mathias/tapir
1
0
Fork 0
Code Issues 25 Pull Requests Actions Packages Projects Releases Wiki Activity
257 Commits 1 Branch 36 Tags
72cb25111fcdcef634284cf0222c9289c8d12cfb
Commit Graph
3 Commits
Author SHA1 Message Date
mathiasandClaude Sonnet 4.6 38f222c931 chore: rename Go module path gitea.d-ma.be → git.d-ma.be
CI / Lint / Test / Vet (push) Successful in 11s
Details
CI / Build & Import (push) Successful in 12s
Details 
Infra ADR-0004 renamed the Gitea host. Bulk replace across go.mod and
all .go import paths. Build and tests pass unchanged.

Closes #20

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dt6aHEDWRjkK14Voi6HnGh
 2026-07-02 14:37:33 +02:00
mathiasandClaude Opus 4.8 cd461b95f8 feat(observability): instrument AI + HTTP paths, serve /metrics on a side port (ADR-030, #15)
CI / Build & Import (push) Successful in 11s
Details
CI / Lint / Test / Vet (push) Successful in 10s
Details 
Wire the metrics package into the live paths and serve it:
- summarizer: per-endpoint latency by model/outcome(success|error|parse_error)/fallback + slog.
- youtube.FetchTranscript: latency by outcome (captions|none|rate_limited) + slog.
- chat: answer latency by model + slog.
- llm usage hook → token counts (prompt|completion) per model, wired in buildSummarizer/buildChat.
- oidc callback: login counter.
- cmdServe: wrap Router in metrics.HTTPMiddleware (request count + latency by bounded
  route pattern) and serve /metrics on TAPIR_METRICS_ADDR (default :9090), a SEPARATE
  port — never on the public app mux.

BDD: observability.feature scenarios un-pended + mapped. TDD: summarizer wiring tested
black-box via the /metrics scrape; metrics-not-on-public-mux asserted.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-12 08:49:51 +02:00
mathiasandClaude Opus 4.8 cc3cda4ab8 feat(chat): stored-transcript QA service (ADR-027) 
A read-only deeper-dive over a video's already-stored transcript (ADR-021).
Safe by construction: the Service has no VideoSource and no caption-fetch
dependency — only a Completer factory over the existing LiteLLM gateway — so it
cannot reach YouTube or the rate gate. Reuses the summarizer's truncation
discipline (TAPIR_MAX_TRANSCRIPT_CHARS), reporting the cut so the UI can be
honest about a bounded transcript. Model defaults to the summary's model and is
switchable among an offered, local-first list; an un-offered alias is forced
back to the default so chat can never call the gateway with an arbitrary model.
Ephemeral: history is carried per-request, nothing persisted.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-11 09:16:45 +02:00