recap/AGENTS.md

AGENTS.md — Recaps

YouTube + podcast summarizer + library, served as a single-page app from a Node.js backend. Ships as a StartOS .s9pk (single-mode self-host) and as the public recaps.cc cloud (multi-mode tenants).

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

Design: before building or changing any user-facing UI, read design/DESIGN.md and design/tokens.tokens.json and conform to them. Accent is indigo #818cf8; purple #a855f7 is premium-only. The same tokens govern three surfaces that must stay in sync: the main public/index.html stylesheet, its SHARE_PAGE_CSS share-export string, and public/auth.html.

Stack

• Server: Node.js (type: module, ES modules). The dev box currently runs v25.6.1; container runtime is whatever the Dockerfile pins — check before assuming.
• Frontend: One file, public/index.html, with vanilla JS embedded (no framework, no bundler). Render is a render-string-into-innerHTML loop driven by a module-scoped state object.
• DB: SQLite via better-sqlite3. Multi-mode only; single-mode keeps everything on the filesystem.
• Packaging: @start9labs/start-sdk under startos/ — version graph at startos/versions/index.ts.
• Deps of note: @anthropic-ai/sdk, @google/genai, openai, nodemailer, express, @keysat/licensing-client (vendored at vendor/keysat-licensing-client).

Commands

Run from repo root unless noted.

Action	Command
Dev server (single-mode default)	cd server && npm run dev
Prod server	cd server && npm start
Run all tests	cd server && npm test
Run one test file	cd server && node --test --test-reporter=spec test/<file>.test.js
Run one test by name	cd server && node --test --test-reporter=spec --test-name-pattern='<substring>' test/<file>.test.js
Build .s9pk (x86)	make x86
Bump version (interactive)	make bump
Install to local StartOS	make install (see Always/Never — bump first; the binary is start-cli under the hood)
Type-check (StartOS TS)	npm run check (repo root; runs tsc --noEmit over startos/**/*.ts. The server/ is plain JS and is not type-checked.)
Format (StartOS TS)	npm run prettier (repo root; prettier --write startos. There is no ESLint/linter — server/ JS is untooled. Many startos/versions/*.ts are currently unformatted.)

Mode is selected at boot via the RECAP_MODE env var: single (default) or multi. Other runtime env var of note: RECAP_TRUSTED_PROXY_HOPS (default 1) — how many trusted reverse proxies sit in front of the app, so the anonymous-trial per-IP cap reads the real client IP from X-Forwarded-For (set 0 if the app is directly internet-facing, 2+ behind a CDN/LB; setting it too high re-opens the trial-cap bypass).

Directory layout

server/
  index.js                 main HTTP + SSE entry; mounts every route
  providers/               relay.js, gemini.js, openai.js, anthropic.js, ollama.js,
                           openai-compatible.js, whisper.js — each implements the
                           provider interface in providers/index.js
  anon-trial.js            multi-mode trial-cookie minting + IP cap
  tenant-credits.js        multi-mode signed-in-tenant credit pool
  history.js               per-scope library save/load + REST handlers
  config.js                StartOS config snapshot + server-side API-key resolver
  db.js                    SQLite schema apply + getDb() handle (multi-mode only)
  billing-routes.js        multi-mode self-serve purchase: /api/billing/{plans,buy,status};
                           Bitcoin (BTCPay inline Lightning) + card (Zaprite) rails
  subscription-reminders.js  daily expiry-reminder scan → sendMail (multi-mode)
  smtp.js                  StartOS System-SMTP transport (magic links + reminders)
  test/                    node --test files
public/
  index.html               the whole single-page app, ~10k lines vanilla JS
  auth.html                standalone magic-link landing page (multi-mode)
startos/
  manifest/                StartOS package manifest
  versions/<vN>.ts         one file per shipped version + index.ts version graph
  actions/                 operator-facing StartOS Actions
docs/                      design notes; treat as in-progress, not authoritative
bin/bump-version.sh        used by `make bump` and `make deploy`
vendor/keysat-licensing-client/   local-link Keysat SDK

Conventions

• Plain language over jargon, especially for git / packaging / dev-tooling steps.
• Don't be sycophantic. Push back when something doesn't add up.
• Honest reports. A failing test/build is a failure, even if pre-existing or unrelated. Don't fold it into a "success" summary.
• Diff size matches change scope. Small reviewable diffs, not sweeping rewrites.
• Comments explain WHY, not what. No narrating self-evident code. No referencing tasks/PRs/callers in source — that rots.
• Match the file's own style over any default of your own. The frontend's vanilla-JS shape is intentional; don't reach for a framework.
• Write the test alongside the change when the area already has tests (server/test/*.test.js). The repo uses the built-in node --test.
• Plans persist in docs/ when scoped + named (e.g., docs/per-tenant-subscriptions-plan.md); ephemeral planning lives in conversation/tasks, not Markdown files.

Conventions for this codebase specifically

• Relay is the modern default provider. The legacy "must have a Gemini API key configured" gate is dead — server-side callers should pick relay when configured, fall back to gemini only if a local key exists, otherwise surface a clear user-facing error. The frontend stores the choice in localStorage; the server can't read it.
• Sanitize operator-internal language at error boundaries. Strings like "Spark Control", "parakeet", "vLLM", LAN IPs, *.local URLs come from the sibling relay and must not reach cloud users.
• Multi-mode credit gates fire BEFORE the pipeline. See /api/process for the order — admin → license → free tenant → trial → anonymous-mint. Don't reorder without reading the comment block.
• Trial IP cap is per-IP for IPv4, per-/64 prefix for IPv6. Dual-stack home networks would otherwise bypass it via privacy-extension address rotation.
• Client IP comes from req.ip, never a raw X-Forwarded-For entry. Express trust proxy is set in index.js from RECAP_TRUSTED_PROXY_HOPS (default 1); getClientIp (anon-trial.js) returns req.ip. Trusting raw XFF[0] let clients spoof the trial-cap IP — don't reintroduce it.
• safeFilename() is exported from history.js — import and use it for any user-content → on-disk path; don't roll your own. It validates against /^[A-Za-z0-9_-]+$/ and throws on traversal/separators (the library-import file-write hole was a missing call).
• The relay owns cloud Pro/Max tier + expiry (core-decoupling; docs/core-decoupling-plan.md). In multi-mode, paid status is users.tier — cached from the relay, keyed by the Recaps user-id — NOT a per-user Keysat license. Don't gate cloud paid features by keysat_license; the license only matters for self-hosted "take it home" portability. Cloud requests carry X-Recap-User-Id + the operator key; server-to-server tier reads/writes go through providers/relay.js.
• Server-side background relay calls that the operator should eat go through resolveProviderOpts("relay", { req: null }) → the operator install identity, the same relay credit pool free signed-in users' summaries already draw from (providers/index.js pickRelayIdentity). That's the "operator-absorbed" lane — no comped system user-id, no operator action. To bill a specific user instead, pass their cloud identity ({cloud:true, userId, operatorKey}). The Daily Digest synthesis (daily-digest.js) is the reference use.
• Self-serve purchase has two rails, both prepaid (no auto-renew yet). Bitcoin = a BTCPay invoice rendered as an INLINE Lightning QR on-screen — the relay returns the BOLT11 server-to-server, so the buyer never loads BTCPay (replicate the buy-credits inline flow; do NOT redirect to a hosted checkout). Card = a Zaprite one-time hosted order (Zaprite's API has no recurring — see ROADMAP). Both settle webhooks land on the relay (it owns subscription expiry); the frontend just polls /api/billing/status. Expiry reminders go out via the existing System-SMTP transport (smtp.js): the relay enumerates who's expiring (GET /relay/expiring-subscriptions), Recaps maps user-id → email and sends.
• Tier credit allotments are operator-config-driven, never hardcoded. The cards' "N relay credits each period" comes from the relay's tier-quota config (credits_per_period on /relay/tier-plans); null → "Unlimited". Don't bake a number or "Unlimited" into the UI.
• recaps.cc IS the operator's StartOS box, served via Start9 Pages + StartTunnel. So make install (after a version bump) updates the public cloud site automatically — there is no separate cloud deploy step. A frontend-only change reaches recaps.cc as soon as the box serves the new public/ files.
• render() rebuilds the whole view via innerHTML — preserve live media + scroll across it. It re-attaches the live podcast <audio> node (replaceWith, src-matched) and restores .chunks-scroll scrollTop, so a background re-render (e.g. the ~60s relay-credit poll) doesn't stop playback or bounce the reader to the top. YouTube minimize toggles the .results-left.minimized CSS class in place — never render(), because creating the YT iframe inside a display:none container wedges the IFrame API (black frame, needs reload); ensureYtMounted() + a !state.videoMinimized guard on needsMount keep the player from ever being built hidden, and initPodcastPlayer() is idempotent (dataset.inited). Don't reintroduce a full render() on minimize or drop these preservation steps.
• URL parsing is duplicated server + client — edit both in lockstep. extractVideoId (and the sibling classifiers isChannelUrl / isPodcastUrl) live in BOTH server/util.js and public/index.html with the same logic; the server copy is the one that actually rejects a submit (server/index.js → "Invalid YouTube URL"). When you teach one a new URL form, teach the other or the frontend preview and server will disagree. extractVideoId accepts /watch?v=, youtu.be/, /embed/, /v/, /live/, /shorts/, and a bare 11-char id; trailing ?si=… tracking params are fine (the regex stops after the id). Tests: server/test/util.test.js.
• Colors flow from CSS custom properties — edit the token, not the value. public/index.html's <style> opens with a :root token block (the single source of truth, mirroring design/tokens.tokens.json); the stylesheet and the inline style= attributes (var-ified in Phase 2) reference var(--accent) / var(--surface) / etc. Change a brand color there, once. Two surfaces use :root+var() and must stay in sync: the main stylesheet and public/auth.html (a standalone doc with its own :root copy). The SHARE_PAGE_* share export is the exception — a standalone document with no :root, so it's pure literal hex; a token change must be hand-mirrored into its literal values, and you must NOT introduce var() there (it won't resolve). Left literal on purpose even in the main doc (don't blind-sweep): #fff, hexes with no token, hex in JS logic (quoted ternary branches, const c=…), SVG fill/stroke, and <meta theme-color>. Phase 2 var-ified everything else by scoping to CSS-value position (hex preceded by :/space/,, never a quote) — reuse that rule for any future sweep.

Client-side contract with the relay

The full client-side relay contract — env vars, the /relay/* endpoint list, X-Recap-* header directions, and the file map — lives in docs/guides/relay-client.md. Read it before editing server/providers/relay.js, relay-capabilities.js, relay-default.js, billing-routes.js, credits-purchase.js, subscription-reminders.js, or the relay env-var resolution in config.js. Canonical endpoint shapes are in ../recap-relay/AGENTS.md.

Cross-repo changes (sibling: ../recap-relay)

This repo and the relay (../recap-relay) share a live client/server contract — the /relay/* endpoints, the X-Recap-* headers, request/response shapes, and tier/credit semantics. Before finishing any change that touches that boundary, check whether ../recap-relay needs a matching change. If you add/rename/remove a relay call, alter a payload shape or header, or shift tier/credit/billing behavior, update the relay side too — and reflect it in BOTH repos' AGENTS.md (the contract docs) and ROADMAP.md (if it's staged work). Purely local changes (UI, library handling, packaging) don't need this. When unsure whether a change is contract-affecting, assume it is and check.

Always

• Bump the version before make install. StartOS dedupes sideloads by version string — installing the same version twice silently no-ops. Use make bump or edit startos/versions/index.ts + add a vN.ts file. Applies to EVERY iteration, even a one-line edit.
• Add new version files to BOTH the import block AND the other: list in startos/versions/index.ts, and update current: to the new version constant.
• Ask before make deploy / make redeploy. These push to the Start9 community registry — public-facing, attribution-tracked, irreversible from your laptop. make install is the safe iteration loop.
• Verify mDNS resolution before blaming it when make install fails. Substitute the operator's actual StartOS hostname (the host: field in ~/.startos/config.yaml) and run curl -sk "https://${STARTOS_HOST}/rpc/v1" -X POST -d '{}' -H 'Content-Type: application/json' — if that reaches the box but start-cli doesn't on the same target, it's almost certainly macOS Local Network privacy blocking the third-party start-cli binary (Apple's curl/ping are exempt, so the box looks reachable). Tell: node -e TCP-connect to <box-ip>:443 also gives EHOSTUNREACH while curl gets 200. Fix: System Settings → Privacy & Security → Local Network → enable the Claude app (restart Claude Code if it doesn't take). This often flips off after a Claude Code update. Details: memory feedback_macos_local_network_install.
• Reference env-var names, never values. Secrets live in .env / .deploy.env (both gitignored). Examples for new vars belong in .deploy.env.example.

Never

• No "Co-Authored-By" trailers on commits, no mention of "Claude" in source files, comments, or commit messages. Commits are authored by the user.
• Never claim make install succeeded without verifying it. Confirm the make exit code is 0 AND the new version actually shows on the box (start-cli package list) — not just that the command ran (a tail/pipe can mask a non-zero exit). Installs DO work from this agent's shell now; the old "start-cli is blocked by the sandbox" framing was a misdiagnosis — it was macOS Local Network privacy, which is fixable (see the Always "verify mDNS" rule).
• Never make deploy to the registry without explicit per-action approval, even if a prior session ran one.
• Never edit startos/versions/<v>.ts for a version that's already been built and is being tested. Add a new version file instead — operators may already have the prior .s9pk cached.
• Don't add the relay's internal-meetings feature here. That lives in the sibling ../recap-relay repo. This repo is the client/library; the relay does diarization + clustering + meeting analysis.
• Don't push to GitHub by default. The configured remote is self-hosted Gitea unless the user says otherwise.
• Don't pull cookies.txt into commits — it's an operational yt-dlp artifact, not source.
• Never modify ~/.startos/config.yaml without authorization (contains host credentials).

Adjacent repo

• ../recap-relay — the operator-side credit-metered service this client talks to. Owns Gemini/Parakeet/Sortformer routing, diarization, internal-meeting analysis, and the operator dashboard. See ../recap-relay/AGENTS.md for its endpoint shapes, build/deploy rules, and roadmap. Reference it but do not change it from inside this repo.

Current state

Live on the operator's StartOS box — app 0.2.162 + relay 0.2.126. Tests: cd server && npm test → 158 pass.

⚠ Active incident (2026-06-20) — YouTube processing is down. A relay Gemini analyze call black-holed and permanently jammed the relay's single in-memory hardware FIFO slot, blocking ALL manual + background-subscription jobs (operator reports ~a week of no subscription processing). Root cause is relay-side (no AbortSignal on the relay's analyze/transcribe generateContent calls + no dead-holder release on its queue) — full diagnosis + 2-part fix captured to the standards inbox as (recap-relay) [bug][P1]; the fix lands in a separate ../recap-relay session via /triage. Operator is restarting recap-relay to unblock (clears the in-memory jam; recurs until the fix ships).

• Recap-side open question: confirm whether the week-long subscription silence is fully explained by that jam, or whether the background sub-check's Keysat-license entitlement gate (server/index.js:1400) is also skipping silently post-core-decoupling — check https://recaps.cc/api/sub-check-log (needs sign-in).

Just shipped (0.2.162, 890d671): relay-client dedup — providers/relay.js collapsed to handleRelayResponse (pingBalance left separate, different error-recording contract) + operatorPost/operatorGet (write-throws/read-null split preserved); first fetch-mock harness server/test/relay.test.js (+14). Internal-only.

Prior live features (self-serve Pro/Max purchase, core-decoupling, per-tenant subs, expiry reminders, opt-in Daily Digest, /live+/shorts URLs, shareable HTML export, design-system token pass) are in the git log + docs/*-plan.md. Daily Digest is installed but not yet smoke-tested off-box (operator action, ROADMAP.md).

Next steps, in order: (1) operator restart recap-relay → restore service; (2) the recap-relay analyze-hang fix (separate session, /triage the inbox item); (3) answer the sub-check question above; (4) deferred refactor-survey items + pending operator actions + P2/P3 backlog all live in ROADMAP.md.