code-data-ark 2.0.6__tar.gz → 2.0.7__tar.gz

{code_data_ark-2.0.6 → code_data_ark-2.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-data-ark
-Version: 2.0.6
+Version: 2.0.7
 Summary: Code Data Ark — local observability and intelligence platform for VS Code + Copilot Chat sessions
 Project-URL: Homepage, https://github.com/goCosmix/cda
 Project-URL: Repository, https://github.com/goCosmix/cda.git

{code_data_ark-2.0.6 → code_data_ark-2.0.7}/cda/__init__.py

@@ -1,3 +1,3 @@
 """Code Data Ark — local observability and intelligence platform for VS Code + Copilot Chat sessions."""
 
-__version__ = "2.0.2"
+__version__ = "2.0.7"

{code_data_ark-2.0.6 → code_data_ark-2.0.7}/cda/kernel/pmf_kernel.py

@@ -421,6 +421,14 @@ class PMFKernel:
                         pass
                 time.sleep(0.25)
                 wait_seconds += 0.25
+            # Process didn't write its own pid file — write it now using the
+            # spawned process's PID so status checks work correctly.
+            if self._is_process_alive(proc.pid):
+                try:
+                    spec.pid_file.write_text(str(proc.pid))
+                    state["pid"] = proc.pid
+                except Exception:
+                    pass
 
         if spec.service_type == "daemon":
             state["status"] = "running"

{code_data_ark-2.0.6 → code_data_ark-2.0.7}/cda/ui/web.py

@@ -1008,7 +1008,7 @@ def get_overview():
                 {("(SELECT AVG(heat_score) FROM session_analysis WHERE heat_score IS NOT NULL)" if has_analysis else "0")} as avg_heat,
                 {("(SELECT COUNT(*) FROM session_analysis WHERE heat_score >= 50)" if has_analysis else "0")} as critical_sessions,
                 {("(SELECT COUNT(*) FROM anomaly_alerts)" if has_alerts else "0")} as alert_count,
-                (SELECT COUNT(DISTINCT workspace_id) FROM sessions) as workspace_count,
+                (SELECT COUNT(*) FROM workspaces) as workspace_count,
                 (SELECT MAX(created_at) FROM sessions) as last_session
         """)
 
@@ -1041,10 +1041,11 @@ def get_overview():
             LIMIT 15
         """)) if has_signals else []
 
+        exchange_count_expr = "(SELECT COUNT(*) FROM exchanges WHERE exchanges.session_id = s.session_id)" if has_exchanges else "0"
         if has_analysis:
-            recent = safe_rows(query_rows("""
+            recent = safe_rows(query_rows(f"""
                 SELECT s.session_id as id, s.title, sa.heat_score,
-                       {("(SELECT COUNT(*) FROM exchanges WHERE exchanges.session_id = s.session_id)" if has_exchanges else "0")} as exchange_count,
+                       {exchange_count_expr} as exchange_count,
                        s.created_at
                 FROM sessions s
                 LEFT JOIN session_analysis sa ON sa.session_id = s.session_id
@@ -1052,9 +1053,9 @@ def get_overview():
                 LIMIT 10
             """))
         else:
-            recent = safe_rows(query_rows("""
+            recent = safe_rows(query_rows(f"""
                 SELECT s.session_id as id, s.title, NULL as heat_score,
-                       {("(SELECT COUNT(*) FROM exchanges WHERE exchanges.session_id = s.session_id)" if has_exchanges else "0")} as exchange_count,
+                       {exchange_count_expr} as exchange_count,
                        s.created_at
                 FROM sessions s
                 ORDER BY s.created_at DESC
@@ -1161,7 +1162,7 @@ def get_session_detail(session_id):
         signals = safe_rows(query_rows("""
             SELECT * FROM exchange_signals
             WHERE session_id = ?
-            ORDER BY created_at DESC
+            ORDER BY ts DESC
         """, (session_id,))) if has_signals else []
 
         signal_summary = safe_rows(query_rows("""
@@ -1195,18 +1196,20 @@ def get_search_results(query, limit=50):
     """Full-text search across exchanges."""
     try:
         results = query_rows("""
-            SELECT DISTINCT
-                s.id as session_id,
+            SELECT
+                e.session_id,
                 s.title,
-                s.heat_score,
+                sa.heat_score,
                 e.id as exchange_id,
-                e.user_input,
-                e.assistant_response,
-                RANK() OVER (ORDER BY rank) as relevance
-            FROM sessions s
-            JOIN exchanges e ON s.id = e.session_id
-            JOIN full_text_search fts ON e.id = fts.exchange_id
-            WHERE fts.full_text_search MATCH ?
+                e.exchange_index,
+                e.user_message,
+                e.response_text,
+                e.user_ts
+            FROM fts_exchanges fts
+            JOIN exchanges e ON fts.rowid = e.id
+            JOIN sessions s ON e.session_id = s.session_id
+            LEFT JOIN session_analysis sa ON sa.session_id = e.session_id
+            WHERE fts_exchanges MATCH ?
             ORDER BY rank
             LIMIT ?
         """, (query, limit))
@@ -1219,13 +1222,11 @@ def get_workspaces():
     """List all workspaces with session counts."""
     try:
         workspaces = query_rows("""
-            SELECT DISTINCT workspace_id,
-                   COUNT(*) as session_count,
-                   MAX(created_at) as last_session
-            FROM sessions
-            WHERE workspace_id IS NOT NULL
-            GROUP BY workspace_id
-            ORDER BY session_count DESC
+            SELECT w.workspace_id, w.uri, w.name, w.type, w.session_count,
+                   (SELECT MAX(s.created_at) FROM sessions s
+                    WHERE s.workspace_id = w.workspace_id) as last_session
+            FROM workspaces w
+            ORDER BY w.session_count DESC
         """)
         return {"workspaces": workspaces}
     except Exception as e:
@@ -1253,9 +1254,9 @@ def get_memory():
     """Get all memory files."""
     try:
         memory = query_rows("""
-            SELECT id, name, size, created_at, updated_at
+            SELECT id, scope, workspace_id, session_id, filename, size_bytes, ingested_at
             FROM memory_files
-            ORDER BY updated_at DESC
+            ORDER BY ingested_at DESC
         """)
         return {"memory": memory}
     except Exception as e:
@@ -1267,21 +1268,25 @@ def get_tool_calls(query_str=None, limit=50):
     try:
         if query_str:
             results = query_rows("""
-                SELECT tc.*, e.session_id, s.title as session_title
+                SELECT tc.id, tc.session_id, tc.exchange_index, tc.request_id,
+                       tc.tool_call_id, tc.tool_name, tc.file_path,
+                       tc.arguments_json, tc.has_output, tc.ingested_at,
+                       s.title as session_title
                 FROM tool_calls tc
-                JOIN exchanges e ON tc.exchange_id = e.id
-                JOIN sessions s ON e.session_id = s.id
-                WHERE tc.tool_name LIKE ? OR tc.arguments LIKE ?
-                ORDER BY tc.created_at DESC
+                JOIN sessions s ON tc.session_id = s.session_id
+                WHERE tc.tool_name LIKE ? OR tc.arguments_json LIKE ?
+                ORDER BY tc.ingested_at DESC
                 LIMIT ?
             """, (f"%{query_str}%", f"%{query_str}%", limit))
         else:
             results = query_rows("""
-                SELECT tc.*, e.session_id, s.title as session_title
+                SELECT tc.id, tc.session_id, tc.exchange_index, tc.request_id,
+                       tc.tool_call_id, tc.tool_name, tc.file_path,
+                       tc.arguments_json, tc.has_output, tc.ingested_at,
+                       s.title as session_title
                 FROM tool_calls tc
-                JOIN exchanges e ON tc.exchange_id = e.id
-                JOIN sessions s ON e.session_id = s.id
-                ORDER BY tc.created_at DESC
+                JOIN sessions s ON tc.session_id = s.session_id
+                ORDER BY tc.ingested_at DESC
                 LIMIT ?
             """, (limit,))
         return {"tool_calls": results, "query": query_str, "count": len(results)}
@@ -1293,10 +1298,11 @@ def get_vfs(session_id):
     """List VFS files for a session."""
     try:
         vfs = query_rows("""
-            SELECT id, session_id, path, size, created_at
+            SELECT id, session_id, source_type, source_path, filename,
+                   content_type, size_bytes, sha256, ingested_at
             FROM vfs
             WHERE session_id = ?
-            ORDER BY path
+            ORDER BY filename
         """, (session_id,))
         return {"vfs": vfs, "session_id": session_id}
     except Exception as e:
@@ -1354,17 +1360,26 @@ def get_tokens(session_id=None):
         if session_id:
             tokens = query_rows("""
                 SELECT
-                    SUM(CAST(json_extract(metadata, '$.token_count') AS INTEGER)) as total_tokens,
-                    COUNT(*) as exchange_count
-                FROM exchanges
+                    SUM(prompt_tokens) as total_prompt,
+                    SUM(completion_tokens) as total_completion,
+                    SUM(cached_tokens) as total_cached,
+                    SUM(prompt_tokens + completion_tokens) as total_tokens,
+                    COUNT(*) as turn_count,
+                    GROUP_CONCAT(DISTINCT model_id) as models
+                FROM token_usage
                 WHERE session_id = ?
             """, (session_id,))
         else:
             tokens = query_rows("""
                 SELECT
-                    SUM(CAST(json_extract(metadata, '$.token_count') AS INTEGER)) as total_tokens,
-                    COUNT(*) as exchange_count
-                FROM exchanges
+                    SUM(prompt_tokens) as total_prompt,
+                    SUM(completion_tokens) as total_completion,
+                    SUM(cached_tokens) as total_cached,
+                    SUM(prompt_tokens + completion_tokens) as total_tokens,
+                    COUNT(*) as turn_count,
+                    COUNT(DISTINCT session_id) as session_count,
+                    GROUP_CONCAT(DISTINCT model_id) as models
+                FROM token_usage
             """)
         return {"tokens": tokens}
     except Exception as e:
@@ -1726,11 +1741,10 @@ def render_tokens():
     return """
     <div class="page-header">
         <div class="page-title">Token Usage</div>
-        <div class="page-subtitle">Token consumption analysis by session.</div>
-    </div>
-    <div class="card">
-        <p>Token usage analysis coming soon.</p>
+        <div class="page-subtitle">Token consumption across all sessions.</div>
     </div>
+    <div id="tokens-summary" class="loading"><div class="spinner"></div>Loading...</div>
+    <div id="tokens-table" style="margin-top:16px"></div>
     """
 
 
@@ -1910,6 +1924,9 @@ function initializePage(page) {
         case 'alerts':
             initAlerts();
             break;
+        case 'tokens':
+            initTokens();
+            break;
         case 'pipeline':
             initPipeline();
             break;
@@ -2358,6 +2375,46 @@ function initKeywords() {
     });
 }
 
+function initTokens() {
+    const summary = document.getElementById('tokens-summary');
+    const table = document.getElementById('tokens-table');
+    if (!summary) return;
+    summary.innerHTML = '<div class="spinner"></div> Loading...';
+    fetch('/api/tokens').then(r => r.json()).then(data => {
+        const t = (data.tokens || [])[0] || {};
+        const fmt = n => (n || 0).toLocaleString();
+        summary.innerHTML = `
+            <div class="grid-4">
+                <div class="card"><div class="card-header">Total Tokens</div><div class="card-value">${fmt(t.total_tokens)}</div></div>
+                <div class="card"><div class="card-header">Prompt</div><div class="card-value">${fmt(t.total_prompt)}</div></div>
+                <div class="card"><div class="card-header">Completion</div><div class="card-value">${fmt(t.total_completion)}</div></div>
+                <div class="card"><div class="card-header">Cached</div><div class="card-value">${fmt(t.total_cached)}</div></div>
+                <div class="card"><div class="card-header">Sessions</div><div class="card-value">${fmt(t.session_count)}</div></div>
+                <div class="card"><div class="card-header">Turns</div><div class="card-value">${fmt(t.turn_count)}</div></div>
+            </div>
+            <div class="card" style="margin-top:12px"><b>Models:</b> ${t.models || 'n/a'}</div>
+        `;
+    }).catch(() => {
+        summary.innerHTML = '<div class="alert alert-danger">Failed to load token data.</div>';
+    });
+    if (table) {
+        table.innerHTML = '<div class="spinner"></div> Loading sessions...';
+        const sql = 'SELECT s.title, tu.session_id, SUM(tu.prompt_tokens) as prompt, SUM(tu.completion_tokens) as completion, SUM(tu.cached_tokens) as cached, SUM(tu.prompt_tokens + tu.completion_tokens) as total, COUNT(*) as turns, GROUP_CONCAT(DISTINCT tu.model_id) as models FROM token_usage tu JOIN sessions s ON tu.session_id = s.session_id GROUP BY tu.session_id ORDER BY total DESC LIMIT 50';
+        fetch('/api/query', {method: 'POST', headers: {'Content-Type': 'application/json'}, body: JSON.stringify({sql: sql})})
+            .then(r => r.json()).then(data => {
+                const rows = data.rows || [];
+                if (!rows.length) { table.innerHTML = '<p>No per-session data.</p>'; return; }
+                const fmt = n => (n || 0).toLocaleString();
+                let html = '<div class="card"><div class="card-header">Top Sessions by Token Usage</div><table class="table"><thead><tr><th>Session</th><th>Total</th><th>Prompt</th><th>Completion</th><th>Cached</th><th>Turns</th><th>Models</th></tr></thead><tbody>';
+                rows.forEach(r => {
+                    html += '<tr><td class="truncate">' + (r.title || r.session_id) + '</td><td>' + fmt(r.total) + '</td><td>' + fmt(r.prompt) + '</td><td>' + fmt(r.completion) + '</td><td>' + fmt(r.cached) + '</td><td>' + r.turns + '</td><td class="truncate">' + (r.models || '') + '</td></tr>';
+                });
+                html += '</tbody></table></div>';
+                table.innerHTML = html;
+            }).catch(() => { table.innerHTML = '<p>Failed to load session breakdown.</p>'; });
+    }
+}
+
 function initWorkspaces() {
     const container = document.getElementById('workspaces-content');
     if (!container) return;
@@ -2737,6 +2794,13 @@ def application(environ, start_response):
             start_response('200 OK', [('Content-Type', 'application/json')])
             return [response]
 
+        elif path == '/api/tokens':
+            session_id = query.get('session_id', [None])[0]
+            data = get_tokens(session_id)
+            response = json.dumps(data).encode('utf-8')
+            start_response('200 OK', [('Content-Type', 'application/json')])
+            return [response]
+
         elif path == '/api/alerts':
             data = get_alerts()
             response = json.dumps(data).encode('utf-8')

{code_data_ark-2.0.6 → code_data_ark-2.0.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "code-data-ark"
-version = "2.0.6"
+version = "2.0.7"
 description = "Code Data Ark — local observability and intelligence platform for VS Code + Copilot Chat sessions"
 readme = "readme.md"
 license = "MIT"

code_data_ark-2.0.7/version

@@ -0,0 +1 @@
+2.0.7

code_data_ark-2.0.6/version

@@ -1 +0,0 @@
-2.0.6