Merge curation-v2-step3 into curation-v2 (steps 2 and 3 united)

Union merge of the Claude editor (step 2) and the embeddings/signals/telemetry
work (step 3): both config trees, per-provider LLM budgets plus the Voyage
meter, one startup provider log, runs.config_json with ranking and voyage
settings, and selected picks' why lines landing in candidate_runs.editor_why.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe

config.example.toml

@@ -5,6 +5,7 @@
 #   DAILY_EPUB_MINIFLUX__API_KEY=...
 #   DAILY_EPUB_DEEPSEEK__API_KEY=...
 #   DAILY_EPUB_ANTHROPIC__API_KEY=...
+#   DAILY_EPUB_VOYAGE__API_KEY=...
 #   DAILY_EPUB_SERVER__HMAC_SECRET=...
 #   DAILY_EPUB_LOOKBACK_HOURS=30
 
@@ -14,7 +15,7 @@ target_article_count = 20
 prefilter_keep = 120
 retention_days = 21                  # EPUBs, by age
 xtc_retention_count = 5              # XTC issues, by count (~80-100 MB each)
-max_daily_usd = 2.0                  # DeepSeek ceiling per UTC day; [anthropic] has its own
+max_daily_usd = 2.0                  # DeepSeek ceiling per UTC day; [anthropic] and [voyage] have their own
 world_briefing = true
 
 # SQLite database file. Parent directories are created on demand.
@@ -63,6 +64,20 @@ price_output_per_mtok = 25.0
 max_daily_usd = 3.0
 max_concurrent_requests = 4
 
+# Voyage AI embeddings behind the interest and rated-neighbour signals. Set
+# `enabled = false` (or leave the key unset) and the paper still builds: the
+# learned signals are simply absent, never a penalty.
+[voyage]
+enabled = true
+base_url = "https://api.voyageai.com/v1"
+model = "voyage-4-lite"
+# api_key via DAILY_EPUB_VOYAGE__API_KEY env
+output_dimension = 512               # 256 | 512 | 1024 | 2048
+batch_size = 32
+max_concurrent_requests = 4
+max_input_chars = 60000              # per article, cut on a char boundary
+max_daily_usd = 0.50                 # runaway guard ($0.02 / M tokens)
+
 [curation]
 max_article_count = 28               # hard ceiling; there is no minimum (§13)
 always_include_feeds = []            # miniflux feed ids or site urls
@@ -87,6 +102,55 @@ good_value = 0.35
 not_for_me_value = -1.0
 verdicts_in_prompt = 60
 
+# Every weight, quota, gate and threshold of the personalized ranker. The
+# learned signals (`knn`, `feed`) contribute nothing until their gates open:
+# the weight ramps linearly from `*_floor` to `*_full` rated articles.
+[curation.ranking]
+triage_max = 800                     # eligible articles the triage LLM reads
+deep_keep = 120                      # deep-assessment set
+shortlist_keep = 60                  # what the editor sees
+assessment_reuse_days = 3
+rating_lookback_days = 180
+rating_half_life_days = 60
+neighbour_k = 5
+negative_coefficient = 0.75
+knn_floor = 8
+knn_full = 25
+feed_floor = 15
+feed_full = 40
+semantic_min_words = 300
+exploration_slots = 5
+embedding_retention_days = 120       # `features prune`: unrated, unpublished vectors
+telemetry_retention_days = 180       # `features prune`: candidate_runs rows
+
+[curation.ranking.quotas]
+triage = 60
+interest = 20
+knn = 20
+
+# Weights need not sum to 1; they are renormalized over the present signals.
+[curation.ranking.weights.preliminary]
+interest = 0.35
+knn = 0.25
+heuristic = 0.20
+feed = 0.10
+social = 0.10
+
+[curation.ranking.weights.utility]
+quality = 0.40
+fit = 0.20
+knn = 0.15
+interest = 0.10
+feed = 0.05
+triage = 0.05
+social = 0.03
+heuristic = 0.02
+
+[curation.ranking.diversity]
+cluster_threshold = 0.85
+per_cluster_cap = 2
+utility_protected = 10
+
 [editorial]
 summary_model = "editor"             # editor (Claude) | bulk (DeepSeek)
 summary_input_tokens = 3000          # article text offered per summary