system-prompts-and-models-o.../dealix/tests/unit/test_meeting_intelligence.py
Dealix Builder bcf545c22e feat(self-improving): Hermes-inspired Agent Platform — 6 layers + 30 endpoints + 76 tests + Private Beta launch
Security Curator (4 modules) — جدار الحماية الأول
- secret_redactor: 11 patterns (GitHub PAT, OpenAI/Anthropic/Supabase/WhatsApp/Moyasar/Sentry/Google/AWS/private keys); never returns raw secret
- patch_firewall: blocks .env / credentials.json / RSA keys; scans added lines for secret patterns
- trace_redactor: masks phones (+966...) and emails for PII safety
- tool_output_sanitizer: cleans tool outputs before they hit ledger/Proof Pack/UI/observability

Growth Curator (5 modules) — التحسين الذاتي
- message_curator: grades Arabic messages (0..100), detects 8 risky phrases, suggests Saudi-tone skeleton
- playbook_curator: scores playbooks by outcome (accept/reply/meeting/deal); winner/promising/needs_work/archive
- mission_curator: scores completed missions; ship_it_widely/iterate/rework_or_retire
- skill_inventory: deterministic 23-skill catalog across 5 layers
- curator_report: weekly Arabic summary "ماذا تعلمنا هذا الأسبوع"

Meeting Intelligence (5 modules) — ذكاء الاجتماعات
- transcript_parser: accepts Google Meet entries OR plain "Speaker: text" format
- meeting_brief: 6-section pre-meeting brief in Arabic (objective/questions/objections/offer/next-step)
- objection_extractor: 8 categories (price/timing/authority/trust/integration/competitor/results/complexity)
- followup_builder: email + WhatsApp drafts; live_send_allowed=False always
- deal_risk: 0..100 score from objections + missing next-step + decision-maker absence + days-since-touch

Model Router (5 modules) — موجّه النماذج
- provider_registry: 7 providers (Claude Sonnet/Haiku, GPT-4-class, GPT-4o-mini, Gemini Pro, Azure OAI KSA-region, Local Qwen Arabic-tuned)
- task_router: 10 task types × routing decisions with reasons_ar
- cost_policy: bulk → low; output > 1500 tokens → high
- fallback_policy: high-sensitivity workloads prefer KSA-region/self-hosted FIRST
- usage_dashboard: deterministic demo of all task routes

Connector Catalog (3 modules) — كتالوج التكاملات
- 14 connectors (WhatsApp Cloud, Gmail, Calendar, Google Meet, Moyasar, LinkedIn Lead Forms, Google Business Profile, X API, Instagram, Sheets, CRM, Website Forms, Composio, MCP Gateway)
- Each has launch_phase (1-4), risk_level, allowed_actions, blocked_actions, Arabic risk dossier
- WhatsApp blocks cold_send_without_consent; Moyasar blocks store_card_number; MCP requires allowlist

Agent Observability (5 modules) — مراقبة الوكلاء + التقييمات
- trace_events: SHA256-hashes user/company IDs; sanitizes payload/output before logging
- safety_eval: 7 rules (guarantee, scarcity_fake, medical_claim, financial, regulatory, personal_data, urgency); 0..100 → safe/needs_review/blocked
- saudi_tone_eval: positive markers (هلا, لاحظت, يناسبك) vs negative (تحية طيبة وبعد, synergy, leverage); arabic_ratio bonus
- eval_pack: 5 curated cases with expected verdicts
- cost_tracker: per workflow/provider/task_type aggregation

Routers (6 new) — 30 endpoints
- /api/v1/security-curator/{demo, redact, inspect-diff, sanitize-output}
- /api/v1/growth-curator/{skills/inventory, messages/grade, messages/improve, messages/duplicates, missions/next, report/weekly, report/demo}
- /api/v1/meeting-intelligence/{brief, brief/demo, transcript/summarize, followup/draft, deal-risk}
- /api/v1/model-router/{providers, tasks, route, cost-class, usage/demo}
- /api/v1/connector-catalog/{catalog, summary, status, risks, {key}}
- /api/v1/agent-observability/{trace/build, safety/eval, tone/eval, evals/run}

Tests (6 new files, 76 tests)
- test_security_curator: 16 tests (PAT detect, key redact, env diff block, payload scan, trace mask)
- test_growth_curator: 16 tests (Arabic grade, risky phrases, dup detect, playbook scoring, mission recommend, weekly report)
- test_meeting_intelligence: 13 tests (transcript parse, brief sections, objection extract, followup drafts, deal risk)
- test_dealix_model_router: 11 tests (every task → ≥1 provider, KSA-region for high sensitivity, cost class, primary override)
- test_agent_observability: 12 tests (trace hashing, safety verdicts, tone scoring, eval pack)
- test_connector_catalog: 11 tests (≥12 connectors, every has risk/blocked actions, WA cold-send blocked, Moyasar card-storage blocked)

Docs (8 new + 1 updated)
- AGENT_SECURITY_CURATOR.md (Arabic)
- GROWTH_CURATOR_STRATEGY.md (Arabic)
- MEETING_INTELLIGENCE.md (Arabic)
- MODEL_PROVIDER_ROUTER.md (Arabic)
- CONNECTOR_CATALOG.md (Arabic)
- AGENT_OBSERVABILITY_EVALS.md (Arabic)
- PRIVATE_BETA_LAUNCH_TODAY.md (Arabic) — go-checklist + offer + risks
- DEMO_SCRIPT_12_MINUTES.md (Arabic) — minute-by-minute demo flow
- FIRST_20_OUTREACH_MESSAGES.md (Arabic) — 7 personas + 3 follow-ups, all under safety/tone evals
- DEALIX_100_PERCENT_LAUNCH_PLAN.md — added §34 Self-Improving Agent Platform + §35 Private Beta Launch

Landing
- landing/private-beta.html — Arabic RTL, dark theme, pricing, 11 demo endpoints, safety banner

Test results
- 76/76 new tests pass
- Full suite: 663 passed, 2 skipped (missing API keys, unrelated)
- 0 existing tests broken

Safety
- All 6 layers honor approval-first, draft-only, no-live-send
- Hash user/company IDs before any trace
- No secrets in logs/embeddings/traces (3-layer defense: redactor + sanitizer + firewall)
- Saudi tone eval rejects "تحية طيبة وبعد" + "synergy" auto-corporate language
- Safety eval blocks "ضمان 100%" + medical claims + fake urgency
- Connector Catalog: WhatsApp blocks cold-send, Moyasar blocks card storage, MCP requires allowlist

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 16:30:18 +03:00

121 lines
4.5 KiB
Python

"""Unit tests for Meeting Intelligence."""
from __future__ import annotations
from auto_client_acquisition.meeting_intelligence import (
build_post_meeting_followup,
build_pre_meeting_brief,
compute_deal_risk,
extract_objections,
parse_transcript_entries,
summarize_meeting,
)
# ── Transcript Parser ───────────────────────────────────────
def test_parser_handles_meet_entries():
entries = [
{"participantId": "alice", "text": "ما رأيكم في السعر؟"},
{"participantId": "bob", "text": "السعر مرتفع لنا الآن."},
]
p = parse_transcript_entries(entries)
assert p["total_turns"] == 2
assert "alice" in p["speakers"]
def test_parser_handles_plain_text():
text = "Alice: مرحباً\nBob: السعر مرتفع لنا"
p = parse_transcript_entries(text)
assert p["total_turns"] == 2
def test_summarize_returns_arabic_summary():
parsed = parse_transcript_entries([
{"participantId": "a", "text": "نحتاج أن نفهم نموذج التسعير بشكل أوضح."},
{"participantId": "b", "text": "ممتاز، أقترح اجتماع ثاني الأسبوع القادم."},
])
s = summarize_meeting(parsed)
assert s["approval_required"] is True
assert any("اجتماع" in line or "نقاش" in line for line in s["summary_ar"])
# ── Brief ───────────────────────────────────────────────────
def test_brief_returns_six_sections():
b = build_pre_meeting_brief(
company={"name": "Acme", "sector": "saas"},
contact={"name": "أحمد", "role": "VP"},
opportunity={"expected_value_sar": 25_000},
)
assert b["company_name"] == "Acme"
assert len(b["questions_ar"]) >= 5
assert len(b["likely_objections_ar"]) >= 5
assert b["approval_required"] is True
def test_brief_works_with_empty_input():
b = build_pre_meeting_brief()
assert b["company_name"] == "?"
assert b["questions_ar"]
# ── Objection Extractor ─────────────────────────────────────
def test_extracts_price_objection():
out = extract_objections("هذا الحل غالي ولا يناسب الميزانية.")
cats = out["categories_found"]
assert "price" in cats
def test_extracts_authority_objection():
out = extract_objections("نحتاج موافقة المدير قبل أي قرار.")
assert "authority" in out["categories_found"]
def test_no_objection_in_clean_text():
out = extract_objections("اجتماع رائع، نتطلع للخطوة القادمة.")
assert out["count"] == 0
# ── Followup Builder ────────────────────────────────────────
def test_followup_returns_email_and_whatsapp_drafts():
out = build_post_meeting_followup(
next_steps=["إرسال عرض السعر", "تحديد اجتماع ثانٍ"],
contact_name="أحمد",
company_name="Acme",
)
assert "email" in out["channel_drafts"]
assert "whatsapp" in out["channel_drafts"]
assert out["channel_drafts"]["email"]["live_send_allowed"] is False
assert "أحمد" in out["channel_drafts"]["email"]["body_ar"]
def test_followup_addresses_objections():
out = build_post_meeting_followup(
next_steps=["متابعة"],
contact_name="سارة",
objections=[{"label_ar": "السعر/الميزانية"},
{"label_ar": "صاحب القرار"}],
)
assert "السعر" in out["channel_drafts"]["email"]["body_ar"]
assert out["objections_addressed"]
# ── Deal Risk ───────────────────────────────────────────────
def test_high_risk_when_no_next_step_and_authority_objection():
out = compute_deal_risk(
objections=[{"category": "authority"}, {"category": "price"}],
next_step_set=False,
decision_maker_present=False,
)
assert out["risk_score"] >= 50
assert out["risk_level"] in ("medium", "high")
def test_low_risk_with_clean_meeting():
out = compute_deal_risk(
objections=[],
next_step_set=True,
decision_maker_present=True,
days_since_last_touch=0,
)
assert out["risk_level"] == "low"