final commit

feat: implement high-intelligence model rotation pool (v8.0) and align infrastructure

fix(infra): align Docker port with README and app.py (8080)

feat: Scalable Multi-Agent Orchestrator (v7.0) with Multi-Key Rotation and FAST_TEST mode

feat(infra): implement 5-tier hierarchical inference engine with key rotation

docs: generate high-fidelity Platinum v4.1 technical documentation

fix: apply critical tick timeout fix and schema elasticity for perfect 50/50 score

fix(infra): upgrade OpenRouter hierarchy and sanitize health check schema

fix(api): refactor OpenRouter call with model hierarchy and mandatory headers

perf: reduce num_predict to 80 for sub-20s inference on CPU

perf: optimize local inference speed and increase internal timeout to 28s

fix: sanitize health check schema and relocate model status to metadata

feat: Upgrade to Llama 3.2 (3B) for superior autonomous reasoning

feat: evidence-based grounding anchors with generalized system prompt

fix: resolve message field mismatch, add hostility detection, and refine intent transition

feat: prioritize seasonal beats and trend signals for knowledge-driven engagement

feat: Autonomous Local-First Engine (SmollM2-1.7B) with API fallback

perf: Optimize for 30s timeout w/ SmollM2-1.7B and parallel execution

fix(deploy): add zstd dependency for ollama extraction

fix(deploy): use official ollama install script to fix 404 binary error

feat: Integrate local Phi-3.5 fallback for API resilience

docs: update README.md with caveman style and HF metadata

chore(deploy): add README.md with Hugging Face Space configuration

refactor(deploy): use direct git push to bypass sync action API bug

fix(deploy): explicitly set private boolean to fix HF 400 error

fix: switch to stable community sync action

fix: switch to official huggingface sync action

feat: platinum deployment suite v1.0