- shared/consent.ts: ONE consent value. Signed in → the Hanzo account is the
source of truth (GET/PUT /v1/iam/consent); signed out → local, pushed on next
sign-in. Two switches: anonymous usage insights (default on, no query text) +
opt-in training contribution (share your own searches/answers; off until asked).
- Onboarding on new install (background onInstalled → onboarding.html) explicitly
ASKS consent; settings toggles in the popup mirror the same value.
- Answer engine instrumented: anonymous answer_search/answer_shown events +
contributeTrainingSample (no-op unless opted in). All fail-soft.
- release: browser-extension 1.9.36
Ships the Hanzo AI answer engine (new-tab landing + address-bar search over the
@hanzo/ai search primitive) with the newtab out()-path fix. v1.9.34 was the
pre-fix tag; this is the buildable release.
The answer-engine's esbuild wrote newtab.js to a literal dist/browser-extension/
path while every other bundle + the copy step use out() (=<root>/dist), so the
per-browser copy would miss it. Unify on out('newtab.js'). Build verified: Chrome/
Firefox/Safari bundles + newtab.js produced.
The @hanzo/usage sibling-path alias pointed at /…/usage that doesn't exist on
CI, breaking every release build. Both are now published deps resolved from
node_modules — CI build works. Bump 1.9.33→1.9.34 (1.9.33 store build failed here).
De-brand the native-CI dir to the Hanzo convention. .hanzo is the highest-
priority WORKFLOW_DIR on git.hanzo.ai and GitHub ignores it exactly as it
ignored .gitea, so this is behavior-neutral on GitHub and canonical on the
native runner.
Git of record moves to git.hanzo.ai; GitHub becomes a mirror.
- .gitea/workflows/{ci,publish}.yml — native pipeline on hanzo-build-linux-amd64
act_runners. publish.yml pulls Chrome Web Store + Firefox AMO + npm creds from
KMS via the machine identity (no store cred in any Actions secret store).
- deploy/kms/extension-publish-kms-sync.yaml — KMSSecret CR; canonical KMS path
hanzo:/extension-publish (env prod) for the store creds.
- .github/workflows/sync.yml — mirror main+tags to git.hanzo.ai (the only thing
GitHub does as system of record; no-op until HANZO_GIT_TOKEN seeded).
- .github/workflows/publish.yml — remove store-publish steps (CWS/AMO/VSCE/OVSX/
JetBrains — all no-ops today, those secrets never existed on GitHub). Keep the
live npm publish (interim) + the downloadable GitHub Release.
- docs: PUBLISHING.md + LLM.md rewritten to the native topology.
Non-breaking: npm publish (@hanzo/browser-extension) untouched. No store publish
in this pass. Gated on operator: seed KMS store values, Gitea secrets, mirror.
Add an AI Usage card to the action popup showing Claude and Codex
session/weekly % used + reset time, a refresh button, and a link to
console.hanzo.ai/ai-accounts.
- shared/usage.ts: browser UsageHost (fetch with credentials:'include',
no-op fs) running the @hanzo/usage engine in the background context,
where host permissions attach live claude.ai/chatgpt.com cookies and
bypass CORS. Claude via the package web strategy (empty cookieHeader
passes its gate; real cookie rides credentials:'include'); Codex via a
local fetch to /backend-api/wham/usage mapped onto the package's public
UsageSnapshot/RateWindow types (its provider only ships an auth.json
OAuth lane, unusable without disk).
- background.ts + background-firefox.ts: usage.fetch message handler.
- popup: AI Usage card + renderer, refresh, accounts link.
- build.js: alias @hanzo/usage to the sibling repo's built ESM for both
background bundles (same pattern as the @hanzo/gui shim).
- manifests: host_permissions for claude.ai + chatgpt.com (Chrome MV3 +
Firefox).
- version 1.9.31 -> 1.9.32 (patch).
Hanzo AI