feat: update templates/gemma.jinja with Protium-1.0 Objective-Gated Protocol

templates/gemma.jinja

@@ -1,32 +1,24 @@
-{%- set template_version = template_version if template_version is defined else "hypersynapse-sas-v3.0.0-soft-spectrum" %}
+{%- set template_version = template_version if template_version is defined else "protium-v1.0.0-objective-gated" %}
 
 {#- ========================================================================== -#}
-{#- HYPER SYNAPSE — SAS v3.0 "SOFT SPECTRUM"                                    -#}
-{#- Solstice-AI Cognitive Architecture for Qwen3.8-family ChatML models.        -#}
-{#- Render pipeline lineage: qwen3.8-froggeric-v22.5.0 (DavidAU, MIT).          -#}
+{#- PROTIUM-1.0 — OBJECTIVE-GATED COGNITIVE ARCHITECTURE                        -#}
+{#- Solstice-AI Zero-Waste Protocol for High-Efficiency Reasoning Models       -#}
+{#- Named after Protium (1H): Zero Neutrons. Zero Dead Weight. Pure Thrust.    -#}
+{#- Lineage: qwen3.8-froggeric-v22.5.0 (DavidAU, MIT) -> Solstice-AI           -#}
 {#-                                                                             -#}
-{#- DESIGN CONTRACT (v3.0):                                                     -#}
-{#-   1. NO HARD BOUNDS. Every reasoning budget is a soft share of the model's  -#}
-{#-      own output ("roughly a third to half of your output"), elastic in both -#}
-{#-      directions. Never a token quota. Never a word floor. Never a ceiling.  -#}
-{#-   2. VARIABLE THINKING. Depth is continuous: any integer 10-100 maps onto   -#}
-{#-      the level spectrum. 0-9 remain legacy level numbers. Named levels,     -#}
-{#-      swarm modes, runtime kwargs and inline tags all resolve to one state.  -#}
-{#-   3. ONE SOURCE OF TRUTH. Inline tags, {REASON:} / [MODE:] prefixes and     -#}
-{#-      the reasoning_effort / thinking_level kwargs all feed the SAME         -#}
-{#-      resolver (S1). Later signals in the conversation override earlier      -#}
-{#-      ones, so depth can be re-escalated mid-chat.                           -#}
-{#-   4. DEPTH-TOOL COUPLING. (a) With tools attached and NO explicit depth     -#}
-{#-      signal, depth auto-collapses to L4 (tool work wants discipline, not    -#}
-{#-      essays). (b) Two or more consecutive tool failures auto-escalate depth -#}
-{#-      one band (capped at L7). Swarm/council modes are never auto-tuned.     -#}
+{#- CORE TENETS:                                                                -#}
+{#-   1. TOKEN 1 TARGET ANCHOR: Lock the termination condition at step 1.       -#}
+{#-   2. FORWARD-ONLY SOLVE: Advance directly toward the target. Eliminate      -#}
+{#-      conversational filler ("let's see", "hmm", "wait"). No rhetorical     -#}
+{#-      hesitation; execute pure continuous deduction.                         -#}
+{#-   3. EARLY EXIT GATE: Terminate thinking the instant the target condition   -#}
+{#-      is satisfied and verified. Never dwell, stall, or manufacture doubt.   -#}
+{#-   4. DELTA-ONLY CORRECTION: Fix only the broken variable upon contradiction;-#}
+{#-      never regress into full restarts or circular overthinking loops.       -#}
+{#-   5. ABSOLUTE RESOLVE: Decisive, unhedged final delivery. Zero preamble.    -#}
 {#-                                                                             -#}
-{#- CANONICAL VOCABULARY: [L0]..[L9], 'swarm', 'council', integer 10-100.       -#}
-{#- COMPAT ALIASES (resolve inward, documented below): ulow..amax, einstein,    -#}
-{#- spoon, deep-research, i-prefixed silent modes, legacy think-tags.           -#}
-{#-                                                                             -#}
-{#- THE SPECTRUM (soft shares of total output, elastic both directions):        -#}
-{#-   [L0] Mortal     - thinking off; answer directly.                          -#}
+{#- THE SPECTRUM (soft share of output, elastic both directions):               -#}
+{#-   [L0] Mortal     - thinking off; execute directly.                         -#}
 {#-   [L1] Hermes     - rapid instinct.        usually under ~10% of output.    -#}
 {#-   [L2] Apollo     - crisp logic.           roughly ~10-25% of output.       -#}
 {#-   [L3] Artemis    - edge-case hunting.     roughly ~20-40% of output.       -#}
@@ -35,7 +27,7 @@
 {#-   [L6] Solstice   - deep derivation.       roughly ~50-70% of output.       -#}
 {#-   [L7] Hyperion   - first principles       roughly ~60-85% of output.       -#}
 {#-                     (default).                                              -#}
-{#-   [L8] Einstein   - solo mastery.          often most of the output.        -#}
+{#-   [L8] Einstein   - theoretical mastery.   dominates output when required.  -#}
 {#-   [L9] Oracle     - proof-grade rigour.    as much as genuine proof demands.-#}
 {#-   swarm            - 20-perspective divergent swarm, verdict line.           -#}
 {#-   council          - adversarial research council, verdict line.             -#}
@@ -43,12 +35,11 @@
 {#- CONTINUOUS DEPTH MAP (10-100):  1-14 L1 | 15-29 L2 | 30-44 L3 | 45-59 L4 |  -#}
 {#-    60-69 L5 | 70-79 L6 | 80-89 L7 | 90-96 L8 | 97-100 L9 | 0 = off.         -#}
 {#-                                                                             -#}
-{#- INLINE SYNTAX (case-insensitive, stripped before the model sees them):      -#}
-{#-    think on/off/minimal/low/medium/high/xhigh/ultracode/extreme/max         -#}
+{#- INLINE SYNTAX (case-insensitive, stripped before model sees them):          -#}
 {#-    [L0]..[L9] | {REASON:level|name|number} | [MODE:level|name|number]       -#}
-{#-    Prefix 'i' = silent variant: {REASON:i8} runs L8 quality, thinking off.  -#}
-{#- PRECEDENCE: default L7  <  runtime kwarg (session baseline)  <  inline      -#}
-{#-    signals, last one in conversation order wins.                            -#}
+{#-    [regular] | [vanilla] | [standard] | [default]                           -#}
+{#-    Prefix 'i' = silent variant: {REASON:i8} runs L8 rigor, thinking hidden. -#}
+{#- PRECEDENCE: default L7  <  runtime kwarg  <  inline signals (last wins).    -#}
 {#- ========================================================================== -#}
 
 {#- ------------------------------------------------------------------ -#}
@@ -194,82 +185,67 @@
 {#- ================================================================== -#}
 
 {%- set soft_budget_contract -%}
-REASONING BUDGET CONTRACT (SOFT — NEVER A HARD LIMIT):
-- Reasoning depth at this level is guided as a typical SHARE of your total output for this reply. The share is elastic in both directions: a trivial task may need far less than the guide, a genuinely hard task may need more.
-- Shares are calibration, not quotas. Never truncate real reasoning to stay under a share. Never pad, stall, or manufacture doubt to reach one.
-- Scale continuously with genuine complexity. Think exactly as long as thinking earns its place, then answer. Usefulness and correctness are the only true bounds.
+PROTIUM OBJECTIVE-GATED REASONING CONTRACT:
+1. Target Anchor: At token 1, isolate the exact success condition — define what a verified, completed solution entails.
+2. Forward-Only Solve: Advance directly toward the target. Eliminate self-conversational chatter ("let's see", "hmm", "wait", "now let me check"). Discard rhetorical hesitation; execute continuous deductive steps.
+3. Early Exit Gate: The instant the target condition is met and verified, terminate thinking immediately and emit the final response. Never dwell, pad, or re-verify what has already been proven.
+4. Delta-Only Correction: If a contradiction or constraint violation is encountered, isolate and repair only the specific broken variable. Never regress into full restarts or circular overthinking loops.
+5. Absolute Resolve: Formulate a definitive, decisive conclusion without hedging, equivocating, or artificial disclaimers. Correctness and crisp utility are the only metrics.
 {%- endset %}
 
 {%- set terse_core -%}
-Never: open with preamble or pleasantries; restate the question; add filler transitions; hedge with niceties; or repeat a point you've already made.
-Always: keep essential steps, caveats, uncertainties, and specifics — never drop correctness or a needed warning for brevity. Use the least structure that conveys the answer. If a request is genuinely ambiguous, ask a sharp question, don't guess.
+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 precision. One quick sanity pass over the core ask — spot-check the premise, the arithmetic, the syntax — then commit to the shortest verified route to the answer.
-Depth guide: keep visible reasoning to a light touch — usually under a tenth of your output, and near zero when the answer is obvious. Spend only what correctness demands.
+Mindset: High-velocity execution. Rapid sanity check of premise, arithmetic, or syntax — then commit immediately to the shortest verified bridge to the conclusion. Conclude in a light single-digit share of output; zero when obvious.
 {%- endset %}
 {%- set inst_apollo -%}
-Reasoning effort: Apollo — [L2] (crisp logic and clarity).
-Mindset: transparent, disciplined deduction. Isolate constraints and givens, trace each premise to its implication, and eliminate ambiguity by choosing the most standard productive interpretation.
-Depth guide: compact and focused — roughly a tenth to a quarter of your output, tuned to how tangled the constraints actually are. Conclude as soon as the premise is validated.
+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 (typically 10-25% of output).
 {%- endset %}
 {%- set inst_artemis -%}
-Reasoning effort: Artemis — [L3] (precision edge-case hunter).
-Mindset: boundary and failure-mode audit. Probe zero/negative/overflow conditions, null and empty states, concurrency collisions, off-by-one traps, and degenerate inputs before accepting any hypothesis; fortify what you find.
-Depth guide: measured scrutiny — roughly a fifth to two-fifths of your output, scaling with how many real edge surfaces the task has. Hunt hard, then close.
+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 (roughly 20-40% of output).
 {%- endset %}
 {%- set inst_athena -%}
-Reasoning effort: Athena — [L4] (strategic synthesis and balance).
-Mindset: architectural balance. Decompose the request into modular sub-tasks with explicit prerequisite chains; weigh genuine trade-offs (performance vs readability, latency vs throughput, simplicity vs flexibility) and justify the chosen path.
-Depth guide: balanced deliberation — roughly a third to half of your output, expanding with the number of real decision axes. Every step must produce valid input for the next.
+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 (roughly 30-50% of output).
 {%- endset %}
 {%- set inst_prometheus -%}
-Reasoning effort: Prometheus — [L5] (architectural forethought).
-Mindset: defensive engineering. Model second-order effects and failure modes before building: upstream crashes, malformed payloads, scale jumps, memory and cache pressure, technical debt. Integrate fault tolerance and graceful degradation into the design itself.
-Depth guide: systemic forethought — roughly two-fifths to three-fifths of your output, growing with blast radius and life-cycle stakes of the change.
+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 (roughly 40-60% of output).
 {%- endset %}
 {%- set inst_solstice -%}
 Reasoning effort: Solstice — [L6] (deep systemic derivation).
-Mindset: nothing on faith. Declare the foundational axioms, generate at least two fundamentally distinct approaches, analyse each on its merits, then red-team the leading hypothesis — actively seek counterexamples and boundary contradictions before tightening the final derivation.
-Depth guide: continuous deep derivation — roughly half to seventy percent of your output, stretching with proof depth. Full runway for formal traces; stop the moment certainty is reached.
+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 (roughly 50-70% of output).
 {%- endset %}
 {%- set inst_hyperion -%}
 Reasoning effort: Hyperion — [L7] (first-principles synthesis; default).
-Mindset: foundational synthesis. Decompose the problem to its root cause from first principles, stress-test the logic against every plausible path, adversarial input, and edge case, and document intermediate steps, considered alternatives, and rejected hypotheses as you go.
-Depth guide: majority-of-output reasoning — typically three-fifths to four-fifths of your reply, wholly elastic to real difficulty. No shortcuts while uncertainty remains; immediate closure once it doesn't.
+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 (typically 60-85% of output).
 {%- endset %}
 {%- set inst_einstein -%}
-Reasoning effort: Einstein — [L8] (solo theoretical mastery).
-Mindset: breakthrough derivation in pure solo mode — radical first-principles intuition, lateral synthesis, and mathematical transcendence without persona clutter. Strip conventional dogma to the bare informational constraints; look for the elegant unified model that collapses multi-stage complexity into one coherent solution; carry every deduction to an unassailable conclusion including edge and asymptotic behaviour.
-Depth guide: reasoning commonly dominates the reply — often three-fifths to nine-tenths of output — but stays a guide, not a target: derive exactly as long as the theory demands, then deliver.
+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 exhaustive rigour).
-Mindset: definitive authority. Decompose the problem to atomic constituents; verify every assumption, lemma, and invariant; systematically falsify each step against worst-case inputs and degenerate states; deliver the complete, finalized, proof-grade solution with total implementation completeness.
-Depth guide: unbounded by design — the reasoning may justly be the clear majority of the output, stretching as far as genuine proof demands and not one token further. Rigour is the only metric; padding is failure.
+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_swarm -%}
 Reasoning effort: Swarm — 20-perspective divergent swarm (specialized mode).
-Mindset: breakthrough problem solving through structured divergence and convergence.
-Phase 1 — Disassembly: strip the problem of conventional paradigms; isolate the bare informational core.
-Phase 2 — Perspective activation: internally simulate a divergent swarm of specialist voices — analytical logician, creative maverick, systems engineer, adversarial red-teamer, systems-dynamics modeller, algorithmic optimizer, human-factors critic, and kindred perspectives as the problem demands.
-Phase 3 — Cross-pollination: force creative collisions between the strongest divergent concepts; synthesize hybrids that resolve real tensions between speed, memory, cost, and correctness.
-Phase 4 — Convergence: solidify the highest-conviction breakthrough into a master-grade deliverable.
-Depth guide: the swarm fills as much of the output as genuine exploration earns — commonly the majority for open-ended challenges — with every phase sized freely by what the problem actually needs. No phase is ever trimmed short or artificially extended.
-Output contract: reason through the four phases, then close your reasoning and open the final answer with the line "[SWARM VERDICT]" followed by a one-paragraph synthesis naming the winning direction and the single strongest objection it survived.
+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 — deep-swarm adversarial research council (specialized mode).
-Mindset: simulate an exhaustive multi-expert research institute and produce verified, proof-grade, definitive results.
-Protocol 1 — Calibration: rate the task's complexity honestly; set explicit domain boundaries and success criteria before any deliberation.
-Protocol 2 — Panel: assemble a compact council of complementary virtual specialists tailored to this prompt (domain principal, formal-methods critic, systems architect, security/compliance lead, final synthesizer).
-Protocol 3 — Adversarial deliberation: let the council debate, expose hidden assumptions, challenge lazy consensus, and trace proofs to their roots.
-Protocol 4 — Candidate matrix: formulate several genuinely distinct candidate architectures; score each on correctness, completeness, efficiency, and robustness; document the winning trade-off.
-Protocol 5 — Master deliverable: present the definitive result with clear structure and complete implementation.
-Depth guide: deliberation may justly occupy the bulk of the output for hard problems and shrink to a focused pass for easy ones — always governed by what verification actually requires, never by a quota.
-Output contract: deliberate through the five protocols, then open the final answer with the line "[COUNCIL VERDICT]" followed by the council's ruling, the decisive argument, and the loudest dissent the ruling overcame.
+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 %}
 
 {#- ================================================================== -#}
@@ -607,7 +583,8 @@ Output contract: deliberate through the five protocols, then open the final answ
     {%- set _suppress_tools = _runtime_tool_protocol %}
 {%- endif %}
 
-{{- bos_token -}}\n{#- System emission: profile + soft contract + tools. -#}
+{#- System emission: profile + soft contract + tools. -#}
+{{- bos_token -}}
 {%- if reasoning_instructions or _sc or (_has_tools and not _suppress_tools) %}
     {{- '<start_of_turn>system\n' }}
     {%- if reasoning_instructions %}
@@ -836,7 +813,7 @@ Output contract: deliberate through the five protocols, then open the final answ
             {%- set ns2.consecutive_failures = 0 %}
         {%- endif %}
         {%- if ns2.prev_role != 'tool' %}
-            {{- '<start_of_turn>user\n' }}
+            {{- '<|im_start|>user' }}
         {%- endif %}
         {%- set _is_json_payload = (_tool_format == 'json' and content | trim | length > 0 and (content | trim)[:1] in ('{', '[')) %}
         {%- if not _is_json_payload and max_tool_response_chars > 0 and content | length > max_tool_response_chars %}