feat(observer): parser v2 — environment, task_size, prompt_signal extractors

tools/observer-transcript-parser.mjs

@@ -19,16 +19,19 @@ const SUPERPOWERS_PREFIX = 'superpowers:';
 
 function parseLines(text) {
   const entries = [];
+  let broken = 0;
+  let total = 0;
   for (const line of String(text || '').split('\n')) {
     const trimmed = line.trim();
     if (!trimmed) continue;
+    total += 1;
     try {
       entries.push(JSON.parse(trimmed));
     } catch {
-      // broken line — skip, never throw
+      broken += 1; // broken line — counted for parse_gap, never thrown
     }
   }
-  return entries;
+  return { entries, broken, total };
 }
 
 // A genuine user prompt (turn boundary) — not a tool_result carrier message.
@@ -96,6 +99,78 @@ function collectToolUse(entries) {
   return { skills, counts, errorCount };
 }
 
+const FILE_TOOLS = new Set(['Read', 'Edit', 'Write', 'MultiEdit', 'NotebookEdit']);
+
+/**
+ * Deterministic environment factors for the turn that starts at turnStartIdx.
+ * economy_level / parallel_session are scanned from the stringified turn;
+ * model / post_compaction / session_turn from structural fields.
+ */
+export function extractEnvironment(allEntries, turnStartIdx) {
+  const turn = allEntries.slice(turnStartIdx);
+  const rawTurn = JSON.stringify(turn);
+
+  const econ = rawTurn.match(/=== ECONOMY MODE:\s*(\d+)\s*%/);
+  const economy_level = econ ? Number(econ[1]) : null;
+
+  let model = null;
+  for (const e of turn) {
+    if (e && e.message && e.message.model) {
+      model = e.message.model;
+      break;
+    }
+  }
+
+  let post_compaction = false;
+  for (let i = 0; i < turnStartIdx && i < allEntries.length; i++) {
+    if (allEntries[i] && allEntries[i].isCompactSummary === true) {
+      post_compaction = true;
+      break;
+    }
+  }
+
+  let session_turn = 0;
+  for (let i = 0; i <= turnStartIdx && i < allEntries.length; i++) {
+    if (isRealUserPrompt(allEntries[i])) session_turn += 1;
+  }
+
+  const parallel_session = /параллельн|parallel session|чужой staged|foreign git index/i.test(rawTurn);
+
+  return { economy_level, model, post_compaction, session_turn, parallel_session };
+}
+
+/** Task size: total tool calls + unique file paths touched (per spec §3, gap-resolution 2). */
+export function extractTaskSize(turn) {
+  let tool_calls = 0;
+  const files = new Set();
+  for (const e of turn) {
+    const content = e && e.message && Array.isArray(e.message.content) ? e.message.content : [];
+    for (const b of content) {
+      if (b && b.type === 'tool_use') {
+        tool_calls += 1;
+        if (FILE_TOOLS.has(b.name) && b.input) {
+          const p = b.input.file_path || b.input.notebook_path;
+          if (p) files.add(String(p));
+        }
+      }
+    }
+  }
+  return { tool_calls, files_touched: files.size, files: [...files] };
+}
+
+/** Classify the opening user-prompt sentiment (per spec §6 / gap-resolution 1). */
+export function classifyPromptSignal(text) {
+  const t = String(text || '').toLowerCase().trim();
+  if (/не то\b|не так\b|переделай|отбой|\bстоп\b|почему ты|неверно|не верно|это не /.test(t)) {
+    return 'correction';
+  }
+  if (/^(ок|окей|ok|спасибо|супер|отлично|готово|дальше|идеально)([,\s]|$)/.test(t)) {
+    return 'approval';
+  }
+  if (classifyTask(t) !== 'other' && t.length > 15) return 'new_task';
+  return 'neutral';
+}
+
 /**
  * Parse a transcript JSONL string into observer episode fields.
  * @param {string} transcriptText - Raw JSONL transcript contents.
@@ -103,7 +178,7 @@ function collectToolUse(entries) {
  * @returns {object} Episode with 5 mandatory fields + events.
  */
 export function parseTranscript(transcriptText, fallbackSessionId = null) {
-  const entries = parseLines(transcriptText);
+  const { entries } = parseLines(transcriptText);
 
   const withSession = entries.find((e) => e && e.sessionId);
   const sessionId =