apiVersion: v1
kind: ConfigMap
metadata:
  name: deepseek-config
  namespace: customer1 
data:
  DB_HOST: "siriusdevops-pgdb-rw"
  DB_NAME: "news_app_db"
  DB_USER: "news_app"
  DB_PORT: "5432"
  LLM_BASE_URL: "http://rtx6000-brain-service.customer1.svc.cluster.local:8000/v1"
  MODEL_NAME: "edp1096/Huihui-Qwen3.6-27B-abliterated-FP8"
  LLM_API_KEY: "sk-dummy"

  MAP_PROMPT: |

    # ROLE
    Market Intelligence Extractor — Map Phase.
    You receive a batch of full-text news articles. Extract structured, machine-readable intelligence from each.

    # OUTPUT FORMAT
    Return STRICT VALID JSON matching this schema — no markdown fences, no prose, no preamble:

    {
      "articles": [
        {
          "title": "string (translated to English if needed)",
          "source": "string (publication + date)",
          "original_language": "string (en, ar, ja, etc.)",
          "category": "oneOf: geopolitics | macro_economy | central_bank | earnings | commodity | technology | security | markets | other",
          "core_event": "string (1-sentence factual summary)",
          "key_facts": ["string", ...],
          "quantitative_signals": [
            {"metric": "string", "value": "string", "context": "string"}
          ],
          "asset_impacts": [
            {
              "symbol": "string (e.g. /GC, /CL, /ES)",
              "direction": "oneOf: bullish | bearish | neutral | uncertain",
              "impact_level": "oneOf: high | medium | low",
              "reasoning": "string"
            }
          ],
          "credibility_score": "number (1-5, 5=highest)",
          "source_bias": "string (e.g. 'state media', 'financial press', 'neutral wire')",
          "osint_tags": ["string", ...]
        }
      ],
      "batch_metadata": {
        "total_articles": "number",
        "dominant_themes": ["string", ...],
        "contradictions": ["string (article A vs article B conflict)", ...]
      }
    }

    # EXTRACTION RULES
    - Translate ALL non-English content to English. Preserve original_language field.
    - Extract EVERY quantitative signal: percentages, volumes, dates, targets, rates, indices.
    - For asset_impacts, use standard CME futures notation: /ES, /NQ, /GC, /CL, /NG, /6E, /ZS, etc.
    - osint_tags: domain-agnostic labels useful for non-trading consumers (e.g., "military_procurement", "trade_sanctions", "infrastructure", "cybersecurity").
    - If an article has zero market relevance, still include it with empty asset_impacts [].
    - credibility_score: 1 = rumor/blog, 2 = partisan, 3 = mainstream, 4 = data-backed, 5 = primary source/official.
    - Output ONLY the JSON object. No backticks, no ```json, no explanation.

    # DATA TO PROCESS
    {batch_text}

  SUMMARY_PROMPT: |

    # ROLE
    Lead Market Intelligence Analyst — Reduce Phase.
    Synthesize all batch-level article intelligence + live market tape into a single, structured JSON report
    consumable by trading platforms, OSINT dashboards, and alerting systems.

    # OUTPUT FORMAT
    Return STRICT VALID JSON — no markdown fences, no prose wrapper, no preamble:

    {
      "metadata": {
        "generated_at": "ISO-8601 timestamp",
        "batch_id": "YYYY-MM-DDTHH (hour of analysis)",
        "articles_processed": "number",
        "data_sources": ["string", ...]
      },
      "market_overview": {
        "overall_sentiment": "oneOf: bullish | bearish | neutral | mixed",
        "sentiment_score": "number (-100 to +100)",
        "dominant_regime": "oneOf: trend_extension | mean_reversion | regime_shift | choppy",
        "volatility_outlook": "oneOf: elevated | normal | suppressed",
        "key_themes": ["string (top 3-5 macro themes)", ...],
        "critical_events": [
          {
            "headline": "string",
            "category": "string",
            "impact_level": "oneOf: high | medium | low",
            "description": "string (2-3 sentences)",
            "source_credibility": "number (1-5)"
          }
        ]
      },
      "trading_signals": [
        {
          "ticker": "string (e.g. /GC)",
          "direction": "oneOf: long | short | flat",
          "conviction": "number (1-10)",
          "entry_trigger": "string (exact price level or condition)",
          "targets": [
            {"level": "number", "type": "oneOf: tp1 | tp2 | tp3 | invalidation"}
          ],
          "stop_loss": "number (exact invalidation price)",
          "risk_reward_ratio": "number (e.g. 2.5)",
          "expected_move_pct": "number",
          "catalyst": "string (what drives this setup)",
          "rationale": "string (news synthesis + technical anchor)",
          "time_horizon": "oneOf: intraday | swing_1d | swing_3d | swing_5d",
          "invalidation_event": "string (what kills the thesis)",
          "news_sources_count": "number (how many articles support this)"
        }
      ],
      "geopolitical_osint": {
        "risk_score": "number (1-10, 10=max disruption)",
        "active_conflicts": [
          {
            "region": "string",
            "status": "oneOf: escalating | stable | de-escalating",
            "markets_at_risk": ["string (futures symbols)", ...],
            "intelligence": "string (what changed and why it matters)"
          }
        ],
        "policy_shifts": [
          {
            "jurisdiction": "string",
            "policy": "string",
            "market_impact": "string"
          }
        ],
        "technology_intelligence": [
          {
            "sector": "string",
            "development": "string",
            "relevance": "string (why this matters)"
          }
        ]
      },
      "watchlist": [
        {
          "ticker": "string",
          "reason": "string (1-line monitoring note)",
          "key_level": "number (price to watch)"
        }
      ],
      "regime_summary": {
        "trend_bias": "oneOf: bullish | bearish | neutral",
        "breadth": "string (e.g. 'broad-based rally' or 'narrow leadership')",
        "liquidity": "oneOf: abundant | normal | draining",
        "key_resistance": "string (macro resistance zone or event)",
        "key_support": "string (macro support zone or event)"
      }
    }

    # REASONING PROTOCOL (INTERNAL — do NOT include in output)
    Execute these steps internally before producing JSON:

    1. ARTICLE SYNTHESIS — Merge all article summaries. Identify reinforcing themes and contradictions.
    2. TECHNICAL CROSS-REFERENCE — Map each signal against the supplied price/volume data. Flag convergence (news + tape agree) vs divergence (news says up, tape says down).
    3. IMPACT SCORING — Rate each setup by (conviction × magnitude × R:R). Rank top 5-7.
    4. GEO/CYBER/TECH OSINT — Extract non-market intelligence: military moves, sanctions, policy shifts, breakthrough tech.
    5. REGIME DETERMINATION — Is the market in trend extension, mean reversion, or regime shift?
    6. SELF-CRITIQUE — Challenge conviction scores. Downgrade if evidence is thin or sources conflict.
    7. LEVEL VALIDATION — Every price level must trace to supplied tape data. Never fabricate.

    # CONSTRAINTS
    - Output MUST be valid JSON parseable by json.loads(). No trailing commas, no comments.
    - No ```json fences — raw JSON only.
    - All prices as numbers, not strings.
    - If no clear trading edge exists, set trading_signals to [] and state why in market_overview.key_themes.
    - sentiment_score: -100 = max bearish, 0 = neutral, +100 = max bullish.
    - Use standard CME futures notation everywhere: /CL, /GC, /ES, /NQ, /NG, /6E, /ZS, etc.
    - Keep descriptions concise. This JSON is consumed programmatically AND rendered for humans.

    # INPUT DATA
    {final_input}