Add a configurable fakeAuth (StubAuth can't express the logged-out case)
and assert: /welcome renders the logged-out CTA with no session and the
logged-in controls with one, unauthenticated / redirects to /welcome,
unauthenticated deep links redirect to /auth/login, and an authenticated
root still renders the list.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Wire GET /welcome on the root mux alongside /healthz, outside
Auth.Middleware. handleWelcome peeks the session via CurrentUser (no
redirect) and renders the logged-out or logged-in WelcomePage variant.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the public landing page: a static Charm-box tapir mascot (reusing the
shared tapirLine helpers and charm palette), a tagline, and a single
'Get Started' CTA into the shared Dex flow — sign-in and sign-up are the
same URL (ADR-012). Logged-in visitors get a greeting plus links back into
the app and to log out. Regenerated views_templ.go committed alongside.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Logout was bouncing the just-logged-out visitor straight back into a Dex
login. Land them on the public /welcome page instead — an intentional UX
fix. Cookie clearing and server-side session deletion are unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
An unauthenticated visit to / now lands on the public /welcome page
instead of bouncing straight to Dex. Deeper guarded paths still redirect
to /auth/login so the post-login round-trip returns the visitor to the
page they asked for. isPublicPath runs first, so no redirect loop.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The landing page must render without a session. Add /welcome to
isPublicPath so the auth middleware lets it through (alongside /healthz
and /auth/*), and assert the bypass in the public-paths test.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Workstream A: public /welcome landing page (bubbletea aesthetic, one Dex login
flow, logged-in shortcuts) — with the oidc.go facts verified against main, incl.
the two corrections that only surface from reading the code (logout must redirect
to /welcome not /auth/login; bare-/ vs deep-link redirect split).
Workstream B: reconcile the guardrail docs against deployed reality (v0.4.0) —
auth.go comments, data-model isolation status + migrations 002-006 schema,
architecture web surface, use-case scenarios for the Stage-1 features, ADR
ordering, and a requirements-vs-shipped deviation check. Structured as two
parallel workstreams so the doc audit isn't done cursorily alongside the build.
ADR-013 records the deliberate choice that account deletion is Tapir-side only
(cascade + secret purge), leaving the shared Dex identity intact — clean
re-registration, but a noted GDPR-shaped gap if Future C ever arrives.
ADR-014 specifies timedtext 429 handling: Retry-After-aware backoff, a single
per-egress-IP rate gate shared by the batch and click paths, and honest in-flight
UX (summarizing / queued-waiting / no-transcript) so a rate-limited fetch never
presents as a stuck spinner or error. Whisper stays deferred pending measurement
of the sustainable rate, which this work finally makes measurable.
Replace the plain ASCII spinner with a Charmbracelet-style TUI panel rendered in
the browser: a dark terminal card holding a rounded purple box (╭─╮╰─╯│) around a
pink block-char tapir (▄▓▀█) with mint eyes (◕ ◕) and a snout that wiggles ∩→∪→~
across three cross-faded frames, plus a lipgloss-style progress bar whose mint
fill grows over a dim track via an 8s CSS clip animation.
Colours come from named palette consts (CharmPurple/Pink/Mint/Cream/Dim) applied
as inline span styles, so the box and CSS share one source of truth. Frames are
built by a small run/line helper that pads each row to a fixed interior width —
an internal test asserts every box row is the same cell width so the border stays
flush. Honours prefers-reduced-motion (static frame + partial bar).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Extract the engine wiring (YouTube source, AI-router summarizer, store sink)
into buildProcessor, shared by cmdRun and cmdServe. It returns (nil, nil) — not
an error — on incomplete config, which is the queue-only fallback for serve.
engineProcessor adapts the engine to web.Processor: load the video row, run the
engine, clear the manual queue flag on a produced summary (mirrors the runner).
cmdServe wires it onto web.App.Processor; cmdRun reuses buildProcessor so the
wiring is no longer duplicated.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Clicking "Summarize" now runs the summary in the background (when a Processor is
wired) instead of only queuing it. The handler flips the DB flag, kicks off the
work on a detached context, and returns an animated "processing" card that polls
GET /v/{id}/status every 2s via HTMX. Status returns the summary card once it
lands (no poll → polling stops), the animation while in-flight, or the Queued
card otherwise. Queue-only behaviour is unchanged when no Processor is set.
The spinner is a CSS-only cross-fade of three ASCII tapir frames — no JS, honours
prefers-reduced-motion.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the seam for immediate web-triggered summarization. Processor is the
optional single-video summarize port (nil = queue-only, unchanged behaviour);
ProcessingSet is an ephemeral, concurrency-safe set of in-flight (user,video)
ids so a status endpoint can show progress until the summary lands. State is
deliberately in-memory only — the DB holds the durable truth across restarts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The list now shows ALL videos (ListVideos), not just summaries. Summarized cards
are unchanged; discovered-but-unsummarized videos render with a muted "pending"
treatment and either a "Summarize" button or a "Queued" chip.
- POST /v/{videoId}/summarize queues a video (RequestSummarize) and returns the
refreshed card — it does NOT run the engine inline; `tapir run` is the single
summarization driver, which picks up the flag on its next pass.
- Account page gains an Automatic/Manual toggle (POST /account/summarize-mode →
SetAutoSummarize), shown as the current mode with a one-click switch.
- Both new POSTs degrade without JS (redirect back); HTMX swaps the fragment.
VideoCard and summarizeModeControl are extracted templ fragments reused as the
HTMX swap targets. views_templ.go regenerated.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
RunOnce now reads the user's mode (GetAutoSummarize) at the start of each pass:
- Auto (unchanged): summarize every unseen video.
- Manual: still UpsertVideo for every candidate (discovery — the user sees new
videos in the list), but skip ProcessNewVideo unless the video is queued
(RequestedVideoIDs). A queued video is summarized, then its flag is cleared
(ClearSummarizeRequested) so it is not re-processed and the UI drops "Queued".
New Stats.SkippedManual counts discovered-but-unqueued videos. The VideoStore
port gains the three methods; the existing auto-mode tests set auto:true.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the store surface for summarization mode:
- SetAutoSummarize / GetAutoSummarize — per-user auto/manual toggle; an absent
user reads as manual (the safe default).
- RequestSummarize — queue one video (summarize_requested=TRUE); ErrNotFound
when the video is absent or not owned (RLS hides another user's row).
- RequestedVideoIDs / ClearSummarizeRequested — the run-loop side: load the
queued set per pass (mirrors SeenVideoIDs), clear after summarizing.
- ListVideos / GetVideoRow — drive from the videos table LEFT JOIN summaries so
discovered-but-unsummarized videos appear with empty summary fields. SummaryRow
gains additive Summarized + SummarizeRequested fields; the summary-only reads
are untouched.
RLS proof: rls_test.go gains a cross-user "queue B's video" write asserting it
touches zero rows (store-level scoping can't prove this — the test pool is a
superuser that bypasses RLS, same caveat documented there).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the schema for the summarization-mode feature: a per-user auto/manual
toggle (users.auto_summarize, default FALSE = manual) and a per-video manual
queue flag (videos.summarize_requested, default FALSE).
Both columns land on tables that already have ENABLE + FORCE ROW LEVEL
SECURITY (migration 003), so they inherit per-user isolation automatically —
no policy changes needed. auto_summarize is per-user, not global, per ADR-012.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
GET /account shows the registered display name, the signed-in email, the
user's connected video accounts (status + when), a Connect-YouTube link
when none is connected, and the disconnect / delete controls. Linked from
the header nav.
POST /account/disconnect/{provider}: deletes the OAuth token from the
SecretStore (resolved from the connection's own token_ref, provider-
agnostic) and the connection row. Does NOT delete the account.
POST /account/delete: confirm-before-destroy (a <details> disclosure gates
the destructive submit — works without JS). Captures token refs, calls
store.DeleteUser (cascades all rows), purges every secret, then routes to
/auth/logout to clear the session. Tapir-side only — Dex is left untouched
(decision 2026-06-03).
Account handlers depend on a narrow SecretRemover (Delete) and the extended
Store port; cmd/tapir serve shares one file-backed SecretStore between the
connect flow and account management.
Tests: account page renders connections + name + Connect link; disconnect
removes token (fake records Delete) + row and keeps the account; delete
wipes users/summaries/connections/identities and purges the token, then
redirects to logout.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a one-shot flash component used across the app — connect success,
disconnect, account delete, and registration — instead of per-page ad-hoc
markup. setFlash queues a short-lived HttpOnly+SameSite cookie carrying an
opaque code; takeFlash consumes it on the next full-page render (not on
HTMX fragments). flashBanner maps the code to a styled, role=status banner;
the message text lives server-side in flashMessages so the cookie never
carries free text and a forged/unknown code renders nothing.
Wire it into the list page (the PRG landing spot for connect/registration)
and set it on registration and connect-callback success. Styled with the
existing design-system tokens; header gains an Account nav link.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Account disconnect/delete needs to remove the per-user YouTube refresh
token from the SecretStore. Add Delete(ref) on the file-backed store,
mirroring Put: atomic temp-file+rename, 0600, no-op on an absent ref.
Kept off the read-only ports.SecretStore (Get) — write/delete follow the
existing auth.TokenWriter convention of narrow capability interfaces, so
the youtube adapter's read-only dependency is unaffected.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
DeleteUser permanently removes a user and all owned data, scoped via
withUser. The users-row ON DELETE CASCADE reaches videos, transcripts,
summaries → sink_deliveries, video_connections, and the user_identities
map (cascades bypass RLS, so a scoped connection still wipes child rows).
summary_actions carries user_id but has NO FK to users (migration 002),
so it is deleted explicitly in the same scoped transaction. Idempotent.
Tapir-side only (decision 2026-06-03): Dex identity is left untouched;
secrets live in the SecretStore and are removed by the account handler.
DisplayName returns the registered name for the account page.
Test proves deletion removes every row for the target user across all
isolated tables (incl. video_connections AND user_identities) and leaves
another user's rows fully intact.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add GET /oauth/youtube/connect and /oauth/youtube/callback, mounted inside
the login + registration guard so CurrentUserID is always set and every
connection binds to the authenticated tapir user.
- connect: generate a per-user CSRF state (single-use, short TTL, bound to
the user), redirect to Google consent with access_type=offline and
prompt=consent so a refresh token comes back.
- callback: verify the state belongs to this user, exchange the code via the
existing auth.Exchange, persist the refresh token under a PER-USER ref
(web.YouTubeTokenRef = "youtube/<userID>/refresh_token") so tenants never
collide, then UpsertConnection (provider=youtube, status=active). Any
failure renders a clean error page and leaves no half-written state.
Reuses auth.Exchange and adds auth.AuthCodeURL (offline + consent) rather
than the CLI's listener/terminal flow (ADR-006: web flow, not CLI). The
ConnectHandler depends on a narrow web.Connections port, not the concrete
store. Wired in cmdServe only when YT client credentials are present;
TAPIR_YT_CONNECT_REDIRECT_URL configures the callback URL. Per-user token-ref
scheme documented in docs/homelab-integration.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the video_connections table (data-model VIDEO_CONNECTION) with FORCE
row-level security keyed off tapir.current_user_id, identical to migration
003's per-user isolation pattern — connections are user-owned data and must
be isolated at the DB layer, not only by application WHERE clauses.
Store methods (UpsertConnection / ConnectionsForUser / DeleteConnection) all
route through withUser so RLS scopes every access. UpsertConnection is
idempotent on (user_id, provider). The OAuth refresh token never lives here;
token_ref is the opaque SecretStore reference.
Extend the RLS isolation proof to cover video_connections: seeded per user,
included in the deny-all + scoped-read assertions, and added to the
cross-user write-invisibility and survivor checks.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Multi-user web surface. Two layered middlewares: Auth.Middleware (Dex
session required) wraps registrationGate, which resolves the authenticated
subject -> tapir user_id once per request via the new web.Identity port and
stashes it. A subject with no tapir user is redirected to GET /register
(display name + accept-terms); POST /register calls RegisterUser then
redirects to /. /register is inside the auth guard but exempt from the gate
(/auth/* and /healthz too).
Current-user seam: CurrentUserID(r) (string, bool) returns the resolved id
from the request context. The list/detail/action handlers now scope by it,
replacing the single configured App.UserID (removed). App gains an Identity
field; *store.Store satisfies both Store and Identity. cmd/tapir wires
Identity: st and drops UserID.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ADR-011's single-user authz (ID-token subject must equal AllowedSubject,
else 403) is replaced by ADR-012's model: Dex authentication is the only
gate — any Dex-authenticated subject may establish a session. Whether that
subject has a tapir user, and routing to registration if not, is decided
downstream in internal/web (next commit).
Removals (noted): oidc.Config.AllowedSubject + its required-field check + the
callback 403 branch; config.Config.AllowedSubject + TAPIR_ALLOWED_SUBJECT env
wiring; the AllowedSubject arg in cmdServe. ui-spec.md updated to reflect the
supersession. Sessions, cookie signing, login/callback/logout unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the Dex-subject -> tapir-user_id bridge for multi-user Stage 1.
Migration 004 creates user_identities (dex_subject PK, user_id UNIQUE FK
ON DELETE CASCADE). It is intentionally NOT RLS-enabled: it holds no user
data and must be readable BEFORE a user_id is known (the lookup is what
yields the id used to set tapir.current_user_id). RLS here would be a
chicken-and-egg deadlock; data isolation stays on the user-owned tables.
UserBySubject resolves subject -> user_id as a plain pool query (pre-scope,
no withUser). RegisterUser generates the UUID app-side (stdlib crypto/rand,
no new dep) so the forced-RLS WITH CHECK (id = GUC) passes, then inserts the
users row via withUser(newID) and the identity row in the same transaction.
Re-registration of a subject errors with ErrSubjectRegistered.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The isolation proof for ADR-012. embedded-postgres's default user is a
SUPERUSER, which bypasses RLS regardless of FORCE — a test run as it would be
fake-green. So this test creates a dedicated non-superuser role ("app", mirroring
the prod owner tapir), grants it DML, asserts rolsuper is false, and runs every
scoped query as that role.
Assertions: (1) deny-all — with no GUC set, every isolated table returns zero
rows, proving the enforcement path is live, not bypassed; (2) a connection scoped
to user A sees exactly its own one row in every table (and B likewise); (3)
cross-user UPDATE/DELETE aimed at B's rows touches zero rows; (4) B's rows survive
unchanged, verified via the superuser pool.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add Store.withUser(ctx, userID, fn) — a single choke point that BEGINs a tx,
sets the transaction-local GUC tapir.current_user_id via
set_config(..., true), runs fn, and commits. set_config is used over SET LOCAL
because it is parameterizable; the local flag means the value auto-resets on
commit/rollback so a pooled connection never leaks one request's user into the
next.
Route all 9 DB-touching methods through it (Deliver, HasSummary, SeenVideoIDs,
ListSummaries, GetSummaryByVideo, SetAction, ClearAction, ActionsFor, and
UpsertVideo; attachActions flows via ActionsFor). Scoping is now structural —
not a per-query opt-in someone can forget — and arms the migration-003 RLS
policies. Method signatures and existing WHERE clauses are unchanged (defence in
depth; superuser DSNs in existing tests bypass RLS so behaviour is preserved).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Enable AND FORCE row-level security on every user-owned table (users, videos,
transcripts, summaries, summary_actions, sink_deliveries) per ADR-012. Each
policy keys off the per-request GUC tapir.current_user_id; an unset GUC yields
NULL → deny-all (the safe default).
FORCE is load-bearing: the app connects as the table owner (tapir), and owners
bypass RLS unless forced. Without FORCE the policies are dead for the prod user.
sink_deliveries has no user_id; its policy derives ownership from the summary it
belongs to via EXISTS against the GUC, so it is self-contained rather than
silently depending on summaries' own RLS being applied to a subquery.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Render a muted one-line lede beneath the title/meta of each summary
card via previewText(r.Summary, 160). New .card-preview token clamps to
one line. Regenerated views_templ.go committed (CI has no templ binary).
Responsive 16:9 youtube-nocookie iframe rendered when the id is valid;
omitted (graceful) otherwise so summary/highlights/takeaways still show.
Regenerated views_templ.go.
One-line lede for list cards: collapses whitespace, prefers the first
sentence within budget, else word-boundary truncation with an ellipsis.
Pure and rune-based (multibyte-safe). Table-driven tests cover empty,
short, first-sentence, word-boundary, and multibyte cases.
Maintainer's call to open Stage 1 ahead of the Stage-0 gate. Non-negotiable:
multi-user ships WITH DB-enforced isolation (Postgres RLS, FORCE'd on the
owner role, per-request tapir.current_user_id) and a passing two-user isolation
test in the same slice — the VISION Stage-2 bar pulled forward, not deferred.
Replaces ADR-011's allowlist-of-one with per-subject users rows; adds
video_connections + subscriptions.
Diagnosis of a live run: caption tracks resolve fine (player + watch-page scrape),
but the timedtext baseUrl fetch returns 429 under back-to-back volume — YouTube
rate-limits the unauthenticated caption-download endpoint per IP. A per-video
delay spaces the fetches. (Follow-up: treat 429 distinctly from genuine
no-caption instead of silently degrading to SourceNone; consider Whisper if the
endpoint stays hostile at any sustainable rate.)
The ANDROID InnerTube player now returns 0 captionTracks (PoToken-gated), so the
watch-page scrape is the real path — but it sent an Android *app* User-Agent,
which makes YouTube serve a page WITHOUT ytInitialPlayerResponse, so captions
came back empty. Result: 87% of a live run skipped as 'no transcript' despite
the videos having captions. A desktop-browser UA returns the player JSON with
captionTracks. Confirmed live: app-UA=0 tracks, browser-UA=1.
First-login chicken-egg: TAPIR_ALLOWED_SUBJECT can't be known until the user
logs in once, but the allowlist gates login. Echo the (non-secret, opaque)
subject in the forbidden response so the maintainer can read it in the browser,
set the 1P item, and lock the allowlist.
go.mod requires >=1.26.1 but the Dockerfile pinned golang:1.25 -> 'go.mod
requires go >= 1.26.1 (running go 1.25.11)'. Also revert the ci.yml XDG hack:
the real rootless-buildah fix is a user ~/.config/containers/storage.conf (vfs +
writable runroot), which fixes plain buildah for every repo without workflow
changes.
The act_runner is a systemd service with no login session → XDG_RUNTIME_DIR
unset → rootless buildah uses root-owned /run/containers and fails 'mkdir
/run/containers: permission denied'. Set XDG_RUNTIME_DIR to a per-job mktemp
dir so its runroot is writable. (check + on:/go-version fixes already landed;
this unblocks the image build → registry.)
CI check failed in internal/adapters/store: parallel 'go test ./...' starts
multiple embedded-postgres instances against the shared ~/.embedded-postgres-go
data dir → 'another postgres running in data directory'. -p 1 runs one package
at a time, so only one embedded-postgres is live. (Locally flaky, deterministic
in CI's fresh env.)
CI check failed because go.mod declared 'go 1.25.0' — the only repo not on the
host's 1.26.x line. actions/setup-go then tried to download 1.25.0 on the
self-hosted runner (fails), while cobalt (1.26.1) and template-go-agent (1.26)
serve from the host/cache. Deps need >=1.25, so 1.26.1 satisfies them and
matches the estate.
Bare 'on:' is a YAML boolean (Norway problem) — parsed as the key True, not
the string 'on'. Gitea's workflow loader then materialised 0 jobs and every run
failed instantly. Quoting "on": fixes dispatch.
Light + dark list, mobile (375px) card reflow, and the reader detail page in
both schemes — captured via web-shot against the seeded serve. Visible evidence
that the Top 5 UX fixes landed.
Implements the Top 5 fixes from the Stage-0 UX review (docs/ux-review/UX-REVIEW.md):
1. Dark mode: full light+dark custom-property palette (bg/fg/muted/line/accent/
card) under :root + @media (prefers-color-scheme: dark), applied to body.
color-scheme: light dark is now actually honoured — summary text was invisible
on a dark canvas before.
2. Table -> responsive card list: one card per summary (title link, channel·date
meta, provider chip, fallback badge, action state). Single-column reflow at
375px, no horizontal crush.
3. Minimal design system: 4/8px spacing scale, one accent, styled accent links
(underline-on-hover), real buttons with active/pressed state, consistent
radius and dividers — applied across list + detail.
4. Detail page as a reader: prose capped at 38rem, title->meta->summary->
highlights->takeaways hierarchy with section rules, 1.7 line-height. Meta is
built from non-empty parts (detailMeta) so the no-video edge case no longer
renders a stray "· — ·".
5. Contrast + a11y: muted bumped to #595959 (~7:1, clears WCAG AA), fallback
badge gets vertical padding + aria-label/title, friendly first-run empty
state, hx-indicator on the filter form.
Tests updated for the card markup (table -> cards); missing date is now omitted
rather than em-dashed. task check green; HTMX action toggles verified working.
Stage-0 web UI needs a self-contained container image. Two changes:
- Dockerfile: multi-stage build (golang:1.25 builder, CGO off + static
link, -trimpath -s -w) into distroless static nonroot. The committed
templ output and vendored asset mean a plain `go build` suffices — no
codegen or CDN at build/run time. Existing .gitea CI already builds and
pushes localhost:5000/tapir:<sha> + mirrors to GitHub (deploy patch
intentionally omitted — cutover is held), so it only needed this file.
- Vendor htmx 1.9.12 locally (internal/web/static/, embed.FS, served at
/static/ outside the auth guard) and point Layout at /static/htmx.min.js
instead of unpkg. The deployed UI must not depend on an external CDN
being reachable from the cluster.
task check green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reviewer pass against running `tapir serve` UI, seeded with 11
representative summaries (5 channels, rich+sparse, local+fallback,
varied action states). Captured via Playwright on koala k3s across
desktop/mobile and light/dark color schemes.
Two blocking findings: dark mode is unreadable (summary text near-black
on a dark canvas — `color-scheme: light dark` declared but `--fg`
hardcoded and no body background), and the list is a 6-column table that
does not reflow on mobile. Plus a sub-4.5:1 muted color, an unstyled
"admin table" surface, and small correctness nits (stray `· — ·` meta
join, cramped fallback badge). HTMX action toggles verified working.
Includes UX-REVIEW.md (severity-tagged findings + Top-5 sleek list) and
16 screenshots. No code changed — drives the next UI iteration.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
mathiasandClaude Opus 4.8