materializer + replay ports + vectord substrate fix verified at scale

Two threads landing together — the doc edits interleave so they ship
in a single commit.

1. **vectord substrate fix verified at original scale** (closes the
   2026-05-01 thread). Re-ran multitier 5min @ conc=50: 132,211
   scenarios at 438/sec, 6/6 classes at 0% failure (was 4/6 pre-fix).
   Throughput dropped 1,115 → 438/sec because previously-broken
   scenarios now do real HNSW Add work — honest cost of correctness.
   The fix (i.vectors side-store + safeGraphAdd recover wrappers +
   smallIndexRebuildThreshold=32 + saveTask coalescing) holds at the
   footprint that originally surfaced the bug.

2. **Materializer port** — internal/materializer + cmd/materializer +
   scripts/materializer_smoke.sh. Ports scripts/distillation/transforms.ts
   (12 transforms) + build_evidence_index.ts (idempotency, day-partition,
   receipt). On-wire JSON shape matches TS so Bun and Go runs are
   interchangeable. 14 tests green.

3. **Replay port** — internal/replay + cmd/replay +
   scripts/replay_smoke.sh. Ports scripts/distillation/replay.ts
   (retrieve → bundle → /v1/chat → validate → log). Closes audit-FULL
   phase 7 live invocation on the Go side. Both runtimes append to the
   same data/_kb/replay_runs.jsonl (schema=replay_run.v1). 14 tests green.

Side effect on internal/distillation/types.go: EvidenceRecord gained
prompt_tokens, completion_tokens, and metadata fields to mirror the TS
shape the materializer transforms produce.

STATE_OF_PLAY refreshed to 2026-05-02; ARCHITECTURE_COMPARISON decisions
tracker moves the materializer + replay items from _open_ to DONE and
adds the substrate-fix scale verification row.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
root
2026-05-02 03:31:02 -05:00
co-authored by Claude Opus 4.7
parent 277884b5eb
commit 89ca72d471
26 changed files with 3961 additions and 124 deletions
+11 -3
View File
@@ -182,9 +182,17 @@ type EvidenceRecord struct {
HumanOverride *HumanOverride `json:"human_override,omitempty"`
CostUSD float64 `json:"cost_usd,omitempty"`
LatencyMs int64 `json:"latency_ms,omitempty"`
Text string `json:"text,omitempty"`
CostUSD float64 `json:"cost_usd,omitempty"`
LatencyMs int64 `json:"latency_ms,omitempty"`
PromptTokens int64 `json:"prompt_tokens,omitempty"`
CompletionTokens int64 `json:"completion_tokens,omitempty"`
Text string `json:"text,omitempty"`
// Domain-specific bucket for source-row fields that don't earn a
// top-level slot. e.g. contract_analyses carries `contractor` here.
// Typed scalar values only — keep this small or it becomes a junk
// drawer. Mirrors EvidenceRecord.metadata in evidence_record.ts.
Metadata map[string]any `json:"metadata,omitempty"`
}
// RetrievedContext captures what the model saw via retrieval. Matches