $input.trigger('focus');
@@ -87,75 +158,220 @@ define('modules/knowledge-base/views/kb/index', ['view'], function (Dep) {
         },
 
         runSearch: function (query, kind) {
+            // A new search invalidates the prior cached one.
+            _lastSearch = null;
+            _clear(sessionStorage, SS_SEARCH);
+
             this.setLoading(true);
-            Espo.Ajax.postRequest('KnowledgeBase/action/search', {
+            const promise = Espo.Ajax.postRequest('KnowledgeBase/action/search', {
                 query: query,
                 kind: kind,
                 topK: 8,
-            }).then(res => {
-                this.setLoading(false);
-                this.renderSearchResults(res.hits || []);
+            });
+            _activeSearch = {query: query, kind: kind, promise: promise};
+            this._attachSearchHandlers(_activeSearch);
+        },
+
+        _attachSearchHandlers: function (search) {
+            const self = this;
+            search.promise.then(res => {
+                const hits = res.hits || [];
+                const entry = {
+                    query: search.query,
+                    kind: search.kind,
+                    hits: hits,
+                    selectedIdx: 0,
+                    completedAt: Date.now(),
+                };
+                _lastSearch = entry;
+                _saveJson(sessionStorage, SS_SEARCH, entry);
+                if (_activeSearch === search) _activeSearch = null;
+                if (self.$el && self.$el.length) {
+                    self.setLoading(false);
+                    if (self.mode === 'search') {
+                        self.renderSearchResults(hits);
+                    }
+                }
             }).catch(err => {
-                this.setLoading(false);
-                this.showError(err);
+                if (_activeSearch === search) _activeSearch = null;
+                if (self.$el && self.$el.length) {
+                    self.setLoading(false);
+                    self.showError(err);
+                }
             });
         },
 
         runAsk: function (message) {
+            // A new ask invalidates whatever last-result was on screen.
+            _lastAsk = null;
+            _clear(sessionStorage, SS_ASK);
+
             this.setLoading(true);
-            this.startAskProgress();
-            // Ask goes through the full agent loop (search + rerank + LLM),
-            // which routinely takes 30-90s. The default jQuery Ajax timeout
-            // is too short; override it here so the browser doesn't give up
-            // before shira-hermes responds.
-            Espo.Ajax.postRequest('KnowledgeBase/action/ask', {
-                message: message,
-            }, {timeout: 240000}).then(res => {
-                this.stopAskProgress();
-                this.setLoading(false);
-                this.renderAskAnswer(res.text || '', res.sources || []);
-            }).catch(err => {
-                this.stopAskProgress();
-                this.setLoading(false);
-                this.showError(err);
-            });
+            // Streaming via Server-Sent Events. The browser opens an
+            // EventSource against KnowledgeBaseAskStream which proxies
+            // /kb/ask/stream on shira-hermes; one SSE event per agent step
+            // (thinking, tool_start, tool_done) plus a final answer event.
+            const url = '?entryPoint=KnowledgeBaseAskStream&message='
+                + encodeURIComponent(message);
+            const es = new EventSource(url);
+            _activeAsk = {
+                question: message,
+                es: es,
+                events: [],
+                startedAt: Date.now(),
+            };
+            this.startAskProgress(_activeAsk);
+            this._attachAskHandlers(_activeAsk);
         },
 
-        startAskProgress: function () {
-            // Show a live elapsed-time indicator so users know the request
-            // is still running rather than stuck. Typical answers arrive in
-            // 30-90s; we warn after 2 minutes.
+        // Wire SSE handlers on a (possibly module-level) ask. Called from
+        // runAsk for the initial bind and from afterRender when the user
+        // navigates back to the KB view while an earlier stream is still
+        // open. The EventSource itself lives at module scope (in _activeAsk)
+        // so handlers can be re-bound without dropping the connection.
+        _attachAskHandlers: function (ask) {
+            const self = this;
+            ask.es.onmessage = function (msgEvent) {
+                let data;
+                try { data = JSON.parse(msgEvent.data); }
+                catch (e) {
+                    console.warn('KB: malformed SSE payload', e);
+                    return;
+                }
+                if (data.type === 'answer') {
+                    self._finishAsk(ask, {
+                        question: ask.question,
+                        text: data.text || '',
+                        sources: data.sources || [],
+                        completedAt: Date.now(),
+                    });
+                } else if (data.type === 'error') {
+                    self._failAsk(ask, data.message || 'שגיאה בשרת');
+                } else {
+                    // Status event — record it and append to the live log.
+                    ask.events.push(Object.assign({_clientTs: Date.now()}, data));
+                    if (self.$el && self.$el.length && self.mode === 'ask') {
+                        self._appendAskEvent(ask, ask.events[ask.events.length - 1]);
+                    }
+                }
+            };
+            ask.es.onerror = function () {
+                // Don't tear down on transient blips while the answer is
+                // already arriving; only treat it as a hard failure if no
+                // answer has been delivered.
+                if (ask._completed) return;
+                self._failAsk(ask, 'הזרם נסגר לפני שהגיעה תשובה');
+            };
+        },
+
+        _finishAsk: function (ask, entry) {
+            ask._completed = true;
+            try { ask.es.close(); } catch (e) { /* ignore */ }
+            _lastAsk = entry;
+            _saveJson(sessionStorage, SS_ASK, entry);
+            if (_activeAsk === ask) _activeAsk = null;
+            if (this.$el && this.$el.length) {
+                this.stopAskProgress();
+                this.setLoading(false);
+                if (this.mode === 'ask') {
+                    this.renderAskAnswer(entry.text, entry.sources);
+                }
+            }
+        },
+
+        _failAsk: function (ask, message) {
+            try { ask.es.close(); } catch (e) { /* ignore */ }
+            if (_activeAsk === ask) _activeAsk = null;
+            if (this.$el && this.$el.length) {
+                this.stopAskProgress();
+                this.setLoading(false);
+                this.showError(new Error(message));
+            }
+        },
+
+        startAskProgress: function (askOrStartedAt) {
+            // Render a live progress panel: a "thinking" header with elapsed
+            // time, plus a stacked log of the events Shira's emitted so far
+            // (one line per LLM step / tool call). `askOrStartedAt` is
+            // either the active-ask object (from runAsk and afterRender) or
+            // a bare timestamp (legacy call sites). Re-mounting on view
+            // switch replays the accumulated event list from ask.events.
             if (this.mode !== 'ask') return;
+            this.stopAskProgress();
+            let ask = null;
+            let startedAt;
+            if (askOrStartedAt && typeof askOrStartedAt === 'object') {
+                ask = askOrStartedAt;
+                startedAt = ask.startedAt || Date.now();
+            } else {
+                startedAt = askOrStartedAt || Date.now();
+            }
+
             const $results = this.$el.find('.kb-results');
             $results.html(
                 '<div class="kb-ask-progress panel panel-info">' +
                 '  <div class="panel-body" style="direction:rtl;text-align:right;">' +
-                '    <i class="fas fa-circle-notch fa-spin" style="margin-left:8px;"></i>' +
-                '    <strong>שירה חושבת…</strong>' +
-                '    <div class="small text-muted" style="margin-top:6px;">' +
-                '      שירה מחפשת בבסיס הידע, מסכמת ומציגה ציטוטים מדויקים.' +
-                '      זה יכול לקחת בין 30 ל-90 שניות.' +
-                '    </div>' +
-                '    <div class="small" style="margin-top:10px;">' +
-                '      <span>זמן שעבר: </span>' +
-                '      <span class="kb-elapsed">0</span>' +
-                '      <span> שניות</span>' +
+                '    <div style="display:flex;align-items:center;gap:8px;margin-bottom:10px;">' +
+                '      <i class="fas fa-circle-notch fa-spin"></i>' +
+                '      <strong>שירה חושבת</strong>' +
+                '      <span class="text-muted small kb-elapsed-pill" ' +
+                          'style="margin-right:auto;font-variant-numeric:tabular-nums;">0 שניות</span>' +
                 '    </div>' +
+                '    <div class="kb-events" style="' +
+                       'border-top:1px solid #d8e0e8;padding-top:8px;' +
+                       'max-height:60vh;overflow-y:auto;font-size:0.95em;"></div>' +
                 '  </div>' +
                 '</div>'
             );
-            const startedAt = Date.now();
-            this._askTimer = setInterval(() => {
+
+            // Replay any events already collected (matters when the user
+            // navigates away mid-think and comes back to a still-streaming
+            // ask — the stream kept going at module scope, but the DOM was
+            // freshly re-rendered).
+            if (ask && Array.isArray(ask.events)) {
+                ask.events.forEach(ev => this._appendAskEvent(ask, ev));
+            }
+
+            const tick = () => {
                 const sec = Math.round((Date.now() - startedAt) / 1000);
-                const $elapsed = this.$el.find('.kb-elapsed');
-                if ($elapsed.length) $elapsed.text(sec);
-                if (sec === 120) {
-                    this.$el.find('.kb-ask-progress .panel-body').append(
-                        '<div class="alert alert-warning" style="margin-top:10px;">' +
-                        'לוקח יותר זמן מהרגיל. עדיין ממתינים…</div>'
-                    );
-                }
-            }, 1000);
+                this.$el.find('.kb-elapsed-pill').text(sec + ' שניות');
+            };
+            tick();
+            this._askTimer = setInterval(tick, 1000);
+        },
+
+        _appendAskEvent: function (ask, ev) {
+            const $events = this.$el.find('.kb-events');
+            if (!$events.length) return;
+            const startedAt = (ask && ask.startedAt) || Date.now();
+            const ts = ev._clientTs || Date.now();
+            const sec = Math.max(0, Math.round((ts - startedAt) / 1000));
+            const icon = {
+                thinking: '🧠',
+                tool_start: '🔍',
+                tool_done: '✓',
+                tool_error: '⚠',
+                writing: '✍️',
+            }[ev.type] || '·';
+            const colour = {
+                thinking: '#475569',
+                tool_start: '#0f5298',
+                tool_done: '#1e6f40',
+                tool_error: '#a02622',
+                writing: '#5a3a91',
+            }[ev.type] || '#475569';
+            const label = this.escape(ev.label || ev.type);
+            const row = $(
+                '<div style="padding:3px 0;color:' + colour + ';display:flex;gap:8px;align-items:flex-start;">' +
+                '  <span style="display:inline-block;min-width:40px;color:#94a3b8;font-variant-numeric:tabular-nums;">' +
+                       sec + 'ש</span>' +
+                '  <span style="margin:0 2px;">' + icon + '</span>' +
+                '  <span style="flex:1 1 auto;word-break:break-word;">' + label + '</span>' +
+                '</div>'
+            );
+            $events.append(row);
+            // Always keep the latest line visible.
+            $events.scrollTop($events[0].scrollHeight);
         },
 
         stopAskProgress: function () {
@@ -165,12 +381,13 @@ define('modules/knowledge-base/views/kb/index', ['view'], function (Dep) {
             }
         },
 
-        renderSearchResults: function (hits) {
+        renderSearchResults: function (hits, selectedIdx) {
             const $results = this.$el.find('.kb-results');
             if (!hits.length) {
                 $results.html('<div class="text-muted">לא נמצאו תוצאות.</div>');
                 return;
             }
+            const initialIdx = (typeof selectedIdx === 'number' && hits[selectedIdx]) ? selectedIdx : 0;
             const kindHe = {law: 'חוק', regulation: 'תקנה', circular: 'חוזר'};
             const self = this;
 
@@ -188,7 +405,7 @@ define('modules/knowledge-base/views/kb/index', ['view'], function (Dep) {
                 const pub = h.published_at ? ' · פורסם ' + h.published_at : '';
                 const pageLabel = (isPdfBacked(h) && h.page_number)
                     ? ` · <span class="label label-default">עמ׳ ${h.page_number}</span>` : '';
-                const activeClass = i === 0 ? 'panel-primary' : 'panel-default';
+                const activeClass = i === initialIdx ? 'panel-primary' : 'panel-default';
                 return `
                     <div class="kb-hit panel ${activeClass}" data-hit-idx="${i}"
                          style="margin-bottom:8px;cursor:pointer;">
@@ -201,20 +418,15 @@ define('modules/knowledge-base/views/kb/index', ['view'], function (Dep) {
                     </div>`;
             }).join('');
 
-            $results.html(`
-                <div class="row" style="margin:0;">
-                  <div class="col-md-5" style="padding-right:0;max-height:86vh;overflow-y:auto;">
-                    ${listHtml}
-                  </div>
-                  <div class="col-md-7 kb-search-preview" style="padding-left:0;">
-                    <div class="kb-preview-slot"></div>
-                  </div>
-                </div>
-            `);
+            $results.html(this._buildSplitShell({
+                leftHtml: `<div class="kb-search-list" style="height:100%;overflow-y:auto;padding-left:6px;">${listHtml}</div>`,
+                rightHtml: '<div class="kb-preview-slot" style="height:100%;"></div>',
+            }));
+            this._wireSplitter($results.find('.kb-split'));
 
             // Cache hits on the view so click handlers can reach them.
             this._searchHits = hits;
-            this.showSearchPreview(0);
+            this.showSearchPreview(initialIdx);
 
             this.$el.find('.kb-hit').off('click').on('click', function () {
                 const idx = parseInt($(this).data('hit-idx'), 10);
@@ -223,6 +435,90 @@ define('modules/knowledge-base/views/kb/index', ['view'], function (Dep) {
                     .removeClass('panel-primary').addClass('panel-default');
                 $(this).removeClass('panel-default').addClass('panel-primary');
                 self.showSearchPreview(idx);
+                if (_lastSearch && _lastSearch.hits === self._searchHits) {
+                    _lastSearch.selectedIdx = idx;
+                    _saveJson(sessionStorage, SS_SEARCH, _lastSearch);
+                }
+            });
+        },
+
+        // Returns the HTML for a flex-row split layout with a draggable
+        // 6px handle. The container's flex direction is forced LTR so the
+        // splitter math (clientX) doesn't get inverted by RTL — content
+        // inside each pane keeps its own direction.
+        _buildSplitShell: function ({leftHtml, rightHtml}) {
+            const pct = this._loadSplitPct();
+            return (
+                '<div class="kb-split" style="' +
+                  'display:flex;flex-direction:row;direction:ltr;' +
+                  'gap:0;height:86vh;align-items:stretch;">' +
+                '  <div class="kb-split-left" style="' +
+                       'flex:0 0 ' + pct + '%;min-width:200px;overflow:hidden;">' +
+                       leftHtml +
+                '  </div>' +
+                '  <div class="kb-split-handle" title="גרור כדי לשנות חלוקה" style="' +
+                       'flex:0 0 6px;background:#dde1e7;cursor:col-resize;' +
+                       'border-left:1px solid #cbd0d8;border-right:1px solid #cbd0d8;' +
+                       'transition:background 0.15s;"></div>' +
+                '  <div class="kb-split-right" style="' +
+                       'flex:1 1 auto;min-width:200px;overflow:hidden;">' +
+                       rightHtml +
+                '  </div>' +
+                '</div>'
+            );
+        },
+
+        _loadSplitPct: function () {
+            try {
+                const v = parseFloat(localStorage.getItem(LS_SPLIT));
+                if (!isNaN(v) && v >= 15 && v <= 85) return v;
+            } catch (e) { /* ignore */ }
+            return 42;
+        },
+
+        _saveSplitPct: function (pct) {
+            try { localStorage.setItem(LS_SPLIT, String(pct)); }
+            catch (e) { /* ignore */ }
+        },
+
+        // Wires mousedown/move/up on the handle to resize the left pane.
+        // While dragging we cover any iframe with a transparent overlay so
+        // mouse events don't disappear into PDF.js. On mouseup the chosen
+        // ratio persists to localStorage.
+        _wireSplitter: function ($split) {
+            if (!$split.length) return;
+            const $handle = $split.find('.kb-split-handle');
+            const $left = $split.find('.kb-split-left');
+            const self = this;
+            $handle.on('mouseenter', () => $handle.css('background', '#b9c0cb'));
+            $handle.on('mouseleave', () => $handle.css('background', '#dde1e7'));
+            $handle.on('mousedown', function (e) {
+                e.preventDefault();
+                const rect = $split[0].getBoundingClientRect();
+                const $overlay = $('<div class="kb-drag-overlay">').css({
+                    position: 'fixed',
+                    inset: '0',
+                    cursor: 'col-resize',
+                    zIndex: 9999,
+                    background: 'transparent',
+                });
+                $('body').append($overlay).css('user-select', 'none');
+                const onMove = function (ev) {
+                    const x = ev.clientX - rect.left;
+                    let pct = (x / rect.width) * 100;
+                    pct = Math.max(15, Math.min(85, pct));
+                    $left.css('flex', '0 0 ' + pct + '%');
+                    self._dragPct = pct;
+                };
+                const onUp = function () {
+                    $(document).off('mousemove', onMove).off('mouseup', onUp);
+                    $overlay.remove();
+                    $('body').css('user-select', '');
+                    if (typeof self._dragPct === 'number') {
+                        self._saveSplitPct(self._dragPct);
+                    }
+                };
+                $(document).on('mousemove', onMove).on('mouseup', onUp);
             });
         },
 
@@ -239,34 +535,126 @@ define('modules/knowledge-base/views/kb/index', ['view'], function (Dep) {
                     + encodeURIComponent(h.source_id)
                     + '#page=' + encodeURIComponent(page);
                 $slot.html(`
-                    <div style="direction:rtl;text-align:right;margin-bottom:6px;">
-                      <span class="text-muted small">מציג עמ׳ ${page} של המסמך</span>
+                    <div style="display:flex;flex-direction:column;height:100%;">
+                      <div style="direction:rtl;text-align:right;margin-bottom:6px;flex:0 0 auto;">
+                        <span class="text-muted small">מציג עמ׳ ${page} של המסמך</span>
+                      </div>
+                      <iframe class="kb-pdf-iframe" src="${url}"
+                              style="flex:1 1 auto;width:100%;border:1px solid #ddd;background:#fafafa;"
+                              title="מקור"></iframe>
                     </div>
-                    <iframe class="kb-pdf-iframe"
-                            src="${url}"
-                            style="width:100%;height:82vh;border:1px solid #ddd;background:#fafafa;"
-                            title="מקור"></iframe>
                 `);
                 return;
             }
 
-            // Text source (law from Wikisource) — show the full chunk content
-            // and a link to the public source page.
+            // Text source (law from Wikisource): fetch the matched chunk +
+            // surrounding sections so the preview pane shows context, not a
+            // copy of what's already in the left card. While loading, show a
+            // placeholder; on failure fall back to the chunk-only view.
+            this._renderSectionContextPlaceholder(h);
+            const token = this._previewToken;
+            const sourceId = h.source_id;
+            const around = (typeof h.chunk_index === 'number') ? h.chunk_index : null;
+            if (sourceId == null || around == null) {
+                this._renderSectionContextSingle(h);
+                return;
+            }
+            const self = this;
+            Espo.Ajax.getRequest('KnowledgeBase/action/chunks', {
+                sourceId: sourceId,
+                around: around,
+                ctx: 2,
+            }).then(res => {
+                // Bail if user has clicked a different hit while we were waiting.
+                if (self._previewToken !== token) return;
+                self._renderSectionContext(h, res && res.chunks ? res.chunks : []);
+            }).catch(err => {
+                console.warn('KB: section-window fetch failed', err);
+                if (self._previewToken === token) self._renderSectionContextSingle(h);
+            });
+        },
+
+        _renderSectionContextPlaceholder: function (h) {
+            this._previewToken = (this._previewToken || 0) + 1;
+            const $slot = this.$el.find('.kb-preview-slot');
+            const title = this.escape(h.title || '');
+            $slot.html(
+                '<div class="panel panel-default" style="direction:rtl;text-align:right;height:100%;display:flex;flex-direction:column;">' +
+                '  <div class="panel-heading" style="flex:0 0 auto;">' + title +
+                '    <span class="text-muted small" style="margin-right:8px;">— טוען הקשר…</span>' +
+                '  </div>' +
+                '  <div class="panel-body" style="flex:1 1 auto;overflow-y:auto;">' +
+                '    <i class="fas fa-circle-notch fa-spin"></i>' +
+                '  </div>' +
+                '</div>'
+            );
+        },
+
+        _renderSectionContextSingle: function (h) {
+            // Fallback when we can't fetch the window — render just the
+            // matched chunk, which is at least the full section for the
+            // statute chunker (1 section = 1 chunk).
+            this._renderSectionContext(h, [{
+                chunk_index: h.chunk_index,
+                section_ref: h.section_ref || '',
+                heading_path: h.heading_path || '',
+                content: h.content || '',
+            }]);
+        },
+
+        _renderSectionContext: function (h, chunks) {
+            const $slot = this.$el.find('.kb-preview-slot');
             const bodyStyle =
                 'direction:rtl;unicode-bidi:plaintext;white-space:pre-wrap;' +
                 'font-family:"Segoe UI",Arial,sans-serif;line-height:1.7;text-align:right;';
             const srcLink = h.source_url
-                ? `<a href="${this.escape(h.source_url)}" target="_blank" rel="noopener">מקור ב-Wikisource</a>`
+                ? '<a href="' + this.escape(h.source_url) + '" target="_blank" rel="noopener" ' +
+                  'class="btn btn-xs btn-default" style="margin-right:6px;">' +
+                  '<i class="fas fa-external-link-alt"></i> פתח ב-Wikisource</a>'
                 : '';
-            $slot.html(`
-                <div class="panel panel-default" style="direction:rtl;text-align:right;">
-                  <div class="panel-heading">${this.escape(h.title || '')}</div>
-                  <div class="panel-body" style="${bodyStyle};max-height:80vh;overflow-y:auto;">
-                    ${this.escape(h.content || '')}
-                  </div>
-                  ${srcLink ? '<div class="panel-footer small">' + srcLink + '</div>' : ''}
-                </div>
-            `);
+            // The matched chunk is highlighted; siblings render as muted
+            // context blocks above and below so the user can read into the
+            // section without leaving the CRM.
+            const sectionsHtml = chunks.map(c => {
+                const isMatch = c.chunk_index === h.chunk_index;
+                const ref = c.section_ref || c.heading_path || '';
+                const headerStyle = isMatch
+                    ? 'background:#fff3cd;border-bottom:1px solid #ffe69c;color:#664d03;font-weight:600;'
+                    : 'background:#f5f5f7;border-bottom:1px solid #e7e7ea;color:#6c757d;';
+                return (
+                    '<div style="margin-bottom:12px;border:1px solid ' +
+                      (isMatch ? '#ffe69c' : '#e7e7ea') + ';border-radius:4px;overflow:hidden;">' +
+                    '  <div style="' + headerStyle + 'padding:6px 10px;direction:rtl;text-align:right;font-size:0.9em;">' +
+                         (isMatch ? 'התאמה — ' : '') + this.escape(ref) +
+                    '  </div>' +
+                    '  <div style="' + bodyStyle + ';padding:10px;">' +
+                         this.escape(c.content || '') +
+                    '  </div>' +
+                    '</div>'
+                );
+            }).join('');
+
+            $slot.html(
+                '<div class="panel panel-default" style="direction:rtl;text-align:right;height:100%;display:flex;flex-direction:column;">' +
+                '  <div class="panel-heading" style="flex:0 0 auto;display:flex;justify-content:space-between;align-items:center;">' +
+                '    <div><strong>' + this.escape(h.title || '') + '</strong>' +
+                '      <span class="text-muted small" style="margin-right:6px;">— הסעיף בהקשרו</span>' +
+                '    </div>' +
+                     srcLink +
+                '  </div>' +
+                '  <div class="panel-body" style="flex:1 1 auto;overflow-y:auto;background:#fafbfc;">' +
+                     sectionsHtml +
+                '  </div>' +
+                '</div>'
+            );
+
+            // Scroll the matched chunk into view inside the preview pane.
+            const $body = $slot.find('.panel-body');
+            const $match = $body.find('div[style*="#fff3cd"]').closest('div[style*="border-radius:4px"]');
+            if ($match.length && $body.length) {
+                const offset = $match.position().top - 20;
+                $body.scrollTop(Math.max(0, offset));
+            }
         },
 
         renderAskAnswer: function (text, sources) {
@@ -353,32 +741,32 @@ define('modules/knowledge-base/views/kb/index', ['view'], function (Dep) {
                 + encodeURIComponent(first.source_id)
                 + '#page=' + encodeURIComponent(firstPage);
 
-            $results.html(`
-                <div class="row" style="margin:0;">
-                  <div class="col-md-6" style="padding-right:0;">
-                    <div class="kb-answer panel panel-info">
-                      <div class="panel-body" style="direction:rtl;text-align:right;max-height:80vh;overflow-y:auto;">
-                        ${answerHtml}
-                      </div>
-                    </div>
-                    <div class="panel panel-default" style="direction:rtl;text-align:right;">
-                      <div class="panel-heading"><strong>📎 מקורות</strong></div>
-                      <div class="panel-body">
-                        <div style="margin-bottom:6px;">${pickerItems}</div>
-                        <div class="kb-page-links" style="font-size:0.9em;">
-                          <span class="text-muted">עמודים רלוונטיים:</span> ${pageLinks}
-                        </div>
-                      </div>
+            const leftHtml = `
+                <div style="height:100%;overflow-y:auto;padding-left:6px;">
+                  <div class="kb-answer panel panel-info">
+                    <div class="panel-body" style="direction:rtl;text-align:right;">
+                      ${answerHtml}
                     </div>
                   </div>
-                  <div class="col-md-6" style="padding-left:0;">
-                    <iframe class="kb-pdf-iframe"
-                            src="${initialUrl}"
-                            style="width:100%;height:86vh;border:1px solid #ddd;background:#fafafa;"
-                            title="מקור"></iframe>
+                  <div class="panel panel-default" style="direction:rtl;text-align:right;">
+                    <div class="panel-heading"><strong>📎 מקורות</strong></div>
+                    <div class="panel-body">
+                      <div style="margin-bottom:6px;">${pickerItems}</div>
+                      <div class="kb-page-links" style="font-size:0.9em;">
+                        <span class="text-muted">עמודים רלוונטיים:</span> ${pageLinks}
+                      </div>
+                    </div>
                   </div>
                 </div>
-            `);
+            `;
+            const rightHtml = `
+                <iframe class="kb-pdf-iframe"
+                        src="${initialUrl}"
+                        style="width:100%;height:100%;border:1px solid #ddd;background:#fafafa;"
+                        title="מקור"></iframe>
+            `;
+            $results.html(this._buildSplitShell({leftHtml, rightHtml}));
+            this._wireSplitter($results.find('.kb-split'));
 
             const self = this;
             this.$el.find('.kb-pdf-pick').off('click').on('click', function () {

files/custom/Espo/Modules/KnowledgeBase/Controllers/KnowledgeBase.php

@@ -73,7 +73,12 @@ class KnowledgeBase
             throw new BadRequest('sourceId (numeric) is required.');
         }
 
-        return $this->getService()->sourceChunks((int) $sourceId);
+        $around = $request->getQueryParam('around');
+        $ctx = $request->getQueryParam('ctx');
+        $aroundInt = ($around !== null && is_numeric($around)) ? (int) $around : null;
+        $ctxInt = ($ctx !== null && is_numeric($ctx)) ? (int) $ctx : 2;
+
+        return $this->getService()->sourceChunks((int) $sourceId, $aroundInt, $ctxInt);
     }
 
     public function postActionAsk(Request $request, Response $response): array

files/custom/Espo/Modules/KnowledgeBase/EntryPoints/KnowledgeBaseAskStream.php

@@ -0,0 +1,128 @@
+<?php
+
+namespace Espo\Modules\KnowledgeBase\EntryPoints;
+
+use Espo\Core\Api\Request;
+use Espo\Core\Api\Response;
+use Espo\Core\EntryPoint\EntryPoint;
+use Espo\Core\Exceptions\BadRequest;
+use Espo\Core\Exceptions\Error;
+use Espo\Core\Exceptions\Forbidden;
+use Espo\Core\InjectableFactory;
+use Espo\Entities\User;
+use Espo\Modules\KnowledgeBase\Services\KnowledgeBaseService;
+
+/**
+ * Streams Server-Sent Events from shira-hermes /kb/ask/stream to the
+ * browser's EventSource. The browser opens this with a GET (EventSource
+ * has no POST), passes the question via ?message=, and we forward it
+ * to shira-hermes with the firm-wide API key — the credential never
+ * leaves the EspoCRM server.
+ *
+ * Response is text/event-stream with no buffering. We bypass EspoCRM's
+ * Response wrapper entirely (echo + flush + exit) because the framework
+ * is wired for buffered JSON responses, not infinite streams.
+ *
+ * Access: `?entryPoint=KnowledgeBaseAskStream&message=<urlencoded>`
+ */
+class KnowledgeBaseAskStream implements EntryPoint
+{
+    public function __construct(
+        private InjectableFactory $injectableFactory,
+        private User $user,
+    ) {}
+
+    public function run(Request $request, Response $response): void
+    {
+        if ($this->user->isPortal()) {
+            throw new Forbidden('Portal users have no KB access.');
+        }
+
+        $message = $request->getQueryParam('message');
+        if (!is_string($message) || trim($message) === '') {
+            throw new BadRequest('message (string) is required.');
+        }
+        if (strlen($message) > 2000) {
+            throw new BadRequest('message is too long.');
+        }
+
+        $service = $this->injectableFactory->create(KnowledgeBaseService::class);
+        try {
+            $upstreamUrl = $service->getStreamingUrl('/kb/ask/stream');
+            $apiKey = $service->getStreamingApiKey();
+        } catch (\Throwable $e) {
+            throw new Error('SmartAssistant integration is not configured: ' . $e->getMessage());
+        }
+
+        // Disable PHP/Apache output buffering and compression so each SSE
+        // event flushes to the wire as soon as it arrives from upstream.
+        // Order matters: clean any open buffers BEFORE setting headers.
+        while (ob_get_level() > 0) {
+            @ob_end_clean();
+        }
+        @ini_set('zlib.output_compression', 'Off');
+        @ini_set('output_buffering', 'Off');
+        @ini_set('implicit_flush', '1');
+        if (function_exists('apache_setenv')) {
+            @apache_setenv('no-gzip', '1');
+        }
+
+        ignore_user_abort(false);
+        @set_time_limit(300);
+
+        header('Content-Type: text/event-stream; charset=utf-8');
+        header('Cache-Control: no-cache, no-transform');
+        header('X-Accel-Buffering: no');
+        header('Connection: keep-alive');
+        // Defense in depth: same locked-down CSP we use for the PDF entry.
+        header("Content-Security-Policy: default-src 'self'");
+
+        $payload = json_encode(['message' => $message], JSON_UNESCAPED_UNICODE);
+
+        $ch = curl_init();
+        curl_setopt_array($ch, [
+            CURLOPT_URL => $upstreamUrl,
+            CURLOPT_POST => true,
+            CURLOPT_POSTFIELDS => $payload,
+            CURLOPT_HTTPHEADER => [
+                'Content-Type: application/json',
+                'Accept: text/event-stream',
+                'X-Api-Key: ' . $apiKey,
+            ],
+            CURLOPT_RETURNTRANSFER => false,
+            CURLOPT_BUFFERSIZE => 1024,
+            CURLOPT_TIMEOUT => 300,
+            CURLOPT_CONNECTTIMEOUT => 10,
+            CURLOPT_WRITEFUNCTION => function ($ch, $data) {
+                if (connection_aborted()) {
+                    // Browser closed the EventSource — bail so cURL stops.
+                    return -1;
+                }
+                echo $data;
+                @ob_flush();
+                @flush();
+                return strlen($data);
+            },
+        ]);
+        $ok = curl_exec($ch);
+        $errno = curl_errno($ch);
+        $errmsg = curl_error($ch);
+        curl_close($ch);
+
+        if (!$ok && $errno !== 23 /* aborted by callback */) {
+            // Best effort: if upstream errored before any data was
+            // flushed, surface a final SSE error event so the client
+            // doesn't silently spin.
+            echo "data: " . json_encode(
+                ['type' => 'error', 'message' => 'upstream: ' . $errmsg],
+                JSON_UNESCAPED_UNICODE,
+            ) . "\n\n";
+            @ob_flush();
+            @flush();
+        }
+
+        // We've fully written the response. Bypass EspoCRM's Response
+        // emit() to avoid double-headers / extra buffering.
+        exit;
+    }
+}

files/custom/Espo/Modules/KnowledgeBase/Resources/metadata/app/entryPoints.json

@@ -1,5 +1,8 @@
 {
     "KnowledgeBasePdf": {
         "className": "Espo\\Modules\\KnowledgeBase\\EntryPoints\\KnowledgeBasePdf"
+    },
+    "KnowledgeBaseAskStream": {
+        "className": "Espo\\Modules\\KnowledgeBase\\EntryPoints\\KnowledgeBaseAskStream"
     }
 }

files/custom/Espo/Modules/KnowledgeBase/Services/KnowledgeBaseService.php

@@ -48,9 +48,13 @@ class KnowledgeBaseService
         return $this->get('/kb/sources');
     }
 
-    public function sourceChunks(int $sourceId): array
+    public function sourceChunks(int $sourceId, ?int $around = null, int $ctx = 2): array
     {
-        return $this->get('/kb/source/' . $sourceId . '/chunks');
+        $path = '/kb/source/' . $sourceId . '/chunks';
+        if ($around !== null) {
+            $path .= '?around=' . $around . '&ctx=' . $ctx;
+        }
+        return $this->get($path);
     }
 
     public function ask(string $message, ?string $conversationId, array $history): array
@@ -136,6 +140,25 @@ class KnowledgeBaseService
         return $data->apiKey ?? null;
     }
 
+    /**
+     * Public accessors so the streaming EntryPoint can build a cURL
+     * connection to shira-hermes without going through the JSON request()
+     * helper (which buffers the whole body).
+     */
+    public function getStreamingUrl(string $path): string
+    {
+        return rtrim($this->getBaseUrl(), '/') . $path;
+    }
+
+    public function getStreamingApiKey(): string
+    {
+        $key = $this->getApiKey();
+        if (!$key) {
+            throw new Error('SmartAssistant API key is not configured.');
+        }
+        return $key;
+    }
+
     private function get(string $path): array
     {
         return $this->request('GET', $path, null);

manifest.json

@@ -1,14 +1,14 @@
 {
     "name": "KnowledgeBase",
     "module": "KnowledgeBase",
-    "version": "0.1.8",
+    "version": "0.2.0",
     "acceptableVersions": [
         ">=8.0.0"
     ],
     "php": [
         ">=8.1"
     ],
-    "releaseDate": "2026-04-24",
+    "releaseDate": "2026-04-25",
     "author": "klear",
     "description": "Knowledge Base — Israeli National Insurance law, regulations, and circulars. Hybrid search + ask-shira, powered by shira-hermes KB."
 }