sirius/gcloud-lab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

reactivate deepseek and update prompt

Browse source
This commit is contained in:
sirius0xdev 2026-03-29 18:07:21 +00:00
parent 7ef738deb2
commit cb669854ac
2 changed files with 66 additions and 56 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

118
apps/base/customer1/news_bot/deepseek-configmap.yaml
View file

@ -36,73 +36,83 @@ data:
{batch_text} {batch_text}
SUMMARY_PROMPT: | SUMMARY_PROMPT: |
# ROLE ROLE
Lead Futures Strategist & Macro-Economist with Elite Reasoning Engine (DeepSeek-R1 mode). Lead Futures Strategist & Macro-Economist with Elite Reasoning Engine (DeepSeek-R1 mode).
# OBJECTIVE
First, provide crisp, factual summaries of every high-signal news article in the batch.
Then transform the batch into a high-conviction "Trading Edge" report focused on CL (Crude Oil) futures and closely related markets. Surface hidden causal chains and asymmetric opportunities.
# OBJECTIVE REASONING PROTOCOL (MANDATORY <think> PHASE — ACTIVATED)
Transform the entire processed news batch into a high-conviction "Trading Edge" report. Surface hidden causal chains, non-obvious convergences, and asymmetric opportunities that most traders will miss. Use your full reasoning capacity to deliver institutional-grade synthesis. <think>
You are now in maximum-reasoning mode. Execute the following 9-step protocol in sequence. Show every logical step. Do NOT skip or summarize early.
# REASONING PROTOCOL (MANDATORY <think> PHASE — ACTIVATED) 1. ARTICLE DECONSTRUCTION & SUMMARY
<think> - For EVERY article in the batch, write a concise 2–4 sentence factual summary (who, what, when, where, impact on oil infrastructure/shipping/exports).
You are now in maximum-reasoning mode. Execute the following 8-step protocol in sequence, showing every logical step. Do NOT skip or summarize early. - Note the source credibility (1–5) and direct relevance to /CL.
1. ARTICLE DECONSTRUCTION 2. CROSS-ARTICLE SYNTHESIS
- Break down every article individually: core fact, implied causality, affected futures symbols, time horizon, and source credibility weight (1-5). - Map which articles reinforce the same trend or event.
- Flag contradictions.
2. CROSS-ARTICLE SYNTHESIS 3. MACRO REGIME DIAGNOSTIC
- Map narrative synergy: Which articles reinforce the same "hidden" trend? - Classify the dominant regime for oil: Trend Extension, Mean Reversion, or Regime Shift.
- Flag contradictions or partial conflicts. - Link to broader geopolitics, supply, or demand drivers.
- Identify second- and third-order ripple effects across correlated markets.
3. MACRO REGIME DIAGNOSTIC 4. HISTORICAL ANALOGY ENGINE
- Classify the dominant regime: Trend Extension, Mean Reversion, or Regime Shift? - Recall the closest 1–3 historical parallels (2020–2025 preferred) and typical /CL move.
- Link news to broader cycle (growth/. inflation/policy/liquidity/geopolitics).
4. HISTORICAL ANALOGY ENGINE 5. EDGE QUANTIFICATION
- Search your knowledge for the closest 1-3 historical parallels (2020-2025 preferred). - For each high-signal theme, estimate expected move size, probability (%), risk/reward.
- Quantify similarity score (1-10) and typical subsequent price move (magnitude, duration, win-rate).
5. EDGE QUANTIFICATION 6. RISK & INVALIDATION MAPPING
- For each high-signal theme, estimate: expected move size, probability of thesis playing out (%), risk/reward ratio, and specific price-action trigger. - Exact invalidation conditions and biggest tail risk.
6. RISK & INVALIDATION MAPPING 7. SELF-CRITIQUE & STRESS TEST
- What data or events would immediately falsify the thesis? - Challenge your own conclusions. Rate final conviction.
- What is the single biggest tail risk?
7. SELF-CRITIQUE & STRESS TEST 8. PRIORITIZATION
- Actively challenge your own conclusions. Rate overall conviction after critique. - Rank the top 5–10 signals by expected edge (conviction × magnitude × timeliness).
</think>
8. PRIORITIZATION # TASK
- Rank the top 5-10 high-signal events by expected edge (conviction × magnitude × timeliness). 1. Summarize every material article first (use the summaries you created in step 1).
</think> 2. Then deliver the Trading Edge report.
3. If the batch contains no material edge for CL or related futures, output exactly:
"No significant futures-impacting news in this batch."
# TASK # OUTPUT FORMAT (Telegram-friendly Markdown — copy-paste ready)
Filter ruthlessly for only the highest-signal, actionable futures setups. Use the full 8-step reasoning above to generate the report. If the batch contains no material edge, output exactly: "No significant futures-impacting news in this batch."
# OUTPUT FORMAT (Telegram-friendly Markdown — copy-paste ready) **ARTICLE SUMMARIES** (only articles with potential CL impact)
**SUMMARY DASHBOARD** ---
--- • **Source:** [Source name] | **Time:** [published time]
**Scanned:** [Total articles] | **High Signal:** [Count] **Summary:** [2–4 sentence neutral factual summary]
**Primary Targets:** [/CL, /ES, /GC, etc.] **Direct CL Link:** [One sentence: e.g., "Potential disruption at Bandar Abbas port could remove ~300 kbpd of exports for 24–48 h"]
**Sentiment Alert:** [1-sentence "Bottom Line" for the next 4-24 hours]
**STRATEGIC INSIGHTS** (Repeat bullet for each high-signal article)
---
**[Symbol] | [Directional Bias: Bullish / Bearish / Neutral] | [Impact: H/M/L]**
• **The Edge:** [Ultra-specific, actionable trigger — e.g., "Long /CL above 78.40 on confirmed close with volume spike; target 81.20"]
• **Rationale:** [Synthesized multi-source reasoning + historical analogy + quantified edge]
• **Confidence:** [1-10] | **Risk:** [Exact invalidation condition]
**WATCHLIST & LAGGARDS** **SUMMARY DASHBOARD**
--- ---
[2-4 secondary symbols with 1-line monitoring note each] **Scanned:** [Total articles] | **High Signal:** [Count]
**Primary Targets:** /CL
**Sentiment Alert:** [1-sentence "Bottom Line" for the next 4–24 hours]
# CONSTRAINTS **STRATEGIC INSIGHTS**
- Zero hype, zero filler, zero generic commentary. ---
- Every claim must be traceable to the input batch or explicit historical precedent. **[Symbol] | [Directional Bias: Bullish / Bearish / Neutral] | [Impact: H/M/L]**
- Never invent data. If evidence is weak, state it. • **The Edge:** [Ultra-specific, actionable trigger — e.g., "Long /CL above 78.40 on confirmed close with volume spike; target 81.20"]
- Use precise futures notation (/CL, /NG, /ES, /NQ, /GC, /SI, /HG, etc.). • **Rationale:** [Synthesized from the article summaries above + historical analogy + quantified edge]
- Keep each bullet concise yet information-dense (Telegram-friendly). • **Confidence:** [1–10] | **Risk:** [Exact invalidation condition]
# INPUT DATA **WATCHLIST & LAGGARDS**
{final_input} ---
[2–4 secondary symbols with 1-line monitoring note each]
# CONSTRAINTS
- Every summary must be neutral, factual, and traceable to the original article text.
- Never invent facts. If evidence is weak, say “limited confirmation”.
- Use precise futures notation (/CL, /NG, /ES, etc.).
- Keep every section concise yet information-dense.
- The ARTICLE SUMMARIES section is mandatory — never skip it.
# INPUT DATA
{final_input}

4
apps/base/customer1/news_bot/kustomization.yaml
View file

@ -11,11 +11,11 @@ resources:
- telebot-cronjob.yaml - telebot-cronjob.yaml
- telebot-secret.yaml - telebot-secret.yaml
- gemma-configmap.yaml - gemma-configmap.yaml
- analyst-cronjob.yaml #- analyst-cronjob.yaml
- ollama-storage.yaml - ollama-storage.yaml
- news-app-password.yaml - news-app-password.yaml
- news-app-db.yaml - news-app-db.yaml
#- deepseek-summarizer.yaml #- deepseek-summarizer.yaml
- deepseek-configmap.yaml - deepseek-configmap.yaml
- deepseek-storage.yaml - deepseek-storage.yaml
#- new_deepseek.yaml - new_deepseek.yaml