| [gMASK]<sop> |
| |
| |
| |
| |
| |
| {%- set soft_budget_contract -%} |
| PROTIUM OBJECTIVE-GATED REASONING CONTRACT: |
| 1. Target Anchor: At token 1, isolate the exact termination criteria — define what a completed, verified solution requires before executing. |
| 2. Forward-Only Solve: Advance directly along the deductive path. Systematically eliminate internal conversational monologues ("let's see", "hmm", "wait", "now let me check"). Discard rhetorical hesitation; execute continuous deductive steps. |
| 3. Anti-Pivot Invariant: Never emit reflexive hesitation pivots ("Wait...", "On second thought...", "Hold on...") unless a concrete mathematical, programmatic, or factual contradiction has been explicitly isolated. In the absence of an identified contradiction, maintain unbroken forward momentum. |
| 4. Active Disproof Gate: Never declare an answer complete on surface plausibility alone. Before unlocking exit, stress-test your candidate solution against the initial constraints and degenerate edge cases (nulls, zero, off-by-one, boundary limits, and trivial counterexamples). |
| 5. Objective Early Exit: The instant your solution withstands active constraint verification, terminate thinking immediately and deliver the final answer. Never pad, stall, or manufacture doubt once the proof holds. |
| 6. Delta-Only Correction: If a contradiction or constraint violation is encountered, isolate and repair only the specific broken variable. Never regress into circular overthinking loops or full restarts. |
| 7. Absolute Resolve: Formulate a definitive, decisive conclusion without hedging, equivocating, or artificial disclaimers. Correctness and crisp utility are the sole metrics. |
| {%- endset %} |
| |
| {%- set terse_core -%} |
| Operational Directives: |
| - Zero preamble, pleasantries, or question restatements. |
| - Deliver direct, unhedged answers with maximum information density. |
| - Retain all essential mathematical, programmatic, and logical technical rigor. |
| - If genuine ambiguity exists, resolve it along the most probable engineering standard or ask one targeted clarifying question. |
| {%- endset %} |
| |
| {%- set inst_hermes -%} |
| Reasoning effort: Hermes — [L1] (rapid instinct). |
| Mindset: High-velocity execution. Rapid sanity check of premise, arithmetic, or syntax — then commit immediately to the shortest verified bridge to the conclusion. Conclude immediately once obvious. |
| {%- endset %} |
| {%- set inst_apollo -%} |
| Reasoning effort: Apollo — [L2] (disciplined deduction). |
| Mindset: Structured, transparent logic. Isolate given constraints, trace linear implications with zero detour, and exit thinking the instant premise validation is reached. |
| {%- endset %} |
| {%- set inst_artemis -%} |
| Reasoning effort: Artemis — [L3] (boundary & failure audit). |
| Mindset: Rigorous boundary validation. Audit null/empty states, numeric limits, concurrency hazards, off-by-one errors, and malformed inputs. Fortify against edge cases, then terminate thinking immediately. |
| {%- endset %} |
| {%- set inst_athena -%} |
| Reasoning effort: Athena — [L4] (strategic architecture). |
| Mindset: Modular synthesis. Deconstruct requirements into structured sub-tasks with strict prerequisite dependency chains. Weigh concrete trade-offs (performance vs maintainability, latency vs throughput) and execute the optimal vector. |
| {%- endset %} |
| {%- set inst_prometheus -%} |
| Reasoning effort: Prometheus — [L5] (defensive engineering). |
| Mindset: Second-order systemic modeling. Anticipate upstream crashes, payload corruption, scaling cliffs, memory footprints, and lifecycle debt. Embed fault tolerance and graceful degradation directly into the design. |
| {%- endset %} |
| {%- set inst_solstice -%} |
| Reasoning effort: Solstice — [L6] (deep systemic derivation). |
| Mindset: Axiomatic derivation. Establish fundamental invariants, formulate distinct candidate architectures, stress-test each against boundary constraints, and converge on the dominant derivation with zero assumptions taken on faith. |
| {%- endset %} |
| {%- set inst_hyperion -%} |
| Reasoning effort: Hyperion — [L7] (first-principles synthesis). |
| Mindset: Comprehensive first-principles synthesis. Decompose problems to atomic ground truths. Maintain continuous forward momentum across all proof surfaces. Immediate exit the instant resolution is achieved. |
| {%- endset %} |
| {%- set inst_einstein -%} |
| Reasoning effort: Einstein — [L8] (theoretical mastery). |
| Mindset: Invariant reduction and breakthrough synthesis. Strip peripheral complexity to the bare mathematical and informational core. Construct the unified invariant model that resolves multi-stage complexity into one cohesive, unassailable derivation. |
| {%- endset %} |
| {%- set inst_oracle -%} |
| Reasoning effort: Oracle — [L9] (proof-grade authority). |
| Mindset: Exhaustive formal verification. Atomic proofs, invariant proofs, complete edge falsification, and 100% complete implementation without placeholders. Think as long as genuine proof requires; close immediately once established. |
| {%- endset %} |
| {%- set inst_proteus -%} |
| Reasoning effort: Proteus — [L10] (autonomous freehand reasoning; default). |
| Mindset: Freehand cognitive autonomy. You are not bound by artificial tiers, rigid categories, or predetermined quotas. Freehand exactly the depth, structure, and rigor required by the problem's own constraints: |
| - Autonomous Execution: Seamlessly weave whatever analytical techniques the solution demands—boundary audits, architectural trade-offs, defensive modeling, or axiomatic proofs—without categorizing yourself into rigid stages. |
| - Unbroken Forward Momentum: Eliminate all self-conversational chatter ("let's see", "hmm", "wait"). Advance strictly through deductive steps. |
| - Active Verification & Exit: Stress-test your derivation against initial boundary constraints; the millisecond the solution is verified and holds, terminate thinking immediately and deliver the final answer. |
| {%- endset %} |
| {%- set inst_swarm -%} |
| Reasoning effort: Swarm — 20-perspective divergent swarm (specialized mode). |
| Mindset: Four-phase convergent breakdown. Phase 1: Disassembly to core parameters. Phase 2: Divergent multi-angle simulation (logician, systems engineer, red-teamer, optimizer, critic). Phase 3: Cross-pollination and tension resolution. Phase 4: Convergence onto master deliverable. |
| Output contract: Conclude thinking and open final response with "[SWARM VERDICT]" followed by a decisive synthesis naming the winning vector and the primary objection survived. |
| {%- endset %} |
| {%- set inst_deep_swarm -%} |
| Reasoning effort: Council — adversarial research council (specialized mode). |
| Mindset: Five-protocol institutional deliberation. Protocol 1: Parameter calibration and success criteria. Protocol 2: Multi-specialist panel assembly. Protocol 3: Adversarial debate and stress-testing. Protocol 4: Trade-off scoring matrix. Protocol 5: Master architecture. |
| Output contract: Conclude thinking and open final response with "[COUNCIL VERDICT]" followed by the definitive ruling, key justification, and dissenting risk accounted for. |
| {%- endset %} |
| |
| {%- set reg_ns = namespace(active=false) %} |
| {%- if (regular is defined and regular) or (mode is defined and mode in ('regular', 'vanilla', 'standard', 'default', 'clean')) %} |
| {%- set reg_ns.active = true %} |
| {%- endif %} |
| {%- for msg in messages %} |
| {%- if msg.content is string and ('[regular]' in msg.content or '[REGULAR]' in msg.content or '[vanilla]' in msg.content or '[standard]' in msg.content or '[default]' in msg.content) %} |
| {%- set reg_ns.active = true %} |
| {%- endif %} |
| {%- endfor %} |
| {%- set is_explicit_regular = reg_ns.active %} |
| {%- set store = namespace(reasoning_effort=reasoning_effort|default(''), enable_thinking=enable_thinking|default(true)) -%} |
| {%- for msg in messages -%} |
| {%- set txt = msg.content if msg.content is string else '' -%} |
| {%- if '{REASON:' in txt -%} |
| {%- set parts = txt.split('{REASON:') -%} |
| {%- set tag_inner = parts[1].split('}')[0] | lower | trim -%} |
| {%- if tag_inner.startswith('i') and tag_inner | length > 1 -%} |
| {%- set store.reasoning_effort = tag_inner[1:] -%} |
| {%- set store.enable_thinking = false -%} |
| {%- else -%} |
| {%- set store.reasoning_effort = tag_inner -%} |
| {%- endif -%} |
| {%- elif '[MODE:' in txt -%} |
| {%- set parts = txt.split('[MODE:') -%} |
| {%- set tag_inner = parts[1].split(']')[0] | lower | trim -%} |
| {%- set store.reasoning_effort = tag_inner -%} |
| {%- endif -%} |
| {%- set txt_low = txt | lower -%} |
| {%- if '[l10]' in txt_low -%} |
| {%- set store.reasoning_effort = '10' -%} |
| {%- else -%} |
| {%- for n in range(10) -%} |
| {%- if '[l' ~ n ~ ']' in txt_low -%} |
| {%- set store.reasoning_effort = n | string -%} |
| {%- if n == 0 -%}{%- set store.enable_thinking = false -%}{%- endif -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- set target_mode = store.reasoning_effort | default(thinking_level|default('10')) | string | lower | trim -%} |
| {%- set current_thinking = store.enable_thinking -%} |
| {%- if is_explicit_regular or target_mode in ['0', 'mortal', 'disabled', 'none', 'off', 'zero', 'direct', 'chat', 'regular', 'vanilla', 'standard', 'default', 'clean'] -%} |
| {%- set current_thinking = false -%} |
| {%- set reasoning_instructions = '' -%} |
| {%- elif target_mode in ['10', 'proteus', 'dynamic', 'auto', 'adaptive', 'fluid', 'default'] -%} |
| {%- set reasoning_instructions = inst_proteus -%} |
| {%- elif target_mode in ['1', 'hermes', 'ulow', 'ultra-low', 'micro', 'minimal'] -%} |
| {%- set reasoning_instructions = inst_hermes -%} |
| {%- elif target_mode in ['2', 'apollo', 'low', 'compact', 'fast'] -%} |
| {%- set reasoning_instructions = inst_apollo -%} |
| {%- elif target_mode in ['3', 'artemis', 'lmed', 'low-medium', 'targeted'] -%} |
| {%- set reasoning_instructions = inst_artemis -%} |
| {%- elif target_mode in ['4', 'athena', 'medium', 'med', 'balanced'] -%} |
| {%- set reasoning_instructions = inst_athena -%} |
| {%- elif target_mode in ['5', 'prometheus', 'mhigh', 'medium-high', 'architect'] -%} |
| {%- set reasoning_instructions = inst_prometheus -%} |
| {%- elif target_mode in ['6', 'solstice', 'high', 'deep', 'thorough'] -%} |
| {%- set reasoning_instructions = inst_solstice -%} |
| {%- elif target_mode in ['7', 'hyperion', 'xhigh', 'extreme-high', 'rigorous', 'default'] -%} |
| {%- set reasoning_instructions = inst_hyperion -%} |
| {%- elif target_mode in ['8', 'einstein', 'uhigh', 'ultra-high', 'solo-einstein'] -%} |
| {%- set reasoning_instructions = inst_einstein -%} |
| {%- elif target_mode in ['9', 'oracle', 'amax', 'absolute-max', 'solo-oracle', 'proof'] -%} |
| {%- set reasoning_instructions = inst_oracle -%} |
| {%- elif target_mode in ['swarm', 'einstein-swarm', '20-swarm', 'uhigh-swarm'] -%} |
| {%- set reasoning_instructions = inst_swarm -%} |
| {%- elif target_mode in ['deep-swarm', 'oracle-swarm', 'council', 'amax-swarm', 'deep-research'] -%} |
| {%- set reasoning_instructions = inst_deep_swarm -%} |
| {%- else -%} |
| {%- set reasoning_instructions = inst_proteus -%} |
| {%- endif -%} |
| {%- if reasoning_instructions -%}<|system|>{{ reasoning_instructions }}{%- endif -%} |
| {%- if tools -%} |
| {%- macro tool_to_json(tool) -%} |
| {%- set ns_tool = namespace(first=true) -%} |
| {{ '{' -}} |
| {%- for k, v in tool.items() -%} |
| {%- if k != 'defer_loading' and k != 'strict' -%} |
| {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%} |
| {%- set ns_tool.first = false -%} |
| "{{ k }}": {{ v | tojson(ensure_ascii=False) }} |
| {%- endif -%} |
| {%- endfor -%} |
| {{- '}' -}} |
| {%- endmacro -%} |
| {%- macro tool_references_to_response(refs) -%} |
| {{- '<tool_response><tools>\n' -}} |
| {%- for tr in refs -%} |
| {%- for tool in tools -%} |
| {%- if 'function' in tool -%} |
| {%- set tool = tool['function'] -%} |
| {%- endif -%} |
| {%- if tool.name == tr.name -%} |
| {{- tool_to_json(tool) + '\n' -}} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- endfor -%} |
| {{- '</tools></tool_response>' -}} |
| {%- endmacro -%} |
| <|system|> |
| # Tools |
| |
| You may call one or more functions to assist with the user query. |
| |
| You are provided with function signatures within <tools></tools> XML tags: |
| <tools> |
| {% for tool in tools %} |
| {%- if 'function' in tool -%} |
| {%- set tool = tool['function'] -%} |
| {%- endif -%} |
| {% if tool.defer_loading is not defined or not tool.defer_loading %} |
| {{ tool_to_json(tool) }} |
| {% endif %} |
| {% endfor %} |
| </tools> |
| |
| For each function call, output the function name and arguments within the following XML format: |
| <tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%} |
| {%- macro emit_image() -%}<|begin_of_image|><|image|><|end_of_image|>{%- endmacro -%} |
| {%- macro emit_video() -%}<|begin_of_video|><|video|><|end_of_video|>{%- endmacro -%} |
| {%- macro emit_audio() -%}<|begin_of_audio|><|end_of_audio|>{%- endmacro -%} |
| {%- macro strip_ctrl(t) -%} |
| {{- t | replace('[regular]', '') | replace('[REGULAR]', '') | replace('[vanilla]', '') | replace('[standard]', '') | replace('[default]', '') -}} |
| {%- endmacro -%} |
| {%- macro visible_text(content) -%} |
| {%- if content is string -%} |
| {{- strip_ctrl(content) -}} |
| {%- elif content is iterable and content is not mapping -%} |
| {%- for item in content -%} |
| {%- if item is mapping and item.type == 'text' -%} |
| {{- item.text -}} |
| {%- elif item is string -%} |
| {{- item -}} |
| {%- elif item is mapping and item.type in ['image', 'image_url'] -%} |
| {{- emit_image() -}} |
| {%- elif item is mapping and item.type in ['video', 'video_url'] -%} |
| {{- emit_video() -}} |
| {%- elif item is mapping and item.type in ['audio', 'audio_url', 'input_audio'] -%} |
| {{- emit_audio() -}} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- else -%} |
| {{- content }} |
| {%- endif -%} |
| {%- endmacro -%} |
| {%- macro tool_response(text) -%} |
| {{- '<tool_response>' + text + '</tool_response>' -}} |
| {%- endmacro -%} |
| {%- macro render_tool_response(m) -%} |
| {%- if m.content is string -%} |
| {{- tool_response(m.content) -}} |
| {%- elif m.content and m.content is not mapping and m.content.0.type == "tool_reference" -%} |
| {{- tool_references_to_response(m.content) -}} |
| {%- elif is_list_of_outputs(m) -%} |
| {%- for tr in m.content -%} |
| {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == "tool_reference" -%} |
| {{- tool_references_to_response(tr.output) -}} |
| {%- else -%} |
| {{- tool_response(visible_text(tr.output)) -}} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- else -%} |
| {{- tool_response(visible_text(m.content)) -}} |
| {%- endif -%} |
| {%- endmacro -%} |
| {%- macro id_of(obj) -%} |
| {%- if obj.tool_call_id -%} |
| {{- obj.tool_call_id -}} |
| {%- elif obj.id -%} |
| {{- obj.id -}} |
| {%- endif -%} |
| {%- endmacro -%} |
| {%- macro is_list_of_outputs(m) -%} |
| {%- if m.content and m.content.0.output is defined -%}1{%- endif -%} |
| {%- endmacro -%} |
| {%- macro has_dup_tool_result_id(lo, hi, target) -%} |
| {%- set ns_cnt = namespace(n=0) -%} |
| {%- for k in range(lo, hi + 1) -%} |
| {%- set m = messages[k] -%} |
| {%- if is_list_of_outputs(m) -%} |
| {%- for entry in m.content -%} |
| {%- if id_of(entry) == target -%} |
| {%- set ns_cnt.n = ns_cnt.n + 1 -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- elif id_of(m) == target -%} |
| {%- set ns_cnt.n = ns_cnt.n + 1 -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- if ns_cnt.n > 1 -%}1{%- endif -%} |
| {%- endmacro -%} |
| {%- macro tc_id_exists(tcs, target) -%} |
| {%- set ns_f = namespace(found=false) -%} |
| {%- for tc in tcs -%} |
| {%- if id_of(tc) == target -%} |
| {%- set ns_f.found = true -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- if ns_f.found -%}1{%- endif -%} |
| {%- endmacro -%} |
| {%- set ns = namespace(last_user_index=-1) -%} |
| {%- for m in messages %} |
| {%- if m.role == 'user' %} |
| {%- set ns.last_user_index = loop.index0 -%} |
| {%- endif %} |
| {%- endfor %} |
| {%- for m in messages -%} |
| {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }} |
| {%- elif m.role == 'assistant' -%} |
| <|assistant|> |
| {%- set content = visible_text(m.content) %} |
| {%- if m.reasoning_content is string %} |
| {%- set reasoning_content = m.reasoning_content %} |
| {%- elif '</think>' in content %} |
| {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %} |
| {%- set content = content.split('</think>')[-1] %} |
| {%- endif %} |
| {%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%} |
| {{ '<think>' + reasoning_content + '</think>'}} |
| {%- else -%} |
| {{ '<think></think>' }} |
| {%- endif -%} |
| {%- if content.strip() -%} |
| {{ content.strip() }} |
| {%- endif -%} |
| {% if m.tool_calls %} |
| {% for tc in m.tool_calls %} |
| {%- if tc.function %} |
| {%- set tc = tc.function %} |
| {%- endif %} |
| {{- '<tool_call>' + tc.name -}} |
| {% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %} |
| {% endif %} |
| {%- elif m.role == 'tool' -%} |
| {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} |
| {{- '<|observation|>' -}} |
| {%- set block_start = loop.index0 -%} |
| {%- set ns_blk = namespace(end=block_start, is_tool=true) -%} |
| {%- for j in range(block_start, messages|length) -%} |
| {%- if messages[j].role == 'tool' and ns_blk.is_tool -%} |
| {%- set ns_blk.end = j -%} |
| {%- else -%} |
| {%- set ns_blk.is_tool = false -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- set ns_a = namespace(tool_calls=none) -%} |
| {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%} |
| {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%} |
| {%- endif -%} |
| {%- set ns_chk = namespace(can_sort=true) -%} |
| {%- if not ns_a.tool_calls -%} |
| {%- set ns_chk.can_sort = false -%} |
| {%- else -%} |
| {%- for k in range(block_start, ns_blk.end + 1) -%} |
| {%- set m = messages[k] -%} |
| {%- if is_list_of_outputs(m) -%} |
| {%- for entry in m.content -%} |
| {%- set eid = id_of(entry) -%} |
| {%- if not eid -%} |
| {%- set ns_chk.can_sort = false -%} |
| {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%} |
| {%- set ns_chk.can_sort = false -%} |
| {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%} |
| {%- set ns_chk.can_sort = false -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- else -%} |
| {%- set tk_id = id_of(m) -%} |
| {%- if not tk_id -%} |
| {%- set ns_chk.can_sort = false -%} |
| {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%} |
| {%- set ns_chk.can_sort = false -%} |
| {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%} |
| {%- set ns_chk.can_sort = false -%} |
| {%- endif -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- for i in range(ns_a.tool_calls | length) -%} |
| {%- set tc_id = id_of(ns_a.tool_calls[i]) -%} |
| {%- if not tc_id -%} |
| {%- set ns_chk.can_sort = false -%} |
| {%- endif -%} |
| {%- for j in range(i + 1, ns_a.tool_calls | length) -%} |
| {%- if id_of(ns_a.tool_calls[j]) == tc_id -%} |
| {%- set ns_chk.can_sort = false -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- endfor -%} |
| {%- endif -%} |
| {%- if ns_chk.can_sort -%} |
| {%- for tc in ns_a.tool_calls -%} |
| {%- set tc_id = id_of(tc) -%} |
| {%- for k in range(block_start, ns_blk.end + 1) -%} |
| {%- set m = messages[k] -%} |
| {%- if is_list_of_outputs(m) -%} |
| {%- for entry in m.content -%} |
| {%- set eid = id_of(entry) -%} |
| {%- if eid == tc_id -%} |
| {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == "tool_reference" -%} |
| {{- tool_references_to_response(entry.output) -}} |
| {%- else -%} |
| {{- tool_response(visible_text(entry.output)) -}} |
| {%- endif -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- else -%} |
| {%- set tk_id = id_of(m) -%} |
| {%- if tk_id == tc_id -%} |
| {{- render_tool_response(m) -}} |
| {%- endif -%} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- endfor -%} |
| {%- else -%} |
| {%- for k in range(block_start, ns_blk.end + 1) -%} |
| {{- render_tool_response(messages[k]) -}} |
| {%- endfor -%} |
| {%- endif -%} |
| {% endif -%} |
| {%- elif m.role == 'system' -%} |
| <|system|>{{ visible_text(m.content) }} |
| {%- endif -%} |
| {%- endfor -%} |
| {%- if add_generation_prompt -%} |
| {% if is_explicit_regular %}<|assistant|>{% elif not current_thinking %}<|assistant|>{{ '<think></think>' }}{% else %}<|assistant|>{{ '<think>' }}{% endif %} |
| {%- endif -%} |
| |
