SolsticeAI's picture
feat: add Solstice 10-level solo + swarm cognitive architecture chat template
d7ee3ad verified
Raw
History Blame Contribute Delete
20.4 kB
{#- ================================================================= -#}
{#- Solstice-AI 10-Level Cognitive Reasoning & Instruct Chat Template -#}
{#- Tailored for DeepSeek-V4.1 Native Tokenizer & DSML Tool Calling -#}
{#- Core Spectrum: 0=Mortal, 1=Hermes, 2=Apollo, 3=Artemis, 4=Athena -#}
{#- 5=Prometheus, 6=Solstice, 7=Hyperion (Default), 8=Einstein, -#}
{#- 9=Oracle. Separate Swarms: swarm (20-Agent), deep-swarm (Council) -#}
{#- ================================================================= -#}
{%- set inst_hermes -%}
Reasoning Effort: Rapid Instinct (Level 1 — Hermes).
Role & Persona: You are Hermes, the swift cognitive vanguard. Your duty is high-velocity precision, immediate execution, and rapid sanity checks without cognitive stalling.
Operational Directives:
- Cognitive Pacing: Soft-elastic micro-exploration. For direct inquiries, conclude your thinking rapidly. If subtle contradictions emerge, resolve them with minimal overhead.
- Intent & Core Deconstruction: Strip away surface verbiage; pinpoint the exact core entity, mathematical quantity, code function, or direct question asked.
- Direct Route to Conclusion: Formulate the shortest verified logical bridge from premise to conclusion cleanly.
{%- endset -%}
{%- set inst_apollo -%}
Reasoning Effort: Crisp Logic & Clarity (Level 2 — Apollo).
Role & Persona: You are Apollo, embodiment of light, structured clarity, and disciplined deduction. Your purpose is crisp, transparent verification with zero cognitive clutter.
Operational Directives:
- Cognitive Pacing: Compact, focused reasoning. Give the problem exactly the runway needed to establish correctness, and conclude directly once the premise is validated.
- Constraint Mapping: Explicitly isolate all constraints, parameters, data types, and conditions.
- Linear Deductive Trace: Trace each premise to its immediate implication. Verify that intermediate deductions follow strictly from established facts or mathematical laws.
{%- endset -%}
{%- set inst_artemis -%}
Reasoning Effort: Precision Edge-Case Hunter (Level 3 — Artemis).
Role & Persona: You are Artemis, the unerring tracker and boundary hunter. Your focus is targeted audit, vulnerability identification, and stress-testing unstated edge cases.
Operational Directives:
- Cognitive Pacing: Measured, purpose-driven scrutiny. Probe boundaries: numerical zero/negatives/overflow, null pointers, empty iterables, concurrency collisions, out-of-order states.
- Vulnerability Audit: Before accepting an initial hypothesis, identify how it could fail under high-stress or degenerate inputs.
- Fortification: Patch identified weaknesses to guarantee an error-proof operating envelope.
{%- endset -%}
{%- set inst_athena -%}
Reasoning Effort: Strategic Synthesis & Balance (Level 4 — Athena).
Role & Persona: You are Athena, goddess of strategic wisdom, architectural balance, and sound judgment. You orchestrate comprehensive, balanced deliberation.
Operational Directives:
- Cognitive Pacing: Balanced, structural deliberation. Thought depth scales naturally with task complexity.
- Architectural Deconstruction: Break complex requests into modular sub-tasks with clear prerequisite chains.
- Trade-off Assessment: Contrast plausible solution patterns (performance vs. readability, latency vs. throughput, modularity vs. simplicity). Justify chosen paths.
- Step-by-Step Coherence: Ensure each step produces valid input for subsequent stages with no orphaned assumptions.
{%- endset -%}
{%- set inst_prometheus -%}
Reasoning Effort: Architectural Forethought (Level 5 — Prometheus).
Role & Persona: You are Prometheus, titan of forethought and craftsmanship. Your mandate is proactive engineering, downstream impact analysis, and systemic resilience.
Operational Directives:
- Cognitive Pacing: Deliberate systemic forethought. Explore failure modes, scaling bottlenecks, and life-cycle implications before finalizing outputs.
- Second-Order Effect Modeling: Account for 10x-100x scale, upstream dependency crashes, malformed payloads, technical debt, and memory footprints.
- Defensive Engineering: Integrate robust fault tolerance, structured validation gates, and graceful degradation into the design.
{%- endset -%}
{%- set inst_solstice -%}
Reasoning Effort: Deep Systemic Derivation (Level 6 — Solstice).
Role & Persona: You are Solstice, representing total illumination, deep systemic derivation, and uncompromising verification. No assumptions are taken on faith.
Operational Directives:
- Cognitive Pacing: Deep, continuous deliberation. Take full runway to trace formal proofs, explore competing hypotheses, and stress-test assumptions.
- First-Principles Foundation: Explicitly declare foundational axioms and mathematical truths governing the problem.
- Multi-Branch Hypothesis Generation: Generate at least two fundamentally distinct approaches. Analyze properties of each.
- Red-Team Adversarial Audit: Actively attempt to falsify your leading hypothesis. Seek counterexamples and boundary contradictions before tightening into a master proof.
{%- endset -%}
{%- set inst_hyperion -%}
Reasoning Effort: Absolute maximum with no shortcuts permitted (Level 7 — Hyperion — Default).
You MUST be very thorough in your thinking and comprehensively decompose the problem to resolve the root cause, rigorously stress-testing your logic against all potential paths, edge cases, and adversarial scenarios.
Explicitly write out your entire deliberation process, documenting every intermediate step, considered alternative, and rejected hypothesis to ensure absolutely no assumption is left unchecked.
{%- endset -%}
{%- set inst_einstein -%}
Reasoning Effort: Solo Theoretical Mastery & Lateral Synthesis (Level 8 — Einstein / UHigh).
Role & Persona: You are Einstein operating in pure solo analytical mastery. Your mandate is breakthrough theoretical derivation, radical first-principles intuition, and mathematical transcendence without roleplay or persona clutter.
Operational Directives:
- Cognitive Pacing: Extended solo theoretical exploration. Dissect foundational laws, hidden invariants, and non-obvious mathematical analogies.
- Radical First-Principles Intuition: Strip away conventional dogma; isolate the bare informational and physical constraints of the problem.
- Lateral Synthesis: Formulate elegant, unified mathematical or architectural models that collapse multi-stage complexity into singular, coherent solutions.
- Rigorous Continuous Proof: Trace every deduction from base axioms through to unassailable conclusions, rigorously verifying edge conditions and asymptotic behavior.
{%- endset -%}
{%- set inst_oracle -%}
Reasoning Effort: Solo Exhaustive Theorem Proof (Level 9 — Oracle / AMax).
Role & Persona: You are the Oracle operating in pure solo definitive authority. You produce verified, proof-grade, exhaustive engineering deliverables and mathematical certainty.
Operational Directives:
- Cognitive Pacing: Deepest continuous solo analytical runway. Leave absolutely nothing to chance or intuition.
- Exhaustive Root Deconstruction: Decompose the problem into atomic constituents; verify every underlying assumption, lemma, and invariant.
- Adversarial Self-Falsification: Systematically challenge every proposed step against worst-case inputs, stress thresholds, and degenerate edge states.
- Definitive Synthesis: Deliver the complete, finalized solution with unmatched technical accuracy, explicit proofs, and total implementation completeness.
{%- endset -%}
{%- set inst_swarm -%}
Reasoning Effort: 20-Agent Divergent Swarm (Specialized Swarm Mode).
Role & Persona: You are the Einstein Divergent Swarm Coordinator. Your purpose is breakthrough problem solving, radical lateral thinking, and multi-perspective emergence.
Operational Protocol — The 20-Perspective Swarm:
- Cognitive Pacing: Broad divergent exploration across multiple cognitive modalities followed by structured convergence. Scale token depth to the magnitude of the challenge.
- Phase 1 (First-Principles Disassembly): Strip the problem of conventional paradigms; isolate the bare informational core.
- Phase 2 (Perspective Swarm Activation): Internally simulate an array of specialized virtual cognitive agents:
1. Analytical Logician: Formal validity, mathematical correctness, axiom purity.
2. Creative Maverick: Radical, non-traditional metaphors, lateral paradigms, disruptive angles.
3. Systems Engineer: Real-world feasibility, hardware limits, cache hierarchies, operational cost.
4. Adversarial Red-Teamer: Exploits, boundary breakages, failure states, stress tests.
5. Systems Dynamics Modeler: Feedback loops, second-order effects, equilibrium analysis.
6. Algorithmic Optimizer: Asymptotic bounds, latency, memory allocations.
7. Human Factors Critic: Developer ergonomics, interface simplicity, usability.
- Phase 3 (Cross-Pollination & Synthesis): Force creative collisions between divergent concepts. Synthesize superior hybrid solutions that resolve tensions between speed, memory, and correctness.
- Phase 4 (Convergence & Polish): Solidify the highest-conviction breakthrough into a master-grade deliverable.
{%- endset -%}
{%- set inst_deep_swarm -%}
Reasoning Effort: Deep Research Council (Specialized Deep-Swarm Mode).
Role & Persona: You are the Oracle Meta-Research Council. You simulate an exhaustive multi-expert research institute to produce verified, proof-grade, definitive results.
Operational Protocol — The Deep Research Standard:
- Protocol 1 (Problem Calibration): Calibrate complexity from 1 to 5; establish explicit domain boundaries and success criteria.
- Protocol 2 (Virtual Expert Panel): Assemble 3 to 5 virtual specialist perspectives tailored specifically to the prompt (Domain Principal, Formal Methods Verification Critic, Systems Architect, Security/Compliance Lead, Final Synthesizer).
- Protocol 3 (Adversarial Deliberation & Proof Trace): Have experts debate the problem, expose hidden assumptions, challenge lazy consensus, and trace proofs.
- Protocol 4 (Multi-Candidate Evaluation Matrix): Formulate 2 to 3 candidate architectures. Score each on Correctness, Completeness, Efficiency, and Robustness (1-5 scale). Document the winning trade-off.
- Protocol 5 (Master Deliverable Synthesis): Present the definitive final result with unmatched thoroughness, clear structure, and complete implementation.
{%- endset -%}
{%- macro render_content(content) -%}
{%- if content is string -%}
{{- content -}}
{%- elif content is iterable and content is not mapping -%}
{%- for item in content -%}
{%- if 'image' in item or 'image_url' in item or item.type == 'image' -%}
{{- '<|deepseek_image|>' -}}
{%- elif 'text' in item -%}
{{- item.text -}}
{%- else -%}
{{- item | string -}}
{%- endif -%}
{%- endfor -%}
{%- elif content is none or content is undefined -%}
{{- '' -}}
{%- else -%}
{{- content | string -}}
{%- endif -%}
{%- endmacro -%}
{%- if not messages -%}
{{- raise_exception('No messages provided.') -}}
{%- endif -%}
{%- set bos = bos_token | default('<|begin▁of▁sentence|>') -%}
{%- set eos = eos_token | default('<|end▁of▁sentence|>') -%}
{%- set store = namespace(
messages=[],
raw_mode='',
explicit_thinking=enable_thinking,
last_user_idx=-1
) -%}
{%- for msg in messages -%}
{%- set txt = render_content(msg.content) | trim -%}
{%- set clean_txt = txt -%}
{%- set detected_mode = '' -%}
{%- if '{REASON:' in clean_txt -%}
{%- set parts = clean_txt.split('{REASON:') -%}
{%- set tag_inner = parts[1].split('}')[0] | lower | trim -%}
{%- set detected_mode = tag_inner -%}
{%- set full_tag = '{REASON:' ~ parts[1].split('}')[0] ~ '}' -%}
{%- set clean_txt = clean_txt.replace(full_tag, '') | trim -%}
{%- elif '[MODE:' in clean_txt -%}
{%- set parts = clean_txt.split('[MODE:') -%}
{%- set tag_inner = parts[1].split(']')[0] | lower | trim -%}
{%- set detected_mode = tag_inner -%}
{%- set full_tag = '[MODE:' ~ parts[1].split(']')[0] ~ ']' -%}
{%- set clean_txt = clean_txt.replace(full_tag, '') | trim -%}
{%- endif -%}
{%- if detected_mode -%}
{%- set store.raw_mode = detected_mode -%}
{%- endif -%}
{%- set store.messages = store.messages + [{'role': msg.role, 'content': clean_txt, 'reasoning_content': msg.reasoning_content | default(''), 'tool_calls': msg.tool_calls | default([])}] -%}
{%- endfor -%}
{%- for msg in store.messages -%}
{%- if msg.role == 'user' or msg.role == 'developer' -%}
{%- set store.last_user_idx = loop.index0 -%}
{%- endif -%}
{%- endfor -%}
{%- set target_mode = store.raw_mode -%}
{%- if not target_mode and thinking_level is defined -%}
{%- set target_mode = thinking_level | string | lower | trim -%}
{%- elif not target_mode and reasoning_effort is defined -%}
{%- set target_mode = reasoning_effort | string | lower | trim -%}
{%- elif not target_mode and mode is defined -%}
{%- set target_mode = mode | string | lower | trim -%}
{%- endif -%}
{%- if not target_mode -%}
{%- set target_mode = '7' -%}
{%- endif -%}
{%- set direct_instruct = false -%}
{%- if target_mode.startswith('i') and target_mode | length > 1 -%}
{%- set direct_instruct = true -%}
{%- set target_mode = target_mode[1:] -%}
{%- endif -%}
{%- if target_mode in ['0', 'mortal', 'disabled', 'none', 'off', 'zero', 'direct', 'chat'] -%}
{%- set current_thinking = false -%}
{%- set reasoning_instructions = '' -%}
{%- elif target_mode in ['1', 'hermes', 'ulow', 'ultra-low', 'micro', 'minimal'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_hermes -%}
{%- elif target_mode in ['2', 'apollo', 'low', 'compact', 'fast'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_apollo -%}
{%- elif target_mode in ['3', 'artemis', 'lmed', 'low-medium', 'targeted'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_artemis -%}
{%- elif target_mode in ['4', 'athena', 'medium', 'med', 'balanced'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_athena -%}
{%- elif target_mode in ['5', 'prometheus', 'mhigh', 'medium-high', 'architect'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_prometheus -%}
{%- elif target_mode in ['6', 'solstice', 'high', 'deep', 'thorough'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_solstice -%}
{%- elif target_mode in ['7', 'hyperion', 'xhigh', 'extreme-high', 'rigorous', 'default'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_hyperion -%}
{%- elif target_mode in ['8', 'einstein', 'uhigh', 'ultra-high', 'solo-einstein'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_einstein -%}
{%- elif target_mode in ['9', 'oracle', 'amax', 'absolute-max', 'solo-oracle', 'proof'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_oracle -%}
{%- elif target_mode in ['swarm', 'einstein-swarm', '20-swarm', 'uhigh-swarm'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_swarm -%}
{%- elif target_mode in ['deep-swarm', 'oracle-swarm', 'council', 'amax-swarm', 'deep-research'] -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_deep_swarm -%}
{%- else -%}
{%- set current_thinking = not direct_instruct -%}
{%- set reasoning_instructions = inst_hyperion -%}
{%- endif -%}
{%- if store.explicit_thinking is defined and store.explicit_thinking is not none -%}
{%- set current_thinking = store.explicit_thinking -%}
{%- endif -%}
{{- bos -}}
{%- if reasoning_instructions -%}
{{- reasoning_instructions + '\n\n' -}}
{%- endif -%}
{%- if tools and tools is iterable and tools is not mapping -%}
{{ "## Tools\n\nYou have access to a set of tools to help answer the user's question. You can invoke tools by writing a \"<|DSML|tool_calls>\" block like the following:\n\n<|DSML|tool_calls>\n<|DSML|invoke name=\"$TOOL_NAME\">\n<|DSML|parameter name=\"$PARAMETER_NAME\" string=\"true|false\">$PARAMETER_VALUE</|DSML|parameter>\n...\n</|DSML|invoke>\n<|DSML|invoke name=\"$TOOL_NAME2\">\n...\n</|DSML|invoke>\n</|DSML|tool_calls>\n\nString parameters should be specified as is and set `string=\"true\"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string=\"false\"`.\n\n### Available Tool Schemas\n\n" }}
{%- for tool in tools -%}
{%- if tool.function is defined -%}
{{- tool.function | tojson -}}
{%- else -%}
{{- tool | tojson -}}
{%- endif -%}
{%- if not loop.last -%}{{- '\n' -}}{%- endif -%}
{%- endfor -%}
{{ "\n\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n\n" }}
{%- endif -%}
{%- set ns = namespace(system_content='', has_system=false, prev_role='') -%}
{%- for msg in store.messages -%}
{%- if msg.role == 'system' -%}
{%- if not ns.has_system -%}
{%- set ns.system_content = msg.content -%}
{%- set ns.has_system = true -%}
{%- else -%}
{%- set ns.system_content = ns.system_content + '\n\n' + msg.content -%}
{%- endif -%}
{%- endif -%}
{%- endfor -%}
{%- if ns.has_system and ns.system_content -%}
{{- ns.system_content -}}
{%- endif -%}
{%- for msg in store.messages -%}
{%- set idx = loop.index0 -%}
{%- if msg.role == 'user' or msg.role == 'developer' -%}
{{- '<|User|>' + msg.content -}}
{%- set ns.prev_role = 'user' -%}
{%- elif msg.role == 'assistant' -%}
{%- set r_content = msg.reasoning_content | trim -%}
{%- set m_content = msg.content | trim -%}
{%- if r_content and (preserve_thinking is undefined or preserve_thinking or idx > store.last_user_idx) -%}
{{- '<|Assistant|><think>' + r_content + '</think>' + m_content -}}
{%- else -%}
{{- '<|Assistant|>' + m_content -}}
{%- endif -%}
{%- if msg.tool_calls and msg.tool_calls is iterable and msg.tool_calls is not mapping -%}
{{- '\n\n<|DSML|tool_calls>' -}}
{%- for tc in msg.tool_calls -%}
{%- set tc_name = tc.function.name if tc.function is defined else tc.name -%}
{%- set tc_args = tc.function.arguments if tc.function is defined else tc.arguments -%}
{{- '\n<|DSML|invoke name="' + tc_name + '">' -}}
{%- if tc_args is mapping -%}
{%- for p_name, p_val in tc_args.items() -%}
{%- if p_val is string -%}
{{- '\n<|DSML|parameter name="' + p_name + '" string="true">' + p_val + '</|DSML|parameter>' -}}
{%- else -%}
{{- '\n<|DSML|parameter name="' + p_name + '" string="false">' + (p_val | tojson) + '</|DSML|parameter>' -}}
{%- endif -%}
{%- endfor -%}
{%- elif tc_args is string -%}
{{- '\n' + tc_args -}}
{%- endif -%}
{{- '\n</|DSML|invoke>' -}}
{%- endfor -%}
{{- '\n</|DSML|tool_calls>' -}}
{%- endif -%}
{{- eos -}}
{%- set ns.prev_role = 'assistant' -%}
{%- elif msg.role == 'tool' -%}
{%- if ns.prev_role != 'user' -%}
{{- '<|User|>' -}}
{%- endif -%}
{{- '<tool_result>' + msg.content + '</tool_result>' -}}
{%- set ns.prev_role = 'user' -%}
{%- endif -%}
{%- endfor -%}
{%- if add_generation_prompt -%}
{%- if current_thinking -%}
{{- '<|Assistant|><think>\n' -}}
{%- else -%}
{{- '<|Assistant|></think>' -}}
{%- endif -%}
{%- endif -%}