mirror of https://github.com/hanzoai/extension.git synced 2026-10-31 21:57:06 +00:00

Files

T

zooqueenandHanzo Dev f717dd89ad keys: the key a user pastes is sk-, not the retired hk-

28 apps told the user to paste an `hk-` key — input placeholders, settings
help text, READMEs, the error thrown when the field is empty — and five of
them validated that paste against /^hk-/ before sending it as a bearer.
Nothing mints that prefix any more: cloud accepts pk- and sk-, IAM mints
sk-. So the guard admitted a credential that authenticates nothing, and the
panel failed later at the gateway with nothing on screen to explain it.

The three leak detectors keep hk- and gain sk-. Salesforce's source scan
and the two Zendesk tests exist to catch a key committed to source or
echoed back through a request; retired keys are still in circulation and
leak exactly as badly, while a detector that only knew hk- would have gone
blind to every key minted from here on.

`sk-` used to be the example of the foreign key the guard screened out — an
OpenAI key. It cannot mean that now, and shape alone cannot tell one
vendor's sk- from another's, so those comments say what the check really
proves and point at the /v1/models call that proves the rest. The three
tests that pinned "sk- is rejected" now pin "hk- is rejected", which is the
invariant that survived.

Verified: 2029 tests pass across the 28 packages; typecheck clean on 25 of
them (hubspot, jupyter and teams fail identically at HEAD on JSX and ESM
type conflicts in files this does not touch); salesforce validate-source
green.

Co-authored-by: Hanzo Dev <[email protected]>

2026-08-13 18:07:16 -07:00

4.4 KiB

Raw Permalink Blame History

Hanzo AI for PDFs

A self-contained web PDF workspace: a PDF.js viewer on the left, a Hanzo AI panel on the right. Open a filing, an executed contract, or a discovery document, then ask, summarize, and extract over it. This is the surface a lawyer spends the most time in — and unlike Acrobat's C++/Windows plugin SDK, this runs anywhere a browser does, with no Adobe license.

It reuses the same backend as the rest of the Hanzo productivity suite: model calls go through api.hanzo.ai/v1 (OpenAI-compatible, streamed over SSE), the same gateway the Office add-in (@hanzo/office-addin) uses. No new API surface.

What it does

Renders the PDF (PDF.js) with page navigation and text selection.
Extracts the selectable text of every page in the browser.
Answers questions grounded in that text, streaming the reply — with a legal-analyst system prompt that cites page numbers and refuses to guess.
Law-office quick actions: Summarize · Extract parties, dates & obligations · Find & explain risky clauses · Explain the selection plainly · Draft a summary memo.

Nothing leaves the browser except the pages sent with a question. Scanned image PDFs (no text layer) are detected and reported honestly — there is no OCR here.

Large PDFs — honest context windowing

A 500-page filing does not fit a model context window and is never sent wholesale. buildContext (in src/config.ts, pure and unit-tested) caps the attached text at CONTEXT_CHAR_BUDGET (48 000 chars) and:

Whole document scope windows from page 1, including as many whole pages as fit the budget, in order.
Current page only scope windows from the page you're viewing, so a question about what's on screen sends that page and its neighbours, not the top of the document.
The first line of every request is a context note stating the exact page range sent and, when pages were dropped, telling the model to answer only from what it sees and to say so if a full answer needs the omitted pages. The model is never told it has the whole document when it doesn't.

An oversized single page is hard-cut to the budget (and flagged truncated) rather than silently overflowing.

Auth

Paste a Hanzo API key (sk-…); it is validated by a real /v1/models call before it is saved to localStorage, so a dead key is rejected at paste time, not at first question. An empty key still reaches the gateway's public models. OAuth via hanzo.id (device login) is the documented future upgrade — the bearer plumbing already tolerates any token, so it slots in without a rewrite.

Build

pnpm --filter @hanzo/pdf build      # production (base https://pdf.hanzo.ai)
pnpm --filter @hanzo/pdf test        # vitest — pure logic
pnpm --filter @hanzo/pdf typecheck   # tsc --noEmit

build.js (esbuild → dist/) bundles app.ts as ESM and copies PDF.js's worker (pdf.worker.mjs) beside it — app.js resolves it at runtime via new URL('./pdf.worker.mjs', import.meta.url), so the worker must sit next to app.js. dist/ is fully static: index.html, app.js, pdf.worker.mjs, styles.css, assets/. Override the hosting base for local dev:

HANZO_PDF_BASE=https://localhost:8080 pnpm --filter @hanzo/pdf build

Run / host

dist/ is a static site — serve it over HTTPS from any static host. Locally:

pnpm --filter @hanzo/pdf build
cd packages/pdf/dist && python3 -m http.server 8080   # then open http://localhost:8080

Deploy target: pdf.hanzo.ai over hanzoai/static (the k8s-native static plugin behind hanzoai/ingress — no nginx/caddy). Point the static plugin at the built dist/; there is no server-side component. CORS is not needed — api.hanzo.ai is same-origin-policy-friendly for the browser fetch; the gateway sets the response headers.

The engine is small, pure, and tested

The logic-heavy parts live in their own modules with vitest coverage (tests/):

config.ts — endpoints, pickBearer, and buildContext/contextNote (the large-PDF windowing and the honest scope note).
chat.ts — request/response shaping (buildMessages, requestBody, extractContent, streamDelta, ask, askStream, listModels) — the same wire contract as the Office add-in.
pdf-view.ts — the PDF.js binding; itemsToText (the text-flattening helper) is isolated and unit-tested without a real PDF.

app.ts is the thin, browser-only DOM glue that binds them together.

4.4 KiB Raw Permalink Blame History