mirror of
https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git
synced 2026-06-18 15:29:36 +00:00
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>
172 lines
5.4 KiB
Python
172 lines
5.4 KiB
Python
"""Registry of model providers + task types."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
|
|
# Task types Dealix actually routes.
|
|
ALL_TASK_TYPES: tuple[str, ...] = (
|
|
"strategic_reasoning",
|
|
"arabic_copywriting",
|
|
"classification",
|
|
"compliance_guardrail",
|
|
"meeting_analysis",
|
|
"vision_analysis",
|
|
"extraction",
|
|
"summarization",
|
|
"coding_project_understanding",
|
|
"low_cost_bulk",
|
|
)
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class Provider:
|
|
"""A model provider entry."""
|
|
key: str
|
|
label: str
|
|
family: str # "anthropic" | "openai" | "google" | "azure" | "local"
|
|
capabilities: tuple[str, ...] # subset of ALL_TASK_TYPES
|
|
cost_class: str # "low" | "mid" | "high"
|
|
latency_class: str # "fast" | "balanced" | "slow"
|
|
supports_vision: bool
|
|
supports_arabic: bool
|
|
privacy_tier: str # "vendor_cloud" | "ksa_region" | "self_hosted"
|
|
notes_ar: str = ""
|
|
|
|
def to_dict(self) -> dict[str, object]:
|
|
return {
|
|
"key": self.key, "label": self.label, "family": self.family,
|
|
"capabilities": list(self.capabilities),
|
|
"cost_class": self.cost_class, "latency_class": self.latency_class,
|
|
"supports_vision": self.supports_vision,
|
|
"supports_arabic": self.supports_arabic,
|
|
"privacy_tier": self.privacy_tier,
|
|
"notes_ar": self.notes_ar,
|
|
}
|
|
|
|
|
|
# Conservative provider list — Dealix can swap any of these without code change.
|
|
ALL_PROVIDERS: tuple[Provider, ...] = (
|
|
Provider(
|
|
key="claude_sonnet",
|
|
label="Claude Sonnet",
|
|
family="anthropic",
|
|
capabilities=(
|
|
"strategic_reasoning", "arabic_copywriting",
|
|
"compliance_guardrail", "meeting_analysis", "summarization",
|
|
"coding_project_understanding",
|
|
),
|
|
cost_class="mid",
|
|
latency_class="balanced",
|
|
supports_vision=True,
|
|
supports_arabic=True,
|
|
privacy_tier="vendor_cloud",
|
|
notes_ar="مناسب للاستراتيجية والكتابة العربية والامتثال.",
|
|
),
|
|
Provider(
|
|
key="claude_haiku",
|
|
label="Claude Haiku",
|
|
family="anthropic",
|
|
capabilities=("classification", "extraction", "low_cost_bulk", "summarization"),
|
|
cost_class="low",
|
|
latency_class="fast",
|
|
supports_vision=False,
|
|
supports_arabic=True,
|
|
privacy_tier="vendor_cloud",
|
|
notes_ar="رخيص وسريع — للتصنيف الكثيف والاستخراج.",
|
|
),
|
|
Provider(
|
|
key="gpt_4_class",
|
|
label="GPT-4-class",
|
|
family="openai",
|
|
capabilities=(
|
|
"strategic_reasoning", "vision_analysis",
|
|
"coding_project_understanding", "meeting_analysis",
|
|
),
|
|
cost_class="high",
|
|
latency_class="balanced",
|
|
supports_vision=True,
|
|
supports_arabic=True,
|
|
privacy_tier="vendor_cloud",
|
|
notes_ar="بديل قوي للاستراتيجية والرؤية.",
|
|
),
|
|
Provider(
|
|
key="gpt_4o_mini",
|
|
label="GPT-4o mini",
|
|
family="openai",
|
|
capabilities=("classification", "extraction", "low_cost_bulk"),
|
|
cost_class="low",
|
|
latency_class="fast",
|
|
supports_vision=True,
|
|
supports_arabic=True,
|
|
privacy_tier="vendor_cloud",
|
|
notes_ar="بديل رخيص للمهام الكثيفة.",
|
|
),
|
|
Provider(
|
|
key="gemini_pro",
|
|
label="Gemini Pro",
|
|
family="google",
|
|
capabilities=(
|
|
"vision_analysis", "summarization", "meeting_analysis",
|
|
"extraction",
|
|
),
|
|
cost_class="mid",
|
|
latency_class="balanced",
|
|
supports_vision=True,
|
|
supports_arabic=True,
|
|
privacy_tier="vendor_cloud",
|
|
notes_ar="ممتاز للرؤية والاجتماعات.",
|
|
),
|
|
Provider(
|
|
key="azure_oai_ksa",
|
|
label="Azure OpenAI (KSA region)",
|
|
family="azure",
|
|
capabilities=(
|
|
"strategic_reasoning", "arabic_copywriting",
|
|
"compliance_guardrail", "extraction", "summarization",
|
|
),
|
|
cost_class="mid",
|
|
latency_class="balanced",
|
|
supports_vision=True,
|
|
supports_arabic=True,
|
|
privacy_tier="ksa_region",
|
|
notes_ar="منطقة KSA — مناسب للعملاء الحساسين للامتثال.",
|
|
),
|
|
Provider(
|
|
key="local_qwen_ar",
|
|
label="Local Qwen (Arabic-tuned)",
|
|
family="local",
|
|
capabilities=("classification", "extraction", "low_cost_bulk", "arabic_copywriting"),
|
|
cost_class="low",
|
|
latency_class="balanced",
|
|
supports_vision=False,
|
|
supports_arabic=True,
|
|
privacy_tier="self_hosted",
|
|
notes_ar="نموذج محلي — للحالات الحساسة جداً.",
|
|
),
|
|
)
|
|
|
|
|
|
def get_provider(key: str) -> Provider | None:
|
|
return next((p for p in ALL_PROVIDERS if p.key == key), None)
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class TaskType:
|
|
"""Description of a routed task."""
|
|
key: str
|
|
label_ar: str
|
|
requires_arabic: bool
|
|
requires_vision: bool
|
|
sensitivity: str # "low" | "medium" | "high"
|
|
notes_ar: str = ""
|
|
|
|
def to_dict(self) -> dict[str, object]:
|
|
return {
|
|
"key": self.key, "label_ar": self.label_ar,
|
|
"requires_arabic": self.requires_arabic,
|
|
"requires_vision": self.requires_vision,
|
|
"sensitivity": self.sensitivity,
|
|
"notes_ar": self.notes_ar,
|
|
}
|