ten31-signal-engine/AGENTS.md

# Ten31 Signal Engine — AGENTS.md

> **Inbox check:** At session start, if `~/Projects/standards/INBOX.md` exists, scan it for items
> tagged `(ten31-signal-engine)` and surface them before proposing next steps; triage with `/triage`.

A recurring pipeline that ingests a growing corpus of **audio** (podcasts, YouTube) and **text** (SEC
filings, earnings calls, policy/lender/research docs), extracts structured **propositions ("claims")**,
and surfaces **signal over time** through Ten31's investment thesis as a *relevance lens* — logging every
surfaced signal as a **falsifiable prediction** scored against reality.

**Source of truth (in order):** `ten31-signal-engine-handoff.md` (the spec — wins on any conflict; §refs
point into it) › `DESIGN_v2.md` (the living decision/falsification log — read before changing scoring) ›
this file's **Current state**. `README.md` is the user-facing intro.

## The spine — NON-NEGOTIABLE guardrails (never violate)

1. **Nominate-then-judge.** Statistics & graph structure NOMINATE candidates; the frontier model only
   JUDGES / FANS OUT a pre-filtered shortlist. The frontier never nominates from the raw corpus.
2. **Propositions, not vibes.** Extract atomic claims; separate **topic** from **stance**.
3. **Discount convergence by connectedness.** Independence is earned, not counted — the EISC graph
   (source edges + voiceprints) downweights echo. Bitcoin is one *capped* cluster: within-cluster
   agreement can NOT masquerade as independent corroboration; cross-cluster earns the multiplier.
4. **Thesis is a LENS, not a gate on truth.** The engine must surface signals *against* Ten31's thesis,
   not just for it.
5. **Dual-evaluation ledger from day one** — precision AND recall; every signal is a logged prediction.
6. **~95% local compute via Spark Control.** Call the gateway's HTTP endpoints; do NOT stand up your own
   vLLM / Whisper / Qdrant. Gemini is an explicit *overflow* lever for PUBLIC data only.
7. **Sovereignty boundary (hard).** Exposure/positioning/conviction data and the Strike/Battery
   investment memos NEVER go to the frontier. Route sensitive frontier calls through
   `/scrub → frontier → /rehydrate` (scrub identities, not substance). Read the memos LOCALLY only.

**Two jobs:** **A — Discovery** (emergent themes via independent cross-cluster *convergence* scored on
acceleration; contrarian stances; their intersection). **B — Conviction-action gap** (fan held
convictions to 2nd/3rd-order derivatives, catch early corroboration — the countermeasure to the 2023
"power is the binding constraint on AI/compute" miss: right on the root, late to the derivatives).

## Architecture

`signal_engine/` (Python package, run as `python -m signal_engine <cmd>`):
- `config.py` — env-driven `Config` (+ `.env` loader). `spark/client.py` — the SINGLE gateway chokepoint
  (no other module knows the gateway URL); scrub/rehydrate live here.
- `ingest/` — `edgar` (SEC), `earnings` (FMP REST), `feeds`+`podcasts` (RSS), `download`, `chunker`,
  `transcribe_worker` (local Parakeet), `gemini_transcribe` (bulk overflow), `docs` (HTML/PDF/RSS text
  fetcher for policy/lender/research), `identify`, `speaker_stitch`.
- `extract/` — `claims`+`worker` (proposition extraction), `backends` (LocalQwen | Gemini), `prompt`,
  `html_text`. `embedstore/` — `embedder` + `qdrant_store` (hybrid dense+BM25).
- `signals/` (the scoring brain) — `independence` (EISC), `asof` (look-ahead guard), `windows`,
  `under_acted` (Job B), `bar` (two-tier gate), `two_sided` (affirms−denies net-corroboration),
  `llm_helpers` (`derivative_relevance`), `confusion` (precision/recall), `external` (price/outcome
  fetcher), `ledger_writer` (§6.6 prediction ledger), `resolver` (stub), `run`.
- `store/` — `db` (SQLite + idempotent migrations), `schema.sql`, `seed`, `sources`. `backfill/queue.py`
  (the job queue). `ui/app.py` (FastAPI corpus/eval UI). `util.py`.
- Data lands in `data/` (gitignored): `signal.db`, `transcripts/`, `docs/`, `audio-cache/`.

**Flow:** seed sources/convictions/fanout → ingest (→ `documents` + `transcribe`/`extract` jobs) →
`run-transcribe` / `run-extract` drain the queue → `claims` → `embed-claims` (Qdrant) → scorers
(`backtest`, `two-sided`) read the proposition store as-of a date.

## Build / run

- **Setup:** virtualenv at `.venv` (Python 3.14). `.venv/bin/pip install -r requirements.txt`.
- **Invoke:** `.venv/bin/python -m signal_engine <cmd>`. **`--help` is authoritative**; the rest is a
  map: `init-db`; seeding `seed-sources`/`seed-convictions`/`seed-fanout`/`seed-edges`/`load-feeds`;
  ingest `ingest-edgar`/`ingest-earnings`/`ingest-podcast`/`ingest-doc`/`ingest-doc-manifest`/
  `ingest-feed-text`; queue drain `run-transcribe`/`run-transcribe-gemini`/`run-extract`; index
  `embed-claims`/`search`; score `backtest`/`two-sided`/`confusion-matrix`; inspect `queue-status`/
  `spark-status`/`feed-peek`/`provenance`/`db-tables`; `serve` (UI).
- **DB:** `python -m signal_engine init-db` (idempotent — re-creates schema + runs additive migrations).
- **Tests:** ⚠️ **no automated test suite yet** (no `tests/`, no pytest). Verification is by running
  commands against the live gateway. Adding a test harness is on the ROADMAP.
- **Lint/format:** none configured. Match the surrounding style (dense, §-referenced docstrings).

## Spark Control infra (`SPARK_CONTROL_URL`, self-signed TLS → `SPARK_VERIFY_TLS=false`)

One gateway fronts two DGX Sparks: **vLLM** `RedHatAI/Qwen3.6-35B-A3B-NVFP4` on `:103`; **Parakeet**
ASR + diarizer, **bge-m3** embeddings, **Qdrant** on `:87`. The gateway is the only URL anything calls.
- **AUDIO concurrency (learned 2026-06-09):** single serial GPU shared with the operator's production
  meeting app. Cap **2 in-flight (ceiling 3), GLOBAL across both audio endpoints** — a process-wide
  `BoundedSemaphore` (`AUDIO_CONCURRENCY` env, default 2). Going wider buys zero throughput. Transient
  1–4s "busy blips" (broken-pipe/503/timeout) are NOT failures → short retry-backoff. The
  `transcribe_worker` runs a 2-wide chunk pool; the old size-1 lock was ~2.5× slower.

## Key operational rules (learned this build — easy to get wrong)

- **`own_network` quarantine is MATERIALITY-driven, not "any investment."** Quarantine (drop in live
  scoring, keep in test) only for MATERIAL ties where the source is part of Ten31's voice: the partners'
  own shows (TFTC, Citadel Dispatch, Rabbit Hole Recap), the Battery *partnership*, material portfolio
  leads. **Immaterial passive stakes → INDEPENDENT** (River and Swan/Cafe Bitcoin were corrected to
  independent). Unconfirmed: Unchained, Debifi, Coinkite (held quarantined pending Grant's materiality call).
- **Gemini quota is a rolling ~24h window** (~291 hour-long episodes / ~51M tokens), not a calendar-day
  reset. Bulk transcription overflows there; expect 429 RESOURCE_EXHAUSTED past the window.
- **Transcript chunking is recall-first and MUST cap every chunk.** ASR transcripts have NO blank-line
  paragraphs (speaker turns joined by a single `\n`), so `extract.claims.chunk_text` falls through
  `\n\n`→`\n`→sentence→word→hard-slice; splitting only on `\n\n` (the old bug) sent whole 2–3 h episodes
  in ONE call → context-overflow 400s. Extraction defaults to full coverage at 12K chars/chunk
  (`run-extract --chunk-chars/--max-chunks`); bigger chunks risk lost-in-the-middle recall loss.
- **Gemini extraction backend: disable thinking AND set a timeout.** `gemini-2.5-flash` thinks by
  default and burns the output-token budget on reasoning → MAX_TOKENS → truncated JSON → 0 claims, so
  the backend sets `thinking_budget=0` (mirrors local `enable_thinking=False`). It also sets an HTTP
  **timeout (120 s) + 4 retries** — a timeout-less call once hung the single-threaded worker ~50 min
  (transient 504/read-timeouts then self-heal). Gemini = overflow for PUBLIC data only; keep
  `EXTRACTION_BACKEND=local` in `.env`, flip it inline per-run when overflowing.
- **Scoring-brain internals are scoped to a guide.** Before editing `signal_engine/signals/`, read
  **`docs/guides/scoring-brain.md`** — the classifier invariants (REALIZED-ONLY, ROLE-MATCH, claim_type
  hard-evidence guard, max_tokens budget, claim_id bracket-strip), the EISC cluster-cap, and the
  Battery/Strike adversarial-test PASS criteria. Don't regress those invariants (they're what make
  Battery pass). Full decision log: `DESIGN_v2.md`.

## Secrets / env

Real values live in **`.env`** (gitignored). `.env.example` lists the names. Keys used: `SPARK_CONTROL_URL`,
`SPARK_VERIFY_TLS`, `LOCAL_LLM_MODEL`, `EMBED_MODEL`, `TRANSCRIBE_MODEL`, `AUDIO_CONCURRENCY`,
`EXTRACTION_BACKEND`, `GEMINI_API_KEY`, `GEMINI_MODEL`, `ANTHROPIC_API_KEY`, `FMP_API_KEY`,
`EDGAR_USER_AGENT`, `DATA_DIR`, `UI_PORT`, `LOG_LEVEL`. Never commit key values; the private LAN gateway
IP appears only as an env-var default.

## Current state (snapshot — overwrite each session; longer-term backlog → `ROADMAP.md`)

- **Strike adversarial test: CONDITIONAL PASS (2026-06-16).** Pipeline complete end-to-end — extraction
  drained the last 63 filing jobs (Gemini, 3,330 claims, 0 failures) → **56,008 claims** all embedded in
  Qdrant → `two-sided --conviction STRIKE2022 --modes live,test`. The engine **refuses the false positive**:
  the Lightning-retail nodes net `+0.25` (capped single bitcoin cluster, ≪ `EISC_FLOOR=2.0`), §3 guardrail
  holding. The own_network-drop *reflexivity demo* is unexercised (`own_net=0`, live==test) because
  RHR/CD/Bitcoin.Review (169 eps) were deferred at transcription 2026-06-08; operator accepted the
  conditional pass, no audio-GPU spend now. How to read the net value + the full follow-up:
  `docs/guides/scoring-brain.md` (STRIKE2022) and `ROADMAP.md`.
- **Battery test PASSES; §7.1 power-infra qualified YES** (both unchanged).
- **Corpus:** bitcoin podcasts (own_network: TFTC partial 19/80; RHR/CD/Bitcoin.Review deferred), SEC/FMP
  filings (`banks` cluster now extracted + power-infra names Oklo/NuScale/Cipher/TeraWulf), Battery corpus,
  River research; EISC edges seeded for the bitcoin cluster.
- **Repo:** clean, in sync with `origin/main` (Gitea). No automated test suite (on ROADMAP).
- **NEXT (priority order, all fresh scopes — confirm direction first):** (1) frontier-fan-out test H6, the
  untested half of the §1.1 validation; (2) complete the Strike reflexivity demo when audio-GPU budget
  allows (un-defer RHR/CD 2022–23 → re-extract → re-run); (3) Job A discovery scorers for the forward pilot.