ten31-database/AGENTS.md

Ten31 Venture CRM + Agentic System — AGENTS.md

The foundation is a self-hosted venture-fund CRM — a purpose-built fundraising tool that replaced Airtable to (1) keep sensitive LP/prospect data off third-party servers, (2) drop subscription cost, and (3) fit the fund's workflow: managing ~150 existing LPs, tracking 250+ prospects, and running the capital-raise pipeline. Core CRM domain: contacts (investor/prospect/advisor), organizations, opportunities (the deal pipeline), and communications; investor commitments live in the canonical fundraising_* grid (the legacy single-fund lp_profiles table was retired in v0.1.0:78). The fund (Ten31, ~$200M AUM, bitcoin/energy/AI thesis) runs it on a Start9 box, accessed over ClearNet (StartOS StartTunnel) with app-level user auth by a team of ~5 (Tailscale is not in use). Schema/API tour: docs/crm-overview.md.

The agentic system is new functionality built on top of that CRM — an in-house AI layer to widen the fundraising funnel, sharpen the thesis, and automate outreach drafting. Frontier reasoning runs on Claude (Agent SDK/API); privacy-sensitive and bulk work runs on local DGX Spark models via the Spark Control gateway. Phase 0/1 — no live outward-facing agents; agents draft, humans send.

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

Stack (versions that matter)

• Python 3.11, standard library only at runtime. The CRM is one monolith, backend/server.py (~5k lines): a stdlib http.server.ThreadingHTTPServer + hand-written CRMHandler with manual path dispatch (do_GET/do_POST). Not FastAPI. backend/requirements.txt lists FastAPI/SQLAlchemy/Alembic/Pydantic/pytest-style deps but none are imported at runtime (vestigial).
• SQLite at data/crm.db (WAL, foreign_keys=ON), opened per-request via get_db(). Schema via ordered migrations.
• Frontend: single frontend/index.html, inline-Babel React. No build step.
• Optional runtime deps, used only if present: bcrypt, PyJWT (jwt), cryptography (Gmail module).
• MCP + ingest (in the Docker image, not the bare CRM): mcp==1.2.0 (FastMCP, backend/mcp/server.py), fastembed==0.4.2, anthropic, cryptography==42.0.5.
• Packaging: StartOS 0.4, TypeScript SDK (@start9labs/start-sdk) under start9/0.4/startos/. Live target is start9/0.4/.
• Local models (bge-m3 embeddings, bge-reranker-v2-m3, /api/search, Qdrant): always via Spark Control. Contract: docs/EMBEDDINGS.md.

Commands

# Run locally (dev, port 8080; or ./start.sh <port>) — runs python3 backend/server.py
./start.sh
# Run prod-mode (beta) — requires CRM_SECRET_KEY
./start_beta.sh
# Sanity-check edits (there is no compiler/build for the CRM)
python3 -m py_compile backend/server.py
# Run ONE test (tests are standalone scripts with `if __name__ == "__main__"`; no pytest installed)
python3 backend/redaction/test_scrub_leak.py        # substitute any backend/**/test_*.py
# Run all tests (aggregate runner — runs each backend/**/test_*.py in its own subprocess)
python3 backend/run_tests.py                         # add substrings to filter, e.g. `... soft_delete redaction`
# Build + install the s9pk — BUMP THE VERSION FIRST. See docs/guides/packaging.md.
cd start9/0.4 && make

• Migrations apply automatically at startup (backend/core_migrations.py, schema_migrations ledger). See docs/guides/migrations.md before adding one.
• Lint: none configured.

Directory layout (day-one)

• backend/server.py — the CRM monolith: HTTP handler, route dispatch, init_db(), auth (username/password → HS256 JWT, roles admin/member/bot).
• backend/core_migrations.py + backend/migrations/NNNN_*.sql (+ paired .down.sql) — additive schema migrations, applied at startup.
• backend/thesis_seed.py — Thesis Workshop seed + idempotent ensure_* one-time seeders, wired in server.init_db().
• backend/thesis_review.py — thesis version review/approval (human dual sign-off → canonical).
• backend/mcp/ — architect_agent.py (Claude thesis copilot), architect_tools.py, outreach_agent.py (LP draft assistant), architect_grounding.py, crm_tools.py, server.py (FastMCP).
• backend/email_integration/ — Gmail capture via domain-wide delegation + Tier-B draft creation (compose.py).
• backend/redaction/ — scrub.py + client.py: the scrub→Claude→re-hydrate privacy boundary.
• backend/ingest/ — chunk→embed→Qdrant + retrieval modes.
• backend/entity_*.py — entity resolution/merge (the two-investor-model reconciliation).
• backend/nl_query/ — read-only natural-language query (W2): intents.py (curated parameterized query catalog), runner.py (slot validator = trust boundary), translate.py (local-Qwen question→{intent,slots}). See the nl-query guide.
• backend/matrix_intake/ — Matrix intake bot (separate process; matrix-nio, isolated to this component): typed message → local-Qwen parse → in-thread approve → write via the CRM's own log-communication. See the matrix-intake guide.
• frontend/index.html — the entire UI.
• docs/ — architecture, phase plans, contracts, runbooks (see Deeper docs). docs/guides/ — scoped subsystem rules (see below).
• start9/0.4/ — StartOS package (startos/utils.ts holds PACKAGE_VERSION).
• data/crm.db — the live DB (gitignored). .env / .env.example — config (.env gitignored).

Scoped guides

Subsystem rules live in docs/guides/ and lazy-load in Claude Code via .claude/rules/ symlinks (scoped by paths: frontmatter). Read the guide before editing that area:

• Migrations or seeders (backend/migrations/, core_migrations.py, thesis_seed.py) → docs/guides/migrations.md
• Thesis logic (backend/thesis_*.py, backend/mcp/architect_*.py) → docs/guides/thesis.md
• Redaction or any MCP/Claude path (backend/redaction/, backend/mcp/) → docs/guides/redaction.md
• Ingest / retrieval (backend/ingest/) → docs/guides/spark-ingest.md
• Email capture / drafts + digest send (backend/email_integration/, backend/digest_mailer.py, backend/smtp_send.py) → docs/guides/email.md
• Building or deploying the s9pk (start9/) → docs/guides/packaging.md
• Matrix intake bot (backend/matrix_intake/) → docs/guides/matrix-intake.md
• Natural-language query (backend/nl_query/) → docs/guides/nl-query.md

Conventions

• Investor model — the grid is canonical (since v0.1.0:78). The fundraising_* grid is the system of record: an investor entity (row) → many contact "pills" → per-fund commitments. The classic contacts table is a read-only per-person directory, auto-populated from the grid — create/edit people in the grid, not the Contacts page. Email capture rolls multiple people up to one investor. The legacy single-fund lp_profiles model is retired (empty table kept, per never-hard-delete). Reconciling grid ↔ classic contacts to canonical IDs is the core entity-resolution task — see docs/crm-overview.md.
• Soft-delete only: deleted_at and/or status='retired'; never hard-delete. Every READ path must filter deleted_at IS NULL — list handlers, get-by-id, nested related-data sub-selects, and aggregate sub-selects (COUNT/SUM/MAX). Audits found leaks in all of these (2026-06-12 detail + nested; 2026-06-13 list-view contact_count/total_funded/comm_count); the opportunities/pipeline aggregates were fixed in v0.1.0:87 (handle_pipeline_report + dashboard pipeline metrics now filter deleted_at), but the reports subsystem's communications-side aggregates (dashboard recent_comms/comms_this_month/meetings_this_month, activity report) still leak (see Current state). Regression-guarded by backend/test_soft_delete_reads.py (+ test_reminders.py for the reminders read paths, incl. the recency rollup whose email-activity liveness signal is email_account_messages.deleted_at, not emails). (Thesis has a subtlety here — see the thesis guide.)
• Env: secrets in .env (gitignored); names in .env.example. Verified names: ANTHROPIC_API_KEY, SPARK_CONTROL_URL, SPARK_CONTROL_VERIFY_TLS, QDRANT_URL, X_API_KEY, CRM_DB_PATH, CRM_DEV_DB_PATH. Also used: CRM_SECRET_KEY (beta/prod), CRM_HOST/CRM_PORT, CRM_DATA_DIR; digest mailer: CRM_DIGEST_SENDER (DWD impersonation sender) + SMTP_HOST/SMTP_PORT/SMTP_SECURITY/SMTP_FROM/SMTP_USERNAME/SMTP_PASSWORD (SMTP fallback); daily digest (Phase B): CRM_DIGEST_ENABLED + CRM_DIGEST_SEND_HOUR only seed the first-boot default — the live control is the DB policy (app_settings.digest_policy, set in Settings → Admin).
• Config placement: operational/feature toggles live in the admin panel, DB-backed via app_settings (read-merge through a load_*_policy(conn) helper shared by the API + any scheduler; precedence DB-row → env-seed → default), so they're discoverable and take effect live. Reserve StartOS actions / env for secrets and deploy-time config (SMTP creds, API keys, DWD sender). Precedent: digest_policy (GET/PATCH /api/admin/digest/policy), fundraising_backup_policy.
• Agent/bot API access — three roles now (admin/member/bot). require_admin is the only hard gate; everything else is "authenticated" (member, admin, and bot all pass). The bot role (added v0.1.0:89) is authenticated-but-never-admin: require_bot_or_admin gates agent-facing endpoints (e.g. /api/intake/email-proposals*) so a bot credential reaches only what it needs, never user-management/settings/security. Provision it via Settings → Admin edit-user dropdown (kept out of the teammate-invite form). Two axes to keep separate as more agent capability lands: the role controls reach (which endpoints); the per-feature human draft→approve gate controls autonomy (acting unattended). Money/merge/delete mutations stay behind the approval gate regardless of role. Don't build a finer capability/scope system until real NL-mutation endpoints exist to scope against.
• Design: before building or changing any user-facing UI, read design/DESIGN.md and design/tokens.tokens.json and conform to them. A mobile-first redesign is in flight — read design/BRIEF.md before any responsive/layout work. (Note: inline style={{}} objects can't respond to media queries; responsive layout belongs in the CSS <style> block.)
• Commit style: imperative subject, concise body explaining the why; put the package version in the subject (… (v0.1.0:NN)) for shippable changes. No AI co-author / attribution trailers — commits are authored by the user.

Always

• Verify before shipping: python3 -m py_compile the edited files; for DB logic, run the change against a copy of data/crm.db, never production.
• Keep real LP data out of Claude: develop only on code/schema/synthetic-or-locally-redacted data; route any real record substance through backend/redaction first.
• Get explicit user authorization before any production deploy/install to $START9_BOX_HOST.

Never

• Never treat Qdrant (or any derived index) as source of truth — the CRM/SQLite is canonical and rebuildable-from.
• Never hard-delete CRM records or thesis history — soft-delete/archive only.
• Never let an agent send email, post, or contact an LP autonomously — agents draft; a human approves and sends.
• Never set a thesis_version canonical from code/seeds — that is human dual sign-off.
• Never call a Spark directly — go through Spark Control (SPARK_CONTROL_URL).
• Never commit secrets, data/crm.db, .env, or data/backups/ (all gitignored). Scan staged files before committing. (.claude/ is tracked — launch.json and rules/ symlinks ship with the repo; keep local-only settings in .claude/settings.local.json.)
• Never bulk-export the LP list to any third party; send only minimal non-sensitive context to Claude.
• Never assume FastAPI / SQLAlchemy / pytest are in play — they sit in requirements.txt unused; runtime is stdlib + SQLite.
• Never add a Co-Authored-By / "Generated with" trailer to commits or PRs — commits are the user's.

Deeper docs

• Full constitution + guardrails: docs/ten31-constitution.md
• Architecture & rationale: docs/Ten31_Agentic_Build_Plan.md
• Retrieval/embeddings contract: docs/EMBEDDINGS.md
• CRM schema/API tour: docs/crm-overview.md
• Current thesis handoff: docs/thesis-handoff.md
• Operations & runbooks: docs/OPERATIONS.md, docs/go-live-runbook.md, docs/gmail-enablement-runbook.md

Current state

Phase 0 + Phase 1 built; box + repo live at v0.1.0:94 (reminders W1 + NL-query W2 deployed 2026-06-18; v94 = NL-query matched-only fix). The fundraising grid + email capture is the canonical system of record. Active thread: W2 natural-language query — backend + Matrix Q&A live; web "Ask" box is the last piece. Feature/deploy history: git log + start9/0.4/startos/versions/; longer-term backlog/debt: ROADMAP.md / EVALUATION.md.

• W2 — NL query (read-only): LIVE on the box (backend + Matrix Q&A shipped v93; matched-only fix v94). Curated parameterized catalog + slot validator (trust boundary; no generic SQL) + local-Qwen translator (backend/nl_query/; nothing leaves the box, no Claude/redaction). POST /api/query/nl + GET /api/query/catalog (require_bot_or_admin, audited). Matrix Q&A client deployed (backend/matrix_intake/query.py + crm_client.nl_query, read-only, no approval gate): dedicated Q&A room !RGlJEObVaIUtUVcHtx:matrix.gilliam.ai (every message is a question) + the ?/@bot trigger in the intake room (cross-room convenience). Email/comms intents are matched-only (investor-linked email only — v94 fixed comms_by_user/email_counts_by_user which had counted the whole sent corpus). Guides: docs/guides/nl-query.md + matrix-intake. Remaining: (a) the actual in-room Matrix smoke — a human typing a question (not yet done); (b) step 4 web "Ask" box (Communications tab), the last thin client.

• W1 — reminders & follow-ups: LIVE (shipped v93). First-class tickler tied to the grid (migration 0006; CRUD /api/reminders; derived reminder_status grid column; Reminders page + dashboard card + digest section; the last_activity_at recency rollup W2 reuses). Deferred W1b = nurture-gap auto-suggested reminders.

• Done & live (detail in git log / ROADMAP): email-proposal Matrix review + bot role (box v91); grid-driven Pipeline (v88); Matrix intake bot (Spark matrix-intake container); Gmail capture (DWD) + propose→approve + daily digest; Thesis Workshop + Architect (Claude, dual-approval); outreach drafts + radar. All draft-only.

• Built, deploy pending: drag-reorder fundraising grid views (frontend-only; sidebar view list, moveViewBefore in index.html, persists via the existing grid autosave → views_json; render-smoke green, browser interaction not yet tested). Part of a one-off feature batch triaged 2026-06-18 (mobile-first follow-on) now captured in ROADMAP.md → "One-off feature batch" (Squarespace-lead capture, outreach-detector contacts, new pipeline stages, voice-note→Spark transcription, intake LLM-search, email approve/reject learning) + a spark-control dashboard-card item in standards/INBOX.md.

• Tests: 35/35 backend green (python3 backend/run_tests.py), py_compile clean; render-smoke gates make.

• Next (priority order): 1) in-room Matrix smoke of the Q&A room (type a real question; confirm the answer renders well on mobile — broad questions like "cold investors" hit the 500-row cap → 30 shown + refine note) + the intake ?/@bot trigger; 2) W2 step 4 web Ask box (last NL-query client); 3) W3 bot grid-mutations behind the Matrix approval gate (local-Qwen parse); 4) W1b nurture-gap reminders; 5) Grant + Jonathan freeze v2.0 canonical; 6) in-room smoke of the intake disambiguation numbered-pick grammar; then P2 debt (reports comms-aggregate soft-delete sweep, ?limit=abc crash, auth regression test, oversized StartOS icon).

• Open / risks: W2 translation only happy-path-validated (typos/ambiguous/no-match phrasings shake out in live use); Claude/Architect path still unverified live on the box; v2.0 reserve-asset spine is the working approved spine but not canonical (needs dual sign-off); doc drift — crm-overview.md + EVALUATION.md still call lp_profiles live.