6 Commits

Include renames

Author	SHA1	Message	Date
mathias	0af2991d79	merge: captions-first YouTube VideoSource (Worker C, agent/youtube-source)	2026-06-02 17:22:51 +02:00
mathiasandClaude Opus 4.8	39e8756e77	docs(homelab): note YouTube secret-ref is parameterized + captions.download owner-only caveat ... Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-02 17:06:40 +02:00
mathiasandClaude Opus 4.8	6da9d61e63	feat(adapters): add Summarizer backed by local-first llm routing ... 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>	2026-06-02 17:04:29 +02:00
mathiasandClaude Opus 4.8	bb47f54a41	docs(homelab): pin verified LiteLLM endpoint (NodePort 30401, not 31234) ... 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>	2026-06-02 16:58:07 +02:00
mathias	b211cd08f2	docs: add build + runtime network egress requirements ... 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.	2026-06-02 11:40:50 +00:00
mathias	32e06843f1	docs: add homelab integration facts reference ... Pins the concrete endpoints/conventions Tapir depends on so independent sessions don't rediscover them: LiteLLM gateway (http://koala:4000/v1/, sk-local-123, host/name alias format), BYO fallback, brain-mcp HTTP sink, Dex identity, ESO+1Password secrets, hosts, and Flux GitOps deploy location. Verified facts recorded as such; unconfirmed items (brain-mcp URL, exact secret-ref naming, post-relocation LiteLLM location, summarization model alias) explicitly flagged 'confirm' rather than invented.	2026-06-02 10:37:55 +00:00