PRD: add Phase 20 (model matrix, wired) and Phase 21 (context stability,
partial). Phase 21 exists because LLM Team hit this exact wall — running
multi-model ranking on large context silently truncated, rankings
degraded, no pipeline caught it. The stable answer: every agent call
goes through a budget check against the model's declared context_window
minus safety_margin, with a declared overflow_policy when the check
fails.
config/models.json:
- context_window + context_budget per tier
- overflow_policies block: summarize_oldest_tool_results_via_t3,
chunk_lessons_via_cosine_topk, two_pass_map_reduce,
escalate_to_kimi_k2_1t_or_split_decision
- chunking_cache spec (data/_chunk_cache/, corpus-hash keyed)
agent.ts:
- estimateTokens() chars/4 biased safe ~15%
- CONTEXT_WINDOWS table (fallback; prod reads models.json)
- assertContextBudget() — throws on overflow with exact numbers, can
bypass with bypass_budget:true for callers with their own policy
- Wired into generate() and generateCloud() so EVERY call is checked
scenario.ts:
- T3 lesson archive to data/_playbook_lessons/*.json (the old
/vectors/playbook_memory/seed path was silently failing with HTTP 400
because it requires 'fill: Role xN in City, ST' operation shape)
- loadPriorLessons() at scenario start — filters by city/state match,
date-sorted, takes top-3
- prior_lessons.json archived per-run (honest signal for A/B)
- guidanceFor() injects up to 2 prior lessons (≤500 chars each) into
the executor's per-event context
- Retrospective shows explicit "Prior lessons loaded: N" line
Verified: mistral correctly rejects a 150K-char prompt (7532 tokens
over), gpt-oss:120b accepts it with 90K headroom. The enforcement is
in-band on every call now, not an afterthought.
Full chunking service (Rust) remains deferred to the sprint this feeds:
crates/aibridge/src/budget.rs + chunk.rs + storaged/chunk_cache.rs
Status updated to reflect hybrid SQL+vector search, IVF_PQ 0.97
recall, 10K Ethereal worker profiles, autonomous agent validation.
Query Paths section updated with the shipped hybrid endpoint and
its verified zero-hallucination results from the staffing simulation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Standalone benchmark crate `crates/lance-bench` running Lance 4.0 against
our Parquet+HNSW at 100K × 768d (resumes_100k_v2) measured 8 dimensions.
Results (see docs/ADR-019-vector-storage.md for full scorecard):
Cold load: Parquet 0.17s vs Lance 0.13s (tie — not ≥2× threshold)
Disk size: 330.3 MB vs 330.4 MB (tie)
Search p50: 873us vs 2229us (Parquet 2.55× faster)
Search p95: 1413us vs 4998us (Parquet 3.54× faster)
Index build: 230s (ec=80) vs 16s (IVF_PQ) (Lance 14× faster)
Random access: 35ms (scan) vs 311us (Lance 112× faster)
Append 10K rows: full rewrite vs 0.08s/+31MB (Lance structural win)
Decision (ADR-019): hybrid, not migrate-or-reject.
- Parquet+HNSW stays primary — our HNSW at ec=80 es=30 recall=1.00 is
2.55× faster than Lance IVF_PQ at 100K in-RAM scale
- Lance joins as second backend per-profile for workloads where it wins
architecturally: random row access (RAG text fetch), append-heavy
pipelines (Phase C), hot-swap generations (Phase 16, 14× faster
builds), and indexes past the ~5M RAM ceiling
- Phase 17 ModelProfile gets vector_backend: Parquet | Lance field
- Ceiling table in PRD updated — 5M ceiling now says "switch to Lance"
instead of "migrate" since Lance runs alongside, not instead of
Isolation: lance-bench is a standalone workspace crate with its own dep
tree (Lance pulls DataFusion 52 + Arrow 57 incompatible with main stack
DataFusion 47 + Arrow 55). Kept off the critical path until API is
stable enough to promote into vectord::lance_store.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
