- connect_account.feature: refine the burst scenario to "best recent" (likely-good
selection, skips too-short/too-long) and add a scenario for the stronger model.
- scenario_coverage: remap to TestOnboardBurstVideoIDs + add the model scenario
(the old NewestUnsummarizedVideoIDs test was removed).
- architecture.md: new "Connect-time onboarding burst" subsection — junk-avoiding
selection over persisted duration, the burst-only stronger-model chain, and why
has-captions/cached-first are not selection signals.
Phase-1 live-DB investigation found the connect-time burst (ADR-018) fires
but delivers a weak first impression: pure newest-first selection picks junk
(a livestream + regional news for pilot user Jonte), and all burst summaries
run on the weak koala/phi4-mini instead of the validated iguana/gemma4-26b.
Cached-first was investigated and rejected — ~3% cross-user overlap, 0
cached-and-unsummarized, newest-20 all uncached (newest-first and cached-first
are structurally incompatible).
ADR-028 records: persist duration_s at discovery (ADR-023 already fetches it,
just stops discarding), junk-avoiding burst selection (drop known too-short/
too-long), and a stronger burst-only summarizer chain. Not a throughput change.
The chat was a separate page — opening it left the summary behind, the very
context you're asking about. Now the chat docks open IN PLACE below the summary:
"Dig deeper" reveals the chat section (HTMX, outerHTML over the closed dock) so
the summary stays on screen above it; no navigation. The no-JS fallback renders
the full summary AND the open chat on one page (the same integrated view), so
progressive enhancement holds.
Extracts a shared summaryBody templ so the detail page and the chat page render
one identical summary, not two divergent ones. GET /v/{id}/chat returns just the
open chat section as a fragment for the inline reveal, or the full summary+chat
page for a no-JS navigation; POST swaps the panel inline or re-renders the whole
page. Tests assert summary+chat coexist on the page and the reveal is a fragment.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A deeper-dive chat entered from the summary view: ask questions about a video
against its already-stored transcript (ADR-021), no caption fetch, ever.
Safety by construction — the load-bearing property. The chat handlers reach the
chat.Service only after reading the SHARED stored transcript via Store.GetTranscript
(a pure DB read); the service holds no VideoSource. So an enabled chat cannot
trigger a caption fetch, touch the rate gate, or reach YouTube. A video with no
stored transcript gets an honest "not available" — no fetch, no model call. The
key web test wires the summarize/fetch collaborators as tripwires that fail the
test if chat ever routes into them, and asserts the model answered from the
stored text.
Model defaults to the summary's own model and is switchable among the ADR-022
chain (phi4-mini → gemma4-26b → mistral-small); switching re-runs against the
same transcript — deliberate model-comparison instrumentation. The cloud model
is absent from the switcher when TAPIR_CLOUD_FALLBACK_MODEL="" (the local-first /
NDA lever), honoured the same way the summarizer honours it. Reuses the existing
LiteLLM gateway client (a chat is a different call, not a new integration) and
the TAPIR_MAX_TRANSCRIPT_CHARS truncation, surfacing an honest bounded-context
note when a long transcript is cut.
Ephemeral v1: the multi-turn conversation rides in hidden request fields; no
table, no migration, nothing persisted. Entry is RLS-scoped through
GetSummaryByVideo, so chat is reachable only from the user's own summary view.
Show-source verification and on-demand fetch are deferred (ADR-027).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Per-video chat against the ADR-021 stored transcript, entered from the summary
view, born from observed demand (maintainer read real summaries, some made him
want to dig deeper). HARD constraint: stored-transcript-only — never fetches
captions, never touches the rate gate or YouTube, safe by construction. Default
model = the summary's model, user-switchable among the ADR-022 chain models
(doubles as model-comparison instrumentation). Ephemeral v1 (no persisted
history); chat-only/trust-the-model with show-source verification recorded as the
natural v2. ADR-027 to be appended to DECISIONS.md as the first commit.
koala now carries other GPU loads, so the first fallback should not run there.
Change the default chain to koala/phi4-mini → iguana/gemma4-26b → berget/mistral-small:
the local fallback now runs on iguana (M2 Ultra headroom, different host = different
egress IP for the rare fallback fetch). gemma4-26b is the brain-validated homelab
general-purpose model (agentsquad H2/H3 executor) and returned valid summary JSON on
the real prompt in a smoke test (~37s incl. cold-load — fine for a fallback path).
Pure config default (TAPIR_FALLBACK_MODEL); chain mechanism (ADR-022) unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
After transcript caching (ADR-021) and the Shorts filter (ADR-023), the remaining
caption waste is the first fetch on every new video of a channel that never has
English captions — each costs one rate-limited fetch to resolve to "none", and on
a throttled IP churns the backoff machinery first.
Remember, per (user, channel), a streak of consecutive no-caption outcomes
(channel_caption_state, migration 016, RLS-scoped). Once it reaches
TAPIR_CHANNEL_CAPTIONLESS_THRESHOLD (default 5) the channel is suppressed — videos
discovered/listed but not caption-fetched — for TAPIR_CHANNEL_CAPTIONLESS_WINDOW
(default 14d), then one is re-probed (auto-recovery). A successful fetch resets
the streak; a 429 does not count; an explicit manual request bypasses suppression.
threshold=0 disables.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The scarce resource is the per-IP timedtext caption fetch (ADR-014); the pilot's
candidate set was mostly Shorts/clips/livestreams, each burning a fetch (a "none"
result is a completed fetch — it costs budget even when it yields nothing).
NewVideos now enriches candidates with one cheap Data API videos.list call
(contentDetails.duration + snippet.liveBroadcastContent — the quota API, a
DIFFERENT limit from the timedtext 429) and drops, before returning: videos
shorter than TAPIR_MIN_VIDEO_SECONDS (default 60) and any live/upcoming
broadcast. Dropped videos are never persisted, so the list declutters too.
Degrade-open: MinVideoSeconds=0 disables it (no quota call); a videos.list error
returns candidates unfiltered so discovery never breaks on a metadata hiccup. The
paste-a-URL path (VideoByID) is not filtered — an explicit request is honoured.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The first friendly-pilot live run produced zero summaries: koala/phi4-mini hit
three silent failure modes — 8k context overflow on long transcripts (HTTP 400),
intermittent malformed JSON (highlights as a bare string), and no fallback wired
at all (summarizer.New(primary, nil)).
Keep phi4-mini as the fast primary and add resilience around it:
- Ordered endpoint chain (summarizer.NewChain): phi4-mini → koala/phi4-14b
(local) → berget/mistral-small (worst-case external). All reached through the
one LiteLLM gateway by alias.
- A parse failure now advances the chain like a transport error — the old
Primary→Fallback shape returned the parse error without trying anyone else.
- Tolerant parse: highlights/takeaways coerce string→[]string, absorbing the
common small-model quirk without spending a fallback round-trip.
- Transcript truncation (TAPIR_MAX_TRANSCRIPT_CHARS=18000) prevents the overflow
rather than recovering from it; validated to fit phi4-mini's 8k window.
- Bounded completion budget (TAPIR_SUMMARY_MAX_TOKENS=1500) — the old 8192 budget
itself contributed to the overflow.
Local-first guarantee preserved by ordering: external endpoint is tried only
after every local one fails. TAPIR_CLOUD_FALLBACK_MODEL="" disables it entirely
for client/NDA deployments.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Capture the ADR-021 promise as a mapped BDD scenario: re-analyzing a
stored video reads the stored transcript and does not fetch captions.
Since paste-a-URL and the onboarding burst summarize through the same
engine chokepoint (resolveTranscript, store-first), this one scenario
covers their reuse path too — there is exactly one gated caption entry
point (youtube.FetchTranscript → WaitFetchGate) and one engine caller in
front of it, so the dedup is structural, not per-feature.
Mapped to TestProcessNewVideo_SecondSummarizeDoesNotRefetch.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reshape the dead per-user transcripts table (PK videos.id, user_id,
RLS-FORCEd — never read or written by app code) into the shared public
caption store ADR-021 specifies: keyed by (provider, provider_video_id),
no user_id, NOT RLS-scoped. Migration 015 (reversible). Add
ports.TranscriptStore + Store.GetTranscript/SaveTranscript via the raw
pool (no withUser): public content, shared across users by construction.
SaveTranscript persists only terminal outcomes (captions/none) and
refuses SourceRateLimited so a transient 429 can never be stored as a
false permanent absence (ADR-014).
Flip the isolation proof: transcripts leaves the RLS-scoped set;
TestTranscriptsTableIsSharedNotRLS asserts it is the SINGLE non-RLS
surface (writable/readable with no user scope, no user_id column, RLS off
on it alone, still on every user-owned table) — the proof the
public-content classification was applied exactly here and leaked nowhere.
appPool made idempotent so two tests can build it. Adjust the 010/011/014
up-down migration tests for the new HEAD. account.go: user deletion no
longer strips shared transcripts. Reconcile data-model.md + CLAUDE.md.
Wiring the engine to read-stored-first is the next commit.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds paste_url.feature (valid/invalid/not-found/dedup, +@pending no-captions)
and an onboarding-burst scenario on connect; all non-pending scenarios mapped in
the coverage gate to their existing Go tests.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A newly connected account showed no videos until the next 2h scheduled pass —
the gap that made onboarding look broken (a second user connected, saw nothing,
read as failure). The connect callback now fires an out-of-band discovery pass
for the connecting user, so videos appear promptly.
Concurrency: scheduled and connect-triggered passes share one lock (serialize),
preserving the single-fetcher invariant (ADR-018). A trigger interleaves between
the scheduler's per-user passes rather than fetching concurrently or waiting for
a whole pass. The trigger runs on the server ctx (survives the redirect) and is
non-blocking for the request goroutine.
Scope: connect-trigger only. The optional login-refresh / "Discover now" button
from #6 are intentionally not built — an unconditional login hook risks 429
storms (per the ticket's own recommendation); defer until wanted.
TDD: TestCallbackTriggersDiscovery, TestSerializeRunsOneAtATime,
TestDiscoveryTriggerEnqueueRunsUser; new BDD scenario mapped.
Refs #6
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Close the gap where docs/use-cases/*.feature claimed to be the behavior spec
but nothing executed them — so scenarios drifted (the stale "auto summarizes
every new video" and "manual is the default" were proof).
Decision (per issue #5 BDD-runner fork): no godog — keep .feature as design
records, add a cheap name-coverage gate instead. TestScenarioCoverage parses
every scenario and asserts each non-@pending one maps to an existing Go test in
the scenarioCoverage manifest; it flags unmapped scenarios, missing/renamed
tests, and stale entries. It checks the link, not that the test exercises the
scenario (the deliberate trade for skipping godog).
Also:
- Fix the stale ADR-018 drift: "Manual is the default" -> auto is the default
for new users; added an explicit default scenario + a plain manual scenario.
- Tag 4 documented-but-unbuilt/untested scenarios @pending with reasons (Vimeo
connect, BYO config flow, logout->welcome, re-register-after-delete) so they
are tracked without a false coverage claim.
- CLAUDE.md BDD section now describes the real setup (design records + the gate
+ @pending convention) instead of claiming an executable spec.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Bring the living docs current with the recency-bounded auto-summarize + sparse
honesty + feed IA bundle (ADR-020):
- requirements (BDD): summarize_mode.feature — auto now summarizes RECENT new
videos; added a scenario for older videos (listed, on-demand), recency note.
- architecture.md: summarization-mode + new list-surface paragraph; scheduler
diagram + two-path table + three-phase pass now show the recency pre-filter;
dropped stale "Summarize now".
- data-model.md: auto_summarize is recent-only, older on-demand.
- README.md: one-line recency note on the serve scheduler.
- ui-spec.md: appended the as-built ADR-020 row (supersedes earlier copy/sort).
- specs/{video-card-states,newest-first-ordering,scheduled-discovery}.md:
superseded/extended banners pointing at ADR-020 (kept as design records).
Docs-only; task check green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Prioritized UX findings for the product as it actually is — sparse feed,
respected caption rate limit, recency-bounded auto-summarize (incoming),
single-user. 15 findings, NOW/LATER tagged. P0s target the first-contact
return-cliff that the Stage-0 gate depends on.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Record the invite-provisioning removal; mark ADR-017 superseded; fix
ui-spec invite-onboarding + auth-delegation sections to reflect Authentik.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The card shows two verbs ("Try now" for rate-limited, "Summarize" for pending)
for one user intent, and — the real bug — a no-captions video falls into the
pending branch and wrongly shows a Summarize button that can only fail. Spec
collapses to one quiet "Summarize now" verb wherever a nudge is possible (both
handlers unchanged underneath), adds an honest no-button "No transcript
available" state, and keeps the card status-first (buttons are exceptions in auto
mode). View-layer only.
'Try now' and the newest-first batch implement onboarding prioritisation:
foreground (user-clicked 'Try now') summarises a chosen video on demand;
background batch summarises newest-first; both honour the shared rate gate.
Remove any prior framing that described 'Try now' as making traffic 'look
organic to YouTube' or as rate-limit evasion — that was not the rationale
and contradicts ADR-014's explicit account-safety constraint.
Correct statement: rate limiting is respected, not evaded. TAPIR_FETCH_RATE
and TAPIR_FETCH_BACKOFF are honest rate controls; they govern how fast Tapir
fetches captions, not how the requests appear to YouTube.
Architecture: add two-path model table (foreground/background, both through
globalFetchGate) and newest-first batch ordering doc (three-phase RunOnce,
before/after example).
ui-spec: add 'Try now' row with correct rationale; add pipeline stats bar row;
update Summarized-only filter row to mention sort-to-top.
Product intent: new users get summaries of their newest videos fast while the
back-catalogue fills behind, within the shared rate gate. The background batch
currently processes in subscription/channel order, not newest-first — this spec
closes that gap (collect candidates, sort published_at DESC NULLS LAST, process
in order, gate unchanged). Also corrects the docs to describe Try-now as
onboarding prioritisation, explicitly removing the prior "looks organic to
YouTube" traffic-disguising framing — rate limiting is respected, not evaded.
homelab-integration.md gains a "Scheduled discovery" section documenting
TAPIR_DISCOVERY_INTERVAL and TAPIR_FETCH_RATE and the load-bearing
single-replica constraint (in-process scheduler → replicas: 1 is required;
>1 double-runs discovery). VISION Stage 0 carries a pointer to ADR-018's
gate-clock reset so nothing in docs implies the window started before
unprompted use was possible.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Stage-0 usability fix: tapir serve runs discovery for all users on an
interval (reusing the existing Runner.Loop, enumerate-users-then-withUser),
auto-summarize defaults ON for Future-B users so the list fills itself, and the
ADR-014 process-wide per-egress-IP rate gate is confirmed/finished in the same
slice because in-process + auto + multi-user makes it load-bearing. Records the
single-replica constraint as load-bearing, and a fallback (auto-summarize OFF
until the gate exists) so the dangerous combination never ships half-built.
Small tapir slice to make the gate measurable as written: append-only
login_events (RLS, per-user-per-day throttle) + a union query over reads
(login_events) and acts (summary_actions) for distinct-active-weeks. Carries the
honesty caveats (unprompted not measurable; data accrues from deploy; week-bucket
noise at low N) and the delete-cascade footgun (no FK, needs explicit delete +
test) from the prior delete work. Out of scope: analytics, prompt-tracking,
dashboards.
429 from the caption endpoint means the IP is rate-limited (retry later),
not that the video has no captions. Distinguishing it from SourceNone is the
prerequisite for the runner's backoff/retry logic.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Stage-0 ui-spec (ADR-011) predated multi-user and several UX
features. Appended a "Deviations and additions (as-built)" table —
without rewriting the spec — recording each feature shipped beyond it
(multi-user+RLS, registration gate, per-user YouTube connect, account
management, immediate web summarization, charmbracelet spinner,
auto/manual mode, public landing page) with the why and the
commit/ADR that covers each. Preserves the intent-vs-reality split.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The .feature spec lagged shipped behaviour. Added three files, no
duplication of existing scenarios:
- registration.feature: new Dex subject -> registration gate (users +
user_identities), returning subject straight through, account delete
is tapir-side only and leaves other users intact, clean
re-registration (ADR-012, ADR-013).
- summarize_mode.feature: auto summarizes every new video; manual
(default) leaves them unsummarized until queued; queued video is
processed and the flag cleared (migration 006).
- landing_page.feature: unauthenticated / -> /welcome, Get Started for
guests, summary link + logout for authed users, logout -> /welcome.
Scoped to built features only — no Vimeo/Whisper/billing scenarios.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The C4 view predated the web transport. Added a "Web surface" section
with a component diagram and prose covering: tapir serve (HTMX+Templ
over the unchanged store), oidc authenticate-only session, registration
gate (users + user_identities), per-user YouTube web connect callback,
account disconnect/delete (ADR-013 tapir-side only), immediate
summarization via background goroutine + HTMX status poll, and
auto/manual summarize mode (migration 006). Relabeled the L2 http node
to tapir serve. Corrected the out-of-scope isolation bullet: RLS is live
(ADR-012, migration 003), not deferred. ADR-003 stance preserved — the
engine/ports/sinks core is untouched; the web is a new transport.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The ER diagram and notes predated migrations 002-006. Brought them to
code truth:
- add summary_actions (002), user_identities (004), video_connections
(005) with real columns/constraints; rename token_secret_ref ->
token_ref to match migration 005.
- add users.auto_summarize and videos.summarize_requested (006).
- note FORCE RLS coverage and sink_deliveries' EXISTS-derived policy
(003); user_identities NOT RLS'd.
- mark AI_CREDENTIAL and SUBSCRIPTION as planned (no table exists; only
videos.subscription_id, no FK).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The "Isolation invariant" section said enforcement was dormant at
Stage 0. ADR-012 turned it on: Postgres RLS ENABLE+FORCE on every
user-owned table (migration 003_rls.up.sql), keyed off the
tapir.current_user_id GUC set by the store's withUser helper, deny-by-
default on an unset GUC. The Stage-2 two-user isolation test
(internal/adapters/store/rls_test.go) is pulled forward and passing.
Kept the ADR-011 single-user history honest.
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.
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>
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>
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.
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>
Reader + watch/skip/save (instruments the Stage-0 'acts on a summary' metric),
HTMX+Templ over the existing store, Dex OIDC login with single-user allowlist
authz (authn now, tenancy deferred), deployed at tapir.d-ma.be via Flux GitOps
with ESO secrets and in-cluster postgres18. Build decomposed into 4 gated lanes.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Vimeo texttracks API is owner-only (worse than YouTube, no public timedtext) → defer.
Whisper viable as a no-caption fallback; berget/whisper-large-v3 already on the gateway
(cloud), local options on iguana/koala carry setup+GPU-contention cost (ADR-007). Both
investigated inline (session sub-agents are network-sandboxed).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
main.go dispatches `tapir auth` (interactive OAuth → persist refresh token via
SecretStore) and `tapir run` (wire YouTube source + local summarizer + store
sink, build engine, run the dedup-aware loop). Config-driven so live creds plug
in at demo time; SIGINT stops the loop cleanly. Block kept minimal so Worker E's
list/show cases union cleanly at merge.
Add .env.example documenting every TAPIR_* var and a README demo runbook. Pin
the summarizer alias-as-config decision and record the max_tokens fix in
docs/homelab-integration.md (clears two `confirm` items).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Implement ports.Summarizer in internal/adapters/summarizer. It routes through a
local Primary endpoint first and an optional BYO Fallback, owning the routing
itself (not delegating to llm.Router) so it can record AIProvider, AIModel, and
FallbackUsed on domain.Summary. Prompt asks for JSON {summary, highlights,
takeaways}; the parser tolerates thinking-model fences/reasoning and rejects an
empty summary.
The summarizer is the single egress point for content toward an AI model, so it
enforces the local-first guarantee from ai_routing.feature: with no BYO
configured (nil fallback) there is no external endpoint, so content reaches the
local stack and nowhere else. Tests assert all four scenarios via a fake client.
Model alias is config (TAPIR_SUMMARIZER_MODEL, host/name) — not hardcoded;
docs/homelab-integration.md notes it stays `confirm` and that thinking models
need an explicit max_tokens or they return empty content.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Conductor verified against the live koala k3s cluster before launching the
adapter workers: LiteLLM is in ns ai-stack, ClusterIP 10.43.159.89:4000,
off-cluster NodePort 30401. The doc's 31234 was actually llama-swap. Also
flag that sk-local-123 now 401s — use LITELLM_MASTER_KEY from the vault.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Lists the egress the build assumes (Go module proxy, toolchain download,
raw.githubusercontent for golangci-lint, github for non-proxied modules) and the
runtime assumes (LiteLLM gateway, brain-mcp, YouTube/Vimeo APIs, per-user BYO-AI
hosts only on opt-in), so a locked-down koala act_runner or dev env knows what to
allow or which GOPROXY to set. Notes the claude.ai sandbox allowlist is separate
and unrelated.
Gherkin spec for connecting YouTube/Vimeo accounts and configuring optional
per-provider BYO AI credentials: connections sync subscriptions, tokens/keys are
stored only as secret references (never in the clear), revocation stops watching
but preserves history. Encodes the secrets-by-reference and data-isolation
guardrails (ADR-002, ADR-006, data-model).
mathias
