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

docs/observer/STATUS.md

@@ -1,6 +1,6 @@
 # Brain Status (auto-generated)
 
-Last updated: 2026-05-19T06:15:36.829Z
+Last updated: 2026-05-19T07:10:08.281Z
 
 | Контролёр | Состояние | Детали |
 |---|---|---|
@@ -11,7 +11,7 @@ Last updated: 2026-05-19T06:15:36.829Z
 
 ## Метрики (информационные, не алерты)
 
-- Observer evidence: 7 episodes this month, 0 PII matches before filter
+- Observer evidence: 10 episodes this month, 0 PII matches before filter
 - Использование узлов: см. `/brain-retro` (раз в спринт). **Неиспользованные узлы — не проблема** (capability-readiness; см. memory `feedback_brain_unused_tools_not_problem` — outside-repo memory store).
 
 ## Алерт-индикаторы

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 =

tools/observer-transcript-parser.test.mjs

@@ -1,5 +1,10 @@
 import { describe, it, expect } from 'vitest';
-import { parseTranscript } from './observer-transcript-parser.mjs';
+import {
+  parseTranscript,
+  extractEnvironment,
+  extractTaskSize,
+  classifyPromptSignal,
+} from './observer-transcript-parser.mjs';
 
 // Build a JSONL transcript string from entry objects.
 function jsonl(entries) {
@@ -215,3 +220,88 @@ describe('parseTranscript', () => {
     }
   });
 });
+
+describe('extractEnvironment', () => {
+  it('reads economy_level from the ECONOMY MODE marker', () => {
+    const entries = [
+      userPrompt('=== ECONOMY MODE: 0% (пользователь указал явно) ===\nfix it', '2026-05-19T10:00:00Z'),
+    ];
+    expect(extractEnvironment(entries, 0).economy_level).toBe(0);
+  });
+
+  it('economy_level is null when no marker present', () => {
+    const entries = [userPrompt('just do it', '2026-05-19T10:00:00Z')];
+    expect(extractEnvironment(entries, 0).economy_level).toBeNull();
+  });
+
+  it('reads model from an assistant message', () => {
+    const entries = [
+      userPrompt('go', '2026-05-19T10:00:00Z'),
+      { type: 'assistant', message: { role: 'assistant', model: 'claude-opus-4-7', content: [] }, timestamp: '2026-05-19T10:01:00Z', sessionId: 's1' },
+    ];
+    expect(extractEnvironment(entries, 0).model).toBe('claude-opus-4-7');
+  });
+
+  it('post_compaction is true when an isCompactSummary entry precedes the turn', () => {
+    const entries = [
+      { type: 'user', isCompactSummary: true, message: { role: 'user', content: 'summary' }, timestamp: '2026-05-19T09:00:00Z' },
+      userPrompt('the real turn', '2026-05-19T10:00:00Z'),
+    ];
+    expect(extractEnvironment(entries, 1).post_compaction).toBe(true);
+  });
+
+  it('post_compaction is false with no compaction marker', () => {
+    const entries = [userPrompt('turn one', '2026-05-19T09:00:00Z'), userPrompt('turn two', '2026-05-19T10:00:00Z')];
+    expect(extractEnvironment(entries, 1).post_compaction).toBe(false);
+  });
+
+  it('session_turn counts real user prompts up to and including the turn start', () => {
+    const entries = [
+      userPrompt('one', '2026-05-19T09:00:00Z'),
+      userPrompt('two', '2026-05-19T09:30:00Z'),
+      userPrompt('three', '2026-05-19T10:00:00Z'),
+    ];
+    expect(extractEnvironment(entries, 2).session_turn).toBe(3);
+  });
+});
+
+describe('extractTaskSize', () => {
+  it('counts tool calls and unique file paths', () => {
+    const turn = [
+      assistantTurn(
+        [
+          { type: 'tool_use', id: 't1', name: 'Read', input: { file_path: '/a.js' } },
+          { type: 'tool_use', id: 't2', name: 'Edit', input: { file_path: '/a.js' } },
+          { type: 'tool_use', id: 't3', name: 'Write', input: { file_path: '/b.js' } },
+          { type: 'tool_use', id: 't4', name: 'Bash', input: {} },
+        ],
+        '2026-05-19T10:01:00Z'
+      ),
+    ];
+    const size = extractTaskSize(turn);
+    expect(size.tool_calls).toBe(4);
+    expect(size.files_touched).toBe(2);
+    expect(size.files.sort()).toEqual(['/a.js', '/b.js']);
+  });
+
+  it('returns zeros for an empty turn', () => {
+    expect(extractTaskSize([])).toEqual({ tool_calls: 0, files_touched: 0, files: [] });
+  });
+});
+
+describe('classifyPromptSignal', () => {
+  it('detects corrections', () => {
+    expect(classifyPromptSignal('не то, переделай')).toBe('correction');
+    expect(classifyPromptSignal('почему ты это сделал')).toBe('correction');
+  });
+  it('detects approvals', () => {
+    expect(classifyPromptSignal('ок, спасибо')).toBe('approval');
+    expect(classifyPromptSignal('готово, дальше')).toBe('approval');
+  });
+  it('detects a new task', () => {
+    expect(classifyPromptSignal('добавь новую фичу экспорта в CSV')).toBe('new_task');
+  });
+  it('falls back to neutral', () => {
+    expect(classifyPromptSignal('hmm')).toBe('neutral');
+  });
+});