29ff50c63d
Some checks failed
Docker Build and Publish / build-and-push (pull_request) Has been skipped
Nix / nix (ubuntu-latest) (pull_request) Failing after 3s
Supply Chain Audit / Scan PR for supply chain risks (pull_request) Failing after 1m6s
Tests / e2e (pull_request) Successful in 2m0s
Tests / test (pull_request) Failing after 33m14s
Nix / nix (macos-latest) (pull_request) Has been cancelled
Implements adaptive retrieval strategy that adjusts prefetch behavior based on context pressure. With models at 128K-1M context windows, always prefetching RAG is wasteful when context is empty and insufficient when context is full. Core changes: - agent/context_strategy.py: Strategy module with ContextBudget, compute_prefetch_params(), should_prefetch() - STUFF/HYBRID/SELECTIVE tiers based on context pressure (30%/70% thresholds) - agent/memory_manager.py: set_context_budget() method + adaptive prefetch in prefetch_all() with provider fallback for non-supporting - plugins/memory/holographic: Accept limit/min_trust kwargs in prefetch() - run_agent.py: Wire context_compressor state to memory_manager before prefetch_all() call - tools/context_strategy.py: Agent-facing tool with task classification (crisis/factual/creative/analysis) and decision engine with 6 rules Research basis: - Self-RAG (Asai et al., 2023) - arxiv 2310.11511 - Long Context vs RAG Decision Framework (Timmy Foundation #4.3) - FrugalGPT - arxiv 2305.05176 Tests: 19 new tests pass. Full context strategy, prefetch params, should_prefetch decision logic, and strategy report generation. Impact: Ratio 4.0 (Impact 4, Effort 1). Eliminates over-retrieval on large-context models and prevents under-retrieval when context is tight. Crisis intervention tasks always get HYBRID minimum for safety.