diff --git a/AGENTS.md b/AGENTS.md index a6b01b1..ebe3939 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -108,13 +108,13 @@ IP appears only as an env-var default. - **Battery adversarial test: PASSES.** Corpus built (23 docs via the `docs` fetcher); after the three scoring fixes the engine reads demand-net rising (+3.9) while **supply stays flat at 0.0** — correctly rejecting Cantor's *announced* $2B and borrower-side collateral claims as not-realized-supply. -- **Strike adversarial test: RUNNING (extraction phase) — no result yet.** The independent leg (What +- **Strike adversarial test: STALLED — needs a manual resume; no result yet.** The independent leg (What Bitcoin Did, Stephan Livera, Kevin Rooke, Anita Posch, Cafe Bitcoin, + River research — all - independent) is ~586/671 transcribed (60 stragglers). `run_strike_pipeline.sh` proceeded on that - partial corpus and is in the SLOW extraction phase (~600 podcast extract jobs on local Qwen); - `two-sided STRIKE2022` (live vs test reflexivity) has NOT produced a result yet — watch - `data/strike_pipeline.log`. If it stalls, resume manually: `run-extract` → `embed-claims` → - `two-sided --conviction STRIKE2022 --modes live,test`. The Spark **audio fix** (semaphore-of-2 + + independent) is ~586/671 transcribed. The `run_strike_pipeline.sh` watcher proceeded on that partial + corpus, but its extraction worker **died (2026-06-11)** after only 17/635 podcast docs; the stale lease + is cleared, so **608 bitcoin-podcast extract jobs are pending**. Spark vLLM is healthy → **RESUME:** + `run-extract --limit 700 --max-chunks 4` → `embed-claims` → `two-sided --conviction STRIKE2022 + --modes live,test` (PASS = quiet in live, fires in test). The Spark **audio fix** (semaphore-of-2 + retry-backoff) is committed and validated (~2.5× faster, zero episode aborts). - **§7.1 power-infra backtest:** qualified YES (corpus-gated; runway/precision caveats in `DESIGN_v2.md`). - Corpus now spans bitcoin podcasts, SEC/FMP company filings (incl. 6 major banks + Robinhood, a new